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>

2 files changed, 26 insertions, 30 deletions

diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h
index a6e0cf1..b757d37 100644
--- a/include/exec/cpu-defs.h
+++ b/include/exec/cpu-defs.h
@@ -65,11 +65,7 @@
 /* use a fully associative victim tlb of 8 entries */
 #define CPU_VTLB_SIZE 8
 
-#if HOST_LONG_BITS == 32 && TARGET_LONG_BITS == 32
-#define CPU_TLB_ENTRY_BITS 4
-#else
 #define CPU_TLB_ENTRY_BITS 5
-#endif
 
 #define CPU_TLB_DYN_MIN_BITS 6
 #define CPU_TLB_DYN_DEFAULT_BITS 8
@@ -95,33 +91,26 @@
 # endif
 
 /* Minimalized TLB entry for use by TCG fast path. */
-typedef struct CPUTLBEntry {
-    /* bit TARGET_LONG_BITS to TARGET_PAGE_BITS : virtual address
-       bit TARGET_PAGE_BITS-1..4  : Nonzero for accesses that should not
-                                    go directly to ram.
-       bit 3                      : indicates that the entry is invalid
-       bit 2..0                   : zero
-    */
-    union {
-        struct {
-            target_ulong addr_read;
-            target_ulong addr_write;
-            target_ulong addr_code;
-            /* Addend to virtual address to get host address.  IO accesses
-               use the corresponding iotlb value.  */
-            uintptr_t addend;
-        };
+typedef union CPUTLBEntry {
+    struct {
+        uint64_t addr_read;
+        uint64_t addr_write;
+        uint64_t addr_code;
         /*
-         * Padding to get a power of two size, as well as index
-         * access to addr_{read,write,code}.
+         * Addend to virtual address to get host address.  IO accesses
+         * use the corresponding iotlb value.
          */
-        target_ulong addr_idx[(1 << CPU_TLB_ENTRY_BITS) / TARGET_LONG_SIZE];
+        uintptr_t addend;
     };
+    /*
+     * Padding to get a power of two size, as well as index
+     * access to addr_{read,write,code}.
+     */
+    uint64_t addr_idx[(1 << CPU_TLB_ENTRY_BITS) / sizeof(uint64_t)];
 } CPUTLBEntry;
 
 QEMU_BUILD_BUG_ON(sizeof(CPUTLBEntry) != (1 << CPU_TLB_ENTRY_BITS));
 
-
 #endif  /* !CONFIG_USER_ONLY && CONFIG_TCG */
 
 #if !defined(CONFIG_USER_ONLY)
diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h
index 5939688..a43b34e 100644
--- a/include/exec/cpu_ldst.h
+++ b/include/exec/cpu_ldst.h
@@ -334,18 +334,25 @@ static inline target_ulong tlb_read_idx(const CPUTLBEntry *entry,
 {
     /* Do not rearrange the CPUTLBEntry structure members. */
     QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_read) !=
-                      MMU_DATA_LOAD * TARGET_LONG_SIZE);
+                      MMU_DATA_LOAD * sizeof(uint64_t));
     QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_write) !=
-                      MMU_DATA_STORE * TARGET_LONG_SIZE);
+                      MMU_DATA_STORE * sizeof(uint64_t));
     QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_code) !=
-                      MMU_INST_FETCH * TARGET_LONG_SIZE);
+                      MMU_INST_FETCH * sizeof(uint64_t));
 
-    const target_ulong *ptr = &entry->addr_idx[access_type];
-#if TCG_OVERSIZED_GUEST
-    return *ptr;
+#if TARGET_LONG_BITS == 32
+    /* Use qatomic_read, in case of addr_write; only care about low bits. */
+    const uint32_t *ptr = (uint32_t *)&entry->addr_idx[access_type];
+    ptr += HOST_BIG_ENDIAN;
+    return qatomic_read(ptr);
 #else
+    const uint64_t *ptr = &entry->addr_idx[access_type];
+# if TCG_OVERSIZED_GUEST
+    return *ptr;
+# else
     /* ofs might correspond to .addr_write, so use qatomic_read */
     return qatomic_read(ptr);
+# endif
 #endif
 }