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>

1 files changed, 32 insertions, 0 deletions

diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index ddbe06b71a..1a41dfa908 100644
--- 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) {