From 54ef6df3f3f1353d99c80c437259d317b2cd1cbd Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 27 Oct 2014 21:11:27 -0700 Subject: rcu: Provide counterpart to rcu_dereference() for non-RCU situations Although rcu_dereference() and friends can be used in situations where object lifetimes are being managed by something other than RCU, the resulting sparse and lockdep-RCU noise can be annoying. This commit therefore supplies a lockless_dereference(), which provides the protection for dereferences without the RCU-related debugging noise. Reported-by: Al Viro Signed-off-by: Paul E. McKenney Signed-off-by: Al Viro --- include/linux/rcupdate.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index a4a819ffb2d1..53ff1a752d7e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -616,6 +616,21 @@ static inline void rcu_preempt_sleep_check(void) */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) +/** + * lockless_dereference() - safely load a pointer for later dereference + * @p: The pointer to load + * + * Similar to rcu_dereference(), but for situations where the pointed-to + * object's lifetime is managed by something other than RCU. That + * "something other" might be reference counting or simple immortality. + */ +#define lockless_dereference(p) \ +({ \ + typeof(p) _________p1 = ACCESS_ONCE(p); \ + smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ + (_________p1); \ +}) + /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to -- cgit v1.2.3 From d1b72cc6d8cb766c802fdc70a5edc2f0ba8a2b57 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 27 Oct 2014 15:42:01 +0100 Subject: overlayfs: fix lockdep misannotation In an overlay directory that shadows an empty lower directory, say /mnt/a/empty102, do: touch /mnt/a/empty102/x unlink /mnt/a/empty102/x rmdir /mnt/a/empty102 It's actually harmless, but needs another level of nesting between I_MUTEX_CHILD and I_MUTEX_NORMAL. Signed-off-by: Miklos Szeredi Tested-by: David Howells Signed-off-by: Al Viro --- fs/namei.c | 2 +- fs/overlayfs/readdir.c | 2 +- include/linux/fs.h | 9 ++++++--- 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index 42df664e95e5..922f27068c4c 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2497,7 +2497,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) } mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD); + mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT2); return NULL; } EXPORT_SYMBOL(lock_rename); diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 3fbf0d306e12..401f0840f5cc 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -571,7 +571,7 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list) { struct ovl_cache_entry *p; - mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_CHILD); list_for_each_entry(p, list, l_node) { struct dentry *dentry; diff --git a/include/linux/fs.h b/include/linux/fs.h index 4e41a4a331bb..01036262095f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -639,11 +639,13 @@ static inline int inode_unhashed(struct inode *inode) * 2: child/target * 3: xattr * 4: second non-directory - * The last is for certain operations (such as rename) which lock two + * 5: second parent (when locking independent directories in rename) + * + * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is - * parent -> child -> normal -> xattr -> second non-directory + * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { @@ -651,7 +653,8 @@ enum inode_i_mutex_lock_class I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, - I_MUTEX_NONDIR2 + I_MUTEX_NONDIR2, + I_MUTEX_PARENT2, }; void lock_two_nondirectories(struct inode *, struct inode*); -- cgit v1.2.3 From b2de525f095708b2adbadaec3f1e4017a23d1e09 Mon Sep 17 00:00:00 2001 From: David Jeffery Date: Mon, 29 Sep 2014 10:21:10 -0400 Subject: Return short read or 0 at end of a raw device, not EIO Author: David Jeffery Changes to the basic direct I/O code have broken the raw driver when reading to the end of a raw device. Instead of returning a short read for a read that extends partially beyond the device's end or 0 when at the end of the device, these reads now return EIO. The raw driver needs the same end of device handling as was added for normal block devices. Using blkdev_read_iter, which has the needed size checks, prevents the EIO conditions at the end of the device. Signed-off-by: David Jeffery Signed-off-by: Al Viro --- drivers/char/raw.c | 2 +- fs/block_dev.c | 3 ++- include/linux/fs.h | 1 + 3 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/raw.c b/drivers/char/raw.c index 0102dc788608..a24891b97547 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -285,7 +285,7 @@ static long raw_ctl_compat_ioctl(struct file *file, unsigned int cmd, static const struct file_operations raw_fops = { .read = new_sync_read, - .read_iter = generic_file_read_iter, + .read_iter = blkdev_read_iter, .write = new_sync_write, .write_iter = blkdev_write_iter, .fsync = blkdev_fsync, diff --git a/fs/block_dev.c b/fs/block_dev.c index cc9d4114cda0..1d9c9f3754f8 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1585,7 +1585,7 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) } EXPORT_SYMBOL_GPL(blkdev_write_iter); -static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) +ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct inode *bd_inode = file->f_mapping->host; @@ -1599,6 +1599,7 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) iov_iter_truncate(to, size); return generic_file_read_iter(iocb, to); } +EXPORT_SYMBOL_GPL(blkdev_read_iter); /* * Try to release a page associated with block device when the system diff --git a/include/linux/fs.h b/include/linux/fs.h index 01036262095f..9ab779e8a63c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2469,6 +2469,7 @@ extern ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo extern ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); /* fs/block_dev.c */ +extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from); extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync); -- cgit v1.2.3