Merge tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Highlights are usual, more AMD IP blocks for future hw, i915/xe
  changes, Displayport tunnelling support for i915, msm YUV over DP
  changes, new tests for ttm, but its mostly a lot of stuff all over the
  place from lots of people.

  core:
   - EDID cleanups
   - scheduler error handling fixes
   - managed: add drmm_release_action() with tests
   - add ratelimited drm debug print
   - DPCD PSR early transport macro
   - DP tunneling and bandwidth allocation helpers
   - remove built-in edids
   - dp: Avoid AUX transfers on powered-down displays
   - dp: Add VSC SDP helpers

  cross drivers:
   - use new drm print helpers
   - switch to ->read_edid callback
   - gem: add stats for shared buffers plus updates to amdgpu, i915, xe

  syncobj:
   - fixes to waiting and sleeping

  ttm:
   - add tests
   - fix errno codes
   - simply busy-placement handling
   - fix page decryption

  media:
   - tc358743: fix v4l device registration

  video:
   - move all kernel parameters for video behind CONFIG_VIDEO

  sound:
   - remove <drm/drm_edid.h> include from header

  ci:
   - add tests for msm
   - fix apq8016 runner

  efifb:
   - use copy of global screen_info state

  vesafb:
   - use copy of global screen_info state

  simplefb:
   - fix logging

  bridge:
   - ite-6505: fix DP link-training bug
   - samsung-dsim: fix error checking in probe
   - samsung-dsim: add bsh-smm-s2/pro boards
   - tc358767: fix regmap usage
   - imx: add i.MX8MP HDMI PVI plus DT bindings
   - imx: add i.MX8MP HDMI TX plus DT bindings
   - sii902x: fix probing and unregistration
   - tc358767: limit pixel PLL input range
   - switch to new drm_bridge_read_edid() interface

  panel:
   - ltk050h3146w: error-handling fixes
   - panel-edp: support delay between power-on and enable; use put_sync
     in unprepare; support Mediatek MT8173 Chromebooks, BOE NV116WHM-N49
     V8.0, BOE NV122WUM-N41, CSO MNC207QS1-1 plus DT bindings
   - panel-lvds: support EDT ETML0700Z9NDHA plus DT bindings
   - panel-novatek: FRIDA FRD400B25025-A-CTK plus DT bindings
   - add BOE TH101MB31IG002-28A plus DT bindings
   - add EDT ETML1010G3DRA plus DT bindings
   - add Novatek NT36672E LCD DSI plus DT bindings
   - nt36523: support 120Hz timings, fix includes
   - simple: fix display timings on RK32FN48H
   - visionox-vtdr6130: fix initialization
   - add Powkiddy RGB10MAX3 plus DT bindings
   - st7703: support panel rotation plus DT bindings
   - add Himax HX83112A plus DT bindings
   - ltk500hd1829: add support for ltk101b4029w and admatec 9904370
   - simple: add BOE BP082WX1-100 8.2" panel plus DT bindungs

  panel-orientation-quirks:
   - GPD Win Mini

  amdgpu:
   - Validate DMABuf imports in compute VMs
   - Add RAS ACA framework
   - PSP 13 fixes
   - Misc code cleanups
   - Replay fixes
   - Atom interpretor PS, WS bounds checking
   - DML2 fixes
   - Audio fixes
   - DCN 3.5 Z state fixes
   - Remove deprecated ida_simple usage
   - UBSAN fixes
   - RAS fixes
   - Enable seq64 infrastructure
   - DC color block enablement
   - Documentation updates
   - DC documentation updates
   - DMCUB updates
   - ATHUB 4.1 support
   - LSDMA 7.0 support
   - JPEG DPG support
   - IH 7.0 support
   - HDP 7.0 support
   - VCN 5.0 support
   - SMU 13.0.6 updates
   - NBIO 7.11 updates
   - SDMA 6.1 updates
   - MMHUB 3.3 updates
   - DCN 3.5.1 support
   - NBIF 6.3.1 support
   - VPE 6.1.1 support

  amdkfd:
   - Validate DMABuf imports in compute VMs
   - SVM fixes
   - Trap handler updates and enhancements
   - Fix cache size reporting
   - Relocate the trap handler

  radeon:
   - Atom interpretor PS, WS bounds checking
   - Misc code cleanups

  xe:
   - new query for GuC submission version
   - Remove unused persistent exec_queues
   - Add vram frequency sysfs attributes
   - Add the flag XE_VM_BIND_FLAG_DUMPABLE
   - Drop pre-production workarounds
   - Drop kunit tests for unsupported platforms
   - Start pumbling SR-IOV support with memory based interrupts for VF
   - Allow to map BO in GGTT with PAT index corresponding to XE_CACHE_UC
     to work with memory based interrupts
   - Add GuC Doorbells Manager as prep work SR-IOV
   - Implement additional workarounds for xe2 and MTL
   - Program a few registers according to perfomance guide spec for Xe2
   - Fix remaining 32b build issues and enable it back
   - Fix build with CONFIG_DEBUG_FS=n
   - Fix warnings from GuC ABI headers
   - Introduce Relay Communication for SR-IOV for VF <-> GuC <-> PF
   - Release mmap mappings on rpm suspend
   - Disable mid-thread preemption when not properly supported by
     hardware
   - Fix xe_exec by reserving extra fence slot for CPU bind
   - Fix xe_exec with full long running exec queue
   - Canonicalize addresses where needed for Xe2 and add to devcoredum
   - Toggle USM support for Xe2
   - Only allow 1 ufence per exec / bind IOCTL
   - Add GuC firmware loading for Lunar Lake
   - Add XE_VMA_PTE_64K VMA flag

  i915:
   - Add more ADL-N PCI IDs
   - Enable fastboot also on older platforms
   - Early transport for panel replay and PSR
   - New ARL PCI IDs
   - DP TPS4 PHY test pattern support
   - Unify and improve VSC SDP for PSR and non-PSR cases
   - Refactor memory regions and improve debug logging
   - Rework global state serialization
   - Remove unused CDCLK divider fields
   - Unify HDCP connector logging format
   - Use display instead of graphics version in display code
   - Move VBT and opregion debugfs next to the implementation
   - Abstract opregion interface, use opaque type
   - MTL fixes
   - HPD handling fixes
   - Add GuC submission interface version query
   - Atomically invalidate userptr on mmu-notifier
   - Update handling of MMIO triggered reports
   - Don't make assumptions about intel_wakeref_t type
   - Extend driver code of Xe_LPG to Xe_LPG+
   - Add flex arrays to struct i915_syncmap
   - Allow for very slow HuC loading
   - DP tunneling and bandwidth allocation support

  msm:
   - Correct bindings for MSM8976 and SM8650 platforms
   - Start migration of MDP5 platforms to DPU driver
   - X1E80100 MDSS support
   - DPU:
      - Improve DSC allocation, fixing several important corner cases
      - Add support for SDM630/SDM660 platforms
      - Simplify dpu_encoder_phys_ops
      - Apply fixes targeting DSC support with a single DSC encoder
      - Apply fixes for HCTL_EN timing configuration
      - X1E80100 support
      - Add support for YUV420 over DP
   - GPU:
      - fix sc7180 UBWC config
      - fix a7xx LLC config
      - new gpu support: a305B, a750, a702
      - machine support: SM7150 (different power levels than other a618)
      - a7xx devcoredump support

  habanalabs:
   - configure IRQ affinity according to NUMA node
   - move HBM MMU page tables inside the HBM
   - improve device reset
   - check extended PCIe errors

  ivpu:
   - updates to firmware API
   - refactor BO allocation

  imx:
   - use devm_ functions during init

  hisilicon:
   - fix EDID includes

  mgag200:
   - improve ioremap usage
   - convert to struct drm_edid
   - Work around PCI write bursts

  nouveau:
   - disp: use kmemdup()
   - fix EDID includes
   - documentation fixes

  qaic:
   - fixes to BO handling
   - make use of DRM managed release
   - fix order of remove operations

  rockchip:
   - analogix_dp: get encoder port from DT
   - inno_hdmi: support HDMI for RK3128
   - lvds: error-handling fixes

  ssd130x:
   - support SSD133x plus DT bindings

  tegra:
   - fix error handling

  tilcdc:
   - make use of DRM managed release

  v3d:
   - show memory stats in debugfs
   - Support display MMU page size

  vc4:
   - fix error handling in plane prepare_fb
   - fix framebuffer test in plane helpers

  virtio:
   - add venus capset defines

  vkms:
   - fix OOB access when programming the LUT
   - Kconfig improvements

  vmwgfx:
   - unmap surface before changing plane state
   - fix memory leak in error handling
   - documentation fixes
   - list command SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 as invalid
   - fix null-pointer deref in execbuf
   - refactor display-mode probing
   - fix fencing for creating cursor MOBs
   - fix cursor-memory lifetime

  xlnx:
   - fix live video input for ZynqMP DPSUB

  lima:
   - fix memory leak

  loongson:
   - fail if no VRAM present

  meson:
   - switch to new drm_bridge_read_edid() interface

  renesas:
   - add RZ/G2L DU support plus DT bindings

  mxsfb:
   - Use managed mode config

  sun4i:
   - HDMI: updates to atomic mode setting

  mediatek:
   - Add display driver for MT8188 VDOSYS1
   - DSI driver cleanups
   - Filter modes according to hardware capability
   - Fix a null pointer crash in mtk_drm_crtc_finish_page_flip

  etnaviv:
   - enhancements for NPU and MRT support"

* tag 'drm-next-2024-03-13' of https://gitlab.freedesktop.org/drm/kernel: (1420 commits)
  drm/amd/display: Removed redundant @ symbol to fix kernel-doc warnings in -next repo
  drm/amd/pm: wait for completion of the EnableGfxImu message
  drm/amdgpu/soc21: add mode2 asic reset for SMU IP v14.0.1
  drm/amdgpu: add smu 14.0.1 support
  drm/amdgpu: add VPE 6.1.1 discovery support
  drm/amdgpu/vpe: add VPE 6.1.1 support
  drm/amdgpu/vpe: don't emit cond exec command under collaborate mode
  drm/amdgpu/vpe: add collaborate mode support for VPE
  drm/amdgpu/vpe: add PRED_EXE and COLLAB_SYNC OPCODE
  drm/amdgpu/vpe: add multi instance VPE support
  drm/amdgpu/discovery: add nbif v6_3_1 ip block
  drm/amdgpu: Add nbif v6_3_1 ip block support
  drm/amdgpu: Add pcie v6_1_0 ip headers (v5)
  drm/amdgpu: Add nbif v6_3_1 ip headers (v5)
  arch/powerpc: Remove <linux/fb.h> from backlight code
  macintosh/via-pmu-backlight: Include <linux/backlight.h>
  fbdev/chipsfb: Include <linux/backlight.h>
  drm/etnaviv: Restore some id values
  drm/amdkfd: make kfd_class constant
  drm/amdgpu: add ring timeout information in devcoredump
  ...

1 files changed, 81 insertions, 42 deletions

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 49223026c89f..11e150f4c0c1 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -30,21 +30,23 @@ enum xe_exec_queue_sched_prop {
 	XE_EXEC_QUEUE_SCHED_PROP_MAX = 3,
 };
 
-static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
-						    struct xe_vm *vm,
-						    u32 logical_mask,
-						    u16 width, struct xe_hw_engine *hwe,
-						    u32 flags)
+static int exec_queue_user_extensions(struct xe_device *xe, struct xe_exec_queue *q,
+				      u64 extensions, int ext_number, bool create);
+
+static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
+						   struct xe_vm *vm,
+						   u32 logical_mask,
+						   u16 width, struct xe_hw_engine *hwe,
+						   u32 flags, u64 extensions)
 {
 	struct xe_exec_queue *q;
 	struct xe_gt *gt = hwe->gt;
 	int err;
-	int i;
 
 	/* only kernel queues can be permanent */
 	XE_WARN_ON((flags & EXEC_QUEUE_FLAG_PERMANENT) && !(flags & EXEC_QUEUE_FLAG_KERNEL));
 
-	q = kzalloc(sizeof(*q) + sizeof(struct xe_lrc) * width, GFP_KERNEL);
+	q = kzalloc(struct_size(q, lrc, width), GFP_KERNEL);
 	if (!q)
 		return ERR_PTR(-ENOMEM);
 
@@ -52,8 +54,6 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
 	q->flags = flags;
 	q->hwe = hwe;
 	q->gt = gt;
-	if (vm)
-		q->vm = xe_vm_get(vm);
 	q->class = hwe->class;
 	q->width = width;
 	q->logical_mask = logical_mask;
@@ -66,23 +66,51 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
 	q->sched_props.timeslice_us = hwe->eclass->sched_props.timeslice_us;
 	q->sched_props.preempt_timeout_us =
 				hwe->eclass->sched_props.preempt_timeout_us;
+	q->sched_props.job_timeout_ms =
+				hwe->eclass->sched_props.job_timeout_ms;
 	if (q->flags & EXEC_QUEUE_FLAG_KERNEL &&
 	    q->flags & EXEC_QUEUE_FLAG_HIGH_PRIORITY)
 		q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_KERNEL;
 	else
 		q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_NORMAL;
 
+	if (extensions) {
+		/*
+		 * may set q->usm, must come before xe_lrc_init(),
+		 * may overwrite q->sched_props, must come before q->ops->init()
+		 */
+		err = exec_queue_user_extensions(xe, q, extensions, 0, true);
+		if (err) {
+			kfree(q);
+			return ERR_PTR(err);
+		}
+	}
+
+	if (vm)
+		q->vm = xe_vm_get(vm);
+
 	if (xe_exec_queue_is_parallel(q)) {
 		q->parallel.composite_fence_ctx = dma_fence_context_alloc(1);
 		q->parallel.composite_fence_seqno = XE_FENCE_INITIAL_SEQNO;
 	}
-	if (q->flags & EXEC_QUEUE_FLAG_VM) {
-		q->bind.fence_ctx = dma_fence_context_alloc(1);
-		q->bind.fence_seqno = XE_FENCE_INITIAL_SEQNO;
-	}
 
-	for (i = 0; i < width; ++i) {
-		err = xe_lrc_init(q->lrc + i, hwe, q, vm, SZ_16K);
+	return q;
+}
+
+static void __xe_exec_queue_free(struct xe_exec_queue *q)
+{
+	if (q->vm)
+		xe_vm_put(q->vm);
+	kfree(q);
+}
+
+static int __xe_exec_queue_init(struct xe_exec_queue *q)
+{
+	struct xe_device *xe = gt_to_xe(q->gt);
+	int i, err;
+
+	for (i = 0; i < q->width; ++i) {
+		err = xe_lrc_init(q->lrc + i, q->hwe, q, q->vm, SZ_16K);
 		if (err)
 			goto err_lrc;
 	}
@@ -99,35 +127,47 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
 	 * can perform GuC CT actions when needed. Caller is expected to have
 	 * already grabbed the rpm ref outside any sensitive locks.
 	 */
-	if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && (q->flags & EXEC_QUEUE_FLAG_VM || !vm))
+	if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && (q->flags & EXEC_QUEUE_FLAG_VM || !q->vm))
 		drm_WARN_ON(&xe->drm, !xe_device_mem_access_get_if_ongoing(xe));
 
-	return q;
+	return 0;
 
 err_lrc:
 	for (i = i - 1; i >= 0; --i)
 		xe_lrc_finish(q->lrc + i);
-	kfree(q);
-	return ERR_PTR(err);
+	return err;
 }
 
 struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *vm,
 					   u32 logical_mask, u16 width,
-					   struct xe_hw_engine *hwe, u32 flags)
+					   struct xe_hw_engine *hwe, u32 flags,
+					   u64 extensions)
 {
 	struct xe_exec_queue *q;
 	int err;
 
+	q = __xe_exec_queue_alloc(xe, vm, logical_mask, width, hwe, flags,
+				  extensions);
+	if (IS_ERR(q))
+		return q;
+
 	if (vm) {
 		err = xe_vm_lock(vm, true);
 		if (err)
-			return ERR_PTR(err);
+			goto err_post_alloc;
 	}
-	q = __xe_exec_queue_create(xe, vm, logical_mask, width, hwe, flags);
+
+	err = __xe_exec_queue_init(q);
 	if (vm)
 		xe_vm_unlock(vm);
+	if (err)
+		goto err_post_alloc;
 
 	return q;
+
+err_post_alloc:
+	__xe_exec_queue_free(q);
+	return ERR_PTR(err);
 }
 
 struct xe_exec_queue *xe_exec_queue_create_class(struct xe_device *xe, struct xe_gt *gt,
@@ -152,7 +192,7 @@ struct xe_exec_queue *xe_exec_queue_create_class(struct xe_device *xe, struct xe
 	if (!logical_mask)
 		return ERR_PTR(-ENODEV);
 
-	return xe_exec_queue_create(xe, vm, logical_mask, 1, hwe0, flags);
+	return xe_exec_queue_create(xe, vm, logical_mask, 1, hwe0, flags, 0);
 }
 
 void xe_exec_queue_destroy(struct kref *ref)
@@ -178,10 +218,7 @@ void xe_exec_queue_fini(struct xe_exec_queue *q)
 		xe_lrc_finish(q->lrc + i);
 	if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && (q->flags & EXEC_QUEUE_FLAG_VM || !q->vm))
 		xe_device_mem_access_put(gt_to_xe(q->gt));
-	if (q->vm)
-		xe_vm_put(q->vm);
-
-	kfree(q);
+	__xe_exec_queue_free(q);
 }
 
 void xe_exec_queue_assign_name(struct xe_exec_queue *q, u32 instance)
@@ -239,7 +276,11 @@ static int exec_queue_set_priority(struct xe_device *xe, struct xe_exec_queue *q
 	if (XE_IOCTL_DBG(xe, value > xe_exec_queue_device_get_max_priority(xe)))
 		return -EPERM;
 
-	return q->ops->set_priority(q, value);
+	if (!create)
+		return q->ops->set_priority(q, value);
+
+	q->sched_props.priority = value;
+	return 0;
 }
 
 static bool xe_exec_queue_enforce_schedule_limit(void)
@@ -306,7 +347,11 @@ static int exec_queue_set_timeslice(struct xe_device *xe, struct xe_exec_queue *
 	    !xe_hw_engine_timeout_in_range(value, min, max))
 		return -EINVAL;
 
-	return q->ops->set_timeslice(q, value);
+	if (!create)
+		return q->ops->set_timeslice(q, value);
+
+	q->sched_props.timeslice_us = value;
+	return 0;
 }
 
 typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe,
@@ -535,6 +580,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 	if (eci[0].engine_class == DRM_XE_ENGINE_CLASS_VM_BIND) {
 		for_each_gt(gt, xe, id) {
 			struct xe_exec_queue *new;
+			u32 flags;
 
 			if (xe_gt_is_media_type(gt))
 				continue;
@@ -553,14 +599,12 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 			/* The migration vm doesn't hold rpm ref */
 			xe_device_mem_access_get(xe);
 
+			flags = EXEC_QUEUE_FLAG_VM | (id ? EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD : 0);
+
 			migrate_vm = xe_migrate_get_vm(gt_to_tile(gt)->migrate);
 			new = xe_exec_queue_create(xe, migrate_vm, logical_mask,
-						   args->width, hwe,
-						   EXEC_QUEUE_FLAG_PERSISTENT |
-						   EXEC_QUEUE_FLAG_VM |
-						   (id ?
-						    EXEC_QUEUE_FLAG_BIND_ENGINE_CHILD :
-						    0));
+						   args->width, hwe, flags,
+						   args->extensions);
 
 			xe_device_mem_access_put(xe); /* now held by engine */
 
@@ -606,7 +650,8 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 		}
 
 		q = xe_exec_queue_create(xe, vm, logical_mask,
-					 args->width, hwe, 0);
+					 args->width, hwe, 0,
+					 args->extensions);
 		up_read(&vm->lock);
 		xe_vm_put(vm);
 		if (IS_ERR(q))
@@ -622,12 +667,6 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 		}
 	}
 
-	if (args->extensions) {
-		err = exec_queue_user_extensions(xe, q, args->extensions, 0, true);
-		if (XE_IOCTL_DBG(xe, err))
-			goto kill_exec_queue;
-	}
-
 	mutex_lock(&xef->exec_queue.lock);
 	err = xa_alloc(&xef->exec_queue.xa, &id, q, xa_limit_32b, GFP_KERNEL);
 	mutex_unlock(&xef->exec_queue.lock);