drm/nouveau/svm: new ioctl to migrate process memory to GPU memory

This add an ioctl to migrate a range of process address space to the
device memory. On platform without cache coherent bus (x86, ARM, ...)
this means that CPU can not access that range directly, instead CPU
will fault which will migrate the memory back to system memory.

This is behind a staging flag so that we can evolve the API.

Signed-off-by: Jérôme Glisse <jglisse@redhat.com>

drivers/gpu/drm/nouveau/nouveau_drm.c

@@ -1043,6 +1043,7 @@ nouveau_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(NOUVEAU_NOTIFIEROBJ_ALLOC, nouveau_abi16_ioctl_notifierobj_alloc, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(NOUVEAU_GPUOBJ_FREE, nouveau_abi16_ioctl_gpuobj_free, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(NOUVEAU_SVM_INIT, nouveau_svmm_init, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_SVM_BIND, nouveau_svmm_bind, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_NEW, nouveau_gem_ioctl_new, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_PUSHBUF, nouveau_gem_ioctl_pushbuf, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_PREP, nouveau_gem_ioctl_cpu_prep, DRM_AUTH|DRM_RENDER_ALLOW),

drivers/gpu/drm/nouveau/nouveau_svm.c

@@ -22,6 +22,7 @@
 #include "nouveau_svm.h"
 #include "nouveau_drv.h"
 #include "nouveau_chan.h"
+#include "nouveau_dmem.h"
 
 #include <nvif/notify.h>
 #include <nvif/object.h>
@@ -104,6 +105,101 @@ struct nouveau_svmm {
 #define SVMM_ERR(s,f,a...)                                                     \
 	NV_WARN((s)->vmm->cli->drm, "svm-%p: "f"\n", (s), ##a)
 
+int
+nouveau_svmm_bind(struct drm_device *dev, void *data,
+		  struct drm_file *file_priv)
+{
+	struct nouveau_cli *cli = nouveau_cli(file_priv);
+	struct drm_nouveau_svm_bind *args = data;
+	unsigned target, cmd, priority;
+	unsigned long addr, end, size;
+	struct mm_struct *mm;
+
+	args->va_start &= PAGE_MASK;
+	args->va_end &= PAGE_MASK;
+
+	/* Sanity check arguments */
+	if (args->reserved0 || args->reserved1)
+		return -EINVAL;
+	if (args->header & (~NOUVEAU_SVM_BIND_VALID_MASK))
+		return -EINVAL;
+	if (args->va_start >= args->va_end)
+		return -EINVAL;
+	if (!args->npages)
+		return -EINVAL;
+
+	cmd = args->header >> NOUVEAU_SVM_BIND_COMMAND_SHIFT;
+	cmd &= NOUVEAU_SVM_BIND_COMMAND_MASK;
+	switch (cmd) {
+	case NOUVEAU_SVM_BIND_COMMAND__MIGRATE:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	priority = args->header >> NOUVEAU_SVM_BIND_PRIORITY_SHIFT;
+	priority &= NOUVEAU_SVM_BIND_PRIORITY_MASK;
+
+	/* FIXME support CPU target ie all target value < GPU_VRAM */
+	target = args->header >> NOUVEAU_SVM_BIND_TARGET_SHIFT;
+	target &= NOUVEAU_SVM_BIND_TARGET_MASK;
+	switch (target) {
+	case NOUVEAU_SVM_BIND_TARGET__GPU_VRAM:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/*
+	 * FIXME: For now refuse non 0 stride, we need to change the migrate
+	 * kernel function to handle stride to avoid to create a mess within
+	 * each device driver.
+	 */
+	if (args->stride)
+		return -EINVAL;
+
+	size = ((unsigned long)args->npages) << PAGE_SHIFT;
+	if ((args->va_start + size) <= args->va_start)
+		return -EINVAL;
+	if ((args->va_start + size) > args->va_end)
+		return -EINVAL;
+
+	/*
+	 * Ok we are ask to do something sane, for now we only support migrate
+	 * commands but we will add things like memory policy (what to do on
+	 * page fault) and maybe some other commands.
+	 */
+
+	mm = get_task_mm(current);
+	down_read(&mm->mmap_sem);
+
+	for (addr = args->va_start, end = args->va_start + size; addr < end;) {
+		struct vm_area_struct *vma;
+		unsigned long next;
+
+		vma = find_vma_intersection(mm, addr, end);
+		if (!vma)
+			break;
+
+		next = min(vma->vm_end, end);
+		/* This is a best effort so we ignore errors */
+		nouveau_dmem_migrate_vma(cli->drm, vma, addr, next);
+		addr = next;
+	}
+
+	/*
+	 * FIXME Return the number of page we have migrated, again we need to
+	 * update the migrate API to return that information so that we can
+	 * report it to user space.
+	 */
+	args->result = 0;
+
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+
+	return 0;
+}
+
 /* Unlink channel instance from SVMM. */
 void
 nouveau_svmm_part(struct nouveau_svmm *svmm, u64 inst)

drivers/gpu/drm/nouveau/nouveau_svm.h

@@ -17,6 +17,7 @@ int nouveau_svmm_init(struct drm_device *, void *, struct drm_file *);
 void nouveau_svmm_fini(struct nouveau_svmm **);
 int nouveau_svmm_join(struct nouveau_svmm *, u64 inst);
 void nouveau_svmm_part(struct nouveau_svmm *, u64 inst);
+int nouveau_svmm_bind(struct drm_device *, void *, struct drm_file *);
 #else /* IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM) */
 static inline void nouveau_svm_init(struct nouveau_drm *drm) {}
 static inline void nouveau_svm_fini(struct nouveau_drm *drm) {}
@@ -37,5 +38,11 @@ static inline int nouveau_svmm_join(struct nouveau_svmm *svmm, u64 inst)
 }
 
 static inline void nouveau_svmm_part(struct nouveau_svmm *svmm, u64 inst) {}
+
+static inline int nouveau_svmm_bind(struct drm_device *device, void *p,
+				    struct drm_file *file)
+{
+	return -ENOSYS;
+}
 #endif /* IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM) */
 #endif

include/uapi/drm/nouveau_drm.h

@@ -134,6 +134,7 @@ struct drm_nouveau_gem_cpu_fini {
 #define DRM_NOUVEAU_GPUOBJ_FREE        0x06 /* deprecated */
 #define DRM_NOUVEAU_NVIF               0x07
 #define DRM_NOUVEAU_SVM_INIT           0x08
+#define DRM_NOUVEAU_SVM_BIND           0x09
 #define DRM_NOUVEAU_GEM_NEW            0x40
 #define DRM_NOUVEAU_GEM_PUSHBUF        0x41
 #define DRM_NOUVEAU_GEM_CPU_PREP       0x42
@@ -145,7 +146,49 @@ struct drm_nouveau_svm_init {
 	__u64 unmanaged_size;
 };
 
+struct drm_nouveau_svm_bind {
+	__u64 header;
+	__u64 va_start;
+	__u64 va_end;
+	__u64 npages;
+	__u64 stride;
+	__u64 result;
+	__u64 reserved0;
+	__u64 reserved1;
+};
+
+#define NOUVEAU_SVM_BIND_COMMAND_SHIFT          0
+#define NOUVEAU_SVM_BIND_COMMAND_BITS           8
+#define NOUVEAU_SVM_BIND_COMMAND_MASK           ((1 << 8) - 1)
+#define NOUVEAU_SVM_BIND_PRIORITY_SHIFT         8
+#define NOUVEAU_SVM_BIND_PRIORITY_BITS          8
+#define NOUVEAU_SVM_BIND_PRIORITY_MASK          ((1 << 8) - 1)
+#define NOUVEAU_SVM_BIND_TARGET_SHIFT           16
+#define NOUVEAU_SVM_BIND_TARGET_BITS            32
+#define NOUVEAU_SVM_BIND_TARGET_MASK            0xffffffff
+
+/*
+ * Below is use to validate ioctl argument, userspace can also use it to make
+ * sure that no bit are set beyond known fields for a given kernel version.
+ */
+#define NOUVEAU_SVM_BIND_VALID_BITS     48
+#define NOUVEAU_SVM_BIND_VALID_MASK     ((1ULL << NOUVEAU_SVM_BIND_VALID_BITS) - 1)
+
+
+/*
+ * NOUVEAU_BIND_COMMAND__MIGRATE: synchronous migrate to target memory.
+ * result: number of page successfuly migrate to the target memory.
+ */
+#define NOUVEAU_SVM_BIND_COMMAND__MIGRATE               0
+
+/*
+ * NOUVEAU_SVM_BIND_HEADER_TARGET__GPU_VRAM: target the GPU VRAM memory.
+ */
+#define NOUVEAU_SVM_BIND_TARGET__GPU_VRAM               (1UL << 31)
+
+
 #define DRM_IOCTL_NOUVEAU_SVM_INIT           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_SVM_INIT, struct drm_nouveau_svm_init)
+#define DRM_IOCTL_NOUVEAU_SVM_BIND           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_SVM_BIND, struct drm_nouveau_svm_bind)
 
 #define DRM_IOCTL_NOUVEAU_GEM_NEW            DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_NEW, struct drm_nouveau_gem_new)
 #define DRM_IOCTL_NOUVEAU_GEM_PUSHBUF        DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_PUSHBUF, struct drm_nouveau_gem_pushbuf)