From patchwork Mon Jul 26 15:00:21 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 76002 Received: from vger.kernel.org ([23.128.96.18]) by www.linuxtv.org with esmtp (Exim 4.92) (envelope-from ) id 1m822J-006AT3-UA; Mon, 26 Jul 2021 14:56:59 +0000 Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234949AbhGZOQX (ORCPT + 1 other); Mon, 26 Jul 2021 10:16:23 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:35532 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234935AbhGZOQW (ORCPT ); Mon, 26 Jul 2021 10:16:22 -0400 Received: from mail-pl1-x62a.google.com (mail-pl1-x62a.google.com [IPv6:2607:f8b0:4864:20::62a]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 3C2BBC061757; Mon, 26 Jul 2021 07:56:51 -0700 (PDT) Received: by mail-pl1-x62a.google.com with SMTP id d1so4645605pll.1; Mon, 26 Jul 2021 07:56:51 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=DealqZ52rle5Sxs0OYfG57W/B0C5w2BihQ08hiiaTrI=; b=DyASpC+YLT9N7O0Uq7lGf/OwlGbIdLNvnykMSAbmllJutFM5tA0suXGsgAoOa1pIdT RfHcHVSzlj7Rg3vHzQfBBjuPaAVhVDH4hSluMvcHihyTwtI+VXICKf6ziqh3Ahfkkcfy VOGL5MlFrXhhObnWih1RwSvX6YKCQgFqwmWWLp0PVo1PPdeP7JMzHacIA467ITdnH3Xg oxb4G0aOTNDcfOOsCUVLmCFjA+ASmtVS1t9HlUmcLhFWDIg4bGj4CITnyrJwR3l08QyP Vm9VZU5WKPVo2Vzhcb9a5mwYu1OT0RaEgPcP/gnzv0y2NuektehWZ6P+DinXPYJ9ylrx ljIw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=DealqZ52rle5Sxs0OYfG57W/B0C5w2BihQ08hiiaTrI=; b=LTAu1EImxuQY9fyRfnddHEWs2AhLavcIk485HuHMriwaha2s0vz5qBDftKfeKVDTf6 453m9KRFzXzCYAdzscHN8gT0p2s1na/rNttpwV5qIjGD440VGXpUVK8pDiLUvIF4ycGI XWmOayGAfjPhiEtLkBKExDEPC3AlIaO1MNsZ1QnaDFne9wtRbWJSBfiDwjmO6D5Bj4Sf 0A3P/CKZZ9I2SGQCIRHq91gd1QhjRBU3pXCAWsW5u28H/hn2aMU5WNBuNZniLeL+Yvap eQZnpfRu35jm+R3DZCMo45HfN77ZND/FCZZTvRFjYvr2T6bO3m5DfIJT/t3bMU/uR1cl TVyw== X-Gm-Message-State: AOAM532e3HYZUzuhC7ntgcnMlGiNY3oAqL0TN+s51TpGEJySsnnQFfmd Z9zw5YLtIg1SLeUez/KdBsY= X-Google-Smtp-Source: ABdhPJz2H5ichqwatlBbq8PZI6dR64xARsn0yQ0bJq3Rpn8p7rOz0FD3+AGQKz6pEJEfDn/u0HgCxg== X-Received: by 2002:a17:90b:2112:: with SMTP id kz18mr26733930pjb.137.1627311410773; Mon, 26 Jul 2021 07:56:50 -0700 (PDT) Received: from localhost ([2601:1c0:5200:a6:307:a401:7b76:c6e5]) by smtp.gmail.com with ESMTPSA id g12sm243940pfv.167.2021.07.26.07.56.49 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 26 Jul 2021 07:56:49 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: Rob Clark , =?utf-8?q?Christian_K=C3=B6nig?= , Rob Clark , Sean Paul , David Airlie , Daniel Vetter , Sumit Semwal , linux-arm-msm@vger.kernel.org (open list:DRM DRIVER FOR MSM ADRENO GPU), freedreno@lists.freedesktop.org (open list:DRM DRIVER FOR MSM ADRENO GPU), linux-kernel@vger.kernel.org (open list), linux-media@vger.kernel.org (open list:DMA BUFFER SHARING FRAMEWORK), linaro-mm-sig@lists.linaro.org (moderated list:DMA BUFFER SHARING FRAMEWORK) Subject: [PATCH v2 07/12] drm/msm: Track "seqno" fences by idr Date: Mon, 26 Jul 2021 08:00:21 -0700 Message-Id: <20210726150038.2187631-8-robdclark@gmail.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210726150038.2187631-1-robdclark@gmail.com> References: <20210726150038.2187631-1-robdclark@gmail.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-media@vger.kernel.org X-LSpam-Score: -2.5 (--) X-LSpam-Report: No, score=-2.5 required=5.0 tests=BAYES_00=-1.9,DKIM_SIGNED=0.1,DKIM_VALID=-0.1,DKIM_VALID_AU=-0.1,FREEMAIL_FORGED_FROMDOMAIN=0.001,FREEMAIL_FROM=0.001,HEADER_FROM_DIFFERENT_DOMAINS=0.5,MAILING_LIST_MULTI=-1,RCVD_IN_DNSWL_NONE=-0.0001 autolearn=ham autolearn_force=no From: Rob Clark Previously the (non-fd) fence returned from submit ioctl was a raw seqno, which is scoped to the ring. But from UABI standpoint, the ioctls related to seqno fences all specify a submitqueue. We can take advantage of that to replace the seqno fences with a cyclic idr handle. This is in preperation for moving to drm scheduler, at which point the submit ioctl will return after queuing the submit job to the scheduler, but before the submit is written into the ring (and therefore before a ring seqno has been assigned). Which means we need to replace the dma_fence that userspace may need to wait on with a scheduler fence. Signed-off-by: Rob Clark Acked-by: Christian König --- drivers/gpu/drm/msm/msm_drv.c | 30 +++++++++++++++++++-- drivers/gpu/drm/msm/msm_fence.c | 39 --------------------------- drivers/gpu/drm/msm/msm_fence.h | 2 -- drivers/gpu/drm/msm/msm_gem.h | 1 + drivers/gpu/drm/msm/msm_gem_submit.c | 23 +++++++++++++++- drivers/gpu/drm/msm/msm_gpu.h | 5 ++++ drivers/gpu/drm/msm/msm_submitqueue.c | 5 ++++ 7 files changed, 61 insertions(+), 44 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 9b8fa2ad0d84..1594ae39d54f 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -911,6 +911,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, ktime_t timeout = to_ktime(args->timeout); struct msm_gpu_submitqueue *queue; struct msm_gpu *gpu = priv->gpu; + struct dma_fence *fence; int ret; if (args->pad) { @@ -925,10 +926,35 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, if (!queue) return -ENOENT; - ret = msm_wait_fence(gpu->rb[queue->prio]->fctx, args->fence, &timeout, - true); + /* + * Map submitqueue scoped "seqno" (which is actually an idr key) + * back to underlying dma-fence + * + * The fence is removed from the fence_idr when the submit is + * retired, so if the fence is not found it means there is nothing + * to wait for + */ + ret = mutex_lock_interruptible(&queue->lock); + if (ret) + return ret; + fence = idr_find(&queue->fence_idr, args->fence); + if (fence) + fence = dma_fence_get_rcu(fence); + mutex_unlock(&queue->lock); + + if (!fence) + return 0; + ret = dma_fence_wait_timeout(fence, true, timeout_to_jiffies(&timeout)); + if (ret == 0) { + ret = -ETIMEDOUT; + } else if (ret != -ERESTARTSYS) { + ret = 0; + } + + dma_fence_put(fence); msm_submitqueue_put(queue); + return ret; } diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c index b92a9091a1e2..d8228029708e 100644 --- a/drivers/gpu/drm/msm/msm_fence.c +++ b/drivers/gpu/drm/msm/msm_fence.c @@ -45,45 +45,6 @@ static inline bool fence_completed(struct msm_fence_context *fctx, uint32_t fenc (int32_t)(*fctx->fenceptr - fence) >= 0; } -/* legacy path for WAIT_FENCE ioctl: */ -int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence, - ktime_t *timeout, bool interruptible) -{ - int ret; - - if (fence > fctx->last_fence) { - DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n", - fctx->name, fence, fctx->last_fence); - return -EINVAL; - } - - if (!timeout) { - /* no-wait: */ - ret = fence_completed(fctx, fence) ? 0 : -EBUSY; - } else { - unsigned long remaining_jiffies = timeout_to_jiffies(timeout); - - if (interruptible) - ret = wait_event_interruptible_timeout(fctx->event, - fence_completed(fctx, fence), - remaining_jiffies); - else - ret = wait_event_timeout(fctx->event, - fence_completed(fctx, fence), - remaining_jiffies); - - if (ret == 0) { - DBG("timeout waiting for fence: %u (completed: %u)", - fence, fctx->completed_fence); - ret = -ETIMEDOUT; - } else if (ret != -ERESTARTSYS) { - ret = 0; - } - } - - return ret; -} - /* called from workqueue */ void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence) { diff --git a/drivers/gpu/drm/msm/msm_fence.h b/drivers/gpu/drm/msm/msm_fence.h index 6ab97062ff1a..6de97d0f5153 100644 --- a/drivers/gpu/drm/msm/msm_fence.h +++ b/drivers/gpu/drm/msm/msm_fence.h @@ -57,8 +57,6 @@ struct msm_fence_context * msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr, const char *name); void msm_fence_context_free(struct msm_fence_context *fctx); -int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence, - ktime_t *timeout, bool interruptible); void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence); struct dma_fence * msm_fence_alloc(struct msm_fence_context *fctx); diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index da3af702a6c8..e0579abda5b9 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -320,6 +320,7 @@ struct msm_gem_submit { struct ww_acquire_ctx ticket; uint32_t seqno; /* Sequence number of the submit on the ring */ struct dma_fence *fence; + int fence_id; /* key into queue->fence_idr */ struct msm_gpu_submitqueue *queue; struct pid *pid; /* submitting process */ bool fault_dumped; /* Limit devcoredump dumping to one per submit */ diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 4f02fa3c78f9..f6f595aae2c5 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -68,7 +68,14 @@ void __msm_gem_submit_destroy(struct kref *kref) container_of(kref, struct msm_gem_submit, ref); unsigned i; + if (submit->fence_id) { + mutex_lock(&submit->queue->lock); + idr_remove(&submit->queue->fence_idr, submit->fence_id); + mutex_unlock(&submit->queue->lock); + } + dma_fence_put(submit->fence); + put_pid(submit->pid); msm_submitqueue_put(submit->queue); @@ -872,6 +879,20 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, goto out; } + /* + * Allocate an id which can be used by WAIT_FENCE ioctl to map back + * to the underlying fence. + */ + mutex_lock(&queue->lock); + submit->fence_id = idr_alloc_cyclic(&queue->fence_idr, + submit->fence, 0, INT_MAX, GFP_KERNEL); + mutex_unlock(&queue->lock); + if (submit->fence_id < 0) { + ret = submit->fence_id = 0; + submit->fence_id = 0; + goto out; + } + if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) { struct sync_file *sync_file = sync_file_create(submit->fence); if (!sync_file) { @@ -886,7 +907,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, msm_gpu_submit(gpu, submit); - args->fence = submit->fence->seqno; + args->fence = submit->fence_id; msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs); msm_process_post_deps(post_deps, args->nr_out_syncobjs, diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 96efcb31e502..579627252540 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -263,6 +263,9 @@ struct msm_gpu_perfcntr { * which set of pgtables do submits jobs associated with the * submitqueue use) * @node: node in the context's list of submitqueues + * @fence_idr: maps fence-id to dma_fence for userspace visible fence + * seqno, protected by submitqueue lock + * @lock: submitqueue lock * @ref: reference count */ struct msm_gpu_submitqueue { @@ -272,6 +275,8 @@ struct msm_gpu_submitqueue { int faults; struct msm_file_private *ctx; struct list_head node; + struct idr fence_idr; + struct mutex lock; struct kref ref; }; diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index 9e9fec61d629..66f8d0fb38b0 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -12,6 +12,8 @@ void msm_submitqueue_destroy(struct kref *kref) struct msm_gpu_submitqueue *queue = container_of(kref, struct msm_gpu_submitqueue, ref); + idr_destroy(&queue->fence_idr); + msm_file_private_put(queue->ctx); kfree(queue); @@ -89,6 +91,9 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx, if (id) *id = queue->id; + idr_init(&queue->fence_idr); + mutex_init(&queue->lock); + list_add_tail(&queue->node, &ctx->submitqueues); write_unlock(&ctx->queuelock); From patchwork Mon Jul 26 15:00:23 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 76003 Received: from vger.kernel.org ([23.128.96.18]) by www.linuxtv.org with esmtp (Exim 4.92) (envelope-from ) id 1m822U-006ATS-1l; Mon, 26 Jul 2021 14:57:08 +0000 Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234887AbhGZOQe (ORCPT + 1 other); Mon, 26 Jul 2021 10:16:34 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:35572 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235007AbhGZOQ2 (ORCPT ); Mon, 26 Jul 2021 10:16:28 -0400 Received: from mail-pj1-x1029.google.com (mail-pj1-x1029.google.com [IPv6:2607:f8b0:4864:20::1029]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 5C8A0C061760; Mon, 26 Jul 2021 07:56:56 -0700 (PDT) Received: by mail-pj1-x1029.google.com with SMTP id b1-20020a17090a8001b029017700de3903so172676pjn.1; Mon, 26 Jul 2021 07:56:56 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=jHOVb6r3WpAofmlGsmL5mtg0yFx6CL86twSso5VEFMc=; b=nASXoX0u7PbJ5b5yDhy2tDjlhCB1i3pzkZap/gO8wA+EpivKEaTfP6fVxGm1L26jd8 H2Wgrq1Pgnj0OA7zAdt6/U/+OIdSAFZIxSnQrbcEdVPodzQw7YXfJFr1gt42Pl/wK6LO qhfX9UuJRI/bT440gaW+xkftI5+0atNWWYisOJi96rcup/PDRgp1JPTNiBj/TgUfkkYv +Vchb3UV6V0b3dfFscYppZYo4Tq3cbEPzhrYDBtieRl0XtpTaq+oZ5yLr0ylFqHvk+jq q0C1Jn3aLQkImlSog5JcVRSdhA/ANKfmr6RLmw+AePBMI6o6MlkZ01fU9/QV9yucK5jW Wo6g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=jHOVb6r3WpAofmlGsmL5mtg0yFx6CL86twSso5VEFMc=; b=jWFpNiFEqDv/6/JxP7SGTm3OwNjqmWN1A/1Tzk4FsvcEqlrkebYKtAcBroWR1Ftqbe dwYnJNlsZl3//XJ+IQL5ennDqH4H3U/MiH2Mlp0c6yCfvTMSrhXiOL1gWOnewKC8e0FW hz4hNHkllwtQmVoNldIRu+YM8psPL3QkZyzaiUkuUJZ97ZtggpQ8Exvv8yHWaNblNt7Q L5Aya00BEQ5dzCexGDk3JhtNQF02o33qaBSXfb/Yl0NbuojCjAcB3NKikxu6BZY6loMU Hhsrc3tC5G6Q0tZOQ2kzI8ODBnMufPFqcnnpdTiTBziL7aTIy8HxtJe8C3250uVom1av 5DiA== X-Gm-Message-State: AOAM530lAmloksQvDRdfnwKXcLKUjP3vLkh+rgicLZTvzGkS21vgZ8J0 qkwAiKE4CjFkWDeCxjoMKLI= X-Google-Smtp-Source: ABdhPJyU3D09tWWyq5XsRn3NEufDpH+uG/cjmiUcn5bNss01MB3N13+RNI0a0xXny1WftzqenLoAgg== X-Received: by 2002:a17:903:1cf:b029:12a:da08:f8e3 with SMTP id e15-20020a17090301cfb029012ada08f8e3mr14554030plh.15.1627311415760; Mon, 26 Jul 2021 07:56:55 -0700 (PDT) Received: from localhost ([2601:1c0:5200:a6:307:a401:7b76:c6e5]) by smtp.gmail.com with ESMTPSA id g3sm232577pfi.197.2021.07.26.07.56.54 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 26 Jul 2021 07:56:54 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: Rob Clark , =?utf-8?q?Christian_K=C3=B6nig?= , Rob Clark , Sean Paul , David Airlie , Daniel Vetter , Sumit Semwal , linux-arm-msm@vger.kernel.org (open list:DRM DRIVER FOR MSM ADRENO GPU), freedreno@lists.freedesktop.org (open list:DRM DRIVER FOR MSM ADRENO GPU), linux-kernel@vger.kernel.org (open list), linux-media@vger.kernel.org (open list:DMA BUFFER SHARING FRAMEWORK), linaro-mm-sig@lists.linaro.org (moderated list:DMA BUFFER SHARING FRAMEWORK) Subject: [PATCH v2 09/12] drm/msm: Conversion to drm scheduler Date: Mon, 26 Jul 2021 08:00:23 -0700 Message-Id: <20210726150038.2187631-10-robdclark@gmail.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210726150038.2187631-1-robdclark@gmail.com> References: <20210726150038.2187631-1-robdclark@gmail.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-media@vger.kernel.org X-LSpam-Score: -2.5 (--) X-LSpam-Report: No, score=-2.5 required=5.0 tests=BAYES_00=-1.9,DKIM_SIGNED=0.1,DKIM_VALID=-0.1,DKIM_VALID_AU=-0.1,FREEMAIL_FORGED_FROMDOMAIN=0.001,FREEMAIL_FROM=0.001,HEADER_FROM_DIFFERENT_DOMAINS=0.5,MAILING_LIST_MULTI=-1,RCVD_IN_DNSWL_NONE=-0.0001 autolearn=ham autolearn_force=no From: Rob Clark For existing adrenos, there is one or more ringbuffer, depending on whether preemption is supported. When preemption is supported, each ringbuffer has it's own priority. A submitqueue (which maps to a gl context or vk queue in userspace) is mapped to a specific ring- buffer at creation time, based on the submitqueue's priority. Each ringbuffer has it's own drm_gpu_scheduler. Each submitqueue maps to a drm_sched_entity. And each submit maps to a drm_sched_job. Closes: https://gitlab.freedesktop.org/drm/msm/-/issues/4 Signed-off-by: Rob Clark Acked-by: Christian König --- drivers/gpu/drm/msm/Kconfig | 1 + drivers/gpu/drm/msm/msm_gem.c | 35 ------ drivers/gpu/drm/msm/msm_gem.h | 26 ++++- drivers/gpu/drm/msm/msm_gem_submit.c | 161 +++++++++++++------------- drivers/gpu/drm/msm/msm_gpu.c | 13 +-- drivers/gpu/drm/msm/msm_gpu.h | 2 + drivers/gpu/drm/msm/msm_rd.c | 6 +- drivers/gpu/drm/msm/msm_ringbuffer.c | 66 +++++++++++ drivers/gpu/drm/msm/msm_ringbuffer.h | 12 ++ drivers/gpu/drm/msm/msm_submitqueue.c | 26 +++++ 10 files changed, 217 insertions(+), 131 deletions(-) diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 10f693ea89d3..896266267ad7 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -12,6 +12,7 @@ config DRM_MSM select REGULATOR select DRM_KMS_HELPER select DRM_PANEL + select DRM_SCHED select SHMEM select TMPFS select QCOM_SCM if ARCH_QCOM diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 00a6289678dd..41a111c49cc7 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -806,41 +806,6 @@ void msm_gem_vunmap(struct drm_gem_object *obj) msm_obj->vaddr = NULL; } -/* must be called before _move_to_active().. */ -int msm_gem_sync_object(struct drm_gem_object *obj, - struct msm_fence_context *fctx, bool exclusive) -{ - struct dma_resv_list *fobj; - struct dma_fence *fence; - int i, ret; - - fobj = dma_resv_get_list(obj->resv); - if (!fobj || (fobj->shared_count == 0)) { - fence = dma_resv_get_excl(obj->resv); - /* don't need to wait on our own fences, since ring is fifo */ - if (fence && (fence->context != fctx->context)) { - ret = dma_fence_wait(fence, true); - if (ret) - return ret; - } - } - - if (!exclusive || !fobj) - return 0; - - for (i = 0; i < fobj->shared_count; i++) { - fence = rcu_dereference_protected(fobj->shared[i], - dma_resv_held(obj->resv)); - if (fence->context != fctx->context) { - ret = dma_fence_wait(fence, true); - if (ret) - return ret; - } - } - - return 0; -} - void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu) { struct msm_gem_object *msm_obj = to_msm_bo(obj); diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index e0579abda5b9..a48114058ff9 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -9,6 +9,7 @@ #include #include +#include "drm/gpu_scheduler.h" #include "msm_drv.h" /* Make all GEM related WARN_ON()s ratelimited.. when things go wrong they @@ -143,8 +144,6 @@ void *msm_gem_get_vaddr_active(struct drm_gem_object *obj); void msm_gem_put_vaddr_locked(struct drm_gem_object *obj); void msm_gem_put_vaddr(struct drm_gem_object *obj); int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv); -int msm_gem_sync_object(struct drm_gem_object *obj, - struct msm_fence_context *fctx, bool exclusive); void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu); void msm_gem_active_put(struct drm_gem_object *obj); int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout); @@ -311,6 +310,7 @@ void msm_gem_vunmap(struct drm_gem_object *obj); * make it easier to unwind when things go wrong, etc). */ struct msm_gem_submit { + struct drm_sched_job base; struct kref ref; struct drm_device *dev; struct msm_gpu *gpu; @@ -319,7 +319,22 @@ struct msm_gem_submit { struct list_head bo_list; struct ww_acquire_ctx ticket; uint32_t seqno; /* Sequence number of the submit on the ring */ - struct dma_fence *fence; + + /* Array of struct dma_fence * to block on before submitting this job. + */ + struct xarray deps; + unsigned long last_dep; + + /* Hw fence, which is created when the scheduler executes the job, and + * is signaled when the hw finishes (via seqno write from cmdstream) + */ + struct dma_fence *hw_fence; + + /* Userspace visible fence, which is signaled by the scheduler after + * the hw_fence is signaled. + */ + struct dma_fence *user_fence; + int fence_id; /* key into queue->fence_idr */ struct msm_gpu_submitqueue *queue; struct pid *pid; /* submitting process */ @@ -350,6 +365,11 @@ struct msm_gem_submit { } bos[]; }; +static inline struct msm_gem_submit *to_msm_submit(struct drm_sched_job *job) +{ + return container_of(job, struct msm_gem_submit, base); +} + void __msm_gem_submit_destroy(struct kref *kref); static inline void msm_gem_submit_get(struct msm_gem_submit *submit) diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index f570155bc086..2b158433a6e5 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -33,6 +33,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, { struct msm_gem_submit *submit; uint64_t sz; + int ret; sz = struct_size(submit, bos, nr_bos) + ((u64)nr_cmds * sizeof(submit->cmd[0])); @@ -44,6 +45,14 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, if (!submit) return ERR_PTR(-ENOMEM); + ret = drm_sched_job_init(&submit->base, &queue->entity, queue); + if (ret) { + kfree(submit); + return ERR_PTR(ret); + } + + xa_init_flags(&submit->deps, XA_FLAGS_ALLOC); + kref_init(&submit->ref); submit->dev = dev; submit->aspace = queue->ctx->aspace; @@ -63,6 +72,8 @@ void __msm_gem_submit_destroy(struct kref *kref) { struct msm_gem_submit *submit = container_of(kref, struct msm_gem_submit, ref); + unsigned long index; + struct dma_fence *fence; unsigned i; if (submit->fence_id) { @@ -71,7 +82,14 @@ void __msm_gem_submit_destroy(struct kref *kref) mutex_unlock(&submit->queue->lock); } - dma_fence_put(submit->fence); + xa_for_each (&submit->deps, index, fence) { + dma_fence_put(fence); + } + + xa_destroy(&submit->deps); + + dma_fence_put(submit->user_fence); + dma_fence_put(submit->hw_fence); put_pid(submit->pid); msm_submitqueue_put(submit->queue); @@ -307,7 +325,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit) int i, ret = 0; for (i = 0; i < submit->nr_bos; i++) { - struct msm_gem_object *msm_obj = submit->bos[i].obj; + struct drm_gem_object *obj = &submit->bos[i].obj->base; bool write = submit->bos[i].flags & MSM_SUBMIT_BO_WRITE; if (!write) { @@ -316,8 +334,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit) * strange place to call it. OTOH this is a * convenient can-fail point to hook it in. */ - ret = dma_resv_reserve_shared(msm_obj->base.resv, - 1); + ret = dma_resv_reserve_shared(obj->resv, 1); if (ret) return ret; } @@ -325,7 +342,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit) if (no_implicit) continue; - ret = msm_gem_sync_object(&msm_obj->base, submit->ring->fctx, + ret = drm_gem_fence_array_add_implicit(&submit->deps, obj, write); if (ret) break; @@ -376,9 +393,9 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit) struct drm_gem_object *obj = &submit->bos[i].obj->base; if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE) - dma_resv_add_excl_fence(obj->resv, submit->fence); + dma_resv_add_excl_fence(obj->resv, submit->user_fence); else if (submit->bos[i].flags & MSM_SUBMIT_BO_READ) - dma_resv_add_shared_fence(obj->resv, submit->fence); + dma_resv_add_shared_fence(obj->resv, submit->user_fence); } } @@ -517,12 +534,12 @@ struct msm_submit_post_dep { struct dma_fence_chain *chain; }; -static struct drm_syncobj **msm_wait_deps(struct drm_device *dev, - struct drm_file *file, - uint64_t in_syncobjs_addr, - uint32_t nr_in_syncobjs, - size_t syncobj_stride, - struct msm_ringbuffer *ring) +static struct drm_syncobj **msm_parse_deps(struct msm_gem_submit *submit, + struct drm_file *file, + uint64_t in_syncobjs_addr, + uint32_t nr_in_syncobjs, + size_t syncobj_stride, + struct msm_ringbuffer *ring) { struct drm_syncobj **syncobjs = NULL; struct drm_msm_gem_submit_syncobj syncobj_desc = {0}; @@ -546,7 +563,7 @@ static struct drm_syncobj **msm_wait_deps(struct drm_device *dev, } if (syncobj_desc.point && - !drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) { + !drm_core_check_feature(submit->dev, DRIVER_SYNCOBJ_TIMELINE)) { ret = -EOPNOTSUPP; break; } @@ -561,10 +578,7 @@ static struct drm_syncobj **msm_wait_deps(struct drm_device *dev, if (ret) break; - if (!dma_fence_match_context(fence, ring->fctx->context)) - ret = dma_fence_wait(fence, true); - - dma_fence_put(fence); + ret = drm_gem_fence_array_add(&submit->deps, fence); if (ret) break; @@ -741,47 +755,6 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, trace_msm_gpu_submit(pid_nr(pid), ring->id, submitid, args->nr_bos, args->nr_cmds); - if (args->flags & MSM_SUBMIT_FENCE_FD_IN) { - struct dma_fence *in_fence; - - in_fence = sync_file_get_fence(args->fence_fd); - - if (!in_fence) - return -EINVAL; - - /* - * Wait if the fence is from a foreign context, or if the fence - * array contains any fence from a foreign context. - */ - ret = 0; - if (!dma_fence_match_context(in_fence, ring->fctx->context)) - ret = dma_fence_wait(in_fence, true); - - dma_fence_put(in_fence); - if (ret) - return ret; - } - - if (args->flags & MSM_SUBMIT_SYNCOBJ_IN) { - syncobjs_to_reset = msm_wait_deps(dev, file, - args->in_syncobjs, - args->nr_in_syncobjs, - args->syncobj_stride, ring); - if (IS_ERR(syncobjs_to_reset)) - return PTR_ERR(syncobjs_to_reset); - } - - if (args->flags & MSM_SUBMIT_SYNCOBJ_OUT) { - post_deps = msm_parse_post_deps(dev, file, - args->out_syncobjs, - args->nr_out_syncobjs, - args->syncobj_stride); - if (IS_ERR(post_deps)) { - ret = PTR_ERR(post_deps); - goto out_post_unlock; - } - } - ret = mutex_lock_interruptible(&dev->struct_mutex); if (ret) goto out_post_unlock; @@ -807,22 +780,50 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (args->flags & MSM_SUBMIT_SUDO) submit->in_rb = true; + if (args->flags & MSM_SUBMIT_FENCE_FD_IN) { + struct dma_fence *in_fence; + + in_fence = sync_file_get_fence(args->fence_fd); + + if (!in_fence) { + ret = -EINVAL; + goto out_unlock; + } + + ret = drm_gem_fence_array_add(&submit->deps, in_fence); + if (ret) + goto out_unlock; + } + + if (args->flags & MSM_SUBMIT_SYNCOBJ_IN) { + syncobjs_to_reset = msm_parse_deps(submit, file, + args->in_syncobjs, + args->nr_in_syncobjs, + args->syncobj_stride, ring); + if (IS_ERR(syncobjs_to_reset)) { + ret = PTR_ERR(syncobjs_to_reset); + goto out_unlock; + } + } + + if (args->flags & MSM_SUBMIT_SYNCOBJ_OUT) { + post_deps = msm_parse_post_deps(dev, file, + args->out_syncobjs, + args->nr_out_syncobjs, + args->syncobj_stride); + if (IS_ERR(post_deps)) { + ret = PTR_ERR(post_deps); + goto out_unlock; + } + } + ret = submit_lookup_objects(submit, args, file); if (ret) - goto out_pre_pm; + goto out; ret = submit_lookup_cmds(submit, args, file); if (ret) - goto out_pre_pm; - - /* - * Thanks to dev_pm_opp opp_table_lock interactions with mm->mmap_sem - * in the resume path, we need to to rpm get before we lock objs. - * Which unfortunately might involve powering up the GPU sooner than - * is necessary. But at least in the explicit fencing case, we will - * have already done all the fence waiting. - */ - pm_runtime_get_sync(&gpu->pdev->dev); + goto out; /* copy_*_user while holding a ww ticket upsets lockdep */ ww_acquire_init(&submit->ticket, &reservation_ww_class); @@ -869,12 +870,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, submit->nr_cmds = i; - submit->fence = msm_fence_alloc(ring->fctx); - if (IS_ERR(submit->fence)) { - ret = PTR_ERR(submit->fence); - submit->fence = NULL; - goto out; - } + submit->user_fence = dma_fence_get(&submit->base.s_fence->finished); /* * Allocate an id which can be used by WAIT_FENCE ioctl to map back @@ -882,7 +878,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, */ mutex_lock(&queue->lock); submit->fence_id = idr_alloc_cyclic(&queue->fence_idr, - submit->fence, 0, INT_MAX, GFP_KERNEL); + submit->user_fence, 0, INT_MAX, GFP_KERNEL); mutex_unlock(&queue->lock); if (submit->fence_id < 0) { ret = submit->fence_id = 0; @@ -891,7 +887,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, } if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) { - struct sync_file *sync_file = sync_file_create(submit->fence); + struct sync_file *sync_file = sync_file_create(submit->user_fence); if (!sync_file) { ret = -ENOMEM; goto out; @@ -902,18 +898,19 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, submit_attach_object_fences(submit); - msm_gpu_submit(gpu, submit); + /* The scheduler owns a ref now: */ + msm_gem_submit_get(submit); + + drm_sched_entity_push_job(&submit->base, &queue->entity); args->fence = submit->fence_id; msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs); msm_process_post_deps(post_deps, args->nr_out_syncobjs, - submit->fence); + submit->user_fence); out: - pm_runtime_put(&gpu->pdev->dev); -out_pre_pm: submit_cleanup(submit, !!ret); if (has_ww_ticket) ww_acquire_fini(&submit->ticket); diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 5bfc4d24a956..8a3a592da3a4 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -176,8 +176,8 @@ static void update_fences(struct msm_gpu *gpu, struct msm_ringbuffer *ring, break; msm_update_fence(submit->ring->fctx, - submit->fence->seqno); - dma_fence_signal(submit->fence); + submit->hw_fence->seqno); + dma_fence_signal(submit->hw_fence); } spin_unlock_irqrestore(&ring->submit_lock, flags); } @@ -380,10 +380,6 @@ static void recover_worker(struct kthread_work *work) put_task_struct(task); } - /* msm_rd_dump_submit() needs bo locked to dump: */ - for (i = 0; i < submit->nr_bos; i++) - msm_gem_lock(&submit->bos[i].obj->base); - if (comm && cmd) { DRM_DEV_ERROR(dev->dev, "%s: offending task: %s (%s)\n", gpu->name, comm, cmd); @@ -393,9 +389,6 @@ static void recover_worker(struct kthread_work *work) } else { msm_rd_dump_submit(priv->hangrd, submit, NULL); } - - for (i = 0; i < submit->nr_bos; i++) - msm_gem_unlock(&submit->bos[i].obj->base); } /* Record the crash state */ @@ -704,7 +697,7 @@ static void retire_submits(struct msm_gpu *gpu) * been signalled, then later submits are not signalled * either, so we are also done. */ - if (submit && dma_fence_is_signaled(submit->fence)) { + if (submit && dma_fence_is_signaled(submit->hw_fence)) { retire_submit(gpu, ring, submit); } else { break; diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 579627252540..b912cacaecc0 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -267,6 +267,7 @@ struct msm_gpu_perfcntr { * seqno, protected by submitqueue lock * @lock: submitqueue lock * @ref: reference count + * @entity: the submit job-queue */ struct msm_gpu_submitqueue { int id; @@ -278,6 +279,7 @@ struct msm_gpu_submitqueue { struct idr fence_idr; struct mutex lock; struct kref ref; + struct drm_sched_entity entity; }; struct msm_gpu_state_bo { diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c index 659e5cc4b40a..b55398a34fa4 100644 --- a/drivers/gpu/drm/msm/msm_rd.c +++ b/drivers/gpu/drm/msm/msm_rd.c @@ -325,15 +325,19 @@ static void snapshot_buf(struct msm_rd_state *rd, if (!(submit->bos[idx].flags & MSM_SUBMIT_BO_READ)) return; + msm_gem_lock(&obj->base); buf = msm_gem_get_vaddr_active(&obj->base); if (IS_ERR(buf)) - return; + goto out_unlock; buf += offset; rd_write_section(rd, RD_BUFFER_CONTENTS, buf, size); msm_gem_put_vaddr_locked(&obj->base); + +out_unlock: + msm_gem_unlock(&obj->base); } /* called under struct_mutex */ diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 437cca57d005..5643f579ac46 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -7,10 +7,64 @@ #include "msm_ringbuffer.h" #include "msm_gpu.h" +/** + * The max # of jobs to write into the hw ringbuffer. + */ +static uint num_hw_submissions = 8; +MODULE_PARM_DESC(num_hw_submissions, "The max number of HW submissions (default 8)"); +module_param(num_hw_submissions, uint, 0600); + +static struct dma_fence *msm_job_dependency(struct drm_sched_job *job, + struct drm_sched_entity *s_entity) +{ + struct msm_gem_submit *submit = to_msm_submit(job); + + if (!xa_empty(&submit->deps)) + return xa_erase(&submit->deps, submit->last_dep++); + + return NULL; +} + +static struct dma_fence *msm_job_run(struct drm_sched_job *job) +{ + struct msm_gem_submit *submit = to_msm_submit(job); + struct msm_gpu *gpu = submit->gpu; + + submit->hw_fence = msm_fence_alloc(submit->ring->fctx); + + pm_runtime_get_sync(&gpu->pdev->dev); + + /* TODO move submit path over to using a per-ring lock.. */ + mutex_lock(&gpu->dev->struct_mutex); + + msm_gpu_submit(gpu, submit); + + mutex_unlock(&gpu->dev->struct_mutex); + + pm_runtime_put(&gpu->pdev->dev); + + return dma_fence_get(submit->hw_fence); +} + +static void msm_job_free(struct drm_sched_job *job) +{ + struct msm_gem_submit *submit = to_msm_submit(job); + + drm_sched_job_cleanup(job); + msm_gem_submit_put(submit); +} + +const struct drm_sched_backend_ops msm_sched_ops = { + .dependency = msm_job_dependency, + .run_job = msm_job_run, + .free_job = msm_job_free +}; + struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, void *memptrs, uint64_t memptrs_iova) { struct msm_ringbuffer *ring; + long sched_timeout; char name[32]; int ret; @@ -45,6 +99,16 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, ring->memptrs = memptrs; ring->memptrs_iova = memptrs_iova; + /* currently managing hangcheck ourselves: */ + sched_timeout = MAX_SCHEDULE_TIMEOUT; + + ret = drm_sched_init(&ring->sched, &msm_sched_ops, + num_hw_submissions, 0, sched_timeout, + NULL, to_msm_bo(ring->bo)->name); + if (ret) { + goto fail; + } + INIT_LIST_HEAD(&ring->submits); spin_lock_init(&ring->submit_lock); spin_lock_init(&ring->preempt_lock); @@ -65,6 +129,8 @@ void msm_ringbuffer_destroy(struct msm_ringbuffer *ring) if (IS_ERR_OR_NULL(ring)) return; + drm_sched_fini(&ring->sched); + msm_fence_context_free(ring->fctx); msm_gem_kernel_put(ring->bo, ring->gpu->aspace); diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h index fe55d4a1aa16..d8c63df4e9ca 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.h +++ b/drivers/gpu/drm/msm/msm_ringbuffer.h @@ -7,6 +7,7 @@ #ifndef __MSM_RINGBUFFER_H__ #define __MSM_RINGBUFFER_H__ +#include "drm/gpu_scheduler.h" #include "msm_drv.h" #define rbmemptr(ring, member) \ @@ -40,8 +41,19 @@ struct msm_ringbuffer { struct drm_gem_object *bo; uint32_t *start, *end, *cur, *next; + /* + * The job scheduler for this ring. + */ + struct drm_gpu_scheduler sched; + /* * List of in-flight submits on this ring. Protected by submit_lock. + * + * Currently just submits that are already written into the ring, not + * submits that are still in drm_gpu_scheduler's queues. At a later + * step we could probably move to letting drm_gpu_scheduler manage + * hangcheck detection and keep track of submit jobs that are in- + * flight. */ struct list_head submits; spinlock_t submit_lock; diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index 66f8d0fb38b0..682ba2a7c0ec 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -14,6 +14,8 @@ void msm_submitqueue_destroy(struct kref *kref) idr_destroy(&queue->fence_idr); + drm_sched_entity_destroy(&queue->entity); + msm_file_private_put(queue->ctx); kfree(queue); @@ -64,6 +66,9 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx, { struct msm_drm_private *priv = drm->dev_private; struct msm_gpu_submitqueue *queue; + struct msm_ringbuffer *ring; + struct drm_gpu_scheduler *sched; + int ret; if (!ctx) return -ENODEV; @@ -83,6 +88,27 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx, queue->flags = flags; queue->prio = prio; + ring = priv->gpu->rb[prio]; + sched = &ring->sched; + + /* + * TODO we can allow more priorities than we have ringbuffers by + * mapping: + * + * ring = prio / 3; + * ent_prio = DRM_SCHED_PRIORITY_MIN + (prio % 3); + * + * Probably avoid using DRM_SCHED_PRIORITY_KERNEL as that is + * treated specially in places. + */ + ret = drm_sched_entity_init(&queue->entity, + DRM_SCHED_PRIORITY_NORMAL, + &sched, 1, NULL); + if (ret) { + kfree(queue); + return ret; + } + write_lock(&ctx->queuelock); queue->ctx = msm_file_private_get(ctx);