Merge branch 'tcg-sparc' of git://repo.or.cz/qemu/rth

* 'tcg-sparc' of git://repo.or.cz/qemu/rth:
  tcg-sparc: Preserve branch destinations during retranslation
  tcg-sparc: Fix and enable direct TB chaining.
  tcg-sparc: Add %g/%o registers to alloc_order
  tcg-sparc: Use defines for temporaries.
  tcg-sparc: Mask shift immediates to avoid illegal insns.
  tcg-sparc: Clean up cruft stemming from attempts to use global registers.
  tcg-sparc: Change AREG0 in generated code to %i0.
  tcg-sparc: Support GUEST_BASE.
  tcg-sparc: Fix qemu_ld/st to handle 32-bit host.
  tcg-sparc: Assume v9 cpu always, i.e. force v8plus in 32-bit mode.
  tcg-sparc: Don't MAP_FIXED on top of the program
  tcg-sparc: Fix ADDX opcode.
  tcg-sparc: Hack in qemu_ld/st64 for 32-bit.
  linux-user: Use memcpy in get_user/put_user.

Author: blueswirl

Diff for: configure

@@ -111,7 +111,6 @@ source_path=`dirname "$0"`
 cpu=""
 interp_prefix="/usr/gnemul/qemu-%M"
 static="no"
-sparc_cpu=""
 cross_prefix=""
 audio_drv_list=""
 audio_card_list="ac97 es1370 sb16 hda"
@@ -241,21 +240,6 @@ for opt do
   ;;
   --disable-debug-info) debug_info="no"
   ;;
-  --sparc_cpu=*)
-    sparc_cpu="$optarg"
-    case $sparc_cpu in
-    v7|v8|v8plus|v8plusa)
-      cpu="sparc"
-    ;;
-    v9)
-      cpu="sparc64"
-    ;;
-    *)
-      echo "undefined SPARC architecture. Exiting";
-      exit 1
-    ;;
-    esac
-  ;;
   esac
 done
 # OS specific
@@ -343,8 +327,6 @@ elif check_define __i386__ ; then
 elif check_define __x86_64__ ; then
   cpu="x86_64"
 elif check_define __sparc__ ; then
-  # We can't check for 64 bit (when gcc is biarch) or V8PLUSA
-  # They must be specified using --sparc_cpu
   if check_define __arch64__ ; then
     cpu="sparc64"
   else
@@ -792,8 +774,6 @@ for opt do
   ;;
   --enable-uname-release=*) uname_release="$optarg"
   ;;
-  --sparc_cpu=*)
-  ;;
   --enable-werror) werror="yes"
   ;;
   --disable-werror) werror="no"
@@ -881,35 +861,17 @@ for opt do
   esac
 done
 
-#
-# If cpu ~= sparc and  sparc_cpu hasn't been defined, plug in the right
-# QEMU_CFLAGS/LDFLAGS (assume sparc_v8plus for 32-bit and sparc_v9 for 64-bit)
-#
 host_guest_base="no"
 case "$cpu" in
-    sparc) case $sparc_cpu in
-           v7|v8)
-             QEMU_CFLAGS="-mcpu=${sparc_cpu} -D__sparc_${sparc_cpu}__ $QEMU_CFLAGS"
-           ;;
-           v8plus|v8plusa)
-             QEMU_CFLAGS="-mcpu=ultrasparc -D__sparc_${sparc_cpu}__ $QEMU_CFLAGS"
-           ;;
-           *) # sparc_cpu not defined in the command line
-             QEMU_CFLAGS="-mcpu=ultrasparc -D__sparc_v8plus__ $QEMU_CFLAGS"
-           esac
+    sparc)
            LDFLAGS="-m32 $LDFLAGS"
-           QEMU_CFLAGS="-m32 -ffixed-g2 -ffixed-g3 $QEMU_CFLAGS"
-           if test "$solaris" = "no" ; then
-             QEMU_CFLAGS="-ffixed-g1 -ffixed-g6 $QEMU_CFLAGS"
-           fi
+           QEMU_CFLAGS="-m32 -mcpu=ultrasparc $QEMU_CFLAGS"
+           host_guest_base="yes"
            ;;
     sparc64)
-           QEMU_CFLAGS="-m64 -mcpu=ultrasparc -D__sparc_v9__ $QEMU_CFLAGS"
            LDFLAGS="-m64 $LDFLAGS"
-           QEMU_CFLAGS="-ffixed-g5 -ffixed-g6 -ffixed-g7 $QEMU_CFLAGS"
-           if test "$solaris" != "no" ; then
-             QEMU_CFLAGS="-ffixed-g1 $QEMU_CFLAGS"
-           fi
+           QEMU_CFLAGS="-m64 -mcpu=ultrasparc $QEMU_CFLAGS"
+           host_guest_base="yes"
            ;;
     s390)
            QEMU_CFLAGS="-m31 -march=z990 $QEMU_CFLAGS"
@@ -4131,10 +4093,6 @@ fi
 
 if test "$target_linux_user" = "yes" -o "$target_bsd_user" = "yes" ; then
   case "$ARCH" in
-  sparc)
-    # -static is used to avoid g1/g3 usage by the dynamic linker
-    ldflags="$linker_script -static $ldflags"
-    ;;
   alpha | s390x)
     # The default placement of the application is fine.
     ;;

Diff for: disas.c

@@ -316,9 +316,7 @@ void disas(FILE *out, void *code, unsigned long size)
     print_insn = print_insn_alpha;
 #elif defined(__sparc__)
     print_insn = print_insn_sparc;
-#if defined(__sparc_v8plus__) || defined(__sparc_v8plusa__) || defined(__sparc_v9__)
     disasm_info.mach = bfd_mach_sparc_v9b;
-#endif
 #elif defined(__arm__)
     print_insn = print_insn_arm;
 #elif defined(__MIPSEB__)

Diff for: exec-all.h

@@ -132,9 +132,10 @@ static inline void tlb_flush(CPUArchState *env, int flush_global)
 #define CODE_GEN_AVG_BLOCK_SIZE 64
 #endif
 
-#if defined(_ARCH_PPC) || defined(__x86_64__) || defined(__arm__) || defined(__i386__)
-#define USE_DIRECT_JUMP
-#elif defined(CONFIG_TCG_INTERPRETER)
+#if defined(__arm__) || defined(_ARCH_PPC) \
+    || defined(__x86_64__) || defined(__i386__) \
+    || defined(__sparc__) \
+    || defined(CONFIG_TCG_INTERPRETER)
 #define USE_DIRECT_JUMP
 #endif
 
@@ -244,6 +245,8 @@ static inline void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr)
     __asm __volatile__ ("swi 0x9f0002" : : "r" (_beg), "r" (_end), "r" (_flg));
 #endif
 }
+#elif defined(__sparc__)
+void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr);
 #else
 #error tb_set_jmp_target1 is missing
 #endif

Diff for: exec.c

@@ -86,7 +86,7 @@ static int nb_tbs;
 /* any access to the tbs or the page table must use this lock */
 spinlock_t tb_lock = SPIN_LOCK_UNLOCKED;
 
-#if defined(__arm__) || defined(__sparc_v9__)
+#if defined(__arm__) || defined(__sparc__)
 /* The prologue must be reachable with a direct jump. ARM and Sparc64
  have limited branch ranges (possibly also PPC) so place it in a
  section close to code segment. */
@@ -541,10 +541,9 @@ static void code_gen_alloc(unsigned long tb_size)
         /* Cannot map more than that */
         if (code_gen_buffer_size > (800 * 1024 * 1024))
             code_gen_buffer_size = (800 * 1024 * 1024);
-#elif defined(__sparc_v9__)
+#elif defined(__sparc__) && HOST_LONG_BITS == 64
         // Map the buffer below 2G, so we can use direct calls and branches
-        flags |= MAP_FIXED;
-        start = (void *) 0x60000000UL;
+        start = (void *) 0x40000000UL;
         if (code_gen_buffer_size > (512 * 1024 * 1024))
             code_gen_buffer_size = (512 * 1024 * 1024);
 #elif defined(__arm__)
@@ -582,10 +581,9 @@ static void code_gen_alloc(unsigned long tb_size)
         /* Cannot map more than that */
         if (code_gen_buffer_size > (800 * 1024 * 1024))
             code_gen_buffer_size = (800 * 1024 * 1024);
-#elif defined(__sparc_v9__)
+#elif defined(__sparc__) && HOST_LONG_BITS == 64
         // Map the buffer below 2G, so we can use direct calls and branches
-        flags |= MAP_FIXED;
-        addr = (void *) 0x60000000UL;
+        addr = (void *) 0x40000000UL;
         if (code_gen_buffer_size > (512 * 1024 * 1024)) {
             code_gen_buffer_size = (512 * 1024 * 1024);
         }

Diff for: linux-user/qemu.h

@@ -289,46 +289,29 @@ static inline int access_ok(int type, abi_ulong addr, abi_ulong size)
  * struct has been locked - usually with lock_user_struct().
  */
 #define __put_user(x, hptr)\
-({\
+({ __typeof(*hptr) pu_ = (x);\
     switch(sizeof(*hptr)) {\
-    case 1:\
-        *(uint8_t *)(hptr) = (uint8_t)(typeof(*hptr))(x);\
-        break;\
-    case 2:\
-        *(uint16_t *)(hptr) = tswap16((uint16_t)(typeof(*hptr))(x));\
-        break;\
-    case 4:\
-        *(uint32_t *)(hptr) = tswap32((uint32_t)(typeof(*hptr))(x));\
-        break;\
-    case 8:\
-        *(uint64_t *)(hptr) = tswap64((typeof(*hptr))(x));\
-        break;\
-    default:\
-        abort();\
+    case 1: break;\
+    case 2: pu_ = tswap16(pu_); break; \
+    case 4: pu_ = tswap32(pu_); break; \
+    case 8: pu_ = tswap64(pu_); break; \
+    default: abort();\
     }\
+    memcpy(hptr, &pu_, sizeof(pu_)); \
     0;\
 })
 
 #define __get_user(x, hptr) \
-({\
+({ __typeof(*hptr) gu_; \
+    memcpy(&gu_, hptr, sizeof(gu_)); \
     switch(sizeof(*hptr)) {\
-    case 1:\
-        x = (typeof(*hptr))*(uint8_t *)(hptr);\
-        break;\
-    case 2:\
-        x = (typeof(*hptr))tswap16(*(uint16_t *)(hptr));\
-        break;\
-    case 4:\
-        x = (typeof(*hptr))tswap32(*(uint32_t *)(hptr));\
-        break;\
-    case 8:\
-        x = (typeof(*hptr))tswap64(*(uint64_t *)(hptr));\
-        break;\
-    default:\
-        /* avoid warning */\
-        x = 0;\
-        abort();\
+    case 1: break; \
+    case 2: gu_ = tswap16(gu_); break; \
+    case 4: gu_ = tswap32(gu_); break; \
+    case 8: gu_ = tswap64(gu_); break; \
+    default: abort();\
     }\
+    (x) = gu_; \
     0;\
 })
 

Diff for: qemu-timer.h

@@ -218,7 +218,7 @@ static inline int64_t cpu_get_real_ticks(void)
     return val;
 }
 
-#elif defined(__sparc_v8plus__) || defined(__sparc_v8plusa__) || defined(__sparc_v9__)
+#elif defined(__sparc__)
 
 static inline int64_t cpu_get_real_ticks (void)
 {
@@ -227,15 +227,17 @@ static inline int64_t cpu_get_real_ticks (void)
     asm volatile("rd %%tick,%0" : "=r"(rval));
     return rval;
 #else
+    /* We need an %o or %g register for this.  For recent enough gcc
+       there is an "h" constraint for that.  Don't bother with that.  */
     union {
         uint64_t i64;
         struct {
             uint32_t high;
             uint32_t low;
         }       i32;
     } rval;
-    asm volatile("rd %%tick,%1; srlx %1,32,%0"
-                 : "=r"(rval.i32.high), "=r"(rval.i32.low));
+    asm volatile("rd %%tick,%%g1; srlx %%g1,32,%0; mov %%g1,%1"
+                 : "=r"(rval.i32.high), "=r"(rval.i32.low) : : "g1");
     return rval.i64;
 #endif
 }