From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-19.4 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS, USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 03CFEC433ED for ; Mon, 10 May 2021 12:17:36 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id BD73361482 for ; Mon, 10 May 2021 12:17:35 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S239034AbhEJMSK (ORCPT ); Mon, 10 May 2021 08:18:10 -0400 Received: from mail.kernel.org ([198.145.29.99]:41148 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S236739AbhEJLIl (ORCPT ); Mon, 10 May 2021 07:08:41 -0400 Received: by mail.kernel.org (Postfix) with ESMTPSA id 1E92C6101D; Mon, 10 May 2021 11:03:46 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linuxfoundation.org; s=korg; t=1620644627; bh=C/RaOZWprDkk/jUwgIW45mnSsIH0kSo1oa1cMF3YENw=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=HYE2f30TBlIhkEthhz3Ri9fv9wcD3d1Krya0Kg1AuO3ridHqMYofhsXjU+y/E5mdA E18n/YEcXaWTLO5WUI3FKX3g97XPe2aQCXrPIRJlXUQ+1zx9w0QCwQDKBCxtWB+hOi myV0UR+EHdkOf73zS9RciGZFNTHcn1+zHbHIM29A= From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Emily Deng , =?UTF-8?q?Christian=20K=C3=B6nig?= , Alex Deucher , Sasha Levin Subject: [PATCH 5.12 160/384] drm/amdgpu: Fix some unload driver issues Date: Mon, 10 May 2021 12:19:09 +0200 Message-Id: <20210510102020.151414368@linuxfoundation.org> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210510102014.849075526@linuxfoundation.org> References: <20210510102014.849075526@linuxfoundation.org> User-Agent: quilt/0.66 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Emily Deng [ Upstream commit bb0cd09be45ea457f25fdcbcb3d6cf2230f26c46 ] When unloading driver after killing some applications, it will hit sdma flush tlb job timeout which is called by ttm_bo_delay_delete. So to avoid the job submit after fence driver fini, call ttm_bo_lock_delayed_workqueue before fence driver fini. And also put drm_sched_fini before waiting fence. Signed-off-by: Emily Deng Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 5 +++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 8a5a8ff5d362..5eee251e3335 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3613,6 +3613,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev) { dev_info(adev->dev, "amdgpu: finishing device.\n"); flush_delayed_work(&adev->delayed_init_work); + ttm_bo_lock_delayed_workqueue(&adev->mman.bdev); adev->shutdown = true; kfree(adev->pci_state); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index d56f4023ebb3..7e8e46c39dbd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -533,6 +533,8 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev) if (!ring || !ring->fence_drv.initialized) continue; + if (!ring->no_scheduler) + drm_sched_fini(&ring->sched); r = amdgpu_fence_wait_empty(ring); if (r) { /* no need to trigger GPU reset as we are unloading */ @@ -541,8 +543,7 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev) if (ring->fence_drv.irq_src) amdgpu_irq_put(adev, ring->fence_drv.irq_src, ring->fence_drv.irq_type); - if (!ring->no_scheduler) - drm_sched_fini(&ring->sched); + del_timer_sync(&ring->fence_drv.fallback_timer); for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j) dma_fence_put(ring->fence_drv.fences[j]); -- 2.30.2