s390x/tcg: Fix VERIM with 32/64 bit elements

Wrong order of operands. The constant always comes last. Makes QEMU crash
reliably on specific git fetch invocations.

Reported-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20190814151242.27199-1-david@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Fixes: 5c4b0ab460ef ("s390x/tcg: Implement VECTOR ELEMENT ROTATE AND INSERT UNDER MASK")
Cc: qemu-stable@nongnu.org
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
(cherry picked from commit 25bcb45d1b81d22634daa2b1a2d8bee746ac129b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>

diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
index 41d5cf869f94ef4c5842582bf830e86be1ba3e68..0caddb3958cdbc820c0d4f1a074bb48586863625 100644 (file)
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -213,7 +213,7 @@ static void get_vec_element_ptr_i64(TCGv_ptr ptr, uint8_t reg, TCGv_i64 enr,
                        vec_full_reg_offset(v3), ptr, 16, 16, data, fn)
 #define gen_gvec_3i(v1, v2, v3, c, gen) \
     tcg_gen_gvec_3i(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
-                    vec_full_reg_offset(v3), c, 16, 16, gen)
+                    vec_full_reg_offset(v3), 16, 16, c, gen)
 #define gen_gvec_4(v1, v2, v3, v4, gen) \
     tcg_gen_gvec_4(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
                    vec_full_reg_offset(v3), vec_full_reg_offset(v4), \