I failed to account for either the 160 bytes of saved XMM registers
(because the stupid ABI demands that XMM6--XMM15 be preserved across
calls), or for the daft 32-byte shadow space between the return address
and the stacked arguments.
# define ARG6 STKARG(2)
# define ARG7 STKARG(3)
# define ARG8 STKARG(4)
# define ARG6 STKARG(2)
# define ARG7 STKARG(3)
# define ARG8 STKARG(4)
-# define STKARG_OFFSET 40
+# define STKARG_OFFSET 224
#endif
#define STKARG(i) [rsp + STKARG_OFFSET + 8*(i)]
#endif
#define STKARG(i) [rsp + STKARG_OFFSET + 8*(i)]