[Qemu-devel] [PATCH 4/4] tcg/aarch64: implement tlb lookup fast path

[Jani Kokkonen <Jani.Kokkonen@huawei.com>]

From: Jani Kokkonen <jani.kokkonen@huawei.com>

implement the fast path for tcg_out_qemu_ld/st.

Signed-off-by: Jani Kokkonen <jani.kokkonen@huawei.com>
---
 tcg/aarch64/tcg-target.c | 161 +++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 157 insertions(+), 4 deletions(-)

diff --git a/tcg/aarch64/tcg-target.c b/tcg/aarch64/tcg-target.c
index 24b2862..47ec4a7 100644
--- a/tcg/aarch64/tcg-target.c
+++ b/tcg/aarch64/tcg-target.c
@@ -700,6 +700,36 @@ static inline void tcg_out_uxt(TCGContext *s, int s_bits,
 #ifdef CONFIG_SOFTMMU
 #include "exec/softmmu_defs.h"
 
+/* Load and compare a TLB entry, leaving the flags set.  Leaves X2 pointing
+   to the tlb entry.  Clobbers X0,X1,X2,X3 and TMP.  */
+
+static void tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg,
+                             int s_bits, uint8_t **label_ptr, int tlb_offset)
+{
+    TCGReg base = TCG_AREG0;
+
+    tcg_out_shr(s, 1, TCG_REG_TMP, addr_reg, TARGET_PAGE_BITS);
+    tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X1, tlb_offset);
+    tcg_out_arith(s, ARITH_ADD, 1, TCG_REG_X2, base, TCG_REG_X1, 0);
+    tcg_out_andi(s, 1, TCG_REG_X0, TCG_REG_TMP, CPU_TLB_BITS, 0);
+    tcg_out_arith(s, ARITH_ADD, 1, TCG_REG_X2, TCG_REG_X2,
+                             TCG_REG_X0, -CPU_TLB_ENTRY_BITS);
+#if TARGET_LONG_BITS == 64
+    tcg_out_ldst(s, LDST_64, LDST_LD, TCG_REG_X3, TCG_REG_X2, 0);
+#else
+    tcg_out_ldst(s, LDST_32, LDST_LD, TCG_REG_X3, TCG_REG_X2, 0);
+#endif
+    /* check alignment */
+    if (s_bits) {
+        tcg_out_tst(s, 1, addr_reg, s_bits, 0);
+        label_ptr[0] = s->code_ptr;
+        tcg_out_goto_cond_noaddr(s, TCG_COND_NE);
+    }
+    tcg_out_cmp(s, 1, TCG_REG_X3, TCG_REG_TMP, -TARGET_PAGE_BITS);
+    label_ptr[1] = s->code_ptr;
+    tcg_out_goto_cond_noaddr(s, TCG_COND_NE);
+}
+
 /* helper signature: helper_ld_mmu(CPUState *env, target_ulong addr,
    int mmu_idx) */
 static const void * const qemu_ld_helpers[4] = {
@@ -723,18 +753,85 @@ static const void * const qemu_st_helpers[4] = {
 static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, int opc)
 {
     TCGReg addr_reg, data_reg;
+    bool bswap;
 #ifdef CONFIG_SOFTMMU
     int mem_index, s_bits;
+    int i;
+    uint8_t *label_ptr[2] = { NULL };
+    uint8_t *label_ptr2;
 #endif
     data_reg = args[0];
     addr_reg = args[1];
+#ifdef TARGET_WORDS_BIGENDIAN
+    bswap = 1;
+#else
+    bswap = 0;
+#endif
 
 #ifdef CONFIG_SOFTMMU
     mem_index = args[2];
     s_bits = opc & 3;
 
-    /* TODO: insert TLB lookup here */
+    tcg_out_tlb_read(s, addr_reg, s_bits, label_ptr,
+                     offsetof(CPUArchState, tlb_table[mem_index][0].addr_read));
 
+    tcg_out_ldst(s, LDST_64, LDST_LD, TCG_REG_X1, TCG_REG_X2,
+             offsetof(CPUTLBEntry, addend) - offsetof(CPUTLBEntry, addr_read));
+    switch (opc) {
+    case 0:
+        tcg_out_ldst_r(s, LDST_8, LDST_LD, data_reg, addr_reg, TCG_REG_X1);
+        break;
+    case 0 | 4:
+        tcg_out_ldst_r(s, LDST_8, LDST_LD_S_X, data_reg, addr_reg, TCG_REG_X1);
+        break;
+    case 1:
+        tcg_out_ldst_r(s, LDST_16, LDST_LD, data_reg, addr_reg, TCG_REG_X1);
+        if (bswap) {
+            tcg_out_rev16(s, 1, data_reg, data_reg);
+        }
+        break;
+    case 1 | 4:
+        if (bswap) {
+            tcg_out_ldst_r(s, LDST_16, LDST_LD, data_reg, addr_reg, TCG_REG_X1);
+            tcg_out_rev16(s, 1, data_reg, data_reg);
+            tcg_out_sxt(s, 1, s_bits, data_reg, data_reg);
+        } else {
+            tcg_out_ldst_r(s, LDST_16, LDST_LD_S_X,
+                           data_reg, addr_reg, TCG_REG_X1);
+        }
+        break;
+    case 2:
+        tcg_out_ldst_r(s, LDST_32, LDST_LD, data_reg, addr_reg, TCG_REG_X1);
+        if (bswap) {
+            tcg_out_rev32(s, data_reg, data_reg);
+        }
+        break;
+    case 2 | 4:
+        if (bswap) {
+            tcg_out_ldst_r(s, LDST_32, LDST_LD, data_reg, addr_reg, TCG_REG_X1);
+            tcg_out_rev32(s, data_reg, data_reg);
+            tcg_out_sxt(s, 1, s_bits, data_reg, data_reg);
+        } else {
+            tcg_out_ldst_r(s, LDST_32, LDST_LD_S_X,
+                           data_reg, addr_reg, TCG_REG_X1);
+        }
+        break;
+    case 3:
+        tcg_out_ldst_r(s, LDST_64, LDST_LD, data_reg, addr_reg, TCG_REG_X1);
+         if (bswap) {
+            tcg_out_rev(s, 1, data_reg, data_reg);
+        }
+        break;
+    default:
+        tcg_abort();
+    }
+    label_ptr2 = s->code_ptr;
+    tcg_out_goto_noaddr(s);
+    for (i = 0; i < 2; i++) {
+        if (label_ptr[i]) {
+            reloc_pc19(label_ptr[i], (tcg_target_long)s->code_ptr);
+        }
+    }
     /* all arguments passed via registers */
     tcg_out_movr(s, 1, TCG_REG_X0, TCG_AREG0);
     tcg_out_movr(s, (TARGET_LONG_BITS == 64), TCG_REG_X1, addr_reg);
@@ -748,7 +845,7 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, int opc)
     } else {
         tcg_out_movr(s, 1, data_reg, TCG_REG_X0);
     }
-
+    reloc_pc26(label_ptr2, (tcg_target_long)s->code_ptr);
 #else /* !CONFIG_SOFTMMU */
     tcg_abort(); /* TODO */
 #endif
@@ -757,8 +854,17 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, int opc)
 static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, int opc)
 {
     TCGReg addr_reg, data_reg;
+    bool bswap;
 #ifdef CONFIG_SOFTMMU
     int mem_index, s_bits;
+    int i;
+    uint8_t *label_ptr[2] = { NULL };
+    uint8_t *label_ptr2;
+#endif
+#ifdef TARGET_WORDS_BIGENDIAN
+    bswap = 1;
+#else
+    bswap = 0;
 #endif
     data_reg = args[0];
     addr_reg = args[1];
@@ -767,8 +873,55 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, int opc)
     mem_index = args[2];
     s_bits = opc & 3;
 
-    /* TODO: insert TLB lookup here */
+    tcg_out_tlb_read(s, addr_reg, s_bits, label_ptr,
+                  offsetof(CPUArchState, tlb_table[mem_index][0].addr_write));
 
+    tcg_out_ldst(s, LDST_64, LDST_LD, TCG_REG_X1, TCG_REG_X2,
+           offsetof(CPUTLBEntry, addend) - offsetof(CPUTLBEntry, addr_write));
+    switch (opc) {
+    case 0:
+        tcg_out_ldst_r(s, LDST_8, LDST_ST, data_reg, addr_reg, TCG_REG_X1);
+        break;
+    case 1:
+        if (bswap) {
+            tcg_out_rev16(s, 1, TCG_REG_X0, data_reg);
+            tcg_out_ldst_r(s, LDST_16, LDST_ST, TCG_REG_X0,
+                      addr_reg, TCG_REG_X1);
+        } else {
+            tcg_out_ldst_r(s, LDST_16, LDST_ST, data_reg,
+                      addr_reg, TCG_REG_X1);
+        }
+        break;
+    case 2:
+        if (bswap) {
+            tcg_out_rev32(s, TCG_REG_X0, data_reg);
+            tcg_out_ldst_r(s, LDST_32, LDST_ST, TCG_REG_X0,
+                       addr_reg, TCG_REG_X1);
+        } else {
+            tcg_out_ldst_r(s, LDST_32, LDST_ST, data_reg,
+                       addr_reg, TCG_REG_X1);
+        }
+        break;
+    case 3:
+        if (bswap) {
+            tcg_out_rev(s, 1, TCG_REG_X0, data_reg);
+            tcg_out_ldst_r(s, LDST_64, LDST_ST, TCG_REG_X0,
+                       addr_reg, TCG_REG_X1);
+        } else {
+            tcg_out_ldst_r(s, LDST_64, LDST_ST, data_reg,
+                       addr_reg, TCG_REG_X1);
+        }
+        break;
+    default:
+        tcg_abort();
+    }
+    label_ptr2 = s->code_ptr;
+    tcg_out_goto_noaddr(s);
+    for (i = 0; i < 2; i++) {
+        if (label_ptr[i]) {
+            reloc_pc19(label_ptr[i], (tcg_target_long)s->code_ptr);
+        }
+    }
     /* all arguments passed via registers */
     tcg_out_movr(s, 1, TCG_REG_X0, TCG_AREG0);
     tcg_out_movr(s, (TARGET_LONG_BITS == 64), TCG_REG_X1, addr_reg);
@@ -777,7 +930,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, int opc)
     tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP,
                  (tcg_target_long)qemu_st_helpers[s_bits]);
     tcg_out_callr(s, TCG_REG_TMP);
-
+    reloc_pc26(label_ptr2, (tcg_target_long)s->code_ptr);
 #else /* !CONFIG_SOFTMMU */
     tcg_abort(); /* TODO */
 #endif
-- 
1.8.1