tcg: Widen CPUTLBEntry comparators to 64-bits

This makes CPUTLBEntry agnostic to the address size of the guest.
When 32-bit addresses are in effect, we can simply read the low
32 bits of the 64-bit field.  Similarly when we need to update
the field for setting TLB_NOTDIRTY.

For TCG backends that could in theory be big-endian, but in
practice are not (arm, loongarch, riscv), use QEMU_BUILD_BUG_ON
to document and ensure this is not accidentally missed.

For s390x, which is always big-endian, use HOST_BIG_ENDIAN anyway,
to document the reason for the adjustment.

For sparc64 and ppc64, always perform a 64-bit load, and rely on
the following 32-bit comparison to ignore the high bits.

Rearrange mips and ppc if ladders for clarity.

Reviewed-by: Anton Johansson <anjo@rev.ng>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

8 files changed, 35 insertions, 19 deletions

diff --git a/tcg/aarch64/tcg-target.c.inc b/tcg/aarch64/tcg-target.c.inc
index 261ad25210..e23c57e2cd 100644
--- a/tcg/aarch64/tcg-target.c.inc
+++ b/tcg/aarch64/tcg-target.c.inc
@@ -1690,6 +1690,7 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
     tcg_out_insn(s, 3502, ADD, 1, TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_TMP0);
 
     /* Load the tlb comparator into TMP0, and the fast path addend into TMP1. */
+    QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN);
     tcg_out_ld(s, addr_type, TCG_REG_TMP0, TCG_REG_TMP1,
                is_ld ? offsetof(CPUTLBEntry, addr_read)
                      : offsetof(CPUTLBEntry, addr_write));
diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc
index 20cc1cc477..64eb0cb5dc 100644
--- a/tcg/arm/tcg-target.c.inc
+++ b/tcg/arm/tcg-target.c.inc
@@ -1430,6 +1430,7 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
      * Add the tlb_table pointer, creating the CPUTLBEntry address in R1.
      * Load the tlb comparator into R2/R3 and the fast path addend into R1.
      */
+    QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN);
     if (cmp_off == 0) {
         if (s->addr_type == TCG_TYPE_I32) {
             tcg_out_ld32_rwb(s, COND_AL, TCG_REG_R2, TCG_REG_R1, TCG_REG_R0);
diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 0bae922982..e89f3b848b 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -875,6 +875,7 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
     tcg_out_opc_add_d(s, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP1);
 
     /* Load the tlb comparator and the addend.  */
+    QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN);
     tcg_out_ld(s, addr_type, TCG_REG_TMP0, TCG_REG_TMP2,
                is_ld ? offsetof(CPUTLBEntry, addr_read)
                      : offsetof(CPUTLBEntry, addr_write));
diff --git a/tcg/mips/tcg-target.c.inc b/tcg/mips/tcg-target.c.inc
index 3274d9aace..4c0de0a380 100644
--- a/tcg/mips/tcg-target.c.inc
+++ b/tcg/mips/tcg-target.c.inc
@@ -1311,14 +1311,17 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
     /* Add the tlb_table pointer, creating the CPUTLBEntry address in TMP3.  */
     tcg_out_opc_reg(s, ALIAS_PADD, TCG_TMP3, TCG_TMP3, TCG_TMP1);
 
+    if (TCG_TARGET_REG_BITS == 32 || addr_type == TCG_TYPE_I32) {
+        /* Load the (low half) tlb comparator.  */
+        tcg_out_ld(s, TCG_TYPE_I32, TCG_TMP0, TCG_TMP3,
+                   cmp_off + HOST_BIG_ENDIAN * 4);
+    } else {
+        tcg_out_ld(s, TCG_TYPE_I64, TCG_TMP0, TCG_TMP3, cmp_off);
+    }
+
     if (TCG_TARGET_REG_BITS == 64 || addr_type == TCG_TYPE_I32) {
-        /* Load the tlb comparator.  */
-        tcg_out_ld(s, addr_type, TCG_TMP0, TCG_TMP3, cmp_off);
         /* Load the tlb addend for the fast path.  */
         tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP3, TCG_TMP3, add_off);
-    } else {
-        /* Load the low half of the tlb comparator.  */
-        tcg_out_ldst(s, OPC_LW, TCG_TMP0, TCG_TMP3, cmp_off + LO_OFF);
     }
 
     /*
diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc
index 11955a6cc2..73f6ea0393 100644
--- a/tcg/ppc/tcg-target.c.inc
+++ b/tcg/ppc/tcg-target.c.inc
@@ -2098,20 +2098,24 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
     }
     tcg_out32(s, AND | SAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_R0));
 
-    /* Load the (low part) TLB comparator into TMP2.  */
-    if (cmp_off == 0
-        && (TCG_TARGET_REG_BITS == 64 || addr_type == TCG_TYPE_I32)) {
-        uint32_t lxu = (TCG_TARGET_REG_BITS == 32 || addr_type == TCG_TYPE_I32
-                        ? LWZUX : LDUX);
-        tcg_out32(s, lxu | TAB(TCG_REG_TMP2, TCG_REG_TMP1, TCG_REG_TMP2));
-    } else {
-        tcg_out32(s, ADD | TAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_TMP2));
-        if (TCG_TARGET_REG_BITS == 32 && addr_type != TCG_TYPE_I32) {
-            tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP2,
-                       TCG_REG_TMP1, cmp_off + 4 * HOST_BIG_ENDIAN);
+    /*
+     * Load the (low part) TLB comparator into TMP2.
+     * For 64-bit host, always load the entire 64-bit slot for simplicity.
+     * We will ignore the high bits with tcg_out_cmp(..., addr_type).
+     */
+    if (TCG_TARGET_REG_BITS == 64) {
+        if (cmp_off == 0) {
+            tcg_out32(s, LDUX | TAB(TCG_REG_TMP2, TCG_REG_TMP1, TCG_REG_TMP2));
         } else {
-            tcg_out_ld(s, addr_type, TCG_REG_TMP2, TCG_REG_TMP1, cmp_off);
+            tcg_out32(s, ADD | TAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_TMP2));
+            tcg_out_ld(s, TCG_TYPE_I64, TCG_REG_TMP2, TCG_REG_TMP1, cmp_off);
         }
+    } else if (cmp_off == 0 && !HOST_BIG_ENDIAN) {
+        tcg_out32(s, LWZUX | TAB(TCG_REG_TMP2, TCG_REG_TMP1, TCG_REG_TMP2));
+    } else {
+        tcg_out32(s, ADD | TAB(TCG_REG_TMP1, TCG_REG_TMP1, TCG_REG_TMP2));
+        tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP2, TCG_REG_TMP1,
+                   cmp_off + 4 * HOST_BIG_ENDIAN);
     }
 
     /*
diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc
index a8f99f7e77..a6d56e2d0e 100644
--- a/tcg/riscv/tcg-target.c.inc
+++ b/tcg/riscv/tcg-target.c.inc
@@ -1249,6 +1249,7 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase,
     }
 
     /* Load the tlb comparator and the addend.  */
+    QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN);
     tcg_out_ld(s, addr_type, TCG_REG_TMP0, TCG_REG_TMP2,
                is_ld ? offsetof(CPUTLBEntry, addr_read)
                      : offsetof(CPUTLBEntry, addr_write));
diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc
index 2795242b60..03be800c3b 100644
--- a/tcg/s390x/tcg-target.c.inc
+++ b/tcg/s390x/tcg-target.c.inc
@@ -1796,6 +1796,7 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
         ofs = offsetof(CPUTLBEntry, addr_write);
     }
     if (addr_type == TCG_TYPE_I32) {
+        ofs += HOST_BIG_ENDIAN * 4;
         tcg_out_insn(s, RX, C, TCG_REG_R0, TCG_TMP0, TCG_REG_NONE, ofs);
     } else {
         tcg_out_insn(s, RXY, CG, TCG_REG_R0, TCG_TMP0, TCG_REG_NONE, ofs);
diff --git a/tcg/sparc64/tcg-target.c.inc b/tcg/sparc64/tcg-target.c.inc
index 48efd83817..6c60657c36 100644
--- a/tcg/sparc64/tcg-target.c.inc
+++ b/tcg/sparc64/tcg-target.c.inc
@@ -1063,8 +1063,12 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
     /* Add the tlb_table pointer, creating the CPUTLBEntry address into R2.  */
     tcg_out_arith(s, TCG_REG_T1, TCG_REG_T1, TCG_REG_T3, ARITH_ADD);
 
-    /* Load the tlb comparator and the addend. */
-    tcg_out_ld(s, addr_type, TCG_REG_T2, TCG_REG_T1, cmp_off);
+    /*
+     * Load the tlb comparator and the addend.
+     * Always load the entire 64-bit comparator for simplicity.
+     * We will ignore the high bits via BPCC_ICC below.
+     */
+    tcg_out_ld(s, TCG_TYPE_I64, TCG_REG_T2, TCG_REG_T1, cmp_off);
     tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_T1, TCG_REG_T1, add_off);
     h->base = TCG_REG_T1;