misc: fastrpc: add mmap/unmap support

Support the allocation/deallocation of buffers mapped to the DSP.

When the memory mapped to the DSP at process creation is not enough,
the fastrpc library can extend it at runtime. This avoids having to do
large preallocations by default.

Signed-off-by: Jorge Ramirez-Ortiz <[e-mail]>
Reviewed-by: Srinivas Kandagatla <[e-mail]>
Signed-off-by: Srinivas Kandagatla <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Greg Kroah-Hartman <[e-mail]>

drivers/misc/fastrpc.c

···
 #define FASTRPC_CTXID_MASK (0xFF0)
 #define INIT_FILELEN_MAX (64 * 1024 * 1024)
 #define FASTRPC_DEVICE_NAME	"fastrpc"
+#define ADSP_MMAP_ADD_PAGES 0x1000
 
 /* Retrives number of input buffers from the scalars parameter */
 #define REMOTE_SCALARS_INBUFS(sc)	(((sc) >> 16) & 0x0ff)
···
 /* Remote Method id table */
 #define FASTRPC_RMID_INIT_ATTACH	0
 #define FASTRPC_RMID_INIT_RELEASE	1
+#define FASTRPC_RMID_INIT_MMAP		4
+#define FASTRPC_RMID_INIT_MUNMAP	5
 #define FASTRPC_RMID_INIT_CREATE	6
 #define FASTRPC_RMID_INIT_CREATE_ATTR	7
 #define FASTRPC_RMID_INIT_CREATE_STATIC	8
···
 struct fastrpc_remote_arg {
 	u64 pv;
 	u64 len;
+};
+
+struct fastrpc_mmap_rsp_msg {
+	u64 vaddr;
+};
+
+struct fastrpc_mmap_req_msg {
+	s32 pgid;
+	u32 flags;
+	u64 vaddr;
+	s32 num;
+};
+
+struct fastrpc_munmap_req_msg {
+	s32 pgid;
+	u64 vaddr;
+	u64 size;
 };
 
 struct fastrpc_msg {
···
 	/* Lock for dma buf attachments */
 	struct mutex lock;
 	struct list_head attachments;
+	/* mmap support */
+	struct list_head node; /* list of user requested mmaps */
+	uintptr_t raddr;
 };
 
 struct fastrpc_dma_buf_attachment {
···
 	struct list_head user;
 	struct list_head maps;
 	struct list_head pending;
+	struct list_head mmaps;
 
 	struct fastrpc_channel_ctx *cctx;
 	struct fastrpc_session_ctx *sctx;
···
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&buf->attachments);
+	INIT_LIST_HEAD(&buf->node);
 	mutex_init(&buf->lock);
 
 	buf->fl = fl;
···
 	buf->phys = 0;
 	buf->size = size;
 	buf->dev = dev;
+	buf->raddr = 0;
 
 	buf->virt = dma_alloc_coherent(dev, buf->size, (dma_addr_t *)&buf->phys,
 				       GFP_KERNEL);
···
 	struct fastrpc_channel_ctx *cctx = fl->cctx;
 	struct fastrpc_invoke_ctx *ctx, *n;
 	struct fastrpc_map *map, *m;
+	struct fastrpc_buf *buf, *b;
 	unsigned long flags;
 
 	fastrpc_release_current_dsp_process(fl);
···
 	list_for_each_entry_safe(map, m, &fl->maps, node) {
 		list_del(&map->node);
 		fastrpc_map_put(map);
+	}
+
+	list_for_each_entry_safe(buf, b, &fl->mmaps, node) {
+		list_del(&buf->node);
+		fastrpc_buf_free(buf);
 	}
 
 	fastrpc_session_free(cctx, fl->sctx);
···
 	mutex_init(&fl->mutex);
 	INIT_LIST_HEAD(&fl->pending);
 	INIT_LIST_HEAD(&fl->maps);
+	INIT_LIST_HEAD(&fl->mmaps);
 	INIT_LIST_HEAD(&fl->user);
 	fl->tgid = current->tgid;
 	fl->cctx = cctx;
···
 	return err;
 }
 
+static int fastrpc_req_munmap_impl(struct fastrpc_user *fl,
+				   struct fastrpc_req_munmap *req)
+{
+	struct fastrpc_invoke_args args[1] = { [0] = { 0 } };
+	struct fastrpc_buf *buf, *b;
+	struct fastrpc_munmap_req_msg req_msg;
+	struct device *dev = fl->sctx->dev;
+	int err;
+	u32 sc;
+
+	spin_lock(&fl->lock);
+	list_for_each_entry_safe(buf, b, &fl->mmaps, node) {
+		if ((buf->raddr == req->vaddrout) && (buf->size == req->size))
+			break;
+		buf = NULL;
+	}
+	spin_unlock(&fl->lock);
+
+	if (!buf) {
+		dev_err(dev, "mmap not in list\n");
+		return -EINVAL;
+	}
+
+	req_msg.pgid = fl->tgid;
+	req_msg.size = buf->size;
+	req_msg.vaddr = buf->raddr;
+
+	args[0].ptr = (u64) (uintptr_t) &req_msg;
+	args[0].length = sizeof(req_msg);
+
+	sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_MUNMAP, 1, 0);
+	err = fastrpc_internal_invoke(fl, true, FASTRPC_INIT_HANDLE, sc,
+				      &args[0]);
+	if (!err) {
+		dev_dbg(dev, "unmmap\tpt 0x%09lx OK\n", buf->raddr);
+		spin_lock(&fl->lock);
+		list_del(&buf->node);
+		spin_unlock(&fl->lock);
+		fastrpc_buf_free(buf);
+	} else {
+		dev_err(dev, "unmmap\tpt 0x%09lx ERROR\n", buf->raddr);
+	}
+
+	return err;
+}
+
+static int fastrpc_req_munmap(struct fastrpc_user *fl, char __user *argp)
+{
+	struct fastrpc_req_munmap req;
+
+	if (copy_from_user(&req, argp, sizeof(req)))
+		return -EFAULT;
+
+	return fastrpc_req_munmap_impl(fl, &req);
+}
+
+static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)
+{
+	struct fastrpc_invoke_args args[3] = { [0 ... 2] = { 0 } };
+	struct fastrpc_buf *buf = NULL;
+	struct fastrpc_mmap_req_msg req_msg;
+	struct fastrpc_mmap_rsp_msg rsp_msg;
+	struct fastrpc_req_munmap req_unmap;
+	struct fastrpc_phy_page pages;
+	struct fastrpc_req_mmap req;
+	struct device *dev = fl->sctx->dev;
+	int err;
+	u32 sc;
+
+	if (copy_from_user(&req, argp, sizeof(req)))
+		return -EFAULT;
+
+	if (req.flags != ADSP_MMAP_ADD_PAGES) {
+		dev_err(dev, "flag not supported 0x%x\n", req.flags);
+		return -EINVAL;
+	}
+
+	if (req.vaddrin) {
+		dev_err(dev, "adding user allocated pages is not supported\n");
+		return -EINVAL;
+	}
+
+	err = fastrpc_buf_alloc(fl, fl->sctx->dev, req.size, &buf);
+	if (err) {
+		dev_err(dev, "failed to allocate buffer\n");
+		return err;
+	}
+
+	req_msg.pgid = fl->tgid;
+	req_msg.flags = req.flags;
+	req_msg.vaddr = req.vaddrin;
+	req_msg.num = sizeof(pages);
+
+	args[0].ptr = (u64) (uintptr_t) &req_msg;
+	args[0].length = sizeof(req_msg);
+
+	pages.addr = buf->phys;
+	pages.size = buf->size;
+
+	args[1].ptr = (u64) (uintptr_t) &pages;
+	args[1].length = sizeof(pages);
+
+	args[2].ptr = (u64) (uintptr_t) &rsp_msg;
+	args[2].length = sizeof(rsp_msg);
+
+	sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_MMAP, 2, 1);
+	err = fastrpc_internal_invoke(fl, true, FASTRPC_INIT_HANDLE, sc,
+				      &args[0]);
+	if (err) {
+		dev_err(dev, "mmap error (len 0x%08llx)\n", buf->size);
+		goto err_invoke;
+	}
+
+	/* update the buffer to be able to deallocate the memory on the DSP */
+	buf->raddr = (uintptr_t) rsp_msg.vaddr;
+
+	/* let the client know the address to use */
+	req.vaddrout = rsp_msg.vaddr;
+
+	spin_lock(&fl->lock);
+	list_add_tail(&buf->node, &fl->mmaps);
+	spin_unlock(&fl->lock);
+
+	if (copy_to_user((void __user *)argp, &req, sizeof(req))) {
+		/* unmap the memory and release the buffer */
+		req_unmap.vaddrout = buf->raddr;
+		req_unmap.size = buf->size;
+		fastrpc_req_munmap_impl(fl, &req_unmap);
+		return -EFAULT;
+	}
+
+	dev_dbg(dev, "mmap\t\tpt 0x%09lx OK [len 0x%08llx]\n",
+		buf->raddr, buf->size);
+
+	return 0;
+
+err_invoke:
+	fastrpc_buf_free(buf);
+
+	return err;
+}
+
 static long fastrpc_device_ioctl(struct file *file, unsigned int cmd,
 				 unsigned long arg)
 {
···
 		break;
 	case FASTRPC_IOCTL_ALLOC_DMA_BUFF:
 		err = fastrpc_dmabuf_alloc(fl, argp);
+		break;
+	case FASTRPC_IOCTL_MMAP:
+		err = fastrpc_req_mmap(fl, argp);
+		break;
+	case FASTRPC_IOCTL_MUNMAP:
+		err = fastrpc_req_munmap(fl, argp);
 		break;
 	default:
 		err = -ENOTTY;

include/uapi/misc/fastrpc.h

···
 #define FASTRPC_IOCTL_INVOKE		_IOWR('R', 3, struct fastrpc_invoke)
 #define FASTRPC_IOCTL_INIT_ATTACH	_IO('R', 4)
 #define FASTRPC_IOCTL_INIT_CREATE	_IOWR('R', 5, struct fastrpc_init_create)
+#define FASTRPC_IOCTL_MMAP              _IOWR('R', 6, struct fastrpc_req_mmap)
+#define FASTRPC_IOCTL_MUNMAP            _IOWR('R', 7, struct fastrpc_req_munmap)
 
 struct fastrpc_invoke_args {
 	__u64 ptr;
···
 struct fastrpc_alloc_dma_buf {
 	__s32 fd;	/* fd */
 	__u32 flags;	/* flags to map with */
+	__u64 size;	/* size */
+};
+
+struct fastrpc_req_mmap {
+	__s32 fd;
+	__u32 flags;	/* flags for dsp to map with */
+	__u64 vaddrin;	/* optional virtual address */
+	__u64 size;	/* size */
+	__u64 vaddrout;	/* dsp virtual address */
+};
+
+struct fastrpc_req_munmap {
+	__u64 vaddrout;	/* address to unmap */
 	__u64 size;	/* size */
 };