NVMe: Change the definition of nvme_user_io

The read and write commands don't define a 'result', so there's no need
to copy it back to userspace.

Remove the ability of the ioctl to submit commands to a different
namespace; it's just asking for trouble, and the use case I have in mind
will be addressed througha  different ioctl in the future.  That removes
the need for both the block_shift and nsid arguments.

Check that the opcode is one of 'read' or 'write'.  Future opcodes may
be added in the future, but we will need a different structure definition
for them.

The nblocks field is redefined to be 0-based.  This allows the user to
request the full 65536 blocks.

Don't byteswap the reftag, apptag and appmask.  Martin Petersen tells
me these are calculated in big-endian and are transmitted to the device
in big-endian.
Signed-off-by: NMatthew Wilcox <matthew.r.wilcox@intel.com>

drivers/block/nvme.c

@@ -1035,29 +1035,37 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	struct nvme_user_io io;
 	struct nvme_command c;
 	unsigned length;
-	u32 result;
 	int nents, status;
 	struct scatterlist *sg;
 	struct nvme_prps *prps;
 
 	if (copy_from_user(&io, uio, sizeof(io)))
 		return -EFAULT;
-	length = io.nblocks << io.block_shift;
-	nents = nvme_map_user_pages(dev, io.opcode & 1, io.addr, length, &sg);
+	length = (io.nblocks + 1) << ns->lba_shift;
+
+	switch (io.opcode) {
+	case nvme_cmd_write:
+	case nvme_cmd_read:
+		nents = nvme_map_user_pages(dev, io.opcode & 1, io.addr,
+								length, &sg);
+	default:
+		return -EFAULT;
+	}
+
 	if (nents < 0)
 		return nents;
 
 	memset(&c, 0, sizeof(c));
 	c.rw.opcode = io.opcode;
 	c.rw.flags = io.flags;
-	c.rw.nsid = cpu_to_le32(io.nsid);
+	c.rw.nsid = cpu_to_le32(ns->ns_id);
 	c.rw.slba = cpu_to_le64(io.slba);
-	c.rw.length = cpu_to_le16(io.nblocks - 1);
+	c.rw.length = cpu_to_le16(io.nblocks);
 	c.rw.control = cpu_to_le16(io.control);
 	c.rw.dsmgmt = cpu_to_le16(io.dsmgmt);
-	c.rw.reftag = cpu_to_le32(io.reftag);	/* XXX: endian? */
-	c.rw.apptag = cpu_to_le16(io.apptag);
-	c.rw.appmask = cpu_to_le16(io.appmask);
+	c.rw.reftag = io.reftag;
+	c.rw.apptag = io.apptag;
+	c.rw.appmask = io.appmask;
 	/* XXX: metadata */
 	prps = nvme_setup_prps(dev, &c.common, sg, length);
 
@@ -1069,11 +1077,10 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	 * additional races since q_lock already protects against other CPUs.
 	 */
 	put_nvmeq(nvmeq);
-	status = nvme_submit_sync_cmd(nvmeq, &c, &result, IO_TIMEOUT);
+	status = nvme_submit_sync_cmd(nvmeq, &c, NULL, IO_TIMEOUT);
 
 	nvme_unmap_user_pages(dev, io.opcode & 1, io.addr, length, sg, nents);
 	nvme_free_prps(dev, prps);
-	put_user(result, &uio->result);
 	return status;
 }
 

include/linux/nvme.h

@@ -373,17 +373,15 @@ struct nvme_user_io {
 	__u8	opcode;
 	__u8	flags;
 	__u16	control;
-	__u32	nsid;
+	__u16	nblocks;
+	__u16	rsvd;
 	__u64	metadata;
 	__u64	addr;
 	__u64	slba;
-	__u16	nblocks;
-	__u16	block_shift;
 	__u32	dsmgmt;
 	__u32	reftag;
 	__u16	apptag;
 	__u16	appmask;
-	__u32	result;
 };
 
 struct nvme_dlfw {
@@ -395,7 +393,7 @@ struct nvme_dlfw {
 #define NVME_IOCTL_IDENTIFY_NS	_IOW('N', 0x40, struct nvme_id_ns)
 #define NVME_IOCTL_IDENTIFY_CTRL _IOW('N', 0x41, struct nvme_id_ctrl)
 #define NVME_IOCTL_GET_RANGE_TYPE _IOW('N', 0x42, struct nvme_lba_range_type)
-#define NVME_IOCTL_SUBMIT_IO	_IOWR('N', 0x43, struct nvme_user_io)
+#define NVME_IOCTL_SUBMIT_IO	_IOW('N', 0x43, struct nvme_user_io)
 #define NVME_IOCTL_DOWNLOAD_FW	_IOW('N', 0x44, struct nvme_dlfw)
 #define NVME_IOCTL_ACTIVATE_FW	_IO('N', 0x45)