tcg: Use memset for large vector byte replication

In f47db80cc07, we handled odd-sized tail clearing for
the case of hosts that have vector operations, but did
not handle the case of hosts that do not have vector ops.

This was ok until e2e7168a214b, which changed the encoding
of simd_desc such that the odd sizes are impossible.

Add memset as a tcg helper, and use that for all out-of-line
byte stores to vectors.  This includes, but is not limited to,
the tail clearing operation in question.

Cc: qemu-stable@nongnu.org
Buglink: https://bugs.launchpad.net/bugs/1907817
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

diff --git a/accel/tcg/tcg-runtime.h b/accel/tcg/tcg-runtime.h
index 4eda24e63af46de4873822cdabf5faa070a41e85..2e36d6eb0c66393ffa3656e884012dac98aa38f4 100644 (file)
--- a/accel/tcg/tcg-runtime.h
+++ b/accel/tcg/tcg-runtime.h
@@ -28,6 +28,17 @@ DEF_HELPER_FLAGS_1(lookup_tb_ptr, TCG_CALL_NO_WG_SE, ptr, env)
 
 DEF_HELPER_FLAGS_1(exit_atomic, TCG_CALL_NO_WG, noreturn, env)
 
+#ifndef IN_HELPER_PROTO
+/*
+ * Pass calls to memset directly to libc, without a thunk in qemu.
+ * Do not re-declare memset, especially since we fudge the type here;
+ * we assume sizeof(void *) == sizeof(size_t), which is true for
+ * all supported hosts.
+ */
+#define helper_memset memset
+DEF_HELPER_FLAGS_3(memset, TCG_CALL_NO_RWG, ptr, ptr, int, ptr)
+#endif /* IN_HELPER_PROTO */
+
 #ifdef CONFIG_SOFTMMU
 
 DEF_HELPER_FLAGS_5(atomic_cmpxchgb, TCG_CALL_NO_WG,

diff --git a/include/exec/helper-proto.h b/include/exec/helper-proto.h
index a0a8d9aa46f02eaeec1ffdd6a54772a100cbaa83..659f9298e8fe2935cd3ea9931d448dd9b6f88c69 100644 (file)
--- a/include/exec/helper-proto.h
+++ b/include/exec/helper-proto.h
@@ -35,11 +35,15 @@ dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), dh_ctype(t3), \
                             dh_ctype(t4), dh_ctype(t5), dh_ctype(t6), \
                             dh_ctype(t7));
 
+#define IN_HELPER_PROTO
+
 #include "helper.h"
 #include "trace/generated-helpers.h"
 #include "tcg-runtime.h"
 #include "plugin-helpers.h"
 
+#undef IN_HELPER_PROTO
+
 #undef DEF_HELPER_FLAGS_0
 #undef DEF_HELPER_FLAGS_1
 #undef DEF_HELPER_FLAGS_2

diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index ddbe06b71a81fad997c6348b68d9a1f233553118..1a41dfa90871740669799867f34d20d5d60d9e3d 100644 (file)
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -547,6 +547,9 @@ static void do_dup(unsigned vece, uint32_t dofs, uint32_t oprsz,
         in_c = dup_const(vece, in_c);
         if (in_c == 0) {
             oprsz = maxsz;
+            vece = MO_8;
+        } else if (in_c == dup_const(MO_8, in_c)) {
+            vece = MO_8;
         }
     }
 
@@ -628,6 +631,35 @@ static void do_dup(unsigned vece, uint32_t dofs, uint32_t oprsz,
     /* Otherwise implement out of line.  */
     t_ptr = tcg_temp_new_ptr();
     tcg_gen_addi_ptr(t_ptr, cpu_env, dofs);
+
+    /*
+     * This may be expand_clr for the tail of an operation, e.g.
+     * oprsz == 8 && maxsz == 64.  The size of the clear is misaligned
+     * wrt simd_desc and will assert.  Simply pass all replicated byte
+     * stores through to memset.
+     */
+    if (oprsz == maxsz && vece == MO_8) {
+        TCGv_ptr t_size = tcg_const_ptr(oprsz);
+        TCGv_i32 t_val;
+
+        if (in_32) {
+            t_val = in_32;
+        } else if (in_64) {
+            t_val = tcg_temp_new_i32();
+            tcg_gen_extrl_i64_i32(t_val, in_64);
+        } else {
+            t_val = tcg_const_i32(in_c);
+        }
+        gen_helper_memset(t_ptr, t_ptr, t_val, t_size);
+
+        if (!in_32) {
+            tcg_temp_free_i32(t_val);
+        }
+        tcg_temp_free_ptr(t_size);
+        tcg_temp_free_ptr(t_ptr);
+        return;
+    }
+
     t_desc = tcg_const_i32(simd_desc(oprsz, maxsz, 0));
 
     if (vece == MO_64) {