diff options
Diffstat (limited to 'drivers/block/loop.c')
| -rw-r--r-- | drivers/block/loop.c | 1440 |
1 files changed, 1013 insertions, 427 deletions
diff --git a/drivers/block/loop.c b/drivers/block/loop.c index b35e08876dd..6cb1beb47c2 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -29,7 +29,7 @@ * * Maximum number of loop devices when compiled-in now selectable by passing * max_loop=<1-255> to the kernel on boot. - * Erik I. Bolsø, <eriki@himolde.no>, Oct 31, 1999 + * Erik I. Bolsø, <eriki@himolde.no>, Oct 31, 1999 * * Completely rewrite request handling to be make_request_fn style and * non blocking, pushing work to a helper thread. Lots of fixes from @@ -40,8 +40,7 @@ * Heinz Mauelshagen <mge@sistina.com>, Feb 2002 * * Support for falling back on the write file operation when the address space - * operations prepare_write and/or commit_write are not available on the - * backing filesystem. + * operations write_begin is not available on the backing filesystem. * Anton Altaparmakov, 16 Feb 2005 * * Still To Fix: @@ -50,7 +49,6 @@ * */ -#include <linux/config.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/sched.h> @@ -63,23 +61,29 @@ #include <linux/blkdev.h> #include <linux/blkpg.h> #include <linux/init.h> -#include <linux/devfs_fs_kernel.h> -#include <linux/smp_lock.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> +#include <linux/mutex.h> #include <linux/writeback.h> -#include <linux/buffer_head.h> /* for invalidate_bdev() */ #include <linux/completion.h> #include <linux/highmem.h> -#include <linux/gfp.h> +#include <linux/kthread.h> +#include <linux/splice.h> +#include <linux/sysfs.h> +#include <linux/miscdevice.h> +#include <linux/falloc.h> +#include "loop.h" #include <asm/uaccess.h> -static int max_loop = 8; -static struct loop_device *loop_dev; -static struct gendisk **disks; +static DEFINE_IDR(loop_index_idr); +static DEFINE_MUTEX(loop_index_mutex); + +static int max_part; +static int part_shift; /* * Transfer functions @@ -89,16 +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(raw_buf, KM_USER0); - kunmap_atomic(loop_buf, KM_USER1); + kunmap_atomic(loop_buf); + kunmap_atomic(raw_buf); cond_resched(); return 0; } @@ -108,8 +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; @@ -126,8 +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(raw_buf, KM_USER0); - kunmap_atomic(loop_buf, KM_USER1); + kunmap_atomic(loop_buf); + kunmap_atomic(raw_buf); cond_resched(); return 0; } @@ -156,17 +160,20 @@ static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = { &xor_funcs }; -static loff_t get_loop_size(struct loop_device *lo, struct file *file) +static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file) { - loff_t size, offset, loopsize; + loff_t loopsize; /* Compute loopsize in bytes */ - size = i_size_read(file->f_mapping->host); - offset = lo->lo_offset; - loopsize = size - offset; - if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize) - loopsize = lo->lo_sizelimit; + 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; + if (sizelimit > 0 && sizelimit < loopsize) + loopsize = sizelimit; /* * Unfortunately, if we want to do I/O on the device, * the number of 512-byte sectors has to fit into a sector_t. @@ -174,17 +181,29 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file) return loopsize >> 9; } +static loff_t get_loop_size(struct loop_device *lo, struct file *file) +{ + return get_size(lo->lo_offset, lo->lo_sizelimit, file); +} + static int -figure_loop_size(struct loop_device *lo) +figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit) { - loff_t size = get_loop_size(lo, lo->lo_backing_file); + 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; - - set_capacity(disks[lo->lo_number], x); - return 0; + if (lo->lo_offset != offset) + lo->lo_offset = offset; + 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; } static inline int @@ -200,99 +219,25 @@ lo_do_transfer(struct loop_device *lo, int cmd, } /** - * do_lo_send_aops - helper for writing data to a loop device - * - * This is the fast version for backing filesystems which implement the address - * space operations prepare_write and commit_write. - */ -static int do_lo_send_aops(struct loop_device *lo, struct bio_vec *bvec, - int bsize, loff_t pos, struct page *page) -{ - struct file *file = lo->lo_backing_file; /* kudos to NFsckingS */ - struct address_space *mapping = file->f_mapping; - struct address_space_operations *aops = mapping->a_ops; - pgoff_t index; - unsigned offset, bv_offs; - int len, ret = 0; - - down(&mapping->host->i_sem); - index = pos >> PAGE_CACHE_SHIFT; - offset = pos & ((pgoff_t)PAGE_CACHE_SIZE - 1); - bv_offs = bvec->bv_offset; - len = bvec->bv_len; - while (len > 0) { - sector_t IV; - unsigned size; - int transfer_result; - - IV = ((sector_t)index << (PAGE_CACHE_SHIFT - 9))+(offset >> 9); - size = PAGE_CACHE_SIZE - offset; - if (size > len) - size = len; - page = grab_cache_page(mapping, index); - if (unlikely(!page)) - goto fail; - if (unlikely(aops->prepare_write(file, page, offset, - offset + size))) - goto unlock; - transfer_result = lo_do_transfer(lo, WRITE, page, offset, - bvec->bv_page, bv_offs, size, IV); - if (unlikely(transfer_result)) { - char *kaddr; - - /* - * The transfer failed, but we still write the data to - * keep prepare/commit calls balanced. - */ - printk(KERN_ERR "loop: transfer error block %llu\n", - (unsigned long long)index); - kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr + offset, 0, size); - kunmap_atomic(kaddr, KM_USER0); - } - flush_dcache_page(page); - if (unlikely(aops->commit_write(file, page, offset, - offset + size))) - goto unlock; - if (unlikely(transfer_result)) - goto unlock; - bv_offs += size; - len -= size; - offset = 0; - index++; - pos += size; - unlock_page(page); - page_cache_release(page); - } -out: - up(&mapping->host->i_sem); - return ret; -unlock: - unlock_page(page); - page_cache_release(page); -fail: - ret = -1; - goto out; -} - -/** * __do_lo_send_write - helper for writing data to a loop device * * This helper just factors out common code between do_lo_send_direct_write() * and do_lo_send_write(). */ -static inline int __do_lo_send_write(struct file *file, - u8 __user *buf, const int len, loff_t pos) +static int __do_lo_send_write(struct file *file, + u8 *buf, const int len, loff_t pos) { 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; @@ -302,16 +247,14 @@ static inline int __do_lo_send_write(struct file *file, /** * do_lo_send_direct_write - helper for writing data to a loop device * - * This is the fast, non-transforming version for backing filesystems which do - * not implement the address space operations prepare_write and commit_write. - * It uses the write file operation which should be present on all writeable - * filesystems. + * This is the fast, non-transforming version that does not need double + * buffering. */ static int do_lo_send_direct_write(struct loop_device *lo, - struct bio_vec *bvec, int bsize, loff_t pos, struct page *page) + struct bio_vec *bvec, loff_t pos, struct page *page) { ssize_t bw = __do_lo_send_write(lo->lo_backing_file, - (u8 __user *)kmap(bvec->bv_page) + bvec->bv_offset, + kmap(bvec->bv_page) + bvec->bv_offset, bvec->bv_len, pos); kunmap(bvec->bv_page); cond_resched(); @@ -321,57 +264,50 @@ static int do_lo_send_direct_write(struct loop_device *lo, /** * do_lo_send_write - helper for writing data to a loop device * - * This is the slow, transforming version for filesystems which do not - * implement the address space operations prepare_write and commit_write. It - * uses the write file operation which should be present on all writeable - * filesystems. - * - * Using fops->write is slower than using aops->{prepare,commit}_write in the - * transforming case because we need to double buffer the data as we cannot do - * the transformations in place as we do not have direct access to the - * destination pages of the backing file. + * This is the slow, transforming version that needs to double buffer the + * data as it cannot do the transformations in place without having direct + * access to the destination pages of the backing file. */ static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec, - int bsize, loff_t pos, struct page *page) + loff_t pos, struct page *page) { int ret = lo_do_transfer(lo, WRITE, page, 0, bvec->bv_page, bvec->bv_offset, bvec->bv_len, pos >> 9); if (likely(!ret)) return __do_lo_send_write(lo->lo_backing_file, - (u8 __user *)page_address(page), bvec->bv_len, + 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; return ret; } -static int lo_send(struct loop_device *lo, struct bio *bio, int bsize, - loff_t pos) +static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos) { - int (*do_lo_send)(struct loop_device *, struct bio_vec *, int, loff_t, + 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; - do_lo_send = do_lo_send_aops; - if (!(lo->lo_flags & LO_FLAGS_USE_AOPS)) { + if (lo->transfer != transfer_none) { + page = alloc_page(GFP_NOIO | __GFP_HIGHMEM); + if (unlikely(!page)) + goto fail; + kmap(page); + do_lo_send = do_lo_send_write; + } else { do_lo_send = do_lo_send_direct_write; - if (lo->transfer != transfer_none) { - page = alloc_page(GFP_NOIO | __GFP_HIGHMEM); - if (unlikely(!page)) - goto fail; - kmap(page); - do_lo_send = do_lo_send_write; - } } - bio_for_each_segment(bvec, bio, i) { - ret = do_lo_send(lo, bvec, bsize, 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); @@ -380,7 +316,7 @@ static int lo_send(struct loop_device *lo, struct bio *bio, int bsize, 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; } @@ -393,65 +329,86 @@ struct lo_read_data { }; static int -lo_read_actor(read_descriptor_t *desc, struct page *page, - unsigned long offset, unsigned long size) +lo_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, + struct splice_desc *sd) { - unsigned long count = desc->count; - struct lo_read_data *p = desc->arg.data; + struct lo_read_data *p = sd->u.data; struct loop_device *lo = p->lo; + struct page *page = buf->page; sector_t IV; + int size; - IV = ((sector_t) page->index << (PAGE_CACHE_SHIFT - 9))+(offset >> 9); + IV = ((sector_t) page->index << (PAGE_CACHE_SHIFT - 9)) + + (buf->offset >> 9); + size = sd->len; + if (size > p->bsize) + size = p->bsize; - if (size > count) - size = count; - - if (lo_do_transfer(lo, READ, page, offset, p->page, p->offset, size, IV)) { - size = 0; - printk(KERN_ERR "loop: transfer error block %ld\n", + if (lo_do_transfer(lo, READ, page, buf->offset, p->page, p->offset, size, IV)) { + printk_ratelimited(KERN_ERR "loop: transfer error block %ld\n", page->index); - desc->error = -EINVAL; + size = -EINVAL; } flush_dcache_page(p->page); - desc->count = count - size; - desc->written += size; - p->offset += size; + if (size > 0) + p->offset += size; + return size; } static int +lo_direct_splice_actor(struct pipe_inode_info *pipe, struct splice_desc *sd) +{ + return __splice_from_pipe(pipe, sd, lo_splice_actor); +} + +static ssize_t do_lo_receive(struct loop_device *lo, struct bio_vec *bvec, int bsize, loff_t pos) { struct lo_read_data cookie; + struct splice_desc sd; struct file *file; - int retval; + ssize_t retval; cookie.lo = lo; cookie.page = bvec->bv_page; cookie.offset = bvec->bv_offset; cookie.bsize = bsize; + + sd.len = 0; + sd.total_len = bvec->bv_len; + sd.flags = 0; + sd.pos = pos; + sd.u.data = &cookie; + file = lo->lo_backing_file; - retval = file->f_op->sendfile(file, &pos, bvec->bv_len, - lo_read_actor, &cookie); - return (retval < 0)? retval: 0; + retval = splice_direct_to_actor(file, &sd, lo_direct_splice_actor); + + return retval; } static int lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos) { - struct bio_vec *bvec; - int i, ret = 0; + struct bio_vec bvec; + struct bvec_iter iter; + ssize_t s; - bio_for_each_segment(bvec, bio, i) { - ret = do_lo_receive(lo, bvec, bsize, pos); - if (ret < 0) + 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) { + zero_fill_bio(bio); break; - pos += bvec->bv_len; + } + pos += bvec.bv_len; } - return ret; + return 0; } static int do_bio_filebacked(struct loop_device *lo, struct bio *bio) @@ -459,11 +416,53 @@ 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; - if (bio_rw(bio) == WRITE) - ret = lo_send(lo, bio, lo->lo_blocksize, pos); - else + pos = ((loff_t) bio->bi_iter.bi_sector << 9) + lo->lo_offset; + + if (bio_rw(bio) == WRITE) { + struct file *file = lo->lo_backing_file; + + if (bio->bi_rw & REQ_FLUSH) { + ret = vfs_fsync(file, 0); + if (unlikely(ret && ret != -EINVAL)) { + ret = -EIO; + goto out; + } + } + + /* + * We use punch hole to reclaim the free space used by the + * image a.k.a. discard. However we do not support discard if + * encryption is enabled, because it may give an attacker + * useful information. + */ + if (bio->bi_rw & REQ_DISCARD) { + struct file *file = lo->lo_backing_file; + int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE; + + if ((!file->f_op->fallocate) || + lo->lo_encrypt_key_size) { + ret = -EOPNOTSUPP; + goto out; + } + ret = file->f_op->fallocate(file, mode, pos, + bio->bi_iter.bi_size); + if (unlikely(ret && ret != -EINVAL && + ret != -EOPNOTSUPP)) + ret = -EIO; + goto out; + } + + ret = lo_send(lo, bio, pos); + + if ((bio->bi_rw & REQ_FUA) && !ret) { + ret = vfs_fsync(file, 0); + if (unlikely(ret && ret != -EINVAL)) + ret = -EIO; + } + } else ret = lo_receive(lo, bio, lo->lo_blocksize, pos); + +out: return ret; } @@ -472,11 +471,8 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio) */ static void loop_add_bio(struct loop_device *lo, struct bio *bio) { - if (lo->lo_biotail) { - lo->lo_biotail->bi_next = bio; - lo->lo_biotail = bio; - } else - lo->lo_bio = lo->lo_biotail = bio; + lo->lo_bio_count++; + bio_list_add(&lo->lo_bio_list, bio); } /* @@ -484,19 +480,11 @@ static void loop_add_bio(struct loop_device *lo, struct bio *bio) */ static struct bio *loop_get_bio(struct loop_device *lo) { - struct bio *bio; - - if ((bio = lo->lo_bio)) { - if (bio == lo->lo_biotail) - lo->lo_biotail = NULL; - lo->lo_bio = bio->bi_next; - bio->bi_next = NULL; - } - - return bio; + lo->lo_bio_count--; + return bio_list_pop(&lo->lo_bio_list); } -static int loop_make_request(request_queue_t *q, struct bio *old_bio) +static void loop_make_request(struct request_queue *q, struct bio *old_bio) { struct loop_device *lo = q->queuedata; int rw = bio_rw(old_bio); @@ -511,29 +499,18 @@ static int loop_make_request(request_queue_t *q, struct bio *old_bio) goto out; if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY))) goto out; - lo->lo_pending++; + 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); - up(&lo->lo_bh_mutex); - return 0; + return; out: - if (lo->lo_pending == 0) - up(&lo->lo_bh_mutex); spin_unlock_irq(&lo->lo_lock); - bio_io_error(old_bio, old_bio->bi_size); - return 0; -} - -/* - * kick off io on the underlying address space - */ -static void loop_unplug(request_queue_t *q) -{ - struct loop_device *lo = q->queuedata; - - clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags); - blk_run_address_space(lo->lo_backing_file->f_mapping); + bio_io_error(old_bio); } struct switch_request { @@ -550,7 +527,7 @@ static inline void loop_handle_bio(struct loop_device *lo, struct bio *bio) bio_put(bio); } else { int ret = do_bio_filebacked(lo, bio); - bio_endio(bio, bio->bi_size, ret); + bio_endio(bio, ret); } } @@ -559,67 +536,38 @@ static inline void loop_handle_bio(struct loop_device *lo, struct bio *bio) * to avoid blocking in our make_request_fn. it also does loop decrypting * on reads for block backed loop, as that is too heavy to do from * b_end_io context where irqs may be disabled. + * + * Loop explanation: loop_clr_fd() sets lo_state to Lo_rundown before + * calling kthread_stop(). Therefore once kthread_should_stop() is + * true, make_request will not place any more requests. Therefore + * once kthread_should_stop() is true and lo_bio is NULL, we are + * done with the loop. */ static int loop_thread(void *data) { struct loop_device *lo = data; struct bio *bio; - daemonize("loop%d", lo->lo_number); + set_user_nice(current, MIN_NICE); - /* - * loop can be used in an encrypted device, - * hence, it mustn't be stopped at all - * because it could be indirectly used during suspension - */ - current->flags |= PF_NOFREEZE; - - set_user_nice(current, -20); - - lo->lo_state = Lo_bound; - lo->lo_pending = 1; + while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) { - /* - * up sem, we are running - */ - up(&lo->lo_sem); + wait_event_interruptible(lo->lo_event, + !bio_list_empty(&lo->lo_bio_list) || + kthread_should_stop()); - for (;;) { - int pending; - - /* - * interruptible just to not contribute to load avg - */ - if (down_interruptible(&lo->lo_bh_mutex)) + if (bio_list_empty(&lo->lo_bio_list)) continue; - spin_lock_irq(&lo->lo_lock); - - /* - * could be upped because of tear-down, not pending work - */ - if (unlikely(!lo->lo_pending)) { - spin_unlock_irq(&lo->lo_lock); - break; - } - bio = loop_get_bio(lo); - lo->lo_pending--; - pending = lo->lo_pending; + 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); loop_handle_bio(lo, bio); - - /* - * upped both for pending work and tear-down, lo_pending - * will hit zero then - */ - if (unlikely(!pending)) - break; } - up(&lo->lo_sem); return 0; } @@ -631,7 +579,7 @@ static int loop_thread(void *data) static int loop_switch(struct loop_device *lo, struct file *file) { struct switch_request w; - struct bio *bio = bio_alloc(GFP_KERNEL, 1); + struct bio *bio = bio_alloc(GFP_KERNEL, 0); if (!bio) return -ENOMEM; init_completion(&w.wait); @@ -644,19 +592,38 @@ static int loop_switch(struct loop_device *lo, struct file *file) } /* + * Helper to flush the IOs in loop, but keeping loop thread running + */ +static int loop_flush(struct loop_device *lo) +{ + /* loop not yet configured, no running thread, nothing to flush */ + if (!lo->lo_thread) + return 0; + + return loop_switch(lo, NULL); +} + +/* * Do the actual switch; called from the BIO completion routine */ static void do_loop_switch(struct loop_device *lo, struct switch_request *p) { struct file *file = p->file; struct file *old_file = lo->lo_backing_file; - struct address_space *mapping = file->f_mapping; + struct address_space *mapping; + + /* if no new file, only flush of queued bios requested */ + if (!file) + goto out; + mapping = file->f_mapping; mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); lo->lo_backing_file = file; - lo->lo_blocksize = mapping->host->i_blksize; + lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ? + mapping->host->i_bdev->bd_block_size : PAGE_SIZE; lo->old_gfp_mask = mapping_gfp_mask(mapping); mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); +out: complete(&p->wait); } @@ -669,8 +636,8 @@ static void do_loop_switch(struct loop_device *lo, struct switch_request *p) * This can only work if the loop device is used read-only, and if the * new backing store is the same size and type as the old backing store. */ -static int loop_change_fd(struct loop_device *lo, struct file *lo_file, - struct block_device *bdev, unsigned int arg) +static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, + unsigned int arg) { struct file *file, *old_file; struct inode *inode; @@ -698,10 +665,6 @@ static int loop_change_fd(struct loop_device *lo, struct file *lo_file, if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) goto out_putf; - /* new backing store needs to support loop (eg sendfile) */ - if (!inode->i_fop->sendfile) - goto out_putf; - /* size of the new backing store needs to be the same */ if (get_loop_size(lo, file) != get_loop_size(lo, old_file)) goto out_putf; @@ -712,6 +675,8 @@ static int loop_change_fd(struct loop_device *lo, struct file *lo_file, goto out_putf; fput(old_file); + if (lo->lo_flags & LO_FLAGS_PARTSCAN) + ioctl_by_bdev(bdev, BLKRRPART, 0); return 0; out_putf: @@ -727,7 +692,135 @@ static inline int is_loop_device(struct file *file) return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR; } -static int loop_set_fd(struct loop_device *lo, struct file *lo_file, +/* loop sysfs attributes */ + +static ssize_t loop_attr_show(struct device *dev, char *page, + ssize_t (*callback)(struct loop_device *, char *)) +{ + struct gendisk *disk = dev_to_disk(dev); + struct loop_device *lo = disk->private_data; + + return callback(lo, page); +} + +#define LOOP_ATTR_RO(_name) \ +static ssize_t loop_attr_##_name##_show(struct loop_device *, char *); \ +static ssize_t loop_attr_do_show_##_name(struct device *d, \ + struct device_attribute *attr, char *b) \ +{ \ + return loop_attr_show(d, b, loop_attr_##_name##_show); \ +} \ +static struct device_attribute loop_attr_##_name = \ + __ATTR(_name, S_IRUGO, loop_attr_do_show_##_name, NULL); + +static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf) +{ + ssize_t ret; + char *p = NULL; + + spin_lock_irq(&lo->lo_lock); + if (lo->lo_backing_file) + p = d_path(&lo->lo_backing_file->f_path, buf, PAGE_SIZE - 1); + spin_unlock_irq(&lo->lo_lock); + + if (IS_ERR_OR_NULL(p)) + ret = PTR_ERR(p); + else { + ret = strlen(p); + memmove(buf, p, ret); + buf[ret++] = '\n'; + buf[ret] = 0; + } + + return ret; +} + +static ssize_t loop_attr_offset_show(struct loop_device *lo, char *buf) +{ + return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_offset); +} + +static ssize_t loop_attr_sizelimit_show(struct loop_device *lo, char *buf) +{ + return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit); +} + +static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf) +{ + int autoclear = (lo->lo_flags & LO_FLAGS_AUTOCLEAR); + + return sprintf(buf, "%s\n", autoclear ? "1" : "0"); +} + +static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf) +{ + int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN); + + return sprintf(buf, "%s\n", partscan ? "1" : "0"); +} + +LOOP_ATTR_RO(backing_file); +LOOP_ATTR_RO(offset); +LOOP_ATTR_RO(sizelimit); +LOOP_ATTR_RO(autoclear); +LOOP_ATTR_RO(partscan); + +static struct attribute *loop_attrs[] = { + &loop_attr_backing_file.attr, + &loop_attr_offset.attr, + &loop_attr_sizelimit.attr, + &loop_attr_autoclear.attr, + &loop_attr_partscan.attr, + NULL, +}; + +static struct attribute_group loop_attribute_group = { + .name = "loop", + .attrs= loop_attrs, +}; + +static int loop_sysfs_init(struct loop_device *lo) +{ + return sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj, + &loop_attribute_group); +} + +static void loop_sysfs_exit(struct loop_device *lo) +{ + sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj, + &loop_attribute_group); +} + +static void loop_config_discard(struct loop_device *lo) +{ + struct file *file = lo->lo_backing_file; + struct inode *inode = file->f_mapping->host; + struct request_queue *q = lo->lo_queue; + + /* + * We use punch hole to reclaim the free space used by the + * image a.k.a. discard. However we do not support discard if + * encryption is enabled, because it may give an attacker + * useful information. + */ + if ((!file->f_op->fallocate) || + lo->lo_encrypt_key_size) { + q->limits.discard_granularity = 0; + q->limits.discard_alignment = 0; + q->limits.max_discard_sectors = 0; + q->limits.discard_zeroes_data = 0; + queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q); + return; + } + + q->limits.discard_granularity = inode->i_sb->s_blocksize; + q->limits.discard_alignment = 0; + q->limits.max_discard_sectors = UINT_MAX >> 9; + q->limits.discard_zeroes_data = 1; + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); +} + +static int loop_set_fd(struct loop_device *lo, fmode_t mode, struct block_device *bdev, unsigned int arg) { struct file *file, *f; @@ -755,7 +848,7 @@ static int loop_set_fd(struct loop_device *lo, struct file *lo_file, while (is_loop_device(f)) { struct loop_device *l; - if (f->f_mapping->host->i_rdev == lo_file->f_mapping->host->i_rdev) + if (f->f_mapping->host->i_bdev == bdev) goto out_putf; l = f->f_mapping->host->i_bdev->bd_disk->private_data; @@ -769,38 +862,23 @@ static int loop_set_fd(struct loop_device *lo, struct file *lo_file, mapping = file->f_mapping; inode = mapping->host; - if (!(file->f_mode & FMODE_WRITE)) - lo_flags |= LO_FLAGS_READ_ONLY; - error = -EINVAL; - if (S_ISREG(inode->i_mode) || S_ISBLK(inode->i_mode)) { - struct address_space_operations *aops = mapping->a_ops; - /* - * If we can't read - sorry. If we only can't write - well, - * it's going to be read-only. - */ - if (!file->f_op->sendfile) - goto out_putf; - if (aops->prepare_write && aops->commit_write) - lo_flags |= LO_FLAGS_USE_AOPS; - if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write) - lo_flags |= LO_FLAGS_READ_ONLY; - - lo_blocksize = inode->i_blksize; - error = 0; - } else { + if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) goto out_putf; - } - size = get_loop_size(lo, file); + if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) || + !file->f_op->write) + lo_flags |= LO_FLAGS_READ_ONLY; - if ((loff_t)(sector_t)size != size) { - error = -EFBIG; + lo_blocksize = S_ISBLK(inode->i_mode) ? + inode->i_bdev->bd_block_size : PAGE_SIZE; + + error = -EFBIG; + size = get_loop_size(lo, file); + if ((loff_t)(sector_t)size != size) goto out_putf; - } - if (!(lo_file->f_mode & FMODE_WRITE)) - lo_flags |= LO_FLAGS_READ_ONLY; + error = 0; set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0); @@ -808,31 +886,57 @@ static int loop_set_fd(struct loop_device *lo, struct file *lo_file, lo->lo_device = bdev; lo->lo_flags = lo_flags; lo->lo_backing_file = file; - lo->transfer = NULL; + 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)); - lo->lo_bio = lo->lo_biotail = NULL; + 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; - lo->lo_queue->unplug_fn = loop_unplug; + if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) + blk_queue_flush(lo->lo_queue, REQ_FLUSH); - set_capacity(disks[lo->lo_number], size); + set_capacity(lo->lo_disk, size); bd_set_size(bdev, size << 9); + loop_sysfs_init(lo); + /* let user-space know about the new size */ + kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); set_blocksize(bdev, lo_blocksize); - kernel_thread(loop_thread, lo, CLONE_KERNEL); - down(&lo->lo_sem); + lo->lo_thread = kthread_create(loop_thread, lo, "loop%d", + lo->lo_number); + if (IS_ERR(lo->lo_thread)) { + error = PTR_ERR(lo->lo_thread); + goto out_clr; + } + lo->lo_state = Lo_bound; + wake_up_process(lo->lo_thread); + if (part_shift) + 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: + loop_sysfs_exit(lo); + lo->lo_thread = NULL; + lo->lo_device = NULL; + lo->lo_backing_file = NULL; + lo->lo_flags = 0; + set_capacity(lo->lo_disk, 0); + invalidate_bdev(bdev); + bd_set_size(bdev, 0); + kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); + mapping_set_gfp_mask(mapping, lo->old_gfp_mask); + lo->lo_state = Lo_unbound; out_putf: fput(file); out: @@ -878,30 +982,43 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer, return err; } -static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev) +static int loop_clr_fd(struct loop_device *lo) { struct file *filp = lo->lo_backing_file; - int gfp = lo->old_gfp_mask; + gfp_t gfp = lo->old_gfp_mask; + struct block_device *bdev = lo->lo_device; 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; spin_lock_irq(&lo->lo_lock); lo->lo_state = Lo_rundown; - lo->lo_pending--; - if (!lo->lo_pending) - up(&lo->lo_bh_mutex); spin_unlock_irq(&lo->lo_lock); - down(&lo->lo_sem); + kthread_stop(lo->lo_thread); + spin_lock_irq(&lo->lo_lock); lo->lo_backing_file = NULL; + spin_unlock_irq(&lo->lo_lock); loop_release_xfer(lo); lo->transfer = NULL; @@ -911,18 +1028,38 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev) lo->lo_offset = 0; lo->lo_sizelimit = 0; lo->lo_encrypt_key_size = 0; - lo->lo_flags = 0; + lo->lo_thread = NULL; 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); - invalidate_bdev(bdev, 0); - set_capacity(disks[lo->lo_number], 0); - bd_set_size(bdev, 0); + if (bdev) { + bdput(bdev); + invalidate_bdev(bdev); + } + set_capacity(lo->lo_disk, 0); + loop_sysfs_exit(lo); + if (bdev) { + bd_set_size(bdev, 0); + /* let user-space know about this change */ + kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); + } 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 (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev) + ioctl_by_bdev(bdev, BLKRRPART, 0); + lo->lo_flags = 0; + if (!part_shift) + lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; + 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; } @@ -931,8 +1068,10 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) { int err; struct loop_func_table *xfer; + kuid_t uid = current_uid(); - if (lo->lo_encrypt_key_size && lo->lo_key_owner != current->uid && + if (lo->lo_encrypt_key_size && + !uid_eq(lo->lo_key_owner, uid) && !capable(CAP_SYS_ADMIN)) return -EPERM; if (lo->lo_state != Lo_bound) @@ -960,12 +1099,11 @@ 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_offset = info->lo_offset; - lo->lo_sizelimit = info->lo_sizelimit; - if (figure_loop_size(lo)) + 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); memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE); @@ -977,13 +1115,24 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) lo->transfer = xfer->transfer; lo->ioctl = xfer->ioctl; + if ((lo->lo_flags & LO_FLAGS_AUTOCLEAR) != + (info->lo_flags & LO_FLAGS_AUTOCLEAR)) + lo->lo_flags ^= LO_FLAGS_AUTOCLEAR; + + if ((info->lo_flags & LO_FLAGS_PARTSCAN) && + !(lo->lo_flags & LO_FLAGS_PARTSCAN)) { + lo->lo_flags |= LO_FLAGS_PARTSCAN; + lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; + ioctl_by_bdev(lo->lo_device, BLKRRPART, 0); + } + lo->lo_encrypt_key_size = info->lo_encrypt_key_size; lo->lo_init[0] = info->lo_init[0]; lo->lo_init[1] = info->lo_init[1]; if (info->lo_encrypt_key_size) { memcpy(lo->lo_encrypt_key, info->lo_encrypt_key, info->lo_encrypt_key_size); - lo->lo_key_owner = current->uid; + lo->lo_key_owner = uid; } return 0; @@ -998,7 +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_vfsmnt, file->f_dentry, &stat); + error = vfs_getattr(&file->f_path, &stat); if (error) return error; memset(info, 0, sizeof(*info)); @@ -1128,76 +1277,289 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { return err; } -static int lo_ioctl(struct inode * inode, struct file * file, +static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev) +{ + if (unlikely(lo->lo_state != Lo_bound)) + return -ENXIO; + + return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit); +} + +static int lo_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { - struct loop_device *lo = inode->i_bdev->bd_disk->private_data; + struct loop_device *lo = bdev->bd_disk->private_data; int err; - down(&lo->lo_ctl_mutex); + mutex_lock_nested(&lo->lo_ctl_mutex, 1); switch (cmd) { case LOOP_SET_FD: - err = loop_set_fd(lo, file, inode->i_bdev, arg); + err = loop_set_fd(lo, mode, bdev, arg); break; case LOOP_CHANGE_FD: - err = loop_change_fd(lo, file, inode->i_bdev, arg); + err = loop_change_fd(lo, bdev, arg); break; case LOOP_CLR_FD: - err = loop_clr_fd(lo, inode->i_bdev); + /* loop_clr_fd would have unlocked lo_ctl_mutex on success */ + err = loop_clr_fd(lo); + if (!err) + goto out_unlocked; break; case LOOP_SET_STATUS: - err = loop_set_status_old(lo, (struct loop_info __user *) arg); + err = -EPERM; + if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) + err = loop_set_status_old(lo, + (struct loop_info __user *)arg); break; case LOOP_GET_STATUS: err = loop_get_status_old(lo, (struct loop_info __user *) arg); break; case LOOP_SET_STATUS64: - err = loop_set_status64(lo, (struct loop_info64 __user *) arg); + err = -EPERM; + if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) + err = loop_set_status64(lo, + (struct loop_info64 __user *) arg); break; 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; } - up(&lo->lo_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); + +out_unlocked: return err; } -static int lo_open(struct inode *inode, struct file *file) +#ifdef CONFIG_COMPAT +struct compat_loop_info { + compat_int_t lo_number; /* ioctl r/o */ + compat_dev_t lo_device; /* ioctl r/o */ + compat_ulong_t lo_inode; /* ioctl r/o */ + compat_dev_t lo_rdevice; /* ioctl r/o */ + compat_int_t lo_offset; + compat_int_t lo_encrypt_type; + compat_int_t lo_encrypt_key_size; /* ioctl w/o */ + compat_int_t lo_flags; /* ioctl r/o */ + char lo_name[LO_NAME_SIZE]; + unsigned char lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */ + compat_ulong_t lo_init[2]; + char reserved[4]; +}; + +/* + * Transfer 32-bit compatibility structure in userspace to 64-bit loop info + * - noinlined to reduce stack space usage in main part of driver + */ +static noinline int +loop_info64_from_compat(const struct compat_loop_info __user *arg, + struct loop_info64 *info64) { - struct loop_device *lo = inode->i_bdev->bd_disk->private_data; + struct compat_loop_info info; - down(&lo->lo_ctl_mutex); - lo->lo_refcnt++; - up(&lo->lo_ctl_mutex); + if (copy_from_user(&info, arg, sizeof(info))) + return -EFAULT; + memset(info64, 0, sizeof(*info64)); + info64->lo_number = info.lo_number; + info64->lo_device = info.lo_device; + info64->lo_inode = info.lo_inode; + info64->lo_rdevice = info.lo_rdevice; + info64->lo_offset = info.lo_offset; + info64->lo_sizelimit = 0; + info64->lo_encrypt_type = info.lo_encrypt_type; + info64->lo_encrypt_key_size = info.lo_encrypt_key_size; + info64->lo_flags = info.lo_flags; + info64->lo_init[0] = info.lo_init[0]; + info64->lo_init[1] = info.lo_init[1]; + if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI) + memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE); + else + memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE); + memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE); return 0; } -static int lo_release(struct inode *inode, struct file *file) +/* + * Transfer 64-bit loop info to 32-bit compatibility structure in userspace + * - noinlined to reduce stack space usage in main part of driver + */ +static noinline int +loop_info64_to_compat(const struct loop_info64 *info64, + struct compat_loop_info __user *arg) { - struct loop_device *lo = inode->i_bdev->bd_disk->private_data; + struct compat_loop_info info; + + memset(&info, 0, sizeof(info)); + info.lo_number = info64->lo_number; + info.lo_device = info64->lo_device; + info.lo_inode = info64->lo_inode; + info.lo_rdevice = info64->lo_rdevice; + info.lo_offset = info64->lo_offset; + info.lo_encrypt_type = info64->lo_encrypt_type; + info.lo_encrypt_key_size = info64->lo_encrypt_key_size; + info.lo_flags = info64->lo_flags; + info.lo_init[0] = info64->lo_init[0]; + info.lo_init[1] = info64->lo_init[1]; + if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI) + memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE); + else + memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE); + memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE); - down(&lo->lo_ctl_mutex); - --lo->lo_refcnt; - up(&lo->lo_ctl_mutex); + /* error in case values were truncated */ + if (info.lo_device != info64->lo_device || + info.lo_rdevice != info64->lo_rdevice || + info.lo_inode != info64->lo_inode || + info.lo_offset != info64->lo_offset || + info.lo_init[0] != info64->lo_init[0] || + info.lo_init[1] != info64->lo_init[1]) + return -EOVERFLOW; + if (copy_to_user(arg, &info, sizeof(info))) + return -EFAULT; return 0; } -static struct block_device_operations lo_fops = { +static int +loop_set_status_compat(struct loop_device *lo, + const struct compat_loop_info __user *arg) +{ + struct loop_info64 info64; + int ret; + + ret = loop_info64_from_compat(arg, &info64); + if (ret < 0) + return ret; + return loop_set_status(lo, &info64); +} + +static int +loop_get_status_compat(struct loop_device *lo, + struct compat_loop_info __user *arg) +{ + struct loop_info64 info64; + int err = 0; + + if (!arg) + err = -EINVAL; + if (!err) + err = loop_get_status(lo, &info64); + if (!err) + err = loop_info64_to_compat(&info64, arg); + return err; +} + +static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + struct loop_device *lo = bdev->bd_disk->private_data; + int err; + + switch(cmd) { + case LOOP_SET_STATUS: + mutex_lock(&lo->lo_ctl_mutex); + err = loop_set_status_compat( + lo, (const struct compat_loop_info __user *) arg); + mutex_unlock(&lo->lo_ctl_mutex); + break; + case LOOP_GET_STATUS: + mutex_lock(&lo->lo_ctl_mutex); + err = loop_get_status_compat( + 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: + arg = (unsigned long) compat_ptr(arg); + case LOOP_SET_FD: + case LOOP_CHANGE_FD: + err = lo_ioctl(bdev, mode, cmd, arg); + break; + default: + err = -ENOIOCTLCMD; + break; + } + return err; +} +#endif + +static int lo_open(struct block_device *bdev, fmode_t mode) +{ + struct loop_device *lo; + int err = 0; + + mutex_lock(&loop_index_mutex); + lo = bdev->bd_disk->private_data; + if (!lo) { + err = -ENXIO; + goto out; + } + + mutex_lock(&lo->lo_ctl_mutex); + lo->lo_refcnt++; + mutex_unlock(&lo->lo_ctl_mutex); +out: + mutex_unlock(&loop_index_mutex); + return err; +} + +static void lo_release(struct gendisk *disk, fmode_t mode) +{ + struct loop_device *lo = disk->private_data; + int err; + + mutex_lock(&lo->lo_ctl_mutex); + + if (--lo->lo_refcnt) + goto out; + + if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { + /* + * In autoclear mode, stop the loop thread + * and remove configuration after last close. + */ + err = loop_clr_fd(lo); + if (!err) + return; + } else { + /* + * Otherwise keep thread (if running) and config, + * but flush possible ongoing bios in thread. + */ + loop_flush(lo); + } + +out: + mutex_unlock(&lo->lo_ctl_mutex); +} + +static const struct block_device_operations lo_fops = { .owner = THIS_MODULE, .open = lo_open, .release = lo_release, .ioctl = lo_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = lo_compat_ioctl, +#endif }; /* * And now the modules code and kernel interface. */ -module_param(max_loop, int, 0); -MODULE_PARM_DESC(max_loop, "Maximum number of loop devices (1-256)"); +static int max_loop; +module_param(max_loop, int, S_IRUGO); +MODULE_PARM_DESC(max_loop, "Maximum number of loop devices"); +module_param(max_part, int, S_IRUGO); +MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device"); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR); @@ -1211,122 +1573,346 @@ int loop_register_transfer(struct loop_func_table *funcs) return 0; } +static int unregister_transfer_cb(int id, void *ptr, void *data) +{ + struct loop_device *lo = ptr; + struct loop_func_table *xfer = data; + + mutex_lock(&lo->lo_ctl_mutex); + if (lo->lo_encryption == xfer) + loop_release_xfer(lo); + mutex_unlock(&lo->lo_ctl_mutex); + return 0; +} + int loop_unregister_transfer(int number) { unsigned int n = number; - struct loop_device *lo; struct loop_func_table *xfer; if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL) return -EINVAL; xfer_funcs[n] = NULL; + idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer); + return 0; +} - for (lo = &loop_dev[0]; lo < &loop_dev[max_loop]; lo++) { - down(&lo->lo_ctl_mutex); +EXPORT_SYMBOL(loop_register_transfer); +EXPORT_SYMBOL(loop_unregister_transfer); - if (lo->lo_encryption == xfer) - loop_release_xfer(lo); +static int loop_add(struct loop_device **l, int i) +{ + struct loop_device *lo; + struct gendisk *disk; + int err; + + err = -ENOMEM; + lo = kzalloc(sizeof(*lo), GFP_KERNEL); + if (!lo) + goto out; - up(&lo->lo_ctl_mutex); + lo->lo_state = Lo_unbound; + + /* allocate id, if @id >= 0, we're requesting that specific id */ + if (i >= 0) { + err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL); + if (err == -ENOSPC) + err = -EEXIST; + } else { + 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_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) + goto out_free_queue; + + /* + * Disable partition scanning by default. The in-kernel partition + * scanning can be requested individually per-device during its + * setup. Userspace can always add and remove partitions from all + * devices. The needed partition minors are allocated from the + * extended minor space, the main loop device numbers will continue + * to match the loop minors, regardless of the number of partitions + * used. + * + * If max_part is given, partition scanning is globally enabled for + * all loop devices. The minors for the main loop devices will be + * multiples of max_part. + * + * Note: Global-for-all-devices, set-only-at-init, read-only module + * parameteters like 'max_loop' and 'max_part' make things needlessly + * complicated, are too static, inflexible and may surprise + * userspace tools. Parameters like this in general should be avoided. + */ + if (!part_shift) + disk->flags |= GENHD_FL_NO_PART_SCAN; + disk->flags |= GENHD_FL_EXT_DEVT; + mutex_init(&lo->lo_ctl_mutex); + 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; + disk->fops = &lo_fops; + disk->private_data = lo; + disk->queue = lo->lo_queue; + sprintf(disk->disk_name, "loop%d", i); + add_disk(disk); + *l = lo; + return lo->lo_number; + +out_free_queue: + blk_cleanup_queue(lo->lo_queue); +out_free_idr: + idr_remove(&loop_index_idr, i); +out_free_dev: + kfree(lo); +out: + return err; +} + +static void loop_remove(struct loop_device *lo) +{ + del_gendisk(lo->lo_disk); + blk_cleanup_queue(lo->lo_queue); + put_disk(lo->lo_disk); + kfree(lo); +} + +static int find_free_cb(int id, void *ptr, void *data) +{ + struct loop_device *lo = ptr; + struct loop_device **l = data; + + if (lo->lo_state == Lo_unbound) { + *l = lo; + return 1; + } return 0; } -EXPORT_SYMBOL(loop_register_transfer); -EXPORT_SYMBOL(loop_unregister_transfer); +static int loop_lookup(struct loop_device **l, int i) +{ + struct loop_device *lo; + int ret = -ENODEV; -static int __init loop_init(void) + if (i < 0) { + int err; + + err = idr_for_each(&loop_index_idr, &find_free_cb, &lo); + if (err == 1) { + *l = lo; + ret = lo->lo_number; + } + goto out; + } + + /* lookup and return a specific i */ + lo = idr_find(&loop_index_idr, i); + if (lo) { + *l = lo; + ret = lo->lo_number; + } +out: + return ret; +} + +static struct kobject *loop_probe(dev_t dev, int *part, void *data) +{ + struct loop_device *lo; + struct kobject *kobj; + int err; + + mutex_lock(&loop_index_mutex); + err = loop_lookup(&lo, MINOR(dev) >> part_shift); + if (err < 0) + err = loop_add(&lo, MINOR(dev) >> part_shift); + if (err < 0) + kobj = NULL; + else + kobj = get_disk(lo->lo_disk); + mutex_unlock(&loop_index_mutex); + + *part = 0; + return kobj; +} + +static long loop_control_ioctl(struct file *file, unsigned int cmd, + unsigned long parm) { - int i; + struct loop_device *lo; + int ret = -ENOSYS; - if (max_loop < 1 || max_loop > 256) { - printk(KERN_WARNING "loop: invalid max_loop (must be between" - " 1 and 256), using default (8)\n"); - max_loop = 8; + mutex_lock(&loop_index_mutex); + switch (cmd) { + case LOOP_CTL_ADD: + ret = loop_lookup(&lo, parm); + if (ret >= 0) { + ret = -EEXIST; + break; + } + ret = loop_add(&lo, parm); + break; + case LOOP_CTL_REMOVE: + ret = loop_lookup(&lo, parm); + if (ret < 0) + break; + mutex_lock(&lo->lo_ctl_mutex); + if (lo->lo_state != Lo_unbound) { + ret = -EBUSY; + mutex_unlock(&lo->lo_ctl_mutex); + break; + } + if (lo->lo_refcnt > 0) { + ret = -EBUSY; + mutex_unlock(&lo->lo_ctl_mutex); + break; + } + lo->lo_disk->private_data = NULL; + mutex_unlock(&lo->lo_ctl_mutex); + idr_remove(&loop_index_idr, lo->lo_number); + loop_remove(lo); + break; + case LOOP_CTL_GET_FREE: + ret = loop_lookup(&lo, -1); + if (ret >= 0) + break; + ret = loop_add(&lo, -1); } + mutex_unlock(&loop_index_mutex); + + return ret; +} + +static const struct file_operations loop_ctl_fops = { + .open = nonseekable_open, + .unlocked_ioctl = loop_control_ioctl, + .compat_ioctl = loop_control_ioctl, + .owner = THIS_MODULE, + .llseek = noop_llseek, +}; + +static struct miscdevice loop_misc = { + .minor = LOOP_CTRL_MINOR, + .name = "loop-control", + .fops = &loop_ctl_fops, +}; + +MODULE_ALIAS_MISCDEV(LOOP_CTRL_MINOR); +MODULE_ALIAS("devname:loop-control"); + +static int __init loop_init(void) +{ + int i, nr; + unsigned long range; + struct loop_device *lo; + int err; + + err = misc_register(&loop_misc); + if (err < 0) + return err; - if (register_blkdev(LOOP_MAJOR, "loop")) - return -EIO; + part_shift = 0; + if (max_part > 0) { + part_shift = fls(max_part); - loop_dev = kmalloc(max_loop * sizeof(struct loop_device), GFP_KERNEL); - if (!loop_dev) - goto out_mem1; - memset(loop_dev, 0, max_loop * sizeof(struct loop_device)); + /* + * Adjust max_part according to part_shift as it is exported + * to user space so that user can decide correct minor number + * if [s]he want to create more devices. + * + * Note that -1 is required because partition 0 is reserved + * for the whole disk. + */ + max_part = (1UL << part_shift) - 1; + } - disks = kmalloc(max_loop * sizeof(struct gendisk *), GFP_KERNEL); - if (!disks) - goto out_mem2; + if ((1UL << part_shift) > DISK_MAX_PARTS) { + err = -EINVAL; + goto misc_out; + } - for (i = 0; i < max_loop; i++) { - disks[i] = alloc_disk(1); - if (!disks[i]) - goto out_mem3; + if (max_loop > 1UL << (MINORBITS - part_shift)) { + err = -EINVAL; + goto misc_out; } - devfs_mk_dir("loop"); - - for (i = 0; i < max_loop; i++) { - struct loop_device *lo = &loop_dev[i]; - struct gendisk *disk = disks[i]; - - memset(lo, 0, sizeof(*lo)); - lo->lo_queue = blk_alloc_queue(GFP_KERNEL); - if (!lo->lo_queue) - goto out_mem4; - init_MUTEX(&lo->lo_ctl_mutex); - init_MUTEX_LOCKED(&lo->lo_sem); - init_MUTEX_LOCKED(&lo->lo_bh_mutex); - lo->lo_number = i; - spin_lock_init(&lo->lo_lock); - disk->major = LOOP_MAJOR; - disk->first_minor = i; - disk->fops = &lo_fops; - sprintf(disk->disk_name, "loop%d", i); - sprintf(disk->devfs_name, "loop/%d", i); - disk->private_data = lo; - disk->queue = lo->lo_queue; + /* + * If max_loop is specified, create that many devices upfront. + * This also becomes a hard limit. If max_loop is not specified, + * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module + * init time. Loop devices can be requested on-demand with the + * /dev/loop-control interface, or be instantiated by accessing + * a 'dead' device node. + */ + if (max_loop) { + nr = max_loop; + range = max_loop << part_shift; + } else { + nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT; + range = 1UL << MINORBITS; } - /* We cannot fail after we call this, so another loop!*/ - for (i = 0; i < max_loop; i++) - add_disk(disks[i]); - printk(KERN_INFO "loop: loaded (max %d devices)\n", max_loop); + 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); + + /* pre-create number of devices given by config or max_loop */ + mutex_lock(&loop_index_mutex); + for (i = 0; i < nr; i++) + loop_add(&lo, i); + mutex_unlock(&loop_index_mutex); + + printk(KERN_INFO "loop: module loaded\n"); return 0; -out_mem4: - while (i--) - blk_put_queue(loop_dev[i].lo_queue); - devfs_remove("loop"); - i = max_loop; -out_mem3: - while (i--) - put_disk(disks[i]); - kfree(disks); -out_mem2: - kfree(loop_dev); -out_mem1: - unregister_blkdev(LOOP_MAJOR, "loop"); - printk(KERN_ERR "loop: ran out of memory\n"); - return -ENOMEM; +misc_out: + misc_deregister(&loop_misc); + return err; } -static void loop_exit(void) +static int loop_exit_cb(int id, void *ptr, void *data) { - int i; + struct loop_device *lo = ptr; - for (i = 0; i < max_loop; i++) { - del_gendisk(disks[i]); - blk_put_queue(loop_dev[i].lo_queue); - put_disk(disks[i]); - } - devfs_remove("loop"); - if (unregister_blkdev(LOOP_MAJOR, "loop")) - printk(KERN_WARNING "loop: cannot unregister blkdev\n"); + loop_remove(lo); + return 0; +} + +static void __exit loop_exit(void) +{ + unsigned long range; + + range = max_loop ? max_loop << part_shift : 1UL << MINORBITS; + + idr_for_each(&loop_index_idr, &loop_exit_cb, NULL); + idr_destroy(&loop_index_idr); + + blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range); + unregister_blkdev(LOOP_MAJOR, "loop"); - kfree(disks); - kfree(loop_dev); + misc_deregister(&loop_misc); } module_init(loop_init); |