include/exec: Use uintptr_t in CPUTLBEntry

Since we no longer support 64-bit guests on 32-bit hosts,
we can use a 32-bit type on a 32-bit host.  This shrinks
the size of the structure to 16 bytes on a 32-bit host.

Reviewed-by: Philippe Mathieu-Daudé <[email protected]>
Signed-off-by: Richard Henderson <[email protected]>

Author: rth7680

accel/tcg/cputlb.c

@@ -104,22 +104,15 @@ static inline uint64_t tlb_read_idx(const CPUTLBEntry *entry,
 {
     /* Do not rearrange the CPUTLBEntry structure members. */
     QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_read) !=
-                      MMU_DATA_LOAD * sizeof(uint64_t));
+                      MMU_DATA_LOAD * sizeof(uintptr_t));
     QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_write) !=
-                      MMU_DATA_STORE * sizeof(uint64_t));
+                      MMU_DATA_STORE * sizeof(uintptr_t));
     QEMU_BUILD_BUG_ON(offsetof(CPUTLBEntry, addr_code) !=
-                      MMU_INST_FETCH * sizeof(uint64_t));
+                      MMU_INST_FETCH * sizeof(uintptr_t));
 
-#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];
+    const uintptr_t *ptr = &entry->addr_idx[access_type];
     /* ofs might correspond to .addr_write, so use qatomic_read */
     return qatomic_read(ptr);
-#endif
 }
 
 static inline uint64_t tlb_addr_write(const CPUTLBEntry *entry)
@@ -899,14 +892,8 @@ static void tlb_reset_dirty_range_locked(CPUTLBEntry *tlb_entry,
         addr &= TARGET_PAGE_MASK;
         addr += tlb_entry->addend;
         if ((addr - start) < length) {
-#if TARGET_LONG_BITS == 32
-            uint32_t *ptr_write = (uint32_t *)&tlb_entry->addr_write;
-            ptr_write += HOST_BIG_ENDIAN;
-            qatomic_set(ptr_write, *ptr_write | TLB_NOTDIRTY);
-#else
             qatomic_set(&tlb_entry->addr_write,
                         tlb_entry->addr_write | TLB_NOTDIRTY);
-#endif
         }
     }
 }

include/exec/tlb-common.h

@@ -19,14 +19,14 @@
 #ifndef EXEC_TLB_COMMON_H
 #define EXEC_TLB_COMMON_H 1
 
-#define CPU_TLB_ENTRY_BITS 5
+#define CPU_TLB_ENTRY_BITS (HOST_LONG_BITS == 32 ? 4 : 5)
 
 /* Minimalized TLB entry for use by TCG fast path. */
 typedef union CPUTLBEntry {
     struct {
-        uint64_t addr_read;
-        uint64_t addr_write;
-        uint64_t addr_code;
+        uintptr_t addr_read;
+        uintptr_t addr_write;
+        uintptr_t addr_code;
         /*
          * Addend to virtual address to get host address.  IO accesses
          * use the corresponding iotlb value.
@@ -37,7 +37,7 @@ typedef union CPUTLBEntry {
      * 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)];
+    uintptr_t addr_idx[(1 << CPU_TLB_ENTRY_BITS) / sizeof(uintptr_t)];
 } CPUTLBEntry;
 
 QEMU_BUILD_BUG_ON(sizeof(CPUTLBEntry) != (1 << CPU_TLB_ENTRY_BITS));

tcg/arm/tcg-target.c.inc

@@ -1500,7 +1500,6 @@ 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 and the fast path addend into R1.
          */
-        QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN);
         if (cmp_off == 0) {
             tcg_out_ld32_rwb(s, COND_AL, TCG_REG_R2, TCG_REG_R1, TCG_REG_R0);
         } else {

tcg/mips/tcg-target.c.inc

@@ -1262,18 +1262,16 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, HostAddress *h,
         /* Add the tlb_table pointer, creating the CPUTLBEntry address.  */
         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.  */
+        /* Load the tlb comparator.  */
+        if (TCG_TARGET_REG_BITS == 64 && addr_type == TCG_TYPE_I32) {
             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);
+            tcg_out_ld(s, TCG_TYPE_REG, TCG_TMP0, TCG_TMP3, cmp_off);
         }
 
-        if (TCG_TARGET_REG_BITS == 64 || addr_type == TCG_TYPE_I32) {
-            /* Load the tlb addend for the fast path.  */
-            tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP3, TCG_TMP3, add_off);
-        }
+        /* Load the tlb addend for the fast path.  */
+        tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP3, TCG_TMP3, add_off);
 
         /*
          * Mask the page bits, keeping the alignment bits to compare against.

tcg/ppc/tcg-target.c.inc

@@ -2490,27 +2490,16 @@ 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.
+         * Load the 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_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));
+        if (cmp_off == 0) {
+            tcg_out32(s, (TCG_TARGET_REG_BITS == 64 ? LDUX : 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);
+            tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP2, TCG_REG_TMP1, cmp_off);
         }
 
         /*