drm/amdgpu: Add init levels

Add init levels to define the level to which device needs to be
initialized.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Tested-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -823,6 +823,24 @@ struct amdgpu_mqd {
 			struct amdgpu_mqd_prop *p);
 };
 
+/*
+ * Custom Init levels could be defined for different situations where a full
+ * initialization of all hardware blocks are not expected. Sample cases are
+ * custom init sequences after resume after S0i3/S3, reset on initialization,
+ * partial reset of blocks etc. Presently, this defines only two levels. Levels
+ * are described in corresponding struct definitions - amdgpu_init_default,
+ * amdgpu_init_minimal_xgmi.
+ */
+enum amdgpu_init_lvl_id {
+	AMDGPU_INIT_LEVEL_DEFAULT,
+	AMDGPU_INIT_LEVEL_MINIMAL_XGMI,
+};
+
+struct amdgpu_init_level {
+	enum amdgpu_init_lvl_id level;
+	uint32_t hwini_ip_block_mask;
+};
+
 #define AMDGPU_RESET_MAGIC_NUM 64
 #define AMDGPU_MAX_DF_PERFMONS 4
 struct amdgpu_reset_domain;
@@ -1168,6 +1186,8 @@ struct amdgpu_device {
 	bool				enforce_isolation[MAX_XCP];
 	/* Added this mutex for cleaner shader isolation between GFX and compute processes */
 	struct mutex                    enforce_isolation_mutex;
+
+	struct amdgpu_init_level *init_lvl;
 };
 
 static inline uint32_t amdgpu_ip_version(const struct amdgpu_device *adev,
@@ -1621,4 +1641,6 @@ extern const struct attribute_group amdgpu_vram_mgr_attr_group;
 extern const struct attribute_group amdgpu_gtt_mgr_attr_group;
 extern const struct attribute_group amdgpu_flash_attr_group;
 
+void amdgpu_set_init_level(struct amdgpu_device *adev,
+			   enum amdgpu_init_lvl_id lvl);
 #endif

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -144,6 +144,50 @@ const char *amdgpu_asic_name[] = {
 	"LAST",
 };
 
+#define AMDGPU_IP_BLK_MASK_ALL GENMASK(AMDGPU_MAX_IP_NUM - 1, 0)
+/*
+ * Default init level where all blocks are expected to be initialized. This is
+ * the level of initialization expected by default and also after a full reset
+ * of the device.
+ */
+struct amdgpu_init_level amdgpu_init_default = {
+	.level = AMDGPU_INIT_LEVEL_DEFAULT,
+	.hwini_ip_block_mask = AMDGPU_IP_BLK_MASK_ALL,
+};
+
+/*
+ * Minimal blocks needed to be initialized before a XGMI hive can be reset. This
+ * is used for cases like reset on initialization where the entire hive needs to
+ * be reset before first use.
+ */
+struct amdgpu_init_level amdgpu_init_minimal_xgmi = {
+	.level = AMDGPU_INIT_LEVEL_MINIMAL_XGMI,
+	.hwini_ip_block_mask =
+		BIT(AMD_IP_BLOCK_TYPE_GMC) | BIT(AMD_IP_BLOCK_TYPE_SMC) |
+		BIT(AMD_IP_BLOCK_TYPE_COMMON) | BIT(AMD_IP_BLOCK_TYPE_IH)
+};
+
+static inline bool amdgpu_ip_member_of_hwini(struct amdgpu_device *adev,
+					     enum amd_ip_block_type block)
+{
+	return (adev->init_lvl->hwini_ip_block_mask & (1U << block)) != 0;
+}
+
+void amdgpu_set_init_level(struct amdgpu_device *adev,
+			   enum amdgpu_init_lvl_id lvl)
+{
+	switch (lvl) {
+	case AMDGPU_INIT_LEVEL_MINIMAL_XGMI:
+		adev->init_lvl = &amdgpu_init_minimal_xgmi;
+		break;
+	case AMDGPU_INIT_LEVEL_DEFAULT:
+		fallthrough;
+	default:
+		adev->init_lvl = &amdgpu_init_default;
+		break;
+	}
+}
+
 static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev);
 
 /**
@@ -2655,6 +2699,9 @@ static int amdgpu_device_ip_hw_init_phase1(struct amdgpu_device *adev)
 			continue;
 		if (adev->ip_blocks[i].status.hw)
 			continue;
+		if (!amdgpu_ip_member_of_hwini(
+			    adev, adev->ip_blocks[i].version->type))
+			continue;
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
 		    (amdgpu_sriov_vf(adev) && (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP)) ||
 		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH) {
@@ -2680,6 +2727,9 @@ static int amdgpu_device_ip_hw_init_phase2(struct amdgpu_device *adev)
 			continue;
 		if (adev->ip_blocks[i].status.hw)
 			continue;
+		if (!amdgpu_ip_member_of_hwini(
+			    adev, adev->ip_blocks[i].version->type))
+			continue;
 		r = adev->ip_blocks[i].version->funcs->hw_init(adev);
 		if (r) {
 			DRM_ERROR("hw_init of IP block <%s> failed %d\n",
@@ -2703,6 +2753,10 @@ static int amdgpu_device_fw_loading(struct amdgpu_device *adev)
 			if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_PSP)
 				continue;
 
+			if (!amdgpu_ip_member_of_hwini(adev,
+						       AMD_IP_BLOCK_TYPE_PSP))
+				break;
+
 			if (!adev->ip_blocks[i].status.sw)
 				continue;
 
@@ -2825,6 +2879,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 		}
 		adev->ip_blocks[i].status.sw = true;
 
+		if (!amdgpu_ip_member_of_hwini(
+			    adev, adev->ip_blocks[i].version->type))
+			continue;
+
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON) {
 			/* need to do common hw init early so everything is set up for gmc */
 			r = adev->ip_blocks[i].version->funcs->hw_init((void *)adev);
@@ -4215,6 +4273,12 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 
 	amdgpu_device_set_mcbp(adev);
 
+	/*
+	 * By default, use default mode where all blocks are expected to be
+	 * initialized. At present a 'swinit' of blocks is required to be
+	 * completed before the need for a different level is detected.
+	 */
+	amdgpu_set_init_level(adev, AMDGPU_INIT_LEVEL_DEFAULT);
 	/* early init functions */
 	r = amdgpu_device_ip_early_init(adev);
 	if (r)
@@ -5414,6 +5478,8 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 	}
 
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
+		/* After reset, it's default init level */
+		amdgpu_set_init_level(tmp_adev, AMDGPU_INIT_LEVEL_DEFAULT);
 		if (need_full_reset) {
 			/* post card */
 			amdgpu_ras_set_fed(tmp_adev, false);