public inbox for linux-media@vger.kernel.org
 help / color / mirror / Atom feed
From: "Christian König" <ckoenig.leichtzumerken@gmail.com>
To: sumit.semwal@linaro.org, daniel@ffwll.ch
Cc: linux-media@vger.kernel.org, dri-devel@lists.freedesktop.org,
	linaro-mm-sig@lists.linaro.org
Subject: [PATCH 01/26] drm/amdgpu: partially revert "svm bo enable_signal call condition"
Date: Tue, 23 Nov 2021 15:20:46 +0100	[thread overview]
Message-ID: <20211123142111.3885-2-christian.koenig@amd.com> (raw)
In-Reply-To: <20211123142111.3885-1-christian.koenig@amd.com>

Partially revert commit 5f319c5c21b5909abb43d8aadc92a8aa549ee443.

First of all this is illegal use of RCU to call dma_fence_enable_sw_signaling()
since we don't hold a reference to the fence in question and can crash badly.

Then the code doesn't seem to have the intended effect since only the
exclusive fence is handled, but the KFD fences are always added as shared fence.

Only keep the handling to throw away the content of SVM BOs.

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index eab4380f28e5..c15687ce67c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -116,17 +116,8 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 
 	abo = ttm_to_amdgpu_bo(bo);
 	if (abo->flags & AMDGPU_AMDKFD_CREATE_SVM_BO) {
-		struct dma_fence *fence;
-		struct dma_resv *resv = &bo->base._resv;
-
-		rcu_read_lock();
-		fence = rcu_dereference(resv->fence_excl);
-		if (fence && !fence->ops->signaled)
-			dma_fence_enable_sw_signaling(fence);
-
 		placement->num_placement = 0;
 		placement->num_busy_placement = 0;
-		rcu_read_unlock();
 		return;
 	}
 
-- 
2.25.1


  reply	other threads:[~2021-11-23 14:21 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-23 14:20 completely rework the dma_resv semantic Christian König
2021-11-23 14:20 ` Christian König [this message]
2021-11-23 14:20 ` [PATCH 02/26] dma-buf: cleanup pruning of dma_resv objects Christian König
2021-11-23 14:20 ` [PATCH 03/26] dma-buf: make fence mandatory for dma_resv_add_excl_fence Christian König
2021-11-23 14:20 ` [PATCH 04/26] drm/qxl: use iterator instead of dma_resv_shared_list Christian König
2021-11-23 14:20 ` [PATCH 05/26] dma-buf: add dma_resv_replace_fences Christian König
2021-11-23 14:20 ` [PATCH 06/26] dma-buf: finally make the dma_resv_list private Christian König
2021-11-23 14:20 ` [PATCH 07/26] dma-buf: drop excl_fence parameter from dma_resv_get_fences Christian König
2021-11-23 14:20 ` [PATCH 08/26] dma-buf: add dma_resv_get_singleton Christian König
2021-11-23 14:20 ` [PATCH 09/26] RDMA: use dma_resv_wait() instead of extracting the fence Christian König
2021-11-23 14:20 ` [PATCH 10/26] drm/etnaviv: stop using dma_resv_excl_fence Christian König
2021-11-23 14:20 ` [PATCH 11/26] drm/nouveau: " Christian König
2021-11-23 14:20 ` [PATCH 12/26] drm/vmwgfx: " Christian König
2021-11-23 14:20 ` [PATCH 13/26] drm/radeon: " Christian König
2021-11-23 14:20 ` [PATCH 14/26] drm/amdgpu: remove excl as shared workarounds Christian König
2021-11-23 14:21 ` [PATCH 15/26] drm/amdgpu: use dma_resv_for_each_fence for CS workaround Christian König
2021-11-23 14:21 ` [PATCH 16/26] dma-buf: finally make dma_resv_excl_fence private Christian König
2021-11-23 14:21 ` [PATCH 17/26] dma-buf: drop the DAG approach for the dma_resv object Christian König
2021-11-23 14:21 ` [PATCH 18/26] dma-buf/drivers: make reserving a shared slot mandatory Christian König
2021-11-23 14:21 ` [PATCH 19/26] drm: support more than one write fence in drm_gem_plane_helper_prepare_fb Christian König
2021-11-25 15:47   ` Daniel Vetter
2021-11-26 10:30     ` Christian König
2021-11-26 15:37       ` Daniel Vetter
2021-11-23 14:21 ` [PATCH 20/26] drm/nouveau: support more than one write fence in fenv50_wndw_prepare_fb Christian König
2021-11-23 14:21 ` [PATCH 21/26] drm/amdgpu: use dma_resv_get_singleton in amdgpu_pasid_free_cb Christian König
2021-11-23 14:21 ` [PATCH 22/26] dma-buf: add enum dma_resv_usage Christian König
2021-11-25 15:50   ` Daniel Vetter
2021-11-25 15:59   ` Daniel Vetter
2021-11-29 12:19     ` Christian König
2021-11-30  8:31       ` Daniel Vetter
2021-11-23 14:21 ` [PATCH 23/26] dma-buf: specify usage while adding fences to dma_resv obj Christian König
2021-11-23 14:21 ` [PATCH 24/26] dma-buf: wait for map to complete for static attachments Christian König
2021-11-23 14:21 ` [PATCH 25/26] amdgpu: remove DMA-buf fence workaround Christian König
2021-11-23 14:21 ` [PATCH 26/26] drm/ttm: remove bo->moving Christian König
2021-11-24  8:31 ` completely rework the dma_resv semantic Pekka Paalanen
2021-11-24  8:39   ` Christian König
2021-11-25 16:04 ` Daniel Vetter

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20211123142111.3885-2-christian.koenig@amd.com \
    --to=ckoenig.leichtzumerken@gmail.com \
    --cc=daniel@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=linaro-mm-sig@lists.linaro.org \
    --cc=linux-media@vger.kernel.org \
    --cc=sumit.semwal@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox