Merge remote-tracking branch 'remotes/rth/tags/pull-tcg-20180502' into staging

Queued TCG patches

# gpg: Signature made Wed 02 May 2018 18:43:33 BST
# gpg:                using RSA key 64DF38E8AF7E215F
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>"
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth/tags/pull-tcg-20180502:
  tcg: workaround branch instruction overflow in tcg_out_qemu_ld/st
  tcg: Improve TCGv_ptr support
  tcg: Allow wider vectors for cmp and mul
  tcg/arm: Fix memory barrier encoding
  tcg: Document INDEX_mul[us]h_*

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

8 files changed, 150 insertions, 106 deletions

diff --git a/target/hppa/translate.c b/target/hppa/translate.c
index c532889b1f..cdc397308b 100644
--- a/target/hppa/translate.c
+++ b/target/hppa/translate.c
@@ -151,13 +151,7 @@
 #define tcg_gen_qemu_ld_reg  tcg_gen_qemu_ld_i64
 #define tcg_gen_qemu_st_reg  tcg_gen_qemu_st_i64
 #define tcg_gen_atomic_xchg_reg tcg_gen_atomic_xchg_i64
-#if UINTPTR_MAX == UINT32_MAX
-# define tcg_gen_trunc_reg_ptr(p, r) \
-    tcg_gen_trunc_i64_i32(TCGV_PTR_TO_NAT(p), r)
-#else
-# define tcg_gen_trunc_reg_ptr(p, r) \
-    tcg_gen_mov_i64(TCGV_PTR_TO_NAT(p), r)
-#endif
+#define tcg_gen_trunc_reg_ptr   tcg_gen_trunc_i64_ptr
 #else
 #define TCGv_reg             TCGv_i32
 #define tcg_temp_new         tcg_temp_new_i32
@@ -251,13 +245,7 @@
 #define tcg_gen_qemu_ld_reg  tcg_gen_qemu_ld_i32
 #define tcg_gen_qemu_st_reg  tcg_gen_qemu_st_i32
 #define tcg_gen_atomic_xchg_reg tcg_gen_atomic_xchg_i32
-#if UINTPTR_MAX == UINT32_MAX
-# define tcg_gen_trunc_reg_ptr(p, r) \
-    tcg_gen_mov_i32(TCGV_PTR_TO_NAT(p), r)
-#else
-# define tcg_gen_trunc_reg_ptr(p, r) \
-    tcg_gen_extu_i32_i64(TCGV_PTR_TO_NAT(p), r)
-#endif
+#define tcg_gen_trunc_reg_ptr   tcg_gen_ext_i32_ptr
 #endif /* TARGET_REGISTER_BITS */
 
 typedef struct DisasCond {
diff --git a/tcg/README b/tcg/README
index bb2ea5121b..a5237a9edb 100644
--- a/tcg/README
+++ b/tcg/README
@@ -431,6 +431,14 @@ double-word product T0.  The later is returned in two single-word outputs.
 
 Similar to mulu2, except the two inputs T1 and T2 are signed.
 
+* mulsh_i32/i64 t0, t1, t2
+* muluh_i32/i64 t0, t1, t2
+
+Provide the high part of a signed or unsigned multiply, respectively.
+If mulu2/muls2 are not provided by the backend, the tcg-op generator
+can obtain the same results can be obtained by emitting a pair of
+opcodes, mul+muluh/mulsh.
+
 ********* Memory Barrier support
 
 * mb <$arg>
diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c
index dc83f3e5be..56a32a470f 100644
--- a/tcg/arm/tcg-target.inc.c
+++ b/tcg/arm/tcg-target.inc.c
@@ -159,8 +159,8 @@ typedef enum {
     INSN_STRD_IMM  = 0x004000f0,
     INSN_STRD_REG  = 0x000000f0,
 
-    INSN_DMB_ISH   = 0x5bf07ff5,
-    INSN_DMB_MCR   = 0xba0f07ee,
+    INSN_DMB_ISH   = 0xf57ff05b,
+    INSN_DMB_MCR   = 0xee070fba,
 
     /* Architected nop introduced in v6k.  */
     /* ??? This is an MSR (imm) 0,0,0 insn.  Anyone know if this
diff --git a/tcg/tcg-ldst.inc.c b/tcg/tcg-ldst.inc.c
index 0e14cf4357..47f41b921b 100644
--- a/tcg/tcg-ldst.inc.c
+++ b/tcg/tcg-ldst.inc.c
@@ -30,7 +30,7 @@ typedef struct TCGLabelQemuLdst {
     TCGReg datahi_reg;      /* reg index for high word to be loaded or stored */
     tcg_insn_unit *raddr;   /* gen code addr of the next IR of qemu_ld/st IR */
     tcg_insn_unit *label_ptr[2]; /* label pointers to be updated */
-    struct TCGLabelQemuLdst *next;
+    QSIMPLEQ_ENTRY(TCGLabelQemuLdst) next;
 } TCGLabelQemuLdst;
 
 
@@ -46,7 +46,7 @@ static bool tcg_out_ldst_finalize(TCGContext *s)
     TCGLabelQemuLdst *lb;
 
     /* qemu_ld/st slow paths */
-    for (lb = s->ldst_labels; lb != NULL; lb = lb->next) {
+    QSIMPLEQ_FOREACH(lb, &s->ldst_labels, next) {
         if (lb->is_ld) {
             tcg_out_qemu_ld_slow_path(s, lb);
         } else {
@@ -72,7 +72,7 @@ static inline TCGLabelQemuLdst *new_ldst_label(TCGContext *s)
 {
     TCGLabelQemuLdst *l = tcg_malloc(sizeof(*l));
 
-    l->next = s->ldst_labels;
-    s->ldst_labels = l;
+    QSIMPLEQ_INSERT_TAIL(&s->ldst_labels, l, next);
+
     return l;
 }
diff --git a/tcg/tcg-op-vec.c b/tcg/tcg-op-vec.c
index 70ec889bc1..2ca219734d 100644
--- a/tcg/tcg-op-vec.c
+++ b/tcg/tcg-op-vec.c
@@ -355,8 +355,8 @@ void tcg_gen_cmp_vec(TCGCond cond, unsigned vece,
     TCGType type = rt->base_type;
     int can;
 
-    tcg_debug_assert(at->base_type == type);
-    tcg_debug_assert(bt->base_type == type);
+    tcg_debug_assert(at->base_type >= type);
+    tcg_debug_assert(bt->base_type >= type);
     can = tcg_can_emit_vec_op(INDEX_op_cmp_vec, type, vece);
     if (can > 0) {
         vec_gen_4(INDEX_op_cmp_vec, type, vece, ri, ai, bi, cond);
@@ -377,8 +377,8 @@ void tcg_gen_mul_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
     TCGType type = rt->base_type;
     int can;
 
-    tcg_debug_assert(at->base_type == type);
-    tcg_debug_assert(bt->base_type == type);
+    tcg_debug_assert(at->base_type >= type);
+    tcg_debug_assert(bt->base_type >= type);
     can = tcg_can_emit_vec_op(INDEX_op_mul_vec, type, vece);
     if (can > 0) {
         vec_gen_3(INDEX_op_mul_vec, type, vece, ri, ai, bi);
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index 75bb55aeac..5d2c91a1b6 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -1137,25 +1137,74 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t);
 #endif
 
 #if UINTPTR_MAX == UINT32_MAX
-# define tcg_gen_ld_ptr(R, A, O) \
-    tcg_gen_ld_i32(TCGV_PTR_TO_NAT(R), (A), (O))
-# define tcg_gen_discard_ptr(A) \
-    tcg_gen_discard_i32(TCGV_PTR_TO_NAT(A))
-# define tcg_gen_add_ptr(R, A, B) \
-    tcg_gen_add_i32(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), TCGV_PTR_TO_NAT(B))
-# define tcg_gen_addi_ptr(R, A, B) \
-    tcg_gen_addi_i32(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), (B))
-# define tcg_gen_ext_i32_ptr(R, A) \
-    tcg_gen_mov_i32(TCGV_PTR_TO_NAT(R), (A))
+# define PTR  i32
+# define NAT  TCGv_i32
 #else
-# define tcg_gen_ld_ptr(R, A, O) \
-    tcg_gen_ld_i64(TCGV_PTR_TO_NAT(R), (A), (O))
-# define tcg_gen_discard_ptr(A) \
-    tcg_gen_discard_i64(TCGV_PTR_TO_NAT(A))
-# define tcg_gen_add_ptr(R, A, B) \
-    tcg_gen_add_i64(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), TCGV_PTR_TO_NAT(B))
-# define tcg_gen_addi_ptr(R, A, B) \
-    tcg_gen_addi_i64(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), (B))
-# define tcg_gen_ext_i32_ptr(R, A) \
-    tcg_gen_ext_i32_i64(TCGV_PTR_TO_NAT(R), (A))
-#endif /* UINTPTR_MAX == UINT32_MAX */
+# define PTR  i64
+# define NAT  TCGv_i64
+#endif
+
+static inline void tcg_gen_ld_ptr(TCGv_ptr r, TCGv_ptr a, intptr_t o)
+{
+    glue(tcg_gen_ld_,PTR)((NAT)r, a, o);
+}
+
+static inline void tcg_gen_discard_ptr(TCGv_ptr a)
+{
+    glue(tcg_gen_discard_,PTR)((NAT)a);
+}
+
+static inline void tcg_gen_add_ptr(TCGv_ptr r, TCGv_ptr a, TCGv_ptr b)
+{
+    glue(tcg_gen_add_,PTR)((NAT)r, (NAT)a, (NAT)b);
+}
+
+static inline void tcg_gen_addi_ptr(TCGv_ptr r, TCGv_ptr a, intptr_t b)
+{
+    glue(tcg_gen_addi_,PTR)((NAT)r, (NAT)a, b);
+}
+
+static inline void tcg_gen_brcondi_ptr(TCGCond cond, TCGv_ptr a,
+                                       intptr_t b, TCGLabel *label)
+{
+    glue(tcg_gen_brcondi_,PTR)(cond, (NAT)a, b, label);
+}
+
+static inline void tcg_gen_ext_i32_ptr(TCGv_ptr r, TCGv_i32 a)
+{
+#if UINTPTR_MAX == UINT32_MAX
+    tcg_gen_mov_i32((NAT)r, a);
+#else
+    tcg_gen_ext_i32_i64((NAT)r, a);
+#endif
+}
+
+static inline void tcg_gen_trunc_i64_ptr(TCGv_ptr r, TCGv_i64 a)
+{
+#if UINTPTR_MAX == UINT32_MAX
+    tcg_gen_extrl_i64_i32((NAT)r, a);
+#else
+    tcg_gen_mov_i64((NAT)r, a);
+#endif
+}
+
+static inline void tcg_gen_extu_ptr_i64(TCGv_i64 r, TCGv_ptr a)
+{
+#if UINTPTR_MAX == UINT32_MAX
+    tcg_gen_extu_i32_i64(r, (NAT)a);
+#else
+    tcg_gen_mov_i64(r, (NAT)a);
+#endif
+}
+
+static inline void tcg_gen_trunc_ptr_i32(TCGv_i32 r, TCGv_ptr a)
+{
+#if UINTPTR_MAX == UINT32_MAX
+    tcg_gen_mov_i32(r, (NAT)a);
+#else
+    tcg_gen_extrl_i64_i32(r, (NAT)a);
+#endif
+}
+
+#undef PTR
+#undef NAT
diff --git a/tcg/tcg.c b/tcg/tcg.c
index bb24526c93..551caf1c53 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -980,7 +980,7 @@ TCGTemp *tcg_global_mem_new_internal(TCGType type, TCGv_ptr base,
     return ts;
 }
 
-static TCGTemp *tcg_temp_new_internal(TCGType type, int temp_local)
+TCGTemp *tcg_temp_new_internal(TCGType type, bool temp_local)
 {
     TCGContext *s = tcg_ctx;
     TCGTemp *ts;
@@ -1025,18 +1025,6 @@ static TCGTemp *tcg_temp_new_internal(TCGType type, int temp_local)
     return ts;
 }
 
-TCGv_i32 tcg_temp_new_internal_i32(int temp_local)
-{
-    TCGTemp *t = tcg_temp_new_internal(TCG_TYPE_I32, temp_local);
-    return temp_tcgv_i32(t);
-}
-
-TCGv_i64 tcg_temp_new_internal_i64(int temp_local)
-{
-    TCGTemp *t = tcg_temp_new_internal(TCG_TYPE_I64, temp_local);
-    return temp_tcgv_i64(t);
-}
-
 TCGv_vec tcg_temp_new_vec(TCGType type)
 {
     TCGTemp *t;
@@ -1072,7 +1060,7 @@ TCGv_vec tcg_temp_new_vec_matching(TCGv_vec match)
     return temp_tcgv_vec(t);
 }
 
-static void tcg_temp_free_internal(TCGTemp *ts)
+void tcg_temp_free_internal(TCGTemp *ts)
 {
     TCGContext *s = tcg_ctx;
     int k, idx;
@@ -1093,21 +1081,6 @@ static void tcg_temp_free_internal(TCGTemp *ts)
     set_bit(idx, s->free_temps[k].l);
 }
 
-void tcg_temp_free_i32(TCGv_i32 arg)
-{
-    tcg_temp_free_internal(tcgv_i32_temp(arg));
-}
-
-void tcg_temp_free_i64(TCGv_i64 arg)
-{
-    tcg_temp_free_internal(tcgv_i64_temp(arg));
-}
-
-void tcg_temp_free_vec(TCGv_vec arg)
-{
-    tcg_temp_free_internal(tcgv_vec_temp(arg));
-}
-
 TCGv_i32 tcg_const_i32(int32_t val)
 {
     TCGv_i32 t0;
@@ -3324,7 +3297,7 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb)
     s->code_ptr = tb->tc.ptr;
 
 #ifdef TCG_TARGET_NEED_LDST_LABELS
-    s->ldst_labels = NULL;
+    QSIMPLEQ_INIT(&s->ldst_labels);
 #endif
 #ifdef TCG_TARGET_NEED_POOL_LABELS
     s->pool_labels = NULL;
diff --git a/tcg/tcg.h b/tcg/tcg.h
index 30896ca304..75fbad128b 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -699,7 +699,7 @@ struct TCGContext {
 
     /* These structures are private to tcg-target.inc.c.  */
 #ifdef TCG_TARGET_NEED_LDST_LABELS
-    struct TCGLabelQemuLdst *ldst_labels;
+    QSIMPLEQ_HEAD(ldst_labels, TCGLabelQemuLdst) ldst_labels;
 #endif
 #ifdef TCG_TARGET_NEED_POOL_LABELS
     struct TCGLabelPoolData *pool_labels;
@@ -890,15 +890,30 @@ void tcg_set_frame(TCGContext *s, TCGReg reg, intptr_t start, intptr_t size);
 
 TCGTemp *tcg_global_mem_new_internal(TCGType, TCGv_ptr,
                                      intptr_t, const char *);
-
-TCGv_i32 tcg_temp_new_internal_i32(int temp_local);
-TCGv_i64 tcg_temp_new_internal_i64(int temp_local);
+TCGTemp *tcg_temp_new_internal(TCGType, bool);
+void tcg_temp_free_internal(TCGTemp *);
 TCGv_vec tcg_temp_new_vec(TCGType type);
 TCGv_vec tcg_temp_new_vec_matching(TCGv_vec match);
 
-void tcg_temp_free_i32(TCGv_i32 arg);
-void tcg_temp_free_i64(TCGv_i64 arg);
-void tcg_temp_free_vec(TCGv_vec arg);
+static inline void tcg_temp_free_i32(TCGv_i32 arg)
+{
+    tcg_temp_free_internal(tcgv_i32_temp(arg));
+}
+
+static inline void tcg_temp_free_i64(TCGv_i64 arg)
+{
+    tcg_temp_free_internal(tcgv_i64_temp(arg));
+}
+
+static inline void tcg_temp_free_ptr(TCGv_ptr arg)
+{
+    tcg_temp_free_internal(tcgv_ptr_temp(arg));
+}
+
+static inline void tcg_temp_free_vec(TCGv_vec arg)
+{
+    tcg_temp_free_internal(tcgv_vec_temp(arg));
+}
 
 static inline TCGv_i32 tcg_global_mem_new_i32(TCGv_ptr reg, intptr_t offset,
                                               const char *name)
@@ -909,12 +924,14 @@ static inline TCGv_i32 tcg_global_mem_new_i32(TCGv_ptr reg, intptr_t offset,
 
 static inline TCGv_i32 tcg_temp_new_i32(void)
 {
-    return tcg_temp_new_internal_i32(0);
+    TCGTemp *t = tcg_temp_new_internal(TCG_TYPE_I32, false);
+    return temp_tcgv_i32(t);
 }
 
 static inline TCGv_i32 tcg_temp_local_new_i32(void)
 {
-    return tcg_temp_new_internal_i32(1);
+    TCGTemp *t = tcg_temp_new_internal(TCG_TYPE_I32, true);
+    return temp_tcgv_i32(t);
 }
 
 static inline TCGv_i64 tcg_global_mem_new_i64(TCGv_ptr reg, intptr_t offset,
@@ -926,12 +943,33 @@ static inline TCGv_i64 tcg_global_mem_new_i64(TCGv_ptr reg, intptr_t offset,
 
 static inline TCGv_i64 tcg_temp_new_i64(void)
 {
-    return tcg_temp_new_internal_i64(0);
+    TCGTemp *t = tcg_temp_new_internal(TCG_TYPE_I64, false);
+    return temp_tcgv_i64(t);
 }
 
 static inline TCGv_i64 tcg_temp_local_new_i64(void)
 {
-    return tcg_temp_new_internal_i64(1);
+    TCGTemp *t = tcg_temp_new_internal(TCG_TYPE_I64, true);
+    return temp_tcgv_i64(t);
+}
+
+static inline TCGv_ptr tcg_global_mem_new_ptr(TCGv_ptr reg, intptr_t offset,
+                                              const char *name)
+{
+    TCGTemp *t = tcg_global_mem_new_internal(TCG_TYPE_PTR, reg, offset, name);
+    return temp_tcgv_ptr(t);
+}
+
+static inline TCGv_ptr tcg_temp_new_ptr(void)
+{
+    TCGTemp *t = tcg_temp_new_internal(TCG_TYPE_PTR, false);
+    return temp_tcgv_ptr(t);
+}
+
+static inline TCGv_ptr tcg_temp_local_new_ptr(void)
+{
+    TCGTemp *t = tcg_temp_new_internal(TCG_TYPE_PTR, true);
+    return temp_tcgv_ptr(t);
 }
 
 #if defined(CONFIG_DEBUG_TCG)
@@ -1009,26 +1047,6 @@ do {\
     abort();\
 } while (0)
 
-#if UINTPTR_MAX == UINT32_MAX
-static inline TCGv_ptr TCGV_NAT_TO_PTR(TCGv_i32 n) { return (TCGv_ptr)n; }
-static inline TCGv_i32 TCGV_PTR_TO_NAT(TCGv_ptr n) { return (TCGv_i32)n; }
-
-#define tcg_const_ptr(V) TCGV_NAT_TO_PTR(tcg_const_i32((intptr_t)(V)))
-#define tcg_global_mem_new_ptr(R, O, N) \
-    TCGV_NAT_TO_PTR(tcg_global_mem_new_i32((R), (O), (N)))
-#define tcg_temp_new_ptr() TCGV_NAT_TO_PTR(tcg_temp_new_i32())
-#define tcg_temp_free_ptr(T) tcg_temp_free_i32(TCGV_PTR_TO_NAT(T))
-#else
-static inline TCGv_ptr TCGV_NAT_TO_PTR(TCGv_i64 n) { return (TCGv_ptr)n; }
-static inline TCGv_i64 TCGV_PTR_TO_NAT(TCGv_ptr n) { return (TCGv_i64)n; }
-
-#define tcg_const_ptr(V) TCGV_NAT_TO_PTR(tcg_const_i64((intptr_t)(V)))
-#define tcg_global_mem_new_ptr(R, O, N) \
-    TCGV_NAT_TO_PTR(tcg_global_mem_new_i64((R), (O), (N)))
-#define tcg_temp_new_ptr() TCGV_NAT_TO_PTR(tcg_temp_new_i64())
-#define tcg_temp_free_ptr(T) tcg_temp_free_i64(TCGV_PTR_TO_NAT(T))
-#endif
-
 bool tcg_op_supported(TCGOpcode op);
 
 void tcg_gen_callN(void *func, TCGTemp *ret, int nargs, TCGTemp **args);
@@ -1052,6 +1070,14 @@ TCGv_vec tcg_const_ones_vec(TCGType);
 TCGv_vec tcg_const_zeros_vec_matching(TCGv_vec);
 TCGv_vec tcg_const_ones_vec_matching(TCGv_vec);
 
+#if UINTPTR_MAX == UINT32_MAX
+# define tcg_const_ptr(x)        ((TCGv_ptr)tcg_const_i32((intptr_t)(x)))
+# define tcg_const_local_ptr(x)  ((TCGv_ptr)tcg_const_local_i32((intptr_t)(x)))
+#else
+# define tcg_const_ptr(x)        ((TCGv_ptr)tcg_const_i64((intptr_t)(x)))
+# define tcg_const_local_ptr(x)  ((TCGv_ptr)tcg_const_local_i64((intptr_t)(x)))
+#endif
+
 TCGLabel *gen_new_label(void);
 
 /**