From: Rob Clark robdclark@chromium.org

Propagate the deadline to all the fences in the chain.

v2: Use dma_fence_chain_contained [Tvrtko]

Signed-off-by: Rob Clark robdclark@chromium.org Reviewed-by: Christian König christian.koenig@amd.com for this one. --- drivers/dma-buf/dma-fence-chain.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)

diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c index a0d920576ba6..9663ba1bb6ac 100644 --- a/drivers/dma-buf/dma-fence-chain.c +++ b/drivers/dma-buf/dma-fence-chain.c @@ -206,6 +206,17 @@ static void dma_fence_chain_release(struct dma_fence *fence) dma_fence_free(fence); }

+ +static void dma_fence_chain_set_deadline(struct dma_fence *fence, + ktime_t deadline) +{ + dma_fence_chain_for_each(fence, fence) { + struct dma_fence *f = dma_fence_chain_contained(fence); + + dma_fence_set_deadline(f, deadline); + } +} + const struct dma_fence_ops dma_fence_chain_ops = { .use_64bit_seqno = true, .get_driver_name = dma_fence_chain_get_driver_name, @@ -213,6 +224,7 @@ const struct dma_fence_ops dma_fence_chain_ops = { .enable_signaling = dma_fence_chain_enable_signaling, .signaled = dma_fence_chain_signaled, .release = dma_fence_chain_release, + .set_deadline = dma_fence_chain_set_deadline, }; EXPORT_SYMBOL(dma_fence_chain_ops);

From: Rob Clark robdclark@chromium.org

We had all of the internal driver APIs, but not the all important userspace uABI, in the dma-buf doc. Fix that. And re-arrange the comments slightly as otherwise the comments for the ioctl nr defines would not show up.

Signed-off-by: Rob Clark robdclark@chromium.org --- Documentation/driver-api/dma-buf.rst | 10 ++++++-- include/uapi/linux/sync_file.h | 35 +++++++++++----------------- 2 files changed, 22 insertions(+), 23 deletions(-)

diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index 183e480d8cea..ff3f8da296af 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -203,8 +203,8 @@ DMA Fence unwrap .. kernel-doc:: include/linux/dma-fence-unwrap.h :internal:

-DMA Fence uABI/Sync File -~~~~~~~~~~~~~~~~~~~~~~~~ +DMA Fence Sync File +~~~~~~~~~~~~~~~~~~~

.. kernel-doc:: drivers/dma-buf/sync_file.c :export: @@ -212,6 +212,12 @@ DMA Fence uABI/Sync File .. kernel-doc:: include/linux/sync_file.h :internal:

+DMA Fence Sync File uABI +~~~~~~~~~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/uapi/linux/sync_file.h + :internal: + Indefinite DMA Fences ~~~~~~~~~~~~~~~~~~~~~

diff --git a/include/uapi/linux/sync_file.h b/include/uapi/linux/sync_file.h index ee2dcfb3d660..eced40c204d7 100644 --- a/include/uapi/linux/sync_file.h +++ b/include/uapi/linux/sync_file.h @@ -16,12 +16,16 @@ #include <linux/types.h>

/** - * struct sync_merge_data - data passed to merge ioctl + * struct sync_merge_data - SYNC_IOC_MERGE: merge two fences * @name: name of new fence * @fd2: file descriptor of second fence * @fence: returns the fd of the new fence to userspace * @flags: merge_data flags * @pad: padding for 64-bit alignment, should always be zero + * + * Creates a new fence containing copies of the sync_pts in both + * the calling fd and sync_merge_data.fd2. Returns the new fence's + * fd in sync_merge_data.fence */ struct sync_merge_data { char name[32]; @@ -34,8 +38,8 @@ struct sync_merge_data { /** * struct sync_fence_info - detailed fence information * @obj_name: name of parent sync_timeline -* @driver_name: name of driver implementing the parent -* @status: status of the fence 0:active 1:signaled <0:error + * @driver_name: name of driver implementing the parent + * @status: status of the fence 0:active 1:signaled <0:error * @flags: fence_info flags * @timestamp_ns: timestamp of status change in nanoseconds */ @@ -48,14 +52,19 @@ struct sync_fence_info { };

/** - * struct sync_file_info - data returned from fence info ioctl + * struct sync_file_info - SYNC_IOC_FILE_INFO: get detailed information on a sync_file * @name: name of fence * @status: status of fence. 1: signaled 0:active <0:error * @flags: sync_file_info flags * @num_fences number of fences in the sync_file * @pad: padding for 64-bit alignment, should always be zero - * @sync_fence_info: pointer to array of structs sync_fence_info with all + * @sync_fence_info: pointer to array of struct &sync_fence_info with all * fences in the sync_file + * + * Takes a struct sync_file_info. If num_fences is 0, the field is updated + * with the actual number of fences. If num_fences is > 0, the system will + * use the pointer provided on sync_fence_info to return up to num_fences of + * struct sync_fence_info, with detailed fence information. */ struct sync_file_info { char name[32]; @@ -76,23 +85,7 @@ struct sync_file_info { * no upstream users available. */

-/** - * DOC: SYNC_IOC_MERGE - merge two fences - * - * Takes a struct sync_merge_data. Creates a new fence containing copies of - * the sync_pts in both the calling fd and sync_merge_data.fd2. Returns the - * new fence's fd in sync_merge_data.fence - */ #define SYNC_IOC_MERGE _IOWR(SYNC_IOC_MAGIC, 3, struct sync_merge_data) - -/** - * DOC: SYNC_IOC_FILE_INFO - get detailed information on a sync_file - * - * Takes a struct sync_file_info. If num_fences is 0, the field is updated - * with the actual number of fences. If num_fences is > 0, the system will - * use the pointer provided on sync_fence_info to return up to num_fences of - * struct sync_fence_info, with detailed fence information. - */ #define SYNC_IOC_FILE_INFO _IOWR(SYNC_IOC_MAGIC, 4, struct sync_file_info)

#endif /* _UAPI_LINUX_SYNC_H */

From: Rob Clark robdclark@chromium.org

The initial purpose is for igt tests, but this would also be useful for compositors that wait until close to vblank deadline to make decisions about which frame to show.

The igt tests can be found at:

https://gitlab.freedesktop.org/robclark/igt-gpu-tools/-/commits/fence-deadli...

v2: Clarify the timebase, add link to igt tests v3: Use u64 value in ns to express deadline. v4: More doc

Signed-off-by: Rob Clark robdclark@chromium.org Acked-by: Pekka Paalanen pekka.paalanen@collabora.com --- drivers/dma-buf/dma-fence.c | 3 ++- drivers/dma-buf/sync_file.c | 19 +++++++++++++++++++ include/uapi/linux/sync_file.h | 22 ++++++++++++++++++++++ 3 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index f177c56269bb..74e36f6d05b0 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -933,7 +933,8 @@ EXPORT_SYMBOL(dma_fence_wait_any_timeout); * the GPU's devfreq to reduce frequency, when in fact the opposite is what is * needed. * - * To this end, deadline hint(s) can be set on a &dma_fence via &dma_fence_set_deadline. + * To this end, deadline hint(s) can be set on a &dma_fence via &dma_fence_set_deadline + * (or indirectly via userspace facing ioctls like &sync_set_deadline). * The deadline hint provides a way for the waiting driver, or userspace, to * convey an appropriate sense of urgency to the signaling driver. * diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index af57799c86ce..418021cfb87c 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -350,6 +350,22 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, return ret; }

+static int sync_file_ioctl_set_deadline(struct sync_file *sync_file, + unsigned long arg) +{ + struct sync_set_deadline ts; + + if (copy_from_user(&ts, (void __user *)arg, sizeof(ts))) + return -EFAULT; + + if (ts.pad) + return -EINVAL; + + dma_fence_set_deadline(sync_file->fence, ns_to_ktime(ts.deadline_ns)); + + return 0; +} + static long sync_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -362,6 +378,9 @@ static long sync_file_ioctl(struct file *file, unsigned int cmd, case SYNC_IOC_FILE_INFO: return sync_file_ioctl_fence_info(sync_file, arg);

+ case SYNC_IOC_SET_DEADLINE: + return sync_file_ioctl_set_deadline(sync_file, arg); + default: return -ENOTTY; } diff --git a/include/uapi/linux/sync_file.h b/include/uapi/linux/sync_file.h index eced40c204d7..594b8bba7948 100644 --- a/include/uapi/linux/sync_file.h +++ b/include/uapi/linux/sync_file.h @@ -76,6 +76,27 @@ struct sync_file_info { __u64 sync_fence_info; };

+/** + * struct sync_set_deadline - SYNC_IOC_SET_DEADLINE - set a deadline hint on a fence + * @deadline_ns: absolute time of the deadline + * @pad: must be zero + * + * Allows userspace to set a deadline on a fence, see &dma_fence_set_deadline + * + * The timebase for the deadline is CLOCK_MONOTONIC (same as vblank). For + * example + * + * clock_gettime(CLOCK_MONOTONIC, &t); + * deadline_ns = (t.tv_sec * 1000000000L) + t.tv_nsec + ns_until_deadline + */ +struct sync_set_deadline { + __u64 deadline_ns; + /* Not strictly needed for alignment but gives some possibility + * for future extension: + */ + __u64 pad; +}; + #define SYNC_IOC_MAGIC '>'

/** @@ -87,5 +108,6 @@ struct sync_file_info {

#define SYNC_IOC_MERGE _IOWR(SYNC_IOC_MAGIC, 3, struct sync_merge_data) #define SYNC_IOC_FILE_INFO _IOWR(SYNC_IOC_MAGIC, 4, struct sync_file_info) +#define SYNC_IOC_SET_DEADLINE _IOW(SYNC_IOC_MAGIC, 5, struct sync_set_deadline)

#endif /* _UAPI_LINUX_SYNC_H */

From: Rob Clark robdclark@chromium.org

This consists of simply storing the most recent deadline, and adding an ioctl to retrieve the deadline. This can be used in conjunction with the SET_DEADLINE ioctl on a fence fd for testing. Ie. create various sw_sync fences, merge them into a fence-array, set deadline on the fence-array and confirm that it is propagated properly to each fence.

v2: Switch UABI to express deadline as u64 v3: More verbose UAPI docs, show how to convert from timespec v4: Better comments, track the soonest deadline, as a normal fence implementation would, return an error if no deadline set.

Signed-off-by: Rob Clark robdclark@chromium.org Reviewed-by: Christian König christian.koenig@amd.com --- drivers/dma-buf/sw_sync.c | 81 ++++++++++++++++++++++++++++++++++++ drivers/dma-buf/sync_debug.h | 2 + 2 files changed, 83 insertions(+)

diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index 348b3a9170fa..f53071bca3af 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -52,12 +52,33 @@ struct sw_sync_create_fence_data { __s32 fence; /* fd of new fence */ };

+/** + * struct sw_sync_get_deadline - get the deadline hint of a sw_sync fence + * @deadline_ns: absolute time of the deadline + * @pad: must be zero + * @fence_fd: the sw_sync fence fd (in) + * + * Return the earliest deadline set on the fence. The timebase for the + * deadline is CLOCK_MONOTONIC (same as vblank). If there is no deadline + * set on the fence, this ioctl will return -ENOENT. + */ +struct sw_sync_get_deadline { + __u64 deadline_ns; + __u32 pad; + __s32 fence_fd; +}; + #define SW_SYNC_IOC_MAGIC 'W'

#define SW_SYNC_IOC_CREATE_FENCE _IOWR(SW_SYNC_IOC_MAGIC, 0,\ struct sw_sync_create_fence_data)

#define SW_SYNC_IOC_INC _IOW(SW_SYNC_IOC_MAGIC, 1, __u32) +#define SW_SYNC_GET_DEADLINE _IOWR(SW_SYNC_IOC_MAGIC, 2, \ + struct sw_sync_get_deadline) + + +#define SW_SYNC_HAS_DEADLINE_BIT DMA_FENCE_FLAG_USER_BITS

static const struct dma_fence_ops timeline_fence_ops;

@@ -171,6 +192,22 @@ static void timeline_fence_timeline_value_str(struct dma_fence *fence, snprintf(str, size, "%d", parent->value); }

+static void timeline_fence_set_deadline(struct dma_fence *fence, ktime_t deadline) +{ + struct sync_pt *pt = dma_fence_to_sync_pt(fence); + unsigned long flags; + + spin_lock_irqsave(fence->lock, flags); + if (test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) { + if (ktime_before(deadline, pt->deadline)) + pt->deadline = deadline; + } else { + pt->deadline = deadline; + set_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags); + } + spin_unlock_irqrestore(fence->lock, flags); +} + static const struct dma_fence_ops timeline_fence_ops = { .get_driver_name = timeline_fence_get_driver_name, .get_timeline_name = timeline_fence_get_timeline_name, @@ -179,6 +216,7 @@ static const struct dma_fence_ops timeline_fence_ops = { .release = timeline_fence_release, .fence_value_str = timeline_fence_value_str, .timeline_value_str = timeline_fence_timeline_value_str, + .set_deadline = timeline_fence_set_deadline, };

/** @@ -387,6 +425,46 @@ static long sw_sync_ioctl_inc(struct sync_timeline *obj, unsigned long arg) return 0; }

+static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long arg) +{ + struct sw_sync_get_deadline data; + struct dma_fence *fence; + struct sync_pt *pt; + int ret = 0; + + if (copy_from_user(&data, (void __user *)arg, sizeof(data))) + return -EFAULT; + + if (data.deadline_ns || data.pad) + return -EINVAL; + + fence = sync_file_get_fence(data.fence_fd); + if (!fence) + return -EINVAL; + + pt = dma_fence_to_sync_pt(fence); + if (!pt) + return -EINVAL; + + spin_lock(fence->lock); + if (test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) { + data.deadline_ns = ktime_to_ns(pt->deadline); + } else { + ret = -ENOENT; + } + spin_unlock(fence->lock); + + dma_fence_put(fence); + + if (ret) + return ret; + + if (copy_to_user((void __user *)arg, &data, sizeof(data))) + return -EFAULT; + + return 0; +} + static long sw_sync_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -399,6 +477,9 @@ static long sw_sync_ioctl(struct file *file, unsigned int cmd, case SW_SYNC_IOC_INC: return sw_sync_ioctl_inc(obj, arg);

+ case SW_SYNC_GET_DEADLINE: + return sw_sync_ioctl_get_deadline(obj, arg); + default: return -ENOTTY; } diff --git a/drivers/dma-buf/sync_debug.h b/drivers/dma-buf/sync_debug.h index 6176e52ba2d7..2e0146d0bdbb 100644 --- a/drivers/dma-buf/sync_debug.h +++ b/drivers/dma-buf/sync_debug.h @@ -55,11 +55,13 @@ static inline struct sync_timeline *dma_fence_parent(struct dma_fence *fence) * @base: base fence object * @link: link on the sync timeline's list * @node: node in the sync timeline's tree + * @deadline: the most recently set fence deadline */ struct sync_pt { struct dma_fence base; struct list_head link; struct rb_node node; + ktime_t deadline; };

extern const struct file_operations sw_sync_debugfs_fops;

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.

v2: Split into drm_sched_fence_set_parent() (ckoenig) v3: Ensure a thread calling drm_sched_fence_set_deadline_finished() sees fence->parent set before drm_sched_fence_set_parent() does this test_bit(DMA_FENCE_FLAG_HAS_DEADLINE_BIT).

Signed-off-by: Rob Clark robdclark@chromium.org Acked-by: Luben Tuikov luben.tuikov@amd.com --- drivers/gpu/drm/scheduler/sched_fence.c | 46 +++++++++++++++++++++++++ drivers/gpu/drm/scheduler/sched_main.c | 2 +- include/drm/gpu_scheduler.h | 17 +++++++++ 3 files changed, 64 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index 7fd869520ef2..fe9c6468e440 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -123,6 +123,37 @@ 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); + struct dma_fence *parent; + unsigned long flags; + + spin_lock_irqsave(&fence->lock, flags); + + /* If we already have an earlier deadline, keep it: */ + if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, &f->flags) && + ktime_before(fence->deadline, deadline)) { + spin_unlock_irqrestore(&fence->lock, flags); + return; + } + + fence->deadline = deadline; + set_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, &f->flags); + + spin_unlock_irqrestore(&fence->lock, flags); + + /* + * smp_load_aquire() to ensure that if we are racing another + * thread calling drm_sched_fence_set_parent(), that we see + * the parent set before it calls test_bit(HAS_DEADLINE_BIT) + */ + parent = smp_load_acquire(&fence->parent); + if (parent) + dma_fence_set_deadline(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, @@ -133,6 +164,7 @@ 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) @@ -147,6 +179,20 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f) } EXPORT_SYMBOL(to_drm_sched_fence);

+void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence, + struct dma_fence *fence) +{ + /* + * smp_store_release() to ensure another thread racing us + * in drm_sched_fence_set_deadline_finished() sees the + * fence's parent set before test_bit() + */ + smp_store_release(&s_fence->parent, dma_fence_get(fence)); + if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, + &s_fence->finished.flags)) + dma_fence_set_deadline(fence, s_fence->deadline); +} + struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *entity, void *owner) { diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 4e6ad6e122bc..007f98c48f8d 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1019,7 +1019,7 @@ static int drm_sched_main(void *param) drm_sched_fence_scheduled(s_fence);

if (!IS_ERR_OR_NULL(fence)) { - s_fence->parent = dma_fence_get(fence); + drm_sched_fence_set_parent(s_fence, fence); /* Drop for original kref_init of the fence */ dma_fence_put(fence);

diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 9db9e5e504ee..99584e457153 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -41,6 +41,15 @@ */ #define DRM_SCHED_FENCE_DONT_PIPELINE DMA_FENCE_FLAG_USER_BITS

+/** + * DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT - A fence deadline hint has been set + * + * Because we could have a deadline hint can be set before the backing hw + * fence is created, we need to keep track of whether a deadline has already + * been set. + */ +#define DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT (DMA_FENCE_FLAG_USER_BITS + 1) + enum dma_resv_usage; struct dma_resv; struct drm_gem_object; @@ -280,6 +289,12 @@ struct drm_sched_fence { */ struct dma_fence finished;

+ /** + * @deadline: deadline set on &drm_sched_fence.finished which + * potentially needs to be propagated to &drm_sched_fence.parent + */ + ktime_t deadline; + /** * @parent: the fence returned by &drm_sched_backend_ops.run_job * when scheduling the job on hardware. We signal the @@ -568,6 +583,8 @@ void drm_sched_entity_set_priority(struct drm_sched_entity *entity, enum drm_sched_priority priority); bool drm_sched_entity_is_ready(struct drm_sched_entity *entity);

+void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence, + struct dma_fence *fence); struct drm_sched_fence *drm_sched_fence_alloc( struct drm_sched_entity *s_entity, void *owner); void drm_sched_fence_init(struct drm_sched_fence *fence,

From: Rob Clark robdclark@chromium.org

v2: rebase

Signed-off-by: Rob Clark robdclark@chromium.org --- drivers/gpu/drm/i915/i915_request.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 7503dcb9043b..44491e7e214c 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -97,6 +97,25 @@ static bool i915_fence_enable_signaling(struct dma_fence *fence) return i915_request_enable_breadcrumb(to_request(fence)); }

+static void i915_fence_set_deadline(struct dma_fence *fence, ktime_t deadline) +{ + struct i915_request *rq = to_request(fence); + + if (i915_request_completed(rq)) + return; + + if (i915_request_started(rq)) + return; + + /* + * TODO something more clever for deadlines that are in the + * future. I think probably track the nearest deadline in + * rq->timeline and set timer to trigger boost accordingly? + */ + + intel_rps_boost(rq); +} + static signed long i915_fence_wait(struct dma_fence *fence, bool interruptible, signed long timeout) @@ -182,6 +201,7 @@ const struct dma_fence_ops i915_fence_ops = { .signaled = i915_fence_signaled, .wait = i915_fence_wait, .release = i915_fence_release, + .set_deadline = i915_fence_set_deadline, };

static void irq_execute_cb(struct irq_work *wrk)