[PATCH v2 5/5] loop: Add LOOP_SET_FD_AND_STATUS ioctl

[Martijn Coenen]

This allows userspace to completely setup a loop device with a single
ioctl, removing the in-between state where the device can be partially
configured - eg the loop device has a backing file associated with it,
but is reading from the wrong offset.

Besides removing the intermediate state, another big benefit of this
ioctl is that LOOP_SET_STATUS can be slow; the main reason for this
slowness is that LOOP_SET_STATUS(64) calls blk_mq_freeze_queue() to
freeze the associated queue; this requires waiting for RCU
synchronization, which I've measured can take about 15-20ms on this
device on average.

Here's setting up ~70 regular loop devices with an offset on an x86
Android device, using LOOP_SET_FD and LOOP_SET_STATUS:

vsoc_x86:/system/apex # time for i in `seq 30 100`;
do losetup -r -o 4096 /dev/block/loop$i com.android.adbd.apex; done
    0m03.40s real     0m00.02s user     0m00.03s system

Here's configuring ~70 devices in the same way, but using a modified
losetup that uses the new LOOP_SET_FD_AND_STATUS ioctl:

vsoc_x86:/system/apex # time for i in `seq 30 100`;
do losetup -r -o 4096 /dev/block/loop$i com.android.adbd.apex; done
    0m01.94s real     0m00.01s user     0m00.01s system

Signed-off-by: Martijn Coenen <maco@xxxxxxxxxxx>
---
 drivers/block/loop.c      | 45 ++++++++++++++++++++++++++++-----------
 include/uapi/linux/loop.h |  7 ++++++
 2 files changed, 40 insertions(+), 12 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index b10f1d5306a2..4df1f03de27e 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1074,8 +1074,9 @@ loop_set_status_from_info(struct loop_device *lo,
 	return 0;
 }
 
-static int loop_set_fd(struct loop_device *lo, fmode_t mode,
-		       struct block_device *bdev, unsigned int arg)
+static int loop_set_fd_and_status(struct loop_device *lo, fmode_t mode,
+				  struct block_device *bdev, unsigned int fd,
+				  const struct loop_info64 *info)
 {
 	struct file	*file;
 	struct inode	*inode;
@@ -1090,7 +1091,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	__module_get(THIS_MODULE);
 
 	error = -EBADF;
-	file = fget(arg);
+	file = fget(fd);
 	if (!file)
 		goto out;
 
@@ -1099,7 +1100,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	 * here to avoid changing device under exclusive owner.
 	 */
 	if (!(mode & FMODE_EXCL)) {
-		claimed_bdev = bd_start_claiming(bdev, loop_set_fd);
+		claimed_bdev = bd_start_claiming(bdev, loop_set_fd_and_status);
 		if (IS_ERR(claimed_bdev)) {
 			error = PTR_ERR(claimed_bdev);
 			goto out_putf;
@@ -1126,9 +1127,14 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 		lo_flags |= LO_FLAGS_READ_ONLY;
 
 	error = -EFBIG;
-	size = get_loop_size(lo, file);
+	size = get_size(info->lo_offset, info->lo_sizelimit, file);
 	if ((loff_t)(sector_t)size != size)
 		goto out_unlock;
+
+	error = loop_set_status_from_info(lo, info);
+	if (error)
+		goto out_unlock;
+
 	error = loop_prepare_queue(lo);
 	if (error)
 		goto out_unlock;
@@ -1141,9 +1147,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->lo_device = bdev;
 	lo->lo_flags = lo_flags;
 	lo->lo_backing_file = file;
-	lo->transfer = NULL;
-	lo->ioctl = NULL;
-	lo->lo_sizelimit = 0;
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
@@ -1181,14 +1184,14 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	if (partscan)
 		loop_reread_partitions(lo, bdev);
 	if (claimed_bdev)
-		bd_abort_claiming(bdev, claimed_bdev, loop_set_fd);
+		bd_abort_claiming(bdev, claimed_bdev, loop_set_fd_and_status);
 	return 0;
 
 out_unlock:
 	mutex_unlock(&loop_ctl_mutex);
 out_bdev:
 	if (claimed_bdev)
-		bd_abort_claiming(bdev, claimed_bdev, loop_set_fd);
+		bd_abort_claiming(bdev, claimed_bdev, loop_set_fd_and_status);
 out_putf:
 	fput(file);
 out:
@@ -1662,8 +1665,25 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	int err;
 
 	switch (cmd) {
-	case LOOP_SET_FD:
-		return loop_set_fd(lo, mode, bdev, arg);
+	case LOOP_SET_FD: {
+		/* legacy case - pass in a zeroed out loop_info64, which
+		 * corresponds with the default parameters we'd have used
+		 * otherwise.
+		 */
+		struct loop_info64 info;
+
+		memset(&info, 0, sizeof(info));
+		return loop_set_fd_and_status(lo, mode, bdev, arg, &info);
+	}
+	case LOOP_SET_FD_AND_STATUS: {
+		struct loop_fd_and_status fds;
+
+		if (copy_from_user(&fds, argp, sizeof(fds)))
+			return -EFAULT;
+
+		return loop_set_fd_and_status(lo, mode, bdev, fds.fd,
+					      &fds.info);
+	}
 	case LOOP_CHANGE_FD:
 		return loop_change_fd(lo, bdev, arg);
 	case LOOP_CLR_FD:
@@ -1835,6 +1855,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_CLR_FD:
 	case LOOP_GET_STATUS64:
 	case LOOP_SET_STATUS64:
+	case LOOP_SET_FD_AND_STATUS:
 		arg = (unsigned long) compat_ptr(arg);
 		/* fall through */
 	case LOOP_SET_FD:
diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h
index 080a8df134ef..05ab625c40db 100644
--- a/include/uapi/linux/loop.h
+++ b/include/uapi/linux/loop.h
@@ -60,6 +60,12 @@ struct loop_info64 {
 	__u64		   lo_init[2];
 };
 
+struct loop_fd_and_status {
+	struct loop_info64	info;
+	__u32			fd;
+	__u32			__pad;
+};
+
 /*
  * Loop filter types
  */
@@ -90,6 +96,7 @@ struct loop_info64 {
 #define LOOP_SET_CAPACITY	0x4C07
 #define LOOP_SET_DIRECT_IO	0x4C08
 #define LOOP_SET_BLOCK_SIZE	0x4C09
+#define LOOP_SET_FD_AND_STATUS	0x4C0A
 
 /* /dev/loop-control interface */
 #define LOOP_CTL_ADD		0x4C80
-- 
2.26.2.303.gf8c07b1a785-goog