From patchwork Mon Jul 26 23:38:48 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 76006 Received: from vger.kernel.org ([23.128.96.18]) by www.linuxtv.org with esmtp (Exim 4.92) (envelope-from ) id 1m8A7X-006nAk-B7; Mon, 26 Jul 2021 23:34:51 +0000 Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233965AbhGZWyV (ORCPT + 1 other); Mon, 26 Jul 2021 18:54:21 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:42606 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233380AbhGZWyU (ORCPT ); Mon, 26 Jul 2021 18:54:20 -0400 Received: from mail-pl1-x634.google.com (mail-pl1-x634.google.com [IPv6:2607:f8b0:4864:20::634]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 81F18C061757; Mon, 26 Jul 2021 16:34:47 -0700 (PDT) Received: by mail-pl1-x634.google.com with SMTP id f13so3114624plj.2; Mon, 26 Jul 2021 16:34:47 -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=Hr8TbT0NY8bhwRPFfOulQoFlLUKAkASJhK+Ly3YzODY=; b=j8LlgSPw1RFIs8exl6aXPn3feuweS/2CJIHKyHEB7xVGXTNTC85mtEg/Uq+42kAlt2 3QjXHcRqxRY2YLBc/jRGnCj71ESXb3kYFw4vm/zBJUYQ8kIHhxPNUw8U5SBxXsPeo0++ +0KYr1u29WW/FfVUqJJhz1n67eMRUY2pPWVlZ2NKZJ4YtMbcgkyjTi++nbRozr3VyCpB /Def4VylyfYnxhrjrlupA1NQ22I3TDfVPJqR6eoJLDGBYyvFR7ANRtd5Gu4fX47qDI8U T6fC5hASr8PoHrvYYtUpfai0fxI/yp8YrtOmOrPcSJnWieo53lWJRaIQyIskGWwapfcy PvRQ== 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=Hr8TbT0NY8bhwRPFfOulQoFlLUKAkASJhK+Ly3YzODY=; b=Z/IHy8zzhnJnBdy4VhEziJVDv9xP90yM0H/JyltnXy/5XNgNi+4AyJqKW5YzRtfUYY /7dlX5SYkV4QgxfwYEhdkV9ZHFJ+hGsjEaPiAlokwREv5UZspghDwNSONQatYMpYtil4 gFB+QJG6zsQdKiUNMMDcYqzJ1Cu8prrDUtK6tyL2ZF3/T9A9DS98D7OhyeHNH5ppgAZ6 zaNxhSe1sHFIOvZqmQyOoFbjl5Pp8XLNy77weHoBtccJ0PJyDrR+HhM9njFfRtHuOi4g vD22o6f0GXwH9FbGnSH3236rRd8ol0Dicy/1sKEg1ARwOxklHyeikBB9PoUkQIGE00Bc tzyQ== X-Gm-Message-State: AOAM530Ua/axOy6z8fNbYcuUI1z8YK3hY+WOh7d75cYtO4h9dnn3zKgL RV3GAmZ4e7KiLq6680cm0ro= X-Google-Smtp-Source: ABdhPJzCJR1KRrhEUmpZNBEL+HoO6bZ9tT6NUdNFHH+pky+Hz4zM8T717wtK0Zidl77XkVjEvdhVFw== X-Received: by 2002:a17:90a:940e:: with SMTP id r14mr1342648pjo.41.1627342487091; Mon, 26 Jul 2021 16:34:47 -0700 (PDT) Received: from localhost ([2601:1c0:5200:a6:307:a401:7b76:c6e5]) by smtp.gmail.com with ESMTPSA id u190sm1212457pfb.95.2021.07.26.16.34.46 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 26 Jul 2021 16:34:46 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: Daniel Vetter , Matthew Brost , =?utf-8?q?Christian_K=C3=B6nig?= , Rob Clark , Sumit Semwal , Gustavo Padovan , =?utf-8?q?Christian_K=C3=B6nig?= , linux-media@vger.kernel.org (open list:SYNC FILE FRAMEWORK), linaro-mm-sig@lists.linaro.org (moderated list:DMA BUFFER SHARING FRAMEWORK), linux-kernel@vger.kernel.org (open list) Subject: [RFC 1/4] dma-fence: Add deadline awareness Date: Mon, 26 Jul 2021 16:38:48 -0700 Message-Id: <20210726233854.2453899-2-robdclark@gmail.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210726233854.2453899-1-robdclark@gmail.com> References: <20210726233854.2453899-1-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 Add a way to hint to the fence signaler of an upcoming deadline, such as vblank, which the fence waiter would prefer not to miss. This is to aid the fence signaler in making power management decisions, like boosting frequency as the deadline approaches and awareness of missing deadlines so that can be factored in to the frequency scaling. Signed-off-by: Rob Clark --- drivers/dma-buf/dma-fence.c | 39 +++++++++++++++++++++++++++++++++++++ include/linux/dma-fence.h | 17 ++++++++++++++++ 2 files changed, 56 insertions(+) diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index ce0f5eff575d..2e0d25ab457e 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -910,6 +910,45 @@ dma_fence_wait_any_timeout(struct dma_fence **fences, uint32_t count, } EXPORT_SYMBOL(dma_fence_wait_any_timeout); + +/** + * dma_fence_set_deadline - set desired fence-wait deadline + * @fence: the fence that is to be waited on + * @deadline: the time by which the waiter hopes for the fence to be + * signaled + * + * Inform the fence signaler of an upcoming deadline, such as vblank, by + * which point the waiter would prefer the fence to be signaled by. This + * is intended to give feedback to the fence signaler to aid in power + * management decisions, such as boosting GPU frequency if a periodic + * vblank deadline is approaching. + */ +void dma_fence_set_deadline(struct dma_fence *fence, ktime_t deadline) +{ + unsigned long flags; + + if (dma_fence_is_signaled(fence)) + return; + + spin_lock_irqsave(fence->lock, flags); + + /* If we already have an earlier deadline, keep it: */ + if (test_bit(DMA_FENCE_FLAG_HAS_DEADLINE_BIT, &fence->flags) && + ktime_before(fence->deadline, deadline)) { + spin_unlock_irqrestore(fence->lock, flags); + return; + } + + fence->deadline = deadline; + set_bit(DMA_FENCE_FLAG_HAS_DEADLINE_BIT, &fence->flags); + + spin_unlock_irqrestore(fence->lock, flags); + + if (fence->ops->set_deadline) + fence->ops->set_deadline(fence, deadline); +} +EXPORT_SYMBOL(dma_fence_set_deadline); + /** * dma_fence_init - Initialize a custom fence. * @fence: the fence to initialize diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 6ffb4b2c6371..4e6cfe4e6fbc 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -88,6 +88,7 @@ struct dma_fence { /* @timestamp replaced by @rcu on dma_fence_release() */ struct rcu_head rcu; }; + ktime_t deadline; u64 context; u64 seqno; unsigned long flags; @@ -99,6 +100,7 @@ enum dma_fence_flag_bits { DMA_FENCE_FLAG_SIGNALED_BIT, DMA_FENCE_FLAG_TIMESTAMP_BIT, DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, + DMA_FENCE_FLAG_HAS_DEADLINE_BIT, DMA_FENCE_FLAG_USER_BITS, /* must always be last member */ }; @@ -261,6 +263,19 @@ struct dma_fence_ops { */ void (*timeline_value_str)(struct dma_fence *fence, char *str, int size); + + /** + * @set_deadline: + * + * Callback to allow a fence waiter to inform the fence signaler of an + * upcoming deadline, such as vblank, by which point the waiter would + * prefer the fence to be signaled by. This is intended to give feedback + * to the fence signaler to aid in power management decisions, such as + * boosting GPU frequency. + * + * This callback is optional. + */ + void (*set_deadline)(struct dma_fence *fence, ktime_t deadline); }; void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, @@ -586,6 +601,8 @@ static inline signed long dma_fence_wait(struct dma_fence *fence, bool intr) return ret < 0 ? ret : 0; } +void dma_fence_set_deadline(struct dma_fence *fence, ktime_t deadline); + struct dma_fence *dma_fence_get_stub(void); struct dma_fence *dma_fence_allocate_private_stub(void); u64 dma_fence_context_alloc(unsigned num); From patchwork Mon Jul 26 23:38:51 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 76007 Received: from vger.kernel.org ([23.128.96.18]) by www.linuxtv.org with esmtp (Exim 4.92) (envelope-from ) id 1m8A7h-006nBE-Pm; Mon, 26 Jul 2021 23:35:02 +0000 Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234077AbhGZWya (ORCPT + 1 other); Mon, 26 Jul 2021 18:54:30 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:42656 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234038AbhGZWy3 (ORCPT ); Mon, 26 Jul 2021 18:54:29 -0400 Received: from mail-pj1-x102a.google.com (mail-pj1-x102a.google.com [IPv6:2607:f8b0:4864:20::102a]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9B5C4C061764; Mon, 26 Jul 2021 16:34:56 -0700 (PDT) Received: by mail-pj1-x102a.google.com with SMTP id g23-20020a17090a5797b02901765d605e14so2297406pji.5; Mon, 26 Jul 2021 16:34:56 -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=oOCwRi9hxpNHgxPfLImA8XjRn0qGzkVI05nd0NTq6uk=; b=UMdDGkO5sH4beFwSPlOOtv6JRzN+gpzELhacSFi7vvaQQ1PwmNbkfYf44YSJQaBLpr vVV0beEQqJV0NuTrh3WVluml5kosYKXPr9U5iyNbGEHEnWPREtu7FUB2q7w+oJTefR1N nxhrxUsL/yhwl8fKcflbrIpY5obQR2TALxuMCayo8c8wDQO0eaI6GFbUCJf3pr8RanC3 lpKxIhzu44oKfzHbedvRslZeVPkbiBMj0MBXvllJzc/2Ok4djmZsXBK3c9DbPUgVz+GT Ad5XrI/AMY80dotYjiTUCM0Zb4DP3NOJpJAs9lA+0Yu8rBP+Sisqs25ugYEbBPneZq4S A5ng== 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=oOCwRi9hxpNHgxPfLImA8XjRn0qGzkVI05nd0NTq6uk=; b=tl3mk+FL7DWE+MK4T0S/V/V9+tJMh9XZCggGxAALBFHnaNQI1VG9Wg9CtTvHohnr0y eAhP/9F+zTaHXOOPB9lFCXZ1orMrzjN/O2BpHVj7oTZ5ViG9SWbPS2BJPMFhUCA6g6a+ oNUCei1LAI34TgzP1o2nfBACdYTK2VeFpl4f5tV1sgTF9pxZytJrZV9a5DV2iSeqn7aF kqlj4mmmLdYmtdEv1eeZeqp2o9T0KpO5yYW6GLf+93TLIVVKO0j0hzkxZjlBTw527yOH J7n8SDulBgyRBJVXI9W3VU8UKsmAda48Z6KK4TOfD6kXT/Y6X3pjOvAvNyOjTArGoirZ 0kBw== X-Gm-Message-State: AOAM533/+5wmoh1jZXTaKB6BM5Si8icp+1ncEbUrgZFk5MVqnjAOorVN XkUwqffkHv1TE5a19JxqYkE= X-Google-Smtp-Source: ABdhPJyKNvvOsVEx6SQdxLRvjXmblFnYyDE+d88dd2vCChknqQFuJLEJg/rykB5kBwIJAy520O/kiQ== X-Received: by 2002:a63:3445:: with SMTP id b66mr20626420pga.141.1627342496218; Mon, 26 Jul 2021 16:34:56 -0700 (PDT) Received: from localhost ([2601:1c0:5200:a6:307:a401:7b76:c6e5]) by smtp.gmail.com with ESMTPSA id t205sm1171971pfc.32.2021.07.26.16.34.54 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 26 Jul 2021 16:34:55 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: Daniel Vetter , Matthew Brost , =?utf-8?q?Christian_K=C3=B6nig?= , Rob Clark , David Airlie , Sumit Semwal , =?utf-8?q?Christian_K=C3=B6nig?= , Alex Deucher , Tian Tao , Luben Tuikov , Andrey Grodzovsky , Alyssa Rosenzweig , Maarten Lankhorst , Jack Zhang , 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: [RFC 4/4] drm/scheduler: Add fence deadline support Date: Mon, 26 Jul 2021 16:38:51 -0700 Message-Id: <20210726233854.2453899-5-robdclark@gmail.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210726233854.2453899-1-robdclark@gmail.com> References: <20210726233854.2453899-1-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 As the finished fence is the one that is exposed to userspace, and therefore the one that other operations, like atomic update, would block on, we need to propagate the deadline from from the finished fence to the actual hw fence. Signed-off-by: Rob Clark --- drivers/gpu/drm/scheduler/sched_fence.c | 10 ++++++++++ drivers/gpu/drm/scheduler/sched_main.c | 3 +++ 2 files changed, 13 insertions(+) diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index 69de2c76731f..3aa6351d2101 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -128,6 +128,15 @@ static void drm_sched_fence_release_finished(struct dma_fence *f) dma_fence_put(&fence->scheduled); } +static void drm_sched_fence_set_deadline_finished(struct dma_fence *f, + ktime_t deadline) +{ + struct drm_sched_fence *fence = to_drm_sched_fence(f); + + if (fence->parent) + dma_fence_set_deadline(fence->parent, deadline); +} + static const struct dma_fence_ops drm_sched_fence_ops_scheduled = { .get_driver_name = drm_sched_fence_get_driver_name, .get_timeline_name = drm_sched_fence_get_timeline_name, @@ -138,6 +147,7 @@ static const struct dma_fence_ops drm_sched_fence_ops_finished = { .get_driver_name = drm_sched_fence_get_driver_name, .get_timeline_name = drm_sched_fence_get_timeline_name, .release = drm_sched_fence_release_finished, + .set_deadline = drm_sched_fence_set_deadline_finished, }; struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f) diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index a2a953693b45..fcc601962e92 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -818,6 +818,9 @@ static int drm_sched_main(void *param) if (!IS_ERR_OR_NULL(fence)) { s_fence->parent = dma_fence_get(fence); + if (test_bit(DMA_FENCE_FLAG_HAS_DEADLINE_BIT, + &s_fence->finished.flags)) + dma_fence_set_deadline(fence, s_fence->finished.deadline); r = dma_fence_add_callback(fence, &sched_job->cb, drm_sched_job_done_cb); if (r == -ENOENT) From patchwork Tue Jul 27 21:17:33 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 76062 Received: from vger.kernel.org ([23.128.96.18]) by www.linuxtv.org with esmtp (Exim 4.92) (envelope-from ) id 1m8UOC-007ywr-NS; Tue, 27 Jul 2021 21:13:25 +0000 Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232066AbhG0VNX (ORCPT + 1 other); Tue, 27 Jul 2021 17:13:23 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57394 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231339AbhG0VNW (ORCPT ); Tue, 27 Jul 2021 17:13:22 -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 6FDB4C061757; Tue, 27 Jul 2021 14:13:21 -0700 (PDT) Received: by mail-pl1-x62a.google.com with SMTP id t21so17570243plr.13; Tue, 27 Jul 2021 14:13:21 -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=6mvxUJ87sudxyMnXk+SNmSJl9hv8ghFMGniXKOiMPtw=; b=tG9WekqbBueWHLkIaofNI4gJul/Ff/LZEIIRon+7eeHH7dxCEXnE8PCmGkTPgTCzVo XtQvndCanVJ0+n1YwrTx2ZRjAXOFT6z0wzixrW5wRmIUVAyndD7jC7gv0zyafFFoB3f6 BtcEZi5j8k2gPE6CGhMf7uHVd6x9baVvFrUpPUTNQkqIioU8QDm4bo4tRogTUtUxw2iQ ZvIgK8fHCbW0kyBozaOHpnklgpB85APCVzst8/8oxtV01jhc7V0EXaXh20jj6B+9cRYp OR4uI+ZdkJvEm9o2vAoD9K3UKsdCr5PmDzBrIfrlw/OFD+civsEkBq6PL3te8JUfpOX+ WgDw== 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=6mvxUJ87sudxyMnXk+SNmSJl9hv8ghFMGniXKOiMPtw=; b=Hw5STqu5A3wlM74bwugx/PrqSbsd9r9w0xQP+IsnirNTqP38q8LMvzcBJOIfbuLOnq fvtKLpvpOZ8V7kIMciA6/TYP/v1IASV+6l0JgTyE1eWYUeN4JCDcEUO+HbcywMBkpB8J 5o8EPdNL9VJjUp2K4QK6lpyzkh4j50pkjTDeEGxv3YOL3SppvZy6XcCTvkg6p3yFBapq /V/ccTlCQSYVsnhvv6yDTYL4D6bpQrZtrqBdaPP0d9LG1jACjtdv9v47VqoMeo1VHlyH oR+ycMK/bJuS1dctzw+9nuG9DtcPJ/la7lLWrTGdbgo2ZW5eUSSLXTQbxQ0M1T2RiAQW uDBQ== X-Gm-Message-State: AOAM5330LTz842xiZkSpCgJA78P/DZzJGPmAqS4PMNzuNyzfQa8VbjfI AAuKDW8FmrRVOJCTqueIcXUgDfvnXYZzNw== X-Google-Smtp-Source: ABdhPJwlu23/8UGfbxmy7j094ac+mE1XH3PWlXuLAcE1QcDyqPajFuwNr8Z0PkkfDL+6yOJEOJ+Y0g== X-Received: by 2002:a17:90a:e558:: with SMTP id ei24mr10926413pjb.97.1627420400775; Tue, 27 Jul 2021 14:13:20 -0700 (PDT) Received: from localhost (c-73-25-156-94.hsd1.or.comcast.net. [73.25.156.94]) by smtp.gmail.com with ESMTPSA id 143sm4922203pfz.13.2021.07.27.14.13.19 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 27 Jul 2021 14:13:19 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: Daniel Vetter , Matthew Brost , =?utf-8?q?Michel_D=C3=A4nzer?= , =?utf-8?q?Christian_K?= =?utf-8?q?=C3=B6nig?= , Rob Clark , Rob Clark , Sean Paul , David Airlie , Sumit Semwal , =?utf-8?q?Christian_K=C3=B6nig?= , 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: [RFC 5/4] drm/msm: Add deadline based boost support Date: Tue, 27 Jul 2021 14:17:33 -0700 Message-Id: <20210727211733.2601469-1-robdclark@gmail.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210726233854.2453899-1-robdclark@gmail.com> References: <20210726233854.2453899-1-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 Signed-off-by: Rob Clark --- This is a quick implementation of what I had in mind for driver side of deadline boost. For a couple games with bad gpu devfreq behavior this boosts "Render quality" from ~35% to ~95%. (The "Render quality" metric in chrome://arc-overview-tracing is basically a measure of the deviation in frame/commit time, so 100% would be a consistent fps with no variantion.) Not quite 100%, this is still a bit of a re- active mechanism. A similar result can be had by tuning devfreq to boost to max OPP at a much lower threshold of busyness. With the obvious downside that you spend a lot of time running the GPU much faster than needed. drivers/gpu/drm/msm/msm_fence.c | 76 +++++++++++++++++++++++++++ drivers/gpu/drm/msm/msm_fence.h | 20 +++++++ drivers/gpu/drm/msm/msm_gpu.h | 1 + drivers/gpu/drm/msm/msm_gpu_devfreq.c | 20 +++++++ 4 files changed, 117 insertions(+) diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c index f2cece542c3f..67c2a96e1c85 100644 --- a/drivers/gpu/drm/msm/msm_fence.c +++ b/drivers/gpu/drm/msm/msm_fence.c @@ -8,6 +8,37 @@ #include "msm_drv.h" #include "msm_fence.h" +#include "msm_gpu.h" + +static inline bool fence_completed(struct msm_fence_context *fctx, uint32_t fence); + +static struct msm_gpu *fctx2gpu(struct msm_fence_context *fctx) +{ + struct msm_drm_private *priv = fctx->dev->dev_private; + return priv->gpu; +} + +static enum hrtimer_restart deadline_timer(struct hrtimer *t) +{ + struct msm_fence_context *fctx = container_of(t, + struct msm_fence_context, deadline_timer); + + kthread_queue_work(fctx2gpu(fctx)->worker, &fctx->deadline_work); + + return HRTIMER_NORESTART; +} + +static void deadline_work(struct kthread_work *work) +{ + struct msm_fence_context *fctx = container_of(work, + struct msm_fence_context, deadline_work); + + /* If deadline fence has already passed, nothing to do: */ + if (fence_completed(fctx, fctx->next_deadline_fence)) + return; + + msm_devfreq_boost(fctx2gpu(fctx), 2); +} struct msm_fence_context * @@ -26,6 +57,13 @@ msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr, fctx->fenceptr = fenceptr; spin_lock_init(&fctx->spinlock); + hrtimer_init(&fctx->deadline_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + fctx->deadline_timer.function = deadline_timer; + + kthread_init_work(&fctx->deadline_work, deadline_work); + + fctx->next_deadline = ktime_get(); + return fctx; } @@ -49,6 +87,8 @@ void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence) { spin_lock(&fctx->spinlock); fctx->completed_fence = max(fence, fctx->completed_fence); + if (fence_completed(fctx, fctx->next_deadline_fence)) + hrtimer_cancel(&fctx->deadline_timer); spin_unlock(&fctx->spinlock); } @@ -79,10 +119,46 @@ static bool msm_fence_signaled(struct dma_fence *fence) return fence_completed(f->fctx, f->base.seqno); } +static void msm_fence_set_deadline(struct dma_fence *fence, ktime_t deadline) +{ + struct msm_fence *f = to_msm_fence(fence); + struct msm_fence_context *fctx = f->fctx; + unsigned long flags; + ktime_t now; + + spin_lock_irqsave(&fctx->spinlock, flags); + now = ktime_get(); + + if (ktime_after(now, fctx->next_deadline) || + ktime_before(deadline, fctx->next_deadline)) { + fctx->next_deadline = deadline; + fctx->next_deadline_fence = + max(fctx->next_deadline_fence, (uint32_t)fence->seqno); + + /* + * Set timer to trigger boost 3ms before deadline, or + * if we are already less than 3ms before the deadline + * schedule boost work immediately. + */ + deadline = ktime_sub(deadline, ms_to_ktime(3)); + + if (ktime_after(now, deadline)) { + kthread_queue_work(fctx2gpu(fctx)->worker, + &fctx->deadline_work); + } else { + hrtimer_start(&fctx->deadline_timer, deadline, + HRTIMER_MODE_ABS); + } + } + + spin_unlock_irqrestore(&fctx->spinlock, flags); +} + static const struct dma_fence_ops msm_fence_ops = { .get_driver_name = msm_fence_get_driver_name, .get_timeline_name = msm_fence_get_timeline_name, .signaled = msm_fence_signaled, + .set_deadline = msm_fence_set_deadline, }; struct dma_fence * diff --git a/drivers/gpu/drm/msm/msm_fence.h b/drivers/gpu/drm/msm/msm_fence.h index 4783db528bcc..d34e853c555a 100644 --- a/drivers/gpu/drm/msm/msm_fence.h +++ b/drivers/gpu/drm/msm/msm_fence.h @@ -50,6 +50,26 @@ struct msm_fence_context { volatile uint32_t *fenceptr; spinlock_t spinlock; + + /* + * TODO this doesn't really deal with multiple deadlines, like + * if userspace got multiple frames ahead.. OTOH atomic updates + * don't queue, so maybe that is ok + */ + + /** next_deadline: Time of next deadline */ + ktime_t next_deadline; + + /** + * next_deadline_fence: + * + * Fence value for next pending deadline. The deadline timer is + * canceled when this fence is signaled. + */ + uint32_t next_deadline_fence; + + struct hrtimer deadline_timer; + struct kthread_work deadline_work; }; struct msm_fence_context * msm_fence_context_alloc(struct drm_device *dev, diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 0e4b45bff2e6..e031c9b495ed 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -425,6 +425,7 @@ void msm_devfreq_init(struct msm_gpu *gpu); void msm_devfreq_cleanup(struct msm_gpu *gpu); void msm_devfreq_resume(struct msm_gpu *gpu); void msm_devfreq_suspend(struct msm_gpu *gpu); +void msm_devfreq_boost(struct msm_gpu *gpu, unsigned factor); void msm_devfreq_active(struct msm_gpu *gpu); void msm_devfreq_idle(struct msm_gpu *gpu); diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c index 0a1ee20296a2..8a8d7b9028a3 100644 --- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c +++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c @@ -144,6 +144,26 @@ void msm_devfreq_suspend(struct msm_gpu *gpu) devfreq_suspend_device(gpu->devfreq.devfreq); } +void msm_devfreq_boost(struct msm_gpu *gpu, unsigned factor) +{ + struct msm_gpu_devfreq *df = &gpu->devfreq; + unsigned long freq; + + /* + * Hold devfreq lock to synchronize with get_dev_status()/ + * target() callbacks + */ + mutex_lock(&df->devfreq->lock); + + freq = get_freq(gpu); + + freq *= factor; + + msm_devfreq_target(&gpu->pdev->dev, &freq, 0); + + mutex_unlock(&df->devfreq->lock); +} + void msm_devfreq_active(struct msm_gpu *gpu) { struct msm_gpu_devfreq *df = &gpu->devfreq;