Re: [Intel-gfx] [PATCH 5/5] DONOTMERGE: dma-buf: Get rid of dma_fence_get_rcu_safe

From: "Christian König" <christian.koenig@amd.com>
To: Jason Ekstrand <jason@jlekstrand.net>,
	dri-devel@lists.freedesktop.org, intel-gfx@lists.freedesktop.org
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>,
	Matthew Auld <matthew.auld@intel.com>
Subject: Re: [Intel-gfx] [PATCH 5/5] DONOTMERGE: dma-buf: Get rid of dma_fence_get_rcu_safe
Date: Thu, 10 Jun 2021 08:51:16 +0200	[thread overview]
Message-ID: <ea36431d-521a-c1c0-59e5-a196f55c28dd@amd.com> (raw)
In-Reply-To: <20210609212959.471209-6-jason@jlekstrand.net>

Am 09.06.21 um 23:29 schrieb Jason Ekstrand:
> This helper existed to handle the weird corner-cases caused by using
> SLAB_TYPESAFE_BY_RCU for backing dma_fence.  Now that no one is using
> that anymore (i915 was the only real user), dma_fence_get_rcu is
> sufficient.  The one slightly annoying thing we have to deal with here
> is that dma_fence_get_rcu_safe did an rcu_dereference as well as a
> SLAB_TYPESAFE_BY_RCU-safe dma_fence_get_rcu.  This means each call site
> ends up being 3 lines instead of 1.

That's an outright NAK.

The loop in dma_fence_get_rcu_safe is necessary because the underlying 
fence object can be replaced while taking the reference.

This is completely unrelated to SLAB_TYPESAFE_BY_RCU. See the 
dma_fence_chain usage for reference.

What you can remove is the sequence number handling in dma-buf. That 
should make adding fences quite a bit quicker.

Regards,
Christian.

>
> Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
> Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
> Cc: Christian König <christian.koenig@amd.com>
> Cc: Matthew Auld <matthew.auld@intel.com>
> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
> ---
>   drivers/dma-buf/dma-fence-chain.c         |  8 ++--
>   drivers/dma-buf/dma-resv.c                |  4 +-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c |  4 +-
>   drivers/gpu/drm/i915/i915_active.h        |  4 +-
>   drivers/gpu/drm/i915/i915_vma.c           |  4 +-
>   include/drm/drm_syncobj.h                 |  4 +-
>   include/linux/dma-fence.h                 | 50 -----------------------
>   include/linux/dma-resv.h                  |  4 +-
>   8 files changed, 23 insertions(+), 59 deletions(-)
>
> diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c
> index 7d129e68ac701..46dfc7d94d8ed 100644
> --- a/drivers/dma-buf/dma-fence-chain.c
> +++ b/drivers/dma-buf/dma-fence-chain.c
> @@ -15,15 +15,17 @@ static bool dma_fence_chain_enable_signaling(struct dma_fence *fence);
>    * dma_fence_chain_get_prev - use RCU to get a reference to the previous fence
>    * @chain: chain node to get the previous node from
>    *
> - * Use dma_fence_get_rcu_safe to get a reference to the previous fence of the
> - * chain node.
> + * Use rcu_dereference and dma_fence_get_rcu to get a reference to the
> + * previous fence of the chain node.
>    */
>   static struct dma_fence *dma_fence_chain_get_prev(struct dma_fence_chain *chain)
>   {
>   	struct dma_fence *prev;
>   
>   	rcu_read_lock();
> -	prev = dma_fence_get_rcu_safe(&chain->prev);
> +	prev = rcu_dereference(chain->prev);
> +	if (prev)
> +		prev = dma_fence_get_rcu(prev);
>   	rcu_read_unlock();
>   	return prev;
>   }
> diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
> index f26c71747d43a..cfe0db3cca292 100644
> --- a/drivers/dma-buf/dma-resv.c
> +++ b/drivers/dma-buf/dma-resv.c
> @@ -376,7 +376,9 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src)
>   		dst_list = NULL;
>   	}
>   
> -	new = dma_fence_get_rcu_safe(&src->fence_excl);
> +	new = rcu_dereference(src->fence_excl);
> +	if (new)
> +		new = dma_fence_get_rcu(new);
>   	rcu_read_unlock();
>   
>   	src_list = dma_resv_shared_list(dst);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> index 72d9b92b17547..0aeb6117f3893 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> @@ -161,7 +161,9 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
>   		struct dma_fence *old;
>   
>   		rcu_read_lock();
> -		old = dma_fence_get_rcu_safe(ptr);
> +		old = rcu_dereference(*ptr);
> +		if (old)
> +			old = dma_fence_get_rcu(old);
>   		rcu_read_unlock();
>   
>   		if (old) {
> diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
> index d0feda68b874f..bd89cfc806ca5 100644
> --- a/drivers/gpu/drm/i915/i915_active.h
> +++ b/drivers/gpu/drm/i915/i915_active.h
> @@ -103,7 +103,9 @@ i915_active_fence_get(struct i915_active_fence *active)
>   	struct dma_fence *fence;
>   
>   	rcu_read_lock();
> -	fence = dma_fence_get_rcu_safe(&active->fence);
> +	fence = rcu_dereference(active->fence);
> +	if (fence)
> +		fence = dma_fence_get_rcu(fence);
>   	rcu_read_unlock();
>   
>   	return fence;
> diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
> index 0f227f28b2802..ed0388d99197e 100644
> --- a/drivers/gpu/drm/i915/i915_vma.c
> +++ b/drivers/gpu/drm/i915/i915_vma.c
> @@ -351,7 +351,9 @@ int i915_vma_wait_for_bind(struct i915_vma *vma)
>   		struct dma_fence *fence;
>   
>   		rcu_read_lock();
> -		fence = dma_fence_get_rcu_safe(&vma->active.excl.fence);
> +		fence = rcu_dereference(vma->active.excl.fence);
> +		if (fence)
> +			fence = dma_fence_get_rcu(fence);
>   		rcu_read_unlock();
>   		if (fence) {
>   			err = dma_fence_wait(fence, MAX_SCHEDULE_TIMEOUT);
> diff --git a/include/drm/drm_syncobj.h b/include/drm/drm_syncobj.h
> index 6cf7243a1dc5e..6c45d52988bcc 100644
> --- a/include/drm/drm_syncobj.h
> +++ b/include/drm/drm_syncobj.h
> @@ -105,7 +105,9 @@ drm_syncobj_fence_get(struct drm_syncobj *syncobj)
>   	struct dma_fence *fence;
>   
>   	rcu_read_lock();
> -	fence = dma_fence_get_rcu_safe(&syncobj->fence);
> +	fence = rcu_dereference(syncobj->fence);
> +	if (fence)
> +		fence = dma_fence_get_rcu(syncobj->fence);
>   	rcu_read_unlock();
>   
>   	return fence;
> diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
> index 6ffb4b2c63715..f4a2ab2b1ae46 100644
> --- a/include/linux/dma-fence.h
> +++ b/include/linux/dma-fence.h
> @@ -307,56 +307,6 @@ static inline struct dma_fence *dma_fence_get_rcu(struct dma_fence *fence)
>   		return NULL;
>   }
>   
> -/**
> - * dma_fence_get_rcu_safe  - acquire a reference to an RCU tracked fence
> - * @fencep: pointer to fence to increase refcount of
> - *
> - * Function returns NULL if no refcount could be obtained, or the fence.
> - * This function handles acquiring a reference to a fence that may be
> - * reallocated within the RCU grace period (such as with SLAB_TYPESAFE_BY_RCU),
> - * so long as the caller is using RCU on the pointer to the fence.
> - *
> - * An alternative mechanism is to employ a seqlock to protect a bunch of
> - * fences, such as used by struct dma_resv. When using a seqlock,
> - * the seqlock must be taken before and checked after a reference to the
> - * fence is acquired (as shown here).
> - *
> - * The caller is required to hold the RCU read lock.
> - */
> -static inline struct dma_fence *
> -dma_fence_get_rcu_safe(struct dma_fence __rcu **fencep)
> -{
> -	do {
> -		struct dma_fence *fence;
> -
> -		fence = rcu_dereference(*fencep);
> -		if (!fence)
> -			return NULL;
> -
> -		if (!dma_fence_get_rcu(fence))
> -			continue;
> -
> -		/* The atomic_inc_not_zero() inside dma_fence_get_rcu()
> -		 * provides a full memory barrier upon success (such as now).
> -		 * This is paired with the write barrier from assigning
> -		 * to the __rcu protected fence pointer so that if that
> -		 * pointer still matches the current fence, we know we
> -		 * have successfully acquire a reference to it. If it no
> -		 * longer matches, we are holding a reference to some other
> -		 * reallocated pointer. This is possible if the allocator
> -		 * is using a freelist like SLAB_TYPESAFE_BY_RCU where the
> -		 * fence remains valid for the RCU grace period, but it
> -		 * may be reallocated. When using such allocators, we are
> -		 * responsible for ensuring the reference we get is to
> -		 * the right fence, as below.
> -		 */
> -		if (fence == rcu_access_pointer(*fencep))
> -			return rcu_pointer_handoff(fence);
> -
> -		dma_fence_put(fence);
> -	} while (1);
> -}
> -
>   #ifdef CONFIG_LOCKDEP
>   bool dma_fence_begin_signalling(void);
>   void dma_fence_end_signalling(bool cookie);
> diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h
> index 562b885cf9c3d..a38c021f379af 100644
> --- a/include/linux/dma-resv.h
> +++ b/include/linux/dma-resv.h
> @@ -248,7 +248,9 @@ dma_resv_get_excl_unlocked(struct dma_resv *obj)
>   		return NULL;
>   
>   	rcu_read_lock();
> -	fence = dma_fence_get_rcu_safe(&obj->fence_excl);
> +	fence = rcu_dereference(obj->fence_excl);
> +	if (fence)
> +		fence = dma_fence_get_rcu(fence);
>   	rcu_read_unlock();
>   
>   	return fence;

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx