From patchwork Wed Jul 9 12:29:42 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Maarten Lankhorst X-Patchwork-Id: 4515031 Return-Path: X-Original-To: patchwork-dri-devel@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.19.201]) by patchwork1.web.kernel.org (Postfix) with ESMTP id D2F659F1C4 for ; Wed, 9 Jul 2014 12:29:50 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 00EAA2015E for ; Wed, 9 Jul 2014 12:29:49 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) by mail.kernel.org (Postfix) with ESMTP id 07D8420357 for ; Wed, 9 Jul 2014 12:29:47 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 2D1866E674; Wed, 9 Jul 2014 05:29:46 -0700 (PDT) X-Original-To: dri-devel@lists.freedesktop.org Delivered-To: dri-devel@lists.freedesktop.org Received: from adelie.canonical.com (adelie.canonical.com [91.189.90.139]) by gabe.freedesktop.org (Postfix) with ESMTP id C48E96E674 for ; Wed, 9 Jul 2014 05:29:43 -0700 (PDT) Received: from lillypilly.canonical.com ([91.189.89.62]) by adelie.canonical.com with esmtp (Exim 4.71 #1 (Debian)) id 1X4r0J-0004Sd-1U; Wed, 09 Jul 2014 12:29:43 +0000 Received: by lillypilly.canonical.com (Postfix, from userid 3489) id 06FB026C297D; Wed, 9 Jul 2014 12:29:43 +0000 (UTC) Subject: [PATCH 07/17] drm/nouveau: rework to new fence interface To: airlied@linux.ie From: Maarten Lankhorst Date: Wed, 09 Jul 2014 14:29:42 +0200 Message-ID: <20140709122942.11354.32255.stgit@patser> In-Reply-To: <20140709093124.11354.3774.stgit@patser> References: <20140709093124.11354.3774.stgit@patser> User-Agent: StGit/0.15 MIME-Version: 1.0 Cc: thellstrom@vmware.com, nouveau@lists.freedesktop.org, linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org, bskeggs@redhat.com, alexander.deucher@amd.com, christian.koenig@amd.com X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" X-Spam-Status: No, score=-4.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_MED, RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Maarten Lankhorst Signed-off-by: Maarten Lankhorst --- drivers/gpu/drm/nouveau/core/core/event.c | 4 drivers/gpu/drm/nouveau/nouveau_bo.c | 6 drivers/gpu/drm/nouveau/nouveau_display.c | 4 drivers/gpu/drm/nouveau/nouveau_fence.c | 435 ++++++++++++++++++++--------- drivers/gpu/drm/nouveau/nouveau_fence.h | 20 + drivers/gpu/drm/nouveau/nouveau_gem.c | 17 - drivers/gpu/drm/nouveau/nv04_fence.c | 4 drivers/gpu/drm/nouveau/nv10_fence.c | 4 drivers/gpu/drm/nouveau/nv17_fence.c | 2 drivers/gpu/drm/nouveau/nv50_fence.c | 2 drivers/gpu/drm/nouveau/nv84_fence.c | 11 - 11 files changed, 330 insertions(+), 179 deletions(-) diff --git a/drivers/gpu/drm/nouveau/core/core/event.c b/drivers/gpu/drm/nouveau/core/core/event.c index ae81d3b5d8b7..5ddc28ec7660 100644 --- a/drivers/gpu/drm/nouveau/core/core/event.c +++ b/drivers/gpu/drm/nouveau/core/core/event.c @@ -139,14 +139,14 @@ nouveau_event_ref(struct nouveau_eventh *handler, struct nouveau_eventh **ref) void nouveau_event_trigger(struct nouveau_event *event, u32 types, int index) { - struct nouveau_eventh *handler; + struct nouveau_eventh *handler, *next; unsigned long flags; if (WARN_ON(index >= event->index_nr)) return; spin_lock_irqsave(&event->list_lock, flags); - list_for_each_entry(handler, &event->list[index], head) { + list_for_each_entry_safe(handler, next, &event->list[index], head) { if (!test_bit(NVKM_EVENT_ENABLE, &handler->flags)) continue; if (!(handler->types & types)) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index e98af2e9a1cb..84aba3fa1bd0 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -959,7 +959,7 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr, } mutex_lock_nested(&chan->cli->mutex, SINGLE_DEPTH_NESTING); - ret = nouveau_fence_sync(bo->sync_obj, chan); + ret = nouveau_fence_sync(nouveau_bo(bo), chan); if (ret == 0) { ret = drm->ttm.move(chan, bo, &bo->mem, new_mem); if (ret == 0) { @@ -1432,10 +1432,12 @@ nouveau_bo_fence_unref(void **sync_obj) void nouveau_bo_fence(struct nouveau_bo *nvbo, struct nouveau_fence *fence) { - lockdep_assert_held(&nvbo->bo.resv->lock.base); + struct reservation_object *resv = nvbo->bo.resv; nouveau_bo_fence_unref(&nvbo->bo.sync_obj); nvbo->bo.sync_obj = nouveau_fence_ref(fence); + + reservation_object_add_excl_fence(resv, &fence->base); } static void * diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 7928f8f07334..2c4798750b20 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -660,7 +660,7 @@ nouveau_page_flip_emit(struct nouveau_channel *chan, spin_unlock_irqrestore(&dev->event_lock, flags); /* Synchronize with the old framebuffer */ - ret = nouveau_fence_sync(old_bo->bo.sync_obj, chan); + ret = nouveau_fence_sync(old_bo, chan); if (ret) goto fail; @@ -721,7 +721,7 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, goto fail_unpin; /* synchronise rendering channel with the kernel's channel */ - ret = nouveau_fence_sync(new_bo->bo.sync_obj, chan); + ret = nouveau_fence_sync(new_bo, chan); if (ret) { ttm_bo_unreserve(&new_bo->bo); goto fail_unpin; diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index ab5ea3b0d666..d24f8ce4341a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -32,91 +32,139 @@ #include "nouveau_drm.h" #include "nouveau_dma.h" #include "nouveau_fence.h" +#include #include -struct fence_work { - struct work_struct base; - struct list_head head; - void (*func)(void *); - void *data; -}; +static const struct fence_ops nouveau_fence_ops_uevent; +static const struct fence_ops nouveau_fence_ops_legacy; static void nouveau_fence_signal(struct nouveau_fence *fence) { - struct fence_work *work, *temp; + fence_signal_locked(&fence->base); + list_del(&fence->head); + + if (fence->base.ops == &nouveau_fence_ops_uevent && + fence->event.head.next) { + struct nouveau_event *event; - list_for_each_entry_safe(work, temp, &fence->work, head) { - schedule_work(&work->base); - list_del(&work->head); + list_del(&fence->event.head); + fence->event.head.next = NULL; + + event = container_of(fence->base.lock, typeof(*event), list_lock); + nouveau_event_put(&fence->event); } - fence->channel = NULL; - list_del(&fence->head); + fence_put(&fence->base); +} + +static struct nouveau_fence * +nouveau_local_fence(struct fence *fence, struct nouveau_drm *drm) { + struct nouveau_fence_priv *priv = (void*)drm->fence; + struct nouveau_fence *f = container_of(fence, + struct nouveau_fence, + base); + + if (fence->ops != &nouveau_fence_ops_legacy && + fence->ops != &nouveau_fence_ops_uevent) + return NULL; + + if (fence->context < priv->context_base || + fence->context >= priv->context_base + priv->contexts) + return NULL; + + return f; } void nouveau_fence_context_del(struct nouveau_fence_chan *fctx) { struct nouveau_fence *fence, *fnext; - spin_lock(&fctx->lock); - list_for_each_entry_safe(fence, fnext, &fctx->pending, head) { + + spin_lock_irq(fctx->lock); + list_for_each_entry_safe(fence, fnext, &fctx->pending, head) nouveau_fence_signal(fence); - } - spin_unlock(&fctx->lock); + spin_unlock_irq(fctx->lock); } void -nouveau_fence_context_new(struct nouveau_fence_chan *fctx) +nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_chan *fctx) { + struct nouveau_fifo *pfifo = nouveau_fifo(chan->drm->device); + struct nouveau_fifo_chan *fifo = (void*)chan->object; + + fctx->lock = &pfifo->uevent->list_lock; INIT_LIST_HEAD(&fctx->flip); INIT_LIST_HEAD(&fctx->pending); - spin_lock_init(&fctx->lock); + + snprintf(fctx->name, sizeof(fctx->name) - 1, "nouveau channel %i", fifo->chid); } +struct nouveau_fence_work { + struct work_struct work; + struct fence_cb cb; + void (*func)(void *); + void *data; +}; + static void nouveau_fence_work_handler(struct work_struct *kwork) { - struct fence_work *work = container_of(kwork, typeof(*work), base); + struct nouveau_fence_work *work = container_of(kwork, typeof(*work), work); work->func(work->data); kfree(work); } +static void nouveau_fence_work_cb(struct fence *fence, struct fence_cb *cb) +{ + struct nouveau_fence_work *work = container_of(cb, typeof(*work), cb); + + schedule_work(&work->work); +} + +/* + * In an ideal world, read would not assume the channel context is still alive. + * This function may be called from another device, running into free memory as a + * result. The drm node should still be there, so we can derive the index from + * the fence context. + */ +static bool nouveau_fence_is_signaled(struct fence *f) +{ + struct nouveau_fence *fence = container_of(f, struct nouveau_fence, base); + struct nouveau_channel *chan = fence->channel; + struct nouveau_fence_chan *fctx = chan->fence; + + return (int)(fctx->read(chan) - fence->base.seqno) >= 0; +} + void nouveau_fence_work(struct nouveau_fence *fence, void (*func)(void *), void *data) { - struct nouveau_channel *chan = fence->channel; - struct nouveau_fence_chan *fctx; - struct fence_work *work = NULL; + struct nouveau_fence_work *work; - if (nouveau_fence_done(fence)) { - func(data); - return; - } + if (fence_is_signaled(&fence->base)) + goto err; - fctx = chan->fence; work = kmalloc(sizeof(*work), GFP_KERNEL); if (!work) { WARN_ON(nouveau_fence_wait(fence, false, false)); - func(data); - return; + goto err; } - spin_lock(&fctx->lock); - if (!fence->channel) { - spin_unlock(&fctx->lock); - kfree(work); - func(data); - return; - } - - INIT_WORK(&work->base, nouveau_fence_work_handler); + INIT_WORK(&work->work, nouveau_fence_work_handler); work->func = func; work->data = data; - list_add(&work->head, &fence->work); - spin_unlock(&fctx->lock); + + if (fence_add_callback(&fence->base, &work->cb, nouveau_fence_work_cb) < 0) + goto err_free; + return; + +err_free: + kfree(work); +err: + func(data); } static void @@ -125,33 +173,45 @@ nouveau_fence_update(struct nouveau_channel *chan) struct nouveau_fence_chan *fctx = chan->fence; struct nouveau_fence *fence, *fnext; - spin_lock(&fctx->lock); + u32 seq = fctx->read(chan); + list_for_each_entry_safe(fence, fnext, &fctx->pending, head) { - if (fctx->read(chan) < fence->sequence) + if ((int)(seq - fence->base.seqno) < 0) break; nouveau_fence_signal(fence); - nouveau_fence_unref(&fence); } - spin_unlock(&fctx->lock); } int nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan) { struct nouveau_fence_chan *fctx = chan->fence; + struct nouveau_fifo *pfifo = nouveau_fifo(chan->drm->device); + struct nouveau_fifo_chan *fifo = (void*)chan->object; + struct nouveau_fence_priv *priv = (void*)chan->drm->fence; int ret; fence->channel = chan; fence->timeout = jiffies + (15 * HZ); - fence->sequence = ++fctx->sequence; + if (priv->uevent) + fence_init(&fence->base, &nouveau_fence_ops_uevent, + &pfifo->uevent->list_lock, + priv->context_base + fifo->chid, ++fctx->sequence); + else + fence_init(&fence->base, &nouveau_fence_ops_legacy, + &pfifo->uevent->list_lock, + priv->context_base + fifo->chid, ++fctx->sequence); + + trace_fence_emit(&fence->base); ret = fctx->emit(fence); if (!ret) { - kref_get(&fence->kref); - spin_lock(&fctx->lock); + fence_get(&fence->base); + spin_lock_irq(fctx->lock); + nouveau_fence_update(chan); list_add_tail(&fence->head, &fctx->pending); - spin_unlock(&fctx->lock); + spin_unlock_irq(fctx->lock); } return ret; @@ -160,104 +220,71 @@ nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan) bool nouveau_fence_done(struct nouveau_fence *fence) { - if (fence->channel) + if (fence->base.ops == &nouveau_fence_ops_legacy || + fence->base.ops == &nouveau_fence_ops_uevent) { + struct nouveau_fence_chan *fctx; + unsigned long flags; + + if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->base.flags)) + return true; + + fctx = fence->channel->fence; + spin_lock_irqsave(fctx->lock, flags); nouveau_fence_update(fence->channel); - return !fence->channel; + spin_unlock_irqrestore(fctx->lock, flags); + } + return fence_is_signaled(&fence->base); } -static int -nouveau_fence_wait_uevent_handler(void *data, u32 type, int index) +static long +nouveau_fence_wait_legacy(struct fence *f, bool intr, long wait) { - struct nouveau_fence_priv *priv = data; - wake_up_all(&priv->waiting); - return NVKM_EVENT_KEEP; -} + struct nouveau_fence *fence = container_of(f, typeof(*fence), base); + unsigned long sleep_time = NSEC_PER_MSEC / 1000; + unsigned long t = jiffies, timeout = t + wait; -static int -nouveau_fence_wait_uevent(struct nouveau_fence *fence, bool intr) + while (!nouveau_fence_done(fence)) { + ktime_t kt; -{ - struct nouveau_channel *chan = fence->channel; - struct nouveau_fifo *pfifo = nouveau_fifo(chan->drm->device); - struct nouveau_fence_priv *priv = chan->drm->fence; - struct nouveau_eventh *handler; - int ret = 0; + t = jiffies; - ret = nouveau_event_new(pfifo->uevent, 1, 0, - nouveau_fence_wait_uevent_handler, - priv, &handler); - if (ret) - return ret; + if (wait != MAX_SCHEDULE_TIMEOUT && time_after_eq(t, timeout)) { + __set_current_state(TASK_RUNNING); + return 0; + } - nouveau_event_get(handler); + __set_current_state(intr ? TASK_INTERRUPTIBLE : + TASK_UNINTERRUPTIBLE); - if (fence->timeout) { - unsigned long timeout = fence->timeout - jiffies; - - if (time_before(jiffies, fence->timeout)) { - if (intr) { - ret = wait_event_interruptible_timeout( - priv->waiting, - nouveau_fence_done(fence), - timeout); - } else { - ret = wait_event_timeout(priv->waiting, - nouveau_fence_done(fence), - timeout); - } - } + kt = ktime_set(0, sleep_time); + schedule_hrtimeout(&kt, HRTIMER_MODE_REL); + sleep_time *= 2; + if (sleep_time > NSEC_PER_MSEC) + sleep_time = NSEC_PER_MSEC; - if (ret >= 0) { - fence->timeout = jiffies + ret; - if (time_after_eq(jiffies, fence->timeout)) - ret = -EBUSY; - } - } else { - if (intr) { - ret = wait_event_interruptible(priv->waiting, - nouveau_fence_done(fence)); - } else { - wait_event(priv->waiting, nouveau_fence_done(fence)); - } + if (intr && signal_pending(current)) + return -ERESTARTSYS; } - nouveau_event_ref(NULL, &handler); - if (unlikely(ret < 0)) - return ret; + __set_current_state(TASK_RUNNING); - return 0; + return timeout - t; } -int -nouveau_fence_wait(struct nouveau_fence *fence, bool lazy, bool intr) +static int +nouveau_fence_wait_busy(struct nouveau_fence *fence, bool intr) { - struct nouveau_channel *chan = fence->channel; - struct nouveau_fence_priv *priv = chan ? chan->drm->fence : NULL; - unsigned long sleep_time = NSEC_PER_MSEC / 1000; - ktime_t t; int ret = 0; - while (priv && priv->uevent && lazy && !nouveau_fence_done(fence)) { - ret = nouveau_fence_wait_uevent(fence, intr); - if (ret < 0) - return ret; - } - while (!nouveau_fence_done(fence)) { - if (fence->timeout && time_after_eq(jiffies, fence->timeout)) { + if (time_after_eq(jiffies, fence->timeout)) { ret = -EBUSY; break; } - __set_current_state(intr ? TASK_INTERRUPTIBLE : - TASK_UNINTERRUPTIBLE); - if (lazy) { - t = ktime_set(0, sleep_time); - schedule_hrtimeout(&t, HRTIMER_MODE_REL); - sleep_time *= 2; - if (sleep_time > NSEC_PER_MSEC) - sleep_time = NSEC_PER_MSEC; - } + __set_current_state(intr ? + TASK_INTERRUPTIBLE : + TASK_UNINTERRUPTIBLE); if (intr && signal_pending(current)) { ret = -ERESTARTSYS; @@ -270,36 +297,79 @@ nouveau_fence_wait(struct nouveau_fence *fence, bool lazy, bool intr) } int -nouveau_fence_sync(struct nouveau_fence *fence, struct nouveau_channel *chan) +nouveau_fence_wait(struct nouveau_fence *fence, bool lazy, bool intr) +{ + long ret; + + if (!lazy) + return nouveau_fence_wait_busy(fence, intr); + + ret = fence_wait_timeout(&fence->base, intr, 15 * HZ); + if (ret < 0) + return ret; + else if (!ret) + return -EBUSY; + else + return 0; +} + +int +nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan) { struct nouveau_fence_chan *fctx = chan->fence; - struct nouveau_channel *prev; - int ret = 0; + struct fence *fence = NULL; + struct reservation_object *resv = nvbo->bo.resv; + struct reservation_object_list *fobj; + int ret = 0, i; + + fence = nvbo->bo.sync_obj; + if (fence && fence_is_signaled(fence)) { + nouveau_fence_unref((struct nouveau_fence **) + &nvbo->bo.sync_obj); + fence = NULL; + } + + if (fence) { + struct nouveau_fence *f = container_of(fence, + struct nouveau_fence, + base); + struct nouveau_channel *prev = f->channel; - prev = fence ? fence->channel : NULL; - if (prev) { - if (unlikely(prev != chan && !nouveau_fence_done(fence))) { - ret = fctx->sync(fence, prev, chan); + if (prev != chan) { + ret = fctx->sync(f, prev, chan); if (unlikely(ret)) - ret = nouveau_fence_wait(fence, true, false); + ret = nouveau_fence_wait(f, true, true); } } - return ret; -} + if (ret) + return ret; -static void -nouveau_fence_del(struct kref *kref) -{ - struct nouveau_fence *fence = container_of(kref, typeof(*fence), kref); - kfree(fence); + fence = reservation_object_get_excl(resv); + if (fence && !nouveau_local_fence(fence, chan->drm)) + ret = fence_wait(fence, true); + + fobj = reservation_object_get_list(resv); + if (!fobj || ret) + return ret; + + for (i = 0; i < fobj->shared_count && !ret; ++i) { + fence = rcu_dereference_protected(fobj->shared[i], + reservation_object_held(resv)); + + /* should always be true, for now */ + if (!nouveau_local_fence(fence, chan->drm)) + ret = fence_wait(fence, true); + } + + return ret; } void nouveau_fence_unref(struct nouveau_fence **pfence) { if (*pfence) - kref_put(&(*pfence)->kref, nouveau_fence_del); + fence_put(&(*pfence)->base); *pfence = NULL; } @@ -307,7 +377,7 @@ struct nouveau_fence * nouveau_fence_ref(struct nouveau_fence *fence) { if (fence) - kref_get(&fence->kref); + fence_get(&fence->base); return fence; } @@ -325,9 +395,7 @@ nouveau_fence_new(struct nouveau_channel *chan, bool sysmem, if (!fence) return -ENOMEM; - INIT_LIST_HEAD(&fence->work); fence->sysmem = sysmem; - kref_init(&fence->kref); ret = nouveau_fence_emit(fence, chan); if (ret) @@ -336,3 +404,86 @@ nouveau_fence_new(struct nouveau_channel *chan, bool sysmem, *pfence = fence; return ret; } + + +static bool nouveau_fence_no_signaling(struct fence *f) +{ + /* + * This needs uevents to work correctly, but fence_add_callback relies on + * being able to enable signaling. It will still get signaled eventually, + * just not right away. + */ + if (nouveau_fence_is_signaled(f)) + return false; + + return true; +} + +static const char *nouveau_fence_get_get_driver_name(struct fence *fence) +{ + return "nouveau"; +} + +static const char *nouveau_fence_get_timeline_name(struct fence *f) +{ + struct nouveau_fence *fence = + container_of(f, struct nouveau_fence, base); + struct nouveau_fence_chan *fctx = fence->channel->fence; + + return fctx ? fctx->name : "dead channel"; +} + +static const struct fence_ops nouveau_fence_ops_legacy = { + .get_driver_name = nouveau_fence_get_get_driver_name, + .get_timeline_name = nouveau_fence_get_timeline_name, + .enable_signaling = nouveau_fence_no_signaling, + .signaled = nouveau_fence_is_signaled, + .wait = nouveau_fence_wait_legacy, + .release = NULL +}; + +static int +nouveau_fence_wait_uevent_handler(void *priv, u32 types, int index) +{ + struct nouveau_fence *fence = priv; + + if (nouveau_fence_is_signaled(&fence->base)) + nouveau_fence_signal(fence); + + /* + * NVKM_EVENT_DROP is never appropriate here, nouveau_fence_signal + * will unlink and free the event if needed. + */ + return NVKM_EVENT_KEEP; +} + +static bool nouveau_fence_enable_signaling(struct fence *f) +{ + struct nouveau_fence *fence = container_of(f, struct nouveau_fence, base); + struct nouveau_event *event = container_of(f->lock, struct nouveau_event, list_lock); + struct nouveau_eventh *handler = &fence->event; + + handler->event = event; + handler->func = nouveau_fence_wait_uevent_handler; + handler->priv = fence; + handler->types = 1; + + nouveau_event_get(handler); + if (nouveau_fence_is_signaled(f)) { + nouveau_event_put(handler); + return false; + } + + list_add_tail(&handler->head, &event->list[0]); + + return true; +} + +static const struct fence_ops nouveau_fence_ops_uevent = { + .get_driver_name = nouveau_fence_get_get_driver_name, + .get_timeline_name = nouveau_fence_get_timeline_name, + .enable_signaling = nouveau_fence_enable_signaling, + .signaled = nouveau_fence_is_signaled, + .wait = fence_default_wait, + .release = NULL +}; diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index c57bb61da58c..1989ec22e66e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -1,18 +1,21 @@ #ifndef __NOUVEAU_FENCE_H__ #define __NOUVEAU_FENCE_H__ +#include + struct nouveau_drm; +struct nouveau_bo; struct nouveau_fence { + struct fence base; + struct list_head head; - struct list_head work; - struct kref kref; + struct nouveau_eventh event; bool sysmem; struct nouveau_channel *channel; unsigned long timeout; - u32 sequence; }; int nouveau_fence_new(struct nouveau_channel *, bool sysmem, @@ -25,7 +28,7 @@ int nouveau_fence_emit(struct nouveau_fence *, struct nouveau_channel *); bool nouveau_fence_done(struct nouveau_fence *); void nouveau_fence_work(struct nouveau_fence *, void (*)(void *), void *); int nouveau_fence_wait(struct nouveau_fence *, bool lazy, bool intr); -int nouveau_fence_sync(struct nouveau_fence *, struct nouveau_channel *); +int nouveau_fence_sync(struct nouveau_bo *, struct nouveau_channel *); struct nouveau_fence_chan { struct list_head pending; @@ -38,8 +41,10 @@ struct nouveau_fence_chan { int (*emit32)(struct nouveau_channel *, u64, u32); int (*sync32)(struct nouveau_channel *, u64, u32); - spinlock_t lock; + spinlock_t *lock; u32 sequence; + u32 context; + char name[24]; }; struct nouveau_fence_priv { @@ -49,13 +54,14 @@ struct nouveau_fence_priv { int (*context_new)(struct nouveau_channel *); void (*context_del)(struct nouveau_channel *); - wait_queue_head_t waiting; bool uevent; + + u32 contexts, context_base; }; #define nouveau_fence(drm) ((struct nouveau_fence_priv *)(drm)->fence) -void nouveau_fence_context_new(struct nouveau_fence_chan *); +void nouveau_fence_context_new(struct nouveau_channel *, struct nouveau_fence_chan *); void nouveau_fence_context_del(struct nouveau_fence_chan *); int nv04_fence_create(struct nouveau_drm *); diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 6cd5298cbb53..a61530becfb9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -428,18 +428,6 @@ retry: } static int -validate_sync(struct nouveau_channel *chan, struct nouveau_bo *nvbo) -{ - struct nouveau_fence *fence = nvbo->bo.sync_obj; - int ret = 0; - - if (fence) - ret = nouveau_fence_sync(fence, chan); - - return ret; -} - -static int validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli, struct list_head *list, struct drm_nouveau_gem_pushbuf_bo *pbbo, uint64_t user_pbbo_ptr) @@ -468,9 +456,10 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli, return ret; } - ret = validate_sync(chan, nvbo); + ret = nouveau_fence_sync(nvbo, chan); if (unlikely(ret)) { - NV_ERROR(cli, "fail post-validate sync\n"); + if (ret != -ERESTARTSYS) + NV_ERROR(cli, "fail post-validate sync\n"); return ret; } diff --git a/drivers/gpu/drm/nouveau/nv04_fence.c b/drivers/gpu/drm/nouveau/nv04_fence.c index 94eadd1dd10a..997c54122ed9 100644 --- a/drivers/gpu/drm/nouveau/nv04_fence.c +++ b/drivers/gpu/drm/nouveau/nv04_fence.c @@ -43,7 +43,7 @@ nv04_fence_emit(struct nouveau_fence *fence) int ret = RING_SPACE(chan, 2); if (ret == 0) { BEGIN_NV04(chan, NvSubSw, 0x0150, 1); - OUT_RING (chan, fence->sequence); + OUT_RING (chan, fence->base.seqno); FIRE_RING (chan); } return ret; @@ -77,7 +77,7 @@ nv04_fence_context_new(struct nouveau_channel *chan) { struct nv04_fence_chan *fctx = kzalloc(sizeof(*fctx), GFP_KERNEL); if (fctx) { - nouveau_fence_context_new(&fctx->base); + nouveau_fence_context_new(chan, &fctx->base); fctx->base.emit = nv04_fence_emit; fctx->base.sync = nv04_fence_sync; fctx->base.read = nv04_fence_read; diff --git a/drivers/gpu/drm/nouveau/nv10_fence.c b/drivers/gpu/drm/nouveau/nv10_fence.c index 06f434f03fba..e8f73f7f31ef 100644 --- a/drivers/gpu/drm/nouveau/nv10_fence.c +++ b/drivers/gpu/drm/nouveau/nv10_fence.c @@ -36,7 +36,7 @@ nv10_fence_emit(struct nouveau_fence *fence) int ret = RING_SPACE(chan, 2); if (ret == 0) { BEGIN_NV04(chan, 0, NV10_SUBCHAN_REF_CNT, 1); - OUT_RING (chan, fence->sequence); + OUT_RING (chan, fence->base.seqno); FIRE_RING (chan); } return ret; @@ -74,7 +74,7 @@ nv10_fence_context_new(struct nouveau_channel *chan) if (!fctx) return -ENOMEM; - nouveau_fence_context_new(&fctx->base); + nouveau_fence_context_new(chan, &fctx->base); fctx->base.emit = nv10_fence_emit; fctx->base.read = nv10_fence_read; fctx->base.sync = nv10_fence_sync; diff --git a/drivers/gpu/drm/nouveau/nv17_fence.c b/drivers/gpu/drm/nouveau/nv17_fence.c index 22aa9963ea6f..e404bab31e9d 100644 --- a/drivers/gpu/drm/nouveau/nv17_fence.c +++ b/drivers/gpu/drm/nouveau/nv17_fence.c @@ -83,7 +83,7 @@ nv17_fence_context_new(struct nouveau_channel *chan) if (!fctx) return -ENOMEM; - nouveau_fence_context_new(&fctx->base); + nouveau_fence_context_new(chan, &fctx->base); fctx->base.emit = nv10_fence_emit; fctx->base.read = nv10_fence_read; fctx->base.sync = nv17_fence_sync; diff --git a/drivers/gpu/drm/nouveau/nv50_fence.c b/drivers/gpu/drm/nouveau/nv50_fence.c index 0ee363840035..19f6fccb84a1 100644 --- a/drivers/gpu/drm/nouveau/nv50_fence.c +++ b/drivers/gpu/drm/nouveau/nv50_fence.c @@ -47,7 +47,7 @@ nv50_fence_context_new(struct nouveau_channel *chan) if (!fctx) return -ENOMEM; - nouveau_fence_context_new(&fctx->base); + nouveau_fence_context_new(chan, &fctx->base); fctx->base.emit = nv10_fence_emit; fctx->base.read = nv10_fence_read; fctx->base.sync = nv17_fence_sync; diff --git a/drivers/gpu/drm/nouveau/nv84_fence.c b/drivers/gpu/drm/nouveau/nv84_fence.c index 9fd475c89820..8a06727b23d1 100644 --- a/drivers/gpu/drm/nouveau/nv84_fence.c +++ b/drivers/gpu/drm/nouveau/nv84_fence.c @@ -89,7 +89,7 @@ nv84_fence_emit(struct nouveau_fence *fence) else addr += fctx->vma.offset; - return fctx->base.emit32(chan, addr, fence->sequence); + return fctx->base.emit32(chan, addr, fence->base.seqno); } static int @@ -105,7 +105,7 @@ nv84_fence_sync(struct nouveau_fence *fence, else addr += fctx->vma.offset; - return fctx->base.sync32(chan, addr, fence->sequence); + return fctx->base.sync32(chan, addr, fence->base.seqno); } static u32 @@ -149,12 +149,14 @@ nv84_fence_context_new(struct nouveau_channel *chan) if (!fctx) return -ENOMEM; - nouveau_fence_context_new(&fctx->base); + nouveau_fence_context_new(chan, &fctx->base); fctx->base.emit = nv84_fence_emit; fctx->base.sync = nv84_fence_sync; fctx->base.read = nv84_fence_read; fctx->base.emit32 = nv84_fence_emit32; fctx->base.sync32 = nv84_fence_sync32; + fctx->base.sequence = nv84_fence_read(chan); + fctx->base.context = priv->base.context_base + fifo->chid; ret = nouveau_bo_vma_add(priv->bo, client->vm, &fctx->vma); if (ret == 0) { @@ -239,7 +241,8 @@ nv84_fence_create(struct nouveau_drm *drm) priv->base.context_new = nv84_fence_context_new; priv->base.context_del = nv84_fence_context_del; - init_waitqueue_head(&priv->base.waiting); + priv->base.contexts = pfifo->max + 1; + priv->base.context_base = fence_context_alloc(priv->base.contexts); priv->base.uevent = true; ret = nouveau_bo_new(drm->dev, 16 * (pfifo->max + 1), 0,