Messages in this thread | | | Date | Tue, 27 Feb 2018 18:16:05 +0800 | From | Boqun Feng <> | Subject | Re: [RFC PATCH] riscv/locking: Strengthen spin_lock() and spin_unlock() |
| |
On Tue, Feb 27, 2018 at 01:06:35PM +0800, Boqun Feng wrote: > On Mon, Feb 26, 2018 at 04:24:27PM +0000, Will Deacon wrote: > > On Mon, Feb 26, 2018 at 08:06:59AM -0800, Linus Torvalds wrote: > > > On Mon, Feb 26, 2018 at 6:21 AM, Luc Maranget <luc.maranget@inria.fr> wrote: > > > > > > > > That is, locks are not implemented from more basic primitive but are specified. > > > > The specification can be described as behaving that way: > > > > - A lock behaves as a read-modify-write. the read behaving as a read-acquire > > > > > > This is wrong, or perhaps just misleading. > > > > > > The *whole* r-m-w acts as an acquire. Not just the read part. The > > > write is very much part of it. > > > > > > Maybe that's what you meant, but it read to me as "just the read part > > > of the rmw behaves as a read-acquire". > > > > > > Because it is very important that the _write_ part of the rmw is also > > > ordered wrt everything that is inside the spinlock. > > > > > > So doing a spinlock as > > > > > > (a) read-locked-acquire > > > modify > > > (c) write-conditional > > > > > > would be wrong, because the accesses inside the spinlock are ordered > > > not just wrt the read-acquire, they have to be ordered wrt the write > > > too. > > > > > > So it is closer to say that it's the _write_ of the r-m-w sequence > > > that has the acquire semantics, not the read. > > > > Strictly speaking, that's not what we've got implemented on arm64: only > > the read part of the RmW has Acquire semantics, but there is a total > > order on the lock/unlock operations for the lock. For example, if one > > CPU does: > > > > spin_lock(&lock); > > WRITE_ONCE(foo, 42); > > > > then another CPU could do: > > > > if (smp_load_acquire(&foo) == 42) > > BUG_ON(!spin_is_locked(&lock)); > > > > Hmm.. this is new to me. So the write part of spin_lock() and the > WRITE_ONCE() will not get reordered? Could you explain more about this > or point where I should look in the document? I understand the write > part of spin_lock() must be committed earlier than the WRITE_ONCE() > committed due to the ll/sc, but I thought the ordering of their arrivals > in memory system is undefined/arbitary. > > Regards, > Boqun > > > and that could fire. Is that relied on somewhere? > >
My bad, I misunderstood your mail. So you were saying the BUG_ON() can be triggered in currently implementations. Never mind my reply above.
Regards, Boqun
> > Will
[unhandled content-type:application/pgp-signature] | |