Skip to contentSkip to conversation

loop: Add LOOP_SET_FD_WITH_OFFSET ioctl.

PATCH In review Martijn Coenen 1 participant 2 messages Mar 31, 2020 Block layer

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 loop: Add LOOP_SET_FD_WITH_OFFSET ioctl.

Configuring a loop device for a filesystem that is located at an offset currently requires calling LOOP_SET_FD and LOOP_SET_STATUS(64) consecutively. This has some downsides.

The most important downside is that it can be slow. Here's setting up ~70 regular loop devices on an x86 Android device:

vsoc_x86:/system/apex # time for i in seq 30 100; do losetup -r /dev/block/loop$i com.android.adbd.apex; done

    0m01.85s real     0m00.01s user     0m00.01s system

Here's configuring ~70 devices in the same way, but with an offset:

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

This is almost twice as 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.

A more minor downside of having to do two ioctls is that on devices with max_part > 0, the kernel will initiate a partition scan, which is needless work if the image is at an offset.

This change introduces a new ioctl to combine setting the backing file together with the offset, which avoids the above problems. Adding more parameters could be a consideration, but offset appears to be the only commonly used parameter that is required for accessing the device safely.

---
 drivers/block/loop.c      | 25 +++++++++++++++++++------
 include/uapi/linux/loop.h |  6 ++++++
 2 files changed, 25 insertions(+), 6 deletions(-)
drivers/block/loop.c +19 -6
index a42c49e04954..517031e1d10c 100644
@@ -932,8 +932,8 @@ static void loop_update_rotational(struct loop_device *lo)
 		blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
 }
 
-static int loop_set_fd(struct loop_device *lo, fmode_t mode,
-		       struct block_device *bdev, unsigned int arg)
+static int loop_set_fd_with_offset(struct loop_device *lo, fmode_t mode,
+		struct block_device *bdev, unsigned int arg, loff_t offset)
 {
 	struct file	*file;
 	struct inode	*inode;
@@ -957,7 +957,7 @@ 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_with_offset);
 		if (IS_ERR(claimed_bdev)) {
 			error = PTR_ERR(claimed_bdev);
 			goto out_putf;
@@ -1002,6 +1002,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->transfer = NULL;
 	lo->ioctl = NULL;
 	lo->lo_sizelimit = 0;
+	lo->lo_offset = offset;
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
@@ -1042,14 +1043,14 @@ 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_with_offset);
 	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_with_offset);
 out_putf:
 	fput(file);
 out:
@@ -1601,7 +1602,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 
 	switch (cmd) {
 	case LOOP_SET_FD:
-		return loop_set_fd(lo, mode, bdev, arg);
+		return loop_set_fd_with_offset(lo, mode, bdev, arg, 0);
 	case LOOP_CHANGE_FD:
 		return loop_change_fd(lo, bdev, arg);
 	case LOOP_CLR_FD:
@@ -1624,6 +1625,17 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 		break;
 	case LOOP_GET_STATUS64:
 		return loop_get_status64(lo, (struct loop_info64 __user *) arg);
+	case LOOP_SET_FD_WITH_OFFSET: {
+		struct loop_fd_with_offset fdwo;
+
+		if (copy_from_user(&fdwo,
+				(struct loop_fd_with_offset __user *) arg,
+				sizeof(struct loop_fd_with_offset)))
+			return -EFAULT;
+
+		return loop_set_fd_with_offset(lo, mode, bdev, fdwo.fd,
+				fdwo.lo_offset);
+	}
 	case LOOP_SET_CAPACITY:
 	case LOOP_SET_DIRECT_IO:
 	case LOOP_SET_BLOCK_SIZE:
@@ -1774,6 +1786,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_SET_CAPACITY:
 	case LOOP_CLR_FD:
 	case LOOP_GET_STATUS64:
+	case LOOP_SET_FD_WITH_OFFSET:
 	case LOOP_SET_STATUS64:
 		arg = (unsigned long) compat_ptr(arg);
 		/* fall through */
include/uapi/linux/loop.h +6 -0
index 080a8df134ef..289829bc5abd 100644
@@ -60,6 +60,11 @@ struct loop_info64 {
 	__u64		   lo_init[2];
 };
 
+struct loop_fd_with_offset {
+	__u64          lo_offset;
+	__u32          fd;
+};
+
 /*
  * Loop filter types
  */
@@ -90,6 +95,7 @@ struct loop_info64 {
 #define LOOP_SET_CAPACITY	0x4C07
 #define LOOP_SET_DIRECT_IO	0x4C08
 #define LOOP_SET_BLOCK_SIZE	0x4C09
+#define LOOP_SET_FD_WITH_OFFSET	0x4C0A
 
 /* /dev/loop-control interface */
 #define LOOP_CTL_ADD		0x4C80
Signature · 1 line
2.26.0.rc2.310.g2932bb562d-goog
#1 lore raw

Apologies for the resend, will follow up with a new series.

Martijn

Quoted 150 lines · Martijn Coenen

Configuring a loop device for a filesystem that is located at an offset currently requires calling LOOP_SET_FD and LOOP_SET_STATUS(64) consecutively. This has some downsides.

The most important downside is that it can be slow. Here's setting up ~70 regular loop devices on an x86 Android device:

vsoc_x86:/system/apex # time for i in seq 30 100; do losetup -r /dev/block/loop$i com.android.adbd.apex; done

    0m01.85s real     0m00.01s user     0m00.01s system

Here's configuring ~70 devices in the same way, but with an offset:

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

This is almost twice as 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.

A more minor downside of having to do two ioctls is that on devices with max_part > 0, the kernel will initiate a partition scan, which is needless work if the image is at an offset.

This change introduces a new ioctl to combine setting the backing file together with the offset, which avoids the above problems. Adding more parameters could be a consideration, but offset appears to be the only commonly used parameter that is required for accessing the device safely.

---
 drivers/block/loop.c      | 25 +++++++++++++++++++------
 include/uapi/linux/loop.h |  6 ++++++
 2 files changed, 25 insertions(+), 6 deletions(-)
drivers/block/loop.c +19 -6
index a42c49e04954..517031e1d10c 100644
@@ -932,8 +932,8 @@ static void loop_update_rotational(struct loop_device *lo)
                blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
 }
 
-static int loop_set_fd(struct loop_device *lo, fmode_t mode,
-                      struct block_device *bdev, unsigned int arg)
+static int loop_set_fd_with_offset(struct loop_device *lo, fmode_t mode,
+               struct block_device *bdev, unsigned int arg, loff_t offset)
 {
        struct file     *file;
        struct inode    *inode;
@@ -957,7 +957,7 @@ 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_with_offset);
                if (IS_ERR(claimed_bdev)) {
                        error = PTR_ERR(claimed_bdev);
                        goto out_putf;
@@ -1002,6 +1002,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
        lo->transfer = NULL;
        lo->ioctl = NULL;
        lo->lo_sizelimit = 0;
+       lo->lo_offset = offset;
        lo->old_gfp_mask = mapping_gfp_mask(mapping);
        mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
@@ -1042,14 +1043,14 @@ 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_with_offset);
        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_with_offset);
 out_putf:
        fput(file);
 out:
@@ -1601,7 +1602,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 
        switch (cmd) {
        case LOOP_SET_FD:
-               return loop_set_fd(lo, mode, bdev, arg);
+               return loop_set_fd_with_offset(lo, mode, bdev, arg, 0);
        case LOOP_CHANGE_FD:
                return loop_change_fd(lo, bdev, arg);
        case LOOP_CLR_FD:
@@ -1624,6 +1625,17 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
                break;
        case LOOP_GET_STATUS64:
                return loop_get_status64(lo, (struct loop_info64 __user *) arg);
+       case LOOP_SET_FD_WITH_OFFSET: {
+               struct loop_fd_with_offset fdwo;
+
+               if (copy_from_user(&fdwo,
+                               (struct loop_fd_with_offset __user *) arg,
+                               sizeof(struct loop_fd_with_offset)))
+                       return -EFAULT;
+
+               return loop_set_fd_with_offset(lo, mode, bdev, fdwo.fd,
+                               fdwo.lo_offset);
+       }
        case LOOP_SET_CAPACITY:
        case LOOP_SET_DIRECT_IO:
        case LOOP_SET_BLOCK_SIZE:
@@ -1774,6 +1786,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
        case LOOP_SET_CAPACITY:
        case LOOP_CLR_FD:
        case LOOP_GET_STATUS64:
+       case LOOP_SET_FD_WITH_OFFSET:
        case LOOP_SET_STATUS64:
                arg = (unsigned long) compat_ptr(arg);
                /* fall through */
include/uapi/linux/loop.h +6 -1
index 080a8df134ef..289829bc5abd 100644
@@ -60,6 +60,11 @@ struct loop_info64 {
        __u64              lo_init[2];
 };
 
+struct loop_fd_with_offset {
+       __u64          lo_offset;
+       __u32          fd;
+};
+
 /*
  * Loop filter types
  */
@@ -90,6 +95,7 @@ struct loop_info64 {
 #define LOOP_SET_CAPACITY      0x4C07
 #define LOOP_SET_DIRECT_IO     0x4C08
 #define LOOP_SET_BLOCK_SIZE    0x4C09
+#define LOOP_SET_FD_WITH_OFFSET        0x4C0A
 
 /* /dev/loop-control interface */
 #define LOOP_CTL_ADD           0x4C80
--

2.26.0.rc2.310.g2932bb562d-goog