On Mon, Jan 07, 2019 at 03:00:17PM +0800, Jason Wang wrote: > > On 2019/1/5 上午8:33, Sean Christopherson wrote: > > On Fri, Jan 04, 2019 at 04:29:34PM -0500, Michael S. Tsirkin wrote: > > > On Sat, Dec 29, 2018 at 08:46:52PM +0800, Jason Wang wrote: > > > > Use one generic vhost_copy_to_user() instead of two dedicated > > > > accessor. This will simplify the conversion to fine grain > > > > accessors. About 2% improvement of PPS were seen during vitio-user > > > > txonly test. > > > > > > > > Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx> > > > I don't hve a problem with this patch but do you have > > > any idea how come removing what's supposed to be > > > an optimization speeds things up? > > With SMAP, the 2x vhost_put_user() will also mean an extra STAC/CLAC pair, > > which is probably slower than the overhead of CALL+RET to whatever flavor > > of copy_user_generic() gets used. CALL+RET is really the only overhead > > since all variants of copy_user_generic() unroll accesses smaller than > > 64 bytes, e.g. on a 64-bit system, __copy_to_user() will write all 8 > > bytes in a single MOV. > > > > Removing the special casing also eliminates a few hundred bytes of code > > as well as the need for hardware to predict count==1 vs. count>1. > > > > Yes, I don't measure, but STAC/CALC is pretty expensive when we are do very > small copies based on the result of nosmap PPS. > > Thanks Yes all this really looks like a poster child for uaccess_begin/end plus unsafe accesses. And if these APIs don't do the job for us then maybe better ones are needed ... -- MST
