Merge tag 'drm-next-2024-11-21' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "There's a lot of rework, the panic helper support is being added to
  more drivers, v3d gets support for HW superpages, scheduler
  documentation, drm client and video aperture reworks, some new
  MAINTAINERS added, amdgpu has the usual lots of IP refactors, Intel
  has some Pantherlake enablement and xe is getting some SRIOV bits, but
  just lots of stuff everywhere.

  core:
   - split DSC helpers from DP helpers
   - clang build fixes for drm/mm test
   - drop simple pipeline support for gem vram
   - document submission error signaling
   - move drm_rect to drm core module from kms helper
   - add default client setup to most drivers
   - move to video aperture helpers instead of drm ones

  tests:
   - new framebuffer tests

  ttm:
   - remove swapped and pinned BOs from TTM lru

  panic:
   - fix uninit spinlock
   - add ABGR2101010 support

  bridge:
   - add TI TDP158 support
   - use standard PM OPS

  dma-fence:
   - use read_trylock instead of read_lock to help lockdep

  scheduler:
   - add errno to sched start to report different errors
   - add locking to drm_sched_entity_modify_sched
   - improve documentation

  xe:
   - add drm_line_printer
   - lots of refactoring
   - Enable Xe2 + PES disaggregation
   - add new ARL PCI ID
   - SRIOV development work
   - fix exec unnecessary implicit fence
   - define and parse OA sync props
   - forcewake refactoring

  i915:
   - Enable BMG/LNL ultra joiner
   - Enable 10bpx + CCS scanout on ICL+, fp16/CCS on TGL+
   - use DSB for plane/color mgmt
   - Arrow lake PCI IDs
   - lots of i915/xe display refactoring
   - enable PXP GuC autoteardown
   - Pantherlake (PTL) Xe3 LPD display enablement
   - Allow fastset HDR infoframe changes
   - write DP source OUI for non-eDP sinks
   - share PCI IDs between i915 and xe

  amdgpu:
   - SDMA queue reset support
   - SMU 13.0.6, JPEG 4.0.3 updates
   - Initial runtime repartitioning support
   - rework IP structs for multiple IP instances
   - Fetch EDID from _DDC if available
   - SMU13 zero rpm user control
   - lots of fixes/cleanups

  amdkfd:
   - Increase event FIFO size
   - add topology cap flag for per queue reset

  msm:
   - DPU:
      - SA8775P support
      - (disabled by default) MSM8917, MSM8937, MSM8953 and MSM8996 support
      - Enable large framebuffer support
      - Drop MSM8998 and SDM845
   - DP:
      - SA8775P support
   - GPU:
      - a7xx preemption support
      - Adreno A663 support

  ast:
   - warn about unsupported TX chips

  ivpu:
   - add coredump
   - add pantherlake support

  rockchip:
   - 4K@60Hz display enablement
   - generate pll programming tables

  panthor:
   - add timestamp query API
   - add realtime group priority
   - add fdinfo support

  etnaviv:
   - improve handling of DMA address limits
   - improve GPU hangcheck

  exynos:
   - Decon Exynos7870 support

  mediatek:
   - add OF graph support

  omap:
   - locking fixes

  bochs:
   - convert to gem/shmem from simpledrm

  v3d:
   - support big/super pages
   - add gemfs

  vc4:
   - BCM2712 support refactoring
   - add YUV444 format support

  udmabuf:
   - folio related fixes

  nouveau:
   - add panic support on nv50+"

* tag 'drm-next-2024-11-21' of https://gitlab.freedesktop.org/drm/kernel: (1583 commits)
  drm/xe/guc: Fix dereference before NULL check
  drm/amd: Fix initialization mistake for NBIO 7.7.0
  Revert "drm/amd/display: parse umc_info or vram_info based on ASIC"
  drm/amd/display: Fix failure to read vram info due to static BP_RESULT
  drm/amdgpu: enable GTT fallback handling for dGPUs only
  drm/amd/amdgpu: limit single process inside MES
  drm/fourcc: add AMD_FMT_MOD_TILE_GFX9_4K_D_X
  drm/amdgpu/mes12: correct kiq unmap latency
  drm/amdgpu: Support vcn and jpeg error info parsing
  drm/amd : Update MES API header file for v11 & v12
  drm/amd/amdkfd: add/remove kfd queues on start/stop KFD scheduling
  drm/amdkfd: change kfd process kref count at creation
  drm/amdgpu: Cleanup shift coding style
  drm/amd/amdgpu: Increase MES log buffer to dump mes scratch data
  drm/amdgpu: Implement virt req_ras_err_count
  drm/amdgpu: VF Query RAS Caps from Host if supported
  drm/amdgpu: Add msg handlers for SRIOV RAS Telemetry
  drm/amdgpu: Update SRIOV Exchange Headers for RAS Telemetry Support
  drm/amd/display: 3.2.309
  drm/amd/display: Adjust VSDB parser for replay feature
  ...

1 files changed, 112 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
index 6e9eeaeb3de1..b4f9c2f4e92c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
@@ -28,17 +28,21 @@
 #define AMD_SRIOV_MSG_VBIOS_SIZE_KB	     64
 #define AMD_SRIOV_MSG_DATAEXCHANGE_OFFSET_KB AMD_SRIOV_MSG_VBIOS_SIZE_KB
 #define AMD_SRIOV_MSG_DATAEXCHANGE_SIZE_KB   4
-
+#define AMD_SRIOV_MSG_TMR_OFFSET_KB	     2048
+#define AMD_SRIOV_MSG_BAD_PAGE_SIZE_KB	     2
+#define AMD_SRIOV_RAS_TELEMETRY_SIZE_KB	     64
 /*
  * layout
- * 0           64KB        65KB        66KB
- * |   VBIOS   |   PF2VF   |   VF2PF   |   Bad Page   | ...
- * |   64KB    |   1KB     |   1KB     |
+ * 0           64KB        65KB        66KB           68KB                   132KB
+ * |   VBIOS   |   PF2VF   |   VF2PF   |   Bad Page   | RAS Telemetry Region | ...
+ * |   64KB    |   1KB     |   1KB     |   2KB        | 64KB                 | ...
  */
+
 #define AMD_SRIOV_MSG_SIZE_KB                   1
 #define AMD_SRIOV_MSG_PF2VF_OFFSET_KB           AMD_SRIOV_MSG_DATAEXCHANGE_OFFSET_KB
 #define AMD_SRIOV_MSG_VF2PF_OFFSET_KB           (AMD_SRIOV_MSG_PF2VF_OFFSET_KB + AMD_SRIOV_MSG_SIZE_KB)
 #define AMD_SRIOV_MSG_BAD_PAGE_OFFSET_KB        (AMD_SRIOV_MSG_VF2PF_OFFSET_KB + AMD_SRIOV_MSG_SIZE_KB)
+#define AMD_SRIOV_MSG_RAS_TELEMETRY_OFFSET_KB   (AMD_SRIOV_MSG_BAD_PAGE_OFFSET_KB + AMD_SRIOV_MSG_BAD_PAGE_SIZE_KB)
 
 /*
  * PF2VF history log:
@@ -86,30 +90,59 @@ enum amd_sriov_ucode_engine_id {
 
 union amd_sriov_msg_feature_flags {
 	struct {
-		uint32_t error_log_collect : 1;
-		uint32_t host_load_ucodes  : 1;
-		uint32_t host_flr_vramlost : 1;
-		uint32_t mm_bw_management  : 1;
-		uint32_t pp_one_vf_mode    : 1;
-		uint32_t reg_indirect_acc  : 1;
-		uint32_t av1_support       : 1;
-		uint32_t vcn_rb_decouple   : 1;
-		uint32_t mes_info_enable   : 1;
-		uint32_t reserved          : 23;
+		uint32_t error_log_collect	: 1;
+		uint32_t host_load_ucodes	: 1;
+		uint32_t host_flr_vramlost	: 1;
+		uint32_t mm_bw_management	: 1;
+		uint32_t pp_one_vf_mode		: 1;
+		uint32_t reg_indirect_acc	: 1;
+		uint32_t av1_support		: 1;
+		uint32_t vcn_rb_decouple 	: 1;
+		uint32_t mes_info_dump_enable	: 1;
+		uint32_t ras_caps		: 1;
+		uint32_t ras_telemetry		: 1;
+		uint32_t reserved		: 21;
 	} flags;
 	uint32_t all;
 };
 
 union amd_sriov_reg_access_flags {
 	struct {
-		uint32_t vf_reg_access_ih 	 : 1;
-		uint32_t vf_reg_access_mmhub : 1;
-		uint32_t vf_reg_access_gc 	 : 1;
-		uint32_t reserved	         : 29;
+		uint32_t vf_reg_access_ih	: 1;
+		uint32_t vf_reg_access_mmhub	: 1;
+		uint32_t vf_reg_access_gc	: 1;
+		uint32_t reserved		: 29;
 	} flags;
 	uint32_t all;
 };
 
+union amd_sriov_ras_caps {
+	struct {
+		uint64_t block_umc			: 1;
+		uint64_t block_sdma			: 1;
+		uint64_t block_gfx			: 1;
+		uint64_t block_mmhub			: 1;
+		uint64_t block_athub			: 1;
+		uint64_t block_pcie_bif			: 1;
+		uint64_t block_hdp			: 1;
+		uint64_t block_xgmi_wafl		: 1;
+		uint64_t block_df			: 1;
+		uint64_t block_smn			: 1;
+		uint64_t block_sem			: 1;
+		uint64_t block_mp0			: 1;
+		uint64_t block_mp1			: 1;
+		uint64_t block_fuse			: 1;
+		uint64_t block_mca			: 1;
+		uint64_t block_vcn			: 1;
+		uint64_t block_jpeg			: 1;
+		uint64_t block_ih			: 1;
+		uint64_t block_mpio			: 1;
+		uint64_t poison_propogation_mode	: 1;
+		uint64_t reserved			: 44;
+	} bits;
+	uint64_t all;
+};
+
 union amd_sriov_msg_os_info {
 	struct {
 		uint32_t windows  : 1;
@@ -158,7 +191,7 @@ struct amd_sriov_msg_pf2vf_info_header {
 	uint32_t reserved[2];
 };
 
-#define AMD_SRIOV_MSG_PF2VF_INFO_FILLED_SIZE (49)
+#define AMD_SRIOV_MSG_PF2VF_INFO_FILLED_SIZE (55)
 struct amd_sriov_msg_pf2vf_info {
 	/* header contains size and version */
 	struct amd_sriov_msg_pf2vf_info_header header;
@@ -211,6 +244,12 @@ struct amd_sriov_msg_pf2vf_info {
 	uint32_t pcie_atomic_ops_support_flags;
 	/* Portion of GPU memory occupied by VF.  MAX value is 65535, but set to uint32_t to maintain alignment with reserved size */
 	uint32_t gpu_capacity;
+	/* vf bdf on host pci tree for debug only */
+	uint32_t bdf_on_host;
+	uint32_t more_bp;	//Reserved for future use.
+	union amd_sriov_ras_caps ras_en_caps;
+	union amd_sriov_ras_caps ras_telemetry_en_caps;
+
 	/* reserved */
 	uint32_t reserved[256 - AMD_SRIOV_MSG_PF2VF_INFO_FILLED_SIZE];
 } __packed;
@@ -283,8 +322,12 @@ enum amd_sriov_mailbox_request_message {
 	MB_REQ_MSG_REL_GPU_FINI_ACCESS,
 	MB_REQ_MSG_REQ_GPU_RESET_ACCESS,
 	MB_REQ_MSG_REQ_GPU_INIT_DATA,
+	MB_REQ_MSG_PSP_VF_CMD_RELAY,
 
 	MB_REQ_MSG_LOG_VF_ERROR = 200,
+	MB_REQ_MSG_READY_TO_RESET = 201,
+	MB_REQ_MSG_RAS_POISON = 202,
+	MB_REQ_RAS_ERROR_COUNT = 203,
 };
 
 /* mailbox message send from host to guest  */
@@ -297,10 +340,60 @@ enum amd_sriov_mailbox_response_message {
 	MB_RES_MSG_FAIL,
 	MB_RES_MSG_QUERY_ALIVE,
 	MB_RES_MSG_GPU_INIT_DATA_READY,
+	MB_RES_MSG_RAS_ERROR_COUNT_READY = 11,
 
 	MB_RES_MSG_TEXT_MESSAGE = 255
 };
 
+enum amd_sriov_ras_telemetry_gpu_block {
+	RAS_TELEMETRY_GPU_BLOCK_UMC		= 0,
+	RAS_TELEMETRY_GPU_BLOCK_SDMA		= 1,
+	RAS_TELEMETRY_GPU_BLOCK_GFX		= 2,
+	RAS_TELEMETRY_GPU_BLOCK_MMHUB		= 3,
+	RAS_TELEMETRY_GPU_BLOCK_ATHUB		= 4,
+	RAS_TELEMETRY_GPU_BLOCK_PCIE_BIF	= 5,
+	RAS_TELEMETRY_GPU_BLOCK_HDP		= 6,
+	RAS_TELEMETRY_GPU_BLOCK_XGMI_WAFL	= 7,
+	RAS_TELEMETRY_GPU_BLOCK_DF		= 8,
+	RAS_TELEMETRY_GPU_BLOCK_SMN		= 9,
+	RAS_TELEMETRY_GPU_BLOCK_SEM		= 10,
+	RAS_TELEMETRY_GPU_BLOCK_MP0		= 11,
+	RAS_TELEMETRY_GPU_BLOCK_MP1		= 12,
+	RAS_TELEMETRY_GPU_BLOCK_FUSE		= 13,
+	RAS_TELEMETRY_GPU_BLOCK_MCA		= 14,
+	RAS_TELEMETRY_GPU_BLOCK_VCN		= 15,
+	RAS_TELEMETRY_GPU_BLOCK_JPEG		= 16,
+	RAS_TELEMETRY_GPU_BLOCK_IH		= 17,
+	RAS_TELEMETRY_GPU_BLOCK_MPIO		= 18,
+	RAS_TELEMETRY_GPU_BLOCK_COUNT		= 19,
+};
+
+struct amd_sriov_ras_telemetry_header {
+	uint32_t checksum;
+	uint32_t used_size;
+	uint32_t reserved[2];
+};
+
+struct amd_sriov_ras_telemetry_error_count {
+	struct {
+		uint32_t ce_count;
+		uint32_t ue_count;
+		uint32_t de_count;
+		uint32_t ce_overflow_count;
+		uint32_t ue_overflow_count;
+		uint32_t de_overflow_count;
+		uint32_t reserved[6];
+	} block[RAS_TELEMETRY_GPU_BLOCK_COUNT];
+};
+
+struct amdsriov_ras_telemetry {
+	struct amd_sriov_ras_telemetry_header header;
+
+	union {
+		struct amd_sriov_ras_telemetry_error_count error_count;
+	} body;
+};
+
 /* version data stored in MAILBOX_MSGBUF_RCV_DW1 for future expansion */
 enum amd_sriov_gpu_init_data_version {
 	GPU_INIT_DATA_READY_V1 = 1,