Merge tag 'amd-drm-next-6.13-2024-11-15' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.13-2024-11-15:

amdgpu:
- Parition fixes
- GFX 12 fixes
- SR-IOV fixes
- MES fixes
- RAS fixes
- GC queue handling fixes
- VCN fixes
- Add sysfs reset masks
- Better error messages for P2P failurs
- SMU fixes
- Documentation updates
- GFX11 enforce isolation updates
- Display HPD fixes
- PSR fixes
- Panel replay fixes
- DP MST fixes
- USB4 fixes
- Misc display fixes and cleanups
- VRAM handling fix for APUs
- NBIO fix

amdkfd:
- INIT_WORK fix
- Refcount fix
- KFD MES scheduling fixes

drm/fourcc:
- Add missing tiling mode

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241115165012.573465-1-alexander.deucher@amd.com

1 files changed, 53 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 0450eab6ade74..0171d240fcb05 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4236,7 +4236,10 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	 * for throttling interrupt) = 60 seconds.
 	 */
 	ratelimit_state_init(&adev->throttling_logging_rs, (60 - 1) * HZ, 1);
+	ratelimit_state_init(&adev->virt.ras_telemetry_rs, 5 * HZ, 1);
+
 	ratelimit_set_flags(&adev->throttling_logging_rs, RATELIMIT_MSG_ON_RELEASE);
+	ratelimit_set_flags(&adev->virt.ras_telemetry_rs, RATELIMIT_MSG_ON_RELEASE);
 
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */
@@ -5186,6 +5189,9 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
 	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 0, 3))
 		amdgpu_ras_resume(adev);
+
+	amdgpu_virt_ras_telemetry_post_reset(adev);
+
 	return 0;
 }
 
@@ -6200,6 +6206,9 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
 	bool p2p_access =
 		!adev->gmc.xgmi.connected_to_cpu &&
 		!(pci_p2pdma_distance(adev->pdev, peer_adev->dev, false) < 0);
+	if (!p2p_access)
+		dev_info(adev->dev, "PCIe P2P access from peer device %s is not supported by the chipset\n",
+			pci_name(peer_adev->pdev));
 
 	bool is_large_bar = adev->gmc.visible_vram_size &&
 		adev->gmc.real_vram_size == adev->gmc.visible_vram_size;
@@ -6715,3 +6724,47 @@ uint32_t amdgpu_device_wait_on_rreg(struct amdgpu_device *adev,
 	}
 	return ret;
 }
+
+ssize_t amdgpu_get_soft_full_reset_mask(struct amdgpu_ring *ring)
+{
+	ssize_t size = 0;
+
+	if (!ring || !ring->adev)
+		return size;
+
+	if (amdgpu_device_should_recover_gpu(ring->adev))
+		size |= AMDGPU_RESET_TYPE_FULL;
+
+	if (unlikely(!ring->adev->debug_disable_soft_recovery) &&
+	    !amdgpu_sriov_vf(ring->adev) && ring->funcs->soft_recovery)
+		size |= AMDGPU_RESET_TYPE_SOFT_RESET;
+
+	return size;
+}
+
+ssize_t amdgpu_show_reset_mask(char *buf, uint32_t supported_reset)
+{
+	ssize_t size = 0;
+
+	if (supported_reset == 0) {
+		size += sysfs_emit_at(buf, size, "unsupported");
+		size += sysfs_emit_at(buf, size, "\n");
+		return size;
+
+	}
+
+	if (supported_reset & AMDGPU_RESET_TYPE_SOFT_RESET)
+		size += sysfs_emit_at(buf, size, "soft ");
+
+	if (supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)
+		size += sysfs_emit_at(buf, size, "queue ");
+
+	if (supported_reset & AMDGPU_RESET_TYPE_PER_PIPE)
+		size += sysfs_emit_at(buf, size, "pipe ");
+
+	if (supported_reset & AMDGPU_RESET_TYPE_FULL)
+		size += sysfs_emit_at(buf, size, "full ");
+
+	size += sysfs_emit_at(buf, size, "\n");
+	return size;
+}