Merge tag 'drm-misc-next-2023-12-07' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for 6.8:

UAPI Changes:
  - Remove Userspace Mode-Setting ioctls
  - v3d: New uapi to handle jobs involving the CPU

Cross-subsystem Changes:

Core Changes:
  - atomic: Add support for FB-less planes which got reverted a bit
    later for lack of IGT tests and userspace code, Dump private objects
    state in drm_state_dump.
  - dma-buf: Add fence deadline support
  - encoder: Create per-encoder debugfs directory, move the bridge chain
    file to that directory

Driver Changes:
  - Include drm_auth.h in driver that use it but don't include it, Drop
    drm_plane_helper.h from drivers that include it but don't use it
  - imagination: Plenty of small fixes
  - panfrost: Improve interrupt handling at poweroff
  - qaic: Convert to persistent DRM devices
  - tidss: Support for the AM62A7, a few probe improvements, some cleanups
  - v3d: Support for jobs involving the CPU

  - bridge:
    - Create transparent aux-bridge for DP/USB-C
    - lt8912b: Add suspend/resume support and power regulator support

  - panel:
    - himax-hx8394: Drop prepare, unprepare and shutdown logic, Support
      panel rotation
    - New panels: BOE BP101WX1-100, Powkiddy X55, Ampire AM8001280G,
      Evervision VGG644804, SDC ATNA45AF01

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Maxime Ripard <mripard@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/yu5heqaufyeo4nlowzieu4s5unwqrqyx4jixbfjmzdon677rpk@t53vceua2dao

5 files changed, 325 insertions, 8 deletions

diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 8662b5aeea0c..16122819edfe 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -713,7 +713,8 @@ struct drm_gem_open {
 /**
  * DRM_CAP_ASYNC_PAGE_FLIP
  *
- * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC.
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for legacy
+ * page-flips.
  */
 #define DRM_CAP_ASYNC_PAGE_FLIP		0x7
 /**
@@ -773,6 +774,13 @@ struct drm_gem_open {
  * :ref:`drm_sync_objects`.
  */
 #define DRM_CAP_SYNCOBJ_TIMELINE	0x14
+/**
+ * DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP
+ *
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for atomic
+ * commits.
+ */
+#define DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP	0x15
 
 /* DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {
@@ -842,6 +850,31 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
 
+/**
+ * DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT
+ *
+ * Drivers for para-virtualized hardware (e.g. vmwgfx, qxl, virtio and
+ * virtualbox) have additional restrictions for cursor planes (thus
+ * making cursor planes on those drivers not truly universal,) e.g.
+ * they need cursor planes to act like one would expect from a mouse
+ * cursor and have correctly set hotspot properties.
+ * If this client cap is not set the DRM core will hide cursor plane on
+ * those virtualized drivers because not setting it implies that the
+ * client is not capable of dealing with those extra restictions.
+ * Clients which do set cursor hotspot and treat the cursor plane
+ * like a mouse cursor should set this property.
+ * The client must enable &DRM_CLIENT_CAP_ATOMIC first.
+ *
+ * Setting this property on drivers which do not special case
+ * cursor planes (i.e. non-virtualized drivers) will return
+ * EOPNOTSUPP, which can be used by userspace to gauge
+ * requirements of the hardware/drivers they're running on.
+ *
+ * This capability is always supported for atomic-capable virtualized
+ * drivers starting from kernel version 6.6.
+ */
+#define DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT	6
+
 /* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
@@ -893,6 +926,7 @@ struct drm_syncobj_transfer {
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE (1 << 3) /* set fence deadline to deadline_nsec */
 struct drm_syncobj_wait {
 	__u64 handles;
 	/* absolute timeout */
@@ -901,6 +935,14 @@ struct drm_syncobj_wait {
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
 };
 
 struct drm_syncobj_timeline_wait {
@@ -913,6 +955,14 @@ struct drm_syncobj_timeline_wait {
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
 };
 
 /**
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 09e7a471ee30..95630f170110 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -957,6 +957,15 @@ struct hdr_output_metadata {
  * Request that the page-flip is performed as soon as possible, ie. with no
  * delay due to waiting for vblank. This may cause tearing to be visible on
  * the screen.
+ *
+ * When used with atomic uAPI, the driver will return an error if the hardware
+ * doesn't support performing an asynchronous page-flip for this update.
+ * User-space should handle this, e.g. by falling back to a regular page-flip.
+ *
+ * Note, some hardware might need to perform one last synchronous page-flip
+ * before being able to switch to asynchronous page-flips. As an exception,
+ * the driver will return success even though that first page-flip is not
+ * asynchronous.
  */
 #define DRM_MODE_PAGE_FLIP_ASYNC 0x02
 #define DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE 0x4
diff --git a/include/uapi/drm/pvr_drm.h b/include/uapi/drm/pvr_drm.h
index 1834375390c4..ccf6c2112468 100644
--- a/include/uapi/drm/pvr_drm.h
+++ b/include/uapi/drm/pvr_drm.h
@@ -741,20 +741,18 @@ enum drm_pvr_ctx_priority {
  */
 enum drm_pvr_ctx_type {
 	/**
-	 * @DRM_PVR_CTX_TYPE_RENDER: Render context. Use &struct
-	 * drm_pvr_ioctl_create_render_context_args for context creation arguments.
+	 * @DRM_PVR_CTX_TYPE_RENDER: Render context.
 	 */
 	DRM_PVR_CTX_TYPE_RENDER = 0,
 
 	/**
-	 * @DRM_PVR_CTX_TYPE_COMPUTE: Compute context. Use &struct
-	 * drm_pvr_ioctl_create_compute_context_args for context creation arguments.
+	 * @DRM_PVR_CTX_TYPE_COMPUTE: Compute context.
 	 */
 	DRM_PVR_CTX_TYPE_COMPUTE,
 
 	/**
-	 * @DRM_PVR_CTX_TYPE_TRANSFER_FRAG: Transfer context for fragment data masters. Use
-	 * &struct drm_pvr_ioctl_create_transfer_context_args for context creation arguments.
+	 * @DRM_PVR_CTX_TYPE_TRANSFER_FRAG: Transfer context for fragment data
+	 * master.
 	 */
 	DRM_PVR_CTX_TYPE_TRANSFER_FRAG,
 };
diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h
index 1a7d7a689de3..dce1835eced4 100644
--- a/include/uapi/drm/v3d_drm.h
+++ b/include/uapi/drm/v3d_drm.h
@@ -41,6 +41,7 @@ extern "C" {
 #define DRM_V3D_PERFMON_CREATE                    0x08
 #define DRM_V3D_PERFMON_DESTROY                   0x09
 #define DRM_V3D_PERFMON_GET_VALUES                0x0a
+#define DRM_V3D_SUBMIT_CPU                        0x0b
 
 #define DRM_IOCTL_V3D_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CL, struct drm_v3d_submit_cl)
 #define DRM_IOCTL_V3D_WAIT_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_WAIT_BO, struct drm_v3d_wait_bo)
@@ -56,6 +57,7 @@ extern "C" {
 						   struct drm_v3d_perfmon_destroy)
 #define DRM_IOCTL_V3D_PERFMON_GET_VALUES  DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_GET_VALUES, \
 						   struct drm_v3d_perfmon_get_values)
+#define DRM_IOCTL_V3D_SUBMIT_CPU          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CPU, struct drm_v3d_submit_cpu)
 
 #define DRM_V3D_SUBMIT_CL_FLUSH_CACHE             0x01
 #define DRM_V3D_SUBMIT_EXTENSION		  0x02
@@ -69,7 +71,13 @@ extern "C" {
 struct drm_v3d_extension {
 	__u64 next;
 	__u32 id;
-#define DRM_V3D_EXT_ID_MULTI_SYNC		0x01
+#define DRM_V3D_EXT_ID_MULTI_SYNC			0x01
+#define DRM_V3D_EXT_ID_CPU_INDIRECT_CSD		0x02
+#define DRM_V3D_EXT_ID_CPU_TIMESTAMP_QUERY		0x03
+#define DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY	0x04
+#define DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY	0x05
+#define DRM_V3D_EXT_ID_CPU_RESET_PERFORMANCE_QUERY	0x06
+#define DRM_V3D_EXT_ID_CPU_COPY_PERFORMANCE_QUERY	0x07
 	__u32 flags; /* mbz */
 };
 
@@ -93,6 +101,7 @@ enum v3d_queue {
 	V3D_TFU,
 	V3D_CSD,
 	V3D_CACHE_CLEAN,
+	V3D_CPU,
 };
 
 /**
@@ -276,6 +285,7 @@ enum drm_v3d_param {
 	DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH,
 	DRM_V3D_PARAM_SUPPORTS_PERFMON,
 	DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT,
+	DRM_V3D_PARAM_SUPPORTS_CPU_QUEUE,
 };
 
 struct drm_v3d_get_param {
@@ -361,6 +371,234 @@ struct drm_v3d_submit_csd {
 	__u32 pad;
 };
 
+/**
+ * struct drm_v3d_indirect_csd - ioctl extension for the CPU job to create an
+ * indirect CSD
+ *
+ * When an extension of DRM_V3D_EXT_ID_CPU_INDIRECT_CSD id is defined, it
+ * points to this extension to define a indirect CSD submission. It creates a
+ * CPU job linked to a CSD job. The CPU job waits for the indirect CSD
+ * dependencies and, once they are signaled, it updates the CSD job config
+ * before allowing the CSD job execution.
+ */
+struct drm_v3d_indirect_csd {
+	struct drm_v3d_extension base;
+
+	/* Indirect CSD */
+	struct drm_v3d_submit_csd submit;
+
+	/* Handle of the indirect BO, that should be also attached to the
+	 * indirect CSD.
+	 */
+	__u32 indirect;
+
+	/* Offset within the BO where the workgroup counts are stored */
+	__u32 offset;
+
+	/* Workgroups size */
+	__u32 wg_size;
+
+	/* Indices of the uniforms with the workgroup dispatch counts
+	 * in the uniform stream. If the uniform rewrite is not needed,
+	 * the offset must be 0xffffffff.
+	 */
+	__u32 wg_uniform_offsets[3];
+};
+
+/**
+ * struct drm_v3d_timestamp_query - ioctl extension for the CPU job to calculate
+ * a timestamp query
+ *
+ * When an extension DRM_V3D_EXT_ID_TIMESTAMP_QUERY is defined, it points to
+ * this extension to define a timestamp query submission. This CPU job will
+ * calculate the timestamp query and update the query value within the
+ * timestamp BO. Moreover, it will signal the timestamp syncobj to indicate
+ * query availability.
+ */
+struct drm_v3d_timestamp_query {
+	struct drm_v3d_extension base;
+
+	/* Array of queries' offsets within the timestamp BO for their value */
+	__u64 offsets;
+
+	/* Array of timestamp's syncobjs to indicate its availability */
+	__u64 syncs;
+
+	/* Number of queries */
+	__u32 count;
+
+	/* mbz */
+	__u32 pad;
+};
+
+/**
+ * struct drm_v3d_reset_timestamp_query - ioctl extension for the CPU job to
+ * reset timestamp queries
+ *
+ * When an extension DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY is defined, it
+ * points to this extension to define a reset timestamp submission. This CPU
+ * job will reset the timestamp queries based on value offset of the first
+ * query. Moreover, it will reset the timestamp syncobj to reset query
+ * availability.
+ */
+struct drm_v3d_reset_timestamp_query {
+	struct drm_v3d_extension base;
+
+	/* Array of timestamp's syncobjs to indicate its availability */
+	__u64 syncs;
+
+	/* Offset of the first query within the timestamp BO for its value */
+	__u32 offset;
+
+	/* Number of queries */
+	__u32 count;
+};
+
+/**
+ * struct drm_v3d_copy_timestamp_query - ioctl extension for the CPU job to copy
+ * query results to a buffer
+ *
+ * When an extension DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY is defined, it
+ * points to this extension to define a copy timestamp query submission. This
+ * CPU job will copy the timestamp queries results to a BO with the offset
+ * and stride defined in the extension.
+ */
+struct drm_v3d_copy_timestamp_query {
+	struct drm_v3d_extension base;
+
+	/* Define if should write to buffer using 64 or 32 bits */
+	__u8 do_64bit;
+
+	/* Define if it can write to buffer even if the query is not available */
+	__u8 do_partial;
+
+	/* Define if it should write availability bit to buffer */
+	__u8 availability_bit;
+
+	/* mbz */
+	__u8 pad;
+
+	/* Offset of the buffer in the BO */
+	__u32 offset;
+
+	/* Stride of the buffer in the BO */
+	__u32 stride;
+
+	/* Number of queries */
+	__u32 count;
+
+	/* Array of queries' offsets within the timestamp BO for their value */
+	__u64 offsets;
+
+	/* Array of timestamp's syncobjs to indicate its availability */
+	__u64 syncs;
+};
+
+/**
+ * struct drm_v3d_reset_performance_query - ioctl extension for the CPU job to
+ * reset performance queries
+ *
+ * When an extension DRM_V3D_EXT_ID_CPU_RESET_PERFORMANCE_QUERY is defined, it
+ * points to this extension to define a reset performance submission. This CPU
+ * job will reset the performance queries by resetting the values of the
+ * performance monitors. Moreover, it will reset the syncobj to reset query
+ * availability.
+ */
+struct drm_v3d_reset_performance_query {
+	struct drm_v3d_extension base;
+
+	/* Array of performance queries's syncobjs to indicate its availability */
+	__u64 syncs;
+
+	/* Number of queries */
+	__u32 count;
+
+	/* Number of performance monitors */
+	__u32 nperfmons;
+
+	/* Array of u64 user-pointers that point to an array of kperfmon_ids */
+	__u64 kperfmon_ids;
+};
+
+/**
+ * struct drm_v3d_copy_performance_query - ioctl extension for the CPU job to copy
+ * performance query results to a buffer
+ *
+ * When an extension DRM_V3D_EXT_ID_CPU_COPY_PERFORMANCE_QUERY is defined, it
+ * points to this extension to define a copy performance query submission. This
+ * CPU job will copy the performance queries results to a BO with the offset
+ * and stride defined in the extension.
+ */
+struct drm_v3d_copy_performance_query {
+	struct drm_v3d_extension base;
+
+	/* Define if should write to buffer using 64 or 32 bits */
+	__u8 do_64bit;
+
+	/* Define if it can write to buffer even if the query is not available */
+	__u8 do_partial;
+
+	/* Define if it should write availability bit to buffer */
+	__u8 availability_bit;
+
+	/* mbz */
+	__u8 pad;
+
+	/* Offset of the buffer in the BO */
+	__u32 offset;
+
+	/* Stride of the buffer in the BO */
+	__u32 stride;
+
+	/* Number of performance monitors */
+	__u32 nperfmons;
+
+	/* Number of performance counters related to this query pool */
+	__u32 ncounters;
+
+	/* Number of queries */
+	__u32 count;
+
+	/* Array of performance queries's syncobjs to indicate its availability */
+	__u64 syncs;
+
+	/* Array of u64 user-pointers that point to an array of kperfmon_ids */
+	__u64 kperfmon_ids;
+};
+
+struct drm_v3d_submit_cpu {
+	/* Pointer to a u32 array of the BOs that are referenced by the job.
+	 *
+	 * For DRM_V3D_EXT_ID_CPU_INDIRECT_CSD, it must contain only one BO,
+	 * that contains the workgroup counts.
+	 *
+	 * For DRM_V3D_EXT_ID_TIMESTAMP_QUERY, it must contain only one BO,
+	 * that will contain the timestamp.
+	 *
+	 * For DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY, it must contain only
+	 * one BO, that contains the timestamp.
+	 *
+	 * For DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY, it must contain two
+	 * BOs. The first is the BO where the timestamp queries will be written
+	 * to. The second is the BO that contains the timestamp.
+	 *
+	 * For DRM_V3D_EXT_ID_CPU_RESET_PERFORMANCE_QUERY, it must contain no
+	 * BOs.
+	 *
+	 * For DRM_V3D_EXT_ID_CPU_COPY_PERFORMANCE_QUERY, it must contain one
+	 * BO, where the performance queries will be written.
+	 */
+	__u64 bo_handles;
+
+	/* Number of BO handles passed in (size is that times 4). */
+	__u32 bo_handle_count;
+
+	__u32 flags;
+
+	/* Pointer to an array of ioctl extensions*/
+	__u64 extensions;
+};
+
 enum {
 	V3D_PERFCNT_FEP_VALID_PRIMTS_NO_PIXELS,
 	V3D_PERFCNT_FEP_VALID_PRIMS,
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 */