diff mbox series

[2/5] target/loongarch: Add am{swap/add}[_db].{b/h}

Message ID 20231023153029.269211-4-c@jia.je (mailing list archive)
State New, archived
Headers show
Series Add LoongArch v1.1 instructions | expand

Commit Message

Jiajie Chen Oct. 23, 2023, 3:29 p.m. UTC
The new instructions are introduced in LoongArch v1.1:

- amswap.b
- amswap.h
- amadd.b
- amadd.h
- amswap_db.b
- amswap_db.h
- amadd_db.b
- amadd_db.h

The instructions are gated by CPUCFG2.LAM_BH.

Signed-off-by: Jiajie Chen <c@jia.je>
---
 target/loongarch/cpu.h                         |  1 +
 target/loongarch/disas.c                       |  8 ++++++++
 target/loongarch/insn_trans/trans_atomic.c.inc |  8 ++++++++
 target/loongarch/insns.decode                  |  8 ++++++++
 target/loongarch/translate.h                   | 17 +++++++++--------
 5 files changed, 34 insertions(+), 8 deletions(-)

Comments

Richard Henderson Oct. 23, 2023, 10:50 p.m. UTC | #1
On 10/23/23 08:29, Jiajie Chen wrote:
> The new instructions are introduced in LoongArch v1.1:
> 
> - amswap.b
> - amswap.h
> - amadd.b
> - amadd.h
> - amswap_db.b
> - amswap_db.h
> - amadd_db.b
> - amadd_db.h
> 
> The instructions are gated by CPUCFG2.LAM_BH.
> 
> Signed-off-by: Jiajie Chen <c@jia.je>

Except for the use of MO_TESB,

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>


r~
diff mbox series

Patch

diff --git a/target/loongarch/cpu.h b/target/loongarch/cpu.h
index 8b54cf109c..7166c07756 100644
--- a/target/loongarch/cpu.h
+++ b/target/loongarch/cpu.h
@@ -155,6 +155,7 @@  FIELD(CPUCFG2, LBT_ARM, 19, 1)
 FIELD(CPUCFG2, LBT_MIPS, 20, 1)
 FIELD(CPUCFG2, LSPW, 21, 1)
 FIELD(CPUCFG2, LAM, 22, 1)
+FIELD(CPUCFG2, LAM_BH, 27, 1)
 
 /* cpucfg[3] bits */
 FIELD(CPUCFG3, CCDMA, 0, 1)
diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index 2040f3e44d..d33aa8173a 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -575,6 +575,14 @@  INSN(fldx_s,       frr)
 INSN(fldx_d,       frr)
 INSN(fstx_s,       frr)
 INSN(fstx_d,       frr)
+INSN(amswap_b,     rrr)
+INSN(amswap_h,     rrr)
+INSN(amadd_b,      rrr)
+INSN(amadd_h,      rrr)
+INSN(amswap_db_b,  rrr)
+INSN(amswap_db_h,  rrr)
+INSN(amadd_db_b,   rrr)
+INSN(amadd_db_h,   rrr)
 INSN(amswap_w,     rrr)
 INSN(amswap_d,     rrr)
 INSN(amadd_w,      rrr)
diff --git a/target/loongarch/insn_trans/trans_atomic.c.inc b/target/loongarch/insn_trans/trans_atomic.c.inc
index 80c2e286fd..cd28e217ad 100644
--- a/target/loongarch/insn_trans/trans_atomic.c.inc
+++ b/target/loongarch/insn_trans/trans_atomic.c.inc
@@ -73,6 +73,14 @@  TRANS(ll_w, ALL, gen_ll, MO_TESL)
 TRANS(sc_w, ALL, gen_sc, MO_TESL)
 TRANS(ll_d, 64, gen_ll, MO_TEUQ)
 TRANS(sc_d, 64, gen_sc, MO_TEUQ)
+TRANS(amswap_b, LAM_BH, gen_am, tcg_gen_atomic_xchg_tl, MO_TESB)
+TRANS(amswap_h, LAM_BH, gen_am, tcg_gen_atomic_xchg_tl, MO_TESW)
+TRANS(amadd_b, LAM_BH, gen_am, tcg_gen_atomic_fetch_add_tl, MO_TESB)
+TRANS(amadd_h, LAM_BH, gen_am, tcg_gen_atomic_fetch_add_tl, MO_TESW)
+TRANS(amswap_db_b, LAM_BH, gen_am, tcg_gen_atomic_xchg_tl, MO_TESB)
+TRANS(amswap_db_h, LAM_BH, gen_am, tcg_gen_atomic_xchg_tl, MO_TESW)
+TRANS(amadd_db_b, LAM_BH, gen_am, tcg_gen_atomic_fetch_add_tl, MO_TESB)
+TRANS(amadd_db_h, LAM_BH, gen_am, tcg_gen_atomic_fetch_add_tl, MO_TESW)
 TRANS(amswap_w, LAM, gen_am, tcg_gen_atomic_xchg_tl, MO_TESL)
 TRANS(amswap_d, LAM, gen_am, tcg_gen_atomic_xchg_tl, MO_TEUQ)
 TRANS(amadd_w, LAM, gen_am, tcg_gen_atomic_fetch_add_tl, MO_TESL)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index 62f58cc541..678ce42038 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -261,6 +261,14 @@  ll_w            0010 0000 .............. ..... .....     @rr_i14s2
 sc_w            0010 0001 .............. ..... .....     @rr_i14s2
 ll_d            0010 0010 .............. ..... .....     @rr_i14s2
 sc_d            0010 0011 .............. ..... .....     @rr_i14s2
+amswap_b        0011 10000101 11000 ..... ..... .....    @rrr
+amswap_h        0011 10000101 11001 ..... ..... .....    @rrr
+amadd_b         0011 10000101 11010 ..... ..... .....    @rrr
+amadd_h         0011 10000101 11011 ..... ..... .....    @rrr
+amswap_db_b     0011 10000101 11100 ..... ..... .....    @rrr
+amswap_db_h     0011 10000101 11101 ..... ..... .....    @rrr
+amadd_db_b      0011 10000101 11110 ..... ..... .....    @rrr
+amadd_db_h      0011 10000101 11111 ..... ..... .....    @rrr
 amswap_w        0011 10000110 00000 ..... ..... .....    @rrr
 amswap_d        0011 10000110 00001 ..... ..... .....    @rrr
 amadd_w         0011 10000110 00010 ..... ..... .....    @rrr
diff --git a/target/loongarch/translate.h b/target/loongarch/translate.h
index 195f53573a..0b230530e7 100644
--- a/target/loongarch/translate.h
+++ b/target/loongarch/translate.h
@@ -17,14 +17,15 @@ 
 #define avail_ALL(C)   true
 #define avail_64(C)    (FIELD_EX32((C)->cpucfg1, CPUCFG1, ARCH) == \
                         CPUCFG1_ARCH_LA64)
-#define avail_FP(C)    (FIELD_EX32((C)->cpucfg2, CPUCFG2, FP))
-#define avail_FP_SP(C) (FIELD_EX32((C)->cpucfg2, CPUCFG2, FP_SP))
-#define avail_FP_DP(C) (FIELD_EX32((C)->cpucfg2, CPUCFG2, FP_DP))
-#define avail_LSPW(C)  (FIELD_EX32((C)->cpucfg2, CPUCFG2, LSPW))
-#define avail_LAM(C)   (FIELD_EX32((C)->cpucfg2, CPUCFG2, LAM))
-#define avail_LSX(C)   (FIELD_EX32((C)->cpucfg2, CPUCFG2, LSX))
-#define avail_LASX(C)  (FIELD_EX32((C)->cpucfg2, CPUCFG2, LASX))
-#define avail_IOCSR(C) (FIELD_EX32((C)->cpucfg1, CPUCFG1, IOCSR))
+#define avail_FP(C)     (FIELD_EX32((C)->cpucfg2, CPUCFG2, FP))
+#define avail_FP_SP(C)  (FIELD_EX32((C)->cpucfg2, CPUCFG2, FP_SP))
+#define avail_FP_DP(C)  (FIELD_EX32((C)->cpucfg2, CPUCFG2, FP_DP))
+#define avail_LSPW(C)   (FIELD_EX32((C)->cpucfg2, CPUCFG2, LSPW))
+#define avail_LAM(C)    (FIELD_EX32((C)->cpucfg2, CPUCFG2, LAM))
+#define avail_LAM_BH(C) (FIELD_EX32((C)->cpucfg2, CPUCFG2, LAM_BH))
+#define avail_LSX(C)    (FIELD_EX32((C)->cpucfg2, CPUCFG2, LSX))
+#define avail_LASX(C)   (FIELD_EX32((C)->cpucfg2, CPUCFG2, LASX))
+#define avail_IOCSR(C)  (FIELD_EX32((C)->cpucfg1, CPUCFG1, IOCSR))
 
 /*
  * If an operation is being performed on less than TARGET_LONG_BITS,