target/arm: Implement MVE long shifts by immediate

The MVE extension to v8.1M includes some new shift instructions which
sit entirely within the non-coprocessor part of the encoding space
and which operate only on general-purpose registers.  They take up
the space which was previously UNPREDICTABLE MOVS and ORRS encodings
with Rm == 13 or 15.

Implement the long shifts by immediate, which perform shifts on a
pair of general-purpose registers treated as a 64-bit quantity, with
an immediate shift count between 1 and 32.

Awkwardly, because the MOVS and ORRS trans functions do not UNDEF for
the Rm==13,15 case, we need to explicitly emit code to UNDEF for the
cases where v8.1M now requires that.  (Trying to change MOVS and ORRS
is too difficult, because the functions that generate the code are
shared between a dozen different kinds of arithmetic or logical
instruction for all A32, T16 and T32 encodings, and for some insns
and some encodings Rm==13,15 are valid.)

We make the helper functions we need for UQSHLL and SQSHLL take
a 32-bit value which the helper casts to int8_t because we'll need
these helpers also for the shift-by-register insns, where the shift
count might be < 0 or > 32.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-16-peter.maydell@linaro.org

target/arm/helper-mve.h

@@ -449,3 +449,6 @@ DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32)
+
+DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32)
+DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32)

target/arm/mve_helper.c

@@ -1525,3 +1525,13 @@ uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm,
     mve_advance_vpt(env);
     return rdm;
 }
+
+uint64_t HELPER(mve_sqshll)(CPUARMState *env, uint64_t n, uint32_t shift)
+{
+    return do_sqrshl_d(n, (int8_t)shift, false, &env->QF);
+}
+
+uint64_t HELPER(mve_uqshll)(CPUARMState *env, uint64_t n, uint32_t shift)
+{
+    return do_uqrshl_d(n, (int8_t)shift, false, &env->QF);
+}

target/arm/t32.decode

@@ -48,6 +48,13 @@
 &mcr             !extern cp opc1 crn crm opc2 rt
 &mcrr            !extern cp opc1 crm rt rt2
 
+&mve_shl_ri      rdalo rdahi shim
+
+# rdahi: bits [3:1] from insn, bit 0 is 1
+# rdalo: bits [3:1] from insn, bit 0 is 0
+%rdahi_9 9:3 !function=times_2_plus_1
+%rdalo_17 17:3 !function=times_2
+
 # Data-processing (register)
 
 %imm5_12_6       12:3 6:2
@@ -59,12 +66,33 @@
 @S_xrr_shi       ....... .... .   rn:4 .... .... .. shty:2 rm:4 \
                  &s_rrr_shi shim=%imm5_12_6 s=1 rd=0
 
+@mve_shl_ri      ....... .... . ... . . ... ... . .. .. .... \
+                 &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9
+
 {
   TST_xrri       1110101 0000 1 .... 0 ... 1111 .... ....     @S_xrr_shi
   AND_rrri       1110101 0000 . .... 0 ... .... .... ....     @s_rrr_shi
 }
 BIC_rrri         1110101 0001 . .... 0 ... .... .... ....     @s_rrr_shi
 {
+  # The v8.1M MVE shift insns overlap in encoding with MOVS/ORRS
+  # and are distinguished by having Rm==13 or 15. Those are UNPREDICTABLE
+  # cases for MOVS/ORRS. We decode the MVE cases first, ensuring that
+  # they explicitly call unallocated_encoding() for cases that must UNDEF
+  # (eg "using a new shift insn on a v8.1M CPU without MVE"), and letting
+  # the rest fall through (where ORR_rrri and MOV_rxri will end up
+  # handling them as r13 and r15 accesses with the same semantics as A32).
+  [
+    LSLL_ri      1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111  @mve_shl_ri
+    LSRL_ri      1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111  @mve_shl_ri
+    ASRL_ri      1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111  @mve_shl_ri
+
+    UQSHLL_ri    1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111  @mve_shl_ri
+    URSHRL_ri    1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111  @mve_shl_ri
+    SRSHRL_ri    1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111  @mve_shl_ri
+    SQSHLL_ri    1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111  @mve_shl_ri
+  ]
+
   MOV_rxri       1110101 0010 . 1111 0 ... .... .... ....     @s_rxr_shi
   ORR_rrri       1110101 0010 . .... 0 ... .... .... ....     @s_rrr_shi
 }

target/arm/translate.c

@@ -5702,6 +5702,96 @@ static bool trans_MOVT(DisasContext *s, arg_MOVW *a)
     return true;
 }
 
+/*
+ * v8.1M MVE wide-shifts
+ */
+static bool do_mve_shl_ri(DisasContext *s, arg_mve_shl_ri *a,
+                          WideShiftImmFn *fn)
+{
+    TCGv_i64 rda;
+    TCGv_i32 rdalo, rdahi;
+
+    if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
+        /* Decode falls through to ORR/MOV UNPREDICTABLE handling */
+        return false;
+    }
+    if (a->rdahi == 15) {
+        /* These are a different encoding (SQSHL/SRSHR/UQSHL/URSHR) */
+        return false;
+    }
+    if (!dc_isar_feature(aa32_mve, s) ||
+        !arm_dc_feature(s, ARM_FEATURE_M_MAIN) ||
+        a->rdahi == 13) {
+        /* RdaHi == 13 is UNPREDICTABLE; we choose to UNDEF */
+        unallocated_encoding(s);
+        return true;
+    }
+
+    if (a->shim == 0) {
+        a->shim = 32;
+    }
+
+    rda = tcg_temp_new_i64();
+    rdalo = load_reg(s, a->rdalo);
+    rdahi = load_reg(s, a->rdahi);
+    tcg_gen_concat_i32_i64(rda, rdalo, rdahi);
+
+    fn(rda, rda, a->shim);
+
+    tcg_gen_extrl_i64_i32(rdalo, rda);
+    tcg_gen_extrh_i64_i32(rdahi, rda);
+    store_reg(s, a->rdalo, rdalo);
+    store_reg(s, a->rdahi, rdahi);
+    tcg_temp_free_i64(rda);
+
+    return true;
+}
+
+static bool trans_ASRL_ri(DisasContext *s, arg_mve_shl_ri *a)
+{
+    return do_mve_shl_ri(s, a, tcg_gen_sari_i64);
+}
+
+static bool trans_LSLL_ri(DisasContext *s, arg_mve_shl_ri *a)
+{
+    return do_mve_shl_ri(s, a, tcg_gen_shli_i64);
+}
+
+static bool trans_LSRL_ri(DisasContext *s, arg_mve_shl_ri *a)
+{
+    return do_mve_shl_ri(s, a, tcg_gen_shri_i64);
+}
+
+static void gen_mve_sqshll(TCGv_i64 r, TCGv_i64 n, int64_t shift)
+{
+    gen_helper_mve_sqshll(r, cpu_env, n, tcg_constant_i32(shift));
+}
+
+static bool trans_SQSHLL_ri(DisasContext *s, arg_mve_shl_ri *a)
+{
+    return do_mve_shl_ri(s, a, gen_mve_sqshll);
+}
+
+static void gen_mve_uqshll(TCGv_i64 r, TCGv_i64 n, int64_t shift)
+{
+    gen_helper_mve_uqshll(r, cpu_env, n, tcg_constant_i32(shift));
+}
+
+static bool trans_UQSHLL_ri(DisasContext *s, arg_mve_shl_ri *a)
+{
+    return do_mve_shl_ri(s, a, gen_mve_uqshll);
+}
+
+static bool trans_SRSHRL_ri(DisasContext *s, arg_mve_shl_ri *a)
+{
+    return do_mve_shl_ri(s, a, gen_srshr64_i64);
+}
+
+static bool trans_URSHRL_ri(DisasContext *s, arg_mve_shl_ri *a)
+{
+    return do_mve_shl_ri(s, a, gen_urshr64_i64);
+}
+
 /*
  * Multiply and multiply accumulate
  */

target/arm/translate.h

@@ -464,6 +464,7 @@ typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr);
 typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
 typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
 typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp);
+typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift);
 
 /**
  * arm_tbflags_from_tb: