On Wed, Sep 23, 2020 at 04:10:43PM -0700, Dave Jiang wrote: > +/* The dst parameter must be 64-bytes aligned */ > +static inline void movdir64b(void *dst, const void *src) > +{ > + /* > + * Note that this isn't an "on-stack copy", just definition of "dst" > + * as a pointer to 64-bytes of stuff that is going to be overwritten. > + * In the MOVDIR64B case that may be needed as you can use the > + * MOVDIR64B instruction to copy arbitrary memory around. This trick > + * lets the compiler know how much gets clobbered. > + */ > + volatile struct { char _[64]; } *__dst = dst; > + > + /* MOVDIR64B [rdx], rax */ > + asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" > + : > + : "m" (*(struct { char _[64];} **)src), "a" (__dst) > + : "memory"); > +} Ok, Micha and I hashed it out on IRC, here's what you do. Please keep the comments too because we will forget soon again. static inline void movdir64b(void *__dst, const void *src) { struct { char _[64]; } *__src = src; struct { char _[64]; } *__dst = dst; /* * MOVDIR64B %(rdx), rax. * * Both __src and __dst must be memory constraints in order to tell the * compiler that no other memory accesses should be reordered around * this one. * * Also, both must be supplied as lvalues because this tells * the compiler what the object is (its size) the instruction accesses. * I.e., not the pointers but what they point, thus the deref'ing '*'. */ asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" : "+m" (*__dst) : "m" (*__src), "a" (__dst), "d" (__src)); } Thx. -- Regards/Gruss, Boris. https://people.kernel.org/tglx/notes-about-netiquette