linux/block/bdev.c

1059 lines
27 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
* Copyright (C) 2016 - 2020 Christoph Hellwig
*/
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/major.h>
#include <linux/device_cgroup.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/module.h>
#include <linux/blkpg.h>
#include <linux/magic.h>
#include <linux/buffer_head.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/mount.h>
#include <linux/pseudo_fs.h>
#include <linux/uio.h>
#include <linux/namei.h>
#include <linux/cleancache.h>
#include <linux/part_stat.h>
#include <linux/uaccess.h>
#include "../fs/internal.h"
#include "blk.h"
struct bdev_inode {
struct block_device bdev;
struct inode vfs_inode;
};
static inline struct bdev_inode *BDEV_I(struct inode *inode)
{
return container_of(inode, struct bdev_inode, vfs_inode);
}
struct block_device *I_BDEV(struct inode *inode)
{
return &BDEV_I(inode)->bdev;
}
EXPORT_SYMBOL(I_BDEV);
static void bdev_write_inode(struct block_device *bdev)
{
struct inode *inode = bdev->bd_inode;
int ret;
spin_lock(&inode->i_lock);
while (inode->i_state & I_DIRTY) {
spin_unlock(&inode->i_lock);
ret = write_inode_now(inode, true);
if (ret) {
char name[BDEVNAME_SIZE];
pr_warn_ratelimited("VFS: Dirty inode writeback failed "
"for block device %s (err=%d).\n",
bdevname(bdev, name), ret);
}
spin_lock(&inode->i_lock);
}
spin_unlock(&inode->i_lock);
}
/* Kill _all_ buffers and pagecache , dirty or not.. */
static void kill_bdev(struct block_device *bdev)
{
struct address_space *mapping = bdev->bd_inode->i_mapping;
if (mapping_empty(mapping))
return;
invalidate_bh_lrus();
truncate_inode_pages(mapping, 0);
}
/* Invalidate clean unused buffers and pagecache. */
void invalidate_bdev(struct block_device *bdev)
{
struct address_space *mapping = bdev->bd_inode->i_mapping;
if (mapping->nrpages) {
invalidate_bh_lrus();
lru_add_drain_all(); /* make sure all lru add caches are flushed */
invalidate_mapping_pages(mapping, 0, -1);
}
/* 99% of the time, we don't need to flush the cleancache on the bdev.
* But, for the strange corners, lets be cautious
*/
cleancache_invalidate_inode(mapping);
}
EXPORT_SYMBOL(invalidate_bdev);
/*
* Drop all buffers & page cache for given bdev range. This function bails
* with error if bdev has other exclusive owner (such as filesystem).
*/
int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
loff_t lstart, loff_t lend)
{
/*
* If we don't hold exclusive handle for the device, upgrade to it
* while we discard the buffer cache to avoid discarding buffers
* under live filesystem.
*/
if (!(mode & FMODE_EXCL)) {
int err = bd_prepare_to_claim(bdev, truncate_bdev_range);
if (err)
goto invalidate;
}
truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
if (!(mode & FMODE_EXCL))
bd_abort_claiming(bdev, truncate_bdev_range);
return 0;
invalidate:
/*
* Someone else has handle exclusively open. Try invalidating instead.
* The 'end' argument is inclusive so the rounding is safe.
*/
return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping,
lstart >> PAGE_SHIFT,
lend >> PAGE_SHIFT);
}
blockdev: Fix livelocks on loop device bd_set_size() updates also block device's block size. This is somewhat unexpected from its name and at this point, only blkdev_open() uses this functionality. Furthermore, this can result in changing block size under a filesystem mounted on a loop device which leads to livelocks inside __getblk_gfp() like: Sending NMI from CPU 0 to CPUs 1: NMI backtrace for cpu 1 CPU: 1 PID: 10863 Comm: syz-executor0 Not tainted 4.18.0-rc5+ #151 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__sanitizer_cov_trace_pc+0x3f/0x50 kernel/kcov.c:106 ... Call Trace: init_page_buffers+0x3e2/0x530 fs/buffer.c:904 grow_dev_page fs/buffer.c:947 [inline] grow_buffers fs/buffer.c:1009 [inline] __getblk_slow fs/buffer.c:1036 [inline] __getblk_gfp+0x906/0xb10 fs/buffer.c:1313 __bread_gfp+0x2d/0x310 fs/buffer.c:1347 sb_bread include/linux/buffer_head.h:307 [inline] fat12_ent_bread+0x14e/0x3d0 fs/fat/fatent.c:75 fat_ent_read_block fs/fat/fatent.c:441 [inline] fat_alloc_clusters+0x8ce/0x16e0 fs/fat/fatent.c:489 fat_add_cluster+0x7a/0x150 fs/fat/inode.c:101 __fat_get_block fs/fat/inode.c:148 [inline] ... Trivial reproducer for the problem looks like: truncate -s 1G /tmp/image losetup /dev/loop0 /tmp/image mkfs.ext4 -b 1024 /dev/loop0 mount -t ext4 /dev/loop0 /mnt losetup -c /dev/loop0 l /mnt Fix the problem by moving initialization of a block device block size into a separate function and call it when needed. Thanks to Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> for help with debugging the problem. Reported-by: syzbot+9933e4476f365f5d5a1b@syzkaller.appspotmail.com Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-01-14 16:48:10 +08:00
static void set_init_blocksize(struct block_device *bdev)
{
Revert "block: simplify set_init_blocksize" to regain lost performance The cited commit introduced a serious regression with SATA write speed, as found by bisecting. This patch reverts this commit, which restores write speed back to the values observed before this commit. The performance tests were done on a Helios4 NAS (2nd batch) with 4 HDDs (WD8003FFBX) using dd (bs=1M count=2000). "Direct" is a test with a single HDD, the rest are different RAID levels built over the first partitions of 4 HDDs. Test results are in MB/s, R is read, W is write. | Direct | RAID0 | RAID10 f2 | RAID10 n2 | RAID6 ----------------+--------+-------+-----------+-----------+-------- 9011495c9466 | R:256 | R:313 | R:276 | R:313 | R:323 (before faulty) | W:254 | W:253 | W:195 | W:204 | W:117 ----------------+--------+-------+-----------+-----------+-------- 5ff9f19231a0 | R:257 | R:398 | R:312 | R:344 | R:391 (faulty commit) | W:154 | W:122 | W:67.7 | W:66.6 | W:67.2 ----------------+--------+-------+-----------+-----------+-------- 5.10.10 | R:256 | R:401 | R:312 | R:356 | R:375 unpatched | W:149 | W:123 | W:64 | W:64.1 | W:61.5 ----------------+--------+-------+-----------+-----------+-------- 5.10.10 | R:255 | R:396 | R:312 | R:340 | R:393 patched | W:247 | W:274 | W:220 | W:225 | W:121 Applying this patch doesn't hurt read performance, while improves the write speed by 1.5x - 3.5x (more impact on RAID tests). The write speed is restored back to the state before the faulty commit, and even a bit higher in RAID tests (which aren't HDD-bound on this device) - that is likely related to other optimizations done between the faulty commit and 5.10.10 which also improved the read speed. Signed-off-by: Maxim Mikityanskiy <maxtram95@gmail.com> Fixes: 5ff9f19231a0 ("block: simplify set_init_blocksize") Cc: Christoph Hellwig <hch@lst.de> Cc: Jens Axboe <axboe@kernel.dk> Acked-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-01-27 03:59:07 +08:00
unsigned int bsize = bdev_logical_block_size(bdev);
loff_t size = i_size_read(bdev->bd_inode);
while (bsize < PAGE_SIZE) {
if (size & bsize)
break;
bsize <<= 1;
}
bdev->bd_inode->i_blkbits = blksize_bits(bsize);
blockdev: Fix livelocks on loop device bd_set_size() updates also block device's block size. This is somewhat unexpected from its name and at this point, only blkdev_open() uses this functionality. Furthermore, this can result in changing block size under a filesystem mounted on a loop device which leads to livelocks inside __getblk_gfp() like: Sending NMI from CPU 0 to CPUs 1: NMI backtrace for cpu 1 CPU: 1 PID: 10863 Comm: syz-executor0 Not tainted 4.18.0-rc5+ #151 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__sanitizer_cov_trace_pc+0x3f/0x50 kernel/kcov.c:106 ... Call Trace: init_page_buffers+0x3e2/0x530 fs/buffer.c:904 grow_dev_page fs/buffer.c:947 [inline] grow_buffers fs/buffer.c:1009 [inline] __getblk_slow fs/buffer.c:1036 [inline] __getblk_gfp+0x906/0xb10 fs/buffer.c:1313 __bread_gfp+0x2d/0x310 fs/buffer.c:1347 sb_bread include/linux/buffer_head.h:307 [inline] fat12_ent_bread+0x14e/0x3d0 fs/fat/fatent.c:75 fat_ent_read_block fs/fat/fatent.c:441 [inline] fat_alloc_clusters+0x8ce/0x16e0 fs/fat/fatent.c:489 fat_add_cluster+0x7a/0x150 fs/fat/inode.c:101 __fat_get_block fs/fat/inode.c:148 [inline] ... Trivial reproducer for the problem looks like: truncate -s 1G /tmp/image losetup /dev/loop0 /tmp/image mkfs.ext4 -b 1024 /dev/loop0 mount -t ext4 /dev/loop0 /mnt losetup -c /dev/loop0 l /mnt Fix the problem by moving initialization of a block device block size into a separate function and call it when needed. Thanks to Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> for help with debugging the problem. Reported-by: syzbot+9933e4476f365f5d5a1b@syzkaller.appspotmail.com Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-01-14 16:48:10 +08:00
}
int set_blocksize(struct block_device *bdev, int size)
{
/* Size must be a power of two, and between 512 and PAGE_SIZE */
if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
return -EINVAL;
/* Size cannot be smaller than the size supported by the device */
if (size < bdev_logical_block_size(bdev))
return -EINVAL;
/* Don't change the size if it is same as current */
if (bdev->bd_inode->i_blkbits != blksize_bits(size)) {
sync_blockdev(bdev);
bdev->bd_inode->i_blkbits = blksize_bits(size);
kill_bdev(bdev);
}
return 0;
}
EXPORT_SYMBOL(set_blocksize);
int sb_set_blocksize(struct super_block *sb, int size)
{
if (set_blocksize(sb->s_bdev, size))
return 0;
/* If we get here, we know size is power of two
* and it's value is between 512 and PAGE_SIZE */
sb->s_blocksize = size;
sb->s_blocksize_bits = blksize_bits(size);
return sb->s_blocksize;
}
EXPORT_SYMBOL(sb_set_blocksize);
int sb_min_blocksize(struct super_block *sb, int size)
{
int minsize = bdev_logical_block_size(sb->s_bdev);
if (size < minsize)
size = minsize;
return sb_set_blocksize(sb, size);
}
EXPORT_SYMBOL(sb_min_blocksize);
int __sync_blockdev(struct block_device *bdev, int wait)
{
if (!bdev)
return 0;
if (!wait)
return filemap_flush(bdev->bd_inode->i_mapping);
return filemap_write_and_wait(bdev->bd_inode->i_mapping);
}
/*
* Write out and wait upon all the dirty data associated with a block
* device via its mapping. Does not take the superblock lock.
*/
int sync_blockdev(struct block_device *bdev)
{
return __sync_blockdev(bdev, 1);
}
EXPORT_SYMBOL(sync_blockdev);
/*
* Write out and wait upon all dirty data associated with this
* device. Filesystem data as well as the underlying block
* device. Takes the superblock lock.
*/
int fsync_bdev(struct block_device *bdev)
{
struct super_block *sb = get_super(bdev);
if (sb) {
int res = sync_filesystem(sb);
drop_super(sb);
return res;
}
return sync_blockdev(bdev);
}
EXPORT_SYMBOL(fsync_bdev);
/**
* freeze_bdev -- lock a filesystem and force it into a consistent state
* @bdev: blockdevice to lock
*
* If a superblock is found on this device, we take the s_umount semaphore
* on it to make sure nobody unmounts until the snapshot creation is done.
* The reference counter (bd_fsfreeze_count) guarantees that only the last
* unfreeze process can unfreeze the frozen filesystem actually when multiple
* freeze requests arrive simultaneously. It counts up in freeze_bdev() and
* count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze
* actually.
*/
int freeze_bdev(struct block_device *bdev)
{
struct super_block *sb;
int error = 0;
mutex_lock(&bdev->bd_fsfreeze_mutex);
if (++bdev->bd_fsfreeze_count > 1)
goto done;
sb = get_active_super(bdev);
if (!sb)
goto sync;
if (sb->s_op->freeze_super)
error = sb->s_op->freeze_super(sb);
else
error = freeze_super(sb);
deactivate_super(sb);
if (error) {
bdev->bd_fsfreeze_count--;
goto done;
}
bdev->bd_fsfreeze_sb = sb;
sync:
sync_blockdev(bdev);
done:
mutex_unlock(&bdev->bd_fsfreeze_mutex);
return error;
}
EXPORT_SYMBOL(freeze_bdev);
/**
* thaw_bdev -- unlock filesystem
* @bdev: blockdevice to unlock
*
* Unlocks the filesystem and marks it writeable again after freeze_bdev().
*/
int thaw_bdev(struct block_device *bdev)
{
struct super_block *sb;
int error = -EINVAL;
mutex_lock(&bdev->bd_fsfreeze_mutex);
if (!bdev->bd_fsfreeze_count)
goto out;
error = 0;
if (--bdev->bd_fsfreeze_count > 0)
goto out;
sb = bdev->bd_fsfreeze_sb;
if (!sb)
goto out;
if (sb->s_op->thaw_super)
error = sb->s_op->thaw_super(sb);
else
error = thaw_super(sb);
if (error)
bdev->bd_fsfreeze_count++;
fs: Fix freeze_bdev()/thaw_bdev() accounting of bd_fsfreeze_sb freeze/thaw_bdev() currently use bdev->bd_fsfreeze_count to infer whether or not bdev->bd_fsfreeze_sb is valid (it's valid iff bd_fsfreeze_count is non-zero). thaw_bdev() doesn't nullify bd_fsfreeze_sb. But this means a freeze_bdev() call followed by a thaw_bdev() call can leave bd_fsfreeze_sb with a non-null value, while bd_fsfreeze_count is zero. If freeze_bdev() is called again, and this time get_active_super() returns NULL (e.g. because the FS is unmounted), we'll end up with bd_fsfreeze_count > 0, but bd_fsfreeze_sb is *untouched* - it stays the same (now garbage) value. A subsequent thaw_bdev() will decide that the bd_fsfreeze_sb value is legitimate (since bd_fsfreeze_count > 0), and attempt to use it. Fix this by always setting bd_fsfreeze_sb to NULL when bd_fsfreeze_count is successfully decremented to 0 in thaw_sb(). Alternatively, we could set bd_fsfreeze_sb to whatever get_active_super() returns in freeze_bdev() whenever bd_fsfreeze_count is successfully incremented to 1 from 0 (which can be achieved cleanly by moving the line currently setting bd_fsfreeze_sb to immediately after the "sync:" label, but it might be a little too subtle/easily overlooked in future). This fixes the currently panicking xfstests generic/085. Fixes: 040f04bd2e82 ("fs: simplify freeze_bdev/thaw_bdev") Signed-off-by: Satya Tangirala <satyat@google.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-12-24 12:49:54 +08:00
else
bdev->bd_fsfreeze_sb = NULL;
out:
mutex_unlock(&bdev->bd_fsfreeze_mutex);
return error;
}
EXPORT_SYMBOL(thaw_bdev);
/**
* bdev_read_page() - Start reading a page from a block device
* @bdev: The device to read the page from
* @sector: The offset on the device to read the page to (need not be aligned)
* @page: The page to read
*
* On entry, the page should be locked. It will be unlocked when the page
* has been read. If the block driver implements rw_page synchronously,
* that will be true on exit from this function, but it need not be.
*
* Errors returned by this function are usually "soft", eg out of memory, or
* queue full; callers should try a different route to read this page rather
* than propagate an error back up the stack.
*
* Return: negative errno if an error occurs, 0 if submission was successful.
*/
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 result;
result = blk_queue_enter(bdev->bd_disk->queue, 0);
if (result)
return result;
result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
REQ_OP_READ);
blk_queue_exit(bdev->bd_disk->queue);
return result;
}
/**
* bdev_write_page() - Start writing a page to a block device
* @bdev: The device to write the page to
* @sector: The offset on the device to write the page to (need not be aligned)
* @page: The page to write
* @wbc: The writeback_control for the write
*
* On entry, the page should be locked and not currently under writeback.
* On exit, if the write started successfully, the page will be unlocked and
* under writeback. If the write failed already (eg the driver failed to
* queue the page to the device), the page will still be locked. If the
* caller is a ->writepage implementation, it will need to unlock the page.
*
* Errors returned by this function are usually "soft", eg out of memory, or
* queue full; callers should try a different route to write this page rather
* than propagate an error back up the stack.
*
* Return: negative errno if an error occurs, 0 if submission was successful.
*/
int bdev_write_page(struct block_device *bdev, sector_t sector,
struct page *page, struct writeback_control *wbc)
{
int result;
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_disk->queue, 0);
if (result)
return result;
set_page_writeback(page);
result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
REQ_OP_WRITE);
if (result) {
end_page_writeback(page);
} else {
clean_page_buffers(page);
unlock_page(page);
}
blk_queue_exit(bdev->bd_disk->queue);
return result;
}
/*
* pseudo-fs
*/
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
static struct kmem_cache * bdev_cachep __read_mostly;
static struct inode *bdev_alloc_inode(struct super_block *sb)
{
struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
if (!ei)
return NULL;
memset(&ei->bdev, 0, sizeof(ei->bdev));
return &ei->vfs_inode;
}
static void bdev_free_inode(struct inode *inode)
{
struct block_device *bdev = I_BDEV(inode);
free_percpu(bdev->bd_stats);
kfree(bdev->bd_meta_info);
if (!bdev_is_partition(bdev)) {
if (bdev->bd_disk && bdev->bd_disk->bdi)
bdi_put(bdev->bd_disk->bdi);
kfree(bdev->bd_disk);
}
if (MAJOR(bdev->bd_dev) == BLOCK_EXT_MAJOR)
blk_free_ext_minor(MINOR(bdev->bd_dev));
kmem_cache_free(bdev_cachep, BDEV_I(inode));
2011-01-07 14:49:49 +08:00
}
static void init_once(void *data)
{
struct bdev_inode *ei = data;
inode_init_once(&ei->vfs_inode);
}
static void bdev_evict_inode(struct inode *inode)
{
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-04 05:47:49 +08:00
truncate_inode_pages_final(&inode->i_data);
invalidate_inode_buffers(inode); /* is it needed here? */
clear_inode(inode);
}
static const struct super_operations bdev_sops = {
.statfs = simple_statfs,
.alloc_inode = bdev_alloc_inode,
.free_inode = bdev_free_inode,
.drop_inode = generic_delete_inode,
.evict_inode = bdev_evict_inode,
};
static int bd_init_fs_context(struct fs_context *fc)
{
struct pseudo_fs_context *ctx = init_pseudo(fc, BDEVFS_MAGIC);
if (!ctx)
return -ENOMEM;
fc->s_iflags |= SB_I_CGROUPWB;
ctx->ops = &bdev_sops;
return 0;
}
static struct file_system_type bd_type = {
.name = "bdev",
.init_fs_context = bd_init_fs_context,
.kill_sb = kill_anon_super,
};
struct super_block *blockdev_superblock __read_mostly;
EXPORT_SYMBOL_GPL(blockdev_superblock);
void __init bdev_cache_init(void)
{
int err;
block_dev: Suppress bdev_cache_init() kmemleak warninig Kmemleak reports the following warning in bdev_cache_init() [ 0.003738] kmemleak: Object 0xffff880153035200 (size 256): [ 0.003823] kmemleak: comm "swapper/0", pid 0, jiffies 4294667299 [ 0.003909] kmemleak: min_count = 1 [ 0.003988] kmemleak: count = 0 [ 0.004066] kmemleak: flags = 0x1 [ 0.004144] kmemleak: checksum = 0 [ 0.004224] kmemleak: backtrace: [ 0.004303] [<ffffffff814755ac>] kmemleak_alloc+0x21/0x3e [ 0.004446] [<ffffffff811100ba>] kmem_cache_alloc+0xca/0x1dc [ 0.004592] [<ffffffff811371b1>] alloc_vfsmnt+0x1f/0x198 [ 0.004736] [<ffffffff811375c5>] vfs_kern_mount+0x36/0xd2 [ 0.004879] [<ffffffff8113929a>] kern_mount_data+0x18/0x32 [ 0.005025] [<ffffffff81ab9075>] bdev_cache_init+0x51/0x81 [ 0.005169] [<ffffffff81ab8abf>] vfs_caches_init+0x101/0x10d [ 0.005313] [<ffffffff81a9bae3>] start_kernel+0x344/0x383 [ 0.005456] [<ffffffff81a9b2a7>] x86_64_start_reservations+0xae/0xb2 [ 0.005602] [<ffffffff81a9b3ad>] x86_64_start_kernel+0x102/0x111 [ 0.005747] [<ffffffffffffffff>] 0xffffffffffffffff [ 0.008653] kmemleak: Trying to color unknown object at 0xffff880153035220 as Grey [ 0.008754] Pid: 0, comm: swapper/0 Not tainted 3.3.0-rc0-dbg-04200-g8180888-dirty #888 [ 0.008856] Call Trace: [ 0.008934] [<ffffffff81118704>] ? find_and_get_object+0x44/0x118 [ 0.009023] [<ffffffff81118fe6>] paint_ptr+0x57/0x8f [ 0.009109] [<ffffffff81475935>] kmemleak_not_leak+0x23/0x42 [ 0.009195] [<ffffffff81ab9096>] bdev_cache_init+0x72/0x81 [ 0.009282] [<ffffffff81ab8abf>] vfs_caches_init+0x101/0x10d [ 0.009368] [<ffffffff81a9bae3>] start_kernel+0x344/0x383 [ 0.009466] [<ffffffff81a9b2a7>] x86_64_start_reservations+0xae/0xb2 [ 0.009555] [<ffffffff81a9b140>] ? early_idt_handlers+0x140/0x140 [ 0.009643] [<ffffffff81a9b3ad>] x86_64_start_kernel+0x102/0x111 due to attempt to mark pointer to `struct vfsmount' as a gray object, which is embedded into `struct mount' returned from alloc_vfsmnt(). Make `bd_mnt' static, avoiding need to tell kmemleak to mark it gray, as suggested by Al Viro. Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-01-10 07:43:59 +08:00
static struct vfsmount *bd_mnt;
bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
2016-01-15 07:18:21 +08:00
SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC),
init_once);
err = register_filesystem(&bd_type);
if (err)
panic("Cannot register bdev pseudo-fs");
bd_mnt = kern_mount(&bd_type);
if (IS_ERR(bd_mnt))
panic("Cannot create bdev pseudo-fs");
block_dev: Suppress bdev_cache_init() kmemleak warninig Kmemleak reports the following warning in bdev_cache_init() [ 0.003738] kmemleak: Object 0xffff880153035200 (size 256): [ 0.003823] kmemleak: comm "swapper/0", pid 0, jiffies 4294667299 [ 0.003909] kmemleak: min_count = 1 [ 0.003988] kmemleak: count = 0 [ 0.004066] kmemleak: flags = 0x1 [ 0.004144] kmemleak: checksum = 0 [ 0.004224] kmemleak: backtrace: [ 0.004303] [<ffffffff814755ac>] kmemleak_alloc+0x21/0x3e [ 0.004446] [<ffffffff811100ba>] kmem_cache_alloc+0xca/0x1dc [ 0.004592] [<ffffffff811371b1>] alloc_vfsmnt+0x1f/0x198 [ 0.004736] [<ffffffff811375c5>] vfs_kern_mount+0x36/0xd2 [ 0.004879] [<ffffffff8113929a>] kern_mount_data+0x18/0x32 [ 0.005025] [<ffffffff81ab9075>] bdev_cache_init+0x51/0x81 [ 0.005169] [<ffffffff81ab8abf>] vfs_caches_init+0x101/0x10d [ 0.005313] [<ffffffff81a9bae3>] start_kernel+0x344/0x383 [ 0.005456] [<ffffffff81a9b2a7>] x86_64_start_reservations+0xae/0xb2 [ 0.005602] [<ffffffff81a9b3ad>] x86_64_start_kernel+0x102/0x111 [ 0.005747] [<ffffffffffffffff>] 0xffffffffffffffff [ 0.008653] kmemleak: Trying to color unknown object at 0xffff880153035220 as Grey [ 0.008754] Pid: 0, comm: swapper/0 Not tainted 3.3.0-rc0-dbg-04200-g8180888-dirty #888 [ 0.008856] Call Trace: [ 0.008934] [<ffffffff81118704>] ? find_and_get_object+0x44/0x118 [ 0.009023] [<ffffffff81118fe6>] paint_ptr+0x57/0x8f [ 0.009109] [<ffffffff81475935>] kmemleak_not_leak+0x23/0x42 [ 0.009195] [<ffffffff81ab9096>] bdev_cache_init+0x72/0x81 [ 0.009282] [<ffffffff81ab8abf>] vfs_caches_init+0x101/0x10d [ 0.009368] [<ffffffff81a9bae3>] start_kernel+0x344/0x383 [ 0.009466] [<ffffffff81a9b2a7>] x86_64_start_reservations+0xae/0xb2 [ 0.009555] [<ffffffff81a9b140>] ? early_idt_handlers+0x140/0x140 [ 0.009643] [<ffffffff81a9b3ad>] x86_64_start_kernel+0x102/0x111 due to attempt to mark pointer to `struct vfsmount' as a gray object, which is embedded into `struct mount' returned from alloc_vfsmnt(). Make `bd_mnt' static, avoiding need to tell kmemleak to mark it gray, as suggested by Al Viro. Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-01-10 07:43:59 +08:00
blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */
}
struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
{
struct block_device *bdev;
struct inode *inode;
inode = new_inode(blockdev_superblock);
if (!inode)
return NULL;
inode->i_mode = S_IFBLK;
inode->i_rdev = 0;
inode->i_data.a_ops = &def_blk_aops;
mapping_set_gfp_mask(&inode->i_data, GFP_USER);
bdev = I_BDEV(inode);
mutex_init(&bdev->bd_fsfreeze_mutex);
spin_lock_init(&bdev->bd_size_lock);
bdev->bd_disk = disk;
bdev->bd_partno = partno;
bdev->bd_inode = inode;
bdev->bd_stats = alloc_percpu(struct disk_stats);
if (!bdev->bd_stats) {
iput(inode);
return NULL;
}
return bdev;
}
void bdev_add(struct block_device *bdev, dev_t dev)
{
bdev->bd_dev = dev;
bdev->bd_inode->i_rdev = dev;
bdev->bd_inode->i_ino = dev;
insert_inode_hash(bdev->bd_inode);
}
long nr_blockdev_pages(void)
{
struct inode *inode;
long ret = 0;
spin_lock(&blockdev_superblock->s_inode_list_lock);
list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list)
ret += inode->i_mapping->nrpages;
spin_unlock(&blockdev_superblock->s_inode_list_lock);
return ret;
}
/**
* bd_may_claim - test whether a block device can be claimed
* @bdev: block device of interest
* @whole: whole block device containing @bdev, may equal @bdev
* @holder: holder trying to claim @bdev
*
* Test whether @bdev can be claimed by @holder.
*
* CONTEXT:
* spin_lock(&bdev_lock).
*
* RETURNS:
* %true if @bdev can be claimed, %false otherwise.
*/
static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
void *holder)
{
if (bdev->bd_holder == holder)
return true; /* already a holder */
else if (bdev->bd_holder != NULL)
return false; /* held by someone else */
block_dev: don't test bdev->bd_contains when it is not stable bdev->bd_contains is not stable before calling __blkdev_get(). When __blkdev_get() is called on a parition with ->bd_openers == 0 it sets bdev->bd_contains = bdev; which is not correct for a partition. After a call to __blkdev_get() succeeds, ->bd_openers will be > 0 and then ->bd_contains is stable. When FMODE_EXCL is used, blkdev_get() calls bd_start_claiming() -> bd_prepare_to_claim() -> bd_may_claim() This call happens before __blkdev_get() is called, so ->bd_contains is not stable. So bd_may_claim() cannot safely use ->bd_contains. It currently tries to use it, and this can lead to a BUG_ON(). This happens when a whole device is already open with a bd_holder (in use by dm in my particular example) and two threads race to open a partition of that device for the first time, one opening with O_EXCL and one without. The thread that doesn't use O_EXCL gets through blkdev_get() to __blkdev_get(), gains the ->bd_mutex, and sets bdev->bd_contains = bdev; Immediately thereafter the other thread, using FMODE_EXCL, calls bd_start_claiming() from blkdev_get(). This should fail because the whole device has a holder, but because bdev->bd_contains == bdev bd_may_claim() incorrectly reports success. This thread continues and blocks on bd_mutex. The first thread then sets bdev->bd_contains correctly and drops the mutex. The thread using FMODE_EXCL then continues and when it calls bd_may_claim() again in: BUG_ON(!bd_may_claim(bdev, whole, holder)); The BUG_ON fires. Fix this by removing the dependency on ->bd_contains in bd_may_claim(). As bd_may_claim() has direct access to the whole device, it can simply test if the target bdev is the whole device. Fixes: 6b4517a7913a ("block: implement bd_claiming and claiming block") Cc: stable@vger.kernel.org (v2.6.35+) Signed-off-by: NeilBrown <neilb@suse.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-12-12 23:21:51 +08:00
else if (whole == bdev)
return true; /* is a whole device which isn't held */
block: make blkdev_get/put() handle exclusive access Over time, block layer has accumulated a set of APIs dealing with bdev open, close, claim and release. * blkdev_get/put() are the primary open and close functions. * bd_claim/release() deal with exclusive open. * open/close_bdev_exclusive() are combination of open and claim and the other way around, respectively. * bd_link/unlink_disk_holder() to create and remove holder/slave symlinks. * open_by_devnum() wraps bdget() + blkdev_get(). The interface is a bit confusing and the decoupling of open and claim makes it impossible to properly guarantee exclusive access as in-kernel open + claim sequence can disturb the existing exclusive open even before the block layer knows the current open if for another exclusive access. Reorganize the interface such that, * blkdev_get() is extended to include exclusive access management. @holder argument is added and, if is @FMODE_EXCL specified, it will gain exclusive access atomically w.r.t. other exclusive accesses. * blkdev_put() is similarly extended. It now takes @mode argument and if @FMODE_EXCL is set, it releases an exclusive access. Also, when the last exclusive claim is released, the holder/slave symlinks are removed automatically. * bd_claim/release() and close_bdev_exclusive() are no longer necessary and either made static or removed. * bd_link_disk_holder() remains the same but bd_unlink_disk_holder() is no longer necessary and removed. * open_bdev_exclusive() becomes a simple wrapper around lookup_bdev() and blkdev_get(). It also has an unexpected extra bdev_read_only() test which probably should be moved into blkdev_get(). * open_by_devnum() is modified to take @holder argument and pass it to blkdev_get(). Most of bdev open/close operations are unified into blkdev_get/put() and most exclusive accesses are tested atomically at the open time (as it should). This cleans up code and removes some, both valid and invalid, but unnecessary all the same, corner cases. open_bdev_exclusive() and open_by_devnum() can use further cleanup - rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop special features. Well, let's leave them for another day. Most conversions are straight-forward. drbd conversion is a bit more involved as there was some reordering, but the logic should stay the same. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Neil Brown <neilb@suse.de> Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Acked-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Philipp Reisner <philipp.reisner@linbit.com> Cc: Peter Osterlund <petero2@telia.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Cc: Alex Elder <aelder@sgi.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: dm-devel@redhat.com Cc: drbd-dev@lists.linbit.com Cc: Leo Chen <leochen@broadcom.com> Cc: Scott Branden <sbranden@broadcom.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Cc: Joern Engel <joern@logfs.org> Cc: reiserfs-devel@vger.kernel.org Cc: Alexander Viro <viro@zeniv.linux.org.uk>
2010-11-13 18:55:17 +08:00
else if (whole->bd_holder == bd_may_claim)
return true; /* is a partition of a device that is being partitioned */
else if (whole->bd_holder != NULL)
return false; /* is a partition of a held device */
else
return true; /* is a partition of an un-held device */
}
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
/**
* bd_prepare_to_claim - claim a block device
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
* @bdev: block device of interest
* @holder: holder trying to claim @bdev
*
* Claim @bdev. This function fails if @bdev is already claimed by another
* holder and waits if another claiming is in progress. return, the caller
* has ownership of bd_claiming and bd_holder[s].
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
*
* RETURNS:
* 0 if @bdev can be claimed, -EBUSY otherwise.
*/
int bd_prepare_to_claim(struct block_device *bdev, void *holder)
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
{
struct block_device *whole = bdev_whole(bdev);
if (WARN_ON_ONCE(!holder))
return -EINVAL;
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
retry:
spin_lock(&bdev_lock);
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
/* if someone else claimed, fail */
if (!bd_may_claim(bdev, whole, holder)) {
spin_unlock(&bdev_lock);
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
return -EBUSY;
}
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
/* if claiming is already in progress, wait for it to finish */
if (whole->bd_claiming) {
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0);
DEFINE_WAIT(wait);
prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
spin_unlock(&bdev_lock);
schedule();
finish_wait(wq, &wait);
goto retry;
}
/* yay, all mine */
whole->bd_claiming = holder;
spin_unlock(&bdev_lock);
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
return 0;
}
EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
static void bd_clear_claiming(struct block_device *whole, void *holder)
{
lockdep_assert_held(&bdev_lock);
/* tell others that we're done */
BUG_ON(whole->bd_claiming != holder);
whole->bd_claiming = NULL;
wake_up_bit(&whole->bd_claiming, 0);
}
/**
* bd_finish_claiming - finish claiming of a block device
* @bdev: block device of interest
* @holder: holder that has claimed @bdev
*
* Finish exclusive open of a block device. Mark the device as exlusively
* open by the holder and wake up all waiters for exclusive open to finish.
*/
static void bd_finish_claiming(struct block_device *bdev, void *holder)
{
struct block_device *whole = bdev_whole(bdev);
spin_lock(&bdev_lock);
BUG_ON(!bd_may_claim(bdev, whole, holder));
/*
* Note that for a whole device bd_holders will be incremented twice,
* and bd_holder will be set to bd_may_claim before being set to holder
*/
whole->bd_holders++;
whole->bd_holder = bd_may_claim;
bdev->bd_holders++;
bdev->bd_holder = holder;
bd_clear_claiming(whole, holder);
spin_unlock(&bdev_lock);
}
/**
* bd_abort_claiming - abort claiming of a block device
* @bdev: block device of interest
* @holder: holder that has claimed @bdev
*
* Abort claiming of a block device when the exclusive open failed. This can be
* also used when exclusive open is not actually desired and we just needed
* to block other exclusive openers for a while.
*/
void bd_abort_claiming(struct block_device *bdev, void *holder)
{
spin_lock(&bdev_lock);
bd_clear_claiming(bdev_whole(bdev), holder);
spin_unlock(&bdev_lock);
}
EXPORT_SYMBOL(bd_abort_claiming);
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 17:53:59 +08:00
static void blkdev_flush_mapping(struct block_device *bdev)
{
WARN_ON_ONCE(bdev->bd_holders);
sync_blockdev(bdev);
kill_bdev(bdev);
bdev_write_inode(bdev);
}
[PATCH] lockdep: simplify some aspects of bd_mutex nesting When we open (actually blkdev_get) a partition we need to also open (get) the whole device that holds the partition. The involves some limited recursion. This patch tries to simplify some aspects of this. As well as opening the whole device, we need to increment ->bd_part_count when a partition is opened (this is used by rescan_partitions to avoid a rescan if any partition is active, as that would be confusing). The main change this patch makes is to move the inc/dec of bd_part_count into blkdev_{get,put} for the whole rather than doing it in blkdev_{get,put} for the partition. More specifically, we introduce __blkdev_get and __blkdev_put which do exactly what blkdev_{get,put} did, only with an extra "for_part" argument (blkget_{get,put} then call the __ version with a '0' for the extra argument). If for_part is 1, then the blkdev is being get(put) because a partition is being opened(closed) for the first(last) time, and so bd_part_count should be updated (on success). The particular advantage of pushing this function down is that the bd_mutex lock (which is needed to update bd_part_count) is already held at the lower level. Note that this slightly changes the semantics of bd_part_count. Instead of updating it whenever a partition is opened or released, it is now only updated on the first open or last release. This is an adequate semantic as it is only ever tested for "== 0". Having introduced these functions we remove the current bd_part_count updates from do_open (which is really the body of blkdev_get) and call __blkdev_get(... 1). Similarly in blkget_put we remove the old bd_part_count updates and call __blkget_put(..., 1). This call is moved to the end of __blkdev_put to avoid nested locks of bd_mutex. Finally the mutex_lock on whole->bd_mutex in do_open can be removed. It was only really needed to protect bd_part_count, and that is now managed (and protected) within the recursive call. The observation that bd_part_count is central to the locking issues, and the modifications to create __blkdev_put are from Peter Zijlstra. Cc: Ingo Molnar <mingo@elte.hu> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 18:36:16 +08:00
static int blkdev_get_whole(struct block_device *bdev, fmode_t mode)
{
struct gendisk *disk = bdev->bd_disk;
int ret = 0;
if (disk->fops->open) {
ret = disk->fops->open(bdev, mode);
if (ret) {
/* avoid ghost partitions on a removed medium */
if (ret == -ENOMEDIUM &&
test_bit(GD_NEED_PART_SCAN, &disk->state))
bdev_disk_changed(disk, true);
return ret;
}
}
if (!bdev->bd_openers)
set_init_blocksize(bdev);
if (test_bit(GD_NEED_PART_SCAN, &disk->state))
bdev_disk_changed(disk, false);
bdev->bd_openers++;
return 0;;
}
static void blkdev_put_whole(struct block_device *bdev, fmode_t mode)
{
if (!--bdev->bd_openers)
blkdev_flush_mapping(bdev);
if (bdev->bd_disk->fops->release)
bdev->bd_disk->fops->release(bdev->bd_disk, mode);
}
static int blkdev_get_part(struct block_device *part, fmode_t mode)
{
struct gendisk *disk = part->bd_disk;
int ret;
if (part->bd_openers)
goto done;
ret = blkdev_get_whole(bdev_whole(part), mode);
if (ret)
return ret;
ret = -ENXIO;
if (!bdev_nr_sectors(part))
goto out_blkdev_put;
disk->open_partitions++;
set_init_blocksize(part);
done:
part->bd_openers++;
return 0;
out_blkdev_put:
blkdev_put_whole(bdev_whole(part), mode);
return ret;
}
static void blkdev_put_part(struct block_device *part, fmode_t mode)
{
struct block_device *whole = bdev_whole(part);
if (--part->bd_openers)
return;
blkdev_flush_mapping(part);
whole->bd_disk->open_partitions--;
blkdev_put_whole(whole, mode);
}
struct block_device *blkdev_get_no_open(dev_t dev)
{
struct block_device *bdev;
struct inode *inode;
inode = ilookup(blockdev_superblock, dev);
if (!inode) {
blk_request_module(dev);
inode = ilookup(blockdev_superblock, dev);
if (!inode)
return NULL;
}
/* switch from the inode reference to a device mode one: */
bdev = &BDEV_I(inode)->bdev;
if (!kobject_get_unless_zero(&bdev->bd_device.kobj))
bdev = NULL;
iput(inode);
if (!bdev)
return NULL;
if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN) ||
!try_module_get(bdev->bd_disk->fops->owner)) {
put_device(&bdev->bd_device);
return NULL;
}
return bdev;
}
void blkdev_put_no_open(struct block_device *bdev)
{
module_put(bdev->bd_disk->fops->owner);
put_device(&bdev->bd_device);
}
/**
* blkdev_get_by_dev - open a block device by device number
* @dev: device number of block device to open
* @mode: FMODE_* mask
* @holder: exclusive holder identifier
*
* Open the block device described by device number @dev. If @mode includes
* %FMODE_EXCL, the block device is opened with exclusive access. Specifying
* %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may nest for
* the same @holder.
*
* Use this interface ONLY if you really do not have anything better - i.e. when
* you are behind a truly sucky interface and all you are given is a device
* number. Everything else should use blkdev_get_by_path().
*
* CONTEXT:
* Might sleep.
*
* RETURNS:
* Reference to the block_device on success, ERR_PTR(-errno) on failure.
*/
struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
{
bool unblock_events = true;
struct block_device *bdev;
struct gendisk *disk;
int ret;
block: make blkdev_get/put() handle exclusive access Over time, block layer has accumulated a set of APIs dealing with bdev open, close, claim and release. * blkdev_get/put() are the primary open and close functions. * bd_claim/release() deal with exclusive open. * open/close_bdev_exclusive() are combination of open and claim and the other way around, respectively. * bd_link/unlink_disk_holder() to create and remove holder/slave symlinks. * open_by_devnum() wraps bdget() + blkdev_get(). The interface is a bit confusing and the decoupling of open and claim makes it impossible to properly guarantee exclusive access as in-kernel open + claim sequence can disturb the existing exclusive open even before the block layer knows the current open if for another exclusive access. Reorganize the interface such that, * blkdev_get() is extended to include exclusive access management. @holder argument is added and, if is @FMODE_EXCL specified, it will gain exclusive access atomically w.r.t. other exclusive accesses. * blkdev_put() is similarly extended. It now takes @mode argument and if @FMODE_EXCL is set, it releases an exclusive access. Also, when the last exclusive claim is released, the holder/slave symlinks are removed automatically. * bd_claim/release() and close_bdev_exclusive() are no longer necessary and either made static or removed. * bd_link_disk_holder() remains the same but bd_unlink_disk_holder() is no longer necessary and removed. * open_bdev_exclusive() becomes a simple wrapper around lookup_bdev() and blkdev_get(). It also has an unexpected extra bdev_read_only() test which probably should be moved into blkdev_get(). * open_by_devnum() is modified to take @holder argument and pass it to blkdev_get(). Most of bdev open/close operations are unified into blkdev_get/put() and most exclusive accesses are tested atomically at the open time (as it should). This cleans up code and removes some, both valid and invalid, but unnecessary all the same, corner cases. open_bdev_exclusive() and open_by_devnum() can use further cleanup - rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop special features. Well, let's leave them for another day. Most conversions are straight-forward. drbd conversion is a bit more involved as there was some reordering, but the logic should stay the same. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Neil Brown <neilb@suse.de> Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Acked-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Philipp Reisner <philipp.reisner@linbit.com> Cc: Peter Osterlund <petero2@telia.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Cc: Alex Elder <aelder@sgi.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: dm-devel@redhat.com Cc: drbd-dev@lists.linbit.com Cc: Leo Chen <leochen@broadcom.com> Cc: Scott Branden <sbranden@broadcom.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Cc: Joern Engel <joern@logfs.org> Cc: reiserfs-devel@vger.kernel.org Cc: Alexander Viro <viro@zeniv.linux.org.uk>
2010-11-13 18:55:17 +08:00
ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
MAJOR(dev), MINOR(dev),
((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) |
((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0));
if (ret)
return ERR_PTR(ret);
bdev = blkdev_get_no_open(dev);
if (!bdev)
return ERR_PTR(-ENXIO);
disk = bdev->bd_disk;
if (mode & FMODE_EXCL) {
ret = bd_prepare_to_claim(bdev, holder);
if (ret)
goto put_blkdev;
}
disk_block_events(disk);
mutex_lock(&disk->open_mutex);
ret = -ENXIO;
if (!disk_live(disk))
goto abort_claiming;
if (bdev_is_partition(bdev))
ret = blkdev_get_part(bdev, mode);
else
ret = blkdev_get_whole(bdev, mode);
if (ret)
goto abort_claiming;
if (mode & FMODE_EXCL) {
bd_finish_claiming(bdev, holder);
/*
* Block event polling for write claims if requested. Any write
* holder makes the write_holder state stick until all are
* released. This is good enough and tracking individual
* writeable reference is too fragile given the way @mode is
* used in blkdev_get/put().
*/
if ((mode & FMODE_WRITE) && !bdev->bd_write_holder &&
(disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
bdev->bd_write_holder = true;
unblock_events = false;
}
}
mutex_unlock(&disk->open_mutex);
if (unblock_events)
disk_unblock_events(disk);
return bdev;
abort_claiming:
if (mode & FMODE_EXCL)
bd_abort_claiming(bdev, holder);
mutex_unlock(&disk->open_mutex);
disk_unblock_events(disk);
put_blkdev:
blkdev_put_no_open(bdev);
return ERR_PTR(ret);
[PATCH] lockdep: simplify some aspects of bd_mutex nesting When we open (actually blkdev_get) a partition we need to also open (get) the whole device that holds the partition. The involves some limited recursion. This patch tries to simplify some aspects of this. As well as opening the whole device, we need to increment ->bd_part_count when a partition is opened (this is used by rescan_partitions to avoid a rescan if any partition is active, as that would be confusing). The main change this patch makes is to move the inc/dec of bd_part_count into blkdev_{get,put} for the whole rather than doing it in blkdev_{get,put} for the partition. More specifically, we introduce __blkdev_get and __blkdev_put which do exactly what blkdev_{get,put} did, only with an extra "for_part" argument (blkget_{get,put} then call the __ version with a '0' for the extra argument). If for_part is 1, then the blkdev is being get(put) because a partition is being opened(closed) for the first(last) time, and so bd_part_count should be updated (on success). The particular advantage of pushing this function down is that the bd_mutex lock (which is needed to update bd_part_count) is already held at the lower level. Note that this slightly changes the semantics of bd_part_count. Instead of updating it whenever a partition is opened or released, it is now only updated on the first open or last release. This is an adequate semantic as it is only ever tested for "== 0". Having introduced these functions we remove the current bd_part_count updates from do_open (which is really the body of blkdev_get) and call __blkdev_get(... 1). Similarly in blkget_put we remove the old bd_part_count updates and call __blkget_put(..., 1). This call is moved to the end of __blkdev_put to avoid nested locks of bd_mutex. Finally the mutex_lock on whole->bd_mutex in do_open can be removed. It was only really needed to protect bd_part_count, and that is now managed (and protected) within the recursive call. The observation that bd_part_count is central to the locking issues, and the modifications to create __blkdev_put are from Peter Zijlstra. Cc: Ingo Molnar <mingo@elte.hu> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 18:36:16 +08:00
}
EXPORT_SYMBOL(blkdev_get_by_dev);
/**
* blkdev_get_by_path - open a block device by name
* @path: path to the block device to open
* @mode: FMODE_* mask
* @holder: exclusive holder identifier
*
* Open the block device described by the device file at @path. If @mode
* includes %FMODE_EXCL, the block device is opened with exclusive access.
* Specifying %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may
* nest for the same @holder.
*
* CONTEXT:
* Might sleep.
*
* RETURNS:
* Reference to the block_device on success, ERR_PTR(-errno) on failure.
*/
struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
void *holder)
{
struct block_device *bdev;
dev_t dev;
int error;
error = lookup_bdev(path, &dev);
if (error)
return ERR_PTR(error);
bdev = blkdev_get_by_dev(dev, mode, holder);
if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
blkdev_put(bdev, mode);
return ERR_PTR(-EACCES);
}
return bdev;
}
EXPORT_SYMBOL(blkdev_get_by_path);
void blkdev_put(struct block_device *bdev, fmode_t mode)
{
struct gendisk *disk = bdev->bd_disk;
bdev: Reduce time holding bd_mutex in sync in blkdev_close() While trying to "dd" to the block device for a USB stick, I encountered a hung task warning (blocked for > 120 seconds). I managed to come up with an easy way to reproduce this on my system (where /dev/sdb is the block device for my USB stick) with: while true; do dd if=/dev/zero of=/dev/sdb bs=4M; done With my reproduction here are the relevant bits from the hung task detector: INFO: task udevd:294 blocked for more than 122 seconds. ... udevd D 0 294 1 0x00400008 Call trace: ... mutex_lock_nested+0x40/0x50 __blkdev_get+0x7c/0x3d4 blkdev_get+0x118/0x138 blkdev_open+0x94/0xa8 do_dentry_open+0x268/0x3a0 vfs_open+0x34/0x40 path_openat+0x39c/0xdf4 do_filp_open+0x90/0x10c do_sys_open+0x150/0x3c8 ... ... Showing all locks held in the system: ... 1 lock held by dd/2798: #0: ffffff814ac1a3b8 (&bdev->bd_mutex){+.+.}, at: __blkdev_put+0x50/0x204 ... dd D 0 2798 2764 0x00400208 Call trace: ... schedule+0x8c/0xbc io_schedule+0x1c/0x40 wait_on_page_bit_common+0x238/0x338 __lock_page+0x5c/0x68 write_cache_pages+0x194/0x500 generic_writepages+0x64/0xa4 blkdev_writepages+0x24/0x30 do_writepages+0x48/0xa8 __filemap_fdatawrite_range+0xac/0xd8 filemap_write_and_wait+0x30/0x84 __blkdev_put+0x88/0x204 blkdev_put+0xc4/0xe4 blkdev_close+0x28/0x38 __fput+0xe0/0x238 ____fput+0x1c/0x28 task_work_run+0xb0/0xe4 do_notify_resume+0xfc0/0x14bc work_pending+0x8/0x14 The problem appears related to the fact that my USB disk is terribly slow and that I have a lot of RAM in my system to cache things. Specifically my writes seem to be happening at ~15 MB/s and I've got ~4 GB of RAM in my system that can be used for buffering. To write 4 GB of buffer to disk thus takes ~4000 MB / ~15 MB/s = ~267 seconds. The 267 second number is a problem because in __blkdev_put() we call sync_blockdev() while holding the bd_mutex. Any other callers who want the bd_mutex will be blocked for the whole time. The problem is made worse because I believe blkdev_put() specifically tells other tasks (namely udev) to go try to access the device at right around the same time we're going to hold the mutex for a long time. Putting some traces around this (after disabling the hung task detector), I could confirm: dd: 437.608600: __blkdev_put() right before sync_blockdev() for sdb udevd: 437.623901: blkdev_open() right before blkdev_get() for sdb dd: 661.468451: __blkdev_put() right after sync_blockdev() for sdb udevd: 663.820426: blkdev_open() right after blkdev_get() for sdb A simple fix for this is to realize that sync_blockdev() works fine if you're not holding the mutex. Also, it's not the end of the world if you sync a little early (though it can have performance impacts). Thus we can make a guess that we're going to need to do the sync and then do it without holding the mutex. We still do one last sync with the mutex but it should be much, much faster. With this, my hung task warnings for my test case are gone. Signed-off-by: Douglas Anderson <dianders@chromium.org> Reviewed-by: Guenter Roeck <groeck@chromium.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-03-25 05:48:27 +08:00
/*
* Sync early if it looks like we're the last one. If someone else
* opens the block device between now and the decrement of bd_openers
* then we did a sync that we didn't need to, but that's not the end
* of the world and we want to avoid long (could be several minute)
* syncs while holding the mutex.
*/
if (bdev->bd_openers == 1)
sync_blockdev(bdev);
mutex_lock(&disk->open_mutex);
block: make blkdev_get/put() handle exclusive access Over time, block layer has accumulated a set of APIs dealing with bdev open, close, claim and release. * blkdev_get/put() are the primary open and close functions. * bd_claim/release() deal with exclusive open. * open/close_bdev_exclusive() are combination of open and claim and the other way around, respectively. * bd_link/unlink_disk_holder() to create and remove holder/slave symlinks. * open_by_devnum() wraps bdget() + blkdev_get(). The interface is a bit confusing and the decoupling of open and claim makes it impossible to properly guarantee exclusive access as in-kernel open + claim sequence can disturb the existing exclusive open even before the block layer knows the current open if for another exclusive access. Reorganize the interface such that, * blkdev_get() is extended to include exclusive access management. @holder argument is added and, if is @FMODE_EXCL specified, it will gain exclusive access atomically w.r.t. other exclusive accesses. * blkdev_put() is similarly extended. It now takes @mode argument and if @FMODE_EXCL is set, it releases an exclusive access. Also, when the last exclusive claim is released, the holder/slave symlinks are removed automatically. * bd_claim/release() and close_bdev_exclusive() are no longer necessary and either made static or removed. * bd_link_disk_holder() remains the same but bd_unlink_disk_holder() is no longer necessary and removed. * open_bdev_exclusive() becomes a simple wrapper around lookup_bdev() and blkdev_get(). It also has an unexpected extra bdev_read_only() test which probably should be moved into blkdev_get(). * open_by_devnum() is modified to take @holder argument and pass it to blkdev_get(). Most of bdev open/close operations are unified into blkdev_get/put() and most exclusive accesses are tested atomically at the open time (as it should). This cleans up code and removes some, both valid and invalid, but unnecessary all the same, corner cases. open_bdev_exclusive() and open_by_devnum() can use further cleanup - rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop special features. Well, let's leave them for another day. Most conversions are straight-forward. drbd conversion is a bit more involved as there was some reordering, but the logic should stay the same. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Neil Brown <neilb@suse.de> Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Acked-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Philipp Reisner <philipp.reisner@linbit.com> Cc: Peter Osterlund <petero2@telia.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Cc: Alex Elder <aelder@sgi.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: dm-devel@redhat.com Cc: drbd-dev@lists.linbit.com Cc: Leo Chen <leochen@broadcom.com> Cc: Scott Branden <sbranden@broadcom.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Cc: Joern Engel <joern@logfs.org> Cc: reiserfs-devel@vger.kernel.org Cc: Alexander Viro <viro@zeniv.linux.org.uk>
2010-11-13 18:55:17 +08:00
if (mode & FMODE_EXCL) {
struct block_device *whole = bdev_whole(bdev);
bool bdev_free;
/*
* Release a claim on the device. The holder fields
* are protected with bdev_lock. open_mutex is to
* synchronize disk_holder unlinking.
*/
spin_lock(&bdev_lock);
WARN_ON_ONCE(--bdev->bd_holders < 0);
WARN_ON_ONCE(--whole->bd_holders < 0);
if ((bdev_free = !bdev->bd_holders))
bdev->bd_holder = NULL;
if (!whole->bd_holders)
whole->bd_holder = NULL;
spin_unlock(&bdev_lock);
implement in-kernel gendisk events handling Currently, media presence polling for removeable block devices is done from userland. There are several issues with this. * Polling is done by periodically opening the device. For SCSI devices, the command sequence generated by such action involves a few different commands including TEST_UNIT_READY. This behavior, while perfectly legal, is different from Windows which only issues single command, GET_EVENT_STATUS_NOTIFICATION. Unfortunately, some ATAPI devices lock up after being periodically queried such command sequences. * There is no reliable and unintrusive way for a userland program to tell whether the target device is safe for media presence polling. For example, polling for media presence during an on-going burning session can make it fail. The polling program can avoid this by opening the device with O_EXCL but then it risks making a valid exclusive user of the device fail w/ -EBUSY. * Userland polling is unnecessarily heavy and in-kernel implementation is lighter and better coordinated (workqueue, timer slack). This patch implements framework for in-kernel disk event handling, which includes media presence polling. * bdops->check_events() is added, which supercedes ->media_changed(). It should check whether there's any pending event and return if so. Currently, two events are defined - DISK_EVENT_MEDIA_CHANGE and DISK_EVENT_EJECT_REQUEST. ->check_events() is guaranteed not to be called parallelly. * gendisk->events and ->async_events are added. These should be initialized by block driver before passing the device to add_disk(). The former contains the mask of all supported events and the latter the mask of all events which the device can report without polling. /sys/block/*/events[_async] export these to userland. * Kernel parameter block.events_dfl_poll_msecs controls the system polling interval (default is 0 which means disable) and /sys/block/*/events_poll_msecs control polling intervals for individual devices (default is -1 meaning use system setting). Note that if a device can report all supported events asynchronously and its polling interval isn't explicitly set, the device won't be polled regardless of the system polling interval. * If a device is opened exclusively with write access, event checking is automatically disabled until all write exclusive accesses are released. * There are event 'clearing' events. For example, both of currently defined events are cleared after the device has been successfully opened. This information is passed to ->check_events() callback using @clearing argument as a hint. * Event checking is always performed from system_nrt_wq and timer slack is set to 25% for polling. * Nothing changes for drivers which implement ->media_changed() but not ->check_events(). Going forward, all drivers will be converted to ->check_events() and ->media_change() will be dropped. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-12-09 03:57:37 +08:00
/*
* If this was the last claim, remove holder link and
* unblock evpoll if it was a write holder.
*/
2011-07-01 22:17:47 +08:00
if (bdev_free && bdev->bd_write_holder) {
disk_unblock_events(disk);
2011-07-01 22:17:47 +08:00
bdev->bd_write_holder = false;
implement in-kernel gendisk events handling Currently, media presence polling for removeable block devices is done from userland. There are several issues with this. * Polling is done by periodically opening the device. For SCSI devices, the command sequence generated by such action involves a few different commands including TEST_UNIT_READY. This behavior, while perfectly legal, is different from Windows which only issues single command, GET_EVENT_STATUS_NOTIFICATION. Unfortunately, some ATAPI devices lock up after being periodically queried such command sequences. * There is no reliable and unintrusive way for a userland program to tell whether the target device is safe for media presence polling. For example, polling for media presence during an on-going burning session can make it fail. The polling program can avoid this by opening the device with O_EXCL but then it risks making a valid exclusive user of the device fail w/ -EBUSY. * Userland polling is unnecessarily heavy and in-kernel implementation is lighter and better coordinated (workqueue, timer slack). This patch implements framework for in-kernel disk event handling, which includes media presence polling. * bdops->check_events() is added, which supercedes ->media_changed(). It should check whether there's any pending event and return if so. Currently, two events are defined - DISK_EVENT_MEDIA_CHANGE and DISK_EVENT_EJECT_REQUEST. ->check_events() is guaranteed not to be called parallelly. * gendisk->events and ->async_events are added. These should be initialized by block driver before passing the device to add_disk(). The former contains the mask of all supported events and the latter the mask of all events which the device can report without polling. /sys/block/*/events[_async] export these to userland. * Kernel parameter block.events_dfl_poll_msecs controls the system polling interval (default is 0 which means disable) and /sys/block/*/events_poll_msecs control polling intervals for individual devices (default is -1 meaning use system setting). Note that if a device can report all supported events asynchronously and its polling interval isn't explicitly set, the device won't be polled regardless of the system polling interval. * If a device is opened exclusively with write access, event checking is automatically disabled until all write exclusive accesses are released. * There are event 'clearing' events. For example, both of currently defined events are cleared after the device has been successfully opened. This information is passed to ->check_events() callback using @clearing argument as a hint. * Event checking is always performed from system_nrt_wq and timer slack is set to 25% for polling. * Nothing changes for drivers which implement ->media_changed() but not ->check_events(). Going forward, all drivers will be converted to ->check_events() and ->media_change() will be dropped. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-12-09 03:57:37 +08:00
}
}
implement in-kernel gendisk events handling Currently, media presence polling for removeable block devices is done from userland. There are several issues with this. * Polling is done by periodically opening the device. For SCSI devices, the command sequence generated by such action involves a few different commands including TEST_UNIT_READY. This behavior, while perfectly legal, is different from Windows which only issues single command, GET_EVENT_STATUS_NOTIFICATION. Unfortunately, some ATAPI devices lock up after being periodically queried such command sequences. * There is no reliable and unintrusive way for a userland program to tell whether the target device is safe for media presence polling. For example, polling for media presence during an on-going burning session can make it fail. The polling program can avoid this by opening the device with O_EXCL but then it risks making a valid exclusive user of the device fail w/ -EBUSY. * Userland polling is unnecessarily heavy and in-kernel implementation is lighter and better coordinated (workqueue, timer slack). This patch implements framework for in-kernel disk event handling, which includes media presence polling. * bdops->check_events() is added, which supercedes ->media_changed(). It should check whether there's any pending event and return if so. Currently, two events are defined - DISK_EVENT_MEDIA_CHANGE and DISK_EVENT_EJECT_REQUEST. ->check_events() is guaranteed not to be called parallelly. * gendisk->events and ->async_events are added. These should be initialized by block driver before passing the device to add_disk(). The former contains the mask of all supported events and the latter the mask of all events which the device can report without polling. /sys/block/*/events[_async] export these to userland. * Kernel parameter block.events_dfl_poll_msecs controls the system polling interval (default is 0 which means disable) and /sys/block/*/events_poll_msecs control polling intervals for individual devices (default is -1 meaning use system setting). Note that if a device can report all supported events asynchronously and its polling interval isn't explicitly set, the device won't be polled regardless of the system polling interval. * If a device is opened exclusively with write access, event checking is automatically disabled until all write exclusive accesses are released. * There are event 'clearing' events. For example, both of currently defined events are cleared after the device has been successfully opened. This information is passed to ->check_events() callback using @clearing argument as a hint. * Event checking is always performed from system_nrt_wq and timer slack is set to 25% for polling. * Nothing changes for drivers which implement ->media_changed() but not ->check_events(). Going forward, all drivers will be converted to ->check_events() and ->media_change() will be dropped. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-12-09 03:57:37 +08:00
2011-07-01 22:17:47 +08:00
/*
* Trigger event checking and tell drivers to flush MEDIA_CHANGE
* event. This is to ensure detection of media removal commanded
* from userland - e.g. eject(1).
*/
disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE);
2011-07-01 22:17:47 +08:00
if (bdev_is_partition(bdev))
blkdev_put_part(bdev, mode);
else
blkdev_put_whole(bdev, mode);
mutex_unlock(&disk->open_mutex);
blkdev_put_no_open(bdev);
[PATCH] lockdep: simplify some aspects of bd_mutex nesting When we open (actually blkdev_get) a partition we need to also open (get) the whole device that holds the partition. The involves some limited recursion. This patch tries to simplify some aspects of this. As well as opening the whole device, we need to increment ->bd_part_count when a partition is opened (this is used by rescan_partitions to avoid a rescan if any partition is active, as that would be confusing). The main change this patch makes is to move the inc/dec of bd_part_count into blkdev_{get,put} for the whole rather than doing it in blkdev_{get,put} for the partition. More specifically, we introduce __blkdev_get and __blkdev_put which do exactly what blkdev_{get,put} did, only with an extra "for_part" argument (blkget_{get,put} then call the __ version with a '0' for the extra argument). If for_part is 1, then the blkdev is being get(put) because a partition is being opened(closed) for the first(last) time, and so bd_part_count should be updated (on success). The particular advantage of pushing this function down is that the bd_mutex lock (which is needed to update bd_part_count) is already held at the lower level. Note that this slightly changes the semantics of bd_part_count. Instead of updating it whenever a partition is opened or released, it is now only updated on the first open or last release. This is an adequate semantic as it is only ever tested for "== 0". Having introduced these functions we remove the current bd_part_count updates from do_open (which is really the body of blkdev_get) and call __blkdev_get(... 1). Similarly in blkget_put we remove the old bd_part_count updates and call __blkget_put(..., 1). This call is moved to the end of __blkdev_put to avoid nested locks of bd_mutex. Finally the mutex_lock on whole->bd_mutex in do_open can be removed. It was only really needed to protect bd_part_count, and that is now managed (and protected) within the recursive call. The observation that bd_part_count is central to the locking issues, and the modifications to create __blkdev_put are from Peter Zijlstra. Cc: Ingo Molnar <mingo@elte.hu> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 18:36:16 +08:00
}
EXPORT_SYMBOL(blkdev_put);
/**
* lookup_bdev - lookup a struct block_device by name
* @pathname: special file representing the block device
* @dev: return value of the block device's dev_t
*
* Get a reference to the blockdevice at @pathname in the current
* namespace if possible and return it. Return ERR_PTR(error)
* otherwise.
*/
int lookup_bdev(const char *pathname, dev_t *dev)
{
struct inode *inode;
struct path path;
int error;
if (!pathname || !*pathname)
return -EINVAL;
error = kern_path(pathname, LOOKUP_FOLLOW, &path);
if (error)
return error;
inode = d_backing_inode(path.dentry);
error = -ENOTBLK;
if (!S_ISBLK(inode->i_mode))
goto out_path_put;
error = -EACCES;
if (!may_open_dev(&path))
goto out_path_put;
*dev = inode->i_rdev;
error = 0;
out_path_put:
path_put(&path);
return error;
}
EXPORT_SYMBOL(lookup_bdev);
Fix over-zealous flush_disk when changing device size. There are two cases when we call flush_disk. In one, the device has disappeared (check_disk_change) so any data will hold becomes irrelevant. In the oter, the device has changed size (check_disk_size_change) so data we hold may be irrelevant. In both cases it makes sense to discard any 'clean' buffers, so they will be read back from the device if needed. In the former case it makes sense to discard 'dirty' buffers as there will never be anywhere safe to write the data. In the second case it *does*not* make sense to discard dirty buffers as that will lead to file system corruption when you simply enlarge the containing devices. flush_disk calls __invalidate_devices. __invalidate_device calls both invalidate_inodes and invalidate_bdev. invalidate_inodes *does* discard I_DIRTY inodes and this does lead to fs corruption. invalidate_bev *does*not* discard dirty pages, but I don't really care about that at present. So this patch adds a flag to __invalidate_device (calling it __invalidate_device2) to indicate whether dirty buffers should be killed, and this is passed to invalidate_inodes which can choose to skip dirty inodes. flusk_disk then passes true from check_disk_change and false from check_disk_size_change. dm avoids tripping over this problem by calling i_size_write directly rathher than using check_disk_size_change. md does use check_disk_size_change and so is affected. This regression was introduced by commit 608aeef17a which causes check_disk_size_change to call flush_disk, so it is suitable for any kernel since 2.6.27. Cc: stable@kernel.org Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: Andrew Patterson <andrew.patterson@hp.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: NeilBrown <neilb@suse.de>
2011-02-24 14:25:47 +08:00
int __invalidate_device(struct block_device *bdev, bool kill_dirty)
{
struct super_block *sb = get_super(bdev);
int res = 0;
if (sb) {
/*
* no need to lock the super, get_super holds the
* read mutex so the filesystem cannot go away
* under us (->put_super runs with the write lock
* hold).
*/
shrink_dcache_sb(sb);
Fix over-zealous flush_disk when changing device size. There are two cases when we call flush_disk. In one, the device has disappeared (check_disk_change) so any data will hold becomes irrelevant. In the oter, the device has changed size (check_disk_size_change) so data we hold may be irrelevant. In both cases it makes sense to discard any 'clean' buffers, so they will be read back from the device if needed. In the former case it makes sense to discard 'dirty' buffers as there will never be anywhere safe to write the data. In the second case it *does*not* make sense to discard dirty buffers as that will lead to file system corruption when you simply enlarge the containing devices. flush_disk calls __invalidate_devices. __invalidate_device calls both invalidate_inodes and invalidate_bdev. invalidate_inodes *does* discard I_DIRTY inodes and this does lead to fs corruption. invalidate_bev *does*not* discard dirty pages, but I don't really care about that at present. So this patch adds a flag to __invalidate_device (calling it __invalidate_device2) to indicate whether dirty buffers should be killed, and this is passed to invalidate_inodes which can choose to skip dirty inodes. flusk_disk then passes true from check_disk_change and false from check_disk_size_change. dm avoids tripping over this problem by calling i_size_write directly rathher than using check_disk_size_change. md does use check_disk_size_change and so is affected. This regression was introduced by commit 608aeef17a which causes check_disk_size_change to call flush_disk, so it is suitable for any kernel since 2.6.27. Cc: stable@kernel.org Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: Andrew Patterson <andrew.patterson@hp.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: NeilBrown <neilb@suse.de>
2011-02-24 14:25:47 +08:00
res = invalidate_inodes(sb, kill_dirty);
drop_super(sb);
}
invalidate_bdev(bdev);
return res;
}
EXPORT_SYMBOL(__invalidate_device);
void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
{
struct inode *inode, *old_inode = NULL;
spin_lock(&blockdev_superblock->s_inode_list_lock);
list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
struct address_space *mapping = inode->i_mapping;
block: protect iterate_bdevs() against concurrent close If a block device is closed while iterate_bdevs() is handling it, the following NULL pointer dereference occurs because bdev->b_disk is NULL in bdev_get_queue(), which is called from blk_get_backing_dev_info() (in turn called by the mapping_cap_writeback_dirty() call in __filemap_fdatawrite_range()): BUG: unable to handle kernel NULL pointer dereference at 0000000000000508 IP: [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20 PGD 9e62067 PUD 9ee8067 PMD 0 Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 1 PID: 2422 Comm: sync Not tainted 4.5.0-rc7+ #400 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) task: ffff880009f4d700 ti: ffff880009f5c000 task.ti: ffff880009f5c000 RIP: 0010:[<ffffffff81314790>] [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20 RSP: 0018:ffff880009f5fe68 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff88000ec17a38 RCX: ffffffff81a4e940 RDX: 7fffffffffffffff RSI: 0000000000000000 RDI: ffff88000ec176c0 RBP: ffff880009f5fe68 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffff88000ec17860 R13: ffffffff811b25c0 R14: ffff88000ec178e0 R15: ffff88000ec17a38 FS: 00007faee505d700(0000) GS:ffff88000fb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000508 CR3: 0000000009e8a000 CR4: 00000000000006e0 Stack: ffff880009f5feb8 ffffffff8112e7f5 0000000000000000 7fffffffffffffff 0000000000000000 0000000000000000 7fffffffffffffff 0000000000000001 ffff88000ec178e0 ffff88000ec17860 ffff880009f5fec8 ffffffff8112e81f Call Trace: [<ffffffff8112e7f5>] __filemap_fdatawrite_range+0x85/0x90 [<ffffffff8112e81f>] filemap_fdatawrite+0x1f/0x30 [<ffffffff811b25d6>] fdatawrite_one_bdev+0x16/0x20 [<ffffffff811bc402>] iterate_bdevs+0xf2/0x130 [<ffffffff811b2763>] sys_sync+0x63/0x90 [<ffffffff815d4272>] entry_SYSCALL_64_fastpath+0x12/0x76 Code: 0f 1f 44 00 00 48 8b 87 f0 00 00 00 55 48 89 e5 <48> 8b 80 08 05 00 00 5d RIP [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20 RSP <ffff880009f5fe68> CR2: 0000000000000508 ---[ end trace 2487336ceb3de62d ]--- The crash is easily reproducible by running the following command, if an msleep(100) is inserted before the call to func() in iterate_devs(): while :; do head -c1 /dev/nullb0; done > /dev/null & while :; do sync; done Fix it by holding the bd_mutex across the func() call and only calling func() if the bdev is opened. Cc: stable@vger.kernel.org Fixes: 5c0d6b60a0ba ("vfs: Create function for iterating over block devices") Reported-and-tested-by: Wei Fang <fangwei1@huawei.com> Signed-off-by: Rabin Vincent <rabinv@axis.com> Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-12-01 16:18:28 +08:00
struct block_device *bdev;
spin_lock(&inode->i_lock);
if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) ||
mapping->nrpages == 0) {
spin_unlock(&inode->i_lock);
continue;
}
__iget(inode);
spin_unlock(&inode->i_lock);
spin_unlock(&blockdev_superblock->s_inode_list_lock);
/*
* We hold a reference to 'inode' so it couldn't have been
* removed from s_inodes list while we dropped the
* s_inode_list_lock We cannot iput the inode now as we can
* be holding the last reference and we cannot iput it under
* s_inode_list_lock. So we keep the reference and iput it
* later.
*/
iput(old_inode);
old_inode = inode;
block: protect iterate_bdevs() against concurrent close If a block device is closed while iterate_bdevs() is handling it, the following NULL pointer dereference occurs because bdev->b_disk is NULL in bdev_get_queue(), which is called from blk_get_backing_dev_info() (in turn called by the mapping_cap_writeback_dirty() call in __filemap_fdatawrite_range()): BUG: unable to handle kernel NULL pointer dereference at 0000000000000508 IP: [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20 PGD 9e62067 PUD 9ee8067 PMD 0 Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 1 PID: 2422 Comm: sync Not tainted 4.5.0-rc7+ #400 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) task: ffff880009f4d700 ti: ffff880009f5c000 task.ti: ffff880009f5c000 RIP: 0010:[<ffffffff81314790>] [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20 RSP: 0018:ffff880009f5fe68 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff88000ec17a38 RCX: ffffffff81a4e940 RDX: 7fffffffffffffff RSI: 0000000000000000 RDI: ffff88000ec176c0 RBP: ffff880009f5fe68 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffff88000ec17860 R13: ffffffff811b25c0 R14: ffff88000ec178e0 R15: ffff88000ec17a38 FS: 00007faee505d700(0000) GS:ffff88000fb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000508 CR3: 0000000009e8a000 CR4: 00000000000006e0 Stack: ffff880009f5feb8 ffffffff8112e7f5 0000000000000000 7fffffffffffffff 0000000000000000 0000000000000000 7fffffffffffffff 0000000000000001 ffff88000ec178e0 ffff88000ec17860 ffff880009f5fec8 ffffffff8112e81f Call Trace: [<ffffffff8112e7f5>] __filemap_fdatawrite_range+0x85/0x90 [<ffffffff8112e81f>] filemap_fdatawrite+0x1f/0x30 [<ffffffff811b25d6>] fdatawrite_one_bdev+0x16/0x20 [<ffffffff811bc402>] iterate_bdevs+0xf2/0x130 [<ffffffff811b2763>] sys_sync+0x63/0x90 [<ffffffff815d4272>] entry_SYSCALL_64_fastpath+0x12/0x76 Code: 0f 1f 44 00 00 48 8b 87 f0 00 00 00 55 48 89 e5 <48> 8b 80 08 05 00 00 5d RIP [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20 RSP <ffff880009f5fe68> CR2: 0000000000000508 ---[ end trace 2487336ceb3de62d ]--- The crash is easily reproducible by running the following command, if an msleep(100) is inserted before the call to func() in iterate_devs(): while :; do head -c1 /dev/nullb0; done > /dev/null & while :; do sync; done Fix it by holding the bd_mutex across the func() call and only calling func() if the bdev is opened. Cc: stable@vger.kernel.org Fixes: 5c0d6b60a0ba ("vfs: Create function for iterating over block devices") Reported-and-tested-by: Wei Fang <fangwei1@huawei.com> Signed-off-by: Rabin Vincent <rabinv@axis.com> Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-12-01 16:18:28 +08:00
bdev = I_BDEV(inode);
mutex_lock(&bdev->bd_disk->open_mutex);
block: protect iterate_bdevs() against concurrent close If a block device is closed while iterate_bdevs() is handling it, the following NULL pointer dereference occurs because bdev->b_disk is NULL in bdev_get_queue(), which is called from blk_get_backing_dev_info() (in turn called by the mapping_cap_writeback_dirty() call in __filemap_fdatawrite_range()): BUG: unable to handle kernel NULL pointer dereference at 0000000000000508 IP: [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20 PGD 9e62067 PUD 9ee8067 PMD 0 Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 1 PID: 2422 Comm: sync Not tainted 4.5.0-rc7+ #400 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) task: ffff880009f4d700 ti: ffff880009f5c000 task.ti: ffff880009f5c000 RIP: 0010:[<ffffffff81314790>] [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20 RSP: 0018:ffff880009f5fe68 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff88000ec17a38 RCX: ffffffff81a4e940 RDX: 7fffffffffffffff RSI: 0000000000000000 RDI: ffff88000ec176c0 RBP: ffff880009f5fe68 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffff88000ec17860 R13: ffffffff811b25c0 R14: ffff88000ec178e0 R15: ffff88000ec17a38 FS: 00007faee505d700(0000) GS:ffff88000fb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000508 CR3: 0000000009e8a000 CR4: 00000000000006e0 Stack: ffff880009f5feb8 ffffffff8112e7f5 0000000000000000 7fffffffffffffff 0000000000000000 0000000000000000 7fffffffffffffff 0000000000000001 ffff88000ec178e0 ffff88000ec17860 ffff880009f5fec8 ffffffff8112e81f Call Trace: [<ffffffff8112e7f5>] __filemap_fdatawrite_range+0x85/0x90 [<ffffffff8112e81f>] filemap_fdatawrite+0x1f/0x30 [<ffffffff811b25d6>] fdatawrite_one_bdev+0x16/0x20 [<ffffffff811bc402>] iterate_bdevs+0xf2/0x130 [<ffffffff811b2763>] sys_sync+0x63/0x90 [<ffffffff815d4272>] entry_SYSCALL_64_fastpath+0x12/0x76 Code: 0f 1f 44 00 00 48 8b 87 f0 00 00 00 55 48 89 e5 <48> 8b 80 08 05 00 00 5d RIP [<ffffffff81314790>] blk_get_backing_dev_info+0x10/0x20 RSP <ffff880009f5fe68> CR2: 0000000000000508 ---[ end trace 2487336ceb3de62d ]--- The crash is easily reproducible by running the following command, if an msleep(100) is inserted before the call to func() in iterate_devs(): while :; do head -c1 /dev/nullb0; done > /dev/null & while :; do sync; done Fix it by holding the bd_mutex across the func() call and only calling func() if the bdev is opened. Cc: stable@vger.kernel.org Fixes: 5c0d6b60a0ba ("vfs: Create function for iterating over block devices") Reported-and-tested-by: Wei Fang <fangwei1@huawei.com> Signed-off-by: Rabin Vincent <rabinv@axis.com> Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-12-01 16:18:28 +08:00
if (bdev->bd_openers)
func(bdev, arg);
mutex_unlock(&bdev->bd_disk->open_mutex);
spin_lock(&blockdev_superblock->s_inode_list_lock);
}
spin_unlock(&blockdev_superblock->s_inode_list_lock);
iput(old_inode);
}