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, 128 insertions, 20 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 0b28b2cf1517..17cf10c0b72b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -159,9 +159,9 @@ static int psp_init_sriov_microcode(struct psp_context *psp)
 	return ret;
 }
 
-static int psp_early_init(void *handle)
+static int psp_early_init(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	struct psp_context *psp = &adev->psp;
 
 	psp->autoload_supported = true;
@@ -421,9 +421,9 @@ static bool psp_get_runtime_db_entry(struct amdgpu_device *adev,
 	return ret;
 }
 
-static int psp_sw_init(void *handle)
+static int psp_sw_init(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	struct psp_context *psp = &adev->psp;
 	int ret;
 	struct psp_runtime_boot_cfg_entry boot_cfg_entry;
@@ -527,9 +527,9 @@ failed1:
 	return ret;
 }
 
-static int psp_sw_fini(void *handle)
+static int psp_sw_fini(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	struct psp_context *psp = &adev->psp;
 	struct psp_gfx_cmd_resp *cmd = psp->cmd;
 
@@ -639,6 +639,8 @@ static const char *psp_gfx_cmd_name(enum psp_gfx_cmd_id cmd_id)
 		return "AUTOLOAD_RLC";
 	case GFX_CMD_ID_BOOT_CFG:
 		return "BOOT_CFG";
+	case GFX_CMD_ID_CONFIG_SQ_PERFMON:
+		return "CONFIG_SQ_PERFMON";
 	default:
 		return "UNKNOWN CMD";
 	}
@@ -1043,6 +1045,31 @@ static int psp_rl_load(struct amdgpu_device *adev)
 	return ret;
 }
 
+int psp_memory_partition(struct psp_context *psp, int mode)
+{
+	struct psp_gfx_cmd_resp *cmd;
+	int ret;
+
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	cmd = acquire_psp_cmd_buf(psp);
+
+	cmd->cmd_id = GFX_CMD_ID_FB_NPS_MODE;
+	cmd->cmd.cmd_memory_part.mode = mode;
+
+	dev_info(psp->adev->dev,
+		 "Requesting %d memory partition change through PSP", mode);
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+	if (ret)
+		dev_err(psp->adev->dev,
+			"PSP request failed to change to NPS%d mode\n", mode);
+
+	release_psp_cmd_buf(psp);
+
+	return ret;
+}
+
 int psp_spatial_partition(struct psp_context *psp, int mode)
 {
 	struct psp_gfx_cmd_resp *cmd;
@@ -1807,6 +1834,9 @@ int psp_ras_initialize(struct psp_context *psp)
 	ras_cmd->ras_in_message.init_flags.xcc_mask =
 		adev->gfx.xcc_mask;
 	ras_cmd->ras_in_message.init_flags.channel_dis_num = hweight32(adev->gmc.m_half_use) * 2;
+	if (adev->gmc.gmc_funcs->query_mem_partition_mode)
+		ras_cmd->ras_in_message.init_flags.nps_mode =
+			adev->gmc.gmc_funcs->query_mem_partition_mode(adev);
 
 	ret = psp_ta_load(psp, &psp->ras_context.context);
 
@@ -2264,6 +2294,19 @@ bool amdgpu_psp_get_ras_capability(struct psp_context *psp)
 	}
 }
 
+bool amdgpu_psp_tos_reload_needed(struct amdgpu_device *adev)
+{
+	struct psp_context *psp = &adev->psp;
+
+	if (amdgpu_sriov_vf(adev) || (adev->flags & AMD_IS_APU))
+		return false;
+
+	if (psp->funcs && psp->funcs->is_reload_needed)
+		return psp->funcs->is_reload_needed(psp);
+
+	return false;
+}
+
 static int psp_hw_start(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
@@ -2958,10 +3001,10 @@ failed:
 	return ret;
 }
 
-static int psp_hw_init(void *handle)
+static int psp_hw_init(struct amdgpu_ip_block *ip_block)
 {
 	int ret;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 
 	mutex_lock(&adev->firmware.mutex);
 	/*
@@ -2987,9 +3030,9 @@ failed:
 	return -EINVAL;
 }
 
-static int psp_hw_fini(void *handle)
+static int psp_hw_fini(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	struct psp_context *psp = &adev->psp;
 
 	if (psp->ta_fw) {
@@ -3011,10 +3054,10 @@ static int psp_hw_fini(void *handle)
 	return 0;
 }
 
-static int psp_suspend(void *handle)
+static int psp_suspend(struct amdgpu_ip_block *ip_block)
 {
 	int ret = 0;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	struct psp_context *psp = &adev->psp;
 
 	if (adev->gmc.xgmi.num_physical_nodes > 1 &&
@@ -3074,10 +3117,10 @@ out:
 	return ret;
 }
 
-static int psp_resume(void *handle)
+static int psp_resume(struct amdgpu_ip_block *ip_block)
 {
 	int ret;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = ip_block->adev;
 	struct psp_context *psp = &adev->psp;
 
 	dev_info(adev->dev, "PSP is resuming...\n");
@@ -3523,6 +3566,36 @@ out:
 	return err;
 }
 
+static bool is_ta_fw_applicable(struct psp_context *psp,
+			     const struct psp_fw_bin_desc *desc)
+{
+	struct amdgpu_device *adev = psp->adev;
+	uint32_t fw_version;
+
+	switch (desc->fw_type) {
+	case TA_FW_TYPE_PSP_XGMI:
+	case TA_FW_TYPE_PSP_XGMI_AUX:
+		/* for now, AUX TA only exists on 13.0.6 ta bin,
+		 * from v20.00.0x.14
+		 */
+		if (amdgpu_ip_version(adev, MP0_HWIP, 0) ==
+		    IP_VERSION(13, 0, 6)) {
+			fw_version = le32_to_cpu(desc->fw_version);
+
+			if (adev->flags & AMD_IS_APU &&
+			    (fw_version & 0xff) >= 0x14)
+				return desc->fw_type == TA_FW_TYPE_PSP_XGMI_AUX;
+			else
+				return desc->fw_type == TA_FW_TYPE_PSP_XGMI;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return true;
+}
+
 static int parse_ta_bin_descriptor(struct psp_context *psp,
 				   const struct psp_fw_bin_desc *desc,
 				   const struct ta_firmware_header_v2_0 *ta_hdr)
@@ -3532,6 +3605,9 @@ static int parse_ta_bin_descriptor(struct psp_context *psp,
 	if (!psp || !desc || !ta_hdr)
 		return -EINVAL;
 
+	if (!is_ta_fw_applicable(psp, desc))
+		return 0;
+
 	ucode_start_addr  = (uint8_t *)ta_hdr +
 			    le32_to_cpu(desc->offset_bytes) +
 			    le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
@@ -3544,6 +3620,7 @@ static int parse_ta_bin_descriptor(struct psp_context *psp,
 		psp->asd_context.bin_desc.start_addr        = ucode_start_addr;
 		break;
 	case TA_FW_TYPE_PSP_XGMI:
+	case TA_FW_TYPE_PSP_XGMI_AUX:
 		psp->xgmi_context.context.bin_desc.fw_version       = le32_to_cpu(desc->fw_version);
 		psp->xgmi_context.context.bin_desc.size_bytes       = le32_to_cpu(desc->size_bytes);
 		psp->xgmi_context.context.bin_desc.start_addr       = ucode_start_addr;
@@ -3736,8 +3813,44 @@ out:
 	return err;
 }
 
+int psp_config_sq_perfmon(struct psp_context *psp,
+		uint32_t xcp_id, bool core_override_enable,
+		bool reg_override_enable, bool perfmon_override_enable)
+{
+	int ret;
+
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	if (xcp_id > MAX_XCP) {
+		dev_err(psp->adev->dev, "invalid xcp_id %d\n", xcp_id);
+		return -EINVAL;
+	}
+
+	if (amdgpu_ip_version(psp->adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6)) {
+		dev_err(psp->adev->dev, "Unsupported MP0 version 0x%x for CONFIG_SQ_PERFMON command\n",
+			amdgpu_ip_version(psp->adev, MP0_HWIP, 0));
+		return -EINVAL;
+	}
+	struct psp_gfx_cmd_resp *cmd = acquire_psp_cmd_buf(psp);
+
+	cmd->cmd_id	=	GFX_CMD_ID_CONFIG_SQ_PERFMON;
+	cmd->cmd.config_sq_perfmon.gfx_xcp_mask	=	BIT_MASK(xcp_id);
+	cmd->cmd.config_sq_perfmon.core_override	=	core_override_enable;
+	cmd->cmd.config_sq_perfmon.reg_override	=	reg_override_enable;
+	cmd->cmd.config_sq_perfmon.perfmon_override = perfmon_override_enable;
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+	if (ret)
+		dev_warn(psp->adev->dev, "PSP failed to config sq: xcp%d core%d reg%d perfmon%d\n",
+			xcp_id, core_override_enable, reg_override_enable, perfmon_override_enable);
+
+	release_psp_cmd_buf(psp);
+	return ret;
+}
+
 static int psp_set_clockgating_state(void *handle,
-				     enum amd_clockgating_state state)
+					enum amd_clockgating_state state)
 {
 	return 0;
 }
@@ -4019,17 +4132,12 @@ const struct attribute_group amdgpu_flash_attr_group = {
 const struct amd_ip_funcs psp_ip_funcs = {
 	.name = "psp",
 	.early_init = psp_early_init,
-	.late_init = NULL,
 	.sw_init = psp_sw_init,
 	.sw_fini = psp_sw_fini,
 	.hw_init = psp_hw_init,
 	.hw_fini = psp_hw_fini,
 	.suspend = psp_suspend,
 	.resume = psp_resume,
-	.is_idle = NULL,
-	.check_soft_reset = NULL,
-	.wait_for_idle = NULL,
-	.soft_reset = NULL,
 	.set_clockgating_state = psp_set_clockgating_state,
 	.set_powergating_state = psp_set_powergating_state,
 };