On March 6, 2017 9:12:41 AM PST, Logan Gunthorpe <log...@deltatee.com> wrote: > > >On 06/03/17 12:28 AM, H. Peter Anvin wrote: >> On 03/05/17 23:01, Logan Gunthorpe wrote: >>> >>> On 05/03/17 12:54 PM, Borislav Petkov wrote: >>>> Logan, wanna give that a try, see if it takes care of your issue? >>> >>> Well honestly my issue was solved by fixing my kernel config. I have >no >>> idea why I had optimize for size in there in the first place. >>> >> >> Yes, to gcc "optimize for size" means exactly that... intended for >cases >> where saving storage (e.g. ROM) or code download time is paramount. > >I agree and understand, however placing a poorly performing _inline_ >memcpy instead of a single call instruction to a performant memcopy >probably took more code space in the end. So like Linus, I just have to >scratch my head at the -Os optimization option. > >Logan
No, it will be smaller: -Os counts bytes. If you think about it, there is no way that replacing a five-byte subroutine call with a two-byte instruction opcode can make it bigger! The only other difference between the two from a size perspective is that the compiler doesn't have to worry about clobbered registers other than the argument registers. -- Sent from my Android device with K-9 Mail. Please excuse my brevity.
