Merge tag 'drm-next-2024-09-19' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "This adds a couple of patches outside the drm core, all should be
  acked appropriately, the string and pstore ones are the main ones that
  come to mind.

  Otherwise it's the usual drivers, xe is getting enabled by default on
  some new hardware, we've changed the device number handling to allow
  more devices, and we added some optional rust code to create QR codes
  in the panic handler, an idea first suggested I think 10 years ago :-)

  string:
   - add mem_is_zero()

  core:
   - support more device numbers
   - use XArray for minor ids
   - add backlight constants
   - Split dma fence array creation into alloc and arm

  fbdev:
   - remove usage of old fbdev hooks

  kms:
   - Add might_fault() to drm_modeset_lock priming
   - Add dynamic per-crtc vblank configuration support

  dma-buf:
   - docs cleanup

  buddy:
   - Add start address support for trim function

  printk:
   - pass description to kmsg_dump

  scheduler:
   - Remove full_recover from drm_sched_start

  ttm:
   - Make LRU walk restartable after dropping locks
   - Allow direct reclaim to allocate local memory

  panic:
   - add display QR code (in rust)

  displayport:
   - mst: GUID improvements

  bridge:
   - Silence error message on -EPROBE_DEFER
   - analogix: Clean aup
   - bridge-connector: Fix double free
   - lt6505: Disable interrupt when powered off
   - tc358767: Make default DP port preemphasis configurable
   - lt9611uxc: require DRM_BRIDGE_ATTACH_NO_CONNECTOR
   - anx7625: simplify OF array handling
   - dw-hdmi: simplify clock handling
   - lontium-lt8912b: fix mode validation
   - nwl-dsi: fix mode vsync/hsync polarity

  xe:
   - Enable LunarLake and Battlemage support
   - Introducing Xe2 ccs modifiers for integrated and discrete graphics
   - rename xe perf to xe observation
   - use wb caching on DGFX for system memory
   - add fence timeouts
   - Lunar Lake graphics/media/display workarounds
   - Battlemage workarounds
   - Battlemage GSC support
   - GSC and HuC fw updates for LL/BM
   - use dma_fence_chain_free
   - refactor hw engine lookup and mmio access
   - enable priority mem read for Xe2
   - Add first GuC BMG fw
   - fix dma-resv lock
   - Fix DGFX display suspend/resume
   - Use xe_managed for kernel BOs
   - Use reserved copy engine for user binds on faulting devices
   - Allow mixing dma-fence jobs and long-running faulting jobs
   - fix media TLB invalidation
   - fix rpm in TTM swapout path
   - track resources and VF state by PF

  i915:
   - Type-C programming fix for MTL+
   - FBC cleanup
   - Calc vblank delay more accurately
   - On DP MST, Enable LT fallback for UHBR<->non-UHBR rates
   - Fix DP LTTPR detection
   - limit relocations to INT_MAX
   - fix long hangs in buddy allocator on DG2/A380

  amdgpu:
   - Per-queue reset support
   - SDMA devcoredump support
   - DCN 4.0.1 updates
   - GFX12/VCN4/JPEG4 updates
   - Convert vbios embedded EDID to drm_edid
   - GFX9.3/9.4 devcoredump support
   - process isolation framework for GFX 9.4.3/4
   - take IOMMU mappings into account for P2P DMA

  amdkfd:
   - CRIU fixes
   - HMM fix
   - Enable process isolation support for GFX 9.4.3/4
   - Allow users to target recommended SDMA engines
   - KFD support for targetting queues on recommended SDMA engines

  radeon:
   - remove .load and drm_dev_alloc
   - Fix vbios embedded EDID size handling
   - Convert vbios embedded EDID to drm_edid
   - Use GEM references instead of TTM
   - r100 cp init cleanup
   - Fix potential overflows in evergreen CS offset tracking

  msm:
   - DPU:
      - implement DP/PHY mapping on SC8180X
      - Enable writeback on SM8150, SC8180X, SM6125, SM6350
   - DP:
      - Enable widebus on all relevant chipsets
      - MSM8998 HDMI support
   - GPU:
      - A642L speedbin support
      - A615/A306/A621 support
      - A7xx devcoredump support

  ast:
   - astdp: Support AST2600 with VGA
   - Clean up HPD
   - Fix timeout loop for DP link training
   - reorganize output code by type (VGA, DP, etc)
   - convert to struct drm_edid
   - fix BMC handling for all outputs

  exynos:
   - drop stale MAINTAINERS pattern
   - constify struct

  loongson:
   - use GEM refcount over TTM

  mgag200:
   - Improve BMC handling
   - Support VBLANK intterupts
   - transparently support BMC outputs

  nouveau:
   - Refactor and clean up internals
   - Use GEM refcount over TTM's

  gm12u320:
   - convert to struct drm_edid

  gma500:
   - update i2c terms

  lcdif:
   - pixel clock fix

  host1x:
   - fix syncpoint IRQ during resume
   - use iommu_paging_domain_alloc()

  imx:
   - ipuv3: convert to struct drm_edid

  omapdrm:
   - improve error handling
   - use common helper for_each_endpoint_of_node()

  panel:
   - add support for BOE TV101WUM-LL2 plus DT bindings
   - novatek-nt35950: improve error handling
   - nv3051d: improve error handling
   - panel-edp:
      - add support for BOE NE140WUM-N6G
      - revert support for SDC ATNA45AF01
   - visionox-vtdr6130:
      - improve error handling
      - use devm_regulator_bulk_get_const()
   - boe-th101mb31ig002:
      - Support for starry-er88577 MIPI-DSI panel plus DT
      - Fix porch parameter
   - edp: Support AOU B116XTN02.3, AUO B116XAN06.1, AOU B116XAT04.1, BOE
     NV140WUM-N41, BOE NV133WUM-N63, BOE NV116WHM-A4D, CMN N116BCA-EA2,
     CMN N116BCP-EA2, CSW MNB601LS1-4
   - himax-hx8394: Support Microchip AC40T08A MIPI Display panel plus DT
   - ilitek-ili9806e: Support Densitron DMT028VGHMCMI-1D TFT plus DT
   - jd9365da:
      - Support Melfas lmfbx101117480 MIPI-DSI panel plus DT
      - Refactor for code sharing
   - panel-edp: fix name for HKC MB116AN01
   - jd9365da: fix "exit sleep" commands
   - jdi-fhd-r63452: simplify error handling with DSI multi-style
     helpers
   - mantix-mlaf057we51: simplify error handling with DSI multi-style
     helpers
   - simple:
      - support Innolux G070ACE-LH3 plus DT bindings
      - support On Tat Industrial Company KD50G21-40NT-A1 plus DT
        bindings
   - st7701:
      - decouple DSI and DRM code
      - add SPI support
      - support Anbernic RG28XX plus DT bindings

  mediatek:
   - support alpha blending
   - remove cl in struct cmdq_pkt
   - ovl adaptor fix
   - add power domain binding for mediatek DPI controller

  renesas:
   - rz-du: add support for RZ/G2UL plus DT bindings

  rockchip:
   - Improve DP sink-capability reporting
   - dw_hdmi: Support 4k@60Hz
   - vop:
      - Support RGB display on Rockchip RK3066
      - Support 4096px width

  sti:
   - convert to struct drm_edid

  stm:
   - Avoid UAF wih managed plane and CRTC helpers
   - Fix module owner
   - Fix error handling in probe
   - Depend on COMMON_CLK
   - ltdc:
      - Fix transparency after disabling plane
      - Remove unused interrupt

  tegra:
   - gr3d: improve PM domain handling
   - convert to struct drm_edid
   - Call drm_atomic_helper_shutdown()

  vc4:
   - fix PM during detect
   - replace DRM_ERROR() with drm_error()
   - v3d: simplify clock retrieval

  v3d:
   - Clean up perfmon

  virtio:
   - add DRM capset"

* tag 'drm-next-2024-09-19' of https://gitlab.freedesktop.org/drm/kernel: (1326 commits)
  drm/xe: Fix missing conversion to xe_display_pm_runtime_resume
  drm/xe/xe2hpg: Add Wa_15016589081
  drm/xe: Don't keep stale pointer to bo->ggtt_node
  drm/xe: fix missing 'xe_vm_put'
  drm/xe: fix build warning with CONFIG_PM=n
  drm/xe: Suppress missing outer rpm protection warning
  drm/xe: prevent potential UAF in pf_provision_vf_ggtt()
  drm/amd/display: Add all planes on CRTC to state for overlay cursor
  drm/i915/bios: fix printk format width
  drm/i915/display: Fix BMG CCS modifiers
  drm/amdgpu: get rid of bogus includes of fdtable.h
  drm/amdkfd: CRIU fixes
  drm/amdgpu: fix a race in kfd_mem_export_dmabuf()
  drm: new helper: drm_gem_prime_handle_to_dmabuf()
  drm/amdgpu/atomfirmware: Silence UBSAN warning
  drm/amdgpu: Fix kdoc entry in 'amdgpu_vm_cpu_prepare'
  drm/amd/amdgpu: apply command submission parser for JPEG v1
  drm/amd/amdgpu: apply command submission parser for JPEG v2+
  drm/amd/pm: fix the pp_dpm_pcie issue on smu v14.0.2/3
  drm/amd/pm: update the features set on smu v14.0.2/3
  ...

2 files changed, 93 insertions, 14 deletions

diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 285a36601dc9..717307d6b5b7 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -42,9 +42,10 @@
  * - 1.14 - Update kfd_event_data
  * - 1.15 - Enable managing mappings in compute VMs with GEM_VA ioctl
  * - 1.16 - Add contiguous VRAM allocation flag
+ * - 1.17 - Add SDMA queue creation with target SDMA engine ID
  */
 #define KFD_IOCTL_MAJOR_VERSION 1
-#define KFD_IOCTL_MINOR_VERSION 16
+#define KFD_IOCTL_MINOR_VERSION 17
 
 struct kfd_ioctl_get_version_args {
 	__u32 major_version;	/* from KFD */
@@ -56,6 +57,7 @@ struct kfd_ioctl_get_version_args {
 #define KFD_IOC_QUEUE_TYPE_SDMA			0x1
 #define KFD_IOC_QUEUE_TYPE_COMPUTE_AQL		0x2
 #define KFD_IOC_QUEUE_TYPE_SDMA_XGMI		0x3
+#define KFD_IOC_QUEUE_TYPE_SDMA_BY_ENG_ID	0x4
 
 #define KFD_MAX_QUEUE_PERCENTAGE	100
 #define KFD_MAX_QUEUE_PRIORITY		15
@@ -78,6 +80,8 @@ struct kfd_ioctl_create_queue_args {
 	__u64 ctx_save_restore_address; /* to KFD */
 	__u32 ctx_save_restore_size;	/* to KFD */
 	__u32 ctl_stack_size;		/* to KFD */
+	__u32 sdma_engine_id;		/* to KFD */
+	__u32 pad;
 };
 
 struct kfd_ioctl_destroy_queue_args {
@@ -536,26 +540,29 @@ enum kfd_smi_event {
 	KFD_SMI_EVENT_ALL_PROCESS = 64
 };
 
+/* The reason of the page migration event */
 enum KFD_MIGRATE_TRIGGERS {
-	KFD_MIGRATE_TRIGGER_PREFETCH,
-	KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU,
-	KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU,
-	KFD_MIGRATE_TRIGGER_TTM_EVICTION
+	KFD_MIGRATE_TRIGGER_PREFETCH,		/* Prefetch to GPU VRAM or system memory */
+	KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU,	/* GPU page fault recover */
+	KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU,	/* CPU page fault recover */
+	KFD_MIGRATE_TRIGGER_TTM_EVICTION	/* TTM eviction */
 };
 
+/* The reason of user queue evition event */
 enum KFD_QUEUE_EVICTION_TRIGGERS {
-	KFD_QUEUE_EVICTION_TRIGGER_SVM,
-	KFD_QUEUE_EVICTION_TRIGGER_USERPTR,
-	KFD_QUEUE_EVICTION_TRIGGER_TTM,
-	KFD_QUEUE_EVICTION_TRIGGER_SUSPEND,
-	KFD_QUEUE_EVICTION_CRIU_CHECKPOINT,
-	KFD_QUEUE_EVICTION_CRIU_RESTORE
+	KFD_QUEUE_EVICTION_TRIGGER_SVM,		/* SVM buffer migration */
+	KFD_QUEUE_EVICTION_TRIGGER_USERPTR,	/* userptr movement */
+	KFD_QUEUE_EVICTION_TRIGGER_TTM,		/* TTM move buffer */
+	KFD_QUEUE_EVICTION_TRIGGER_SUSPEND,	/* GPU suspend */
+	KFD_QUEUE_EVICTION_CRIU_CHECKPOINT,	/* CRIU checkpoint */
+	KFD_QUEUE_EVICTION_CRIU_RESTORE		/* CRIU restore */
 };
 
+/* The reason of unmap buffer from GPU event */
 enum KFD_SVM_UNMAP_TRIGGERS {
-	KFD_SVM_UNMAP_TRIGGER_MMU_NOTIFY,
-	KFD_SVM_UNMAP_TRIGGER_MMU_NOTIFY_MIGRATE,
-	KFD_SVM_UNMAP_TRIGGER_UNMAP_FROM_CPU
+	KFD_SVM_UNMAP_TRIGGER_MMU_NOTIFY,	/* MMU notifier CPU buffer movement */
+	KFD_SVM_UNMAP_TRIGGER_MMU_NOTIFY_MIGRATE,/* MMU notifier page migration */
+	KFD_SVM_UNMAP_TRIGGER_UNMAP_FROM_CPU	/* Unmap to free the buffer */
 };
 
 #define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1))
@@ -566,6 +573,77 @@ struct kfd_ioctl_smi_events_args {
 	__u32 anon_fd;	/* from KFD */
 };
 
+/*
+ * SVM event tracing via SMI system management interface
+ *
+ * Open event file descriptor
+ *    use ioctl AMDKFD_IOC_SMI_EVENTS, pass in gpuid and return a anonymous file
+ *    descriptor to receive SMI events.
+ *    If calling with sudo permission, then file descriptor can be used to receive
+ *    SVM events from all processes, otherwise, to only receive SVM events of same
+ *    process.
+ *
+ * To enable the SVM event
+ *    Write event file descriptor with KFD_SMI_EVENT_MASK_FROM_INDEX(event) bitmap
+ *    mask to start record the event to the kfifo, use bitmap mask combination
+ *    for multiple events. New event mask will overwrite the previous event mask.
+ *    KFD_SMI_EVENT_MASK_FROM_INDEX(KFD_SMI_EVENT_ALL_PROCESS) bit requires sudo
+ *    permisson to receive SVM events from all process.
+ *
+ * To receive the event
+ *    Application can poll file descriptor to wait for the events, then read event
+ *    from the file into a buffer. Each event is one line string message, starting
+ *    with the event id, then the event specific information.
+ *
+ * To decode event information
+ *    The following event format string macro can be used with sscanf to decode
+ *    the specific event information.
+ *    event triggers: the reason to generate the event, defined as enum for unmap,
+ *    eviction and migrate events.
+ *    node, from, to, prefetch_loc, preferred_loc: GPU ID, or 0 for system memory.
+ *    addr: user mode address, in pages
+ *    size: in pages
+ *    pid: the process ID to generate the event
+ *    ns: timestamp in nanosecond-resolution, starts at system boot time but
+ *        stops during suspend
+ *    migrate_update: GPU page fault is recovered by 'M' for migrate, 'U' for update
+ *    rw: 'W' for write page fault, 'R' for read page fault
+ *    rescheduled: 'R' if the queue restore failed and rescheduled to try again
+ */
+#define KFD_EVENT_FMT_UPDATE_GPU_RESET(reset_seq_num, reset_cause)\
+		"%x %s\n", (reset_seq_num), (reset_cause)
+
+#define KFD_EVENT_FMT_THERMAL_THROTTLING(bitmask, counter)\
+		"%llx:%llx\n", (bitmask), (counter)
+
+#define KFD_EVENT_FMT_VMFAULT(pid, task_name)\
+		"%x:%s\n", (pid), (task_name)
+
+#define KFD_EVENT_FMT_PAGEFAULT_START(ns, pid, addr, node, rw)\
+		"%lld -%d @%lx(%x) %c\n", (ns), (pid), (addr), (node), (rw)
+
+#define KFD_EVENT_FMT_PAGEFAULT_END(ns, pid, addr, node, migrate_update)\
+		"%lld -%d @%lx(%x) %c\n", (ns), (pid), (addr), (node), (migrate_update)
+
+#define KFD_EVENT_FMT_MIGRATE_START(ns, pid, start, size, from, to, prefetch_loc,\
+		preferred_loc, migrate_trigger)\
+		"%lld -%d @%lx(%lx) %x->%x %x:%x %d\n", (ns), (pid), (start), (size),\
+		(from), (to), (prefetch_loc), (preferred_loc), (migrate_trigger)
+
+#define KFD_EVENT_FMT_MIGRATE_END(ns, pid, start, size, from, to, migrate_trigger)\
+		"%lld -%d @%lx(%lx) %x->%x %d\n", (ns), (pid), (start), (size),\
+		(from), (to), (migrate_trigger)
+
+#define KFD_EVENT_FMT_QUEUE_EVICTION(ns, pid, node, evict_trigger)\
+		"%lld -%d %x %d\n", (ns), (pid), (node), (evict_trigger)
+
+#define KFD_EVENT_FMT_QUEUE_RESTORE(ns, pid, node, rescheduled)\
+		"%lld -%d %x %c\n", (ns), (pid), (node), (rescheduled)
+
+#define KFD_EVENT_FMT_UNMAP_FROM_GPU(ns, pid, addr, size, node, unmap_trigger)\
+		"%lld -%d @%lx(%lx) %x %d\n", (ns), (pid), (addr), (size),\
+		(node), (unmap_trigger)
+
 /**************************************************************************************************
  * CRIU IOCTLs (Checkpoint Restore In Userspace)
  *
diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h
index 0e21f3998108..bf2c9cabd207 100644
--- a/include/uapi/linux/virtio_gpu.h
+++ b/include/uapi/linux/virtio_gpu.h
@@ -311,6 +311,7 @@ struct virtio_gpu_cmd_submit {
 #define VIRTIO_GPU_CAPSET_VIRGL2 2
 /* 3 is reserved for gfxstream */
 #define VIRTIO_GPU_CAPSET_VENUS 4
+#define VIRTIO_GPU_CAPSET_DRM 6
 
 /* VIRTIO_GPU_CMD_GET_CAPSET_INFO */
 struct virtio_gpu_get_capset_info {