Merge branch 'drm-next-4.13' of git://people.freedesktop.org/~agd5f/linux into drm-next

New radeon and amdgpu features for 4.13:
- Lots of Vega10 bug fixes
- Preliminary Raven support
- KIQ support for compute rings
- MEC queue management rework from Andres
- Audio support for DCE6
- SR-IOV improvements
- Improved module parameters for controlling radeon vs amdgpu support
  for SI and CIK
- Bug fixes
- General code cleanups

[airlied: dropped drmP.h header from one file was needed and build broke]

* 'drm-next-4.13' of git://people.freedesktop.org/~agd5f/linux: (362 commits)
  drm/amdgpu: Fix compiler warnings
  drm/amdgpu: vm_update_ptes remove code duplication
  drm/amd/amdgpu: Port VCN over to new SOC15 macros
  drm/amd/amdgpu: Port PSP v10.0 over to new SOC15 macros
  drm/amd/amdgpu: Port PSP v3.1 over to new SOC15 macros
  drm/amd/amdgpu: Port NBIO v7.0 driver over to new SOC15 macros
  drm/amd/amdgpu: Port NBIO v6.1 driver over to new SOC15 macros
  drm/amd/amdgpu: Port UVD 7.0 over to new SOC15 macros
  drm/amd/amdgpu: Port MMHUB over to new SOC15 macros
  drm/amd/amdgpu: Cleanup gfxhub read-modify-write patterns
  drm/amd/amdgpu: Port GFXHUB over to new SOC15 macros
  drm/amd/amdgpu: Add offset variant to SOC15 macros
  drm/amd/powerplay: add avfs control for Vega10
  drm/amdgpu: add virtual display support for raven
  drm/amdgpu/gfx9: fix compute ring doorbell index
  drm/amd/amdgpu: Rename KIQ ring to avoid spaces
  drm/amd/amdgpu: gfx9 tidy ups (v2)
  drm/amdgpu: add contiguous flag in ucode bo create
  drm/amdgpu: fix missed gpu info firmware when cache firmware during S3
  drm/amdgpu: export test ib debugfs interface
  ...

80 files changed, 9413 insertions, 4627 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/Kconfig b/drivers/gpu/drm/amd/amdgpu/Kconfig
index 61360e27715f..26682454a446 100644
--- a/drivers/gpu/drm/amd/amdgpu/Kconfig
+++ b/drivers/gpu/drm/amd/amdgpu/Kconfig
@@ -5,15 +5,23 @@ config DRM_AMDGPU_SI
 	  Choose this option if you want to enable experimental support
 	  for SI asics.
 
+	  SI is already supported in radeon. Experimental support for SI
+	  in amdgpu will be disabled by default and is still provided by
+	  radeon. Use module options to override this:
+
+	  radeon.si_support=0 amdgpu.si_support=1
+
 config DRM_AMDGPU_CIK
 	bool "Enable amdgpu support for CIK parts"
 	depends on DRM_AMDGPU
 	help
-	  Choose this option if you want to enable experimental support
-	  for CIK asics.
+	  Choose this option if you want to enable support for CIK asics.
+
+	  CIK is already supported in radeon. Support for CIK in amdgpu
+	  will be disabled by default and is still provided by radeon.
+	  Use module options to override this:
 
-	  CIK is already supported in radeon.  CIK support in amdgpu
-	  is for experimentation and testing.
+	  radeon.cik_support=0 amdgpu.cik_support=1
 
 config DRM_AMDGPU_USERPTR
 	bool "Always enable userptr write support"
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 20bde726419e..faea6349228f 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -24,7 +24,8 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	atombios_encoders.o amdgpu_sa.o atombios_i2c.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_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \
+	amdgpu_queue_mgr.o
 
 # add asic specific block
 amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \
@@ -34,7 +35,7 @@ amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \
 amdgpu-$(CONFIG_DRM_AMDGPU_SI)+= si.o gmc_v6_0.o gfx_v6_0.o si_ih.o si_dma.o dce_v6_0.o si_dpm.o si_smc.o
 
 amdgpu-y += \
-	vi.o mxgpu_vi.o nbio_v6_1.o soc15.o mxgpu_ai.o
+	vi.o mxgpu_vi.o nbio_v6_1.o soc15.o mxgpu_ai.o nbio_v7_0.o
 
 # add GMC block
 amdgpu-y += \
@@ -54,7 +55,8 @@ amdgpu-y += \
 # add PSP block
 amdgpu-y += \
 	amdgpu_psp.o \
-	psp_v3_1.o
+	psp_v3_1.o \
+	psp_v10_0.o
 
 # add SMC block
 amdgpu-y += \
@@ -92,6 +94,11 @@ amdgpu-y += \
 	vce_v3_0.o \
 	vce_v4_0.o
 
+# add VCN block
+amdgpu-y += \
+	amdgpu_vcn.o \
+	vcn_v1_0.o
+
 # add amdkfd interfaces
 amdgpu-y += \
 	 amdgpu_amdkfd.o \
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 77ff68f9932b..e0adad590ecb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -46,6 +46,8 @@
 #include <drm/drm_gem.h>
 #include <drm/amdgpu_drm.h>
 
+#include <kgd_kfd_interface.h>
+
 #include "amd_shared.h"
 #include "amdgpu_mode.h"
 #include "amdgpu_ih.h"
@@ -62,6 +64,7 @@
 #include "amdgpu_acp.h"
 #include "amdgpu_uvd.h"
 #include "amdgpu_vce.h"
+#include "amdgpu_vcn.h"
 
 #include "gpu_scheduler.h"
 #include "amdgpu_virt.h"
@@ -92,6 +95,7 @@ extern int amdgpu_vm_size;
 extern int amdgpu_vm_block_size;
 extern int amdgpu_vm_fault_stop;
 extern int amdgpu_vm_debug;
+extern int amdgpu_vm_update_mode;
 extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
 extern int amdgpu_no_evict;
@@ -109,6 +113,15 @@ extern int amdgpu_prim_buf_per_se;
 extern int amdgpu_pos_buf_per_se;
 extern int amdgpu_cntl_sb_buf_per_se;
 extern int amdgpu_param_buf_per_se;
+extern int amdgpu_job_hang_limit;
+extern int amdgpu_lbpw;
+
+#ifdef CONFIG_DRM_AMDGPU_SI
+extern int amdgpu_si_support;
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+extern int amdgpu_cik_support;
+#endif
 
 #define AMDGPU_DEFAULT_GTT_SIZE_MB		3072ULL /* 3GB by default */
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
@@ -305,8 +318,8 @@ struct amdgpu_gart_funcs {
 	/* set pte flags based per asic */
 	uint64_t (*get_vm_pte_flags)(struct amdgpu_device *adev,
 				     uint32_t flags);
-	/* adjust mc addr in fb for APU case */
-	u64 (*adjust_mc_addr)(struct amdgpu_device *adev, u64 addr);
+	/* get the pde for a given mc addr */
+	u64 (*get_vm_pde)(struct amdgpu_device *adev, u64 addr);
 	uint32_t (*get_invalidate_req)(unsigned int vm_id);
 };
 
@@ -554,7 +567,7 @@ int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev);
 void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev);
 int amdgpu_gart_init(struct amdgpu_device *adev);
 void amdgpu_gart_fini(struct amdgpu_device *adev);
-void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
+int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 			int pages);
 int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 		     int pages, struct page **pagelist,
@@ -602,6 +615,7 @@ struct amdgpu_mc {
 	uint32_t                srbm_soft_reset;
 	struct amdgpu_mode_mc_save save;
 	bool			prt_warning;
+	uint64_t		stolen_size;
 	/* apertures */
 	u64					shared_aperture_start;
 	u64					shared_aperture_end;
@@ -772,6 +786,29 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
 		      struct dma_fence **f);
 
 /*
+ * Queue manager
+ */
+struct amdgpu_queue_mapper {
+	int 		hw_ip;
+	struct mutex	lock;
+	/* protected by lock */
+	struct amdgpu_ring *queue_map[AMDGPU_MAX_RINGS];
+};
+
+struct amdgpu_queue_mgr {
+	struct amdgpu_queue_mapper mapper[AMDGPU_MAX_IP_NUM];
+};
+
+int amdgpu_queue_mgr_init(struct amdgpu_device *adev,
+			  struct amdgpu_queue_mgr *mgr);
+int amdgpu_queue_mgr_fini(struct amdgpu_device *adev,
+			  struct amdgpu_queue_mgr *mgr);
+int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
+			 struct amdgpu_queue_mgr *mgr,
+			 int hw_ip, int instance, int ring,
+			 struct amdgpu_ring **out_ring);
+
+/*
  * context related structures
  */
 
@@ -784,6 +821,7 @@ struct amdgpu_ctx_ring {
 struct amdgpu_ctx {
 	struct kref		refcount;
 	struct amdgpu_device    *adev;
+	struct amdgpu_queue_mgr queue_mgr;
 	unsigned		reset_counter;
 	spinlock_t		ring_lock;
 	struct dma_fence	**fences;
@@ -822,6 +860,7 @@ struct amdgpu_fpriv {
 	struct mutex		bo_list_lock;
 	struct idr		bo_list_handles;
 	struct amdgpu_ctx_mgr	ctx_mgr;
+	u32			vram_lost_counter;
 };
 
 /*
@@ -893,20 +932,26 @@ struct amdgpu_rlc {
 	u32 *register_restore;
 };
 
+#define AMDGPU_MAX_COMPUTE_QUEUES KGD_MAX_QUEUES
+
 struct amdgpu_mec {
 	struct amdgpu_bo	*hpd_eop_obj;
 	u64			hpd_eop_gpu_addr;
 	struct amdgpu_bo	*mec_fw_obj;
 	u64			mec_fw_gpu_addr;
-	u32 num_pipe;
 	u32 num_mec;
-	u32 num_queue;
+	u32 num_pipe_per_mec;
+	u32 num_queue_per_pipe;
 	void			*mqd_backup[AMDGPU_MAX_COMPUTE_RINGS + 1];
+
+	/* These are the resources for which amdgpu takes ownership */
+	DECLARE_BITMAP(queue_bitmap, AMDGPU_MAX_COMPUTE_QUEUES);
 };
 
 struct amdgpu_kiq {
 	u64			eop_gpu_addr;
 	struct amdgpu_bo	*eop_obj;
+	struct mutex		ring_mutex;
 	struct amdgpu_ring	ring;
 	struct amdgpu_irq_src	irq;
 };
@@ -983,7 +1028,10 @@ struct amdgpu_gfx_config {
 struct amdgpu_cu_info {
 	uint32_t number; /* total active CU number */
 	uint32_t ao_cu_mask;
+	uint32_t max_waves_per_simd;
 	uint32_t wave_front_size;
+	uint32_t max_scratch_slots_per_cu;
+	uint32_t lds_size;
 	uint32_t bitmap[4][4];
 };
 
@@ -1061,6 +1109,8 @@ struct amdgpu_gfx {
 	uint32_t                        grbm_soft_reset;
 	uint32_t                        srbm_soft_reset;
 	bool                            in_reset;
+	/* s3/s4 mask */
+	bool                            in_suspend;
 	/* NGG */
 	struct amdgpu_ngg		ngg;
 };
@@ -1114,7 +1164,6 @@ struct amdgpu_cs_parser {
 #define AMDGPU_PREAMBLE_IB_PRESENT          (1 << 0) /* bit set means command submit involves a preamble IB */
 #define AMDGPU_PREAMBLE_IB_PRESENT_FIRST    (1 << 1) /* bit set means preamble IB is first presented in belonging context */
 #define AMDGPU_HAVE_CTX_SWITCH              (1 << 2) /* bit set means context switch occured */
-#define AMDGPU_VM_DOMAIN                    (1 << 3) /* bit set means in virtual memory context */
 
 struct amdgpu_job {
 	struct amd_sched_job    base;
@@ -1122,6 +1171,8 @@ 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 */
 	uint32_t		preamble_status;
@@ -1129,7 +1180,6 @@ struct amdgpu_job {
 	void			*owner;
 	uint64_t		fence_ctx; /* the fence_context this job uses */
 	bool                    vm_needs_flush;
-	bool			need_pipeline_sync;
 	unsigned		vm_id;
 	uint64_t		vm_pd_addr;
 	uint32_t		gds_base, gds_size;
@@ -1221,6 +1271,9 @@ struct amdgpu_firmware {
 	const struct amdgpu_psp_funcs *funcs;
 	struct amdgpu_bo *rbuf;
 	struct mutex mutex;
+
+	/* gpu info firmware data pointer */
+	const struct firmware *gpu_info_fw;
 };
 
 /*
@@ -1296,7 +1349,6 @@ struct amdgpu_smumgr {
  */
 struct amdgpu_allowed_register_entry {
 	uint32_t reg_offset;
-	bool untouched;
 	bool grbm_indexed;
 };
 
@@ -1424,6 +1476,7 @@ 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);
 
+#define AMDGPU_RESET_MAGIC_NUM 64
 struct amdgpu_device {
 	struct device			*dev;
 	struct drm_device		*ddev;
@@ -1523,7 +1576,9 @@ struct amdgpu_device {
 	atomic64_t			gtt_usage;
 	atomic64_t			num_bytes_moved;
 	atomic64_t			num_evictions;
+	atomic64_t			num_vram_cpu_page_faults;
 	atomic_t			gpu_reset_counter;
+	atomic_t			vram_lost_counter;
 
 	/* data for buffer migration throttling */
 	struct {
@@ -1570,11 +1625,18 @@ struct amdgpu_device {
 	/* sdma */
 	struct amdgpu_sdma		sdma;
 
-	/* uvd */
-	struct amdgpu_uvd		uvd;
+	union {
+		struct {
+			/* uvd */
+			struct amdgpu_uvd		uvd;
+
+			/* vce */
+			struct amdgpu_vce		vce;
+		};
 
-	/* vce */
-	struct amdgpu_vce		vce;
+		/* vcn */
+		struct amdgpu_vcn		vcn;
+	};
 
 	/* firmwares */
 	struct amdgpu_firmware		firmware;
@@ -1598,6 +1660,9 @@ struct amdgpu_device {
 	/* amdkfd interface */
 	struct kfd_dev          *kfd;
 
+	/* delayed work_func for deferring clockgating during resume */
+	struct delayed_work     late_init_work;
+
 	struct amdgpu_virt	virt;
 
 	/* link all shadow bo */
@@ -1606,9 +1671,13 @@ struct amdgpu_device {
 	/* 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;
 
 	/* record hw reset is performed */
 	bool has_hw_reset;
+	u8				reset_magic[AMDGPU_RESET_MAGIC_NUM];
 
 };
 
@@ -1617,7 +1686,6 @@ static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)
 	return container_of(bdev, struct amdgpu_device, mman.bdev);
 }
 
-bool amdgpu_device_is_px(struct drm_device *dev);
 int amdgpu_device_init(struct amdgpu_device *adev,
 		       struct drm_device *ddev,
 		       struct pci_dev *pdev,
@@ -1733,30 +1801,31 @@ static inline void amdgpu_ring_write_multiple(struct amdgpu_ring *ring, void *sr
 	unsigned occupied, chunk1, chunk2;
 	void *dst;
 
-	if (ring->count_dw < count_dw) {
+	if (unlikely(ring->count_dw < count_dw)) {
 		DRM_ERROR("amdgpu: writing more dwords to the ring than expected!\n");
-	} else {
-		occupied = ring->wptr & ring->buf