Merge branch 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/l…

…inux into drm-next

Last set of features for 4.15.  Highlights:
- Add a bo flag to allow buffers to opt out of implicit sync
- Add ctx priority setting interface
- Lots more powerplay cleanups
- Start to plumb through vram lost infrastructure for gpu reset
- ttm support for huge pages
- misc cleanups and bug fixes

* 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux: (73 commits)
  drm/amd/powerplay: Place the constant on the right side of the test
  drm/amd/powerplay: Remove useless variable
  drm/amd/powerplay: Don't cast kzalloc() return value
  drm/amdgpu: allow GTT overcommit during bind
  drm/amdgpu: linear validate first then bind to GART
  drm/amd/pp: Fix overflow when setup decf/pix/disp dpm table.
  drm/amd/pp: thermal control not enabled on vega10.
  drm/amdgpu: busywait KIQ register accessing (v4)
  drm/amdgpu: report more amdgpu_fence_info
  drm/amdgpu:don't check soft_reset for sriov
  drm/amdgpu:fix duplicated setting job's vram_lost
  drm/amdgpu:reduce wb to 512 slot
  drm/amdgpu: fix regresstion on SR-IOV gpu reset failed
  drm/amd/powerplay: Tidy up cz_dpm_powerup_vce()
  drm/amd/powerplay: Tidy up cz_dpm_powerdown_vce()
  drm/amd/powerplay: Tidy up cz_dpm_update_vce_dpm()
  drm/amd/powerplay: Tidy up cz_dpm_update_uvd_dpm()
  drm/amd/powerplay: Tidy up cz_dpm_powerup_uvd()
  drm/amd/powerplay: Tidy up cz_dpm_powerdown_uvd()
  drm/amd/powerplay: Tidy up cz_start_dpm()
  ...

drivers/gpu/drm/amd/amdgpu/Makefile

@@ -25,7 +25,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_prime.o amdgpu_vm.o amdgpu_ib.o amdgpu_pll.o \
 	amdgpu_ucode.o amdgpu_bo_list.o amdgpu_ctx.o amdgpu_sync.o \
 	amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \
-	amdgpu_queue_mgr.o amdgpu_vf_error.o
+	amdgpu_queue_mgr.o amdgpu_vf_error.o amdgpu_sched.o
 
 # add asic specific block
 amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \

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

@@ -732,10 +732,14 @@ struct amdgpu_ctx {
 	struct amdgpu_device    *adev;
 	struct amdgpu_queue_mgr queue_mgr;
 	unsigned		reset_counter;
+	uint32_t		vram_lost_counter;
 	spinlock_t		ring_lock;
 	struct dma_fence	**fences;
 	struct amdgpu_ctx_ring	rings[AMDGPU_MAX_RINGS];
-	bool preamble_presented;
+	bool			preamble_presented;
+	enum amd_sched_priority init_priority;
+	enum amd_sched_priority override_priority;
+	struct mutex            lock;
 };
 
 struct amdgpu_ctx_mgr {
@@ -752,13 +756,18 @@ int amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
 			      struct dma_fence *fence, uint64_t *seq);
 struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,
 				   struct amdgpu_ring *ring, uint64_t seq);
+void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx,
+				  enum amd_sched_priority priority);
 
 int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 		     struct drm_file *filp);
 
+int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx, unsigned ring_id);
+
 void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr);
 void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr);
 
+
 /*
  * file private structure
  */
@@ -770,7 +779,6 @@ struct amdgpu_fpriv {
 	struct mutex		bo_list_lock;
 	struct idr		bo_list_handles;
 	struct amdgpu_ctx_mgr	ctx_mgr;
-	u32			vram_lost_counter;
 };
 
 /*
@@ -871,7 +879,7 @@ struct amdgpu_mec {
 struct amdgpu_kiq {
 	u64			eop_gpu_addr;
 	struct amdgpu_bo	*eop_obj;
-	struct mutex		ring_mutex;
+	spinlock_t              ring_lock;
 	struct amdgpu_ring	ring;
 	struct amdgpu_irq_src	irq;
 };
@@ -1035,6 +1043,10 @@ struct amdgpu_gfx {
 	bool                            in_suspend;
 	/* NGG */
 	struct amdgpu_ngg		ngg;
+
+	/* pipe reservation */
+	struct mutex			pipe_reserve_mutex;
+	DECLARE_BITMAP			(pipe_reserve_bitmap, AMDGPU_MAX_COMPUTE_QUEUES);
 };
 
 int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
@@ -1113,6 +1125,7 @@ struct amdgpu_job {
 	uint32_t		gds_base, gds_size;
 	uint32_t		gws_base, gws_size;
 	uint32_t		oa_base, oa_size;
+	uint32_t		vram_lost_counter;
 
 	/* user fence handling */
 	uint64_t		uf_addr;
@@ -1138,7 +1151,7 @@ static inline void amdgpu_set_ib_value(struct amdgpu_cs_parser *p,
 /*
  * Writeback
  */
-#define AMDGPU_MAX_WB 1024	/* Reserve at most 1024 WB slots for amdgpu-owned rings. */
+#define AMDGPU_MAX_WB 512	/* Reserve at most 512 WB slots for amdgpu-owned rings. */
 
 struct amdgpu_wb {
 	struct amdgpu_bo	*wb_obj;
@@ -1378,6 +1391,18 @@ struct amdgpu_atcs {
 	struct amdgpu_atcs_functions functions;
 };
 
+/*
+ * Firmware VRAM reservation
+ */
+struct amdgpu_fw_vram_usage {
+	u64 start_offset;
+	u64 size;
+	struct amdgpu_bo *reserved_bo;
+	void *va;
+};
+
+int amdgpu_fw_reserve_vram_init(struct amdgpu_device *adev);
+
 /*
  * CGS
  */
@@ -1582,6 +1607,8 @@ struct amdgpu_device {
 	struct delayed_work     late_init_work;
 
 	struct amdgpu_virt	virt;
+	/* firmware VRAM reservation */
+	struct amdgpu_fw_vram_usage fw_vram_usage;
 
 	/* link all shadow bo */
 	struct list_head                shadow_list;
@@ -1833,8 +1860,6 @@ static inline bool amdgpu_has_atpx(void) { return false; }
 extern const struct drm_ioctl_desc amdgpu_ioctls_kms[];
 extern const int amdgpu_max_kms_ioctl;
 
-bool amdgpu_kms_vram_lost(struct amdgpu_device *adev,
-			  struct amdgpu_fpriv *fpriv);
 int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags);
 void amdgpu_driver_unload_kms(struct drm_device *dev);
 void amdgpu_driver_lastclose_kms(struct drm_device *dev);

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

@@ -1807,6 +1807,8 @@ int amdgpu_atombios_allocate_fb_scratch(struct amdgpu_device *adev)
 	uint16_t data_offset;
 	int usage_bytes = 0;
 	struct _ATOM_VRAM_USAGE_BY_FIRMWARE *firmware_usage;
+	u64 start_addr;
+	u64 size;
 
 	if (amdgpu_atom_parse_data_header(ctx, index, NULL, NULL, NULL, &data_offset)) {
 		firmware_usage = (struct _ATOM_VRAM_USAGE_BY_FIRMWARE *)(ctx->bios + data_offset);
@@ -1815,7 +1817,21 @@ int amdgpu_atombios_allocate_fb_scratch(struct amdgpu_device *adev)
 			  le32_to_cpu(firmware_usage->asFirmwareVramReserveInfo[0].ulStartAddrUsedByFirmware),
 			  le16_to_cpu(firmware_usage->asFirmwareVramReserveInfo[0].usFirmwareUseInKb));
 
-		usage_bytes = le16_to_cpu(firmware_usage->asFirmwareVramReserveInfo[0].usFirmwareUseInKb) * 1024;
+		start_addr = firmware_usage->asFirmwareVramReserveInfo[0].ulStartAddrUsedByFirmware;
+		size = firmware_usage->asFirmwareVramReserveInfo[0].usFirmwareUseInKb;
+
+		if ((uint32_t)(start_addr & ATOM_VRAM_OPERATION_FLAGS_MASK) ==
+			(uint32_t)(ATOM_VRAM_BLOCK_SRIOV_MSG_SHARE_RESERVATION <<
+			ATOM_VRAM_OPERATION_FLAGS_SHIFT)) {
+			/* Firmware request VRAM reservation for SR-IOV */
+			adev->fw_vram_usage.start_offset = (start_addr &
+				(~ATOM_VRAM_OPERATION_FLAGS_MASK)) << 10;
+			adev->fw_vram_usage.size = size << 10;
+			/* Use the default scratch size */
+			usage_bytes = 0;
+		} else {
+			usage_bytes = le16_to_cpu(firmware_usage->asFirmwareVramReserveInfo[0].usFirmwareUseInKb) * 1024;
+		}
 	}
 	ctx->scratch_size_bytes = 0;
 	if (usage_bytes == 0)