aboutsummaryrefslogtreecommitdiff
path: root/drivers/block/loop.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block/loop.c')
-rw-r--r--drivers/block/loop.c218
1 files changed, 117 insertions, 101 deletions
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index cd504353b27..6cb1beb47c2 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -63,7 +63,6 @@
#include <linux/init.h>
#include <linux/swap.h>
#include <linux/slab.h>
-#include <linux/loop.h>
#include <linux/compat.h>
#include <linux/suspend.h>
#include <linux/freezer.h>
@@ -76,6 +75,7 @@
#include <linux/sysfs.h>
#include <linux/miscdevice.h>
#include <linux/falloc.h>
+#include "loop.h"
#include <asm/uaccess.h>
@@ -93,16 +93,16 @@ static int transfer_none(struct loop_device *lo, int cmd,
struct page *loop_page, unsigned loop_off,
int size, sector_t real_block)
{
- char *raw_buf = kmap_atomic(raw_page, KM_USER0) + raw_off;
- char *loop_buf = kmap_atomic(loop_page, KM_USER1) + loop_off;
+ char *raw_buf = kmap_atomic(raw_page) + raw_off;
+ char *loop_buf = kmap_atomic(loop_page) + loop_off;
if (cmd == READ)
memcpy(loop_buf, raw_buf, size);
else
memcpy(raw_buf, loop_buf, size);
- kunmap_atomic(loop_buf, KM_USER1);
- kunmap_atomic(raw_buf, KM_USER0);
+ kunmap_atomic(loop_buf);
+ kunmap_atomic(raw_buf);
cond_resched();
return 0;
}
@@ -112,8 +112,8 @@ static int transfer_xor(struct loop_device *lo, int cmd,
struct page *loop_page, unsigned loop_off,
int size, sector_t real_block)
{
- char *raw_buf = kmap_atomic(raw_page, KM_USER0) + raw_off;
- char *loop_buf = kmap_atomic(loop_page, KM_USER1) + loop_off;
+ char *raw_buf = kmap_atomic(raw_page) + raw_off;
+ char *loop_buf = kmap_atomic(loop_page) + loop_off;
char *in, *out, *key;
int i, keysize;
@@ -130,8 +130,8 @@ static int transfer_xor(struct loop_device *lo, int cmd,
for (i = 0; i < size; i++)
*out++ = *in++ ^ key[(i & 511) % keysize];
- kunmap_atomic(loop_buf, KM_USER1);
- kunmap_atomic(raw_buf, KM_USER0);
+ kunmap_atomic(loop_buf);
+ kunmap_atomic(raw_buf);
cond_resched();
return 0;
}
@@ -162,12 +162,13 @@ static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = {
static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
{
- loff_t size, loopsize;
+ loff_t loopsize;
/* Compute loopsize in bytes */
- size = i_size_read(file->f_mapping->host);
- loopsize = size - offset;
- /* offset is beyond i_size, wierd but possible */
+ loopsize = i_size_read(file->f_mapping->host);
+ if (offset > 0)
+ loopsize -= offset;
+ /* offset is beyond i_size, weird but possible */
if (loopsize < 0)
return 0;
@@ -190,6 +191,7 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
{
loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
sector_t x = (sector_t)size;
+ struct block_device *bdev = lo->lo_device;
if (unlikely((loff_t)x != size))
return -EFBIG;
@@ -198,6 +200,9 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
if (lo->lo_sizelimit != sizelimit)
lo->lo_sizelimit = sizelimit;
set_capacity(lo->lo_disk, x);
+ bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9);
+ /* let user-space know about the new size */
+ kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
return 0;
}
@@ -225,12 +230,14 @@ static int __do_lo_send_write(struct file *file,
ssize_t bw;
mm_segment_t old_fs = get_fs();
+ file_start_write(file);
set_fs(get_ds());
bw = file->f_op->write(file, buf, len, &pos);
set_fs(old_fs);
+ file_end_write(file);
if (likely(bw == len))
return 0;
- printk(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n",
+ printk_ratelimited(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n",
(unsigned long long)pos, len);
if (bw >= 0)
bw = -EIO;
@@ -270,7 +277,7 @@ static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
return __do_lo_send_write(lo->lo_backing_file,
page_address(page), bvec->bv_len,
pos);
- printk(KERN_ERR "loop: Transfer error at byte offset %llu, "
+ printk_ratelimited(KERN_ERR "loop: Transfer error at byte offset %llu, "
"length %i.\n", (unsigned long long)pos, bvec->bv_len);
if (ret > 0)
ret = -EIO;
@@ -281,9 +288,10 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
{
int (*do_lo_send)(struct loop_device *, struct bio_vec *, loff_t,
struct page *page);
- struct bio_vec *bvec;
+ struct bio_vec bvec;
+ struct bvec_iter iter;
struct page *page = NULL;
- int i, ret = 0;
+ int ret = 0;
if (lo->transfer != transfer_none) {
page = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
@@ -295,11 +303,11 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
do_lo_send = do_lo_send_direct_write;
}
- bio_for_each_segment(bvec, bio, i) {
- ret = do_lo_send(lo, bvec, pos, page);
+ bio_for_each_segment(bvec, bio, iter) {
+ ret = do_lo_send(lo, &bvec, pos, page);
if (ret < 0)
break;
- pos += bvec->bv_len;
+ pos += bvec.bv_len;
}
if (page) {
kunmap(page);
@@ -308,7 +316,7 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
out:
return ret;
fail:
- printk(KERN_ERR "loop: Failed to allocate temporary page for write.\n");
+ printk_ratelimited(KERN_ERR "loop: Failed to allocate temporary page for write.\n");
ret = -ENOMEM;
goto out;
}
@@ -337,7 +345,7 @@ lo_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
size = p->bsize;
if (lo_do_transfer(lo, READ, page, buf->offset, p->page, p->offset, size, IV)) {
- printk(KERN_ERR "loop: transfer error block %ld\n",
+ printk_ratelimited(KERN_ERR "loop: transfer error block %ld\n",
page->index);
size = -EINVAL;
}
@@ -385,20 +393,20 @@ do_lo_receive(struct loop_device *lo,
static int
lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
{
- struct bio_vec *bvec;
+ struct bio_vec bvec;
+ struct bvec_iter iter;
ssize_t s;
- int i;
- bio_for_each_segment(bvec, bio, i) {
- s = do_lo_receive(lo, bvec, bsize, pos);
+ bio_for_each_segment(bvec, bio, iter) {
+ s = do_lo_receive(lo, &bvec, bsize, pos);
if (s < 0)
return s;
- if (s != bvec->bv_len) {
+ if (s != bvec.bv_len) {
zero_fill_bio(bio);
break;
}
- pos += bvec->bv_len;
+ pos += bvec.bv_len;
}
return 0;
}
@@ -408,7 +416,7 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
loff_t pos;
int ret;
- pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
+ pos = ((loff_t) bio->bi_iter.bi_sector << 9) + lo->lo_offset;
if (bio_rw(bio) == WRITE) {
struct file *file = lo->lo_backing_file;
@@ -437,7 +445,7 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
goto out;
}
ret = file->f_op->fallocate(file, mode, pos,
- bio->bi_size);
+ bio->bi_iter.bi_size);
if (unlikely(ret && ret != -EINVAL &&
ret != -EOPNOTSUPP))
ret = -EIO;
@@ -463,6 +471,7 @@ out:
*/
static void loop_add_bio(struct loop_device *lo, struct bio *bio)
{
+ lo->lo_bio_count++;
bio_list_add(&lo->lo_bio_list, bio);
}
@@ -471,6 +480,7 @@ static void loop_add_bio(struct loop_device *lo, struct bio *bio)
*/
static struct bio *loop_get_bio(struct loop_device *lo)
{
+ lo->lo_bio_count--;
return bio_list_pop(&lo->lo_bio_list);
}
@@ -489,6 +499,10 @@ static void loop_make_request(struct request_queue *q, struct bio *old_bio)
goto out;
if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY)))
goto out;
+ if (lo->lo_bio_count >= q->nr_congestion_on)
+ wait_event_lock_irq(lo->lo_req_wait,
+ lo->lo_bio_count < q->nr_congestion_off,
+ lo->lo_lock);
loop_add_bio(lo, old_bio);
wake_up(&lo->lo_event);
spin_unlock_irq(&lo->lo_lock);
@@ -534,7 +548,7 @@ static int loop_thread(void *data)
struct loop_device *lo = data;
struct bio *bio;
- set_user_nice(current, -20);
+ set_user_nice(current, MIN_NICE);
while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) {
@@ -546,6 +560,8 @@ static int loop_thread(void *data)
continue;
spin_lock_irq(&lo->lo_lock);
bio = loop_get_bio(lo);
+ if (lo->lo_bio_count < lo->lo_queue->nr_congestion_off)
+ wake_up(&lo->lo_req_wait);
spin_unlock_irq(&lo->lo_lock);
BUG_ON(!bio);
@@ -783,7 +799,7 @@ static void loop_config_discard(struct loop_device *lo)
/*
* We use punch hole to reclaim the free space used by the
- * image a.k.a. discard. However we do support discard if
+ * image a.k.a. discard. However we do not support discard if
* encryption is enabled, because it may give an attacker
* useful information.
*/
@@ -873,18 +889,12 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
lo->transfer = transfer_none;
lo->ioctl = NULL;
lo->lo_sizelimit = 0;
+ lo->lo_bio_count = 0;
lo->old_gfp_mask = mapping_gfp_mask(mapping);
mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
bio_list_init(&lo->lo_bio_list);
- /*
- * set queue make_request_fn, and add limits based on lower level
- * device
- */
- blk_queue_make_request(lo->lo_queue, loop_make_request);
- lo->lo_queue->queuedata = lo;
-
if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
blk_queue_flush(lo->lo_queue, REQ_FLUSH);
@@ -908,6 +918,11 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
lo->lo_flags |= LO_FLAGS_PARTSCAN;
if (lo->lo_flags & LO_FLAGS_PARTSCAN)
ioctl_by_bdev(bdev, BLKRRPART, 0);
+
+ /* Grab the block_device to prevent its destruction after we
+ * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev).
+ */
+ bdgrab(bdev);
return 0;
out_clr:
@@ -976,8 +991,21 @@ static int loop_clr_fd(struct loop_device *lo)
if (lo->lo_state != Lo_bound)
return -ENXIO;
- if (lo->lo_refcnt > 1) /* we needed one fd for the ioctl */
- return -EBUSY;
+ /*
+ * If we've explicitly asked to tear down the loop device,
+ * and it has an elevated reference count, set it for auto-teardown when
+ * the last reference goes away. This stops $!~#$@ udev from
+ * preventing teardown because it decided that it needs to run blkid on
+ * the loopback device whenever they appear. xfstests is notorious for
+ * failing tests because blkid via udev races with a losetup
+ * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
+ * command to fail with EBUSY.
+ */
+ if (lo->lo_refcnt > 1) {
+ lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
+ mutex_unlock(&lo->lo_ctl_mutex);
+ return 0;
+ }
if (filp == NULL)
return -EINVAL;
@@ -1004,8 +1032,10 @@ static int loop_clr_fd(struct loop_device *lo)
memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
memset(lo->lo_file_name, 0, LO_NAME_SIZE);
- if (bdev)
+ if (bdev) {
+ bdput(bdev);
invalidate_bdev(bdev);
+ }
set_capacity(lo->lo_disk, 0);
loop_sysfs_exit(lo);
if (bdev) {
@@ -1038,10 +1068,10 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
{
int err;
struct loop_func_table *xfer;
- uid_t uid = current_uid();
+ kuid_t uid = current_uid();
if (lo->lo_encrypt_key_size &&
- lo->lo_key_owner != uid &&
+ !uid_eq(lo->lo_key_owner, uid) &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
if (lo->lo_state != Lo_bound)
@@ -1069,10 +1099,10 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
return err;
if (lo->lo_offset != info->lo_offset ||
- lo->lo_sizelimit != info->lo_sizelimit) {
+ lo->lo_sizelimit != info->lo_sizelimit)
if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit))
return -EFBIG;
- }
+
loop_config_discard(lo);
memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
@@ -1117,7 +1147,7 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info)
if (lo->lo_state != Lo_bound)
return -ENXIO;
- error = vfs_getattr(file->f_path.mnt, file->f_path.dentry, &stat);
+ error = vfs_getattr(&file->f_path, &stat);
if (error)
return error;
memset(info, 0, sizeof(*info));
@@ -1249,28 +1279,10 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
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, lo->lo_offset, lo->lo_sizelimit);
- 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);
- /* let user-space know about the new size */
- kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
- mutex_unlock(&bdev->bd_mutex);
+ return -ENXIO;
- out:
- return err;
+ return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
}
static int lo_ioctl(struct block_device *bdev, fmode_t mode,
@@ -1500,7 +1512,7 @@ out:
return err;
}
-static int lo_release(struct gendisk *disk, fmode_t mode)
+static void lo_release(struct gendisk *disk, fmode_t mode)
{
struct loop_device *lo = disk->private_data;
int err;
@@ -1517,7 +1529,7 @@ static int lo_release(struct gendisk *disk, fmode_t mode)
*/
err = loop_clr_fd(lo);
if (!err)
- goto out_unlocked;
+ return;
} else {
/*
* Otherwise keep thread (if running) and config,
@@ -1528,8 +1540,6 @@ static int lo_release(struct gendisk *disk, fmode_t mode)
out:
mutex_unlock(&lo->lo_ctl_mutex);
-out_unlocked:
- return 0;
}
static const struct block_device_operations lo_fops = {
@@ -1597,41 +1607,35 @@ static int loop_add(struct loop_device **l, int i)
struct gendisk *disk;
int err;
+ err = -ENOMEM;
lo = kzalloc(sizeof(*lo), GFP_KERNEL);
- if (!lo) {
- err = -ENOMEM;
+ if (!lo)
goto out;
- }
- err = idr_pre_get(&loop_index_idr, GFP_KERNEL);
- if (err < 0)
- goto out_free_dev;
+ lo->lo_state = Lo_unbound;
+ /* allocate id, if @id >= 0, we're requesting that specific id */
if (i >= 0) {
- int m;
-
- /* create specific i in the index */
- err = idr_get_new_above(&loop_index_idr, lo, i, &m);
- if (err >= 0 && i != m) {
- idr_remove(&loop_index_idr, m);
+ err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL);
+ if (err == -ENOSPC)
err = -EEXIST;
- }
- } else if (i == -1) {
- int m;
-
- /* get next free nr */
- err = idr_get_new(&loop_index_idr, lo, &m);
- if (err >= 0)
- i = m;
} else {
- err = -EINVAL;
+ err = idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL);
}
if (err < 0)
goto out_free_dev;
+ i = err;
+ err = -ENOMEM;
lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
if (!lo->lo_queue)
- goto out_free_dev;
+ goto out_free_idr;
+
+ /*
+ * set queue make_request_fn
+ */
+ blk_queue_make_request(lo->lo_queue, loop_make_request);
+ lo->lo_queue->queuedata = lo;
disk = lo->lo_disk = alloc_disk(1 << part_shift);
if (!disk)
@@ -1662,6 +1666,7 @@ static int loop_add(struct loop_device **l, int i)
lo->lo_number = i;
lo->lo_thread = NULL;
init_waitqueue_head(&lo->lo_event);
+ init_waitqueue_head(&lo->lo_req_wait);
spin_lock_init(&lo->lo_lock);
disk->major = LOOP_MAJOR;
disk->first_minor = i << part_shift;
@@ -1675,6 +1680,8 @@ static int loop_add(struct loop_device **l, int i)
out_free_queue:
blk_cleanup_queue(lo->lo_queue);
+out_free_idr:
+ idr_remove(&loop_index_idr, i);
out_free_dev:
kfree(lo);
out:
@@ -1738,7 +1745,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data)
if (err < 0)
err = loop_add(&lo, MINOR(dev) >> part_shift);
if (err < 0)
- kobj = ERR_PTR(err);
+ kobj = NULL;
else
kobj = get_disk(lo->lo_disk);
mutex_unlock(&loop_index_mutex);
@@ -1837,11 +1844,15 @@ static int __init loop_init(void)
max_part = (1UL << part_shift) - 1;
}
- if ((1UL << part_shift) > DISK_MAX_PARTS)
- return -EINVAL;
+ if ((1UL << part_shift) > DISK_MAX_PARTS) {
+ err = -EINVAL;
+ goto misc_out;
+ }
- if (max_loop > 1UL << (MINORBITS - part_shift))
- return -EINVAL;
+ if (max_loop > 1UL << (MINORBITS - part_shift)) {
+ err = -EINVAL;
+ goto misc_out;
+ }
/*
* If max_loop is specified, create that many devices upfront.
@@ -1859,8 +1870,10 @@ static int __init loop_init(void)
range = 1UL << MINORBITS;
}
- if (register_blkdev(LOOP_MAJOR, "loop"))
- return -EIO;
+ if (register_blkdev(LOOP_MAJOR, "loop")) {
+ err = -EIO;
+ goto misc_out;
+ }
blk_register_region(MKDEV(LOOP_MAJOR, 0), range,
THIS_MODULE, loop_probe, NULL, NULL);
@@ -1873,6 +1886,10 @@ static int __init loop_init(void)
printk(KERN_INFO "loop: module loaded\n");
return 0;
+
+misc_out:
+ misc_deregister(&loop_misc);
+ return err;
}
static int loop_exit_cb(int id, void *ptr, void *data)
@@ -1890,7 +1907,6 @@ static void __exit loop_exit(void)
range = max_loop ? max_loop << part_shift : 1UL << MINORBITS;
idr_for_each(&loop_index_idr, &loop_exit_cb, NULL);
- idr_remove_all(&loop_index_idr);
idr_destroy(&loop_index_idr);
blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 17:35:04 +0000