Messages in this thread | | | From | David Howells <> | Subject | Re: [PATCH 3/8] i386: bitops: Rectify bogus "+m" constraints | Date | Tue, 24 Jul 2007 10:22:44 +0100 |
| |
Linus Torvalds <torvalds@linux-foundation.org> wrote:
> > So, using the "+" constraint modifier for memory, like "+m" is bogus. > > We must simply specify "=m" which handles the case correctly. > > No. This is wrong.
Agreed.
> "=m" means that the new value of the memory location is *set*. > > Which means that gcc will potentially optimize away any previous stores to > that memory location. > > And yes, it happens, and yes, we've seen it.
I had a lot of "fun" with this when mucking around with the asm-optimised R/W semaphores.
David - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |