From: Rob Clark robdclark@chromium.org
This is a re-post of the remaining patches from: https://patchwork.freedesktop.org/series/114490/
Part of the hold-up of the remaining uabi patches was compositor support, but now an MR for kwin exists:
https://invent.kde.org/plasma/kwin/-/merge_requests/4358
The syncobj userspace is:
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21973
v1: https://patchwork.freedesktop.org/series/93035/ v2: Move filtering out of later deadlines to fence implementation to avoid increasing the size of dma_fence v3: Add support in fence-array and fence-chain; Add some uabi to support igt tests and userspace compositors. v4: Rebase, address various comments, and add syncobj deadline support, and sync_file EPOLLPRI based on experience with perf/ freq issues with clvk compute workloads on i915 (anv) v5: Clarify that this is a hint as opposed to a more hard deadline guarantee, switch to using u64 ns values in UABI (still absolute CLOCK_MONOTONIC values), drop syncobj related cap and driver feature flag in favor of allowing count_handles==0 for probing kernel support. v6: Re-work vblank helper to calculate time of _start_ of vblank, and work correctly if the last vblank event was more than a frame ago. Add (mostly unrelated) drm/msm patch which also uses the vblank helper. Use dma_fence_chain_contained(). More verbose syncobj UABI comments. Drop DMA_FENCE_FLAG_HAS_DEADLINE_BIT. v7: Fix kbuild complaints about vblank helper. Add more docs. v8: Add patch to surface sync_file UAPI, and more docs updates. v9: Repost the remaining patches that expose new uabi to userspace.
Rob Clark (3): drm/syncobj: Add deadline support for syncobj waits dma-buf/sync_file: Add SET_DEADLINE ioctl dma-buf/sw_sync: Add fence deadline support
drivers/dma-buf/dma-fence.c | 3 +- drivers/dma-buf/sw_sync.c | 82 ++++++++++++++++++++++++++++++++++ drivers/dma-buf/sync_debug.h | 2 + drivers/dma-buf/sync_file.c | 19 ++++++++ drivers/gpu/drm/drm_syncobj.c | 64 ++++++++++++++++++++------ include/uapi/drm/drm.h | 17 +++++++ include/uapi/linux/sync_file.h | 22 +++++++++ 7 files changed, 195 insertions(+), 14 deletions(-)
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 ff0a931833e2..ff1f38889dcf 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 Acked-by: Pekka Paalanen pekka.paalanen@collabora.com --- drivers/dma-buf/sw_sync.c | 82 ++++++++++++++++++++++++++++++++++++ drivers/dma-buf/sync_debug.h | 2 + 2 files changed, 84 insertions(+)
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index f0a35277fd84..c353029789cf 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 +425,47 @@ 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; + unsigned long flags; + 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_irqsave(fence->lock, flags); + if (test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) { + data.deadline_ns = ktime_to_ns(pt->deadline); + } else { + ret = -ENOENT; + } + spin_unlock_irqrestore(fence->lock, flags); + + 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 +478,9 @@ 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..a1bdd62efccd 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 earliest fence deadline hint */ 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;
On Wed, 23 Aug 2023 14:54:53 -0700, Rob Clark wrote:
This is a re-post of the remaining patches from: https://patchwork.freedesktop.org/series/114490/
Part of the hold-up of the remaining uabi patches was compositor support, but now an MR for kwin exists:
https://invent.kde.org/plasma/kwin/-/merge_requests/4358
[...]
Applied to drm-misc-next, thanks!
[1/3] drm/syncobj: Add deadline support for syncobj waits commit: 8570c27932e132d2663e8120311891deb2a853de [2/3] dma-buf/sync_file: Add SET_DEADLINE ioctl commit: 63ee44540205d993854f143a5ab1d7d9e63ffcf1 [3/3] dma-buf/sw_sync: Add fence deadline support commit: 70e67aaec2f4706df0006423eebca813b00f5840
Best regards,
linaro-mm-sig@lists.linaro.org