From d28574e043e8b7cb35482de6e9a553118a32803d Mon Sep 17 00:00:00 2001 From: Maxim Patlasov Date: Fri, 26 Oct 2012 19:50:04 +0400 Subject: mm: minor cleanup of iov_iter_single_seg_count() The function does not modify iov_iter which 'i' points to. Signed-off-by: Maxim Patlasov Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7617ee04f066..7d2e893ec3d1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -301,7 +301,7 @@ size_t iov_iter_copy_from_user(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); -size_t iov_iter_single_seg_count(struct iov_iter *i); +size_t iov_iter_single_seg_count(const struct iov_iter *i); static inline void iov_iter_init(struct iov_iter *i, const struct iovec *iov, unsigned long nr_segs, -- cgit v1.2.2 From 496ad9aa8ef448058e36ca7a787c61f2e63f0f54 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 23 Jan 2013 17:07:38 -0500 Subject: new helper: file_inode(file) Signed-off-by: Al Viro --- include/linux/fs.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7617ee04f066..3ab69777b4d8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2217,6 +2217,11 @@ static inline bool execute_ok(struct inode *inode) return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } +static inline struct inode *file_inode(struct file *f) +{ + return f->f_path.dentry->d_inode; +} + /* * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. @@ -2239,7 +2244,7 @@ static inline int get_write_access(struct inode *inode) } static inline int deny_write_access(struct file *file) { - struct inode *inode = file->f_path.dentry->d_inode; + struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline void put_write_access(struct inode * inode) @@ -2249,7 +2254,7 @@ static inline void put_write_access(struct inode * inode) static inline void allow_write_access(struct file *file) { if (file) - atomic_inc(&file->f_path.dentry->d_inode->i_writecount); + atomic_inc(&file_inode(file)->i_writecount); } #ifdef CONFIG_IMA static inline void i_readcount_dec(struct inode *inode) -- cgit v1.2.2 From 3dadecce20603aa380023c65e6f55f108fd5e952 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 24 Jan 2013 02:18:08 -0500 Subject: switch vfs_getattr() to struct path Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3ab69777b4d8..7f471520b88b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2468,7 +2468,7 @@ extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern int generic_readlink(struct dentry *, char __user *, int); extern void generic_fillattr(struct inode *, struct kstat *); -extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); +extern int vfs_getattr(struct path *, struct kstat *); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); -- cgit v1.2.2 From ecf3d1f1aa74da0d632b651a2e05a911f60e92c0 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 20 Feb 2013 11:19:05 -0500 Subject: vfs: kill FS_REVAL_DOT by adding a d_weak_revalidate dentry op The following set of operations on a NFS client and server will cause server# mkdir a client# cd a server# mv a a.bak client# sleep 30 # (or whatever the dir attrcache timeout is) client# stat . stat: cannot stat `.': Stale NFS file handle Obviously, we should not be getting an ESTALE error back there since the inode still exists on the server. The problem is that the lookup code will call d_revalidate on the dentry that "." refers to, because NFS has FS_REVAL_DOT set. nfs_lookup_revalidate will see that the parent directory has changed and will try to reverify the dentry by redoing a LOOKUP. That of course fails, so the lookup code returns ESTALE. The problem here is that d_revalidate is really a bad fit for this case. What we really want to know at this point is whether the inode is still good or not, but we don't really care what name it goes by or whether the dcache is still valid. Add a new d_op->d_weak_revalidate operation and have complete_walk call that instead of d_revalidate. The intent there is to allow for a "weaker" d_revalidate that just checks to see whether the inode is still good. This is also gives us an opportunity to kill off the FS_REVAL_DOT special casing. [AV: changed method name, added note in porting, fixed confusion re having it possibly called from RCU mode (it won't be)] Cc: NeilBrown Signed-off-by: Jeff Layton Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7f471520b88b..da94011ae83c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1807,7 +1807,6 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */ -#define FS_REVAL_DOT 16384 /* Check the paths ".", ".." for staleness */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); -- cgit v1.2.2 From 182be684784334598eee1d90274e7f7aa0063616 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 24 Jan 2013 02:21:54 -0500 Subject: kill f_vfsmnt very few users left... Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index da94011ae83c..c766afd1e684 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -769,7 +769,6 @@ struct file { } f_u; struct path f_path; #define f_dentry f_path.dentry -#define f_vfsmnt f_path.mnt const struct file_operations *f_op; /* -- cgit v1.2.2 From 7bb307e894d51308aa0582a8c4cc5875bbc645b9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Feb 2013 14:51:48 -0500 Subject: export kernel_write(), convert open-coded instances Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index c766afd1e684..d858363a7c17 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2277,6 +2277,7 @@ static inline void i_readcount_inc(struct inode *inode) extern int do_pipe_flags(int *, int); extern int kernel_read(struct file *, loff_t, char *, unsigned long); +extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ -- cgit v1.2.2 From dd37978c50bc8b354e5c4633f69387f16572fdac Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 1 Mar 2013 19:48:30 -0500 Subject: cache the value of file_inode() in struct file Note that this thing does *not* contribute to inode refcount; it's pinned down by dentry. Signed-off-by: Al Viro --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4e686a099465..74a907b8b950 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -769,6 +769,7 @@ struct file { } f_u; struct path f_path; #define f_dentry f_path.dentry + struct inode *f_inode; /* cached value */ const struct file_operations *f_op; /* @@ -2217,7 +2218,7 @@ static inline bool execute_ok(struct inode *inode) static inline struct inode *file_inode(struct file *f) { - return f->f_path.dentry->d_inode; + return f->f_inode; } /* -- cgit v1.2.2 From 7f78e0351394052e1a6293e175825eb5c7869507 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 2 Mar 2013 19:39:14 -0800 Subject: fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn Acked-by: Kees Cook Reported-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 74a907b8b950..2c28271ab9d4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1825,6 +1825,8 @@ struct file_system_type { struct lock_class_key i_mutex_dir_key; }; +#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) + extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_bdev(struct file_system_type *fs_type, -- cgit v1.2.2