mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH v2] dma-buf/dma-fence: Prevent misordering for error checks
@ 2026-11-18 11:09 Philipp Stanner
  2026-11-18 12:59 ` Gary Guo
  0 siblings, 1 reply; 4+ messages in thread
From: Philipp Stanner @ 2026-11-18 11:09 UTC (permalink / raw)
  To: Sumit Semwal, Christian König, Philipp Stanner,
	Simona Vetter, Chris Wilson, Danilo Krummrich, Gary Guo,
	Alice Ryhl, Daniel Almeida, Tvrtko Ursulin
  Cc: linux-media, dri-devel, linux-kernel, stable

Many users of dma_fence do things like:

// Thread A
dma_fence_set_error(f, -EINVAL);
dma_fence_signal(f); // <- Takes lock, which orders against the above.

// Thread B
if (dma_fence_is_signaled(f)) // <- Does test_bit(), no ordering.
	pr_info("err: %i\n", f->error); // <- Can be loaded first.

There is no memory ordering between reading of the signaled-bit and
reading of the error code. This can result in outdated, wrong error
codes being evaluated by the user.

Though dma_fence_get_status() does take the fence lock, it is equally
broken because the misordering can simply happen within the critical
section.

It's not entirely clear since when this bug exists, but at least since
dma_fence_get_status() was added, which is why its birth commit is
marked as the Fixes commit here.

Ensure ordering for everyone evaluating the error code centrally by
using test_bit_acquire() in dma_fence_test_signaled_flag().

Cc: stable@vger.kernel.org
Fixes: d6c99f4bf093 ("dma-fence: Wrap querying the fence->status")
Signed-off-by: Philipp Stanner <phasta@kernel.org>
---
Changes in v2:
  - Use classic C style comments. (Christian)
---
 include/linux/dma-fence.h | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index dd07d128adc3..a3fa1341765e 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -496,7 +496,18 @@ const char __rcu *dma_fence_timeline_name(struct dma_fence *fence);
 static inline bool
 dma_fence_test_signaled_flag(struct dma_fence *fence)
 {
-	return test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags);
+	/*
+	 * Best-effort ordering of the locklessly evaluated signaled-bit,
+	 * especially so that reads of fence->error are not misordered.
+	 *
+	 * The release counterpart is typically ensured like this:
+	 *   a) Error codes must only be set before a fence signals and
+	 *   b) The fence's spinlock's barriers effective in dma_fence_signal()
+	 *      ensure ordering.
+	 *   c) For users of dma_fence_signal_locked(), the barrier implied in
+	 *      test_and_set_bit() should do the trick.
+	 */
+	return test_bit_acquire(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags);
 }
 
 /**
-- 
2.56.0


^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [PATCH v2] dma-buf/dma-fence: Prevent misordering for error checks
  2026-11-18 11:09 [PATCH v2] dma-buf/dma-fence: Prevent misordering for error checks Philipp Stanner
@ 2026-11-18 12:59 ` Gary Guo
  2026-11-18 13:15   ` Philipp Stanner
  0 siblings, 1 reply; 4+ messages in thread
From: Gary Guo @ 2026-11-18 12:59 UTC (permalink / raw)
  To: Philipp Stanner, Sumit Semwal, Christian König,
	Simona Vetter, Chris Wilson, Danilo Krummrich, Gary Guo,
	Alice Ryhl, Daniel Almeida, Tvrtko Ursulin
  Cc: linux-media, dri-devel, linux-kernel, stable

On Wed Nov 18, 2026 at 11:09 AM GMT, Philipp Stanner wrote:
> Many users of dma_fence do things like:
>
> // Thread A
> dma_fence_set_error(f, -EINVAL);
> dma_fence_signal(f); // <- Takes lock, which orders against the above.
>
> // Thread B
> if (dma_fence_is_signaled(f)) // <- Does test_bit(), no ordering.
> 	pr_info("err: %i\n", f->error); // <- Can be loaded first.
>
> There is no memory ordering between reading of the signaled-bit and
> reading of the error code. This can result in outdated, wrong error
> codes being evaluated by the user.
>
> Though dma_fence_get_status() does take the fence lock, it is equally
> broken because the misordering can simply happen within the critical
> section.
>
> It's not entirely clear since when this bug exists, but at least since
> dma_fence_get_status() was added, which is why its birth commit is
> marked as the Fixes commit here.
>
> Ensure ordering for everyone evaluating the error code centrally by
> using test_bit_acquire() in dma_fence_test_signaled_flag().
>
> Cc: stable@vger.kernel.org
> Fixes: d6c99f4bf093 ("dma-fence: Wrap querying the fence->status")
> Signed-off-by: Philipp Stanner <phasta@kernel.org>
> ---
> Changes in v2:
>   - Use classic C style comments. (Christian)
> ---
>  include/linux/dma-fence.h | 13 ++++++++++++-
>  1 file changed, 12 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
> index dd07d128adc3..a3fa1341765e 100644
> --- a/include/linux/dma-fence.h
> +++ b/include/linux/dma-fence.h
> @@ -496,7 +496,18 @@ const char __rcu *dma_fence_timeline_name(struct dma_fence *fence);
>  static inline bool
>  dma_fence_test_signaled_flag(struct dma_fence *fence)
>  {
> -	return test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags);
> +	/*
> +	 * Best-effort ordering of the locklessly evaluated signaled-bit,
> +	 * especially so that reads of fence->error are not misordered.

I am not sure if this should focus on the error, or it should just provide a
general guarantee that anything happens before dma_fence_signal is visible when
signal test returns true. I would lean on the latter?

> +	 *
> +	 * The release counterpart is typically ensured like this:
> +	 *   a) Error codes must only be set before a fence signals and
> +	 *   b) The fence's spinlock's barriers effective in dma_fence_signal()
> +	 *      ensure ordering.

Spinlock has nothing to do with this. The only thing that guarantees the
ordering is test_and_set_bit in (c).

So probably easier just to say something like

    /* Pairs with test_and_set_bit() in dma_fence_signal_timestamp_locked */

Best,
Gary

> +	 *   c) For users of dma_fence_signal_locked(), the barrier implied in
> +	 *      test_and_set_bit() should do the trick.
> +	 */
> +	return test_bit_acquire(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags);
>  }
>  
>  /**



^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [PATCH v2] dma-buf/dma-fence: Prevent misordering for error checks
  2026-11-18 12:59 ` Gary Guo
@ 2026-11-18 13:15   ` Philipp Stanner
  2026-11-18 13:49     ` Gary Guo
  0 siblings, 1 reply; 4+ messages in thread
From: Philipp Stanner @ 2026-11-18 13:15 UTC (permalink / raw)
  To: Gary Guo, Philipp Stanner, Sumit Semwal, Christian König,
	Simona Vetter, Chris Wilson, Danilo Krummrich, Alice Ryhl,
	Daniel Almeida, Tvrtko Ursulin
  Cc: linux-media, dri-devel, linux-kernel, stable

On Wed, 2026-11-18 at 12:59 +0000, Gary Guo wrote:
> On Wed Nov 18, 2026 at 11:09 AM GMT, Philipp Stanner wrote:

[…]

> >  static inline bool
> >  dma_fence_test_signaled_flag(struct dma_fence *fence)
> >  {
> > -	return test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags);
> > +	/*
> > +	 * Best-effort ordering of the locklessly evaluated signaled-bit,
> > +	 * especially so that reads of fence->error are not misordered.
> 
> I am not sure if this should focus on the error, or it should just provide a
> general guarantee that anything happens before dma_fence_signal is visible when
> signal test returns true. I would lean on the latter?

See below.

> 
> > +	 *
> > +	 * The release counterpart is typically ensured like this:
> > +	 *   a) Error codes must only be set before a fence signals and
> > +	 *   b) The fence's spinlock's barriers effective in dma_fence_signal()
> > +	 *      ensure ordering.
> 
> Spinlock has nothing to do with this. The only thing that guarantees the
> ordering is test_and_set_bit in (c).

Why not? A spinlock includes full barriers. If it were set_bit()
instead of test_and_set_bit(), it would still work.

> 
> So probably easier just to say something like
> 
>     /* Pairs with test_and_set_bit() in dma_fence_signal_timestamp_locked */

It is easier.

I am, however, unhappy with the unclear state of the API contract. It's
still unclear what the signaled-flag even is supposed to mean. So this
comment was also supposed to hint at the unclear state.

The desired meaning aimed for by Christian is that it's only meaning is
"hardware is done".

But as we see here it has implications for the entire semantic, too:
a) signaled == true -> the error code is valid (what else?)
b) The fence has either signaled or "is still signaling", i.e. running
callbacks

I still maintain the position that it is inconsistent to run
test_and_set_bit() under lock protection and evaluate it without the
lock. Should be one or the other, not both.

Note that this patch intends just to hot-fix the error code evaluation,
not to make the fence API fully consistent. It's currently not even
clear whether manual flag evaluation is legal. It used to be legal. I'm
the one who added dma_fence_test_signaled_flag(), but mostly for
readability, not for semantic correctness.

It should be illegal to evaluate error codes with anything other than
dma_fence_get_status(). But there then the meaning of the spinlock is
currently also undefined. The lock there, with the current thinking,
would seem surplus with this patch here.


P.

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [PATCH v2] dma-buf/dma-fence: Prevent misordering for error checks
  2026-11-18 13:15   ` Philipp Stanner
@ 2026-11-18 13:49     ` Gary Guo
  0 siblings, 0 replies; 4+ messages in thread
From: Gary Guo @ 2026-11-18 13:49 UTC (permalink / raw)
  To: phasta, Gary Guo, Sumit Semwal, Christian König,
	Simona Vetter, Chris Wilson, Danilo Krummrich, Alice Ryhl,
	Daniel Almeida, Tvrtko Ursulin
  Cc: linux-media, dri-devel, linux-kernel, stable

On Wed Nov 18, 2026 at 1:15 PM GMT, Philipp Stanner wrote:
> On Wed, 2026-11-18 at 12:59 +0000, Gary Guo wrote:
>> On Wed Nov 18, 2026 at 11:09 AM GMT, Philipp Stanner wrote:
>
> […]
>
>> >  static inline bool
>> >  dma_fence_test_signaled_flag(struct dma_fence *fence)
>> >  {
>> > -	return test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags);
>> > +	/*
>> > +	 * Best-effort ordering of the locklessly evaluated signaled-bit,
>> > +	 * especially so that reads of fence->error are not misordered.
>> 
>> I am not sure if this should focus on the error, or it should just provide a
>> general guarantee that anything happens before dma_fence_signal is visible when
>> signal test returns true. I would lean on the latter?
>
> See below.
>
>> 
>> > +	 *
>> > +	 * The release counterpart is typically ensured like this:
>> > +	 *   a) Error codes must only be set before a fence signals and
>> > +	 *   b) The fence's spinlock's barriers effective in dma_fence_signal()
>> > +	 *      ensure ordering.
>> 
>> Spinlock has nothing to do with this. The only thing that guarantees the
>> ordering is test_and_set_bit in (c).
>
> Why not? A spinlock includes full barriers. If it were set_bit()
> instead of test_and_set_bit(), it would still work.

No. spin_lock is a marked acquire access and spin_unlock is a marked release
access. The order guarantee for these are restricted to the spinlock variable
only (there is no acquire or release barriers in the kernel).

If you need to establish order using spinlock, you can only establish it with

    CPU 0  A --> spin_unlock 
                            \
                             \
                              \
    CPU 1                     spin_lock -> B

You cannot establish relation just by putting some atomic operation inside
spinlock critical sections.

You can make spin_lock a full barrier by using smp_mb__after_spinlock(), but
it's not there. I also think it's much easier to reason about test_bit_acquire()
pairing with test_and_set_bit() than "this code will only be executed after a
spin_lock".

>> 
>> So probably easier just to say something like
>> 
>>     /* Pairs with test_and_set_bit() in dma_fence_signal_timestamp_locked */
>
> It is easier.
>
> I am, however, unhappy with the unclear state of the API contract. It's
> still unclear what the signaled-flag even is supposed to mean. So this
> comment was also supposed to hint at the unclear state.
>
> The desired meaning aimed for by Christian is that it's only meaning is
> "hardware is done".

Hmm, if the dma-fence doesn't provide ordering guarantee, then how would a
consumer get ordering guarantee without knowing about the implementation detail on
the producer side?

To me it seems that providing ordering guarantee that "when a DMA fence is
observed to be signaled, everything prior to dma_fence_signal is visible"
wouldn't be that expensive to implement (practically just need to upgrade a few
test_bit to test_bit_acquire).

Best,
Gary

>
> But as we see here it has implications for the entire semantic, too:
> a) signaled == true -> the error code is valid (what else?)
> b) The fence has either signaled or "is still signaling", i.e. running
> callbacks
>
> I still maintain the position that it is inconsistent to run
> test_and_set_bit() under lock protection and evaluate it without the
> lock. Should be one or the other, not both.
>
> Note that this patch intends just to hot-fix the error code evaluation,
> not to make the fence API fully consistent. It's currently not even
> clear whether manual flag evaluation is legal. It used to be legal. I'm
> the one who added dma_fence_test_signaled_flag(), but mostly for
> readability, not for semantic correctness.
>
> It should be illegal to evaluate error codes with anything other than
> dma_fence_get_status(). But there then the meaning of the spinlock is
> currently also undefined. The lock there, with the current thinking,
> would seem surplus with this patch here.
>
>
> P.



^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2026-11-18 13:49 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-11-18 11:09 [PATCH v2] dma-buf/dma-fence: Prevent misordering for error checks Philipp Stanner
2026-11-18 12:59 ` Gary Guo
2026-11-18 13:15   ` Philipp Stanner
2026-11-18 13:49     ` Gary Guo

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®