linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Peter Oskolkov <posk@posk.io>
Cc: mingo@redhat.com, tglx@linutronix.de, juri.lelli@redhat.com,
	vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
	rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
	bristot@redhat.com, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-api@vger.kernel.org, x86@kernel.org,
	pjt@google.com, posk@google.com, avagin@google.com,
	jannh@google.com, tdelisle@uwaterloo.ca
Subject: Re: [RFC][PATCH 3/3] sched: User Mode Concurency Groups
Date: Mon, 17 Jan 2022 12:35:29 +0100	[thread overview]
Message-ID: <YeVUgXd6C85VmaP7@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <YeGEM7TP3tekBVEh@hirez.programming.kicks-ass.net>

On Fri, Jan 14, 2022 at 03:09:55PM +0100, Peter Zijlstra wrote:
> > > +SYSCALL_DEFINE3(umcg_ctl, u32, flags, struct umcg_task __user *, self, clockid_t, which_clock)
> > > +{
> > > +	struct task_struct *server;
> > > +	struct umcg_task ut;
> > > +
> > > +	if ((unsigned long)self % UMCG_TASK_ALIGN)
> > > +		return -EINVAL;
> > > +
> > > +	if (flags & ~(UMCG_CTL_REGISTER |
> > > +		      UMCG_CTL_UNREGISTER |
> > > +		      UMCG_CTL_WORKER))
> > > +		return -EINVAL;
> > > +
> > > +	if (flags == UMCG_CTL_UNREGISTER) {
> > > +		if (self || !current->umcg_task)
> > > +			return -EINVAL;
> > > +
> > > +		if (current->flags & PF_UMCG_WORKER)
> > > +			umcg_worker_exit();
> > 
> > The server should be woken here. Imagine: one server, one worker.
> > The server is sleeping, the worker is running. The worker unregisters,
> > the server keeps sleeping forever?
> > 
> > I'm OK re: NOT waking the server if the worker thread exits without
> > unregistering, as this is the userspace breaking the contract/protocol.
> > But here we do need to notify the server. At the minimum so that the
> > server can schedule a worker to run in its place.
> > 
> > (Why is this important? Worker count can fluctuate considerably:
> > on load spikes many new workers may be created, and later in
> > quiet times they exit to free resources.)
> 
> Fair enough. Will do.

Something like so then...

---
--- a/kernel/sched/umcg.c
+++ b/kernel/sched/umcg.c
@@ -185,13 +185,6 @@ void umcg_clear_child(struct task_struct
 	umcg_clear_task(tsk);
 }
 
-/* Called both by normally (unregister) and abnormally exiting workers. */
-void umcg_worker_exit(void)
-{
-	umcg_unpin_pages();
-	umcg_clear_task(current);
-}
-
 /*
  * Do a state transition: @from -> @to.
  *
@@ -748,32 +741,43 @@ SYSCALL_DEFINE2(umcg_wait, u32, flags, u
  * sys_umcg_ctl: (un)register the current task as a UMCG task.
  * @flags:       ORed values from enum umcg_ctl_flag; see below;
  * @self:        a pointer to struct umcg_task that describes this
- *               task and governs the behavior of sys_umcg_wait if
- *               registering; must be NULL if unregistering.
+ *               task and governs the behavior of sys_umcg_wait.
  * @which_clock: clockid to use for timestamps and timeouts
  *
  * @flags & UMCG_CTL_REGISTER: register a UMCG task:
  *
- *         UMCG workers:
- *              - @flags & UMCG_CTL_WORKER
- *              - self->state must be UMCG_TASK_BLOCKED
- *
- *         UMCG servers:
- *              - !(@flags & UMCG_CTL_WORKER)
- *              - self->state must be UMCG_TASK_RUNNING
- *
- *         All tasks:
- *              - self->server_tid must be a valid server
- *              - self->next_tid must be zero
- *
- *         If the conditions above are met, sys_umcg_ctl() immediately returns
- *         if the registered task is a server. If the registered task is a
- *         worker it will be added to it's server's runnable_workers_ptr list
- *         and the server will be woken.
- *
- * @flags == UMCG_CTL_UNREGISTER: unregister a UMCG task. If the current task
- *           is a UMCG worker, the userspace is responsible for waking its
- *           server (before or after calling sys_umcg_ctl).
+ *	UMCG workers:
+ *	 - @flags & UMCG_CTL_WORKER
+ *	 - self->state must be UMCG_TASK_BLOCKED
+ *
+ *	UMCG servers:
+ *	 - !(@flags & UMCG_CTL_WORKER)
+ *	 - self->state must be UMCG_TASK_RUNNING
+ *
+ *	All tasks:
+ *	 - self->server_tid must be a valid server
+ *	 - self->next_tid must be zero
+ *
+ *	If the conditions above are met, sys_umcg_ctl() immediately returns
+ *	if the registered task is a server. If the registered task is a
+ *	worker it will be added to it's server's runnable_workers_ptr list
+ *	and the server will be woken.
+ *
+ * @flags & UMCG_CTL_UNREGISTER: unregister a UMCG task.
+ *
+ *	UMCG workers:
+ *	 - @flags & UMCG_CTL_WORKER
+ *
+ *	UMCG servers:
+ *	 - !(@flags & UMCG_CTL_WORKER)
+ *
+ *	All tasks:
+ *	 - self must match with UMCG_CTL_REGISTER
+ *	 - self->state must be UMCG_TASK_RUNNING
+ *	 - self->server_tid must be a valid server
+ *
+ * 	If the conditions above are met, sys_umcg_ctl() will change state to
+ * 	UMCG_TASK_NONE, and for workers, wake either next or server.
  *
  * Return:
  * 0		- success
@@ -794,16 +798,31 @@ SYSCALL_DEFINE3(umcg_ctl, u32, flags, st
 		      UMCG_CTL_WORKER))
 		return -EINVAL;
 
-	if (flags == UMCG_CTL_UNREGISTER) {
-		if (self || !current->umcg_task)
+	if (flags & UMCG_CTL_UNREGISTER) {
+		int ret;
+
+		if (!self || self != current->umcg_task)
 			return -EINVAL;
 
-		if (current->flags & PF_UMCG_WORKER) {
-			umcg_worker_exit();
-			// XXX wake server
-		} else
-			umcg_clear_task(current);
+		current->flags &= ~PF_UMCG_WORKER;
 
+		ret = umcg_pin_pages();
+		if (ret) {
+			current->flags |= PF_UMCG_WORKER;
+			return ret;
+		}
+
+		ret = umcg_update_state(current, self, UMCG_TASK_RUNNING, UMCG_TASK_NONE);
+		if (ret) {
+			current->flags |= PF_UMCG_WORKER;
+			return ret;
+		}
+
+		if (current->flags & PF_UMCG_WORKER)
+			umcg_wake(current);
+
+		umcg_unpin_pages();
+		umcg_clear_task(current);
 		return 0;
 	}
 


  parent reply	other threads:[~2022-01-17 11:35 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-12-14 20:44 [RFC][PATCH 0/3] sched: User Managed Concurrency Groups Peter Zijlstra
2021-12-14 20:44 ` [RFC][PATCH 1/3] sched/umcg: add WF_CURRENT_CPU and externise ttwu Peter Zijlstra
2021-12-14 20:44 ` [RFC][PATCH 2/3] x86/uaccess: Implement unsafe_try_cmpxchg_user() Peter Zijlstra
2021-12-20 17:30   ` Sean Christopherson
2021-12-21 11:17     ` Peter Zijlstra
2021-12-14 20:44 ` [RFC][PATCH 3/3] sched: User Mode Concurency Groups Peter Zijlstra
2021-12-21 17:19   ` Peter Oskolkov
2022-01-14 14:09     ` Peter Zijlstra
2022-01-14 15:16       ` Peter Zijlstra
2022-01-14 17:15       ` Peter Zijlstra
2022-01-17 11:35       ` Peter Zijlstra [this message]
2022-01-17 12:22         ` Peter Zijlstra
2022-01-17 12:12       ` Peter Zijlstra
2022-01-18 10:09       ` Peter Zijlstra
2022-01-18 18:19         ` Peter Oskolkov
2022-01-19  8:47           ` Peter Zijlstra
2022-01-19 17:33             ` Peter Oskolkov
2022-01-19  8:51           ` Peter Zijlstra
2022-01-19  8:59           ` Peter Zijlstra
2022-01-19 17:52             ` Peter Oskolkov
2022-01-20 10:37               ` Peter Zijlstra
2022-01-17 13:04     ` Peter Zijlstra
2021-12-24 11:27   ` Peter Zijlstra
2021-12-14 21:00 ` [RFC][PATCH 0/3] sched: User Managed Concurrency Groups Peter Zijlstra
2021-12-15  3:46 ` Peter Oskolkov
2021-12-15 10:06   ` Peter Zijlstra
2021-12-15 13:03     ` Peter Zijlstra
2021-12-15 17:56     ` Peter Oskolkov
2021-12-15 18:18       ` Peter Zijlstra
2021-12-15 19:49         ` Peter Oskolkov
2021-12-15 22:25           ` Peter Zijlstra
2021-12-15 23:26             ` Peter Oskolkov
2021-12-16 13:23               ` Thomas Gleixner
2021-12-15 18:25       ` Peter Zijlstra
2021-12-15 21:04         ` Peter Oskolkov
2021-12-15 23:16           ` Peter Zijlstra
2021-12-15 23:31             ` Peter Oskolkov
2021-12-15 10:44   ` Peter Zijlstra
2021-12-15 13:49     ` Matthew Wilcox
2021-12-15 17:54       ` Peter Zijlstra

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=YeVUgXd6C85VmaP7@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=avagin@google.com \
    --cc=bristot@redhat.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=jannh@google.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=pjt@google.com \
    --cc=posk@google.com \
    --cc=posk@posk.io \
    --cc=rostedt@goodmis.org \
    --cc=tdelisle@uwaterloo.ca \
    --cc=tglx@linutronix.de \
    --cc=vincent.guittot@linaro.org \
    --cc=x86@kernel.org \
    /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