drm/amdkfd: Add CONFIG_HSA_AMD_SVM

Control whether to build SVM support into amdgpu with a Kconfig option.
This makes it easier to disable it in production kernels if this new
feature causes problems in production environments.

Use "depends on" instead of "select" for DEVICE_PRIVATE, as is
recommended for visible options.

Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

5 files changed, 67 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/Kconfig b/drivers/gpu/drm/amd/amdkfd/Kconfig
index fb8d85716599..8cc0a76ddf9f 100644
--- a/drivers/gpu/drm/amd/amdkfd/Kconfig
+++ b/drivers/gpu/drm/amd/amdkfd/Kconfig
@@ -8,9 +8,20 @@ config HSA_AMD
 	depends on DRM_AMDGPU && (X86_64 || ARM64 || PPC64)
 	imply AMD_IOMMU_V2 if X86_64
 	select HMM_MIRROR
-	select ZONE_DEVICE
-	select DEVICE_PRIVATE
 	select MMU_NOTIFIER
 	select DRM_AMDGPU_USERPTR
 	help
 	  Enable this if you want to use HSA features on AMD GPU devices.
+
+config HSA_AMD_SVM
+	bool "Enable HMM-based shared virtual memory manager"
+	depends on HSA_AMD && DEVICE_PRIVATE
+	default y
+	select HMM_MIRROR
+	select MMU_NOTIFIER
+	help
+	  Enable this to use unified memory and managed memory in HIP. This
+	  memory manager supports two modes of operation. One based on
+	  preemptions and one based on page faults. To enable page fault
+	  based memory management on most GFXv9 GPUs, set the module
+	  parameter amdgpu.noretry=0.
diff --git a/drivers/gpu/drm/amd/amdkfd/Makefile b/drivers/gpu/drm/amd/amdkfd/Makefile
index a93301dbc464..c4f3aff11072 100644
--- a/drivers/gpu/drm/amd/amdkfd/Makefile
+++ b/drivers/gpu/drm/amd/amdkfd/Makefile
@@ -54,9 +54,7 @@ AMDKFD_FILES	:= $(AMDKFD_PATH)/kfd_module.o \
 		$(AMDKFD_PATH)/kfd_dbgdev.o \
 		$(AMDKFD_PATH)/kfd_dbgmgr.o \
 		$(AMDKFD_PATH)/kfd_smi_events.o \
-		$(AMDKFD_PATH)/kfd_crat.o \
-		$(AMDKFD_PATH)/kfd_svm.o \
-		$(AMDKFD_PATH)/kfd_migrate.o
+		$(AMDKFD_PATH)/kfd_crat.o
 
 ifneq ($(CONFIG_AMD_IOMMU_V2),)
 AMDKFD_FILES += $(AMDKFD_PATH)/kfd_iommu.o
@@ -65,3 +63,8 @@ endif
 ifneq ($(CONFIG_DEBUG_FS),)
 AMDKFD_FILES += $(AMDKFD_PATH)/kfd_debugfs.o
 endif
+
+ifneq ($(CONFIG_HSA_AMD_SVM),)
+AMDKFD_FILES += $(AMDKFD_PATH)/kfd_svm.o \
+		$(AMDKFD_PATH)/kfd_migrate.o
+endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 913cc29d8857..059c3f1ca27d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1770,6 +1770,7 @@ static int kfd_ioctl_set_xnack_mode(struct file *filep,
 	return r;
 }
 
+#if IS_ENABLED(CONFIG_HSA_AMD_SVM)
 static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data)
 {
 	struct kfd_ioctl_svm_args *args = data;
@@ -1795,6 +1796,12 @@ static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data)
 
 	return r;
 }
+#else
+static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data)
+{
+	return -EPERM;
+}
+#endif
 
 #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \
 	[_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h
index 37ad99cb073d..0de76b5d4973 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h
@@ -25,6 +25,8 @@
 #ifndef KFD_MIGRATE_H_
 #define KFD_MIGRATE_H_
 
+#if IS_ENABLED(CONFIG_HSA_AMD_SVM)
+
 #include <linux/rwsem.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
@@ -44,17 +46,20 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm);
 unsigned long
 svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr);
 
-#if defined(CONFIG_DEVICE_PRIVATE)
 int svm_migrate_init(struct amdgpu_device *adev);
 void svm_migrate_fini(struct amdgpu_device *adev);
 
 #else
+
 static inline int svm_migrate_init(struct amdgpu_device *adev)
 {
-	DRM_WARN_ONCE("DEVICE_PRIVATE kernel config option is not enabled, "
-		      "add CONFIG_DEVICE_PRIVATE=y in config file to fix\n");
-	return -ENODEV;
+	return 0;
+}
+static inline void svm_migrate_fini(struct amdgpu_device *adev)
+{
+	/* empty */
 }
-static inline void svm_migrate_fini(struct amdgpu_device *adev) {}
-#endif
+
+#endif /* IS_ENABLED(CONFIG_HSA_AMD_SVM) */
+
 #endif /* KFD_MIGRATE_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index aa829b3c992d..573f984b81fe 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -25,6 +25,8 @@
 #ifndef KFD_SVM_H_
 #define KFD_SVM_H_
 
+#if IS_ENABLED(CONFIG_HSA_AMD_SVM)
+
 #include <linux/rwsem.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
@@ -173,4 +175,32 @@ void svm_range_dma_unmap(struct device *dev, dma_addr_t *dma_addr,
 void svm_range_free_dma_mappings(struct svm_range *prange);
 void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm);
 
+#else
+
+struct kfd_process;
+
+static inline int svm_range_list_init(struct kfd_process *p)
+{
+	return 0;
+}
+static inline void svm_range_list_fini(struct kfd_process *p)
+{
+	/* empty */
+}
+
+static inline int svm_range_restore_pages(struct amdgpu_device *adev,
+					  unsigned int pasid, uint64_t addr)
+{
+	return -EFAULT;
+}
+
+static inline int svm_range_schedule_evict_svm_bo(
+		struct amdgpu_amdkfd_fence *fence)
+{
+	WARN_ONCE(1, "SVM eviction fence triggered, but SVM is disabled");
+	return -EINVAL;
+}
+
+#endif /* IS_ENABLED(CONFIG_HSA_AMD_SVM) */
+
 #endif /* KFD_SVM_H_ */