Merge tag 'amd-drm-next-5.17-2021-12-16' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amdgpu:
- Add some display debugfs entries
- RAS fixes
- SR-IOV fixes
- W=1 fixes
- Documentation fixes
- IH timestamp fix
- Misc power fixes
- IP discovery fixes
- Large driver documentation updates
- Multi-GPU memory use reductions
- Misc display fixes and cleanups
- Add new SMU debug option

amdkfd:
- SVM fixes

radeon:
- Fix typo in comment

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211216202731.5900-1-alexander.deucher@amd.com

1 files changed, 118 insertions, 27 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 90d22a376632..8219e40240ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -30,6 +30,7 @@
 #include <linux/module.h>
 #include <linux/console.h>
 #include <linux/slab.h>
+#include <linux/iommu.h>
 
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_probe_helper.h>
@@ -331,7 +332,7 @@ void amdgpu_device_mm_access(struct amdgpu_device *adev, loff_t pos,
 }
 
 /**
- * amdgpu_device_vram_access - access vram by vram aperature
+ * amdgpu_device_aper_access - access vram by vram aperature
  *
  * @adev: amdgpu_device pointer
  * @pos: offset of the buffer in vram
@@ -550,11 +551,11 @@ void amdgpu_device_wreg(struct amdgpu_device *adev,
 	trace_amdgpu_device_wreg(adev->pdev->device, reg, v);
 }
 
-/*
+/**
  * amdgpu_mm_wreg_mmio_rlc -  write register either with mmio or with RLC path if in range
  *
  * this function is invoked only the debugfs register access
- * */
+ */
 void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev,
 			     uint32_t reg, uint32_t v)
 {
@@ -1100,7 +1101,7 @@ static void amdgpu_device_wb_fini(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_device_wb_init- Init Writeback driver info and allocate memory
+ * amdgpu_device_wb_init - Init Writeback driver info and allocate memory
  *
  * @adev: amdgpu_device pointer
  *
@@ -2657,6 +2658,36 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * amdgpu_device_smu_fini_early - smu hw_fini wrapper
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * For ASICs need to disable SMC first
+ */
+static void amdgpu_device_smu_fini_early(struct amdgpu_device *adev)
+{
+	int i, r;
+
+	if (adev->ip_versions[GC_HWIP][0] > IP_VERSION(9, 0, 0))
+		return;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].status.hw)
+			continue;
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC) {
+			r = adev->ip_blocks[i].version->funcs->hw_fini((void *)adev);
+			/* XXX handle errors */
+			if (r) {
+				DRM_DEBUG("hw_fini of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].version->funcs->name, r);
+			}
+			adev->ip_blocks[i].status.hw = false;
+			break;
+		}
+	}
+}
+
 static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
 {
 	int i, r;
@@ -2677,21 +2708,8 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
 	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
 
-	/* need to disable SMC first */
-	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_blocks[i].status.hw)
-			continue;
-		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC) {
-			r = adev->ip_blocks[i].version->funcs->hw_fini((void *)adev);
-			/* XXX handle errors */
-			if (r) {
-				DRM_DEBUG("hw_fini of IP block <%s> failed %d\n",
-					  adev->ip_blocks[i].version->funcs->name, r);
-			}
-			adev->ip_blocks[i].status.hw = false;
-			break;
-		}
-	}
+	/* Workaroud for ASICs need to disable SMC first */
+	amdgpu_device_smu_fini_early(adev);
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.hw)
@@ -2733,8 +2751,6 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev) && adev->virt.ras_init_done)
 		amdgpu_virt_release_ras_err_handler_data(adev);
 
-	amdgpu_ras_pre_fini(adev);
-
 	if (adev->gmc.xgmi.num_physical_nodes > 1)
 		amdgpu_xgmi_remove_device(adev);
 
@@ -3367,6 +3383,22 @@ static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
 	return ret;
 }
 
+/**
+ * amdgpu_device_check_iommu_direct_map - check if RAM direct mapped to GPU
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * RAM direct mapped to GPU if IOMMU is not enabled or is pass through mode
+ */
+static void amdgpu_device_check_iommu_direct_map(struct amdgpu_device *adev)
+{
+	struct iommu_domain *domain;
+
+	domain = iommu_get_domain_for_dev(adev->dev);
+	if (!domain || domain->type == IOMMU_DOMAIN_IDENTITY)
+		adev->ram_is_direct_mapped = true;
+}
+
 static const struct attribute *amdgpu_dev_attributes[] = {
 	&dev_attr_product_name.attr,
 	&dev_attr_product_number.attr,
@@ -3770,6 +3802,8 @@ fence_driver_init:
 		queue_delayed_work(system_wq, &mgpu_info.delayed_reset_work,
 				   msecs_to_jiffies(AMDGPU_RESUME_MS));
 
+	amdgpu_device_check_iommu_direct_map(adev);
+
 	return 0;
 
 release_ras_con:
@@ -3803,7 +3837,7 @@ static void amdgpu_device_unmap_mmio(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_device_fini - tear down the driver
+ * amdgpu_device_fini_hw - tear down the driver
  *
  * @adev: amdgpu_device pointer
  *
@@ -3844,6 +3878,9 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 		amdgpu_ucode_sysfs_fini(adev);
 	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
 
+	/* disable ras feature must before hw fini */
+	amdgpu_ras_pre_fini(adev);
+
 	amdgpu_device_ip_fini_early(adev);
 
 	amdgpu_irq_fini_hw(adev);
@@ -4284,6 +4321,9 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 				     bool from_hypervisor)
 {
 	int r;
+	struct amdgpu_hive_info *hive = NULL;
+
+	amdgpu_amdkfd_pre_reset(adev);
 
 	amdgpu_amdkfd_pre_reset(adev);
 
@@ -4312,8 +4352,19 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		goto error;
 
-	amdgpu_irq_gpu_reset_resume_helper(adev);
-	r = amdgpu_ib_ring_tests(adev);
+	hive = amdgpu_get_xgmi_hive(adev);
+	/* Update PSP FW topology after reset */
+	if (hive && adev->gmc.xgmi.num_physical_nodes > 1)
+		r = amdgpu_xgmi_update_topology(hive, adev);
+
+	if (hive)
+		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);
+	}
 
 error:
 	if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
@@ -4745,7 +4796,7 @@ static int amdgpu_device_lock_hive_adev(struct amdgpu_device *adev, struct amdgp
 {
 	struct amdgpu_device *tmp_adev = NULL;
 
-	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+	if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) {
 		if (!hive) {
 			dev_err(adev->dev, "Hive is NULL while device has multiple xgmi nodes");
 			return -ENODEV;
@@ -4957,7 +5008,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	 * We always reset all schedulers for device and all devices for XGMI
 	 * hive so that should take care of them too.
 	 */
-	hive = amdgpu_get_xgmi_hive(adev);
+	if (!amdgpu_sriov_vf(adev))
+		hive = amdgpu_get_xgmi_hive(adev);
 	if (hive) {
 		if (atomic_cmpxchg(&hive->in_reset, 0, 1) != 0) {
 			DRM_INFO("Bailing on TDR for s_job:%llx, hive: %llx as another already in progress",
@@ -4998,7 +5050,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	 * to put adev in the 1st position.
 	 */
 	INIT_LIST_HEAD(&device_list);
-	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+	if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) {
 		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head)
 			list_add_tail(&tmp_adev->reset_list, &device_list);
 		if (!list_is_first(&adev->reset_list, &device_list))
@@ -5632,3 +5684,42 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev,
 
 	amdgpu_asic_invalidate_hdp(adev, ring);
 }
+
+/**
+ * amdgpu_device_halt() - bring hardware to some kind of halt state
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Bring hardware to some kind of halt state so that no one can touch it
+ * any more. It will help to maintain error context when error occurred.
+ * Compare to a simple hang, the system will keep stable at least for SSH
+ * access. Then it should be trivial to inspect the hardware state and
+ * see what's going on. Implemented as following:
+ *
+ * 1. drm_dev_unplug() makes device inaccessible to user space(IOCTLs, etc),
+ *    clears all CPU mappings to device, disallows remappings through page faults
+ * 2. amdgpu_irq_disable_all() disables all interrupts
+ * 3. amdgpu_fence_driver_hw_fini() signals all HW fences
+ * 4. set adev->no_hw_access to avoid potential crashes after setp 5
+ * 5. amdgpu_device_unmap_mmio() clears all MMIO mappings
+ * 6. pci_disable_device() and pci_wait_for_pending_transaction()
+ *    flush any in flight DMA operations
+ */
+void amdgpu_device_halt(struct amdgpu_device *adev)
+{
+	struct pci_dev *pdev = adev->pdev;
+	struct drm_device *ddev = adev_to_drm(adev);
+
+	drm_dev_unplug(ddev);
+
+	amdgpu_irq_disable_all(adev);
+
+	amdgpu_fence_driver_hw_fini(adev);
+
+	adev->no_hw_access = true;
+
+	amdgpu_device_unmap_mmio(adev);
+
+	pci_disable_device(pdev);
+	pci_wait_for_pending_transaction(pdev);
+}