From 68db1961bbf4e16c220ccec4a780e966bc1fece3 Mon Sep 17 00:00:00 2001 From: Nikanth Karthikesan Date: Tue, 24 Mar 2009 12:29:54 +0100 Subject: loop: support barrier writes Honour barrier requests in the loop back block device driver. In case of barrier bios, flush the backing file once before processing the barrier and once after to guarantee ordering. In case of filesystems that does not support fsync, barrier bios would be failed with -EOPNOTSUPP. Signed-off-by: Nikanth Karthikesan Signed-off-by: Jens Axboe --- drivers/block/loop.c | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) (limited to 'drivers/block/loop.c') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index bf0345577672..9721d100caf1 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -474,10 +474,35 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio) int ret; pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset; - if (bio_rw(bio) == WRITE) + + if (bio_rw(bio) == WRITE) { + int barrier = bio_barrier(bio); + struct file *file = lo->lo_backing_file; + + if (barrier) { + if (unlikely(!file->f_op->fsync)) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = vfs_fsync(file, file->f_path.dentry, 0); + if (unlikely(ret)) { + ret = -EIO; + goto out; + } + } + ret = lo_send(lo, bio, pos); - else + + if (barrier && !ret) { + ret = vfs_fsync(file, file->f_path.dentry, 0); + if (unlikely(ret)) + ret = -EIO; + } + } else ret = lo_receive(lo, bio, lo->lo_blocksize, pos); + +out: return ret; } @@ -826,6 +851,9 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, lo->lo_queue->queuedata = lo; lo->lo_queue->unplug_fn = loop_unplug; + if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) + blk_queue_ordered(lo->lo_queue, QUEUE_ORDERED_DRAIN, NULL); + set_capacity(lo->lo_disk, size); bd_set_size(bdev, size << 9); -- cgit v1.3-8-gc7d7 From f028f3b2f987ebc61cef382ab7a5c449917b728e Mon Sep 17 00:00:00 2001 From: Nikanth Karthikesan Date: Tue, 24 Mar 2009 12:33:41 +0100 Subject: loop: fix circular locking in loop_clr_fd() With CONFIG_PROVE_LOCKING enabled $ losetup /dev/loop0 file $ losetup -o 32256 /dev/loop1 /dev/loop0 $ losetup -d /dev/loop1 $ losetup -d /dev/loop0 triggers a [ INFO: possible circular locking dependency detected ] I think this warning is a false positive. Open/close on a loop device acquires bd_mutex of the device before acquiring lo_ctl_mutex of the same device. For ioctl(LOOP_CLR_FD) after acquiring lo_ctl_mutex, fput on the backing_file might acquire the bd_mutex of a device, if backing file is a device and this is the last reference to the file being dropped . But it is guaranteed that it is impossible to have a circular list of backing devices.(say loop2->loop1->loop0->loop2 is not possible), which guarantees that this can never deadlock. So this warning should be suppressed. It is very difficult to annotate lockdep not to warn here in the correct way. A simple way to silence lockdep could be to mark the lo_ctl_mutex in ioctl to be a sub class, but this might mask some other real bugs. @@ -1164,7 +1164,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, struct loop_device *lo = bdev->bd_disk->private_data; int err; - mutex_lock(&lo->lo_ctl_mutex); + mutex_lock_nested(&lo->lo_ctl_mutex, 1); switch (cmd) { case LOOP_SET_FD: err = loop_set_fd(lo, mode, bdev, arg); Or actually marking the bd_mutex after lo_ctl_mutex as a sub class could be a better solution. Luckily it is easy to avoid calling fput on backing file with lo_ctl_mutex held, so no lockdep annotation is required. If you do not like the special handling of the lo_ctl_mutex just for the LOOP_CLR_FD ioctl in lo_ioctl(), the mutex handling could be moved inside each of the individual ioctl handlers and I could send you another patch. Signed-off-by: Jens Axboe --- drivers/block/loop.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'drivers/block/loop.c') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 9721d100caf1..2621ed2ce6d2 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -969,11 +969,18 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev) bd_set_size(bdev, 0); mapping_set_gfp_mask(filp->f_mapping, gfp); lo->lo_state = Lo_unbound; - fput(filp); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); if (max_part > 0) ioctl_by_bdev(bdev, BLKRRPART, 0); + mutex_unlock(&lo->lo_ctl_mutex); + /* + * Need not hold lo_ctl_mutex to fput backing file. + * Calling fput holding lo_ctl_mutex triggers a circular + * lock dependency possibility warning as fput can take + * bd_mutex which is usually taken before lo_ctl_mutex. + */ + fput(filp); return 0; } @@ -1191,7 +1198,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, struct loop_device *lo = bdev->bd_disk->private_data; int err; - mutex_lock(&lo->lo_ctl_mutex); + mutex_lock_nested(&lo->lo_ctl_mutex, 1); switch (cmd) { case LOOP_SET_FD: err = loop_set_fd(lo, mode, bdev, arg); @@ -1200,7 +1207,10 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, err = loop_change_fd(lo, bdev, arg); break; case LOOP_CLR_FD: + /* loop_clr_fd would have unlocked lo_ctl_mutex on success */ err = loop_clr_fd(lo, bdev); + if (!err) + goto out_unlocked; break; case LOOP_SET_STATUS: err = loop_set_status_old(lo, (struct loop_info __user *) arg); @@ -1218,6 +1228,8 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; } mutex_unlock(&lo->lo_ctl_mutex); + +out_unlocked: return err; } -- cgit v1.3-8-gc7d7 From 53d6660836f233df66490707365ab177e5fb2bb4 Mon Sep 17 00:00:00 2001 From: "J. R. Okajima" Date: Tue, 31 Mar 2009 15:23:43 -0700 Subject: loop: add ioctl to resize a loop device Add the ability to 'resize' the loop device on the fly. One practical application is a loop file with XFS filesystem, already mounted: You can easily enlarge the file (append some bytes) and then call ioctl(fd, LOOP_SET_CAPACITY, new); The loop driver will learn about the new size and you can use xfs_growfs later on, which will allow you to use full capacity of the loop file without the need to unmount. Test app: #include #include #include #include #include #include #include #include #include #include #include #define _GNU_SOURCE #include char *me; void usage(FILE *f) { fprintf(f, "%s [options] loop_dev [backend_file]\n" "-s, --set new_size_in_bytes\n" "\twhen backend_file is given, " "it will be expanded too while keeping the original contents\n", me); } struct option opts[] = { { .name = "set", .has_arg = 1, .flag = NULL, .val = 's' }, { .name = "help", .has_arg = 0, .flag = NULL, .val = 'h' } }; void err_size(char *name, __u64 old) { fprintf(stderr, "size must be larger than current %s (%llu)\n", name, old); } int main(int argc, char *argv[]) { int fd, err, c, i, bfd; ssize_t ssz; size_t sz; __u64 old, new, append; char a[BUFSIZ]; struct stat st; FILE *out; char *backend, *dev; err = EINVAL; out = stderr; me = argv[0]; new = 0; while ((c = getopt_long(argc, argv, "s:h", opts, &i)) != -1) { switch (c) { case 's': errno = 0; new = strtoull(optarg, NULL, 0); if (errno) { err = errno; perror(argv[i]); goto out; } break; case 'h': err = 0; out = stdout; goto err; default: perror(argv[i]); goto err; } } if (optind < argc) dev = argv[optind++]; else goto err; fd = open(dev, O_RDONLY); if (fd < 0) { err = errno; perror(dev); goto out; } err = ioctl(fd, BLKGETSIZE64, &old); if (err) { err = errno; perror("ioctl BLKGETSIZE64"); goto out; } if (!new) { printf("%llu\n", old); goto out; } if (new < old) { err = EINVAL; err_size(dev, old); goto out; } if (optind < argc) { backend = argv[optind++]; bfd = open(backend, O_WRONLY|O_APPEND); if (bfd < 0) { err = errno; perror(backend); goto out; } err = fstat(bfd, &st); if (err) { err = errno; perror(backend); goto out; } if (new < st.st_size) { err = EINVAL; err_size(backend, st.st_size); goto out; } append = new - st.st_size; sz = sizeof(a); while (append > 0) { if (append < sz) sz = append; ssz = write(bfd, a, sz); if (ssz != sz) { err = errno; perror(backend); goto out; } append -= sz; } err = fsync(bfd); if (err) { err = errno; perror(backend); goto out; } } err = ioctl(fd, LOOP_SET_CAPACITY, new); if (err) { err = errno; perror("ioctl LOOP_SET_CAPACITY"); } goto out; err: usage(out); out: return err; } Signed-off-by: J. R. Okajima Signed-off-by: Tomas Matejicek Cc: Cc: Karel Zak Cc: Jens Axboe Cc: Al Viro Cc: Christoph Hellwig Cc: Akinobu Mita Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/loop.c | 30 ++++++++++++++++++++++++++++++ include/linux/loop.h | 1 + 2 files changed, 31 insertions(+) (limited to 'drivers/block/loop.c') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 2621ed2ce6d2..40b17d3b55a1 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1192,6 +1192,30 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { return err; } +static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev) +{ + int err; + sector_t sec; + loff_t sz; + + err = -ENXIO; + if (unlikely(lo->lo_state != Lo_bound)) + goto out; + err = figure_loop_size(lo); + if (unlikely(err)) + goto out; + sec = get_capacity(lo->lo_disk); + /* the width of sector_t may be narrow for bit-shift */ + sz = sec; + sz <<= 9; + mutex_lock(&bdev->bd_mutex); + bd_set_size(bdev, sz); + mutex_unlock(&bdev->bd_mutex); + + out: + return err; +} + static int lo_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { @@ -1224,6 +1248,11 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, case LOOP_GET_STATUS64: err = loop_get_status64(lo, (struct loop_info64 __user *) arg); break; + case LOOP_SET_CAPACITY: + err = -EPERM; + if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) + err = loop_set_capacity(lo, bdev); + break; default: err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; } @@ -1371,6 +1400,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, lo, (struct compat_loop_info __user *) arg); mutex_unlock(&lo->lo_ctl_mutex); break; + case LOOP_SET_CAPACITY: case LOOP_CLR_FD: case LOOP_GET_STATUS64: case LOOP_SET_STATUS64: diff --git a/include/linux/loop.h b/include/linux/loop.h index 6ffd6db5bb0d..40725447f5e0 100644 --- a/include/linux/loop.h +++ b/include/linux/loop.h @@ -160,5 +160,6 @@ int loop_unregister_transfer(int number); #define LOOP_SET_STATUS64 0x4C04 #define LOOP_GET_STATUS64 0x4C05 #define LOOP_CHANGE_FD 0x4C06 +#define LOOP_SET_CAPACITY 0x4C07 #endif -- cgit v1.3-8-gc7d7