diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index 4303614..5ade4a8 100644 --- a/Documentation/filesystems/00-INDEX +++ b/Documentation/filesystems/00-INDEX @@ -112,6 +112,8 @@ udf.txt - info and mount options for the UDF filesystem. ufs.txt - info on the ufs filesystem. +unionfs/ + - info on the unionfs filesystem vfat.txt - info on using the VFAT filesystem used in Windows NT and Windows 95 vfs.txt diff --git a/Documentation/filesystems/unionfs/00-INDEX b/Documentation/filesystems/unionfs/00-INDEX new file mode 100644 index 0000000..96fdf67 --- /dev/null +++ b/Documentation/filesystems/unionfs/00-INDEX @@ -0,0 +1,10 @@ +00-INDEX + - this file. +concepts.txt + - A brief introduction of concepts. +issues.txt + - A summary of known issues with unionfs. +rename.txt + - Information regarding rename operations. +usage.txt + - Usage information and examples. diff --git a/Documentation/filesystems/unionfs/concepts.txt b/Documentation/filesystems/unionfs/concepts.txt new file mode 100644 index 0000000..b853788 --- /dev/null +++ b/Documentation/filesystems/unionfs/concepts.txt @@ -0,0 +1,287 @@ +Unionfs 2.x CONCEPTS: +===================== + +This file describes the concepts needed by a namespace unification file +system. + + +Branch Priority: +================ + +Each branch is assigned a unique priority - starting from 0 (highest +priority). No two branches can have the same priority. + + +Branch Mode: +============ + +Each branch is assigned a mode - read-write or read-only. This allows +directories on media mounted read-write to be used in a read-only manner. + + +Whiteouts: +========== + +A whiteout removes a file name from the namespace. Whiteouts are needed when +one attempts to remove a file on a read-only branch. + +Suppose we have a two-branch union, where branch 0 is read-write and branch +1 is read-only. And a file 'foo' on branch 1: + +./b0/ +./b1/ +./b1/foo + +The unified view would simply be: + +./union/ +./union/foo + +Since 'foo' is stored on a read-only branch, it cannot be removed. A +whiteout is used to remove the name 'foo' from the unified namespace. Again, +since branch 1 is read-only, the whiteout cannot be created there. So, we +try on a higher priority (lower numerically) branch and create the whiteout +there. + +./b0/ +./b0/.wh.foo +./b1/ +./b1/foo + +Later, when Unionfs traverses branches (due to lookup or readdir), it +eliminate 'foo' from the namespace (as well as the whiteout itself.) + + +Opaque Directories: +=================== + +Assume we have a unionfs mount comprising of two branches. Branch 0 is +empty; branch 1 has the directory /a and file /a/f. Let's say we mount a +union of branch 0 as read-write and branch 1 as read-only. Now, let's say +we try to perform the following operation in the union: + + rm -fr a + +Because branch 1 is not writable, we cannot physically remove the file /a/f +or the directory /a. So instead, we will create a whiteout in branch 0 +named /.wh.a, masking out the name "a" from branch 1. Next, let's say we +try to create a directory named "a" as follows: + + mkdir a + +Because we have a whiteout for "a" already, Unionfs behaves as if "a" +doesn't exist, and thus will delete the whiteout and replace it with an +actual directory named "a". + +The problem now is that if you try to "ls" in the union, Unionfs will +perform is normal directory name unification, for *all* directories named +"a" in all branches. This will cause the file /a/f from branch 1 to +re-appear in the union's namespace, which violates Unix semantics. + +To avoid this problem, we have a different form of whiteouts for +directories, called "opaque directories" (same as BSD Union Mount does). +Whenever we replace a whiteout with a directory, that directory is marked as +opaque. In Unionfs 2.x, it means that we create a file named +/a/.wh.__dir_opaque in branch 0, after having created directory /a there. +When unionfs notices that a directory is opaque, it stops all namespace +operations (including merging readdir contents) at that opaque directory. +This prevents re-exposing names from masked out directories. + + +Duplicate Elimination: +====================== + +It is possible for files on different branches to have the same name. +Unionfs then has to select which instance of the file to show to the user. +Given the fact that each branch has a priority associated with it, the +simplest solution is to take the instance from the highest priority +(numerically lowest value) and "hide" the others. + + +Unlinking: +========= + +Unlink operation on non-directory instances is optimized to remove the +maximum possible objects in case multiple underlying branches have the same +file name. The unlink operation will first try to delete file instances +from highest priority branch and then move further to delete from remaining +branches in order of their decreasing priority. Consider a case (F..D..F), +where F is a file and D is a directory of the same name; here, some +intermediate branch could have an empty directory instance with the same +name, so this operation also tries to delete this directory instance and +proceed further to delete from next possible lower priority branch. The +unionfs unlink operation will smoothly delete the files with same name from +all possible underlying branches. In case if some error occurs, it creates +whiteout in highest priority branch that will hide file instance in rest of +the branches. An error could occur either if an unlink operations in any of +the underlying branch failed or if a branch has no write permission. + +This unlinking policy is known as "delete all" and it has the benefit of +overall reducing the number of inodes used by duplicate files, and further +reducing the total number of inodes consumed by whiteouts. The cost is of +extra processing, but testing shows this extra processing is well worth the +savings. + + +Copyup: +======= + +When a change is made to the contents of a file's data or meta-data, they +have to be stored somewhere. The best way is to create a copy of the +original file on a branch that is writable, and then redirect the write +though to this copy. The copy must be made on a higher priority branch so +that lookup and readdir return this newer "version" of the file rather than +the original (see duplicate elimination). + +An entire unionfs mount can be read-only or read-write. If it's read-only, +then none of the branches will be written to, even if some of the branches +are physically writeable. If the unionfs mount is read-write, then the +leftmost (highest priority) branch must be writeable (for copyup to take +place); the remaining branches can be any mix of read-write and read-only. + +In a writeable mount, unionfs will create new files/dir in the leftmost +branch. If one tries to modify a file in a read-only branch/media, unionfs +will copyup the file to the leftmost branch and modify it there. If you try +to modify a file from a writeable branch which is not the leftmost branch, +then unionfs will modify it in that branch; this is useful if you, say, +unify differnet packages (e.g., apache, sendmail, ftpd, etc.) and you want +changes to specific package files to remain logically in the directory where +they came from. + +Cache Coherency: +================ + +Unionfs users often want to be able to modify files and directories directly +on the lower branches, and have those changes be visible at the Unionfs +level. This means that data (e.g., pages) and meta-data (dentries, inodes, +open files, etc.) have to be synchronized between the upper and lower +layers. In other words, the newest changes from a layer below have to be +propagated to the Unionfs layer above. If the two layers are not in sync, a +cache incoherency ensues, which could lead to application failures and even +oopses. The Linux kernel, however, has a rather limited set of mechanisms +to ensure this inter-layer cache coherency---so Unionfs has to do most of +the hard work on its own. + +Maintaining Invariants: + +The way Unionfs ensures cache coherency is as follows. At each entry point +to a Unionfs file system method, we call a utility function to validate the +primary objects of this method. Generally, we call unionfs_file_revalidate +on open files, and __unionfs_d_revalidate_chain on dentries (which also +validates inodes). These utility functions check to see whether the upper +Unionfs object is in sync with any of the lower objects that it represents. +The checks we perform include whether the Unionfs superblock has a newer +generation number, or if any of the lower objects mtime's or ctime's are +newer. (Note: generation numbers change when branch-management commands are +issued, so in a way, maintaining cache coherency is also very important for +branch-management.) If indeed we determine that any Unionfs object is no +longer in sync with its lower counterparts, then we rebuild that object +similarly to how we do so for branch-management. + +While rebuilding Unionfs's objects, we also purge any page mappings and +truncate inode pages (see fs/unionfs/dentry.c:purge_inode_data). This is to +ensure that Unionfs will re-get the newer data from the lower branches. We +perform this purging only if the Unionfs operation in question is a reading +operation; if Unionfs is performing a data writing operation (e.g., ->write, +->commit_write, etc.) then we do NOT flush the lower mappings/pages: this is +because (1) a self-deadlock could occur and (2) the upper Unionfs pages are +considered more authoritative anyway, as they are newer and will overwrite +any lower pages. + +Unionfs maintains the following important invariant regarding mtime's, +ctime's, and atime's: the upper inode object's times are the max() of all of +the lower ones. For non-directory objects, there's only one object below, +so the mapping is simple; for directory objects, there could me multiple +lower objects and we have to sync up with the newest one of all the lower +ones. This invariant is important to maintain, especially for directories +(besides, we need this to be POSIX compliant). A union could comprise +multiple writable branches, each of which could change. If we don't reflect +the newest possible mtime/ctime, some applications could fail. For example, +NFSv2/v3 exports check for newer directory mtimes on the server to determine +if the client-side attribute cache should be purged. + +To maintain these important invariants, of course, Unionfs carefully +synchronizes upper and lower times in various places. For example, if we +copy-up a file to a top-level branch, the parent directory where the file +was copied up to will now have a new mtime: so after a successful copy-up, +we sync up with the new top-level branch's parent directory mtime. + +Implementation: + +This cache-coherency implementation is efficient because it defers any +synchronizing between the upper and lower layers until absolutely needed. +Consider the example a common situation where users perform a lot of lower +changes, such as untarring a whole package. While these take place, +typically the user doesn't access the files via Unionfs; only after the +lower changes are done, does the user try to access the lower files. With +our cache-coherency implementation, the entirety of the changes to the lower +branches will not result in a single CPU cycle spent at the Unionfs level +until the user invokes a system call that goes through Unionfs. + +We have considered two alternate cache-coherency designs. (1) Using the +dentry/inode notify functionality to register interest in finding out about +any lower changes. This is a somewhat limited and also a heavy-handed +approach which could result in many notifications to the Unionfs layer upon +each small change at the lower layer (imagine a file being modified multiple +times in rapid succession). (2) Rewriting the VFS to support explicit +callbacks from lower objects to upper objects. We began exploring such an +implementation, but found it to be very complicated--it would have resulted +in massive VFS/MM changes which are unlikely to be accepted by the LKML +community. We therefore believe that our current cache-coherency design and +implementation represent the best approach at this time. + +Limitations: + +Our implementation works in that as long as a user process will have caused +Unionfs to be called, directly or indirectly, even to just do +->d_revalidate; then we will have purged the current Unionfs data and the +process will see the new data. For example, a process that continually +re-reads the same file's data will see the NEW data as soon as the lower +file had changed, upon the next read(2) syscall (even if the file is still +open!) However, this doesn't work when the process re-reads the open file's +data via mmap(2) (unless the user unmaps/closes the file and remaps/reopens +it). Once we respond to ->readpage(s), then the kernel maps the page into +the process's address space and there doesn't appear to be a way to force +the kernel to invalidate those pages/mappings, and force the process to +re-issue ->readpage. If there's a way to invalidate active mappings and +force a ->readpage, let us know please (invalidate_inode_pages2 doesn't do +the trick). + +Our current Unionfs code has to perform many file-revalidation calls. It +would be really nice if the VFS would export an optional file system hook +->file_revalidate (similarly to dentry->d_revalidate) that will be called +before each VFS op that has a "struct file" in it. + +Certain file systems have micro-second granularity (or better) for inode +times, and asynchronous actions could cause those times to change with some +small delay. In such cases, Unionfs may see a changed inode time that only +differs by a tiny fraction of a second: such a change may be a false +positive indication that the lower object has changed, whereas if unionfs +waits a little longer, that false indication will not be seen. (These false +positives are harmless, because they would at most cause unionfs to +re-validate an object that may need no revalidation, and print a debugging +message that clutters the console/logs.) Therefore, to minimize the chances +of these situations, we delay the detection of changed times by a small +factor of a few seconds, called UNIONFS_MIN_CC_TIME (which defaults to 3 +seconds, as does NFS). This means that we will detect the change, only a +couple of seconds later, if indeed the time change persists in the lower +file object. This delayed detection has an added performance benefit: we +reduce the number of times that unionfs has to revalidate objects, in case +there's a lot of concurrent activity on both the upper and lower objects, +for the same file(s). Lastly, this delayed time attribute detection is +similar to how NFS clients operate (e.g., acregmin). + +Finally, there is no way currently in Linux to prevent lower directories +from being moved around (i.e., topology changes); there's no way to prevent +modifications to directory sub-trees of whole file systems which are mounted +read-write. It is therefore possible for in-flight operations in unionfs to +take place, while a lower directory is being moved around. Therefore, if +you try to, say, create a new file in a directory through unionfs, while the +directory is being moved around directly, then the new file may get created +in the new location where that directory was moved to. This is a somewhat +similar behaviour in NFS: an NFS client could be creating a new file while +th NFS server is moving th directory around; the file will get successfully +created in the new location. (The one exception in unionfs is that if the +branch is marked read-only by unionfs, then a copyup will take place.) + +For more information, see . diff --git a/Documentation/filesystems/unionfs/issues.txt b/Documentation/filesystems/unionfs/issues.txt new file mode 100644 index 0000000..f4b7e7e --- /dev/null +++ b/Documentation/filesystems/unionfs/issues.txt @@ -0,0 +1,28 @@ +KNOWN Unionfs 2.x ISSUES: +========================= + +1. Unionfs should not use lookup_one_len() on the underlying f/s as it + confuses NFSv4. Currently, unionfs_lookup() passes lookup intents to the + lower file-system, this eliminates part of the problem. The remaining + calls to lookup_one_len may need to be changed to pass an intent. We are + currently introducing VFS changes to fs/namei.c's do_path_lookup() to + allow proper file lookup and opening in stackable file systems. + +2. Lockdep (a debugging feature) isn't aware of stacking, and so it + incorrectly complains about locking problems. The problem boils down to + this: Lockdep considers all objects of a certain type to be in the same + class, for example, all inodes. Lockdep doesn't like to see a lock held + on two inodes within the same task, and warns that it could lead to a + deadlock. However, stackable file systems do precisely that: they lock + an upper object, and then a lower object, in a strict order to avoid + locking problems; in addition, Unionfs, as a fan-out file system, may + have to lock several lower inodes. We are currently looking into Lockdep + to see how to make it aware of stackable file systems. For now, we + temporarily disable lockdep when calling vfs methods on lower objects, + but only for those places where lockdep complained. While this solution + may seem unclean, it is not without precedent: other places in the kernel + also do similar temporary disabling, of course after carefully having + checked that it is the right thing to do. Anyway, you get any warnings + from Lockdep, please report them to the Unionfs maintainers. + +For more information, see . diff --git a/Documentation/filesystems/unionfs/rename.txt b/Documentation/filesystems/unionfs/rename.txt new file mode 100644 index 0000000..e20bb82 --- /dev/null +++ b/Documentation/filesystems/unionfs/rename.txt @@ -0,0 +1,31 @@ +Rename is a complex beast. The following table shows which rename(2) operations +should succeed and which should fail. + +o: success +E: error (either unionfs or vfs) +X: EXDEV + +none = file does not exist +file = file is a file +dir = file is a empty directory +child= file is a non-empty directory +wh = file is a directory containing only whiteouts; this makes it logically + empty + + none file dir child wh +file o o E E E +dir o E o E o +child X E X E X +wh o E o E o + + +Renaming directories: +===================== + +Whenever a empty (either physically or logically) directory is being renamed, +the following sequence of events should take place: + +1) Remove whiteouts from both source and destination directory +2) Rename source to destination +3) Make destination opaque to prevent anything under it from showing up + diff --git a/Documentation/filesystems/unionfs/usage.txt b/Documentation/filesystems/unionfs/usage.txt new file mode 100644 index 0000000..1adde69 --- /dev/null +++ b/Documentation/filesystems/unionfs/usage.txt @@ -0,0 +1,134 @@ +Unionfs is a stackable unification file system, which can appear to merge +the contents of several directories (branches), while keeping their physical +content separate. Unionfs is useful for unified source tree management, +merged contents of split CD-ROM, merged separate software package +directories, data grids, and more. Unionfs allows any mix of read-only and +read-write branches, as well as insertion and deletion of branches anywhere +in the fan-out. To maintain Unix semantics, Unionfs handles elimination of +duplicates, partial-error conditions, and more. + +GENERAL SYNTAX +============== + +# mount -t unionfs -o , none MOUNTPOINT + +OPTIONS can be any legal combination of: + +- ro # mount file system read-only +- rw # mount file system read-write +- remount # remount the file system (see Branch Management below) +- incgen # increment generation no. (see Cache Consistency below) + +BRANCH-OPTIONS can be either (1) a list of branches given to the "dirs=" +option, or (2) a list of individual branch manipulation commands, combined +with the "remount" option, and is further described in the "Branch +Management" section below. + +The syntax for the "dirs=" mount option is: + + dirs=branch[=ro|=rw][:...] + +The "dirs=" option takes a colon-delimited list of directories to compose +the union, with an optional branch mode for each of those directories. +Directories that come earlier (specified first, on the left) in the list +have a higher precedence than those which come later. Additionally, +read-only or read-write permissions of the branch can be specified by +appending =ro or =rw (default) to each directory. See the Copyup section in +concepts.txt, for a description of Unionfs's behavior when mixing read-only +and read-write branches and mounts. + +Syntax: + + dirs=/branch1[=ro|=rw]:/branch2[=ro|=rw]:...:/branchN[=ro|=rw] + +Example: + + dirs=/writable_branch=rw:/read-only_branch=ro + + +BRANCH MANAGEMENT +================= + +Once you mount your union for the first time, using the "dirs=" option, you +can then change the union's overall mode or reconfigure the branches, using +the remount option, as follows. + +To downgrade a union from read-write to read-only: + +# mount -t unionfs -o remount,ro none MOUNTPOINT + +To upgrade a union from read-only to read-write: + +# mount -t unionfs -o remount,rw none MOUNTPOINT + +To delete a branch /foo, regardless where it is in the current union: + +# mount -t unionfs -o remount,del=/foo none MOUNTPOINT + +To insert (add) a branch /foo before /bar: + +# mount -t unionfs -o remount,add=/bar:/foo none MOUNTPOINT + +To insert (add) a branch /foo (with the "rw" mode flag) before /bar: + +# mount -t unionfs -o remount,add=/bar:/foo=rw none MOUNTPOINT + +To insert (add) a branch /foo (in "rw" mode) at the very beginning (i.e., a +new highest-priority branch), you can use the above syntax, or use a short +hand version as follows: + +# mount -t unionfs -o remount,add=/foo none MOUNTPOINT + +To append a branch to the very end (new lowest-priority branch): + +# mount -t unionfs -o remount,add=:/foo none MOUNTPOINT + +To append a branch to the very end (new lowest-priority branch), in +read-only mode: + +# mount -t unionfs -o remount,add=:/foo=ro none MOUNTPOINT + +Finally, to change the mode of one existing branch, say /foo, from read-only +to read-write, and change /bar from read-write to read-only: + +# mount -t unionfs -o remount,mode=/foo=rw,mode=/bar=ro none MOUNTPOINT + +Note: in Unionfs 2.x, you cannot set the leftmost branch to readonly because +then Unionfs won't have any writable place for copyups to take place. +Moreover, the VFS can get confused when it tries to modify something in a +file system mounted read-write, but isn't permitted to write to it. +Instead, you should set the whole union as readonly, as described above. +If, however, you must set the leftmost branch as readonly, perhaps so you +can get a snapshot of it at a point in time, then you should insert a new +writable top-level branch, and mark the one you want as readonly. This can +be accomplished as follows, assuming that /foo is your current leftmost +branch: + +# mount -t tmpfs -o size=NNN /new +# mount -t unionfs -o remount,add=/new,mode=/foo=ro none MOUNTPOINT + +# mount -t unionfs -o remount,del=/new,mode=/foo=rw none MOUNTPOINT + +# umount /new + +CACHE CONSISTENCY +================= + +If you modify any file on any of the lower branches directly, while there is +a Unionfs 2.x mounted above any of those branches, you should tell Unionfs +to purge its caches and re-get the objects. To do that, you have to +increment the generation number of the superblock using the following +command: + +# mount -t unionfs -o remount,incgen none MOUNTPOINT + +Note that the older way of incrementing the generation number using an +ioctl, is no longer supported in Unionfs 2.0 and newer. Ioctls in general +are not encouraged. Plus, an ioctl is per-file concept, whereas the +generation number is a per-file-system concept. Worse, such an ioctl +requires an open file, which then has to be invalidated by the very nature +of the generation number increase (read: the old generation increase ioctl +was pretty racy). + + +For more information, see . diff --git a/MAINTAINERS b/MAINTAINERS index f2a2b8e..11d7f45 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5917,6 +5917,14 @@ F: Documentation/cdrom/ F: drivers/cdrom/cdrom.c F: include/linux/cdrom.h +UNIONFS +P: Erez Zadok +M: ezk@cs.sunysb.edu +L: unionfs@filesystems.org +W: http://unionfs.filesystems.org/ +T: git git.kernel.org/pub/scm/linux/kernel/git/ezk/unionfs.git +S: Maintained + UNSORTED BLOCK IMAGES (UBI) M: Artem Bityutskiy W: http://www.linux-mtd.infradead.org/ diff --git a/fs/Kconfig b/fs/Kconfig index 3d18530..65b6aa1 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -169,6 +169,7 @@ if MISC_FILESYSTEMS source "fs/adfs/Kconfig" source "fs/affs/Kconfig" source "fs/ecryptfs/Kconfig" +source "fs/unionfs/Kconfig" source "fs/hfs/Kconfig" source "fs/hfsplus/Kconfig" source "fs/befs/Kconfig" diff --git a/fs/Makefile b/fs/Makefile index e6ec1d3..787332e 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_ISO9660_FS) += isofs/ obj-$(CONFIG_HFSPLUS_FS) += hfsplus/ # Before hfs to find wrapped HFS+ obj-$(CONFIG_HFS_FS) += hfs/ obj-$(CONFIG_ECRYPT_FS) += ecryptfs/ +obj-$(CONFIG_UNION_FS) += unionfs/ obj-$(CONFIG_VXFS_FS) += freevxfs/ obj-$(CONFIG_NFS_FS) += nfs/ obj-$(CONFIG_EXPORTFS) += exportfs/ diff --git a/fs/namei.c b/fs/namei.c index 24896e8..db22420 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -385,6 +385,7 @@ void release_open_intent(struct nameidata *nd) else fput(nd->intent.open.file); } +EXPORT_SYMBOL_GPL(release_open_intent); static inline struct dentry * do_revalidate(struct dentry *dentry, struct nameidata *nd) diff --git a/fs/splice.c b/fs/splice.c index 8f1dfae..7a57fab 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1092,8 +1092,8 @@ EXPORT_SYMBOL(generic_splice_sendpage); /* * Attempt to initiate a splice from pipe to file. */ -static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags) +long vfs_splice_from(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) { ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); @@ -1116,13 +1116,14 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, return splice_write(pipe, out, ppos, len, flags); } +EXPORT_SYMBOL_GPL(vfs_splice_from); /* * Attempt to initiate a splice from a file to a pipe. */ -static long do_splice_to(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) +long vfs_splice_to(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); @@ -1142,6 +1143,7 @@ static long do_splice_to(struct file *in, loff_t *ppos, return splice_read(in, ppos, pipe, len, flags); } +EXPORT_SYMBOL_GPL(vfs_splice_to); /** * splice_direct_to_actor - splices data directly between two non-pipes @@ -1211,7 +1213,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, size_t read_len; loff_t pos = sd->pos, prev_pos = pos; - ret = do_splice_to(in, &pos, pipe, len, flags); + ret = vfs_splice_to(in, &pos, pipe, len, flags); if (unlikely(ret <= 0)) goto out_release; @@ -1270,8 +1272,8 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, { struct file *file = sd->u.file; - return do_splice_from(pipe, file, &file->f_pos, sd->total_len, - sd->flags); + return vfs_splice_from(pipe, file, &file->f_pos, sd->total_len, + sd->flags); } /** @@ -1368,7 +1370,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, } else off = &out->f_pos; - ret = do_splice_from(ipipe, out, off, len, flags); + ret = vfs_splice_from(ipipe, out, off, len, flags); if (off_out && copy_to_user(off_out, off, sizeof(loff_t))) ret = -EFAULT; @@ -1388,7 +1390,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, } else off = &in->f_pos; - ret = do_splice_to(in, off, opipe, len, flags); + ret = vfs_splice_to(in, off, opipe, len, flags); if (off_in && copy_to_user(off_in, off, sizeof(loff_t))) ret = -EFAULT; diff --git a/fs/stack.c b/fs/stack.c index 4a6f7f4..7eeef12 100644 --- a/fs/stack.c +++ b/fs/stack.c @@ -1,8 +1,20 @@ +/* + * Copyright (c) 2006-2009 Erez Zadok + * Copyright (c) 2006-2007 Josef 'Jeff' Sipek + * Copyright (c) 2006-2009 Stony Brook University + * Copyright (c) 2006-2009 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + #include #include #include -/* does _NOT_ require i_mutex to be held. +/* + * does _NOT_ require i_mutex to be held. * * This function cannot be inlined since i_size_{read,write} is rather * heavy-weight on 32-bit systems diff --git a/fs/unionfs/Kconfig b/fs/unionfs/Kconfig new file mode 100644 index 0000000..f3c1ac4 --- /dev/null +++ b/fs/unionfs/Kconfig @@ -0,0 +1,24 @@ +config UNION_FS + tristate "Union file system (EXPERIMENTAL)" + depends on EXPERIMENTAL + help + Unionfs is a stackable unification file system, which appears to + merge the contents of several directories (branches), while keeping + their physical content separate. + + See for details + +config UNION_FS_XATTR + bool "Unionfs extended attributes" + depends on UNION_FS + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page). + + If unsure, say N. + +config UNION_FS_DEBUG + bool "Debug Unionfs" + depends on UNION_FS + help + If you say Y here, you can turn on debugging output from Unionfs. diff --git a/fs/unionfs/Makefile b/fs/unionfs/Makefile new file mode 100644 index 0000000..86c32ba --- /dev/null +++ b/fs/unionfs/Makefile @@ -0,0 +1,17 @@ +UNIONFS_VERSION="2.5.7 (for 2.6.36)" + +EXTRA_CFLAGS += -DUNIONFS_VERSION=\"$(UNIONFS_VERSION)\" + +obj-$(CONFIG_UNION_FS) += unionfs.o + +unionfs-y := subr.o dentry.o file.o inode.o main.o super.o \ + rdstate.o copyup.o dirhelper.o rename.o unlink.o \ + lookup.o commonfops.o dirfops.o sioq.o mmap.o whiteout.o + +unionfs-$(CONFIG_UNION_FS_XATTR) += xattr.o + +unionfs-$(CONFIG_UNION_FS_DEBUG) += debug.o + +ifeq ($(CONFIG_UNION_FS_DEBUG),y) +EXTRA_CFLAGS += -DDEBUG +endif diff --git a/fs/unionfs/commonfops.c b/fs/unionfs/commonfops.c new file mode 100644 index 0000000..51ea65e --- /dev/null +++ b/fs/unionfs/commonfops.c @@ -0,0 +1,896 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* + * 1) Copyup the file + * 2) Rename the file to '.unionfs' - obviously + * stolen from NFS's silly rename + */ +static int copyup_deleted_file(struct file *file, struct dentry *dentry, + struct dentry *parent, int bstart, int bindex) +{ + static unsigned int counter; + const int i_inosize = sizeof(dentry->d_inode->i_ino) * 2; + const int countersize = sizeof(counter) * 2; + const int nlen = sizeof(".unionfs") + i_inosize + countersize - 1; + char name[nlen + 1]; + int err; + struct dentry *tmp_dentry = NULL; + struct dentry *lower_dentry; + struct dentry *lower_dir_dentry = NULL; + + lower_dentry = unionfs_lower_dentry_idx(dentry, bstart); + + sprintf(name, ".unionfs%*.*lx", + i_inosize, i_inosize, lower_dentry->d_inode->i_ino); + + /* + * Loop, looking for an unused temp name to copyup to. + * + * It's somewhat silly that we look for a free temp tmp name in the + * source branch (bstart) instead of the dest branch (bindex), where + * the final name will be created. We _will_ catch it if somehow + * the name exists in the dest branch, but it'd be nice to catch it + * sooner than later. + */ +retry: + tmp_dentry = NULL; + do { + char *suffix = name + nlen - countersize; + + dput(tmp_dentry); + counter++; + sprintf(suffix, "%*.*x", countersize, countersize, counter); + + pr_debug("unionfs: trying to rename %s to %s\n", + dentry->d_name.name, name); + + tmp_dentry = lookup_lck_len(name, lower_dentry->d_parent, + nlen); + if (IS_ERR(tmp_dentry)) { + err = PTR_ERR(tmp_dentry); + goto out; + } + } while (tmp_dentry->d_inode != NULL); /* need negative dentry */ + dput(tmp_dentry); + + err = copyup_named_file(parent->d_inode, file, name, bstart, bindex, + i_size_read(file->f_path.dentry->d_inode)); + if (err) { + if (unlikely(err == -EEXIST)) + goto retry; + goto out; + } + + /* bring it to the same state as an unlinked file */ + lower_dentry = unionfs_lower_dentry_idx(dentry, dbstart(dentry)); + if (!unionfs_lower_inode_idx(dentry->d_inode, bindex)) { + atomic_inc(&lower_dentry->d_inode->i_count); + unionfs_set_lower_inode_idx(dentry->d_inode, bindex, + lower_dentry->d_inode); + } + lower_dir_dentry = lock_parent(lower_dentry); + err = vfs_unlink(lower_dir_dentry->d_inode, lower_dentry); + unlock_dir(lower_dir_dentry); + +out: + if (!err) + unionfs_check_dentry(dentry); + return err; +} + +/* + * put all references held by upper struct file and free lower file pointer + * array + */ +static void cleanup_file(struct file *file) +{ + int bindex, bstart, bend; + struct file **lower_files; + struct file *lower_file; + struct super_block *sb = file->f_path.dentry->d_sb; + + lower_files = UNIONFS_F(file)->lower_files; + bstart = fbstart(file); + bend = fbend(file); + + for (bindex = bstart; bindex <= bend; bindex++) { + int i; /* holds (possibly) updated branch index */ + int old_bid; + + lower_file = unionfs_lower_file_idx(file, bindex); + if (!lower_file) + continue; + + /* + * Find new index of matching branch with an open + * file, since branches could have been added or + * deleted causing the one with open files to shift. + */ + old_bid = UNIONFS_F(file)->saved_branch_ids[bindex]; + i = branch_id_to_idx(sb, old_bid); + if (unlikely(i < 0)) { + printk(KERN_ERR "unionfs: no superblock for " + "file %p\n", file); + continue; + } + + /* decrement count of open files */ + branchput(sb, i); + /* + * fput will perform an mntput for us on the correct branch. + * Although we're using the file's old branch configuration, + * bindex, which is the old index, correctly points to the + * right branch in the file's branch list. In other words, + * we're going to mntput the correct branch even if branches + * have been added/removed. + */ + fput(lower_file); + UNIONFS_F(file)->lower_files[bindex] = NULL; + UNIONFS_F(file)->saved_branch_ids[bindex] = -1; + } + + UNIONFS_F(file)->lower_files = NULL; + kfree(lower_files); + kfree(UNIONFS_F(file)->saved_branch_ids); + /* set to NULL because caller needs to know if to kfree on error */ + UNIONFS_F(file)->saved_branch_ids = NULL; +} + +/* open all lower files for a given file */ +static int open_all_files(struct file *file) +{ + int bindex, bstart, bend, err = 0; + struct file *lower_file; + struct dentry *lower_dentry; + struct dentry *dentry = file->f_path.dentry; + struct super_block *sb = dentry->d_sb; + + bstart = dbstart(dentry); + bend = dbend(dentry); + + for (bindex = bstart; bindex <= bend; bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (!lower_dentry) + continue; + + dget(lower_dentry); + unionfs_mntget(dentry, bindex); + branchget(sb, bindex); + + lower_file = + dentry_open(lower_dentry, + unionfs_lower_mnt_idx(dentry, bindex), + file->f_flags, current_cred()); + if (IS_ERR(lower_file)) { + branchput(sb, bindex); + err = PTR_ERR(lower_file); + goto out; + } else { + unionfs_set_lower_file_idx(file, bindex, lower_file); + } + } +out: + return err; +} + +/* open the highest priority file for a given upper file */ +static int open_highest_file(struct file *file, bool willwrite) +{ + int bindex, bstart, bend, err = 0; + struct file *lower_file; + struct dentry *lower_dentry; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent = dget_parent(dentry); + struct inode *parent_inode = parent->d_inode; + struct super_block *sb = dentry->d_sb; + + bstart = dbstart(dentry); + bend = dbend(dentry); + + lower_dentry = unionfs_lower_dentry(dentry); + if (willwrite && IS_WRITE_FLAG(file->f_flags) && is_robranch(dentry)) { + for (bindex = bstart - 1; bindex >= 0; bindex--) { + err = copyup_file(parent_inode, file, bstart, bindex, + i_size_read(dentry->d_inode)); + if (!err) + break; + } + atomic_set(&UNIONFS_F(file)->generation, + atomic_read(&UNIONFS_I(dentry->d_inode)-> + generation)); + goto out; + } + + dget(lower_dentry); + unionfs_mntget(dentry, bstart); + lower_file = dentry_open(lower_dentry, + unionfs_lower_mnt_idx(dentry, bstart), + file->f_flags, current_cred()); + if (IS_ERR(lower_file)) { + err = PTR_ERR(lower_file); + goto out; + } + branchget(sb, bstart); + unionfs_set_lower_file(file, lower_file); + /* Fix up the position. */ + lower_file->f_pos = file->f_pos; + + memcpy(&lower_file->f_ra, &file->f_ra, sizeof(struct file_ra_state)); +out: + dput(parent); + return err; +} + +/* perform a delayed copyup of a read-write file on a read-only branch */ +static int do_delayed_copyup(struct file *file, struct dentry *parent) +{ + int bindex, bstart, bend, err = 0; + struct dentry *dentry = file->f_path.dentry; + struct inode *parent_inode = parent->d_inode; + + bstart = fbstart(file); + bend = fbend(file); + + BUG_ON(!S_ISREG(dentry->d_inode->i_mode)); + + unionfs_check_file(file); + for (bindex = bstart - 1; bindex >= 0; bindex--) { + if (!d_deleted(dentry)) + err = copyup_file(parent_inode, file, bstart, + bindex, + i_size_read(dentry->d_inode)); + else + err = copyup_deleted_file(file, dentry, parent, + bstart, bindex); + /* if succeeded, set lower open-file flags and break */ + if (!err) { + struct file *lower_file; + lower_file = unionfs_lower_file_idx(file, bindex); + lower_file->f_flags = file->f_flags; + break; + } + } + if (err || (bstart <= fbstart(file))) + goto out; + bend = fbend(file); + for (bindex = bstart; bindex <= bend; bindex++) { + if (unionfs_lower_file_idx(file, bindex)) { + branchput(dentry->d_sb, bindex); + fput(unionfs_lower_file_idx(file, bindex)); + unionfs_set_lower_file_idx(file, bindex, NULL); + } + } + path_put_lowers(dentry, bstart, bend, false); + iput_lowers(dentry->d_inode, bstart, bend, false); + /* for reg file, we only open it "once" */ + fbend(file) = fbstart(file); + dbend(dentry) = dbstart(dentry); + ibend(dentry->d_inode) = ibstart(dentry->d_inode); + +out: + unionfs_check_file(file); + return err; +} + +/* + * Helper function for unionfs_file_revalidate/locked. + * Expects dentry/parent to be locked already, and revalidated. + */ +static int __unionfs_file_revalidate(struct file *file, struct dentry *dentry, + struct dentry *parent, + struct super_block *sb, int sbgen, + int dgen, bool willwrite) +{ + int fgen; + int bstart, bend, orig_brid; + int size; + int err = 0; + + fgen = atomic_read(&UNIONFS_F(file)->generation); + + /* + * There are two cases we are interested in. The first is if the + * generation is lower than the super-block. The second is if + * someone has copied up this file from underneath us, we also need + * to refresh things. + */ + if (d_deleted(dentry) || + (sbgen <= fgen && + dbstart(dentry) == fbstart(file) && + unionfs_lower_file(file))) + goto out_may_copyup; + + /* save orig branch ID */ + orig_brid = UNIONFS_F(file)->saved_branch_ids[fbstart(file)]; + + /* First we throw out the existing files. */ + cleanup_file(file); + + /* Now we reopen the file(s) as in unionfs_open. */ + bstart = fbstart(file) = dbstart(dentry); + bend = fbend(file) = dbend(dentry); + + size = sizeof(struct file *) * sbmax(sb); + UNIONFS_F(file)->lower_files = kzalloc(size, GFP_KERNEL); + if (unlikely(!UNIONFS_F(file)->lower_files)) { + err = -ENOMEM; + goto out; + } + size = sizeof(int) * sbmax(sb); + UNIONFS_F(file)->saved_branch_ids = kzalloc(size, GFP_KERNEL); + if (unlikely(!UNIONFS_F(file)->saved_branch_ids)) { + err = -ENOMEM; + goto out; + } + + if (S_ISDIR(dentry->d_inode->i_mode)) { + /* We need to open all the files. */ + err = open_all_files(file); + if (err) + goto out; + } else { + int new_brid; + /* We only open the highest priority branch. */ + err = open_highest_file(file, willwrite); + if (err) + goto out; + new_brid = UNIONFS_F(file)->saved_branch_ids[fbstart(file)]; + if (unlikely(new_brid != orig_brid && sbgen > fgen)) { + /* + * If we re-opened the file on a different branch + * than the original one, and this was due to a new + * branch inserted, then update the mnt counts of + * the old and new branches accordingly. + */ + unionfs_mntget(dentry, bstart); + unionfs_mntput(sb->s_root, + branch_id_to_idx(sb, orig_brid)); + } + /* regular files have only one open lower file */ + fbend(file) = fbstart(file); + } + atomic_set(&UNIONFS_F(file)->generation, + atomic_read(&UNIONFS_I(dentry->d_inode)->generation)); + +out_may_copyup: + /* Copyup on the first write to a file on a readonly branch. */ + if (willwrite && IS_WRITE_FLAG(file->f_flags) && + !IS_WRITE_FLAG(unionfs_lower_file(file)->f_flags) && + is_robranch(dentry)) { + pr_debug("unionfs: do delay copyup of \"%s\"\n", + dentry->d_name.name); + err = do_delayed_copyup(file, parent); + /* regular files have only one open lower file */ + if (!err && !S_ISDIR(dentry->d_inode->i_mode)) + fbend(file) = fbstart(file); + } + +out: + if (err) { + kfree(UNIONFS_F(file)->lower_files); + kfree(UNIONFS_F(file)->saved_branch_ids); + } + return err; +} + +/* + * Revalidate the struct file + * @file: file to revalidate + * @parent: parent dentry (locked by caller) + * @willwrite: true if caller may cause changes to the file; false otherwise. + * Caller must lock/unlock dentry's branch configuration. + */ +int unionfs_file_revalidate(struct file *file, struct dentry *parent, + bool willwrite) +{ + struct super_block *sb; + struct dentry *dentry; + int sbgen, dgen; + int err = 0; + + dentry = file->f_path.dentry; + sb = dentry->d_sb; + verify_locked(dentry); + verify_locked(parent); + + /* + * First revalidate the dentry inside struct file, + * but not unhashed dentries. + */ + if (!d_deleted(dentry) && + !__unionfs_d_revalidate(dentry, parent, willwrite)) { + err = -ESTALE; + goto out; + } + + sbgen = atomic_read(&UNIONFS_SB(sb)->generation); + dgen = atomic_read(&UNIONFS_D(dentry)->generation); + + if (unlikely(sbgen > dgen)) { /* XXX: should never happen */ + pr_debug("unionfs: failed to revalidate dentry (%s)\n", + dentry->d_name.name); + err = -ESTALE; + goto out; + } + + err = __unionfs_file_revalidate(file, dentry, parent, sb, + sbgen, dgen, willwrite); +out: + return err; +} + +/* unionfs_open helper function: open a directory */ +static int __open_dir(struct inode *inode, struct file *file) +{ + struct dentry *lower_dentry; + struct file *lower_file; + int bindex, bstart, bend; + struct vfsmount *mnt; + + bstart = fbstart(file) = dbstart(file->f_path.dentry); + bend = fbend(file) = dbend(file->f_path.dentry); + + for (bindex = bstart; bindex <= bend; bindex++) { + lower_dentry = + unionfs_lower_dentry_idx(file->f_path.dentry, bindex); + if (!lower_dentry) + continue; + + dget(lower_dentry); + unionfs_mntget(file->f_path.dentry, bindex); + mnt = unionfs_lower_mnt_idx(file->f_path.dentry, bindex); + lower_file = dentry_open(lower_dentry, mnt, file->f_flags, + current_cred()); + if (IS_ERR(lower_file)) + return PTR_ERR(lower_file); + + unionfs_set_lower_file_idx(file, bindex, lower_file); + + /* + * The branchget goes after the open, because otherwise + * we would miss the reference on release. + */ + branchget(inode->i_sb, bindex); + } + + return 0; +} + +/* unionfs_open helper function: open a file */ +static int __open_file(struct inode *inode, struct file *file, + struct dentry *parent) +{ + struct dentry *lower_dentry; + struct file *lower_file; + int lower_flags; + int bindex, bstart, bend; + + lower_dentry = unionfs_lower_dentry(file->f_path.dentry); + lower_flags = file->f_flags; + + bstart = fbstart(file) = dbstart(file->f_path.dentry); + bend = fbend(file) = dbend(file->f_path.dentry); + + /* + * check for the permission for lower file. If the error is + * COPYUP_ERR, copyup the file. + */ + if (lower_dentry->d_inode && is_robranch(file->f_path.dentry)) { + /* + * if the open will change the file, copy it up otherwise + * defer it. + */ + if (lower_flags & O_TRUNC) { + int size = 0; + int err = -EROFS; + + /* copyup the file */ + for (bindex = bstart - 1; bindex >= 0; bindex--) { + err = copyup_file(parent->d_inode, file, + bstart, bindex, size); + if (!err) + break; + } + return err; + } else { + /* + * turn off writeable flags, to force delayed copyup + * by caller. + */ + lower_flags &= ~(OPEN_WRITE_FLAGS); + } + } + + dget(lower_dentry); + + /* + * dentry_open will decrement mnt refcnt if err. + * otherwise fput() will do an mntput() for us upon file close. + */ + unionfs_mntget(file->f_path.dentry, bstart); + lower_file = + dentry_open(lower_dentry, + unionfs_lower_mnt_idx(file->f_path.dentry, bstart), + lower_flags, current_cred()); + if (IS_ERR(lower_file)) + return PTR_ERR(lower_file); + + unionfs_set_lower_file(file, lower_file); + branchget(inode->i_sb, bstart); + + return 0; +} + +int unionfs_open(struct inode *inode, struct file *file) +{ + int err = 0; + struct file *lower_file = NULL; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + int bindex = 0, bstart = 0, bend = 0; + int size; + int valid = 0; + + unionfs_read_lock(inode->i_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + /* don't open unhashed/deleted files */ + if (d_deleted(dentry)) { + err = -ENOENT; + goto out_nofree; + } + + /* XXX: should I change 'false' below to the 'willwrite' flag? */ + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out_nofree; + } + + file->private_data = + kzalloc(sizeof(struct unionfs_file_info), GFP_KERNEL); + if (unlikely(!UNIONFS_F(file))) { + err = -ENOMEM; + goto out_nofree; + } + fbstart(file) = -1; + fbend(file) = -1; + atomic_set(&UNIONFS_F(file)->generation, + atomic_read(&UNIONFS_I(inode)->generation)); + + size = sizeof(struct file *) * sbmax(inode->i_sb); + UNIONFS_F(file)->lower_files = kzalloc(size, GFP_KERNEL); + if (unlikely(!UNIONFS_F(file)->lower_files)) { + err = -ENOMEM; + goto out; + } + size = sizeof(int) * sbmax(inode->i_sb); + UNIONFS_F(file)->saved_branch_ids = kzalloc(size, GFP_KERNEL); + if (unlikely(!UNIONFS_F(file)->saved_branch_ids)) { + err = -ENOMEM; + goto out; + } + + bstart = fbstart(file) = dbstart(dentry); + bend = fbend(file) = dbend(dentry); + + /* + * open all directories and make the unionfs file struct point to + * these lower file structs + */ + if (S_ISDIR(inode->i_mode)) + err = __open_dir(inode, file); /* open a dir */ + else + err = __open_file(inode, file, parent); /* open a file */ + + /* freeing the allocated resources, and fput the opened files */ + if (err) { + for (bindex = bstart; bindex <= bend; bindex++) { + lower_file = unionfs_lower_file_idx(file, bindex); + if (!lower_file) + continue; + + branchput(dentry->d_sb, bindex); + /* fput calls dput for lower_dentry */ + fput(lower_file); + } + } + +out: + if (err) { + kfree(UNIONFS_F(file)->lower_files); + kfree(UNIONFS_F(file)->saved_branch_ids); + kfree(UNIONFS_F(file)); + } +out_nofree: + if (!err) { + unionfs_postcopyup_setmnt(dentry); + unionfs_copy_attr_times(inode); + unionfs_check_file(file); + unionfs_check_inode(inode); + } + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(inode->i_sb); + return err; +} + +/* + * release all lower object references & free the file info structure + * + * No need to grab sb info's rwsem. + */ +int unionfs_file_release(struct inode *inode, struct file *file) +{ + struct file *lower_file = NULL; + struct unionfs_file_info *fileinfo; + struct unionfs_inode_info *inodeinfo; + struct super_block *sb = inode->i_sb; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + int bindex, bstart, bend; + int fgen, err = 0; + + /* + * Since mm/memory.c:might_fault() (under PROVE_LOCKING) was + * modified in 2.6.29-rc1 to call might_lock_read on mmap_sem, this + * has been causing false positives in file system stacking layers. + * In particular, our ->mmap is called after sys_mmap2 already holds + * mmap_sem, then we lock our own mutexes; but earlier, it's + * possible for lockdep to have locked our mutexes first, and then + * we call a lower ->readdir which could call might_fault. The + * different ordering of the locks is what lockdep complains about + * -- unnecessarily. Therefore, we have no choice but to tell + * lockdep to temporarily turn off lockdep here. Note: the comments + * inside might_sleep also suggest that it would have been + * nicer to only annotate paths that needs that might_lock_read. + */ + lockdep_off(); + unionfs_read_lock(sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + /* + * We try to revalidate, but the VFS ignores return return values + * from file->release, so we must always try to succeed here, + * including to do the kfree and dput below. So if revalidation + * failed, all we can do is print some message and keep going. + */ + err = unionfs_file_revalidate(file, parent, + UNIONFS_F(file)->wrote_to_file); + if (!err) + unionfs_check_file(file); + fileinfo = UNIONFS_F(file); + BUG_ON(file->f_path.dentry->d_inode != inode); + inodeinfo = UNIONFS_I(inode); + + /* fput all the lower files */ + fgen = atomic_read(&fileinfo->generation); + bstart = fbstart(file); + bend = fbend(file); + + for (bindex = bstart; bindex <= bend; bindex++) { + lower_file = unionfs_lower_file_idx(file, bindex); + + if (lower_file) { + unionfs_set_lower_file_idx(file, bindex, NULL); + fput(lower_file); + branchput(sb, bindex); + } + + /* if there are no more refs to the dentry, dput it */ + if (d_deleted(dentry)) { + dput(unionfs_lower_dentry_idx(dentry, bindex)); + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); + } + } + + kfree(fileinfo->lower_files); + kfree(fileinfo->saved_branch_ids); + + if (fileinfo->rdstate) { + fileinfo->rdstate->access = jiffies; + spin_lock(&inodeinfo->rdlock); + inodeinfo->rdcount++; + list_add_tail(&fileinfo->rdstate->cache, + &inodeinfo->readdircache); + mark_inode_dirty(inode); + spin_unlock(&inodeinfo->rdlock); + fileinfo->rdstate = NULL; + } + kfree(fileinfo); + + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(sb); + lockdep_on(); + return err; +} + +/* pass the ioctl to the lower fs */ +static long do_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct file *lower_file; + int err; + + lower_file = unionfs_lower_file(file); + + err = -ENOTTY; + if (!lower_file || !lower_file->f_op) + goto out; + if (lower_file->f_op->unlocked_ioctl) { + err = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg); +#ifdef CONFIG_COMPAT + } else if (lower_file->f_op->ioctl) { + err = lower_file->f_op->compat_ioctl( + lower_file->f_path.dentry->d_inode, + lower_file, cmd, arg); +#endif + } + +out: + return err; +} + +/* + * return to user-space the branch indices containing the file in question + * + * We use fd_set and therefore we are limited to the number of the branches + * to FD_SETSIZE, which is currently 1024 - plenty for most people + */ +static int unionfs_ioctl_queryfile(struct file *file, struct dentry *parent, + unsigned int cmd, unsigned long arg) +{ + int err = 0; + fd_set branchlist; + int bstart = 0, bend = 0, bindex = 0; + int orig_bstart, orig_bend; + struct dentry *dentry, *lower_dentry; + struct vfsmount *mnt; + + dentry = file->f_path.dentry; + orig_bstart = dbstart(dentry); + orig_bend = dbend(dentry); + err = unionfs_partial_lookup(dentry, parent); + if (err) + goto out; + bstart = dbstart(dentry); + bend = dbend(dentry); + + FD_ZERO(&branchlist); + + for (bindex = bstart; bindex <= bend; bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (!lower_dentry) + continue; + if (likely(lower_dentry->d_inode)) + FD_SET(bindex, &branchlist); + /* purge any lower objects after partial_lookup */ + if (bindex < orig_bstart || bindex > orig_bend) { + dput(lower_dentry); + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); + iput(unionfs_lower_inode_idx(dentry->d_inode, bindex)); + unionfs_set_lower_inode_idx(dentry->d_inode, bindex, + NULL); + mnt = unionfs_lower_mnt_idx(dentry, bindex); + if (!mnt) + continue; + unionfs_mntput(dentry, bindex); + unionfs_set_lower_mnt_idx(dentry, bindex, NULL); + } + } + /* restore original dentry's offsets */ + dbstart(dentry) = orig_bstart; + dbend(dentry) = orig_bend; + ibstart(dentry->d_inode) = orig_bstart; + ibend(dentry->d_inode) = orig_bend; + + err = copy_to_user((void __user *)arg, &branchlist, sizeof(fd_set)); + if (unlikely(err)) + err = -EFAULT; + +out: + return err < 0 ? err : bend; +} + +long unionfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + long err; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + err = unionfs_file_revalidate(file, parent, true); + if (unlikely(err)) + goto out; + + /* check if asked for local commands */ + switch (cmd) { + case UNIONFS_IOCTL_INCGEN: + /* Increment the superblock generation count */ + pr_info("unionfs: incgen ioctl deprecated; " + "use \"-o remount,incgen\"\n"); + err = -ENOSYS; + break; + + case UNIONFS_IOCTL_QUERYFILE: + /* Return list of branches containing the given file */ + err = unionfs_ioctl_queryfile(file, parent, cmd, arg); + break; + + default: + /* pass the ioctl down */ + err = do_ioctl(file, cmd, arg); + break; + } + +out: + unionfs_check_file(file); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +int unionfs_flush(struct file *file, fl_owner_t id) +{ + int err = 0; + struct file *lower_file = NULL; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + int bindex, bstart, bend; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + err = unionfs_file_revalidate(file, parent, + UNIONFS_F(file)->wrote_to_file); + if (unlikely(err)) + goto out; + unionfs_check_file(file); + + bstart = fbstart(file); + bend = fbend(file); + for (bindex = bstart; bindex <= bend; bindex++) { + lower_file = unionfs_lower_file_idx(file, bindex); + + if (lower_file && lower_file->f_op && + lower_file->f_op->flush) { + err = lower_file->f_op->flush(lower_file, id); + if (err) + goto out; + } + + } + +out: + if (!err) + unionfs_check_file(file); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} diff --git a/fs/unionfs/copyup.c b/fs/unionfs/copyup.c new file mode 100644 index 0000000..bba3a75 --- /dev/null +++ b/fs/unionfs/copyup.c @@ -0,0 +1,896 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* + * For detailed explanation of copyup see: + * Documentation/filesystems/unionfs/concepts.txt + */ + +#ifdef CONFIG_UNION_FS_XATTR +/* copyup all extended attrs for a given dentry */ +static int copyup_xattrs(struct dentry *old_lower_dentry, + struct dentry *new_lower_dentry) +{ + int err = 0; + ssize_t list_size = -1; + char *name_list = NULL; + char *attr_value = NULL; + char *name_list_buf = NULL; + + /* query the actual size of the xattr list */ + list_size = vfs_listxattr(old_lower_dentry, NULL, 0); + if (list_size <= 0) { + err = list_size; + goto out; + } + + /* allocate space for the actual list */ + name_list = unionfs_xattr_alloc(list_size + 1, XATTR_LIST_MAX); + if (unlikely(!name_list || IS_ERR(name_list))) { + err = PTR_ERR(name_list); + goto out; + } + + name_list_buf = name_list; /* save for kfree at end */ + + /* now get the actual xattr list of the source file */ + list_size = vfs_listxattr(old_lower_dentry, name_list, list_size); + if (list_size <= 0) { + err = list_size; + goto out; + } + + /* allocate space to hold each xattr's value */ + attr_value = unionfs_xattr_alloc(XATTR_SIZE_MAX, XATTR_SIZE_MAX); + if (unlikely(!attr_value || IS_ERR(attr_value))) { + err = PTR_ERR(name_list); + goto out; + } + + /* in a loop, get and set each xattr from src to dst file */ + while (*name_list) { + ssize_t size; + + /* Lock here since vfs_getxattr doesn't lock for us */ + mutex_lock(&old_lower_dentry->d_inode->i_mutex); + size = vfs_getxattr(old_lower_dentry, name_list, + attr_value, XATTR_SIZE_MAX); + mutex_unlock(&old_lower_dentry->d_inode->i_mutex); + if (size < 0) { + err = size; + goto out; + } + if (size > XATTR_SIZE_MAX) { + err = -E2BIG; + goto out; + } + /* Don't lock here since vfs_setxattr does it for us. */ + err = vfs_setxattr(new_lower_dentry, name_list, attr_value, + size, 0); + /* + * Selinux depends on "security.*" xattrs, so to maintain + * the security of copied-up files, if Selinux is active, + * then we must copy these xattrs as well. So we need to + * temporarily get FOWNER privileges. + * XXX: move entire copyup code to SIOQ. + */ + if (err == -EPERM && !capable(CAP_FOWNER)) { + const struct cred *old_creds; + struct cred *new_creds; + + new_creds = prepare_creds(); + if (unlikely(!new_creds)) { + err = -ENOMEM; + goto out; + } + cap_raise(new_creds->cap_effective, CAP_FOWNER); + old_creds = override_creds(new_creds); + err = vfs_setxattr(new_lower_dentry, name_list, + attr_value, size, 0); + revert_creds(old_creds); + } + if (err < 0) + goto out; + name_list += strlen(name_list) + 1; + } +out: + unionfs_xattr_kfree(name_list_buf); + unionfs_xattr_kfree(attr_value); + /* Ignore if xattr isn't supported */ + if (err == -ENOTSUPP || err == -EOPNOTSUPP) + err = 0; + return err; +} +#endif /* CONFIG_UNION_FS_XATTR */ + +/* + * Determine the mode based on the copyup flags, and the existing dentry. + * + * Handle file systems which may not support certain options. For example + * jffs2 doesn't allow one to chmod a symlink. So we ignore such harmless + * errors, rather than propagating them up, which results in copyup errors + * and errors returned back to users. + */ +static int copyup_permissions(struct super_block *sb, + struct dentry *old_lower_dentry, + struct dentry *new_lower_dentry) +{ + struct inode *i = old_lower_dentry->d_inode; + struct iattr newattrs; + int err; + + newattrs.ia_atime = i->i_atime; + newattrs.ia_mtime = i->i_mtime; + newattrs.ia_ctime = i->i_ctime; + newattrs.ia_gid = i->i_gid; + newattrs.ia_uid = i->i_uid; + newattrs.ia_valid = ATTR_CTIME | ATTR_ATIME | ATTR_MTIME | + ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_FORCE | + ATTR_GID | ATTR_UID; + mutex_lock(&new_lower_dentry->d_inode->i_mutex); + err = notify_change(new_lower_dentry, &newattrs); + if (err) + goto out; + + /* now try to change the mode and ignore EOPNOTSUPP on symlinks */ + newattrs.ia_mode = i->i_mode; + newattrs.ia_valid = ATTR_MODE | ATTR_FORCE; + err = notify_change(new_lower_dentry, &newattrs); + if (err == -EOPNOTSUPP && + S_ISLNK(new_lower_dentry->d_inode->i_mode)) { + printk(KERN_WARNING + "unionfs: changing \"%s\" symlink mode unsupported\n", + new_lower_dentry->d_name.name); + err = 0; + } + +out: + mutex_unlock(&new_lower_dentry->d_inode->i_mutex); + return err; +} + +/* + * create the new device/file/directory - use copyup_permission to copyup + * times, and mode + * + * if the object being copied up is a regular file, the file is only created, + * the contents have to be copied up separately + */ +static int __copyup_ndentry(struct dentry *old_lower_dentry, + struct dentry *new_lower_dentry, + struct dentry *new_lower_parent_dentry, + char *symbuf) +{ + int err = 0; + umode_t old_mode = old_lower_dentry->d_inode->i_mode; + struct sioq_args args; + + if (S_ISDIR(old_mode)) { + args.mkdir.parent = new_lower_parent_dentry->d_inode; + args.mkdir.dentry = new_lower_dentry; + args.mkdir.mode = old_mode; + + run_sioq(__unionfs_mkdir, &args); + err = args.err; + } else if (S_ISLNK(old_mode)) { + args.symlink.parent = new_lower_parent_dentry->d_inode; + args.symlink.dentry = new_lower_dentry; + args.symlink.symbuf = symbuf; + + run_sioq(__unionfs_symlink, &args); + err = args.err; + } else if (S_ISBLK(old_mode) || S_ISCHR(old_mode) || + S_ISFIFO(old_mode) || S_ISSOCK(old_mode)) { + args.mknod.parent = new_lower_parent_dentry->d_inode; + args.mknod.dentry = new_lower_dentry; + args.mknod.mode = old_mode; + args.mknod.dev = old_lower_dentry->d_inode->i_rdev; + + run_sioq(__unionfs_mknod, &args); + err = args.err; + } else if (S_ISREG(old_mode)) { + struct nameidata nd; + err = init_lower_nd(&nd, LOOKUP_CREATE); + if (unlikely(err < 0)) + goto out; + args.create.nd = &nd; + args.create.parent = new_lower_parent_dentry->d_inode; + args.create.dentry = new_lower_dentry; + args.create.mode = old_mode; + + run_sioq(__unionfs_create, &args); + err = args.err; + release_lower_nd(&nd, err); + } else { + printk(KERN_CRIT "unionfs: unknown inode type %d\n", + old_mode); + BUG(); + } + +out: + return err; +} + +static int __copyup_reg_data(struct dentry *dentry, + struct dentry *new_lower_dentry, int new_bindex, + struct dentry *old_lower_dentry, int old_bindex, + struct file **copyup_file, loff_t len) +{ + struct super_block *sb = dentry->d_sb; + struct file *input_file; + struct file *output_file; + struct vfsmount *output_mnt; + mm_segment_t old_fs; + char *buf = NULL; + ssize_t read_bytes, write_bytes; + loff_t size; + int err = 0; + + /* open old file */ + unionfs_mntget(dentry, old_bindex); + branchget(sb, old_bindex); + /* dentry_open calls dput and mntput if it returns an error */ + input_file = dentry_open(old_lower_dentry, + unionfs_lower_mnt_idx(dentry, old_bindex), + O_RDONLY | O_LARGEFILE, current_cred()); + if (IS_ERR(input_file)) { + dput(old_lower_dentry); + err = PTR_ERR(input_file); + goto out; + } + if (unlikely(!input_file->f_op || !input_file->f_op->read)) { + err = -EINVAL; + goto out_close_in; + } + + /* open new file */ + dget(new_lower_dentry); + output_mnt = unionfs_mntget(sb->s_root, new_bindex); + branchget(sb, new_bindex); + output_file = dentry_open(new_lower_dentry, output_mnt, + O_RDWR | O_LARGEFILE, current_cred()); + if (IS_ERR(output_file)) { + err = PTR_ERR(output_file); + goto out_close_in2; + } + if (unlikely(!output_file->f_op || !output_file->f_op->write)) { + err = -EINVAL; + goto out_close_out; + } + + /* allocating a buffer */ + buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (unlikely(!buf)) { + err = -ENOMEM; + goto out_close_out; + } + + input_file->f_pos = 0; + output_file->f_pos = 0; + + old_fs = get_fs(); + set_fs(KERNEL_DS); + + size = len; + err = 0; + do { + if (len >= PAGE_SIZE) + size = PAGE_SIZE; + else if ((len < PAGE_SIZE) && (len > 0)) + size = len; + + len -= PAGE_SIZE; + + read_bytes = + input_file->f_op->read(input_file, + (char __user *)buf, size, + &input_file->f_pos); + if (read_bytes <= 0) { + err = read_bytes; + break; + } + + /* see Documentation/filesystems/unionfs/issues.txt */ + lockdep_off(); + write_bytes = + output_file->f_op->write(output_file, + (char __user *)buf, + read_bytes, + &output_file->f_pos); + lockdep_on(); + if ((write_bytes < 0) || (write_bytes < read_bytes)) { + err = write_bytes; + break; + } + } while ((read_bytes > 0) && (len > 0)); + + set_fs(old_fs); + + kfree(buf); + + if (!err) + err = output_file->f_op->fsync(output_file, 0); + + if (err) + goto out_close_out; + + if (copyup_file) { + *copyup_file = output_file; + goto out_close_in; + } + +out_close_out: + fput(output_file); + +out_close_in2: + branchput(sb, new_bindex); + +out_close_in: + fput(input_file); + +out: + branchput(sb, old_bindex); + + return err; +} + +/* + * dput the lower references for old and new dentry & clear a lower dentry + * pointer + */ +static void __clear(struct dentry *dentry, struct dentry *old_lower_dentry, + int old_bstart, int old_bend, + struct dentry *new_lower_dentry, int new_bindex) +{ + /* get rid of the lower dentry and all its traces */ + unionfs_set_lower_dentry_idx(dentry, new_bindex, NULL); + dbstart(dentry) = old_bstart; + dbend(dentry) = old_bend; + + dput(new_lower_dentry); + dput(old_lower_dentry); +} + +/* + * Copy up a dentry to a file of specified name. + * + * @dir: used to pull the ->i_sb to access other branches + * @dentry: the non-negative dentry whose lower_inode we should copy + * @bstart: the branch of the lower_inode to copy from + * @new_bindex: the branch to create the new file in + * @name: the name of the file to create + * @namelen: length of @name + * @copyup_file: the "struct file" to return (optional) + * @len: how many bytes to copy-up? + */ +int copyup_dentry(struct inode *dir, struct dentry *dentry, int bstart, + int new_bindex, const char *name, int namelen, + struct file **copyup_file, loff_t len) +{ + struct dentry *new_lower_dentry; + struct dentry *old_lower_dentry = NULL; + struct super_block *sb; + int err = 0; + int old_bindex; + int old_bstart; + int old_bend; + struct dentry *new_lower_parent_dentry = NULL; + mm_segment_t oldfs; + char *symbuf = NULL; + + verify_locked(dentry); + + old_bindex = bstart; + old_bstart = dbstart(dentry); + old_bend = dbend(dentry); + + BUG_ON(new_bindex < 0); + BUG_ON(new_bindex >= old_bindex); + + sb = dir->i_sb; + + err = is_robranch_super(sb, new_bindex); + if (err) + goto out; + + /* Create the directory structure above this dentry. */ + new_lower_dentry = create_parents(dir, dentry, name, new_bindex); + if (IS_ERR(new_lower_dentry)) { + err = PTR_ERR(new_lower_dentry); + goto out; + } + + old_lower_dentry = unionfs_lower_dentry_idx(dentry, old_bindex); + /* we conditionally dput this old_lower_dentry at end of function */ + dget(old_lower_dentry); + + /* For symlinks, we must read the link before we lock the directory. */ + if (S_ISLNK(old_lower_dentry->d_inode->i_mode)) { + + symbuf = kmalloc(PATH_MAX, GFP_KERNEL); + if (unlikely(!symbuf)) { + __clear(dentry, old_lower_dentry, + old_bstart, old_bend, + new_lower_dentry, new_bindex); + err = -ENOMEM; + goto out_free; + } + + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = old_lower_dentry->d_inode->i_op->readlink( + old_lower_dentry, + (char __user *)symbuf, + PATH_MAX); + set_fs(oldfs); + if (err < 0) { + __clear(dentry, old_lower_dentry, + old_bstart, old_bend, + new_lower_dentry, new_bindex); + goto out_free; + } + symbuf[err] = '\0'; + } + + /* Now we lock the parent, and create the object in the new branch. */ + new_lower_parent_dentry = lock_parent(new_lower_dentry); + + /* create the new inode */ + err = __copyup_ndentry(old_lower_dentry, new_lower_dentry, + new_lower_parent_dentry, symbuf); + + if (err) { + __clear(dentry, old_lower_dentry, + old_bstart, old_bend, + new_lower_dentry, new_bindex); + goto out_unlock; + } + + /* We actually copyup the file here. */ + if (S_ISREG(old_lower_dentry->d_inode->i_mode)) + err = __copyup_reg_data(dentry, new_lower_dentry, new_bindex, + old_lower_dentry, old_bindex, + copyup_file, len); + if (err) + goto out_unlink; + + /* Set permissions. */ + err = copyup_permissions(sb, old_lower_dentry, new_lower_dentry); + if (err) + goto out_unlink; + +#ifdef CONFIG_UNION_FS_XATTR + /* Selinux uses extended attributes for permissions. */ + err = copyup_xattrs(old_lower_dentry, new_lower_dentry); + if (err) + goto out_unlink; +#endif /* CONFIG_UNION_FS_XATTR */ + + /* do not allow files getting deleted to be re-interposed */ + if (!d_deleted(dentry)) + unionfs_reinterpose(dentry); + + goto out_unlock; + +out_unlink: + /* + * copyup failed, because we possibly ran out of space or + * quota, or something else happened so let's unlink; we don't + * really care about the return value of vfs_unlink + */ + vfs_unlink(new_lower_parent_dentry->d_inode, new_lower_dentry); + + if (copyup_file) { + /* need to close the file */ + + fput(*copyup_file); + branchput(sb, new_bindex); + } + + /* + * TODO: should we reset the error to something like -EIO? + * + * If we don't reset, the user may get some nonsensical errors, but + * on the other hand, if we reset to EIO, we guarantee that the user + * will get a "confusing" error message. + */ + +out_unlock: + unlock_dir(new_lower_parent_dentry); + +out_free: + /* + * If old_lower_dentry was not a file, then we need to dput it. If + * it was a file, then it was already dput indirectly by other + * functions we call above which operate on regular files. + */ + if (old_lower_dentry && old_lower_dentry->d_inode && + !S_ISREG(old_lower_dentry->d_inode->i_mode)) + dput(old_lower_dentry); + kfree(symbuf); + + if (err) { + /* + * if directory creation succeeded, but inode copyup failed, + * then purge new dentries. + */ + if (dbstart(dentry) < old_bstart && + ibstart(dentry->d_inode) > dbstart(dentry)) + __clear(dentry, NULL, old_bstart, old_bend, + unionfs_lower_dentry(dentry), dbstart(dentry)); + goto out; + } + if (!S_ISDIR(dentry->d_inode->i_mode)) { + unionfs_postcopyup_release(dentry); + if (!unionfs_lower_inode(dentry->d_inode)) { + /* + * If we got here, then we copied up to an + * unlinked-open file, whose name is .unionfsXXXXX. + */ + struct inode *inode = new_lower_dentry->d_inode; + atomic_inc(&inode->i_count); + unionfs_set_lower_inode_idx(dentry->d_inode, + ibstart(dentry->d_inode), + inode); + } + } + unionfs_postcopyup_setmnt(dentry); + /* sync inode times from copied-up inode to our inode */ + unionfs_copy_attr_times(dentry->d_inode); + unionfs_check_inode(dir); + unionfs_check_dentry(dentry); +out: + return err; +} + +/* + * This function creates a copy of a file represented by 'file' which + * currently resides in branch 'bstart' to branch 'new_bindex.' The copy + * will be named "name". + */ +int copyup_named_file(struct inode *dir, struct file *file, char *name, + int bstart, int new_bindex, loff_t len) +{ + int err = 0; + struct file *output_file = NULL; + + err = copyup_dentry(dir, file->f_path.dentry, bstart, new_bindex, + name, strlen(name), &output_file, len); + if (!err) { + fbstart(file) = new_bindex; + unionfs_set_lower_file_idx(file, new_bindex, output_file); + } + + return err; +} + +/* + * This function creates a copy of a file represented by 'file' which + * currently resides in branch 'bstart' to branch 'new_bindex'. + */ +int copyup_file(struct inode *dir, struct file *file, int bstart, + int new_bindex, loff_t len) +{ + int err = 0; + struct file *output_file = NULL; + struct dentry *dentry = file->f_path.dentry; + + err = copyup_dentry(dir, dentry, bstart, new_bindex, + dentry->d_name.name, dentry->d_name.len, + &output_file, len); + if (!err) { + fbstart(file) = new_bindex; + unionfs_set_lower_file_idx(file, new_bindex, output_file); + } + + return err; +} + +/* purge a dentry's lower-branch states (dput/mntput, etc.) */ +static void __cleanup_dentry(struct dentry *dentry, int bindex, + int old_bstart, int old_bend) +{ + int loop_start; + int loop_end; + int new_bstart = -1; + int new_bend = -1; + int i; + + loop_start = min(old_bstart, bindex); + loop_end = max(old_bend, bindex); + + /* + * This loop sets the bstart and bend for the new dentry by + * traversing from left to right. It also dputs all negative + * dentries except bindex + */ + for (i = loop_start; i <= loop_end; i++) { + if (!unionfs_lower_dentry_idx(dentry, i)) + continue; + + if (i == bindex) { + new_bend = i; + if (new_bstart < 0) + new_bstart = i; + continue; + } + + if (!unionfs_lower_dentry_idx(dentry, i)->d_inode) { + dput(unionfs_lower_dentry_idx(dentry, i)); + unionfs_set_lower_dentry_idx(dentry, i, NULL); + + unionfs_mntput(dentry, i); + unionfs_set_lower_mnt_idx(dentry, i, NULL); + } else { + if (new_bstart < 0) + new_bstart = i; + new_bend = i; + } + } + + if (new_bstart < 0) + new_bstart = bindex; + if (new_bend < 0) + new_bend = bindex; + dbstart(dentry) = new_bstart; + dbend(dentry) = new_bend; + +} + +/* set lower inode ptr and update bstart & bend if necessary */ +static void __set_inode(struct dentry *upper, struct dentry *lower, + int bindex) +{ + unionfs_set_lower_inode_idx(upper->d_inode, bindex, + igrab(lower->d_inode)); + if (likely(ibstart(upper->d_inode) > bindex)) + ibstart(upper->d_inode) = bindex; + if (likely(ibend(upper->d_inode) < bindex)) + ibend(upper->d_inode) = bindex; + +} + +/* set lower dentry ptr and update bstart & bend if necessary */ +static void __set_dentry(struct dentry *upper, struct dentry *lower, + int bindex) +{ + unionfs_set_lower_dentry_idx(upper, bindex, lower); + if (likely(dbstart(upper) > bindex)) + dbstart(upper) = bindex; + if (likely(dbend(upper) < bindex)) + dbend(upper) = bindex; +} + +/* + * This function replicates the directory structure up-to given dentry + * in the bindex branch. + */ +struct dentry *create_parents(struct inode *dir, struct dentry *dentry, + const char *name, int bindex) +{ + int err; + struct dentry *child_dentry; + struct dentry *parent_dentry; + struct dentry *lower_parent_dentry = NULL; + struct dentry *lower_dentry = NULL; + const char *childname; + unsigned int childnamelen; + int nr_dentry; + int count = 0; + int old_bstart; + int old_bend; + struct dentry **path = NULL; + struct super_block *sb; + + verify_locked(dentry); + + err = is_robranch_super(dir->i_sb, bindex); + if (err) { + lower_dentry = ERR_PTR(err); + goto out; + } + + old_bstart = dbstart(dentry); + old_bend = dbend(dentry); + + lower_dentry = ERR_PTR(-ENOMEM); + + /* There is no sense allocating any less than the minimum. */ + nr_dentry = 1; + path = kmalloc(nr_dentry * sizeof(struct dentry *), GFP_KERNEL); + if (unlikely(!path)) + goto out; + + /* assume the negative dentry of unionfs as the parent dentry */ + parent_dentry = dentry; + + /* + * This loop finds the first parent that exists in the given branch. + * We start building the directory structure from there. At the end + * of the loop, the following should hold: + * - child_dentry is the first nonexistent child + * - parent_dentry is the first existent parent + * - path[0] is the = deepest child + * - path[count] is the first child to create + */ + do { + child_dentry = parent_dentry; + + /* find the parent directory dentry in unionfs */ + parent_dentry = dget_parent(child_dentry); + + /* find out the lower_parent_dentry in the given branch */ + lower_parent_dentry = + unionfs_lower_dentry_idx(parent_dentry, bindex); + + /* grow path table */ + if (count == nr_dentry) { + void *p; + + nr_dentry *= 2; + p = krealloc(path, nr_dentry * sizeof(struct dentry *), + GFP_KERNEL); + if (unlikely(!p)) { + lower_dentry = ERR_PTR(-ENOMEM); + goto out; + } + path = p; + } + + /* store the child dentry */ + path[count++] = child_dentry; + } while (!lower_parent_dentry); + count--; + + sb = dentry->d_sb; + + /* + * This code goes between the begin/end labels and basically + * emulates a while(child_dentry != dentry), only cleaner and + * shorter than what would be a much longer while loop. + */ +begin: + /* get lower parent dir in the current branch */ + lower_parent_dentry = unionfs_lower_dentry_idx(parent_dentry, bindex); + dput(parent_dentry); + + /* init the values to lookup */ + childname = child_dentry->d_name.name; + childnamelen = child_dentry->d_name.len; + + if (child_dentry != dentry) { + /* lookup child in the underlying file system */ + lower_dentry = lookup_lck_len(childname, lower_parent_dentry, + childnamelen); + if (IS_ERR(lower_dentry)) + goto out; + } else { + /* + * Is the name a whiteout of the child name ? lookup the + * whiteout child in the underlying file system + */ + lower_dentry = lookup_lck_len(name, lower_parent_dentry, + strlen(name)); + if (IS_ERR(lower_dentry)) + goto out; + + /* Replace the current dentry (if any) with the new one */ + dput(unionfs_lower_dentry_idx(dentry, bindex)); + unionfs_set_lower_dentry_idx(dentry, bindex, + lower_dentry); + + __cleanup_dentry(dentry, bindex, old_bstart, old_bend); + goto out; + } + + if (lower_dentry->d_inode) { + /* + * since this already exists we dput to avoid + * multiple references on the same dentry + */ + dput(lower_dentry); + } else { + struct sioq_args args; + + /* it's a negative dentry, create a new dir */ + lower_parent_dentry = lock_parent(lower_dentry); + + args.mkdir.parent = lower_parent_dentry->d_inode; + args.mkdir.dentry = lower_dentry; + args.mkdir.mode = child_dentry->d_inode->i_mode; + + run_sioq(__unionfs_mkdir, &args); + err = args.err; + + if (!err) + err = copyup_permissions(dir->i_sb, child_dentry, + lower_dentry); + unlock_dir(lower_parent_dentry); + if (err) { + dput(lower_dentry); + lower_dentry = ERR_PTR(err); + goto out; + } + + } + + __set_inode(child_dentry, lower_dentry, bindex); + __set_dentry(child_dentry, lower_dentry, bindex); + /* + * update times of this dentry, but also the parent, because if + * we changed, the parent may have changed too. + */ + fsstack_copy_attr_times(parent_dentry->d_inode, + lower_parent_dentry->d_inode); + unionfs_copy_attr_times(child_dentry->d_inode); + + parent_dentry = child_dentry; + child_dentry = path[--count]; + goto begin; +out: + /* cleanup any leftover locks from the do/while loop above */ + if (IS_ERR(lower_dentry)) + while (count) + dput(path[count--]); + kfree(path); + return lower_dentry; +} + +/* + * Post-copyup helper to ensure we have valid mnts: set lower mnt of + * dentry+parents to the first parent node that has an mnt. + */ +void unionfs_postcopyup_setmnt(struct dentry *dentry) +{ + struct dentry *parent, *hasone; + int bindex = dbstart(dentry); + + if (unionfs_lower_mnt_idx(dentry, bindex)) + return; + hasone = dentry->d_parent; + /* this loop should stop at root dentry */ + while (!unionfs_lower_mnt_idx(hasone, bindex)) + hasone = hasone->d_parent; + parent = dentry; + while (!unionfs_lower_mnt_idx(parent, bindex)) { + unionfs_set_lower_mnt_idx(parent, bindex, + unionfs_mntget(hasone, bindex)); + parent = parent->d_parent; + } +} + +/* + * Post-copyup helper to release all non-directory source objects of a + * copied-up file. Regular files should have only one lower object. + */ +void unionfs_postcopyup_release(struct dentry *dentry) +{ + int bstart, bend; + + BUG_ON(S_ISDIR(dentry->d_inode->i_mode)); + bstart = dbstart(dentry); + bend = dbend(dentry); + + path_put_lowers(dentry, bstart + 1, bend, false); + iput_lowers(dentry->d_inode, bstart + 1, bend, false); + + dbend(dentry) = bstart; + ibend(dentry->d_inode) = ibstart(dentry->d_inode) = bstart; +} diff --git a/fs/unionfs/debug.c b/fs/unionfs/debug.c new file mode 100644 index 0000000..100d2c6 --- /dev/null +++ b/fs/unionfs/debug.c @@ -0,0 +1,532 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* + * Helper debugging functions for maintainers (and for users to report back + * useful information back to maintainers) + */ + +/* it's always useful to know what part of the code called us */ +#define PRINT_CALLER(fname, fxn, line) \ + do { \ + if (!printed_caller) { \ + pr_debug("PC:%s:%s:%d\n", (fname), (fxn), (line)); \ + printed_caller = 1; \ + } \ + } while (0) + +/* + * __unionfs_check_{inode,dentry,file} perform exhaustive sanity checking on + * the fan-out of various Unionfs objects. We check that no lower objects + * exist outside the start/end branch range; that all objects within are + * non-NULL (with some allowed exceptions); that for every lower file + * there's a lower dentry+inode; that the start/end ranges match for all + * corresponding lower objects; that open files/symlinks have only one lower + * objects, but directories can have several; and more. + */ +void __unionfs_check_inode(const struct inode *inode, + const char *fname, const char *fxn, int line) +{ + int bindex; + int istart, iend; + struct inode *lower_inode; + struct super_block *sb; + int printed_caller = 0; + void *poison_ptr; + + /* for inodes now */ + BUG_ON(!inode); + sb = inode->i_sb; + istart = ibstart(inode); + iend = ibend(inode); + /* don't check inode if no lower branches */ + if (istart < 0 && iend < 0) + return; + if (unlikely(istart > iend)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" Ci0: inode=%p istart/end=%d:%d\n", + inode, istart, iend); + } + if (unlikely((istart == -1 && iend != -1) || + (istart != -1 && iend == -1))) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" Ci1: inode=%p istart/end=%d:%d\n", + inode, istart, iend); + } + if (!S_ISDIR(inode->i_mode)) { + if (unlikely(iend != istart)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" Ci2: inode=%p istart=%d iend=%d\n", + inode, istart, iend); + } + } + + for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) { + if (unlikely(!UNIONFS_I(inode))) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" Ci3: no inode_info %p\n", inode); + return; + } + if (unlikely(!UNIONFS_I(inode)->lower_inodes)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" Ci4: no lower_inodes %p\n", inode); + return; + } + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (lower_inode) { + memset(&poison_ptr, POISON_INUSE, sizeof(void *)); + if (unlikely(bindex < istart || bindex > iend)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" Ci5: inode/linode=%p:%p bindex=%d " + "istart/end=%d:%d\n", inode, + lower_inode, bindex, istart, iend); + } else if (unlikely(lower_inode == poison_ptr)) { + /* freed inode! */ + PRINT_CALLER(fname, fxn, line); + pr_debug(" Ci6: inode/linode=%p:%p bindex=%d " + "istart/end=%d:%d\n", inode, + lower_inode, bindex, istart, iend); + } + continue; + } + /* if we get here, then lower_inode == NULL */ + if (bindex < istart || bindex > iend) + continue; + /* + * directories can have NULL lower inodes in b/t start/end, + * but NOT if at the start/end range. + */ + if (unlikely(S_ISDIR(inode->i_mode) && + bindex > istart && bindex < iend)) + continue; + PRINT_CALLER(fname, fxn, line); + pr_debug(" Ci7: inode/linode=%p:%p " + "bindex=%d istart/end=%d:%d\n", + inode, lower_inode, bindex, istart, iend); + } +} + +void __unionfs_check_dentry(const struct dentry *dentry, + const char *fname, const char *fxn, int line) +{ + int bindex; + int dstart, dend, istart, iend; + struct dentry *lower_dentry; + struct inode *inode, *lower_inode; + struct super_block *sb; + struct vfsmount *lower_mnt; + int printed_caller = 0; + void *poison_ptr; + + BUG_ON(!dentry); + sb = dentry->d_sb; + inode = dentry->d_inode; + dstart = dbstart(dentry); + dend = dbend(dentry); + /* don't check dentry/mnt if no lower branches */ + if (dstart < 0 && dend < 0) + goto check_inode; + BUG_ON(dstart > dend); + + if (unlikely((dstart == -1 && dend != -1) || + (dstart != -1 && dend == -1))) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CD0: dentry=%p dstart/end=%d:%d\n", + dentry, dstart, dend); + } + /* + * check for NULL dentries inside the start/end range, or + * non-NULL dentries outside the start/end range. + */ + for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (lower_dentry) { + if (unlikely(bindex < dstart || bindex > dend)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CD1: dentry/lower=%p:%p(%p) " + "bindex=%d dstart/end=%d:%d\n", + dentry, lower_dentry, + (lower_dentry ? lower_dentry->d_inode : + (void *) -1L), + bindex, dstart, dend); + } + } else { /* lower_dentry == NULL */ + if (bindex < dstart || bindex > dend) + continue; + /* + * Directories can have NULL lower inodes in b/t + * start/end, but NOT if at the start/end range. + * Ignore this rule, however, if this is a NULL + * dentry or a deleted dentry. + */ + if (unlikely(!d_deleted((struct dentry *) dentry) && + inode && + !(inode && S_ISDIR(inode->i_mode) && + bindex > dstart && bindex < dend))) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CD2: dentry/lower=%p:%p(%p) " + "bindex=%d dstart/end=%d:%d\n", + dentry, lower_dentry, + (lower_dentry ? + lower_dentry->d_inode : + (void *) -1L), + bindex, dstart, dend); + } + } + } + + /* check for vfsmounts same as for dentries */ + for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) { + lower_mnt = unionfs_lower_mnt_idx(dentry, bindex); + if (lower_mnt) { + if (unlikely(bindex < dstart || bindex > dend)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CM0: dentry/lmnt=%p:%p bindex=%d " + "dstart/end=%d:%d\n", dentry, + lower_mnt, bindex, dstart, dend); + } + } else { /* lower_mnt == NULL */ + if (bindex < dstart || bindex > dend) + continue; + /* + * Directories can have NULL lower inodes in b/t + * start/end, but NOT if at the start/end range. + * Ignore this rule, however, if this is a NULL + * dentry. + */ + if (unlikely(inode && + !(inode && S_ISDIR(inode->i_mode) && + bindex > dstart && bindex < dend))) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CM1: dentry/lmnt=%p:%p " + "bindex=%d dstart/end=%d:%d\n", + dentry, lower_mnt, bindex, + dstart, dend); + } + } + } + +check_inode: + /* for inodes now */ + if (!inode) + return; + istart = ibstart(inode); + iend = ibend(inode); + /* don't check inode if no lower branches */ + if (istart < 0 && iend < 0) + return; + BUG_ON(istart > iend); + if (unlikely((istart == -1 && iend != -1) || + (istart != -1 && iend == -1))) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CI0: dentry/inode=%p:%p istart/end=%d:%d\n", + dentry, inode, istart, iend); + } + if (unlikely(istart != dstart)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CI1: dentry/inode=%p:%p istart=%d dstart=%d\n", + dentry, inode, istart, dstart); + } + if (unlikely(iend != dend)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CI2: dentry/inode=%p:%p iend=%d dend=%d\n", + dentry, inode, iend, dend); + } + + if (!S_ISDIR(inode->i_mode)) { + if (unlikely(dend != dstart)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CI3: dentry/inode=%p:%p dstart=%d dend=%d\n", + dentry, inode, dstart, dend); + } + if (unlikely(iend != istart)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CI4: dentry/inode=%p:%p istart=%d iend=%d\n", + dentry, inode, istart, iend); + } + } + + for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (lower_inode) { + memset(&poison_ptr, POISON_INUSE, sizeof(void *)); + if (unlikely(bindex < istart || bindex > iend)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CI5: dentry/linode=%p:%p bindex=%d " + "istart/end=%d:%d\n", dentry, + lower_inode, bindex, istart, iend); + } else if (unlikely(lower_inode == poison_ptr)) { + /* freed inode! */ + PRINT_CALLER(fname, fxn, line); + pr_debug(" CI6: dentry/linode=%p:%p bindex=%d " + "istart/end=%d:%d\n", dentry, + lower_inode, bindex, istart, iend); + } + continue; + } + /* if we get here, then lower_inode == NULL */ + if (bindex < istart || bindex > iend) + continue; + /* + * directories can have NULL lower inodes in b/t start/end, + * but NOT if at the start/end range. + */ + if (unlikely(S_ISDIR(inode->i_mode) && + bindex > istart && bindex < iend)) + continue; + PRINT_CALLER(fname, fxn, line); + pr_debug(" CI7: dentry/linode=%p:%p " + "bindex=%d istart/end=%d:%d\n", + dentry, lower_inode, bindex, istart, iend); + } + + /* + * If it's a directory, then intermediate objects b/t start/end can + * be NULL. But, check that all three are NULL: lower dentry, mnt, + * and inode. + */ + if (dstart >= 0 && dend >= 0 && S_ISDIR(inode->i_mode)) + for (bindex = dstart+1; bindex < dend; bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + lower_dentry = unionfs_lower_dentry_idx(dentry, + bindex); + lower_mnt = unionfs_lower_mnt_idx(dentry, bindex); + if (unlikely(!((lower_inode && lower_dentry && + lower_mnt) || + (!lower_inode && + !lower_dentry && !lower_mnt)))) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" Cx: lmnt/ldentry/linode=%p:%p:%p " + "bindex=%d dstart/end=%d:%d\n", + lower_mnt, lower_dentry, lower_inode, + bindex, dstart, dend); + } + } + /* check if lower inode is newer than upper one (it shouldn't) */ + if (unlikely(is_newer_lower(dentry) && !is_negative_lower(dentry))) { + PRINT_CALLER(fname, fxn, line); + for (bindex = ibstart(inode); bindex <= ibend(inode); + bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (unlikely(!lower_inode)) + continue; + pr_debug(" CI8: bindex=%d mtime/lmtime=%lu.%lu/%lu.%lu " + "ctime/lctime=%lu.%lu/%lu.%lu\n", + bindex, + inode->i_mtime.tv_sec, + inode->i_mtime.tv_nsec, + lower_inode->i_mtime.tv_sec, + lower_inode->i_mtime.tv_nsec, + inode->i_ctime.tv_sec, + inode->i_ctime.tv_nsec, + lower_inode->i_ctime.tv_sec, + lower_inode->i_ctime.tv_nsec); + } + } +} + +void __unionfs_check_file(const struct file *file, + const char *fname, const char *fxn, int line) +{ + int bindex; + int dstart, dend, fstart, fend; + struct dentry *dentry; + struct file *lower_file; + struct inode *inode; + struct super_block *sb; + int printed_caller = 0; + + BUG_ON(!file); + dentry = file->f_path.dentry; + sb = dentry->d_sb; + dstart = dbstart(dentry); + dend = dbend(dentry); + BUG_ON(dstart > dend); + fstart = fbstart(file); + fend = fbend(file); + BUG_ON(fstart > fend); + + if (unlikely((fstart == -1 && fend != -1) || + (fstart != -1 && fend == -1))) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CF0: file/dentry=%p:%p fstart/end=%d:%d\n", + file, dentry, fstart, fend); + } + if (unlikely(fstart != dstart)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CF1: file/dentry=%p:%p fstart=%d dstart=%d\n", + file, dentry, fstart, dstart); + } + if (unlikely(fend != dend)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CF2: file/dentry=%p:%p fend=%d dend=%d\n", + file, dentry, fend, dend); + } + inode = dentry->d_inode; + if (!S_ISDIR(inode->i_mode)) { + if (unlikely(fend != fstart)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CF3: file/inode=%p:%p fstart=%d fend=%d\n", + file, inode, fstart, fend); + } + if (unlikely(dend != dstart)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CF4: file/dentry=%p:%p dstart=%d dend=%d\n", + file, dentry, dstart, dend); + } + } + + /* + * check for NULL dentries inside the start/end range, or + * non-NULL dentries outside the start/end range. + */ + for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) { + lower_file = unionfs_lower_file_idx(file, bindex); + if (lower_file) { + if (unlikely(bindex < fstart || bindex > fend)) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CF5: file/lower=%p:%p bindex=%d " + "fstart/end=%d:%d\n", file, + lower_file, bindex, fstart, fend); + } + } else { /* lower_file == NULL */ + if (bindex >= fstart && bindex <= fend) { + /* + * directories can have NULL lower inodes in + * b/t start/end, but NOT if at the + * start/end range. + */ + if (unlikely(!(S_ISDIR(inode->i_mode) && + bindex > fstart && + bindex < fend))) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CF6: file/lower=%p:%p " + "bindex=%d fstart/end=%d:%d\n", + file, lower_file, bindex, + fstart, fend); + } + } + } + } + + __unionfs_check_dentry(dentry, fname, fxn, line); +} + +void __unionfs_check_nd(const struct nameidata *nd, + const char *fname, const char *fxn, int line) +{ + struct file *file; + int printed_caller = 0; + + if (unlikely(!nd)) + return; + if (nd->flags & LOOKUP_OPEN) { + file = nd->intent.open.file; + if (unlikely(file->f_path.dentry && + strcmp(file->f_path.dentry->d_sb->s_type->name, + UNIONFS_NAME))) { + PRINT_CALLER(fname, fxn, line); + pr_debug(" CND1: lower_file of type %s\n", + file->f_path.dentry->d_sb->s_type->name); + } + } +} + +/* useful to track vfsmount leaks that could cause EBUSY on unmount */ +void __show_branch_counts(const struct super_block *sb, + const char *file, const char *fxn, int line) +{ + int i; + struct vfsmount *mnt; + + pr_debug("BC:"); + for (i = 0; i < sbmax(sb); i++) { + if (likely(sb->s_root)) + mnt = UNIONFS_D(sb->s_root)->lower_paths[i].mnt; + else + mnt = NULL; + printk(KERN_CONT "%d:", + (mnt ? atomic_read(&mnt->mnt_count) : -99)); + } + printk(KERN_CONT "%s:%s:%d\n", file, fxn, line); +} + +void __show_inode_times(const struct inode *inode, + const char *file, const char *fxn, int line) +{ + struct inode *lower_inode; + int bindex; + + for (bindex = ibstart(inode); bindex <= ibend(inode); bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (unlikely(!lower_inode)) + continue; + pr_debug("IT(%lu:%d): %s:%s:%d " + "um=%lu/%lu lm=%lu/%lu uc=%lu/%lu lc=%lu/%lu\n", + inode->i_ino, bindex, + file, fxn, line, + inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec, + lower_inode->i_mtime.tv_sec, + lower_inode->i_mtime.tv_nsec, + inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec, + lower_inode->i_ctime.tv_sec, + lower_inode->i_ctime.tv_nsec); + } +} + +void __show_dinode_times(const struct dentry *dentry, + const char *file, const char *fxn, int line) +{ + struct inode *inode = dentry->d_inode; + struct inode *lower_inode; + int bindex; + + for (bindex = ibstart(inode); bindex <= ibend(inode); bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (!lower_inode) + continue; + pr_debug("DT(%s:%lu:%d): %s:%s:%d " + "um=%lu/%lu lm=%lu/%lu uc=%lu/%lu lc=%lu/%lu\n", + dentry->d_name.name, inode->i_ino, bindex, + file, fxn, line, + inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec, + lower_inode->i_mtime.tv_sec, + lower_inode->i_mtime.tv_nsec, + inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec, + lower_inode->i_ctime.tv_sec, + lower_inode->i_ctime.tv_nsec); + } +} + +void __show_inode_counts(const struct inode *inode, + const char *file, const char *fxn, int line) +{ + struct inode *lower_inode; + int bindex; + + if (unlikely(!inode)) { + pr_debug("SiC: Null inode\n"); + return; + } + for (bindex = sbstart(inode->i_sb); bindex <= sbend(inode->i_sb); + bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (unlikely(!lower_inode)) + continue; + pr_debug("SIC(%lu:%d:%d): lc=%d %s:%s:%d\n", + inode->i_ino, bindex, + atomic_read(&(inode)->i_count), + atomic_read(&(lower_inode)->i_count), + file, fxn, line); + } +} diff --git a/fs/unionfs/dentry.c b/fs/unionfs/dentry.c new file mode 100644 index 0000000..a0c3bba --- /dev/null +++ b/fs/unionfs/dentry.c @@ -0,0 +1,397 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +bool is_negative_lower(const struct dentry *dentry) +{ + int bindex; + struct dentry *lower_dentry; + + BUG_ON(!dentry); + /* cache coherency: check if file was deleted on lower branch */ + if (dbstart(dentry) < 0) + return true; + for (bindex = dbstart(dentry); bindex <= dbend(dentry); bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + /* unhashed (i.e., unlinked) lower dentries don't count */ + if (lower_dentry && lower_dentry->d_inode && + !d_deleted(lower_dentry) && + !(lower_dentry->d_flags & DCACHE_NFSFS_RENAMED)) + return false; + } + return true; +} + +static inline void __dput_lowers(struct dentry *dentry, int start, int end) +{ + struct dentry *lower_dentry; + int bindex; + + if (start < 0) + return; + for (bindex = start; bindex <= end; bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (!lower_dentry) + continue; + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); + dput(lower_dentry); + } +} + +/* + * Purge and invalidate as many data pages of a unionfs inode. This is + * called when the lower inode has changed, and we want to force processes + * to re-get the new data. + */ +static inline void purge_inode_data(struct inode *inode) +{ + /* remove all non-private mappings */ + unmap_mapping_range(inode->i_mapping, 0, 0, 0); + /* invalidate as many pages as possible */ + invalidate_mapping_pages(inode->i_mapping, 0, -1); + /* + * Don't try to truncate_inode_pages here, because this could lead + * to a deadlock between some of address_space ops and dentry + * revalidation: the address space op is invoked with a lock on our + * own page, and truncate_inode_pages will block on locked pages. + */ +} + +/* + * Revalidate a single file/symlink/special dentry. Assume that info nodes + * of the @dentry and its @parent are locked. Assume parent is valid, + * otherwise return false (and let's hope the VFS will try to re-lookup this + * dentry). Returns true if valid, false otherwise. + */ +bool __unionfs_d_revalidate(struct dentry *dentry, struct dentry *parent, + bool willwrite) +{ + bool valid = true; /* default is valid */ + struct dentry *lower_dentry; + struct dentry *result; + int bindex, bstart, bend; + int sbgen, dgen, pdgen; + int positive = 0; + int interpose_flag; + + verify_locked(dentry); + verify_locked(parent); + + /* if the dentry is unhashed, do NOT revalidate */ + if (d_deleted(dentry)) + goto out; + + dgen = atomic_read(&UNIONFS_D(dentry)->generation); + + if (is_newer_lower(dentry)) { + /* root dentry is always valid */ + if (IS_ROOT(dentry)) { + unionfs_copy_attr_times(dentry->d_inode); + } else { + /* + * reset generation number to zero, guaranteed to be + * "old" + */ + dgen = 0; + atomic_set(&UNIONFS_D(dentry)->generation, dgen); + } + if (!willwrite) + purge_inode_data(dentry->d_inode); + } + + sbgen = atomic_read(&UNIONFS_SB(dentry->d_sb)->generation); + + BUG_ON(dbstart(dentry) == -1); + if (dentry->d_inode) + positive = 1; + + /* if our dentry is valid, then validate all lower ones */ + if (sbgen == dgen) + goto validate_lowers; + + /* The root entry should always be valid */ + BUG_ON(IS_ROOT(dentry)); + + /* We can't work correctly if our parent isn't valid. */ + pdgen = atomic_read(&UNIONFS_D(parent)->generation); + + /* Free the pointers for our inodes and this dentry. */ + path_put_lowers_all(dentry, false); + + interpose_flag = INTERPOSE_REVAL_NEG; + if (positive) { + interpose_flag = INTERPOSE_REVAL; + iput_lowers_all(dentry->d_inode, true); + } + + if (realloc_dentry_private_data(dentry) != 0) { + valid = false; + goto out; + } + + result = unionfs_lookup_full(dentry, parent, interpose_flag); + if (result) { + if (IS_ERR(result)) { + valid = false; + goto out; + } + /* + * current unionfs_lookup_backend() doesn't return + * a valid dentry + */ + dput(dentry); + dentry = result; + } + + if (unlikely(positive && is_negative_lower(dentry))) { + /* call make_bad_inode here ? */ + d_drop(dentry); + valid = false; + goto out; + } + + /* + * if we got here then we have revalidated our dentry and all lower + * ones, so we can return safely. + */ + if (!valid) /* lower dentry revalidation failed */ + goto out; + + /* + * If the parent's gen no. matches the superblock's gen no., then + * we can update our denty's gen no. If they didn't match, then it + * was OK to revalidate this dentry with a stale parent, but we'll + * purposely not update our dentry's gen no. (so it can be redone); + * and, we'll mark our parent dentry as invalid so it'll force it + * (and our dentry) to be revalidated. + */ + if (pdgen == sbgen) + atomic_set(&UNIONFS_D(dentry)->generation, sbgen); + goto out; + +validate_lowers: + + /* The revalidation must occur across all branches */ + bstart = dbstart(dentry); + bend = dbend(dentry); + BUG_ON(bstart == -1); + for (bindex = bstart; bindex <= bend; bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (!lower_dentry || !lower_dentry->d_op + || !lower_dentry->d_op->d_revalidate) + continue; + /* + * Don't pass nameidata to lower file system, because we + * don't want an arbitrary lower file being opened or + * returned to us: it may be useless to us because of the + * fanout nature of unionfs (cf. file/directory open-file + * invariants). We will open lower files as and when needed + * later on. + */ + if (!lower_dentry->d_op->d_revalidate(lower_dentry, NULL)) + valid = false; + } + + if (!dentry->d_inode || + ibstart(dentry->d_inode) < 0 || + ibend(dentry->d_inode) < 0) { + valid = false; + goto out; + } + + if (valid) { + /* + * If we get here, and we copy the meta-data from the lower + * inode to our inode, then it is vital that we have already + * purged all unionfs-level file data. We do that in the + * caller (__unionfs_d_revalidate) by calling + * purge_inode_data. + */ + unionfs_copy_attr_all(dentry->d_inode, + unionfs_lower_inode(dentry->d_inode)); + fsstack_copy_inode_size(dentry->d_inode, + unionfs_lower_inode(dentry->d_inode)); + } + +out: + return valid; +} + +/* + * Determine if the lower inode objects have changed from below the unionfs + * inode. Return true if changed, false otherwise. + * + * We check if the mtime or ctime have changed. However, the inode times + * can be changed by anyone without much protection, including + * asynchronously. This can sometimes cause unionfs to find that the lower + * file system doesn't change its inode times quick enough, resulting in a + * false positive indication (which is harmless, it just makes unionfs do + * extra work in re-validating the objects). To minimize the chances of + * these situations, we still consider such small time changes valid, but we + * don't print debugging messages unless the time changes are greater than + * UNIONFS_MIN_CC_TIME (which defaults to 3 seconds, as with NFS's acregmin) + * because significant changes are more likely due to users manually + * touching lower files. + */ +bool is_newer_lower(const struct dentry *dentry) +{ + int bindex; + struct inode *inode; + struct inode *lower_inode; + + /* ignore if we're called on semi-initialized dentries/inodes */ + if (!dentry || !UNIONFS_D(dentry)) + return false; + inode = dentry->d_inode; + if (!inode || !UNIONFS_I(inode)->lower_inodes || + ibstart(inode) < 0 || ibend(inode) < 0) + return false; + + for (bindex = ibstart(inode); bindex <= ibend(inode); bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (!lower_inode) + continue; + + /* check if mtime/ctime have changed */ + if (unlikely(timespec_compare(&inode->i_mtime, + &lower_inode->i_mtime) < 0)) { + if ((lower_inode->i_mtime.tv_sec - + inode->i_mtime.tv_sec) > UNIONFS_MIN_CC_TIME) { + pr_info("unionfs: new lower inode mtime " + "(bindex=%d, name=%s)\n", bindex, + dentry->d_name.name); + show_dinode_times(dentry); + } + return true; + } + if (unlikely(timespec_compare(&inode->i_ctime, + &lower_inode->i_ctime) < 0)) { + if ((lower_inode->i_ctime.tv_sec - + inode->i_ctime.tv_sec) > UNIONFS_MIN_CC_TIME) { + pr_info("unionfs: new lower inode ctime " + "(bindex=%d, name=%s)\n", bindex, + dentry->d_name.name); + show_dinode_times(dentry); + } + return true; + } + } + + /* + * Last check: if this is a positive dentry, but somehow all lower + * dentries are negative or unhashed, then this dentry needs to be + * revalidated, because someone probably deleted the objects from + * the lower branches directly. + */ + if (is_negative_lower(dentry)) + return true; + + return false; /* default: lower is not newer */ +} + +static int unionfs_d_revalidate(struct dentry *dentry, + struct nameidata *nd_unused) +{ + bool valid = true; + int err = 1; /* 1 means valid for the VFS */ + struct dentry *parent; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (valid) { + unionfs_postcopyup_setmnt(dentry); + unionfs_check_dentry(dentry); + } else { + d_drop(dentry); + err = valid; + } + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + + return err; +} + +static void unionfs_d_release(struct dentry *dentry) +{ + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + if (unlikely(!UNIONFS_D(dentry))) + goto out; /* skip if no lower branches */ + /* must lock our branch configuration here */ + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + unionfs_check_dentry(dentry); + /* this could be a negative dentry, so check first */ + if (dbstart(dentry) < 0) { + unionfs_unlock_dentry(dentry); + goto out; /* due to a (normal) failed lookup */ + } + + /* Release all the lower dentries */ + path_put_lowers_all(dentry, true); + + unionfs_unlock_dentry(dentry); + +out: + free_dentry_private_data(dentry); + unionfs_read_unlock(dentry->d_sb); + return; +} + +/* + * Called when we're removing the last reference to our dentry. So we + * should drop all lower references too. + */ +static void unionfs_d_iput(struct dentry *dentry, struct inode *inode) +{ + int rc; + + BUG_ON(!dentry); + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + if (!UNIONFS_D(dentry) || dbstart(dentry) < 0) + goto drop_lower_inodes; + path_put_lowers_all(dentry, false); + +drop_lower_inodes: + rc = atomic_read(&inode->i_count); + if (rc == 1 && inode->i_nlink == 1 && ibstart(inode) >= 0) { + /* see Documentation/filesystems/unionfs/issues.txt */ + lockdep_off(); + iput(unionfs_lower_inode(inode)); + lockdep_on(); + unionfs_set_lower_inode(inode, NULL); + /* XXX: may need to set start/end to -1? */ + } + + iput(inode); + + unionfs_unlock_dentry(dentry); + unionfs_read_unlock(dentry->d_sb); +} + +struct dentry_operations unionfs_dops = { + .d_revalidate = unionfs_d_revalidate, + .d_release = unionfs_d_release, + .d_iput = unionfs_d_iput, +}; diff --git a/fs/unionfs/dirfops.c b/fs/unionfs/dirfops.c new file mode 100644 index 0000000..7da0ff0 --- /dev/null +++ b/fs/unionfs/dirfops.c @@ -0,0 +1,302 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* Make sure our rdstate is playing by the rules. */ +static void verify_rdstate_offset(struct unionfs_dir_state *rdstate) +{ + BUG_ON(rdstate->offset >= DIREOF); + BUG_ON(rdstate->cookie >= MAXRDCOOKIE); +} + +struct unionfs_getdents_callback { + struct unionfs_dir_state *rdstate; + void *dirent; + int entries_written; + int filldir_called; + int filldir_error; + filldir_t filldir; + struct super_block *sb; +}; + +/* based on generic filldir in fs/readir.c */ +static int unionfs_filldir(void *dirent, const char *oname, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct unionfs_getdents_callback *buf = dirent; + struct filldir_node *found = NULL; + int err = 0; + int is_whiteout; + char *name = (char *) oname; + + buf->filldir_called++; + + is_whiteout = is_whiteout_name(&name, &namelen); + + found = find_filldir_node(buf->rdstate, name, namelen, is_whiteout); + + if (found) { + /* + * If we had non-whiteout entry in dir cache, then mark it + * as a whiteout and but leave it in the dir cache. + */ + if (is_whiteout && !found->whiteout) + found->whiteout = is_whiteout; + goto out; + } + + /* if 'name' isn't a whiteout, filldir it. */ + if (!is_whiteout) { + off_t pos = rdstate2offset(buf->rdstate); + u64 unionfs_ino = ino; + + err = buf->filldir(buf->dirent, name, namelen, pos, + unionfs_ino, d_type); + buf->rdstate->offset++; + verify_rdstate_offset(buf->rdstate); + } + /* + * If we did fill it, stuff it in our hash, otherwise return an + * error. + */ + if (err) { + buf->filldir_error = err; + goto out; + } + buf->entries_written++; + err = add_filldir_node(buf->rdstate, name, namelen, + buf->rdstate->bindex, is_whiteout); + if (err) + buf->filldir_error = err; + +out: + return err; +} + +static int unionfs_readdir(struct file *file, void *dirent, filldir_t filldir) +{ + int err = 0; + struct file *lower_file = NULL; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + struct inode *inode = NULL; + struct unionfs_getdents_callback buf; + struct unionfs_dir_state *uds; + int bend; + loff_t offset; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + err = unionfs_file_revalidate(file, parent, false); + if (unlikely(err)) + goto out; + + inode = dentry->d_inode; + + uds = UNIONFS_F(file)->rdstate; + if (!uds) { + if (file->f_pos == DIREOF) { + goto out; + } else if (file->f_pos > 0) { + uds = find_rdstate(inode, file->f_pos); + if (unlikely(!uds)) { + err = -ESTALE; + goto out; + } + UNIONFS_F(file)->rdstate = uds; + } else { + init_rdstate(file); + uds = UNIONFS_F(file)->rdstate; + } + } + bend = fbend(file); + + while (uds->bindex <= bend) { + lower_file = unionfs_lower_file_idx(file, uds->bindex); + if (!lower_file) { + uds->bindex++; + uds->dirpos = 0; + continue; + } + + /* prepare callback buffer */ + buf.filldir_called = 0; + buf.filldir_error = 0; + buf.entries_written = 0; + buf.dirent = dirent; + buf.filldir = filldir; + buf.rdstate = uds; + buf.sb = inode->i_sb; + + /* Read starting from where we last left off. */ + offset = vfs_llseek(lower_file, uds->dirpos, SEEK_SET); + if (offset < 0) { + err = offset; + goto out; + } + err = vfs_readdir(lower_file, unionfs_filldir, &buf); + + /* Save the position for when we continue. */ + offset = vfs_llseek(lower_file, 0, SEEK_CUR); + if (offset < 0) { + err = offset; + goto out; + } + uds->dirpos = offset; + + /* Copy the atime. */ + fsstack_copy_attr_atime(inode, + lower_file->f_path.dentry->d_inode); + + if (err < 0) + goto out; + + if (buf.filldir_error) + break; + + if (!buf.entries_written) { + uds->bindex++; + uds->dirpos = 0; + } + } + + if (!buf.filldir_error && uds->bindex >= bend) { + /* Save the number of hash entries for next time. */ + UNIONFS_I(inode)->hashsize = uds->hashentries; + free_rdstate(uds); + UNIONFS_F(file)->rdstate = NULL; + file->f_pos = DIREOF; + } else { + file->f_pos = rdstate2offset(uds); + } + +out: + if (!err) + unionfs_check_file(file); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +/* + * This is not meant to be a generic repositioning function. If you do + * things that aren't supported, then we return EINVAL. + * + * What is allowed: + * (1) seeking to the same position that you are currently at + * This really has no effect, but returns where you are. + * (2) seeking to the beginning of the file + * This throws out all state, and lets you begin again. + */ +static loff_t unionfs_dir_llseek(struct file *file, loff_t offset, int origin) +{ + struct unionfs_dir_state *rdstate; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + loff_t err; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + err = unionfs_file_revalidate(file, parent, false); + if (unlikely(err)) + goto out; + + rdstate = UNIONFS_F(file)->rdstate; + + /* + * we let users seek to their current position, but not anywhere + * else. + */ + if (!offset) { + switch (origin) { + case SEEK_SET: + if (rdstate) { + free_rdstate(rdstate); + UNIONFS_F(file)->rdstate = NULL; + } + init_rdstate(file); + err = 0; + break; + case SEEK_CUR: + err = file->f_pos; + break; + case SEEK_END: + /* Unsupported, because we would break everything. */ + err = -EINVAL; + break; + } + } else { + switch (origin) { + case SEEK_SET: + if (rdstate) { + if (offset == rdstate2offset(rdstate)) + err = offset; + else if (file->f_pos == DIREOF) + err = DIREOF; + else + err = -EINVAL; + } else { + struct inode *inode; + inode = dentry->d_inode; + rdstate = find_rdstate(inode, offset); + if (rdstate) { + UNIONFS_F(file)->rdstate = rdstate; + err = rdstate->offset; + } else { + err = -EINVAL; + } + } + break; + case SEEK_CUR: + case SEEK_END: + /* Unsupported, because we would break everything. */ + err = -EINVAL; + break; + } + } + +out: + if (!err) + unionfs_check_file(file); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +/* + * Trimmed directory options, we shouldn't pass everything down since + * we don't want to operate on partial directories. + */ +struct file_operations unionfs_dir_fops = { + .llseek = unionfs_dir_llseek, + .read = generic_read_dir, + .readdir = unionfs_readdir, + .unlocked_ioctl = unionfs_ioctl, + .open = unionfs_open, + .release = unionfs_file_release, + .flush = unionfs_flush, + .fsync = unionfs_fsync, + .fasync = unionfs_fasync, +}; diff --git a/fs/unionfs/dirhelper.c b/fs/unionfs/dirhelper.c new file mode 100644 index 0000000..033343b --- /dev/null +++ b/fs/unionfs/dirhelper.c @@ -0,0 +1,158 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +#define RD_NONE 0 +#define RD_CHECK_EMPTY 1 +/* The callback structure for check_empty. */ +struct unionfs_rdutil_callback { + int err; + int filldir_called; + struct unionfs_dir_state *rdstate; + int mode; +}; + +/* This filldir function makes sure only whiteouts exist within a directory. */ +static int readdir_util_callback(void *dirent, const char *oname, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + int err = 0; + struct unionfs_rdutil_callback *buf = dirent; + int is_whiteout; + struct filldir_node *found; + char *name = (char *) oname; + + buf->filldir_called = 1; + + if (name[0] == '.' && (namelen == 1 || + (name[1] == '.' && namelen == 2))) + goto out; + + is_whiteout = is_whiteout_name(&name, &namelen); + + found = find_filldir_node(buf->rdstate, name, namelen, is_whiteout); + /* If it was found in the table there was a previous whiteout. */ + if (found) + goto out; + + /* + * if it wasn't found and isn't a whiteout, the directory isn't + * empty. + */ + err = -ENOTEMPTY; + if ((buf->mode == RD_CHECK_EMPTY) && !is_whiteout) + goto out; + + err = add_filldir_node(buf->rdstate, name, namelen, + buf->rdstate->bindex, is_whiteout); + +out: + buf->err = err; + return err; +} + +/* Is a directory logically empty? */ +int check_empty(struct dentry *dentry, struct dentry *parent, + struct unionfs_dir_state **namelist) +{ + int err = 0; + struct dentry *lower_dentry = NULL; + struct vfsmount *mnt; + struct super_block *sb; + struct file *lower_file; + struct unionfs_rdutil_callback *buf = NULL; + int bindex, bstart, bend, bopaque; + + sb = dentry->d_sb; + + + BUG_ON(!S_ISDIR(dentry->d_inode->i_mode)); + + err = unionfs_partial_lookup(dentry, parent); + if (err) + goto out; + + bstart = dbstart(dentry); + bend = dbend(dentry); + bopaque = dbopaque(dentry); + if (0 <= bopaque && bopaque < bend) + bend = bopaque; + + buf = kmalloc(sizeof(struct unionfs_rdutil_callback), GFP_KERNEL); + if (unlikely(!buf)) { + err = -ENOMEM; + goto out; + } + buf->err = 0; + buf->mode = RD_CHECK_EMPTY; + buf->rdstate = alloc_rdstate(dentry->d_inode, bstart); + if (unlikely(!buf->rdstate)) { + err = -ENOMEM; + goto out; + } + + /* Process the lower directories with rdutil_callback as a filldir. */ + for (bindex = bstart; bindex <= bend; bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (!lower_dentry) + continue; + if (!lower_dentry->d_inode) + continue; + if (!S_ISDIR(lower_dentry->d_inode->i_mode)) + continue; + + dget(lower_dentry); + mnt = unionfs_mntget(dentry, bindex); + branchget(sb, bindex); + lower_file = dentry_open(lower_dentry, mnt, O_RDONLY, current_cred()); + if (IS_ERR(lower_file)) { + err = PTR_ERR(lower_file); + branchput(sb, bindex); + goto out; + } + + do { + buf->filldir_called = 0; + buf->rdstate->bindex = bindex; + err = vfs_readdir(lower_file, + readdir_util_callback, buf); + if (buf->err) + err = buf->err; + } while ((err >= 0) && buf->filldir_called); + + /* fput calls dput for lower_dentry */ + fput(lower_file); + branchput(sb, bindex); + + if (err < 0) + goto out; + } + +out: + if (buf) { + if (namelist && !err) + *namelist = buf->rdstate; + else if (buf->rdstate) + free_rdstate(buf->rdstate); + kfree(buf); + } + + + return err; +} diff --git a/fs/unionfs/fanout.h b/fs/unionfs/fanout.h new file mode 100644 index 0000000..5b77eac --- /dev/null +++ b/fs/unionfs/fanout.h @@ -0,0 +1,407 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _FANOUT_H_ +#define _FANOUT_H_ + +/* + * Inode to private data + * + * Since we use containers and the struct inode is _inside_ the + * unionfs_inode_info structure, UNIONFS_I will always (given a non-NULL + * inode pointer), return a valid non-NULL pointer. + */ +static inline struct unionfs_inode_info *UNIONFS_I(const struct inode *inode) +{ + return container_of(inode, struct unionfs_inode_info, vfs_inode); +} + +#define ibstart(ino) (UNIONFS_I(ino)->bstart) +#define ibend(ino) (UNIONFS_I(ino)->bend) + +/* Dentry to private data */ +#define UNIONFS_D(dent) ((struct unionfs_dentry_info *)(dent)->d_fsdata) +#define dbstart(dent) (UNIONFS_D(dent)->bstart) +#define dbend(dent) (UNIONFS_D(dent)->bend) +#define dbopaque(dent) (UNIONFS_D(dent)->bopaque) + +/* Superblock to private data */ +#define UNIONFS_SB(super) ((struct unionfs_sb_info *)(super)->s_fs_info) +#define sbstart(sb) 0 +#define sbend(sb) (UNIONFS_SB(sb)->bend) +#define sbmax(sb) (UNIONFS_SB(sb)->bend + 1) +#define sbhbid(sb) (UNIONFS_SB(sb)->high_branch_id) + +/* File to private Data */ +#define UNIONFS_F(file) ((struct unionfs_file_info *)((file)->private_data)) +#define fbstart(file) (UNIONFS_F(file)->bstart) +#define fbend(file) (UNIONFS_F(file)->bend) + +/* macros to manipulate branch IDs in stored in our superblock */ +static inline int branch_id(struct super_block *sb, int index) +{ + BUG_ON(!sb || index < 0); + return UNIONFS_SB(sb)->data[index].branch_id; +} + +static inline void set_branch_id(struct super_block *sb, int index, int val) +{ + BUG_ON(!sb || index < 0); + UNIONFS_SB(sb)->data[index].branch_id = val; +} + +static inline void new_branch_id(struct super_block *sb, int index) +{ + BUG_ON(!sb || index < 0); + set_branch_id(sb, index, ++UNIONFS_SB(sb)->high_branch_id); +} + +/* + * Find new index of matching branch with an existing superblock of a known + * (possibly old) id. This is needed because branches could have been + * added/deleted causing the branches of any open files to shift. + * + * @sb: the new superblock which may have new/different branch IDs + * @id: the old/existing id we're looking for + * Returns index of newly found branch (0 or greater), -1 otherwise. + */ +static inline int branch_id_to_idx(struct super_block *sb, int id) +{ + int i; + for (i = 0; i < sbmax(sb); i++) { + if (branch_id(sb, i) == id) + return i; + } + /* in the non-ODF code, this should really never happen */ + printk(KERN_WARNING "unionfs: cannot find branch with id %d\n", id); + return -1; +} + +/* File to lower file. */ +static inline struct file *unionfs_lower_file(const struct file *f) +{ + BUG_ON(!f); + return UNIONFS_F(f)->lower_files[fbstart(f)]; +} + +static inline struct file *unionfs_lower_file_idx(const struct file *f, + int index) +{ + BUG_ON(!f || index < 0); + return UNIONFS_F(f)->lower_files[index]; +} + +static inline void unionfs_set_lower_file_idx(struct file *f, int index, + struct file *val) +{ + BUG_ON(!f || index < 0); + UNIONFS_F(f)->lower_files[index] = val; + /* save branch ID (may be redundant?) */ + UNIONFS_F(f)->saved_branch_ids[index] = + branch_id((f)->f_path.dentry->d_sb, index); +} + +static inline void unionfs_set_lower_file(struct file *f, struct file *val) +{ + BUG_ON(!f); + unionfs_set_lower_file_idx((f), fbstart(f), (val)); +} + +/* Inode to lower inode. */ +static inline struct inode *unionfs_lower_inode(const struct inode *i) +{ + BUG_ON(!i); + return UNIONFS_I(i)->lower_inodes[ibstart(i)]; +} + +static inline struct inode *unionfs_lower_inode_idx(const struct inode *i, + int index) +{ + BUG_ON(!i || index < 0); + return UNIONFS_I(i)->lower_inodes[index]; +} + +static inline void unionfs_set_lower_inode_idx(struct inode *i, int index, + struct inode *val) +{ + BUG_ON(!i || index < 0); + UNIONFS_I(i)->lower_inodes[index] = val; +} + +static inline void unionfs_set_lower_inode(struct inode *i, struct inode *val) +{ + BUG_ON(!i); + UNIONFS_I(i)->lower_inodes[ibstart(i)] = val; +} + +/* Superblock to lower superblock. */ +static inline struct super_block *unionfs_lower_super( + const struct super_block *sb) +{ + BUG_ON(!sb); + return UNIONFS_SB(sb)->data[sbstart(sb)].sb; +} + +static inline struct super_block *unionfs_lower_super_idx( + const struct super_block *sb, + int index) +{ + BUG_ON(!sb || index < 0); + return UNIONFS_SB(sb)->data[index].sb; +} + +static inline void unionfs_set_lower_super_idx(struct super_block *sb, + int index, + struct super_block *val) +{ + BUG_ON(!sb || index < 0); + UNIONFS_SB(sb)->data[index].sb = val; +} + +static inline void unionfs_set_lower_super(struct super_block *sb, + struct super_block *val) +{ + BUG_ON(!sb); + UNIONFS_SB(sb)->data[sbstart(sb)].sb = val; +} + +/* Branch count macros. */ +static inline int branch_count(const struct super_block *sb, int index) +{ + BUG_ON(!sb || index < 0); + return atomic_read(&UNIONFS_SB(sb)->data[index].open_files); +} + +static inline void set_branch_count(struct super_block *sb, int index, int val) +{ + BUG_ON(!sb || index < 0); + atomic_set(&UNIONFS_SB(sb)->data[index].open_files, val); +} + +static inline void branchget(struct super_block *sb, int index) +{ + BUG_ON(!sb || index < 0); + atomic_inc(&UNIONFS_SB(sb)->data[index].open_files); +} + +static inline void branchput(struct super_block *sb, int index) +{ + BUG_ON(!sb || index < 0); + atomic_dec(&UNIONFS_SB(sb)->data[index].open_files); +} + +/* Dentry macros */ +static inline void unionfs_set_lower_dentry_idx(struct dentry *dent, int index, + struct dentry *val) +{ + BUG_ON(!dent || index < 0); + UNIONFS_D(dent)->lower_paths[index].dentry = val; +} + +static inline struct dentry *unionfs_lower_dentry_idx( + const struct dentry *dent, + int index) +{ + BUG_ON(!dent || index < 0); + return UNIONFS_D(dent)->lower_paths[index].dentry; +} + +static inline struct dentry *unionfs_lower_dentry(const struct dentry *dent) +{ + BUG_ON(!dent); + return unionfs_lower_dentry_idx(dent, dbstart(dent)); +} + +static inline void unionfs_set_lower_mnt_idx(struct dentry *dent, int index, + struct vfsmount *mnt) +{ + BUG_ON(!dent || index < 0); + UNIONFS_D(dent)->lower_paths[index].mnt = mnt; +} + +static inline struct vfsmount *unionfs_lower_mnt_idx( + const struct dentry *dent, + int index) +{ + BUG_ON(!dent || index < 0); + return UNIONFS_D(dent)->lower_paths[index].mnt; +} + +static inline struct vfsmount *unionfs_lower_mnt(const struct dentry *dent) +{ + BUG_ON(!dent); + return unionfs_lower_mnt_idx(dent, dbstart(dent)); +} + +/* Macros for locking a dentry. */ +enum unionfs_dentry_lock_class { + UNIONFS_DMUTEX_NORMAL, + UNIONFS_DMUTEX_ROOT, + UNIONFS_DMUTEX_PARENT, + UNIONFS_DMUTEX_CHILD, + UNIONFS_DMUTEX_WHITEOUT, + UNIONFS_DMUTEX_REVAL_PARENT, /* for file/dentry revalidate */ + UNIONFS_DMUTEX_REVAL_CHILD, /* for file/dentry revalidate */ +}; + +static inline void unionfs_lock_dentry(struct dentry *d, + unsigned int subclass) +{ + BUG_ON(!d); + mutex_lock_nested(&UNIONFS_D(d)->lock, subclass); +} + +static inline void unionfs_unlock_dentry(struct dentry *d) +{ + BUG_ON(!d); + mutex_unlock(&UNIONFS_D(d)->lock); +} + +static inline struct dentry *unionfs_lock_parent(struct dentry *d, + unsigned int subclass) +{ + struct dentry *p; + + BUG_ON(!d); + p = dget_parent(d); + if (p != d) + mutex_lock_nested(&UNIONFS_D(p)->lock, subclass); + return p; +} + +static inline void unionfs_unlock_parent(struct dentry *d, struct dentry *p) +{ + BUG_ON(!d); + BUG_ON(!p); + if (p != d) { + BUG_ON(!mutex_is_locked(&UNIONFS_D(p)->lock)); + mutex_unlock(&UNIONFS_D(p)->lock); + } + dput(p); +} + +static inline void verify_locked(struct dentry *d) +{ + BUG_ON(!d); + BUG_ON(!mutex_is_locked(&UNIONFS_D(d)->lock)); +} + +/* macros to put lower objects */ + +/* + * iput lower inodes of an unionfs dentry, from bstart to bend. If + * @free_lower is true, then also kfree the memory used to hold the lower + * object pointers. + */ +static inline void iput_lowers(struct inode *inode, + int bstart, int bend, bool free_lower) +{ + struct inode *lower_inode; + int bindex; + + BUG_ON(!inode); + BUG_ON(!UNIONFS_I(inode)); + BUG_ON(bstart < 0); + + for (bindex = bstart; bindex <= bend; bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (lower_inode) { + unionfs_set_lower_inode_idx(inode, bindex, NULL); + /* see Documentation/filesystems/unionfs/issues.txt */ + lockdep_off(); + iput(lower_inode); + lockdep_on(); + } + } + + if (free_lower) { + kfree(UNIONFS_I(inode)->lower_inodes); + UNIONFS_I(inode)->lower_inodes = NULL; + } +} + +/* iput all lower inodes, and reset start/end branch indices to -1 */ +static inline void iput_lowers_all(struct inode *inode, bool free_lower) +{ + int bstart, bend; + + BUG_ON(!inode); + BUG_ON(!UNIONFS_I(inode)); + bstart = ibstart(inode); + bend = ibend(inode); + BUG_ON(bstart < 0); + + iput_lowers(inode, bstart, bend, free_lower); + ibstart(inode) = ibend(inode) = -1; +} + +/* + * dput/mntput all lower dentries and vfsmounts of an unionfs dentry, from + * bstart to bend. If @free_lower is true, then also kfree the memory used + * to hold the lower object pointers. + * + * XXX: implement using path_put VFS macros + */ +static inline void path_put_lowers(struct dentry *dentry, + int bstart, int bend, bool free_lower) +{ + struct dentry *lower_dentry; + struct vfsmount *lower_mnt; + int bindex; + + BUG_ON(!dentry); + BUG_ON(!UNIONFS_D(dentry)); + BUG_ON(bstart < 0); + + for (bindex = bstart; bindex <= bend; bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (lower_dentry) { + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); + dput(lower_dentry); + } + lower_mnt = unionfs_lower_mnt_idx(dentry, bindex); + if (lower_mnt) { + unionfs_set_lower_mnt_idx(dentry, bindex, NULL); + mntput(lower_mnt); + } + } + + if (free_lower) { + kfree(UNIONFS_D(dentry)->lower_paths); + UNIONFS_D(dentry)->lower_paths = NULL; + } +} + +/* + * dput/mntput all lower dentries and vfsmounts, and reset start/end branch + * indices to -1. + */ +static inline void path_put_lowers_all(struct dentry *dentry, bool free_lower) +{ + int bstart, bend; + + BUG_ON(!dentry); + BUG_ON(!UNIONFS_D(dentry)); + bstart = dbstart(dentry); + bend = dbend(dentry); + BUG_ON(bstart < 0); + + path_put_lowers(dentry, bstart, bend, free_lower); + dbstart(dentry) = dbend(dentry) = -1; +} + +#endif /* not _FANOUT_H */ diff --git a/fs/unionfs/file.c b/fs/unionfs/file.c new file mode 100644 index 0000000..1c694c3 --- /dev/null +++ b/fs/unionfs/file.c @@ -0,0 +1,382 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +static ssize_t unionfs_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + int err; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + err = unionfs_file_revalidate(file, parent, false); + if (unlikely(err)) + goto out; + + lower_file = unionfs_lower_file(file); + err = vfs_read(lower_file, buf, count, ppos); + /* update our inode atime upon a successful lower read */ + if (err >= 0) { + fsstack_copy_attr_atime(dentry->d_inode, + lower_file->f_path.dentry->d_inode); + unionfs_check_file(file); + } + +out: + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +static ssize_t unionfs_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + int err = 0; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + err = unionfs_file_revalidate(file, parent, true); + if (unlikely(err)) + goto out; + + lower_file = unionfs_lower_file(file); + err = vfs_write(lower_file, buf, count, ppos); + /* update our inode times+sizes upon a successful lower write */ + if (err >= 0) { + fsstack_copy_inode_size(dentry->d_inode, + lower_file->f_path.dentry->d_inode); + fsstack_copy_attr_times(dentry->d_inode, + lower_file->f_path.dentry->d_inode); + UNIONFS_F(file)->wrote_to_file = true; /* for delayed copyup */ + unionfs_check_file(file); + } + +out: + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +static int unionfs_file_readdir(struct file *file, void *dirent, + filldir_t filldir) +{ + return -ENOTDIR; +} + +static int unionfs_mmap(struct file *file, struct vm_area_struct *vma) +{ + int err = 0; + bool willwrite; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + const struct vm_operations_struct *saved_vm_ops = NULL; + + /* + * Since mm/memory.c:might_fault() (under PROVE_LOCKING) was + * modified in 2.6.29-rc1 to call might_lock_read on mmap_sem, this + * has been causing false positives in file system stacking layers. + * In particular, our ->mmap is called after sys_mmap2 already holds + * mmap_sem, then we lock our own mutexes; but earlier, it's + * possible for lockdep to have locked our mutexes first, and then + * we call a lower ->readdir which could call might_fault. The + * different ordering of the locks is what lockdep complains about + * -- unnecessarily. Therefore, we have no choice but to tell + * lockdep to temporarily turn off lockdep here. Note: the comments + * inside might_sleep also suggest that it would have been + * nicer to only annotate paths that needs that might_lock_read. + */ + lockdep_off(); + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + /* This might be deferred to mmap's writepage */ + willwrite = ((vma->vm_flags | VM_SHARED | VM_WRITE) == vma->vm_flags); + err = unionfs_file_revalidate(file, parent, willwrite); + if (unlikely(err)) + goto out; + unionfs_check_file(file); + + /* + * File systems which do not implement ->writepage may use + * generic_file_readonly_mmap as their ->mmap op. If you call + * generic_file_readonly_mmap with VM_WRITE, you'd get an -EINVAL. + * But we cannot call the lower ->mmap op, so we can't tell that + * writeable mappings won't work. Therefore, our only choice is to + * check if the lower file system supports the ->writepage, and if + * not, return EINVAL (the same error that + * generic_file_readonly_mmap returns in that case). + */ + lower_file = unionfs_lower_file(file); + if (willwrite && !lower_file->f_mapping->a_ops->writepage) { + err = -EINVAL; + printk(KERN_ERR "unionfs: branch %d file system does not " + "support writeable mmap\n", fbstart(file)); + goto out; + } + + /* + * find and save lower vm_ops. + * + * XXX: the VFS should have a cleaner way of finding the lower vm_ops + */ + if (!UNIONFS_F(file)->lower_vm_ops) { + err = lower_file->f_op->mmap(lower_file, vma); + if (err) { + printk(KERN_ERR "unionfs: lower mmap failed %d\n", err); + goto out; + } + saved_vm_ops = vma->vm_ops; + err = do_munmap(current->mm, vma->vm_start, + vma->vm_end - vma->vm_start); + if (err) { + printk(KERN_ERR "unionfs: do_munmap failed %d\n", err); + goto out; + } + } + + file->f_mapping->a_ops = &unionfs_dummy_aops; + err = generic_file_mmap(file, vma); + file->f_mapping->a_ops = &unionfs_aops; + if (err) { + printk(KERN_ERR "unionfs: generic_file_mmap failed %d\n", err); + goto out; + } + vma->vm_ops = &unionfs_vm_ops; + if (!UNIONFS_F(file)->lower_vm_ops) + UNIONFS_F(file)->lower_vm_ops = saved_vm_ops; + +out: + if (!err) { + /* copyup could cause parent dir times to change */ + unionfs_copy_attr_times(parent->d_inode); + unionfs_check_file(file); + } + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + lockdep_on(); + return err; +} + +int unionfs_fsync(struct file *file, int datasync) +{ + int bindex, bstart, bend; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; + struct dentry *lower_dentry; + struct dentry *parent; + struct inode *lower_inode, *inode; + int err = -EINVAL; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + err = unionfs_file_revalidate(file, parent, true); + if (unlikely(err)) + goto out; + unionfs_check_file(file); + + bstart = fbstart(file); + bend = fbend(file); + if (bstart < 0 || bend < 0) + goto out; + + inode = dentry->d_inode; + if (unlikely(!inode)) { + printk(KERN_ERR + "unionfs: null lower inode in unionfs_fsync\n"); + goto out; + } + for (bindex = bstart; bindex <= bend; bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (!lower_inode || !lower_inode->i_fop->fsync) + continue; + lower_file = unionfs_lower_file_idx(file, bindex); + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + mutex_lock(&lower_inode->i_mutex); + err = lower_inode->i_fop->fsync(lower_file, datasync); + if (!err && bindex == bstart) + fsstack_copy_attr_times(inode, lower_inode); + mutex_unlock(&lower_inode->i_mutex); + if (err) + goto out; + } + +out: + if (!err) + unionfs_check_file(file); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +int unionfs_fasync(int fd, struct file *file, int flag) +{ + int bindex, bstart, bend; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + struct inode *lower_inode, *inode; + int err = 0; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + err = unionfs_file_revalidate(file, parent, true); + if (unlikely(err)) + goto out; + unionfs_check_file(file); + + bstart = fbstart(file); + bend = fbend(file); + if (bstart < 0 || bend < 0) + goto out; + + inode = dentry->d_inode; + if (unlikely(!inode)) { + printk(KERN_ERR + "unionfs: null lower inode in unionfs_fasync\n"); + goto out; + } + for (bindex = bstart; bindex <= bend; bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (!lower_inode || !lower_inode->i_fop->fasync) + continue; + lower_file = unionfs_lower_file_idx(file, bindex); + mutex_lock(&lower_inode->i_mutex); + err = lower_inode->i_fop->fasync(fd, lower_file, flag); + if (!err && bindex == bstart) + fsstack_copy_attr_times(inode, lower_inode); + mutex_unlock(&lower_inode->i_mutex); + if (err) + goto out; + } + +out: + if (!err) + unionfs_check_file(file); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +static ssize_t unionfs_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + ssize_t err; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + err = unionfs_file_revalidate(file, parent, false); + if (unlikely(err)) + goto out; + + lower_file = unionfs_lower_file(file); + err = vfs_splice_to(lower_file, ppos, pipe, len, flags); + /* update our inode atime upon a successful lower splice-read */ + if (err >= 0) { + fsstack_copy_attr_atime(dentry->d_inode, + lower_file->f_path.dentry->d_inode); + unionfs_check_file(file); + } + +out: + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +static ssize_t unionfs_splice_write(struct pipe_inode_info *pipe, + struct file *file, loff_t *ppos, + size_t len, unsigned int flags) +{ + ssize_t err = 0; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + err = unionfs_file_revalidate(file, parent, true); + if (unlikely(err)) + goto out; + + lower_file = unionfs_lower_file(file); + err = vfs_splice_from(pipe, lower_file, ppos, len, flags); + /* update our inode times+sizes upon a successful lower write */ + if (err >= 0) { + fsstack_copy_inode_size(dentry->d_inode, + lower_file->f_path.dentry->d_inode); + fsstack_copy_attr_times(dentry->d_inode, + lower_file->f_path.dentry->d_inode); + unionfs_check_file(file); + } + +out: + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +struct file_operations unionfs_main_fops = { + .llseek = generic_file_llseek, + .read = unionfs_read, + .write = unionfs_write, + .readdir = unionfs_file_readdir, + .unlocked_ioctl = unionfs_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = unionfs_ioctl, +#endif + .mmap = unionfs_mmap, + .open = unionfs_open, + .flush = unionfs_flush, + .release = unionfs_file_release, + .fsync = unionfs_fsync, + .fasync = unionfs_fasync, + .splice_read = unionfs_splice_read, + .splice_write = unionfs_splice_write, +}; diff --git a/fs/unionfs/inode.c b/fs/unionfs/inode.c new file mode 100644 index 0000000..4c36f16 --- /dev/null +++ b/fs/unionfs/inode.c @@ -0,0 +1,1061 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* + * Find a writeable branch to create new object in. Checks all writeble + * branches of the parent inode, from istart to iend order; if none are + * suitable, also tries branch 0 (which may require a copyup). + * + * Return a lower_dentry we can use to create object in, or ERR_PTR. + */ +static struct dentry *find_writeable_branch(struct inode *parent, + struct dentry *dentry) +{ + int err = -EINVAL; + int bindex, istart, iend; + struct dentry *lower_dentry = NULL; + + istart = ibstart(parent); + iend = ibend(parent); + if (istart < 0) + goto out; + +begin: + for (bindex = istart; bindex <= iend; bindex++) { + /* skip non-writeable branches */ + err = is_robranch_super(dentry->d_sb, bindex); + if (err) { + err = -EROFS; + continue; + } + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (!lower_dentry) + continue; + /* + * check for whiteouts in writeable branch, and remove them + * if necessary. + */ + err = check_unlink_whiteout(dentry, lower_dentry, bindex); + if (err > 0) /* ignore if whiteout found and removed */ + err = 0; + if (err) + continue; + /* if get here, we can write to the branch */ + break; + } + /* + * If istart wasn't already branch 0, and we got any error, then try + * branch 0 (which may require copyup) + */ + if (err && istart > 0) { + istart = iend = 0; + goto begin; + } + + /* + * If we tried even branch 0, and still got an error, abort. But if + * the error was an EROFS, then we should try to copyup. + */ + if (err && err != -EROFS) + goto out; + + /* + * If we get here, then check if copyup needed. If lower_dentry is + * NULL, create the entire dentry directory structure in branch 0. + */ + if (!lower_dentry) { + bindex = 0; + lower_dentry = create_parents(parent, dentry, + dentry->d_name.name, bindex); + if (IS_ERR(lower_dentry)) { + err = PTR_ERR(lower_dentry); + goto out; + } + } + err = 0; /* all's well */ +out: + if (err) + return ERR_PTR(err); + return lower_dentry; +} + +static int unionfs_create(struct inode *dir, struct dentry *dentry, + int mode, struct nameidata *nd_unused) +{ + int err = 0; + struct dentry *lower_dentry = NULL; + struct dentry *lower_parent_dentry = NULL; + struct dentry *parent; + int valid = 0; + struct nameidata lower_nd; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; /* same as what real_lookup does */ + goto out; + } + + lower_dentry = find_writeable_branch(dir, dentry); + if (IS_ERR(lower_dentry)) { + err = PTR_ERR(lower_dentry); + goto out; + } + + lower_parent_dentry = lock_parent(lower_dentry); + if (IS_ERR(lower_parent_dentry)) { + err = PTR_ERR(lower_parent_dentry); + goto out_unlock; + } + + err = init_lower_nd(&lower_nd, LOOKUP_CREATE); + if (unlikely(err < 0)) + goto out_unlock; + err = vfs_create(lower_parent_dentry->d_inode, lower_dentry, mode, + &lower_nd); + release_lower_nd(&lower_nd, err); + + if (!err) { + err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0)); + if (!err) { + unionfs_copy_attr_times(dir); + fsstack_copy_inode_size(dir, + lower_parent_dentry->d_inode); + /* update no. of links on parent directory */ + dir->i_nlink = unionfs_get_nlinks(dir); + } + } + +out_unlock: + unlock_dir(lower_parent_dentry); +out: + if (!err) { + unionfs_postcopyup_setmnt(dentry); + unionfs_check_inode(dir); + unionfs_check_dentry(dentry); + } + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +/* + * unionfs_lookup is the only special function which takes a dentry, yet we + * do NOT want to call __unionfs_d_revalidate_chain because by definition, + * we don't have a valid dentry here yet. + */ +static struct dentry *unionfs_lookup(struct inode *dir, + struct dentry *dentry, + struct nameidata *nd_unused) +{ + struct dentry *ret, *parent; + int err = 0; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + + /* + * As long as we lock/dget the parent, then can skip validating the + * parent now; we may have to rebuild this dentry on the next + * ->d_revalidate, however. + */ + + /* allocate dentry private data. We free it in ->d_release */ + err = new_dentry_private_data(dentry, UNIONFS_DMUTEX_CHILD); + if (unlikely(err)) { + ret = ERR_PTR(err); + goto out; + } + + ret = unionfs_lookup_full(dentry, parent, INTERPOSE_LOOKUP); + + if (!IS_ERR(ret)) { + if (ret) + dentry = ret; + /* lookup_full can return multiple positive dentries */ + if (dentry->d_inode && !S_ISDIR(dentry->d_inode->i_mode)) { + BUG_ON(dbstart(dentry) < 0); + unionfs_postcopyup_release(dentry); + } + unionfs_copy_attr_times(dentry->d_inode); + } + + unionfs_check_inode(dir); + if (!IS_ERR(ret)) + unionfs_check_dentry(dentry); + unionfs_check_dentry(parent); + unionfs_unlock_dentry(dentry); /* locked in new_dentry_private data */ + +out: + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + + return ret; +} + +static int unionfs_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *new_dentry) +{ + int err = 0; + struct dentry *lower_old_dentry = NULL; + struct dentry *lower_new_dentry = NULL; + struct dentry *lower_dir_dentry = NULL; + struct dentry *old_parent, *new_parent; + char *name = NULL; + bool valid; + + unionfs_read_lock(old_dentry->d_sb, UNIONFS_SMUTEX_CHILD); + old_parent = dget_parent(old_dentry); + new_parent = dget_parent(new_dentry); + unionfs_double_lock_parents(old_parent, new_parent); + unionfs_double_lock_dentry(old_dentry, new_dentry); + + valid = __unionfs_d_revalidate(old_dentry, old_parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out; + } + if (new_dentry->d_inode) { + valid = __unionfs_d_revalidate(new_dentry, new_parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out; + } + } + + lower_new_dentry = unionfs_lower_dentry(new_dentry); + + /* check for a whiteout in new dentry branch, and delete it */ + err = check_unlink_whiteout(new_dentry, lower_new_dentry, + dbstart(new_dentry)); + if (err > 0) { /* whiteout found and removed successfully */ + lower_dir_dentry = dget_parent(lower_new_dentry); + fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode); + dput(lower_dir_dentry); + dir->i_nlink = unionfs_get_nlinks(dir); + err = 0; + } + if (err) + goto out; + + /* check if parent hierachy is needed, then link in same branch */ + if (dbstart(old_dentry) != dbstart(new_dentry)) { + lower_new_dentry = create_parents(dir, new_dentry, + new_dentry->d_name.name, + dbstart(old_dentry)); + err = PTR_ERR(lower_new_dentry); + if (IS_COPYUP_ERR(err)) + goto docopyup; + if (!lower_new_dentry || IS_ERR(lower_new_dentry)) + goto out; + } + lower_new_dentry = unionfs_lower_dentry(new_dentry); + lower_old_dentry = unionfs_lower_dentry(old_dentry); + + BUG_ON(dbstart(old_dentry) != dbstart(new_dentry)); + lower_dir_dentry = lock_parent(lower_new_dentry); + err = is_robranch(old_dentry); + if (!err) { + /* see Documentation/filesystems/unionfs/issues.txt */ + lockdep_off(); + err = vfs_link(lower_old_dentry, lower_dir_dentry->d_inode, + lower_new_dentry); + lockdep_on(); + } + unlock_dir(lower_dir_dentry); + +docopyup: + if (IS_COPYUP_ERR(err)) { + int old_bstart = dbstart(old_dentry); + int bindex; + + for (bindex = old_bstart - 1; bindex >= 0; bindex--) { + err = copyup_dentry(old_parent->d_inode, + old_dentry, old_bstart, + bindex, old_dentry->d_name.name, + old_dentry->d_name.len, NULL, + i_size_read(old_dentry->d_inode)); + if (err) + continue; + lower_new_dentry = + create_parents(dir, new_dentry, + new_dentry->d_name.name, + bindex); + lower_old_dentry = unionfs_lower_dentry(old_dentry); + lower_dir_dentry = lock_parent(lower_new_dentry); + /* see Documentation/filesystems/unionfs/issues.txt */ + lockdep_off(); + /* do vfs_link */ + err = vfs_link(lower_old_dentry, + lower_dir_dentry->d_inode, + lower_new_dentry); + lockdep_on(); + unlock_dir(lower_dir_dentry); + goto check_link; + } + goto out; + } + +check_link: + if (err || !lower_new_dentry->d_inode) + goto out; + + /* Its a hard link, so use the same inode */ + new_dentry->d_inode = igrab(old_dentry->d_inode); + d_add(new_dentry, new_dentry->d_inode); + unionfs_copy_attr_all(dir, lower_new_dentry->d_parent->d_inode); + fsstack_copy_inode_size(dir, lower_new_dentry->d_parent->d_inode); + + /* propagate number of hard-links */ + old_dentry->d_inode->i_nlink = unionfs_get_nlinks(old_dentry->d_inode); + /* new dentry's ctime may have changed due to hard-link counts */ + unionfs_copy_attr_times(new_dentry->d_inode); + +out: + if (!new_dentry->d_inode) + d_drop(new_dentry); + + kfree(name); + if (!err) + unionfs_postcopyup_setmnt(new_dentry); + + unionfs_check_inode(dir); + unionfs_check_dentry(new_dentry); + unionfs_check_dentry(old_dentry); + + unionfs_double_unlock_dentry(old_dentry, new_dentry); + unionfs_double_unlock_parents(old_parent, new_parent); + dput(new_parent); + dput(old_parent); + unionfs_read_unlock(old_dentry->d_sb); + + return err; +} + +static int unionfs_symlink(struct inode *dir, struct dentry *dentry, + const char *symname) +{ + int err = 0; + struct dentry *lower_dentry = NULL; + struct dentry *wh_dentry = NULL; + struct dentry *lower_parent_dentry = NULL; + struct dentry *parent; + char *name = NULL; + int valid = 0; + umode_t mode; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out; + } + + /* + * It's only a bug if this dentry was not negative and couldn't be + * revalidated (shouldn't happen). + */ + BUG_ON(!valid && dentry->d_inode); + + lower_dentry = find_writeable_branch(dir, dentry); + if (IS_ERR(lower_dentry)) { + err = PTR_ERR(lower_dentry); + goto out; + } + + lower_parent_dentry = lock_parent(lower_dentry); + if (IS_ERR(lower_parent_dentry)) { + err = PTR_ERR(lower_parent_dentry); + goto out_unlock; + } + + mode = S_IALLUGO; + err = vfs_symlink(lower_parent_dentry->d_inode, lower_dentry, symname); + if (!err) { + err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0)); + if (!err) { + unionfs_copy_attr_times(dir); + fsstack_copy_inode_size(dir, + lower_parent_dentry->d_inode); + /* update no. of links on parent directory */ + dir->i_nlink = unionfs_get_nlinks(dir); + } + } + +out_unlock: + unlock_dir(lower_parent_dentry); +out: + dput(wh_dentry); + kfree(name); + + if (!err) { + unionfs_postcopyup_setmnt(dentry); + unionfs_check_inode(dir); + unionfs_check_dentry(dentry); + } + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +static int unionfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) +{ + int err = 0; + struct dentry *lower_dentry = NULL; + struct dentry *lower_parent_dentry = NULL; + struct dentry *parent; + int bindex = 0, bstart; + char *name = NULL; + int valid; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; /* same as what real_lookup does */ + goto out; + } + + bstart = dbstart(dentry); + + lower_dentry = unionfs_lower_dentry(dentry); + + /* check for a whiteout in new dentry branch, and delete it */ + err = check_unlink_whiteout(dentry, lower_dentry, bstart); + if (err > 0) /* whiteout found and removed successfully */ + err = 0; + if (err) { + /* exit if the error returned was NOT -EROFS */ + if (!IS_COPYUP_ERR(err)) + goto out; + bstart--; + } + + /* check if copyup's needed, and mkdir */ + for (bindex = bstart; bindex >= 0; bindex--) { + int i; + int bend = dbend(dentry); + + if (is_robranch_super(dentry->d_sb, bindex)) + continue; + + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (!lower_dentry) { + lower_dentry = create_parents(dir, dentry, + dentry->d_name.name, + bindex); + if (!lower_dentry || IS_ERR(lower_dentry)) { + printk(KERN_ERR "unionfs: lower dentry " + " NULL for bindex = %d\n", bindex); + continue; + } + } + + lower_parent_dentry = lock_parent(lower_dentry); + + if (IS_ERR(lower_parent_dentry)) { + err = PTR_ERR(lower_parent_dentry); + goto out; + } + + err = vfs_mkdir(lower_parent_dentry->d_inode, lower_dentry, + mode); + + unlock_dir(lower_parent_dentry); + + /* did the mkdir succeed? */ + if (err) + break; + + for (i = bindex + 1; i <= bend; i++) { + /* XXX: use path_put_lowers? */ + if (unionfs_lower_dentry_idx(dentry, i)) { + dput(unionfs_lower_dentry_idx(dentry, i)); + unionfs_set_lower_dentry_idx(dentry, i, NULL); + } + } + dbend(dentry) = bindex; + + /* + * Only INTERPOSE_LOOKUP can return a value other than 0 on + * err. + */ + err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0)); + if (!err) { + unionfs_copy_attr_times(dir); + fsstack_copy_inode_size(dir, + lower_parent_dentry->d_inode); + + /* update number of links on parent directory */ + dir->i_nlink = unionfs_get_nlinks(dir); + } + + err = make_dir_opaque(dentry, dbstart(dentry)); + if (err) { + printk(KERN_ERR "unionfs: mkdir: error creating " + ".wh.__dir_opaque: %d\n", err); + goto out; + } + + /* we are done! */ + break; + } + +out: + if (!dentry->d_inode) + d_drop(dentry); + + kfree(name); + + if (!err) { + unionfs_copy_attr_times(dentry->d_inode); + unionfs_postcopyup_setmnt(dentry); + } + unionfs_check_inode(dir); + unionfs_check_dentry(dentry); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + + return err; +} + +static int unionfs_mknod(struct inode *dir, struct dentry *dentry, int mode, + dev_t dev) +{ + int err = 0; + struct dentry *lower_dentry = NULL; + struct dentry *wh_dentry = NULL; + struct dentry *lower_parent_dentry = NULL; + struct dentry *parent; + char *name = NULL; + int valid = 0; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out; + } + + /* + * It's only a bug if this dentry was not negative and couldn't be + * revalidated (shouldn't happen). + */ + BUG_ON(!valid && dentry->d_inode); + + lower_dentry = find_writeable_branch(dir, dentry); + if (IS_ERR(lower_dentry)) { + err = PTR_ERR(lower_dentry); + goto out; + } + + lower_parent_dentry = lock_parent(lower_dentry); + if (IS_ERR(lower_parent_dentry)) { + err = PTR_ERR(lower_parent_dentry); + goto out_unlock; + } + + err = vfs_mknod(lower_parent_dentry->d_inode, lower_dentry, mode, dev); + if (!err) { + err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0)); + if (!err) { + unionfs_copy_attr_times(dir); + fsstack_copy_inode_size(dir, + lower_parent_dentry->d_inode); + /* update no. of links on parent directory */ + dir->i_nlink = unionfs_get_nlinks(dir); + } + } + +out_unlock: + unlock_dir(lower_parent_dentry); +out: + dput(wh_dentry); + kfree(name); + + if (!err) { + unionfs_postcopyup_setmnt(dentry); + unionfs_check_inode(dir); + unionfs_check_dentry(dentry); + } + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +/* requires sb, dentry, and parent to already be locked */ +static int __unionfs_readlink(struct dentry *dentry, char __user *buf, + int bufsiz) +{ + int err; + struct dentry *lower_dentry; + + lower_dentry = unionfs_lower_dentry(dentry); + + if (!lower_dentry->d_inode->i_op || + !lower_dentry->d_inode->i_op->readlink) { + err = -EINVAL; + goto out; + } + + err = lower_dentry->d_inode->i_op->readlink(lower_dentry, + buf, bufsiz); + if (err >= 0) + fsstack_copy_attr_atime(dentry->d_inode, + lower_dentry->d_inode); + +out: + return err; +} + +static int unionfs_readlink(struct dentry *dentry, char __user *buf, + int bufsiz) +{ + int err; + struct dentry *parent; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + if (unlikely(!__unionfs_d_revalidate(dentry, parent, false))) { + err = -ESTALE; + goto out; + } + + err = __unionfs_readlink(dentry, buf, bufsiz); + +out: + unionfs_check_dentry(dentry); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + + return err; +} + +static void *unionfs_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + char *buf; + int len = PAGE_SIZE, err; + mm_segment_t old_fs; + struct dentry *parent; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + /* This is freed by the put_link method assuming a successful call. */ + buf = kmalloc(len, GFP_KERNEL); + if (unlikely(!buf)) { + err = -ENOMEM; + goto out; + } + + /* read the symlink, and then we will follow it */ + old_fs = get_fs(); + set_fs(KERNEL_DS); + err = __unionfs_readlink(dentry, buf, len); + set_fs(old_fs); + if (err < 0) { + kfree(buf); + buf = NULL; + goto out; + } + buf[err] = 0; + nd_set_link(nd, buf); + err = 0; + +out: + if (err >= 0) { + unionfs_check_nd(nd); + unionfs_check_dentry(dentry); + } + + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + + return ERR_PTR(err); +} + +/* this @nd *IS* still used */ +static void unionfs_put_link(struct dentry *dentry, struct nameidata *nd, + void *cookie) +{ + struct dentry *parent; + char *buf; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + if (unlikely(!__unionfs_d_revalidate(dentry, parent, false))) + printk(KERN_ERR + "unionfs: put_link failed to revalidate dentry\n"); + + unionfs_check_dentry(dentry); +#if 0 + /* XXX: can't run this check b/c this fxn can receive a poisoned 'nd' PTR */ + unionfs_check_nd(nd); +#endif + buf = nd_get_link(nd); + if (!IS_ERR(buf)) + kfree(buf); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); +} + +/* + * This is a variant of fs/namei.c:permission() or inode_permission() which + * skips over EROFS tests (because we perform copyup on EROFS). + */ +static int __inode_permission(struct inode *inode, int mask) +{ + int retval; + + /* nobody gets write access to an immutable file */ + if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode)) + return -EACCES; + + /* Ordinary permission routines do not understand MAY_APPEND. */ + if (inode->i_op && inode->i_op->permission) { + retval = inode->i_op->permission(inode, mask); + if (!retval) { + /* + * Exec permission on a regular file is denied if none + * of the execute bits are set. + * + * This check should be done by the ->permission() + * method. + */ + if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode) && + !(inode->i_mode & S_IXUGO)) + return -EACCES; + } + } else { + retval = generic_permission(inode, mask, NULL); + } + if (retval) + return retval; + + return security_inode_permission(inode, + mask & (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND)); +} + +/* + * Don't grab the superblock read-lock in unionfs_permission, which prevents + * a deadlock with the branch-management "add branch" code (which grabbed + * the write lock). It is safe to not grab the read lock here, because even + * with branch management taking place, there is no chance that + * unionfs_permission, or anything it calls, will use stale branch + * information. + */ +static int unionfs_permission(struct inode *inode, int mask) +{ + struct inode *lower_inode = NULL; + int err = 0; + int bindex, bstart, bend; + const int is_file = !S_ISDIR(inode->i_mode); + const int write_mask = (mask & MAY_WRITE) && !(mask & MAY_READ); + struct inode *inode_grabbed = igrab(inode); + struct dentry *dentry = d_find_alias(inode); + + if (dentry) + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + if (!UNIONFS_I(inode)->lower_inodes) { + if (is_file) /* dirs can be unlinked but chdir'ed to */ + err = -ESTALE; /* force revalidate */ + goto out; + } + bstart = ibstart(inode); + bend = ibend(inode); + if (unlikely(bstart < 0 || bend < 0)) { + /* + * With branch-management, we can get a stale inode here. + * If so, we return ESTALE back to link_path_walk, which + * would discard the dcache entry and re-lookup the + * dentry+inode. This should be equivalent to issuing + * __unionfs_d_revalidate_chain on nd.dentry here. + */ + if (is_file) /* dirs can be unlinked but chdir'ed to */ + err = -ESTALE; /* force revalidate */ + goto out; + } + + for (bindex = bstart; bindex <= bend; bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (!lower_inode) + continue; + + /* + * check the condition for D-F-D underlying files/directories, + * we don't have to check for files, if we are checking for + * directories. + */ + if (!is_file && !S_ISDIR(lower_inode->i_mode)) + continue; + + /* + * We check basic permissions, but we ignore any conditions + * such as readonly file systems or branches marked as + * readonly, because those conditions should lead to a + * copyup taking place later on. However, if user never had + * access to the file, then no copyup could ever take place. + */ + err = __inode_permission(lower_inode, mask); + if (err && err != -EACCES && err != EPERM && bindex > 0) { + umode_t mode = lower_inode->i_mode; + if ((is_robranch_super(inode->i_sb, bindex) || + __is_rdonly(lower_inode)) && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) + err = 0; + if (IS_COPYUP_ERR(err)) + err = 0; + } + + /* + * NFS HACK: NFSv2/3 return EACCES on readonly-exported, + * locally readonly-mounted file systems, instead of EROFS + * like other file systems do. So we have no choice here + * but to intercept this and ignore it for NFS branches + * marked readonly. Specifically, we avoid using NFS's own + * "broken" ->permission method, and rely on + * generic_permission() to do basic checking for us. + */ + if (err && err == -EACCES && + is_robranch_super(inode->i_sb, bindex) && + lower_inode->i_sb->s_magic == NFS_SUPER_MAGIC) + err = generic_permission(lower_inode, mask, NULL); + + /* + * The permissions are an intersection of the overall directory + * permissions, so we fail if one fails. + */ + if (err) + goto out; + + /* only the leftmost file matters. */ + if (is_file || write_mask) { + if (is_file && write_mask) { + err = get_write_access(lower_inode); + if (!err) + put_write_access(lower_inode); + } + break; + } + } + /* sync times which may have changed (asynchronously) below */ + unionfs_copy_attr_times(inode); + +out: + unionfs_check_inode(inode); + if (dentry) { + unionfs_unlock_dentry(dentry); + dput(dentry); + } + iput(inode_grabbed); + return err; +} + +static int unionfs_setattr(struct dentry *dentry, struct iattr *ia) +{ + int err = 0; + struct dentry *lower_dentry; + struct dentry *parent; + struct inode *inode; + struct inode *lower_inode; + int bstart, bend, bindex; + loff_t size; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + if (unlikely(!__unionfs_d_revalidate(dentry, parent, false))) { + err = -ESTALE; + goto out; + } + + bstart = dbstart(dentry); + bend = dbend(dentry); + inode = dentry->d_inode; + + /* + * mode change is for clearing setuid/setgid. Allow lower filesystem + * to reinterpret it in its own way. + */ + if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) + ia->ia_valid &= ~ATTR_MODE; + + lower_dentry = unionfs_lower_dentry(dentry); + if (!lower_dentry) { /* should never happen after above revalidate */ + err = -EINVAL; + goto out; + } + lower_inode = unionfs_lower_inode(inode); + + /* check if user has permission to change lower inode */ + err = inode_change_ok(lower_inode, ia); + if (err) + goto out; + + /* copyup if the file is on a read only branch */ + if (is_robranch_super(dentry->d_sb, bstart) + || __is_rdonly(lower_inode)) { + /* check if we have a branch to copy up to */ + if (bstart <= 0) { + err = -EACCES; + goto out; + } + + if (ia->ia_valid & ATTR_SIZE) + size = ia->ia_size; + else + size = i_size_read(inode); + /* copyup to next available branch */ + for (bindex = bstart - 1; bindex >= 0; bindex--) { + err = copyup_dentry(parent->d_inode, + dentry, bstart, bindex, + dentry->d_name.name, + dentry->d_name.len, + NULL, size); + if (!err) + break; + } + if (err) + goto out; + /* get updated lower_dentry/inode after copyup */ + lower_dentry = unionfs_lower_dentry(dentry); + lower_inode = unionfs_lower_inode(inode); + } + + /* + * If shrinking, first truncate upper level to cancel writing dirty + * pages beyond the new eof; and also if its' maxbytes is more + * limiting (fail with -EFBIG before making any change to the lower + * level). There is no need to vmtruncate the upper level + * afterwards in the other cases: we fsstack_copy_inode_size from + * the lower level. + */ + if (ia->ia_valid & ATTR_SIZE) { + size = i_size_read(inode); + if (ia->ia_size < size || (ia->ia_size > size && + inode->i_sb->s_maxbytes < lower_inode->i_sb->s_maxbytes)) { + err = vmtruncate(inode, ia->ia_size); + if (err) + goto out; + } + } + + /* notify the (possibly copied-up) lower inode */ + /* + * Note: we use lower_dentry->d_inode, because lower_inode may be + * unlinked (no inode->i_sb and i_ino==0. This happens if someone + * tries to open(), unlink(), then ftruncate() a file. + */ + mutex_lock(&lower_dentry->d_inode->i_mutex); + err = notify_change(lower_dentry, ia); + mutex_unlock(&lower_dentry->d_inode->i_mutex); + if (err) + goto out; + + /* get attributes from the first lower inode */ + if (ibstart(inode) >= 0) + unionfs_copy_attr_all(inode, lower_inode); + /* + * unionfs_copy_attr_all will copy the lower times to our inode if + * the lower ones are newer (useful for cache coherency). However, + * ->setattr is the only place in which we may have to copy the + * lower inode times absolutely, to support utimes(2). + */ + if (ia->ia_valid & ATTR_MTIME_SET) + inode->i_mtime = lower_inode->i_mtime; + if (ia->ia_valid & ATTR_CTIME) + inode->i_ctime = lower_inode->i_ctime; + if (ia->ia_valid & ATTR_ATIME_SET) + inode->i_atime = lower_inode->i_atime; + fsstack_copy_inode_size(inode, lower_inode); + +out: + if (!err) + unionfs_check_dentry(dentry); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + + return err; +} + +struct inode_operations unionfs_symlink_iops = { + .readlink = unionfs_readlink, + .permission = unionfs_permission, + .follow_link = unionfs_follow_link, + .setattr = unionfs_setattr, + .put_link = unionfs_put_link, +}; + +struct inode_operations unionfs_dir_iops = { + .create = unionfs_create, + .lookup = unionfs_lookup, + .link = unionfs_link, + .unlink = unionfs_unlink, + .symlink = unionfs_symlink, + .mkdir = unionfs_mkdir, + .rmdir = unionfs_rmdir, + .mknod = unionfs_mknod, + .rename = unionfs_rename, + .permission = unionfs_permission, + .setattr = unionfs_setattr, +#ifdef CONFIG_UNION_FS_XATTR + .setxattr = unionfs_setxattr, + .getxattr = unionfs_getxattr, + .removexattr = unionfs_removexattr, + .listxattr = unionfs_listxattr, +#endif /* CONFIG_UNION_FS_XATTR */ +}; + +struct inode_operations unionfs_main_iops = { + .permission = unionfs_permission, + .setattr = unionfs_setattr, +#ifdef CONFIG_UNION_FS_XATTR + .setxattr = unionfs_setxattr, + .getxattr = unionfs_getxattr, + .removexattr = unionfs_removexattr, + .listxattr = unionfs_listxattr, +#endif /* CONFIG_UNION_FS_XATTR */ +}; diff --git a/fs/unionfs/lookup.c b/fs/unionfs/lookup.c new file mode 100644 index 0000000..b63c17e --- /dev/null +++ b/fs/unionfs/lookup.c @@ -0,0 +1,569 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* + * Lookup one path component @name relative to a path pair. + * Behaves nearly the same as lookup_one_len (i.e., return negative dentry + * on ENOENT), but uses the @mnt passed, so it can cross bind mounts and + * other lower mounts properly. If @new_mnt is non-null, will fill in the + * new mnt there. Caller is responsible to dput/mntput/path_put returned + * @dentry and @new_mnt. + */ +struct dentry *__lookup_one(struct dentry *base, struct vfsmount *mnt, + const char *name, struct vfsmount **new_mnt) +{ + struct dentry *dentry = NULL; + struct nameidata lower_nd; + int err; + + /* we use flags=0 to get basic lookup */ + err = vfs_path_lookup(base, mnt, name, 0, &lower_nd); + + switch (err) { + case 0: /* no error */ + dentry = lower_nd.path.dentry; + if (new_mnt) + *new_mnt = lower_nd.path.mnt; /* rc already inc'ed */ + break; + case -ENOENT: + /* + * We don't consider ENOENT an error, and we want to return + * a negative dentry (ala lookup_one_len). As we know + * there was no inode for this name before (-ENOENT), then + * it's safe to call lookup_one_len (which doesn't take a + * vfsmount). + */ + dentry = lookup_lck_len(name, base, strlen(name)); + if (new_mnt) + *new_mnt = mntget(lower_nd.path.mnt); + break; + default: /* all other real errors */ + dentry = ERR_PTR(err); + break; + } + + return dentry; +} + +/* + * This is a utility function that fills in a unionfs dentry. + * Caller must lock this dentry with unionfs_lock_dentry. + * + * Returns: 0 (ok), or -ERRNO if an error occurred. + * XXX: get rid of _partial_lookup and make callers call _lookup_full directly + */ +int unionfs_partial_lookup(struct dentry *dentry, struct dentry *parent) +{ + struct dentry *tmp; + int err = -ENOSYS; + + tmp = unionfs_lookup_full(dentry, parent, INTERPOSE_PARTIAL); + + if (!tmp) { + err = 0; + goto out; + } + if (IS_ERR(tmp)) { + err = PTR_ERR(tmp); + goto out; + } + /* XXX: need to change the interface */ + BUG_ON(tmp != dentry); +out: + return err; +} + +/* The dentry cache is just so we have properly sized dentries. */ +static struct kmem_cache *unionfs_dentry_cachep; +int unionfs_init_dentry_cache(void) +{ + unionfs_dentry_cachep = + kmem_cache_create("unionfs_dentry", + sizeof(struct unionfs_dentry_info), + 0, SLAB_RECLAIM_ACCOUNT, NULL); + + return (unionfs_dentry_cachep ? 0 : -ENOMEM); +} + +void unionfs_destroy_dentry_cache(void) +{ + if (unionfs_dentry_cachep) + kmem_cache_destroy(unionfs_dentry_cachep); +} + +void free_dentry_private_data(struct dentry *dentry) +{ + if (!dentry || !dentry->d_fsdata) + return; + kfree(UNIONFS_D(dentry)->lower_paths); + UNIONFS_D(dentry)->lower_paths = NULL; + kmem_cache_free(unionfs_dentry_cachep, dentry->d_fsdata); + dentry->d_fsdata = NULL; +} + +static inline int __realloc_dentry_private_data(struct dentry *dentry) +{ + struct unionfs_dentry_info *info = UNIONFS_D(dentry); + void *p; + int size; + + BUG_ON(!info); + + size = sizeof(struct path) * sbmax(dentry->d_sb); + p = krealloc(info->lower_paths, size, GFP_ATOMIC); + if (unlikely(!p)) + return -ENOMEM; + + info->lower_paths = p; + + info->bstart = -1; + info->bend = -1; + info->bopaque = -1; + info->bcount = sbmax(dentry->d_sb); + atomic_set(&info->generation, + atomic_read(&UNIONFS_SB(dentry->d_sb)->generation)); + + memset(info->lower_paths, 0, size); + + return 0; +} + +/* UNIONFS_D(dentry)->lock must be locked */ +int realloc_dentry_private_data(struct dentry *dentry) +{ + if (!__realloc_dentry_private_data(dentry)) + return 0; + + kfree(UNIONFS_D(dentry)->lower_paths); + free_dentry_private_data(dentry); + return -ENOMEM; +} + +/* allocate new dentry private data */ +int new_dentry_private_data(struct dentry *dentry, int subclass) +{ + struct unionfs_dentry_info *info = UNIONFS_D(dentry); + + BUG_ON(info); + + info = kmem_cache_alloc(unionfs_dentry_cachep, GFP_ATOMIC); + if (unlikely(!info)) + return -ENOMEM; + + mutex_init(&info->lock); + mutex_lock_nested(&info->lock, subclass); + + info->lower_paths = NULL; + + dentry->d_fsdata = info; + + if (!__realloc_dentry_private_data(dentry)) + return 0; + + mutex_unlock(&info->lock); + free_dentry_private_data(dentry); + return -ENOMEM; +} + +/* + * scan through the lower dentry objects, and set bstart to reflect the + * starting branch + */ +void update_bstart(struct dentry *dentry) +{ + int bindex; + int bstart = dbstart(dentry); + int bend = dbend(dentry); + struct dentry *lower_dentry; + + for (bindex = bstart; bindex <= bend; bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (!lower_dentry) + continue; + if (lower_dentry->d_inode) { + dbstart(dentry) = bindex; + break; + } + dput(lower_dentry); + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); + } +} + + +/* + * Initialize a nameidata structure (the intent part) we can pass to a lower + * file system. Returns 0 on success or -error (only -ENOMEM possible). + * Inside that nd structure, this function may also return an allocated + * struct file (for open intents). The caller, when done with this nd, must + * kfree the intent file (using release_lower_nd). + * + * XXX: this code, and the callers of this code, should be redone using + * vfs_path_lookup() when (1) the nameidata structure is refactored into a + * separate intent-structure, and (2) open_namei() is broken into a VFS-only + * function and a method that other file systems can call. + */ +int init_lower_nd(struct nameidata *nd, unsigned int flags) +{ + int err = 0; +#ifdef ALLOC_LOWER_ND_FILE + /* + * XXX: one day we may need to have the lower return an open file + * for us. It is not needed in 2.6.23-rc1 for nfs2/nfs3, but may + * very well be needed for nfs4. + */ + struct file *file; +#endif /* ALLOC_LOWER_ND_FILE */ + + memset(nd, 0, sizeof(struct nameidata)); + if (!flags) + return err; + + switch (flags) { + case LOOKUP_CREATE: + nd->intent.open.flags |= O_CREAT; + /* fall through: shared code for create/open cases */ + case LOOKUP_OPEN: + nd->flags = flags; + nd->intent.open.flags |= (FMODE_READ | FMODE_WRITE); +#ifdef ALLOC_LOWER_ND_FILE + file = kzalloc(sizeof(struct file), GFP_KERNEL); + if (unlikely(!file)) { + err = -ENOMEM; + break; /* exit switch statement and thus return */ + } + nd->intent.open.file = file; +#endif /* ALLOC_LOWER_ND_FILE */ + break; + default: + /* + * We should never get here, for now. + * We can add new cases here later on. + */ + pr_debug("unionfs: unknown nameidata flag 0x%x\n", flags); + BUG(); + break; + } + + return err; +} + +void release_lower_nd(struct nameidata *nd, int err) +{ + if (!nd->intent.open.file) + return; + else if (!err) + release_open_intent(nd); +#ifdef ALLOC_LOWER_ND_FILE + kfree(nd->intent.open.file); +#endif /* ALLOC_LOWER_ND_FILE */ +} + +/* + * Main (and complex) driver function for Unionfs's lookup + * + * Returns: NULL (ok), ERR_PTR if an error occurred, or a non-null non-error + * PTR if d_splice returned a different dentry. + * + * If lookupmode is INTERPOSE_PARTIAL/REVAL/REVAL_NEG, the passed dentry's + * inode info must be locked. If lookupmode is INTERPOSE_LOOKUP (i.e., a + * newly looked-up dentry), then unionfs_lookup_backend will return a locked + * dentry's info, which the caller must unlock. + */ +struct dentry *unionfs_lookup_full(struct dentry *dentry, + struct dentry *parent, int lookupmode) +{ + int err = 0; + struct dentry *lower_dentry = NULL; + struct vfsmount *lower_mnt; + struct vfsmount *lower_dir_mnt; + struct dentry *wh_lower_dentry = NULL; + struct dentry *lower_dir_dentry = NULL; + struct dentry *d_interposed = NULL; + int bindex, bstart, bend, bopaque; + int opaque, num_positive = 0; + const char *name; + int namelen; + int pos_start, pos_end; + + /* + * We should already have a lock on this dentry in the case of a + * partial lookup, or a revalidation. Otherwise it is returned from + * new_dentry_private_data already locked. + */ + verify_locked(dentry); + verify_locked(parent); + + /* must initialize dentry operations */ + dentry->d_op = &unionfs_dops; + + /* We never partial lookup the root directory. */ + if (IS_ROOT(dentry)) + goto out; + + name = dentry->d_name.name; + namelen = dentry->d_name.len; + + /* No dentries should get created for possible whiteout names. */ + if (!is_validname(name)) { + err = -EPERM; + goto out_free; + } + + /* Now start the actual lookup procedure. */ + bstart = dbstart(parent); + bend = dbend(parent); + bopaque = dbopaque(parent); + BUG_ON(bstart < 0); + + /* adjust bend to bopaque if needed */ + if ((bopaque >= 0) && (bopaque < bend)) + bend = bopaque; + + /* lookup all possible dentries */ + for (bindex = bstart; bindex <= bend; bindex++) { + + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + lower_mnt = unionfs_lower_mnt_idx(dentry, bindex); + + /* skip if we already have a positive lower dentry */ + if (lower_dentry) { + if (dbstart(dentry) < 0) + dbstart(dentry) = bindex; + if (bindex > dbend(dentry)) + dbend(dentry) = bindex; + if (lower_dentry->d_inode) + num_positive++; + continue; + } + + lower_dir_dentry = + unionfs_lower_dentry_idx(parent, bindex); + /* if the lower dentry's parent does not exist, skip this */ + if (!lower_dir_dentry || !lower_dir_dentry->d_inode) + continue; + + /* also skip it if the parent isn't a directory. */ + if (!S_ISDIR(lower_dir_dentry->d_inode->i_mode)) + continue; /* XXX: should be BUG_ON */ + + /* check for whiteouts: stop lookup if found */ + wh_lower_dentry = lookup_whiteout(name, lower_dir_dentry); + if (IS_ERR(wh_lower_dentry)) { + err = PTR_ERR(wh_lower_dentry); + goto out_free; + } + if (wh_lower_dentry->d_inode) { + dbend(dentry) = dbopaque(dentry) = bindex; + if (dbstart(dentry) < 0) + dbstart(dentry) = bindex; + dput(wh_lower_dentry); + break; + } + dput(wh_lower_dentry); + + /* Now do regular lookup; lookup @name */ + lower_dir_mnt = unionfs_lower_mnt_idx(parent, bindex); + lower_mnt = NULL; /* XXX: needed? */ + + lower_dentry = __lookup_one(lower_dir_dentry, lower_dir_mnt, + name, &lower_mnt); + + if (IS_ERR(lower_dentry)) { + err = PTR_ERR(lower_dentry); + goto out_free; + } + unionfs_set_lower_dentry_idx(dentry, bindex, lower_dentry); + if (!lower_mnt) + lower_mnt = unionfs_mntget(dentry->d_sb->s_root, + bindex); + unionfs_set_lower_mnt_idx(dentry, bindex, lower_mnt); + + /* adjust dbstart/end */ + if (dbstart(dentry) < 0) + dbstart(dentry) = bindex; + if (bindex > dbend(dentry)) + dbend(dentry) = bindex; + /* + * We always store the lower dentries above, and update + * dbstart/dbend, even if the whole unionfs dentry is + * negative (i.e., no lower inodes). + */ + if (!lower_dentry->d_inode) + continue; + num_positive++; + + /* + * check if we just found an opaque directory, if so, stop + * lookups here. + */ + if (!S_ISDIR(lower_dentry->d_inode->i_mode)) + continue; + opaque = is_opaque_dir(dentry, bindex); + if (opaque < 0) { + err = opaque; + goto out_free; + } else if (opaque) { + dbend(dentry) = dbopaque(dentry) = bindex; + break; + } + dbend(dentry) = bindex; + + /* update parent directory's atime with the bindex */ + fsstack_copy_attr_atime(parent->d_inode, + lower_dir_dentry->d_inode); + } + + /* sanity checks, then decide if to process a negative dentry */ + BUG_ON(dbstart(dentry) < 0 && dbend(dentry) >= 0); + BUG_ON(dbstart(dentry) >= 0 && dbend(dentry) < 0); + + if (num_positive > 0) + goto out_positive; + + /*** handle NEGATIVE dentries ***/ + + /* + * If negative, keep only first lower negative dentry, to save on + * memory. + */ + if (dbstart(dentry) < dbend(dentry)) { + path_put_lowers(dentry, dbstart(dentry) + 1, + dbend(dentry), false); + dbend(dentry) = dbstart(dentry); + } + if (lookupmode == INTERPOSE_PARTIAL) + goto out; + if (lookupmode == INTERPOSE_LOOKUP) { + /* + * If all we found was a whiteout in the first available + * branch, then create a negative dentry for a possibly new + * file to be created. + */ + if (dbopaque(dentry) < 0) + goto out; + /* XXX: need to get mnt here */ + bindex = dbstart(dentry); + if (unionfs_lower_dentry_idx(dentry, bindex)) + goto out; + lower_dir_dentry = + unionfs_lower_dentry_idx(parent, bindex); + if (!lower_dir_dentry || !lower_dir_dentry->d_inode) + goto out; + if (!S_ISDIR(lower_dir_dentry->d_inode->i_mode)) + goto out; /* XXX: should be BUG_ON */ + /* XXX: do we need to cross bind mounts here? */ + lower_dentry = lookup_lck_len(name, lower_dir_dentry, namelen); + if (IS_ERR(lower_dentry)) { + err = PTR_ERR(lower_dentry); + goto out; + } + /* XXX: need to mntget/mntput as needed too! */ + unionfs_set_lower_dentry_idx(dentry, bindex, lower_dentry); + /* XXX: wrong mnt for crossing bind mounts! */ + lower_mnt = unionfs_mntget(dentry->d_sb->s_root, bindex); + unionfs_set_lower_mnt_idx(dentry, bindex, lower_mnt); + + goto out; + } + + /* if we're revalidating a positive dentry, don't make it negative */ + if (lookupmode != INTERPOSE_REVAL) + d_add(dentry, NULL); + + goto out; + +out_positive: + /*** handle POSITIVE dentries ***/ + + /* + * This unionfs dentry is positive (at least one lower inode + * exists), so scan entire dentry from beginning to end, and remove + * any negative lower dentries, if any. Then, update dbstart/dbend + * to reflect the start/end of positive dentries. + */ + pos_start = pos_end = -1; + for (bindex = bstart; bindex <= bend; bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, + bindex); + if (lower_dentry && lower_dentry->d_inode) { + if (pos_start < 0) + pos_start = bindex; + if (bindex > pos_end) + pos_end = bindex; + continue; + } + path_put_lowers(dentry, bindex, bindex, false); + } + if (pos_start >= 0) + dbstart(dentry) = pos_start; + if (pos_end >= 0) + dbend(dentry) = pos_end; + + /* Partial lookups need to re-interpose, or throw away older negs. */ + if (lookupmode == INTERPOSE_PARTIAL) { + if (dentry->d_inode) { + unionfs_reinterpose(dentry); + goto out; + } + + /* + * This dentry was positive, so it is as if we had a + * negative revalidation. + */ + lookupmode = INTERPOSE_REVAL_NEG; + update_bstart(dentry); + } + + /* + * Interpose can return a dentry if d_splice returned a different + * dentry. + */ + d_interposed = unionfs_interpose(dentry, dentry->d_sb, lookupmode); + if (IS_ERR(d_interposed)) + err = PTR_ERR(d_interposed); + else if (d_interposed) + dentry = d_interposed; + + if (!err) + goto out; + d_drop(dentry); + +out_free: + /* should dput/mntput all the underlying dentries on error condition */ + if (dbstart(dentry) >= 0) + path_put_lowers_all(dentry, false); + /* free lower_paths unconditionally */ + kfree(UNIONFS_D(dentry)->lower_paths); + UNIONFS_D(dentry)->lower_paths = NULL; + +out: + if (dentry && UNIONFS_D(dentry)) { + BUG_ON(dbstart(dentry) < 0 && dbend(dentry) >= 0); + BUG_ON(dbstart(dentry) >= 0 && dbend(dentry) < 0); + } + if (d_interposed && UNIONFS_D(d_interposed)) { + BUG_ON(dbstart(d_interposed) < 0 && dbend(d_interposed) >= 0); + BUG_ON(dbstart(d_interposed) >= 0 && dbend(d_interposed) < 0); + } + + if (!err && d_interposed) + return d_interposed; + return ERR_PTR(err); +} diff --git a/fs/unionfs/main.c b/fs/unionfs/main.c new file mode 100644 index 0000000..258386e --- /dev/null +++ b/fs/unionfs/main.c @@ -0,0 +1,758 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" +#include +#include + +static void unionfs_fill_inode(struct dentry *dentry, + struct inode *inode) +{ + struct inode *lower_inode; + struct dentry *lower_dentry; + int bindex, bstart, bend; + + bstart = dbstart(dentry); + bend = dbend(dentry); + + for (bindex = bstart; bindex <= bend; bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (!lower_dentry) { + unionfs_set_lower_inode_idx(inode, bindex, NULL); + continue; + } + + /* Initialize the lower inode to the new lower inode. */ + if (!lower_dentry->d_inode) + continue; + + unionfs_set_lower_inode_idx(inode, bindex, + igrab(lower_dentry->d_inode)); + } + + ibstart(inode) = dbstart(dentry); + ibend(inode) = dbend(dentry); + + /* Use attributes from the first branch. */ + lower_inode = unionfs_lower_inode(inode); + + /* Use different set of inode ops for symlinks & directories */ + if (S_ISLNK(lower_inode->i_mode)) + inode->i_op = &unionfs_symlink_iops; + else if (S_ISDIR(lower_inode->i_mode)) + inode->i_op = &unionfs_dir_iops; + + /* Use different set of file ops for directories */ + if (S_ISDIR(lower_inode->i_mode)) + inode->i_fop = &unionfs_dir_fops; + + /* properly initialize special inodes */ + if (S_ISBLK(lower_inode->i_mode) || S_ISCHR(lower_inode->i_mode) || + S_ISFIFO(lower_inode->i_mode) || S_ISSOCK(lower_inode->i_mode)) + init_special_inode(inode, lower_inode->i_mode, + lower_inode->i_rdev); + + /* all well, copy inode attributes */ + unionfs_copy_attr_all(inode, lower_inode); + fsstack_copy_inode_size(inode, lower_inode); +} + +/* + * Connect a unionfs inode dentry/inode with several lower ones. This is + * the classic stackable file system "vnode interposition" action. + * + * @sb: unionfs's super_block + */ +struct dentry *unionfs_interpose(struct dentry *dentry, struct super_block *sb, + int flag) +{ + int err = 0; + struct inode *inode; + int need_fill_inode = 1; + struct dentry *spliced = NULL; + + verify_locked(dentry); + + /* + * We allocate our new inode below by calling unionfs_iget, + * which will initialize some of the new inode's fields + */ + + /* + * On revalidate we've already got our own inode and just need + * to fix it up. + */ + if (flag == INTERPOSE_REVAL) { + inode = dentry->d_inode; + UNIONFS_I(inode)->bstart = -1; + UNIONFS_I(inode)->bend = -1; + atomic_set(&UNIONFS_I(inode)->generation, + atomic_read(&UNIONFS_SB(sb)->generation)); + + UNIONFS_I(inode)->lower_inodes = + kcalloc(sbmax(sb), sizeof(struct inode *), GFP_KERNEL); + if (unlikely(!UNIONFS_I(inode)->lower_inodes)) { + err = -ENOMEM; + goto out; + } + } else { + /* get unique inode number for unionfs */ + inode = unionfs_iget(sb, iunique(sb, UNIONFS_ROOT_INO)); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out; + } + if (atomic_read(&inode->i_count) > 1) + goto skip; + } + + need_fill_inode = 0; + unionfs_fill_inode(dentry, inode); + +skip: + /* only (our) lookup wants to do a d_add */ + switch (flag) { + case INTERPOSE_DEFAULT: + /* for operations which create new inodes */ + d_add(dentry, inode); + break; + case INTERPOSE_REVAL_NEG: + d_instantiate(dentry, inode); + break; + case INTERPOSE_LOOKUP: + spliced = d_splice_alias(inode, dentry); + if (spliced && spliced != dentry) { + /* + * d_splice can return a dentry if it was + * disconnected and had to be moved. We must ensure + * that the private data of the new dentry is + * correct and that the inode info was filled + * properly. Finally we must return this new + * dentry. + */ + spliced->d_op = &unionfs_dops; + spliced->d_fsdata = dentry->d_fsdata; + dentry->d_fsdata = NULL; + dentry = spliced; + if (need_fill_inode) { + need_fill_inode = 0; + unionfs_fill_inode(dentry, inode); + } + goto out_spliced; + } else if (!spliced) { + if (need_fill_inode) { + need_fill_inode = 0; + unionfs_fill_inode(dentry, inode); + goto out_spliced; + } + } + break; + case INTERPOSE_REVAL: + /* Do nothing. */ + break; + default: + printk(KERN_CRIT "unionfs: invalid interpose flag passed!\n"); + BUG(); + } + goto out; + +out_spliced: + if (!err) + return spliced; +out: + return ERR_PTR(err); +} + +/* like interpose above, but for an already existing dentry */ +void unionfs_reinterpose(struct dentry *dentry) +{ + struct dentry *lower_dentry; + struct inode *inode; + int bindex, bstart, bend; + + verify_locked(dentry); + + /* This is pre-allocated inode */ + inode = dentry->d_inode; + + bstart = dbstart(dentry); + bend = dbend(dentry); + for (bindex = bstart; bindex <= bend; bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (!lower_dentry) + continue; + + if (!lower_dentry->d_inode) + continue; + if (unionfs_lower_inode_idx(inode, bindex)) + continue; + unionfs_set_lower_inode_idx(inode, bindex, + igrab(lower_dentry->d_inode)); + } + ibstart(inode) = dbstart(dentry); + ibend(inode) = dbend(dentry); +} + +/* + * make sure the branch we just looked up (nd) makes sense: + * + * 1) we're not trying to stack unionfs on top of unionfs + * 2) it exists + * 3) is a directory + */ +int check_branch(struct nameidata *nd) +{ + /* XXX: remove in ODF code -- stacking unions allowed there */ + if (!strcmp(nd->path.dentry->d_sb->s_type->name, UNIONFS_NAME)) + return -EINVAL; + if (!nd->path.dentry->d_inode) + return -ENOENT; + if (!S_ISDIR(nd->path.dentry->d_inode->i_mode)) + return -ENOTDIR; + return 0; +} + +/* checks if two lower_dentries have overlapping branches */ +static int is_branch_overlap(struct dentry *dent1, struct dentry *dent2) +{ + struct dentry *dent = NULL; + + dent = dent1; + while ((dent != dent2) && (dent->d_parent != dent)) + dent = dent->d_parent; + + if (dent == dent2) + return 1; + + dent = dent2; + while ((dent != dent1) && (dent->d_parent != dent)) + dent = dent->d_parent; + + return (dent == dent1); +} + +/* + * Parse "ro" or "rw" options, but default to "rw" if no mode options was + * specified. Fill the mode bits in @perms. If encounter an unknown + * string, return -EINVAL. Otherwise return 0. + */ +int parse_branch_mode(const char *name, int *perms) +{ + if (!name || !strcmp(name, "rw")) { + *perms = MAY_READ | MAY_WRITE; + return 0; + } + if (!strcmp(name, "ro")) { + *perms = MAY_READ; + return 0; + } + return -EINVAL; +} + +/* + * parse the dirs= mount argument + * + * We don't need to lock the superblock private data's rwsem, as we get + * called only by unionfs_read_super - it is still a long time before anyone + * can even get a reference to us. + */ +static int parse_dirs_option(struct super_block *sb, struct unionfs_dentry_info + *lower_root_info, char *options) +{ + struct nameidata nd; + char *name; + int err = 0; + int branches = 1; + int bindex = 0; + int i = 0; + int j = 0; + struct dentry *dent1; + struct dentry *dent2; + + if (options[0] == '\0') { + printk(KERN_ERR "unionfs: no branches specified\n"); + err = -EINVAL; + goto out; + } + + /* + * Each colon means we have a separator, this is really just a rough + * guess, since strsep will handle empty fields for us. + */ + for (i = 0; options[i]; i++) + if (options[i] == ':') + branches++; + + /* allocate space for underlying pointers to lower dentry */ + UNIONFS_SB(sb)->data = + kcalloc(branches, sizeof(struct unionfs_data), GFP_KERNEL); + if (unlikely(!UNIONFS_SB(sb)->data)) { + err = -ENOMEM; + goto out; + } + + lower_root_info->lower_paths = + kcalloc(branches, sizeof(struct path), GFP_KERNEL); + if (unlikely(!lower_root_info->lower_paths)) { + err = -ENOMEM; + goto out; + } + + /* now parsing a string such as "b1:b2=rw:b3=ro:b4" */ + branches = 0; + while ((name = strsep(&options, ":")) != NULL) { + int perms; + char *mode = strchr(name, '='); + + if (!name) + continue; + if (!*name) { /* bad use of ':' (extra colons) */ + err = -EINVAL; + goto out; + } + + branches++; + + /* strip off '=' if any */ + if (mode) + *mode++ = '\0'; + + err = parse_branch_mode(mode, &perms); + if (err) { + printk(KERN_ERR "unionfs: invalid mode \"%s\" for " + "branch %d\n", mode, bindex); + goto out; + } + /* ensure that leftmost branch is writeable */ + if (!bindex && !(perms & MAY_WRITE)) { + printk(KERN_ERR "unionfs: leftmost branch cannot be " + "read-only (use \"-o ro\" to create a " + "read-only union)\n"); + err = -EINVAL; + goto out; + } + + err = path_lookup(name, LOOKUP_FOLLOW, &nd); + if (err) { + printk(KERN_ERR "unionfs: error accessing " + "lower directory '%s' (error %d)\n", + name, err); + goto out; + } + + err = check_branch(&nd); + if (err) { + printk(KERN_ERR "unionfs: lower directory " + "'%s' is not a valid branch\n", name); + path_put(&nd.path); + goto out; + } + + lower_root_info->lower_paths[bindex].dentry = nd.path.dentry; + lower_root_info->lower_paths[bindex].mnt = nd.path.mnt; + + set_branchperms(sb, bindex, perms); + set_branch_count(sb, bindex, 0); + new_branch_id(sb, bindex); + + if (lower_root_info->bstart < 0) + lower_root_info->bstart = bindex; + lower_root_info->bend = bindex; + bindex++; + } + + if (branches == 0) { + printk(KERN_ERR "unionfs: no branches specified\n"); + err = -EINVAL; + goto out; + } + + BUG_ON(branches != (lower_root_info->bend + 1)); + + /* + * Ensure that no overlaps exist in the branches. + * + * This test is required because the Linux kernel has no support + * currently for ensuring coherency between stackable layers and + * branches. If we were to allow overlapping branches, it would be + * possible, for example, to delete a file via one branch, which + * would not be reflected in another branch. Such incoherency could + * lead to inconsistencies and even kernel oopses. Rather than + * implement hacks to work around some of these cache-coherency + * problems, we prevent branch overlapping, for now. A complete + * solution will involve proper kernel/VFS support for cache + * coherency, at which time we could safely remove this + * branch-overlapping test. + */ + for (i = 0; i < branches; i++) { + dent1 = lower_root_info->lower_paths[i].dentry; + for (j = i + 1; j < branches; j++) { + dent2 = lower_root_info->lower_paths[j].dentry; + if (is_branch_overlap(dent1, dent2)) { + printk(KERN_ERR "unionfs: branches %d and " + "%d overlap\n", i, j); + err = -EINVAL; + goto out; + } + } + } + +out: + if (err) { + for (i = 0; i < branches; i++) + path_put(&lower_root_info->lower_paths[i]); + + kfree(lower_root_info->lower_paths); + kfree(UNIONFS_SB(sb)->data); + + /* + * MUST clear the pointers to prevent potential double free if + * the caller dies later on + */ + lower_root_info->lower_paths = NULL; + UNIONFS_SB(sb)->data = NULL; + } + return err; +} + +/* + * Parse mount options. See the manual page for usage instructions. + * + * Returns the dentry object of the lower-level (lower) directory; + * We want to mount our stackable file system on top of that lower directory. + */ +static struct unionfs_dentry_info *unionfs_parse_options( + struct super_block *sb, + char *options) +{ + struct unionfs_dentry_info *lower_root_info; + char *optname; + int err = 0; + int bindex; + int dirsfound = 0; + + /* allocate private data area */ + err = -ENOMEM; + lower_root_info = + kzalloc(sizeof(struct unionfs_dentry_info), GFP_KERNEL); + if (unlikely(!lower_root_info)) + goto out_error; + lower_root_info->bstart = -1; + lower_root_info->bend = -1; + lower_root_info->bopaque = -1; + + while ((optname = strsep(&options, ",")) != NULL) { + char *optarg; + + if (!optname || !*optname) + continue; + + optarg = strchr(optname, '='); + if (optarg) + *optarg++ = '\0'; + + /* + * All of our options take an argument now. Insert ones that + * don't, above this check. + */ + if (!optarg) { + printk(KERN_ERR "unionfs: %s requires an argument\n", + optname); + err = -EINVAL; + goto out_error; + } + + if (!strcmp("dirs", optname)) { + if (++dirsfound > 1) { + printk(KERN_ERR + "unionfs: multiple dirs specified\n"); + err = -EINVAL; + goto out_error; + } + err = parse_dirs_option(sb, lower_root_info, optarg); + if (err) + goto out_error; + continue; + } + + err = -EINVAL; + printk(KERN_ERR + "unionfs: unrecognized option '%s'\n", optname); + goto out_error; + } + if (dirsfound != 1) { + printk(KERN_ERR "unionfs: dirs option required\n"); + err = -EINVAL; + goto out_error; + } + goto out; + +out_error: + if (lower_root_info && lower_root_info->lower_paths) { + for (bindex = lower_root_info->bstart; + bindex >= 0 && bindex <= lower_root_info->bend; + bindex++) + path_put(&lower_root_info->lower_paths[bindex]); + } + + kfree(lower_root_info->lower_paths); + kfree(lower_root_info); + + kfree(UNIONFS_SB(sb)->data); + UNIONFS_SB(sb)->data = NULL; + + lower_root_info = ERR_PTR(err); +out: + return lower_root_info; +} + +/* + * our custom d_alloc_root work-alike + * + * we can't use d_alloc_root if we want to use our own interpose function + * unchanged, so we simply call our own "fake" d_alloc_root + */ +static struct dentry *unionfs_d_alloc_root(struct super_block *sb) +{ + struct dentry *ret = NULL; + + if (sb) { + static const struct qstr name = { + .name = "/", + .len = 1 + }; + + ret = d_alloc(NULL, &name); + if (likely(ret)) { + ret->d_op = &unionfs_dops; + ret->d_sb = sb; + ret->d_parent = ret; + } + } + return ret; +} + +/* + * There is no need to lock the unionfs_super_info's rwsem as there is no + * way anyone can have a reference to the superblock at this point in time. + */ +static int unionfs_read_super(struct super_block *sb, void *raw_data, + int silent) +{ + int err = 0; + struct unionfs_dentry_info *lower_root_info = NULL; + int bindex, bstart, bend; + + if (!raw_data) { + printk(KERN_ERR + "unionfs: read_super: missing data argument\n"); + err = -EINVAL; + goto out; + } + + /* Allocate superblock private data */ + sb->s_fs_info = kzalloc(sizeof(struct unionfs_sb_info), GFP_KERNEL); + if (unlikely(!UNIONFS_SB(sb))) { + printk(KERN_CRIT "unionfs: read_super: out of memory\n"); + err = -ENOMEM; + goto out; + } + + UNIONFS_SB(sb)->bend = -1; + atomic_set(&UNIONFS_SB(sb)->generation, 1); + init_rwsem(&UNIONFS_SB(sb)->rwsem); + UNIONFS_SB(sb)->high_branch_id = -1; /* -1 == invalid branch ID */ + + lower_root_info = unionfs_parse_options(sb, raw_data); + if (IS_ERR(lower_root_info)) { + printk(KERN_ERR + "unionfs: read_super: error while parsing options " + "(err = %ld)\n", PTR_ERR(lower_root_info)); + err = PTR_ERR(lower_root_info); + lower_root_info = NULL; + goto out_free; + } + if (lower_root_info->bstart == -1) { + err = -ENOENT; + goto out_free; + } + + /* set the lower superblock field of upper superblock */ + bstart = lower_root_info->bstart; + BUG_ON(bstart != 0); + sbend(sb) = bend = lower_root_info->bend; + for (bindex = bstart; bindex <= bend; bindex++) { + struct dentry *d = lower_root_info->lower_paths[bindex].dentry; + atomic_inc(&d->d_sb->s_active); + unionfs_set_lower_super_idx(sb, bindex, d->d_sb); + } + + /* max Bytes is the maximum bytes from highest priority branch */ + sb->s_maxbytes = unionfs_lower_super_idx(sb, 0)->s_maxbytes; + + /* + * Our c/m/atime granularity is 1 ns because we may stack on file + * systems whose granularity is as good. This is important for our + * time-based cache coherency. + */ + sb->s_time_gran = 1; + + sb->s_op = &unionfs_sops; + + /* See comment next to the definition of unionfs_d_alloc_root */ + sb->s_root = unionfs_d_alloc_root(sb); + if (unlikely(!sb->s_root)) { + err = -ENOMEM; + goto out_dput; + } + + /* link the upper and lower dentries */ + sb->s_root->d_fsdata = NULL; + err = new_dentry_private_data(sb->s_root, UNIONFS_DMUTEX_ROOT); + if (unlikely(err)) + goto out_freedpd; + + /* Set the lower dentries for s_root */ + for (bindex = bstart; bindex <= bend; bindex++) { + struct dentry *d; + struct vfsmount *m; + + d = lower_root_info->lower_paths[bindex].dentry; + m = lower_root_info->lower_paths[bindex].mnt; + + unionfs_set_lower_dentry_idx(sb->s_root, bindex, d); + unionfs_set_lower_mnt_idx(sb->s_root, bindex, m); + } + dbstart(sb->s_root) = bstart; + dbend(sb->s_root) = bend; + + /* Set the generation number to one, since this is for the mount. */ + atomic_set(&UNIONFS_D(sb->s_root)->generation, 1); + + /* + * Call interpose to create the upper level inode. Only + * INTERPOSE_LOOKUP can return a value other than 0 on err. + */ + err = PTR_ERR(unionfs_interpose(sb->s_root, sb, 0)); + unionfs_unlock_dentry(sb->s_root); + if (!err) + goto out; + /* else fall through */ + +out_freedpd: + if (UNIONFS_D(sb->s_root)) { + kfree(UNIONFS_D(sb->s_root)->lower_paths); + free_dentry_private_data(sb->s_root); + } + dput(sb->s_root); + +out_dput: + if (lower_root_info && !IS_ERR(lower_root_info)) { + for (bindex = lower_root_info->bstart; + bindex <= lower_root_info->bend; bindex++) { + struct dentry *d; + d = lower_root_info->lower_paths[bindex].dentry; + /* drop refs we took earlier */ + atomic_dec(&d->d_sb->s_active); + path_put(&lower_root_info->lower_paths[bindex]); + } + kfree(lower_root_info->lower_paths); + kfree(lower_root_info); + lower_root_info = NULL; + } + +out_free: + kfree(UNIONFS_SB(sb)->data); + kfree(UNIONFS_SB(sb)); + sb->s_fs_info = NULL; + +out: + if (lower_root_info && !IS_ERR(lower_root_info)) { + kfree(lower_root_info->lower_paths); + kfree(lower_root_info); + } + return err; +} + +static int unionfs_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, + void *raw_data, struct vfsmount *mnt) +{ + int err; + err = get_sb_nodev(fs_type, flags, raw_data, unionfs_read_super, mnt); + if (!err) + UNIONFS_SB(mnt->mnt_sb)->dev_name = + kstrdup(dev_name, GFP_KERNEL); + return err; +} + +static struct file_system_type unionfs_fs_type = { + .owner = THIS_MODULE, + .name = UNIONFS_NAME, + .get_sb = unionfs_get_sb, + .kill_sb = generic_shutdown_super, + .fs_flags = FS_REVAL_DOT, +}; + +static int __init init_unionfs_fs(void) +{ + int err; + + pr_info("Registering unionfs " UNIONFS_VERSION "\n"); + + err = unionfs_init_filldir_cache(); + if (unlikely(err)) + goto out; + err = unionfs_init_inode_cache(); + if (unlikely(err)) + goto out; + err = unionfs_init_dentry_cache(); + if (unlikely(err)) + goto out; + err = init_sioq(); + if (unlikely(err)) + goto out; + err = register_filesystem(&unionfs_fs_type); +out: + if (unlikely(err)) { + stop_sioq(); + unionfs_destroy_filldir_cache(); + unionfs_destroy_inode_cache(); + unionfs_destroy_dentry_cache(); + } + return err; +} + +static void __exit exit_unionfs_fs(void) +{ + stop_sioq(); + unionfs_destroy_filldir_cache(); + unionfs_destroy_inode_cache(); + unionfs_destroy_dentry_cache(); + unregister_filesystem(&unionfs_fs_type); + pr_info("Completed unionfs module unload\n"); +} + +MODULE_AUTHOR("Erez Zadok, Filesystems and Storage Lab, Stony Brook University" + " (http://www.fsl.cs.sunysb.edu)"); +MODULE_DESCRIPTION("Unionfs " UNIONFS_VERSION + " (http://unionfs.filesystems.org)"); +MODULE_LICENSE("GPL"); + +module_init(init_unionfs_fs); +module_exit(exit_unionfs_fs); diff --git a/fs/unionfs/mmap.c b/fs/unionfs/mmap.c new file mode 100644 index 0000000..1f70535 --- /dev/null +++ b/fs/unionfs/mmap.c @@ -0,0 +1,89 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2006 Shaya Potter + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + + +/* + * XXX: we need a dummy readpage handler because generic_file_mmap (which we + * use in unionfs_mmap) checks for the existence of + * mapping->a_ops->readpage, else it returns -ENOEXEC. The VFS will need to + * be fixed to allow a file system to define vm_ops->fault without any + * address_space_ops whatsoever. + * + * Otherwise, we don't want to use our readpage method at all. + */ +static int unionfs_readpage(struct file *file, struct page *page) +{ + BUG(); + return -EINVAL; +} + +static int unionfs_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + int err; + struct file *file, *lower_file; + const struct vm_operations_struct *lower_vm_ops; + struct vm_area_struct lower_vma; + + BUG_ON(!vma); + memcpy(&lower_vma, vma, sizeof(struct vm_area_struct)); + file = lower_vma.vm_file; + lower_vm_ops = UNIONFS_F(file)->lower_vm_ops; + BUG_ON(!lower_vm_ops); + + lower_file = unionfs_lower_file(file); + BUG_ON(!lower_file); + /* + * XXX: vm_ops->fault may be called in parallel. Because we have to + * resort to temporarily changing the vma->vm_file to point to the + * lower file, a concurrent invocation of unionfs_fault could see a + * different value. In this workaround, we keep a different copy of + * the vma structure in our stack, so we never expose a different + * value of the vma->vm_file called to us, even temporarily. A + * better fix would be to change the calling semantics of ->fault to + * take an explicit file pointer. + */ + lower_vma.vm_file = lower_file; + err = lower_vm_ops->fault(&lower_vma, vmf); + return err; +} + +/* + * XXX: the default address_space_ops for unionfs is empty. We cannot set + * our inode->i_mapping->a_ops to NULL because too many code paths expect + * the a_ops vector to be non-NULL. + */ +struct address_space_operations unionfs_aops = { + /* empty on purpose */ +}; + +/* + * XXX: we need a second, dummy address_space_ops vector, to be used + * temporarily during unionfs_mmap, because the latter calls + * generic_file_mmap, which checks if ->readpage exists, else returns + * -ENOEXEC. + */ +struct address_space_operations unionfs_dummy_aops = { + .readpage = unionfs_readpage, +}; + +struct vm_operations_struct unionfs_vm_ops = { + .fault = unionfs_fault, +}; diff --git a/fs/unionfs/rdstate.c b/fs/unionfs/rdstate.c new file mode 100644 index 0000000..f745fbc --- /dev/null +++ b/fs/unionfs/rdstate.c @@ -0,0 +1,285 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* This file contains the routines for maintaining readdir state. */ + +/* + * There are two structures here, rdstate which is a hash table + * of the second structure which is a filldir_node. + */ + +/* + * This is a struct kmem_cache for filldir nodes, because we allocate a lot + * of them and they shouldn't waste memory. If the node has a small name + * (as defined by the dentry structure), then we use an inline name to + * preserve kmalloc space. + */ +static struct kmem_cache *unionfs_filldir_cachep; + +int unionfs_init_filldir_cache(void) +{ + unionfs_filldir_cachep = + kmem_cache_create("unionfs_filldir", + sizeof(struct filldir_node), 0, + SLAB_RECLAIM_ACCOUNT, NULL); + + return (unionfs_filldir_cachep ? 0 : -ENOMEM); +} + +void unionfs_destroy_filldir_cache(void) +{ + if (unionfs_filldir_cachep) + kmem_cache_destroy(unionfs_filldir_cachep); +} + +/* + * This is a tuning parameter that tells us roughly how big to make the + * hash table in directory entries per page. This isn't perfect, but + * at least we get a hash table size that shouldn't be too overloaded. + * The following averages are based on my home directory. + * 14.44693 Overall + * 12.29 Single Page Directories + * 117.93 Multi-page directories + */ +#define DENTPAGE 4096 +#define DENTPERONEPAGE 12 +#define DENTPERPAGE 118 +#define MINHASHSIZE 1 +static int guesstimate_hash_size(struct inode *inode) +{ + struct inode *lower_inode; + int bindex; + int hashsize = MINHASHSIZE; + + if (UNIONFS_I(inode)->hashsize > 0) + return UNIONFS_I(inode)->hashsize; + + for (bindex = ibstart(inode); bindex <= ibend(inode); bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (!lower_inode) + continue; + + if (i_size_read(lower_inode) == DENTPAGE) + hashsize += DENTPERONEPAGE; + else + hashsize += (i_size_read(lower_inode) / DENTPAGE) * + DENTPERPAGE; + } + + return hashsize; +} + +int init_rdstate(struct file *file) +{ + BUG_ON(sizeof(loff_t) != + (sizeof(unsigned int) + sizeof(unsigned int))); + BUG_ON(UNIONFS_F(file)->rdstate != NULL); + + UNIONFS_F(file)->rdstate = alloc_rdstate(file->f_path.dentry->d_inode, + fbstart(file)); + + return (UNIONFS_F(file)->rdstate ? 0 : -ENOMEM); +} + +struct unionfs_dir_state *find_rdstate(struct inode *inode, loff_t fpos) +{ + struct unionfs_dir_state *rdstate = NULL; + struct list_head *pos; + + spin_lock(&UNIONFS_I(inode)->rdlock); + list_for_each(pos, &UNIONFS_I(inode)->readdircache) { + struct unionfs_dir_state *r = + list_entry(pos, struct unionfs_dir_state, cache); + if (fpos == rdstate2offset(r)) { + UNIONFS_I(inode)->rdcount--; + list_del(&r->cache); + rdstate = r; + break; + } + } + spin_unlock(&UNIONFS_I(inode)->rdlock); + return rdstate; +} + +struct unionfs_dir_state *alloc_rdstate(struct inode *inode, int bindex) +{ + int i = 0; + int hashsize; + unsigned long mallocsize = sizeof(struct unionfs_dir_state); + struct unionfs_dir_state *rdstate; + + hashsize = guesstimate_hash_size(inode); + mallocsize += hashsize * sizeof(struct list_head); + mallocsize = __roundup_pow_of_two(mallocsize); + + /* This should give us about 500 entries anyway. */ + if (mallocsize > PAGE_SIZE) + mallocsize = PAGE_SIZE; + + hashsize = (mallocsize - sizeof(struct unionfs_dir_state)) / + sizeof(struct list_head); + + rdstate = kmalloc(mallocsize, GFP_KERNEL); + if (unlikely(!rdstate)) + return NULL; + + spin_lock(&UNIONFS_I(inode)->rdlock); + if (UNIONFS_I(inode)->cookie >= (MAXRDCOOKIE - 1)) + UNIONFS_I(inode)->cookie = 1; + else + UNIONFS_I(inode)->cookie++; + + rdstate->cookie = UNIONFS_I(inode)->cookie; + spin_unlock(&UNIONFS_I(inode)->rdlock); + rdstate->offset = 1; + rdstate->access = jiffies; + rdstate->bindex = bindex; + rdstate->dirpos = 0; + rdstate->hashentries = 0; + rdstate->size = hashsize; + for (i = 0; i < rdstate->size; i++) + INIT_LIST_HEAD(&rdstate->list[i]); + + return rdstate; +} + +static void free_filldir_node(struct filldir_node *node) +{ + if (node->namelen >= DNAME_INLINE_LEN_MIN) + kfree(node->name); + kmem_cache_free(unionfs_filldir_cachep, node); +} + +void free_rdstate(struct unionfs_dir_state *state) +{ + struct filldir_node *tmp; + int i; + + for (i = 0; i < state->size; i++) { + struct list_head *head = &(state->list[i]); + struct list_head *pos, *n; + + /* traverse the list and deallocate space */ + list_for_each_safe(pos, n, head) { + tmp = list_entry(pos, struct filldir_node, file_list); + list_del(&tmp->file_list); + free_filldir_node(tmp); + } + } + + kfree(state); +} + +struct filldir_node *find_filldir_node(struct unionfs_dir_state *rdstate, + const char *name, int namelen, + int is_whiteout) +{ + int index; + unsigned int hash; + struct list_head *head; + struct list_head *pos; + struct filldir_node *cursor = NULL; + int found = 0; + + BUG_ON(namelen <= 0); + + hash = full_name_hash(name, namelen); + index = hash % rdstate->size; + + head = &(rdstate->list[index]); + list_for_each(pos, head) { + cursor = list_entry(pos, struct filldir_node, file_list); + + if (cursor->namelen == namelen && cursor->hash == hash && + !strncmp(cursor->name, name, namelen)) { + /* + * a duplicate exists, and hence no need to create + * entry to the list + */ + found = 1; + + /* + * if a duplicate is found in this branch, and is + * not due to the caller looking for an entry to + * whiteout, then the file system may be corrupted. + */ + if (unlikely(!is_whiteout && + cursor->bindex == rdstate->bindex)) + printk(KERN_ERR "unionfs: filldir: possible " + "I/O error: a file is duplicated " + "in the same branch %d: %s\n", + rdstate->bindex, cursor->name); + break; + } + } + + if (!found) + cursor = NULL; + + return cursor; +} + +int add_filldir_node(struct unionfs_dir_state *rdstate, const char *name, + int namelen, int bindex, int whiteout) +{ + struct filldir_node *new; + unsigned int hash; + int index; + int err = 0; + struct list_head *head; + + BUG_ON(namelen <= 0); + + hash = full_name_hash(name, namelen); + index = hash % rdstate->size; + head = &(rdstate->list[index]); + + new = kmem_cache_alloc(unionfs_filldir_cachep, GFP_KERNEL); + if (unlikely(!new)) { + err = -ENOMEM; + goto out; + } + + INIT_LIST_HEAD(&new->file_list); + new->namelen = namelen; + new->hash = hash; + new->bindex = bindex; + new->whiteout = whiteout; + + if (namelen < DNAME_INLINE_LEN_MIN) { + new->name = new->iname; + } else { + new->name = kmalloc(namelen + 1, GFP_KERNEL); + if (unlikely(!new->name)) { + kmem_cache_free(unionfs_filldir_cachep, new); + new = NULL; + goto out; + } + } + + memcpy(new->name, name, namelen); + new->name[namelen] = '\0'; + + rdstate->hashentries++; + + list_add(&(new->file_list), head); +out: + return err; +} diff --git a/fs/unionfs/rename.c b/fs/unionfs/rename.c new file mode 100644 index 0000000..936700e --- /dev/null +++ b/fs/unionfs/rename.c @@ -0,0 +1,517 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* + * This is a helper function for rename, used when rename ends up with hosed + * over dentries and we need to revert. + */ +static int unionfs_refresh_lower_dentry(struct dentry *dentry, + struct dentry *parent, int bindex) +{ + struct dentry *lower_dentry; + struct dentry *lower_parent; + int err = 0; + + verify_locked(dentry); + + lower_parent = unionfs_lower_dentry_idx(parent, bindex); + + BUG_ON(!S_ISDIR(lower_parent->d_inode->i_mode)); + + lower_dentry = lookup_one_len(dentry->d_name.name, lower_parent, + dentry->d_name.len); + if (IS_ERR(lower_dentry)) { + err = PTR_ERR(lower_dentry); + goto out; + } + + dput(unionfs_lower_dentry_idx(dentry, bindex)); + iput(unionfs_lower_inode_idx(dentry->d_inode, bindex)); + unionfs_set_lower_inode_idx(dentry->d_inode, bindex, NULL); + + if (!lower_dentry->d_inode) { + dput(lower_dentry); + unionfs_set_lower_dentry_idx(dentry, bindex, NULL); + } else { + unionfs_set_lower_dentry_idx(dentry, bindex, lower_dentry); + unionfs_set_lower_inode_idx(dentry->d_inode, bindex, + igrab(lower_dentry->d_inode)); + } + +out: + return err; +} + +static int __unionfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct dentry *old_parent, + struct inode *new_dir, struct dentry *new_dentry, + struct dentry *new_parent, + int bindex) +{ + int err = 0; + struct dentry *lower_old_dentry; + struct dentry *lower_new_dentry; + struct dentry *lower_old_dir_dentry; + struct dentry *lower_new_dir_dentry; + struct dentry *trap; + + lower_new_dentry = unionfs_lower_dentry_idx(new_dentry, bindex); + lower_old_dentry = unionfs_lower_dentry_idx(old_dentry, bindex); + + if (!lower_new_dentry) { + lower_new_dentry = + create_parents(new_parent->d_inode, + new_dentry, new_dentry->d_name.name, + bindex); + if (IS_ERR(lower_new_dentry)) { + err = PTR_ERR(lower_new_dentry); + if (IS_COPYUP_ERR(err)) + goto out; + printk(KERN_ERR "unionfs: error creating directory " + "tree for rename, bindex=%d err=%d\n", + bindex, err); + goto out; + } + } + + /* check for and remove whiteout, if any */ + err = check_unlink_whiteout(new_dentry, lower_new_dentry, bindex); + if (err > 0) /* ignore if whiteout found and successfully removed */ + err = 0; + if (err) + goto out; + + /* check of old_dentry branch is writable */ + err = is_robranch_super(old_dentry->d_sb, bindex); + if (err) + goto out; + + dget(lower_old_dentry); + dget(lower_new_dentry); + lower_old_dir_dentry = dget_parent(lower_old_dentry); + lower_new_dir_dentry = dget_parent(lower_new_dentry); + + trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + /* source should not be ancenstor of target */ + if (trap == lower_old_dentry) { + err = -EINVAL; + goto out_err_unlock; + } + /* target should not be ancenstor of source */ + if (trap == lower_new_dentry) { + err = -ENOTEMPTY; + goto out_err_unlock; + } + err = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry, + lower_new_dir_dentry->d_inode, lower_new_dentry); +out_err_unlock: + if (!err) { + /* update parent dir times */ + fsstack_copy_attr_times(old_dir, lower_old_dir_dentry->d_inode); + fsstack_copy_attr_times(new_dir, lower_new_dir_dentry->d_inode); + } + unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + + dput(lower_old_dir_dentry); + dput(lower_new_dir_dentry); + dput(lower_old_dentry); + dput(lower_new_dentry); + +out: + if (!err) { + /* Fixup the new_dentry. */ + if (bindex < dbstart(new_dentry)) + dbstart(new_dentry) = bindex; + else if (bindex > dbend(new_dentry)) + dbend(new_dentry) = bindex; + } + + return err; +} + +/* + * Main rename code. This is sufficiently complex, that it's documented in + * Documentation/filesystems/unionfs/rename.txt. This routine calls + * __unionfs_rename() above to perform some of the work. + */ +static int do_unionfs_rename(struct inode *old_dir, + struct dentry *old_dentry, + struct dentry *old_parent, + struct inode *new_dir, + struct dentry *new_dentry, + struct dentry *new_parent) +{ + int err = 0; + int bindex; + int old_bstart, old_bend; + int new_bstart, new_bend; + int do_copyup = -1; + int local_err = 0; + int eio = 0; + int revert = 0; + + old_bstart = dbstart(old_dentry); + old_bend = dbend(old_dentry); + + new_bstart = dbstart(new_dentry); + new_bend = dbend(new_dentry); + + /* Rename source to destination. */ + err = __unionfs_rename(old_dir, old_dentry, old_parent, + new_dir, new_dentry, new_parent, + old_bstart); + if (err) { + if (!IS_COPYUP_ERR(err)) + goto out; + do_copyup = old_bstart - 1; + } else { + revert = 1; + } + + /* + * Unlink all instances of destination that exist to the left of + * bstart of source. On error, revert back, goto out. + */ + for (bindex = old_bstart - 1; bindex >= new_bstart; bindex--) { + struct dentry *unlink_dentry; + struct dentry *unlink_dir_dentry; + + BUG_ON(bindex < 0); + unlink_dentry = unionfs_lower_dentry_idx(new_dentry, bindex); + if (!unlink_dentry) + continue; + + unlink_dir_dentry = lock_parent(unlink_dentry); + err = is_robranch_super(old_dir->i_sb, bindex); + if (!err) + err = vfs_unlink(unlink_dir_dentry->d_inode, + unlink_dentry); + + fsstack_copy_attr_times(new_parent->d_inode, + unlink_dir_dentry->d_inode); + /* propagate number of hard-links */ + new_parent->d_inode->i_nlink = + unionfs_get_nlinks(new_parent->d_inode); + + unlock_dir(unlink_dir_dentry); + if (!err) { + if (bindex != new_bstart) { + dput(unlink_dentry); + unionfs_set_lower_dentry_idx(new_dentry, + bindex, NULL); + } + } else if (IS_COPYUP_ERR(err)) { + do_copyup = bindex - 1; + } else if (revert) { + goto revert; + } + } + + if (do_copyup != -1) { + for (bindex = do_copyup; bindex >= 0; bindex--) { + /* + * copyup the file into some left directory, so that + * you can rename it + */ + err = copyup_dentry(old_parent->d_inode, + old_dentry, old_bstart, bindex, + old_dentry->d_name.name, + old_dentry->d_name.len, NULL, + i_size_read(old_dentry->d_inode)); + /* if copyup failed, try next branch to the left */ + if (err) + continue; + /* + * create whiteout before calling __unionfs_rename + * because the latter will change the old_dentry's + * lower name and parent dir, resulting in the + * whiteout getting created in the wrong dir. + */ + err = create_whiteout(old_dentry, bindex); + if (err) { + printk(KERN_ERR "unionfs: can't create a " + "whiteout for %s in rename (err=%d)\n", + old_dentry->d_name.name, err); + continue; + } + err = __unionfs_rename(old_dir, old_dentry, old_parent, + new_dir, new_dentry, new_parent, + bindex); + break; + } + } + + /* make it opaque */ + if (S_ISDIR(old_dentry->d_inode->i_mode)) { + err = make_dir_opaque(old_dentry, dbstart(old_dentry)); + if (err) + goto revert; + } + + /* + * Create whiteout for source, only if: + * (1) There is more than one underlying instance of source. + * (We did a copy_up is taken care of above). + */ + if ((old_bstart != old_bend) && (do_copyup == -1)) { + err = create_whiteout(old_dentry, old_bstart); + if (err) { + /* can't fix anything now, so we exit with -EIO */ + printk(KERN_ERR "unionfs: can't create a whiteout for " + "%s in rename!\n", old_dentry->d_name.name); + err = -EIO; + } + } + +out: + return err; + +revert: + /* Do revert here. */ + local_err = unionfs_refresh_lower_dentry(new_dentry, new_parent, + old_bstart); + if (local_err) { + printk(KERN_ERR "unionfs: revert failed in rename: " + "the new refresh failed\n"); + eio = -EIO; + } + + local_err = unionfs_refresh_lower_dentry(old_dentry, old_parent, + old_bstart); + if (local_err) { + printk(KERN_ERR "unionfs: revert failed in rename: " + "the old refresh failed\n"); + eio = -EIO; + goto revert_out; + } + + if (!unionfs_lower_dentry_idx(new_dentry, bindex) || + !unionfs_lower_dentry_idx(new_dentry, bindex)->d_inode) { + printk(KERN_ERR "unionfs: revert failed in rename: " + "the object disappeared from under us!\n"); + eio = -EIO; + goto revert_out; + } + + if (unionfs_lower_dentry_idx(old_dentry, bindex) && + unionfs_lower_dentry_idx(old_dentry, bindex)->d_inode) { + printk(KERN_ERR "unionfs: revert failed in rename: " + "the object was created underneath us!\n"); + eio = -EIO; + goto revert_out; + } + + local_err = __unionfs_rename(new_dir, new_dentry, new_parent, + old_dir, old_dentry, old_parent, + old_bstart); + + /* If we can't fix it, then we cop-out with -EIO. */ + if (local_err) { + printk(KERN_ERR "unionfs: revert failed in rename!\n"); + eio = -EIO; + } + + local_err = unionfs_refresh_lower_dentry(new_dentry, new_parent, + bindex); + if (local_err) + eio = -EIO; + local_err = unionfs_refresh_lower_dentry(old_dentry, old_parent, + bindex); + if (local_err) + eio = -EIO; + +revert_out: + if (eio) + err = eio; + return err; +} + +/* + * We can't copyup a directory, because it may involve huge numbers of + * children, etc. Doing that in the kernel would be bad, so instead we + * return EXDEV to the user-space utility that caused this, and let the + * user-space recurse and ask us to copy up each file separately. + */ +static int may_rename_dir(struct dentry *dentry, struct dentry *parent) +{ + int err, bstart; + + err = check_empty(dentry, parent, NULL); + if (err == -ENOTEMPTY) { + if (is_robranch(dentry)) + return -EXDEV; + } else if (err) { + return err; + } + + bstart = dbstart(dentry); + if (dbend(dentry) == bstart || dbopaque(dentry) == bstart) + return 0; + + dbstart(dentry) = bstart + 1; + err = check_empty(dentry, parent, NULL); + dbstart(dentry) = bstart; + if (err == -ENOTEMPTY) + err = -EXDEV; + return err; +} + +/* + * The locking rules in unionfs_rename are complex. We could use a simpler + * superblock-level name-space lock for renames and copy-ups. + */ +int unionfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + int err = 0; + struct dentry *wh_dentry; + struct dentry *old_parent, *new_parent; + int valid = true; + + unionfs_read_lock(old_dentry->d_sb, UNIONFS_SMUTEX_CHILD); + old_parent = dget_parent(old_dentry); + new_parent = dget_parent(new_dentry); + /* un/lock parent dentries only if they differ from old/new_dentry */ + if (old_parent != old_dentry && + old_parent != new_dentry) + unionfs_lock_dentry(old_parent, UNIONFS_DMUTEX_REVAL_PARENT); + if (new_parent != old_dentry && + new_parent != new_dentry && + new_parent != old_parent) + unionfs_lock_dentry(new_parent, UNIONFS_DMUTEX_REVAL_CHILD); + unionfs_double_lock_dentry(old_dentry, new_dentry); + + valid = __unionfs_d_revalidate(old_dentry, old_parent, false); + if (!valid) { + err = -ESTALE; + goto out; + } + if (!d_deleted(new_dentry) && new_dentry->d_inode) { + valid = __unionfs_d_revalidate(new_dentry, new_parent, false); + if (!valid) { + err = -ESTALE; + goto out; + } + } + + if (!S_ISDIR(old_dentry->d_inode->i_mode)) + err = unionfs_partial_lookup(old_dentry, old_parent); + else + err = may_rename_dir(old_dentry, old_parent); + + if (err) + goto out; + + err = unionfs_partial_lookup(new_dentry, new_parent); + if (err) + goto out; + + /* + * if new_dentry is already lower because of whiteout, + * simply override it even if the whited-out dir is not empty. + */ + wh_dentry = find_first_whiteout(new_dentry); + if (!IS_ERR(wh_dentry)) { + dput(wh_dentry); + } else if (new_dentry->d_inode) { + if (S_ISDIR(old_dentry->d_inode->i_mode) != + S_ISDIR(new_dentry->d_inode->i_mode)) { + err = S_ISDIR(old_dentry->d_inode->i_mode) ? + -ENOTDIR : -EISDIR; + goto out; + } + + if (S_ISDIR(new_dentry->d_inode->i_mode)) { + struct unionfs_dir_state *namelist = NULL; + /* check if this unionfs directory is empty or not */ + err = check_empty(new_dentry, new_parent, &namelist); + if (err) + goto out; + + if (!is_robranch(new_dentry)) + err = delete_whiteouts(new_dentry, + dbstart(new_dentry), + namelist); + + free_rdstate(namelist); + + if (err) + goto out; + } + } + + err = do_unionfs_rename(old_dir, old_dentry, old_parent, + new_dir, new_dentry, new_parent); + if (err) + goto out; + + /* + * force re-lookup since the dir on ro branch is not renamed, and + * lower dentries still indicate the un-renamed ones. + */ + if (S_ISDIR(old_dentry->d_inode->i_mode)) + atomic_dec(&UNIONFS_D(old_dentry)->generation); + else + unionfs_postcopyup_release(old_dentry); + if (new_dentry->d_inode && !S_ISDIR(new_dentry->d_inode->i_mode)) { + unionfs_postcopyup_release(new_dentry); + unionfs_postcopyup_setmnt(new_dentry); + if (!unionfs_lower_inode(new_dentry->d_inode)) { + /* + * If we get here, it means that no copyup was + * needed, and that a file by the old name already + * existing on the destination branch; that file got + * renamed earlier in this function, so all we need + * to do here is set the lower inode. + */ + struct inode *inode; + inode = unionfs_lower_inode(old_dentry->d_inode); + igrab(inode); + unionfs_set_lower_inode_idx(new_dentry->d_inode, + dbstart(new_dentry), + inode); + } + } + /* if all of this renaming succeeded, update our times */ + unionfs_copy_attr_times(old_dentry->d_inode); + unionfs_copy_attr_times(new_dentry->d_inode); + unionfs_check_inode(old_dir); + unionfs_check_inode(new_dir); + unionfs_check_dentry(old_dentry); + unionfs_check_dentry(new_dentry); + +out: + if (err) /* clear the new_dentry stuff created */ + d_drop(new_dentry); + + unionfs_double_unlock_dentry(old_dentry, new_dentry); + if (new_parent != old_dentry && + new_parent != new_dentry && + new_parent != old_parent) + unionfs_unlock_dentry(new_parent); + if (old_parent != old_dentry && + old_parent != new_dentry) + unionfs_unlock_dentry(old_parent); + dput(new_parent); + dput(old_parent); + unionfs_read_unlock(old_dentry->d_sb); + + return err; +} diff --git a/fs/unionfs/sioq.c b/fs/unionfs/sioq.c new file mode 100644 index 0000000..760c580 --- /dev/null +++ b/fs/unionfs/sioq.c @@ -0,0 +1,101 @@ +/* + * Copyright (c) 2006-2010 Erez Zadok + * Copyright (c) 2006 Charles P. Wright + * Copyright (c) 2006-2007 Josef 'Jeff' Sipek + * Copyright (c) 2006 Junjiro Okajima + * Copyright (c) 2006 David P. Quigley + * Copyright (c) 2006-2010 Stony Brook University + * Copyright (c) 2006-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* + * Super-user IO work Queue - sometimes we need to perform actions which + * would fail due to the unix permissions on the parent directory (e.g., + * rmdir a directory which appears empty, but in reality contains + * whiteouts). + */ + +static struct workqueue_struct *superio_workqueue; + +int __init init_sioq(void) +{ + int err; + + superio_workqueue = create_workqueue("unionfs_siod"); + if (!IS_ERR(superio_workqueue)) + return 0; + + err = PTR_ERR(superio_workqueue); + printk(KERN_ERR "unionfs: create_workqueue failed %d\n", err); + superio_workqueue = NULL; + return err; +} + +void stop_sioq(void) +{ + if (superio_workqueue) + destroy_workqueue(superio_workqueue); +} + +void run_sioq(work_func_t func, struct sioq_args *args) +{ + INIT_WORK(&args->work, func); + + init_completion(&args->comp); + while (!queue_work(superio_workqueue, &args->work)) { + /* TODO: do accounting if needed */ + schedule(); + } + wait_for_completion(&args->comp); +} + +void __unionfs_create(struct work_struct *work) +{ + struct sioq_args *args = container_of(work, struct sioq_args, work); + struct create_args *c = &args->create; + + args->err = vfs_create(c->parent, c->dentry, c->mode, c->nd); + complete(&args->comp); +} + +void __unionfs_mkdir(struct work_struct *work) +{ + struct sioq_args *args = container_of(work, struct sioq_args, work); + struct mkdir_args *m = &args->mkdir; + + args->err = vfs_mkdir(m->parent, m->dentry, m->mode); + complete(&args->comp); +} + +void __unionfs_mknod(struct work_struct *work) +{ + struct sioq_args *args = container_of(work, struct sioq_args, work); + struct mknod_args *m = &args->mknod; + + args->err = vfs_mknod(m->parent, m->dentry, m->mode, m->dev); + complete(&args->comp); +} + +void __unionfs_symlink(struct work_struct *work) +{ + struct sioq_args *args = container_of(work, struct sioq_args, work); + struct symlink_args *s = &args->symlink; + + args->err = vfs_symlink(s->parent, s->dentry, s->symbuf); + complete(&args->comp); +} + +void __unionfs_unlink(struct work_struct *work) +{ + struct sioq_args *args = container_of(work, struct sioq_args, work); + struct unlink_args *u = &args->unlink; + + args->err = vfs_unlink(u->parent, u->dentry); + complete(&args->comp); +} diff --git a/fs/unionfs/sioq.h b/fs/unionfs/sioq.h new file mode 100644 index 0000000..b26d248 --- /dev/null +++ b/fs/unionfs/sioq.h @@ -0,0 +1,91 @@ +/* + * Copyright (c) 2006-2010 Erez Zadok + * Copyright (c) 2006 Charles P. Wright + * Copyright (c) 2006-2007 Josef 'Jeff' Sipek + * Copyright (c) 2006 Junjiro Okajima + * Copyright (c) 2006 David P. Quigley + * Copyright (c) 2006-2010 Stony Brook University + * Copyright (c) 2006-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _SIOQ_H +#define _SIOQ_H + +struct deletewh_args { + struct unionfs_dir_state *namelist; + struct dentry *dentry; + int bindex; +}; + +struct is_opaque_args { + struct dentry *dentry; +}; + +struct create_args { + struct inode *parent; + struct dentry *dentry; + umode_t mode; + struct nameidata *nd; +}; + +struct mkdir_args { + struct inode *parent; + struct dentry *dentry; + umode_t mode; +}; + +struct mknod_args { + struct inode *parent; + struct dentry *dentry; + umode_t mode; + dev_t dev; +}; + +struct symlink_args { + struct inode *parent; + struct dentry *dentry; + char *symbuf; +}; + +struct unlink_args { + struct inode *parent; + struct dentry *dentry; +}; + + +struct sioq_args { + struct completion comp; + struct work_struct work; + int err; + void *ret; + + union { + struct deletewh_args deletewh; + struct is_opaque_args is_opaque; + struct create_args create; + struct mkdir_args mkdir; + struct mknod_args mknod; + struct symlink_args symlink; + struct unlink_args unlink; + }; +}; + +/* Extern definitions for SIOQ functions */ +extern int __init init_sioq(void); +extern void stop_sioq(void); +extern void run_sioq(work_func_t func, struct sioq_args *args); + +/* Extern definitions for our privilege escalation helpers */ +extern void __unionfs_create(struct work_struct *work); +extern void __unionfs_mkdir(struct work_struct *work); +extern void __unionfs_mknod(struct work_struct *work); +extern void __unionfs_symlink(struct work_struct *work); +extern void __unionfs_unlink(struct work_struct *work); +extern void __delete_whiteouts(struct work_struct *work); +extern void __is_opaque_dir(struct work_struct *work); + +#endif /* not _SIOQ_H */ diff --git a/fs/unionfs/subr.c b/fs/unionfs/subr.c new file mode 100644 index 0000000..570a344 --- /dev/null +++ b/fs/unionfs/subr.c @@ -0,0 +1,95 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* + * returns the right n_link value based on the inode type + */ +int unionfs_get_nlinks(const struct inode *inode) +{ + /* don't bother to do all the work since we're unlinked */ + if (inode->i_nlink == 0) + return 0; + + if (!S_ISDIR(inode->i_mode)) + return unionfs_lower_inode(inode)->i_nlink; + + /* + * For directories, we return 1. The only place that could cares + * about links is readdir, and there's d_type there so even that + * doesn't matter. + */ + return 1; +} + +/* copy a/m/ctime from the lower branch with the newest times */ +void unionfs_copy_attr_times(struct inode *upper) +{ + int bindex; + struct inode *lower; + + if (!upper) + return; + if (ibstart(upper) < 0) { +#ifdef CONFIG_UNION_FS_DEBUG + WARN_ON(ibstart(upper) < 0); +#endif /* CONFIG_UNION_FS_DEBUG */ + return; + } + for (bindex = ibstart(upper); bindex <= ibend(upper); bindex++) { + lower = unionfs_lower_inode_idx(upper, bindex); + if (!lower) + continue; /* not all lower dir objects may exist */ + if (unlikely(timespec_compare(&upper->i_mtime, + &lower->i_mtime) < 0)) + upper->i_mtime = lower->i_mtime; + if (unlikely(timespec_compare(&upper->i_ctime, + &lower->i_ctime) < 0)) + upper->i_ctime = lower->i_ctime; + if (unlikely(timespec_compare(&upper->i_atime, + &lower->i_atime) < 0)) + upper->i_atime = lower->i_atime; + } +} + +/* + * A unionfs/fanout version of fsstack_copy_attr_all. Uses a + * unionfs_get_nlinks to properly calcluate the number of links to a file. + * Also, copies the max() of all a/m/ctimes for all lower inodes (which is + * important if the lower inode is a directory type) + */ +void unionfs_copy_attr_all(struct inode *dest, + const struct inode *src) +{ + dest->i_mode = src->i_mode; + dest->i_uid = src->i_uid; + dest->i_gid = src->i_gid; + dest->i_rdev = src->i_rdev; + + unionfs_copy_attr_times(dest); + + dest->i_blkbits = src->i_blkbits; + dest->i_flags = src->i_flags; + + /* + * Update the nlinks AFTER updating the above fields, because the + * get_links callback may depend on them. + */ + dest->i_nlink = unionfs_get_nlinks(dest); +} diff --git a/fs/unionfs/super.c b/fs/unionfs/super.c new file mode 100644 index 0000000..45bb9bf --- /dev/null +++ b/fs/unionfs/super.c @@ -0,0 +1,1029 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* + * The inode cache is used with alloc_inode for both our inode info and the + * vfs inode. + */ +static struct kmem_cache *unionfs_inode_cachep; + +struct inode *unionfs_iget(struct super_block *sb, unsigned long ino) +{ + int size; + struct unionfs_inode_info *info; + struct inode *inode; + + inode = iget_locked(sb, ino); + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode->i_state & I_NEW)) + return inode; + + info = UNIONFS_I(inode); + memset(info, 0, offsetof(struct unionfs_inode_info, vfs_inode)); + info->bstart = -1; + info->bend = -1; + atomic_set(&info->generation, + atomic_read(&UNIONFS_SB(inode->i_sb)->generation)); + spin_lock_init(&info->rdlock); + info->rdcount = 1; + info->hashsize = -1; + INIT_LIST_HEAD(&info->readdircache); + + size = sbmax(inode->i_sb) * sizeof(struct inode *); + info->lower_inodes = kzalloc(size, GFP_KERNEL); + if (unlikely(!info->lower_inodes)) { + printk(KERN_CRIT "unionfs: no kernel memory when allocating " + "lower-pointer array!\n"); + iget_failed(inode); + return ERR_PTR(-ENOMEM); + } + + inode->i_version++; + inode->i_op = &unionfs_main_iops; + inode->i_fop = &unionfs_main_fops; + + inode->i_mapping->a_ops = &unionfs_aops; + + /* + * reset times so unionfs_copy_attr_all can keep out time invariants + * right (upper inode time being the max of all lower ones). + */ + inode->i_atime.tv_sec = inode->i_atime.tv_nsec = 0; + inode->i_mtime.tv_sec = inode->i_mtime.tv_nsec = 0; + inode->i_ctime.tv_sec = inode->i_ctime.tv_nsec = 0; + unlock_new_inode(inode); + return inode; +} + +/* + * final actions when unmounting a file system + * + * No need to lock rwsem. + */ +static void unionfs_put_super(struct super_block *sb) +{ + int bindex, bstart, bend; + struct unionfs_sb_info *spd; + int leaks = 0; + + spd = UNIONFS_SB(sb); + if (!spd) + return; + + bstart = sbstart(sb); + bend = sbend(sb); + + /* Make sure we have no leaks of branchget/branchput. */ + for (bindex = bstart; bindex <= bend; bindex++) + if (unlikely(branch_count(sb, bindex) != 0)) { + printk(KERN_CRIT + "unionfs: branch %d has %d references left!\n", + bindex, branch_count(sb, bindex)); + leaks = 1; + } + WARN_ON(leaks != 0); + + /* decrement lower super references */ + for (bindex = bstart; bindex <= bend; bindex++) { + struct super_block *s; + s = unionfs_lower_super_idx(sb, bindex); + unionfs_set_lower_super_idx(sb, bindex, NULL); + atomic_dec(&s->s_active); + } + + kfree(spd->dev_name); + kfree(spd->data); + kfree(spd); + sb->s_fs_info = NULL; +} + +/* + * Since people use this to answer the "How big of a file can I write?" + * question, we report the size of the highest priority branch as the size of + * the union. + */ +static int unionfs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + int err = 0; + struct super_block *sb; + struct dentry *lower_dentry; + struct dentry *parent; + struct path lower_path; + bool valid; + + sb = dentry->d_sb; + + unionfs_read_lock(sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out; + } + unionfs_check_dentry(dentry); + + lower_dentry = unionfs_lower_dentry(sb->s_root); + lower_path.dentry = lower_dentry; + lower_path.mnt = unionfs_mntget(sb->s_root, 0); + err = vfs_statfs(&lower_path, buf); + mntput(lower_path.mnt); + + /* set return buf to our f/s to avoid confusing user-level utils */ + buf->f_type = UNIONFS_SUPER_MAGIC; + /* + * Our maximum file name can is shorter by a few bytes because every + * file name could potentially be whited-out. + * + * XXX: this restriction goes away with ODF. + */ + unionfs_set_max_namelen(&buf->f_namelen); + + /* + * reset two fields to avoid confusing user-land. + * XXX: is this still necessary? + */ + memset(&buf->f_fsid, 0, sizeof(__kernel_fsid_t)); + memset(&buf->f_spare, 0, sizeof(buf->f_spare)); + +out: + unionfs_check_dentry(dentry); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(sb); + return err; +} + +/* handle mode changing during remount */ +static noinline_for_stack int do_remount_mode_option( + char *optarg, + int cur_branches, + struct unionfs_data *new_data, + struct path *new_lower_paths) +{ + int err = -EINVAL; + int perms, idx; + char *modename = strchr(optarg, '='); + struct nameidata nd; + + /* by now, optarg contains the branch name */ + if (!*optarg) { + printk(KERN_ERR + "unionfs: no branch specified for mode change\n"); + goto out; + } + if (!modename) { + printk(KERN_ERR "unionfs: branch \"%s\" requires a mode\n", + optarg); + goto out; + } + *modename++ = '\0'; + err = parse_branch_mode(modename, &perms); + if (err) { + printk(KERN_ERR "unionfs: invalid mode \"%s\" for \"%s\"\n", + modename, optarg); + goto out; + } + + /* + * Find matching branch index. For now, this assumes that nothing + * has been mounted on top of this Unionfs stack. Once we have /odf + * and cache-coherency resolved, we'll address the branch-path + * uniqueness. + */ + err = path_lookup(optarg, LOOKUP_FOLLOW, &nd); + if (err) { + printk(KERN_ERR "unionfs: error accessing " + "lower directory \"%s\" (error %d)\n", + optarg, err); + goto out; + } + for (idx = 0; idx < cur_branches; idx++) + if (nd.path.mnt == new_lower_paths[idx].mnt && + nd.path.dentry == new_lower_paths[idx].dentry) + break; + path_put(&nd.path); /* no longer needed */ + if (idx == cur_branches) { + err = -ENOENT; /* err may have been reset above */ + printk(KERN_ERR "unionfs: branch \"%s\" " + "not found\n", optarg); + goto out; + } + /* check/change mode for existing branch */ + /* we don't warn if perms==branchperms */ + new_data[idx].branchperms = perms; + err = 0; +out: + return err; +} + +/* handle branch deletion during remount */ +static noinline_for_stack int do_remount_del_option( + char *optarg, int cur_branches, + struct unionfs_data *new_data, + struct path *new_lower_paths) +{ + int err = -EINVAL; + int idx; + struct nameidata nd; + + /* optarg contains the branch name to delete */ + + /* + * Find matching branch index. For now, this assumes that nothing + * has been mounted on top of this Unionfs stack. Once we have /odf + * and cache-coherency resolved, we'll address the branch-path + * uniqueness. + */ + err = path_lookup(optarg, LOOKUP_FOLLOW, &nd); + if (err) { + printk(KERN_ERR "unionfs: error accessing " + "lower directory \"%s\" (error %d)\n", + optarg, err); + goto out; + } + for (idx = 0; idx < cur_branches; idx++) + if (nd.path.mnt == new_lower_paths[idx].mnt && + nd.path.dentry == new_lower_paths[idx].dentry) + break; + path_put(&nd.path); /* no longer needed */ + if (idx == cur_branches) { + printk(KERN_ERR "unionfs: branch \"%s\" " + "not found\n", optarg); + err = -ENOENT; + goto out; + } + /* check if there are any open files on the branch to be deleted */ + if (atomic_read(&new_data[idx].open_files) > 0) { + err = -EBUSY; + goto out; + } + + /* + * Now we have to delete the branch. First, release any handles it + * has. Then, move the remaining array indexes past "idx" in + * new_data and new_lower_paths one to the left. Finally, adjust + * cur_branches. + */ + path_put(&new_lower_paths[idx]); + + if (idx < cur_branches - 1) { + /* if idx==cur_branches-1, we delete last branch: easy */ + memmove(&new_data[idx], &new_data[idx+1], + (cur_branches - 1 - idx) * + sizeof(struct unionfs_data)); + memmove(&new_lower_paths[idx], &new_lower_paths[idx+1], + (cur_branches - 1 - idx) * sizeof(struct path)); + } + + err = 0; +out: + return err; +} + +/* handle branch insertion during remount */ +static noinline_for_stack int do_remount_add_option( + char *optarg, int cur_branches, + struct unionfs_data *new_data, + struct path *new_lower_paths, + int *high_branch_id) +{ + int err = -EINVAL; + int perms; + int idx = 0; /* default: insert at beginning */ + char *new_branch , *modename = NULL; + struct nameidata nd; + + /* + * optarg can be of several forms: + * + * /bar:/foo insert /foo before /bar + * /bar:/foo=ro insert /foo in ro mode before /bar + * /foo insert /foo in the beginning (prepend) + * :/foo insert /foo at the end (append) + */ + if (*optarg == ':') { /* append? */ + new_branch = optarg + 1; /* skip ':' */ + idx = cur_branches; + goto found_insertion_point; + } + new_branch = strchr(optarg, ':'); + if (!new_branch) { /* prepend? */ + new_branch = optarg; + goto found_insertion_point; + } + *new_branch++ = '\0'; /* holds path+mode of new branch */ + + /* + * Find matching branch index. For now, this assumes that nothing + * has been mounted on top of this Unionfs stack. Once we have /odf + * and cache-coherency resolved, we'll address the branch-path + * uniqueness. + */ + err = path_lookup(optarg, LOOKUP_FOLLOW, &nd); + if (err) { + printk(KERN_ERR "unionfs: error accessing " + "lower directory \"%s\" (error %d)\n", + optarg, err); + goto out; + } + for (idx = 0; idx < cur_branches; idx++) + if (nd.path.mnt == new_lower_paths[idx].mnt && + nd.path.dentry == new_lower_paths[idx].dentry) + break; + path_put(&nd.path); /* no longer needed */ + if (idx == cur_branches) { + printk(KERN_ERR "unionfs: branch \"%s\" " + "not found\n", optarg); + err = -ENOENT; + goto out; + } + + /* + * At this point idx will hold the index where the new branch should + * be inserted before. + */ +found_insertion_point: + /* find the mode for the new branch */ + if (new_branch) + modename = strchr(new_branch, '='); + if (modename) + *modename++ = '\0'; + if (!new_branch || !*new_branch) { + printk(KERN_ERR "unionfs: null new branch\n"); + err = -EINVAL; + goto out; + } + err = parse_branch_mode(modename, &perms); + if (err) { + printk(KERN_ERR "unionfs: invalid mode \"%s\" for " + "branch \"%s\"\n", modename, new_branch); + goto out; + } + err = path_lookup(new_branch, LOOKUP_FOLLOW, &nd); + if (err) { + printk(KERN_ERR "unionfs: error accessing " + "lower directory \"%s\" (error %d)\n", + new_branch, err); + goto out; + } + /* + * It's probably safe to check_mode the new branch to insert. Note: + * we don't allow inserting branches which are unionfs's by + * themselves (check_branch returns EINVAL in that case). This is + * because this code base doesn't support stacking unionfs: the ODF + * code base supports that correctly. + */ + err = check_branch(&nd); + if (err) { + printk(KERN_ERR "unionfs: lower directory " + "\"%s\" is not a valid branch\n", optarg); + path_put(&nd.path); + goto out; + } + + /* + * Now we have to insert the new branch. But first, move the bits + * to make space for the new branch, if needed. Finally, adjust + * cur_branches. + * We don't release nd here; it's kept until umount/remount. + */ + if (idx < cur_branches) { + /* if idx==cur_branches, we append: easy */ + memmove(&new_data[idx+1], &new_data[idx], + (cur_branches - idx) * sizeof(struct unionfs_data)); + memmove(&new_lower_paths[idx+1], &new_lower_paths[idx], + (cur_branches - idx) * sizeof(struct path)); + } + new_lower_paths[idx].dentry = nd.path.dentry; + new_lower_paths[idx].mnt = nd.path.mnt; + + new_data[idx].sb = nd.path.dentry->d_sb; + atomic_set(&new_data[idx].open_files, 0); + new_data[idx].branchperms = perms; + new_data[idx].branch_id = ++*high_branch_id; /* assign new branch ID */ + + err = 0; +out: + return err; +} + + +/* + * Support branch management options on remount. + * + * See Documentation/filesystems/unionfs/ for details. + * + * @flags: numeric mount options + * @options: mount options string + * + * This function can rearrange a mounted union dynamically, adding and + * removing branches, including changing branch modes. Clearly this has to + * be done safely and atomically. Luckily, the VFS already calls this + * function with lock_super(sb) and lock_kernel() held, preventing + * concurrent mixing of new mounts, remounts, and unmounts. Moreover, + * do_remount_sb(), our caller function, already called shrink_dcache_sb(sb) + * to purge dentries/inodes from our superblock, and also called + * fsync_super(sb) to purge any dirty pages. So we're good. + * + * XXX: however, our remount code may also need to invalidate mapped pages + * so as to force them to be re-gotten from the (newly reconfigured) lower + * branches. This has to wait for proper mmap and cache coherency support + * in the VFS. + * + */ +static int unionfs_remount_fs(struct super_block *sb, int *flags, + char *options) +{ + int err = 0; + int i; + char *optionstmp, *tmp_to_free; /* kstrdup'ed of "options" */ + char *optname; + int cur_branches = 0; /* no. of current branches */ + int new_branches = 0; /* no. of branches actually left in the end */ + int add_branches; /* est. no. of branches to add */ + int del_branches; /* est. no. of branches to del */ + int max_branches; /* max possible no. of branches */ + struct unionfs_data *new_data = NULL, *tmp_data = NULL; + struct path *new_lower_paths = NULL, *tmp_lower_paths = NULL; + struct inode **new_lower_inodes = NULL; + int new_high_branch_id; /* new high branch ID */ + int size; /* memory allocation size, temp var */ + int old_ibstart, old_ibend; + + unionfs_write_lock(sb); + + /* + * The VFS will take care of "ro" and "rw" flags, and we can safely + * ignore MS_SILENT, but anything else left over is an error. So we + * need to check if any other flags may have been passed (none are + * allowed/supported as of now). + */ + if ((*flags & ~(MS_RDONLY | MS_SILENT)) != 0) { + printk(KERN_ERR + "unionfs: remount flags 0x%x unsupported\n", *flags); + err = -EINVAL; + goto out_error; + } + + /* + * If 'options' is NULL, it's probably because the user just changed + * the union to a "ro" or "rw" and the VFS took care of it. So + * nothing to do and we're done. + */ + if (!options || options[0] == '\0') + goto out_error; + + /* + * Find out how many branches we will have in the end, counting + * "add" and "del" commands. Copy the "options" string because + * strsep modifies the string and we need it later. + */ + tmp_to_free = kstrdup(options, GFP_KERNEL); + optionstmp = tmp_to_free; + if (unlikely(!optionstmp)) { + err = -ENOMEM; + goto out_free; + } + cur_branches = sbmax(sb); /* current no. branches */ + new_branches = sbmax(sb); + del_branches = 0; + add_branches = 0; + new_high_branch_id = sbhbid(sb); /* save current high_branch_id */ + while ((optname = strsep(&optionstmp, ",")) != NULL) { + char *optarg; + + if (!optname || !*optname) + continue; + + optarg = strchr(optname, '='); + if (optarg) + *optarg++ = '\0'; + + if (!strcmp("add", optname)) + add_branches++; + else if (!strcmp("del", optname)) + del_branches++; + } + kfree(tmp_to_free); + /* after all changes, will we have at least one branch left? */ + if ((new_branches + add_branches - del_branches) < 1) { + printk(KERN_ERR + "unionfs: no branches left after remount\n"); + err = -EINVAL; + goto out_free; + } + + /* + * Since we haven't actually parsed all the add/del options, nor + * have we checked them for errors, we don't know for sure how many + * branches we will have after all changes have taken place. In + * fact, the total number of branches left could be less than what + * we have now. So we need to allocate space for a temporary + * placeholder that is at least as large as the maximum number of + * branches we *could* have, which is the current number plus all + * the additions. Once we're done with these temp placeholders, we + * may have to re-allocate the final size, copy over from the temp, + * and then free the temps (done near the end of this function). + */ + max_branches = cur_branches + add_branches; + /* allocate space for new pointers to lower dentry */ + tmp_data = kcalloc(max_branches, + sizeof(struct unionfs_data), GFP_KERNEL); + if (unlikely(!tmp_data)) { + err = -ENOMEM; + goto out_free; + } + /* allocate space for new pointers to lower paths */ + tmp_lower_paths = kcalloc(max_branches, + sizeof(struct path), GFP_KERNEL); + if (unlikely(!tmp_lower_paths)) { + err = -ENOMEM; + goto out_free; + } + /* copy current info into new placeholders, incrementing refcnts */ + memcpy(tmp_data, UNIONFS_SB(sb)->data, + cur_branches * sizeof(struct unionfs_data)); + memcpy(tmp_lower_paths, UNIONFS_D(sb->s_root)->lower_paths, + cur_branches * sizeof(struct path)); + for (i = 0; i < cur_branches; i++) + path_get(&tmp_lower_paths[i]); /* drop refs at end of fxn */ + + /******************************************************************* + * For each branch command, do path_lookup on the requested branch, + * and apply the change to a temp branch list. To handle errors, we + * already dup'ed the old arrays (above), and increased the refcnts + * on various f/s objects. So now we can do all the path_lookups + * and branch-management commands on the new arrays. If it fail mid + * way, we free the tmp arrays and *put all objects. If we succeed, + * then we free old arrays and *put its objects, and then replace + * the arrays with the new tmp list (we may have to re-allocate the + * memory because the temp lists could have been larger than what we + * actually needed). + *******************************************************************/ + + while ((optname = strsep(&options, ",")) != NULL) { + char *optarg; + + if (!optname || !*optname) + continue; + /* + * At this stage optname holds a comma-delimited option, but + * without the commas. Next, we need to break the string on + * the '=' symbol to separate CMD=ARG, where ARG itself can + * be KEY=VAL. For example, in mode=/foo=rw, CMD is "mode", + * KEY is "/foo", and VAL is "rw". + */ + optarg = strchr(optname, '='); + if (optarg) + *optarg++ = '\0'; + /* incgen remount option (instead of old ioctl) */ + if (!strcmp("incgen", optname)) { + err = 0; + goto out_no_change; + } + + /* + * All of our options take an argument now. (Insert ones + * that don't above this check.) So at this stage optname + * contains the CMD part and optarg contains the ARG part. + */ + if (!optarg || !*optarg) { + printk(KERN_ERR "unionfs: all remount options require " + "an argument (%s)\n", optname); + err = -EINVAL; + goto out_release; + } + + if (!strcmp("add", optname)) { + err = do_remount_add_option(optarg, new_branches, + tmp_data, + tmp_lower_paths, + &new_high_branch_id); + if (err) + goto out_release; + new_branches++; + if (new_branches > UNIONFS_MAX_BRANCHES) { + printk(KERN_ERR "unionfs: command exceeds " + "%d branches\n", UNIONFS_MAX_BRANCHES); + err = -E2BIG; + goto out_release; + } + continue; + } + if (!strcmp("del", optname)) { + err = do_remount_del_option(optarg, new_branches, + tmp_data, + tmp_lower_paths); + if (err) + goto out_release; + new_branches--; + continue; + } + if (!strcmp("mode", optname)) { + err = do_remount_mode_option(optarg, new_branches, + tmp_data, + tmp_lower_paths); + if (err) + goto out_release; + continue; + } + + /* + * When you use "mount -o remount,ro", mount(8) will + * reportedly pass the original dirs= string from + * /proc/mounts. So for now, we have to ignore dirs= and + * not consider it an error, unless we want to allow users + * to pass dirs= in remount. Note that to allow the VFS to + * actually process the ro/rw remount options, we have to + * return 0 from this function. + */ + if (!strcmp("dirs", optname)) { + printk(KERN_WARNING + "unionfs: remount ignoring option \"%s\"\n", + optname); + continue; + } + + err = -EINVAL; + printk(KERN_ERR + "unionfs: unrecognized option \"%s\"\n", optname); + goto out_release; + } + +out_no_change: + + /****************************************************************** + * WE'RE ALMOST DONE: check if leftmost branch might be read-only, + * see if we need to allocate a small-sized new vector, copy the + * vectors to their correct place, release the refcnt of the older + * ones, and return. Also handle invalidating any pages that will + * have to be re-read. + *******************************************************************/ + + if (!(tmp_data[0].branchperms & MAY_WRITE)) { + printk(KERN_ERR "unionfs: leftmost branch cannot be read-only " + "(use \"remount,ro\" to create a read-only union)\n"); + err = -EINVAL; + goto out_release; + } + + /* (re)allocate space for new pointers to lower dentry */ + size = new_branches * sizeof(struct unionfs_data); + new_data = krealloc(tmp_data, size, GFP_KERNEL); + if (unlikely(!new_data)) { + err = -ENOMEM; + goto out_release; + } + + /* allocate space for new pointers to lower paths */ + size = new_branches * sizeof(struct path); + new_lower_paths = krealloc(tmp_lower_paths, size, GFP_KERNEL); + if (unlikely(!new_lower_paths)) { + err = -ENOMEM; + goto out_release; + } + + /* allocate space for new pointers to lower inodes */ + new_lower_inodes = kcalloc(new_branches, + sizeof(struct inode *), GFP_KERNEL); + if (unlikely(!new_lower_inodes)) { + err = -ENOMEM; + goto out_release; + } + + /* + * OK, just before we actually put the new set of branches in place, + * we need to ensure that our own f/s has no dirty objects left. + * Luckily, do_remount_sb() already calls shrink_dcache_sb(sb) and + * fsync_super(sb), taking care of dentries, inodes, and dirty + * pages. So all that's left is for us to invalidate any leftover + * (non-dirty) pages to ensure that they will be re-read from the + * new lower branches (and to support mmap). + */ + + /* + * Once we finish the remounting successfully, our superblock + * generation number will have increased. This will be detected by + * our dentry-revalidation code upon subsequent f/s operations + * through unionfs. The revalidation code will rebuild the union of + * lower inodes for a given unionfs inode and invalidate any pages + * of such "stale" inodes (by calling our purge_inode_data + * function). This revalidation will happen lazily and + * incrementally, as users perform operations on cached inodes. We + * would like to encourage this revalidation to happen sooner if + * possible, so we like to try to invalidate as many other pages in + * our superblock as we can. We used to call drop_pagecache_sb() or + * a variant thereof, but either method was racy (drop_caches alone + * is known to be racy). So now we let the revalidation happen on a + * per file basis in ->d_revalidate. + */ + + /* grab new lower super references; release old ones */ + for (i = 0; i < new_branches; i++) + atomic_inc(&new_data[i].sb->s_active); + for (i = 0; i < sbmax(sb); i++) + atomic_dec(&UNIONFS_SB(sb)->data[i].sb->s_active); + + /* copy new vectors into their correct place */ + tmp_data = UNIONFS_SB(sb)->data; + UNIONFS_SB(sb)->data = new_data; + new_data = NULL; /* so don't free good pointers below */ + tmp_lower_paths = UNIONFS_D(sb->s_root)->lower_paths; + UNIONFS_D(sb->s_root)->lower_paths = new_lower_paths; + new_lower_paths = NULL; /* so don't free good pointers below */ + + /* update our unionfs_sb_info and root dentry index of last branch */ + i = sbmax(sb); /* save no. of branches to release at end */ + sbend(sb) = new_branches - 1; + dbend(sb->s_root) = new_branches - 1; + old_ibstart = ibstart(sb->s_root->d_inode); + old_ibend = ibend(sb->s_root->d_inode); + ibend(sb->s_root->d_inode) = new_branches - 1; + UNIONFS_D(sb->s_root)->bcount = new_branches; + new_branches = i; /* no. of branches to release below */ + + /* + * Update lower inodes: 3 steps + * 1. grab ref on all new lower inodes + */ + for (i = dbstart(sb->s_root); i <= dbend(sb->s_root); i++) { + struct dentry *lower_dentry = + unionfs_lower_dentry_idx(sb->s_root, i); + igrab(lower_dentry->d_inode); + new_lower_inodes[i] = lower_dentry->d_inode; + } + /* 2. release reference on all older lower inodes */ + iput_lowers(sb->s_root->d_inode, old_ibstart, old_ibend, true); + /* 3. update root dentry's inode to new lower_inodes array */ + UNIONFS_I(sb->s_root->d_inode)->lower_inodes = new_lower_inodes; + new_lower_inodes = NULL; + + /* maxbytes may have changed */ + sb->s_maxbytes = unionfs_lower_super_idx(sb, 0)->s_maxbytes; + /* update high branch ID */ + sbhbid(sb) = new_high_branch_id; + + /* update our sb->generation for revalidating objects */ + i = atomic_inc_return(&UNIONFS_SB(sb)->generation); + atomic_set(&UNIONFS_D(sb->s_root)->generation, i); + atomic_set(&UNIONFS_I(sb->s_root->d_inode)->generation, i); + if (!(*flags & MS_SILENT)) + pr_info("unionfs: %s: new generation number %d\n", + UNIONFS_SB(sb)->dev_name, i); + /* finally, update the root dentry's times */ + unionfs_copy_attr_times(sb->s_root->d_inode); + err = 0; /* reset to success */ + + /* + * The code above falls through to the next label, and releases the + * refcnts of the older ones (stored in tmp_*): if we fell through + * here, it means success. However, if we jump directly to this + * label from any error above, then an error occurred after we + * grabbed various refcnts, and so we have to release the + * temporarily constructed structures. + */ +out_release: + /* no need to cleanup/release anything in tmp_data */ + if (tmp_lower_paths) + for (i = 0; i < new_branches; i++) + path_put(&tmp_lower_paths[i]); +out_free: + kfree(tmp_lower_paths); + kfree(tmp_data); + kfree(new_lower_paths); + kfree(new_data); + kfree(new_lower_inodes); +out_error: + unionfs_check_dentry(sb->s_root); + unionfs_write_unlock(sb); + return err; +} + +/* + * Called by iput() when the inode reference count reached zero + * and the inode is not hashed anywhere. Used to clear anything + * that needs to be, before the inode is completely destroyed and put + * on the inode free list. + * + * No need to lock sb info's rwsem. + */ +static void unionfs_evict_inode(struct inode *inode) +{ + int bindex, bstart, bend; + struct inode *lower_inode; + struct list_head *pos, *n; + struct unionfs_dir_state *rdstate; + + truncate_inode_pages(&inode->i_data, 0); + end_writeback(inode); + + list_for_each_safe(pos, n, &UNIONFS_I(inode)->readdircache) { + rdstate = list_entry(pos, struct unionfs_dir_state, cache); + list_del(&rdstate->cache); + free_rdstate(rdstate); + } + + /* + * Decrement a reference to a lower_inode, which was incremented + * by our read_inode when it was created initially. + */ + bstart = ibstart(inode); + bend = ibend(inode); + if (bstart >= 0) { + for (bindex = bstart; bindex <= bend; bindex++) { + lower_inode = unionfs_lower_inode_idx(inode, bindex); + if (!lower_inode) + continue; + unionfs_set_lower_inode_idx(inode, bindex, NULL); + /* see Documentation/filesystems/unionfs/issues.txt */ + lockdep_off(); + iput(lower_inode); + lockdep_on(); + } + } + + kfree(UNIONFS_I(inode)->lower_inodes); + UNIONFS_I(inode)->lower_inodes = NULL; +} + +static struct inode *unionfs_alloc_inode(struct super_block *sb) +{ + struct unionfs_inode_info *i; + + i = kmem_cache_alloc(unionfs_inode_cachep, GFP_KERNEL); + if (unlikely(!i)) + return NULL; + + /* memset everything up to the inode to 0 */ + memset(i, 0, offsetof(struct unionfs_inode_info, vfs_inode)); + + i->vfs_inode.i_version = 1; + return &i->vfs_inode; +} + +static void unionfs_destroy_inode(struct inode *inode) +{ + kmem_cache_free(unionfs_inode_cachep, UNIONFS_I(inode)); +} + +/* unionfs inode cache constructor */ +static void init_once(void *obj) +{ + struct unionfs_inode_info *i = obj; + + inode_init_once(&i->vfs_inode); +} + +int unionfs_init_inode_cache(void) +{ + int err = 0; + + unionfs_inode_cachep = + kmem_cache_create("unionfs_inode_cache", + sizeof(struct unionfs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT, init_once); + if (unlikely(!unionfs_inode_cachep)) + err = -ENOMEM; + return err; +} + +/* unionfs inode cache destructor */ +void unionfs_destroy_inode_cache(void) +{ + if (unionfs_inode_cachep) + kmem_cache_destroy(unionfs_inode_cachep); +} + +/* + * Called when we have a dirty inode, right here we only throw out + * parts of our readdir list that are too old. + * + * No need to grab sb info's rwsem. + */ +static int unionfs_write_inode(struct inode *inode, + struct writeback_control *wbc) +{ + struct list_head *pos, *n; + struct unionfs_dir_state *rdstate; + + spin_lock(&UNIONFS_I(inode)->rdlock); + list_for_each_safe(pos, n, &UNIONFS_I(inode)->readdircache) { + rdstate = list_entry(pos, struct unionfs_dir_state, cache); + /* We keep this list in LRU order. */ + if ((rdstate->access + RDCACHE_JIFFIES) > jiffies) + break; + UNIONFS_I(inode)->rdcount--; + list_del(&rdstate->cache); + free_rdstate(rdstate); + } + spin_unlock(&UNIONFS_I(inode)->rdlock); + + return 0; +} + +/* + * Used only in nfs, to kill any pending RPC tasks, so that subsequent + * code can actually succeed and won't leave tasks that need handling. + */ +static void unionfs_umount_begin(struct super_block *sb) +{ + struct super_block *lower_sb; + int bindex, bstart, bend; + + unionfs_read_lock(sb, UNIONFS_SMUTEX_CHILD); + + bstart = sbstart(sb); + bend = sbend(sb); + for (bindex = bstart; bindex <= bend; bindex++) { + lower_sb = unionfs_lower_super_idx(sb, bindex); + + if (lower_sb && lower_sb->s_op && + lower_sb->s_op->umount_begin) + lower_sb->s_op->umount_begin(lower_sb); + } + + unionfs_read_unlock(sb); +} + +static int unionfs_show_options(struct seq_file *m, struct vfsmount *mnt) +{ + struct super_block *sb = mnt->mnt_sb; + int ret = 0; + char *tmp_page; + char *path; + int bindex, bstart, bend; + int perms; + + unionfs_read_lock(sb, UNIONFS_SMUTEX_CHILD); + + unionfs_lock_dentry(sb->s_root, UNIONFS_DMUTEX_CHILD); + + tmp_page = (char *) __get_free_page(GFP_KERNEL); + if (unlikely(!tmp_page)) { + ret = -ENOMEM; + goto out; + } + + bstart = sbstart(sb); + bend = sbend(sb); + + seq_printf(m, ",dirs="); + for (bindex = bstart; bindex <= bend; bindex++) { + struct path p; + p.dentry = unionfs_lower_dentry_idx(sb->s_root, bindex); + p.mnt = unionfs_lower_mnt_idx(sb->s_root, bindex); + path = d_path(&p, tmp_page, PAGE_SIZE); + if (IS_ERR(path)) { + ret = PTR_ERR(path); + goto out; + } + + perms = branchperms(sb, bindex); + + seq_printf(m, "%s=%s", path, + perms & MAY_WRITE ? "rw" : "ro"); + if (bindex != bend) + seq_printf(m, ":"); + } + +out: + free_page((unsigned long) tmp_page); + + unionfs_unlock_dentry(sb->s_root); + + unionfs_read_unlock(sb); + + return ret; +} + +struct super_operations unionfs_sops = { + .put_super = unionfs_put_super, + .statfs = unionfs_statfs, + .remount_fs = unionfs_remount_fs, + .evict_inode = unionfs_evict_inode, + .umount_begin = unionfs_umount_begin, + .show_options = unionfs_show_options, + .write_inode = unionfs_write_inode, + .alloc_inode = unionfs_alloc_inode, + .destroy_inode = unionfs_destroy_inode, +}; diff --git a/fs/unionfs/union.h b/fs/unionfs/union.h new file mode 100644 index 0000000..d49c834 --- /dev/null +++ b/fs/unionfs/union.h @@ -0,0 +1,669 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _UNION_H_ +#define _UNION_H_ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include + +/* the file system name */ +#define UNIONFS_NAME "unionfs" + +/* unionfs root inode number */ +#define UNIONFS_ROOT_INO 1 + +/* number of times we try to get a unique temporary file name */ +#define GET_TMPNAM_MAX_RETRY 5 + +/* maximum number of branches we support, to avoid memory blowup */ +#define UNIONFS_MAX_BRANCHES 128 + +/* minimum time (seconds) required for time-based cache-coherency */ +#define UNIONFS_MIN_CC_TIME 3 + +/* Operations vectors defined in specific files. */ +extern struct file_operations unionfs_main_fops; +extern struct file_operations unionfs_dir_fops; +extern struct inode_operations unionfs_main_iops; +extern struct inode_operations unionfs_dir_iops; +extern struct inode_operations unionfs_symlink_iops; +extern struct super_operations unionfs_sops; +extern struct dentry_operations unionfs_dops; +extern struct address_space_operations unionfs_aops, unionfs_dummy_aops; +extern struct vm_operations_struct unionfs_vm_ops; + +/* How long should an entry be allowed to persist */ +#define RDCACHE_JIFFIES (5*HZ) + +/* compatibility with Real-Time patches */ +#ifdef CONFIG_PREEMPT_RT +# define unionfs_rw_semaphore compat_rw_semaphore +#else /* not CONFIG_PREEMPT_RT */ +# define unionfs_rw_semaphore rw_semaphore +#endif /* not CONFIG_PREEMPT_RT */ + +/* file private data. */ +struct unionfs_file_info { + int bstart; + int bend; + atomic_t generation; + + struct unionfs_dir_state *rdstate; + struct file **lower_files; + int *saved_branch_ids; /* IDs of branches when file was opened */ + const struct vm_operations_struct *lower_vm_ops; + bool wrote_to_file; /* for delayed copyup */ +}; + +/* unionfs inode data in memory */ +struct unionfs_inode_info { + int bstart; + int bend; + atomic_t generation; + /* Stuff for readdir over NFS. */ + spinlock_t rdlock; + struct list_head readdircache; + int rdcount; + int hashsize; + int cookie; + + /* The lower inodes */ + struct inode **lower_inodes; + + struct inode vfs_inode; +}; + +/* unionfs dentry data in memory */ +struct unionfs_dentry_info { + /* + * The semaphore is used to lock the dentry as soon as we get into a + * unionfs function from the VFS. Our lock ordering is that children + * go before their parents. + */ + struct mutex lock; + int bstart; + int bend; + int bopaque; + int bcount; + atomic_t generation; + struct path *lower_paths; +}; + +/* These are the pointers to our various objects. */ +struct unionfs_data { + struct super_block *sb; /* lower super_block */ + atomic_t open_files; /* number of open files on branch */ + int branchperms; + int branch_id; /* unique branch ID at re/mount time */ +}; + +/* unionfs super-block data in memory */ +struct unionfs_sb_info { + int bend; + + atomic_t generation; + + /* + * This rwsem is used to make sure that a branch management + * operation... + * 1) will not begin before all currently in-flight operations + * complete. + * 2) any new operations do not execute until the currently + * running branch management operation completes. + * + * The write_lock_owner records the PID of the task which grabbed + * the rw_sem for writing. If the same task also tries to grab the + * read lock, we allow it. This prevents a self-deadlock when + * branch-management is used on a pivot_root'ed union, because we + * have to ->lookup paths which belong to the same union. + */ + struct unionfs_rw_semaphore rwsem; + pid_t write_lock_owner; /* PID of rw_sem owner (write lock) */ + int high_branch_id; /* last unique branch ID given */ + char *dev_name; /* to identify different unions in pr_debug */ + struct unionfs_data *data; +}; + +/* + * structure for making the linked list of entries by readdir on left branch + * to compare with entries on right branch + */ +struct filldir_node { + struct list_head file_list; /* list for directory entries */ + char *name; /* name entry */ + int hash; /* name hash */ + int namelen; /* name len since name is not 0 terminated */ + + /* + * we can check for duplicate whiteouts and files in the same branch + * in order to return -EIO. + */ + int bindex; + + /* is this a whiteout entry? */ + int whiteout; + + /* Inline name, so we don't need to separately kmalloc small ones */ + char iname[DNAME_INLINE_LEN_MIN]; +}; + +/* Directory hash table. */ +struct unionfs_dir_state { + unsigned int cookie; /* the cookie, based off of rdversion */ + unsigned int offset; /* The entry we have returned. */ + int bindex; + loff_t dirpos; /* offset within the lower level directory */ + int size; /* How big is the hash table? */ + int hashentries; /* How many entries have been inserted? */ + unsigned long access; + + /* This cache list is used when the inode keeps us around. */ + struct list_head cache; + struct list_head list[0]; +}; + +/* externs needed for fanout.h or sioq.h */ +extern int unionfs_get_nlinks(const struct inode *inode); +extern void unionfs_copy_attr_times(struct inode *upper); +extern void unionfs_copy_attr_all(struct inode *dest, const struct inode *src); + +/* include miscellaneous macros */ +#include "fanout.h" +#include "sioq.h" + +/* externs for cache creation/deletion routines */ +extern void unionfs_destroy_filldir_cache(void); +extern int unionfs_init_filldir_cache(void); +extern int unionfs_init_inode_cache(void); +extern void unionfs_destroy_inode_cache(void); +extern int unionfs_init_dentry_cache(void); +extern void unionfs_destroy_dentry_cache(void); + +/* Initialize and free readdir-specific state. */ +extern int init_rdstate(struct file *file); +extern struct unionfs_dir_state *alloc_rdstate(struct inode *inode, + int bindex); +extern struct unionfs_dir_state *find_rdstate(struct inode *inode, + loff_t fpos); +extern void free_rdstate(struct unionfs_dir_state *state); +extern int add_filldir_node(struct unionfs_dir_state *rdstate, + const char *name, int namelen, int bindex, + int whiteout); +extern struct filldir_node *find_filldir_node(struct unionfs_dir_state *rdstate, + const char *name, int namelen, + int is_whiteout); + +extern struct dentry **alloc_new_dentries(int objs); +extern struct unionfs_data *alloc_new_data(int objs); + +/* We can only use 32-bits of offset for rdstate --- blech! */ +#define DIREOF (0xfffff) +#define RDOFFBITS 20 /* This is the number of bits in DIREOF. */ +#define MAXRDCOOKIE (0xfff) +/* Turn an rdstate into an offset. */ +static inline off_t rdstate2offset(struct unionfs_dir_state *buf) +{ + off_t tmp; + + tmp = ((buf->cookie & MAXRDCOOKIE) << RDOFFBITS) + | (buf->offset & DIREOF); + return tmp; +} + +/* Macros for locking a super_block. */ +enum unionfs_super_lock_class { + UNIONFS_SMUTEX_NORMAL, + UNIONFS_SMUTEX_PARENT, /* when locking on behalf of file */ + UNIONFS_SMUTEX_CHILD, /* when locking on behalf of dentry */ +}; +static inline void unionfs_read_lock(struct super_block *sb, int subclass) +{ + if (UNIONFS_SB(sb)->write_lock_owner && + UNIONFS_SB(sb)->write_lock_owner == current->pid) + return; + down_read_nested(&UNIONFS_SB(sb)->rwsem, subclass); +} +static inline void unionfs_read_unlock(struct super_block *sb) +{ + if (UNIONFS_SB(sb)->write_lock_owner && + UNIONFS_SB(sb)->write_lock_owner == current->pid) + return; + up_read(&UNIONFS_SB(sb)->rwsem); +} +static inline void unionfs_write_lock(struct super_block *sb) +{ + down_write(&UNIONFS_SB(sb)->rwsem); + UNIONFS_SB(sb)->write_lock_owner = current->pid; +} +static inline void unionfs_write_unlock(struct super_block *sb) +{ + up_write(&UNIONFS_SB(sb)->rwsem); + UNIONFS_SB(sb)->write_lock_owner = 0; +} + +static inline void unionfs_double_lock_dentry(struct dentry *d1, + struct dentry *d2) +{ + BUG_ON(d1 == d2); + if (d1 < d2) { + unionfs_lock_dentry(d1, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(d2, UNIONFS_DMUTEX_CHILD); + } else { + unionfs_lock_dentry(d2, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(d1, UNIONFS_DMUTEX_CHILD); + } +} + +static inline void unionfs_double_unlock_dentry(struct dentry *d1, + struct dentry *d2) +{ + BUG_ON(d1 == d2); + if (d1 < d2) { /* unlock in reverse order than double_lock_dentry */ + unionfs_unlock_dentry(d1); + unionfs_unlock_dentry(d2); + } else { + unionfs_unlock_dentry(d2); + unionfs_unlock_dentry(d1); + } +} + +static inline void unionfs_double_lock_parents(struct dentry *p1, + struct dentry *p2) +{ + if (p1 == p2) { + unionfs_lock_dentry(p1, UNIONFS_DMUTEX_REVAL_PARENT); + return; + } + if (p1 < p2) { + unionfs_lock_dentry(p1, UNIONFS_DMUTEX_REVAL_PARENT); + unionfs_lock_dentry(p2, UNIONFS_DMUTEX_REVAL_CHILD); + } else { + unionfs_lock_dentry(p2, UNIONFS_DMUTEX_REVAL_PARENT); + unionfs_lock_dentry(p1, UNIONFS_DMUTEX_REVAL_CHILD); + } +} + +static inline void unionfs_double_unlock_parents(struct dentry *p1, + struct dentry *p2) +{ + if (p1 == p2) { + unionfs_unlock_dentry(p1); + return; + } + if (p1 < p2) { /* unlock in reverse order of double_lock_parents */ + unionfs_unlock_dentry(p1); + unionfs_unlock_dentry(p2); + } else { + unionfs_unlock_dentry(p2); + unionfs_unlock_dentry(p1); + } +} + +extern int new_dentry_private_data(struct dentry *dentry, int subclass); +extern int realloc_dentry_private_data(struct dentry *dentry); +extern void free_dentry_private_data(struct dentry *dentry); +extern void update_bstart(struct dentry *dentry); +extern int init_lower_nd(struct nameidata *nd, unsigned int flags); +extern void release_lower_nd(struct nameidata *nd, int err); + +/* + * EXTERNALS: + */ + +/* replicates the directory structure up to given dentry in given branch */ +extern struct dentry *create_parents(struct inode *dir, struct dentry *dentry, + const char *name, int bindex); + +/* partial lookup */ +extern int unionfs_partial_lookup(struct dentry *dentry, + struct dentry *parent); +extern struct dentry *unionfs_lookup_full(struct dentry *dentry, + struct dentry *parent, + int lookupmode); + +/* copies a file from dbstart to newbindex branch */ +extern int copyup_file(struct inode *dir, struct file *file, int bstart, + int newbindex, loff_t size); +extern int copyup_named_file(struct inode *dir, struct file *file, + char *name, int bstart, int new_bindex, + loff_t len); +/* copies a dentry from dbstart to newbindex branch */ +extern int copyup_dentry(struct inode *dir, struct dentry *dentry, + int bstart, int new_bindex, const char *name, + int namelen, struct file **copyup_file, loff_t len); +/* helper functions for post-copyup actions */ +extern void unionfs_postcopyup_setmnt(struct dentry *dentry); +extern void unionfs_postcopyup_release(struct dentry *dentry); + +/* Is this directory empty: 0 if it is empty, -ENOTEMPTY if not. */ +extern int check_empty(struct dentry *dentry, struct dentry *parent, + struct unionfs_dir_state **namelist); +/* whiteout and opaque directory helpers */ +extern char *alloc_whname(const char *name, int len); +extern bool is_whiteout_name(char **namep, int *namelenp); +extern bool is_validname(const char *name); +extern struct dentry *lookup_whiteout(const char *name, + struct dentry *lower_parent); +extern struct dentry *find_first_whiteout(struct dentry *dentry); +extern int unlink_whiteout(struct dentry *wh_dentry); +extern int check_unlink_whiteout(struct dentry *dentry, + struct dentry *lower_dentry, int bindex); +extern int create_whiteout(struct dentry *dentry, int start); +extern int delete_whiteouts(struct dentry *dentry, int bindex, + struct unionfs_dir_state *namelist); +extern int is_opaque_dir(struct dentry *dentry, int bindex); +extern int make_dir_opaque(struct dentry *dir, int bindex); +extern void unionfs_set_max_namelen(long *namelen); + +extern void unionfs_reinterpose(struct dentry *this_dentry); +extern struct super_block *unionfs_duplicate_super(struct super_block *sb); + +/* Locking functions. */ +extern int unionfs_setlk(struct file *file, int cmd, struct file_lock *fl); +extern int unionfs_getlk(struct file *file, struct file_lock *fl); + +/* Common file operations. */ +extern int unionfs_file_revalidate(struct file *file, struct dentry *parent, + bool willwrite); +extern int unionfs_open(struct inode *inode, struct file *file); +extern int unionfs_file_release(struct inode *inode, struct file *file); +extern int unionfs_flush(struct file *file, fl_owner_t id); +extern long unionfs_ioctl(struct file *file, unsigned int cmd, + unsigned long arg); +extern int unionfs_fsync(struct file *file, int datasync); +extern int unionfs_fasync(int fd, struct file *file, int flag); + +/* Inode operations */ +extern struct inode *unionfs_iget(struct super_block *sb, unsigned long ino); +extern int unionfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); +extern int unionfs_unlink(struct inode *dir, struct dentry *dentry); +extern int unionfs_rmdir(struct inode *dir, struct dentry *dentry); + +extern bool __unionfs_d_revalidate(struct dentry *dentry, + struct dentry *parent, bool willwrite); +extern bool is_negative_lower(const struct dentry *dentry); +extern bool is_newer_lower(const struct dentry *dentry); +extern void purge_sb_data(struct super_block *sb); + +/* The values for unionfs_interpose's flag. */ +#define INTERPOSE_DEFAULT 0 +#define INTERPOSE_LOOKUP 1 +#define INTERPOSE_REVAL 2 +#define INTERPOSE_REVAL_NEG 3 +#define INTERPOSE_PARTIAL 4 + +extern struct dentry *unionfs_interpose(struct dentry *this_dentry, + struct super_block *sb, int flag); + +#ifdef CONFIG_UNION_FS_XATTR +/* Extended attribute functions. */ +extern void *unionfs_xattr_alloc(size_t size, size_t limit); +static inline void unionfs_xattr_kfree(const void *p) +{ + kfree(p); +} +extern ssize_t unionfs_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size); +extern int unionfs_removexattr(struct dentry *dentry, const char *name); +extern ssize_t unionfs_listxattr(struct dentry *dentry, char *list, + size_t size); +extern int unionfs_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags); +#endif /* CONFIG_UNION_FS_XATTR */ + +/* The root directory is unhashed, but isn't deleted. */ +static inline int d_deleted(struct dentry *d) +{ + return d_unhashed(d) && (d != d->d_sb->s_root); +} + +/* unionfs_permission, check if we should bypass error to facilitate copyup */ +#define IS_COPYUP_ERR(err) ((err) == -EROFS) + +/* unionfs_open, check if we need to copyup the file */ +#define OPEN_WRITE_FLAGS (O_WRONLY | O_RDWR | O_APPEND) +#define IS_WRITE_FLAG(flag) ((flag) & OPEN_WRITE_FLAGS) + +static inline int branchperms(const struct super_block *sb, int index) +{ + BUG_ON(index < 0); + return UNIONFS_SB(sb)->data[index].branchperms; +} + +static inline int set_branchperms(struct super_block *sb, int index, int perms) +{ + BUG_ON(index < 0); + UNIONFS_SB(sb)->data[index].branchperms = perms; + return perms; +} + +/* check if readonly lower inode, but possibly unlinked (no inode->i_sb) */ +static inline int __is_rdonly(const struct inode *inode) +{ + /* if unlinked, can't be readonly (?) */ + if (!inode->i_sb) + return 0; + return IS_RDONLY(inode); + +} +/* Is this file on a read-only branch? */ +static inline int is_robranch_super(const struct super_block *sb, int index) +{ + int ret; + + ret = (!(branchperms(sb, index) & MAY_WRITE)) ? -EROFS : 0; + return ret; +} + +/* Is this file on a read-only branch? */ +static inline int is_robranch_idx(const struct dentry *dentry, int index) +{ + struct super_block *lower_sb; + + BUG_ON(index < 0); + + if (!(branchperms(dentry->d_sb, index) & MAY_WRITE)) + return -EROFS; + + lower_sb = unionfs_lower_super_idx(dentry->d_sb, index); + BUG_ON(lower_sb == NULL); + /* + * test sb flags directly, not IS_RDONLY(lower_inode) because the + * lower_dentry could be a negative. + */ + if (lower_sb->s_flags & MS_RDONLY) + return -EROFS; + + return 0; +} + +static inline int is_robranch(const struct dentry *dentry) +{ + int index; + + index = UNIONFS_D(dentry)->bstart; + BUG_ON(index < 0); + + return is_robranch_idx(dentry, index); +} + +/* + * EXTERNALS: + */ +extern int check_branch(struct nameidata *nd); +extern int parse_branch_mode(const char *name, int *perms); + +/* locking helpers */ +static inline struct dentry *lock_parent(struct dentry *dentry) +{ + struct dentry *dir = dget_parent(dentry); + mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT); + return dir; +} +static inline struct dentry *lock_parent_wh(struct dentry *dentry) +{ + struct dentry *dir = dget_parent(dentry); + + mutex_lock_nested(&dir->d_inode->i_mutex, UNIONFS_DMUTEX_WHITEOUT); + return dir; +} + +static inline void unlock_dir(struct dentry *dir) +{ + mutex_unlock(&dir->d_inode->i_mutex); + dput(dir); +} + +/* lock base inode mutex before calling lookup_one_len */ +static inline struct dentry *lookup_lck_len(const char *name, + struct dentry *base, int len) +{ + struct dentry *d; + mutex_lock(&base->d_inode->i_mutex); + d = lookup_one_len(name, base, len); + mutex_unlock(&base->d_inode->i_mutex); + return d; +} + +static inline struct vfsmount *unionfs_mntget(struct dentry *dentry, + int bindex) +{ + struct vfsmount *mnt; + + BUG_ON(!dentry || bindex < 0); + + mnt = mntget(unionfs_lower_mnt_idx(dentry, bindex)); +#ifdef CONFIG_UNION_FS_DEBUG + if (!mnt) + pr_debug("unionfs: mntget: mnt=%p bindex=%d\n", + mnt, bindex); +#endif /* CONFIG_UNION_FS_DEBUG */ + + return mnt; +} + +static inline void unionfs_mntput(struct dentry *dentry, int bindex) +{ + struct vfsmount *mnt; + + if (!dentry && bindex < 0) + return; + BUG_ON(!dentry || bindex < 0); + + mnt = unionfs_lower_mnt_idx(dentry, bindex); +#ifdef CONFIG_UNION_FS_DEBUG + /* + * Directories can have NULL lower objects in between start/end, but + * NOT if at the start/end range. We cannot verify that this dentry + * is a type=DIR, because it may already be a negative dentry. But + * if dbstart is greater than dbend, we know that this couldn't have + * been a regular file: it had to have been a directory. + */ + if (!mnt && !(bindex > dbstart(dentry) && bindex < dbend(dentry))) + pr_debug("unionfs: mntput: mnt=%p bindex=%d\n", mnt, bindex); +#endif /* CONFIG_UNION_FS_DEBUG */ + mntput(mnt); +} + +#ifdef CONFIG_UNION_FS_DEBUG + +/* useful for tracking code reachability */ +#define UDBG pr_debug("DBG:%s:%s:%d\n", __FILE__, __func__, __LINE__) + +#define unionfs_check_inode(i) __unionfs_check_inode((i), \ + __FILE__, __func__, __LINE__) +#define unionfs_check_dentry(d) __unionfs_check_dentry((d), \ + __FILE__, __func__, __LINE__) +#define unionfs_check_file(f) __unionfs_check_file((f), \ + __FILE__, __func__, __LINE__) +#define unionfs_check_nd(n) __unionfs_check_nd((n), \ + __FILE__, __func__, __LINE__) +#define show_branch_counts(sb) __show_branch_counts((sb), \ + __FILE__, __func__, __LINE__) +#define show_inode_times(i) __show_inode_times((i), \ + __FILE__, __func__, __LINE__) +#define show_dinode_times(d) __show_dinode_times((d), \ + __FILE__, __func__, __LINE__) +#define show_inode_counts(i) __show_inode_counts((i), \ + __FILE__, __func__, __LINE__) + +extern void __unionfs_check_inode(const struct inode *inode, const char *fname, + const char *fxn, int line); +extern void __unionfs_check_dentry(const struct dentry *dentry, + const char *fname, const char *fxn, + int line); +extern void __unionfs_check_file(const struct file *file, + const char *fname, const char *fxn, int line); +extern void __unionfs_check_nd(const struct nameidata *nd, + const char *fname, const char *fxn, int line); +extern void __show_branch_counts(const struct super_block *sb, + const char *file, const char *fxn, int line); +extern void __show_inode_times(const struct inode *inode, + const char *file, const char *fxn, int line); +extern void __show_dinode_times(const struct dentry *dentry, + const char *file, const char *fxn, int line); +extern void __show_inode_counts(const struct inode *inode, + const char *file, const char *fxn, int line); + +#else /* not CONFIG_UNION_FS_DEBUG */ + +/* we leave useful hooks for these check functions throughout the code */ +#define unionfs_check_inode(i) do { } while (0) +#define unionfs_check_dentry(d) do { } while (0) +#define unionfs_check_file(f) do { } while (0) +#define unionfs_check_nd(n) do { } while (0) +#define show_branch_counts(sb) do { } while (0) +#define show_inode_times(i) do { } while (0) +#define show_dinode_times(d) do { } while (0) +#define show_inode_counts(i) do { } while (0) + +#endif /* not CONFIG_UNION_FS_DEBUG */ + +#endif /* not _UNION_H_ */ diff --git a/fs/unionfs/unlink.c b/fs/unionfs/unlink.c new file mode 100644 index 0000000..542c513 --- /dev/null +++ b/fs/unionfs/unlink.c @@ -0,0 +1,278 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* + * Helper function for Unionfs's unlink operation. + * + * The main goal of this function is to optimize the unlinking of non-dir + * objects in unionfs by deleting all possible lower inode objects from the + * underlying branches having same dentry name as the non-dir dentry on + * which this unlink operation is called. This way we delete as many lower + * inodes as possible, and save space. Whiteouts need to be created in + * branch0 only if unlinking fails on any of the lower branch other than + * branch0, or if a lower branch is marked read-only. + * + * Also, while unlinking a file, if we encounter any dir type entry in any + * intermediate branch, then we remove the directory by calling vfs_rmdir. + * The following special cases are also handled: + + * (1) If an error occurs in branch0 during vfs_unlink, then we return + * appropriate error. + * + * (2) If we get an error during unlink in any of other lower branch other + * than branch0, then we create a whiteout in branch0. + * + * (3) If a whiteout already exists in any intermediate branch, we delete + * all possible inodes only up to that branch (this is an "opaqueness" + * as as per Documentation/filesystems/unionfs/concepts.txt). + * + */ +static int unionfs_unlink_whiteout(struct inode *dir, struct dentry *dentry, + struct dentry *parent) +{ + struct dentry *lower_dentry; + struct dentry *lower_dir_dentry; + int bindex; + int err = 0; + + err = unionfs_partial_lookup(dentry, parent); + if (err) + goto out; + + /* trying to unlink all possible valid instances */ + for (bindex = dbstart(dentry); bindex <= dbend(dentry); bindex++) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + if (!lower_dentry || !lower_dentry->d_inode) + continue; + + lower_dir_dentry = lock_parent(lower_dentry); + + /* avoid destroying the lower inode if the object is in use */ + dget(lower_dentry); + err = is_robranch_super(dentry->d_sb, bindex); + if (!err) { + /* see Documentation/filesystems/unionfs/issues.txt */ + lockdep_off(); + if (!S_ISDIR(lower_dentry->d_inode->i_mode)) + err = vfs_unlink(lower_dir_dentry->d_inode, + lower_dentry); + else + err = vfs_rmdir(lower_dir_dentry->d_inode, + lower_dentry); + lockdep_on(); + } + + /* if lower object deletion succeeds, update inode's times */ + if (!err) + unionfs_copy_attr_times(dentry->d_inode); + dput(lower_dentry); + fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode); + unlock_dir(lower_dir_dentry); + + if (err) + break; + } + + /* + * Create the whiteout in branch 0 (highest priority) only if (a) + * there was an error in any intermediate branch other than branch 0 + * due to failure of vfs_unlink/vfs_rmdir or (b) a branch marked or + * mounted read-only. + */ + if (err) { + if ((bindex == 0) || + ((bindex == dbstart(dentry)) && + (!IS_COPYUP_ERR(err)))) + goto out; + else { + if (!IS_COPYUP_ERR(err)) + pr_debug("unionfs: lower object deletion " + "failed in branch:%d\n", bindex); + err = create_whiteout(dentry, sbstart(dentry->d_sb)); + } + } + +out: + if (!err) + inode_dec_link_count(dentry->d_inode); + + /* We don't want to leave negative leftover dentries for revalidate. */ + if (!err && (dbopaque(dentry) != -1)) + update_bstart(dentry); + + return err; +} + +int unionfs_unlink(struct inode *dir, struct dentry *dentry) +{ + int err = 0; + struct inode *inode = dentry->d_inode; + struct dentry *parent; + int valid; + + BUG_ON(S_ISDIR(inode->i_mode)); + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out; + } + unionfs_check_dentry(dentry); + + err = unionfs_unlink_whiteout(dir, dentry, parent); + /* call d_drop so the system "forgets" about us */ + if (!err) { + unionfs_postcopyup_release(dentry); + unionfs_postcopyup_setmnt(parent); + if (inode->i_nlink == 0) /* drop lower inodes */ + iput_lowers_all(inode, false); + d_drop(dentry); + /* + * if unlink/whiteout succeeded, parent dir mtime has + * changed + */ + unionfs_copy_attr_times(dir); + } + +out: + if (!err) { + unionfs_check_dentry(dentry); + unionfs_check_inode(dir); + } + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +static int unionfs_rmdir_first(struct inode *dir, struct dentry *dentry, + struct unionfs_dir_state *namelist) +{ + int err; + struct dentry *lower_dentry; + struct dentry *lower_dir_dentry = NULL; + + /* Here we need to remove whiteout entries. */ + err = delete_whiteouts(dentry, dbstart(dentry), namelist); + if (err) + goto out; + + lower_dentry = unionfs_lower_dentry(dentry); + + lower_dir_dentry = lock_parent(lower_dentry); + + /* avoid destroying the lower inode if the file is in use */ + dget(lower_dentry); + err = is_robranch(dentry); + if (!err) + err = vfs_rmdir(lower_dir_dentry->d_inode, lower_dentry); + dput(lower_dentry); + + fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode); + /* propagate number of hard-links */ + dentry->d_inode->i_nlink = unionfs_get_nlinks(dentry->d_inode); + +out: + if (lower_dir_dentry) + unlock_dir(lower_dir_dentry); + return err; +} + +int unionfs_rmdir(struct inode *dir, struct dentry *dentry) +{ + int err = 0; + struct unionfs_dir_state *namelist = NULL; + struct dentry *parent; + int dstart, dend; + bool valid; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out; + } + unionfs_check_dentry(dentry); + + /* check if this unionfs directory is empty or not */ + err = check_empty(dentry, parent, &namelist); + if (err) + goto out; + + err = unionfs_rmdir_first(dir, dentry, namelist); + dstart = dbstart(dentry); + dend = dbend(dentry); + /* + * We create a whiteout for the directory if there was an error to + * rmdir the first directory entry in the union. Otherwise, we + * create a whiteout only if there is no chance that a lower + * priority branch might also have the same named directory. IOW, + * if there is not another same-named directory at a lower priority + * branch, then we don't need to create a whiteout for it. + */ + if (!err) { + if (dstart < dend) + err = create_whiteout(dentry, dstart); + } else { + int new_err; + + if (dstart == 0) + goto out; + + /* exit if the error returned was NOT -EROFS */ + if (!IS_COPYUP_ERR(err)) + goto out; + + new_err = create_whiteout(dentry, dstart - 1); + if (new_err != -EEXIST) + err = new_err; + } + +out: + /* + * Drop references to lower dentry/inode so storage space for them + * can be reclaimed. Then, call d_drop so the system "forgets" + * about us. + */ + if (!err) { + iput_lowers_all(dentry->d_inode, false); + dput(unionfs_lower_dentry_idx(dentry, dstart)); + unionfs_set_lower_dentry_idx(dentry, dstart, NULL); + d_drop(dentry); + /* update our lower vfsmnts, in case a copyup took place */ + unionfs_postcopyup_setmnt(dentry); + unionfs_check_dentry(dentry); + unionfs_check_inode(dir); + } + + if (namelist) + free_rdstate(namelist); + + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} diff --git a/fs/unionfs/whiteout.c b/fs/unionfs/whiteout.c new file mode 100644 index 0000000..405073a --- /dev/null +++ b/fs/unionfs/whiteout.c @@ -0,0 +1,584 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* + * whiteout and opaque directory helpers + */ + +/* What do we use for whiteouts. */ +#define UNIONFS_WHPFX ".wh." +#define UNIONFS_WHLEN 4 +/* + * If a directory contains this file, then it is opaque. We start with the + * .wh. flag so that it is blocked by lookup. + */ +#define UNIONFS_DIR_OPAQUE_NAME "__dir_opaque" +#define UNIONFS_DIR_OPAQUE UNIONFS_WHPFX UNIONFS_DIR_OPAQUE_NAME + +/* construct whiteout filename */ +char *alloc_whname(const char *name, int len) +{ + char *buf; + + buf = kmalloc(len + UNIONFS_WHLEN + 1, GFP_KERNEL); + if (unlikely(!buf)) + return ERR_PTR(-ENOMEM); + + strcpy(buf, UNIONFS_WHPFX); + strlcat(buf, name, len + UNIONFS_WHLEN + 1); + + return buf; +} + +/* + * XXX: this can be inline or CPP macro, but is here to keep all whiteout + * code in one place. + */ +void unionfs_set_max_namelen(long *namelen) +{ + *namelen -= UNIONFS_WHLEN; +} + +/* check if @namep is a whiteout, update @namep and @namelenp accordingly */ +bool is_whiteout_name(char **namep, int *namelenp) +{ + if (*namelenp > UNIONFS_WHLEN && + !strncmp(*namep, UNIONFS_WHPFX, UNIONFS_WHLEN)) { + *namep += UNIONFS_WHLEN; + *namelenp -= UNIONFS_WHLEN; + return true; + } + return false; +} + +/* is the filename valid == !(whiteout for a file or opaque dir marker) */ +bool is_validname(const char *name) +{ + if (!strncmp(name, UNIONFS_WHPFX, UNIONFS_WHLEN)) + return false; + if (!strncmp(name, UNIONFS_DIR_OPAQUE_NAME, + sizeof(UNIONFS_DIR_OPAQUE_NAME) - 1)) + return false; + return true; +} + +/* + * Look for a whiteout @name in @lower_parent directory. If error, return + * ERR_PTR. Caller must dput() the returned dentry if not an error. + * + * XXX: some callers can reuse the whname allocated buffer to avoid repeated + * free then re-malloc calls. Need to provide a different API for those + * callers. + */ +struct dentry *lookup_whiteout(const char *name, struct dentry *lower_parent) +{ + char *whname = NULL; + int err = 0, namelen; + struct dentry *wh_dentry = NULL; + + namelen = strlen(name); + whname = alloc_whname(name, namelen); + if (unlikely(IS_ERR(whname))) { + err = PTR_ERR(whname); + goto out; + } + + /* check if whiteout exists in this branch: lookup .wh.foo */ + wh_dentry = lookup_lck_len(whname, lower_parent, strlen(whname)); + if (IS_ERR(wh_dentry)) { + err = PTR_ERR(wh_dentry); + goto out; + } + + /* check if negative dentry (ENOENT) */ + if (!wh_dentry->d_inode) + goto out; + + /* whiteout found: check if valid type */ + if (!S_ISREG(wh_dentry->d_inode->i_mode)) { + printk(KERN_ERR "unionfs: invalid whiteout %s entry type %d\n", + whname, wh_dentry->d_inode->i_mode); + dput(wh_dentry); + err = -EIO; + goto out; + } + +out: + kfree(whname); + if (err) + wh_dentry = ERR_PTR(err); + return wh_dentry; +} + +/* find and return first whiteout in parent directory, else ENOENT */ +struct dentry *find_first_whiteout(struct dentry *dentry) +{ + int bindex, bstart, bend; + struct dentry *parent, *lower_parent, *wh_dentry; + + parent = dget_parent(dentry); + + bstart = dbstart(parent); + bend = dbend(parent); + wh_dentry = ERR_PTR(-ENOENT); + + for (bindex = bstart; bindex <= bend; bindex++) { + lower_parent = unionfs_lower_dentry_idx(parent, bindex); + if (!lower_parent) + continue; + wh_dentry = lookup_whiteout(dentry->d_name.name, lower_parent); + if (IS_ERR(wh_dentry)) + continue; + if (wh_dentry->d_inode) + break; + dput(wh_dentry); + wh_dentry = ERR_PTR(-ENOENT); + } + + dput(parent); + + return wh_dentry; +} + +/* + * Unlink a whiteout dentry. Returns 0 or -errno. Caller must hold and + * release dentry reference. + */ +int unlink_whiteout(struct dentry *wh_dentry) +{ + int err; + struct dentry *lower_dir_dentry; + + /* dget and lock parent dentry */ + lower_dir_dentry = lock_parent_wh(wh_dentry); + + /* see Documentation/filesystems/unionfs/issues.txt */ + lockdep_off(); + err = vfs_unlink(lower_dir_dentry->d_inode, wh_dentry); + lockdep_on(); + unlock_dir(lower_dir_dentry); + + /* + * Whiteouts are special files and should be deleted no matter what + * (as if they never existed), in order to allow this create + * operation to succeed. This is especially important in sticky + * directories: a whiteout may have been created by one user, but + * the newly created file may be created by another user. + * Therefore, in order to maintain Unix semantics, if the vfs_unlink + * above failed, then we have to try to directly unlink the + * whiteout. Note: in the ODF version of unionfs, whiteout are + * handled much more cleanly. + */ + if (err == -EPERM) { + struct inode *inode = lower_dir_dentry->d_inode; + err = inode->i_op->unlink(inode, wh_dentry); + } + if (err) + printk(KERN_ERR "unionfs: could not unlink whiteout %s, " + "err = %d\n", wh_dentry->d_name.name, err); + + return err; + +} + +/* + * Helper function when creating new objects (create, symlink, mknod, etc.). + * Checks to see if there's a whiteout in @lower_dentry's parent directory, + * whose name is taken from @dentry. Then tries to remove that whiteout, if + * found. If is a branch marked readonly, return -EROFS. + * If it finds both a regular file and a whiteout, return -EIO (this should + * never happen). + * + * Return 0 if no whiteout was found. Return 1 if one was found and + * successfully removed. Therefore a value >= 0 tells the caller that + * @lower_dentry belongs to a good branch to create the new object in). + * Return -ERRNO if an error occurred during whiteout lookup or in trying to + * unlink the whiteout. + */ +int check_unlink_whiteout(struct dentry *dentry, struct dentry *lower_dentry, + int bindex) +{ + int err; + struct dentry *wh_dentry = NULL; + struct dentry *lower_dir_dentry = NULL; + + /* look for whiteout dentry first */ + lower_dir_dentry = dget_parent(lower_dentry); + wh_dentry = lookup_whiteout(dentry->d_name.name, lower_dir_dentry); + dput(lower_dir_dentry); + if (IS_ERR(wh_dentry)) { + err = PTR_ERR(wh_dentry); + goto out; + } + + if (!wh_dentry->d_inode) { /* no whiteout exists*/ + err = 0; + goto out_dput; + } + + /* check if regular file and whiteout were both found */ + if (unlikely(lower_dentry->d_inode)) { + err = -EIO; + printk(KERN_ERR "unionfs: found both whiteout and regular " + "file in directory %s (branch %d)\n", + lower_dir_dentry->d_name.name, bindex); + goto out_dput; + } + + /* check if branch is writeable */ + err = is_robranch_super(dentry->d_sb, bindex); + if (err) + goto out_dput; + + /* .wh.foo has been found, so let's unlink it */ + err = unlink_whiteout(wh_dentry); + if (!err) + err = 1; /* a whiteout was found and successfully removed */ +out_dput: + dput(wh_dentry); +out: + return err; +} + +/* + * Pass an unionfs dentry and an index. It will try to create a whiteout + * for the filename in dentry, and will try in branch 'index'. On error, + * it will proceed to a branch to the left. + */ +int create_whiteout(struct dentry *dentry, int start) +{ + int bstart, bend, bindex; + struct dentry *lower_dir_dentry; + struct dentry *lower_dentry; + struct dentry *lower_wh_dentry; + struct nameidata nd; + char *name = NULL; + int err = -EINVAL; + + verify_locked(dentry); + + bstart = dbstart(dentry); + bend = dbend(dentry); + + /* create dentry's whiteout equivalent */ + name = alloc_whname(dentry->d_name.name, dentry->d_name.len); + if (unlikely(IS_ERR(name))) { + err = PTR_ERR(name); + goto out; + } + + for (bindex = start; bindex >= 0; bindex--) { + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + + if (!lower_dentry) { + /* + * if lower dentry is not present, create the + * entire lower dentry directory structure and go + * ahead. Since we want to just create whiteout, we + * only want the parent dentry, and hence get rid of + * this dentry. + */ + lower_dentry = create_parents(dentry->d_inode, + dentry, + dentry->d_name.name, + bindex); + if (!lower_dentry || IS_ERR(lower_dentry)) { + int ret = PTR_ERR(lower_dentry); + if (!IS_COPYUP_ERR(ret)) + printk(KERN_ERR + "unionfs: create_parents for " + "whiteout failed: bindex=%d " + "err=%d\n", bindex, ret); + continue; + } + } + + lower_wh_dentry = + lookup_lck_len(name, lower_dentry->d_parent, + dentry->d_name.len + UNIONFS_WHLEN); + if (IS_ERR(lower_wh_dentry)) + continue; + + /* + * The whiteout already exists. This used to be impossible, + * but now is possible because of opaqueness. + */ + if (lower_wh_dentry->d_inode) { + dput(lower_wh_dentry); + err = 0; + goto out; + } + + err = init_lower_nd(&nd, LOOKUP_CREATE); + if (unlikely(err < 0)) + goto out; + lower_dir_dentry = lock_parent_wh(lower_wh_dentry); + err = is_robranch_super(dentry->d_sb, bindex); + if (!err) + err = vfs_create(lower_dir_dentry->d_inode, + lower_wh_dentry, + current_umask() & S_IRUGO, + &nd); + unlock_dir(lower_dir_dentry); + dput(lower_wh_dentry); + release_lower_nd(&nd, err); + + if (!err || !IS_COPYUP_ERR(err)) + break; + } + + /* set dbopaque so that lookup will not proceed after this branch */ + if (!err) + dbopaque(dentry) = bindex; + +out: + kfree(name); + return err; +} + +/* + * Delete all of the whiteouts in a given directory for rmdir. + * + * lower directory inode should be locked + */ +static int do_delete_whiteouts(struct dentry *dentry, int bindex, + struct unionfs_dir_state *namelist) +{ + int err = 0; + struct dentry *lower_dir_dentry = NULL; + struct dentry *lower_dentry; + char *name = NULL, *p; + struct inode *lower_dir; + int i; + struct list_head *pos; + struct filldir_node *cursor; + + /* Find out lower parent dentry */ + lower_dir_dentry = unionfs_lower_dentry_idx(dentry, bindex); + BUG_ON(!S_ISDIR(lower_dir_dentry->d_inode->i_mode)); + lower_dir = lower_dir_dentry->d_inode; + BUG_ON(!S_ISDIR(lower_dir->i_mode)); + + err = -ENOMEM; + name = __getname(); + if (unlikely(!name)) + goto out; + strcpy(name, UNIONFS_WHPFX); + p = name + UNIONFS_WHLEN; + + err = 0; + for (i = 0; !err && i < namelist->size; i++) { + list_for_each(pos, &namelist->list[i]) { + cursor = + list_entry(pos, struct filldir_node, + file_list); + /* Only operate on whiteouts in this branch. */ + if (cursor->bindex != bindex) + continue; + if (!cursor->whiteout) + continue; + + strlcpy(p, cursor->name, PATH_MAX - UNIONFS_WHLEN); + lower_dentry = + lookup_lck_len(name, lower_dir_dentry, + cursor->namelen + + UNIONFS_WHLEN); + if (IS_ERR(lower_dentry)) { + err = PTR_ERR(lower_dentry); + break; + } + if (lower_dentry->d_inode) + err = vfs_unlink(lower_dir, lower_dentry); + dput(lower_dentry); + if (err) + break; + } + } + + __putname(name); + + /* After all of the removals, we should copy the attributes once. */ + fsstack_copy_attr_times(dentry->d_inode, lower_dir_dentry->d_inode); + +out: + return err; +} + + +void __delete_whiteouts(struct work_struct *work) +{ + struct sioq_args *args = container_of(work, struct sioq_args, work); + struct deletewh_args *d = &args->deletewh; + + args->err = do_delete_whiteouts(d->dentry, d->bindex, d->namelist); + complete(&args->comp); +} + +/* delete whiteouts in a dir (for rmdir operation) using sioq if necessary */ +int delete_whiteouts(struct dentry *dentry, int bindex, + struct unionfs_dir_state *namelist) +{ + int err; + struct super_block *sb; + struct dentry *lower_dir_dentry; + struct inode *lower_dir; + struct sioq_args args; + + sb = dentry->d_sb; + + BUG_ON(!S_ISDIR(dentry->d_inode->i_mode)); + BUG_ON(bindex < dbstart(dentry)); + BUG_ON(bindex > dbend(dentry)); + err = is_robranch_super(sb, bindex); + if (err) + goto out; + + lower_dir_dentry = unionfs_lower_dentry_idx(dentry, bindex); + BUG_ON(!S_ISDIR(lower_dir_dentry->d_inode->i_mode)); + lower_dir = lower_dir_dentry->d_inode; + BUG_ON(!S_ISDIR(lower_dir->i_mode)); + + if (!inode_permission(lower_dir, MAY_WRITE | MAY_EXEC)) { + err = do_delete_whiteouts(dentry, bindex, namelist); + } else { + args.deletewh.namelist = namelist; + args.deletewh.dentry = dentry; + args.deletewh.bindex = bindex; + run_sioq(__delete_whiteouts, &args); + err = args.err; + } + +out: + return err; +} + +/**************************************************************************** + * Opaque directory helpers * + ****************************************************************************/ + +/* + * is_opaque_dir: returns 0 if it is NOT an opaque dir, 1 if it is, and + * -errno if an error occurred trying to figure this out. + */ +int is_opaque_dir(struct dentry *dentry, int bindex) +{ + int err = 0; + struct dentry *lower_dentry; + struct dentry *wh_lower_dentry; + struct inode *lower_inode; + struct sioq_args args; + + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + lower_inode = lower_dentry->d_inode; + + BUG_ON(!S_ISDIR(lower_inode->i_mode)); + + mutex_lock(&lower_inode->i_mutex); + + if (!inode_permission(lower_inode, MAY_EXEC)) { + wh_lower_dentry = + lookup_one_len(UNIONFS_DIR_OPAQUE, lower_dentry, + sizeof(UNIONFS_DIR_OPAQUE) - 1); + } else { + args.is_opaque.dentry = lower_dentry; + run_sioq(__is_opaque_dir, &args); + wh_lower_dentry = args.ret; + } + + mutex_unlock(&lower_inode->i_mutex); + + if (IS_ERR(wh_lower_dentry)) { + err = PTR_ERR(wh_lower_dentry); + goto out; + } + + /* This is an opaque dir iff wh_lower_dentry is positive */ + err = !!wh_lower_dentry->d_inode; + + dput(wh_lower_dentry); +out: + return err; +} + +void __is_opaque_dir(struct work_struct *work) +{ + struct sioq_args *args = container_of(work, struct sioq_args, work); + + args->ret = lookup_one_len(UNIONFS_DIR_OPAQUE, args->is_opaque.dentry, + sizeof(UNIONFS_DIR_OPAQUE) - 1); + complete(&args->comp); +} + +int make_dir_opaque(struct dentry *dentry, int bindex) +{ + int err = 0; + struct dentry *lower_dentry, *diropq; + struct inode *lower_dir; + struct nameidata nd; + const struct cred *old_creds; + struct cred *new_creds; + + /* + * Opaque directory whiteout markers are special files (like regular + * whiteouts), and should appear to the users as if they don't + * exist. They should be created/deleted regardless of directory + * search/create permissions, but only for the duration of this + * creation of the .wh.__dir_opaque: file. Note, this does not + * circumvent normal ->permission). + */ + new_creds = prepare_creds(); + if (unlikely(!new_creds)) { + err = -ENOMEM; + goto out_err; + } + cap_raise(new_creds->cap_effective, CAP_DAC_READ_SEARCH); + cap_raise(new_creds->cap_effective, CAP_DAC_OVERRIDE); + old_creds = override_creds(new_creds); + + lower_dentry = unionfs_lower_dentry_idx(dentry, bindex); + lower_dir = lower_dentry->d_inode; + BUG_ON(!S_ISDIR(dentry->d_inode->i_mode) || + !S_ISDIR(lower_dir->i_mode)); + + mutex_lock(&lower_dir->i_mutex); + diropq = lookup_one_len(UNIONFS_DIR_OPAQUE, lower_dentry, + sizeof(UNIONFS_DIR_OPAQUE) - 1); + if (IS_ERR(diropq)) { + err = PTR_ERR(diropq); + goto out; + } + + err = init_lower_nd(&nd, LOOKUP_CREATE); + if (unlikely(err < 0)) + goto out; + if (!diropq->d_inode) + err = vfs_create(lower_dir, diropq, S_IRUGO, &nd); + if (!err) + dbopaque(dentry) = bindex; + release_lower_nd(&nd, err); + + dput(diropq); + +out: + mutex_unlock(&lower_dir->i_mutex); + revert_creds(old_creds); +out_err: + return err; +} diff --git a/fs/unionfs/xattr.c b/fs/unionfs/xattr.c new file mode 100644 index 0000000..9002e06 --- /dev/null +++ b/fs/unionfs/xattr.c @@ -0,0 +1,173 @@ +/* + * Copyright (c) 2003-2010 Erez Zadok + * Copyright (c) 2003-2006 Charles P. Wright + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2005-2006 Junjiro Okajima + * Copyright (c) 2005 Arun M. Krishnakumar + * Copyright (c) 2004-2006 David P. Quigley + * Copyright (c) 2003-2004 Mohammad Nayyer Zubair + * Copyright (c) 2003 Puja Gupta + * Copyright (c) 2003 Harikesavan Krishnan + * Copyright (c) 2003-2010 Stony Brook University + * Copyright (c) 2003-2010 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "union.h" + +/* This is lifted from fs/xattr.c */ +void *unionfs_xattr_alloc(size_t size, size_t limit) +{ + void *ptr; + + if (size > limit) + return ERR_PTR(-E2BIG); + + if (!size) /* size request, no buffer is needed */ + return NULL; + + ptr = kmalloc(size, GFP_KERNEL); + if (unlikely(!ptr)) + return ERR_PTR(-ENOMEM); + return ptr; +} + +/* + * BKL held by caller. + * dentry->d_inode->i_mutex locked + */ +ssize_t unionfs_getxattr(struct dentry *dentry, const char *name, void *value, + size_t size) +{ + struct dentry *lower_dentry = NULL; + struct dentry *parent; + int err = -EOPNOTSUPP; + bool valid; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out; + } + + lower_dentry = unionfs_lower_dentry(dentry); + + err = vfs_getxattr(lower_dentry, (char *) name, value, size); + +out: + unionfs_check_dentry(dentry); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +/* + * BKL held by caller. + * dentry->d_inode->i_mutex locked + */ +int unionfs_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + struct dentry *lower_dentry = NULL; + struct dentry *parent; + int err = -EOPNOTSUPP; + bool valid; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out; + } + + lower_dentry = unionfs_lower_dentry(dentry); + + err = vfs_setxattr(lower_dentry, (char *) name, (void *) value, + size, flags); + +out: + unionfs_check_dentry(dentry); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +/* + * BKL held by caller. + * dentry->d_inode->i_mutex locked + */ +int unionfs_removexattr(struct dentry *dentry, const char *name) +{ + struct dentry *lower_dentry = NULL; + struct dentry *parent; + int err = -EOPNOTSUPP; + bool valid; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out; + } + + lower_dentry = unionfs_lower_dentry(dentry); + + err = vfs_removexattr(lower_dentry, (char *) name); + +out: + unionfs_check_dentry(dentry); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} + +/* + * BKL held by caller. + * dentry->d_inode->i_mutex locked + */ +ssize_t unionfs_listxattr(struct dentry *dentry, char *list, size_t size) +{ + struct dentry *lower_dentry = NULL; + struct dentry *parent; + int err = -EOPNOTSUPP; + char *encoded_list = NULL; + bool valid; + + unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD); + parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT); + unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD); + + valid = __unionfs_d_revalidate(dentry, parent, false); + if (unlikely(!valid)) { + err = -ESTALE; + goto out; + } + + lower_dentry = unionfs_lower_dentry(dentry); + + encoded_list = list; + err = vfs_listxattr(lower_dentry, encoded_list, size); + +out: + unionfs_check_dentry(dentry); + unionfs_unlock_dentry(dentry); + unionfs_unlock_parent(dentry, parent); + unionfs_read_unlock(dentry->d_sb); + return err; +} diff --git a/include/linux/fs_stack.h b/include/linux/fs_stack.h index da317c7..64f1ced 100644 --- a/include/linux/fs_stack.h +++ b/include/linux/fs_stack.h @@ -1,7 +1,19 @@ +/* + * Copyright (c) 2006-2009 Erez Zadok + * Copyright (c) 2006-2007 Josef 'Jeff' Sipek + * Copyright (c) 2006-2009 Stony Brook University + * Copyright (c) 2006-2009 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + #ifndef _LINUX_FS_STACK_H #define _LINUX_FS_STACK_H -/* This file defines generic functions used primarily by stackable +/* + * This file defines generic functions used primarily by stackable * filesystems; none of these functions require i_mutex to be held. */ diff --git a/include/linux/magic.h b/include/linux/magic.h index eb9800f..9770154 100644 --- a/include/linux/magic.h +++ b/include/linux/magic.h @@ -47,6 +47,8 @@ #define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs" #define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs" +#define UNIONFS_SUPER_MAGIC 0xf15f083d + #define SMB_SUPER_MAGIC 0x517B #define USBDEVICE_SUPER_MAGIC 0x9fa2 #define CGROUP_SUPER_MAGIC 0x27e0eb diff --git a/include/linux/namei.h b/include/linux/namei.h index 05b441d..dca6f9a 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -72,6 +72,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, int (*open)(struct inode *, struct file *)); +extern void release_open_intent(struct nameidata *); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); diff --git a/include/linux/splice.h b/include/linux/splice.h index 997c3b4..54f5501 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -81,6 +81,11 @@ extern ssize_t splice_to_pipe(struct pipe_inode_info *, struct splice_pipe_desc *); extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, splice_direct_actor *); +extern long vfs_splice_from(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags); +extern long vfs_splice_to(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); /* * for dynamic pipe sizing diff --git a/include/linux/union_fs.h b/include/linux/union_fs.h new file mode 100644 index 0000000..c84d97e --- /dev/null +++ b/include/linux/union_fs.h @@ -0,0 +1,22 @@ +/* + * Copyright (c) 2003-2009 Erez Zadok + * Copyright (c) 2005-2007 Josef 'Jeff' Sipek + * Copyright (c) 2003-2009 Stony Brook University + * Copyright (c) 2003-2009 The Research Foundation of SUNY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_UNION_FS_H +#define _LINUX_UNION_FS_H + +/* + * DEFINITIONS FOR USER AND KERNEL CODE: + */ +# define UNIONFS_IOCTL_INCGEN _IOR(0x15, 11, int) +# define UNIONFS_IOCTL_QUERYFILE _IOR(0x15, 15, int) + +#endif /* _LINUX_UNIONFS_H */ + diff --git a/security/security.c b/security/security.c index c53949f..eb71394 100644 --- a/security/security.c +++ b/security/security.c @@ -528,6 +528,7 @@ int security_inode_permission(struct inode *inode, int mask) return 0; return security_ops->inode_permission(inode, mask); } +EXPORT_SYMBOL(security_inode_permission); int security_inode_setattr(struct dentry *dentry, struct iattr *attr) {