OpenCloudOS-Kernel/fs/nfs/super.c

2927 lines
75 KiB
C
Raw Normal View History

/*
* linux/fs/nfs/super.c
*
* Copyright (C) 1992 Rick Sladkey
*
* nfs superblock handling functions
*
* Modularised by Alan Cox <alan@lxorguk.ukuu.org.uk>, while hacking some
* experimental NFS changes. Modularisation taken straight from SYS5 fs.
*
* Change to nfs_read_super() to permit NFS mounts to multi-homed hosts.
* J.S.Peatfield@damtp.cam.ac.uk
*
* Split from inode.c by David Howells <dhowells@redhat.com>
*
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
* - superblocks are indexed on server only - all inodes, dentries, etc. associated with a
* particular server are held in the same superblock
* - NFS superblocks can have several effective roots to the dentry tree
* - directory type roots are spliced into the tree when a path from one root reaches the root
* of another (see nfs_lookup())
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/unistd.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/metrics.h>
#include <linux/sunrpc/xprtsock.h>
#include <linux/sunrpc/xprtrdma.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/nfs4_mount.h>
#include <linux/lockd/bind.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/vfs.h>
#include <linux/inet.h>
#include <linux/in6.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <net/ipv6.h>
#include <linux/netdevice.h>
#include <linux/nfs_xdr.h>
#include <linux/magic.h>
#include <linux/parser.h>
#include <linux/nsproxy.h>
#include <linux/rcupdate.h>
#include <linux/uaccess.h>
#include "nfs4_fs.h"
#include "callback.h"
#include "delegation.h"
#include "iostat.h"
#include "internal.h"
NFS: Define and create superblock-level objects Define and create superblock-level cache index objects (as managed by nfs_server structs). Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The superblock object key is a sequence consisting of: (1) Certain superblock s_flags. (2) Various connection parameters that serve to distinguish superblocks for sget(). (3) The volume FSID. (4) The security flavour. (5) The uniquifier length. (6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier. The key blob is of variable length, depending on the length of (6). The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent. This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com>
2009-04-03 23:42:42 +08:00
#include "fscache.h"
#include "nfs4session.h"
#include "pnfs.h"
#include "nfs.h"
#define NFSDBG_FACILITY NFSDBG_VFS
#define NFS_TEXT_DATA 1
#if IS_ENABLED(CONFIG_NFS_V3)
#define NFS_DEFAULT_VERSION 3
#else
#define NFS_DEFAULT_VERSION 2
#endif
enum {
/* Mount options that take no arguments */
Opt_soft, Opt_hard,
Opt_posix, Opt_noposix,
Opt_cto, Opt_nocto,
Opt_ac, Opt_noac,
Opt_lock, Opt_nolock,
Opt_udp, Opt_tcp, Opt_rdma,
Opt_acl, Opt_noacl,
Opt_rdirplus, Opt_nordirplus,
Opt_sharecache, Opt_nosharecache,
NFS: add "[no]resvport" mount option The standard default security setting for NFS is AUTH_SYS. An NFS client connects to NFS servers via a privileged source port and a fixed standard destination port (2049). The client sends raw uid and gid numbers to identify users making NFS requests, and the server assumes an appropriate authority on the client has vetted these values because the source port is privileged. On Linux, by default in-kernel RPC services use a privileged port in the range between 650 and 1023 to avoid using source ports of well- known IP services. Using such a small range limits the number of NFS mount points and the number of unique NFS servers to which a client can connect concurrently. An NFS client can use unprivileged source ports to expand the range of source port numbers, allowing more concurrent server connections and more NFS mount points. Servers must explicitly allow NFS connections from unprivileged ports for this to work. In the past, bumping the value of the sunrpc.max_resvport sysctl on the client would permit the NFS client to use unprivileged ports. Bumping this setting also changes the maximum port number used by other in-kernel RPC services, some of which still required a port number less than 1023. This is exacerbated by the way source port numbers are chosen by the Linux RPC client, which starts at the top of the range and works downwards. It means that bumping the maximum means all RPC services requesting a source port will likely get an unprivileged port instead of a privileged one. Changing this setting effects all NFS mount points on a client. A sysadmin could not selectively choose which mount points would use non-privileged ports and which could not. Lastly, this mechanism of expanding the limit on the number of NFS mount points was entirely undocumented. To address the need for the NFS client to use a large range of source ports without interfering with the activity of other in-kernel RPC services, we introduce a new NFS mount option. This option explicitly tells only the NFS client to use a non-privileged source port when communicating with the NFS server for one specific mount point. This new mount option is called "resvport," like the similar NFS mount option on FreeBSD and Mac OS X. A sister patch for nfs-utils will be submitted that documents this new option in nfs(5). The default setting for this new mount option requires the NFS client to use a privileged port, as before. Explicitly specifying the "noresvport" mount option allows the NFS client to use an unprivileged source port for this mount point when connecting to the NFS server port. This mount option is supported only for text-based NFS mounts. [ Sidebar: it is widely known that security mechanisms based on the use of privileged source ports are ineffective. However, the NFS client can combine the use of unprivileged ports with the use of secure authentication mechanisms, such as Kerberos. This allows a large number of connections and mount points while ensuring a useful level of security. Eventually we may change the default setting for this option depending on the security flavor used for the mount. For example, if the mount is using only AUTH_SYS, then the default setting will be "resvport;" if the mount is using a strong security flavor such as krb5, the default setting will be "noresvport." ] Signed-off-by: Chuck Lever <chuck.lever@oracle.com> [Trond.Myklebust@netapp.com: Fixed a bug whereby nfs4_init_client() was being called with incorrect arguments.] Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-24 04:21:37 +08:00
Opt_resvport, Opt_noresvport,
Opt_fscache, Opt_nofscache,
2012-09-15 05:24:11 +08:00
Opt_migration, Opt_nomigration,
/* Mount options that take integer arguments */
Opt_port,
Opt_rsize, Opt_wsize, Opt_bsize,
Opt_timeo, Opt_retrans,
Opt_acregmin, Opt_acregmax,
Opt_acdirmin, Opt_acdirmax,
Opt_actimeo,
Opt_namelen,
Opt_mountport,
Opt_mountvers,
Opt_minorversion,
/* Mount options that take string arguments */
Opt_nfsvers,
Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost,
Opt_addr, Opt_mountaddr, Opt_clientaddr,
Opt_lookupcache,
Opt_fscache_uniq,
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 20:55:58 +08:00
Opt_local_lock,
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
/* Special mount options */
Opt_userspace, Opt_deprecated, Opt_sloppy,
Opt_err
};
static const match_table_t nfs_mount_option_tokens = {
{ Opt_userspace, "bg" },
{ Opt_userspace, "fg" },
{ Opt_userspace, "retry=%s" },
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
{ Opt_sloppy, "sloppy" },
{ Opt_soft, "soft" },
{ Opt_hard, "hard" },
{ Opt_deprecated, "intr" },
{ Opt_deprecated, "nointr" },
{ Opt_posix, "posix" },
{ Opt_noposix, "noposix" },
{ Opt_cto, "cto" },
{ Opt_nocto, "nocto" },
{ Opt_ac, "ac" },
{ Opt_noac, "noac" },
{ Opt_lock, "lock" },
{ Opt_nolock, "nolock" },
{ Opt_udp, "udp" },
{ Opt_tcp, "tcp" },
{ Opt_rdma, "rdma" },
{ Opt_acl, "acl" },
{ Opt_noacl, "noacl" },
{ Opt_rdirplus, "rdirplus" },
{ Opt_nordirplus, "nordirplus" },
{ Opt_sharecache, "sharecache" },
{ Opt_nosharecache, "nosharecache" },
NFS: add "[no]resvport" mount option The standard default security setting for NFS is AUTH_SYS. An NFS client connects to NFS servers via a privileged source port and a fixed standard destination port (2049). The client sends raw uid and gid numbers to identify users making NFS requests, and the server assumes an appropriate authority on the client has vetted these values because the source port is privileged. On Linux, by default in-kernel RPC services use a privileged port in the range between 650 and 1023 to avoid using source ports of well- known IP services. Using such a small range limits the number of NFS mount points and the number of unique NFS servers to which a client can connect concurrently. An NFS client can use unprivileged source ports to expand the range of source port numbers, allowing more concurrent server connections and more NFS mount points. Servers must explicitly allow NFS connections from unprivileged ports for this to work. In the past, bumping the value of the sunrpc.max_resvport sysctl on the client would permit the NFS client to use unprivileged ports. Bumping this setting also changes the maximum port number used by other in-kernel RPC services, some of which still required a port number less than 1023. This is exacerbated by the way source port numbers are chosen by the Linux RPC client, which starts at the top of the range and works downwards. It means that bumping the maximum means all RPC services requesting a source port will likely get an unprivileged port instead of a privileged one. Changing this setting effects all NFS mount points on a client. A sysadmin could not selectively choose which mount points would use non-privileged ports and which could not. Lastly, this mechanism of expanding the limit on the number of NFS mount points was entirely undocumented. To address the need for the NFS client to use a large range of source ports without interfering with the activity of other in-kernel RPC services, we introduce a new NFS mount option. This option explicitly tells only the NFS client to use a non-privileged source port when communicating with the NFS server for one specific mount point. This new mount option is called "resvport," like the similar NFS mount option on FreeBSD and Mac OS X. A sister patch for nfs-utils will be submitted that documents this new option in nfs(5). The default setting for this new mount option requires the NFS client to use a privileged port, as before. Explicitly specifying the "noresvport" mount option allows the NFS client to use an unprivileged source port for this mount point when connecting to the NFS server port. This mount option is supported only for text-based NFS mounts. [ Sidebar: it is widely known that security mechanisms based on the use of privileged source ports are ineffective. However, the NFS client can combine the use of unprivileged ports with the use of secure authentication mechanisms, such as Kerberos. This allows a large number of connections and mount points while ensuring a useful level of security. Eventually we may change the default setting for this option depending on the security flavor used for the mount. For example, if the mount is using only AUTH_SYS, then the default setting will be "resvport;" if the mount is using a strong security flavor such as krb5, the default setting will be "noresvport." ] Signed-off-by: Chuck Lever <chuck.lever@oracle.com> [Trond.Myklebust@netapp.com: Fixed a bug whereby nfs4_init_client() was being called with incorrect arguments.] Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-24 04:21:37 +08:00
{ Opt_resvport, "resvport" },
{ Opt_noresvport, "noresvport" },
{ Opt_fscache, "fsc" },
{ Opt_nofscache, "nofsc" },
2012-09-15 05:24:11 +08:00
{ Opt_migration, "migration" },
{ Opt_nomigration, "nomigration" },
{ Opt_port, "port=%s" },
{ Opt_rsize, "rsize=%s" },
{ Opt_wsize, "wsize=%s" },
{ Opt_bsize, "bsize=%s" },
{ Opt_timeo, "timeo=%s" },
{ Opt_retrans, "retrans=%s" },
{ Opt_acregmin, "acregmin=%s" },
{ Opt_acregmax, "acregmax=%s" },
{ Opt_acdirmin, "acdirmin=%s" },
{ Opt_acdirmax, "acdirmax=%s" },
{ Opt_actimeo, "actimeo=%s" },
{ Opt_namelen, "namlen=%s" },
{ Opt_mountport, "mountport=%s" },
{ Opt_mountvers, "mountvers=%s" },
{ Opt_minorversion, "minorversion=%s" },
{ Opt_nfsvers, "nfsvers=%s" },
{ Opt_nfsvers, "vers=%s" },
{ Opt_sec, "sec=%s" },
{ Opt_proto, "proto=%s" },
{ Opt_mountproto, "mountproto=%s" },
{ Opt_addr, "addr=%s" },
{ Opt_clientaddr, "clientaddr=%s" },
{ Opt_mounthost, "mounthost=%s" },
{ Opt_mountaddr, "mountaddr=%s" },
{ Opt_lookupcache, "lookupcache=%s" },
{ Opt_fscache_uniq, "fsc=%s" },
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 20:55:58 +08:00
{ Opt_local_lock, "local_lock=%s" },
/* The following needs to be listed after all other options */
{ Opt_nfsvers, "v%s" },
{ Opt_err, NULL }
};
enum {
Opt_xprt_udp, Opt_xprt_udp6, Opt_xprt_tcp, Opt_xprt_tcp6, Opt_xprt_rdma,
Opt_xprt_rdma6,
Opt_xprt_err
};
static const match_table_t nfs_xprt_protocol_tokens = {
{ Opt_xprt_udp, "udp" },
{ Opt_xprt_udp6, "udp6" },
{ Opt_xprt_tcp, "tcp" },
{ Opt_xprt_tcp6, "tcp6" },
{ Opt_xprt_rdma, "rdma" },
{ Opt_xprt_rdma6, "rdma6" },
{ Opt_xprt_err, NULL }
};
enum {
Opt_sec_none, Opt_sec_sys,
Opt_sec_krb5, Opt_sec_krb5i, Opt_sec_krb5p,
Opt_sec_lkey, Opt_sec_lkeyi, Opt_sec_lkeyp,
Opt_sec_spkm, Opt_sec_spkmi, Opt_sec_spkmp,
Opt_sec_err
};
static const match_table_t nfs_secflavor_tokens = {
{ Opt_sec_none, "none" },
{ Opt_sec_none, "null" },
{ Opt_sec_sys, "sys" },
{ Opt_sec_krb5, "krb5" },
{ Opt_sec_krb5i, "krb5i" },
{ Opt_sec_krb5p, "krb5p" },
{ Opt_sec_lkey, "lkey" },
{ Opt_sec_lkeyi, "lkeyi" },
{ Opt_sec_lkeyp, "lkeyp" },
{ Opt_sec_spkm, "spkm3" },
{ Opt_sec_spkmi, "spkm3i" },
{ Opt_sec_spkmp, "spkm3p" },
{ Opt_sec_err, NULL }
};
enum {
Opt_lookupcache_all, Opt_lookupcache_positive,
Opt_lookupcache_none,
Opt_lookupcache_err
};
static match_table_t nfs_lookupcache_tokens = {
{ Opt_lookupcache_all, "all" },
{ Opt_lookupcache_positive, "pos" },
{ Opt_lookupcache_positive, "positive" },
{ Opt_lookupcache_none, "none" },
{ Opt_lookupcache_err, NULL }
};
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 20:55:58 +08:00
enum {
Opt_local_lock_all, Opt_local_lock_flock, Opt_local_lock_posix,
Opt_local_lock_none,
Opt_local_lock_err
};
static match_table_t nfs_local_lock_tokens = {
{ Opt_local_lock_all, "all" },
{ Opt_local_lock_flock, "flock" },
{ Opt_local_lock_posix, "posix" },
{ Opt_local_lock_none, "none" },
{ Opt_local_lock_err, NULL }
};
enum {
Opt_vers_2, Opt_vers_3, Opt_vers_4, Opt_vers_4_0,
Opt_vers_4_1, Opt_vers_4_2,
Opt_vers_err
};
static match_table_t nfs_vers_tokens = {
{ Opt_vers_2, "2" },
{ Opt_vers_3, "3" },
{ Opt_vers_4, "4" },
{ Opt_vers_4_0, "4.0" },
{ Opt_vers_4_1, "4.1" },
{ Opt_vers_4_2, "4.2" },
{ Opt_vers_err, NULL }
};
static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *raw_data);
struct file_system_type nfs_fs_type = {
.owner = THIS_MODULE,
.name = "nfs",
.mount = nfs_fs_mount,
.kill_sb = nfs_kill_super,
vfs: kill FS_REVAL_DOT by adding a d_weak_revalidate dentry op The following set of operations on a NFS client and server will cause server# mkdir a client# cd a server# mv a a.bak client# sleep 30 # (or whatever the dir attrcache timeout is) client# stat . stat: cannot stat `.': Stale NFS file handle Obviously, we should not be getting an ESTALE error back there since the inode still exists on the server. The problem is that the lookup code will call d_revalidate on the dentry that "." refers to, because NFS has FS_REVAL_DOT set. nfs_lookup_revalidate will see that the parent directory has changed and will try to reverify the dentry by redoing a LOOKUP. That of course fails, so the lookup code returns ESTALE. The problem here is that d_revalidate is really a bad fit for this case. What we really want to know at this point is whether the inode is still good or not, but we don't really care what name it goes by or whether the dcache is still valid. Add a new d_op->d_weak_revalidate operation and have complete_walk call that instead of d_revalidate. The intent there is to allow for a "weaker" d_revalidate that just checks to see whether the inode is still good. This is also gives us an opportunity to kill off the FS_REVAL_DOT special casing. [AV: changed method name, added note in porting, fixed confusion re having it possibly called from RCU mode (it won't be)] Cc: NeilBrown <neilb@suse.de> Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-02-21 00:19:05 +08:00
.fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 11:39:14 +08:00
MODULE_ALIAS_FS("nfs");
EXPORT_SYMBOL_GPL(nfs_fs_type);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
struct file_system_type nfs_xdev_fs_type = {
.owner = THIS_MODULE,
.name = "nfs",
.mount = nfs_xdev_mount,
.kill_sb = nfs_kill_super,
vfs: kill FS_REVAL_DOT by adding a d_weak_revalidate dentry op The following set of operations on a NFS client and server will cause server# mkdir a client# cd a server# mv a a.bak client# sleep 30 # (or whatever the dir attrcache timeout is) client# stat . stat: cannot stat `.': Stale NFS file handle Obviously, we should not be getting an ESTALE error back there since the inode still exists on the server. The problem is that the lookup code will call d_revalidate on the dentry that "." refers to, because NFS has FS_REVAL_DOT set. nfs_lookup_revalidate will see that the parent directory has changed and will try to reverify the dentry by redoing a LOOKUP. That of course fails, so the lookup code returns ESTALE. The problem here is that d_revalidate is really a bad fit for this case. What we really want to know at this point is whether the inode is still good or not, but we don't really care what name it goes by or whether the dcache is still valid. Add a new d_op->d_weak_revalidate operation and have complete_walk call that instead of d_revalidate. The intent there is to allow for a "weaker" d_revalidate that just checks to see whether the inode is still good. This is also gives us an opportunity to kill off the FS_REVAL_DOT special casing. [AV: changed method name, added note in porting, fixed confusion re having it possibly called from RCU mode (it won't be)] Cc: NeilBrown <neilb@suse.de> Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-02-21 00:19:05 +08:00
.fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
};
const struct super_operations nfs_sops = {
.alloc_inode = nfs_alloc_inode,
.destroy_inode = nfs_destroy_inode,
.write_inode = nfs_write_inode,
.drop_inode = nfs_drop_inode,
.statfs = nfs_statfs,
.evict_inode = nfs_evict_inode,
.umount_begin = nfs_umount_begin,
.show_options = nfs_show_options,
.show_devname = nfs_show_devname,
.show_path = nfs_show_path,
.show_stats = nfs_show_stats,
.remount_fs = nfs_remount,
};
EXPORT_SYMBOL_GPL(nfs_sops);
#if IS_ENABLED(CONFIG_NFS_V4)
static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *);
static int nfs4_validate_mount_data(void *options,
struct nfs_parsed_mount_data *args, const char *dev_name);
struct file_system_type nfs4_fs_type = {
.owner = THIS_MODULE,
.name = "nfs4",
.mount = nfs_fs_mount,
.kill_sb = nfs_kill_super,
vfs: kill FS_REVAL_DOT by adding a d_weak_revalidate dentry op The following set of operations on a NFS client and server will cause server# mkdir a client# cd a server# mv a a.bak client# sleep 30 # (or whatever the dir attrcache timeout is) client# stat . stat: cannot stat `.': Stale NFS file handle Obviously, we should not be getting an ESTALE error back there since the inode still exists on the server. The problem is that the lookup code will call d_revalidate on the dentry that "." refers to, because NFS has FS_REVAL_DOT set. nfs_lookup_revalidate will see that the parent directory has changed and will try to reverify the dentry by redoing a LOOKUP. That of course fails, so the lookup code returns ESTALE. The problem here is that d_revalidate is really a bad fit for this case. What we really want to know at this point is whether the inode is still good or not, but we don't really care what name it goes by or whether the dcache is still valid. Add a new d_op->d_weak_revalidate operation and have complete_walk call that instead of d_revalidate. The intent there is to allow for a "weaker" d_revalidate that just checks to see whether the inode is still good. This is also gives us an opportunity to kill off the FS_REVAL_DOT special casing. [AV: changed method name, added note in porting, fixed confusion re having it possibly called from RCU mode (it won't be)] Cc: NeilBrown <neilb@suse.de> Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-02-21 00:19:05 +08:00
.fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 11:39:14 +08:00
MODULE_ALIAS_FS("nfs4");
MODULE_ALIAS("nfs4");
EXPORT_SYMBOL_GPL(nfs4_fs_type);
static int __init register_nfs4_fs(void)
{
return register_filesystem(&nfs4_fs_type);
}
static void unregister_nfs4_fs(void)
{
unregister_filesystem(&nfs4_fs_type);
}
#else
static int __init register_nfs4_fs(void)
{
return 0;
}
static void unregister_nfs4_fs(void)
{
}
#endif
static struct shrinker acl_shrinker = {
fs: convert fs shrinkers to new scan/count API Convert the filesystem shrinkers to use the new API, and standardise some of the behaviours of the shrinkers at the same time. For example, nr_to_scan means the number of objects to scan, not the number of objects to free. I refactored the CIFS idmap shrinker a little - it really needs to be broken up into a shrinker per tree and keep an item count with the tree root so that we don't need to walk the tree every time the shrinker needs to count the number of objects in the tree (i.e. all the time under memory pressure). [glommer@openvz.org: fixes for ext4, ubifs, nfs, cifs and glock. Fixes are needed mainly due to new code merged in the tree] [assorted fixes folded in] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Acked-by: Jan Kara <jack@suse.cz> Acked-by: Steven Whitehouse <swhiteho@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:18:09 +08:00
.count_objects = nfs_access_cache_count,
.scan_objects = nfs_access_cache_scan,
.seeks = DEFAULT_SEEKS,
};
/*
* Register the NFS filesystems
*/
int __init register_nfs_fs(void)
{
int ret;
ret = register_filesystem(&nfs_fs_type);
if (ret < 0)
goto error_0;
ret = register_nfs4_fs();
if (ret < 0)
goto error_1;
ret = nfs_register_sysctl();
if (ret < 0)
goto error_2;
ret = register_shrinker(&acl_shrinker);
if (ret < 0)
goto error_3;
return 0;
error_3:
nfs_unregister_sysctl();
error_2:
unregister_nfs4_fs();
error_1:
unregister_filesystem(&nfs_fs_type);
error_0:
return ret;
}
/*
* Unregister the NFS filesystems
*/
void __exit unregister_nfs_fs(void)
{
unregister_shrinker(&acl_shrinker);
nfs: fix oops re sysctls and V4 support NFS unregisters sysctls only if V4 support is compiled in. However, sysctl table is not V4 specific, so unregister it always. Steps to reproduce: [build nfs.ko with CONFIG_NFS_V4=n] modrobe nfs rmmod nfs ls /proc/sys Unable to handle kernel paging request at ffffffff880661c0 RIP: [<ffffffff802af8e3>] proc_sys_readdir+0xd3/0x350 PGD 203067 PUD 207063 PMD 7e216067 PTE 0 Oops: 0000 [1] SMP CPU 1 Modules linked in: lockd nfs_acl sunrpc Pid: 3335, comm: ls Not tainted 2.6.23-rc3-bloat #2 RIP: 0010:[<ffffffff802af8e3>] [<ffffffff802af8e3>] proc_sys_readdir+0xd3/0x350 RSP: 0018:ffff81007fd93e78 EFLAGS: 00010286 RAX: ffffffff880661c0 RBX: ffffffff80466370 RCX: ffffffff880661c0 RDX: 00000000000014c0 RSI: ffff81007f3ad020 RDI: ffff81007efd8b40 RBP: 0000000000000018 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: ffffffff802a8570 R12: ffffffff880661c0 R13: ffff81007e219640 R14: ffff81007efd8b40 R15: ffff81007ded7280 FS: 00002ba25ef03060(0000) GS:ffff81007ff81258(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffffffff880661c0 CR3: 000000007dfaf000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process ls (pid: 3335, threadinfo ffff81007fd92000, task ffff81007d8a0000) Stack: ffff81007f3ad150 ffffffff80283f30 ffff81007fd93f48 ffff81007efd8b40 ffff81007ee00440 0000000422222222 0000000200035593 ffffffff88037e9a 2222222222222222 ffffffff80466500 ffff81007e416400 ffff81007e219640 Call Trace: [<ffffffff80283f30>] filldir+0x0/0xf0 [<ffffffff80283f30>] filldir+0x0/0xf0 [<ffffffff802840c7>] vfs_readdir+0xa7/0xc0 [<ffffffff80284376>] sys_getdents+0x96/0xe0 [<ffffffff8020bb3e>] system_call+0x7e/0x83 Code: 41 8b 14 24 85 d2 74 dc 49 8b 44 24 08 48 85 c0 74 e7 49 3b RIP [<ffffffff802af8e3>] proc_sys_readdir+0xd3/0x350 RSP <ffff81007fd93e78> CR2: ffffffff880661c0 Kernel panic - not syncing: Fatal exception Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Acked-by: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-09-19 13:46:40 +08:00
nfs_unregister_sysctl();
unregister_nfs4_fs();
unregister_filesystem(&nfs_fs_type);
}
bool nfs_sb_active(struct super_block *sb)
{
struct nfs_server *server = NFS_SB(sb);
if (!atomic_inc_not_zero(&sb->s_active))
return false;
if (atomic_inc_return(&server->active) != 1)
atomic_dec(&sb->s_active);
return true;
}
EXPORT_SYMBOL_GPL(nfs_sb_active);
void nfs_sb_deactive(struct super_block *sb)
{
struct nfs_server *server = NFS_SB(sb);
if (atomic_dec_and_test(&server->active))
deactivate_super(sb);
}
EXPORT_SYMBOL_GPL(nfs_sb_deactive);
/*
* Deliver file system statistics to userspace
*/
int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct nfs_server *server = NFS_SB(dentry->d_sb);
unsigned char blockbits;
unsigned long blockres;
struct nfs_fh *fh = NFS_FH(d_inode(dentry));
struct nfs_fsstat res;
int error = -ENOMEM;
res.fattr = nfs_alloc_fattr();
if (res.fattr == NULL)
goto out_err;
error = server->nfs_client->rpc_ops->statfs(server, fh, &res);
if (unlikely(error == -ESTALE)) {
struct dentry *pd_dentry;
pd_dentry = dget_parent(dentry);
if (pd_dentry != NULL) {
nfs_zap_caches(d_inode(pd_dentry));
dput(pd_dentry);
}
}
nfs_free_fattr(res.fattr);
if (error < 0)
goto out_err;
buf->f_type = NFS_SUPER_MAGIC;
/*
* Current versions of glibc do not correctly handle the
* case where f_frsize != f_bsize. Eventually we want to
* report the value of wtmult in this field.
*/
buf->f_frsize = dentry->d_sb->s_blocksize;
/*
* On most *nix systems, f_blocks, f_bfree, and f_bavail
* are reported in units of f_frsize. Linux hasn't had
* an f_frsize field in its statfs struct until recently,
* thus historically Linux's sys_statfs reports these
* fields in units of f_bsize.
*/
buf->f_bsize = dentry->d_sb->s_blocksize;
blockbits = dentry->d_sb->s_blocksize_bits;
blockres = (1 << blockbits) - 1;
buf->f_blocks = (res.tbytes + blockres) >> blockbits;
buf->f_bfree = (res.fbytes + blockres) >> blockbits;
buf->f_bavail = (res.abytes + blockres) >> blockbits;
buf->f_files = res.tfiles;
buf->f_ffree = res.afiles;
buf->f_namelen = server->namelen;
return 0;
out_err:
dprintk("%s: statfs error = %d\n", __func__, -error);
return error;
}
EXPORT_SYMBOL_GPL(nfs_statfs);
/*
* Map the security flavour number to a name
*/
static const char *nfs_pseudoflavour_to_name(rpc_authflavor_t flavour)
{
static const struct {
rpc_authflavor_t flavour;
const char *str;
} sec_flavours[NFS_AUTH_INFO_MAX_FLAVORS] = {
/* update NFS_AUTH_INFO_MAX_FLAVORS when this list changes! */
{ RPC_AUTH_NULL, "null" },
{ RPC_AUTH_UNIX, "sys" },
{ RPC_AUTH_GSS_KRB5, "krb5" },
{ RPC_AUTH_GSS_KRB5I, "krb5i" },
{ RPC_AUTH_GSS_KRB5P, "krb5p" },
{ RPC_AUTH_GSS_LKEY, "lkey" },
{ RPC_AUTH_GSS_LKEYI, "lkeyi" },
{ RPC_AUTH_GSS_LKEYP, "lkeyp" },
{ RPC_AUTH_GSS_SPKM, "spkm" },
{ RPC_AUTH_GSS_SPKMI, "spkmi" },
{ RPC_AUTH_GSS_SPKMP, "spkmp" },
{ UINT_MAX, "unknown" }
};
int i;
for (i = 0; sec_flavours[i].flavour != UINT_MAX; i++) {
if (sec_flavours[i].flavour == flavour)
break;
}
return sec_flavours[i].str;
}
static void nfs_show_mountd_netid(struct seq_file *m, struct nfs_server *nfss,
int showdefaults)
{
struct sockaddr *sap = (struct sockaddr *) &nfss->mountd_address;
char *proto = NULL;
switch (sap->sa_family) {
case AF_INET:
switch (nfss->mountd_protocol) {
case IPPROTO_UDP:
proto = RPCBIND_NETID_UDP;
break;
case IPPROTO_TCP:
proto = RPCBIND_NETID_TCP;
break;
}
break;
case AF_INET6:
switch (nfss->mountd_protocol) {
case IPPROTO_UDP:
proto = RPCBIND_NETID_UDP6;
break;
case IPPROTO_TCP:
proto = RPCBIND_NETID_TCP6;
break;
}
break;
}
if (proto || showdefaults)
seq_printf(m, ",mountproto=%s", proto ?: "auto");
}
static void nfs_show_mountd_options(struct seq_file *m, struct nfs_server *nfss,
int showdefaults)
{
struct sockaddr *sap = (struct sockaddr *)&nfss->mountd_address;
if (nfss->flags & NFS_MOUNT_LEGACY_INTERFACE)
return;
switch (sap->sa_family) {
case AF_INET: {
struct sockaddr_in *sin = (struct sockaddr_in *)sap;
seq_printf(m, ",mountaddr=%pI4", &sin->sin_addr.s_addr);
break;
}
case AF_INET6: {
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
seq_printf(m, ",mountaddr=%pI6c", &sin6->sin6_addr);
break;
}
default:
if (showdefaults)
seq_printf(m, ",mountaddr=unspecified");
}
if (nfss->mountd_version || showdefaults)
seq_printf(m, ",mountvers=%u", nfss->mountd_version);
if ((nfss->mountd_port &&
nfss->mountd_port != (unsigned short)NFS_UNSPEC_PORT) ||
showdefaults)
seq_printf(m, ",mountport=%u", nfss->mountd_port);
nfs_show_mountd_netid(m, nfss, showdefaults);
}
#if IS_ENABLED(CONFIG_NFS_V4)
static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
int showdefaults)
{
struct nfs_client *clp = nfss->nfs_client;
seq_printf(m, ",clientaddr=%s", clp->cl_ipaddr);
}
#else
static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
int showdefaults)
{
}
#endif
static void nfs_show_nfs_version(struct seq_file *m,
unsigned int version,
unsigned int minorversion)
{
seq_printf(m, ",vers=%u", version);
if (version == 4)
seq_printf(m, ".%u", minorversion);
}
/*
* Describe the mount options in force on this server representation
*/
static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
int showdefaults)
{
static const struct proc_nfs_info {
int flag;
const char *str;
const char *nostr;
} nfs_info[] = {
{ NFS_MOUNT_SOFT, ",soft", ",hard" },
{ NFS_MOUNT_POSIX, ",posix", "" },
{ NFS_MOUNT_NOCTO, ",nocto", "" },
{ NFS_MOUNT_NOAC, ",noac", "" },
{ NFS_MOUNT_NONLM, ",nolock", "" },
{ NFS_MOUNT_NOACL, ",noacl", "" },
{ NFS_MOUNT_NORDIRPLUS, ",nordirplus", "" },
NFS: add "[no]resvport" mount option The standard default security setting for NFS is AUTH_SYS. An NFS client connects to NFS servers via a privileged source port and a fixed standard destination port (2049). The client sends raw uid and gid numbers to identify users making NFS requests, and the server assumes an appropriate authority on the client has vetted these values because the source port is privileged. On Linux, by default in-kernel RPC services use a privileged port in the range between 650 and 1023 to avoid using source ports of well- known IP services. Using such a small range limits the number of NFS mount points and the number of unique NFS servers to which a client can connect concurrently. An NFS client can use unprivileged source ports to expand the range of source port numbers, allowing more concurrent server connections and more NFS mount points. Servers must explicitly allow NFS connections from unprivileged ports for this to work. In the past, bumping the value of the sunrpc.max_resvport sysctl on the client would permit the NFS client to use unprivileged ports. Bumping this setting also changes the maximum port number used by other in-kernel RPC services, some of which still required a port number less than 1023. This is exacerbated by the way source port numbers are chosen by the Linux RPC client, which starts at the top of the range and works downwards. It means that bumping the maximum means all RPC services requesting a source port will likely get an unprivileged port instead of a privileged one. Changing this setting effects all NFS mount points on a client. A sysadmin could not selectively choose which mount points would use non-privileged ports and which could not. Lastly, this mechanism of expanding the limit on the number of NFS mount points was entirely undocumented. To address the need for the NFS client to use a large range of source ports without interfering with the activity of other in-kernel RPC services, we introduce a new NFS mount option. This option explicitly tells only the NFS client to use a non-privileged source port when communicating with the NFS server for one specific mount point. This new mount option is called "resvport," like the similar NFS mount option on FreeBSD and Mac OS X. A sister patch for nfs-utils will be submitted that documents this new option in nfs(5). The default setting for this new mount option requires the NFS client to use a privileged port, as before. Explicitly specifying the "noresvport" mount option allows the NFS client to use an unprivileged source port for this mount point when connecting to the NFS server port. This mount option is supported only for text-based NFS mounts. [ Sidebar: it is widely known that security mechanisms based on the use of privileged source ports are ineffective. However, the NFS client can combine the use of unprivileged ports with the use of secure authentication mechanisms, such as Kerberos. This allows a large number of connections and mount points while ensuring a useful level of security. Eventually we may change the default setting for this option depending on the security flavor used for the mount. For example, if the mount is using only AUTH_SYS, then the default setting will be "resvport;" if the mount is using a strong security flavor such as krb5, the default setting will be "noresvport." ] Signed-off-by: Chuck Lever <chuck.lever@oracle.com> [Trond.Myklebust@netapp.com: Fixed a bug whereby nfs4_init_client() was being called with incorrect arguments.] Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-24 04:21:37 +08:00
{ NFS_MOUNT_UNSHARED, ",nosharecache", "" },
{ NFS_MOUNT_NORESVPORT, ",noresvport", "" },
{ 0, NULL, NULL }
};
const struct proc_nfs_info *nfs_infop;
struct nfs_client *clp = nfss->nfs_client;
u32 version = clp->rpc_ops->version;
int local_flock, local_fcntl;
nfs_show_nfs_version(m, version, clp->cl_minorversion);
seq_printf(m, ",rsize=%u", nfss->rsize);
seq_printf(m, ",wsize=%u", nfss->wsize);
if (nfss->bsize != 0)
seq_printf(m, ",bsize=%u", nfss->bsize);
seq_printf(m, ",namlen=%u", nfss->namelen);
if (nfss->acregmin != NFS_DEF_ACREGMIN*HZ || showdefaults)
seq_printf(m, ",acregmin=%u", nfss->acregmin/HZ);
if (nfss->acregmax != NFS_DEF_ACREGMAX*HZ || showdefaults)
seq_printf(m, ",acregmax=%u", nfss->acregmax/HZ);
if (nfss->acdirmin != NFS_DEF_ACDIRMIN*HZ || showdefaults)
seq_printf(m, ",acdirmin=%u", nfss->acdirmin/HZ);
if (nfss->acdirmax != NFS_DEF_ACDIRMAX*HZ || showdefaults)
seq_printf(m, ",acdirmax=%u", nfss->acdirmax/HZ);
for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) {
if (nfss->flags & nfs_infop->flag)
seq_puts(m, nfs_infop->str);
else
seq_puts(m, nfs_infop->nostr);
}
rcu_read_lock();
seq_printf(m, ",proto=%s",
rpc_peeraddr2str(nfss->client, RPC_DISPLAY_NETID));
rcu_read_unlock();
if (version == 4) {
if (nfss->port != NFS_PORT)
seq_printf(m, ",port=%u", nfss->port);
} else
if (nfss->port)
seq_printf(m, ",port=%u", nfss->port);
seq_printf(m, ",timeo=%lu", 10U * nfss->client->cl_timeout->to_initval / HZ);
seq_printf(m, ",retrans=%u", nfss->client->cl_timeout->to_retries);
seq_printf(m, ",sec=%s", nfs_pseudoflavour_to_name(nfss->client->cl_auth->au_flavor));
if (version != 4)
nfs_show_mountd_options(m, nfss, showdefaults);
else
nfs_show_nfsv4_options(m, nfss, showdefaults);
if (nfss->options & NFS_OPTION_FSCACHE)
seq_printf(m, ",fsc");
2012-09-15 05:24:11 +08:00
if (nfss->options & NFS_OPTION_MIGRATION)
seq_printf(m, ",migration");
if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) {
if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
seq_printf(m, ",lookupcache=none");
else
seq_printf(m, ",lookupcache=pos");
}
local_flock = nfss->flags & NFS_MOUNT_LOCAL_FLOCK;
local_fcntl = nfss->flags & NFS_MOUNT_LOCAL_FCNTL;
if (!local_flock && !local_fcntl)
seq_printf(m, ",local_lock=none");
else if (local_flock && local_fcntl)
seq_printf(m, ",local_lock=all");
else if (local_flock)
seq_printf(m, ",local_lock=flock");
else
seq_printf(m, ",local_lock=posix");
}
/*
* Describe the mount options on this VFS mountpoint
*/
int nfs_show_options(struct seq_file *m, struct dentry *root)
{
struct nfs_server *nfss = NFS_SB(root->d_sb);
nfs_show_mount_options(m, nfss, 0);
rcu_read_lock();
seq_printf(m, ",addr=%s",
rpc_peeraddr2str(nfss->nfs_client->cl_rpcclient,
RPC_DISPLAY_ADDR));
rcu_read_unlock();
return 0;
}
EXPORT_SYMBOL_GPL(nfs_show_options);
#if IS_ENABLED(CONFIG_NFS_V4)
#ifdef CONFIG_NFS_V4_1
static void show_sessions(struct seq_file *m, struct nfs_server *server)
{
if (nfs4_has_session(server->nfs_client))
seq_printf(m, ",sessions");
}
#else
static void show_sessions(struct seq_file *m, struct nfs_server *server) {}
#endif
#endif
#ifdef CONFIG_NFS_V4_1
static void show_pnfs(struct seq_file *m, struct nfs_server *server)
{
seq_printf(m, ",pnfs=");
if (server->pnfs_curr_ld)
seq_printf(m, "%s", server->pnfs_curr_ld->name);
else
seq_printf(m, "not configured");
}
static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
{
if (nfss->nfs_client && nfss->nfs_client->cl_implid) {
struct nfs41_impl_id *impl_id = nfss->nfs_client->cl_implid;
seq_printf(m, "\n\timpl_id:\tname='%s',domain='%s',"
"date='%llu,%u'",
impl_id->name, impl_id->domain,
impl_id->date.seconds, impl_id->date.nseconds);
}
}
#else
#if IS_ENABLED(CONFIG_NFS_V4)
static void show_pnfs(struct seq_file *m, struct nfs_server *server)
{
}
#endif
static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
{
}
#endif
int nfs_show_devname(struct seq_file *m, struct dentry *root)
{
char *page = (char *) __get_free_page(GFP_KERNEL);
char *devname, *dummy;
int err = 0;
if (!page)
return -ENOMEM;
devname = nfs_path(&dummy, root, page, PAGE_SIZE, 0);
if (IS_ERR(devname))
err = PTR_ERR(devname);
else
seq_escape(m, devname, " \t\n\\");
free_page((unsigned long)page);
return err;
}
EXPORT_SYMBOL_GPL(nfs_show_devname);
int nfs_show_path(struct seq_file *m, struct dentry *dentry)
{
seq_puts(m, "/");
return 0;
}
EXPORT_SYMBOL_GPL(nfs_show_path);
/*
* Present statistical information for this VFS mountpoint
*/
int nfs_show_stats(struct seq_file *m, struct dentry *root)
{
int i, cpu;
struct nfs_server *nfss = NFS_SB(root->d_sb);
struct rpc_auth *auth = nfss->client->cl_auth;
struct nfs_iostats totals = { };
seq_printf(m, "statvers=%s", NFS_IOSTAT_VERS);
/*
* Display all mount option settings
*/
seq_printf(m, "\n\topts:\t");
seq_puts(m, root->d_sb->s_flags & MS_RDONLY ? "ro" : "rw");
seq_puts(m, root->d_sb->s_flags & MS_SYNCHRONOUS ? ",sync" : "");
seq_puts(m, root->d_sb->s_flags & MS_NOATIME ? ",noatime" : "");
seq_puts(m, root->d_sb->s_flags & MS_NODIRATIME ? ",nodiratime" : "");
nfs_show_mount_options(m, nfss, 1);
seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ);
show_implementation_id(m, nfss);
seq_printf(m, "\n\tcaps:\t");
seq_printf(m, "caps=0x%x", nfss->caps);
seq_printf(m, ",wtmult=%u", nfss->wtmult);
seq_printf(m, ",dtsize=%u", nfss->dtsize);
seq_printf(m, ",bsize=%u", nfss->bsize);
seq_printf(m, ",namlen=%u", nfss->namelen);
#if IS_ENABLED(CONFIG_NFS_V4)
if (nfss->nfs_client->rpc_ops->version == 4) {
seq_printf(m, "\n\tnfsv4:\t");
seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]);
seq_printf(m, ",bm1=0x%x", nfss->attr_bitmask[1]);
seq_printf(m, ",bm2=0x%x", nfss->attr_bitmask[2]);
seq_printf(m, ",acl=0x%x", nfss->acl_bitmask);
show_sessions(m, nfss);
show_pnfs(m, nfss);
}
#endif
/*
* Display security flavor in effect for this mount
*/
seq_printf(m, "\n\tsec:\tflavor=%u", auth->au_ops->au_flavor);
if (auth->au_flavor)
seq_printf(m, ",pseudoflavor=%u", auth->au_flavor);
/*
* Display superblock I/O counters
*/
for_each_possible_cpu(cpu) {
struct nfs_iostats *stats;
preempt_disable();
stats = per_cpu_ptr(nfss->io_stats, cpu);
for (i = 0; i < __NFSIOS_COUNTSMAX; i++)
totals.events[i] += stats->events[i];
for (i = 0; i < __NFSIOS_BYTESMAX; i++)
totals.bytes[i] += stats->bytes[i];
#ifdef CONFIG_NFS_FSCACHE
for (i = 0; i < __NFSIOS_FSCACHEMAX; i++)
totals.fscache[i] += stats->fscache[i];
#endif
preempt_enable();
}
seq_printf(m, "\n\tevents:\t");
for (i = 0; i < __NFSIOS_COUNTSMAX; i++)
seq_printf(m, "%lu ", totals.events[i]);
seq_printf(m, "\n\tbytes:\t");
for (i = 0; i < __NFSIOS_BYTESMAX; i++)
seq_printf(m, "%Lu ", totals.bytes[i]);
#ifdef CONFIG_NFS_FSCACHE
if (nfss->options & NFS_OPTION_FSCACHE) {
seq_printf(m, "\n\tfsc:\t");
for (i = 0; i < __NFSIOS_FSCACHEMAX; i++)
seq_printf(m, "%Lu ", totals.fscache[i]);
}
#endif
seq_printf(m, "\n");
rpc_print_iostats(m, nfss->client);
return 0;
}
EXPORT_SYMBOL_GPL(nfs_show_stats);
/*
* Begin unmount by attempting to remove all automounted mountpoints we added
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
* in response to xdev traversals and referrals
*/
void nfs_umount_begin(struct super_block *sb)
{
struct nfs_server *server;
struct rpc_clnt *rpc;
server = NFS_SB(sb);
/* -EIO all pending I/O */
rpc = server->client_acl;
if (!IS_ERR(rpc))
rpc_killall_tasks(rpc);
rpc = server->client;
if (!IS_ERR(rpc))
rpc_killall_tasks(rpc);
}
EXPORT_SYMBOL_GPL(nfs_umount_begin);
static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void)
{
struct nfs_parsed_mount_data *data;
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (data) {
data->timeo = NFS_UNSPEC_TIMEO;
data->retrans = NFS_UNSPEC_RETRANS;
data->acregmin = NFS_DEF_ACREGMIN;
data->acregmax = NFS_DEF_ACREGMAX;
data->acdirmin = NFS_DEF_ACDIRMIN;
data->acdirmax = NFS_DEF_ACDIRMAX;
data->mount_server.port = NFS_UNSPEC_PORT;
data->nfs_server.port = NFS_UNSPEC_PORT;
data->nfs_server.protocol = XPRT_TRANSPORT_TCP;
data->selected_flavor = RPC_AUTH_MAXFLAVOR;
data->minorversion = 0;
data->need_mount = true;
data->net = current->nsproxy->net_ns;
security_init_mnt_opts(&data->lsm_opts);
}
return data;
}
static void nfs_free_parsed_mount_data(struct nfs_parsed_mount_data *data)
{
if (data) {
kfree(data->client_address);
kfree(data->mount_server.hostname);
kfree(data->nfs_server.export_path);
kfree(data->nfs_server.hostname);
kfree(data->fscache_uniq);
security_free_mnt_opts(&data->lsm_opts);
kfree(data);
}
}
/*
* Sanity-check a server address provided by the mount command.
*
* Address family must be initialized, and address must not be
* the ANY address for that family.
*/
static int nfs_verify_server_address(struct sockaddr *addr)
{
switch (addr->sa_family) {
case AF_INET: {
struct sockaddr_in *sa = (struct sockaddr_in *)addr;
return sa->sin_addr.s_addr != htonl(INADDR_ANY);
}
case AF_INET6: {
struct in6_addr *sa = &((struct sockaddr_in6 *)addr)->sin6_addr;
return !ipv6_addr_any(sa);
}
}
dfprintk(MOUNT, "NFS: Invalid IP address specified\n");
return 0;
}
/*
* Select between a default port value and a user-specified port value.
* If a zero value is set, then autobind will be used.
*/
static void nfs_set_port(struct sockaddr *sap, int *port,
const unsigned short default_port)
{
if (*port == NFS_UNSPEC_PORT)
*port = default_port;
rpc_set_port(sap, *port);
}
/*
* Sanity check the NFS transport protocol.
*
*/
static void nfs_validate_transport_protocol(struct nfs_parsed_mount_data *mnt)
{
switch (mnt->nfs_server.protocol) {
case XPRT_TRANSPORT_UDP:
case XPRT_TRANSPORT_TCP:
case XPRT_TRANSPORT_RDMA:
break;
default:
mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP;
}
}
/*
* For text based NFSv2/v3 mounts, the mount protocol transport default
* settings should depend upon the specified NFS transport.
*/
static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt)
{
nfs_validate_transport_protocol(mnt);
if (mnt->mount_server.protocol == XPRT_TRANSPORT_UDP ||
mnt->mount_server.protocol == XPRT_TRANSPORT_TCP)
return;
switch (mnt->nfs_server.protocol) {
case XPRT_TRANSPORT_UDP:
mnt->mount_server.protocol = XPRT_TRANSPORT_UDP;
break;
case XPRT_TRANSPORT_TCP:
case XPRT_TRANSPORT_RDMA:
mnt->mount_server.protocol = XPRT_TRANSPORT_TCP;
}
}
/*
* Add 'flavor' to 'auth_info' if not already present.
* Returns true if 'flavor' ends up in the list, false otherwise
*/
static bool nfs_auth_info_add(struct nfs_auth_info *auth_info,
rpc_authflavor_t flavor)
{
unsigned int i;
unsigned int max_flavor_len = ARRAY_SIZE(auth_info->flavors);
/* make sure this flavor isn't already in the list */
for (i = 0; i < auth_info->flavor_len; i++) {
if (flavor == auth_info->flavors[i])
return true;
}
if (auth_info->flavor_len + 1 >= max_flavor_len) {
dfprintk(MOUNT, "NFS: too many sec= flavors\n");
return false;
}
auth_info->flavors[auth_info->flavor_len++] = flavor;
return true;
}
/*
* Return true if 'match' is in auth_info or auth_info is empty.
* Return false otherwise.
*/
bool nfs_auth_info_match(const struct nfs_auth_info *auth_info,
rpc_authflavor_t match)
{
int i;
if (!auth_info->flavor_len)
return true;
for (i = 0; i < auth_info->flavor_len; i++) {
if (auth_info->flavors[i] == match)
return true;
}
return false;
}
EXPORT_SYMBOL_GPL(nfs_auth_info_match);
/*
* Parse the value of the 'sec=' option.
*/
static int nfs_parse_security_flavors(char *value,
struct nfs_parsed_mount_data *mnt)
{
substring_t args[MAX_OPT_ARGS];
rpc_authflavor_t pseudoflavor;
char *p;
dfprintk(MOUNT, "NFS: parsing sec=%s option\n", value);
while ((p = strsep(&value, ":")) != NULL) {
switch (match_token(p, nfs_secflavor_tokens, args)) {
case Opt_sec_none:
pseudoflavor = RPC_AUTH_NULL;
break;
case Opt_sec_sys:
pseudoflavor = RPC_AUTH_UNIX;
break;
case Opt_sec_krb5:
pseudoflavor = RPC_AUTH_GSS_KRB5;
break;
case Opt_sec_krb5i:
pseudoflavor = RPC_AUTH_GSS_KRB5I;
break;
case Opt_sec_krb5p:
pseudoflavor = RPC_AUTH_GSS_KRB5P;
break;
case Opt_sec_lkey:
pseudoflavor = RPC_AUTH_GSS_LKEY;
break;
case Opt_sec_lkeyi:
pseudoflavor = RPC_AUTH_GSS_LKEYI;
break;
case Opt_sec_lkeyp:
pseudoflavor = RPC_AUTH_GSS_LKEYP;
break;
case Opt_sec_spkm:
pseudoflavor = RPC_AUTH_GSS_SPKM;
break;
case Opt_sec_spkmi:
pseudoflavor = RPC_AUTH_GSS_SPKMI;
break;
case Opt_sec_spkmp:
pseudoflavor = RPC_AUTH_GSS_SPKMP;
break;
default:
dfprintk(MOUNT,
"NFS: sec= option '%s' not recognized\n", p);
return 0;
}
if (!nfs_auth_info_add(&mnt->auth_info, pseudoflavor))
return 0;
}
return 1;
}
static int nfs_parse_version_string(char *string,
struct nfs_parsed_mount_data *mnt,
substring_t *args)
{
mnt->flags &= ~NFS_MOUNT_VER3;
switch (match_token(string, nfs_vers_tokens, args)) {
case Opt_vers_2:
mnt->version = 2;
break;
case Opt_vers_3:
mnt->flags |= NFS_MOUNT_VER3;
mnt->version = 3;
break;
case Opt_vers_4:
/* Backward compatibility option. In future,
* the mount program should always supply
* a NFSv4 minor version number.
*/
mnt->version = 4;
break;
case Opt_vers_4_0:
mnt->version = 4;
mnt->minorversion = 0;
break;
case Opt_vers_4_1:
mnt->version = 4;
mnt->minorversion = 1;
break;
case Opt_vers_4_2:
mnt->version = 4;
mnt->minorversion = 2;
break;
default:
return 0;
}
return 1;
}
static int nfs_get_option_str(substring_t args[], char **option)
{
kfree(*option);
*option = match_strdup(args);
return !*option;
}
static int nfs_get_option_ul(substring_t args[], unsigned long *option)
{
int rc;
char *string;
string = match_strdup(args);
if (string == NULL)
return -ENOMEM;
rc = kstrtoul(string, 10, option);
kfree(string);
return rc;
}
static int nfs_get_option_ul_bound(substring_t args[], unsigned long *option,
unsigned long l_bound, unsigned long u_bound)
{
int ret;
ret = nfs_get_option_ul(args, option);
if (ret != 0)
return ret;
if (*option < l_bound || *option > u_bound)
return -ERANGE;
return 0;
}
/*
* Error-check and convert a string of mount options from user space into
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
* a data structure. The whole mount string is processed; bad options are
* skipped as they are encountered. If there were no errors, return 1;
* otherwise return 0 (zero).
*/
static int nfs_parse_mount_options(char *raw,
struct nfs_parsed_mount_data *mnt)
{
char *p, *string, *secdata;
int rc, sloppy = 0, invalid_option = 0;
unsigned short protofamily = AF_UNSPEC;
unsigned short mountfamily = AF_UNSPEC;
if (!raw) {
dfprintk(MOUNT, "NFS: mount options string was NULL.\n");
return 1;
}
dfprintk(MOUNT, "NFS: nfs mount opts='%s'\n", raw);
secdata = alloc_secdata();
if (!secdata)
goto out_nomem;
rc = security_sb_copy_data(raw, secdata);
if (rc)
goto out_security_failure;
rc = security_sb_parse_opts_str(secdata, &mnt->lsm_opts);
if (rc)
goto out_security_failure;
free_secdata(secdata);
while ((p = strsep(&raw, ",")) != NULL) {
substring_t args[MAX_OPT_ARGS];
unsigned long option;
int token;
if (!*p)
continue;
dfprintk(MOUNT, "NFS: parsing nfs mount option '%s'\n", p);
token = match_token(p, nfs_mount_option_tokens, args);
switch (token) {
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
/*
* boolean options: foo/nofoo
*/
case Opt_soft:
mnt->flags |= NFS_MOUNT_SOFT;
break;
case Opt_hard:
mnt->flags &= ~NFS_MOUNT_SOFT;
break;
case Opt_posix:
mnt->flags |= NFS_MOUNT_POSIX;
break;
case Opt_noposix:
mnt->flags &= ~NFS_MOUNT_POSIX;
break;
case Opt_cto:
mnt->flags &= ~NFS_MOUNT_NOCTO;
break;
case Opt_nocto:
mnt->flags |= NFS_MOUNT_NOCTO;
break;
case Opt_ac:
mnt->flags &= ~NFS_MOUNT_NOAC;
break;
case Opt_noac:
mnt->flags |= NFS_MOUNT_NOAC;
break;
case Opt_lock:
mnt->flags &= ~NFS_MOUNT_NONLM;
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 20:55:58 +08:00
mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK |
NFS_MOUNT_LOCAL_FCNTL);
break;
case Opt_nolock:
mnt->flags |= NFS_MOUNT_NONLM;
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 20:55:58 +08:00
mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK |
NFS_MOUNT_LOCAL_FCNTL);
break;
case Opt_udp:
mnt->flags &= ~NFS_MOUNT_TCP;
mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
break;
case Opt_tcp:
mnt->flags |= NFS_MOUNT_TCP;
mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP;
break;
case Opt_rdma:
mnt->flags |= NFS_MOUNT_TCP; /* for side protocols */
mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA;
xprt_load_transport(p);
break;
case Opt_acl:
mnt->flags &= ~NFS_MOUNT_NOACL;
break;
case Opt_noacl:
mnt->flags |= NFS_MOUNT_NOACL;
break;
case Opt_rdirplus:
mnt->flags &= ~NFS_MOUNT_NORDIRPLUS;
break;
case Opt_nordirplus:
mnt->flags |= NFS_MOUNT_NORDIRPLUS;
break;
case Opt_sharecache:
mnt->flags &= ~NFS_MOUNT_UNSHARED;
break;
case Opt_nosharecache:
mnt->flags |= NFS_MOUNT_UNSHARED;
break;
NFS: add "[no]resvport" mount option The standard default security setting for NFS is AUTH_SYS. An NFS client connects to NFS servers via a privileged source port and a fixed standard destination port (2049). The client sends raw uid and gid numbers to identify users making NFS requests, and the server assumes an appropriate authority on the client has vetted these values because the source port is privileged. On Linux, by default in-kernel RPC services use a privileged port in the range between 650 and 1023 to avoid using source ports of well- known IP services. Using such a small range limits the number of NFS mount points and the number of unique NFS servers to which a client can connect concurrently. An NFS client can use unprivileged source ports to expand the range of source port numbers, allowing more concurrent server connections and more NFS mount points. Servers must explicitly allow NFS connections from unprivileged ports for this to work. In the past, bumping the value of the sunrpc.max_resvport sysctl on the client would permit the NFS client to use unprivileged ports. Bumping this setting also changes the maximum port number used by other in-kernel RPC services, some of which still required a port number less than 1023. This is exacerbated by the way source port numbers are chosen by the Linux RPC client, which starts at the top of the range and works downwards. It means that bumping the maximum means all RPC services requesting a source port will likely get an unprivileged port instead of a privileged one. Changing this setting effects all NFS mount points on a client. A sysadmin could not selectively choose which mount points would use non-privileged ports and which could not. Lastly, this mechanism of expanding the limit on the number of NFS mount points was entirely undocumented. To address the need for the NFS client to use a large range of source ports without interfering with the activity of other in-kernel RPC services, we introduce a new NFS mount option. This option explicitly tells only the NFS client to use a non-privileged source port when communicating with the NFS server for one specific mount point. This new mount option is called "resvport," like the similar NFS mount option on FreeBSD and Mac OS X. A sister patch for nfs-utils will be submitted that documents this new option in nfs(5). The default setting for this new mount option requires the NFS client to use a privileged port, as before. Explicitly specifying the "noresvport" mount option allows the NFS client to use an unprivileged source port for this mount point when connecting to the NFS server port. This mount option is supported only for text-based NFS mounts. [ Sidebar: it is widely known that security mechanisms based on the use of privileged source ports are ineffective. However, the NFS client can combine the use of unprivileged ports with the use of secure authentication mechanisms, such as Kerberos. This allows a large number of connections and mount points while ensuring a useful level of security. Eventually we may change the default setting for this option depending on the security flavor used for the mount. For example, if the mount is using only AUTH_SYS, then the default setting will be "resvport;" if the mount is using a strong security flavor such as krb5, the default setting will be "noresvport." ] Signed-off-by: Chuck Lever <chuck.lever@oracle.com> [Trond.Myklebust@netapp.com: Fixed a bug whereby nfs4_init_client() was being called with incorrect arguments.] Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-12-24 04:21:37 +08:00
case Opt_resvport:
mnt->flags &= ~NFS_MOUNT_NORESVPORT;
break;
case Opt_noresvport:
mnt->flags |= NFS_MOUNT_NORESVPORT;
break;
case Opt_fscache:
mnt->options |= NFS_OPTION_FSCACHE;
kfree(mnt->fscache_uniq);
mnt->fscache_uniq = NULL;
break;
case Opt_nofscache:
mnt->options &= ~NFS_OPTION_FSCACHE;
kfree(mnt->fscache_uniq);
mnt->fscache_uniq = NULL;
break;
2012-09-15 05:24:11 +08:00
case Opt_migration:
mnt->options |= NFS_OPTION_MIGRATION;
break;
case Opt_nomigration:
mnt->options &= NFS_OPTION_MIGRATION;
break;
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
/*
* options that take numeric values
*/
case Opt_port:
if (nfs_get_option_ul(args, &option) ||
option > USHRT_MAX)
goto out_invalid_value;
mnt->nfs_server.port = option;
break;
case Opt_rsize:
if (nfs_get_option_ul(args, &option))
goto out_invalid_value;
mnt->rsize = option;
break;
case Opt_wsize:
if (nfs_get_option_ul(args, &option))
goto out_invalid_value;
mnt->wsize = option;
break;
case Opt_bsize:
if (nfs_get_option_ul(args, &option))
goto out_invalid_value;
mnt->bsize = option;
break;
case Opt_timeo:
if (nfs_get_option_ul_bound(args, &option, 1, INT_MAX))
goto out_invalid_value;
mnt->timeo = option;
break;
case Opt_retrans:
if (nfs_get_option_ul_bound(args, &option, 0, INT_MAX))
goto out_invalid_value;
mnt->retrans = option;
break;
case Opt_acregmin:
if (nfs_get_option_ul(args, &option))
goto out_invalid_value;
mnt->acregmin = option;
break;
case Opt_acregmax:
if (nfs_get_option_ul(args, &option))
goto out_invalid_value;
mnt->acregmax = option;
break;
case Opt_acdirmin:
if (nfs_get_option_ul(args, &option))
goto out_invalid_value;
mnt->acdirmin = option;
break;
case Opt_acdirmax:
if (nfs_get_option_ul(args, &option))
goto out_invalid_value;
mnt->acdirmax = option;
break;
case Opt_actimeo:
if (nfs_get_option_ul(args, &option))
goto out_invalid_value;
mnt->acregmin = mnt->acregmax =
mnt->acdirmin = mnt->acdirmax = option;
break;
case Opt_namelen:
if (nfs_get_option_ul(args, &option))
goto out_invalid_value;
mnt->namlen = option;
break;
case Opt_mountport:
if (nfs_get_option_ul(args, &option) ||
option > USHRT_MAX)
goto out_invalid_value;
mnt->mount_server.port = option;
break;
case Opt_mountvers:
if (nfs_get_option_ul(args, &option) ||
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
option < NFS_MNT_VERSION ||
option > NFS_MNT3_VERSION)
goto out_invalid_value;
mnt->mount_server.version = option;
break;
case Opt_minorversion:
if (nfs_get_option_ul(args, &option))
goto out_invalid_value;
if (option > NFS4_MAX_MINOR_VERSION)
goto out_invalid_value;
mnt->minorversion = option;
break;
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
/*
* options that take text values
*/
case Opt_nfsvers:
string = match_strdup(args);
if (string == NULL)
goto out_nomem;
rc = nfs_parse_version_string(string, mnt, args);
kfree(string);
if (!rc)
goto out_invalid_value;
break;
case Opt_sec:
string = match_strdup(args);
if (string == NULL)
goto out_nomem;
rc = nfs_parse_security_flavors(string, mnt);
kfree(string);
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
if (!rc) {
dfprintk(MOUNT, "NFS: unrecognized "
"security flavor\n");
return 0;
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
}
break;
case Opt_proto:
string = match_strdup(args);
if (string == NULL)
goto out_nomem;
token = match_token(string,
nfs_xprt_protocol_tokens, args);
protofamily = AF_INET;
switch (token) {
case Opt_xprt_udp6:
protofamily = AF_INET6;
case Opt_xprt_udp:
mnt->flags &= ~NFS_MOUNT_TCP;
mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
break;
case Opt_xprt_tcp6:
protofamily = AF_INET6;
case Opt_xprt_tcp:
mnt->flags |= NFS_MOUNT_TCP;
mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP;
break;
case Opt_xprt_rdma6:
protofamily = AF_INET6;
case Opt_xprt_rdma:
/* vector side protocols to TCP */
mnt->flags |= NFS_MOUNT_TCP;
mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA;
xprt_load_transport(string);
break;
default:
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
dfprintk(MOUNT, "NFS: unrecognized "
"transport protocol\n");
kfree(string);
return 0;
}
kfree(string);
break;
case Opt_mountproto:
string = match_strdup(args);
if (string == NULL)
goto out_nomem;
token = match_token(string,
nfs_xprt_protocol_tokens, args);
kfree(string);
mountfamily = AF_INET;
switch (token) {
case Opt_xprt_udp6:
mountfamily = AF_INET6;
case Opt_xprt_udp:
mnt->mount_server.protocol = XPRT_TRANSPORT_UDP;
break;
case Opt_xprt_tcp6:
mountfamily = AF_INET6;
case Opt_xprt_tcp:
mnt->mount_server.protocol = XPRT_TRANSPORT_TCP;
break;
case Opt_xprt_rdma: /* not used for side protocols */
default:
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
dfprintk(MOUNT, "NFS: unrecognized "
"transport protocol\n");
return 0;
}
break;
case Opt_addr:
string = match_strdup(args);
if (string == NULL)
goto out_nomem;
mnt->nfs_server.addrlen =
rpc_pton(mnt->net, string, strlen(string),
(struct sockaddr *)
&mnt->nfs_server.address,
sizeof(mnt->nfs_server.address));
kfree(string);
if (mnt->nfs_server.addrlen == 0)
goto out_invalid_address;
break;
case Opt_clientaddr:
if (nfs_get_option_str(args, &mnt->client_address))
goto out_nomem;
break;
case Opt_mounthost:
if (nfs_get_option_str(args,
&mnt->mount_server.hostname))
goto out_nomem;
break;
case Opt_mountaddr:
string = match_strdup(args);
if (string == NULL)
goto out_nomem;
mnt->mount_server.addrlen =
rpc_pton(mnt->net, string, strlen(string),
(struct sockaddr *)
&mnt->mount_server.address,
sizeof(mnt->mount_server.address));
kfree(string);
if (mnt->mount_server.addrlen == 0)
goto out_invalid_address;
break;
case Opt_lookupcache:
string = match_strdup(args);
if (string == NULL)
goto out_nomem;
token = match_token(string,
nfs_lookupcache_tokens, args);
kfree(string);
switch (token) {
case Opt_lookupcache_all:
mnt->flags &= ~(NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE);
break;
case Opt_lookupcache_positive:
mnt->flags &= ~NFS_MOUNT_LOOKUP_CACHE_NONE;
mnt->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG;
break;
case Opt_lookupcache_none:
mnt->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE;
break;
default:
dfprintk(MOUNT, "NFS: invalid "
"lookupcache argument\n");
return 0;
};
break;
case Opt_fscache_uniq:
if (nfs_get_option_str(args, &mnt->fscache_uniq))
goto out_nomem;
mnt->options |= NFS_OPTION_FSCACHE;
break;
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 20:55:58 +08:00
case Opt_local_lock:
string = match_strdup(args);
if (string == NULL)
goto out_nomem;
token = match_token(string, nfs_local_lock_tokens,
args);
kfree(string);
switch (token) {
case Opt_local_lock_all:
mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK |
NFS_MOUNT_LOCAL_FCNTL);
break;
case Opt_local_lock_flock:
mnt->flags |= NFS_MOUNT_LOCAL_FLOCK;
break;
case Opt_local_lock_posix:
mnt->flags |= NFS_MOUNT_LOCAL_FCNTL;
break;
case Opt_local_lock_none:
mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK |
NFS_MOUNT_LOCAL_FCNTL);
break;
default:
dfprintk(MOUNT, "NFS: invalid "
"local_lock argument\n");
return 0;
};
break;
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
/*
* Special options
*/
case Opt_sloppy:
sloppy = 1;
dfprintk(MOUNT, "NFS: relaxing parsing rules\n");
break;
case Opt_userspace:
case Opt_deprecated:
dfprintk(MOUNT, "NFS: ignoring mount option "
"'%s'\n", p);
break;
default:
invalid_option = 1;
NFS: Allow either strict or sloppy mount option parsing The kernel's NFS client mount option parser currently doesn't allow unrecognized or incorrect mount options. This prevents misspellings or incorrectly specified mount options from possibly causing silent data corruption. However, NFS mount options are not standardized, so different operating systems can use differently spelled mount options to support similar features, or can support mount options which no other operating system supports. "Sloppy" mount option parsing, which allows the parser to ignore any option it doesn't recognize, is needed to support automounters that often use maps that are shared between heterogenous operating systems. The legacy mount command ignores the validity of the values of mount options entirely, except for the "sec=" and "proto=" options. If an incorrect value is specified, the out-of-range value is passed to the kernel; if a value is specified that contains non-numeric characters, it appears as though the legacy mount command sets that option to zero (probably incorrect behavior in general). In any case, this sets a precedent which we will partially follow for the kernel mount option parser: + if "sloppy" is not set, the parser will be strict about both unrecognized options (same as legacy) and invalid option values (stricter than legacy) + if "sloppy" is set, the parser will ignore unrecognized options and invalid option values (same as legacy) An "invalid" option value in this case means that either the type (integer, short, or string) or sign (for integer values) of the specified value is incorrect. This patch does two things: it changes the NFS client's mount option parsing loop so that it parses the whole string instead of failing at the first unrecognized option or invalid option value. An unrecognized option or an invalid option value cause the option to be skipped. Then, the patch adds a "sloppy" mount option that allows the parsing to succeed anyway if there were any problems during parsing. When parsing a set of options is complete, if there are errors and "sloppy" was specified, return success anyway. Otherwise, only return success if there are no errors. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-06-25 07:28:02 +08:00
dfprintk(MOUNT, "NFS: unrecognized mount option "
"'%s'\n", p);
}
}
if (!sloppy && invalid_option)
return 0;
if (mnt->minorversion && mnt->version != 4)
goto out_minorversion_mismatch;
2012-09-15 05:24:11 +08:00
if (mnt->options & NFS_OPTION_MIGRATION &&
(mnt->version != 4 || mnt->minorversion != 0))
2012-09-15 05:24:11 +08:00
goto out_migration_misuse;
/*
* verify that any proto=/mountproto= options match the address
* families in the addr=/mountaddr= options.
*/
if (protofamily != AF_UNSPEC &&
protofamily != mnt->nfs_server.address.ss_family)
goto out_proto_mismatch;
if (mountfamily != AF_UNSPEC) {
if (mnt->mount_server.addrlen) {
if (mountfamily != mnt->mount_server.address.ss_family)
goto out_mountproto_mismatch;
} else {
if (mountfamily != mnt->nfs_server.address.ss_family)
goto out_mountproto_mismatch;
}
}
return 1;
out_mountproto_mismatch:
printk(KERN_INFO "NFS: mount server address does not match mountproto= "
"option\n");
return 0;
out_proto_mismatch:
printk(KERN_INFO "NFS: server address does not match proto= option\n");
return 0;
out_invalid_address:
printk(KERN_INFO "NFS: bad IP address specified: %s\n", p);
return 0;
out_invalid_value:
printk(KERN_INFO "NFS: bad mount option value specified: %s\n", p);
return 0;
out_minorversion_mismatch:
printk(KERN_INFO "NFS: mount option vers=%u does not support "
"minorversion=%u\n", mnt->version, mnt->minorversion);
return 0;
2012-09-15 05:24:11 +08:00
out_migration_misuse:
printk(KERN_INFO
"NFS: 'migration' not supported for this NFS version\n");
return 0;
out_nomem:
printk(KERN_INFO "NFS: not enough memory to parse option\n");
return 0;
out_security_failure:
free_secdata(secdata);
printk(KERN_INFO "NFS: security options invalid: %d\n", rc);
return 0;
}
/*
* Ensure that a specified authtype in args->auth_info is supported by
* the server. Returns 0 and sets args->selected_flavor if it's ok, and
* -EACCES if not.
*/
static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args,
rpc_authflavor_t *server_authlist, unsigned int count)
{
rpc_authflavor_t flavor = RPC_AUTH_MAXFLAVOR;
unsigned int i;
int use_auth_null = false;
NFS: Use server-recommended security flavor by default (NFSv3) Since commit ec88f28d in 2009, checking if the user-specified flavor is in the server's flavor list has been the source of a few noticeable regressions (now fixed), but there is one that is still vexing. An NFS server can list AUTH_NULL in its flavor list, which suggests a client should try to mount the server with the flavor of the client's choice, but the server will squash all accesses. In some cases, our client fails to mount a server because of this check, when the mount could have proceeded successfully. Skip this check if the user has specified "sec=" on the mount command line. But do consult the server-provided flavor list to choose a security flavor if no sec= option is specified on the mount command. If a server lists Kerberos pseudoflavors before "sys" in its export options, our client now chooses Kerberos over AUTH_UNIX for mount points, when no security flavor is specified by the mount command. This could be surprising to some administrators or users, who would then need to have Kerberos credentials to access the export. Or, a client administrator may not have enabled rpc.gssd. In this case, auth_rpcgss.ko might still be loadable, which is enough for the new logic to choose Kerberos over AUTH_UNIX. But the mount would fail since no GSS context can be created without rpc.gssd running. To retain the use of AUTH_UNIX by default: o The server administrator can ensure that "sys" is listed before Kerberos flavors in its export security options (see exports(5)), o The client administrator can explicitly specify "sec=sys" on its mount command line (see nfs(5)), o The client administrator can use "Sec=sys" in an appropriate section of /etc/nfsmount.conf (see nfsmount.conf(5)), or o The client administrator can blacklist auth_rpcgss.ko. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-03-23 00:53:17 +08:00
NFSv3: match sec= flavor against server list Older linux clients match the 'sec=' mount option flavor against the server's flavor list (if available) and return EPERM if the specified flavor or AUTH_NULL (which "matches" any flavor) is not found. Recent changes skip this step and allow the vfs mount even though no operations will succeed, creating a 'dud' mount. This patch reverts back to the old behavior of matching specified flavors against the server list and also returns EPERM when no sec= is specified and none of the flavors returned by the server are supported by the client. Example of behavior change: the server's /etc/exports: /export/krb5 *(sec=krb5,rw,no_root_squash) old client behavior: $ uname -a Linux one.apikia.fake 3.8.8-202.fc18.x86_64 #1 SMP Wed Apr 17 23:25:17 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux $ sudo mount -v -o sec=sys,vers=3 zero:/export/krb5 /mnt mount.nfs: timeout set for Sun May 5 17:32:04 2013 mount.nfs: trying text-based options 'sec=sys,vers=3,addr=192.168.100.10' mount.nfs: prog 100003, trying vers=3, prot=6 mount.nfs: trying 192.168.100.10 prog 100003 vers 3 prot TCP port 2049 mount.nfs: prog 100005, trying vers=3, prot=17 mount.nfs: trying 192.168.100.10 prog 100005 vers 3 prot UDP port 20048 mount.nfs: mount(2): Permission denied mount.nfs: access denied by server while mounting zero:/export/krb5 recently changed behavior: $ uname -a Linux one.apikia.fake 3.9.0-testing+ #2 SMP Fri May 3 20:29:32 EDT 2013 x86_64 x86_64 x86_64 GNU/Linux $ sudo mount -v -o sec=sys,vers=3 zero:/export/krb5 /mnt mount.nfs: timeout set for Sun May 5 17:37:17 2013 mount.nfs: trying text-based options 'sec=sys,vers=3,addr=192.168.100.10' mount.nfs: prog 100003, trying vers=3, prot=6 mount.nfs: trying 192.168.100.10 prog 100003 vers 3 prot TCP port 2049 mount.nfs: prog 100005, trying vers=3, prot=17 mount.nfs: trying 192.168.100.10 prog 100005 vers 3 prot UDP port 20048 $ ls /mnt ls: cannot open directory /mnt: Permission denied $ sudo ls /mnt ls: cannot open directory /mnt: Permission denied $ sudo df /mnt df: ‘/mnt’: Permission denied df: no file systems processed $ sudo umount /mnt $ Signed-off-by: Weston Andros Adamson <dros@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-05-07 05:12:13 +08:00
/*
* If the sec= mount option is used, the specified flavor or AUTH_NULL
* must be in the list returned by the server.
*
* AUTH_NULL has a special meaning when it's in the server list - it
* means that the server will ignore the rpc creds, so any flavor
* can be used but still use the sec= that was specified.
NFSv3: match sec= flavor against server list Older linux clients match the 'sec=' mount option flavor against the server's flavor list (if available) and return EPERM if the specified flavor or AUTH_NULL (which "matches" any flavor) is not found. Recent changes skip this step and allow the vfs mount even though no operations will succeed, creating a 'dud' mount. This patch reverts back to the old behavior of matching specified flavors against the server list and also returns EPERM when no sec= is specified and none of the flavors returned by the server are supported by the client. Example of behavior change: the server's /etc/exports: /export/krb5 *(sec=krb5,rw,no_root_squash) old client behavior: $ uname -a Linux one.apikia.fake 3.8.8-202.fc18.x86_64 #1 SMP Wed Apr 17 23:25:17 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux $ sudo mount -v -o sec=sys,vers=3 zero:/export/krb5 /mnt mount.nfs: timeout set for Sun May 5 17:32:04 2013 mount.nfs: trying text-based options 'sec=sys,vers=3,addr=192.168.100.10' mount.nfs: prog 100003, trying vers=3, prot=6 mount.nfs: trying 192.168.100.10 prog 100003 vers 3 prot TCP port 2049 mount.nfs: prog 100005, trying vers=3, prot=17 mount.nfs: trying 192.168.100.10 prog 100005 vers 3 prot UDP port 20048 mount.nfs: mount(2): Permission denied mount.nfs: access denied by server while mounting zero:/export/krb5 recently changed behavior: $ uname -a Linux one.apikia.fake 3.9.0-testing+ #2 SMP Fri May 3 20:29:32 EDT 2013 x86_64 x86_64 x86_64 GNU/Linux $ sudo mount -v -o sec=sys,vers=3 zero:/export/krb5 /mnt mount.nfs: timeout set for Sun May 5 17:37:17 2013 mount.nfs: trying text-based options 'sec=sys,vers=3,addr=192.168.100.10' mount.nfs: prog 100003, trying vers=3, prot=6 mount.nfs: trying 192.168.100.10 prog 100003 vers 3 prot TCP port 2049 mount.nfs: prog 100005, trying vers=3, prot=17 mount.nfs: trying 192.168.100.10 prog 100005 vers 3 prot UDP port 20048 $ ls /mnt ls: cannot open directory /mnt: Permission denied $ sudo ls /mnt ls: cannot open directory /mnt: Permission denied $ sudo df /mnt df: ‘/mnt’: Permission denied df: no file systems processed $ sudo umount /mnt $ Signed-off-by: Weston Andros Adamson <dros@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-05-07 05:12:13 +08:00
*/
NFS: Use server-recommended security flavor by default (NFSv3) Since commit ec88f28d in 2009, checking if the user-specified flavor is in the server's flavor list has been the source of a few noticeable regressions (now fixed), but there is one that is still vexing. An NFS server can list AUTH_NULL in its flavor list, which suggests a client should try to mount the server with the flavor of the client's choice, but the server will squash all accesses. In some cases, our client fails to mount a server because of this check, when the mount could have proceeded successfully. Skip this check if the user has specified "sec=" on the mount command line. But do consult the server-provided flavor list to choose a security flavor if no sec= option is specified on the mount command. If a server lists Kerberos pseudoflavors before "sys" in its export options, our client now chooses Kerberos over AUTH_UNIX for mount points, when no security flavor is specified by the mount command. This could be surprising to some administrators or users, who would then need to have Kerberos credentials to access the export. Or, a client administrator may not have enabled rpc.gssd. In this case, auth_rpcgss.ko might still be loadable, which is enough for the new logic to choose Kerberos over AUTH_UNIX. But the mount would fail since no GSS context can be created without rpc.gssd running. To retain the use of AUTH_UNIX by default: o The server administrator can ensure that "sys" is listed before Kerberos flavors in its export security options (see exports(5)), o The client administrator can explicitly specify "sec=sys" on its mount command line (see nfs(5)), o The client administrator can use "Sec=sys" in an appropriate section of /etc/nfsmount.conf (see nfsmount.conf(5)), or o The client administrator can blacklist auth_rpcgss.ko. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-03-23 00:53:17 +08:00
for (i = 0; i < count; i++) {
flavor = server_authlist[i];
if (nfs_auth_info_match(&args->auth_info, flavor))
goto out;
if (flavor == RPC_AUTH_NULL)
use_auth_null = true;
}
if (use_auth_null) {
flavor = RPC_AUTH_NULL;
goto out;
NFS: Use server-recommended security flavor by default (NFSv3) Since commit ec88f28d in 2009, checking if the user-specified flavor is in the server's flavor list has been the source of a few noticeable regressions (now fixed), but there is one that is still vexing. An NFS server can list AUTH_NULL in its flavor list, which suggests a client should try to mount the server with the flavor of the client's choice, but the server will squash all accesses. In some cases, our client fails to mount a server because of this check, when the mount could have proceeded successfully. Skip this check if the user has specified "sec=" on the mount command line. But do consult the server-provided flavor list to choose a security flavor if no sec= option is specified on the mount command. If a server lists Kerberos pseudoflavors before "sys" in its export options, our client now chooses Kerberos over AUTH_UNIX for mount points, when no security flavor is specified by the mount command. This could be surprising to some administrators or users, who would then need to have Kerberos credentials to access the export. Or, a client administrator may not have enabled rpc.gssd. In this case, auth_rpcgss.ko might still be loadable, which is enough for the new logic to choose Kerberos over AUTH_UNIX. But the mount would fail since no GSS context can be created without rpc.gssd running. To retain the use of AUTH_UNIX by default: o The server administrator can ensure that "sys" is listed before Kerberos flavors in its export security options (see exports(5)), o The client administrator can explicitly specify "sec=sys" on its mount command line (see nfs(5)), o The client administrator can use "Sec=sys" in an appropriate section of /etc/nfsmount.conf (see nfsmount.conf(5)), or o The client administrator can blacklist auth_rpcgss.ko. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-03-23 00:53:17 +08:00
}
dfprintk(MOUNT,
"NFS: specified auth flavors not supported by server\n");
return -EACCES;
NFSv3: match sec= flavor against server list Older linux clients match the 'sec=' mount option flavor against the server's flavor list (if available) and return EPERM if the specified flavor or AUTH_NULL (which "matches" any flavor) is not found. Recent changes skip this step and allow the vfs mount even though no operations will succeed, creating a 'dud' mount. This patch reverts back to the old behavior of matching specified flavors against the server list and also returns EPERM when no sec= is specified and none of the flavors returned by the server are supported by the client. Example of behavior change: the server's /etc/exports: /export/krb5 *(sec=krb5,rw,no_root_squash) old client behavior: $ uname -a Linux one.apikia.fake 3.8.8-202.fc18.x86_64 #1 SMP Wed Apr 17 23:25:17 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux $ sudo mount -v -o sec=sys,vers=3 zero:/export/krb5 /mnt mount.nfs: timeout set for Sun May 5 17:32:04 2013 mount.nfs: trying text-based options 'sec=sys,vers=3,addr=192.168.100.10' mount.nfs: prog 100003, trying vers=3, prot=6 mount.nfs: trying 192.168.100.10 prog 100003 vers 3 prot TCP port 2049 mount.nfs: prog 100005, trying vers=3, prot=17 mount.nfs: trying 192.168.100.10 prog 100005 vers 3 prot UDP port 20048 mount.nfs: mount(2): Permission denied mount.nfs: access denied by server while mounting zero:/export/krb5 recently changed behavior: $ uname -a Linux one.apikia.fake 3.9.0-testing+ #2 SMP Fri May 3 20:29:32 EDT 2013 x86_64 x86_64 x86_64 GNU/Linux $ sudo mount -v -o sec=sys,vers=3 zero:/export/krb5 /mnt mount.nfs: timeout set for Sun May 5 17:37:17 2013 mount.nfs: trying text-based options 'sec=sys,vers=3,addr=192.168.100.10' mount.nfs: prog 100003, trying vers=3, prot=6 mount.nfs: trying 192.168.100.10 prog 100003 vers 3 prot TCP port 2049 mount.nfs: prog 100005, trying vers=3, prot=17 mount.nfs: trying 192.168.100.10 prog 100005 vers 3 prot UDP port 20048 $ ls /mnt ls: cannot open directory /mnt: Permission denied $ sudo ls /mnt ls: cannot open directory /mnt: Permission denied $ sudo df /mnt df: ‘/mnt’: Permission denied df: no file systems processed $ sudo umount /mnt $ Signed-off-by: Weston Andros Adamson <dros@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-05-07 05:12:13 +08:00
NFS: Use server-recommended security flavor by default (NFSv3) Since commit ec88f28d in 2009, checking if the user-specified flavor is in the server's flavor list has been the source of a few noticeable regressions (now fixed), but there is one that is still vexing. An NFS server can list AUTH_NULL in its flavor list, which suggests a client should try to mount the server with the flavor of the client's choice, but the server will squash all accesses. In some cases, our client fails to mount a server because of this check, when the mount could have proceeded successfully. Skip this check if the user has specified "sec=" on the mount command line. But do consult the server-provided flavor list to choose a security flavor if no sec= option is specified on the mount command. If a server lists Kerberos pseudoflavors before "sys" in its export options, our client now chooses Kerberos over AUTH_UNIX for mount points, when no security flavor is specified by the mount command. This could be surprising to some administrators or users, who would then need to have Kerberos credentials to access the export. Or, a client administrator may not have enabled rpc.gssd. In this case, auth_rpcgss.ko might still be loadable, which is enough for the new logic to choose Kerberos over AUTH_UNIX. But the mount would fail since no GSS context can be created without rpc.gssd running. To retain the use of AUTH_UNIX by default: o The server administrator can ensure that "sys" is listed before Kerberos flavors in its export security options (see exports(5)), o The client administrator can explicitly specify "sec=sys" on its mount command line (see nfs(5)), o The client administrator can use "Sec=sys" in an appropriate section of /etc/nfsmount.conf (see nfsmount.conf(5)), or o The client administrator can blacklist auth_rpcgss.ko. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-03-23 00:53:17 +08:00
out:
args->selected_flavor = flavor;
dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->selected_flavor);
NFSv3: match sec= flavor against server list Older linux clients match the 'sec=' mount option flavor against the server's flavor list (if available) and return EPERM if the specified flavor or AUTH_NULL (which "matches" any flavor) is not found. Recent changes skip this step and allow the vfs mount even though no operations will succeed, creating a 'dud' mount. This patch reverts back to the old behavior of matching specified flavors against the server list and also returns EPERM when no sec= is specified and none of the flavors returned by the server are supported by the client. Example of behavior change: the server's /etc/exports: /export/krb5 *(sec=krb5,rw,no_root_squash) old client behavior: $ uname -a Linux one.apikia.fake 3.8.8-202.fc18.x86_64 #1 SMP Wed Apr 17 23:25:17 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux $ sudo mount -v -o sec=sys,vers=3 zero:/export/krb5 /mnt mount.nfs: timeout set for Sun May 5 17:32:04 2013 mount.nfs: trying text-based options 'sec=sys,vers=3,addr=192.168.100.10' mount.nfs: prog 100003, trying vers=3, prot=6 mount.nfs: trying 192.168.100.10 prog 100003 vers 3 prot TCP port 2049 mount.nfs: prog 100005, trying vers=3, prot=17 mount.nfs: trying 192.168.100.10 prog 100005 vers 3 prot UDP port 20048 mount.nfs: mount(2): Permission denied mount.nfs: access denied by server while mounting zero:/export/krb5 recently changed behavior: $ uname -a Linux one.apikia.fake 3.9.0-testing+ #2 SMP Fri May 3 20:29:32 EDT 2013 x86_64 x86_64 x86_64 GNU/Linux $ sudo mount -v -o sec=sys,vers=3 zero:/export/krb5 /mnt mount.nfs: timeout set for Sun May 5 17:37:17 2013 mount.nfs: trying text-based options 'sec=sys,vers=3,addr=192.168.100.10' mount.nfs: prog 100003, trying vers=3, prot=6 mount.nfs: trying 192.168.100.10 prog 100003 vers 3 prot TCP port 2049 mount.nfs: prog 100005, trying vers=3, prot=17 mount.nfs: trying 192.168.100.10 prog 100005 vers 3 prot UDP port 20048 $ ls /mnt ls: cannot open directory /mnt: Permission denied $ sudo ls /mnt ls: cannot open directory /mnt: Permission denied $ sudo df /mnt df: ‘/mnt’: Permission denied df: no file systems processed $ sudo umount /mnt $ Signed-off-by: Weston Andros Adamson <dros@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-05-07 05:12:13 +08:00
return 0;
}
/*
* Use the remote server's MOUNT service to request the NFS file handle
* corresponding to the provided path.
*/
static int nfs_request_mount(struct nfs_parsed_mount_data *args,
struct nfs_fh *root_fh,
rpc_authflavor_t *server_authlist,
unsigned int *server_authlist_len)
{
struct nfs_mount_request request = {
.sap = (struct sockaddr *)
&args->mount_server.address,
.dirpath = args->nfs_server.export_path,
.protocol = args->mount_server.protocol,
.fh = root_fh,
.noresvport = args->flags & NFS_MOUNT_NORESVPORT,
.auth_flav_len = server_authlist_len,
.auth_flavs = server_authlist,
.net = args->net,
};
int status;
if (args->mount_server.version == 0) {
switch (args->version) {
default:
args->mount_server.version = NFS_MNT3_VERSION;
break;
case 2:
args->mount_server.version = NFS_MNT_VERSION;
}
}
request.version = args->mount_server.version;
if (args->mount_server.hostname)
request.hostname = args->mount_server.hostname;
else
request.hostname = args->nfs_server.hostname;
/*
* Construct the mount server's address.
*/
if (args->mount_server.address.ss_family == AF_UNSPEC) {
memcpy(request.sap, &args->nfs_server.address,
args->nfs_server.addrlen);
args->mount_server.addrlen = args->nfs_server.addrlen;
}
request.salen = args->mount_server.addrlen;
nfs_set_port(request.sap, &args->mount_server.port, 0);
/*
* Now ask the mount server to map our export path
* to a file handle.
*/
status = nfs_mount(&request);
if (status != 0) {
dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n",
request.hostname, status);
return status;
}
return 0;
}
static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_info,
struct nfs_subversion *nfs_mod)
{
int status;
unsigned int i;
bool tried_auth_unix = false;
bool auth_null_in_list = false;
struct nfs_server *server = ERR_PTR(-EACCES);
struct nfs_parsed_mount_data *args = mount_info->parsed;
rpc_authflavor_t authlist[NFS_MAX_SECFLAVORS];
unsigned int authlist_len = ARRAY_SIZE(authlist);
status = nfs_request_mount(args, mount_info->mntfh, authlist,
&authlist_len);
if (status)
return ERR_PTR(status);
/*
* Was a sec= authflavor specified in the options? First, verify
* whether the server supports it, and then just try to use it if so.
*/
if (args->auth_info.flavor_len > 0) {
status = nfs_verify_authflavors(args, authlist, authlist_len);
dfprintk(MOUNT, "NFS: using auth flavor %u\n",
args->selected_flavor);
if (status)
return ERR_PTR(status);
return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod);
}
/*
* No sec= option was provided. RFC 2623, section 2.7 suggests we
* SHOULD prefer the flavor listed first. However, some servers list
* AUTH_NULL first. Avoid ever choosing AUTH_NULL.
*/
for (i = 0; i < authlist_len; ++i) {
rpc_authflavor_t flavor;
struct rpcsec_gss_info info;
flavor = authlist[i];
switch (flavor) {
case RPC_AUTH_UNIX:
tried_auth_unix = true;
break;
case RPC_AUTH_NULL:
auth_null_in_list = true;
continue;
default:
if (rpcauth_get_gssinfo(flavor, &info) != 0)
continue;
/* Fallthrough */
}
dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", flavor);
args->selected_flavor = flavor;
server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod);
if (!IS_ERR(server))
return server;
}
/*
* Nothing we tried so far worked. At this point, give up if we've
* already tried AUTH_UNIX or if the server's list doesn't contain
* AUTH_NULL
*/
if (tried_auth_unix || !auth_null_in_list)
return server;
/* Last chance! Try AUTH_UNIX */
dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", RPC_AUTH_UNIX);
args->selected_flavor = RPC_AUTH_UNIX;
return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod);
}
struct dentry *nfs_try_mount(int flags, const char *dev_name,
struct nfs_mount_info *mount_info,
struct nfs_subversion *nfs_mod)
{
struct nfs_server *server;
if (mount_info->parsed->need_mount)
server = nfs_try_mount_request(mount_info, nfs_mod);
else
server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod);
if (IS_ERR(server))
return ERR_CAST(server);
return nfs_fs_mount_common(server, flags, dev_name, mount_info, nfs_mod);
}
EXPORT_SYMBOL_GPL(nfs_try_mount);
/*
* Split "dev_name" into "hostname:export_path".
*
* The leftmost colon demarks the split between the server's hostname
* and the export path. If the hostname starts with a left square
* bracket, then it may contain colons.
*
* Note: caller frees hostname and export path, even on error.
*/
static int nfs_parse_devname(const char *dev_name,
char **hostname, size_t maxnamlen,
char **export_path, size_t maxpathlen)
{
size_t len;
char *end;
/* Is the host name protected with square brakcets? */
if (*dev_name == '[') {
end = strchr(++dev_name, ']');
if (end == NULL || end[1] != ':')
goto out_bad_devname;
len = end - dev_name;
end++;
} else {
char *comma;
end = strchr(dev_name, ':');
if (end == NULL)
goto out_bad_devname;
len = end - dev_name;
/* kill possible hostname list: not supported */
comma = strchr(dev_name, ',');
if (comma != NULL && comma < end)
*comma = 0;
}
if (len > maxnamlen)
goto out_hostname;
/* N.B. caller will free nfs_server.hostname in all cases */
*hostname = kstrndup(dev_name, len, GFP_KERNEL);
if (*hostname == NULL)
goto out_nomem;
len = strlen(++end);
if (len > maxpathlen)
goto out_path;
*export_path = kstrndup(end, len, GFP_KERNEL);
if (!*export_path)
goto out_nomem;
dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", *export_path);
return 0;
out_bad_devname:
dfprintk(MOUNT, "NFS: device name not in host:path format\n");
return -EINVAL;
out_nomem:
dfprintk(MOUNT, "NFS: not enough memory to parse device name\n");
return -ENOMEM;
out_hostname:
dfprintk(MOUNT, "NFS: server hostname too long\n");
return -ENAMETOOLONG;
out_path:
dfprintk(MOUNT, "NFS: export pathname too long\n");
return -ENAMETOOLONG;
}
/*
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
* Validate the NFS2/NFS3 mount data
* - fills in the mount root filehandle
*
* For option strings, user space handles the following behaviors:
*
* + DNS: mapping server host name to IP address ("addr=" option)
*
* + failure mode: how to behave if a mount request can't be handled
* immediately ("fg/bg" option)
*
* + retry: how often to retry a mount request ("retry=" option)
*
* + breaking back: trying proto=udp after proto=tcp, v2 after v3,
* mountproto=tcp after mountproto=udp, and so on
*/
static int nfs23_validate_mount_data(void *options,
struct nfs_parsed_mount_data *args,
struct nfs_fh *mntfh,
const char *dev_name)
{
struct nfs_mount_data *data = (struct nfs_mount_data *)options;
struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
int extra_flags = NFS_MOUNT_LEGACY_INTERFACE;
if (data == NULL)
goto out_no_data;
args->version = NFS_DEFAULT_VERSION;
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
switch (data->version) {
case 1:
data->namlen = 0;
case 2:
data->bsize = 0;
case 3:
if (data->flags & NFS_MOUNT_VER3)
goto out_no_v3;
data->root.size = NFS2_FHSIZE;
memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE);
/* Turn off security negotiation */
extra_flags |= NFS_MOUNT_SECFLAVOUR;
case 4:
if (data->flags & NFS_MOUNT_SECFLAVOUR)
goto out_no_sec;
case 5:
memset(data->context, 0, sizeof(data->context));
case 6:
if (data->flags & NFS_MOUNT_VER3) {
if (data->root.size > NFS3_FHSIZE || data->root.size == 0)
goto out_invalid_fh;
mntfh->size = data->root.size;
args->version = 3;
} else {
mntfh->size = NFS2_FHSIZE;
args->version = 2;
}
memcpy(mntfh->data, data->root.data, mntfh->size);
if (mntfh->size < sizeof(mntfh->data))
memset(mntfh->data + mntfh->size, 0,
sizeof(mntfh->data) - mntfh->size);
/*
* Translate to nfs_parsed_mount_data, which nfs_fill_super
* can deal with.
*/
args->flags = data->flags & NFS_MOUNT_FLAGMASK;
args->flags |= extra_flags;
args->rsize = data->rsize;
args->wsize = data->wsize;
args->timeo = data->timeo;
args->retrans = data->retrans;
args->acregmin = data->acregmin;
args->acregmax = data->acregmax;
args->acdirmin = data->acdirmin;
args->acdirmax = data->acdirmax;
args->need_mount = false;
memcpy(sap, &data->addr, sizeof(data->addr));
args->nfs_server.addrlen = sizeof(data->addr);
args->nfs_server.port = ntohs(data->addr.sin_port);
if (!nfs_verify_server_address(sap))
goto out_no_address;
if (!(data->flags & NFS_MOUNT_TCP))
args->nfs_server.protocol = XPRT_TRANSPORT_UDP;
/* N.B. caller will free nfs_server.hostname in all cases */
args->nfs_server.hostname = kstrdup(data->hostname, GFP_KERNEL);
args->namlen = data->namlen;
args->bsize = data->bsize;
if (data->flags & NFS_MOUNT_SECFLAVOUR)
args->selected_flavor = data->pseudoflavor;
else
args->selected_flavor = RPC_AUTH_UNIX;
if (!args->nfs_server.hostname)
goto out_nomem;
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 20:55:58 +08:00
if (!(data->flags & NFS_MOUNT_NONLM))
args->flags &= ~(NFS_MOUNT_LOCAL_FLOCK|
NFS_MOUNT_LOCAL_FCNTL);
else
args->flags |= (NFS_MOUNT_LOCAL_FLOCK|
NFS_MOUNT_LOCAL_FCNTL);
/*
* The legacy version 6 binary mount data from userspace has a
* field used only to transport selinux information into the
* the kernel. To continue to support that functionality we
* have a touch of selinux knowledge here in the NFS code. The
* userspace code converted context=blah to just blah so we are
* converting back to the full string selinux understands.
*/
if (data->context[0]){
#ifdef CONFIG_SECURITY_SELINUX
int rc;
char *opts_str = kmalloc(sizeof(data->context) + 8, GFP_KERNEL);
if (!opts_str)
return -ENOMEM;
strcpy(opts_str, "context=");
data->context[NFS_MAX_CONTEXT_LEN] = '\0';
strcat(opts_str, &data->context[0]);
rc = security_sb_parse_opts_str(opts_str, &args->lsm_opts);
kfree(opts_str);
if (rc)
return rc;
#else
return -EINVAL;
#endif
}
break;
default:
return NFS_TEXT_DATA;
}
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
return 0;
out_no_data:
dfprintk(MOUNT, "NFS: mount program didn't pass any mount data\n");
return -EINVAL;
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
out_no_v3:
dfprintk(MOUNT, "NFS: nfs_mount_data version %d does not support v3\n",
data->version);
return -EINVAL;
out_no_sec:
dfprintk(MOUNT, "NFS: nfs_mount_data version supports only AUTH_SYS\n");
return -EINVAL;
out_nomem:
dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n");
return -ENOMEM;
out_no_address:
dfprintk(MOUNT, "NFS: mount program didn't pass remote address\n");
return -EINVAL;
out_invalid_fh:
dfprintk(MOUNT, "NFS: invalid root filehandle\n");
return -EINVAL;
}
#if IS_ENABLED(CONFIG_NFS_V4)
static int nfs_validate_mount_data(struct file_system_type *fs_type,
void *options,
struct nfs_parsed_mount_data *args,
struct nfs_fh *mntfh,
const char *dev_name)
{
if (fs_type == &nfs_fs_type)
return nfs23_validate_mount_data(options, args, mntfh, dev_name);
return nfs4_validate_mount_data(options, args, dev_name);
}
#else
static int nfs_validate_mount_data(struct file_system_type *fs_type,
void *options,
struct nfs_parsed_mount_data *args,
struct nfs_fh *mntfh,
const char *dev_name)
{
return nfs23_validate_mount_data(options, args, mntfh, dev_name);
}
#endif
static int nfs_validate_text_mount_data(void *options,
struct nfs_parsed_mount_data *args,
const char *dev_name)
{
int port = 0;
int max_namelen = PAGE_SIZE;
int max_pathlen = NFS_MAXPATHLEN;
struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
if (nfs_parse_mount_options((char *)options, args) == 0)
return -EINVAL;
if (!nfs_verify_server_address(sap))
goto out_no_address;
if (args->version == 4) {
#if IS_ENABLED(CONFIG_NFS_V4)
port = NFS_PORT;
max_namelen = NFS4_MAXNAMLEN;
max_pathlen = NFS4_MAXPATHLEN;
nfs_validate_transport_protocol(args);
if (args->nfs_server.protocol == XPRT_TRANSPORT_UDP)
goto out_invalid_transport_udp;
nfs4_validate_mount_flags(args);
#else
goto out_v4_not_compiled;
#endif /* CONFIG_NFS_V4 */
} else
nfs_set_mount_transport_protocol(args);
nfs_set_port(sap, &args->nfs_server.port, port);
return nfs_parse_devname(dev_name,
&args->nfs_server.hostname,
max_namelen,
&args->nfs_server.export_path,
max_pathlen);
#if !IS_ENABLED(CONFIG_NFS_V4)
out_v4_not_compiled:
dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n");
return -EPROTONOSUPPORT;
#else
out_invalid_transport_udp:
dfprintk(MOUNT, "NFSv4: Unsupported transport protocol udp\n");
return -EINVAL;
#endif /* !CONFIG_NFS_V4 */
out_no_address:
dfprintk(MOUNT, "NFS: mount program didn't pass remote address\n");
return -EINVAL;
}
#define NFS_REMOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \
| NFS_MOUNT_SECURE \
| NFS_MOUNT_TCP \
| NFS_MOUNT_VER3 \
| NFS_MOUNT_KERBEROS \
| NFS_MOUNT_NONLM \
| NFS_MOUNT_BROKEN_SUID \
| NFS_MOUNT_STRICTLOCK \
| NFS_MOUNT_LEGACY_INTERFACE)
#define NFS_MOUNT_CMP_FLAGMASK (NFS_REMOUNT_CMP_FLAGMASK & \
~(NFS_MOUNT_UNSHARED | NFS_MOUNT_NORESVPORT))
static int
nfs_compare_remount_data(struct nfs_server *nfss,
struct nfs_parsed_mount_data *data)
{
if ((data->flags ^ nfss->flags) & NFS_REMOUNT_CMP_FLAGMASK ||
data->rsize != nfss->rsize ||
data->wsize != nfss->wsize ||
data->version != nfss->nfs_client->rpc_ops->version ||
data->minorversion != nfss->nfs_client->cl_minorversion ||
data->retrans != nfss->client->cl_timeout->to_retries ||
!nfs_auth_info_match(&data->auth_info, nfss->client->cl_auth->au_flavor) ||
data->acregmin != nfss->acregmin / HZ ||
data->acregmax != nfss->acregmax / HZ ||
data->acdirmin != nfss->acdirmin / HZ ||
data->acdirmax != nfss->acdirmax / HZ ||
data->timeo != (10U * nfss->client->cl_timeout->to_initval / HZ) ||
data->nfs_server.port != nfss->port ||
data->nfs_server.addrlen != nfss->nfs_client->cl_addrlen ||
!rpc_cmp_addr((struct sockaddr *)&data->nfs_server.address,
(struct sockaddr *)&nfss->nfs_client->cl_addr))
return -EINVAL;
return 0;
}
int
nfs_remount(struct super_block *sb, int *flags, char *raw_data)
{
int error;
struct nfs_server *nfss = sb->s_fs_info;
struct nfs_parsed_mount_data *data;
struct nfs_mount_data *options = (struct nfs_mount_data *)raw_data;
struct nfs4_mount_data *options4 = (struct nfs4_mount_data *)raw_data;
u32 nfsvers = nfss->nfs_client->rpc_ops->version;
fs: push sync_filesystem() down to the file system's remount_fs() Previously, the no-op "mount -o mount /dev/xxx" operation when the file system is already mounted read-write causes an implied, unconditional syncfs(). This seems pretty stupid, and it's certainly documented or guaraunteed to do this, nor is it particularly useful, except in the case where the file system was mounted rw and is getting remounted read-only. However, it's possible that there might be some file systems that are actually depending on this behavior. In most file systems, it's probably fine to only call sync_filesystem() when transitioning from read-write to read-only, and there are some file systems where this is not needed at all (for example, for a pseudo-filesystem or something like romfs). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: linux-fsdevel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Evgeniy Dushistov <dushistov@mail.ru> Cc: Jan Kara <jack@suse.cz> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Anders Larsen <al@alarsen.net> Cc: Phillip Lougher <phillip@squashfs.org.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz> Cc: Petr Vandrovec <petr@vandrovec.name> Cc: xfs@oss.sgi.com Cc: linux-btrfs@vger.kernel.org Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Cc: codalist@coda.cs.cmu.edu Cc: linux-ext4@vger.kernel.org Cc: linux-f2fs-devel@lists.sourceforge.net Cc: fuse-devel@lists.sourceforge.net Cc: cluster-devel@redhat.com Cc: linux-mtd@lists.infradead.org Cc: jfs-discussion@lists.sourceforge.net Cc: linux-nfs@vger.kernel.org Cc: linux-nilfs@vger.kernel.org Cc: linux-ntfs-dev@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Cc: reiserfs-devel@vger.kernel.org
2014-03-13 22:14:33 +08:00
sync_filesystem(sb);
/*
* Userspace mount programs that send binary options generally send
* them populated with default values. We have no way to know which
* ones were explicitly specified. Fall back to legacy behavior and
* just return success.
*/
nfs_remount oops when rebooting + possible fix Jeff, Trond, The commit 48b605f83c920d8daa50e43fc2c7f718e04c7bfa (NFS: implement option checking when remounting NFS filesystems (resend)) generate an Oops on my platform when rebooting while its root FS on an NFS share (NFSv3, TCP) : Unmounting local filesystems...done. Unable to handle kernel NULL pointer dereference at virtual address 00000000 pgd = c3d00000 [00000000] *pgd=a3d72031, *pte=00000000, *ppte=00000000 Internal error: Oops: 17 [#1] Modules linked in: cpufreq_powersave cpufreq_ondemand cpufreq_userspace cpufreq_conservative ext3 jbd sd_mod pata_pcmcia libata scsi_mod pcmcia loop firmware_class pxafb cfbcopyarea cfbimgblt cfbfillrect pxa2xx_cs pxa2xx_core pcmcia_core snd_pxa2xx_ac97 snd_ac97_codec ac97_bus snd_pxa2xx_pcm snd_pcm_oss snd_mixer_oss snd_pcm snd_timer snd isp116x_hcd soundcore rtc_sa1100 snd_page_alloc pxa25x_udc usbcore rtc_ds1307 rtc_core CPU: 0 Not tainted (2.6.26-03414-g33af79d-dirty #15) PC is at nfs_remount+0x40/0x264 LR is at do_remount_sb+0x158/0x194 pc : [<c00bbf54>] lr : [<c0076c40>] psr: 60000013 sp : c2dd1e70 ip : c2dd1e98 fp : c2dd1e94 r10: 00000040 r9 : c3d17000 r8 : c3c3fc40 r7 : 00000000 r6 : 00000000 r5 : c3d2b200 r4 : 00000000 r3 : 00000003 r2 : 00000000 r1 : c2dd1e9c r0 : c3c3fc00 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user Control: 0000397f Table: a3d00000 DAC: 00000015 Process mount (pid: 1462, stack limit = 0xc2dd0270) Stack: (0xc2dd1e70 to 0xc2dd2000) 1e60: 00000000 c3c3fc00 00000000 00000000 1e80: c3c3fc40 c3d17000 c2dd1ebc c2dd1e98 c0076c40 c00bbf20 c01c61e4 00000001 1ea0: c2dd1ebc 00000001 c3c3fc00 c2dd1ef0 c2dd1ee4 c2dd1ec0 c008c6d8 c0076af4 1ec0: 00000021 00000040 c2dd1ef0 c3d77000 c3eaa000 00000000 c2dd1f6c c2dd1ee8 1ee0: c008d1bc c008c5f8 00000000 c2dd0000 c3c0c320 c3805b38 c002064c 0001f820 1f00: 0001f810 00000001 00000001 00000000 c2dd0000 00000000 c2dd1f34 c2dd1f28 1f20: c005ead8 c005e6f8 c2dd1f44 c2dd1f38 c005eaf8 c005ead0 c2dd1f6c c2dd1f48 1f40: c008ae3c 00000000 c3d77000 0001f810 c0ed0021 c0020ca8 c2dd0000 00000000 1f60: c2dd1fa4 c2dd1f70 c008d2d4 c008d0bc 00000000 0001f810 c2dd1f9c c3eaa000 1f80: c3d17000 00000000 00000000 be8b6aa8 be8b6ad0 00000015 00000000 c2dd1fa8 1fa0: c0020b00 c008d254 00000000 be8b6aa8 0001f810 0001f820 0001f830 c0ed0021 1fc0: 00000000 be8b6aa8 be8b6ad0 00000015 00000000 be8b6ad0 0001f810 be8b6aa8 1fe0: 0001f810 be8b6964 0000aab8 40125124 60000010 0001f810 00000000 00000000 Backtrace: [<c00bbf14>] (nfs_remount+0x0/0x264) from [<c0076c40>] (do_remount_sb+0x158/0x194) r9:c3d17000 r8:c3c3fc40 r7:00000000 r6:00000000 r5:c3c3fc00 r4:00000000 [<c0076ae8>] (do_remount_sb+0x0/0x194) from [<c008c6d8>] (do_remount+0xec/0x118) r6:c2dd1ef0 r5:c3c3fc00 r4:00000001 [<c008c5ec>] (do_remount+0x0/0x118) from [<c008d1bc>] (do_mount+0x10c/0x198) [<c008d0b0>] (do_mount+0x0/0x198) from [<c008d2d4>] (sys_mount+0x8c/0xd4) [<c008d248>] (sys_mount+0x0/0xd4) from [<c0020b00>] (ret_fast_syscall+0x0/0x2c) r7:00000015 r6:be8b6ad0 r5:be8b6aa8 r4:00000000 Code: 0a000086 ea000006 e3530003 8a000004 (e5923000) ---[ end trace 55e1b689cf8c8a6a ]--- ------------[ cut here ]------------ WARNING: at kernel/exit.c:966 do_exit+0x3c/0x628() Modules linked in: cpufreq_powersave cpufreq_ondemand cpufreq_userspace cpufreq_conservative ext3 jbd sd_mod pata_pcmcia libata scsi_mod pcmcia loop firmware_class pxafb cfbcopyarea cfbimgblt cfbfillrect pxa2xx_cs pxa2xx_core pcmcia_core snd_pxa2xx_ac97 snd_ac97_codec ac97_bus snd_pxa2xx_pcm snd_pcm_oss snd_mixer_oss snd_pcm snd_timer snd isp116x_hcd soundcore rtc_sa1100 snd_page_alloc pxa25x_udc usbcore rtc_ds1307 rtc_core [<c0025168>] (dump_stack+0x0/0x14) from [<c0032154>] (warn_on_slowpath+0x4c/0x68) [<c0032108>] (warn_on_slowpath+0x0/0x68) from [<c003531c>] (do_exit+0x3c/0x628) r6:0000000b r5:c3c3dc80 r4:c2dd0000 [<c00352e0>] (do_exit+0x0/0x628) from [<c0025004>] (die+0x2b0/0x30c) [<c0024d54>] (die+0x0/0x30c) from [<c00270bc>] (__do_kernel_fault+0x6c/0x80) [<c0027050>] (__do_kernel_fault+0x0/0x80) from [<c00272e0>] (do_page_fault+0x210/0x230) r7:c3fa7118 r6:c3c3dc80 r5:c3d166a8 r4:00010000 [<c00270d0>] (do_page_fault+0x0/0x230) from [<c00201ec>] (do_DataAbort+0x3c/0xa0) [<c00201b0>] (do_DataAbort+0x0/0xa0) from [<c002064c>] (__dabt_svc+0x4c/0x60) Exception stack(0xc2dd1e28 to 0xc2dd1e70) 1e20: c3c3fc00 c2dd1e9c 00000000 00000003 00000000 c3d2b200 1e40: 00000000 00000000 c3c3fc40 c3d17000 00000040 c2dd1e94 c2dd1e98 c2dd1e70 1e60: c0076c40 c00bbf54 60000013 ffffffff r8:c3c3fc40 r7:00000000 r6:00000000 r5:c2dd1e5c r4:ffffffff [<c00bbf14>] (nfs_remount+0x0/0x264) from [<c0076c40>] (do_remount_sb+0x158/0x194) r9:c3d17000 r8:c3c3fc40 r7:00000000 r6:00000000 r5:c3c3fc00 r4:00000000 [<c0076ae8>] (do_remount_sb+0x0/0x194) from [<c008c6d8>] (do_remount+0xec/0x118) r6:c2dd1ef0 r5:c3c3fc00 r4:00000001 [<c008c5ec>] (do_remount+0x0/0x118) from [<c008d1bc>] (do_mount+0x10c/0x198) [<c008d0b0>] (do_mount+0x0/0x198) from [<c008d2d4>] (sys_mount+0x8c/0xd4) [<c008d248>] (sys_mount+0x0/0xd4) from [<c0020b00>] (ret_fast_syscall+0x0/0x2c) r7:00000015 r6:be8b6ad0 r5:be8b6aa8 r4:00000000 ---[ end trace 55e1b689cf8c8a6a ]--- /etc/rc6.d/S60umountroot: line 17: 1462 Segmentation fault mount $MOUNT_FORCE_OPT -n -o remount,ro -t dummytype dummydev / 2> /dev/null The new super.c:nfs_remount function doesn't check the validity of the options/options4 pointers. Unfortunately, this seems to happend. The obvious patch seems to check the pointers, and not to do anything if the happend to be NULL. Tested on an XScale PXA255 system, latest git. Regards, M. Signed-off-by: Marc Zyngier <marc.zyngier@altran.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2008-07-17 19:21:55 +08:00
if ((nfsvers == 4 && (!options4 || options4->version == 1)) ||
(nfsvers <= 3 && (!options || (options->version >= 1 &&
options->version <= 6))))
return 0;
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (data == NULL)
return -ENOMEM;
/* fill out struct with values from existing mount */
data->flags = nfss->flags;
data->rsize = nfss->rsize;
data->wsize = nfss->wsize;
data->retrans = nfss->client->cl_timeout->to_retries;
data->selected_flavor = nfss->client->cl_auth->au_flavor;
data->acregmin = nfss->acregmin / HZ;
data->acregmax = nfss->acregmax / HZ;
data->acdirmin = nfss->acdirmin / HZ;
data->acdirmax = nfss->acdirmax / HZ;
data->timeo = 10U * nfss->client->cl_timeout->to_initval / HZ;
data->nfs_server.port = nfss->port;
data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen;
data->version = nfsvers;
data->minorversion = nfss->nfs_client->cl_minorversion;
data->net = current->nsproxy->net_ns;
memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr,
data->nfs_server.addrlen);
/* overwrite those values with any that were specified */
error = -EINVAL;
if (!nfs_parse_mount_options((char *)options, data))
goto out;
/*
* noac is a special case. It implies -o sync, but that's not
* necessarily reflected in the mtab options. do_remount_sb
* will clear MS_SYNCHRONOUS if -o sync wasn't specified in the
* remount options, so we have to explicitly reset it.
*/
if (data->flags & NFS_MOUNT_NOAC)
*flags |= MS_SYNCHRONOUS;
/* compare new mount options with old ones */
error = nfs_compare_remount_data(nfss, data);
out:
kfree(data);
return error;
}
EXPORT_SYMBOL_GPL(nfs_remount);
/*
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
* Initialise the common bits of the superblock
*/
static void nfs_initialise_sb(struct super_block *sb)
{
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
struct nfs_server *server = NFS_SB(sb);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
sb->s_magic = NFS_SUPER_MAGIC;
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
/* We probably want something more informative here */
snprintf(sb->s_id, sizeof(sb->s_id),
"%u:%u", MAJOR(sb->s_dev), MINOR(sb->s_dev));
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
if (sb->s_blocksize == 0)
sb->s_blocksize = nfs_block_bits(server->wsize,
&sb->s_blocksize_bits);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
nfs_super_set_maxbytes(sb, server->maxfilesize);
}
/*
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
* Finish setting up an NFS2/3 superblock
*/
nfs: Fix bdi handling for cloned superblocks In commit 0d3b12584972 "nfs: Convert to separately allocated bdi" I have wrongly cloned bdi reference in nfs_clone_super(). Further inspection has shown that originally the code was actually allocating a new bdi (in ->clone_server callback) which was later registered in nfs_fs_mount_common() and used for sb->s_bdi in nfs_initialise_sb(). This could later result in bdi for the original superblock not getting unregistered when that superblock got shutdown (as the cloned sb still held bdi reference) and later when a new superblock was created under the same anonymous device number, a clash in sysfs has happened on bdi registration: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 10284 at /linux-next/fs/sysfs/dir.c:31 sysfs_warn_dup+0x64/0x74 sysfs: cannot create duplicate filename '/devices/virtual/bdi/0:32' Modules linked in: axp20x_usb_power gpio_axp209 nvmem_sunxi_sid sun4i_dma sun4i_ss virt_dma CPU: 1 PID: 10284 Comm: mount.nfs Not tainted 4.11.0-rc4+ #14 Hardware name: Allwinner sun7i (A20) Family [<c010f19c>] (unwind_backtrace) from [<c010bc74>] (show_stack+0x10/0x14) [<c010bc74>] (show_stack) from [<c03c6e24>] (dump_stack+0x78/0x8c) [<c03c6e24>] (dump_stack) from [<c0122200>] (__warn+0xe8/0x100) [<c0122200>] (__warn) from [<c0122250>] (warn_slowpath_fmt+0x38/0x48) [<c0122250>] (warn_slowpath_fmt) from [<c02ac178>] (sysfs_warn_dup+0x64/0x74) [<c02ac178>] (sysfs_warn_dup) from [<c02ac254>] (sysfs_create_dir_ns+0x84/0x94) [<c02ac254>] (sysfs_create_dir_ns) from [<c03c8b8c>] (kobject_add_internal+0x9c/0x2ec) [<c03c8b8c>] (kobject_add_internal) from [<c03c8e24>] (kobject_add+0x48/0x98) [<c03c8e24>] (kobject_add) from [<c048d75c>] (device_add+0xe4/0x5a0) [<c048d75c>] (device_add) from [<c048ddb4>] (device_create_groups_vargs+0xac/0xbc) [<c048ddb4>] (device_create_groups_vargs) from [<c048dde4>] (device_create_vargs+0x20/0x28) [<c048dde4>] (device_create_vargs) from [<c02075c8>] (bdi_register_va+0x44/0xfc) [<c02075c8>] (bdi_register_va) from [<c023d378>] (super_setup_bdi_name+0x48/0xa4) [<c023d378>] (super_setup_bdi_name) from [<c0312ef4>] (nfs_fill_super+0x1a4/0x204) [<c0312ef4>] (nfs_fill_super) from [<c03133f0>] (nfs_fs_mount_common+0x140/0x1e8) [<c03133f0>] (nfs_fs_mount_common) from [<c03335cc>] (nfs4_remote_mount+0x50/0x58) [<c03335cc>] (nfs4_remote_mount) from [<c023ef98>] (mount_fs+0x14/0xa4) [<c023ef98>] (mount_fs) from [<c025cba0>] (vfs_kern_mount+0x54/0x128) [<c025cba0>] (vfs_kern_mount) from [<c033352c>] (nfs_do_root_mount+0x80/0xa0) [<c033352c>] (nfs_do_root_mount) from [<c0333818>] (nfs4_try_mount+0x28/0x3c) [<c0333818>] (nfs4_try_mount) from [<c0313874>] (nfs_fs_mount+0x2cc/0x8c4) [<c0313874>] (nfs_fs_mount) from [<c023ef98>] (mount_fs+0x14/0xa4) [<c023ef98>] (mount_fs) from [<c025cba0>] (vfs_kern_mount+0x54/0x128) [<c025cba0>] (vfs_kern_mount) from [<c02600f0>] (do_mount+0x158/0xc7c) [<c02600f0>] (do_mount) from [<c0260f98>] (SyS_mount+0x8c/0xb4) [<c0260f98>] (SyS_mount) from [<c0107840>] (ret_fast_syscall+0x0/0x3c) Fix the problem by always creating new bdi for a superblock as we used to do. Reported-and-tested-by: Corentin Labbe <clabbe.montjoie@gmail.com> Fixes: 0d3b12584972ce5781179ad3f15cca3cdb5cae05 Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-04 15:02:42 +08:00
void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
{
struct nfs_parsed_mount_data *data = mount_info->parsed;
struct nfs_server *server = NFS_SB(sb);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
sb->s_blocksize_bits = 0;
sb->s_blocksize = 0;
sb->s_xattr = server->nfs_client->cl_nfs_mod->xattr;
sb->s_op = server->nfs_client->cl_nfs_mod->sops;
if (data && data->bsize)
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits);
if (server->nfs_client->rpc_ops->version != 2) {
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
/* The VFS shouldn't apply the umask to mode bits. We will do
* so ourselves when necessary.
*/
sb->s_flags |= MS_POSIXACL;
sb->s_time_gran = 1;
sb->s_export_op = &nfs_export_ops;
}
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
nfs_initialise_sb(sb);
}
EXPORT_SYMBOL_GPL(nfs_fill_super);
/*
* Finish setting up a cloned NFS2/3/4 superblock
*/
static void nfs_clone_super(struct super_block *sb,
struct nfs_mount_info *mount_info)
{
const struct super_block *old_sb = mount_info->cloned->sb;
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
struct nfs_server *server = NFS_SB(sb);
sb->s_blocksize_bits = old_sb->s_blocksize_bits;
sb->s_blocksize = old_sb->s_blocksize;
sb->s_maxbytes = old_sb->s_maxbytes;
sb->s_xattr = old_sb->s_xattr;
sb->s_op = old_sb->s_op;
sb->s_time_gran = 1;
sb->s_export_op = old_sb->s_export_op;
if (server->nfs_client->rpc_ops->version != 2) {
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
/* The VFS shouldn't apply the umask to mode bits. We will do
* so ourselves when necessary.
*/
sb->s_flags |= MS_POSIXACL;
}
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
nfs_initialise_sb(sb);
}
static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags)
{
const struct nfs_server *a = s->s_fs_info;
const struct rpc_clnt *clnt_a = a->client;
const struct rpc_clnt *clnt_b = b->client;
if ((s->s_flags & NFS_MS_MASK) != (flags & NFS_MS_MASK))
goto Ebusy;
if (a->nfs_client != b->nfs_client)
goto Ebusy;
if ((a->flags ^ b->flags) & NFS_MOUNT_CMP_FLAGMASK)
goto Ebusy;
if (a->wsize != b->wsize)
goto Ebusy;
if (a->rsize != b->rsize)
goto Ebusy;
if (a->acregmin != b->acregmin)
goto Ebusy;
if (a->acregmax != b->acregmax)
goto Ebusy;
if (a->acdirmin != b->acdirmin)
goto Ebusy;
if (a->acdirmax != b->acdirmax)
goto Ebusy;
if (b->auth_info.flavor_len > 0 &&
clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor)
goto Ebusy;
return 1;
Ebusy:
return 0;
}
struct nfs_sb_mountdata {
struct nfs_server *server;
int mntflags;
};
static int nfs_set_super(struct super_block *s, void *data)
{
struct nfs_sb_mountdata *sb_mntdata = data;
struct nfs_server *server = sb_mntdata->server;
int ret;
s->s_flags = sb_mntdata->mntflags;
s->s_fs_info = server;
s->s_d_op = server->nfs_client->rpc_ops->dentry_ops;
ret = set_anon_super(s, server);
if (ret == 0)
server->s_dev = s->s_dev;
return ret;
}
static int nfs_compare_super_address(struct nfs_server *server1,
struct nfs_server *server2)
{
struct sockaddr *sap1, *sap2;
struct rpc_xprt *xprt1 = server1->client->cl_xprt;
struct rpc_xprt *xprt2 = server2->client->cl_xprt;
if (!net_eq(xprt1->xprt_net, xprt2->xprt_net))
return 0;
sap1 = (struct sockaddr *)&server1->nfs_client->cl_addr;
sap2 = (struct sockaddr *)&server2->nfs_client->cl_addr;
if (sap1->sa_family != sap2->sa_family)
return 0;
switch (sap1->sa_family) {
case AF_INET: {
struct sockaddr_in *sin1 = (struct sockaddr_in *)sap1;
struct sockaddr_in *sin2 = (struct sockaddr_in *)sap2;
if (sin1->sin_addr.s_addr != sin2->sin_addr.s_addr)
return 0;
if (sin1->sin_port != sin2->sin_port)
return 0;
break;
}
case AF_INET6: {
struct sockaddr_in6 *sin1 = (struct sockaddr_in6 *)sap1;
struct sockaddr_in6 *sin2 = (struct sockaddr_in6 *)sap2;
if (!ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr))
return 0;
if (sin1->sin6_port != sin2->sin6_port)
return 0;
break;
}
default:
return 0;
}
return 1;
}
static int nfs_compare_super(struct super_block *sb, void *data)
{
struct nfs_sb_mountdata *sb_mntdata = data;
struct nfs_server *server = sb_mntdata->server, *old = NFS_SB(sb);
int mntflags = sb_mntdata->mntflags;
if (!nfs_compare_super_address(old, server))
return 0;
/* Note: NFS_MOUNT_UNSHARED == NFS4_MOUNT_UNSHARED */
if (old->flags & NFS_MOUNT_UNSHARED)
return 0;
if (memcmp(&old->fsid, &server->fsid, sizeof(old->fsid)) != 0)
return 0;
return nfs_compare_mount_options(sb, server, mntflags);
}
#ifdef CONFIG_NFS_FSCACHE
static void nfs_get_cache_cookie(struct super_block *sb,
struct nfs_parsed_mount_data *parsed,
struct nfs_clone_mount *cloned)
{
struct nfs_server *nfss = NFS_SB(sb);
char *uniq = NULL;
int ulen = 0;
nfss->fscache_key = NULL;
nfss->fscache = NULL;
if (parsed) {
if (!(parsed->options & NFS_OPTION_FSCACHE))
return;
if (parsed->fscache_uniq) {
uniq = parsed->fscache_uniq;
ulen = strlen(parsed->fscache_uniq);
}
} else if (cloned) {
struct nfs_server *mnt_s = NFS_SB(cloned->sb);
if (!(mnt_s->options & NFS_OPTION_FSCACHE))
return;
if (mnt_s->fscache_key) {
uniq = mnt_s->fscache_key->key.uniquifier;
ulen = mnt_s->fscache_key->key.uniq_len;
};
} else
return;
nfs_fscache_get_super_cookie(sb, uniq, ulen);
}
#else
static void nfs_get_cache_cookie(struct super_block *sb,
struct nfs_parsed_mount_data *parsed,
struct nfs_clone_mount *cloned)
{
}
#endif
int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
struct nfs_mount_info *mount_info)
{
int error;
unsigned long kflags = 0, kflags_out = 0;
if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL)
kflags |= SECURITY_LSM_NATIVE_LABELS;
error = security_sb_set_mnt_opts(s, &mount_info->parsed->lsm_opts,
kflags, &kflags_out);
if (error)
goto err;
if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL &&
!(kflags_out & SECURITY_LSM_NATIVE_LABELS))
NFS_SB(s)->caps &= ~NFS_CAP_SECURITY_LABEL;
err:
return error;
}
EXPORT_SYMBOL_GPL(nfs_set_sb_security);
int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
struct nfs_mount_info *mount_info)
{
security/selinux: allow security_sb_clone_mnt_opts to enable/disable native labeling behavior When an NFSv4 client performs a mount operation, it first mounts the NFSv4 root and then does path walk to the exported path and performs a submount on that, cloning the security mount options from the root's superblock to the submount's superblock in the process. Unless the NFS server has an explicit fsid=0 export with the "security_label" option, the NFSv4 root superblock will not have SBLABEL_MNT set, and neither will the submount superblock after cloning the security mount options. As a result, setxattr's of security labels over NFSv4.2 will fail. In a similar fashion, NFSv4.2 mounts mounted with the context= mount option will not show the correct labels because the nfs_server->caps flags of the cloned superblock will still have NFS_CAP_SECURITY_LABEL set. Allowing the NFSv4 client to enable or disable SECURITY_LSM_NATIVE_LABELS behavior will ensure that the SBLABEL_MNT flag has the correct value when the client traverses from an exported path without the "security_label" option to one with the "security_label" option and vice versa. Similarly, checking to see if SECURITY_LSM_NATIVE_LABELS is set upon return from security_sb_clone_mnt_opts() and clearing NFS_CAP_SECURITY_LABEL if necessary will allow the correct labels to be displayed for NFSv4.2 mounts mounted with the context= mount option. Resolves: https://github.com/SELinuxProject/selinux-kernel/issues/35 Signed-off-by: Scott Mayhew <smayhew@redhat.com> Reviewed-by: Stephen Smalley <sds@tycho.nsa.gov> Tested-by: Stephen Smalley <sds@tycho.nsa.gov> Signed-off-by: Paul Moore <paul@paul-moore.com>
2017-06-05 23:45:04 +08:00
int error;
unsigned long kflags = 0, kflags_out = 0;
/* clone any lsm security options from the parent to the new sb */
if (d_inode(mntroot)->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops)
return -ESTALE;
security/selinux: allow security_sb_clone_mnt_opts to enable/disable native labeling behavior When an NFSv4 client performs a mount operation, it first mounts the NFSv4 root and then does path walk to the exported path and performs a submount on that, cloning the security mount options from the root's superblock to the submount's superblock in the process. Unless the NFS server has an explicit fsid=0 export with the "security_label" option, the NFSv4 root superblock will not have SBLABEL_MNT set, and neither will the submount superblock after cloning the security mount options. As a result, setxattr's of security labels over NFSv4.2 will fail. In a similar fashion, NFSv4.2 mounts mounted with the context= mount option will not show the correct labels because the nfs_server->caps flags of the cloned superblock will still have NFS_CAP_SECURITY_LABEL set. Allowing the NFSv4 client to enable or disable SECURITY_LSM_NATIVE_LABELS behavior will ensure that the SBLABEL_MNT flag has the correct value when the client traverses from an exported path without the "security_label" option to one with the "security_label" option and vice versa. Similarly, checking to see if SECURITY_LSM_NATIVE_LABELS is set upon return from security_sb_clone_mnt_opts() and clearing NFS_CAP_SECURITY_LABEL if necessary will allow the correct labels to be displayed for NFSv4.2 mounts mounted with the context= mount option. Resolves: https://github.com/SELinuxProject/selinux-kernel/issues/35 Signed-off-by: Scott Mayhew <smayhew@redhat.com> Reviewed-by: Stephen Smalley <sds@tycho.nsa.gov> Tested-by: Stephen Smalley <sds@tycho.nsa.gov> Signed-off-by: Paul Moore <paul@paul-moore.com>
2017-06-05 23:45:04 +08:00
if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL)
kflags |= SECURITY_LSM_NATIVE_LABELS;
error = security_sb_clone_mnt_opts(mount_info->cloned->sb, s, kflags,
&kflags_out);
if (error)
return error;
if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL &&
!(kflags_out & SECURITY_LSM_NATIVE_LABELS))
NFS_SB(s)->caps &= ~NFS_CAP_SECURITY_LABEL;
return 0;
}
EXPORT_SYMBOL_GPL(nfs_clone_sb_security);
struct dentry *nfs_fs_mount_common(struct nfs_server *server,
int flags, const char *dev_name,
struct nfs_mount_info *mount_info,
struct nfs_subversion *nfs_mod)
{
struct super_block *s;
struct dentry *mntroot = ERR_PTR(-ENOMEM);
int (*compare_super)(struct super_block *, void *) = nfs_compare_super;
struct nfs_sb_mountdata sb_mntdata = {
.mntflags = flags,
.server = server,
};
int error;
if (server->flags & NFS_MOUNT_UNSHARED)
compare_super = NULL;
/* -o noac implies -o sync */
if (server->flags & NFS_MOUNT_NOAC)
sb_mntdata.mntflags |= MS_SYNCHRONOUS;
if (mount_info->cloned != NULL && mount_info->cloned->sb != NULL)
if (mount_info->cloned->sb->s_flags & MS_SYNCHRONOUS)
sb_mntdata.mntflags |= MS_SYNCHRONOUS;
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
/* Get a superblock - note that we may end up sharing one that already exists */
s = sget(nfs_mod->nfs_fs, compare_super, nfs_set_super, flags, &sb_mntdata);
if (IS_ERR(s)) {
mntroot = ERR_CAST(s);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
goto out_err_nosb;
}
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
if (s->s_fs_info != server) {
nfs_free_server(server);
server = NULL;
} else {
nfs: Fix bdi handling for cloned superblocks In commit 0d3b12584972 "nfs: Convert to separately allocated bdi" I have wrongly cloned bdi reference in nfs_clone_super(). Further inspection has shown that originally the code was actually allocating a new bdi (in ->clone_server callback) which was later registered in nfs_fs_mount_common() and used for sb->s_bdi in nfs_initialise_sb(). This could later result in bdi for the original superblock not getting unregistered when that superblock got shutdown (as the cloned sb still held bdi reference) and later when a new superblock was created under the same anonymous device number, a clash in sysfs has happened on bdi registration: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 10284 at /linux-next/fs/sysfs/dir.c:31 sysfs_warn_dup+0x64/0x74 sysfs: cannot create duplicate filename '/devices/virtual/bdi/0:32' Modules linked in: axp20x_usb_power gpio_axp209 nvmem_sunxi_sid sun4i_dma sun4i_ss virt_dma CPU: 1 PID: 10284 Comm: mount.nfs Not tainted 4.11.0-rc4+ #14 Hardware name: Allwinner sun7i (A20) Family [<c010f19c>] (unwind_backtrace) from [<c010bc74>] (show_stack+0x10/0x14) [<c010bc74>] (show_stack) from [<c03c6e24>] (dump_stack+0x78/0x8c) [<c03c6e24>] (dump_stack) from [<c0122200>] (__warn+0xe8/0x100) [<c0122200>] (__warn) from [<c0122250>] (warn_slowpath_fmt+0x38/0x48) [<c0122250>] (warn_slowpath_fmt) from [<c02ac178>] (sysfs_warn_dup+0x64/0x74) [<c02ac178>] (sysfs_warn_dup) from [<c02ac254>] (sysfs_create_dir_ns+0x84/0x94) [<c02ac254>] (sysfs_create_dir_ns) from [<c03c8b8c>] (kobject_add_internal+0x9c/0x2ec) [<c03c8b8c>] (kobject_add_internal) from [<c03c8e24>] (kobject_add+0x48/0x98) [<c03c8e24>] (kobject_add) from [<c048d75c>] (device_add+0xe4/0x5a0) [<c048d75c>] (device_add) from [<c048ddb4>] (device_create_groups_vargs+0xac/0xbc) [<c048ddb4>] (device_create_groups_vargs) from [<c048dde4>] (device_create_vargs+0x20/0x28) [<c048dde4>] (device_create_vargs) from [<c02075c8>] (bdi_register_va+0x44/0xfc) [<c02075c8>] (bdi_register_va) from [<c023d378>] (super_setup_bdi_name+0x48/0xa4) [<c023d378>] (super_setup_bdi_name) from [<c0312ef4>] (nfs_fill_super+0x1a4/0x204) [<c0312ef4>] (nfs_fill_super) from [<c03133f0>] (nfs_fs_mount_common+0x140/0x1e8) [<c03133f0>] (nfs_fs_mount_common) from [<c03335cc>] (nfs4_remote_mount+0x50/0x58) [<c03335cc>] (nfs4_remote_mount) from [<c023ef98>] (mount_fs+0x14/0xa4) [<c023ef98>] (mount_fs) from [<c025cba0>] (vfs_kern_mount+0x54/0x128) [<c025cba0>] (vfs_kern_mount) from [<c033352c>] (nfs_do_root_mount+0x80/0xa0) [<c033352c>] (nfs_do_root_mount) from [<c0333818>] (nfs4_try_mount+0x28/0x3c) [<c0333818>] (nfs4_try_mount) from [<c0313874>] (nfs_fs_mount+0x2cc/0x8c4) [<c0313874>] (nfs_fs_mount) from [<c023ef98>] (mount_fs+0x14/0xa4) [<c023ef98>] (mount_fs) from [<c025cba0>] (vfs_kern_mount+0x54/0x128) [<c025cba0>] (vfs_kern_mount) from [<c02600f0>] (do_mount+0x158/0xc7c) [<c02600f0>] (do_mount) from [<c0260f98>] (SyS_mount+0x8c/0xb4) [<c0260f98>] (SyS_mount) from [<c0107840>] (ret_fast_syscall+0x0/0x3c) Fix the problem by always creating new bdi for a superblock as we used to do. Reported-and-tested-by: Corentin Labbe <clabbe.montjoie@gmail.com> Fixes: 0d3b12584972ce5781179ad3f15cca3cdb5cae05 Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-04 15:02:42 +08:00
error = super_setup_bdi_name(s, "%u:%u", MAJOR(server->s_dev),
MINOR(server->s_dev));
if (error) {
mntroot = ERR_PTR(error);
goto error_splat_super;
}
s->s_bdi->ra_pages = server->rpages * NFS_MAX_READAHEAD;
server->super = s;
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
}
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
if (!s->s_root) {
/* initial superblock/root creation */
nfs: Fix bdi handling for cloned superblocks In commit 0d3b12584972 "nfs: Convert to separately allocated bdi" I have wrongly cloned bdi reference in nfs_clone_super(). Further inspection has shown that originally the code was actually allocating a new bdi (in ->clone_server callback) which was later registered in nfs_fs_mount_common() and used for sb->s_bdi in nfs_initialise_sb(). This could later result in bdi for the original superblock not getting unregistered when that superblock got shutdown (as the cloned sb still held bdi reference) and later when a new superblock was created under the same anonymous device number, a clash in sysfs has happened on bdi registration: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 10284 at /linux-next/fs/sysfs/dir.c:31 sysfs_warn_dup+0x64/0x74 sysfs: cannot create duplicate filename '/devices/virtual/bdi/0:32' Modules linked in: axp20x_usb_power gpio_axp209 nvmem_sunxi_sid sun4i_dma sun4i_ss virt_dma CPU: 1 PID: 10284 Comm: mount.nfs Not tainted 4.11.0-rc4+ #14 Hardware name: Allwinner sun7i (A20) Family [<c010f19c>] (unwind_backtrace) from [<c010bc74>] (show_stack+0x10/0x14) [<c010bc74>] (show_stack) from [<c03c6e24>] (dump_stack+0x78/0x8c) [<c03c6e24>] (dump_stack) from [<c0122200>] (__warn+0xe8/0x100) [<c0122200>] (__warn) from [<c0122250>] (warn_slowpath_fmt+0x38/0x48) [<c0122250>] (warn_slowpath_fmt) from [<c02ac178>] (sysfs_warn_dup+0x64/0x74) [<c02ac178>] (sysfs_warn_dup) from [<c02ac254>] (sysfs_create_dir_ns+0x84/0x94) [<c02ac254>] (sysfs_create_dir_ns) from [<c03c8b8c>] (kobject_add_internal+0x9c/0x2ec) [<c03c8b8c>] (kobject_add_internal) from [<c03c8e24>] (kobject_add+0x48/0x98) [<c03c8e24>] (kobject_add) from [<c048d75c>] (device_add+0xe4/0x5a0) [<c048d75c>] (device_add) from [<c048ddb4>] (device_create_groups_vargs+0xac/0xbc) [<c048ddb4>] (device_create_groups_vargs) from [<c048dde4>] (device_create_vargs+0x20/0x28) [<c048dde4>] (device_create_vargs) from [<c02075c8>] (bdi_register_va+0x44/0xfc) [<c02075c8>] (bdi_register_va) from [<c023d378>] (super_setup_bdi_name+0x48/0xa4) [<c023d378>] (super_setup_bdi_name) from [<c0312ef4>] (nfs_fill_super+0x1a4/0x204) [<c0312ef4>] (nfs_fill_super) from [<c03133f0>] (nfs_fs_mount_common+0x140/0x1e8) [<c03133f0>] (nfs_fs_mount_common) from [<c03335cc>] (nfs4_remote_mount+0x50/0x58) [<c03335cc>] (nfs4_remote_mount) from [<c023ef98>] (mount_fs+0x14/0xa4) [<c023ef98>] (mount_fs) from [<c025cba0>] (vfs_kern_mount+0x54/0x128) [<c025cba0>] (vfs_kern_mount) from [<c033352c>] (nfs_do_root_mount+0x80/0xa0) [<c033352c>] (nfs_do_root_mount) from [<c0333818>] (nfs4_try_mount+0x28/0x3c) [<c0333818>] (nfs4_try_mount) from [<c0313874>] (nfs_fs_mount+0x2cc/0x8c4) [<c0313874>] (nfs_fs_mount) from [<c023ef98>] (mount_fs+0x14/0xa4) [<c023ef98>] (mount_fs) from [<c025cba0>] (vfs_kern_mount+0x54/0x128) [<c025cba0>] (vfs_kern_mount) from [<c02600f0>] (do_mount+0x158/0xc7c) [<c02600f0>] (do_mount) from [<c0260f98>] (SyS_mount+0x8c/0xb4) [<c0260f98>] (SyS_mount) from [<c0107840>] (ret_fast_syscall+0x0/0x3c) Fix the problem by always creating new bdi for a superblock as we used to do. Reported-and-tested-by: Corentin Labbe <clabbe.montjoie@gmail.com> Fixes: 0d3b12584972ce5781179ad3f15cca3cdb5cae05 Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-04 15:02:42 +08:00
mount_info->fill_super(s, mount_info);
nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
}
mntroot = nfs_get_root(s, mount_info->mntfh, dev_name);
if (IS_ERR(mntroot))
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
goto error_splat_super;
error = mount_info->set_security(s, mntroot, mount_info);
if (error)
goto error_splat_root;
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
s->s_flags |= MS_ACTIVE;
out:
return mntroot;
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
out_err_nosb:
nfs_free_server(server);
goto out;
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
error_splat_root:
dput(mntroot);
mntroot = ERR_PTR(error);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
error_splat_super:
deactivate_locked_super(s);
goto out;
}
EXPORT_SYMBOL_GPL(nfs_fs_mount_common);
struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *raw_data)
{
struct nfs_mount_info mount_info = {
.fill_super = nfs_fill_super,
.set_security = nfs_set_sb_security,
};
struct dentry *mntroot = ERR_PTR(-ENOMEM);
struct nfs_subversion *nfs_mod;
int error;
mount_info.parsed = nfs_alloc_parsed_mount_data();
mount_info.mntfh = nfs_alloc_fhandle();
if (mount_info.parsed == NULL || mount_info.mntfh == NULL)
goto out;
/* Validate the mount data */
error = nfs_validate_mount_data(fs_type, raw_data, mount_info.parsed, mount_info.mntfh, dev_name);
if (error == NFS_TEXT_DATA)
error = nfs_validate_text_mount_data(raw_data, mount_info.parsed, dev_name);
if (error < 0) {
mntroot = ERR_PTR(error);
goto out;
}
nfs_mod = get_nfs_version(mount_info.parsed->version);
if (IS_ERR(nfs_mod)) {
mntroot = ERR_CAST(nfs_mod);
goto out;
}
mntroot = nfs_mod->rpc_ops->try_mount(flags, dev_name, &mount_info, nfs_mod);
put_nfs_version(nfs_mod);
out:
nfs_free_parsed_mount_data(mount_info.parsed);
nfs_free_fhandle(mount_info.mntfh);
return mntroot;
}
EXPORT_SYMBOL_GPL(nfs_fs_mount);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
/*
* Destroy an NFS2/3 superblock
*/
void nfs_kill_super(struct super_block *s)
{
struct nfs_server *server = NFS_SB(s);
dev_t dev = s->s_dev;
generic_shutdown_super(s);
NFS: Define and create superblock-level objects Define and create superblock-level cache index objects (as managed by nfs_server structs). Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The superblock object key is a sequence consisting of: (1) Certain superblock s_flags. (2) Various connection parameters that serve to distinguish superblocks for sget(). (3) The volume FSID. (4) The security flavour. (5) The uniquifier length. (6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier. The key blob is of variable length, depending on the length of (6). The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent. This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com>
2009-04-03 23:42:42 +08:00
nfs_fscache_release_super_cookie(s);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
nfs_free_server(server);
free_anon_bdev(dev);
}
EXPORT_SYMBOL_GPL(nfs_kill_super);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
/*
* Clone an NFS2/3/4 server record on xdev traversal (FSID-change)
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
*/
static struct dentry *
nfs_xdev_mount(struct file_system_type *fs_type, int flags,
const char *dev_name, void *raw_data)
{
struct nfs_clone_mount *data = raw_data;
struct nfs_mount_info mount_info = {
.fill_super = nfs_clone_super,
.set_security = nfs_clone_sb_security,
.cloned = data,
};
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
struct nfs_server *server;
struct dentry *mntroot = ERR_PTR(-ENOMEM);
struct nfs_subversion *nfs_mod = NFS_SB(data->sb)->nfs_client->cl_nfs_mod;
dprintk("--> nfs_xdev_mount()\n");
mount_info.mntfh = mount_info.cloned->fh;
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
/* create a new volume representation */
server = nfs_mod->rpc_ops->clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
if (IS_ERR(server))
mntroot = ERR_CAST(server);
else
mntroot = nfs_fs_mount_common(server, flags,
dev_name, &mount_info, nfs_mod);
dprintk("<-- nfs_xdev_mount() = %ld\n",
IS_ERR(mntroot) ? PTR_ERR(mntroot) : 0L);
return mntroot;
}
#if IS_ENABLED(CONFIG_NFS_V4)
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args)
{
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 20:55:58 +08:00
args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3|
NFS_MOUNT_LOCAL_FLOCK|NFS_MOUNT_LOCAL_FCNTL);
}
/*
* Validate NFSv4 mount options
*/
static int nfs4_validate_mount_data(void *options,
struct nfs_parsed_mount_data *args,
const char *dev_name)
{
struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
struct nfs4_mount_data *data = (struct nfs4_mount_data *)options;
char *c;
if (data == NULL)
goto out_no_data;
args->version = 4;
switch (data->version) {
case 1:
if (data->host_addrlen > sizeof(args->nfs_server.address))
goto out_no_address;
if (data->host_addrlen == 0)
goto out_no_address;
args->nfs_server.addrlen = data->host_addrlen;
if (copy_from_user(sap, data->host_addr, data->host_addrlen))
return -EFAULT;
if (!nfs_verify_server_address(sap))
goto out_no_address;
args->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port);
if (data->auth_flavourlen) {
rpc_authflavor_t pseudoflavor;
if (data->auth_flavourlen > 1)
goto out_inval_auth;
if (copy_from_user(&pseudoflavor,
data->auth_flavours,
sizeof(pseudoflavor)))
return -EFAULT;
args->selected_flavor = pseudoflavor;
} else
args->selected_flavor = RPC_AUTH_UNIX;
c = strndup_user(data->hostname.data, NFS4_MAXNAMLEN);
if (IS_ERR(c))
return PTR_ERR(c);
args->nfs_server.hostname = c;
c = strndup_user(data->mnt_path.data, NFS4_MAXPATHLEN);
if (IS_ERR(c))
return PTR_ERR(c);
args->nfs_server.export_path = c;
dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", c);
c = strndup_user(data->client_addr.data, 16);
if (IS_ERR(c))
return PTR_ERR(c);
args->client_address = c;
/*
* Translate to nfs_parsed_mount_data, which nfs4_fill_super
* can deal with.
*/
args->flags = data->flags & NFS4_MOUNT_FLAGMASK;
args->rsize = data->rsize;
args->wsize = data->wsize;
args->timeo = data->timeo;
args->retrans = data->retrans;
args->acregmin = data->acregmin;
args->acregmax = data->acregmax;
args->acdirmin = data->acdirmin;
args->acdirmax = data->acdirmax;
args->nfs_server.protocol = data->proto;
nfs_validate_transport_protocol(args);
if (args->nfs_server.protocol == XPRT_TRANSPORT_UDP)
goto out_invalid_transport_udp;
break;
default:
return NFS_TEXT_DATA;
}
return 0;
out_no_data:
dfprintk(MOUNT, "NFS4: mount program didn't pass any mount data\n");
return -EINVAL;
out_inval_auth:
dfprintk(MOUNT, "NFS4: Invalid number of RPC auth flavours %d\n",
data->auth_flavourlen);
return -EINVAL;
out_no_address:
dfprintk(MOUNT, "NFS4: mount program didn't pass remote address\n");
return -EINVAL;
out_invalid_transport_udp:
dfprintk(MOUNT, "NFSv4: Unsupported transport protocol udp\n");
return -EINVAL;
}
/*
* NFS v4 module parameters need to stay in the
* NFS client for backwards compatibility
*/
unsigned int nfs_callback_set_tcpport;
unsigned short nfs_callback_nr_threads;
/* Default cache timeout is 10 minutes */
unsigned int nfs_idmap_cache_timeout = 600;
/* Turn off NFSv4 uid/gid mapping when using AUTH_SYS */
bool nfs4_disable_idmapping = true;
unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE;
unsigned short max_session_cb_slots = NFS4_DEF_CB_SLOT_TABLE_SIZE;
unsigned short send_implementation_id = 1;
char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN] = "";
bool recover_lost_locks = false;
EXPORT_SYMBOL_GPL(nfs_callback_nr_threads);
EXPORT_SYMBOL_GPL(nfs_callback_set_tcpport);
EXPORT_SYMBOL_GPL(nfs_idmap_cache_timeout);
EXPORT_SYMBOL_GPL(nfs4_disable_idmapping);
EXPORT_SYMBOL_GPL(max_session_slots);
EXPORT_SYMBOL_GPL(max_session_cb_slots);
EXPORT_SYMBOL_GPL(send_implementation_id);
EXPORT_SYMBOL_GPL(nfs4_client_id_uniquifier);
EXPORT_SYMBOL_GPL(recover_lost_locks);
#define NFS_CALLBACK_MAXPORTNR (65535U)
static int param_set_portnr(const char *val, const struct kernel_param *kp)
{
unsigned long num;
int ret;
if (!val)
return -EINVAL;
ret = kstrtoul(val, 0, &num);
if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR)
return -EINVAL;
*((unsigned int *)kp->arg) = num;
return 0;
}
static const struct kernel_param_ops param_ops_portnr = {
.set = param_set_portnr,
.get = param_get_uint,
};
#define param_check_portnr(name, p) __param_check(name, p, unsigned int);
module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
module_param_named(callback_nr_threads, nfs_callback_nr_threads, ushort, 0644);
MODULE_PARM_DESC(callback_nr_threads, "Number of threads that will be "
"assigned to the NFSv4 callback channels.");
module_param(nfs_idmap_cache_timeout, int, 0644);
module_param(nfs4_disable_idmapping, bool, 0644);
module_param_string(nfs4_unique_id, nfs4_client_id_uniquifier,
NFS4_CLIENT_ID_UNIQ_LEN, 0600);
MODULE_PARM_DESC(nfs4_disable_idmapping,
"Turn off NFSv4 idmapping when using 'sec=sys'");
module_param(max_session_slots, ushort, 0644);
MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 "
"requests the client will negotiate");
module_param(max_session_cb_slots, ushort, 0644);
MODULE_PARM_DESC(max_session_cb_slots, "Maximum number of parallel NFSv4.1 "
"callbacks the client will process for a given server");
module_param(send_implementation_id, ushort, 0644);
MODULE_PARM_DESC(send_implementation_id,
"Send implementation ID with NFSv4.1 exchange_id");
MODULE_PARM_DESC(nfs4_unique_id, "nfs_client_id4 uniquifier string");
module_param(recover_lost_locks, bool, 0644);
MODULE_PARM_DESC(recover_lost_locks,
"If the server reports that a lock might be lost, "
"try to recover it risking data corruption.");
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 08:06:13 +08:00
#endif /* CONFIG_NFS_V4 */