target/arm: Implement MVE WLSTP insn

Implement the MVE WLSTP insn; this is like the existing WLS insn,
except that it specifies a size value which is used to set
FPSCR.LTPSIZE.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210614151007.4545-8-peter.maydell@linaro.org

target/arm/t32.decode

@@ -672,8 +672,12 @@ BL               1111 0. .......... 11.1 ............         @branch24
     %lob_imm 1:10 11:1 !function=times_2
 
     DLS          1111 0 0000 100     rn:4 1110 0000 0000 0001
-    WLS          1111 0 0000 100     rn:4 1100 . .......... 1 imm=%lob_imm
+    WLS          1111 0 0000 100     rn:4 1100 . .......... 1 imm=%lob_imm size=4
+    {
       LE         1111 0 0000 0 f:1 0 1111 1100 . .......... 1 imm=%lob_imm
+      # This is WLSTP
+      WLS        1111 0 0000 0 size:2 rn:4 1100 . .......... 1 imm=%lob_imm
+    }
 
     LCTP         1111 0 0000 000     1111 1110 0000 0000 0001
   ]

target/arm/translate.c

@@ -8134,7 +8134,11 @@ static bool trans_WLS(DisasContext *s, arg_WLS *a)
         return false;
     }
     if (a->rn == 13 || a->rn == 15) {
-        /* CONSTRAINED UNPREDICTABLE: we choose to UNDEF */
+        /*
+         * For WLSTP rn == 15 is a related encoding (LE); the
+         * other cases caught by this condition are all
+         * CONSTRAINED UNPREDICTABLE: we choose to UNDEF
+         */
         return false;
     }
     if (s->condexec_mask) {
@@ -8147,10 +8151,41 @@ static bool trans_WLS(DisasContext *s, arg_WLS *a)
          */
         return false;
     }
+    if (a->size != 4) {
+        /* WLSTP */
+        if (!dc_isar_feature(aa32_mve, s)) {
+            return false;
+        }
+        /*
+         * We need to check that the FPU is enabled here, but mustn't
+         * call vfp_access_check() to do that because we don't want to
+         * do the lazy state preservation in the "loop count is zero" case.
+         * Do the check-and-raise-exception by hand.
+         */
+        if (s->fp_excp_el) {
+            gen_exception_insn(s, s->pc_curr, EXCP_NOCP,
+                               syn_uncategorized(), s->fp_excp_el);
+            return true;
+        }
+    }
+
     nextlabel = gen_new_label();
     tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_R[a->rn], 0, nextlabel);
     tmp = load_reg(s, a->rn);
     store_reg(s, 14, tmp);
+    if (a->size != 4) {
+        /*
+         * WLSTP: set FPSCR.LTPSIZE. This requires that we do the
+         * lazy state preservation, new FP context creation, etc,
+         * that vfp_access_check() does. We know that the actual
+         * access check will succeed (ie it won't generate code that
+         * throws an exception) because we did that check by hand earlier.
+         */
+        bool ok = vfp_access_check(s);
+        assert(ok);
+        tmp = tcg_const_i32(a->size);
+        store_cpu_field(tmp, v7m.ltpsize);
+    }
     gen_jmp_tb(s, s->base.pc_next, 1);
 
     gen_set_label(nextlabel);