Currently arm64's switch_mm() doesn't always have an smp_mb()
which the core scheduler code has depended upon since commit:
commit 223baf9d17f25 ("sched: Fix performance regression introduced by mm_cid")
If switch_mm() doesn't call smp_mb(), sched_mm_cid_remote_clear()
can unset the activly used cid when it fails to observe active task after it
sets lazy_put.
By adding an smp_mb() in arm64's check_and_switch_context(),
Guarantee to observe active task after sched_mm_cid_remote_clear()
success to set lazy_put.
Signed-off-by: levi.yun <[email protected]>
Fixes: 223baf9d17f2 ("sched: Fix performance regression introduced by mm_cid")
Cc: <[email protected]> # 6.4.x
Cc: Mathieu Desnoyers <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Aaron Lu <[email protected]>
---
I'm really sorry if you got this multiple times.
I had some problems with the SMTP server...
arch/arm64/mm/context.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index 188197590fc9..7a9e8e6647a0 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -268,6 +268,11 @@ void check_and_switch_context(struct mm_struct *mm)
*/
if (!system_uses_ttbr0_pan())
cpu_switch_mm(mm->pgd, mm);
+
+ /*
+ * See the comments on switch_mm_cid describing user -> user transition.
+ */
+ smp_mb();
}
unsigned long arm64_mm_context_get(struct mm_struct *mm)
--
LEVI:{C3F47F37-75D8-414A-A8BA-3980EC8A46D7}
On Tue, Mar 05, 2024 at 02:53:35PM +0000, levi.yun wrote:
> Currently arm64's switch_mm() doesn't always have an smp_mb()
> which the core scheduler code has depended upon since commit:
>
> commit 223baf9d17f25 ("sched: Fix performance regression introduced by mm_cid")
>
> If switch_mm() doesn't call smp_mb(), sched_mm_cid_remote_clear()
> can unset the activly used cid when it fails to observe active task after it
> sets lazy_put.
>
> By adding an smp_mb() in arm64's check_and_switch_context(),
> Guarantee to observe active task after sched_mm_cid_remote_clear()
> success to set lazy_put.
>
> Signed-off-by: levi.yun <[email protected]>
> Fixes: 223baf9d17f2 ("sched: Fix performance regression introduced by mm_cid")
> Cc: <[email protected]> # 6.4.x
> Cc: Mathieu Desnoyers <[email protected]>
> Cc: Catalin Marinas <[email protected]>
> Cc: Mark Rutland <[email protected]>
> Cc: Will Deacon <[email protected]>
> Cc: Peter Zijlstra <[email protected]>
> Cc: Aaron Lu <[email protected]>
> ---
> I'm really sorry if you got this multiple times.
> I had some problems with the SMTP server...
>
> arch/arm64/mm/context.c | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
> index 188197590fc9..7a9e8e6647a0 100644
> --- a/arch/arm64/mm/context.c
> +++ b/arch/arm64/mm/context.c
> @@ -268,6 +268,11 @@ void check_and_switch_context(struct mm_struct *mm)
> */
> if (!system_uses_ttbr0_pan())
> cpu_switch_mm(mm->pgd, mm);
> +
> + /*
> + * See the comments on switch_mm_cid describing user -> user transition.
> + */
> + smp_mb();
> }
We already have a stronger barrier than smp_mb() (dsb ish) in __switch_to().
Is that not sufficient?
Will
Hi will.
> We already have a stronger barrier than smp_mb() (dsb ish) in __switch_to().
> Is that not sufficient?
IIUC, It's not sufficient with smp_mb() in __switch_to().
Because, it can be broken in sched_mm_cid_remote_clear()
CPU0 in __schedule() CPU1 in
sched_mm_cid_remote_clear()
rq->curr = new_task;
<no barrier>
mm_get_cid remote_clear
- check valid cid and use it. Invalidate CID.
<barrier>
rq->curr (not observed).
unset the cid
(<<BUG).
If change of rq->curr couldn't be observed in sched_mm_cid_remote_clear(),
It could unset actively used cid.
Note that __switch_to()'s smp_mb() is called AFTER switch_mm_cid().
That means before __switch_to(), there's possibility that
sched_mm_cid_remote_clear() couldn't observe new active task,
after it sets lazy_put on active cid used by new active task.
On 2024-03-05 09:53, levi.yun wrote:
> Currently arm64's switch_mm() doesn't always have an smp_mb()
> which the core scheduler code has depended upon since commit:
>
> commit 223baf9d17f25 ("sched: Fix performance regression introduced by mm_cid")
>
> If switch_mm() doesn't call smp_mb(), sched_mm_cid_remote_clear()
> can unset the activly used cid when it fails to observe active task after it
> sets lazy_put.
>
> By adding an smp_mb() in arm64's check_and_switch_context(),
> Guarantee to observe active task after sched_mm_cid_remote_clear()
> success to set lazy_put.
This comment from the original implementation of membarrier
MEMBARRIER_CMD_PRIVATE_EXPEDITED states that the original need from
membarrier was to have a full barrier between storing to rq->curr and
return to userspace:
commit 22e4ebb9758 ("membarrier: Provide expedited private command")
commit message:
* Our TSO archs can do RELEASE without being a full barrier. Look at
x86 spin_unlock() being a regular STORE for example. But for those
archs, all atomics imply smp_mb and all of them have atomic ops in
switch_mm() for mm_cpumask(), and on x86 the CR3 load acts as a full
barrier.
* From all weakly ordered machines, only ARM64 and PPC can do RELEASE,
the rest does indeed do smp_mb(), so there the spin_unlock() is a full
barrier and we're good.
* ARM64 has a very heavy barrier in switch_to(), which suffices.
* PPC just removed its barrier from switch_to(), but appears to be
talking about adding something to switch_mm(). So add a
smp_mb__after_unlock_lock() for now, until this is settled on the PPC
side.
associated code:
+ /*
+ * The membarrier system call requires each architecture
+ * to have a full memory barrier after updating
+ * rq->curr, before returning to user-space. For TSO
+ * (e.g. x86), the architecture must provide its own
+ * barrier in switch_mm(). For weakly ordered machines
+ * for which spin_unlock() acts as a full memory
+ * barrier, finish_lock_switch() in common code takes
+ * care of this barrier. For weakly ordered machines for
+ * which spin_unlock() acts as a RELEASE barrier (only
+ * arm64 and PowerPC), arm64 has a full barrier in
+ * switch_to(), and PowerPC has
+ * smp_mb__after_unlock_lock() before
+ * finish_lock_switch().
+ */
Which got updated to this by
commit 306e060435d ("membarrier: Document scheduler barrier requirements")
/*
* The membarrier system call requires each architecture
* to have a full memory barrier after updating
+ * rq->curr, before returning to user-space.
+ *
+ * Here are the schemes providing that barrier on the
+ * various architectures:
+ * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
+ * switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
+ * - finish_lock_switch() for weakly-ordered
+ * architectures where spin_unlock is a full barrier,
+ * - switch_to() for arm64 (weakly-ordered, spin_unlock
+ * is a RELEASE barrier),
*/
However, rseq mm_cid has stricter requirements: the barrier needs to be
issued between store to rq->curr and switch_mm_cid(), which happens
earlier than:
- spin_unlock(),
- switch_to().
So it's fine when the architecture switch_mm happens to have that barrier
already, but less so when the architecture only provides the full barrier
in switch_to() or spin_unlock().
The issue is therefore not specific to arm64, it's actually a bug in the
rseq switch_mm_cid() implementation. All architectures that don't have
memory barriers in switch_mm(), but rather have the full barrier either in
finish_lock_switch() or switch_to() have them too late for the needs of
switch_mm_cid().
I would recommend one of three approaches here:
A) Add smp_mb() in switch_mm_cid() for all architectures that lack that
barrier in switch_mm().
B) Figure out if we can move switch_mm_cid() further down in the scheduler
without breaking anything (within switch_to(), at the very end of
finish_lock_switch() for instance). I'm not sure we can do that though
because switch_mm_cid() touches the "prev" which is tricky after
switch_to().
C) Add barriers in switch_mm() within all architectures that are missing it.
Thoughts ?
Thanks,
Mathieu
>
> Signed-off-by: levi.yun <[email protected]>
> Fixes: 223baf9d17f2 ("sched: Fix performance regression introduced by mm_cid")
> Cc: <[email protected]> # 6.4.x
> Cc: Mathieu Desnoyers <[email protected]>
> Cc: Catalin Marinas <[email protected]>
> Cc: Mark Rutland <[email protected]>
> Cc: Will Deacon <[email protected]>
> Cc: Peter Zijlstra <[email protected]>
> Cc: Aaron Lu <[email protected]>
> ---
> I'm really sorry if you got this multiple times.
> I had some problems with the SMTP server...
>
> arch/arm64/mm/context.c | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
> index 188197590fc9..7a9e8e6647a0 100644
> --- a/arch/arm64/mm/context.c
> +++ b/arch/arm64/mm/context.c
> @@ -268,6 +268,11 @@ void check_and_switch_context(struct mm_struct *mm)
> */
> if (!system_uses_ttbr0_pan())
> cpu_switch_mm(mm->pgd, mm);
> +
> + /*
> + * See the comments on switch_mm_cid describing user -> user transition.
> + */
> + smp_mb();
> }
>
> unsigned long arm64_mm_context_get(struct mm_struct *mm)
> --
> LEVI:{C3F47F37-75D8-414A-A8BA-3980EC8A46D7}
>
--
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com
Hi Mathieu!
On 05/03/2024 20:01, Mathieu Desnoyers wrote:
> On 2024-03-05 09:53, levi.yun wrote:
>> Currently arm64's switch_mm() doesn't always have an smp_mb()
>> which the core scheduler code has depended upon since commit:
>>
>> commit 223baf9d17f25 ("sched: Fix performance regression
>> introduced by mm_cid")
>>
>> If switch_mm() doesn't call smp_mb(), sched_mm_cid_remote_clear()
>> can unset the activly used cid when it fails to observe active task
>> after it
>> sets lazy_put.
>>
>> By adding an smp_mb() in arm64's check_and_switch_context(),
>> Guarantee to observe active task after sched_mm_cid_remote_clear()
>> success to set lazy_put.
>
> This comment from the original implementation of membarrier
> MEMBARRIER_CMD_PRIVATE_EXPEDITED states that the original need from
> membarrier was to have a full barrier between storing to rq->curr and
> return to userspace:
>
> commit 22e4ebb9758 ("membarrier: Provide expedited private command")
>
> commit message:
>
> * Our TSO archs can do RELEASE without being a full barrier. Look at
> x86 spin_unlock() being a regular STORE for example. But for those
> archs, all atomics imply smp_mb and all of them have atomic ops in
> switch_mm() for mm_cpumask(), and on x86 the CR3 load acts as a
> full
> barrier.
> * From all weakly ordered machines, only ARM64 and PPC can do
> RELEASE,
> the rest does indeed do smp_mb(), so there the spin_unlock() is
> a full
> barrier and we're good.
> * ARM64 has a very heavy barrier in switch_to(), which suffices.
> * PPC just removed its barrier from switch_to(), but appears
> to be
> talking about adding something to switch_mm(). So add a
> smp_mb__after_unlock_lock() for now, until this is settled on
> the PPC
> side.
>
> associated code:
>
> + /*
> + * The membarrier system call requires each architecture
> + * to have a full memory barrier after updating
> + * rq->curr, before returning to user-space. For TSO
> + * (e.g. x86), the architecture must provide its own
> + * barrier in switch_mm(). For weakly ordered machines
> + * for which spin_unlock() acts as a full memory
> + * barrier, finish_lock_switch() in common code takes
> + * care of this barrier. For weakly ordered machines for
> + * which spin_unlock() acts as a RELEASE barrier (only
> + * arm64 and PowerPC), arm64 has a full barrier in
> + * switch_to(), and PowerPC has
> + * smp_mb__after_unlock_lock() before
> + * finish_lock_switch().
> + */
>
> Which got updated to this by
>
> commit 306e060435d ("membarrier: Document scheduler barrier
> requirements")
>
> /*
> * The membarrier system call requires each architecture
> * to have a full memory barrier after updating
> + * rq->curr, before returning to user-space.
> + *
> + * Here are the schemes providing that barrier on the
> + * various architectures:
> + * - mm ? switch_mm() : mmdrop() for x86, s390, sparc,
> PowerPC.
> + * switch_mm() rely on membarrier_arch_switch_mm()
> on PowerPC.
> + * - finish_lock_switch() for weakly-ordered
> + * architectures where spin_unlock is a full barrier,
> + * - switch_to() for arm64 (weakly-ordered, spin_unlock
> + * is a RELEASE barrier),
> */
>
> However, rseq mm_cid has stricter requirements: the barrier needs to be
> issued between store to rq->curr and switch_mm_cid(), which happens
> earlier than:
>
> - spin_unlock(),
> - switch_to().
>
> So it's fine when the architecture switch_mm happens to have that barrier
> already, but less so when the architecture only provides the full barrier
> in switch_to() or spin_unlock().
>
> The issue is therefore not specific to arm64, it's actually a bug in the
> rseq switch_mm_cid() implementation. All architectures that don't have
> memory barriers in switch_mm(), but rather have the full barrier
> either in
> finish_lock_switch() or switch_to() have them too late for the needs of
> switch_mm_cid().
Thanks for the great detail explain!
>
> I would recommend one of three approaches here:
>
> A) Add smp_mb() in switch_mm_cid() for all architectures that lack that
> barrier in switch_mm().
>
> B) Figure out if we can move switch_mm_cid() further down in the
> scheduler
> without breaking anything (within switch_to(), at the very end of
> finish_lock_switch() for instance). I'm not sure we can do that though
> because switch_mm_cid() touches the "prev" which is tricky after
> switch_to().
>
> C) Add barriers in switch_mm() within all architectures that are
> missing it.
>
> Thoughts ?
IMHO, A) is look good to me.
Because, In case of B), If you assume spin_unlock() for rq->lock has
full memory barrier,
I'm not sure about the architecture which using queued_spin_unlock().
When I see the queued_spin_unlock()'s implementation, It implements
using smp_store_relasse().
But, when we see the memory_barrier.txt describing MULTICOPY ATOMICITY,
If smp_mb__after_atomic() is implemented with smp_mb(), There might fail
to observe.
Am I wrong?
Many thanks!