Merge tag 'amd-drm-next-5.9-2020-07-17' of git://people.freedesktop.org/~agd5f/linux into drm-next

amd-drm-next-5.9-2020-07-17:

amdgpu:
- SI UVD/VCE clock support
- Updates for Sienna Cichlid
- Expose drm rotation property
- Atomfirmware updates for renoir
- updates to GPUVM hub handling for different register layouts
- swSMU restructuring and cleanups
- RAS fixes
- DC fixes
- mode1 reset support for Sienna Cichlid
- Add support for Navy Flounder GPUs

amdkfd:
- Add SMI events watch interface

UAPI:
- Add amdkfd SMI events watch interface
  Userspace which uses this interface:
  https://github.com/RadeonOpenCompute/rocm_smi_lib/commit/2235ede34c456f1c7d3490f6fe74825d442d272e

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200717132022.4014-1-alexander.deucher@amd.com

69 files changed, 1989 insertions, 489 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 3d2625beacf7..327a0daf4a1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -193,6 +193,7 @@ static const bool debug_evictions; /* = false */
 #endif
 
 extern int amdgpu_tmz;
+extern int amdgpu_reset_method;
 
 #ifdef CONFIG_DRM_AMDGPU_SI
 extern int amdgpu_si_support;
@@ -1010,10 +1011,10 @@ int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev);
 
 void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
 			       uint32_t *buf, size_t size, bool write);
-uint32_t amdgpu_device_rreg(struct amdgpu_device *adev, uint32_t reg,
-			    uint32_t acc_flags);
-void amdgpu_device_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
+uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg,
 			uint32_t acc_flags);
+void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
+		    uint32_t acc_flags);
 void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
 		    uint32_t acc_flags);
 void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value);
@@ -1032,8 +1033,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
  */
 #define AMDGPU_REGS_NO_KIQ    (1<<1)
 
-#define RREG32_NO_KIQ(reg) amdgpu_device_rreg(adev, (reg), AMDGPU_REGS_NO_KIQ)
-#define WREG32_NO_KIQ(reg, v) amdgpu_device_wreg(adev, (reg), (v), AMDGPU_REGS_NO_KIQ)
+#define RREG32_NO_KIQ(reg) amdgpu_mm_rreg(adev, (reg), AMDGPU_REGS_NO_KIQ)
+#define WREG32_NO_KIQ(reg, v) amdgpu_mm_wreg(adev, (reg), (v), AMDGPU_REGS_NO_KIQ)
 
 #define RREG32_KIQ(reg) amdgpu_kiq_rreg(adev, (reg))
 #define WREG32_KIQ(reg, v) amdgpu_kiq_wreg(adev, (reg), (v))
@@ -1041,9 +1042,9 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define RREG8(reg) amdgpu_mm_rreg8(adev, (reg))
 #define WREG8(reg, v) amdgpu_mm_wreg8(adev, (reg), (v))
 
-#define RREG32(reg) amdgpu_device_rreg(adev, (reg), 0)
-#define DREG32(reg) printk(KERN_INFO "REGISTER: " #reg " : 0x%08X\n", amdgpu_device_rreg(adev, (reg), 0))
-#define WREG32(reg, v) amdgpu_device_wreg(adev, (reg), (v), 0)
+#define RREG32(reg) amdgpu_mm_rreg(adev, (reg), 0)
+#define DREG32(reg) printk(KERN_INFO "REGISTER: " #reg " : 0x%08X\n", amdgpu_mm_rreg(adev, (reg), 0))
+#define WREG32(reg, v) amdgpu_mm_wreg(adev, (reg), (v), 0)
 #define REG_SET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK)
 #define REG_GET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK)
 #define RREG32_PCIE(reg) adev->pcie_rreg(adev, (reg))
@@ -1080,7 +1081,16 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 		tmp_ |= ((val) & ~(mask));			\
 		WREG32_PLL(reg, tmp_);				\
 	} while (0)
-#define DREG32_SYS(sqf, adev, reg) seq_printf((sqf), #reg " : 0x%08X\n", amdgpu_device_rreg((adev), (reg), false))
+
+#define WREG32_SMC_P(_Reg, _Val, _Mask)                         \
+	do {                                                    \
+		u32 tmp = RREG32_SMC(_Reg);                     \
+		tmp &= (_Mask);                                 \
+		tmp |= ((_Val) & ~(_Mask));                     \
+		WREG32_SMC(_Reg, tmp);                          \
+	} while (0)
+
+#define DREG32_SYS(sqf, adev, reg) seq_printf((sqf), #reg " : 0x%08X\n", amdgpu_mm_rreg((adev), (reg), false))
 #define RREG32_IO(reg) amdgpu_io_rreg(adev, (reg))
 #define WREG32_IO(reg, v) amdgpu_io_wreg(adev, (reg), (v))
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index ad59ac4423b8..1b865fed74ca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -31,8 +31,6 @@
 #include "amdgpu_xgmi.h"
 #include <uapi/linux/kfd_ioctl.h>
 
-static const unsigned int compute_vmid_bitmap = 0xFF00;
-
 /* Total memory size in system memory and all GPU VRAM. Used to
  * estimate worst case amount of memory to reserve for page tables
  */
@@ -113,7 +111,9 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 
 	if (adev->kfd.dev) {
 		struct kgd2kfd_shared_resources gpu_resources = {
-			.compute_vmid_bitmap = compute_vmid_bitmap,
+			.compute_vmid_bitmap =
+				((1 << AMDGPU_NUM_VMID) - 1) -
+				((1 << adev->vm_manager.first_kfd_vmid) - 1),
 			.num_pipe_per_mec = adev->gfx.mec.num_pipe_per_mec,
 			.num_queue_per_pipe = adev->gfx.mec.num_queue_per_pipe,
 			.gpuvm_size = min(adev->vm_manager.max_pfn
@@ -637,10 +637,8 @@ void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle)
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid)
 {
-	if (adev->kfd.dev) {
-		if ((1 << vmid) & compute_vmid_bitmap)
-			return true;
-	}
+	if (adev->kfd.dev)
+		return vmid >= adev->vm_manager.first_kfd_vmid;
 
 	return false;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index e249b22fef54..1279053324f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -111,6 +111,7 @@ int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev)
 
 union igp_info {
 	struct atom_integrated_system_info_v1_11 v11;
+	struct atom_integrated_system_info_v1_12 v12;
 };
 
 union umc_info {
@@ -214,6 +215,15 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 				if (vram_type)
 					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
 				break;
+			case 12:
+				mem_channel_number = igp_info->v12.umachannelnumber;
+				/* channel width is 64 */
+				if (vram_width)
+					*vram_width = mem_channel_number * 64;
+				mem_type = igp_info->v12.memorytype;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				break;
 			default:
 				return -EINVAL;
 			}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index aeada7c9fbea..a3fa1560de96 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1343,27 +1343,37 @@ static void amdgpu_ib_preempt_job_recovery(struct drm_gpu_scheduler *sched)
 static void amdgpu_ib_preempt_mark_partial_job(struct amdgpu_ring *ring)
 {
 	struct amdgpu_job *job;
-	struct drm_sched_job *s_job;
+	struct drm_sched_job *s_job, *tmp;
 	uint32_t preempt_seq;
 	struct dma_fence *fence, **ptr;
 	struct amdgpu_fence_driver *drv = &ring->fence_drv;
 	struct drm_gpu_scheduler *sched = &ring->sched;
+	bool preempted = true;
 
 	if (ring->funcs->type != AMDGPU_RING_TYPE_GFX)
 		return;
 
 	preempt_seq = le32_to_cpu(*(drv->cpu_addr + 2));
-	if (preempt_seq <= atomic_read(&drv->last_seq))
-		return;
+	if (preempt_seq <= atomic_read(&drv->last_seq)) {
+		preempted = false;
+		goto no_preempt;
+	}
 
 	preempt_seq &= drv->num_fences_mask;
 	ptr = &drv->fences[preempt_seq];
 	fence = rcu_dereference_protected(*ptr, 1);
 
+no_preempt:
 	spin_lock(&sched->job_list_lock);
-	list_for_each_entry(s_job, &sched->ring_mirror_list, node) {
+	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
+		if (dma_fence_is_signaled(&s_job->s_fence->finished)) {
+			/* remove job from ring_mirror_list */
+			list_del_init(&s_job->node);
+			sched->ops->free_job(s_job);
+			continue;
+		}
 		job = to_amdgpu_job(s_job);
-		if (job->fence == fence)
+		if (preempted && job->fence == fence)
 			/* mark the job as preempted */
 			job->preemption_status |= AMDGPU_IB_PREEMPTED;
 	}
@@ -1461,10 +1471,12 @@ static int amdgpu_debugfs_sclk_set(void *data, u64 val)
 	}
 
 	if (is_support_sw_smu(adev)) {
-		ret = smu_get_dpm_freq_range(&adev->smu, SMU_SCLK, &min_freq, &max_freq, true);
+		ret = smu_get_dpm_freq_range(&adev->smu, SMU_SCLK, &min_freq, &max_freq);
 		if (ret || val > max_freq || val < min_freq)
 			return -EINVAL;
-		ret = smu_set_soft_freq_range(&adev->smu, SMU_SCLK, (uint32_t)val, (uint32_t)val, true);
+		ret = smu_set_soft_freq_range(&adev->smu, SMU_SCLK, (uint32_t)val, (uint32_t)val);
+	} else {
+		return 0;
 	}
 
 	pm_runtime_mark_last_busy(adev->ddev->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a649e40fd96f..aa5b54e5a1d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -81,6 +81,7 @@ MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/sienna_cichlid_gpu_info.bin");
+MODULE_FIRMWARE("amdgpu/navy_flounder_gpu_info.bin");
 
 #define AMDGPU_RESUME_MS		2000
 
@@ -114,6 +115,7 @@ const char *amdgpu_asic_name[] = {
 	"NAVI14",
 	"NAVI12",
 	"SIENNA_CICHLID",
+	"NAVY_FLOUNDER",
 	"LAST",
 };
 
@@ -301,10 +303,10 @@ void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
 }
 
 /*
- * device register access helper functions.
+ * MMIO register access helper functions.
  */
 /**
- * amdgpu_device_rreg - read a register
+ * amdgpu_mm_rreg - read a memory mapped IO register
  *
  * @adev: amdgpu_device pointer
  * @reg: dword aligned register offset
@@ -312,8 +314,8 @@ void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
  *
  * Returns the 32 bit value from the offset specified.
  */
-uint32_t amdgpu_device_rreg(struct amdgpu_device *adev, uint32_t reg,
-			    uint32_t acc_flags)
+uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg,
+			uint32_t acc_flags)
 {
 	uint32_t ret;
 
@@ -322,9 +324,15 @@ uint32_t amdgpu_device_rreg(struct amdgpu_device *adev, uint32_t reg,
 
 	if ((reg * 4) < adev->rmmio_size)
 		ret = readl(((void __iomem *)adev->rmmio) + (reg * 4));
-	else
-		ret = adev->pcie_rreg(adev, (reg * 4));
-	trace_amdgpu_device_rreg(adev->pdev->device, reg, ret);
+	else {
+		unsigned long flags;
+
+		spin_lock_irqsave(&adev->mmio_idx_lock, flags);
+		writel((reg * 4), ((void __iomem *)adev->rmmio) + (mmMM_INDEX * 4));
+		ret = readl(((void __iomem *)adev->rmmio) + (mmMM_DATA * 4));
+		spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
+	}
+	trace_amdgpu_mm_rreg(adev->pdev->device, reg, ret);
 	return ret;
 }
 
@@ -370,19 +378,24 @@ void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value)
 		BUG();
 }
 
-void static inline amdgpu_device_wreg_no_kiq(struct amdgpu_device *adev, uint32_t reg,
-					     uint32_t v, uint32_t acc_flags)
+void static inline amdgpu_mm_wreg_mmio(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint32_t acc_flags)
 {
-	trace_amdgpu_device_wreg(adev->pdev->device, reg, v);
+	trace_amdgpu_mm_wreg(adev->pdev->device, reg, v);
 
 	if ((reg * 4) < adev->rmmio_size)
 		writel(v, ((void __iomem *)adev->rmmio) + (reg * 4));
-	else
-		adev->pcie_wreg(adev, (reg * 4), v);
+	else {
+		unsigned long flags;
+
+		spin_lock_irqsave(&adev->mmio_idx_lock, flags);
+		writel((reg * 4), ((void __iomem *)adev->rmmio) + (mmMM_INDEX * 4));
+		writel(v, ((void __iomem *)adev->rmmio) + (mmMM_DATA * 4));
+		spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
+	}
 }
 
 /**
- * amdgpu_device_wreg - write to a register
+ * amdgpu_mm_wreg - write to a memory mapped IO register
  *
  * @adev: amdgpu_device pointer
  * @reg: dword aligned register offset
@@ -391,13 +404,13 @@ void static inline amdgpu_device_wreg_no_kiq(struct amdgpu_device *adev, uint32_
  *
  * Writes the value specified to the offset specified.
  */
-void amdgpu_device_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
-			uint32_t acc_flags)
+void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
+		    uint32_t acc_flags)
 {
 	if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev))
 		return amdgpu_kiq_wreg(adev, reg, v);
 
-	amdgpu_device_wreg_no_kiq(adev, reg, v, acc_flags);
+	amdgpu_mm_wreg_mmio(adev, reg, v, acc_flags);
 }
 
 /*
@@ -416,7 +429,7 @@ void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, uint32_t reg, uint32_t
 			return adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, v);
 	}
 
-	amdgpu_device_wreg_no_kiq(adev, reg, v, acc_flags);
+	amdgpu_mm_wreg_mmio(adev, reg, v, acc_flags);
 }
 
 /**
@@ -1621,6 +1634,9 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 	case CHIP_SIENNA_CICHLID:
 		chip_name = "sienna_cichlid";
 		break;
+	case CHIP_NAVY_FLOUNDER:
+		chip_name = "navy_flounder";
+		break;
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_gpu_info.bin", chip_name);
@@ -1722,6 +1738,12 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 
 	amdgpu_device_enable_virtual_display(adev);
 
+	if (amdgpu_sriov_vf(adev)) {
+		r = amdgpu_virt_request_full_gpu(adev, true);
+		if (r)
+			return r;
+	}
+
 	switch (adev->asic_type) {
 #ifdef CONFIG_DRM_AMDGPU_SI
 	case CHIP_VERDE:
@@ -1788,6 +1810,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	case  CHIP_NAVI14:
 	case  CHIP_NAVI12:
 	case  CHIP_SIENNA_CICHLID:
+	case  CHIP_NAVY_FLOUNDER:
 		adev->family = AMDGPU_FAMILY_NV;
 
 		r = nv_set_ip_blocks(adev);
@@ -1801,31 +1824,6 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 
 	amdgpu_amdkfd_device_probe(adev);
 
-	if (amdgpu_sriov_vf(adev)) {
-		/* handle vbios stuff prior full access mode for new handshake */
-		if (adev->virt.req_init_data_ver == 1) {
-			if (!amdgpu_get_bios(adev)) {
-				DRM_ERROR("failed to get vbios\n");
-				return -EINVAL;
-			}
-
-			r = amdgpu_atombios_init(adev);
-			if (r) {
-				dev_err(adev->dev, "amdgpu_atombios_init failed\n");
-				amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_ATOMBIOS_INIT_FAIL, 0, 0);
-				return r;
-			}
-		}
-	}
-
-	/* we need to send REQ_GPU here for legacy handshaker otherwise the vbios
-	 * will not be prepared by host for this VF */
-	if (amdgpu_sriov_vf(adev) && adev->virt.req_init_data_ver < 1) {
-		r = amdgpu_virt_request_full_gpu(adev, true);
-		if (r)
-			return r;
-	}
-
 	adev->pm.pp_feature = amdgpu_pp_feature_mask;
 	if (amdgpu_sriov_vf(adev) || sched_policy == KFD_SCHED_POLICY_NO_HWS)
 		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
@@ -1857,10 +1855,6 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 			if (r)
 				return r;
 
-			/* skip vbios handling for new handshake */
-			if (amdgpu_sriov_vf(adev) && adev->virt.req_init_data_ver == 1)
-				continue;
-
 			/* Read BIOS */
 			if (!amdgpu_get_bios(adev))
 				return -EINVAL;
@@ -1987,12 +1981,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	if (amdgpu_sriov_vf(adev) && adev->virt.req_init_data_ver > 0) {
-		r = amdgpu_virt_request_full_gpu(adev, true);
-		if (r)
-			return -EAGAIN;
-	}
-
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
@@ -2474,18 +2462,21 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
+
 		/* displays are handled separately */
-		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE) {
-			/* XXX handle errors */
-			r = adev->ip_blocks[i].version->funcs->suspend(adev);
-			/* XXX handle errors */
-			if (r) {
-				DRM_ERROR("suspend of IP block <%s> failed %d\n"