[PULL 32/53] tcg/mips: Reorg tlb load within prepare_host_addr

[Richard Henderson <richard.henderson@linaro.org>]

Compare the address vs the tlb entry with sign-extended values.
This simplifies the page+alignment mask constant, and the
generation of the last byte address for the misaligned test.

Move the tlb addend load up, and the zero-extension down.

This frees up a register, which allows us use TMP3 as the returned base
address register instead of A0, which we were using as a 5th temporary.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/mips/tcg-target.c.inc | 38 ++++++++++++++++++--------------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/tcg/mips/tcg-target.c.inc b/tcg/mips/tcg-target.c.inc
index 31d58e1977..695c137023 100644
--- a/tcg/mips/tcg-target.c.inc
+++ b/tcg/mips/tcg-target.c.inc
@@ -370,6 +370,8 @@ typedef enum {
     ALIAS_PADDI    = sizeof(void *) == 4 ? OPC_ADDIU : OPC_DADDIU,
     ALIAS_TSRL     = TARGET_LONG_BITS == 32 || TCG_TARGET_REG_BITS == 32
                      ? OPC_SRL : OPC_DSRL,
+    ALIAS_TADDI    = TARGET_LONG_BITS == 32 || TCG_TARGET_REG_BITS == 32
+                     ? OPC_ADDIU : OPC_DADDIU,
 } MIPSInsn;
 
 /*
@@ -1263,14 +1265,12 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
     int add_off = offsetof(CPUTLBEntry, addend);
     int cmp_off = is_ld ? offsetof(CPUTLBEntry, addr_read)
                         : offsetof(CPUTLBEntry, addr_write);
-    target_ulong tlb_mask;
 
     ldst = new_ldst_label(s);
     ldst->is_ld = is_ld;
     ldst->oi = oi;
     ldst->addrlo_reg = addrlo;
     ldst->addrhi_reg = addrhi;
-    base = TCG_REG_A0;
 
     /* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx].  */
     QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0);
@@ -1290,15 +1290,12 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
     if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
         tcg_out_ldst(s, OPC_LW, TCG_TMP0, TCG_TMP3, cmp_off + LO_OFF);
     } else {
-        tcg_out_ldst(s, (TARGET_LONG_BITS == 64 ? OPC_LD
-                         : TCG_TARGET_REG_BITS == 64 ? OPC_LWU : OPC_LW),
-                     TCG_TMP0, TCG_TMP3, cmp_off);
+        tcg_out_ld(s, TCG_TYPE_TL, TCG_TMP0, TCG_TMP3, cmp_off);
     }
 
-    /* Zero extend a 32-bit guest address for a 64-bit host. */
-    if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) {
-        tcg_out_ext32u(s, base, addrlo);
-        addrlo = base;
+    if (TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) {
+        /* Load the tlb addend for the fast path.  */
+        tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP3, TCG_TMP3, add_off);
     }
 
     /*
@@ -1306,18 +1303,18 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
      * For unaligned accesses, compare against the end of the access to
      * verify that it does not cross a page boundary.
      */
-    tlb_mask = (target_ulong)TARGET_PAGE_MASK | a_mask;
-    tcg_out_movi(s, TCG_TYPE_I32, TCG_TMP1, tlb_mask);
-    if (a_mask >= s_mask) {
-        tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, addrlo);
-    } else {
-        tcg_out_opc_imm(s, ALIAS_PADDI, TCG_TMP2, addrlo, s_mask - a_mask);
+    tcg_out_movi(s, TCG_TYPE_TL, TCG_TMP1, TARGET_PAGE_MASK | a_mask);
+    if (a_mask < s_mask) {
+        tcg_out_opc_imm(s, ALIAS_TADDI, TCG_TMP2, addrlo, s_mask - a_mask);
         tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, TCG_TMP2);
+    } else {
+        tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, addrlo);
     }
 
-    if (TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) {
-        /* Load the tlb addend for the fast path.  */
-        tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP2, TCG_TMP3, add_off);
+    /* Zero extend a 32-bit guest address for a 64-bit host. */
+    if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) {
+        tcg_out_ext32u(s, TCG_TMP2, addrlo);
+        addrlo = TCG_TMP2;
     }
 
     ldst->label_ptr[0] = s->code_ptr;
@@ -1329,14 +1326,15 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
         tcg_out_ldst(s, OPC_LW, TCG_TMP0, TCG_TMP3, cmp_off + HI_OFF);
 
         /* Load the tlb addend for the fast path.  */
-        tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP2, TCG_TMP3, add_off);
+        tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP3, TCG_TMP3, add_off);
 
         ldst->label_ptr[1] = s->code_ptr;
         tcg_out_opc_br(s, OPC_BNE, addrhi, TCG_TMP0);
     }
 
     /* delay slot */
-    tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_TMP2, addrlo);
+    base = TCG_TMP3;
+    tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_TMP3, addrlo);
 #else
     if (a_mask && (use_mips32r6_instructions || a_bits != s_bits)) {
         ldst = new_ldst_label(s);
-- 
2.34.1