Merge tag 'drm-next-5.3-2019-07-18' of git://people.freedesktop.org/~…

…agd5f/linux into drm-next

drm-next-5.3-2019-07-18:

amdgpu:
- Navi DC fix for secondary adapters
- Fix Navi flickering with high res panels
- Navi SMU fixes
- Vega20 SMU fixes
- Fixes for audio hotplug on HG systems
- Fix for potential integer overflows on large buffer
  migrations
- debugfs fixes for umr
- Various other small fixes

amdkfd:
- Apply noretry setting consistently
- Fix hang in eviction
- Properly clean up GWS on uninit

UAPI:
- clarify a comment on ctx priority

Signed-off-by: Dave Airlie <[email protected]>
From: Alex Deucher <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

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

@@ -164,6 +164,7 @@ extern int amdgpu_async_gfx_ring;
 extern int amdgpu_mcbp;
 extern int amdgpu_discovery;
 extern int amdgpu_mes;
+extern int amdgpu_noretry;
 
 #ifdef CONFIG_DRM_AMDGPU_SI
 extern int amdgpu_si_support;

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

@@ -106,10 +106,10 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 	ssize_t result = 0;
 	int r;
 	bool pm_pg_lock, use_bank, use_ring;
-	unsigned instance_bank, sh_bank, se_bank, me, pipe, queue;
+	unsigned instance_bank, sh_bank, se_bank, me, pipe, queue, vmid;
 
 	pm_pg_lock = use_bank = use_ring = false;
-	instance_bank = sh_bank = se_bank = me = pipe = queue = 0;
+	instance_bank = sh_bank = se_bank = me = pipe = queue = vmid = 0;
 
 	if (size & 0x3 || *pos & 0x3 ||
 			((*pos & (1ULL << 62)) && (*pos & (1ULL << 61))))
@@ -135,6 +135,7 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 		me = (*pos & GENMASK_ULL(33, 24)) >> 24;
 		pipe = (*pos & GENMASK_ULL(43, 34)) >> 34;
 		queue = (*pos & GENMASK_ULL(53, 44)) >> 44;
+		vmid = (*pos & GENMASK_ULL(58, 54)) >> 54;
 
 		use_ring = 1;
 	} else {
@@ -152,7 +153,7 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 					sh_bank, instance_bank);
 	} else if (use_ring) {
 		mutex_lock(&adev->srbm_mutex);
-		amdgpu_gfx_select_me_pipe_q(adev, me, pipe, queue);
+		amdgpu_gfx_select_me_pipe_q(adev, me, pipe, queue, vmid);
 	}
 
 	if (pm_pg_lock)
@@ -185,7 +186,7 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 		mutex_unlock(&adev->grbm_idx_mutex);
 	} else if (use_ring) {
-		amdgpu_gfx_select_me_pipe_q(adev, 0, 0, 0);
+		amdgpu_gfx_select_me_pipe_q(adev, 0, 0, 0, 0);
 		mutex_unlock(&adev->srbm_mutex);
 	}
 

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

@@ -2537,6 +2537,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	hash_init(adev->mn_hash);
 	mutex_init(&adev->lock_reset);
 	mutex_init(&adev->virt.dpm_mutex);
+	mutex_init(&adev->psp.mutex);
 
 	r = amdgpu_device_check_arguments(adev);
 	if (r)

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

@@ -123,7 +123,7 @@ static int hw_id_map[MAX_HWIP] = {
 	[UVD_HWIP]	= UVD_HWID,
 	[VCE_HWIP]	= VCE_HWID,
 	[DF_HWIP]	= DF_HWID,
-	[DCE_HWIP]	= DCEAZ_HWID,
+	[DCE_HWIP]	= DMU_HWID,
 	[OSSSYS_HWIP]	= OSSSYS_HWID,
 	[SMUIO_HWIP]	= SMUIO_HWID,
 	[PWR_HWIP]	= PWR_HWID,

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

@@ -140,8 +140,9 @@ uint amdgpu_smu_memory_pool_size = 0;
 uint amdgpu_dc_feature_mask = 0;
 int amdgpu_async_gfx_ring = 1;
 int amdgpu_mcbp = 0;
-int amdgpu_discovery = 0;
+int amdgpu_discovery = -1;
 int amdgpu_mes = 0;
+int amdgpu_noretry;
 
 struct amdgpu_mgpu_info mgpu_info = {
 	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
@@ -593,6 +594,7 @@ module_param_named(mcbp, amdgpu_mcbp, int, 0444);
 /**
  * DOC: discovery (int)
  * Allow driver to discover hardware IP information from IP Discovery table at the top of VRAM.
+ * (-1 = auto (default), 0 = disabled, 1 = enabled)
  */
 MODULE_PARM_DESC(discovery,
 	"Allow driver to discover hardware IPs from IP Discovery table at the top of VRAM");
@@ -607,6 +609,10 @@ MODULE_PARM_DESC(mes,
 	"Enable Micro Engine Scheduler (0 = disabled (default), 1 = enabled)");
 module_param_named(mes, amdgpu_mes, int, 0444);
 
+MODULE_PARM_DESC(noretry,
+	"Disable retry faults (0 = retry enabled (default), 1 = retry disabled)");
+module_param_named(noretry, amdgpu_noretry, int, 0644);
+
 #ifdef CONFIG_HSA_AMD
 /**
  * DOC: sched_policy (int)
@@ -682,17 +688,6 @@ module_param(ignore_crat, int, 0444);
 MODULE_PARM_DESC(ignore_crat,
 	"Ignore CRAT table during KFD initialization (0 = use CRAT (default), 1 = ignore CRAT)");
 
-/**
- * DOC: noretry (int)
- * This parameter sets sh_mem_config.retry_disable. Default value, 0, enables retry.
- * Setting 1 disables retry.
- * Retry is needed for recoverable page faults.
- */
-int noretry;
-module_param(noretry, int, 0644);
-MODULE_PARM_DESC(noretry,
-	"Set sh_mem_config.retry_disable on Vega10 (0 = retry enabled (default), 1 = retry disabled)");
-
 /**
  * DOC: halt_if_hws_hang (int)
  * Halt if HWS hang is detected. Default value, 0, disables the halt on hang.

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

@@ -195,7 +195,7 @@ struct amdgpu_gfx_funcs {
 				uint32_t wave, uint32_t start, uint32_t size,
 				uint32_t *dst);
 	void (*select_me_pipe_q)(struct amdgpu_device *adev, u32 me, u32 pipe,
-				 u32 queue);
+				 u32 queue, u32 vmid);
 };
 
 struct amdgpu_ngg_buf {
@@ -327,7 +327,7 @@ struct amdgpu_gfx {
 
 #define amdgpu_gfx_get_gpu_clock_counter(adev) (adev)->gfx.funcs->get_gpu_clock_counter((adev))
 #define amdgpu_gfx_select_se_sh(adev, se, sh, instance) (adev)->gfx.funcs->select_se_sh((adev), (se), (sh), (instance))
-#define amdgpu_gfx_select_me_pipe_q(adev, me, pipe, q) (adev)->gfx.funcs->select_me_pipe_q((adev), (me), (pipe), (q))
+#define amdgpu_gfx_select_me_pipe_q(adev, me, pipe, q, vmid) (adev)->gfx.funcs->select_me_pipe_q((adev), (me), (pipe), (q), (vmid))
 
 /**
  * amdgpu_gfx_create_bitmask - create a bitmask

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

@@ -2077,11 +2077,6 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev,
 	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
 		return -EINVAL;
 
-	/* sanity check PP is enabled */
-	if (!(adev->powerplay.pp_funcs &&
-	      adev->powerplay.pp_funcs->read_sensor))
-	      return -EINVAL;
-
 	/* get the sclk */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GFX_SCLK,
 				   (void *)&sclk, &size);
@@ -2112,11 +2107,6 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev,
 	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
 		return -EINVAL;
 
-	/* sanity check PP is enabled */
-	if (!(adev->powerplay.pp_funcs &&
-	      adev->powerplay.pp_funcs->read_sensor))
-	      return -EINVAL;
-
 	/* get the sclk */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GFX_MCLK,
 				   (void *)&mclk, &size);
@@ -2996,13 +2986,10 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 	}
 
 	if (is_support_sw_smu(adev)) {
-		struct smu_context *smu = &adev->smu;
 		struct smu_dpm_context *smu_dpm = &adev->smu.smu_dpm;
-		mutex_lock(&(smu->mutex));
 		smu_handle_task(&adev->smu,
 				smu_dpm->dpm_level,
 				AMD_PP_TASK_DISPLAY_CONFIG_CHANGE);
-		mutex_unlock(&(smu->mutex));
 	} else {
 		if (adev->powerplay.pp_funcs->dispatch_tasks) {
 			if (!amdgpu_device_has_dc_support(adev)) {

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

@@ -130,6 +130,8 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	int index;
 	int timeout = 2000;
 
+	mutex_lock(&psp->mutex);
+
 	memset(psp->cmd_buf_mem, 0, PSP_CMD_BUFFER_SIZE);
 
 	memcpy(psp->cmd_buf_mem, cmd, sizeof(struct psp_gfx_cmd_resp));
@@ -139,6 +141,7 @@ psp_cmd_submit_buf(struct psp_context *psp,
 			     fence_mc_addr, index);
 	if (ret) {
 		atomic_dec(&psp->fence_value);
+		mutex_unlock(&psp->mutex);
 		return ret;
 	}
 
@@ -161,8 +164,10 @@ psp_cmd_submit_buf(struct psp_context *psp,
 				  ucode->ucode_id);
 		DRM_WARN("psp command failed and response status is (%d)\n",
 			  psp->cmd_buf_mem->resp.status);
-		if (!timeout)
+		if (!timeout) {
+			mutex_unlock(&psp->mutex);
 			return -EINVAL;
+		}
 	}
 
 	/* get xGMI session id from response buffer */
@@ -172,6 +177,7 @@ psp_cmd_submit_buf(struct psp_context *psp,
 		ucode->tmr_mc_addr_lo = psp->cmd_buf_mem->resp.fw_addr_lo;
 		ucode->tmr_mc_addr_hi = psp->cmd_buf_mem->resp.fw_addr_hi;
 	}
+	mutex_unlock(&psp->mutex);
 
 	return ret;
 }
@@ -763,6 +769,15 @@ static int psp_hw_start(struct psp_context *psp)
 	int ret;
 
 	if (!amdgpu_sriov_vf(adev) || !adev->in_gpu_reset) {
+		if (psp->kdb_bin_size &&
+		    (psp->funcs->bootloader_load_kdb != NULL)) {
+			ret = psp_bootloader_load_kdb(psp);
+			if (ret) {
+				DRM_ERROR("PSP load kdb failed!\n");
+				return ret;
+			}
+		}
+
 		ret = psp_bootloader_load_sysdrv(psp);
 		if (ret) {
 			DRM_ERROR("PSP load sysdrv failed!\n");
@@ -1188,10 +1203,16 @@ static int psp_resume(void *handle)
 
 int psp_gpu_reset(struct amdgpu_device *adev)
 {
+	int ret;
+
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP)
 		return 0;
 
-	return psp_mode1_reset(&adev->psp);
+	mutex_lock(&adev->psp.mutex);
+	ret = psp_mode1_reset(&adev->psp);
+	mutex_unlock(&adev->psp.mutex);
+
+	return ret;
 }
 
 int psp_rlc_autoload_start(struct psp_context *psp)

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

@@ -42,6 +42,12 @@ struct psp_context;
 struct psp_xgmi_node_info;
 struct psp_xgmi_topology_info;
 
+enum psp_bootloader_cmd {
+	PSP_BL__LOAD_SYSDRV		= 0x10000,
+	PSP_BL__LOAD_SOSDRV		= 0x20000,
+	PSP_BL__LOAD_KEY_DATABASE	= 0x80000,
+};
+
 enum psp_ring_type
 {
 	PSP_RING_TYPE__INVALID = 0,
@@ -73,6 +79,7 @@ enum psp_reg_prog_id {
 struct psp_funcs
 {
 	int (*init_microcode)(struct psp_context *psp);
+	int (*bootloader_load_kdb)(struct psp_context *psp);
 	int (*bootloader_load_sysdrv)(struct psp_context *psp);
 	int (*bootloader_load_sos)(struct psp_context *psp);
 	int (*ring_init)(struct psp_context *psp, enum psp_ring_type ring_type);
@@ -156,9 +163,11 @@ struct psp_context
 	uint32_t			sys_bin_size;
 	uint32_t			sos_bin_size;
 	uint32_t			toc_bin_size;
+	uint32_t			kdb_bin_size;
 	uint8_t				*sys_start_addr;
 	uint8_t				*sos_start_addr;
 	uint8_t				*toc_start_addr;
+	uint8_t				*kdb_start_addr;
 
 	/* tmr buffer */
 	struct amdgpu_bo		*tmr_bo;
@@ -201,6 +210,7 @@ struct psp_context
 	uint8_t				*ta_ras_start_addr;
 	struct psp_xgmi_context		xgmi_context;
 	struct psp_ras_context		ras;
+	struct mutex			mutex;
 };
 
 struct amdgpu_psp_funcs {
@@ -219,6 +229,8 @@ struct amdgpu_psp_funcs {
 		(psp)->funcs->compare_sram_data((psp), (ucode), (type))
 #define psp_init_microcode(psp) \
 		((psp)->funcs->init_microcode ? (psp)->funcs->init_microcode((psp)) : 0)
+#define psp_bootloader_load_kdb(psp) \
+		((psp)->funcs->bootloader_load_kdb ? (psp)->funcs->bootloader_load_kdb((psp)) : 0)
 #define psp_bootloader_load_sysdrv(psp) \
 		((psp)->funcs->bootloader_load_sysdrv ? (psp)->funcs->bootloader_load_sysdrv((psp)) : 0)
 #define psp_bootloader_load_sos(psp) \