Merge tag 'amd-drm-next-6.6-2023-08-11' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amdgpu:
- SDMA 6.1.0 support
- SMU 13.x fixes
- PSP 13.x fixes
- HDP 6.1 support
- SMUIO 14.0 support
- IH 6.1 support
- Coding style cleanups
- Misc display fixes
- Initial Freesync panel replay support
- RAS fixes
- SDMA 5.2 MGCG updates
- SR-IOV fixes
- DCN3+ gamma fix
- Revert zpos properly until IGT regression is fixed
- NBIO 7.9 fixes
- Use TTM to manage the doorbell BAR
- Async flip fix
- DPIA tracing support
- DCN 3.x TMDS HDMI fixes
- FRU fixes

amdkfd:
- Coding style cleanups
- SVM fixes
- Trap handler fixes
- Convert older APUs to use dGPU path like newer APUs
- Drop IOMMUv2 path as it is no longer used

radeon:
- Coding style cleanups

drm buddy:
- Fix debugging output

UAPI:
- A new memory pool was added to amdgpu_drm.h since we converted doorbell BAR management to use TTM,
  but userspace is blocked from allocating from it at this point, so kind of not really anything new
  here per se

Signed-off-by: Dave Airlie <airlied@redhat.com>

# -----BEGIN PGP SIGNATURE-----
#
# iHUEABYKAB0WIQQgO5Idg2tXNTSZAr293/aFa7yZ2AUCZNahZwAKCRC93/aFa7yZ
# 2KNjAP0UV2vJZjrze7OQI/YoI+40UlGjS81nKGlMIN3eR8nzvAD/c9McLJViL82R
# idEAK7tsr/MaCKoPAlED7CkUZiHNlQw=
# =4w7I
# -----END PGP SIGNATURE-----
# gpg: Signature made Sat 12 Aug 2023 07:00:23 AEST
# gpg:                using EDDSA key 203B921D836B5735349902BDBDDFF6856BBC99D8
# gpg: Can't check signature: No public key
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230811211554.7804-1-alexander.deucher@amd.com

1 files changed, 30 insertions, 78 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index dc0e5227119b..91d7f9e4fefc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -164,71 +164,6 @@ static DEVICE_ATTR(pcie_replay_count, 0444,
 
 static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev);
 
-/**
- * DOC: product_name
- *
- * The amdgpu driver provides a sysfs API for reporting the product name
- * for the device
- * The file product_name is used for this and returns the product name
- * as returned from the FRU.
- * NOTE: This is only available for certain server cards
- */
-
-static ssize_t amdgpu_device_get_product_name(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = drm_to_adev(ddev);
-
-	return sysfs_emit(buf, "%s\n", adev->product_name);
-}
-
-static DEVICE_ATTR(product_name, 0444,
-		amdgpu_device_get_product_name, NULL);
-
-/**
- * DOC: product_number
- *
- * The amdgpu driver provides a sysfs API for reporting the part number
- * for the device
- * The file product_number is used for this and returns the part number
- * as returned from the FRU.
- * NOTE: This is only available for certain server cards
- */
-
-static ssize_t amdgpu_device_get_product_number(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = drm_to_adev(ddev);
-
-	return sysfs_emit(buf, "%s\n", adev->product_number);
-}
-
-static DEVICE_ATTR(product_number, 0444,
-		amdgpu_device_get_product_number, NULL);
-
-/**
- * DOC: serial_number
- *
- * The amdgpu driver provides a sysfs API for reporting the serial number
- * for the device
- * The file serial_number is used for this and returns the serial number
- * as returned from the FRU.
- * NOTE: This is only available for certain server cards
- */
-
-static ssize_t amdgpu_device_get_serial_number(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = drm_to_adev(ddev);
-
-	return sysfs_emit(buf, "%s\n", adev->serial);
-}
-
-static DEVICE_ATTR(serial_number, 0444,
-		amdgpu_device_get_serial_number, NULL);
 
 /**
  * amdgpu_device_supports_px - Is the device a dGPU with ATPX power control
@@ -1297,6 +1232,32 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
 }
 
 /*
+ * On APUs with >= 64GB white flickering has been observed w/ SG enabled.
+ * Disable S/G on such systems until we have a proper fix.
+ * https://gitlab.freedesktop.org/drm/amd/-/issues/2354
+ * https://gitlab.freedesktop.org/drm/amd/-/issues/2735
+ */
+bool amdgpu_sg_display_supported(struct amdgpu_device *adev)
+{
+	switch (amdgpu_sg_display) {
+	case -1:
+		break;
+	case 0:
+		return false;
+	case 1:
+		return true;
+	default:
+		return false;
+	}
+	if ((totalram_pages() << (PAGE_SHIFT - 10)) +
+	    (adev->gmc.real_vram_size / 1024) >= 64000000) {
+		DRM_WARN("Disabling S/G due to >=64GB RAM\n");
+		return false;
+	}
+	return true;
+}
+
+/*
  * Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic
  * speed switching. Until we have confirmation from Intel that a specific host
  * supports it, it's safer that we keep it disabled for all.
@@ -3275,12 +3236,6 @@ static int amdgpu_device_ip_resume(struct amdgpu_device *adev)
 {
 	int r;
 
-	if (!adev->in_s0ix) {
-		r = amdgpu_amdkfd_resume_iommu(adev);
-		if (r)
-			return r;
-	}
-
 	r = amdgpu_device_ip_resume_phase1(adev);
 	if (r)
 		return r;
@@ -3524,9 +3479,6 @@ static void amdgpu_device_check_iommu_direct_map(struct amdgpu_device *adev)
 }
 
 static const struct attribute *amdgpu_dev_attributes[] = {
-	&dev_attr_product_name.attr,
-	&dev_attr_product_number.attr,
-	&dev_attr_serial_number.attr,
 	&dev_attr_pcie_replay_count.attr,
 	NULL
 };
@@ -3941,6 +3893,8 @@ fence_driver_init:
 	if (r)
 		dev_err(adev->dev, "Could not create amdgpu device attr\n");
 
+	amdgpu_fru_sysfs_init(adev);
+
 	if (IS_ENABLED(CONFIG_PERF_EVENTS))
 		r = amdgpu_pmu_init(adev);
 	if (r)
@@ -4060,6 +4014,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 	if (adev->ucode_sysfs_en)
 		amdgpu_ucode_sysfs_fini(adev);
 	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
+	amdgpu_fru_sysfs_fini(adev);
 
 	/* disable ras feature must before hw fini */
 	amdgpu_ras_pre_fini(adev);
@@ -4576,6 +4531,7 @@ retry:
 		r = amdgpu_virt_reset_gpu(adev);
 	if (r)
 		return r;
+	amdgpu_irq_gpu_reset_resume_helper(adev);
 
 	/* some sw clean up VF needs to do before recover */
 	amdgpu_virt_post_reset(adev);
@@ -4605,7 +4561,6 @@ retry:
 		amdgpu_put_xgmi_hive(hive);
 
 	if (!r) {
-		amdgpu_irq_gpu_reset_resume_helper(adev);
 		r = amdgpu_ib_ring_tests(adev);
 
 		amdgpu_amdkfd_post_reset(adev);
@@ -4985,9 +4940,6 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 				dev_warn(tmp_adev->dev, "asic atom init failed!");
 			} else {
 				dev_info(tmp_adev->dev, "GPU reset succeeded, trying to resume\n");
-				r = amdgpu_amdkfd_resume_iommu(tmp_adev);
-				if (r)
-					goto out;
 
 				r = amdgpu_device_ip_resume_phase1(tmp_adev);
 				if (r)