mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Suleiman Souhlal <suleiman@google.com>
To: linux-kernel@vger.kernel.org
Cc: "Suleiman Souhlal" <suleiman@google.com>,
	"Thomas Gleixner" <tglx@kernel.org>,
	"Ingo Molnar" <mingo@redhat.com>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Darren Hart" <dvhart@infradead.org>,
	"Davidlohr Bueso" <dave@stgolabs.net>,
	"André Almeida" <andrealmeid@igalia.com>,
	"Juri Lelli" <juri.lelli@redhat.com>,
	"Vincent Guittot" <vincent.guittot@linaro.org>,
	"Dietmar Eggemann" <dietmar.eggemann@arm.com>,
	"Steven Rostedt" <rostedt@goodmis.org>,
	"Ben Segall" <bsegall@google.com>, "Mel Gorman" <mgorman@suse.de>,
	"Valentin Schneider" <vschneid@redhat.com>,
	"K Prateek Nayak" <kprateek.nayak@amd.com>,
	"zhidao su" <soolaugust@gmail.com>,
	"John Stultz" <jstultz@google.com>,
	"Qais Yousef" <qyousef@google.com>,
	ssouhlal@FreeBSD.org
Subject: [RFC PATCH 03/12] futex: Add "ping" parameter to pi_state management functions and export them.
Date: Thu, 17 Sep 2026 04:33:27 +0000	[thread overview]
Message-ID: <20260917043339.2093426-4-suleiman@google.com> (raw)
In-Reply-To: <20260917043339.2093426-1-suleiman@google.com>

In preparation to adding FUTEX_PING, allow the pi_state management
functions to use a different wait_lock, and make them non-static.
Also rename handle_exit_race() to pi_handle_exit_race().

Signed-off-by: Suleiman Souhlal <suleiman@google.com>
---
 kernel/futex/futex.h | 10 ++++++++
 kernel/futex/pi.c    | 61 +++++++++++++++++++++++++-------------------
 2 files changed, 45 insertions(+), 26 deletions(-)

diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h
index f00f0863ed44..e450f60b180b 100644
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -395,6 +395,16 @@ extern int refill_pi_state_cache(void);
 extern void get_pi_state(struct futex_pi_state *pi_state);
 extern void put_pi_state(struct futex_pi_state *pi_state);
 extern int fixup_pi_owner(u32 __user *uaddr, struct futex_q *q, int locked);
+extern int pi_handle_exit_race(u32 __user *uaddr, u32 uval);
+extern struct futex_pi_state *alloc_pi_state(void);
+extern int attach_to_pi_state(u32 __user *uaddr, u32 uval,
+			      struct futex_pi_state *pi_state,
+			      struct futex_pi_state **ps,
+			      bool ping);
+extern int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
+			      struct futex_pi_state **ps,
+			      struct task_struct **exiting,
+			      bool ping);
 
 /*
  * Express the locking dependencies for lockdep:
diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c
index ceeeca1910ca..aefcc0491d60 100644
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -33,7 +33,7 @@ int refill_pi_state_cache(void)
 	return 0;
 }
 
-static struct futex_pi_state *alloc_pi_state(void)
+struct futex_pi_state *alloc_pi_state(void)
 {
 	struct futex_pi_state *pi_state = current->futex.pi_state_cache;
 
@@ -252,9 +252,10 @@ void put_pi_state(struct futex_pi_state *pi_state)
  * the pi_state against the user space value. If correct, attach to
  * it.
  */
-static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
-			      struct futex_pi_state *pi_state,
-			      struct futex_pi_state **ps)
+int attach_to_pi_state(u32 __user *uaddr, u32 uval,
+		       struct futex_pi_state *pi_state,
+		       struct futex_pi_state **ps,
+		       bool ping)
 {
 	pid_t pid = uval & FUTEX_TID_MASK;
 	u32 uval2;
@@ -284,7 +285,8 @@ static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
 	 * Now that we have a pi_state, we can acquire wait_lock
 	 * and do the state validation.
 	 */
-	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+	if (!ping)
+		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	/*
 	 * Since {uval, pi_state} is serialized by wait_lock, and our current
@@ -348,8 +350,10 @@ static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
 		goto out_einval;
 
 out_attach:
-	get_pi_state(pi_state);
-	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+	if (!ping) {
+		get_pi_state(pi_state);
+		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+	}
 	*ps = pi_state;
 	return 0;
 
@@ -370,7 +374,7 @@ static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
 	return ret;
 }
 
-static int handle_exit_race(u32 __user *uaddr, u32 uval)
+int pi_handle_exit_race(u32 __user *uaddr, u32 uval)
 {
 	u32 uval2;
 
@@ -419,7 +423,8 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval)
 }
 
 static void __attach_to_pi_owner(struct task_struct *p, union futex_key *key,
-				 struct futex_pi_state **ps)
+				 struct futex_pi_state **ps,
+				 bool ping)
 {
 	/*
 	 * No existing pi state. First waiter. [2]
@@ -429,18 +434,20 @@ static void __attach_to_pi_owner(struct task_struct *p, union futex_key *key,
 	 */
 	struct futex_pi_state *pi_state = alloc_pi_state();
 
-	/*
-	 * Initialize the pi_mutex in locked state and make @p
-	 * the owner of it:
-	 */
-	__assume_ctx_lock(&pi_state->pi_mutex.wait_lock);
-	rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p);
+	if (!ping) {
+		/*
+		 * Initialize the pi_mutex in locked state and make @p
+		 * the owner of it:
+		 */
+		__assume_ctx_lock(&pi_state->pi_mutex.wait_lock);
+		rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p);
+		WARN_ON(!list_empty(&pi_state->list));
+		list_add(&pi_state->list, &p->futex.pi_state_list);
+	}
 
 	/* Store the key for possible exit cleanups: */
 	pi_state->key = *key;
 
-	WARN_ON(!list_empty(&pi_state->list));
-	list_add(&pi_state->list, &p->futex.pi_state_list);
 	/*
 	 * Assignment without holding pi_state->pi_mutex.wait_lock is safe
 	 * because there is no concurrency as the object is not published yet.
@@ -453,9 +460,10 @@ static void __attach_to_pi_owner(struct task_struct *p, union futex_key *key,
  * Lookup the task for the TID provided from user space and attach to
  * it after doing proper sanity checks.
  */
-static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
-			      struct futex_pi_state **ps,
-			      struct task_struct **exiting)
+int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
+		       struct futex_pi_state **ps,
+		       struct task_struct **exiting,
+		       bool ping)
 {
 	pid_t pid = uval & FUTEX_TID_MASK;
 	struct task_struct *p;
@@ -471,7 +479,7 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
 		return -EAGAIN;
 	p = find_get_task_by_vpid(pid);
 	if (!p)
-		return handle_exit_race(uaddr, uval);
+		return pi_handle_exit_race(uaddr, uval);
 
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		put_task_struct(p);
@@ -508,7 +516,7 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
 			return -EBUSY;
 		}
 
-		int ret = handle_exit_race(uaddr, uval);
+		int ret = pi_handle_exit_race(uaddr, uval);
 
 		raw_spin_unlock_irq(&p->pi_futex_lock);
 		put_task_struct(p);
@@ -530,7 +538,7 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
 		}
 	}
 
-	__attach_to_pi_owner(p, key, ps);
+	__attach_to_pi_owner(p, key, ps, ping);
 	raw_spin_unlock_irq(&p->pi_futex_lock);
 
 	put_task_struct(p);
@@ -614,7 +622,8 @@ int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 	 */
 	top_waiter = futex_top_waiter(hb, key);
 	if (top_waiter)
-		return attach_to_pi_state(uaddr, uval, top_waiter->pi_state, ps);
+		return attach_to_pi_state(uaddr, uval, top_waiter->pi_state,
+		    ps, false);
 
 	/*
 	 * No waiter and user TID is 0. We are here because the
@@ -651,7 +660,7 @@ int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 		 */
 		if (set_waiters) {
 			raw_spin_lock_irq(&task->pi_futex_lock);
-			__attach_to_pi_owner(task, key, ps);
+			__attach_to_pi_owner(task, key, ps, false);
 			raw_spin_unlock_irq(&task->pi_futex_lock);
 		}
 		return 1;
@@ -671,7 +680,7 @@ int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 	 * attach to the owner. If that fails, no harm done, we only
 	 * set the FUTEX_WAITERS bit in the user space variable.
 	 */
-	return attach_to_pi_owner(uaddr, newval, key, ps, exiting);
+	return attach_to_pi_owner(uaddr, newval, key, ps, exiting, false);
 }
 
 /*
-- 
2.55.0.1082.g2b9226bbc0-goog


  parent reply	other threads:[~2026-09-17  4:33 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-17  4:33 [RFC PATCH 00/12] FUTEX_PING: A stealable futex using Proxy Execution Suleiman Souhlal
2026-09-17  4:33 ` [RFC PATCH 01/12] sched: Abstract task_struct->blocked_on by locking primitive Suleiman Souhlal
2026-09-17  4:33 ` [RFC PATCH 02/12] futex: Switch PI futex to use p->pi_futex_lock instead of p->pi_lock Suleiman Souhlal
2026-09-17 15:38   ` Peter Zijlstra
2026-09-17  4:33 ` Suleiman Souhlal [this message]
2026-09-17  4:33 ` [RFC PATCH 04/12] futex: Introduce stealable PI futex, FUTEX_*_PING Suleiman Souhlal
2026-09-17  4:33 ` [RFC PATCH 05/12] futex: Implement exit_ping_state_list() Suleiman Souhlal
2026-09-17  4:33 ` [RFC PATCH 06/12] futex: Address aborting from futex_lock_ping() while owning ping_state Suleiman Souhlal
2026-09-17  4:33 ` [RFC PATCH 07/12] futex: Make FUTEX_*_PING use Proxy Execution Suleiman Souhlal
2026-09-17 13:18   ` Jihan LIN
2026-09-17 14:39     ` K Prateek Nayak
2026-09-17 15:36       ` Peter Zijlstra
2026-09-17  4:33 ` [RFC PATCH 08/12] futex: Implement PING futex handoff Suleiman Souhlal
2026-09-17  4:33 ` [RFC PATCH 09/12] futex: Wake up donor in PING futex unlock Suleiman Souhlal
2026-09-17  4:33 ` [RFC PATCH 10/12] futex: Optimistic spinning for PING futexes Suleiman Souhlal
2026-09-17  4:33 ` [RFC PATCH 11/12] futex: Allow userspace stealing " Suleiman Souhlal
2026-09-17  4:33 ` [RFC PATCH 12/12] tools/testing/futex: Add ping_bench, a tool for benchmarking futexes Suleiman Souhlal
2026-09-17  8:58 ` [RFC PATCH 00/12] FUTEX_PING: A stealable futex using Proxy Execution Peter Zijlstra
2026-09-17 17:53   ` John Stultz
2026-09-17 18:51     ` Steven Rostedt
2026-09-18  6:30       ` Suleiman Souhlal
2026-09-18  6:07   ` Suleiman Souhlal

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=20260917043339.2093426-4-suleiman@google.com \
    --to=suleiman@google.com \
    --cc=andrealmeid@igalia.com \
    --cc=bsegall@google.com \
    --cc=dave@stgolabs.net \
    --cc=dietmar.eggemann@arm.com \
    --cc=dvhart@infradead.org \
    --cc=jstultz@google.com \
    --cc=juri.lelli@redhat.com \
    --cc=kprateek.nayak@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=qyousef@google.com \
    --cc=rostedt@goodmis.org \
    --cc=soolaugust@gmail.com \
    --cc=ssouhlal@FreeBSD.org \
    --cc=tglx@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.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

all inboxes | Powered by JetHome®