target/loongarch: Add llacq/screl instructions

Add the following instructions in LoongArch v1.1:

- llacq.w
- screl.w
- llacq.d
- screl.d

They are guarded by CPUCFG2.LLACQ_SCREL.

Signed-off-by: Jiajie Chen <c@jia.je>
Co-developed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Song Gao <gaosong@loongson.cn>
Signed-off-by: Song Gao <gaosong@loongson.cn>

diff --git a/target/loongarch/cpu.h b/target/loongarch/cpu.h
index 8648d0514a269d6d971b97638d76fd752d5c5dda..77080091fecd705caf67ee62061f2016fb9ad01e 100644 (file)
--- a/target/loongarch/cpu.h
+++ b/target/loongarch/cpu.h
@@ -141,6 +141,7 @@ FIELD(CPUCFG2, HPTW, 24, 1)
 FIELD(CPUCFG2, FRECIPE, 25, 1)
 FIELD(CPUCFG2, LAM_BH, 27, 1)
 FIELD(CPUCFG2, LAMCAS, 28, 1)
+FIELD(CPUCFG2, LLACQ_SCREL, 29, 1)
 
 /* cpucfg[3] bits */
 FIELD(CPUCFG3, CCDMA, 0, 1)

diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index e5e1b37ce026f8deded156f775047d8b827524d7..3164fade9b52ec067951e3e2f424c933dc132a04 100644 (file)
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -584,6 +584,10 @@ INSN(fldx_s,       frr)
 INSN(fldx_d,       frr)
 INSN(fstx_s,       frr)
 INSN(fstx_d,       frr)
+INSN(llacq_w,      rr_i)
+INSN(screl_w,      rr_i)
+INSN(llacq_d,      rr_i)
+INSN(screl_d,      rr_i)
 INSN(amcas_b,      rrr)
 INSN(amcas_h,      rrr)
 INSN(amcas_w,      rrr)

diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index 92078f0f9fa9fde2aa680007989955f66a76c158..7898f5f7190c487a5dd35c8dd00767e197383a44 100644 (file)
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -69,6 +69,7 @@
 @rr_i14s2         .... ....  .............. rj:5 rd:5    &rr_i imm=%i14s2
 @rr_i16                     .... .. imm:s16 rj:5 rd:5    &rr_i
 @rr_i16s2         .... ..  ................ rj:5 rd:5    &rr_i imm=%offs16
+@rr_i0            .... ..  ................ rj:5 rd:5    &rr_i imm=0
 @hint_r_i12           .... ...... imm:s12 rj:5 hint:5    &hint_r_i
 @hint_rr         .... ........ ..... rk:5 rj:5 hint:5    &hint_rr
 @rrr_sa2p1        .... ........ ... .. rk:5 rj:5 rd:5    &rrr_sa  sa=%sa2p1
@@ -261,6 +262,10 @@ ll_w            0010 0000 .............. ..... .....     @rr_i14s2
 sc_w            0010 0001 .............. ..... .....     @rr_i14s2
 ll_d            0010 0010 .............. ..... .....     @rr_i14s2
 sc_d            0010 0011 .............. ..... .....     @rr_i14s2
+llacq_w         0011 10000101 01111 00000 ..... .....    @rr_i0
+screl_w         0011 10000101 01111 00001 ..... .....    @rr_i0
+llacq_d         0011 10000101 01111 00010 ..... .....    @rr_i0
+screl_d         0011 10000101 01111 00011 ..... .....    @rr_i0
 amcas_b         0011 10000101 10000 ..... ..... .....    @rrr
 amcas_h         0011 10000101 10001 ..... ..... .....    @rrr
 amcas_w         0011 10000101 10010 ..... ..... .....    @rrr

diff --git a/target/loongarch/tcg/insn_trans/trans_atomic.c.inc b/target/loongarch/tcg/insn_trans/trans_atomic.c.inc
index b27c91a92757c0b25de90f5994bb06b2d27650b4..a294c5dd52e3b46055514e045318f519409966bd 100644 (file)
--- a/target/loongarch/tcg/insn_trans/trans_atomic.c.inc
+++ b/target/loongarch/tcg/insn_trans/trans_atomic.c.inc
@@ -3,7 +3,7 @@
  * Copyright (c) 2021 Loongson Technology Corporation Limited
  */
 
-static bool gen_ll(DisasContext *ctx, arg_rr_i *a, MemOp mop)
+static bool gen_ll(DisasContext *ctx, arg_rr_i *a, MemOp mop, bool acq)
 {
     TCGv t1 = tcg_temp_new();
     TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
@@ -14,10 +14,14 @@ static bool gen_ll(DisasContext *ctx, arg_rr_i *a, MemOp mop)
     tcg_gen_st_tl(t1, tcg_env, offsetof(CPULoongArchState, llval));
     gen_set_gpr(a->rd, t1, EXT_NONE);
 
+    if (acq) {
+        tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ);
+    }
+
     return true;
 }
 
-static bool gen_sc(DisasContext *ctx, arg_rr_i *a, MemOp mop)
+static bool gen_sc(DisasContext *ctx, arg_rr_i *a, MemOp mop, bool rel)
 {
     TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE);
     TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
@@ -29,6 +33,10 @@ static bool gen_sc(DisasContext *ctx, arg_rr_i *a, MemOp mop)
     TCGLabel *done = gen_new_label();
 
     tcg_gen_addi_tl(t0, src1, a->imm);
+
+    if (rel) {
+        tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL);
+    }
     tcg_gen_brcond_tl(TCG_COND_EQ, t0, cpu_lladdr, l1);
     tcg_gen_movi_tl(dest, 0);
     tcg_gen_br(done);
@@ -86,10 +94,14 @@ static bool gen_am(DisasContext *ctx, arg_rrr *a,
     return true;
 }
 
-TRANS(ll_w, ALL, gen_ll, MO_LESL)
-TRANS(sc_w, ALL, gen_sc, MO_LESL)
-TRANS(ll_d, 64, gen_ll, MO_LEUQ)
-TRANS(sc_d, 64, gen_sc, MO_LEUQ)
+TRANS(ll_w, ALL, gen_ll, MO_LESL, false)
+TRANS(sc_w, ALL, gen_sc, MO_LESL, false)
+TRANS(ll_d, 64, gen_ll, MO_LEUQ, false)
+TRANS(sc_d, 64, gen_sc, MO_LEUQ, false)
+TRANS(llacq_w, LLACQ_SCREL, gen_ll, MO_LESL, true)
+TRANS(screl_w, LLACQ_SCREL, gen_sc, MO_LESL, true)
+TRANS(llacq_d, LLACQ_SCREL_64, gen_ll, MO_LEUQ, true)
+TRANS(screl_d, LLACQ_SCREL_64, gen_sc, MO_LEUQ, true)
 TRANS(amcas_b, LAMCAS, gen_cas, tcg_gen_atomic_cmpxchg_tl, MO_SB)
 TRANS(amcas_h, LAMCAS, gen_cas, tcg_gen_atomic_cmpxchg_tl, MO_LESW)
 TRANS(amcas_w, LAMCAS, gen_cas, tcg_gen_atomic_cmpxchg_tl, MO_LESL)

diff --git a/target/loongarch/translate.h b/target/loongarch/translate.h
index 331f79c8f2ac58fe785471a47063d9b0dcea5657..76bceedf980b7ae6faa9ed939dbbaa12d6df738c 100644 (file)
--- a/target/loongarch/translate.h
+++ b/target/loongarch/translate.h
@@ -39,6 +39,9 @@
 #define avail_FRECIPE_LSX(C)   (avail_FRECIPE(C) && avail_LSX(C))
 #define avail_FRECIPE_LASX(C)   (avail_FRECIPE(C) && avail_LASX(C))
 
+#define avail_LLACQ_SCREL(C)    (FIELD_EX32((C)->cpucfg2, CPUCFG2, LLACQ_SCREL))
+#define avail_LLACQ_SCREL_64(C) (avail_64(C) && avail_LLACQ_SCREL(C))
+
 /*
  * If an operation is being performed on less than TARGET_LONG_BITS,
  * it may require the inputs to be sign- or zero-extended; which will