On Mon, Nov 26, 2018 at 04:52:14PM +0000, Will Deacon wrote: > David Laight explains: > > | A long time ago there was a document from Intel that said that > | inb/outb weren't necessarily synchronised wrt memory accesses. > | (Might be P-pro era). However no processors actually behaved that > | way and more recent docs say that inb/outb are fully ordered. No intention to diminish David Laight's authority of course, but I would have really appreciated a reference to these "recent docs" (section, pg. or the like, especially if a reference manual...) here... > > This also reflects the situation on other architectures, the the port > accessor macros tend to be implemented in terms of readX/writeX. > > Update Documentation/memory-barriers.txt to reflect reality. ..., IOW, what do you mean by "reality"? > > Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx> > Cc: Arnd Bergmann <arnd@xxxxxxxx> > Cc: David Laight <David.Laight@xxxxxxxxxx> > Cc: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx> > Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> > Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx> > Signed-off-by: Will Deacon <will.deacon@xxxxxxx> Please Cc me on future patches to memory-barriers.txt (can not speak for my co-maintainers, but I'm inclined to say that get_maintainers.pl knows better...). Andrea > --- > > Just remembered I had this patch kicking around in my tree... > > Documentation/memory-barriers.txt | 6 ++---- > 1 file changed, 2 insertions(+), 4 deletions(-) > > diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt > index c1d913944ad8..0c34c5dac138 100644 > --- a/Documentation/memory-barriers.txt > +++ b/Documentation/memory-barriers.txt > @@ -2619,10 +2619,8 @@ functions: > intermediary bridges (such as the PCI host bridge) may not fully honour > that. > > - They are guaranteed to be fully ordered with respect to each other. > - > - They are not guaranteed to be fully ordered with respect to other types of > - memory and I/O operation. > + They are guaranteed to be fully ordered with respect to each other and > + also with respect to other types of memory and I/O operation. > > (*) readX(), writeX(): > > -- > 2.1.4 >
