The user_cpus_ptr field is added by commit b90ca8badbd1 ("sched:
Introduce task_struct::user_cpus_ptr to track requested affinity"). It
is currently used only by arm64 arch due to possible asymmetric cpu
setup. This patch extends its usage to save user provided cpumask when
sched_setaffinity() is called for all arches.
To preserve the existing arm64 use case, a new cpus_affinity_set flag is
added to differentiate if user_cpus_ptr is set up by sched_setaffinity()
or by force_compatible_cpus_allowed_ptr(). user_cpus_ptr
set by sched_setaffinity() has priority and won't be
overwritten by force_compatible_cpus_allowed_ptr() or
relax_compatible_cpus_allowed_ptr().
As a call to sched_setaffinity() will no longer clear user_cpus_ptr
but set it instead, the SCA_USER flag is no longer necessary and can
be removed.
Signed-off-by: Waiman Long <longman@redhat.com>
---
include/linux/sched.h | 1 +
kernel/sched/core.c | 71 +++++++++++++++++++++++++++++++------------
kernel/sched/sched.h | 1 -
3 files changed, 52 insertions(+), 21 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e7b2f8a5c711..cf7206a9b29a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -816,6 +816,7 @@ struct task_struct {
unsigned int policy;
int nr_cpus_allowed;
+ int cpus_affinity_set;
const cpumask_t *cpus_ptr;
cpumask_t *user_cpus_ptr;
cpumask_t cpus_mask;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ee28253c9ac0..7e2576068331 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2601,6 +2601,7 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
return -ENOMEM;
cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+ dst->cpus_affinity_set = src->cpus_affinity_set;
return 0;
}
@@ -2848,7 +2849,6 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p);
const struct cpumask *cpu_valid_mask = cpu_active_mask;
bool kthread = p->flags & PF_KTHREAD;
- struct cpumask *user_mask = NULL;
unsigned int dest_cpu;
int ret = 0;
@@ -2907,14 +2907,7 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
__do_set_cpus_allowed(p, new_mask, flags);
- if (flags & SCA_USER)
- user_mask = clear_user_cpus_ptr(p);
-
- ret = affine_move_task(rq, p, rf, dest_cpu, flags);
-
- kfree(user_mask);
-
- return ret;
+ return affine_move_task(rq, p, rf, dest_cpu, flags);
out:
task_rq_unlock(rq, p, rf);
@@ -2988,19 +2981,24 @@ static int restrict_cpus_allowed_ptr(struct task_struct *p,
/*
* We're about to butcher the task affinity, so keep track of what
- * the user asked for in case we're able to restore it later on.
+ * the user asked for in case we're able to restore it later on
+ * unless it has been set before by sched_setaffinity().
*/
- if (user_mask) {
+ if (user_mask && !p->cpus_affinity_set) {
cpumask_copy(user_mask, p->cpus_ptr);
p->user_cpus_ptr = user_mask;
+ user_mask = NULL;
}
- return __set_cpus_allowed_ptr_locked(p, new_mask, 0, rq, &rf);
+ err = __set_cpus_allowed_ptr_locked(p, new_mask, 0, rq, &rf);
-err_unlock:
- task_rq_unlock(rq, p, &rf);
+free_user_mask:
kfree(user_mask);
return err;
+
+err_unlock:
+ task_rq_unlock(rq, p, &rf);
+ goto free_user_mask;
}
/*
@@ -3049,7 +3047,7 @@ void force_compatible_cpus_allowed_ptr(struct task_struct *p)
}
static int
-__sched_setaffinity(struct task_struct *p, const struct cpumask *mask);
+__sched_setaffinity(struct task_struct *p, const struct cpumask *mask, bool save_mask);
/*
* Restore the affinity of a task @p which was previously restricted by a
@@ -3067,9 +3065,10 @@ void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
/*
* Try to restore the old affinity mask. If this fails, then
* we free the mask explicitly to avoid it being inherited across
- * a subsequent fork().
+ * a subsequent fork() unless it is set by sched_setaffinity().
*/
- if (!user_mask || !__sched_setaffinity(p, user_mask))
+ if (!user_mask || !__sched_setaffinity(p, user_mask, false) ||
+ p->cpus_affinity_set)
return;
raw_spin_lock_irqsave(&p->pi_lock, flags);
@@ -8079,10 +8078,11 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
#endif
static int
-__sched_setaffinity(struct task_struct *p, const struct cpumask *mask)
+__sched_setaffinity(struct task_struct *p, const struct cpumask *mask, bool save_mask)
{
int retval;
cpumask_var_t cpus_allowed, new_mask;
+ struct cpumask *user_mask = NULL;
if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL))
return -ENOMEM;
@@ -8098,8 +8098,38 @@ __sched_setaffinity(struct task_struct *p, const struct cpumask *mask)
retval = dl_task_check_affinity(p, new_mask);
if (retval)
goto out_free_new_mask;
+
+ /*
+ * Save the user requested mask into user_cpus_ptr
+ */
+ if (save_mask && !p->user_cpus_ptr) {
+alloc_again:
+ user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
+
+ if (!user_mask) {
+ retval = -ENOMEM;
+ goto out_free_new_mask;
+ }
+ }
+ if (save_mask) {
+ struct rq_flags rf;
+ struct rq *rq = task_rq_lock(p, &rf);
+
+ if (unlikely(!p->user_cpus_ptr && !user_mask)) {
+ task_rq_unlock(rq, p, &rf);
+ goto alloc_again;
+ }
+ if (!p->user_cpus_ptr) {
+ p->user_cpus_ptr = user_mask;
+ user_mask = NULL;
+ }
+
+ cpumask_copy(p->user_cpus_ptr, mask);
+ p->cpus_affinity_set = 1;
+ task_rq_unlock(rq, p, &rf);
+ }
again:
- retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK | SCA_USER);
+ retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK);
if (retval)
goto out_free_new_mask;
@@ -8113,6 +8143,7 @@ __sched_setaffinity(struct task_struct *p, const struct cpumask *mask)
goto again;
}
+ kfree(user_mask);
out_free_new_mask:
free_cpumask_var(new_mask);
out_free_cpus_allowed:
@@ -8156,7 +8187,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
if (retval)
goto out_put_task;
- retval = __sched_setaffinity(p, in_mask);
+ retval = __sched_setaffinity(p, in_mask, true);
out_put_task:
put_task_struct(p);
return retval;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e26688d387ae..15eefcd65faa 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2283,7 +2283,6 @@ extern struct task_struct *pick_next_task_idle(struct rq *rq);
#define SCA_CHECK 0x01
#define SCA_MIGRATE_DISABLE 0x02
#define SCA_MIGRATE_ENABLE 0x04
-#define SCA_USER 0x08
#ifdef CONFIG_SMP
--
2.31.1On Fri, Aug 12, 2022 at 04:39:27PM -0400, Waiman Long wrote:
> The user_cpus_ptr field is added by commit b90ca8badbd1 ("sched:
> Introduce task_struct::user_cpus_ptr to track requested affinity"). It
> is currently used only by arm64 arch due to possible asymmetric cpu
> setup. This patch extends its usage to save user provided cpumask when
> sched_setaffinity() is called for all arches.
>
> To preserve the existing arm64 use case, a new cpus_affinity_set flag is
> added to differentiate if user_cpus_ptr is set up by sched_setaffinity()
> or by force_compatible_cpus_allowed_ptr(). user_cpus_ptr
> set by sched_setaffinity() has priority and won't be
> overwritten by force_compatible_cpus_allowed_ptr() or
> relax_compatible_cpus_allowed_ptr().
What why ?! The only possible case where
restrict_cpus_allowed_ptr() will now need that weird new state is when
the affinity has never been set before, in that case cpus_ptr should be
possible_mask.
Please just make a single consistent rule and don't make weird corner
cases like this.
On 8/15/22 04:57, Peter Zijlstra wrote:
> On Fri, Aug 12, 2022 at 04:39:27PM -0400, Waiman Long wrote:
>> The user_cpus_ptr field is added by commit b90ca8badbd1 ("sched:
>> Introduce task_struct::user_cpus_ptr to track requested affinity"). It
>> is currently used only by arm64 arch due to possible asymmetric cpu
>> setup. This patch extends its usage to save user provided cpumask when
>> sched_setaffinity() is called for all arches.
>>
>> To preserve the existing arm64 use case, a new cpus_affinity_set flag is
>> added to differentiate if user_cpus_ptr is set up by sched_setaffinity()
>> or by force_compatible_cpus_allowed_ptr(). user_cpus_ptr
>> set by sched_setaffinity() has priority and won't be
>> overwritten by force_compatible_cpus_allowed_ptr() or
>> relax_compatible_cpus_allowed_ptr().
> What why ?! The only possible case where
> restrict_cpus_allowed_ptr() will now need that weird new state is when
> the affinity has never been set before, in that case cpus_ptr should be
> possible_mask.
Since I don't have a full history for this particular patch series that
add user_cpus_ptr, I am hesitant to change the current behavior for
arm64 systems. However, given the statement that user_cpus_ptr is for
tracking "requested affinity" which I assume is when user applications
call sched_setaffinity(). It does make sense we may not really need this
if sched_setaffinity() is never called.
> Please just make a single consistent rule and don't make weird corner
> cases like this.
I will take a closer look to try to simplify the rule here.
Cheers,
Longman
On Mon, Aug 15, 2022 at 09:52:27AM -0400, Waiman Long wrote:
>
> On 8/15/22 04:57, Peter Zijlstra wrote:
> > On Fri, Aug 12, 2022 at 04:39:27PM -0400, Waiman Long wrote:
> > > The user_cpus_ptr field is added by commit b90ca8badbd1 ("sched:
> > > Introduce task_struct::user_cpus_ptr to track requested affinity"). It
> > > is currently used only by arm64 arch due to possible asymmetric cpu
> > > setup. This patch extends its usage to save user provided cpumask when
> > > sched_setaffinity() is called for all arches.
> > >
> > > To preserve the existing arm64 use case, a new cpus_affinity_set flag is
> > > added to differentiate if user_cpus_ptr is set up by sched_setaffinity()
> > > or by force_compatible_cpus_allowed_ptr(). user_cpus_ptr
> > > set by sched_setaffinity() has priority and won't be
> > > overwritten by force_compatible_cpus_allowed_ptr() or
> > > relax_compatible_cpus_allowed_ptr().
> > What why ?! The only possible case where
> > restrict_cpus_allowed_ptr() will now need that weird new state is when
> > the affinity has never been set before, in that case cpus_ptr should be
> > possible_mask.
>
> Since I don't have a full history for this particular patch series that add
> user_cpus_ptr, I am hesitant to change the current behavior for arm64
> systems. However, given the statement that user_cpus_ptr is for tracking
> "requested affinity" which I assume is when user applications call
> sched_setaffinity(). It does make sense we may not really need this if
> sched_setaffinity() is never called.
So it comes from the asymmetric arm stuff, where only little cores can
still run arm32 code. This means that on those machines, 32bit code
needs to be contrained so a subset of CPUs.
A direct consequence of that was that if you have any 32bit program in
your process hierarchy, you loose the big cores from you affinity mask.
For some reason that wasn't popular.. Hence the save/restore of cpumasks.
> > Please just make a single consistent rule and don't make weird corner
> > cases like this.
>
> I will take a closer look to try to simplify the rule here.
I think something like:
mask = p->user_cpus_ptr;
if (!mask)
mask = &init_task.cpus_mask;
// impose cpuset masks
should 'just-work'.
On 8/15/22 10:25, Peter Zijlstra wrote:
> On Mon, Aug 15, 2022 at 09:52:27AM -0400, Waiman Long wrote:
>> On 8/15/22 04:57, Peter Zijlstra wrote:
>>> On Fri, Aug 12, 2022 at 04:39:27PM -0400, Waiman Long wrote:
>>>> The user_cpus_ptr field is added by commit b90ca8badbd1 ("sched:
>>>> Introduce task_struct::user_cpus_ptr to track requested affinity"). It
>>>> is currently used only by arm64 arch due to possible asymmetric cpu
>>>> setup. This patch extends its usage to save user provided cpumask when
>>>> sched_setaffinity() is called for all arches.
>>>>
>>>> To preserve the existing arm64 use case, a new cpus_affinity_set flag is
>>>> added to differentiate if user_cpus_ptr is set up by sched_setaffinity()
>>>> or by force_compatible_cpus_allowed_ptr(). user_cpus_ptr
>>>> set by sched_setaffinity() has priority and won't be
>>>> overwritten by force_compatible_cpus_allowed_ptr() or
>>>> relax_compatible_cpus_allowed_ptr().
>>> What why ?! The only possible case where
>>> restrict_cpus_allowed_ptr() will now need that weird new state is when
>>> the affinity has never been set before, in that case cpus_ptr should be
>>> possible_mask.
>> Since I don't have a full history for this particular patch series that add
>> user_cpus_ptr, I am hesitant to change the current behavior for arm64
>> systems. However, given the statement that user_cpus_ptr is for tracking
>> "requested affinity" which I assume is when user applications call
>> sched_setaffinity(). It does make sense we may not really need this if
>> sched_setaffinity() is never called.
> So it comes from the asymmetric arm stuff, where only little cores can
> still run arm32 code. This means that on those machines, 32bit code
> needs to be contrained so a subset of CPUs.
>
> A direct consequence of that was that if you have any 32bit program in
> your process hierarchy, you loose the big cores from you affinity mask.
>
> For some reason that wasn't popular.. Hence the save/restore of cpumasks.
I am aware of that part of the patch series.
>>> Please just make a single consistent rule and don't make weird corner
>>> cases like this.
>> I will take a closer look to try to simplify the rule here.
> I think something like:
>
> mask = p->user_cpus_ptr;
> if (!mask)
> mask = &init_task.cpus_mask;
>
> // impose cpuset masks
>
> should 'just-work'.
I think that should work in relax_compatible_cpus_allowed_ptr().
Thanks,
Longman
© 2016 - 2026 Red Hat, Inc.