[PULL 27/41] target/ppc: Move Fixed-Point Load/Store String instructions to decodetree.

[Harsh Prateek Bora <harshpb@linux.ibm.com>]

From: Shivang Upadhyay <shivangu@linux.ibm.com>

Move below instructions to decodetree specification :

        lsw{i, x},
        stsw{i, x}                       : X-form

The changes were verified by validating that the tcg ops generated by
those instructions remain the same, which were captured with the '-d
in_asm,op' flag.

Signed-off-by: Shivang Upadhyay <shivangu@linux.ibm.com>
Reviewed-by: Glenn Miles <milesg@linux.ibm.com>
Signed-off-by: Chinmay Rath <rathc@linux.ibm.com>
Tested-by: Aniket Sahu <asahu1x@linux.ibm.com>
Link: https://lore.kernel.org/qemu-devel/20260827133010.278889-24-rathc@linux.ibm.com
Signed-off-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
---
 target/ppc/helper.h                        |   6 +-
 target/ppc/insn32.decode                   |   7 ++
 target/ppc/mem_helper.c                    |   6 +-
 target/ppc/translate.c                     | 102 ---------------------
 target/ppc/translate/fixedpoint-impl.c.inc | 102 +++++++++++++++++++++
 5 files changed, 115 insertions(+), 108 deletions(-)

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 6e14f02598..18ef7786a4 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -45,9 +45,9 @@ DEF_HELPER_1(check_tlb_flush_global, void, env)
 
 DEF_HELPER_3(lmw, void, env, tl, i32)
 DEF_HELPER_FLAGS_3(stmw, TCG_CALL_NO_WG, void, env, tl, i32)
-DEF_HELPER_4(lsw, void, env, tl, i32, i32)
-DEF_HELPER_5(lswx, void, env, tl, i32, i32, i32)
-DEF_HELPER_FLAGS_4(stsw, TCG_CALL_NO_WG, void, env, tl, i32, i32)
+DEF_HELPER_4(LSW, void, env, tl, i32, i32)
+DEF_HELPER_5(LSWX, void, env, tl, i32, i32, i32)
+DEF_HELPER_FLAGS_4(STSW, TCG_CALL_NO_WG, void, env, tl, i32, i32)
 DEF_HELPER_FLAGS_3(dcbz, TCG_CALL_NO_WG, void, env, tl, int)
 #ifdef TARGET_PPC64
 DEF_HELPER_FLAGS_2(dcbzl, TCG_CALL_NO_WG, void, env, tl)
diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 5e5490b169..a88ba1fce1 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -527,6 +527,13 @@ CREQV           010011 ..... ..... ..... 0100100001 -  @X
 CRANDC          010011 ..... ..... ..... 0010000001 -  @X
 CRORC           010011 ..... ..... ..... 0110100001 -  @X
 
+# Fixed Point Move Assist Instructions
+
+LSWI            011111 ..... ..... ..... 1 001010101 -  @X
+LSWX            011111 ..... ..... ..... 1 000010101 -  @X
+STSWI           011111 ..... ..... ..... 1 011010101 -  @X
+STSWX           011111 ..... ..... ..... 1 010010101 -  @X
+
 # Fixed-Point Hash Instructions
 
 HASHST          011111 ..... ..... ..... 1011010010 .   @X_DW
diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c
index 8ad6945590..10c648cf06 100644
--- a/target/ppc/mem_helper.c
+++ b/target/ppc/mem_helper.c
@@ -190,7 +190,7 @@ static void do_lsw(CPUPPCState *env, target_ulong addr, uint32_t nb,
     env->gpr[reg] = val;
 }
 
-void helper_lsw(CPUPPCState *env, target_ulong addr,
+void helper_LSW(CPUPPCState *env, target_ulong addr,
                 uint32_t nb, uint32_t reg)
 {
     do_lsw(env, addr, nb, reg, GETPC());
@@ -202,7 +202,7 @@ void helper_lsw(CPUPPCState *env, target_ulong addr,
  * this is valid, but rA won't be loaded.  For now, I'll follow the
  * spec...
  */
-void helper_lswx(CPUPPCState *env, target_ulong addr, uint32_t reg,
+void helper_LSWX(CPUPPCState *env, target_ulong addr, uint32_t reg,
                  uint32_t ra, uint32_t rb)
 {
     if (likely(xer_bc != 0)) {
@@ -218,7 +218,7 @@ void helper_lswx(CPUPPCState *env, target_ulong addr, uint32_t reg,
     }
 }
 
-void helper_stsw(CPUPPCState *env, target_ulong addr, uint32_t nb,
+void helper_STSW(CPUPPCState *env, target_ulong addr, uint32_t nb,
                  uint32_t reg)
 {
     uintptr_t raddr = GETPC();
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index c45883ac30..d17d77a9d9 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -2595,104 +2595,6 @@ static void gen_stmw(DisasContext *ctx)
     gen_helper_stmw(tcg_env, t0, t1);
 }
 
-/***                    Integer load and store strings                     ***/
-
-/* lswi */
-/*
- * PowerPC32 specification says we must generate an exception if rA is
- * in the range of registers to be loaded.  In an other hand, IBM says
- * this is valid, but rA won't be loaded.  For now, I'll follow the
- * spec...
- */
-static void gen_lswi(DisasContext *ctx)
-{
-    TCGv t0;
-    TCGv_i32 t1, t2;
-    int nb = NB(ctx->opcode);
-    int start = rD(ctx->opcode);
-    int ra = rA(ctx->opcode);
-    int nr;
-
-    if (ctx->le_mode) {
-        gen_align_no_le(ctx);
-        return;
-    }
-    if (nb == 0) {
-        nb = 32;
-    }
-    nr = DIV_ROUND_UP(nb, 4);
-    if (unlikely(lsw_reg_in_range(start, nr, ra))) {
-        gen_inval_exception(ctx, POWERPC_EXCP_INVAL_LSWX);
-        return;
-    }
-    gen_set_access_type(ctx, ACCESS_INT);
-    t0 = tcg_temp_new();
-    gen_addr_register(ctx, t0);
-    t1 = tcg_constant_i32(nb);
-    t2 = tcg_constant_i32(start);
-    gen_helper_lsw(tcg_env, t0, t1, t2);
-}
-
-/* lswx */
-static void gen_lswx(DisasContext *ctx)
-{
-    TCGv t0;
-    TCGv_i32 t1, t2, t3;
-
-    if (ctx->le_mode) {
-        gen_align_no_le(ctx);
-        return;
-    }
-    gen_set_access_type(ctx, ACCESS_INT);
-    t0 = tcg_temp_new();
-    gen_addr_reg_index(ctx, t0);
-    t1 = tcg_constant_i32(rD(ctx->opcode));
-    t2 = tcg_constant_i32(rA(ctx->opcode));
-    t3 = tcg_constant_i32(rB(ctx->opcode));
-    gen_helper_lswx(tcg_env, t0, t1, t2, t3);
-}
-
-/* stswi */
-static void gen_stswi(DisasContext *ctx)
-{
-    TCGv t0;
-    TCGv_i32 t1, t2;
-    int nb = NB(ctx->opcode);
-
-    if (ctx->le_mode) {
-        gen_align_no_le(ctx);
-        return;
-    }
-    gen_set_access_type(ctx, ACCESS_INT);
-    t0 = tcg_temp_new();
-    gen_addr_register(ctx, t0);
-    if (nb == 0) {
-        nb = 32;
-    }
-    t1 = tcg_constant_i32(nb);
-    t2 = tcg_constant_i32(rS(ctx->opcode));
-    gen_helper_stsw(tcg_env, t0, t1, t2);
-}
-
-/* stswx */
-static void gen_stswx(DisasContext *ctx)
-{
-    TCGv t0;
-    TCGv_i32 t1, t2;
-
-    if (ctx->le_mode) {
-        gen_align_no_le(ctx);
-        return;
-    }
-    gen_set_access_type(ctx, ACCESS_INT);
-    t0 = tcg_temp_new();
-    gen_addr_reg_index(ctx, t0);
-    t1 = tcg_temp_new_i32();
-    tcg_gen_trunc_tl_i32(t1, cpu_xer);
-    tcg_gen_andi_i32(t1, t1, 0x7F);
-    t2 = tcg_constant_i32(rS(ctx->opcode));
-    gen_helper_stsw(tcg_env, t0, t1, t2);
-}
 
 #if !defined(CONFIG_USER_ONLY)
 static inline void gen_check_tlb_flush(DisasContext *ctx, bool global)
@@ -4901,10 +4803,6 @@ GEN_HANDLER_E(dform39, 0x39, 0xFF, 0xFF, 0x00000000, PPC_NONE, PPC2_ISA205),
 GEN_HANDLER_E(dform3D, 0x3D, 0xFF, 0xFF, 0x00000000, PPC_NONE, PPC2_ISA205),
 GEN_HANDLER(lmw, 0x2E, 0xFF, 0xFF, 0x00000000, PPC_INTEGER),
 GEN_HANDLER(stmw, 0x2F, 0xFF, 0xFF, 0x00000000, PPC_INTEGER),
-GEN_HANDLER(lswi, 0x1F, 0x15, 0x12, 0x00000001, PPC_STRING),
-GEN_HANDLER(lswx, 0x1F, 0x15, 0x10, 0x00000001, PPC_STRING),
-GEN_HANDLER(stswi, 0x1F, 0x15, 0x16, 0x00000001, PPC_STRING),
-GEN_HANDLER(stswx, 0x1F, 0x15, 0x14, 0x00000001, PPC_STRING),
 /* ISA v3.0 changed the extended opcode from 62 to 30 */
 GEN_HANDLER(rfi, 0x13, 0x12, 0x01, 0x03FF8001, PPC_FLOW),
 #if defined(TARGET_PPC64)
diff --git a/target/ppc/translate/fixedpoint-impl.c.inc b/target/ppc/translate/fixedpoint-impl.c.inc
index d0b3bda97f..4b79e24f6f 100644
--- a/target/ppc/translate/fixedpoint-impl.c.inc
+++ b/target/ppc/translate/fixedpoint-impl.c.inc
@@ -584,6 +584,108 @@ TRANS(CRANDC, cr_logic_common, tcg_gen_andc_i32);
 TRANS(CREQV, cr_logic_common, tcg_gen_eqv_i32);
 TRANS(CRORC, cr_logic_common, tcg_gen_orc_i32);
 
+/***                    Integer load and store strings                     ***/
+
+/* lswi */
+static bool trans_LSWI(DisasContext *ctx, arg_LSWI *a)
+{
+    TCGv t0;
+    TCGv_i32 t1, t2;
+    int nb = a->rb;
+    int start = a->rt;
+    int ra = a->ra;
+    int nr;
+
+    REQUIRE_INSNS_FLAGS(ctx, STRING);
+    if (ctx->le_mode) {
+        gen_align_no_le(ctx);
+        return true;
+    }
+    if (nb == 0) {
+        nb = 32;
+    }
+    nr = DIV_ROUND_UP(nb, 4);
+    if (unlikely(lsw_reg_in_range(start, nr, ra))) {
+        gen_inval_exception(ctx, POWERPC_EXCP_INVAL_LSWX);
+        return true;
+    }
+    gen_set_access_type(ctx, ACCESS_INT);
+    t0 = do_ea_calc_ra(ctx, ra);
+    t1 = tcg_constant_i32(nb);
+    t2 = tcg_constant_i32(start);
+    gen_helper_LSW(tcg_env, t0, t1, t2);
+
+    return true;
+}
+
+/* lswx */
+static bool trans_LSWX(DisasContext *ctx, arg_LSWX *a)
+{
+    TCGv t0;
+    TCGv_i32 t1, t2, t3;
+
+    REQUIRE_INSNS_FLAGS(ctx, STRING);
+    if (ctx->le_mode) {
+        gen_align_no_le(ctx);
+        return true;
+    }
+
+    gen_set_access_type(ctx, ACCESS_INT);
+    t0 = do_ea_calc(ctx, a->ra, cpu_gpr[a->rb]);
+    t1 = tcg_constant_i32(a->rt);
+    t2 = tcg_constant_i32(a->ra);
+    t3 = tcg_constant_i32(a->rb);
+    gen_helper_LSWX(tcg_env, t0, t1, t2, t3);
+
+    return true;
+}
+
+/* stswi */
+static bool trans_STSWI(DisasContext *ctx, arg_STSWI *a)
+{
+    TCGv t0;
+    TCGv_i32 t1, t2;
+    int nb = a->rb;
+
+    REQUIRE_INSNS_FLAGS(ctx, STRING);
+    if (ctx->le_mode) {
+        gen_align_no_le(ctx);
+        return true;
+    }
+    gen_set_access_type(ctx, ACCESS_INT);
+    t0 = do_ea_calc_ra(ctx, a->ra);
+    if (nb == 0) {
+        nb = 32;
+    }
+    t1 = tcg_constant_i32(nb);
+    t2 = tcg_constant_i32(a->rt);
+    gen_helper_STSW(tcg_env, t0, t1, t2);
+
+    return true;
+}
+
+/* stswx */
+static bool trans_STSWX(DisasContext *ctx, arg_STSWX *a)
+{
+    TCGv t0;
+    TCGv_i32 t1, t2;
+
+    REQUIRE_INSNS_FLAGS(ctx, STRING);
+    if (ctx->le_mode) {
+        gen_align_no_le(ctx);
+        return true;
+    }
+    gen_set_access_type(ctx, ACCESS_INT);
+    t0 = do_ea_calc(ctx, a->ra, cpu_gpr[a->rb]);
+    t1 = tcg_temp_new_i32();
+    tcg_gen_trunc_tl_i32(t1, cpu_xer);
+    tcg_gen_andi_i32(t1, t1, 0x7F);
+    t2 = tcg_constant_i32(a->rt);
+    gen_helper_STSW(tcg_env, t0, t1, t2);
+
+    return true;
+}
+
 static bool do_add_D(DisasContext *ctx, arg_D *a, bool add_ca, bool compute_ca,
                      bool compute_ov, bool compute_rc0)
 {
-- 
2.52.0