Merge branch 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux into drm-next

First feature request for 4.16.  Highlights:
- RV and Vega header cleanups
- TTM operation context support
- 48 bit GPUVM fixes for Vega/RV
- More smatch fixes
- ECC support for vega10
- Resizeable BAR support
- Multi-display sync support in DC
- SR-IOV fixes
- Various scheduler improvements
- GPU reset fixes and vram lost tracking
- Clean up DC/powerplay interfaces
- DCN display fixes
- Various DC fixes

* 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux: (291 commits)
  drm/radeon: Use drm_fb_helper_lastclose() and _poll_changed()
  drm/amdgpu: Use drm_fb_helper_lastclose() and _poll_changed()
  drm/amd/display: Use drm_fb_helper_poll_changed()
  drm/ttm: swap consecutive allocated pooled pages v4
  drm/amdgpu: fix amdgpu_sync_resv v2
  drm/ttm: swap consecutive allocated cached pages v3
  drm/amd/amdgpu: set gtt size according to system memory size only
  drm/amdgpu: Get rid of dep_sync as a seperate object.
  drm/amdgpu: allow specifying vm_block_size for multi level PDs v2
  drm/amdgpu: move validation of the VM size into the VM code
  drm/amdgpu: allow non pot VM size values
  drm/amdgpu: choose number of VM levels based on VM size
  drm/amdgpu: unify VM size handling of Vega10 with older generation
  drm/amdgpu: fix amdgpu_vm_num_entries
  drm/amdgpu: fix VM PD addr shift
  drm/amdgpu: correct vce4.0 fw config for SRIOV (V2)
  drm/amd/display: Don't call dm_log_to_buffer directly in dc_conn_log
  drm/amd/display: Add dm_logger_append_va API
  drm/ttm: Use a static string instead of an array of char *
  drm/amd/display: remove usage of legacy_cursor_update
  ...

1 files changed, 21 insertions, 8 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 0b14b5373783..5e2958a79928 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -47,6 +47,8 @@
 #include <drm/amdgpu_drm.h>
 
 #include <kgd_kfd_interface.h>
+#include "dm_pp_interface.h"
+#include "kgd_pp_interface.h"
 
 #include "amd_shared.h"
 #include "amdgpu_mode.h"
@@ -59,7 +61,6 @@
 #include "amdgpu_sync.h"
 #include "amdgpu_ring.h"
 #include "amdgpu_vm.h"
-#include "amd_powerplay.h"
 #include "amdgpu_dpm.h"
 #include "amdgpu_acp.h"
 #include "amdgpu_uvd.h"
@@ -67,11 +68,11 @@
 #include "amdgpu_vcn.h"
 #include "amdgpu_mn.h"
 #include "amdgpu_dm.h"
-
 #include "gpu_scheduler.h"
 #include "amdgpu_virt.h"
 #include "amdgpu_gart.h"
 
+
 /*
  * Modules parameters.
  */
@@ -177,6 +178,10 @@ extern int amdgpu_cik_support;
 #define CIK_CURSOR_WIDTH 128
 #define CIK_CURSOR_HEIGHT 128
 
+/* GPU RESET flags */
+#define AMDGPU_RESET_INFO_VRAM_LOST  (1 << 0)
+#define AMDGPU_RESET_INFO_FULLRESET  (1 << 1)
+
 struct amdgpu_device;
 struct amdgpu_ib;
 struct amdgpu_cs_parser;
@@ -735,6 +740,7 @@ struct amdgpu_ctx {
 	struct amdgpu_device    *adev;
 	struct amdgpu_queue_mgr queue_mgr;
 	unsigned		reset_counter;
+	unsigned        reset_counter_query;
 	uint32_t		vram_lost_counter;
 	spinlock_t		ring_lock;
 	struct dma_fence	**fences;
@@ -743,6 +749,7 @@ struct amdgpu_ctx {
 	enum amd_sched_priority init_priority;
 	enum amd_sched_priority override_priority;
 	struct mutex            lock;
+	atomic_t	guilty;
 };
 
 struct amdgpu_ctx_mgr {
@@ -1114,7 +1121,6 @@ struct amdgpu_job {
 	struct amdgpu_vm	*vm;
 	struct amdgpu_ring	*ring;
 	struct amdgpu_sync	sync;
-	struct amdgpu_sync	dep_sync;
 	struct amdgpu_sync	sched_sync;
 	struct amdgpu_ib	*ibs;
 	struct dma_fence	*fence; /* the hw fence */
@@ -1405,6 +1411,7 @@ struct amdgpu_fw_vram_usage {
 };
 
 int amdgpu_fw_reserve_vram_init(struct amdgpu_device *adev);
+void amdgpu_fw_reserve_vram_fini(struct amdgpu_device *adev);
 
 /*
  * CGS
@@ -1421,6 +1428,13 @@ typedef void (*amdgpu_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
 typedef uint32_t (*amdgpu_block_rreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
 typedef void (*amdgpu_block_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t, uint32_t);
 
+struct amd_powerplay {
+	struct cgs_device *cgs_device;
+	void *pp_handle;
+	const struct amd_ip_funcs *ip_funcs;
+	const struct amd_pm_funcs *pp_funcs;
+};
+
 #define AMDGPU_RESET_MAGIC_NUM 64
 struct amdgpu_device {
 	struct device			*dev;
@@ -1616,9 +1630,6 @@ struct amdgpu_device {
 	/* link all shadow bo */
 	struct list_head                shadow_list;
 	struct mutex                    shadow_list_lock;
-	/* link all gtt */
-	spinlock_t			gtt_list_lock;
-	struct list_head                gtt_list;
 	/* keep an lru list of rings by HW IP */
 	struct list_head		ring_lru_list;
 	spinlock_t			ring_lru_list_lock;
@@ -1629,7 +1640,8 @@ struct amdgpu_device {
 
 	/* record last mm index being written through WREG32*/
 	unsigned long last_mm_index;
-	bool                            in_sriov_reset;
+	bool                            in_gpu_reset;
+	struct mutex  lock_reset;
 };
 
 static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)
@@ -1823,7 +1835,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_psp_check_fw_loading_status(adev, i) (adev)->firmware.funcs->check_fw_loading_status((adev), (i))
 
 /* Common functions */
-int amdgpu_gpu_reset(struct amdgpu_device *adev);
+int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job* job);
 bool amdgpu_need_backup(struct amdgpu_device *adev);
 void amdgpu_pci_config_reset(struct amdgpu_device *adev);
 bool amdgpu_need_post(struct amdgpu_device *adev);
@@ -1835,6 +1847,7 @@ void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain);
 bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
 void amdgpu_vram_location(struct amdgpu_device *adev, struct amdgpu_mc *mc, u64 base);
 void amdgpu_gart_location(struct amdgpu_device *adev, struct amdgpu_mc *mc);
+int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev);
 void amdgpu_ttm_set_active_vram_size(struct amdgpu_device *adev, u64 size);
 int amdgpu_ttm_init(struct amdgpu_device *adev);
 void amdgpu_ttm_fini(struct amdgpu_device *adev);