From: Peter Zijlstra <peterz@infradead.org>
To: Florian Weimer <fweimer@redhat.com>
Cc: "Pierre-Loup A. Griffais" <pgriffais@valvesoftware.com>,
"Thomas Gleixner" <tglx@linutronix.de>,
"André Almeida" <andrealmeid@collabora.com>,
linux-kernel@vger.kernel.org, kernel@collabora.com,
krisman@collabora.com, shuah@kernel.org,
linux-kselftest@vger.kernel.org, rostedt@goodmis.org,
ryao@gentoo.org, dvhart@infradead.org, mingo@redhat.com,
z.figura12@gmail.com, steven@valvesoftware.com,
steven@liquorix.net, malteskarupke@web.de, carlos@redhat.com,
adhemerval.zanella@linaro.org, libc-alpha@sourceware.org
Subject: Re: 'simple' futex interface [Was: [PATCH v3 1/4] futex: Implement mechanism to wait on any of several futexes]
Date: Tue, 3 Mar 2020 14:21:50 +0100 [thread overview]
Message-ID: <20200303132150.GD2596@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <87pndth9ur.fsf@oldenburg2.str.redhat.com>
On Tue, Mar 03, 2020 at 02:00:12PM +0100, Florian Weimer wrote:
> * Peter Zijlstra:
>
> > So how about we introduce new syscalls:
> >
> > sys_futex_wait(void *uaddr, unsigned long val, unsigned long flags, ktime_t *timo);
> >
> > struct futex_wait {
> > void *uaddr;
> > unsigned long val;
> > unsigned long flags;
> > };
> > sys_futex_waitv(struct futex_wait *waiters, unsigned int nr_waiters,
> > unsigned long flags, ktime_t *timo);
> >
> > sys_futex_wake(void *uaddr, unsigned int nr, unsigned long flags);
> >
> > sys_futex_cmp_requeue(void *uaddr1, void *uaddr2, unsigned int nr_wake,
> > unsigned int nr_requeue, unsigned long cmpval, unsigned long flags);
> >
> > Where flags:
> >
> > - has 2 bits for size: 8,16,32,64
> > - has 2 more bits for size (requeue) ??
> > - has ... bits for clocks
> > - has private/shared
> > - has numa
>
> What's the actual type of *uaddr? Does it vary by size (which I assume
> is in bits?)? Are there alignment constraints?
Yeah, u8, u16, u32, u64 depending on the size specified in flags.
Naturally aligned.
> These system calls seemed to be type-polymorphic still, which is
> problematic for defining a really nice C interface. I would really like
> to have a strongly typed interface for this, with a nice struct futex
> wrapper type (even if it means that we need four of them).
You mean like: futex_wait1(u8 *,...) futex_wait2(u16 *,...)
futex_wait4(u32 *,...) etc.. ?
I suppose making it 16 or so syscalls (more if we want WAKE_OP or
requeue across size) is a bit daft, so yeah, sucks.
> Will all architectures support all sizes? If not, how do we probe which
> size/flags combinations are supported?
Up to the native word size (long), IOW ILP32 will not support u64.
Overlapping futexes are expressly forbidden, that is:
{
u32 var;
void *addr = &var;
}
P0()
{
futex_wait4(addr,...);
}
P1()
{
futex_wait1(addr+1,...);
}
Will have one of them return something bad.
> > For NUMA I propose that when NUMA_FLAG is set, uaddr-4 will be 'int
> > node_id', with the following semantics:
> >
> > - on WAIT, node_id is read and when 0 <= node_id <= nr_nodes, is
> > directly used to index into per-node hash-tables. When -1, it is
> > replaced by the current node_id and an smp_mb() is issued before we
> > load and compare the @uaddr.
> >
> > - on WAKE/REQUEUE, it is an immediate index.
>
> Does this mean the first waiter determines the NUMA index, and all
> future waiters use the same chain even if they are on different nodes?
Every new waiter could (re)set node_id, after all, when its not actually
waiting, nobody cares what's in that field.
> I think documenting this as a node index would be a mistake. It could
> be an arbitrary hint for locating the corresponding kernel data
> structures.
Nah, it allows explicit placement, after all, we have set_mempolicy()
and sched_setaffinity() and all the other NUMA crud so that programs
that think they know what they're doing, can do explicit placement.
> > Any invalid value with result in EINVAL.
>
> Using uaddr-4 is slightly tricky with a 64-bit futex value, due to the
> need to maintain alignment and avoid padding.
Yes, but it works, unlike uaddr+4 :-) Also, 1 and 2 byte futexes and
NUMA_FLAG are incompatible due to this, but I feel short futexes and
NUMA don't really make sense anyway, the only reason to use a short
futex is to save space, so you don't want another 4 bytes for numa on
top of that anyway.
next prev parent reply other threads:[~2020-03-03 13:22 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-13 21:45 [PATCH v3 0/4] Implement FUTEX_WAIT_MULTIPLE operation André Almeida
2020-02-13 21:45 ` [PATCH v3 1/4] futex: Implement mechanism to wait on any of several futexes André Almeida
2020-02-28 19:07 ` Peter Zijlstra
2020-02-28 19:49 ` Peter Zijlstra
2020-02-28 21:25 ` Thomas Gleixner
2020-02-29 0:29 ` Pierre-Loup A. Griffais
2020-02-29 10:27 ` Thomas Gleixner
2020-03-03 2:47 ` Pierre-Loup A. Griffais
2020-03-03 12:00 ` 'simple' futex interface [Was: [PATCH v3 1/4] futex: Implement mechanism to wait on any of several futexes] Peter Zijlstra
2020-03-03 13:00 ` Florian Weimer
2020-03-03 13:21 ` Peter Zijlstra [this message]
2020-03-03 13:47 ` Florian Weimer
2020-03-03 15:01 ` Peter Zijlstra
2020-03-05 16:14 ` André Almeida
2020-03-05 16:25 ` Florian Weimer
2020-03-05 18:51 ` Peter Zijlstra
2020-03-06 16:57 ` David Laight
2020-02-13 21:45 ` [PATCH v3 2/4] selftests: futex: Add FUTEX_WAIT_MULTIPLE timeout test André Almeida
2020-02-13 21:45 ` [PATCH v3 3/4] selftests: futex: Add FUTEX_WAIT_MULTIPLE wouldblock test André Almeida
2020-02-13 21:45 ` [PATCH v3 4/4] selftests: futex: Add FUTEX_WAIT_MULTIPLE wake up test André Almeida
2020-02-19 16:27 ` [PATCH v3 0/4] Implement FUTEX_WAIT_MULTIPLE operation shuah
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200303132150.GD2596@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=adhemerval.zanella@linaro.org \
--cc=andrealmeid@collabora.com \
--cc=carlos@redhat.com \
--cc=dvhart@infradead.org \
--cc=fweimer@redhat.com \
--cc=kernel@collabora.com \
--cc=krisman@collabora.com \
--cc=libc-alpha@sourceware.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=malteskarupke@web.de \
--cc=mingo@redhat.com \
--cc=pgriffais@valvesoftware.com \
--cc=rostedt@goodmis.org \
--cc=ryao@gentoo.org \
--cc=shuah@kernel.org \
--cc=steven@liquorix.net \
--cc=steven@valvesoftware.com \
--cc=tglx@linutronix.de \
--cc=z.figura12@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).