Merge remote-tracking branch 'airlied/drm-next' into drm-misc-next

Picking up drm-next @ 4.12-rc1 in order to apply Michal Hocko's vmalloc patch set

Signed-off-by: Sean Paul <seanpaul@chromium.org>

1 files changed, 80 insertions, 144 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index edde5fe938d6..139f964196b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
@@ -49,63 +49,6 @@ static void vce_v4_0_mc_resume(struct amdgpu_device *adev);
 static void vce_v4_0_set_ring_funcs(struct amdgpu_device *adev);
 static void vce_v4_0_set_irq_funcs(struct amdgpu_device *adev);
 
-static inline void mmsch_insert_direct_wt(struct mmsch_v1_0_cmd_direct_write *direct_wt,
-					  uint32_t *init_table,
-					  uint32_t reg_offset,
-					  uint32_t value)
-{
-	direct_wt->cmd_header.reg_offset = reg_offset;
-	direct_wt->reg_value = value;
-	memcpy((void *)init_table, direct_wt, sizeof(struct mmsch_v1_0_cmd_direct_write));
-}
-
-static inline void mmsch_insert_direct_rd_mod_wt(struct mmsch_v1_0_cmd_direct_read_modify_write *direct_rd_mod_wt,
-						 uint32_t *init_table,
-						 uint32_t reg_offset,
-						 uint32_t mask, uint32_t data)
-{
-	direct_rd_mod_wt->cmd_header.reg_offset = reg_offset;
-	direct_rd_mod_wt->mask_value = mask;
-	direct_rd_mod_wt->write_data = data;
-	memcpy((void *)init_table, direct_rd_mod_wt,
-	       sizeof(struct mmsch_v1_0_cmd_direct_read_modify_write));
-}
-
-static inline void mmsch_insert_direct_poll(struct mmsch_v1_0_cmd_direct_polling *direct_poll,
-					    uint32_t *init_table,
-					    uint32_t reg_offset,
-					    uint32_t mask, uint32_t wait)
-{
-	direct_poll->cmd_header.reg_offset = reg_offset;
-	direct_poll->mask_value = mask;
-	direct_poll->wait_value = wait;
-	memcpy((void *)init_table, direct_poll, sizeof(struct mmsch_v1_0_cmd_direct_polling));
-}
-
-#define INSERT_DIRECT_RD_MOD_WT(reg, mask, data) { \
-	mmsch_insert_direct_rd_mod_wt(&direct_rd_mod_wt, \
-				      init_table, (reg), \
-				      (mask), (data)); \
-	init_table += sizeof(struct mmsch_v1_0_cmd_direct_read_modify_write)/4; \
-	table_size += sizeof(struct mmsch_v1_0_cmd_direct_read_modify_write)/4; \
-}
-
-#define INSERT_DIRECT_WT(reg, value) { \
-	mmsch_insert_direct_wt(&direct_wt, \
-			       init_table, (reg), \
-			       (value)); \
-	init_table += sizeof(struct mmsch_v1_0_cmd_direct_write)/4; \
-	table_size += sizeof(struct mmsch_v1_0_cmd_direct_write)/4; \
-}
-
-#define INSERT_DIRECT_POLL(reg, mask, wait) { \
-	mmsch_insert_direct_poll(&direct_poll, \
-				 init_table, (reg), \
-				 (mask), (wait)); \
-	init_table += sizeof(struct mmsch_v1_0_cmd_direct_polling)/4; \
-	table_size += sizeof(struct mmsch_v1_0_cmd_direct_polling)/4; \
-}
-
 /**
  * vce_v4_0_ring_get_rptr - get read pointer
  *
@@ -280,60 +223,73 @@ static int vce_v4_0_sriov_start(struct amdgpu_device *adev)
 		init_table += header->vce_table_offset;
 
 		ring = &adev->vce.ring[0];
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_RPTR), ring->wptr);
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR), ring->wptr);
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_BASE_LO), lower_32_bits(ring->gpu_addr));
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_BASE_HI), upper_32_bits(ring->gpu_addr));
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_SIZE), ring->ring_size / 4);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_BASE_LO),
+					    lower_32_bits(ring->gpu_addr));
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_BASE_HI),
+					    upper_32_bits(ring->gpu_addr));
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_SIZE),
+					    ring->ring_size / 4);
 
 		/* BEGING OF MC_RESUME */
-		INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_CLOCK_GATING_A), ~(1 << 16), 0);
-		INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_UENC_CLOCK_GATING), ~0xFF9FF000, 0x1FF000);
-		INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_UENC_REG_CLOCK_GATING), ~0x3F, 0x3F);
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_CLOCK_GATING_B), 0x1FF);
-
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_CTRL), 0x398000);
-		INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_CACHE_CTRL), ~0x1, 0);
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_SWAP_CNTL), 0);
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_SWAP_CNTL1), 0);
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VM_CTRL), 0);
-
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR0), adev->vce.gpu_addr >> 8);
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR1), adev->vce.gpu_addr >> 8);
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR2), adev->vce.gpu_addr >> 8);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_CTRL), 0x398000);
+		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_CACHE_CTRL), ~0x1, 0);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_SWAP_CNTL), 0);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_SWAP_CNTL1), 0);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VM_CTRL), 0);
+
+		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR0),
+						adev->firmware.ucode[AMDGPU_UCODE_ID_VCE].mc_addr >> 8);
+		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR1),
+						adev->firmware.ucode[AMDGPU_UCODE_ID_VCE].mc_addr >> 8);
+		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR2),
+						adev->firmware.ucode[AMDGPU_UCODE_ID_VCE].mc_addr >> 8);
+		} else {
+		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR0),
+						adev->vce.gpu_addr >> 8);
+		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR1),
+						adev->vce.gpu_addr >> 8);
+		    MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VCPU_CACHE_40BIT_BAR2),
+						adev->vce.gpu_addr >> 8);
+		}
 
 		offset = AMDGPU_VCE_FIRMWARE_OFFSET;
 		size = VCE_V4_0_FW_SIZE;
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET0), offset & 0x7FFFFFFF);
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_SIZE0), size);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET0),
+					    offset & 0x7FFFFFFF);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_SIZE0), size);
 
 		offset += size;
 		size = VCE_V4_0_STACK_SIZE;
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET1), offset & 0x7FFFFFFF);
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_SIZE1), size);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET1),
+					    offset & 0x7FFFFFFF);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_SIZE1), size);
 
 		offset += size;
 		size = VCE_V4_0_DATA_SIZE;
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET2), offset & 0x7FFFFFFF);
-		INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_SIZE2), size);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET2),
+					    offset & 0x7FFFFFFF);
+		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_SIZE2), size);
 
-		INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_CTRL2), ~0x100, 0);
-		INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_SYS_INT_EN),
-				0xffffffff, VCE_SYS_INT_EN__VCE_SYS_INT_TRAP_INTERRUPT_EN_MASK);
+		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_CTRL2), ~0x100, 0);
+		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_SYS_INT_EN),
+						   0xffffffff, VCE_SYS_INT_EN__VCE_SYS_INT_TRAP_INTERRUPT_EN_MASK);
 
 		/* end of MC_RESUME */
-		INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CNTL),
-				~0x200001, VCE_VCPU_CNTL__CLK_EN_MASK);
-		INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_SOFT_RESET),
-				~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK, 0);
+		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_STATUS),
+						   VCE_STATUS__JOB_BUSY_MASK, ~VCE_STATUS__JOB_BUSY_MASK);
+		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CNTL),
+						   ~0x200001, VCE_VCPU_CNTL__CLK_EN_MASK);
+		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_SOFT_RESET),
+						   ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK, 0);
 
-		INSERT_DIRECT_POLL(SOC15_REG_OFFSET(VCE, 0, mmVCE_STATUS),
-				VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK,
-				VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK);
+		MMSCH_V1_0_INSERT_DIRECT_POLL(SOC15_REG_OFFSET(VCE, 0, mmVCE_STATUS),
+					      VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK,
+					      VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK);
 
 		/* clear BUSY flag */
-		INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_STATUS),
-				~VCE_STATUS__JOB_BUSY_MASK, 0);
+		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_STATUS),
+						   ~VCE_STATUS__JOB_BUSY_MASK, 0);
 
 		/* add end packet */
 		memcpy((void *)init_table, &end, sizeof(struct mmsch_v1_0_cmd_end));
@@ -494,20 +450,9 @@ static int vce_v4_0_sw_init(void *handle)
 			return r;
 	}
 
-	if (amdgpu_sriov_vf(adev)) {
-		r = amdgpu_bo_create_kernel(adev, PAGE_SIZE, PAGE_SIZE,
-					    AMDGPU_GEM_DOMAIN_VRAM,
-					    &adev->virt.mm_table.bo,
-					    &adev->virt.mm_table.gpu_addr,
-					    (void *)&adev->virt.mm_table.cpu_addr);
-		if (!r) {
-			memset((void *)adev->virt.mm_table.cpu_addr, 0, PAGE_SIZE);
-			printk("mm table gpu addr = 0x%llx, cpu addr = %p. \n",
-			       adev->virt.mm_table.gpu_addr,
-			       adev->virt.mm_table.cpu_addr);
-		}
+	r = amdgpu_virt_alloc_mm_table(adev);
+	if (r)
 		return r;
-	}
 
 	return r;
 }
@@ -518,10 +463,7 @@ static int vce_v4_0_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* free MM table */
-	if (amdgpu_sriov_vf(adev))
-		amdgpu_bo_free_kernel(&adev->virt.mm_table.bo,
-				      &adev->virt.mm_table.gpu_addr,
-				      (void *)&adev->virt.mm_table.cpu_addr);
+	amdgpu_virt_free_mm_table(adev);
 
 	r = amdgpu_vce_suspend(adev);
 	if (r)
@@ -973,44 +915,37 @@ static void vce_v4_0_ring_insert_end(struct amdgpu_ring *ring)
 static void vce_v4_0_emit_vm_flush(struct amdgpu_ring *ring,
 			 unsigned int vm_id, uint64_t pd_addr)
 {
+	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
 	uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vm_id);
-	unsigned eng = ring->idx;
-	unsigned i;
+	unsigned eng = ring->vm_inv_eng;
 
 	pd_addr = pd_addr | 0x1; /* valid bit */
 	/* now only use physical base address of PDE and valid */
 	BUG_ON(pd_addr & 0xFFFF00000000003EULL);
 
-	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
-		struct amdgpu_vmhub *hub = &ring->adev->vmhub[i];
-
-		amdgpu_ring_write(ring, VCE_CMD_REG_WRITE);
-		amdgpu_ring_write(ring,
-			(hub->ctx0_ptb_addr_hi32 + vm_id * 2) << 2);
-		amdgpu_ring_write(ring, upper_32_bits(pd_addr));
-
-		amdgpu_ring_write(ring, VCE_CMD_REG_WRITE);
-		amdgpu_ring_write(ring,
-			(hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
-		amdgpu_ring_write(ring, lower_32_bits(pd_addr));
-
-		amdgpu_ring_write(ring, VCE_CMD_REG_WAIT);
-		amdgpu_ring_write(ring,
-			(hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
-		amdgpu_ring_write(ring, 0xffffffff);
-		amdgpu_ring_write(ring, lower_32_bits(pd_addr));
-
-		/* flush TLB */
-		amdgpu_ring_write(ring, VCE_CMD_REG_WRITE);
-		amdgpu_ring_write(ring,	(hub->vm_inv_eng0_req + eng) << 2);
-		amdgpu_ring_write(ring, req);
-
-		/* wait for flush */
-		amdgpu_ring_write(ring, VCE_CMD_REG_WAIT);
-		amdgpu_ring_write(ring, (hub->vm_inv_eng0_ack + eng) << 2);
-		amdgpu_ring_write(ring, 1 << vm_id);
-		amdgpu_ring_write(ring, 1 << vm_id);
-	}
+	amdgpu_ring_write(ring, VCE_CMD_REG_WRITE);
+	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_hi32 + vm_id * 2) << 2);
+	amdgpu_ring_write(ring, upper_32_bits(pd_addr));
+
+	amdgpu_ring_write(ring, VCE_CMD_REG_WRITE);
+	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
+	amdgpu_ring_write(ring, lower_32_bits(pd_addr));
+
+	amdgpu_ring_write(ring, VCE_CMD_REG_WAIT);
+	amdgpu_ring_write(ring,	(hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
+	amdgpu_ring_write(ring, 0xffffffff);
+	amdgpu_ring_write(ring, lower_32_bits(pd_addr));
+
+	/* flush TLB */
+	amdgpu_ring_write(ring, VCE_CMD_REG_WRITE);
+	amdgpu_ring_write(ring,	(hub->vm_inv_eng0_req + eng) << 2);
+	amdgpu_ring_write(ring, req);
+
+	/* wait for flush */
+	amdgpu_ring_write(ring, VCE_CMD_REG_WAIT);
+	amdgpu_ring_write(ring, (hub->vm_inv_eng0_ack + eng) << 2);
+	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, 1 << vm_id);
 }
 
 static int vce_v4_0_set_interrupt_state(struct amdgpu_device *adev,
@@ -1078,12 +1013,13 @@ static const struct amdgpu_ring_funcs vce_v4_0_ring_vm_funcs = {
 	.align_mask = 0x3f,
 	.nop = VCE_CMD_NO_OP,
 	.support_64bit_ptrs = false,
+	.vmhub = AMDGPU_MMHUB,
 	.get_rptr = vce_v4_0_ring_get_rptr,
 	.get_wptr = vce_v4_0_ring_get_wptr,
 	.set_wptr = vce_v4_0_ring_set_wptr,
 	.parse_cs = amdgpu_vce_ring_parse_cs_vm,
 	.emit_frame_size =
-		17 * AMDGPU_MAX_VMHUBS + /* vce_v4_0_emit_vm_flush */
+		17 + /* vce_v4_0_emit_vm_flush */
 		5 + 5 + /* amdgpu_vce_ring_emit_fence x2 vm fence */
 		1, /* vce_v4_0_ring_insert_end */
 	.emit_ib_size = 5, /* vce_v4_0_ring_emit_ib */