[Qemu-devel] [PATCH v4 32/33] tcg-aarch64: Introduce tcg_out_ldst_pair

[Richard Henderson <rth@twiddle.net>]

Combines 4 other inline functions and tidies the prologue.

Signed-off-by: Richard Henderson <rth@twiddle.net>
---
 tcg/aarch64/tcg-target.c | 84 ++++++++++++++++--------------------------------
 1 file changed, 27 insertions(+), 57 deletions(-)

diff --git a/tcg/aarch64/tcg-target.c b/tcg/aarch64/tcg-target.c
index fa88e4b..94f9ac1 100644
--- a/tcg/aarch64/tcg-target.c
+++ b/tcg/aarch64/tcg-target.c
@@ -333,6 +333,10 @@ typedef enum {
     INSN_BLR   = 0xd63f0000,
     INSN_RET   = 0xd65f0000,
     INSN_B_C   = 0x54000000,
+
+    /* Load/store instructions */
+    INSN_LDP   = 0x28400000,
+    INSN_STP   = 0x28000000,
 } AArch64Insn;
 
 static inline enum aarch64_ldst_op_data
@@ -1331,56 +1335,6 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, int opc)
 
 static uint8_t *tb_ret_addr;
 
-/* callee stack use example:
-   stp     x29, x30, [sp,#-32]!
-   mov     x29, sp
-   stp     x1, x2, [sp,#16]
-   ...
-   ldp     x1, x2, [sp,#16]
-   ldp     x29, x30, [sp],#32
-   ret
-*/
-
-/* push r1 and r2, and alloc stack space for a total of
-   alloc_n elements (1 element=16 bytes, must be between 1 and 31. */
-static inline void tcg_out_push_pair(TCGContext *s, TCGReg addr,
-                                     TCGReg r1, TCGReg r2, int alloc_n)
-{
-    /* using indexed scaled simm7 STP 0x28800000 | (ext) | 0x01000000 (pre-idx)
-       | alloc_n * (-1) << 16 | r2 << 10 | addr << 5 | r1 */
-    assert(alloc_n > 0 && alloc_n < 0x20);
-    alloc_n = (-alloc_n) & 0x3f;
-    tcg_out32(s, 0xa9800000 | alloc_n << 16 | r2 << 10 | addr << 5 | r1);
-}
-
-/* dealloc stack space for a total of alloc_n elements and pop r1, r2.  */
-static inline void tcg_out_pop_pair(TCGContext *s, TCGReg addr,
-                                    TCGReg r1, TCGReg r2, int alloc_n)
-{
-    /* using indexed scaled simm7 LDP 0x28c00000 | (ext) | nothing (post-idx)
-       | alloc_n << 16 | r2 << 10 | addr << 5 | r1 */
-    assert(alloc_n > 0 && alloc_n < 0x20);
-    tcg_out32(s, 0xa8c00000 | alloc_n << 16 | r2 << 10 | addr << 5 | r1);
-}
-
-static inline void tcg_out_store_pair(TCGContext *s, TCGReg addr,
-                                      TCGReg r1, TCGReg r2, int idx)
-{
-    /* using register pair offset simm7 STP 0x29000000 | (ext)
-       | idx << 16 | r2 << 10 | addr << 5 | r1 */
-    assert(idx > 0 && idx < 0x20);
-    tcg_out32(s, 0xa9000000 | idx << 16 | r2 << 10 | addr << 5 | r1);
-}
-
-static inline void tcg_out_load_pair(TCGContext *s, TCGReg addr,
-                                     TCGReg r1, TCGReg r2, int idx)
-{
-    /* using register pair offset simm7 LDP 0x29400000 | (ext)
-       | idx << 16 | r2 << 10 | addr << 5 | r1 */
-    assert(idx > 0 && idx < 0x20);
-    tcg_out32(s, 0xa9400000 | idx << 16 | r2 << 10 | addr << 5 | r1);
-}
-
 static void tcg_out_op(TCGContext *s, TCGOpcode opc,
                        const TCGArg args[TCG_MAX_OP_ARGS],
                        const int const_args[TCG_MAX_OP_ARGS])
@@ -1937,17 +1891,32 @@ static void tcg_target_init(TCGContext *s)
       + TCG_TARGET_STACK_ALIGN - 1) \
      & ~(TCG_TARGET_STACK_ALIGN - 1))
 
+static void tcg_out_ldst_pair(TCGContext *s, AArch64Insn insn,
+                              TCGReg r1, TCGReg r2, TCGReg base,
+                              tcg_target_long ofs, bool pre, bool w)
+{
+    insn |= 1u << 31; /* ext */
+    insn |= pre << 24;
+    insn |= w << 23;
+
+    assert(ofs >= -0x200 && ofs < 0x200 && (ofs & 7) == 0);
+    insn |= (ofs & (0x7f << 3)) << (15 - 3);
+
+    tcg_out32(s, insn | r2 << 10 | base << 5 | r1);
+}
+
 static void tcg_target_qemu_prologue(TCGContext *s)
 {
     TCGReg r;
 
     /* Push (FP, LR) and allocate space for all saved registers.  */
-    tcg_out_push_pair(s, TCG_REG_SP, TCG_REG_FP, TCG_REG_LR, PUSH_SIZE / 16);
+    tcg_out_ldst_pair(s, INSN_STP, TCG_REG_FP, TCG_REG_LR,
+                      TCG_REG_SP, -PUSH_SIZE, 1, 1);
 
     /* Store callee-preserved regs x19..x28.  */
     for (r = TCG_REG_X19; r <= TCG_REG_X27; r += 2) {
-        int idx = (r - TCG_REG_X19) / 2 + 1;
-        tcg_out_store_pair(s, TCG_REG_SP, r, r + 1, idx);
+        int ofs = (r - TCG_REG_X19 + 2) * 8;
+        tcg_out_ldst_pair(s, INSN_STP, r, r + 1, TCG_REG_SP, ofs, 1, 0);
     }
 
     /* Make stack space for TCG locals.  */
@@ -1976,12 +1945,13 @@ static void tcg_target_qemu_prologue(TCGContext *s)
 
     /* Restore callee-preserved registers x19..x28.  */
     for (r = TCG_REG_X19; r <= TCG_REG_X27; r += 2) {
-        int idx = (r - TCG_REG_X19) / 2 + 1;
-        tcg_out_load_pair(s, TCG_REG_SP, r, r + 1, idx);
+        int ofs = (r - TCG_REG_X19 + 2) * 8;
+        tcg_out_ldst_pair(s, INSN_LDP, r, r + 1, TCG_REG_SP, ofs, 1, 0);
     }
 
-    /* Pop (FP, LR), restore SP to previous frame, return.  */
-    tcg_out_pop_pair(s, TCG_REG_SP, TCG_REG_FP, TCG_REG_LR, PUSH_SIZE / 16);
+    /* Pop (FP, LR), restore SP to previous frame.  */
+    tcg_out_ldst_pair(s, INSN_LDP, TCG_REG_FP, TCG_REG_LR,
+                      TCG_REG_SP, PUSH_SIZE, 0, 1);
     tcg_out_ret(s, TCG_REG_LR);
 }
 
-- 
1.8.3.1