* [PATCH v2] mm/mempolicy: fix lock contention on mems_allowed
@ 2022-08-11 12:41 Abel Wu
[not found] ` <YvUM7KaJaY+xnN2Y@dhcp22.suse.cz>
2022-08-18 6:56 ` Muchun Song
0 siblings, 2 replies; 6+ messages in thread
From: Abel Wu @ 2022-08-11 12:41 UTC (permalink / raw)
To: Andrew Morton, Vlastimil Babka, Michal Hocko, Mel Gorman,
Muchun Song
Cc: linux-mm, linux-kernel, Abel Wu
The mems_allowed field can be modified by other tasks, so it isn't
safe to access it with alloc_lock unlocked even in the current
process context.
Say there are two tasks: A from cpusetA is performing set_mempolicy(2),
and B is changing cpusetA's cpuset.mems:
A (set_mempolicy) B (echo xx > cpuset.mems)
-------------------------------------------------------
pol = mpol_new();
update_tasks_nodemask(cpusetA) {
foreach t in cpusetA {
cpuset_change_task_nodemask(t) {
mpol_set_nodemask(pol) {
task_lock(t); // t could be A
new = f(A->mems_allowed);
update t->mems_allowed;
pol.create(pol, new);
task_unlock(t);
}
}
}
}
task_lock(A);
A->mempolicy = pol;
task_unlock(A);
In this case A's pol->nodes is computed by old mems_allowed, and could
be inconsistent with A's new mems_allowed.
While it is different when replacing vmas' policy: the pol->nodes is
gone wild only when current_cpuset_is_being_rebound():
A (mbind) B (echo xx > cpuset.mems)
-------------------------------------------------------
pol = mpol_new();
mmap_write_lock(A->mm);
cpuset_being_rebound = cpusetA;
update_tasks_nodemask(cpusetA) {
foreach t in cpusetA {
cpuset_change_task_nodemask(t) {
mpol_set_nodemask(pol) {
task_lock(t); // t could be A
mask = f(A->mems_allowed);
update t->mems_allowed;
pol.create(pol, mask);
task_unlock(t);
}
}
foreach v in A->mm {
if (cpuset_being_rebound == cpusetA)
pol.rebind(pol, cpuset.mems);
v->vma_policy = pol;
}
mmap_write_unlock(A->mm);
mmap_write_lock(t->mm);
mpol_rebind_mm(t->mm);
mmap_write_unlock(t->mm);
}
}
cpuset_being_rebound = NULL;
In this case, the cpuset.mems, which has already done updating, is
finally used for calculating pol->nodes, rather than A->mems_allowed.
So it is OK to call mpol_set_nodemask() with alloc_lock unlocked when
doing mbind(2).
Fixes: 78b132e9bae9 ("mm/mempolicy: remove or narrow the lock on current")
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
---
mm/mempolicy.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d39b01fd52fe..61e4e6f5cfe8 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -855,12 +855,14 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
goto out;
}
+ task_lock(current);
ret = mpol_set_nodemask(new, nodes, scratch);
if (ret) {
+ task_unlock(current);
mpol_put(new);
goto out;
}
- task_lock(current);
+
old = current->mempolicy;
current->mempolicy = new;
if (new && new->mode == MPOL_INTERLEAVE)
--
2.31.1
^ permalink raw reply related [flat|nested] 6+ messages in thread[parent not found: <YvUM7KaJaY+xnN2Y@dhcp22.suse.cz>]
* Re: [PATCH v2] mm/mempolicy: fix lock contention on mems_allowed
[not found] ` <YvUM7KaJaY+xnN2Y@dhcp22.suse.cz>
@ 2022-08-11 14:11 ` Michal Hocko
2022-08-12 7:07 ` Michal Hocko
2022-08-20 2:06 ` Wei Yang
2022-08-12 10:50 ` Abel Wu
1 sibling, 2 replies; 6+ messages in thread
From: Michal Hocko @ 2022-08-11 14:11 UTC (permalink / raw)
To: Abel Wu
Cc: Andrew Morton, Vlastimil Babka, Mel Gorman, Muchun Song, linux-mm,
linux-kernel, Wei Yang
fix the lkml address (fat fingers, sorry)
On Thu 11-08-22 16:06:37, Michal Hocko wrote:
> [Cc Wei Yang who is author of 78b132e9bae9]
>
> On Thu 11-08-22 20:41:57, Abel Wu wrote:
> > The mems_allowed field can be modified by other tasks, so it isn't
> > safe to access it with alloc_lock unlocked even in the current
> > process context.
> >
> > Say there are two tasks: A from cpusetA is performing set_mempolicy(2),
> > and B is changing cpusetA's cpuset.mems:
> >
> > A (set_mempolicy) B (echo xx > cpuset.mems)
> > -------------------------------------------------------
> > pol = mpol_new();
> > update_tasks_nodemask(cpusetA) {
> > foreach t in cpusetA {
> > cpuset_change_task_nodemask(t) {
> > mpol_set_nodemask(pol) {
> > task_lock(t); // t could be A
> > new = f(A->mems_allowed);
> > update t->mems_allowed;
> > pol.create(pol, new);
> > task_unlock(t);
> > }
> > }
> > }
> > }
> > task_lock(A);
> > A->mempolicy = pol;
> > task_unlock(A);
> >
> > In this case A's pol->nodes is computed by old mems_allowed, and could
> > be inconsistent with A's new mems_allowed.
>
> Just to clarify. With an unfortunate timing and those two nodemasks
> overlap the end user effect could be a premature OOM because some nodes
> wouldn't be considered, right?
>
> > While it is different when replacing vmas' policy: the pol->nodes is
> > gone wild only when current_cpuset_is_being_rebound():
> >
> > A (mbind) B (echo xx > cpuset.mems)
> > -------------------------------------------------------
> > pol = mpol_new();
> > mmap_write_lock(A->mm);
> > cpuset_being_rebound = cpusetA;
> > update_tasks_nodemask(cpusetA) {
> > foreach t in cpusetA {
> > cpuset_change_task_nodemask(t) {
> > mpol_set_nodemask(pol) {
> > task_lock(t); // t could be A
> > mask = f(A->mems_allowed);
> > update t->mems_allowed;
> > pol.create(pol, mask);
> > task_unlock(t);
> > }
> > }
> > foreach v in A->mm {
> > if (cpuset_being_rebound == cpusetA)
> > pol.rebind(pol, cpuset.mems);
> > v->vma_policy = pol;
> > }
> > mmap_write_unlock(A->mm);
> > mmap_write_lock(t->mm);
> > mpol_rebind_mm(t->mm);
> > mmap_write_unlock(t->mm);
> > }
> > }
> > cpuset_being_rebound = NULL;
> >
> > In this case, the cpuset.mems, which has already done updating, is
> > finally used for calculating pol->nodes, rather than A->mems_allowed.
> > So it is OK to call mpol_set_nodemask() with alloc_lock unlocked when
> > doing mbind(2).
> >
> > Fixes: 78b132e9bae9 ("mm/mempolicy: remove or narrow the lock on current")
> > Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
>
> The fix looks correct.
>
> > ---
> > mm/mempolicy.c | 4 +++-
> > 1 file changed, 3 insertions(+), 1 deletion(-)
> >
> > diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> > index d39b01fd52fe..61e4e6f5cfe8 100644
> > --- a/mm/mempolicy.c
> > +++ b/mm/mempolicy.c
> > @@ -855,12 +855,14 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
> > goto out;
> > }
> >
> > + task_lock(current);
> > ret = mpol_set_nodemask(new, nodes, scratch);
> > if (ret) {
> > + task_unlock(current);
> > mpol_put(new);
> > goto out;
> > }
> > - task_lock(current);
> > +
> > old = current->mempolicy;
> > current->mempolicy = new;
> > if (new && new->mode == MPOL_INTERLEAVE)
> > --
> > 2.31.1
>
> --
> Michal Hocko
> SUSE Labs
--
Michal Hocko
SUSE Labs
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH v2] mm/mempolicy: fix lock contention on mems_allowed
2022-08-11 14:11 ` Michal Hocko
@ 2022-08-12 7:07 ` Michal Hocko
2022-08-20 2:06 ` Wei Yang
1 sibling, 0 replies; 6+ messages in thread
From: Michal Hocko @ 2022-08-12 7:07 UTC (permalink / raw)
To: Abel Wu
Cc: Andrew Morton, Vlastimil Babka, Mel Gorman, Muchun Song, linux-mm,
linux-kernel, Wei Yang
On Thu 11-08-22 16:11:23, Michal Hocko wrote:
> fix the lkml address (fat fingers, sorry)
>
> On Thu 11-08-22 16:06:37, Michal Hocko wrote:
> > [Cc Wei Yang who is author of 78b132e9bae9]
> >
> > On Thu 11-08-22 20:41:57, Abel Wu wrote:
> > > The mems_allowed field can be modified by other tasks, so it isn't
> > > safe to access it with alloc_lock unlocked even in the current
> > > process context.
> > >
> > > Say there are two tasks: A from cpusetA is performing set_mempolicy(2),
> > > and B is changing cpusetA's cpuset.mems:
> > >
> > > A (set_mempolicy) B (echo xx > cpuset.mems)
> > > -------------------------------------------------------
> > > pol = mpol_new();
> > > update_tasks_nodemask(cpusetA) {
> > > foreach t in cpusetA {
> > > cpuset_change_task_nodemask(t) {
> > > mpol_set_nodemask(pol) {
> > > task_lock(t); // t could be A
> > > new = f(A->mems_allowed);
> > > update t->mems_allowed;
> > > pol.create(pol, new);
> > > task_unlock(t);
> > > }
> > > }
> > > }
> > > }
> > > task_lock(A);
> > > A->mempolicy = pol;
> > > task_unlock(A);
> > >
> > > In this case A's pol->nodes is computed by old mems_allowed, and could
> > > be inconsistent with A's new mems_allowed.
> >
> > Just to clarify. With an unfortunate timing and those two nodemasks
> > overlap the end user effect could be a premature OOM because some nodes
> > wouldn't be considered, right?
> >
> > > While it is different when replacing vmas' policy: the pol->nodes is
> > > gone wild only when current_cpuset_is_being_rebound():
> > >
> > > A (mbind) B (echo xx > cpuset.mems)
> > > -------------------------------------------------------
> > > pol = mpol_new();
> > > mmap_write_lock(A->mm);
> > > cpuset_being_rebound = cpusetA;
> > > update_tasks_nodemask(cpusetA) {
> > > foreach t in cpusetA {
> > > cpuset_change_task_nodemask(t) {
> > > mpol_set_nodemask(pol) {
> > > task_lock(t); // t could be A
> > > mask = f(A->mems_allowed);
> > > update t->mems_allowed;
> > > pol.create(pol, mask);
> > > task_unlock(t);
> > > }
> > > }
> > > foreach v in A->mm {
> > > if (cpuset_being_rebound == cpusetA)
> > > pol.rebind(pol, cpuset.mems);
> > > v->vma_policy = pol;
> > > }
> > > mmap_write_unlock(A->mm);
> > > mmap_write_lock(t->mm);
> > > mpol_rebind_mm(t->mm);
> > > mmap_write_unlock(t->mm);
> > > }
> > > }
> > > cpuset_being_rebound = NULL;
> > >
> > > In this case, the cpuset.mems, which has already done updating, is
> > > finally used for calculating pol->nodes, rather than A->mems_allowed.
> > > So it is OK to call mpol_set_nodemask() with alloc_lock unlocked when
> > > doing mbind(2).
> > >
> > > Fixes: 78b132e9bae9 ("mm/mempolicy: remove or narrow the lock on current")
> > > Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
> >
> > The fix looks correct.
Forgot
Acked-by: Michal Hocko <mhocko@suse.com>
> >
> > > ---
> > > mm/mempolicy.c | 4 +++-
> > > 1 file changed, 3 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> > > index d39b01fd52fe..61e4e6f5cfe8 100644
> > > --- a/mm/mempolicy.c
> > > +++ b/mm/mempolicy.c
> > > @@ -855,12 +855,14 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
> > > goto out;
> > > }
> > >
> > > + task_lock(current);
> > > ret = mpol_set_nodemask(new, nodes, scratch);
> > > if (ret) {
> > > + task_unlock(current);
> > > mpol_put(new);
> > > goto out;
> > > }
> > > - task_lock(current);
> > > +
> > > old = current->mempolicy;
> > > current->mempolicy = new;
> > > if (new && new->mode == MPOL_INTERLEAVE)
> > > --
> > > 2.31.1
> >
> > --
> > Michal Hocko
> > SUSE Labs
>
> --
> Michal Hocko
> SUSE Labs
--
Michal Hocko
SUSE Labs
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH v2] mm/mempolicy: fix lock contention on mems_allowed
2022-08-11 14:11 ` Michal Hocko
2022-08-12 7:07 ` Michal Hocko
@ 2022-08-20 2:06 ` Wei Yang
1 sibling, 0 replies; 6+ messages in thread
From: Wei Yang @ 2022-08-20 2:06 UTC (permalink / raw)
To: Michal Hocko
Cc: Abel Wu, Andrew Morton, Vlastimil Babka, Mel Gorman, Muchun Song,
linux-mm, linux-kernel, Wei Yang
On Thu, Aug 11, 2022 at 04:11:21PM +0200, Michal Hocko wrote:
>fix the lkml address (fat fingers, sorry)
>
>On Thu 11-08-22 16:06:37, Michal Hocko wrote:
>> [Cc Wei Yang who is author of 78b132e9bae9]
>>
>> On Thu 11-08-22 20:41:57, Abel Wu wrote:
>> > The mems_allowed field can be modified by other tasks, so it isn't
>> > safe to access it with alloc_lock unlocked even in the current
>> > process context.
>> >
>> > Say there are two tasks: A from cpusetA is performing set_mempolicy(2),
>> > and B is changing cpusetA's cpuset.mems:
>> >
>> > A (set_mempolicy) B (echo xx > cpuset.mems)
>> > -------------------------------------------------------
>> > pol = mpol_new();
>> > update_tasks_nodemask(cpusetA) {
>> > foreach t in cpusetA {
>> > cpuset_change_task_nodemask(t) {
>> > mpol_set_nodemask(pol) {
>> > task_lock(t); // t could be A
>> > new = f(A->mems_allowed);
>> > update t->mems_allowed;
>> > pol.create(pol, new);
>> > task_unlock(t);
>> > }
>> > }
>> > }
>> > }
>> > task_lock(A);
>> > A->mempolicy = pol;
>> > task_unlock(A);
>> >
>> > In this case A's pol->nodes is computed by old mems_allowed, and could
>> > be inconsistent with A's new mems_allowed.
>>
>> Just to clarify. With an unfortunate timing and those two nodemasks
>> overlap the end user effect could be a premature OOM because some nodes
>> wouldn't be considered, right?
>>
>> > While it is different when replacing vmas' policy: the pol->nodes is
>> > gone wild only when current_cpuset_is_being_rebound():
>> >
>> > A (mbind) B (echo xx > cpuset.mems)
>> > -------------------------------------------------------
>> > pol = mpol_new();
>> > mmap_write_lock(A->mm);
>> > cpuset_being_rebound = cpusetA;
>> > update_tasks_nodemask(cpusetA) {
>> > foreach t in cpusetA {
>> > cpuset_change_task_nodemask(t) {
>> > mpol_set_nodemask(pol) {
>> > task_lock(t); // t could be A
>> > mask = f(A->mems_allowed);
>> > update t->mems_allowed;
>> > pol.create(pol, mask);
>> > task_unlock(t);
>> > }
>> > }
>> > foreach v in A->mm {
>> > if (cpuset_being_rebound == cpusetA)
>> > pol.rebind(pol, cpuset.mems);
>> > v->vma_policy = pol;
>> > }
>> > mmap_write_unlock(A->mm);
>> > mmap_write_lock(t->mm);
>> > mpol_rebind_mm(t->mm);
>> > mmap_write_unlock(t->mm);
>> > }
>> > }
>> > cpuset_being_rebound = NULL;
>> >
>> > In this case, the cpuset.mems, which has already done updating, is
>> > finally used for calculating pol->nodes, rather than A->mems_allowed.
>> > So it is OK to call mpol_set_nodemask() with alloc_lock unlocked when
>> > doing mbind(2).
>> >
>> > Fixes: 78b132e9bae9 ("mm/mempolicy: remove or narrow the lock on current")
>> > Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
>>
Thanks for pointing out. This looks correct.
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v2] mm/mempolicy: fix lock contention on mems_allowed
[not found] ` <YvUM7KaJaY+xnN2Y@dhcp22.suse.cz>
2022-08-11 14:11 ` Michal Hocko
@ 2022-08-12 10:50 ` Abel Wu
1 sibling, 0 replies; 6+ messages in thread
From: Abel Wu @ 2022-08-12 10:50 UTC (permalink / raw)
To: Michal Hocko
Cc: Andrew Morton, Vlastimil Babka, Mel Gorman, Muchun Song, linux-mm,
linux-kernel, Wei Yang
On 8/11/22 10:06 PM, Michal Hocko Wrote:
> [Cc Wei Yang who is author of 78b132e9bae9]
>
> On Thu 11-08-22 20:41:57, Abel Wu wrote:
>> The mems_allowed field can be modified by other tasks, so it isn't
>> safe to access it with alloc_lock unlocked even in the current
>> process context.
>>
>> Say there are two tasks: A from cpusetA is performing set_mempolicy(2),
>> and B is changing cpusetA's cpuset.mems:
>>
>> A (set_mempolicy) B (echo xx > cpuset.mems)
>> -------------------------------------------------------
>> pol = mpol_new();
>> update_tasks_nodemask(cpusetA) {
>> foreach t in cpusetA {
>> cpuset_change_task_nodemask(t) {
>> mpol_set_nodemask(pol) {
>> task_lock(t); // t could be A
>> new = f(A->mems_allowed);
>> update t->mems_allowed;
>> pol.create(pol, new);
>> task_unlock(t);
>> }
>> }
>> }
>> }
>> task_lock(A);
>> A->mempolicy = pol;
>> task_unlock(A);
>>
>> In this case A's pol->nodes is computed by old mems_allowed, and could
>> be inconsistent with A's new mems_allowed.
>
> Just to clarify. With an unfortunate timing and those two nodemasks
> overlap the end user effect could be a premature OOM because some nodes
> wouldn't be considered, right?
Yes, indeed!
>
>> While it is different when replacing vmas' policy: the pol->nodes is
>> gone wild only when current_cpuset_is_being_rebound():
>>
>> A (mbind) B (echo xx > cpuset.mems)
>> -------------------------------------------------------
>> pol = mpol_new();
>> mmap_write_lock(A->mm);
>> cpuset_being_rebound = cpusetA;
>> update_tasks_nodemask(cpusetA) {
>> foreach t in cpusetA {
>> cpuset_change_task_nodemask(t) {
>> mpol_set_nodemask(pol) {
>> task_lock(t); // t could be A
>> mask = f(A->mems_allowed);
>> update t->mems_allowed;
>> pol.create(pol, mask);
>> task_unlock(t);
>> }
>> }
>> foreach v in A->mm {
>> if (cpuset_being_rebound == cpusetA)
>> pol.rebind(pol, cpuset.mems);
>> v->vma_policy = pol;
>> }
>> mmap_write_unlock(A->mm);
>> mmap_write_lock(t->mm);
>> mpol_rebind_mm(t->mm);
>> mmap_write_unlock(t->mm);
>> }
>> }
>> cpuset_being_rebound = NULL;
>>
>> In this case, the cpuset.mems, which has already done updating, is
>> finally used for calculating pol->nodes, rather than A->mems_allowed.
>> So it is OK to call mpol_set_nodemask() with alloc_lock unlocked when
>> doing mbind(2).
>>
>> Fixes: 78b132e9bae9 ("mm/mempolicy: remove or narrow the lock on current")
>> Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
>
> The fix looks correct.
>
>> ---
>> mm/mempolicy.c | 4 +++-
>> 1 file changed, 3 insertions(+), 1 deletion(-)
>>
>> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
>> index d39b01fd52fe..61e4e6f5cfe8 100644
>> --- a/mm/mempolicy.c
>> +++ b/mm/mempolicy.c
>> @@ -855,12 +855,14 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
>> goto out;
>> }
>>
>> + task_lock(current);
>> ret = mpol_set_nodemask(new, nodes, scratch);
>> if (ret) {
>> + task_unlock(current);
>> mpol_put(new);
>> goto out;
>> }
>> - task_lock(current);
>> +
>> old = current->mempolicy;
>> current->mempolicy = new;
>> if (new && new->mode == MPOL_INTERLEAVE)
>> --
>> 2.31.1
>
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v2] mm/mempolicy: fix lock contention on mems_allowed
2022-08-11 12:41 [PATCH v2] mm/mempolicy: fix lock contention on mems_allowed Abel Wu
[not found] ` <YvUM7KaJaY+xnN2Y@dhcp22.suse.cz>
@ 2022-08-18 6:56 ` Muchun Song
1 sibling, 0 replies; 6+ messages in thread
From: Muchun Song @ 2022-08-18 6:56 UTC (permalink / raw)
To: Abel Wu
Cc: Andrew Morton, Vlastimil Babka, Michal Hocko, Mel Gorman,
Muchun Song, Linux MM, linux-kernel
> On Aug 11, 2022, at 20:41, Abel Wu <wuyun.abel@bytedance.com> wrote:
>
> The mems_allowed field can be modified by other tasks, so it isn't
> safe to access it with alloc_lock unlocked even in the current
> process context.
>
> Say there are two tasks: A from cpusetA is performing set_mempolicy(2),
> and B is changing cpusetA's cpuset.mems:
>
> A (set_mempolicy) B (echo xx > cpuset.mems)
> -------------------------------------------------------
> pol = mpol_new();
> update_tasks_nodemask(cpusetA) {
> foreach t in cpusetA {
> cpuset_change_task_nodemask(t) {
> mpol_set_nodemask(pol) {
> task_lock(t); // t could be A
> new = f(A->mems_allowed);
> update t->mems_allowed;
> pol.create(pol, new);
> task_unlock(t);
> }
> }
> }
> }
> task_lock(A);
> A->mempolicy = pol;
> task_unlock(A);
>
> In this case A's pol->nodes is computed by old mems_allowed, and could
> be inconsistent with A's new mems_allowed.
>
> While it is different when replacing vmas' policy: the pol->nodes is
> gone wild only when current_cpuset_is_being_rebound():
>
> A (mbind) B (echo xx > cpuset.mems)
> -------------------------------------------------------
> pol = mpol_new();
> mmap_write_lock(A->mm);
> cpuset_being_rebound = cpusetA;
> update_tasks_nodemask(cpusetA) {
> foreach t in cpusetA {
> cpuset_change_task_nodemask(t) {
> mpol_set_nodemask(pol) {
> task_lock(t); // t could be A
> mask = f(A->mems_allowed);
> update t->mems_allowed;
> pol.create(pol, mask);
> task_unlock(t);
> }
> }
> foreach v in A->mm {
> if (cpuset_being_rebound == cpusetA)
> pol.rebind(pol, cpuset.mems);
> v->vma_policy = pol;
> }
> mmap_write_unlock(A->mm);
> mmap_write_lock(t->mm);
> mpol_rebind_mm(t->mm);
> mmap_write_unlock(t->mm);
> }
> }
> cpuset_being_rebound = NULL;
>
> In this case, the cpuset.mems, which has already done updating, is
> finally used for calculating pol->nodes, rather than A->mems_allowed.
> So it is OK to call mpol_set_nodemask() with alloc_lock unlocked when
> doing mbind(2).
>
> Fixes: 78b132e9bae9 ("mm/mempolicy: remove or narrow the lock on current")
> Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Thanks.
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2022-08-20 2:07 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2022-08-11 12:41 [PATCH v2] mm/mempolicy: fix lock contention on mems_allowed Abel Wu
[not found] ` <YvUM7KaJaY+xnN2Y@dhcp22.suse.cz>
2022-08-11 14:11 ` Michal Hocko
2022-08-12 7:07 ` Michal Hocko
2022-08-20 2:06 ` Wei Yang
2022-08-12 10:50 ` Abel Wu
2022-08-18 6:56 ` Muchun Song
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.