From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Rothwell Subject: linux-next: manual merge of the block tree with the tree Date: Fri, 1 Nov 2013 14:20:26 +1100 Message-ID: <20131101142026.10390b6e3f70de348770c137@canb.auug.org.au> Mime-Version: 1.0 Content-Type: multipart/signed; protocol="application/pgp-signature"; micalg="PGP-SHA256"; boundary="Signature=_Fri__1_Nov_2013_14_20_26_+1100_zy10_5zZl32k4hMP" Return-path: Sender: linux-kernel-owner@vger.kernel.org To: Jens Axboe Cc: linux-next@vger.kernel.org, linux-kernel@vger.kernel.org, Zach Brown , Dave Kleikamp , Kent Overstreet List-Id: linux-next.vger.kernel.org --Signature=_Fri__1_Nov_2013_14_20_26_+1100_zy10_5zZl32k4hMP Content-Type: multipart/mixed; boundary="Multipart=_Fri__1_Nov_2013_14_20_26_+1100_F6BQQ4h0ke/rPdxm" --Multipart=_Fri__1_Nov_2013_14_20_26_+1100_F6BQQ4h0ke/rPdxm Content-Type: text/plain; charset=US-ASCII Content-Disposition: inline Content-Transfer-Encoding: quoted-printable Hi Jens, Today's linux-next merge of the block tree got a conflict in drivers/block/loop.c between commit 2486740b52fd ("loop: use aio to perform io on the underlying file") from the aio-direct tree and commit ed2d2f9a8265 ("block: Abstract out bvec iterator") from the block tree. I fixed it up (I think - see below - I have also attached the final resulting file) and can carry the fix as necessary (no action is required). --=20 Cheers, Stephen Rothwell sfr@canb.auug.org.au diff --cc drivers/block/loop.c index e5647690a751,33fde3a39759..000000000000 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@@ -458,36 -416,53 +459,36 @@@ static int do_bio_filebacked(struct loo loff_t pos; int ret; =20 - pos =3D ((loff_t) bio->bi_sector << 9) + lo->lo_offset; + pos =3D ((loff_t) bio->bi_iter.bi_sector << 9) + lo->lo_offset; =20 if (bio_rw(bio) =3D=3D WRITE) { - struct file *file =3D lo->lo_backing_file; + ret =3D lo_send(lo, bio, pos); + } else + ret =3D lo_receive(lo, bio, lo->lo_blocksize, pos); =20 - if (bio->bi_rw & REQ_FLUSH) { - ret =3D vfs_fsync(file, 0); - if (unlikely(ret && ret !=3D -EINVAL)) { - ret =3D -EIO; - goto out; - } - } + return ret; +} =20 - /* - * 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 =3D lo->lo_backing_file; - int mode =3D FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE; - - if ((!file->f_op->fallocate) || - lo->lo_encrypt_key_size) { - ret =3D -EOPNOTSUPP; - goto out; - } - ret =3D file->f_op->fallocate(file, mode, pos, - bio->bi_iter.bi_size); - if (unlikely(ret && ret !=3D -EINVAL && - ret !=3D -EOPNOTSUPP)) - ret =3D -EIO; - goto out; - } +static int lo_discard(struct loop_device *lo, struct bio *bio) +{ + struct file *file =3D lo->lo_backing_file; + int mode =3D FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE; + loff_t pos =3D ((loff_t) bio->bi_sector << 9) + lo->lo_offset; + int ret; =20 - ret =3D lo_send(lo, bio, pos); + /* + * 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. + */ =20 - if ((bio->bi_rw & REQ_FUA) && !ret) { - ret =3D vfs_fsync(file, 0); - if (unlikely(ret && ret !=3D -EINVAL)) - ret =3D -EIO; - } - } else - ret =3D lo_receive(lo, bio, lo->lo_blocksize, pos); + if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) + return -EOPNOTSUPP; =20 -out: + ret =3D file->f_op->fallocate(file, mode, pos, bio->bi_size); + if (unlikely(ret && ret !=3D -EINVAL && ret !=3D -EOPNOTSUPP)) + ret =3D -EIO; return ret; } =20 --Multipart=_Fri__1_Nov_2013_14_20_26_+1100_F6BQQ4h0ke/rPdxm Content-Type: text/x-csrc; name="loop.c" Content-Disposition: attachment; filename="loop.c" Content-Transfer-Encoding: quoted-printable /* * linux/drivers/block/loop.c * * Written by Theodore Ts'o, 3/29/93 * * Copyright 1993 by Theodore Ts'o. Redistribution of this file is * permitted under the GNU General Public License. * * DES encryption plus some minor changes by Werner Almesberger, 30-MAY-1993 * more DES encryption plus IDEA encryption by Nicholas J. Leon, June 20, 1= 996 * * Modularized and updated for 1.1.16 kernel - Mitch Dsouza 28th May 1994 * Adapted for 1.3.59 kernel - Andries Brouwer, 1 Feb 1996 * * Fixed do_loop_request() re-entrancy - Vincent.Renardias@waw.com Mar 20, = 1997 * * Added devfs support - Richard Gooch 16-Jan-1998 * * Handle sparse backing files correctly - Kenn Humborg, Jun 28, 1998 * * Loadable modules and other fixes by AK, 1998 * * Make real block number available to downstream transfer functions, enabl= es * CBC (and relatives) mode encryption requiring unique IVs per data block. * Reed H. Petty, rhp@draper.net * * Maximum number of loop devices now dynamic via max_loop module parameter. * Russell Kroll 19990701 * * Maximum number of loop devices when compiled-in now selectable by passing * max_loop=3D<1-255> to the kernel on boot. * Erik I. Bols=C3=B8, , 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 * Al Viro too. * Jens Axboe , Nov 2000 * * Support up to 256 loop devices * Heinz Mauelshagen , Feb 2002 * * Support for falling back on the write file operation when the address sp= ace * operations write_begin is not available on the backing filesystem. * Anton Altaparmakov, 16 Feb 2005 * * Still To Fix: * - Advisory locking is ignored here. * - Should use an own CAP_* category instead of CAP_SYS_ADMIN * */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "loop.h" #include static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_index_mutex); static int max_part; static int part_shift; /* * Transfer functions */ static int transfer_none(struct loop_device *lo, int cmd, struct page *raw_page, unsigned raw_off, struct page *loop_page, unsigned loop_off, int size, sector_t real_block) { char *raw_buf =3D kmap_atomic(raw_page) + raw_off; char *loop_buf =3D kmap_atomic(loop_page) + loop_off; if (cmd =3D=3D READ) memcpy(loop_buf, raw_buf, size); else memcpy(raw_buf, loop_buf, size); kunmap_atomic(loop_buf); kunmap_atomic(raw_buf); cond_resched(); return 0; } static int transfer_xor(struct loop_device *lo, int cmd, struct page *raw_page, unsigned raw_off, struct page *loop_page, unsigned loop_off, int size, sector_t real_block) { char *raw_buf =3D kmap_atomic(raw_page) + raw_off; char *loop_buf =3D kmap_atomic(loop_page) + loop_off; char *in, *out, *key; int i, keysize; if (cmd =3D=3D READ) { in =3D raw_buf; out =3D loop_buf; } else { in =3D loop_buf; out =3D raw_buf; } key =3D lo->lo_encrypt_key; keysize =3D lo->lo_encrypt_key_size; for (i =3D 0; i < size; i++) *out++ =3D *in++ ^ key[(i & 511) % keysize]; kunmap_atomic(loop_buf); kunmap_atomic(raw_buf); cond_resched(); return 0; } static int xor_init(struct loop_device *lo, const struct loop_info64 *info) { if (unlikely(info->lo_encrypt_key_size <=3D 0)) return -EINVAL; return 0; } static struct loop_func_table none_funcs =3D { .number =3D LO_CRYPT_NONE, .transfer =3D transfer_none, }; =09 static struct loop_func_table xor_funcs =3D { .number =3D LO_CRYPT_XOR, .transfer =3D transfer_xor, .init =3D xor_init }; =09 /* xfer_funcs[0] is special - its release function is never called */ static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] =3D { &none_funcs, &xor_funcs }; static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file) { loff_t loopsize; /* Compute loopsize in bytes */ loopsize =3D i_size_read(file->f_mapping->host); if (offset > 0) loopsize -=3D offset; /* offset is beyond i_size, weird but possible */ if (loopsize < 0) return 0; if (sizelimit > 0 && sizelimit < loopsize) loopsize =3D 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. */ 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, loff_t offset, loff_t sizelimit) { loff_t size =3D get_size(offset, sizelimit, lo->lo_backing_file); sector_t x =3D (sector_t)size; struct block_device *bdev =3D lo->lo_device; if (unlikely((loff_t)x !=3D size)) return -EFBIG; if (lo->lo_offset !=3D offset) lo->lo_offset =3D offset; if (lo->lo_sizelimit !=3D sizelimit) lo->lo_sizelimit =3D 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 lo_do_transfer(struct loop_device *lo, int cmd, struct page *rpage, unsigned roffs, struct page *lpage, unsigned loffs, int size, sector_t rblock) { if (unlikely(!lo->transfer)) return 0; return lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock); } #ifdef CONFIG_AIO static void lo_rw_aio_complete(u64 data, long res) { struct bio *bio =3D (struct bio *)(uintptr_t)data; if (res > 0) res =3D 0; else if (res < 0) res =3D -EIO; bio_endio(bio, res); } static int lo_rw_aio(struct loop_device *lo, struct bio *bio) { struct file *file =3D lo->lo_backing_file; struct kiocb *iocb; unsigned int op; struct iov_iter iter; struct bio_vec *bvec; size_t nr_segs; loff_t pos =3D ((loff_t) bio->bi_sector << 9) + lo->lo_offset; iocb =3D aio_kernel_alloc(GFP_NOIO); if (!iocb) return -ENOMEM; if (bio_rw(bio) & WRITE) op =3D IOCB_CMD_WRITE_ITER; else op =3D IOCB_CMD_READ_ITER; bvec =3D bio_iovec_idx(bio, bio->bi_idx); nr_segs =3D bio_segments(bio); iov_iter_init_bvec(&iter, bvec, nr_segs, bvec_length(bvec, nr_segs), 0); aio_kernel_init_rw(iocb, file, iov_iter_count(&iter), pos); aio_kernel_init_callback(iocb, lo_rw_aio_complete, (u64)(uintptr_t)bio); return aio_kernel_submit(iocb, op, &iter); } #endif /* CONFIG_AIO */ /** * __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 int __do_lo_send_write(struct file *file, u8 *buf, const int len, loff_t pos) { ssize_t bw; mm_segment_t old_fs =3D get_fs(); file_start_write(file); set_fs(get_ds()); bw =3D file->f_op->write(file, buf, len, &pos); set_fs(old_fs); file_end_write(file); if (likely(bw =3D=3D len)) return 0; printk(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n", (unsigned long long)pos, len); if (bw >=3D 0) bw =3D -EIO; return bw; } /** * do_lo_send_direct_write - helper for writing data to a loop device * * 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, loff_t pos, struct page *page) { ssize_t bw =3D __do_lo_send_write(lo->lo_backing_file, kmap(bvec->bv_page) + bvec->bv_offset, bvec->bv_len, pos); kunmap(bvec->bv_page); cond_resched(); return bw; } /** * do_lo_send_write - helper for writing data to a loop device * * 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, loff_t pos, struct page *page) { int ret =3D 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, page_address(page), bvec->bv_len, pos); printk(KERN_ERR "loop: Transfer error at byte offset %llu, " "length %i.\n", (unsigned long long)pos, bvec->bv_len); if (ret > 0) ret =3D -EIO; return ret; } 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 bvec_iter iter; struct page *page =3D NULL; int ret =3D 0; if (lo->transfer !=3D transfer_none) { page =3D alloc_page(GFP_NOIO | __GFP_HIGHMEM); if (unlikely(!page)) goto fail; kmap(page); do_lo_send =3D do_lo_send_write; } else { do_lo_send =3D do_lo_send_direct_write; } bio_for_each_segment(bvec, bio, iter) { ret =3D do_lo_send(lo, &bvec, pos, page); if (ret < 0) break; pos +=3D bvec.bv_len; } if (page) { kunmap(page); __free_page(page); } out: return ret; fail: printk(KERN_ERR "loop: Failed to allocate temporary page for write.\n"); ret =3D -ENOMEM; goto out; } struct lo_read_data { struct loop_device *lo; struct page *page; unsigned offset; int bsize; }; static int lo_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { struct lo_read_data *p =3D sd->u.data; struct loop_device *lo =3D p->lo; struct page *page =3D buf->page; sector_t IV; int size; IV =3D ((sector_t) page->index << (PAGE_CACHE_SHIFT - 9)) + (buf->offset >> 9); size =3D sd->len; if (size > p->bsize) size =3D 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", page->index); size =3D -EINVAL; } flush_dcache_page(p->page); if (size > 0) p->offset +=3D 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; ssize_t retval; cookie.lo =3D lo; cookie.page =3D bvec->bv_page; cookie.offset =3D bvec->bv_offset; cookie.bsize =3D bsize; sd.len =3D 0; sd.total_len =3D bvec->bv_len; sd.flags =3D 0; sd.pos =3D pos; sd.u.data =3D &cookie; file =3D lo->lo_backing_file; retval =3D 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; struct bvec_iter iter; ssize_t s; bio_for_each_segment(bvec, bio, iter) { s =3D do_lo_receive(lo, &bvec, bsize, pos); if (s < 0) return s; if (s !=3D bvec.bv_len) { zero_fill_bio(bio); break; } pos +=3D bvec.bv_len; } return 0; } static int do_bio_filebacked(struct loop_device *lo, struct bio *bio) { loff_t pos; int ret; pos =3D ((loff_t) bio->bi_iter.bi_sector << 9) + lo->lo_offset; if (bio_rw(bio) =3D=3D WRITE) { ret =3D lo_send(lo, bio, pos); } else ret =3D lo_receive(lo, bio, lo->lo_blocksize, pos); return ret; } static int lo_discard(struct loop_device *lo, struct bio *bio) { struct file *file =3D lo->lo_backing_file; int mode =3D FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE; loff_t pos =3D ((loff_t) bio->bi_sector << 9) + lo->lo_offset; int ret; /* * 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) return -EOPNOTSUPP; ret =3D file->f_op->fallocate(file, mode, pos, bio->bi_size); if (unlikely(ret && ret !=3D -EINVAL && ret !=3D -EOPNOTSUPP)) ret =3D -EIO; return ret; } /* * Add bio to back of pending list */ static void loop_add_bio(struct loop_device *lo, struct bio *bio) { lo->lo_bio_count++; bio_list_add(&lo->lo_bio_list, bio); } /* * Grab first pending buffer */ static struct bio *loop_get_bio(struct loop_device *lo) { lo->lo_bio_count--; return bio_list_pop(&lo->lo_bio_list); } static void loop_make_request(struct request_queue *q, struct bio *old_bio) { struct loop_device *lo =3D q->queuedata; int rw =3D bio_rw(old_bio); if (rw =3D=3D READA) rw =3D READ; BUG_ON(!lo || (rw !=3D READ && rw !=3D WRITE)); spin_lock_irq(&lo->lo_lock); if (lo->lo_state !=3D Lo_bound) goto out; if (unlikely(rw =3D=3D WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY))) goto out; if (lo->lo_bio_count >=3D 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); return; out: spin_unlock_irq(&lo->lo_lock); bio_io_error(old_bio); } struct switch_request { struct file *file; struct completion wait; }; static void do_loop_switch(struct loop_device *, struct switch_request *); static inline void loop_handle_bio(struct loop_device *lo, struct bio *bio) { if (unlikely(!bio->bi_bdev)) { do_loop_switch(lo, bio->bi_private); bio_put(bio); } else { int ret; if (bio_rw(bio) =3D=3D WRITE) { if (bio->bi_rw & REQ_FLUSH) { ret =3D vfs_fsync(lo->lo_backing_file, 1); if (unlikely(ret && ret !=3D -EINVAL)) goto out; } if (bio->bi_rw & REQ_DISCARD) { ret =3D lo_discard(lo, bio); goto out; } } #ifdef CONFIG_AIO if (lo->lo_flags & LO_FLAGS_USE_AIO && lo->transfer =3D=3D transfer_none) { ret =3D lo_rw_aio(lo, bio); if (ret =3D=3D 0) return; } else #endif ret =3D do_bio_filebacked(lo, bio); if ((bio_rw(bio) =3D=3D WRITE) && bio->bi_rw & REQ_FUA && !ret) { ret =3D vfs_fsync(lo->lo_backing_file, 0); if (unlikely(ret && ret !=3D -EINVAL)) ret =3D -EIO; } out: bio_endio(bio, ret); } } /* * worker thread that handles reads/writes to file backed loop devices, * 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 =3D data; struct bio *bio; /* * In cases where the underlying filesystem calls balance_dirty_pages() * we want less throttling to avoid lock ups trying to write dirty * pages through the loop device */ current->flags |=3D PF_LESS_THROTTLE; set_user_nice(current, -20); while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) { wait_event_interruptible(lo->lo_event, !bio_list_empty(&lo->lo_bio_list) || kthread_should_stop()); if (bio_list_empty(&lo->lo_bio_list)) continue; spin_lock_irq(&lo->lo_lock); bio =3D 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); loop_handle_bio(lo, bio); } return 0; } /* * loop_switch performs the hard work of switching a backing store. * First it needs to flush existing IO, it does this by sending a magic * BIO down the pipe. The completion of this BIO does the actual switch. */ static int loop_switch(struct loop_device *lo, struct file *file) { struct switch_request w; struct bio *bio =3D bio_alloc(GFP_KERNEL, 0); if (!bio) return -ENOMEM; init_completion(&w.wait); w.file =3D file; bio->bi_private =3D &w; bio->bi_bdev =3D NULL; loop_make_request(lo->lo_queue, bio); wait_for_completion(&w.wait); return 0; } /* * 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 =3D p->file; struct file *old_file =3D lo->lo_backing_file; struct address_space *mapping; /* if no new file, only flush of queued bios requested */ if (!file) goto out; mapping =3D file->f_mapping; mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); lo->lo_backing_file =3D file; lo->lo_blocksize =3D S_ISBLK(mapping->host->i_mode) ? mapping->host->i_bdev->bd_block_size : PAGE_SIZE; lo->old_gfp_mask =3D mapping_gfp_mask(mapping); mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); out: complete(&p->wait); } /* * loop_change_fd switched the backing store of a loopback device to * a new file. This is useful for operating system installers to free up * the original file and in High Availability environments to switch to * an alternative location for the content in case of server meltdown. * 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 block_device *bdev, unsigned int arg) { struct file *file, *old_file; struct inode *inode; int error; error =3D -ENXIO; if (lo->lo_state !=3D Lo_bound) goto out; /* the loop device has to be read-only */ error =3D -EINVAL; if (!(lo->lo_flags & LO_FLAGS_READ_ONLY)) goto out; error =3D -EBADF; file =3D fget(arg); if (!file) goto out; inode =3D file->f_mapping->host; old_file =3D lo->lo_backing_file; error =3D -EINVAL; if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) goto out_putf; /* size of the new backing store needs to be the same */ if (get_loop_size(lo, file) !=3D get_loop_size(lo, old_file)) goto out_putf; /* and ... switch */ error =3D loop_switch(lo, file); if (error) goto out_putf; fput(old_file); if (lo->lo_flags & LO_FLAGS_PARTSCAN) ioctl_by_bdev(bdev, BLKRRPART, 0); return 0; out_putf: fput(file); out: return error; } static inline int is_loop_device(struct file *file) { struct inode *i =3D file->f_mapping->host; return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) =3D=3D LOOP_MAJOR; } /* loop sysfs attributes */ static ssize_t loop_attr_show(struct device *dev, char *page, ssize_t (*callback)(struct loop_device *, char *)) { struct gendisk *disk =3D dev_to_disk(dev); struct loop_device *lo =3D 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 =3D \ __ATTR(_name, S_IRUGO, loop_attr_do_show_##_name, NULL); static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *bu= f) { ssize_t ret; char *p =3D NULL; spin_lock_irq(&lo->lo_lock); if (lo->lo_backing_file) p =3D 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 =3D PTR_ERR(p); else { ret =3D strlen(p); memmove(buf, p, ret); buf[ret++] =3D '\n'; buf[ret] =3D 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 =3D (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 =3D (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[] =3D { &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 =3D { .name =3D "loop", .attrs=3D 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 =3D lo->lo_backing_file; struct inode *inode =3D file->f_mapping->host; struct request_queue *q =3D lo->lo_queue; /* * We use punch hole to reclaim the free space used by the * image a.k.a. discard. However we do 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 =3D 0; q->limits.discard_alignment =3D 0; q->limits.max_discard_sectors =3D 0; q->limits.discard_zeroes_data =3D 0; queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q); return; } q->limits.discard_granularity =3D inode->i_sb->s_blocksize; q->limits.discard_alignment =3D 0; q->limits.max_discard_sectors =3D UINT_MAX >> 9; q->limits.discard_zeroes_data =3D 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; struct inode *inode; struct address_space *mapping; unsigned lo_blocksize; int lo_flags =3D 0; int error; loff_t size; /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); error =3D -EBADF; file =3D fget(arg); if (!file) goto out; error =3D -EBUSY; if (lo->lo_state !=3D Lo_unbound) goto out_putf; /* Avoid recursion */ f =3D file; while (is_loop_device(f)) { struct loop_device *l; if (f->f_mapping->host->i_bdev =3D=3D bdev) goto out_putf; l =3D f->f_mapping->host->i_bdev->bd_disk->private_data; if (l->lo_state =3D=3D Lo_unbound) { error =3D -EINVAL; goto out_putf; } f =3D l->lo_backing_file; } mapping =3D file->f_mapping; inode =3D mapping->host; error =3D -EINVAL; if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) goto out_putf; if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) || !file->f_op->write) lo_flags |=3D LO_FLAGS_READ_ONLY; #ifdef CONFIG_AIO if (file->f_op->write_iter && file->f_op->read_iter && mapping->a_ops->direct_IO) { file->f_flags |=3D O_DIRECT; lo_flags |=3D LO_FLAGS_USE_AIO; } #endif lo_blocksize =3D S_ISBLK(inode->i_mode) ? inode->i_bdev->bd_block_size : PAGE_SIZE; error =3D -EFBIG; size =3D get_loop_size(lo, file); if ((loff_t)(sector_t)size !=3D size) goto out_putf; error =3D 0; set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) !=3D 0); lo->lo_blocksize =3D lo_blocksize; lo->lo_device =3D bdev; lo->lo_flags =3D lo_flags; lo->lo_backing_file =3D file; lo->transfer =3D transfer_none; lo->ioctl =3D NULL; lo->lo_sizelimit =3D 0; lo->lo_bio_count =3D 0; lo->old_gfp_mask =3D mapping_gfp_mask(mapping); mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); bio_list_init(&lo->lo_bio_list); if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_flush(lo->lo_queue, REQ_FLUSH); 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); #ifdef CONFIG_AIO /* * We must not send too-small direct-io requests, so we inherit * the logical block size from the underlying device */ if ((lo_flags & LO_FLAGS_USE_AIO) && inode->i_sb->s_bdev) blk_queue_logical_block_size(lo->lo_queue, bdev_logical_block_size(inode->i_sb->s_bdev)); #endif lo->lo_thread =3D kthread_create(loop_thread, lo, "loop%d", lo->lo_number); if (IS_ERR(lo->lo_thread)) { error =3D PTR_ERR(lo->lo_thread); goto out_clr; } lo->lo_state =3D Lo_bound; wake_up_process(lo->lo_thread); if (part_shift) lo->lo_flags |=3D 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 =3D NULL; lo->lo_device =3D NULL; lo->lo_backing_file =3D NULL; lo->lo_flags =3D 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 =3D Lo_unbound; out_putf: fput(file); out: /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); return error; } static int loop_release_xfer(struct loop_device *lo) { int err =3D 0; struct loop_func_table *xfer =3D lo->lo_encryption; if (xfer) { if (xfer->release) err =3D xfer->release(lo); lo->transfer =3D NULL; lo->lo_encryption =3D NULL; module_put(xfer->owner); } return err; } static int loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer, const struct loop_info64 *i) { int err =3D 0; if (xfer) { struct module *owner =3D xfer->owner; if (!try_module_get(owner)) return -EINVAL; if (xfer->init) err =3D xfer->init(lo, i); if (err) module_put(owner); else lo->lo_encryption =3D xfer; } return err; } static int loop_clr_fd(struct loop_device *lo) { struct file *filp =3D lo->lo_backing_file; gfp_t gfp =3D lo->old_gfp_mask; struct block_device *bdev =3D lo->lo_device; if (lo->lo_state !=3D Lo_bound) return -ENXIO; /* * 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 * /do something like mkfs/losetup -d causing the losetup -d * command to fail with EBUSY. */ if (lo->lo_refcnt > 1) { lo->lo_flags |=3D LO_FLAGS_AUTOCLEAR; mutex_unlock(&lo->lo_ctl_mutex); return 0; } if (filp =3D=3D NULL) return -EINVAL; spin_lock_irq(&lo->lo_lock); lo->lo_state =3D Lo_rundown; spin_unlock_irq(&lo->lo_lock); kthread_stop(lo->lo_thread); spin_lock_irq(&lo->lo_lock); lo->lo_backing_file =3D NULL; spin_unlock_irq(&lo->lo_lock); loop_release_xfer(lo); lo->transfer =3D NULL; lo->ioctl =3D NULL; lo->lo_device =3D NULL; lo->lo_encryption =3D NULL; lo->lo_offset =3D 0; lo->lo_sizelimit =3D 0; lo->lo_encrypt_key_size =3D 0; lo->lo_thread =3D 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); 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 =3D Lo_unbound; /* 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 =3D 0; if (!part_shift) lo->lo_disk->flags |=3D 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; } static int loop_set_status(struct loop_device *lo, const struct loop_info64 *info) { int err; struct loop_func_table *xfer; kuid_t uid =3D 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 !=3D Lo_bound) return -ENXIO; if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) return -EINVAL; err =3D loop_release_xfer(lo); if (err) return err; if (info->lo_encrypt_type) { unsigned int type =3D info->lo_encrypt_type; if (type >=3D MAX_LO_CRYPT) return -EINVAL; xfer =3D xfer_funcs[type]; if (xfer =3D=3D NULL) return -EINVAL; } else xfer =3D NULL; err =3D loop_init_xfer(lo, xfer, info); if (err) return err; if (lo->lo_offset !=3D info->lo_offset || lo->lo_sizelimit !=3D 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); lo->lo_file_name[LO_NAME_SIZE-1] =3D 0; lo->lo_crypt_name[LO_NAME_SIZE-1] =3D 0; if (!xfer) xfer =3D &none_funcs; lo->transfer =3D xfer->transfer; lo->ioctl =3D xfer->ioctl; if ((lo->lo_flags & LO_FLAGS_AUTOCLEAR) !=3D (info->lo_flags & LO_FLAGS_AUTOCLEAR)) lo->lo_flags ^=3D LO_FLAGS_AUTOCLEAR; if ((info->lo_flags & LO_FLAGS_PARTSCAN) && !(lo->lo_flags & LO_FLAGS_PARTSCAN)) { lo->lo_flags |=3D LO_FLAGS_PARTSCAN; lo->lo_disk->flags &=3D ~GENHD_FL_NO_PART_SCAN; ioctl_by_bdev(lo->lo_device, BLKRRPART, 0); } lo->lo_encrypt_key_size =3D info->lo_encrypt_key_size; lo->lo_init[0] =3D info->lo_init[0]; lo->lo_init[1] =3D 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 =3D uid; }=09 return 0; } static int loop_get_status(struct loop_device *lo, struct loop_info64 *info) { struct file *file =3D lo->lo_backing_file; struct kstat stat; int error; if (lo->lo_state !=3D Lo_bound) return -ENXIO; error =3D vfs_getattr(&file->f_path, &stat); if (error) return error; memset(info, 0, sizeof(*info)); info->lo_number =3D lo->lo_number; info->lo_device =3D huge_encode_dev(stat.dev); info->lo_inode =3D stat.ino; info->lo_rdevice =3D huge_encode_dev(lo->lo_device ? stat.rdev : stat.dev); info->lo_offset =3D lo->lo_offset; info->lo_sizelimit =3D lo->lo_sizelimit; info->lo_flags =3D lo->lo_flags; memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE); memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE); info->lo_encrypt_type =3D lo->lo_encryption ? lo->lo_encryption->number : 0; if (lo->lo_encrypt_key_size && capable(CAP_SYS_ADMIN)) { info->lo_encrypt_key_size =3D lo->lo_encrypt_key_size; memcpy(info->lo_encrypt_key, lo->lo_encrypt_key, lo->lo_encrypt_key_size); } return 0; } static void loop_info64_from_old(const struct loop_info *info, struct loop_info64 *info= 64) { memset(info64, 0, sizeof(*info64)); info64->lo_number =3D info->lo_number; info64->lo_device =3D info->lo_device; info64->lo_inode =3D info->lo_inode; info64->lo_rdevice =3D info->lo_rdevice; info64->lo_offset =3D info->lo_offset; info64->lo_sizelimit =3D 0; info64->lo_encrypt_type =3D info->lo_encrypt_type; info64->lo_encrypt_key_size =3D info->lo_encrypt_key_size; info64->lo_flags =3D info->lo_flags; info64->lo_init[0] =3D info->lo_init[0]; info64->lo_init[1] =3D info->lo_init[1]; if (info->lo_encrypt_type =3D=3D 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); } static int loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info) { memset(info, 0, sizeof(*info)); info->lo_number =3D info64->lo_number; info->lo_device =3D info64->lo_device; info->lo_inode =3D info64->lo_inode; info->lo_rdevice =3D info64->lo_rdevice; info->lo_offset =3D info64->lo_offset; info->lo_encrypt_type =3D info64->lo_encrypt_type; info->lo_encrypt_key_size =3D info64->lo_encrypt_key_size; info->lo_flags =3D info64->lo_flags; info->lo_init[0] =3D info64->lo_init[0]; info->lo_init[1] =3D info64->lo_init[1]; if (info->lo_encrypt_type =3D=3D 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); /* error in case values were truncated */ if (info->lo_device !=3D info64->lo_device || info->lo_rdevice !=3D info64->lo_rdevice || info->lo_inode !=3D info64->lo_inode || info->lo_offset !=3D info64->lo_offset) return -EOVERFLOW; return 0; } static int loop_set_status_old(struct loop_device *lo, const struct loop_info __user *= arg) { struct loop_info info; struct loop_info64 info64; if (copy_from_user(&info, arg, sizeof (struct loop_info))) return -EFAULT; loop_info64_from_old(&info, &info64); return loop_set_status(lo, &info64); } static int loop_set_status64(struct loop_device *lo, const struct loop_info64 __user *= arg) { struct loop_info64 info64; if (copy_from_user(&info64, arg, sizeof (struct loop_info64))) return -EFAULT; return loop_set_status(lo, &info64); } static int loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) { struct loop_info info; struct loop_info64 info64; int err =3D 0; if (!arg) err =3D -EINVAL; if (!err) err =3D loop_get_status(lo, &info64); if (!err) err =3D loop_info64_to_old(&info64, &info); if (!err && copy_to_user(arg, &info, sizeof(info))) err =3D -EFAULT; return err; } static int loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { struct loop_info64 info64; int err =3D 0; if (!arg) err =3D -EINVAL; if (!err) err =3D loop_get_status(lo, &info64); if (!err && copy_to_user(arg, &info64, sizeof(info64))) err =3D -EFAULT; return err; } static int loop_set_capacity(struct loop_device *lo, struct block_device *b= dev) { if (unlikely(lo->lo_state !=3D 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 =3D bdev->bd_disk->private_data; int err; mutex_lock_nested(&lo->lo_ctl_mutex, 1); switch (cmd) { case LOOP_SET_FD: err =3D loop_set_fd(lo, mode, bdev, arg); break; case LOOP_CHANGE_FD: err =3D loop_change_fd(lo, bdev, arg); break; case LOOP_CLR_FD: /* loop_clr_fd would have unlocked lo_ctl_mutex on success */ err =3D loop_clr_fd(lo); if (!err) goto out_unlocked; break; case LOOP_SET_STATUS: err =3D -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) err =3D loop_set_status_old(lo, (struct loop_info __user *)arg); break; case LOOP_GET_STATUS: err =3D loop_get_status_old(lo, (struct loop_info __user *) arg); break; case LOOP_SET_STATUS64: err =3D -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) err =3D loop_set_status64(lo, (struct loop_info64 __user *) arg); break; case LOOP_GET_STATUS64: err =3D loop_get_status64(lo, (struct loop_info64 __user *) arg); break; case LOOP_SET_CAPACITY: err =3D -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) err =3D loop_set_capacity(lo, bdev); break; default: err =3D lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; } mutex_unlock(&lo->lo_ctl_mutex); out_unlocked: return err; } #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 compat_loop_info info; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; memset(info64, 0, sizeof(*info64)); info64->lo_number =3D info.lo_number; info64->lo_device =3D info.lo_device; info64->lo_inode =3D info.lo_inode; info64->lo_rdevice =3D info.lo_rdevice; info64->lo_offset =3D info.lo_offset; info64->lo_sizelimit =3D 0; info64->lo_encrypt_type =3D info.lo_encrypt_type; info64->lo_encrypt_key_size =3D info.lo_encrypt_key_size; info64->lo_flags =3D info.lo_flags; info64->lo_init[0] =3D info.lo_init[0]; info64->lo_init[1] =3D info.lo_init[1]; if (info.lo_encrypt_type =3D=3D 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; } /* * 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 compat_loop_info info; memset(&info, 0, sizeof(info)); info.lo_number =3D info64->lo_number; info.lo_device =3D info64->lo_device; info.lo_inode =3D info64->lo_inode; info.lo_rdevice =3D info64->lo_rdevice; info.lo_offset =3D info64->lo_offset; info.lo_encrypt_type =3D info64->lo_encrypt_type; info.lo_encrypt_key_size =3D info64->lo_encrypt_key_size; info.lo_flags =3D info64->lo_flags; info.lo_init[0] =3D info64->lo_init[0]; info.lo_init[1] =3D info64->lo_init[1]; if (info.lo_encrypt_type =3D=3D 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); /* error in case values were truncated */ if (info.lo_device !=3D info64->lo_device || info.lo_rdevice !=3D info64->lo_rdevice || info.lo_inode !=3D info64->lo_inode || info.lo_offset !=3D info64->lo_offset || info.lo_init[0] !=3D info64->lo_init[0] || info.lo_init[1] !=3D info64->lo_init[1]) return -EOVERFLOW; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } static int loop_set_status_compat(struct loop_device *lo, const struct compat_loop_info __user *arg) { struct loop_info64 info64; int ret; ret =3D 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 =3D 0; if (!arg) err =3D -EINVAL; if (!err) err =3D loop_get_status(lo, &info64); if (!err) err =3D 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 =3D bdev->bd_disk->private_data; int err; switch(cmd) { case LOOP_SET_STATUS: mutex_lock(&lo->lo_ctl_mutex); err =3D 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 =3D 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 =3D (unsigned long) compat_ptr(arg); case LOOP_SET_FD: case LOOP_CHANGE_FD: err =3D lo_ioctl(bdev, mode, cmd, arg); break; default: err =3D -ENOIOCTLCMD; break; } return err; } #endif static int lo_open(struct block_device *bdev, fmode_t mode) { struct loop_device *lo; int err =3D 0; mutex_lock(&loop_index_mutex); lo =3D bdev->bd_disk->private_data; if (!lo) { err =3D -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 =3D 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 =3D 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 =3D { .owner =3D THIS_MODULE, .open =3D lo_open, .release =3D lo_release, .ioctl =3D lo_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl =3D lo_compat_ioctl, #endif }; /* * And now the modules code and kernel interface. */ 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); int loop_register_transfer(struct loop_func_table *funcs) { unsigned int n =3D funcs->number; if (n >=3D MAX_LO_CRYPT || xfer_funcs[n]) return -EINVAL; xfer_funcs[n] =3D funcs; return 0; } static int unregister_transfer_cb(int id, void *ptr, void *data) { struct loop_device *lo =3D ptr; struct loop_func_table *xfer =3D data; mutex_lock(&lo->lo_ctl_mutex); if (lo->lo_encryption =3D=3D xfer) loop_release_xfer(lo); mutex_unlock(&lo->lo_ctl_mutex); return 0; } int loop_unregister_transfer(int number) { unsigned int n =3D number; struct loop_func_table *xfer; if (n =3D=3D 0 || n >=3D MAX_LO_CRYPT || (xfer =3D xfer_funcs[n]) =3D=3D N= ULL) return -EINVAL; xfer_funcs[n] =3D NULL; idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer); return 0; } EXPORT_SYMBOL(loop_register_transfer); EXPORT_SYMBOL(loop_unregister_transfer); static int loop_add(struct loop_device **l, int i) { struct loop_device *lo; struct gendisk *disk; int err; err =3D -ENOMEM; lo =3D kzalloc(sizeof(*lo), GFP_KERNEL); if (!lo) goto out; lo->lo_state =3D Lo_unbound; /* allocate id, if @id >=3D 0, we're requesting that specific id */ if (i >=3D 0) { err =3D idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL); if (err =3D=3D -ENOSPC) err =3D -EEXIST; } else { err =3D idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL); } if (err < 0) goto out_free_dev; i =3D err; err =3D -ENOMEM; lo->lo_queue =3D 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 =3D lo; disk =3D lo->lo_disk =3D 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 |=3D GENHD_FL_NO_PART_SCAN; disk->flags |=3D GENHD_FL_EXT_DEVT; mutex_init(&lo->lo_ctl_mutex); lo->lo_number =3D i; lo->lo_thread =3D NULL; init_waitqueue_head(&lo->lo_event); init_waitqueue_head(&lo->lo_req_wait); spin_lock_init(&lo->lo_lock); disk->major =3D LOOP_MAJOR; disk->first_minor =3D i << part_shift; disk->fops =3D &lo_fops; disk->private_data =3D lo; disk->queue =3D lo->lo_queue; sprintf(disk->disk_name, "loop%d", i); add_disk(disk); *l =3D 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 =3D ptr; struct loop_device **l =3D data; if (lo->lo_state =3D=3D Lo_unbound) { *l =3D lo; return 1; } return 0; } static int loop_lookup(struct loop_device **l, int i) { struct loop_device *lo; int ret =3D -ENODEV; if (i < 0) { int err; err =3D idr_for_each(&loop_index_idr, &find_free_cb, &lo); if (err =3D=3D 1) { *l =3D lo; ret =3D lo->lo_number; } goto out; } /* lookup and return a specific i */ lo =3D idr_find(&loop_index_idr, i); if (lo) { *l =3D lo; ret =3D 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 =3D loop_lookup(&lo, MINOR(dev) >> part_shift); if (err < 0) err =3D loop_add(&lo, MINOR(dev) >> part_shift); if (err < 0) kobj =3D NULL; else kobj =3D get_disk(lo->lo_disk); mutex_unlock(&loop_index_mutex); *part =3D 0; return kobj; } static long loop_control_ioctl(struct file *file, unsigned int cmd, unsigned long parm) { struct loop_device *lo; int ret =3D -ENOSYS; mutex_lock(&loop_index_mutex); switch (cmd) { case LOOP_CTL_ADD: ret =3D loop_lookup(&lo, parm); if (ret >=3D 0) { ret =3D -EEXIST; break; } ret =3D loop_add(&lo, parm); break; case LOOP_CTL_REMOVE: ret =3D loop_lookup(&lo, parm); if (ret < 0) break; mutex_lock(&lo->lo_ctl_mutex); if (lo->lo_state !=3D Lo_unbound) { ret =3D -EBUSY; mutex_unlock(&lo->lo_ctl_mutex); break; } if (lo->lo_refcnt > 0) { ret =3D -EBUSY; mutex_unlock(&lo->lo_ctl_mutex); break; } lo->lo_disk->private_data =3D 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 =3D loop_lookup(&lo, -1); if (ret >=3D 0) break; ret =3D loop_add(&lo, -1); } mutex_unlock(&loop_index_mutex); return ret; } static const struct file_operations loop_ctl_fops =3D { .open =3D nonseekable_open, .unlocked_ioctl =3D loop_control_ioctl, .compat_ioctl =3D loop_control_ioctl, .owner =3D THIS_MODULE, .llseek =3D noop_llseek, }; static struct miscdevice loop_misc =3D { .minor =3D LOOP_CTRL_MINOR, .name =3D "loop-control", .fops =3D &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 =3D misc_register(&loop_misc); if (err < 0) return err; part_shift =3D 0; if (max_part > 0) { part_shift =3D fls(max_part); /* * 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 =3D (1UL << part_shift) - 1; } if ((1UL << part_shift) > DISK_MAX_PARTS) { err =3D -EINVAL; goto misc_out; } if (max_loop > 1UL << (MINORBITS - part_shift)) { err =3D -EINVAL; goto misc_out; } /* * 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 =3D max_loop; range =3D max_loop << part_shift; } else { nr =3D CONFIG_BLK_DEV_LOOP_MIN_COUNT; range =3D 1UL << MINORBITS; } if (register_blkdev(LOOP_MAJOR, "loop")) { err =3D -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 =3D 0; i < nr; i++) loop_add(&lo, i); mutex_unlock(&loop_index_mutex); 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) { struct loop_device *lo =3D ptr; loop_remove(lo); return 0; } static void __exit loop_exit(void) { unsigned long range; range =3D 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"); misc_deregister(&loop_misc); } module_init(loop_init); module_exit(loop_exit); #ifndef MODULE static int __init max_loop_setup(char *str) { max_loop =3D simple_strtol(str, NULL, 0); return 1; } __setup("max_loop=3D", max_loop_setup); #endif --Multipart=_Fri__1_Nov_2013_14_20_26_+1100_F6BQQ4h0ke/rPdxm-- --Signature=_Fri__1_Nov_2013_14_20_26_+1100_zy10_5zZl32k4hMP Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (GNU/Linux) iQIcBAEBCAAGBQJScx3+AAoJEMDTa8Ir7ZwV9bsP/0sndUTf0WCx4SFLyrcH9vvS 94ngoErB9fU422Ps0e280wPVAPtiFq8GTcR3t1IFYz5FUCZsnrTboALcplgHBlFC CFC+E0qj83vvxy+tYHcQrzJb24++q3a87mjAVJYZvcLtwsiTbh6CD2tsGcCYrG5t 3+aU3CiFW4Z3HUCmkaFN+MCW08pYfP3qbLfgffWuJ9kZS6Ksm5DeeYQgRKo72+zF 3MobjqziLWLV5cMat3S+Xfo1YGw9k2i/IVOL0wvwVncMtki6xtJ15hcWb5Ygis1C 1H/IOc/r02cqCTPnHSjh7/40krthIsOjkYkYw7ZztiZ/tAPx3jdbU6yqKl9/Ob/c FcW9UpSsmd0pHIVOmhDblzT48XNWmdrXY89Cgz/2ItHU1GRFR6qAq97s5Mi1k9bZ 5bcKlkaD/L2NwYinGv9spj003/gMO9RpEpQDxTmw4rds/jIxwshY5vDWmHrJsWQ0 BZfiFsY+5R3LXb7PsvOraiMRx+l0/q+60h4cym6Bu7M5ggKbOLp9COLgqgeLnuOJ gcivcugReq8NKtrADTocjuHV7f/KndmqKHuCqHjLQ5uRda4hbTahxDEXxgKcejx0 NLLKgxc6rYbfmgpsoyymq5prIf0NsA8MZFacl5tO1ClCW5ba7MfHY4laVuQpQJa6 /J42BW3XjkIIf4r95SAT =O/qe -----END PGP SIGNATURE----- --Signature=_Fri__1_Nov_2013_14_20_26_+1100_zy10_5zZl32k4hMP--