Merge branch 'drm-next-4.9' of git://people.freedesktop.org/~agd5f/linux into drm-next

More radeon and amdgpu changes for 4.9. Highlights:
- Initial SI support for amdgpu (controlled by a Kconfig option)
- misc ttm cleanups
- runtimepm fixes
- S3/S4 fixes
- power improvements
- lots of code cleanups and optimizations

* 'drm-next-4.9' of git://people.freedesktop.org/~agd5f/linux: (151 commits)
  drm/ttm: remove cpu_address member from ttm_tt
  drm/radeon/radeon_device: remove unused function
  drm/amdgpu: clean function declarations in amdgpu_ttm.c up
  drm/amdgpu: use the new ring ib and dma frame size callbacks (v2)
  drm/amdgpu/vce3: add ring callbacks for ib and dma frame size
  drm/amdgpu/vce2: add ring callbacks for ib and dma frame size
  drm/amdgpu/vce: add common ring callbacks for ib and dma frame size
  drm/amdgpu/uvd6: add ring callbacks for ib and dma frame size
  drm/amdgpu/uvd5: add ring callbacks for ib and dma frame size
  drm/amdgpu/uvd4.2: add ring callbacks for ib and dma frame size
  drm/amdgpu/sdma3: add ring callbacks for ib and dma frame size
  drm/amdgpu/sdma2.4: add ring callbacks for ib and dma frame size
  drm/amdgpu/cik_sdma: add ring callbacks for ib and dma frame size
  drm/amdgpu/si_dma: add ring callbacks for ib and dma frame size
  drm/amdgpu/gfx8: add ring callbacks for ib and dma frame size
  drm/amdgpu/gfx7: add ring callbacks for ib and dma frame size
  drm/amdgpu/gfx6: add ring callbacks for ib and dma frame size
  drm/amdgpu/ring: add an interface to get dma frame and ib size
  drm/amdgpu/sdma3: drop unused functions
  drm/amdgpu/gfx6: drop gds_switch callback
  ...

6 files changed, 69 insertions, 28 deletions

diff --git a/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h b/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h
index 3f8172f545b0..18f39e89a7aa 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h
@@ -131,9 +131,6 @@ struct amd_pp_init {
 	struct cgs_device *device;
 	uint32_t chip_family;
 	uint32_t chip_id;
-	uint32_t rev_id;
-	uint16_t sub_sys_id;
-	uint16_t sub_vendor_id;
 };
 
 enum amd_pp_display_config_type{
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
index 962cb5385951..d4495839c64c 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
@@ -341,7 +341,6 @@ extern int phm_powerdown_uvd(struct pp_hwmgr *hwmgr);
 extern int phm_setup_asic(struct pp_hwmgr *hwmgr);
 extern int phm_enable_dynamic_state_management(struct pp_hwmgr *hwmgr);
 extern int phm_disable_dynamic_state_management(struct pp_hwmgr *hwmgr);
-extern void phm_init_dynamic_caps(struct pp_hwmgr *hwmgr);
 extern bool phm_is_hw_access_blocked(struct pp_hwmgr *hwmgr);
 extern int phm_block_hw_access(struct pp_hwmgr *hwmgr, bool block);
 extern int phm_set_power_state(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 36b4ec9c9cb1..e98748344801 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -31,18 +31,20 @@
 #include "hwmgr_ppt.h"
 #include "ppatomctrl.h"
 #include "hwmgr_ppt.h"
+#include "power_state.h"
 
 struct pp_instance;
 struct pp_hwmgr;
-struct pp_hw_power_state;
-struct pp_power_state;
-struct PP_VCEState;
 struct phm_fan_speed_info;
 struct pp_atomctrl_voltage_table;
 
-
 extern int amdgpu_powercontainment;
 extern int amdgpu_sclk_deep_sleep_en;
+extern unsigned amdgpu_pp_feature_mask;
+
+#define VOLTAGE_SCALE 4
+
+uint8_t convert_to_vid(uint16_t vddc);
 
 enum DISPLAY_GAP {
 	DISPLAY_GAP_VBLANK_OR_WM = 0,   /* Wait for vblank or MCHG watermark. */
@@ -52,7 +54,6 @@ enum DISPLAY_GAP {
 };
 typedef enum DISPLAY_GAP DISPLAY_GAP;
 
-
 struct vi_dpm_level {
 	bool enabled;
 	uint32_t value;
@@ -74,6 +75,19 @@ enum PP_Result {
 #define PCIE_PERF_REQ_GEN2         3
 #define PCIE_PERF_REQ_GEN3         4
 
+enum PP_FEATURE_MASK {
+	PP_SCLK_DPM_MASK = 0x1,
+	PP_MCLK_DPM_MASK = 0x2,
+	PP_PCIE_DPM_MASK = 0x4,
+	PP_SCLK_DEEP_SLEEP_MASK = 0x8,
+	PP_POWER_CONTAINMENT_MASK = 0x10,
+	PP_UVD_HANDSHAKE_MASK = 0x20,
+	PP_SMC_VOLTAGE_CONTROL_MASK = 0x40,
+	PP_VBI_TIME_SUPPORT_MASK = 0x80,
+	PP_ULV_MASK = 0x100,
+	PP_ENABLE_GFX_CG_THRU_SMU = 0x200
+};
+
 enum PHM_BackEnd_Magic {
 	PHM_Dummy_Magic       = 0xAA5555AA,
 	PHM_RV770_Magic       = 0xDCBAABCD,
@@ -354,7 +368,7 @@ struct pp_table_func {
 	int (*pptable_get_vce_state_table_entry)(
 						struct pp_hwmgr *hwmgr,
 						unsigned long i,
-						struct PP_VCEState *vce_state,
+						struct pp_vce_state *vce_state,
 						void **clock_info,
 						unsigned long *flag);
 };
@@ -573,22 +587,43 @@ struct phm_microcode_version_info {
 	uint32_t NB;
 };
 
+#define PP_MAX_VCE_LEVELS 6
+
+enum PP_VCE_LEVEL {
+	PP_VCE_LEVEL_AC_ALL = 0,     /* AC, All cases */
+	PP_VCE_LEVEL_DC_EE = 1,      /* DC, entropy encoding */
+	PP_VCE_LEVEL_DC_LL_LOW = 2,  /* DC, low latency queue, res <= 720 */
+	PP_VCE_LEVEL_DC_LL_HIGH = 3, /* DC, low latency queue, 1080 >= res > 720 */
+	PP_VCE_LEVEL_DC_GP_LOW = 4,  /* DC, general purpose queue, res <= 720 */
+	PP_VCE_LEVEL_DC_GP_HIGH = 5, /* DC, general purpose queue, 1080 >= res > 720 */
+};
+
+
+enum PP_TABLE_VERSION {
+	PP_TABLE_V0 = 0,
+	PP_TABLE_V1,
+	PP_TABLE_V2,
+	PP_TABLE_MAX
+};
+
 /**
  * The main hardware manager structure.
  */
 struct pp_hwmgr {
 	uint32_t chip_family;
 	uint32_t chip_id;
-	uint32_t hw_revision;
-	uint32_t sub_sys_id;
-	uint32_t sub_vendor_id;
 
+	uint32_t pp_table_version;
 	void *device;
 	struct pp_smumgr *smumgr;
 	const void *soft_pp_table;
 	uint32_t soft_pp_table_size;
 	void *hardcode_pp_table;
 	bool need_pp_table_upload;
+
+	struct pp_vce_state vce_states[PP_MAX_VCE_LEVELS];
+	uint32_t num_vce_state_tables;
+
 	enum amd_dpm_forced_level dpm_level;
 	bool block_hw_access;
 	struct phm_gfx_arbiter gfx_arbiter;
@@ -626,6 +661,7 @@ struct pp_hwmgr {
 	struct pp_power_state    *boot_ps;
 	struct pp_power_state    *uvd_ps;
 	struct amd_pp_display_configuration display_config;
+	uint32_t feature_mask;
 };
 
 
@@ -661,6 +697,8 @@ extern void phm_trim_voltage_table_to_fit_state_table(uint32_t max_vol_steps, st
 extern int phm_reset_single_dpm_table(void *table, uint32_t count, int max);
 extern void phm_setup_pcie_table_entry(void *table, uint32_t index, uint32_t pcie_gen, uint32_t pcie_lanes);
 extern int32_t phm_get_dpm_level_enable_mask_value(void *table);
+extern uint8_t phm_get_voltage_id(struct pp_atomctrl_voltage_table *voltage_table,
+		uint32_t voltage);
 extern uint8_t phm_get_voltage_index(struct phm_ppt_v1_voltage_lookup_table *lookup_table, uint16_t voltage);
 extern uint16_t phm_find_closest_vddci(struct pp_atomctrl_voltage_table *vddci_table, uint16_t vddci);
 extern int phm_find_boot_level(void *table, uint32_t value, uint32_t *boot_level);
@@ -671,6 +709,9 @@ extern int phm_hwmgr_backend_fini(struct pp_hwmgr *hwmgr);
 extern uint32_t phm_get_lowest_enabled_level(struct pp_hwmgr *hwmgr, uint32_t mask);
 extern void phm_apply_dal_min_voltage_request(struct pp_hwmgr *hwmgr);
 
+extern int phm_get_voltage_evv_on_sclk(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
+				uint32_t sclk, uint16_t id, uint16_t *voltage);
+
 #define PHM_ENTIRE_REGISTER_MASK 0xFFFFFFFFU
 
 #define PHM_FIELD_SHIFT(reg, field) reg##__##field##__SHIFT
@@ -685,8 +726,6 @@ extern void phm_apply_dal_min_voltage_request(struct pp_hwmgr *hwmgr);
 	 PHM_FIELD_SHIFT(reg, field))
 
 
-
-
 /* Operations on named fields. */
 
 #define PHM_READ_FIELD(device, reg, field)	\
diff --git a/drivers/gpu/drm/amd/powerplay/inc/power_state.h b/drivers/gpu/drm/amd/powerplay/inc/power_state.h
index a3f0ce4d5835..9ceaed9ac52a 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/power_state.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/power_state.h
@@ -158,7 +158,7 @@ struct pp_power_state {
 
 
 /*Structure to hold a VCE state entry*/
-struct PP_VCEState {
+struct pp_vce_state {
 	uint32_t evclk;
 	uint32_t ecclk;
 	uint32_t sclk;
@@ -171,30 +171,28 @@ enum PP_MMProfilingState {
 	PP_MMProfilingState_Stopped
 };
 
-struct PP_Clock_Engine_Request {
-	unsigned long clientType;
-	unsigned long ctxid;
+struct pp_clock_engine_request {
+	unsigned long client_type;
+	unsigned long ctx_id;
 	uint64_t  context_handle;
 	unsigned long sclk;
-	unsigned long sclkHardMin;
+	unsigned long sclk_hard_min;
 	unsigned long mclk;
 	unsigned long iclk;
 	unsigned long evclk;
 	unsigned long ecclk;
-	unsigned long ecclkHardMin;
+	unsigned long ecclk_hard_min;
 	unsigned long vclk;
 	unsigned long dclk;
-	unsigned long samclk;
-	unsigned long acpclk;
-	unsigned long sclkOverdrive;
-	unsigned long mclkOverdrive;
+	unsigned long sclk_over_drive;
+	unsigned long mclk_over_drive;
 	unsigned long sclk_threshold;
 	unsigned long flag;
 	unsigned long vclk_ceiling;
 	unsigned long dclk_ceiling;
 	unsigned long num_cus;
-	unsigned long pmflag;
-	enum PP_MMProfilingState MMProfilingState;
+	unsigned long pm_flag;
+	enum PP_MMProfilingState mm_profiling_state;
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_debug.h b/drivers/gpu/drm/amd/powerplay/inc/pp_debug.h
index d7d83b7c7f95..bfdbec10cdd5 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/pp_debug.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/pp_debug.h
@@ -43,5 +43,8 @@
 	} while (0)
 
 
+#define GET_FLEXIBLE_ARRAY_MEMBER_ADDR(type, member, ptr, n)	\
+	(type *)((char *)&(ptr)->member + (sizeof(type) * (n)))
+
 #endif /* PP_DEBUG_H */
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
index 3c235f0177cd..34abfd2cde53 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
@@ -74,7 +74,6 @@ struct pp_smumgr_func {
 struct pp_smumgr {
 	uint32_t chip_family;
 	uint32_t chip_id;
-	uint32_t hw_revision;
 	void *device;
 	void *backend;
 	uint32_t usec_timeout;
@@ -122,6 +121,12 @@ extern int smu_allocate_memory(void *device, uint32_t size,
 
 extern int smu_free_memory(void *device, void *handle);
 
+extern int cz_smum_init(struct pp_smumgr *smumgr);
+extern int iceland_smum_init(struct pp_smumgr *smumgr);
+extern int tonga_smum_init(struct pp_smumgr *smumgr);
+extern int fiji_smum_init(struct pp_smumgr *smumgr);
+extern int polaris10_smum_init(struct pp_smumgr *smumgr);
+
 #define SMUM_FIELD_SHIFT(reg, field) reg##__##field##__SHIFT
 
 #define SMUM_FIELD_MASK(reg, field) reg##__##field##_MASK