From:   Waiman Long <longman@redhat.com>
To:     Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        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>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Valentin Schneider <vschneid@redhat.com>,
        Will Deacon <will@kernel.org>
Cc:     Phil Auld <pauld@redhat.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        linux-kernel@vger.kernel.org, Waiman Long <longman@redhat.com>
Subject: [PATCH v3] sched: Store restrict_cpus_allowed_ptr() call state
Date:   Thu, 26 Jan 2023 20:55:27 -0500
Message-Id: <20230127015527.466367-1-longman@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

The user_cpus_ptr field was originally added by commit b90ca8badbd1
("sched: Introduce task_struct::user_cpus_ptr to track requested
affinity"). It was used only by arm64 arch due to possible asymmetric
CPU setup.

Since commit 8f9ea86fdf99 ("sched: Always preserve the user requested
cpumask"), task_struct::user_cpus_ptr is repurposed to store user
requested cpu affinity specified in the sched_setaffinity().

This results in a slight performance regression on an arm64
system when booted with "allow_mismatched_32bit_el0"
on the command-line.  The arch code will (amongst
other things) calls force_compatible_cpus_allowed_ptr() and
relax_compatible_cpus_allowed_ptr() when exec()'ing a 32-bit or a 64-bit
task respectively. Now a call to relax_compatible_cpus_allowed_ptr()
will always result in a __sched_setaffinity() call whether there is a
previous force_compatible_cpus_allowed_ptr() call or not.

In order to fix this regression, a new scheduler flag
task_struct::cpus_allowed_restricted is now added to track if
force_compatible_cpus_allowed_ptr() has been called before or not. This
patch also updates the comments in force_compatible_cpus_allowed_ptr()
and relax_compatible_cpus_allowed_ptr() and handles their interaction
with sched_setaffinity().

This patch also removes the task_user_cpus() helper. In the case of
relax_compatible_cpus_allowed_ptr(), cpu_possible_mask as user_cpu_ptr
masking will be performed within __sched_setaffinity() anyway.

Fixes: 8f9ea86fdf99 ("sched: Always preserve the user requested cpumask")
Reported-by: Will Deacon <will@kernel.org>
Signed-off-by: Waiman Long <longman@redhat.com>
---
 include/linux/sched.h |  3 +++
 kernel/sched/core.c   | 25 +++++++++++++++++--------
 kernel/sched/sched.h  |  8 +-------
 3 files changed, 21 insertions(+), 15 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 853d08f7562b..f93f62a1f858 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -886,6 +886,9 @@ struct task_struct {
 	unsigned			sched_contributes_to_load:1;
 	unsigned			sched_migrated:1;
 
+	/* restrict_cpus_allowed_ptr() bit, serialized by scheduler locks */
+	unsigned			cpus_allowed_restricted:1;
+
 	/* Force alignment to the next boundary: */
 	unsigned			:0;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bb1ee6d7bdde..d7bc809c109e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2999,6 +2999,10 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	struct rq *rq;
 
 	rq = task_rq_lock(p, &rf);
+
+	if (ctx->flags & SCA_CLR_RESTRICT)
+		p->cpus_allowed_restricted = 0;
+
 	/*
 	 * Masking should be skipped if SCA_USER or any of the SCA_MIGRATE_*
 	 * flags are set.
@@ -3025,8 +3029,8 @@ EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
 /*
  * Change a given task's CPU affinity to the intersection of its current
  * affinity mask and @subset_mask, writing the resulting mask to @new_mask.
- * If user_cpus_ptr is defined, use it as the basis for restricting CPU
- * affinity or use cpu_online_mask instead.
+ * The cpus_allowed_restricted bit is set to indicate to a later
+ * relax_compatible_cpus_allowed_ptr() call to relax the cpumask.
  *
  * If the resulting mask is empty, leave the affinity unchanged and return
  * -EINVAL.
@@ -3044,6 +3048,7 @@ static int restrict_cpus_allowed_ptr(struct task_struct *p,
 	int err;
 
 	rq = task_rq_lock(p, &rf);
+	p->cpus_allowed_restricted = 1;
 
 	/*
 	 * Forcefully restricting the affinity of a deadline task is
@@ -3055,7 +3060,8 @@ static int restrict_cpus_allowed_ptr(struct task_struct *p,
 		goto err_unlock;
 	}
 
-	if (!cpumask_and(new_mask, task_user_cpus(p), subset_mask)) {
+	if (p->user_cpu_ptr &&
+	    !cpumask_and(new_mask, p->user_cpu_ptr, subset_mask)) {
 		err = -EINVAL;
 		goto err_unlock;
 	}
@@ -3069,9 +3075,8 @@ static int restrict_cpus_allowed_ptr(struct task_struct *p,
 
 /*
  * Restrict the CPU affinity of task @p so that it is a subset of
- * task_cpu_possible_mask() and point @p->user_cpus_ptr to a copy of the
- * old affinity mask. If the resulting mask is empty, we warn and walk
- * up the cpuset hierarchy until we find a suitable mask.
+ * task_cpu_possible_mask(). If the resulting mask is empty, we warn
+ * and walk up the cpuset hierarchy until we find a suitable mask.
  */
 void force_compatible_cpus_allowed_ptr(struct task_struct *p)
 {
@@ -3125,11 +3130,15 @@ __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx);
 void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
 {
 	struct affinity_context ac = {
-		.new_mask  = task_user_cpus(p),
-		.flags     = 0,
+		.new_mask  = cpu_possible_mask;
+		.flags     = SCA_CLR_RESTRICT,
 	};
 	int ret;
 
+	/* Return if no previous force_compatible_cpus_allowed_ptr() call */
+	if (!data_race(p->cpus_allowed_restricted))
+		return;
+
 	/*
 	 * Try to restore the old affinity mask with __sched_setaffinity().
 	 * Cpuset masking will be done there too.
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 771f8ddb7053..e32ba5d9bb54 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1881,13 +1881,6 @@ static inline void dirty_sched_domain_sysctl(int cpu)
 #endif
 
 extern int sched_update_scaling(void);
-
-static inline const struct cpumask *task_user_cpus(struct task_struct *p)
-{
-	if (!p->user_cpus_ptr)
-		return cpu_possible_mask; /* &init_task.cpus_mask */
-	return p->user_cpus_ptr;
-}
 #endif /* CONFIG_SMP */
 
 #include "stats.h"
@@ -2293,6 +2286,7 @@ extern struct task_struct *pick_next_task_idle(struct rq *rq);
 #define SCA_MIGRATE_DISABLE	0x02
 #define SCA_MIGRATE_ENABLE	0x04
 #define SCA_USER		0x08
+#define SCA_CLR_RESTRICT	0x10
 
 #ifdef CONFIG_SMP
 
-- 
2.31.1