[Qemu-devel] [V3 PATCH 05/14] target-ppc: Add ISA 2.06 divwe[u][o] Instructions

[Tom Musta <tommusta@gmail.com>]

This patch addes the Signed and Unsigned  Divide Word Extended
instructions which were introduced in Power ISA 2.06.

V2: Eliminating extraneous code in the overflow case per comments
from Richard Henderson.  Fixed corner case bug in divweu (check
for (RA) >= (RB)).

Signed-off-by: Tom Musta <tommusta@gmail.com>
---
 target-ppc/translate.c |   70 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 70 insertions(+), 0 deletions(-)

diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index b274a15..3344fa9 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -984,6 +984,72 @@ GEN_INT_ARITH_DIVW(divwuo, 0x1E, 0, 1);
 /* divw  divw.  divwo  divwo.   */
 GEN_INT_ARITH_DIVW(divw, 0x0F, 1, 0);
 GEN_INT_ARITH_DIVW(divwo, 0x1F, 1, 1);
+
+#define GEN_DIVWE(op, signed, compute_ov)                                     \
+static void gen_##op(DisasContext *ctx)                                       \
+{                                                                             \
+    /* Need to use local temps because of the branches */                     \
+    TCGv ra = tcg_temp_local_new();                                           \
+    TCGv rb = tcg_temp_local_new();                                           \
+    int lbl_ov = gen_new_label();                                             \
+    int lbl_rc = gen_new_label();                                             \
+                                                                              \
+    if (signed) {                                                             \
+        TCGv tmp0;                                                            \
+        /* divide by zero ? */                                                \
+        tcg_gen_ext32s_i64(rb, cpu_gpr[rB(ctx->opcode)]);                     \
+        tcg_gen_brcondi_i64(TCG_COND_EQ, rb, 0, lbl_ov);                      \
+        tcg_gen_shli_i64(ra, cpu_gpr[rA(ctx->opcode)], 32);                   \
+        /* check for MIN div -1 */                                            \
+        int l3 = gen_new_label();                                             \
+        tcg_gen_brcondi_i64(TCG_COND_NE, rb, -1l, l3);                        \
+        tcg_gen_brcondi_i64(TCG_COND_EQ, ra, INT64_MIN, lbl_ov);              \
+        gen_set_label(l3);                                                    \
+        tcg_gen_div_i64(cpu_gpr[rD(ctx->opcode)], ra, rb);                    \
+        tmp0 = tcg_temp_local_new();                                          \
+        /* does the result fit in 32 bits? */                                 \
+        tcg_gen_ext32s_i64(tmp0, cpu_gpr[rD(ctx->opcode)]);                   \
+        tcg_gen_brcond_i64(TCG_COND_NE, cpu_gpr[rD(ctx->opcode)], tmp0,       \
+                           lbl_ov);                                           \
+        tcg_temp_free(tmp0);                                                  \
+    } else { /* unsigned */                                                   \
+        /* divide by zero ? */                                                \
+        tcg_gen_ext32u_i64(rb, cpu_gpr[rB(ctx->opcode)]);                     \
+        tcg_gen_brcondi_i64(TCG_COND_EQ, rb, 0, lbl_ov);                      \
+        /* is ra[32:63] >= rb[32:63] ? */                                     \
+        tcg_gen_ext32u_i64(ra, cpu_gpr[rA(ctx->opcode)]);                     \
+        tcg_gen_brcond_i64(TCG_COND_GEU, ra, rb, lbl_ov);                     \
+        tcg_gen_shli_i64(ra, cpu_gpr[rA(ctx->opcode)], 32);                   \
+        tcg_gen_divu_i64(cpu_gpr[rD(ctx->opcode)], ra, rb);                   \
+    }                                                                         \
+                                                                              \
+    if (compute_ov) {                                                         \
+        tcg_gen_movi_tl(cpu_ov, 0);                                           \
+    }                                                                         \
+    tcg_gen_br(lbl_rc);                                                       \
+                                                                              \
+    gen_set_label(lbl_ov); /* overflow handling */                            \
+    tcg_gen_movi_i64(cpu_gpr[rD(ctx->opcode)], 0);                            \
+                                                                              \
+    if (compute_ov) {                                                         \
+        tcg_gen_movi_tl(cpu_ov, 1);                                           \
+        tcg_gen_movi_tl(cpu_so, 1);                                           \
+    }                                                                         \
+                                                                              \
+    gen_set_label(lbl_rc);                                                    \
+    if (unlikely(Rc(ctx->opcode) != 0)) {                                     \
+        gen_set_Rc0(ctx, cpu_gpr[rD(ctx->opcode)]);                           \
+    }                                                                         \
+                                                                              \
+    tcg_temp_free(ra);                                                        \
+    tcg_temp_free(rb);                                                        \
+}
+
+GEN_DIVWE(divweu, 0, 0);
+GEN_DIVWE(divweuo, 0, 1);
+GEN_DIVWE(divwe, 1, 0);
+GEN_DIVWE(divweo, 1, 1);
+
 #if defined(TARGET_PPC64)
 static inline void gen_op_arith_divd(DisasContext *ctx, TCGv ret, TCGv arg1,
                                      TCGv arg2, int sign, int compute_ov)
@@ -9603,6 +9669,10 @@ GEN_INT_ARITH_DIVW(divwu, 0x0E, 0, 0),
 GEN_INT_ARITH_DIVW(divwuo, 0x1E, 0, 1),
 GEN_INT_ARITH_DIVW(divw, 0x0F, 1, 0),
 GEN_INT_ARITH_DIVW(divwo, 0x1F, 1, 1),
+GEN_HANDLER_E(divwe, 0x1F, 0x0B, 0x0D, 0x00000000, PPC_NONE, PPC2_ISA206),
+GEN_HANDLER_E(divweo, 0x1F, 0x0B, 0x1D, 0x00000000, PPC_NONE, PPC2_ISA206),
+GEN_HANDLER_E(divweu, 0x1F, 0x0B, 0x0C, 0x00000000, PPC_NONE, PPC2_ISA206),
+GEN_HANDLER_E(divweuo, 0x1F, 0x0B, 0x1C, 0x00000000, PPC_NONE, PPC2_ISA206),
 
 #if defined(TARGET_PPC64)
 #undef GEN_INT_ARITH_DIVD
-- 
1.7.1