diff --git a/tcg/optimize.c b/tcg/optimize.c
index 7ac63c9231..ef202abbcb 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -43,6 +43,7 @@ typedef struct TempOptInfo {
     TCGTemp *next_copy;
     uint64_t val;
     uint64_t z_mask;  /* mask bit is 0 if and only if value bit is 0 */
+    uint64_t s_mask;  /* a left-aligned mask of clrsb(value) bits. */
 } TempOptInfo;
 
 typedef struct OptContext {
@@ -53,9 +54,37 @@ typedef struct OptContext {
     /* In flight values from optimization. */
     uint64_t a_mask;  /* mask bit is 0 iff value identical to first input */
     uint64_t z_mask;  /* mask bit is 0 iff value bit is 0 */
+    uint64_t s_mask;  /* mask of clrsb(value) bits */
     TCGType type;
 } OptContext;
 
+/* Calculate the smask for a specific value. */
+static uint64_t smask_from_value(uint64_t value)
+{
+    int rep = clrsb64(value);
+    return ~(~0ull >> rep);
+}
+
+/*
+ * Calculate the smask for a given set of known-zeros.
+ * If there are lots of zeros on the left, we can consider the remainder
+ * an unsigned field, and thus the corresponding signed field is one bit
+ * larger.
+ */
+static uint64_t smask_from_zmask(uint64_t zmask)
+{
+    /*
+     * Only the 0 bits are significant for zmask, thus the msb itself
+     * must be zero, else we have no sign information.
+     */
+    int rep = clz64(zmask);
+    if (rep == 0) {
+        return 0;
+    }
+    rep -= 1;
+    return ~(~0ull >> rep);
+}
+
 static inline TempOptInfo *ts_info(TCGTemp *ts)
 {
     return ts->state_ptr;
@@ -94,6 +123,7 @@ static void reset_ts(TCGTemp *ts)
     ti->prev_copy = ts;
     ti->is_const = false;
     ti->z_mask = -1;
+    ti->s_mask = 0;
 }
 
 static void reset_temp(TCGArg arg)
@@ -124,9 +154,11 @@ static void init_ts_info(OptContext *ctx, TCGTemp *ts)
         ti->is_const = true;
         ti->val = ts->val;
         ti->z_mask = ts->val;
+        ti->s_mask = smask_from_value(ts->val);
     } else {
         ti->is_const = false;
         ti->z_mask = -1;
+        ti->s_mask = 0;
     }
 }
 
@@ -220,6 +252,7 @@ static bool tcg_opt_gen_mov(OptContext *ctx, TCGOp *op, TCGArg dst, TCGArg src)
     op->args[1] = src;
 
     di->z_mask = si->z_mask;
+    di->s_mask = si->s_mask;
 
     if (src_ts->type == dst_ts->type) {
         TempOptInfo *ni = ts_info(si->next_copy);
@@ -658,13 +691,15 @@ static void finish_folding(OptContext *ctx, TCGOp *op)
 
     nb_oargs = def->nb_oargs;
     for (i = 0; i < nb_oargs; i++) {
-        reset_temp(op->args[i]);
+        TCGTemp *ts = arg_temp(op->args[i]);
+        reset_ts(ts);
         /*
-         * Save the corresponding known-zero bits mask for the
+         * Save the corresponding known-zero/sign bits mask for the
          * first output argument (only one supported so far).
          */
         if (i == 0) {
-            arg_info(op->args[i])->z_mask = ctx->z_mask;
+            ts_info(ts)->z_mask = ctx->z_mask;
+            ts_info(ts)->s_mask = ctx->s_mask;
         }
     }
 }
@@ -714,6 +749,7 @@ static bool fold_masks(OptContext *ctx, TCGOp *op)
 {
     uint64_t a_mask = ctx->a_mask;
     uint64_t z_mask = ctx->z_mask;
+    uint64_t s_mask = ctx->s_mask;
 
     /*
      * 32-bit ops generate 32-bit results, which for the purpose of
@@ -725,7 +761,9 @@ static bool fold_masks(OptContext *ctx, TCGOp *op)
     if (ctx->type == TCG_TYPE_I32) {
         a_mask = (int32_t)a_mask;
         z_mask = (int32_t)z_mask;
+        s_mask |= MAKE_64BIT_MASK(32, 32);
         ctx->z_mask = z_mask;
+        ctx->s_mask = s_mask;
     }
 
     if (z_mask == 0) {
@@ -1072,7 +1110,7 @@ static bool fold_brcond2(OptContext *ctx, TCGOp *op)
 
 static bool fold_bswap(OptContext *ctx, TCGOp *op)
 {
-    uint64_t z_mask, sign;
+    uint64_t z_mask, s_mask, sign;
 
     if (arg_is_const(op->args[1])) {
         uint64_t t = arg_info(op->args[1])->val;
@@ -1082,6 +1120,7 @@ static bool fold_bswap(OptContext *ctx, TCGOp *op)
     }
 
     z_mask = arg_info(op->args[1])->z_mask;
+
     switch (op->opc) {
     case INDEX_op_bswap16_i32:
     case INDEX_op_bswap16_i64:
@@ -1100,6 +1139,7 @@ static bool fold_bswap(OptContext *ctx, TCGOp *op)
     default:
         g_assert_not_reached();
     }
+    s_mask = smask_from_zmask(z_mask);
 
     switch (op->args[2] & (TCG_BSWAP_OZ | TCG_BSWAP_OS)) {
     case TCG_BSWAP_OZ:
@@ -1108,14 +1148,17 @@ static bool fold_bswap(OptContext *ctx, TCGOp *op)
         /* If the sign bit may be 1, force all the bits above to 1. */
         if (z_mask & sign) {
             z_mask |= sign;
+            s_mask = sign << 1;
         }
         break;
     default:
         /* The high bits are undefined: force all bits above the sign to 1. */
         z_mask |= sign << 1;
+        s_mask = 0;
         break;
     }
     ctx->z_mask = z_mask;
+    ctx->s_mask = s_mask;
 
     return fold_masks(ctx, op);
 }
@@ -1263,21 +1306,24 @@ static bool fold_eqv(OptContext *ctx, TCGOp *op)
 static bool fold_extract(OptContext *ctx, TCGOp *op)
 {
     uint64_t z_mask_old, z_mask;
+    int pos = op->args[2];
+    int len = op->args[3];
 
     if (arg_is_const(op->args[1])) {
         uint64_t t;
 
         t = arg_info(op->args[1])->val;
-        t = extract64(t, op->args[2], op->args[3]);
+        t = extract64(t, pos, len);
         return tcg_opt_gen_movi(ctx, op, op->args[0], t);
     }
 
     z_mask_old = arg_info(op->args[1])->z_mask;
-    z_mask = extract64(z_mask_old, op->args[2], op->args[3]);
-    if (op->args[2] == 0) {
+    z_mask = extract64(z_mask_old, pos, len);
+    if (pos == 0) {
         ctx->a_mask = z_mask_old ^ z_mask;
     }
     ctx->z_mask = z_mask;
+    ctx->s_mask = smask_from_zmask(z_mask);
 
     return fold_masks(ctx, op);
 }
@@ -1303,14 +1349,16 @@ static bool fold_extract2(OptContext *ctx, TCGOp *op)
 
 static bool fold_exts(OptContext *ctx, TCGOp *op)
 {
-    uint64_t z_mask_old, z_mask, sign;
+    uint64_t s_mask_old, s_mask, z_mask, sign;
     bool type_change = false;
 
     if (fold_const1(ctx, op)) {
         return true;
     }
 
-    z_mask_old = z_mask = arg_info(op->args[1])->z_mask;
+    z_mask = arg_info(op->args[1])->z_mask;
+    s_mask = arg_info(op->args[1])->s_mask;
+    s_mask_old = s_mask;
 
     switch (op->opc) {
     CASE_OP_32_64(ext8s):
@@ -1334,10 +1382,14 @@ static bool fold_exts(OptContext *ctx, TCGOp *op)
 
     if (z_mask & sign) {
         z_mask |= sign;
-    } else if (!type_change) {
-        ctx->a_mask = z_mask_old ^ z_mask;
     }
+    s_mask |= sign << 1;
+
     ctx->z_mask = z_mask;
+    ctx->s_mask = s_mask;
+    if (!type_change) {
+        ctx->a_mask = s_mask & ~s_mask_old;
+    }
 
     return fold_masks(ctx, op);
 }
@@ -1376,6 +1428,7 @@ static bool fold_extu(OptContext *ctx, TCGOp *op)
     }
 
     ctx->z_mask = z_mask;
+    ctx->s_mask = smask_from_zmask(z_mask);
     if (!type_change) {
         ctx->a_mask = z_mask_old ^ z_mask;
     }
@@ -1606,8 +1659,12 @@ static bool fold_qemu_ld(OptContext *ctx, TCGOp *op)
     MemOp mop = get_memop(oi);
     int width = 8 * memop_size(mop);
 
-    if (!(mop & MO_SIGN) && width < 64) {
-        ctx->z_mask = MAKE_64BIT_MASK(0, width);
+    if (width < 64) {
+        ctx->s_mask = MAKE_64BIT_MASK(width, 64 - width);
+        if (!(mop & MO_SIGN)) {
+            ctx->z_mask = MAKE_64BIT_MASK(0, width);
+            ctx->s_mask <<= 1;
+        }
     }
 
     /* Opcodes that touch guest memory stop the mb optimization.  */
@@ -1726,23 +1783,31 @@ static bool fold_setcond2(OptContext *ctx, TCGOp *op)
 
 static bool fold_sextract(OptContext *ctx, TCGOp *op)
 {
-    int64_t z_mask_old, z_mask;
+    uint64_t z_mask, s_mask, s_mask_old;
+    int pos = op->args[2];
+    int len = op->args[3];
 
     if (arg_is_const(op->args[1])) {
         uint64_t t;
 
         t = arg_info(op->args[1])->val;
-        t = sextract64(t, op->args[2], op->args[3]);
+        t = sextract64(t, pos, len);
         return tcg_opt_gen_movi(ctx, op, op->args[0], t);
     }
 
-    z_mask_old = arg_info(op->args[1])->z_mask;
-    z_mask = sextract64(z_mask_old, op->args[2], op->args[3]);
-    if (op->args[2] == 0 && z_mask >= 0) {
-        ctx->a_mask = z_mask_old ^ z_mask;
-    }
+    z_mask = arg_info(op->args[1])->z_mask;
+    z_mask = sextract64(z_mask, pos, len);
     ctx->z_mask = z_mask;
 
+    s_mask_old = arg_info(op->args[1])->s_mask;
+    s_mask = sextract64(s_mask_old, pos, len);
+    s_mask |= MAKE_64BIT_MASK(len, 64 - len);
+    ctx->s_mask = s_mask;
+
+    if (pos == 0) {
+        ctx->a_mask = s_mask & ~s_mask_old;
+    }
+
     return fold_masks(ctx, op);
 }
 
@@ -1819,14 +1884,26 @@ static bool fold_tcg_ld(OptContext *ctx, TCGOp *op)
 {
     /* We can't do any folding with a load, but we can record bits. */
     switch (op->opc) {
+    CASE_OP_32_64(ld8s):
+        ctx->s_mask = MAKE_64BIT_MASK(8, 56);
+        break;
     CASE_OP_32_64(ld8u):
         ctx->z_mask = MAKE_64BIT_MASK(0, 8);
+        ctx->s_mask = MAKE_64BIT_MASK(9, 55);
+        break;
+    CASE_OP_32_64(ld16s):
+        ctx->s_mask = MAKE_64BIT_MASK(16, 48);
         break;
     CASE_OP_32_64(ld16u):
         ctx->z_mask = MAKE_64BIT_MASK(0, 16);
+        ctx->s_mask = MAKE_64BIT_MASK(17, 47);
+        break;
+    case INDEX_op_ld32s_i64:
+        ctx->s_mask = MAKE_64BIT_MASK(32, 32);
         break;
     case INDEX_op_ld32u_i64:
         ctx->z_mask = MAKE_64BIT_MASK(0, 32);
+        ctx->s_mask = MAKE_64BIT_MASK(33, 31);
         break;
     default:
         g_assert_not_reached();
@@ -1889,9 +1966,10 @@ void tcg_optimize(TCGContext *s)
             ctx.type = TCG_TYPE_I32;
         }
 
-        /* Assume all bits affected, and no bits known zero. */
+        /* Assume all bits affected, no bits known zero, no sign reps. */
         ctx.a_mask = -1;
         ctx.z_mask = -1;
+        ctx.s_mask = 0;
 
         /*
          * Process each opcode.
@@ -1964,8 +2042,11 @@ void tcg_optimize(TCGContext *s)
         case INDEX_op_extrh_i64_i32:
             done = fold_extu(&ctx, op);
             break;
+        CASE_OP_32_64(ld8s):
         CASE_OP_32_64(ld8u):
+        CASE_OP_32_64(ld16s):
         CASE_OP_32_64(ld16u):
+        case INDEX_op_ld32s_i64:
         case INDEX_op_ld32u_i64:
             done = fold_tcg_ld(&ctx, op);
             break;