@@ -1178,8 +1178,8 @@ static inline void tcg_out_tlb_load(TCGContext *s, TCGReg addrlo, TCGReg addrhi,
const TCGReg r0 = TCG_REG_L0;
const TCGReg r1 = TCG_REG_L1;
TCGType ttype = TCG_TYPE_I32;
- TCGType htype = TCG_TYPE_I32;
- int trexw = 0, hrexw = 0;
+ TCGType tlbtype = TCG_TYPE_I32;
+ int trexw = 0, hrexw = 0, tlbrexw = 0;
if (TCG_TARGET_REG_BITS == 64) {
if (TARGET_LONG_BITS == 64) {
@@ -1187,20 +1187,24 @@ static inline void tcg_out_tlb_load(TCGContext *s, TCGReg addrlo, TCGReg addrhi,
trexw = P_REXW;
}
if (TCG_TYPE_PTR == TCG_TYPE_I64) {
- htype = TCG_TYPE_I64;
hrexw = P_REXW;
+
+ if (TARGET_PAGE_BITS + CPU_TLB_BITS > 32) {
+ tlbtype = TCG_TYPE_I64;
+ tlbrexw = P_REXW;
+ }
}
}
- tcg_out_mov(s, htype, r0, addrlo);
+ tcg_out_mov(s, tlbtype, r0, addrlo);
tcg_out_mov(s, ttype, r1, addrlo);
- tcg_out_shifti(s, SHIFT_SHR + hrexw, r0,
+ tcg_out_shifti(s, SHIFT_SHR + tlbrexw, r0,
TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS);
tgen_arithi(s, ARITH_AND + trexw, r1,
TARGET_PAGE_MASK | ((1 << s_bits) - 1), 0);
- tgen_arithi(s, ARITH_AND + hrexw, r0,
+ tgen_arithi(s, ARITH_AND + tlbrexw, r0,
(CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS, 0);
tcg_out_modrm_sib_offset(s, OPC_LEA + hrexw, r0, TCG_AREG0, r0, 0,
When computing the TLB address we are likely to mask out the high 32-bits by using shr + and. We can use 32-bit instructions in that case. This saves 2 bytes per TLB access. Cc: Richard Henderson <rth@twiddle.net> Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> --- tcg/i386/tcg-target.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-)