Hi all,
Just explaining what is being changed here compared to v6 :
We just noticed that some of our CTS runs are flaky because when importing a dma fence into a drm syncobj we do not update the atomic binary payload. This leads to issues when the userspace drivers tries to add new points to the timeline because the atomic binary payload may then have a value inferior to the seqno of the new installed fence.
Cheers,
Lionel Landwerlin (1): drm/syncobj: add sideband payload
drivers/gpu/drm/drm_internal.h | 2 ++ drivers/gpu/drm/drm_ioctl.c | 3 ++ drivers/gpu/drm/drm_syncobj.c | 64 ++++++++++++++++++++++++++++++++-- include/drm/drm_syncobj.h | 9 +++++ include/uapi/drm/drm.h | 17 +++++++++ 5 files changed, 93 insertions(+), 2 deletions(-)
-- 2.23.0
The Vulkan timeline semaphores allow signaling to happen on the point of the timeline without all of the its dependencies to be created.
The current 2 implementations (AMD/Intel) of the Vulkan spec on top of the Linux kernel are using a thread to wait on the dependencies of a given point to materialize and delay actual submission to the kernel driver until the wait completes.
If a binary semaphore is submitted for signaling along the side of a timeline semaphore waiting for completion that means that the drm syncobj associated with that binary semaphore will not have a DMA fence associated with it by the time vkQueueSubmit() returns. This and the fact that a binary semaphore can be signaled and unsignaled as before its DMA fences materialize mean that we cannot just rely on the fence within the syncobj but we also need a sideband payload verifying that the fence in the syncobj matches the last submission from the Vulkan API point of view.
This change adds a sideband payload that is incremented with signaled syncobj when vkQueueSubmit() is called. The next vkQueueSubmit() waiting on a the syncobj will read the sideband payload and wait for a fence chain element with a seqno superior or equal to the sideband payload value to be added into the fence chain and use that fence to trigger the submission on the kernel driver.
v2: Use a separate ioctl to get/set the sideband value (Christian)
v3: Use 2 ioctls for get/set (Christian)
v4: Use a single new ioctl
v5: a bunch of blattant mistakes Store payload atomically (Chris)
v6: Only touch atomic value once (Jason)
v7: Updated atomic value when importing sync file
Signed-off-by: Lionel Landwerlin lionel.g.landwerlin@intel.com Reviewed-by: David Zhou David1.Zhou@amd.com (v6) Cc: Christian Koenig Christian.Koenig@amd.com Cc: Jason Ekstrand jason@jlekstrand.net Cc: David(ChunMing) Zhou David1.Zhou@amd.com --- drivers/gpu/drm/drm_internal.h | 2 ++ drivers/gpu/drm/drm_ioctl.c | 3 ++ drivers/gpu/drm/drm_syncobj.c | 64 ++++++++++++++++++++++++++++++++-- include/drm/drm_syncobj.h | 9 +++++ include/uapi/drm/drm.h | 17 +++++++++ 5 files changed, 93 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 51a2055c8f18..e297dfd85019 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -208,6 +208,8 @@ int drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); int drm_syncobj_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); +int drm_syncobj_binary_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private);
/* drm_framebuffer.c */ void drm_framebuffer_print_info(struct drm_printer *p, unsigned int indent, diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index f675a3bb2c88..644d0bc800a4 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -703,6 +703,9 @@ static const struct drm_ioctl_desc drm_ioctls[] = { DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_QUERY, drm_syncobj_query_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_BINARY, drm_syncobj_binary_ioctl, + DRM_RENDER_ALLOW), + DRM_IOCTL_DEF(DRM_IOCTL_CRTC_GET_SEQUENCE, drm_crtc_get_sequence_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_CRTC_QUEUE_SEQUENCE, drm_crtc_queue_sequence_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_LEASE, drm_mode_create_lease_ioctl, DRM_MASTER), diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 4b5c7b0ed714..2de8f1380890 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -418,8 +418,10 @@ int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, if (flags & DRM_SYNCOBJ_CREATE_SIGNALED) drm_syncobj_assign_null_handle(syncobj);
- if (fence) + if (fence) { drm_syncobj_replace_fence(syncobj, fence); + atomic64_set(&syncobj->binary_payload, fence->seqno); + }
*out_syncobj = syncobj; return 0; @@ -604,6 +606,7 @@ static int drm_syncobj_import_sync_file_fence(struct drm_file *file_private, }
drm_syncobj_replace_fence(syncobj, fence); + atomic64_set(&syncobj->binary_payload, fence->seqno); dma_fence_put(fence); drm_syncobj_put(syncobj); return 0; @@ -1224,8 +1227,10 @@ drm_syncobj_reset_ioctl(struct drm_device *dev, void *data, if (ret < 0) return ret;
- for (i = 0; i < args->count_handles; i++) + for (i = 0; i < args->count_handles; i++) { drm_syncobj_replace_fence(syncobjs[i], NULL); + atomic64_set(&syncobjs[i]->binary_payload, 0); + }
drm_syncobj_array_free(syncobjs, args->count_handles);
@@ -1395,6 +1400,61 @@ int drm_syncobj_query_ioctl(struct drm_device *dev, void *data, if (ret) break; } + + drm_syncobj_array_free(syncobjs, args->count_handles); + + return ret; +} + +int drm_syncobj_binary_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private) +{ + struct drm_syncobj_binary_array *args = data; + struct drm_syncobj **syncobjs; + u32 __user *access_flags = u64_to_user_ptr(args->access_flags); + u64 __user *values = u64_to_user_ptr(args->values); + u32 i; + int ret; + + if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) + return -EOPNOTSUPP; + + if (args->pad != 0) + return -EINVAL; + + if (args->count_handles == 0) + return -EINVAL; + + ret = drm_syncobj_array_find(file_private, + u64_to_user_ptr(args->handles), + args->count_handles, + &syncobjs); + if (ret < 0) + return ret; + + for (i = 0; i < args->count_handles; i++) { + u32 flags; + u64 value; + + if (get_user(flags, &access_flags[i])) { + ret = -EFAULT; + break; + } + + if (flags & DRM_SYNCOBJ_BINARY_VALUE_INC) + value = atomic64_inc_return(&syncobjs[i]->binary_payload) - 1; + else if (flags & DRM_SYNCOBJ_BINARY_VALUE_READ) + value = atomic64_read(&syncobjs[i]->binary_payload); + + if (flags & DRM_SYNCOBJ_BINARY_VALUE_READ) { + if (put_user(value, &values[i])) { + ret = -EFAULT; + break; + } + } + + } + drm_syncobj_array_free(syncobjs, args->count_handles);
return ret; diff --git a/include/drm/drm_syncobj.h b/include/drm/drm_syncobj.h index 6cf7243a1dc5..aa76cb3f9107 100644 --- a/include/drm/drm_syncobj.h +++ b/include/drm/drm_syncobj.h @@ -61,6 +61,15 @@ struct drm_syncobj { * @file: A file backing for this syncobj. */ struct file *file; + /** + * @binary_payload: A 64bit payload for binary syncobjs. + * + * We use the payload value to wait on binary syncobj fences to + * materialize. It is a reservation mechanism for the signaler to + * express that at some point in the future a dma fence with the same + * seqno will be put into the syncobj. + */ + atomic64_t binary_payload; };
void drm_syncobj_free(struct kref *kref); diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 8a5b2f8f8eb9..78a0a413b788 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -785,6 +785,22 @@ struct drm_syncobj_timeline_array { __u32 pad; };
+struct drm_syncobj_binary_array { + /* A pointer to an array of u32 syncobj handles. */ + __u64 handles; + /* A pointer to an array of u32 access flags for each handle. */ + __u64 access_flags; + /* The binary value of a syncobj is read before it is incremented. */ +#define DRM_SYNCOBJ_BINARY_VALUE_READ (1u << 0) +#define DRM_SYNCOBJ_BINARY_VALUE_INC (1u << 1) + /* A pointer to an array of u64 values written to by the kernel if the + * handle is flagged for reading. + */ + __u64 values; + /* The length of the 3 arrays above. */ + __u32 count_handles; + __u32 pad; +};
/* Query current scanout sequence number */ struct drm_crtc_get_sequence { @@ -946,6 +962,7 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_QUERY DRM_IOWR(0xCB, struct drm_syncobj_timeline_array) #define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer) #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array) +#define DRM_IOCTL_SYNCOBJ_BINARY DRM_IOWR(0xCE, struct drm_syncobj_binary_array)
/** * Device specific ioctls should only be in their respective headers
Hi Lionel, The update looks good to me. I tried your signal-order test, seems it isn't ready to run, not sure if I can reproduce your this issue.
-David ________________________________ From: Lionel Landwerlin lionel.g.landwerlin@intel.com Sent: Tuesday, September 17, 2019 7:03 PM To: dri-devel@lists.freedesktop.org dri-devel@lists.freedesktop.org Cc: Lionel Landwerlin lionel.g.landwerlin@intel.com; Zhou, David(ChunMing) David1.Zhou@amd.com; Koenig, Christian Christian.Koenig@amd.com; Jason Ekstrand jason@jlekstrand.net Subject: [PATCH 1/1] drm/syncobj: add sideband payload
The Vulkan timeline semaphores allow signaling to happen on the point of the timeline without all of the its dependencies to be created.
The current 2 implementations (AMD/Intel) of the Vulkan spec on top of the Linux kernel are using a thread to wait on the dependencies of a given point to materialize and delay actual submission to the kernel driver until the wait completes.
If a binary semaphore is submitted for signaling along the side of a timeline semaphore waiting for completion that means that the drm syncobj associated with that binary semaphore will not have a DMA fence associated with it by the time vkQueueSubmit() returns. This and the fact that a binary semaphore can be signaled and unsignaled as before its DMA fences materialize mean that we cannot just rely on the fence within the syncobj but we also need a sideband payload verifying that the fence in the syncobj matches the last submission from the Vulkan API point of view.
This change adds a sideband payload that is incremented with signaled syncobj when vkQueueSubmit() is called. The next vkQueueSubmit() waiting on a the syncobj will read the sideband payload and wait for a fence chain element with a seqno superior or equal to the sideband payload value to be added into the fence chain and use that fence to trigger the submission on the kernel driver.
v2: Use a separate ioctl to get/set the sideband value (Christian)
v3: Use 2 ioctls for get/set (Christian)
v4: Use a single new ioctl
v5: a bunch of blattant mistakes Store payload atomically (Chris)
v6: Only touch atomic value once (Jason)
v7: Updated atomic value when importing sync file
Signed-off-by: Lionel Landwerlin lionel.g.landwerlin@intel.com Reviewed-by: David Zhou David1.Zhou@amd.com (v6) Cc: Christian Koenig Christian.Koenig@amd.com Cc: Jason Ekstrand jason@jlekstrand.net Cc: David(ChunMing) Zhou David1.Zhou@amd.com --- drivers/gpu/drm/drm_internal.h | 2 ++ drivers/gpu/drm/drm_ioctl.c | 3 ++ drivers/gpu/drm/drm_syncobj.c | 64 ++++++++++++++++++++++++++++++++-- include/drm/drm_syncobj.h | 9 +++++ include/uapi/drm/drm.h | 17 +++++++++ 5 files changed, 93 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 51a2055c8f18..e297dfd85019 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -208,6 +208,8 @@ int drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); int drm_syncobj_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); +int drm_syncobj_binary_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private);
/* drm_framebuffer.c */ void drm_framebuffer_print_info(struct drm_printer *p, unsigned int indent, diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index f675a3bb2c88..644d0bc800a4 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -703,6 +703,9 @@ static const struct drm_ioctl_desc drm_ioctls[] = { DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_QUERY, drm_syncobj_query_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_BINARY, drm_syncobj_binary_ioctl, + DRM_RENDER_ALLOW), + DRM_IOCTL_DEF(DRM_IOCTL_CRTC_GET_SEQUENCE, drm_crtc_get_sequence_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_CRTC_QUEUE_SEQUENCE, drm_crtc_queue_sequence_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_LEASE, drm_mode_create_lease_ioctl, DRM_MASTER), diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 4b5c7b0ed714..2de8f1380890 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -418,8 +418,10 @@ int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, if (flags & DRM_SYNCOBJ_CREATE_SIGNALED) drm_syncobj_assign_null_handle(syncobj);
- if (fence) + if (fence) { drm_syncobj_replace_fence(syncobj, fence); + atomic64_set(&syncobj->binary_payload, fence->seqno); + }
*out_syncobj = syncobj; return 0; @@ -604,6 +606,7 @@ static int drm_syncobj_import_sync_file_fence(struct drm_file *file_private, }
drm_syncobj_replace_fence(syncobj, fence); + atomic64_set(&syncobj->binary_payload, fence->seqno); dma_fence_put(fence); drm_syncobj_put(syncobj); return 0; @@ -1224,8 +1227,10 @@ drm_syncobj_reset_ioctl(struct drm_device *dev, void *data, if (ret < 0) return ret;
- for (i = 0; i < args->count_handles; i++) + for (i = 0; i < args->count_handles; i++) { drm_syncobj_replace_fence(syncobjs[i], NULL); + atomic64_set(&syncobjs[i]->binary_payload, 0); + }
drm_syncobj_array_free(syncobjs, args->count_handles);
@@ -1395,6 +1400,61 @@ int drm_syncobj_query_ioctl(struct drm_device *dev, void *data, if (ret) break; } + + drm_syncobj_array_free(syncobjs, args->count_handles); + + return ret; +} + +int drm_syncobj_binary_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private) +{ + struct drm_syncobj_binary_array *args = data; + struct drm_syncobj **syncobjs; + u32 __user *access_flags = u64_to_user_ptr(args->access_flags); + u64 __user *values = u64_to_user_ptr(args->values); + u32 i; + int ret; + + if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) + return -EOPNOTSUPP; + + if (args->pad != 0) + return -EINVAL; + + if (args->count_handles == 0) + return -EINVAL; + + ret = drm_syncobj_array_find(file_private, + u64_to_user_ptr(args->handles), + args->count_handles, + &syncobjs); + if (ret < 0) + return ret; + + for (i = 0; i < args->count_handles; i++) { + u32 flags; + u64 value; + + if (get_user(flags, &access_flags[i])) { + ret = -EFAULT; + break; + } + + if (flags & DRM_SYNCOBJ_BINARY_VALUE_INC) + value = atomic64_inc_return(&syncobjs[i]->binary_payload) - 1; + else if (flags & DRM_SYNCOBJ_BINARY_VALUE_READ) + value = atomic64_read(&syncobjs[i]->binary_payload); + + if (flags & DRM_SYNCOBJ_BINARY_VALUE_READ) { + if (put_user(value, &values[i])) { + ret = -EFAULT; + break; + } + } + + } + drm_syncobj_array_free(syncobjs, args->count_handles);
return ret; diff --git a/include/drm/drm_syncobj.h b/include/drm/drm_syncobj.h index 6cf7243a1dc5..aa76cb3f9107 100644 --- a/include/drm/drm_syncobj.h +++ b/include/drm/drm_syncobj.h @@ -61,6 +61,15 @@ struct drm_syncobj { * @file: A file backing for this syncobj. */ struct file *file; + /** + * @binary_payload: A 64bit payload for binary syncobjs. + * + * We use the payload value to wait on binary syncobj fences to + * materialize. It is a reservation mechanism for the signaler to + * express that at some point in the future a dma fence with the same + * seqno will be put into the syncobj. + */ + atomic64_t binary_payload; };
void drm_syncobj_free(struct kref *kref); diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 8a5b2f8f8eb9..78a0a413b788 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -785,6 +785,22 @@ struct drm_syncobj_timeline_array { __u32 pad; };
+struct drm_syncobj_binary_array { + /* A pointer to an array of u32 syncobj handles. */ + __u64 handles; + /* A pointer to an array of u32 access flags for each handle. */ + __u64 access_flags; + /* The binary value of a syncobj is read before it is incremented. */ +#define DRM_SYNCOBJ_BINARY_VALUE_READ (1u << 0) +#define DRM_SYNCOBJ_BINARY_VALUE_INC (1u << 1) + /* A pointer to an array of u64 values written to by the kernel if the + * handle is flagged for reading. + */ + __u64 values; + /* The length of the 3 arrays above. */ + __u32 count_handles; + __u32 pad; +};
/* Query current scanout sequence number */ struct drm_crtc_get_sequence { @@ -946,6 +962,7 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_QUERY DRM_IOWR(0xCB, struct drm_syncobj_timeline_array) #define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer) #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array) +#define DRM_IOCTL_SYNCOBJ_BINARY DRM_IOWR(0xCE, struct drm_syncobj_binary_array)
/** * Device specific ioctls should only be in their respective headers -- 2.23.0
Thanks David,
I'll try to fix the test to match AMD's restrictions.
The v7 here was to fix another existing test : dEQP-VK.api.external.fence.sync_fd.transference_temporary
Cheers,
-Lionel
On 17/09/2019 15:36, Zhou, David(ChunMing) wrote:
Hi Lionel, The update looks good to me. I tried your signal-order test, seems it isn't ready to run, not sure if I can reproduce your this issue.
-David
*From:* Lionel Landwerlin lionel.g.landwerlin@intel.com *Sent:* Tuesday, September 17, 2019 7:03 PM *To:* dri-devel@lists.freedesktop.org dri-devel@lists.freedesktop.org *Cc:* Lionel Landwerlin lionel.g.landwerlin@intel.com; Zhou, David(ChunMing) David1.Zhou@amd.com; Koenig, Christian Christian.Koenig@amd.com; Jason Ekstrand jason@jlekstrand.net *Subject:* [PATCH 1/1] drm/syncobj: add sideband payload The Vulkan timeline semaphores allow signaling to happen on the point of the timeline without all of the its dependencies to be created.
The current 2 implementations (AMD/Intel) of the Vulkan spec on top of the Linux kernel are using a thread to wait on the dependencies of a given point to materialize and delay actual submission to the kernel driver until the wait completes.
If a binary semaphore is submitted for signaling along the side of a timeline semaphore waiting for completion that means that the drm syncobj associated with that binary semaphore will not have a DMA fence associated with it by the time vkQueueSubmit() returns. This and the fact that a binary semaphore can be signaled and unsignaled as before its DMA fences materialize mean that we cannot just rely on the fence within the syncobj but we also need a sideband payload verifying that the fence in the syncobj matches the last submission from the Vulkan API point of view.
This change adds a sideband payload that is incremented with signaled syncobj when vkQueueSubmit() is called. The next vkQueueSubmit() waiting on a the syncobj will read the sideband payload and wait for a fence chain element with a seqno superior or equal to the sideband payload value to be added into the fence chain and use that fence to trigger the submission on the kernel driver.
v2: Use a separate ioctl to get/set the sideband value (Christian)
v3: Use 2 ioctls for get/set (Christian)
v4: Use a single new ioctl
v5: a bunch of blattant mistakes Store payload atomically (Chris)
v6: Only touch atomic value once (Jason)
v7: Updated atomic value when importing sync file
Signed-off-by: Lionel Landwerlin lionel.g.landwerlin@intel.com Reviewed-by: David Zhou David1.Zhou@amd.com (v6) Cc: Christian Koenig Christian.Koenig@amd.com Cc: Jason Ekstrand jason@jlekstrand.net Cc: David(ChunMing) Zhou David1.Zhou@amd.com
drivers/gpu/drm/drm_internal.h | 2 ++ drivers/gpu/drm/drm_ioctl.c | 3 ++ drivers/gpu/drm/drm_syncobj.c | 64 ++++++++++++++++++++++++++++++++-- include/drm/drm_syncobj.h | 9 +++++ include/uapi/drm/drm.h | 17 +++++++++ 5 files changed, 93 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 51a2055c8f18..e297dfd85019 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -208,6 +208,8 @@ int drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); int drm_syncobj_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); +int drm_syncobj_binary_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private);
/* drm_framebuffer.c */ void drm_framebuffer_print_info(struct drm_printer *p, unsigned int indent, diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index f675a3bb2c88..644d0bc800a4 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -703,6 +703,9 @@ static const struct drm_ioctl_desc drm_ioctls[] = { DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_QUERY, drm_syncobj_query_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_BINARY, drm_syncobj_binary_ioctl, + DRM_RENDER_ALLOW),
DRM_IOCTL_DEF(DRM_IOCTL_CRTC_GET_SEQUENCE, drm_crtc_get_sequence_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_CRTC_QUEUE_SEQUENCE, drm_crtc_queue_sequence_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_LEASE, drm_mode_create_lease_ioctl, DRM_MASTER), diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 4b5c7b0ed714..2de8f1380890 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -418,8 +418,10 @@ int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, if (flags & DRM_SYNCOBJ_CREATE_SIGNALED) drm_syncobj_assign_null_handle(syncobj);
- if (fence) + if (fence) { drm_syncobj_replace_fence(syncobj, fence);
- atomic64_set(&syncobj->binary_payload, fence->seqno);
+ }
*out_syncobj = syncobj; return 0; @@ -604,6 +606,7 @@ static int drm_syncobj_import_sync_file_fence(struct drm_file *file_private, }
drm_syncobj_replace_fence(syncobj, fence); + atomic64_set(&syncobj->binary_payload, fence->seqno); dma_fence_put(fence); drm_syncobj_put(syncobj); return 0; @@ -1224,8 +1227,10 @@ drm_syncobj_reset_ioctl(struct drm_device *dev, void *data, if (ret < 0) return ret;
- for (i = 0; i < args->count_handles; i++) + for (i = 0; i < args->count_handles; i++) { drm_syncobj_replace_fence(syncobjs[i], NULL);
- atomic64_set(&syncobjs[i]->binary_payload, 0);
+ }
drm_syncobj_array_free(syncobjs, args->count_handles);
@@ -1395,6 +1400,61 @@ int drm_syncobj_query_ioctl(struct drm_device *dev, void *data, if (ret) break; }
+ drm_syncobj_array_free(syncobjs, args->count_handles);
+ return ret; +}
+int drm_syncobj_binary_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private) +{ + struct drm_syncobj_binary_array *args = data; + struct drm_syncobj **syncobjs; + u32 __user *access_flags = u64_to_user_ptr(args->access_flags); + u64 __user *values = u64_to_user_ptr(args->values); + u32 i; + int ret;
+ if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) + return -EOPNOTSUPP;
+ if (args->pad != 0) + return -EINVAL;
+ if (args->count_handles == 0) + return -EINVAL;
+ ret = drm_syncobj_array_find(file_private,
- u64_to_user_ptr(args->handles),
- args->count_handles,
+ &syncobjs); + if (ret < 0) + return ret;
+ for (i = 0; i < args->count_handles; i++) { + u32 flags; + u64 value;
+ if (get_user(flags, &access_flags[i])) { + ret = -EFAULT; + break; + }
+ if (flags & DRM_SYNCOBJ_BINARY_VALUE_INC) + value = atomic64_inc_return(&syncobjs[i]->binary_payload) - 1; + else if (flags & DRM_SYNCOBJ_BINARY_VALUE_READ) + value = atomic64_read(&syncobjs[i]->binary_payload);
+ if (flags & DRM_SYNCOBJ_BINARY_VALUE_READ) { + if (put_user(value, &values[i])) { + ret = -EFAULT; + break; + } + }
+ }
drm_syncobj_array_free(syncobjs, args->count_handles);
return ret; diff --git a/include/drm/drm_syncobj.h b/include/drm/drm_syncobj.h index 6cf7243a1dc5..aa76cb3f9107 100644 --- a/include/drm/drm_syncobj.h +++ b/include/drm/drm_syncobj.h @@ -61,6 +61,15 @@ struct drm_syncobj { * @file: A file backing for this syncobj. */ struct file *file; + /** + * @binary_payload: A 64bit payload for binary syncobjs. + * + * We use the payload value to wait on binary syncobj fences to + * materialize. It is a reservation mechanism for the signaler to + * express that at some point in the future a dma fence with the same + * seqno will be put into the syncobj. + */ + atomic64_t binary_payload; };
void drm_syncobj_free(struct kref *kref); diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 8a5b2f8f8eb9..78a0a413b788 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -785,6 +785,22 @@ struct drm_syncobj_timeline_array { __u32 pad; };
+struct drm_syncobj_binary_array { + /* A pointer to an array of u32 syncobj handles. */ + __u64 handles; + /* A pointer to an array of u32 access flags for each handle. */ + __u64 access_flags; + /* The binary value of a syncobj is read before it is incremented. */ +#define DRM_SYNCOBJ_BINARY_VALUE_READ (1u << 0) +#define DRM_SYNCOBJ_BINARY_VALUE_INC (1u << 1) + /* A pointer to an array of u64 values written to by the kernel if the + * handle is flagged for reading. + */ + __u64 values; + /* The length of the 3 arrays above. */ + __u32 count_handles; + __u32 pad; +};
/* Query current scanout sequence number */ struct drm_crtc_get_sequence { @@ -946,6 +962,7 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_QUERY DRM_IOWR(0xCB, struct drm_syncobj_timeline_array) #define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer) #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array) +#define DRM_IOCTL_SYNCOBJ_BINARY DRM_IOWR(0xCE, struct drm_syncobj_binary_array)
/** * Device specific ioctls should only be in their respective headers -- 2.23.0
Following earlier discussions in particular with James Jones at Nvidia, I think we established this patch/feature is not needed.
This feature was indented to fix a failing test on our implementation. I've just submitted a MR to delete that test : https://gitlab.freedesktop.org/mesa/crucible/merge_requests/55 I think it is invalid.
We should be able to workaround the submission thread race condition issue by just resetting a binary semaphore to be signaled in vkQueueSubmit before submitting the workload, so that further waits happen on the right dma-fence. This might be a bit more costly (more ioctls) than the feature in this patch, so I'm looking for your feedback on this.
Thanks a lot,
-Lionel
On 17/09/2019 16:06, Lionel Landwerlin wrote:
Thanks David,
I'll try to fix the test to match AMD's restrictions.
The v7 here was to fix another existing test : dEQP-VK.api.external.fence.sync_fd.transference_temporary
Cheers,
-Lionel
On 17/09/2019 15:36, Zhou, David(ChunMing) wrote:
Hi Lionel, The update looks good to me. I tried your signal-order test, seems it isn't ready to run, not sure if I can reproduce your this issue.
-David
*From:* Lionel Landwerlin lionel.g.landwerlin@intel.com *Sent:* Tuesday, September 17, 2019 7:03 PM *To:* dri-devel@lists.freedesktop.org dri-devel@lists.freedesktop.org *Cc:* Lionel Landwerlin lionel.g.landwerlin@intel.com; Zhou, David(ChunMing) David1.Zhou@amd.com; Koenig, Christian Christian.Koenig@amd.com; Jason Ekstrand jason@jlekstrand.net *Subject:* [PATCH 1/1] drm/syncobj: add sideband payload The Vulkan timeline semaphores allow signaling to happen on the point of the timeline without all of the its dependencies to be created.
The current 2 implementations (AMD/Intel) of the Vulkan spec on top of the Linux kernel are using a thread to wait on the dependencies of a given point to materialize and delay actual submission to the kernel driver until the wait completes.
If a binary semaphore is submitted for signaling along the side of a timeline semaphore waiting for completion that means that the drm syncobj associated with that binary semaphore will not have a DMA fence associated with it by the time vkQueueSubmit() returns. This and the fact that a binary semaphore can be signaled and unsignaled as before its DMA fences materialize mean that we cannot just rely on the fence within the syncobj but we also need a sideband payload verifying that the fence in the syncobj matches the last submission from the Vulkan API point of view.
This change adds a sideband payload that is incremented with signaled syncobj when vkQueueSubmit() is called. The next vkQueueSubmit() waiting on a the syncobj will read the sideband payload and wait for a fence chain element with a seqno superior or equal to the sideband payload value to be added into the fence chain and use that fence to trigger the submission on the kernel driver.
v2: Use a separate ioctl to get/set the sideband value (Christian)
v3: Use 2 ioctls for get/set (Christian)
v4: Use a single new ioctl
v5: a bunch of blattant mistakes Store payload atomically (Chris)
v6: Only touch atomic value once (Jason)
v7: Updated atomic value when importing sync file
Signed-off-by: Lionel Landwerlin lionel.g.landwerlin@intel.com Reviewed-by: David Zhou David1.Zhou@amd.com (v6) Cc: Christian Koenig Christian.Koenig@amd.com Cc: Jason Ekstrand jason@jlekstrand.net Cc: David(ChunMing) Zhou David1.Zhou@amd.com
drivers/gpu/drm/drm_internal.h | 2 ++ drivers/gpu/drm/drm_ioctl.c | 3 ++ drivers/gpu/drm/drm_syncobj.c | 64 ++++++++++++++++++++++++++++++++-- include/drm/drm_syncobj.h | 9 +++++ include/uapi/drm/drm.h | 17 +++++++++ 5 files changed, 93 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 51a2055c8f18..e297dfd85019 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -208,6 +208,8 @@ int drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); int drm_syncobj_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); +int drm_syncobj_binary_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private);
/* drm_framebuffer.c */ void drm_framebuffer_print_info(struct drm_printer *p, unsigned int indent, diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index f675a3bb2c88..644d0bc800a4 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -703,6 +703,9 @@ static const struct drm_ioctl_desc drm_ioctls[] = { DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_QUERY, drm_syncobj_query_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_BINARY, drm_syncobj_binary_ioctl, + DRM_RENDER_ALLOW),
DRM_IOCTL_DEF(DRM_IOCTL_CRTC_GET_SEQUENCE, drm_crtc_get_sequence_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_CRTC_QUEUE_SEQUENCE, drm_crtc_queue_sequence_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_LEASE, drm_mode_create_lease_ioctl, DRM_MASTER), diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 4b5c7b0ed714..2de8f1380890 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -418,8 +418,10 @@ int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, if (flags & DRM_SYNCOBJ_CREATE_SIGNALED) drm_syncobj_assign_null_handle(syncobj);
- if (fence) + if (fence) { drm_syncobj_replace_fence(syncobj, fence);
- atomic64_set(&syncobj->binary_payload, fence->seqno);
+ }
*out_syncobj = syncobj; return 0; @@ -604,6 +606,7 @@ static int drm_syncobj_import_sync_file_fence(struct drm_file *file_private, }
drm_syncobj_replace_fence(syncobj, fence); + atomic64_set(&syncobj->binary_payload, fence->seqno); dma_fence_put(fence); drm_syncobj_put(syncobj); return 0; @@ -1224,8 +1227,10 @@ drm_syncobj_reset_ioctl(struct drm_device *dev, void *data, if (ret < 0) return ret;
- for (i = 0; i < args->count_handles; i++) + for (i = 0; i < args->count_handles; i++) { drm_syncobj_replace_fence(syncobjs[i], NULL);
- atomic64_set(&syncobjs[i]->binary_payload, 0);
+ }
drm_syncobj_array_free(syncobjs, args->count_handles);
@@ -1395,6 +1400,61 @@ int drm_syncobj_query_ioctl(struct drm_device *dev, void *data, if (ret) break; }
+ drm_syncobj_array_free(syncobjs, args->count_handles);
+ return ret; +}
+int drm_syncobj_binary_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private) +{ + struct drm_syncobj_binary_array *args = data; + struct drm_syncobj **syncobjs; + u32 __user *access_flags = u64_to_user_ptr(args->access_flags); + u64 __user *values = u64_to_user_ptr(args->values); + u32 i; + int ret;
+ if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) + return -EOPNOTSUPP;
+ if (args->pad != 0) + return -EINVAL;
+ if (args->count_handles == 0) + return -EINVAL;
+ ret = drm_syncobj_array_find(file_private,
- u64_to_user_ptr(args->handles),
- args->count_handles,
+ &syncobjs); + if (ret < 0) + return ret;
+ for (i = 0; i < args->count_handles; i++) { + u32 flags; + u64 value;
+ if (get_user(flags, &access_flags[i])) { + ret = -EFAULT; + break; + }
+ if (flags & DRM_SYNCOBJ_BINARY_VALUE_INC) + value = atomic64_inc_return(&syncobjs[i]->binary_payload) - 1; + else if (flags & DRM_SYNCOBJ_BINARY_VALUE_READ) + value = atomic64_read(&syncobjs[i]->binary_payload);
+ if (flags & DRM_SYNCOBJ_BINARY_VALUE_READ) { + if (put_user(value, &values[i])) { + ret = -EFAULT; + break; + } + }
+ }
drm_syncobj_array_free(syncobjs, args->count_handles);
return ret; diff --git a/include/drm/drm_syncobj.h b/include/drm/drm_syncobj.h index 6cf7243a1dc5..aa76cb3f9107 100644 --- a/include/drm/drm_syncobj.h +++ b/include/drm/drm_syncobj.h @@ -61,6 +61,15 @@ struct drm_syncobj { * @file: A file backing for this syncobj. */ struct file *file; + /** + * @binary_payload: A 64bit payload for binary syncobjs. + * + * We use the payload value to wait on binary syncobj fences to + * materialize. It is a reservation mechanism for the signaler to + * express that at some point in the future a dma fence with the same + * seqno will be put into the syncobj. + */ + atomic64_t binary_payload; };
void drm_syncobj_free(struct kref *kref); diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 8a5b2f8f8eb9..78a0a413b788 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -785,6 +785,22 @@ struct drm_syncobj_timeline_array { __u32 pad; };
+struct drm_syncobj_binary_array { + /* A pointer to an array of u32 syncobj handles. */ + __u64 handles; + /* A pointer to an array of u32 access flags for each handle. */ + __u64 access_flags; + /* The binary value of a syncobj is read before it is incremented. */ +#define DRM_SYNCOBJ_BINARY_VALUE_READ (1u << 0) +#define DRM_SYNCOBJ_BINARY_VALUE_INC (1u << 1) + /* A pointer to an array of u64 values written to by the kernel if the + * handle is flagged for reading. + */ + __u64 values; + /* The length of the 3 arrays above. */ + __u32 count_handles; + __u32 pad; +};
/* Query current scanout sequence number */ struct drm_crtc_get_sequence { @@ -946,6 +962,7 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_QUERY DRM_IOWR(0xCB, struct drm_syncobj_timeline_array) #define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer) #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array) +#define DRM_IOCTL_SYNCOBJ_BINARY DRM_IOWR(0xCE, struct drm_syncobj_binary_array)
/** * Device specific ioctls should only be in their respective headers -- 2.23.0
dri-devel@lists.freedesktop.org
-
Lionel Landwerlin -
Zhou, David(ChunMing)