From 04dd17822334871b23ea2862f7798fb0e0007777 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 11 May 2024 08:53:19 +0000
Subject: [PATCH] change otg to host mode
---
kernel/include/uapi/drm/v3d_drm.h | 81 ++++++++++++++++++++++++++++++++++++++--
1 files changed, 77 insertions(+), 4 deletions(-)
diff --git a/kernel/include/uapi/drm/v3d_drm.h b/kernel/include/uapi/drm/v3d_drm.h
index 7b66277..1ce746e 100644
--- a/kernel/include/uapi/drm/v3d_drm.h
+++ b/kernel/include/uapi/drm/v3d_drm.h
@@ -36,6 +36,8 @@
#define DRM_V3D_MMAP_BO 0x03
#define DRM_V3D_GET_PARAM 0x04
#define DRM_V3D_GET_BO_OFFSET 0x05
+#define DRM_V3D_SUBMIT_TFU 0x06
+#define DRM_V3D_SUBMIT_CSD 0x07
#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)
@@ -43,6 +45,10 @@
#define DRM_IOCTL_V3D_MMAP_BO DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_MMAP_BO, struct drm_v3d_mmap_bo)
#define DRM_IOCTL_V3D_GET_PARAM DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_PARAM, struct drm_v3d_get_param)
#define DRM_IOCTL_V3D_GET_BO_OFFSET DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_BO_OFFSET, struct drm_v3d_get_bo_offset)
+#define DRM_IOCTL_V3D_SUBMIT_TFU DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_TFU, struct drm_v3d_submit_tfu)
+#define DRM_IOCTL_V3D_SUBMIT_CSD DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CSD, struct drm_v3d_submit_csd)
+
+#define DRM_V3D_SUBMIT_CL_FLUSH_CACHE 0x01
/**
* struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D
@@ -50,6 +56,14 @@
*
* This asks the kernel to have the GPU execute an optional binner
* command list, and a render command list.
+ *
+ * The L1T, slice, L2C, L2T, and GCA caches will be flushed before
+ * each CL executes. The VCD cache should be flushed (if necessary)
+ * by the submitted CLs. The TLB writes are guaranteed to have been
+ * flushed by the time the render done IRQ happens, which is the
+ * trigger for out_sync. Any dirtying of cachelines by the job (only
+ * possible using TMU writes) must be flushed by the caller using the
+ * DRM_V3D_SUBMIT_CL_FLUSH_CACHE_FLAG flag.
*/
struct drm_v3d_submit_cl {
/* Pointer to the binner command list.
@@ -58,10 +72,15 @@
* coordinate shader to determine where primitives land on the screen,
* then writes out the state updates and draw calls necessary per tile
* to the tile allocation BO.
+ *
+ * This BCL will block on any previous BCL submitted on the
+ * same FD, but not on any RCL or BCLs submitted by other
+ * clients -- that is left up to the submitter to control
+ * using in_sync_bcl if necessary.
*/
__u32 bcl_start;
- /** End address of the BCL (first byte after the BCL) */
+ /** End address of the BCL (first byte after the BCL) */
__u32 bcl_end;
/* Offset of the render command list.
@@ -69,10 +88,15 @@
* This is the second set of commands executed, which will either
* execute the tiles that have been set up by the BCL, or a fixed set
* of tiles (in the case of RCL-only blits).
+ *
+ * This RCL will block on this submit's BCL, and any previous
+ * RCL submitted on the same FD, but not on any RCL or BCLs
+ * submitted by other clients -- that is left up to the
+ * submitter to control using in_sync_rcl if necessary.
*/
__u32 rcl_start;
- /** End address of the RCL (first byte after the RCL) */
+ /** End address of the RCL (first byte after the RCL) */
__u32 rcl_end;
/** An optional sync object to wait on before starting the BCL. */
@@ -102,8 +126,7 @@
/* Number of BO handles passed in (size is that times 4). */
__u32 bo_handle_count;
- /* Pad, must be zero-filled. */
- __u32 pad;
+ __u32 flags;
};
/**
@@ -169,6 +192,9 @@
DRM_V3D_PARAM_V3D_CORE0_IDENT0,
DRM_V3D_PARAM_V3D_CORE0_IDENT1,
DRM_V3D_PARAM_V3D_CORE0_IDENT2,
+ DRM_V3D_PARAM_SUPPORTS_TFU,
+ DRM_V3D_PARAM_SUPPORTS_CSD,
+ DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH,
};
struct drm_v3d_get_param {
@@ -187,6 +213,53 @@
__u32 offset;
};
+struct drm_v3d_submit_tfu {
+ __u32 icfg;
+ __u32 iia;
+ __u32 iis;
+ __u32 ica;
+ __u32 iua;
+ __u32 ioa;
+ __u32 ios;
+ __u32 coef[4];
+ /* First handle is the output BO, following are other inputs.
+ * 0 for unused.
+ */
+ __u32 bo_handles[4];
+ /* sync object to block on before running the TFU job. Each TFU
+ * job will execute in the order submitted to its FD. Synchronization
+ * against rendering jobs requires using sync objects.
+ */
+ __u32 in_sync;
+ /* Sync object to signal when the TFU job is done. */
+ __u32 out_sync;
+};
+
+/* Submits a compute shader for dispatch. This job will block on any
+ * previous compute shaders submitted on this fd, and any other
+ * synchronization must be performed with in_sync/out_sync.
+ */
+struct drm_v3d_submit_csd {
+ __u32 cfg[7];
+ __u32 coef[4];
+
+ /* Pointer to a u32 array of the BOs that are referenced by the job.
+ */
+ __u64 bo_handles;
+
+ /* Number of BO handles passed in (size is that times 4). */
+ __u32 bo_handle_count;
+
+ /* sync object to block on before running the CSD job. Each
+ * CSD job will execute in the order submitted to its FD.
+ * Synchronization against rendering/TFU jobs or CSD from
+ * other fds requires using sync objects.
+ */
+ __u32 in_sync;
+ /* Sync object to signal when the CSD job is done. */
+ __u32 out_sync;
+};
+
#if defined(__cplusplus)
}
#endif
--
Gitblit v1.6.2