Merge tag 'drm-msm-next-2023-04-10' of https://gitlab.freedesktop.org/drm/msm into drm-next

main pull request for v6.4

Core Display:
============
* Bugfixes for error handling during probe
* rework UBWC decoder programming
* prepare_commit cleanup
* bindings for SM8550 (MDSS, DPU), SM8450 (DP)
* timeout calculation fixup
* atomic: use drm_crtc_next_vblank_start() instead of our own
  custom thing to calculate the start of next vblank

DP:
==
* interrupts cleanup

DPU:
===
* DSPP sub-block flush on sc7280
* support AR30 in addition to XR30 format
* Allow using REC_0 and REC_1 to handle wide (4k) RGB planes
* Split the HW catalog into individual per-SoC files

DSI:
===
* rework DSI instance ID detection on obscure platforms

GPU:
===
* uapi C++ compatibility fix
* a6xx: More robust gdsc reset
* a3xx and a4xx devfreq support
* update generated headers
* various cleanups and fixes
* GPU and GEM updates to avoid allocations which could trigger
  reclaim (shrinker) in fence signaling path
* dma-fence deadline hint support and wait-boost
* a640 speedbin support
* a650 speedbin support

Conflicts in drivers/gpu/drm/msm/adreno/adreno_gpu.c:

Conflict between the 7fa5047a43 ("drm: Use of_property_present() for
testing DT property presence") and 9f251f9340 ("drm/msm/adreno: Use
OPP for every GPU generation"). The latter removed the of_ function
call outright, so I went with what's in the PR unchanged.

From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGvwuj5tabyW910+N-B=5kFNAC7QNYoQ=0xi3roBjQvFFQ@mail.gmail.com
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>

include/uapi/drm/msm_drm.h

@@ -151,8 +151,13 @@ struct drm_msm_gem_info {
 #define MSM_PREP_READ        0x01
 #define MSM_PREP_WRITE       0x02
 #define MSM_PREP_NOSYNC      0x04
+#define MSM_PREP_BOOST       0x08
 
-#define MSM_PREP_FLAGS       (MSM_PREP_READ | MSM_PREP_WRITE | MSM_PREP_NOSYNC)
+#define MSM_PREP_FLAGS       (MSM_PREP_READ | \
+			      MSM_PREP_WRITE | \
+			      MSM_PREP_NOSYNC | \
+			      MSM_PREP_BOOST | \
+			      0)
 
 struct drm_msm_gem_cpu_prep {
 	__u32 handle;         /* in */
@@ -181,7 +186,11 @@ struct drm_msm_gem_cpu_fini {
  */
 struct drm_msm_gem_submit_reloc {
 	__u32 submit_offset;  /* in, offset from submit_bo */
+#ifdef __cplusplus
+	__u32 _or;            /* in, value OR'd with result */
+#else
 	__u32 or;             /* in, value OR'd with result */
+#endif
 	__s32 shift;          /* in, amount of left shift (can be negative) */
 	__u32 reloc_idx;      /* in, index of reloc_bo buffer */
 	__u64 reloc_offset;   /* in, offset from start of reloc_bo */
@@ -286,6 +295,11 @@ struct drm_msm_gem_submit {
 
 };
 
+#define MSM_WAIT_FENCE_BOOST	0x00000001
+#define MSM_WAIT_FENCE_FLAGS	( \
+		MSM_WAIT_FENCE_BOOST | \
+		0)
+
 /* The normal way to synchronize with the GPU is just to CPU_PREP on
  * a buffer if you need to access it from the CPU (other cmdstream
  * submission from same or other contexts, PAGE_FLIP ioctl, etc, all
@@ -295,7 +309,7 @@ struct drm_msm_gem_submit {
  */
 struct drm_msm_wait_fence {
 	__u32 fence;          /* in */
-	__u32 pad;
+	__u32 flags;          /* in, bitmask of MSM_WAIT_FENCE_x */
 	struct drm_msm_timespec timeout;   /* in */
 	__u32 queueid;         /* in, submitqueue id */
 };