drm/amdgpu: save vm fault information for amdkfd

amdgpu save the vm fault related information for KFD usage and keep the
copy until KFD read it.

Signed-off-by: shaoyun liu <shaoyun.liu@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

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

@@ -183,6 +183,9 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
 int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
 					    struct dma_fence **ef);
 
+int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
+					      struct kfd_vm_fault_info *info);
+
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_unreserve_system_memory_limit(struct amdgpu_bo *bo);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c

@@ -216,6 +216,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c

@@ -176,6 +176,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void)

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

@@ -1621,6 +1621,20 @@ bo_reserve_failed:
 	return ret;
 }
 
+int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
+					      struct kfd_vm_fault_info *mem)
+{
+	struct amdgpu_device *adev;
+
+	adev = (struct amdgpu_device *)kgd;
+	if (atomic_read(&adev->gmc.vm_fault_info_updated) == 1) {
+		*mem = *adev->gmc.vm_fault_info;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+	}
+	return 0;
+}
+
 /* Evict a userptr BO by stopping the queues if necessary
  *
  * Runs in MMU notifier, may be in RECLAIM_FS context. This means it

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

@@ -105,6 +105,8 @@ struct amdgpu_gmc {
 	/* protects concurrent invalidation */
 	spinlock_t		invalidate_lock;
 	bool			translate_further;
+	struct kfd_vm_fault_info *vm_fault_info;
+	atomic_t		vm_fault_info_updated;
 
 	const struct amdgpu_gmc_funcs	*gmc_funcs;
 };

drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c

@@ -28,6 +28,7 @@
 #include "cik.h"
 #include "gmc_v7_0.h"
 #include "amdgpu_ucode.h"
+#include "amdgpu_amdkfd.h"
 
 #include "bif/bif_4_1_d.h"
 #include "bif/bif_4_1_sh_mask.h"
@@ -1078,6 +1079,12 @@ static int gmc_v7_0_sw_init(void *handle)
 		adev->vm_manager.vram_base_offset = 0;
 	}
 
+	adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info),
+					GFP_KERNEL);
+	if (!adev->gmc.vm_fault_info)
+		return -ENOMEM;
+	atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+
 	return 0;
 }
 
@@ -1087,6 +1094,7 @@ static int gmc_v7_0_sw_fini(void *handle)
 
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
+	kfree(adev->gmc.vm_fault_info);
 	gmc_v7_0_gart_fini(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->gmc.fw);
@@ -1276,7 +1284,7 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
-	u32 addr, status, mc_client;
+	u32 addr, status, mc_client, vmid;
 
 	addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR);
 	status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
@@ -1301,6 +1309,29 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
 					 entry->pasid);
 	}
 
+	vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+			     VMID);
+	if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid)
+		&& !atomic_read(&adev->gmc.vm_fault_info_updated)) {
+		struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info;
+		u32 protections = REG_GET_FIELD(status,
+					VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					PROTECTIONS);
+
+		info->vmid = vmid;
+		info->mc_id = REG_GET_FIELD(status,
+					    VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					    MEMORY_CLIENT_ID);
+		info->status = status;
+		info->page_addr = addr;
+		info->prot_valid = protections & 0x7 ? true : false;
+		info->prot_read = protections & 0x8 ? true : false;
+		info->prot_write = protections & 0x10 ? true : false;
+		info->prot_exec = protections & 0x20 ? true : false;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 1);
+	}
+
 	return 0;
 }
 

drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c

@@ -26,6 +26,7 @@
 #include "amdgpu.h"
 #include "gmc_v8_0.h"
 #include "amdgpu_ucode.h"
+#include "amdgpu_amdkfd.h"
 
 #include "gmc/gmc_8_1_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
@@ -1182,6 +1183,12 @@ static int gmc_v8_0_sw_init(void *handle)
 		adev->vm_manager.vram_base_offset = 0;
 	}
 
+	adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info),
+					GFP_KERNEL);
+	if (!adev->gmc.vm_fault_info)
+		return -ENOMEM;
+	atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+
 	return 0;
 }
 
@@ -1191,6 +1198,7 @@ static int gmc_v8_0_sw_fini(void *handle)
 
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
+	kfree(adev->gmc.vm_fault_info);
 	gmc_v8_0_gart_fini(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->gmc.fw);
@@ -1426,7 +1434,7 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
-	u32 addr, status, mc_client;
+	u32 addr, status, mc_client, vmid;
 
 	if (amdgpu_sriov_vf(adev)) {
 		dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
@@ -1463,6 +1471,29 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 					 entry->pasid);
 	}
 
+	vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+			     VMID);
+	if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid)
+		&& !atomic_read(&adev->gmc.vm_fault_info_updated)) {
+		struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info;
+		u32 protections = REG_GET_FIELD(status,
+					VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					PROTECTIONS);
+
+		info->vmid = vmid;
+		info->mc_id = REG_GET_FIELD(status,
+					    VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					    MEMORY_CLIENT_ID);
+		info->status = status;
+		info->page_addr = addr;
+		info->prot_valid = protections & 0x7 ? true : false;
+		info->prot_read = protections & 0x8 ? true : false;
+		info->prot_write = protections & 0x10 ? true : false;
+		info->prot_exec = protections & 0x20 ? true : false;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 1);
+	}
+
 	return 0;
 }
 

drivers/gpu/drm/amd/include/kgd_kfd_interface.h

@@ -47,6 +47,17 @@ enum kfd_preempt_type {
 	KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 };
 
+struct kfd_vm_fault_info {
+	uint64_t	page_addr;
+	uint32_t	vmid;
+	uint32_t	mc_id;
+	uint32_t	status;
+	bool		prot_valid;
+	bool		prot_read;
+	bool		prot_write;
+	bool		prot_exec;
+};
+
 struct kfd_cu_info {
 	uint32_t num_shader_engines;
 	uint32_t num_shader_arrays_per_engine;
@@ -259,6 +270,12 @@ struct tile_config {
  * IB to the corresponding ring (ring type). The IB is executed with the
  * specified VMID in a user mode context.
  *
+ * @get_vm_fault_info: Return information about a recent VM fault on
+ * GFXv7 and v8. If multiple VM faults occurred since the last call of
+ * this function, it will return information about the first of those
+ * faults. On GFXv9 VM fault information is fully contained in the IH
+ * packet and this function is not needed.
+ *
  * This structure contains function pointers to services that the kgd driver
  * provides to amdkfd driver.
  *
@@ -374,6 +391,9 @@ struct kfd2kgd_calls {
 	int (*submit_ib)(struct kgd_dev *kgd, enum kgd_engine_type engine,
 			uint32_t vmid, uint64_t gpu_addr,
 			uint32_t *ib_cmd, uint32_t ib_len);
+
+	int (*get_vm_fault_info)(struct kgd_dev *kgd,
+			struct kfd_vm_fault_info *info);
 };
 
 /**