From b6b24cb031d1d6e6f50abf0c8bdc1c309e549156 Mon Sep 17 00:00:00 2001
From: Richard Henderson <rth@twiddle.net>
Date: Mon, 4 Mar 2013 21:12:30 -0800
Subject: [PATCH] tcg-arm: Implement deposit for armv7

We have BFI and BFC available for implementing it.

Signed-off-by: Richard Henderson <rth@twiddle.net>
---
 tcg/arm/tcg-target.c | 41 ++++++++++++++++++++++++++++++++++++++---
 tcg/arm/tcg-target.h |  5 ++++-
 2 files changed, 42 insertions(+), 4 deletions(-)

diff --git a/tcg/arm/tcg-target.c b/tcg/arm/tcg-target.c
index dfcc8e61f9..09f11e19e8 100644
--- a/tcg/arm/tcg-target.c
+++ b/tcg/arm/tcg-target.c
@@ -145,9 +145,10 @@ static void patch_reloc(uint8_t *code_ptr, int type,
     }
 }
 
-#define TCG_CT_CONST_ARM 0x100
-#define TCG_CT_CONST_INV 0x200
-#define TCG_CT_CONST_NEG 0x400
+#define TCG_CT_CONST_ARM  0x100
+#define TCG_CT_CONST_INV  0x200
+#define TCG_CT_CONST_NEG  0x400
+#define TCG_CT_CONST_ZERO 0x800
 
 /* parse target specific constraints */
 static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
@@ -165,6 +166,9 @@ static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
     case 'N': /* The gcc constraint letter is L, already used here.  */
         ct->ct |= TCG_CT_CONST_NEG;
         break;
+    case 'Z':
+        ct->ct |= TCG_CT_CONST_ZERO;
+        break;
 
     case 'r':
         ct->ct |= TCG_CT_REG;
@@ -297,6 +301,8 @@ static inline int tcg_target_const_match(tcg_target_long val,
         return 1;
     } else if ((ct & TCG_CT_CONST_NEG) && check_fit_imm(-val)) {
         return 1;
+    } else if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
+        return 1;
     } else {
         return 0;
     }
@@ -702,6 +708,28 @@ static inline void tcg_out_bswap32(TCGContext *s, int cond, int rd, int rn)
     }
 }
 
+bool tcg_target_deposit_valid(int ofs, int len)
+{
+    /* ??? Without bfi, we could improve over generic code by combining
+       the right-shift from a non-zero ofs with the orr.  We do run into
+       problems when rd == rs, and the mask generated from ofs+len doesn't
+       fit into an immediate.  We would have to be careful not to pessimize
+       wrt the optimizations performed on the expanded code.  */
+    return use_armv7_instructions;
+}
+
+static inline void tcg_out_deposit(TCGContext *s, int cond, TCGReg rd,
+                                   TCGArg a1, int ofs, int len, bool const_a1)
+{
+    if (const_a1) {
+        /* bfi becomes bfc with rn == 15.  */
+        a1 = 15;
+    }
+    /* bfi/bfc */
+    tcg_out32(s, 0x07c00010 | (cond << 28) | (rd << 12) | a1
+              | (ofs << 7) | ((ofs + len - 1) << 16));
+}
+
 static inline void tcg_out_ld32_12(TCGContext *s, int cond,
                 int rd, int rn, tcg_target_long im)
 {
@@ -1835,6 +1863,11 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         tcg_out_ext16u(s, COND_AL, args[0], args[1]);
         break;
 
+    case INDEX_op_deposit_i32:
+        tcg_out_deposit(s, COND_AL, args[0], args[2],
+                        args[3], args[4], const_args[2]);
+        break;
+
     default:
         tcg_abort();
     }
@@ -1919,6 +1952,8 @@ static const TCGTargetOpDef arm_op_defs[] = {
     { INDEX_op_ext16s_i32, { "r", "r" } },
     { INDEX_op_ext16u_i32, { "r", "r" } },
 
+    { INDEX_op_deposit_i32, { "r", "0", "rZ" } },
+
     { -1 },
 };
 
diff --git a/tcg/arm/tcg-target.h b/tcg/arm/tcg-target.h
index 354dd8ada8..209f585f39 100644
--- a/tcg/arm/tcg-target.h
+++ b/tcg/arm/tcg-target.h
@@ -71,10 +71,13 @@ typedef enum {
 #define TCG_TARGET_HAS_eqv_i32          0
 #define TCG_TARGET_HAS_nand_i32         0
 #define TCG_TARGET_HAS_nor_i32          0
-#define TCG_TARGET_HAS_deposit_i32      0
+#define TCG_TARGET_HAS_deposit_i32      1
 #define TCG_TARGET_HAS_movcond_i32      1
 #define TCG_TARGET_HAS_muls2_i32        1
 
+extern bool tcg_target_deposit_valid(int ofs, int len);
+#define TCG_TARGET_deposit_i32_valid  tcg_target_deposit_valid
+
 enum {
     TCG_AREG0 = TCG_REG_R6,
 };