Paul E. McKenney <paulmck@xxxxxxxxxx> wrote: > On Mon, Jul 11, 2022 at 05:14:55PM +0200, Paul Heidekrüger wrote: >>> On 8. Jul 2022, at 20:47, Paul E. McKenney <paulmck@xxxxxxxxxx> wrote: >>> >>> On Fri, Jul 08, 2022 at 10:45:06AM -0400, Alan Stern wrote: >>>> On Fri, Jul 08, 2022 at 01:44:06PM +0200, Marco Elver wrote: >>>>> On Tue, 14 Jun 2022 at 17:49, Paul Heidekrüger >>>>> <paul.heidekrueger@xxxxxxxxx> wrote: >>>>>> As discussed, clarify LKMM not recognizing certain kinds of orderings. >>>>>> In particular, highlight the fact that LKMM might deliberately make >>>>>> weaker guarantees than compilers and architectures. >>>>>> >>>>>> Link: https://lore.kernel.org/all/YpoW1deb%2FQeeszO1@xxxxxxxxxxxxxxxxxxxxxxxx/T/#u >>>>>> Signed-off-by: Paul Heidekrüger <paul.heidekrueger@xxxxxxxxx> >>>>>> Co-developed-by: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx> >>>>> >>>>> Reviewed-by: Marco Elver <elver@xxxxxxxxxx> >>>>> >>>>> However with the Co-developed-by, this is missing Alan's SOB. >>>> >>>> For the record: >>>> >>>> Signed-off-by: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx> >>>> >>>> (Note that according to Documentation/process/submitting-patches.rst, >>>> the submitting author's SOB is supposed to come last.) >>> >>> And this is what I ended up with. Please provide additional feedback >>> as needed, and in the meantime, thank you all! >>> >>> Thanx, Paul >> >> Looks great - my first commit in the Linux kernel! > > Congratulations!!! ;-) Thanks! Hopefully many more to come :-) > My commits for the upcoming merge window, which is probably 2-3 weeks > from now, are already set. So this is targeted at the merge window > after that, which is likely to be in late September or early October. > > So it is well on its way! Awesome! Many thanks, Paul > Thanx, Paul > >> Thanks everyone! >> >> Paul >> >>> ------------------------------------------------------------------------ >>> >>> commit 3c7753e959706f39e1ee183ef8dcde3b4cfbb4c7 >>> Author: Paul Heidekrüger <paul.heidekrueger@xxxxxxxxx> >>> Date: Tue Jun 14 15:48:11 2022 +0000 >>> >>> tools/memory-model: Clarify LKMM's limitations in litmus-tests.txt >>> >>> As discussed, clarify LKMM not recognizing certain kinds of orderings. >>> In particular, highlight the fact that LKMM might deliberately make >>> weaker guarantees than compilers and architectures. >>> >>> Link: https://lore.kernel.org/all/YpoW1deb%2FQeeszO1@xxxxxxxxxxxxxxxxxxxxxxxx/T/#u >>> Co-developed-by: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx> >>> Signed-off-by: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx> >>> Signed-off-by: Paul Heidekrüger <paul.heidekrueger@xxxxxxxxx> >>> Reviewed-by: Marco Elver <elver@xxxxxxxxxx> >>> Reviewed-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx> >>> Cc: Charalampos Mainas <charalampos.mainas@xxxxxxxxx> >>> Cc: Pramod Bhatotia <pramod.bhatotia@xxxxxxxxx> >>> Cc: Soham Chakraborty <s.s.chakraborty@xxxxxxxxxx> >>> Cc: Martin Fink <martin.fink@xxxxxxxxx> >>> Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxx> >>> >>> diff --git a/tools/memory-model/Documentation/litmus-tests.txt b/tools/memory-model/Documentation/litmus-tests.txt >>> index 8a9d5d2787f9e..cc355999815cb 100644 >>> --- a/tools/memory-model/Documentation/litmus-tests.txt >>> +++ b/tools/memory-model/Documentation/litmus-tests.txt >>> @@ -946,22 +946,39 @@ Limitations of the Linux-kernel memory model (LKMM) include: >>> carrying a dependency, then the compiler can break that dependency >>> by substituting a constant of that value. >>> >>> - Conversely, LKMM sometimes doesn't recognize that a particular >>> - optimization is not allowed, and as a result, thinks that a >>> - dependency is not present (because the optimization would break it). >>> - The memory model misses some pretty obvious control dependencies >>> - because of this limitation. A simple example is: >>> + Conversely, LKMM will sometimes overestimate the amount of >>> + reordering compilers and CPUs can carry out, leading it to miss >>> + some pretty obvious cases of ordering. A simple example is: >>> >>> r1 = READ_ONCE(x); >>> if (r1 == 0) >>> smp_mb(); >>> WRITE_ONCE(y, 1); >>> >>> - There is a control dependency from the READ_ONCE to the WRITE_ONCE, >>> - even when r1 is nonzero, but LKMM doesn't realize this and thinks >>> - that the write may execute before the read if r1 != 0. (Yes, that >>> - doesn't make sense if you think about it, but the memory model's >>> - intelligence is limited.) >>> + The WRITE_ONCE() does not depend on the READ_ONCE(), and as a >>> + result, LKMM does not claim ordering. However, even though no >>> + dependency is present, the WRITE_ONCE() will not be executed before >>> + the READ_ONCE(). There are two reasons for this: >>> + >>> + The presence of the smp_mb() in one of the branches >>> + prevents the compiler from moving the WRITE_ONCE() >>> + up before the "if" statement, since the compiler has >>> + to assume that r1 will sometimes be 0 (but see the >>> + comment below); >>> + >>> + CPUs do not execute stores before po-earlier conditional >>> + branches, even in cases where the store occurs after the >>> + two arms of the branch have recombined. >>> + >>> + It is clear that it is not dangerous in the slightest for LKMM to >>> + make weaker guarantees than architectures. In fact, it is >>> + desirable, as it gives compilers room for making optimizations. >>> + For instance, suppose that a 0 value in r1 would trigger undefined >>> + behavior elsewhere. Then a clever compiler might deduce that r1 >>> + can never be 0 in the if condition. As a result, said clever >>> + compiler might deem it safe to optimize away the smp_mb(), >>> + eliminating the branch and any ordering an architecture would >>> + guarantee otherwise. >>> >>> 2. Multiple access sizes for a single variable are not supported, >>> and neither are misaligned or partially overlapping accesses.
