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, 180 insertions, 34 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 17a19d49d30a..1c19a65e6553 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -1065,18 +1065,6 @@ uint64_t amdgpu_gmc_vram_pa(struct amdgpu_device *adev, struct amdgpu_bo *bo)
 	return amdgpu_gmc_vram_mc2pa(adev, amdgpu_bo_gpu_offset(bo));
 }
 
-/**
- * amdgpu_gmc_vram_cpu_pa - calculate vram buffer object's physical address
- * from CPU's view
- *
- * @adev: amdgpu_device pointer
- * @bo: amdgpu buffer object
- */
-uint64_t amdgpu_gmc_vram_cpu_pa(struct amdgpu_device *adev, struct amdgpu_bo *bo)
-{
-	return amdgpu_bo_gpu_offset(bo) - adev->gmc.vram_start + adev->gmc.aper_base;
-}
-
 int amdgpu_gmc_vram_checking(struct amdgpu_device *adev)
 {
 	struct amdgpu_bo *vram_bo = NULL;
@@ -1130,6 +1118,79 @@ release_buffer:
 	return ret;
 }
 
+static const char *nps_desc[] = {
+	[AMDGPU_NPS1_PARTITION_MODE] = "NPS1",
+	[AMDGPU_NPS2_PARTITION_MODE] = "NPS2",
+	[AMDGPU_NPS3_PARTITION_MODE] = "NPS3",
+	[AMDGPU_NPS4_PARTITION_MODE] = "NPS4",
+	[AMDGPU_NPS6_PARTITION_MODE] = "NPS6",
+	[AMDGPU_NPS8_PARTITION_MODE] = "NPS8",
+};
+
+static ssize_t available_memory_partition_show(struct device *dev,
+					       struct device_attribute *addr,
+					       char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+	int size = 0, mode;
+	char *sep = "";
+
+	for_each_inst(mode, adev->gmc.supported_nps_modes) {
+		size += sysfs_emit_at(buf, size, "%s%s", sep, nps_desc[mode]);
+		sep = ", ";
+	}
+	size += sysfs_emit_at(buf, size, "\n");
+
+	return size;
+}
+
+static ssize_t current_memory_partition_store(struct device *dev,
+					      struct device_attribute *attr,
+					      const char *buf, size_t count)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+	enum amdgpu_memory_partition mode;
+	struct amdgpu_hive_info *hive;
+	int i;
+
+	mode = UNKNOWN_MEMORY_PARTITION_MODE;
+	for_each_inst(i, adev->gmc.supported_nps_modes) {
+		if (!strncasecmp(nps_desc[i], buf, strlen(nps_desc[i]))) {
+			mode = i;
+			break;
+		}
+	}
+
+	if (mode == UNKNOWN_MEMORY_PARTITION_MODE)
+		return -EINVAL;
+
+	if (mode == adev->gmc.gmc_funcs->query_mem_partition_mode(adev)) {
+		dev_info(
+			adev->dev,
+			"requested NPS mode is same as current NPS mode, skipping\n");
+		return count;
+	}
+
+	/* If device is part of hive, all devices in the hive should request the
+	 * same mode. Hence store the requested mode in hive.
+	 */
+	hive = amdgpu_get_xgmi_hive(adev);
+	if (hive) {
+		atomic_set(&hive->requested_nps_mode, mode);
+		amdgpu_put_xgmi_hive(hive);
+	} else {
+		adev->gmc.requested_nps_mode = mode;
+	}
+
+	dev_info(
+		adev->dev,
+		"NPS mode change requested, please remove and reload the driver\n");
+
+	return count;
+}
+
 static ssize_t current_memory_partition_show(
 	struct device *dev, struct device_attribute *addr, char *buf)
 {
@@ -1138,53 +1199,65 @@ static ssize_t current_memory_partition_show(
 	enum amdgpu_memory_partition mode;
 
 	mode = adev->gmc.gmc_funcs->query_mem_partition_mode(adev);
-	switch (mode) {
-	case AMDGPU_NPS1_PARTITION_MODE:
-		return sysfs_emit(buf, "NPS1\n");
-	case AMDGPU_NPS2_PARTITION_MODE:
-		return sysfs_emit(buf, "NPS2\n");
-	case AMDGPU_NPS3_PARTITION_MODE:
-		return sysfs_emit(buf, "NPS3\n");
-	case AMDGPU_NPS4_PARTITION_MODE:
-		return sysfs_emit(buf, "NPS4\n");
-	case AMDGPU_NPS6_PARTITION_MODE:
-		return sysfs_emit(buf, "NPS6\n");
-	case AMDGPU_NPS8_PARTITION_MODE:
-		return sysfs_emit(buf, "NPS8\n");
-	default:
+	if ((mode >= ARRAY_SIZE(nps_desc)) ||
+	    (BIT(mode) & AMDGPU_ALL_NPS_MASK) != BIT(mode))
 		return sysfs_emit(buf, "UNKNOWN\n");
-	}
+
+	return sysfs_emit(buf, "%s\n", nps_desc[mode]);
 }
 
-static DEVICE_ATTR_RO(current_memory_partition);
+static DEVICE_ATTR_RW(current_memory_partition);
+static DEVICE_ATTR_RO(available_memory_partition);
 
 int amdgpu_gmc_sysfs_init(struct amdgpu_device *adev)
 {
+	bool nps_switch_support;
+	int r = 0;
+
 	if (!adev->gmc.gmc_funcs->query_mem_partition_mode)
 		return 0;
 
+	nps_switch_support = (hweight32(adev->gmc.supported_nps_modes &
+					AMDGPU_ALL_NPS_MASK) > 1);
+	if (!nps_switch_support)
+		dev_attr_current_memory_partition.attr.mode &=
+			~(S_IWUSR | S_IWGRP | S_IWOTH);
+	else
+		r = device_create_file(adev->dev,
+				       &dev_attr_available_memory_partition);
+
+	if (r)
+		return r;
+
 	return device_create_file(adev->dev,
 				  &dev_attr_current_memory_partition);
 }
 
 void amdgpu_gmc_sysfs_fini(struct amdgpu_device *adev)
 {
+	if (!adev->gmc.gmc_funcs->query_mem_partition_mode)
+		return;
+
 	device_remove_file(adev->dev, &dev_attr_current_memory_partition);
+	device_remove_file(adev->dev, &dev_attr_available_memory_partition);
 }
 
 int amdgpu_gmc_get_nps_memranges(struct amdgpu_device *adev,
 				 struct amdgpu_mem_partition_info *mem_ranges,
-				 int exp_ranges)
+				 uint8_t *exp_ranges)
 {
 	struct amdgpu_gmc_memrange *ranges;
 	int range_cnt, ret, i, j;
 	uint32_t nps_type;
+	bool refresh;
 
-	if (!mem_ranges)
+	if (!mem_ranges || !exp_ranges)
 		return -EINVAL;
 
+	refresh = (adev->init_lvl->level != AMDGPU_INIT_LEVEL_MINIMAL_XGMI) &&
+		  (adev->gmc.reset_flags & AMDGPU_GMC_INIT_RESET_NPS);
 	ret = amdgpu_discovery_get_nps_info(adev, &nps_type, &ranges,
-					    &range_cnt);
+					    &range_cnt, refresh);
 
 	if (ret)
 		return ret;
@@ -1192,16 +1265,16 @@ int amdgpu_gmc_get_nps_memranges(struct amdgpu_device *adev,
 	/* TODO: For now, expect ranges and partition count to be the same.
 	 * Adjust if there are holes expected in any NPS domain.
 	 */
-	if (range_cnt != exp_ranges) {
+	if (*exp_ranges && (range_cnt != *exp_ranges)) {
 		dev_warn(
 			adev->dev,
 			"NPS config mismatch - expected ranges: %d discovery - nps mode: %d, nps ranges: %d",
-			exp_ranges, nps_type, range_cnt);
+			*exp_ranges, nps_type, range_cnt);
 		ret = -EINVAL;
 		goto err;
 	}
 
-	for (i = 0; i < exp_ranges; ++i) {
+	for (i = 0; i < range_cnt; ++i) {
 		if (ranges[i].base_address >= ranges[i].limit_address) {
 			dev_warn(
 				adev->dev,
@@ -1242,8 +1315,81 @@ int amdgpu_gmc_get_nps_memranges(struct amdgpu_device *adev,
 			ranges[i].limit_address - ranges[i].base_address + 1;
 	}
 
+	if (!*exp_ranges)
+		*exp_ranges = range_cnt;
 err:
 	kfree(ranges);
 
 	return ret;
 }
+
+int amdgpu_gmc_request_memory_partition(struct amdgpu_device *adev,
+					int nps_mode)
+{
+	/* Not supported on VF devices and APUs */
+	if (amdgpu_sriov_vf(adev) || (adev->flags & AMD_IS_APU))
+		return -EOPNOTSUPP;
+
+	if (!adev->psp.funcs) {
+		dev_err(adev->dev,
+			"PSP interface not available for nps mode change request");
+		return -EINVAL;
+	}
+
+	return psp_memory_partition(&adev->psp, nps_mode);
+}
+
+static inline bool amdgpu_gmc_need_nps_switch_req(struct amdgpu_device *adev,
+						  int req_nps_mode,
+						  int cur_nps_mode)
+{
+	return (((BIT(req_nps_mode) & adev->gmc.supported_nps_modes) ==
+			BIT(req_nps_mode)) &&
+		req_nps_mode != cur_nps_mode);
+}
+
+void amdgpu_gmc_prepare_nps_mode_change(struct amdgpu_device *adev)
+{
+	int req_nps_mode, cur_nps_mode, r;
+	struct amdgpu_hive_info *hive;
+
+	if (amdgpu_sriov_vf(adev) || !adev->gmc.supported_nps_modes ||
+	    !adev->gmc.gmc_funcs->request_mem_partition_mode)
+		return;
+
+	cur_nps_mode = adev->gmc.gmc_funcs->query_mem_partition_mode(adev);
+	hive = amdgpu_get_xgmi_hive(adev);
+	if (hive) {
+		req_nps_mode = atomic_read(&hive->requested_nps_mode);
+		if (!amdgpu_gmc_need_nps_switch_req(adev, req_nps_mode,
+						    cur_nps_mode)) {
+			amdgpu_put_xgmi_hive(hive);
+			return;
+		}
+		r = amdgpu_xgmi_request_nps_change(adev, hive, req_nps_mode);
+		amdgpu_put_xgmi_hive(hive);
+		goto out;
+	}
+
+	req_nps_mode = adev->gmc.requested_nps_mode;
+	if (!amdgpu_gmc_need_nps_switch_req(adev, req_nps_mode, cur_nps_mode))
+		return;
+
+	/* even if this fails, we should let driver unload w/o blocking */
+	r = adev->gmc.gmc_funcs->request_mem_partition_mode(adev, req_nps_mode);
+out:
+	if (r)
+		dev_err(adev->dev, "NPS mode change request failed\n");
+	else
+		dev_info(
+			adev->dev,
+			"NPS mode change request done, reload driver to complete the change\n");
+}
+
+bool amdgpu_gmc_need_reset_on_init(struct amdgpu_device *adev)
+{
+	if (adev->gmc.gmc_funcs->need_reset_on_init)
+		return adev->gmc.gmc_funcs->need_reset_on_init(adev);
+
+	return false;
+}