drm/msm: Add VM_BIND ioctl

Add a VM_BIND ioctl for binding/unbinding buffers into a VM.  This is
only supported if userspace has opted in to MSM_PARAM_EN_VM_BIND.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Tested-by: Antonino Maniscalco <antomani103@gmail.com>
Reviewed-by: Antonino Maniscalco <antomani103@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/661524/

drivers/gpu/drm/msm/msm_drv.c

@@ -802,6 +802,7 @@ static const struct drm_ioctl_desc msm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(MSM_SUBMITQUEUE_NEW,   msm_ioctl_submitqueue_new,   DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(MSM_SUBMITQUEUE_CLOSE, msm_ioctl_submitqueue_close, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(MSM_SUBMITQUEUE_QUERY, msm_ioctl_submitqueue_query, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(MSM_VM_BIND,      msm_ioctl_vm_bind,      DRM_RENDER_ALLOW),
 };
 
 static void msm_show_fdinfo(struct drm_printer *p, struct drm_file *file)

drivers/gpu/drm/msm/msm_drv.h

@@ -255,7 +255,9 @@ struct drm_gpuvm *msm_kms_init_vm(struct drm_device *dev);
 bool msm_use_mmu(struct drm_device *dev);
 
 int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
-		struct drm_file *file);
+			 struct drm_file *file);
+int msm_ioctl_vm_bind(struct drm_device *dev, void *data,
+		      struct drm_file *file);
 
 #ifdef CONFIG_DEBUG_FS
 unsigned long msm_gem_shrinker_shrink(struct drm_device *dev, unsigned long nr_to_scan);

drivers/gpu/drm/msm/msm_gem.c

@@ -251,8 +251,7 @@ static void put_pages(struct drm_gem_object *obj)
 	}
 }
 
-static struct page **msm_gem_get_pages_locked(struct drm_gem_object *obj,
+struct page **msm_gem_get_pages_locked(struct drm_gem_object *obj, unsigned madv)
-					      unsigned madv)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
@@ -1052,18 +1051,37 @@ static void msm_gem_free_object(struct drm_gem_object *obj)
 	/*
 	 * We need to lock any VMs the object is still attached to, but not
 	 * the object itself (see explaination in msm_gem_assert_locked()),
-	 * so just open-code this special case:
+	 * so just open-code this special case.
+	 *
+	 * Note that we skip the dance if we aren't attached to any VM.  This
+	 * is load bearing.  The driver needs to support two usage models:
+	 *
+	 * 1. Legacy kernel managed VM: Userspace expects the VMA's to be
+	 *    implicitly torn down when the object is freed, the VMA's do
+	 *    not hold a hard reference to the BO.
+	 *
+	 * 2. VM_BIND, userspace managed VM: The VMA holds a reference to the
+	 *    BO.  This can be dropped when the VM is closed and it's associated
+	 *    VMAs are torn down.  (See msm_gem_vm_close()).
+	 *
+	 * In the latter case the last reference to a BO can be dropped while
+	 * we already have the VM locked.  It would have already been removed
+	 * from the gpuva list, but lockdep doesn't know that.  Or understand
+	 * the differences between the two usage models.
 	 */
-	drm_exec_init(&exec, 0, 0);
+	if (!list_empty(&obj->gpuva.list)) {
-	drm_exec_until_all_locked (&exec) {
+		drm_exec_init(&exec, 0, 0);
-		struct drm_gpuvm_bo *vm_bo;
+		drm_exec_until_all_locked (&exec) {
-		drm_gem_for_each_gpuvm_bo (vm_bo, obj) {
+			struct drm_gpuvm_bo *vm_bo;
-			drm_exec_lock_obj(&exec, drm_gpuvm_resv_obj(vm_bo->vm));
+			drm_gem_for_each_gpuvm_bo (vm_bo, obj) {
-			drm_exec_retry_on_contention(&exec);
+				drm_exec_lock_obj(&exec,
+						  drm_gpuvm_resv_obj(vm_bo->vm));
+				drm_exec_retry_on_contention(&exec);
+			}
 		}
+		put_iova_spaces(obj, NULL, true);
+		drm_exec_fini(&exec);     /* drop locks */
 	}
-	put_iova_spaces(obj, NULL, true);
-	drm_exec_fini(&exec);     /* drop locks */
 
 	if (drm_gem_is_imported(obj)) {
 		GEM_WARN_ON(msm_obj->vaddr);

drivers/gpu/drm/msm/msm_gem.h

@@ -73,6 +73,9 @@ struct msm_gem_vm {
 	/** @mmu: The mmu object which manages the pgtables */
 	struct msm_mmu *mmu;
 
+	/** @mmu_lock: Protects access to the mmu */
+	struct mutex mmu_lock;
+
 	/**
 	 * @pid: For address spaces associated with a specific process, this
 	 * will be non-NULL:
@@ -205,6 +208,7 @@ int msm_gem_get_and_pin_iova(struct drm_gem_object *obj, struct drm_gpuvm *vm,
 			     uint64_t *iova);
 void msm_gem_unpin_iova(struct drm_gem_object *obj, struct drm_gpuvm *vm);
 void msm_gem_pin_obj_locked(struct drm_gem_object *obj);
+struct page **msm_gem_get_pages_locked(struct drm_gem_object *obj, unsigned madv);
 struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj);
 void msm_gem_unpin_pages_locked(struct drm_gem_object *obj);
 int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev,

drivers/gpu/drm/msm/msm_gem_submit.c

@@ -194,6 +194,7 @@ out:
 static int submit_lookup_cmds(struct msm_gem_submit *submit,
 		struct drm_msm_gem_submit *args, struct drm_file *file)
 {
+	struct msm_context *ctx = file->driver_priv;
 	unsigned i;
 	size_t sz;
 	int ret = 0;
@@ -225,6 +226,20 @@ static int submit_lookup_cmds(struct msm_gem_submit *submit,
 			goto out;
 		}
 
+		if (msm_context_is_vmbind(ctx)) {
+			if (submit_cmd.nr_relocs) {
+				ret = SUBMIT_ERROR(EINVAL, submit, "nr_relocs must be zero");
+				goto out;
+			}
+
+			if (submit_cmd.submit_idx || submit_cmd.submit_offset) {
+				ret = SUBMIT_ERROR(EINVAL, submit, "submit_idx/offset must be zero");
+				goto out;
+			}
+
+			submit->cmd[i].iova = submit_cmd.iova;
+		}
+
 		submit->cmd[i].type = submit_cmd.type;
 		submit->cmd[i].size = submit_cmd.size / 4;
 		submit->cmd[i].offset = submit_cmd.submit_offset / 4;
@@ -537,6 +552,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	struct msm_syncobj_post_dep *post_deps = NULL;
 	struct drm_syncobj **syncobjs_to_reset = NULL;
 	struct sync_file *sync_file = NULL;
+	unsigned cmds_to_parse;
 	int out_fence_fd = -1;
 	unsigned i;
 	int ret;
@@ -661,7 +677,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	if (ret)
 		goto out;
 
-	for (i = 0; i < args->nr_cmds; i++) {
+	cmds_to_parse = msm_context_is_vmbind(ctx) ? 0 : args->nr_cmds;
+
+	for (i = 0; i < cmds_to_parse; i++) {
 		struct drm_gem_object *obj;
 		uint64_t iova;
 
@@ -692,7 +710,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 			goto out;
 	}
 
-	submit->nr_cmds = i;
+	submit->nr_cmds = args->nr_cmds;
 
 	idr_preload(GFP_KERNEL);
 

include/uapi/drm/msm_drm.h

@@ -272,7 +272,10 @@ struct drm_msm_gem_submit_cmd {
 	__u32 size;           /* in, cmdstream size */
 	__u32 pad;
 	__u32 nr_relocs;      /* in, number of submit_reloc's */
-	__u64 relocs;         /* in, ptr to array of submit_reloc's */
+	union {
+		__u64 relocs; /* in, ptr to array of submit_reloc's */
+		__u64 iova;   /* cmdstream address (for VM_BIND contexts) */
+	};
 };
 
 /* Each buffer referenced elsewhere in the cmdstream submit (ie. the
@@ -339,7 +342,74 @@ struct drm_msm_gem_submit {
 	__u32 nr_out_syncobjs; /* in, number of entries in out_syncobj. */
 	__u32 syncobj_stride; /* in, stride of syncobj arrays. */
 	__u32 pad;            /*in, reserved for future use, always 0. */
+};
 
+#define MSM_VM_BIND_OP_UNMAP	0
+#define MSM_VM_BIND_OP_MAP	1
+#define MSM_VM_BIND_OP_MAP_NULL	2
+
+#define MSM_VM_BIND_OP_DUMP	1
+#define MSM_VM_BIND_OP_FLAGS ( \
+		MSM_VM_BIND_OP_DUMP | \
+		0)
+
+/**
+ * struct drm_msm_vm_bind_op - bind/unbind op to run
+ */
+struct drm_msm_vm_bind_op {
+	/** @op: one of MSM_VM_BIND_OP_x */
+	__u32 op;
+	/** @handle: GEM object handle, MBZ for UNMAP or MAP_NULL */
+	__u32 handle;
+	/** @obj_offset: Offset into GEM object, MBZ for UNMAP or MAP_NULL */
+	__u64 obj_offset;
+	/** @iova: Address to operate on */
+	__u64 iova;
+	/** @range: Number of bites to to map/unmap */
+	__u64 range;
+	/** @flags: Bitmask of MSM_VM_BIND_OP_FLAG_x */
+	__u32 flags;
+	/** @pad: MBZ */
+	__u32 pad;
+};
+
+#define MSM_VM_BIND_FENCE_FD_IN		0x00000001
+#define MSM_VM_BIND_FENCE_FD_OUT	0x00000002
+#define MSM_VM_BIND_FLAGS ( \
+		MSM_VM_BIND_FENCE_FD_IN | \
+		MSM_VM_BIND_FENCE_FD_OUT | \
+		0)
+
+/**
+ * struct drm_msm_vm_bind - Input of &DRM_IOCTL_MSM_VM_BIND
+ */
+struct drm_msm_vm_bind {
+	/** @flags: in, bitmask of MSM_VM_BIND_x */
+	__u32 flags;
+	/** @nr_ops: the number of bind ops in this ioctl */
+	__u32 nr_ops;
+	/** @fence_fd: in/out fence fd (see MSM_VM_BIND_FENCE_FD_IN/OUT) */
+	__s32 fence_fd;
+	/** @queue_id: in, submitqueue id */
+	__u32 queue_id;
+	/** @in_syncobjs: in, ptr to array of drm_msm_gem_syncobj */
+	__u64 in_syncobjs;
+	/** @out_syncobjs: in, ptr to array of drm_msm_gem_syncobj */
+	__u64 out_syncobjs;
+	/** @nr_in_syncobjs: in, number of entries in in_syncobj */
+	__u32 nr_in_syncobjs;
+	/** @nr_out_syncobjs: in, number of entries in out_syncobj */
+	__u32 nr_out_syncobjs;
+	/** @syncobj_stride: in, stride of syncobj arrays */
+	__u32 syncobj_stride;
+	/** @op_stride: sizeof each struct drm_msm_vm_bind_op in @ops */
+	__u32 op_stride;
+	union {
+		/** @op: used if num_ops == 1 */
+		struct drm_msm_vm_bind_op op;
+		/** @ops: userptr to array of drm_msm_vm_bind_op if num_ops > 1 */
+		__u64 ops;
+	};
 };
 
 #define MSM_WAIT_FENCE_BOOST	0x00000001
@@ -435,6 +505,7 @@ struct drm_msm_submitqueue_query {
 #define DRM_MSM_SUBMITQUEUE_NEW        0x0A
 #define DRM_MSM_SUBMITQUEUE_CLOSE      0x0B
 #define DRM_MSM_SUBMITQUEUE_QUERY      0x0C
+#define DRM_MSM_VM_BIND                0x0D
 
 #define DRM_IOCTL_MSM_GET_PARAM        DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GET_PARAM, struct drm_msm_param)
 #define DRM_IOCTL_MSM_SET_PARAM        DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SET_PARAM, struct drm_msm_param)
@@ -448,6 +519,7 @@ struct drm_msm_submitqueue_query {
 #define DRM_IOCTL_MSM_SUBMITQUEUE_NEW    DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_NEW, struct drm_msm_submitqueue)
 #define DRM_IOCTL_MSM_SUBMITQUEUE_CLOSE  DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_CLOSE, __u32)
 #define DRM_IOCTL_MSM_SUBMITQUEUE_QUERY  DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_QUERY, struct drm_msm_submitqueue_query)
+#define DRM_IOCTL_MSM_VM_BIND          DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_VM_BIND, struct drm_msm_vm_bind)
 
 #if defined(__cplusplus)
 }