From f44f1ab5a2dcd4e16eab850fd08e40ff2d0c28d4 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Feb 2017 15:56:49 +0100 Subject: block: Unhash block device inodes on gendisk destruction Currently, block device inodes stay around after corresponding gendisk hash died until memory reclaim finds them and frees them. Since we will make block device inode pin the bdi, we want to free the block device inode as soon as the device goes away so that bdi does not stay around unnecessarily. Furthermore we need to avoid issues when new device with the same major,minor pair gets created since reusing the bdi structure would be rather difficult in this case. Unhashing block device inode on gendisk destruction nicely deals with these problems. Once last block device inode reference is dropped (which may be directly in del_gendisk()), the inode gets evicted. Furthermore if the major,minor pair gets reallocated, we are guaranteed to get new block device inode even if old block device inode is not yet evicted and thus we avoid issues with possible reuse of bdi. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- fs/block_dev.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index 5db5d13..ed6a34b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -954,6 +954,21 @@ static int bdev_set(struct inode *inode, void *data) static LIST_HEAD(all_bdevs); +/* + * If there is a bdev inode for this device, unhash it so that it gets evicted + * as soon as last inode reference is dropped. + */ +void bdev_unhash_inode(dev_t dev) +{ + struct inode *inode; + + inode = ilookup5(blockdev_superblock, hash(dev), bdev_test, &dev); + if (inode) { + remove_inode_hash(inode); + iput(inode); + } +} + struct block_device *bdget(dev_t dev) { struct block_device *bdev; -- cgit v1.1 From b1d2dc5659b41741f5a29b2ade76ffb4e5bb13d8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Feb 2017 15:56:52 +0100 Subject: block: Make blk_get_backing_dev_info() safe without open bdev Currenly blk_get_backing_dev_info() is not safe to be called when the block device is not open as bdev->bd_disk is NULL in that case. However inode_to_bdi() uses this function and may be call called from flusher worker or other writeback related functions without bdev being open which leads to crashes such as: [113031.075540] Unable to handle kernel paging request for data at address 0x00000000 [113031.075614] Faulting instruction address: 0xc0000000003692e0 0:mon> t [c0000000fb65f900] c00000000036cb6c writeback_sb_inodes+0x30c/0x590 [c0000000fb65fa10] c00000000036ced4 __writeback_inodes_wb+0xe4/0x150 [c0000000fb65fa70] c00000000036d33c wb_writeback+0x30c/0x450 [c0000000fb65fb40] c00000000036e198 wb_workfn+0x268/0x580 [c0000000fb65fc50] c0000000000f3470 process_one_work+0x1e0/0x590 [c0000000fb65fce0] c0000000000f38c8 worker_thread+0xa8/0x660 [c0000000fb65fd80] c0000000000fc4b0 kthread+0x110/0x130 [c0000000fb65fe30] c0000000000098f0 ret_from_kernel_thread+0x5c/0x6c Signed-off-by: Jens Axboe --- fs/block_dev.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index ed6a34b..601b71b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -884,6 +884,8 @@ static void bdev_evict_inode(struct inode *inode) spin_lock(&bdev_lock); list_del_init(&bdev->bd_list); spin_unlock(&bdev_lock); + if (bdev->bd_bdi != &noop_backing_dev_info) + bdi_put(bdev->bd_bdi); } static const struct super_operations bdev_sops = { @@ -986,6 +988,7 @@ struct block_device *bdget(dev_t dev) bdev->bd_contains = NULL; bdev->bd_super = NULL; bdev->bd_inode = inode; + bdev->bd_bdi = &noop_backing_dev_info; bdev->bd_block_size = (1 << inode->i_blkbits); bdev->bd_part_count = 0; bdev->bd_invalidated = 0; @@ -1542,6 +1545,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = disk; bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; + if (bdev->bd_bdi == &noop_backing_dev_info) + bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); if (!partno) { ret = -ENXIO; @@ -1637,6 +1642,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = NULL; bdev->bd_part = NULL; bdev->bd_queue = NULL; + bdi_put(bdev->bd_bdi); + bdev->bd_bdi = &noop_backing_dev_info; if (bdev != bdev->bd_contains) __blkdev_put(bdev->bd_contains, mode, 1); bdev->bd_contains = NULL; -- cgit v1.1