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, 189 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index b6397d3229e1..c704e9803e11 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -523,6 +523,9 @@ static int amdgpu_virt_read_pf2vf_data(struct amdgpu_device *adev)
 
 		adev->unique_id =
 			((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->uuid;
+		adev->virt.ras_en_caps.all = ((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->ras_en_caps.all;
+		adev->virt.ras_telemetry_en_caps.all =
+			((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->ras_telemetry_en_caps.all;
 		break;
 	default:
 		dev_err(adev->dev, "invalid pf2vf version: 0x%x\n", pf2vf_info->version);
@@ -703,6 +706,8 @@ void amdgpu_virt_exchange_data(struct amdgpu_device *adev)
 			adev->virt.fw_reserve.p_vf2pf =
 				(struct amd_sriov_msg_vf2pf_info_header *)
 				(adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_VF2PF_OFFSET_KB << 10));
+			adev->virt.fw_reserve.ras_telemetry =
+				(adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_RAS_TELEMETRY_OFFSET_KB << 10));
 		} else if (adev->mman.drv_vram_usage_va) {
 			adev->virt.fw_reserve.p_pf2vf =
 				(struct amd_sriov_msg_pf2vf_info_header *)
@@ -710,6 +715,8 @@ void amdgpu_virt_exchange_data(struct amdgpu_device *adev)
 			adev->virt.fw_reserve.p_vf2pf =
 				(struct amd_sriov_msg_vf2pf_info_header *)
 				(adev->mman.drv_vram_usage_va + (AMD_SRIOV_MSG_VF2PF_OFFSET_KB << 10));
+			adev->virt.fw_reserve.ras_telemetry =
+				(adev->mman.drv_vram_usage_va + (AMD_SRIOV_MSG_RAS_TELEMETRY_OFFSET_KB << 10));
 		}
 
 		amdgpu_virt_read_pf2vf_data(adev);
@@ -1144,3 +1151,185 @@ bool amdgpu_sriov_xnack_support(struct amdgpu_device *adev)
 
 	return xnack_mode;
 }
+
+bool amdgpu_virt_get_ras_capability(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+
+	if (!amdgpu_sriov_ras_caps_en(adev))
+		return false;
+
+	if (adev->virt.ras_en_caps.bits.block_umc)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__UMC);
+	if (adev->virt.ras_en_caps.bits.block_sdma)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__SDMA);
+	if (adev->virt.ras_en_caps.bits.block_gfx)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__GFX);
+	if (adev->virt.ras_en_caps.bits.block_mmhub)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MMHUB);
+	if (adev->virt.ras_en_caps.bits.block_athub)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__ATHUB);
+	if (adev->virt.ras_en_caps.bits.block_pcie_bif)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__PCIE_BIF);
+	if (adev->virt.ras_en_caps.bits.block_hdp)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__HDP);
+	if (adev->virt.ras_en_caps.bits.block_xgmi_wafl)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__XGMI_WAFL);
+	if (adev->virt.ras_en_caps.bits.block_df)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__DF);
+	if (adev->virt.ras_en_caps.bits.block_smn)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__SMN);
+	if (adev->virt.ras_en_caps.bits.block_sem)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__SEM);
+	if (adev->virt.ras_en_caps.bits.block_mp0)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MP0);
+	if (adev->virt.ras_en_caps.bits.block_mp1)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MP1);
+	if (adev->virt.ras_en_caps.bits.block_fuse)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__FUSE);
+	if (adev->virt.ras_en_caps.bits.block_mca)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MCA);
+	if (adev->virt.ras_en_caps.bits.block_vcn)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__VCN);
+	if (adev->virt.ras_en_caps.bits.block_jpeg)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__JPEG);
+	if (adev->virt.ras_en_caps.bits.block_ih)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__IH);
+	if (adev->virt.ras_en_caps.bits.block_mpio)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MPIO);
+
+	if (adev->virt.ras_en_caps.bits.poison_propogation_mode)
+		con->poison_supported = true; /* Poison is handled by host */
+
+	return true;
+}
+
+static inline enum amd_sriov_ras_telemetry_gpu_block
+amdgpu_ras_block_to_sriov(struct amdgpu_device *adev, enum amdgpu_ras_block block) {
+	switch (block) {
+	case AMDGPU_RAS_BLOCK__UMC:
+		return RAS_TELEMETRY_GPU_BLOCK_UMC;
+	case AMDGPU_RAS_BLOCK__SDMA:
+		return RAS_TELEMETRY_GPU_BLOCK_SDMA;
+	case AMDGPU_RAS_BLOCK__GFX:
+		return RAS_TELEMETRY_GPU_BLOCK_GFX;
+	case AMDGPU_RAS_BLOCK__MMHUB:
+		return RAS_TELEMETRY_GPU_BLOCK_MMHUB;
+	case AMDGPU_RAS_BLOCK__ATHUB:
+		return RAS_TELEMETRY_GPU_BLOCK_ATHUB;
+	case AMDGPU_RAS_BLOCK__PCIE_BIF:
+		return RAS_TELEMETRY_GPU_BLOCK_PCIE_BIF;
+	case AMDGPU_RAS_BLOCK__HDP:
+		return RAS_TELEMETRY_GPU_BLOCK_HDP;
+	case AMDGPU_RAS_BLOCK__XGMI_WAFL:
+		return RAS_TELEMETRY_GPU_BLOCK_XGMI_WAFL;
+	case AMDGPU_RAS_BLOCK__DF:
+		return RAS_TELEMETRY_GPU_BLOCK_DF;
+	case AMDGPU_RAS_BLOCK__SMN:
+		return RAS_TELEMETRY_GPU_BLOCK_SMN;
+	case AMDGPU_RAS_BLOCK__SEM:
+		return RAS_TELEMETRY_GPU_BLOCK_SEM;
+	case AMDGPU_RAS_BLOCK__MP0:
+		return RAS_TELEMETRY_GPU_BLOCK_MP0;
+	case AMDGPU_RAS_BLOCK__MP1:
+		return RAS_TELEMETRY_GPU_BLOCK_MP1;
+	case AMDGPU_RAS_BLOCK__FUSE:
+		return RAS_TELEMETRY_GPU_BLOCK_FUSE;
+	case AMDGPU_RAS_BLOCK__MCA:
+		return RAS_TELEMETRY_GPU_BLOCK_MCA;
+	case AMDGPU_RAS_BLOCK__VCN:
+		return RAS_TELEMETRY_GPU_BLOCK_VCN;
+	case AMDGPU_RAS_BLOCK__JPEG:
+		return RAS_TELEMETRY_GPU_BLOCK_JPEG;
+	case AMDGPU_RAS_BLOCK__IH:
+		return RAS_TELEMETRY_GPU_BLOCK_IH;
+	case AMDGPU_RAS_BLOCK__MPIO:
+		return RAS_TELEMETRY_GPU_BLOCK_MPIO;
+	default:
+		dev_err(adev->dev, "Unsupported SRIOV RAS telemetry block 0x%x\n", block);
+		return RAS_TELEMETRY_GPU_BLOCK_COUNT;
+	}
+}
+
+static int amdgpu_virt_cache_host_error_counts(struct amdgpu_device *adev,
+					       struct amdsriov_ras_telemetry *host_telemetry)
+{
+	struct amd_sriov_ras_telemetry_error_count *tmp = NULL;
+	uint32_t checksum, used_size;
+
+	checksum = host_telemetry->header.checksum;
+	used_size = host_telemetry->header.used_size;
+
+	if (used_size > (AMD_SRIOV_RAS_TELEMETRY_SIZE_KB << 10))
+		return 0;
+
+	tmp = kmalloc(used_size, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	memcpy(tmp, &host_telemetry->body.error_count, used_size);
+
+	if (checksum != amd_sriov_msg_checksum(tmp, used_size, 0, 0))
+		goto out;
+
+	memcpy(&adev->virt.count_cache, tmp,
+	       min(used_size, sizeof(adev->virt.count_cache)));
+out:
+	kfree(tmp);
+
+	return 0;
+}
+
+static int amdgpu_virt_req_ras_err_count_internal(struct amdgpu_device *adev, bool force_update)
+{
+	struct amdgpu_virt *virt = &adev->virt;
+
+	/* Host allows 15 ras telemetry requests per 60 seconds. Afterwhich, the Host
+	 * will ignore incoming guest messages. Ratelimit the guest messages to
+	 * prevent guest self DOS.
+	 */
+	if (__ratelimit(&adev->virt.ras_telemetry_rs) || force_update) {
+		if (!virt->ops->req_ras_err_count(adev))
+			amdgpu_virt_cache_host_error_counts(adev,
+				adev->virt.fw_reserve.ras_telemetry);
+	}
+
+	return 0;
+}
+
+/* Bypass ACA interface and query ECC counts directly from host */
+int amdgpu_virt_req_ras_err_count(struct amdgpu_device *adev, enum amdgpu_ras_block block,
+				  struct ras_err_data *err_data)
+{
+	enum amd_sriov_ras_telemetry_gpu_block sriov_block;
+
+	sriov_block = amdgpu_ras_block_to_sriov(adev, block);
+
+	if (sriov_block >= RAS_TELEMETRY_GPU_BLOCK_COUNT ||
+	    !amdgpu_sriov_ras_telemetry_block_en(adev, sriov_block))
+		return -EOPNOTSUPP;
+
+	/* Host Access may be lost during reset, just return last cached data. */
+	if (down_read_trylock(&adev->reset_domain->sem)) {
+		amdgpu_virt_req_ras_err_count_internal(adev, false);
+		up_read(&adev->reset_domain->sem);
+	}
+
+	err_data->ue_count = adev->virt.count_cache.block[sriov_block].ue_count;
+	err_data->ce_count = adev->virt.count_cache.block[sriov_block].ce_count;
+	err_data->de_count = adev->virt.count_cache.block[sriov_block].de_count;
+
+	return 0;
+}
+
+int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev)
+{
+	unsigned long ue_count, ce_count;
+
+	if (amdgpu_sriov_ras_telemetry_en(adev)) {
+		amdgpu_virt_req_ras_err_count_internal(adev, true);
+		amdgpu_ras_query_error_count(adev, &ce_count, &ue_count, NULL);
+	}
+
+	return 0;
+}