Re: [RFC PATCH for 4.18 00/14] Restartable Sequences

On Wed, May 2, 2018 at 1:23 PM Peter Zijlstra [off-list ref] wrote:

On Wed, May 02, 2018 at 06:27:22PM +0000, Daniel Colascione wrote:

quoted

On Wed, May 2, 2018 at 10:22 AM Peter Zijlstra [off-list ref]

wrote:

quoted

quoted

quoted

On Wed, May 02, 2018 at 03:53:47AM +0000, Daniel Colascione wrote:
Suppose we make a userspace mutex implemented with a lock word

having

quoted

three

quoted

quoted

bits: acquired, sleep_mode, and wait_pending, with the rest of the

word

quoted

not

quoted

quoted

being relevant at the moment.

quoted

So ideally we'd kill FUTEX_WAIT/FUTEX_WAKE for mutexes entirely, and

go

quoted

quoted

with FUTEX_LOCK/FUTEX_UNLOCK that have the same semantics as the
existing FUTEX_LOCK_PI/FUTEX_UNLOCK_PI, namely, the word contains the
owner TID.

That doesn't work if you want to use the rest of the word for something
else, like a recursion count. With FUTEX_WAIT and FUTEX_WAKE, you can

make

quoted

a lock with two bits.

Recursive locks are teh most horrible crap ever. And having the tid in

What happened to providing mechanism, not policy?

You can't wish away recursive locking. It's baked into Java and the CLR,
and it's enshrined in POSIX. It's not going away, and there's no reason not
to support it efficiently.

the word allows things like kernel based optimistic spins and possibly
PI related things.

Sure. A lot of people don't want PI though, or at least they want to opt
into it. And we shouldn't require an entry into the kernel for what we can
in principle do efficiently in userspace.

quoted

quoted

As brought up in the last time we talked about spin loops, why do we
care if the spin loop is in userspace or not? Aside from the whole PTI
thing, the syscall cost was around 150 cycle or so, while a LOCK

CMPXCHG

quoted

quoted

is around 20 cycles. So ~7 spins gets you the cost of entry.

That's pre-KPTI, isn't it?

Yes, and once the hardware gets sorted, we'll be there again. I don't
think we should design interfaces for 'broken' hardware.

It would be a mistake to design interfaces under the assumption that
everyone has fast permission level transitions.