Merge tag 'amd-drm-next-6.4-2023-03-17' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.4-2023-03-17:

amdgpu:
- Misc code cleanups
- Documentation fixes
- Make kobj structures const
- Add thermal throttling adjustments for supported APUs
- UMC RAS fixes
- Display reset fixes
- DCN 3.2 fixes
- Freesync fixes
- DC code reorg
- Generalize dmabuf import to work with KFD
- DC DML fixes
- SRIOV fixes
- UVD code cleanups
- IH 4.4.2 updates
- HDP 4.4.2 updates
- SDMA 4.4.2 updates
- PSP 13.0.6 updates
- Add capped/uncapped workload handling for supported APUs
- DCN 3.1.4 updates
- Re-org DC Kconfig
- USB4 fixes
- Reorg DC plane and stream handling
- Register vga_switcheroo for apple-gmux
- SMU 13.0.6 updates
- Fix error checking in read_mm_registers functions for affected families
- VCN 4.0.4 fix
- Drop redundant pci_enable_pcie_error_reporting() call
- RDNA2 SMU OD suspend/resume fix
- Expose additional memory stats via fdinfo
- RAS fixes
- Misc display fixes
- DP MST fixes
- IOMMU regression fix for KFD

amdkfd:
- Make kobj structures const
- Support for exporting buffers via dmabuf
- Multi-VMA page migration fixes
- NBIO fixes
- Misc code cleanups
- Fix possible double free
- Fix possible UAF

radeon:
- iMac fix

UAPI:
- KFD dmabuf export support.  Required for importing KFD buffers into GEM contexts and for RDMA P2P support.
  Proposed user mode changes: https://github.com/fxkamd/ROCT-Thunk-Interface/commits/fxkamd/dmabuf

From: Alex Deucher <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

1 files changed, 79 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index bf6d63673b5a..d75a67cfe523 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -91,6 +91,8 @@ const char * const amdgpu_pp_profile_name[] = {
 	"COMPUTE",
 	"CUSTOM",
 	"WINDOW_3D",
+	"CAPPED",
+	"UNCAPPED",
 };
 
 /**
@@ -1686,6 +1688,82 @@ static ssize_t amdgpu_set_thermal_throttling_logging(struct device *dev,
 }
 
 /**
+ * DOC: apu_thermal_cap
+ *
+ * The amdgpu driver provides a sysfs API for retrieving/updating thermal
+ * limit temperature in millidegrees Celsius
+ *
+ * Reading back the file shows you core limit value
+ *
+ * Writing an integer to the file, sets a new thermal limit. The value
+ * should be between 0 and 100. If the value is less than 0 or greater
+ * than 100, then the write request will be ignored.
+ */
+static ssize_t amdgpu_get_apu_thermal_cap(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	int ret, size;
+	u32 limit;
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(ddev->dev);
+		return ret;
+	}
+
+	ret = amdgpu_dpm_get_apu_thermal_limit(adev, &limit);
+	if (!ret)
+		size = sysfs_emit(buf, "%u\n", limit);
+	else
+		size = sysfs_emit(buf, "failed to get thermal limit\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
+}
+
+static ssize_t amdgpu_set_apu_thermal_cap(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf,
+					 size_t count)
+{
+	int ret;
+	u32 value;
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	ret = kstrtou32(buf, 10, &value);
+	if (ret)
+		return ret;
+
+	if (value > 100) {
+		dev_err(dev, "Invalid argument !\n");
+		return -EINVAL;
+	}
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(ddev->dev);
+		return ret;
+	}
+
+	ret = amdgpu_dpm_set_apu_thermal_limit(adev, value);
+	if (ret) {
+		dev_err(dev, "failed to update thermal limit\n");
+		return ret;
+	}
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return count;
+}
+
+/**
  * DOC: gpu_metrics
  *
  * The amdgpu driver provides a sysfs API for retrieving current gpu
@@ -1937,6 +2015,7 @@ static struct amdgpu_device_attr amdgpu_device_attrs[] = {
 	AMDGPU_DEVICE_ATTR_RW(pp_features,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RO(unique_id,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RW(thermal_throttling_logging,		ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
+	AMDGPU_DEVICE_ATTR_RW(apu_thermal_cap,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RO(gpu_metrics,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RO(smartshift_apu_power,			ATTR_FLAG_BASIC,
 			      .attr_update = ss_power_attr_update),