From 2e6edc95382cc36423aff18a237173ad62d5ab52 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 19 Nov 2015 13:29:28 -0800 Subject: block: protect rw_page against device teardown Fix use after free crashes like the following: general protection fault: 0000 [#1] SMP Call Trace: [] ? pmem_do_bvec.isra.12+0xa6/0xf0 [nd_pmem] [] pmem_rw_page+0x42/0x80 [nd_pmem] [] bdev_read_page+0x50/0x60 [] do_mpage_readpage+0x510/0x770 [] ? I_BDEV+0x20/0x20 [] ? lru_cache_add+0x1c/0x50 [] mpage_readpages+0x107/0x170 [] ? I_BDEV+0x20/0x20 [] ? I_BDEV+0x20/0x20 [] blkdev_readpages+0x1d/0x20 [] __do_page_cache_readahead+0x28f/0x310 [] ? __do_page_cache_readahead+0x169/0x310 [] ? pagecache_get_page+0x2d/0x1d0 [] filemap_fault+0x396/0x530 [] __do_fault+0x4e/0xf0 [] handle_mm_fault+0x11bd/0x1b50 Cc: Cc: Jens Axboe Cc: Alexander Viro Reported-by: kbuild test robot Acked-by: Matthew Wilcox [willy: symmetry fixups] Signed-off-by: Dan Williams --- fs/block_dev.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index bb0dfb1c7af1..c25639e907bd 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -390,9 +390,17 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, struct page *page) { const struct block_device_operations *ops = bdev->bd_disk->fops; + int result = -EOPNOTSUPP; + if (!ops->rw_page || bdev_get_integrity(bdev)) - return -EOPNOTSUPP; - return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ); + return result; + + result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL); + if (result) + return result; + result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ); + blk_queue_exit(bdev->bd_queue); + return result; } EXPORT_SYMBOL_GPL(bdev_read_page); @@ -421,14 +429,20 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, int result; int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE; const struct block_device_operations *ops = bdev->bd_disk->fops; + if (!ops->rw_page || bdev_get_integrity(bdev)) return -EOPNOTSUPP; + result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL); + if (result) + return result; + set_page_writeback(page); result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw); if (result) end_page_writeback(page); else unlock_page(page); + blk_queue_exit(bdev->bd_queue); return result; } EXPORT_SYMBOL_GPL(bdev_write_page); -- cgit v1.2.3 From 43d1c0eb7e11919f85200d2fce211173526f7304 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 20 Nov 2015 22:22:34 +0100 Subject: block: detach bdev inode from its wb in __blkdev_put() Since 52ebea749aae ("writeback: make backing_dev_info host cgroup-specific bdi_writebacks") inode, at some point in its lifetime, gets attached to a wb (struct bdi_writeback). Detaching happens on evict, in inode_detach_wb() called from __destroy_inode(), and involves updating wb. However, detaching an internal bdev inode from its wb in __destroy_inode() is too late. Its bdi and by extension root wb are embedded into struct request_queue, which has different lifetime rules and can be freed long before the final bdput() is called (can be from __fput() of a corresponding /dev inode, through dput() - evict() - bd_forget(). bdevs hold onto the underlying disk/queue pair only while opened; as soon as bdev is closed all bets are off. In fact, disk/queue can be gone before __blkdev_put() even returns: 1499 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) 1500 { ... 1518 if (bdev->bd_contains == bdev) { 1519 if (disk->fops->release) 1520 disk->fops->release(disk, mode); [ Driver puts its references to disk/queue ] 1521 } 1522 if (!bdev->bd_openers) { 1523 struct module *owner = disk->fops->owner; 1524 1525 disk_put_part(bdev->bd_part); 1526 bdev->bd_part = NULL; 1527 bdev->bd_disk = NULL; 1528 if (bdev != bdev->bd_contains) 1529 victim = bdev->bd_contains; 1530 bdev->bd_contains = NULL; 1531 1532 put_disk(disk); [ We put ours, the queue is gone The last bdput() would result in a write to invalid memory ] 1533 module_put(owner); ... 1539 } Since bdev inodes are special anyway, detach them in __blkdev_put() after clearing inode's dirty bits, turning the problematic inode_detach_wb() in __destroy_inode() into a noop. add_disk() grabs its disk->queue since 523e1d399ce0 ("block: make gendisk hold a reference to its queue"), so the old ->release comment is removed in favor of the new inode_detach_wb() comment. Cc: stable@vger.kernel.org # 4.2+, needs backporting Signed-off-by: Ilya Dryomov Acked-by: Tejun Heo Tested-by: Raghavendra K T Signed-off-by: Jens Axboe --- fs/block_dev.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index c25639e907bd..44d4a1e9244e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1523,11 +1523,14 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) WARN_ON_ONCE(bdev->bd_holders); sync_blockdev(bdev); kill_bdev(bdev); + + bdev_write_inode(bdev); /* - * ->release can cause the queue to disappear, so flush all - * dirty data before. + * Detaching bdev inode from its wb in __destroy_inode() + * is too late: the queue which embeds its bdi (along with + * root wb) can be gone as soon as we put_disk() below. */ - bdev_write_inode(bdev); + inode_detach_wb(bdev->bd_inode); } if (bdev->bd_contains == bdev) { if (disk->fops->release) -- cgit v1.2.3