Date: Mon, 10 Dec 2018 10:59:55 +0100 From: Peter Zijlstra <peterz@...radead.org> To: Igor Stoppa <igor.stoppa@...il.com> Cc: Andy Lutomirski <luto@...nel.org>, linux-arch <linux-arch@...r.kernel.org>, linux-s390 <linux-s390@...r.kernel.org>, Martin Schwidefsky <schwidefsky@...ibm.com>, Heiko Carstens <heiko.carstens@...ibm.com>, Benjamin Herrenschmidt <benh@...nel.crashing.org>, Kees Cook <keescook@...omium.org>, Matthew Wilcox <willy@...radead.org>, Igor Stoppa <igor.stoppa@...wei.com>, Nadav Amit <nadav.amit@...il.com>, Dave Hansen <dave.hansen@...ux.intel.com>, linux-integrity <linux-integrity@...r.kernel.org>, Kernel Hardening <kernel-hardening@...ts.openwall.com>, Linux-MM <linux-mm@...ck.org>, LKML <linux-kernel@...r.kernel.org> Subject: Re: [PATCH 2/6] __wr_after_init: write rare for static allocation On Mon, Dec 10, 2018 at 12:32:21AM +0200, Igor Stoppa wrote: > > > On 06/12/2018 11:44, Peter Zijlstra wrote: > > On Wed, Dec 05, 2018 at 03:13:56PM -0800, Andy Lutomirski wrote: > > > > > > + if (op == WR_MEMCPY) > > > > + memcpy((void *)wr_poking_addr, (void *)src, len); > > > > + else if (op == WR_MEMSET) > > > > + memset((u8 *)wr_poking_addr, (u8)src, len); > > > > + else if (op == WR_RCU_ASSIGN_PTR) > > > > + /* generic version of rcu_assign_pointer */ > > > > + smp_store_release((void **)wr_poking_addr, > > > > + RCU_INITIALIZER((void **)src)); > > > > + kasan_enable_current(); > > > > > > Hmm. I suspect this will explode quite badly on sane architectures > > > like s390. (In my book, despite how weird s390 is, it has a vastly > > > nicer model of "user" memory than any other architecture I know > > > of...). I think you should use copy_to_user(), etc, instead. I'm not > > > entirely sure what the best smp_store_release() replacement is. > > > Making this change may also mean you can get rid of the > > > kasan_disable_current(). > > > > If you make the MEMCPY one guarantee single-copy atomicity for native > > words then you're basically done. > > > > smp_store_release() can be implemented with: > > > > smp_mb(); > > WRITE_ONCE(); > > > > So if we make MEMCPY provide the WRITE_ONCE(), all we need is that > > barrier, which we can easily place at the call site and not overly > > complicate our interface with this. > > Ok, so the 3rd case (WR_RCU_ASSIGN_PTR) could be handled outside of this > function. > But, since now memcpy() will be replaced by copy_to_user(), can I assume > that also copy_to_user() will be atomic, if the destination is properly > aligned? On x86_64 it seems yes, however it's not clear to me if this is the > outcome of an optimization or if I can expect it to be always true. This would be a new contraint; one that needs to be documented and verified by the various arch maintainers as they enable this feature on their platform.
Powered by blists - more mailing lists
Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.