From c89681ed7d0e4a61d35bdc12c06c6733b718b2cb Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 22 Jun 2006 14:47:22 -0700 Subject: [PATCH] remove steal_locks() This patch removes the steal_locks() function. steal_locks() doesn't work correctly with any filesystem that does it's own lock management, including NFS, CIFS, etc. In addition it has weird semantics on local filesystems in case tasks sharing file-descriptor tables are doing POSIX locking operations in parallel to execve(). The steal_locks() function has an effect on applications doing: clone(CLONE_FILES) /* in child */ lock execve lock POSIX locks acquired before execve (by "child", "parent" or any further task sharing files_struct) will after the execve be owned exclusively by "child". According to Chris Wright some LSB/LTP kind of suite triggers without the stealing behavior, but there's no known real-world application that would also fail. Apps using NPTL are not affected, since all other threads are killed before execve. Apps using LinuxThreads are only affected if they - have multiple threads during exec (LinuxThreads doesn't kill other threads, the app may do it with pthread_kill_other_threads_np()) - rely on POSIX locks being inherited across exec Both conditions are documented, but not their interaction. Apps using clone() natively are affected if they - use clone(CLONE_FILES) - rely on POSIX locks being inherited across exec The above scenarios are unlikely, but possible. If the patch is vetoed, there's a plan B, that involves mostly keeping the weird stealing semantics, but changing the way lock ownership is handled so that network and local filesystems work consistently. That would add more complexity though, so this solution seems to be preferred by most people. Signed-off-by: Miklos Szeredi Cc: Trond Myklebust Cc: Matthew Wilcox Cc: Chris Wright Cc: Christoph Hellwig Cc: Steven French Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 ecc8c2c3d8c..73c7d6f04b3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -782,7 +782,6 @@ extern int setlease(struct file *, long, struct file_lock **); extern int lease_modify(struct file_lock **, int); extern int lock_may_read(struct inode *, loff_t start, unsigned long count); extern int lock_may_write(struct inode *, loff_t start, unsigned long count); -extern void steal_locks(fl_owner_t from); struct fasync_struct { int magic; -- cgit v1.2.3 From 454e2398be9b9fa30433fccc548db34d19aa9958 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 23 Jun 2006 02:02:57 -0700 Subject: [PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells Acked-by: Al Viro Cc: Nathan Scott Cc: Roland Dreier Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 73c7d6f04b3..3e50dd24af8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1269,23 +1269,26 @@ find_exported_dentry(struct super_block *sb, void *obj, void *parent, struct file_system_type { const char *name; int fs_flags; - struct super_block *(*get_sb) (struct file_system_type *, int, - const char *, void *); + int (*get_sb) (struct file_system_type *, int, + const char *, void *, struct vfsmount *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct list_head fs_supers; }; -struct super_block *get_sb_bdev(struct file_system_type *fs_type, +extern int get_sb_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int)); -struct super_block *get_sb_single(struct file_system_type *fs_type, + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt); +extern int get_sb_single(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); -struct super_block *get_sb_nodev(struct file_system_type *fs_type, + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt); +extern int get_sb_nodev(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); @@ -1296,8 +1299,10 @@ struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), void *data); -struct super_block *get_sb_pseudo(struct file_system_type *, char *, - struct super_operations *ops, unsigned long); +extern int get_sb_pseudo(struct file_system_type *, char *, + struct super_operations *ops, unsigned long, + struct vfsmount *mnt); +extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb); int __put_super(struct super_block *sb); int __put_super_and_need_restart(struct super_block *sb); void unnamed_dev_init(void); -- cgit v1.2.3 From 726c334223180e3c0197cc980a432681370d4baf Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 23 Jun 2006 02:02:58 -0700 Subject: [PATCH] VFS: Permit filesystem to perform statfs with a known root dentry Give the statfs superblock operation a dentry pointer rather than a superblock pointer. This complements the get_sb() patch. That reduced the significance of sb->s_root, allowing NFS to place a fake root there. However, NFS does require a dentry to use as a target for the statfs operation. This permits the root in the vfsmount to be used instead. linux/mount.h has been added where necessary to make allyesconfig build successfully. Interest has also been expressed for use with the FUSE and XFS filesystems. Signed-off-by: David Howells Acked-by: Al Viro Cc: Nathan Scott Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3e50dd24af8..c823a3815e2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1096,7 +1096,7 @@ struct super_operations { int (*sync_fs)(struct super_block *sb, int wait); void (*write_super_lockfs) (struct super_block *); void (*unlockfs) (struct super_block *); - int (*statfs) (struct super_block *, struct kstatfs *); + int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*clear_inode) (struct inode *); void (*umount_begin) (struct super_block *); @@ -1325,7 +1325,7 @@ extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int); extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *, struct vfsmount *); -extern int vfs_statfs(struct super_block *, struct kstatfs *); +extern int vfs_statfs(struct dentry *, struct kstatfs *); /* /sys/fs */ extern struct subsystem fs_subsys; @@ -1746,7 +1746,7 @@ extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, void *, filldir_t); extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *); -extern int simple_statfs(struct super_block *, struct kstatfs *); +extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); -- cgit v1.2.3 From 2d1db3b1170db4e8bf0531dd636742269c2cf579 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 23 Jun 2006 02:03:33 -0700 Subject: [PATCH] page migration cleanup: pass "mapping" to migration functions Change handling of address spaces. Pass a pointer to the address space in which the page is migrated to all migration function. This avoids repeatedly having to retrieve the address space pointer from the page and checking it for validity. The old page mapping will change once migration has gone to a certain step, so it is less confusing to have the pointer always available. Move the setting of the mapping and index for the new page into migrate_pages(). Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index c823a3815e2..e917403f4d5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -376,7 +376,8 @@ struct address_space_operations { struct page* (*get_xip_page)(struct address_space *, sector_t, int); /* migrate the contents of a page to the specified target */ - int (*migratepage) (struct page *, struct page *); + int (*migratepage) (struct address_space *, + struct page *, struct page *); }; struct backing_dev_info; @@ -1772,7 +1773,8 @@ extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *, size_t, loff_t *, const void *, size_t); #ifdef CONFIG_MIGRATION -extern int buffer_migrate_page(struct page *, struct page *); +extern int buffer_migrate_page(struct address_space *, + struct page *, struct page *); #else #define buffer_migrate_page NULL #endif -- cgit v1.2.3 From 75e1fcc0b18df0a65ab113198e9dc0e98999a08c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 23 Jun 2006 02:05:12 -0700 Subject: [PATCH] vfs: add lock owner argument to flush operation Pass the POSIX lock owner ID to the flush operation. This is useful for filesystems which don't want to store any locking state in inode->i_flock but want to handle locking/unlocking POSIX locks internally. FUSE is one such filesystem but I think it possible that some network filesystems would need this also. Also add a flag to indicate that a POSIX locking request was generated by close(), so filesystems using the above feature won't send an extra locking request in this case. Signed-off-by: Miklos Szeredi Cc: Trond Myklebust Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 e917403f4d5..56d8bf0d0a7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -683,6 +683,7 @@ extern spinlock_t files_lock; #define FL_FLOCK 2 #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_LEASE 32 /* lease held on this file */ +#define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ /* @@ -1025,7 +1026,7 @@ struct file_operations { long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); - int (*flush) (struct file *); + int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, struct dentry *, int datasync); int (*aio_fsync) (struct kiocb *, int datasync); -- cgit v1.2.3 From b0904e147f7cbe4be3b4dae49ddccd627bb66f16 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 23 Jun 2006 02:05:13 -0700 Subject: [PATCH] fs/locks.c: make posix_locks_deadlock() static We can now make posix_locks_deadlock() static. Signed-off-by: Adrian Bunk Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 56d8bf0d0a7..dba4cbd157e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -776,7 +776,6 @@ extern int posix_lock_file_conf(struct file *, struct file_lock *, struct file_l extern int posix_lock_file(struct file *, struct file_lock *); extern int posix_lock_file_wait(struct file *, struct file_lock *); extern int posix_unblock_lock(struct file *, struct file_lock *); -extern int posix_locks_deadlock(struct file_lock *, struct file_lock *); extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags); extern void lease_get_mtime(struct inode *, struct timespec *time); -- cgit v1.2.3