Merge tag 'drm-next-2025-07-30' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Highlights:

   - Intel xe enable Panthor Lake, started adding WildCat Lake

   - amdgpu has a bunch of reset improvments along with the usual IP
     updates

   - msm got VM_BIND support which is important for vulkan sparse memory

   - more drm_panic users

   - gpusvm common code to handle a bunch of core SVM work outside
     drivers.

  Detail summary:

  Changes outside drm subdirectory:
   - 'shrink_shmem_memory()' for better shmem/hibernate interaction
   - Rust support infrastructure:
      - make ETIMEDOUT available
      - add size constants up to SZ_2G
      - add DMA coherent allocation bindings
   - mtd driver for Intel GPU non-volatile storage
   - i2c designware quirk for Intel xe

  core:
   - atomic helpers: tune enable/disable sequences
   - add task info to wedge API
   - refactor EDID quirks
   - connector: move HDR sink to drm_display_info
   - fourcc: half-float and 32-bit float formats
   - mode_config: pass format info to simplify

  dma-buf:
   - heaps: Give CMA heap a stable name

  ci:
   - add device tree validation and kunit

  displayport:
   - change AUX DPCD access probe address
   - add quirk for DPCD probe
   - add panel replay definitions
   - backlight control helpers

  fbdev:
   - make CONFIG_FIRMWARE_EDID available on all arches

  fence:
   - fix UAF issues

  format-helper:
   - improve tests

  gpusvm:
   - introduce devmem only flag for allocation
   - add timeslicing support to GPU SVM

  ttm:
   - improve eviction

  sched:
   - tracing improvements
   - kunit improvements
   - memory leak fixes
   - reset handling improvements

  color mgmt:
   - add hardware gamma LUT handling helpers

  bridge:
   - add destroy hook
   - switch to reference counted drm_bridge allocations
   - tc358767: convert to devm_drm_bridge_alloc
   - improve CEC handling

  panel:
   - switch to reference counter drm_panel allocations
   - fwnode panel lookup
   - Huiling hl055fhv028c support
   - Raspberry Pi 7" 720x1280 support
   - edp: KDC KD116N3730A05, N160JCE-ELL CMN, N116BCJ-EAK
   - simple: AUO P238HAN01
   - st7701: Winstar wf40eswaa6mnn0
   - visionox: rm69299-shift
   - Renesas R61307, Renesas R69328 support
   - DJN HX83112B

  hdmi:
   - add CEC handling
   - YUV420 output support

  xe:
   - WildCat Lake support
   - Enable PanthorLake by default
   - mark BMG as SRIOV capable
   - update firmware recommendations
   - Expose media OA units
   - aux-bux support for non-volatile memory
   - MTD intel-dg driver for non-volatile memory
   - Expose fan control and voltage regulator in sysfs
   - restructure migration for multi-device
   - Restore GuC submit UAF fix
   - make GEM shrinker drm managed
   - SRIOV VF Post-migration recovery of GGTT nodes
   - W/A additions/reworks
   - Prefetch support for svm ranges
   - Don't allocate managed BO for each policy change
   - HWMON fixes for BMG
   - Create LRC BO without VM
   - PCI ID updates
   - make SLPC debugfs files optional
   - rework eviction rejection of bound external BOs
   - consolidate PAT programming logic for pre/post Xe2
   - init changes for flicker-free boot
   - Enable GuC Dynamic Inhibit Context switch

  i915:
   - drm_panic support for i915/xe
   - initial flip queue off by default for LNL/PNL
   - Wildcat Lake Display support
   - Support for DSC fractional link bpp
   - Support for simultaneous Panel Replay and Adaptive sync
   - Support for PTL+ double buffer LUT
   - initial PIPEDMC event handling
   - drm_panel_follower support
   - DPLL interface renames
   - allocate struct intel_display dynamically
   - flip queue preperation
   - abstract DRAM detection better
   - avoid GuC scheduling stalls
   - remove DG1 force probe requirement
   - fix MEI interrupt handler on RT kernels
   - use backlight control helpers for eDP
   - more shared display code refactoring

  amdgpu:
   - add userq slot to INFO ioctl
   - SR-IOV hibernation support
   - Suspend improvements
   - Backlight improvements
   - Use scaling for non-native eDP modes
   - cleaner shader updates for GC 9.x
   - Remove fence slab
   - SDMA fw checks for userq support
   - RAS updates
   - DMCUB updates
   - DP tunneling fixes
   - Display idle D3 support
   - Per queue reset improvements
   - initial smartmux support

  amdkfd:
   - enable KFD on loongarch
   - mtype fix for ext coherent system memory

  radeon:
   - CS validation additional GL extensions
   - drop console lock during suspend/resume
   - bump driver version

  msm:
   - VM BIND support
   - CI: infrastructure updates
   - UBWC single source of truth
   - decouple GPU and KMS support
   - DP: rework I/O accessors
   - DPU: SM8750 support
   - DSI: SM8750 support
   - GPU: X1-45 support and speedbin support for X1-85
   - MDSS: SM8750 support

  nova:
   - register! macro improvements
   - DMA object abstraction
   - VBIOS parser + fwsec lookup
   - sysmem flush page support
   - falcon: generic falcon boot code and HAL
   - FWSEC-FRTS: fb setup and load/execute

  ivpu:
   - Add Wildcat Lake support
   - Add turbo flag

  ast:
   - improve hardware generations implementation

  imx:
   - IMX8qxq Display Controller support

  lima:
   - Rockchip RK3528 GPU support

  nouveau:
   - fence handling cleanup

  panfrost:
   - MT8370 support
   - bo labeling
   - 64-bit register access

  qaic:
   - add RAS support

  rockchip:
   - convert inno_hdmi to a bridge

  rz-du:
   - add RZ/V2H(P) support
   - MIPI-DSI DCS support

  sitronix:
   - ST7567 support

  sun4i:
   - add H616 support

  tidss:
   - add TI AM62L support
   - AM65x OLDI bridge support

  bochs:
   - drm panic support

  vkms:
   - YUV and R* format support
   - use faux device

  vmwgfx:
   - fence improvements

  hyperv:
   - move out of simple
   - add drm_panic support"

* tag 'drm-next-2025-07-30' of https://gitlab.freedesktop.org/drm/kernel: (1479 commits)
  drm/tidss: oldi: convert to devm_drm_bridge_alloc() API
  drm/tidss: encoder: convert to devm_drm_bridge_alloc()
  drm/amdgpu: move reset support type checks into the caller
  drm/amdgpu/sdma7: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma6: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma5.2: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma5: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx12: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx11: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx10: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx9.4.3: re-emit unprocessed state on kcq reset
  drm/amdgpu/gfx9: re-emit unprocessed state on kcq reset
  drm/amdgpu: Add WARN_ON to the resource clear function
  drm/amd/pm: Use cached metrics data on SMUv13.0.6
  drm/amd/pm: Use cached data for min/max clocks
  gpu: nova-core: fix bounds check in PmuLookupTableEntry::new
  drm/amdgpu: Replace HQD terminology with slots naming
  drm/amdgpu: Add user queue instance count in HW IP info
  drm/amd/amdgpu: Add helper functions for isp buffers
  drm/amd/amdgpu: Initialize swnode for ISP MFD device
  ...

1 files changed, 232 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
index 322816805bfb..c417f8689220 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
@@ -218,15 +218,27 @@ int amdgpu_xcp_restore_partition_mode(struct amdgpu_xcp_mgr *xcp_mgr)
 	return __amdgpu_xcp_switch_partition_mode(xcp_mgr, xcp_mgr->mode);
 }
 
-int amdgpu_xcp_query_partition_mode(struct amdgpu_xcp_mgr *xcp_mgr, u32 flags)
+static bool __amdgpu_xcp_is_cached_mode_valid(struct amdgpu_xcp_mgr *xcp_mgr)
 {
-	int mode;
+	if (!xcp_mgr->funcs || !xcp_mgr->funcs->query_partition_mode)
+		return true;
 
 	if (!amdgpu_sriov_vf(xcp_mgr->adev) &&
 	    xcp_mgr->mode == AMDGPU_XCP_MODE_NONE)
-		return xcp_mgr->mode;
+		return true;
 
-	if (!xcp_mgr->funcs || !xcp_mgr->funcs->query_partition_mode)
+	if (xcp_mgr->mode != AMDGPU_XCP_MODE_NONE &&
+	    xcp_mgr->mode != AMDGPU_XCP_MODE_TRANS)
+		return true;
+
+	return false;
+}
+
+int amdgpu_xcp_query_partition_mode(struct amdgpu_xcp_mgr *xcp_mgr, u32 flags)
+{
+	int mode;
+
+	if (__amdgpu_xcp_is_cached_mode_valid(xcp_mgr))
 		return xcp_mgr->mode;
 
 	if (!(flags & AMDGPU_XCP_FL_LOCKED))
@@ -445,6 +457,222 @@ void amdgpu_xcp_release_sched(struct amdgpu_device *adev,
 	}
 }
 
+int amdgpu_xcp_select_scheds(struct amdgpu_device *adev,
+			     u32 hw_ip, u32 hw_prio,
+			     struct amdgpu_fpriv *fpriv,
+			     unsigned int *num_scheds,
+			     struct drm_gpu_scheduler ***scheds)
+{
+	u32 sel_xcp_id;
+	int i;
+	struct amdgpu_xcp_mgr *xcp_mgr = adev->xcp_mgr;
+
+	if (fpriv->xcp_id == AMDGPU_XCP_NO_PARTITION) {
+		u32 least_ref_cnt = ~0;
+
+		fpriv->xcp_id = 0;
+		for (i = 0; i < xcp_mgr->num_xcps; i++) {
+			u32 total_ref_cnt;
+
+			total_ref_cnt = atomic_read(&xcp_mgr->xcp[i].ref_cnt);
+			if (total_ref_cnt < least_ref_cnt) {
+				fpriv->xcp_id = i;
+				least_ref_cnt = total_ref_cnt;
+			}
+		}
+	}
+	sel_xcp_id = fpriv->xcp_id;
+
+	if (xcp_mgr->xcp[sel_xcp_id].gpu_sched[hw_ip][hw_prio].num_scheds) {
+		*num_scheds =
+			xcp_mgr->xcp[fpriv->xcp_id].gpu_sched[hw_ip][hw_prio].num_scheds;
+		*scheds =
+			xcp_mgr->xcp[fpriv->xcp_id].gpu_sched[hw_ip][hw_prio].sched;
+		atomic_inc(&adev->xcp_mgr->xcp[sel_xcp_id].ref_cnt);
+		dev_dbg(adev->dev, "Selected partition #%d", sel_xcp_id);
+	} else {
+		dev_err(adev->dev, "Failed to schedule partition #%d.", sel_xcp_id);
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+static void amdgpu_set_xcp_id(struct amdgpu_device *adev,
+			      uint32_t inst_idx,
+			      struct amdgpu_ring *ring)
+{
+	int xcp_id;
+	enum AMDGPU_XCP_IP_BLOCK ip_blk;
+	uint32_t inst_mask;
+
+	ring->xcp_id = AMDGPU_XCP_NO_PARTITION;
+	if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE)
+		adev->gfx.enforce_isolation[0].xcp_id = ring->xcp_id;
+	if ((adev->xcp_mgr->mode == AMDGPU_XCP_MODE_NONE) ||
+	    (ring->funcs->type == AMDGPU_RING_TYPE_CPER))
+		return;
+
+	inst_mask = 1 << inst_idx;
+
+	switch (ring->funcs->type) {
+	case AMDGPU_HW_IP_GFX:
+	case AMDGPU_RING_TYPE_COMPUTE:
+	case AMDGPU_RING_TYPE_KIQ:
+		ip_blk = AMDGPU_XCP_GFX;
+		break;
+	case AMDGPU_RING_TYPE_SDMA:
+		ip_blk = AMDGPU_XCP_SDMA;
+		break;
+	case AMDGPU_RING_TYPE_VCN_ENC:
+	case AMDGPU_RING_TYPE_VCN_JPEG:
+		ip_blk = AMDGPU_XCP_VCN;
+		break;
+	default:
+		dev_err(adev->dev, "Not support ring type %d!", ring->funcs->type);
+		return;
+	}
+
+	for (xcp_id = 0; xcp_id < adev->xcp_mgr->num_xcps; xcp_id++) {
+		if (adev->xcp_mgr->xcp[xcp_id].ip[ip_blk].inst_mask & inst_mask) {
+			ring->xcp_id = xcp_id;
+			dev_dbg(adev->dev, "ring:%s xcp_id :%u", ring->name,
+				ring->xcp_id);
+			if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE)
+				adev->gfx.enforce_isolation[xcp_id].xcp_id = xcp_id;
+			break;
+		}
+	}
+}
+
+static void amdgpu_xcp_gpu_sched_update(struct amdgpu_device *adev,
+					struct amdgpu_ring *ring,
+					unsigned int sel_xcp_id)
+{
+	unsigned int *num_gpu_sched;
+
+	num_gpu_sched = &adev->xcp_mgr->xcp[sel_xcp_id]
+			.gpu_sched[ring->funcs->type][ring->hw_prio].num_scheds;
+	adev->xcp_mgr->xcp[sel_xcp_id].gpu_sched[ring->funcs->type][ring->hw_prio]
+			.sched[(*num_gpu_sched)++] = &ring->sched;
+	dev_dbg(adev->dev, "%s :[%d] gpu_sched[%d][%d] = %d",
+		ring->name, sel_xcp_id, ring->funcs->type,
+		ring->hw_prio, *num_gpu_sched);
+}
+
+static int amdgpu_xcp_sched_list_update(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring;
+	int i;
+
+	for (i = 0; i < MAX_XCP; i++) {
+		atomic_set(&adev->xcp_mgr->xcp[i].ref_cnt, 0);
+		memset(adev->xcp_mgr->xcp[i].gpu_sched, 0, sizeof(adev->xcp_mgr->xcp->gpu_sched));
+	}
+
+	if (adev->xcp_mgr->mode == AMDGPU_XCP_MODE_NONE)
+		return 0;
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
+		ring = adev->rings[i];
+		if (!ring || !ring->sched.ready || ring->no_scheduler)
+			continue;
+
+		amdgpu_xcp_gpu_sched_update(adev, ring, ring->xcp_id);
+
+		/* VCN may be shared by two partitions under CPX MODE in certain
+		 * configs.
+		 */
+		if ((ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC ||
+		     ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) &&
+		    (adev->xcp_mgr->num_xcps > adev->vcn.num_vcn_inst))
+			amdgpu_xcp_gpu_sched_update(adev, ring, ring->xcp_id + 1);
+	}
+
+	return 0;
+}
+
+int amdgpu_xcp_update_partition_sched_list(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < adev->num_rings; i++) {
+		struct amdgpu_ring *ring = adev->rings[i];
+
+		if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE ||
+			ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+			amdgpu_set_xcp_id(adev, ring->xcc_id, ring);
+		else
+			amdgpu_set_xcp_id(adev, ring->me, ring);
+	}
+
+	return amdgpu_xcp_sched_list_update(adev);
+}
+
+void amdgpu_xcp_update_supported_modes(struct amdgpu_xcp_mgr *xcp_mgr)
+{
+	struct amdgpu_device *adev = xcp_mgr->adev;
+
+	xcp_mgr->supp_xcp_modes = 0;
+
+	switch (NUM_XCC(adev->gfx.xcc_mask)) {
+	case 8:
+		xcp_mgr->supp_xcp_modes = BIT(AMDGPU_SPX_PARTITION_MODE) |
+					  BIT(AMDGPU_DPX_PARTITION_MODE) |
+					  BIT(AMDGPU_QPX_PARTITION_MODE) |
+					  BIT(AMDGPU_CPX_PARTITION_MODE);
+		break;
+	case 6:
+		xcp_mgr->supp_xcp_modes = BIT(AMDGPU_SPX_PARTITION_MODE) |
+					  BIT(AMDGPU_TPX_PARTITION_MODE) |
+					  BIT(AMDGPU_CPX_PARTITION_MODE);
+		break;
+	case 4:
+		xcp_mgr->supp_xcp_modes = BIT(AMDGPU_SPX_PARTITION_MODE) |
+					  BIT(AMDGPU_DPX_PARTITION_MODE) |
+					  BIT(AMDGPU_CPX_PARTITION_MODE);
+		break;
+	case 2:
+		xcp_mgr->supp_xcp_modes = BIT(AMDGPU_SPX_PARTITION_MODE) |
+					  BIT(AMDGPU_CPX_PARTITION_MODE);
+		break;
+	case 1:
+		xcp_mgr->supp_xcp_modes = BIT(AMDGPU_SPX_PARTITION_MODE) |
+					  BIT(AMDGPU_CPX_PARTITION_MODE);
+		break;
+
+	default:
+		break;
+	}
+}
+
+int amdgpu_xcp_pre_partition_switch(struct amdgpu_xcp_mgr *xcp_mgr, u32 flags)
+{
+	/* TODO:
+	 * Stop user queues and threads, and make sure GPU is empty of work.
+	 */
+
+	if (flags & AMDGPU_XCP_OPS_KFD)
+		amdgpu_amdkfd_device_fini_sw(xcp_mgr->adev);
+
+	return 0;
+}
+
+int amdgpu_xcp_post_partition_switch(struct amdgpu_xcp_mgr *xcp_mgr, u32 flags)
+{
+	int ret = 0;
+
+	if (flags & AMDGPU_XCP_OPS_KFD) {
+		amdgpu_amdkfd_device_probe(xcp_mgr->adev);
+		amdgpu_amdkfd_device_init(xcp_mgr->adev);
+		/* If KFD init failed, return failure */
+		if (!xcp_mgr->adev->kfd.init_complete)
+			ret = -EIO;
+	}
+
+	return ret;
+}
+
 /*====================== xcp sysfs - configuration ======================*/
 #define XCP_CFG_SYSFS_RES_ATTR_SHOW(_name)                         \
 	static ssize_t amdgpu_xcp_res_sysfs_##_name##_show(        \