From 03d6a74b5f85ff46f20e1382982b7f4860f5fec6 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 22 Sep 2009 11:09:12 -0400 Subject: nfsd: fix Documentation typo Caught by Benny, thanks! Signed-off-by: J. Bruce Fields --- Documentation/filesystems/nfs41-server.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/filesystems/nfs41-server.txt b/Documentation/filesystems/nfs41-server.txt index 5920fe26e6f..1f95e773188 100644 --- a/Documentation/filesystems/nfs41-server.txt +++ b/Documentation/filesystems/nfs41-server.txt @@ -41,7 +41,7 @@ interoperability problems with future clients. Known issues: conformant with the spec (for example, we don't use kerberos on the backchannel correctly). - no trunking support: no clients currently take advantage of - trunking, but this is a mandatory failure, and its use is + trunking, but this is a mandatory feature, and its use is recommended to clients in a number of places. (E.g. to ensure timely renewal in case an existing connection's retry timeouts have gotten too long; see section 8.3 of the draft.) -- cgit v1.2.3-18-g5258 From fed83811269d0f559d2da9139e12c5e5d9874d5c Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sat, 26 Sep 2009 16:53:01 -0400 Subject: nfsd4: cross mountpoints when looking up parents 3c394ddaa7ea4205f933fd9b481166b2669368a9 "nfsd4: nfsv4 clients should cross mountpoints" forgot to handle lookups of parents directories. Signed-off-by: J. Bruce Fields --- fs/nfsd/vfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index a293f027326..b8ed58bab8b 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -169,7 +169,7 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, dentry = dget(dparent); else if (dparent != exp->ex_path.dentry) dentry = dget_parent(dparent); - else if (!EX_NOHIDE(exp)) + else if (!EX_NOHIDE(exp) && !nfsd_v4client(rqstp)) dentry = dget(dparent); /* .. == . just like at / */ else { /* checking mountpoint crossing is very different when stepping up */ -- cgit v1.2.3-18-g5258 From 289ede453e5a621de19c61e630302b1845cc1d59 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sat, 26 Sep 2009 20:32:24 -0400 Subject: nfsd: minor nfsd_lookup cleanup Break out some of nfsd_lookup_dentry into helper functions. Signed-off-by: J. Bruce Fields --- fs/nfsd/vfs.c | 60 +++++++++++++++++++++++++++++++++++------------------------ 1 file changed, 36 insertions(+), 24 deletions(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index b8ed58bab8b..638573968dc 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -141,6 +141,40 @@ out: return err; } +static void follow_to_parent(struct path *path) +{ + struct dentry *dp; + + while (path->dentry == path->mnt->mnt_root && follow_up(path)) + ; + dp = dget_parent(path->dentry); + dput(path->dentry); + path->dentry = dp; +} + +static int nfsd_lookup_parent(struct svc_rqst *rqstp, struct dentry *dparent, struct svc_export **exp, struct dentry **dentryp) +{ + struct svc_export *exp2; + struct path path = {.mnt = mntget((*exp)->ex_path.mnt), + .dentry = dget(dparent)}; + + follow_to_parent(&path); + + exp2 = rqst_exp_parent(rqstp, &path); + if (PTR_ERR(exp2) == -ENOENT) { + *dentryp = dget(dparent); + } else if (IS_ERR(exp2)) { + path_put(&path); + return PTR_ERR(exp2); + } else { + *dentryp = dget(path.dentry); + exp_put(*exp); + *exp = exp2; + } + path_put(&path); + return 0; +} + __be32 nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, unsigned int len, @@ -173,31 +207,9 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, dentry = dget(dparent); /* .. == . just like at / */ else { /* checking mountpoint crossing is very different when stepping up */ - struct svc_export *exp2 = NULL; - struct dentry *dp; - struct path path = {.mnt = mntget(exp->ex_path.mnt), - .dentry = dget(dparent)}; - - while (path.dentry == path.mnt->mnt_root && - follow_up(&path)) - ; - dp = dget_parent(path.dentry); - dput(path.dentry); - path.dentry = dp; - - exp2 = rqst_exp_parent(rqstp, &path); - if (PTR_ERR(exp2) == -ENOENT) { - dentry = dget(dparent); - } else if (IS_ERR(exp2)) { - host_err = PTR_ERR(exp2); - path_put(&path); + host_err = nfsd_lookup_parent(rqstp, dparent, &exp, &dentry); + if (host_err) goto out_nfserr; - } else { - dentry = dget(path.dentry); - exp_put(exp); - exp = exp2; - } - path_put(&path); } } else { fh_lock(fhp); -- cgit v1.2.3-18-g5258 From f39bde24b275ddc45df1ed835725b609e178c7a0 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sun, 27 Sep 2009 14:41:43 -0400 Subject: nfsd4: fix error return when pseudoroot missing We really shouldn't hit this case at all, and forthcoming kernel and nfs-utils changes should eliminate this case; if it does happen, consider it a bug rather than reporting an error that doesn't really make sense for the operation (since there's no reason for a server to be accepting v4 traffic yet have no root filehandle). Also move some exp_pseudoroot code into a helper function while we're here. Signed-off-by: J. Bruce Fields --- fs/nfsd/export.c | 22 ++++++++++++++++++---- fs/nfsd/nfsproc.c | 1 + 2 files changed, 19 insertions(+), 4 deletions(-) diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index c1c9e035d4a..b73baba3fb9 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -1320,6 +1320,23 @@ rqst_exp_parent(struct svc_rqst *rqstp, struct path *path) return exp; } +static struct svc_export *find_fsidzero_export(struct svc_rqst *rqstp) +{ + struct svc_export *exp; + u32 fsidv[2]; + + mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL); + + exp = rqst_exp_find(rqstp, FSID_NUM, fsidv); + /* + * We shouldn't have accepting an nfsv4 request at all if we + * don't have a pseudoexport!: + */ + if (IS_ERR(exp) && PTR_ERR(exp) == -ENOENT) + exp = ERR_PTR(-ESERVERFAULT); + return exp; +} + /* * Called when we need the filehandle for the root of the pseudofs, * for a given NFSv4 client. The root is defined to be the @@ -1330,11 +1347,8 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp) { struct svc_export *exp; __be32 rv; - u32 fsidv[2]; - - mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL); - exp = rqst_exp_find(rqstp, FSID_NUM, fsidv); + exp = find_fsidzero_export(rqstp); if (IS_ERR(exp)) return nfserrno(PTR_ERR(exp)); rv = fh_compose(fhp, exp, exp->ex_path.dentry, NULL); diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 0eb9c820b7a..c5393d1b895 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -758,6 +758,7 @@ nfserrno (int errno) { nfserr_io, -ETXTBSY }, { nfserr_notsupp, -EOPNOTSUPP }, { nfserr_toosmall, -ETOOSMALL }, + { nfserr_serverfault, -ESERVERFAULT }, }; int i; -- cgit v1.2.3-18-g5258 From ddc04fd4d5163aee9ebdb38a56c365b602e2b7b7 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Wed, 23 Sep 2009 21:32:21 -0400 Subject: nfsd41: use sv_max_mesg for forechannel max sizes ca_maxresponsesize and ca_maxrequest size include the RPC header. sv_max_mesg is sv_max_payolad plus a page for overhead and is used in svc_init_buffer to allocate server buffer space for both the request and reply. Note that this means we can service an RPC compound that requires ca_maxrequestsize (MAXWRITE) or ca_max_responsesize (MAXREAD) but that we do not support an RPC compound that requires both ca_maxrequestsize and ca_maxresponsesize. Signed-off-by: Andy Adamson [bfields@citi.umich.edu: more documentation updates] Signed-off-by: J. Bruce Fields --- Documentation/filesystems/nfs41-server.txt | 7 +++++++ fs/nfsd/nfs4state.c | 3 ++- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/Documentation/filesystems/nfs41-server.txt b/Documentation/filesystems/nfs41-server.txt index 1f95e773188..1bd0d0c0517 100644 --- a/Documentation/filesystems/nfs41-server.txt +++ b/Documentation/filesystems/nfs41-server.txt @@ -213,3 +213,10 @@ The following cases aren't supported yet: DESTROY_CLIENTID, DESTROY_SESSION, EXCHANGE_ID. * DESTROY_SESSION MUST be the final operation in the COMPOUND request. +Nonstandard compound limitations: +* No support for a sessions fore channel RPC compound that requires both a + ca_maxrequestsize request and a ca_maxresponsesize reply, so we may + fail to live up to the promise we made in CREATE_SESSION fore channel + negotiation. +* No more than one IO operation (read, write, readdir) allowed per + compound. diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 2153f9bdbeb..fcb9817881a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -477,13 +477,14 @@ static int set_forechannel_drc_size(struct nfsd4_channel_attrs *fchan) /* * fchan holds the client values on input, and the server values on output + * sv_max_mesg is the maximum payload plus one page for overhead. */ static int init_forechannel_attrs(struct svc_rqst *rqstp, struct nfsd4_channel_attrs *session_fchan, struct nfsd4_channel_attrs *fchan) { int status = 0; - __u32 maxcount = svc_max_payload(rqstp); + __u32 maxcount = nfsd_serv->sv_max_mesg; /* headerpadsz set to zero in encode routine */ -- cgit v1.2.3-18-g5258 From dc7a08166f3a5f23e79e839a8a88849bd3397c32 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 27 Oct 2009 14:41:35 -0400 Subject: nfs: new subdir Documentation/filesystems/nfs We're adding enough nfs documentation that it may as well have its own subdirectory. Acked-by: Randy Dunlap Signed-off-by: J. Bruce Fields --- Documentation/filesystems/00-INDEX | 10 +- Documentation/filesystems/Exporting | 147 -------------- Documentation/filesystems/nfs-rdma.txt | 271 ------------------------- Documentation/filesystems/nfs.txt | 98 --------- Documentation/filesystems/nfs/00-INDEX | 12 ++ Documentation/filesystems/nfs/Exporting | 147 ++++++++++++++ Documentation/filesystems/nfs/nfs-rdma.txt | 271 +++++++++++++++++++++++++ Documentation/filesystems/nfs/nfs.txt | 98 +++++++++ Documentation/filesystems/nfs/nfs41-server.txt | 222 ++++++++++++++++++++ Documentation/filesystems/nfs/nfsroot.txt | 270 ++++++++++++++++++++++++ Documentation/filesystems/nfs41-server.txt | 222 -------------------- Documentation/filesystems/nfsroot.txt | 270 ------------------------ Documentation/filesystems/porting | 2 +- Documentation/kernel-parameters.txt | 6 +- fs/cifs/export.c | 2 +- fs/exportfs/expfs.c | 2 +- fs/isofs/export.c | 2 +- fs/nfs/Kconfig | 2 +- include/linux/exportfs.h | 2 +- net/ipv4/Kconfig | 6 +- net/ipv4/ipconfig.c | 2 +- 21 files changed, 1035 insertions(+), 1029 deletions(-) delete mode 100644 Documentation/filesystems/Exporting delete mode 100644 Documentation/filesystems/nfs-rdma.txt delete mode 100644 Documentation/filesystems/nfs.txt create mode 100644 Documentation/filesystems/nfs/00-INDEX create mode 100644 Documentation/filesystems/nfs/Exporting create mode 100644 Documentation/filesystems/nfs/nfs-rdma.txt create mode 100644 Documentation/filesystems/nfs/nfs.txt create mode 100644 Documentation/filesystems/nfs/nfs41-server.txt create mode 100644 Documentation/filesystems/nfs/nfsroot.txt delete mode 100644 Documentation/filesystems/nfs41-server.txt delete mode 100644 Documentation/filesystems/nfsroot.txt diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index f15621ee559..482151c883a 100644 --- a/Documentation/filesystems/00-INDEX +++ b/Documentation/filesystems/00-INDEX @@ -1,7 +1,5 @@ 00-INDEX - this file (info on some of the filesystems supported by linux). -Exporting - - explanation of how to make filesystems exportable. Locking - info on locking rules as they pertain to Linux VFS. 9p.txt @@ -66,12 +64,8 @@ mandatory-locking.txt - info on the Linux implementation of Sys V mandatory file locking. ncpfs.txt - info on Novell Netware(tm) filesystem using NCP protocol. -nfs41-server.txt - - info on the Linux server implementation of NFSv4 minor version 1. -nfs-rdma.txt - - how to install and setup the Linux NFS/RDMA client and server software. -nfsroot.txt - - short guide on setting up a diskless box with NFS root filesystem. +nfs/ + - nfs-related documentation. nilfs2.txt - info and mount options for the NILFS2 filesystem. ntfs.txt diff --git a/Documentation/filesystems/Exporting b/Documentation/filesystems/Exporting deleted file mode 100644 index 87019d2b598..00000000000 --- a/Documentation/filesystems/Exporting +++ /dev/null @@ -1,147 +0,0 @@ - -Making Filesystems Exportable -============================= - -Overview --------- - -All filesystem operations require a dentry (or two) as a starting -point. Local applications have a reference-counted hold on suitable -dentries via open file descriptors or cwd/root. However remote -applications that access a filesystem via a remote filesystem protocol -such as NFS may not be able to hold such a reference, and so need a -different way to refer to a particular dentry. As the alternative -form of reference needs to be stable across renames, truncates, and -server-reboot (among other things, though these tend to be the most -problematic), there is no simple answer like 'filename'. - -The mechanism discussed here allows each filesystem implementation to -specify how to generate an opaque (outside of the filesystem) byte -string for any dentry, and how to find an appropriate dentry for any -given opaque byte string. -This byte string will be called a "filehandle fragment" as it -corresponds to part of an NFS filehandle. - -A filesystem which supports the mapping between filehandle fragments -and dentries will be termed "exportable". - - - -Dcache Issues -------------- - -The dcache normally contains a proper prefix of any given filesystem -tree. This means that if any filesystem object is in the dcache, then -all of the ancestors of that filesystem object are also in the dcache. -As normal access is by filename this prefix is created naturally and -maintained easily (by each object maintaining a reference count on -its parent). - -However when objects are included into the dcache by interpreting a -filehandle fragment, there is no automatic creation of a path prefix -for the object. This leads to two related but distinct features of -the dcache that are not needed for normal filesystem access. - -1/ The dcache must sometimes contain objects that are not part of the - proper prefix. i.e that are not connected to the root. -2/ The dcache must be prepared for a newly found (via ->lookup) directory - to already have a (non-connected) dentry, and must be able to move - that dentry into place (based on the parent and name in the - ->lookup). This is particularly needed for directories as - it is a dcache invariant that directories only have one dentry. - -To implement these features, the dcache has: - -a/ A dentry flag DCACHE_DISCONNECTED which is set on - any dentry that might not be part of the proper prefix. - This is set when anonymous dentries are created, and cleared when a - dentry is noticed to be a child of a dentry which is in the proper - prefix. - -b/ A per-superblock list "s_anon" of dentries which are the roots of - subtrees that are not in the proper prefix. These dentries, as - well as the proper prefix, need to be released at unmount time. As - these dentries will not be hashed, they are linked together on the - d_hash list_head. - -c/ Helper routines to allocate anonymous dentries, and to help attach - loose directory dentries at lookup time. They are: - d_alloc_anon(inode) will return a dentry for the given inode. - If the inode already has a dentry, one of those is returned. - If it doesn't, a new anonymous (IS_ROOT and - DCACHE_DISCONNECTED) dentry is allocated and attached. - In the case of a directory, care is taken that only one dentry - can ever be attached. - d_splice_alias(inode, dentry) will make sure that there is a - dentry with the same name and parent as the given dentry, and - which refers to the given inode. - If the inode is a directory and already has a dentry, then that - dentry is d_moved over the given dentry. - If the passed dentry gets attached, care is taken that this is - mutually exclusive to a d_alloc_anon operation. - If the passed dentry is used, NULL is returned, else the used - dentry is returned. This corresponds to the calling pattern of - ->lookup. - - -Filesystem Issues ------------------ - -For a filesystem to be exportable it must: - - 1/ provide the filehandle fragment routines described below. - 2/ make sure that d_splice_alias is used rather than d_add - when ->lookup finds an inode for a given parent and name. - Typically the ->lookup routine will end with a: - - return d_splice_alias(inode, dentry); - } - - - - A file system implementation declares that instances of the filesystem -are exportable by setting the s_export_op field in the struct -super_block. This field must point to a "struct export_operations" -struct which has the following members: - - encode_fh (optional) - Takes a dentry and creates a filehandle fragment which can later be used - to find or create a dentry for the same object. The default - implementation creates a filehandle fragment that encodes a 32bit inode - and generation number for the inode encoded, and if necessary the - same information for the parent. - - fh_to_dentry (mandatory) - Given a filehandle fragment, this should find the implied object and - create a dentry for it (possibly with d_alloc_anon). - - fh_to_parent (optional but strongly recommended) - Given a filehandle fragment, this should find the parent of the - implied object and create a dentry for it (possibly with d_alloc_anon). - May fail if the filehandle fragment is too small. - - get_parent (optional but strongly recommended) - When given a dentry for a directory, this should return a dentry for - the parent. Quite possibly the parent dentry will have been allocated - by d_alloc_anon. The default get_parent function just returns an error - so any filehandle lookup that requires finding a parent will fail. - ->lookup("..") is *not* used as a default as it can leave ".." entries - in the dcache which are too messy to work with. - - get_name (optional) - When given a parent dentry and a child dentry, this should find a name - in the directory identified by the parent dentry, which leads to the - object identified by the child dentry. If no get_name function is - supplied, a default implementation is provided which uses vfs_readdir - to find potential names, and matches inode numbers to find the correct - match. - - -A filehandle fragment consists of an array of 1 or more 4byte words, -together with a one byte "type". -The decode_fh routine should not depend on the stated size that is -passed to it. This size may be larger than the original filehandle -generated by encode_fh, in which case it will have been padded with -nuls. Rather, the encode_fh routine should choose a "type" which -indicates the decode_fh how much of the filehandle is valid, and how -it should be interpreted. diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs-rdma.txt deleted file mode 100644 index e386f7e4bce..00000000000 --- a/Documentation/filesystems/nfs-rdma.txt +++ /dev/null @@ -1,271 +0,0 @@ -################################################################################ -# # -# NFS/RDMA README # -# # -################################################################################ - - Author: NetApp and Open Grid Computing - Date: May 29, 2008 - -Table of Contents -~~~~~~~~~~~~~~~~~ - - Overview - - Getting Help - - Installation - - Check RDMA and NFS Setup - - NFS/RDMA Setup - -Overview -~~~~~~~~ - - This document describes how to install and setup the Linux NFS/RDMA client - and server software. - - The NFS/RDMA client was first included in Linux 2.6.24. The NFS/RDMA server - was first included in the following release, Linux 2.6.25. - - In our testing, we have obtained excellent performance results (full 10Gbit - wire bandwidth at minimal client CPU) under many workloads. The code passes - the full Connectathon test suite and operates over both Infiniband and iWARP - RDMA adapters. - -Getting Help -~~~~~~~~~~~~ - - If you get stuck, you can ask questions on the - - nfs-rdma-devel@lists.sourceforge.net - - mailing list. - -Installation -~~~~~~~~~~~~ - - These instructions are a step by step guide to building a machine for - use with NFS/RDMA. - - - Install an RDMA device - - Any device supported by the drivers in drivers/infiniband/hw is acceptable. - - Testing has been performed using several Mellanox-based IB cards, the - Ammasso AMS1100 iWARP adapter, and the Chelsio cxgb3 iWARP adapter. - - - Install a Linux distribution and tools - - The first kernel release to contain both the NFS/RDMA client and server was - Linux 2.6.25 Therefore, a distribution compatible with this and subsequent - Linux kernel release should be installed. - - The procedures described in this document have been tested with - distributions from Red Hat's Fedora Project (http://fedora.redhat.com/). - - - Install nfs-utils-1.1.2 or greater on the client - - An NFS/RDMA mount point can be obtained by using the mount.nfs command in - nfs-utils-1.1.2 or greater (nfs-utils-1.1.1 was the first nfs-utils - version with support for NFS/RDMA mounts, but for various reasons we - recommend using nfs-utils-1.1.2 or greater). To see which version of - mount.nfs you are using, type: - - $ /sbin/mount.nfs -V - - If the version is less than 1.1.2 or the command does not exist, - you should install the latest version of nfs-utils. - - Download the latest package from: - - http://www.kernel.org/pub/linux/utils/nfs - - Uncompress the package and follow the installation instructions. - - If you will not need the idmapper and gssd executables (you do not need - these to create an NFS/RDMA enabled mount command), the installation - process can be simplified by disabling these features when running - configure: - - $ ./configure --disable-gss --disable-nfsv4 - - To build nfs-utils you will need the tcp_wrappers package installed. For - more information on this see the package's README and INSTALL files. - - After building the nfs-utils package, there will be a mount.nfs binary in - the utils/mount directory. This binary can be used to initiate NFS v2, v3, - or v4 mounts. To initiate a v4 mount, the binary must be called - mount.nfs4. The standard technique is to create a symlink called - mount.nfs4 to mount.nfs. - - This mount.nfs binary should be installed at /sbin/mount.nfs as follows: - - $ sudo cp utils/mount/mount.nfs /sbin/mount.nfs - - In this location, mount.nfs will be invoked automatically for NFS mounts - by the system mount command. - - NOTE: mount.nfs and therefore nfs-utils-1.1.2 or greater is only needed - on the NFS client machine. You do not need this specific version of - nfs-utils on the server. Furthermore, only the mount.nfs command from - nfs-utils-1.1.2 is needed on the client. - - - Install a Linux kernel with NFS/RDMA - - The NFS/RDMA client and server are both included in the mainline Linux - kernel version 2.6.25 and later. This and other versions of the 2.6 Linux - kernel can be found at: - - ftp://ftp.kernel.org/pub/linux/kernel/v2.6/ - - Download the sources and place them in an appropriate location. - - - Configure the RDMA stack - - Make sure your kernel configuration has RDMA support enabled. Under - Device Drivers -> InfiniBand support, update the kernel configuration - to enable InfiniBand support [NOTE: the option name is misleading. Enabling - InfiniBand support is required for all RDMA devices (IB, iWARP, etc.)]. - - Enable the appropriate IB HCA support (mlx4, mthca, ehca, ipath, etc.) or - iWARP adapter support (amso, cxgb3, etc.). - - If you are using InfiniBand, be sure to enable IP-over-InfiniBand support. - - - Configure the NFS client and server - - Your kernel configuration must also have NFS file system support and/or - NFS server support enabled. These and other NFS related configuration - options can be found under File Systems -> Network File Systems. - - - Build, install, reboot - - The NFS/RDMA code will be enabled automatically if NFS and RDMA - are turned on. The NFS/RDMA client and server are configured via the hidden - SUNRPC_XPRT_RDMA config option that depends on SUNRPC and INFINIBAND. The - value of SUNRPC_XPRT_RDMA will be: - - - N if either SUNRPC or INFINIBAND are N, in this case the NFS/RDMA client - and server will not be built - - M if both SUNRPC and INFINIBAND are on (M or Y) and at least one is M, - in this case the NFS/RDMA client and server will be built as modules - - Y if both SUNRPC and INFINIBAND are Y, in this case the NFS/RDMA client - and server will be built into the kernel - - Therefore, if you have followed the steps above and turned no NFS and RDMA, - the NFS/RDMA client and server will be built. - - Build a new kernel, install it, boot it. - -Check RDMA and NFS Setup -~~~~~~~~~~~~~~~~~~~~~~~~ - - Before configuring the NFS/RDMA software, it is a good idea to test - your new kernel to ensure that the kernel is working correctly. - In particular, it is a good idea to verify that the RDMA stack - is functioning as expected and standard NFS over TCP/IP and/or UDP/IP - is working properly. - - - Check RDMA Setup - - If you built the RDMA components as modules, load them at - this time. For example, if you are using a Mellanox Tavor/Sinai/Arbel - card: - - $ modprobe ib_mthca - $ modprobe ib_ipoib - - If you are using InfiniBand, make sure there is a Subnet Manager (SM) - running on the network. If your IB switch has an embedded SM, you can - use it. Otherwise, you will need to run an SM, such as OpenSM, on one - of your end nodes. - - If an SM is running on your network, you should see the following: - - $ cat /sys/class/infiniband/driverX/ports/1/state - 4: ACTIVE - - where driverX is mthca0, ipath5, ehca3, etc. - - To further test the InfiniBand software stack, use IPoIB (this - assumes you have two IB hosts named host1 and host2): - - host1$ ifconfig ib0 a.b.c.x - host2$ ifconfig ib0 a.b.c.y - host1$ ping a.b.c.y - host2$ ping a.b.c.x - - For other device types, follow the appropriate procedures. - - - Check NFS Setup - - For the NFS components enabled above (client and/or server), - test their functionality over standard Ethernet using TCP/IP or UDP/IP. - -NFS/RDMA Setup -~~~~~~~~~~~~~~ - - We recommend that you use two machines, one to act as the client and - one to act as the server. - - One time configuration: - - - On the server system, configure the /etc/exports file and - start the NFS/RDMA server. - - Exports entries with the following formats have been tested: - - /vol0 192.168.0.47(fsid=0,rw,async,insecure,no_root_squash) - /vol0 192.168.0.0/255.255.255.0(fsid=0,rw,async,insecure,no_root_squash) - - The IP address(es) is(are) the client's IPoIB address for an InfiniBand - HCA or the cleint's iWARP address(es) for an RNIC. - - NOTE: The "insecure" option must be used because the NFS/RDMA client does - not use a reserved port. - - Each time a machine boots: - - - Load and configure the RDMA drivers - - For InfiniBand using a Mellanox adapter: - - $ modprobe ib_mthca - $ modprobe ib_ipoib - $ ifconfig ib0 a.b.c.d - - NOTE: use unique addresses for the client and server - - - Start the NFS server - - If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in - kernel config), load the RDMA transport module: - - $ modprobe svcrdma - - Regardless of how the server was built (module or built-in), start the - server: - - $ /etc/init.d/nfs start - - or - - $ service nfs start - - Instruct the server to listen on the RDMA transport: - - $ echo rdma 20049 > /proc/fs/nfsd/portlist - - - On the client system - - If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in - kernel config), load the RDMA client module: - - $ modprobe xprtrdma.ko - - Regardless of how the client was built (module or built-in), use this - command to mount the NFS/RDMA server: - - $ mount -o rdma,port=20049 :/ /mnt - - To verify that the mount is using RDMA, run "cat /proc/mounts" and check - the "proto" field for the given mount. - - Congratulations! You're using NFS/RDMA! diff --git a/Documentation/filesystems/nfs.txt b/Documentation/filesystems/nfs.txt deleted file mode 100644 index f50f26ce6cd..00000000000 --- a/Documentation/filesystems/nfs.txt +++ /dev/null @@ -1,98 +0,0 @@ - -The NFS client -============== - -The NFS version 2 protocol was first documented in RFC1094 (March 1989). -Since then two more major releases of NFS have been published, with NFSv3 -being documented in RFC1813 (June 1995), and NFSv4 in RFC3530 (April -2003). - -The Linux NFS client currently supports all the above published versions, -and work is in progress on adding support for minor version 1 of the NFSv4 -protocol. - -The purpose of this document is to provide information on some of the -upcall interfaces that are used in order to provide the NFS client with -some of the information that it requires in order to fully comply with -the NFS spec. - -The DNS resolver -================ - -NFSv4 allows for one server to refer the NFS client to data that has been -migrated onto another server by means of the special "fs_locations" -attribute. See - http://tools.ietf.org/html/rfc3530#section-6 -and - http://tools.ietf.org/html/draft-ietf-nfsv4-referrals-00 - -The fs_locations information can take the form of either an ip address and -a path, or a DNS hostname and a path. The latter requires the NFS client to -do a DNS lookup in order to mount the new volume, and hence the need for an -upcall to allow userland to provide this service. - -Assuming that the user has the 'rpc_pipefs' filesystem mounted in the usual -/var/lib/nfs/rpc_pipefs, the upcall consists of the following steps: - - (1) The process checks the dns_resolve cache to see if it contains a - valid entry. If so, it returns that entry and exits. - - (2) If no valid entry exists, the helper script '/sbin/nfs_cache_getent' - (may be changed using the 'nfs.cache_getent' kernel boot parameter) - is run, with two arguments: - - the cache name, "dns_resolve" - - the hostname to resolve - - (3) After looking up the corresponding ip address, the helper script - writes the result into the rpc_pipefs pseudo-file - '/var/lib/nfs/rpc_pipefs/cache/dns_resolve/channel' - in the following (text) format: - - " \n" - - Where is in the usual IPv4 (123.456.78.90) or IPv6 - (ffee:ddcc:bbaa:9988:7766:5544:3322:1100, ffee::1100, ...) format. - is identical to the second argument of the helper - script, and is the 'time to live' of this cache entry (in - units of seconds). - - Note: If is invalid, say the string "0", then a negative - entry is created, which will cause the kernel to treat the hostname - as having no valid DNS translation. - - - - -A basic sample /sbin/nfs_cache_getent -===================================== - -#!/bin/bash -# -ttl=600 -# -cut=/usr/bin/cut -getent=/usr/bin/getent -rpc_pipefs=/var/lib/nfs/rpc_pipefs -# -die() -{ - echo "Usage: $0 cache_name entry_name" - exit 1 -} - -[ $# -lt 2 ] && die -cachename="$1" -cache_path=${rpc_pipefs}/cache/${cachename}/channel - -case "${cachename}" in - dns_resolve) - name="$2" - result="$(${getent} hosts ${name} | ${cut} -f1 -d\ )" - [ -z "${result}" ] && result="0" - ;; - *) - die - ;; -esac -echo "${result} ${name} ${ttl}" >${cache_path} - diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX new file mode 100644 index 00000000000..6ff3d212027 --- /dev/null +++ b/Documentation/filesystems/nfs/00-INDEX @@ -0,0 +1,12 @@ +00-INDEX + - this file (nfs-related documentation). +Exporting + - explanation of how to make filesystems exportable. +nfs.txt + - nfs client, and DNS resolution for fs_locations. +nfs41-server.txt + - info on the Linux server implementation of NFSv4 minor version 1. +nfs-rdma.txt + - how to install and setup the Linux NFS/RDMA client and server software +nfsroot.txt + - short guide on setting up a diskless box with NFS root filesystem. diff --git a/Documentation/filesystems/nfs/Exporting b/Documentation/filesystems/nfs/Exporting new file mode 100644 index 00000000000..87019d2b598 --- /dev/null +++ b/Documentation/filesystems/nfs/Exporting @@ -0,0 +1,147 @@ + +Making Filesystems Exportable +============================= + +Overview +-------- + +All filesystem operations require a dentry (or two) as a starting +point. Local applications have a reference-counted hold on suitable +dentries via open file descriptors or cwd/root. However remote +applications that access a filesystem via a remote filesystem protocol +such as NFS may not be able to hold such a reference, and so need a +different way to refer to a particular dentry. As the alternative +form of reference needs to be stable across renames, truncates, and +server-reboot (among other things, though these tend to be the most +problematic), there is no simple answer like 'filename'. + +The mechanism discussed here allows each filesystem implementation to +specify how to generate an opaque (outside of the filesystem) byte +string for any dentry, and how to find an appropriate dentry for any +given opaque byte string. +This byte string will be called a "filehandle fragment" as it +corresponds to part of an NFS filehandle. + +A filesystem which supports the mapping between filehandle fragments +and dentries will be termed "exportable". + + + +Dcache Issues +------------- + +The dcache normally contains a proper prefix of any given filesystem +tree. This means that if any filesystem object is in the dcache, then +all of the ancestors of that filesystem object are also in the dcache. +As normal access is by filename this prefix is created naturally and +maintained easily (by each object maintaining a reference count on +its parent). + +However when objects are included into the dcache by interpreting a +filehandle fragment, there is no automatic creation of a path prefix +for the object. This leads to two related but distinct features of +the dcache that are not needed for normal filesystem access. + +1/ The dcache must sometimes contain objects that are not part of the + proper prefix. i.e that are not connected to the root. +2/ The dcache must be prepared for a newly found (via ->lookup) directory + to already have a (non-connected) dentry, and must be able to move + that dentry into place (based on the parent and name in the + ->lookup). This is particularly needed for directories as + it is a dcache invariant that directories only have one dentry. + +To implement these features, the dcache has: + +a/ A dentry flag DCACHE_DISCONNECTED which is set on + any dentry that might not be part of the proper prefix. + This is set when anonymous dentries are created, and cleared when a + dentry is noticed to be a child of a dentry which is in the proper + prefix. + +b/ A per-superblock list "s_anon" of dentries which are the roots of + subtrees that are not in the proper prefix. These dentries, as + well as the proper prefix, need to be released at unmount time. As + these dentries will not be hashed, they are linked together on the + d_hash list_head. + +c/ Helper routines to allocate anonymous dentries, and to help attach + loose directory dentries at lookup time. They are: + d_alloc_anon(inode) will return a dentry for the given inode. + If the inode already has a dentry, one of those is returned. + If it doesn't, a new anonymous (IS_ROOT and + DCACHE_DISCONNECTED) dentry is allocated and attached. + In the case of a directory, care is taken that only one dentry + can ever be attached. + d_splice_alias(inode, dentry) will make sure that there is a + dentry with the same name and parent as the given dentry, and + which refers to the given inode. + If the inode is a directory and already has a dentry, then that + dentry is d_moved over the given dentry. + If the passed dentry gets attached, care is taken that this is + mutually exclusive to a d_alloc_anon operation. + If the passed dentry is used, NULL is returned, else the used + dentry is returned. This corresponds to the calling pattern of + ->lookup. + + +Filesystem Issues +----------------- + +For a filesystem to be exportable it must: + + 1/ provide the filehandle fragment routines described below. + 2/ make sure that d_splice_alias is used rather than d_add + when ->lookup finds an inode for a given parent and name. + Typically the ->lookup routine will end with a: + + return d_splice_alias(inode, dentry); + } + + + + A file system implementation declares that instances of the filesystem +are exportable by setting the s_export_op field in the struct +super_block. This field must point to a "struct export_operations" +struct which has the following members: + + encode_fh (optional) + Takes a dentry and creates a filehandle fragment which can later be used + to find or create a dentry for the same object. The default + implementation creates a filehandle fragment that encodes a 32bit inode + and generation number for the inode encoded, and if necessary the + same information for the parent. + + fh_to_dentry (mandatory) + Given a filehandle fragment, this should find the implied object and + create a dentry for it (possibly with d_alloc_anon). + + fh_to_parent (optional but strongly recommended) + Given a filehandle fragment, this should find the parent of the + implied object and create a dentry for it (possibly with d_alloc_anon). + May fail if the filehandle fragment is too small. + + get_parent (optional but strongly recommended) + When given a dentry for a directory, this should return a dentry for + the parent. Quite possibly the parent dentry will have been allocated + by d_alloc_anon. The default get_parent function just returns an error + so any filehandle lookup that requires finding a parent will fail. + ->lookup("..") is *not* used as a default as it can leave ".." entries + in the dcache which are too messy to work with. + + get_name (optional) + When given a parent dentry and a child dentry, this should find a name + in the directory identified by the parent dentry, which leads to the + object identified by the child dentry. If no get_name function is + supplied, a default implementation is provided which uses vfs_readdir + to find potential names, and matches inode numbers to find the correct + match. + + +A filehandle fragment consists of an array of 1 or more 4byte words, +together with a one byte "type". +The decode_fh routine should not depend on the stated size that is +passed to it. This size may be larger than the original filehandle +generated by encode_fh, in which case it will have been padded with +nuls. Rather, the encode_fh routine should choose a "type" which +indicates the decode_fh how much of the filehandle is valid, and how +it should be interpreted. diff --git a/Documentation/filesystems/nfs/nfs-rdma.txt b/Documentation/filesystems/nfs/nfs-rdma.txt new file mode 100644 index 00000000000..e386f7e4bce --- /dev/null +++ b/Documentation/filesystems/nfs/nfs-rdma.txt @@ -0,0 +1,271 @@ +################################################################################ +# # +# NFS/RDMA README # +# # +################################################################################ + + Author: NetApp and Open Grid Computing + Date: May 29, 2008 + +Table of Contents +~~~~~~~~~~~~~~~~~ + - Overview + - Getting Help + - Installation + - Check RDMA and NFS Setup + - NFS/RDMA Setup + +Overview +~~~~~~~~ + + This document describes how to install and setup the Linux NFS/RDMA client + and server software. + + The NFS/RDMA client was first included in Linux 2.6.24. The NFS/RDMA server + was first included in the following release, Linux 2.6.25. + + In our testing, we have obtained excellent performance results (full 10Gbit + wire bandwidth at minimal client CPU) under many workloads. The code passes + the full Connectathon test suite and operates over both Infiniband and iWARP + RDMA adapters. + +Getting Help +~~~~~~~~~~~~ + + If you get stuck, you can ask questions on the + + nfs-rdma-devel@lists.sourceforge.net + + mailing list. + +Installation +~~~~~~~~~~~~ + + These instructions are a step by step guide to building a machine for + use with NFS/RDMA. + + - Install an RDMA device + + Any device supported by the drivers in drivers/infiniband/hw is acceptable. + + Testing has been performed using several Mellanox-based IB cards, the + Ammasso AMS1100 iWARP adapter, and the Chelsio cxgb3 iWARP adapter. + + - Install a Linux distribution and tools + + The first kernel release to contain both the NFS/RDMA client and server was + Linux 2.6.25 Therefore, a distribution compatible with this and subsequent + Linux kernel release should be installed. + + The procedures described in this document have been tested with + distributions from Red Hat's Fedora Project (http://fedora.redhat.com/). + + - Install nfs-utils-1.1.2 or greater on the client + + An NFS/RDMA mount point can be obtained by using the mount.nfs command in + nfs-utils-1.1.2 or greater (nfs-utils-1.1.1 was the first nfs-utils + version with support for NFS/RDMA mounts, but for various reasons we + recommend using nfs-utils-1.1.2 or greater). To see which version of + mount.nfs you are using, type: + + $ /sbin/mount.nfs -V + + If the version is less than 1.1.2 or the command does not exist, + you should install the latest version of nfs-utils. + + Download the latest package from: + + http://www.kernel.org/pub/linux/utils/nfs + + Uncompress the package and follow the installation instructions. + + If you will not need the idmapper and gssd executables (you do not need + these to create an NFS/RDMA enabled mount command), the installation + process can be simplified by disabling these features when running + configure: + + $ ./configure --disable-gss --disable-nfsv4 + + To build nfs-utils you will need the tcp_wrappers package installed. For + more information on this see the package's README and INSTALL files. + + After building the nfs-utils package, there will be a mount.nfs binary in + the utils/mount directory. This binary can be used to initiate NFS v2, v3, + or v4 mounts. To initiate a v4 mount, the binary must be called + mount.nfs4. The standard technique is to create a symlink called + mount.nfs4 to mount.nfs. + + This mount.nfs binary should be installed at /sbin/mount.nfs as follows: + + $ sudo cp utils/mount/mount.nfs /sbin/mount.nfs + + In this location, mount.nfs will be invoked automatically for NFS mounts + by the system mount command. + + NOTE: mount.nfs and therefore nfs-utils-1.1.2 or greater is only needed + on the NFS client machine. You do not need this specific version of + nfs-utils on the server. Furthermore, only the mount.nfs command from + nfs-utils-1.1.2 is needed on the client. + + - Install a Linux kernel with NFS/RDMA + + The NFS/RDMA client and server are both included in the mainline Linux + kernel version 2.6.25 and later. This and other versions of the 2.6 Linux + kernel can be found at: + + ftp://ftp.kernel.org/pub/linux/kernel/v2.6/ + + Download the sources and place them in an appropriate location. + + - Configure the RDMA stack + + Make sure your kernel configuration has RDMA support enabled. Under + Device Drivers -> InfiniBand support, update the kernel configuration + to enable InfiniBand support [NOTE: the option name is misleading. Enabling + InfiniBand support is required for all RDMA devices (IB, iWARP, etc.)]. + + Enable the appropriate IB HCA support (mlx4, mthca, ehca, ipath, etc.) or + iWARP adapter support (amso, cxgb3, etc.). + + If you are using InfiniBand, be sure to enable IP-over-InfiniBand support. + + - Configure the NFS client and server + + Your kernel configuration must also have NFS file system support and/or + NFS server support enabled. These and other NFS related configuration + options can be found under File Systems -> Network File Systems. + + - Build, install, reboot + + The NFS/RDMA code will be enabled automatically if NFS and RDMA + are turned on. The NFS/RDMA client and server are configured via the hidden + SUNRPC_XPRT_RDMA config option that depends on SUNRPC and INFINIBAND. The + value of SUNRPC_XPRT_RDMA will be: + + - N if either SUNRPC or INFINIBAND are N, in this case the NFS/RDMA client + and server will not be built + - M if both SUNRPC and INFINIBAND are on (M or Y) and at least one is M, + in this case the NFS/RDMA client and server will be built as modules + - Y if both SUNRPC and INFINIBAND are Y, in this case the NFS/RDMA client + and server will be built into the kernel + + Therefore, if you have followed the steps above and turned no NFS and RDMA, + the NFS/RDMA client and server will be built. + + Build a new kernel, install it, boot it. + +Check RDMA and NFS Setup +~~~~~~~~~~~~~~~~~~~~~~~~ + + Before configuring the NFS/RDMA software, it is a good idea to test + your new kernel to ensure that the kernel is working correctly. + In particular, it is a good idea to verify that the RDMA stack + is functioning as expected and standard NFS over TCP/IP and/or UDP/IP + is working properly. + + - Check RDMA Setup + + If you built the RDMA components as modules, load them at + this time. For example, if you are using a Mellanox Tavor/Sinai/Arbel + card: + + $ modprobe ib_mthca + $ modprobe ib_ipoib + + If you are using InfiniBand, make sure there is a Subnet Manager (SM) + running on the network. If your IB switch has an embedded SM, you can + use it. Otherwise, you will need to run an SM, such as OpenSM, on one + of your end nodes. + + If an SM is running on your network, you should see the following: + + $ cat /sys/class/infiniband/driverX/ports/1/state + 4: ACTIVE + + where driverX is mthca0, ipath5, ehca3, etc. + + To further test the InfiniBand software stack, use IPoIB (this + assumes you have two IB hosts named host1 and host2): + + host1$ ifconfig ib0 a.b.c.x + host2$ ifconfig ib0 a.b.c.y + host1$ ping a.b.c.y + host2$ ping a.b.c.x + + For other device types, follow the appropriate procedures. + + - Check NFS Setup + + For the NFS components enabled above (client and/or server), + test their functionality over standard Ethernet using TCP/IP or UDP/IP. + +NFS/RDMA Setup +~~~~~~~~~~~~~~ + + We recommend that you use two machines, one to act as the client and + one to act as the server. + + One time configuration: + + - On the server system, configure the /etc/exports file and + start the NFS/RDMA server. + + Exports entries with the following formats have been tested: + + /vol0 192.168.0.47(fsid=0,rw,async,insecure,no_root_squash) + /vol0 192.168.0.0/255.255.255.0(fsid=0,rw,async,insecure,no_root_squash) + + The IP address(es) is(are) the client's IPoIB address for an InfiniBand + HCA or the cleint's iWARP address(es) for an RNIC. + + NOTE: The "insecure" option must be used because the NFS/RDMA client does + not use a reserved port. + + Each time a machine boots: + + - Load and configure the RDMA drivers + + For InfiniBand using a Mellanox adapter: + + $ modprobe ib_mthca + $ modprobe ib_ipoib + $ ifconfig ib0 a.b.c.d + + NOTE: use unique addresses for the client and server + + - Start the NFS server + + If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in + kernel config), load the RDMA transport module: + + $ modprobe svcrdma + + Regardless of how the server was built (module or built-in), start the + server: + + $ /etc/init.d/nfs start + + or + + $ service nfs start + + Instruct the server to listen on the RDMA transport: + + $ echo rdma 20049 > /proc/fs/nfsd/portlist + + - On the client system + + If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in + kernel config), load the RDMA client module: + + $ modprobe xprtrdma.ko + + Regardless of how the client was built (module or built-in), use this + command to mount the NFS/RDMA server: + + $ mount -o rdma,port=20049 :/ /mnt + + To verify that the mount is using RDMA, run "cat /proc/mounts" and check + the "proto" field for the given mount. + + Congratulations! You're using NFS/RDMA! diff --git a/Documentation/filesystems/nfs/nfs.txt b/Documentation/filesystems/nfs/nfs.txt new file mode 100644 index 00000000000..f50f26ce6cd --- /dev/null +++ b/Documentation/filesystems/nfs/nfs.txt @@ -0,0 +1,98 @@ + +The NFS client +============== + +The NFS version 2 protocol was first documented in RFC1094 (March 1989). +Since then two more major releases of NFS have been published, with NFSv3 +being documented in RFC1813 (June 1995), and NFSv4 in RFC3530 (April +2003). + +The Linux NFS client currently supports all the above published versions, +and work is in progress on adding support for minor version 1 of the NFSv4 +protocol. + +The purpose of this document is to provide information on some of the +upcall interfaces that are used in order to provide the NFS client with +some of the information that it requires in order to fully comply with +the NFS spec. + +The DNS resolver +================ + +NFSv4 allows for one server to refer the NFS client to data that has been +migrated onto another server by means of the special "fs_locations" +attribute. See + http://tools.ietf.org/html/rfc3530#section-6 +and + http://tools.ietf.org/html/draft-ietf-nfsv4-referrals-00 + +The fs_locations information can take the form of either an ip address and +a path, or a DNS hostname and a path. The latter requires the NFS client to +do a DNS lookup in order to mount the new volume, and hence the need for an +upcall to allow userland to provide this service. + +Assuming that the user has the 'rpc_pipefs' filesystem mounted in the usual +/var/lib/nfs/rpc_pipefs, the upcall consists of the following steps: + + (1) The process checks the dns_resolve cache to see if it contains a + valid entry. If so, it returns that entry and exits. + + (2) If no valid entry exists, the helper script '/sbin/nfs_cache_getent' + (may be changed using the 'nfs.cache_getent' kernel boot parameter) + is run, with two arguments: + - the cache name, "dns_resolve" + - the hostname to resolve + + (3) After looking up the corresponding ip address, the helper script + writes the result into the rpc_pipefs pseudo-file + '/var/lib/nfs/rpc_pipefs/cache/dns_resolve/channel' + in the following (text) format: + + " \n" + + Where is in the usual IPv4 (123.456.78.90) or IPv6 + (ffee:ddcc:bbaa:9988:7766:5544:3322:1100, ffee::1100, ...) format. + is identical to the second argument of the helper + script, and is the 'time to live' of this cache entry (in + units of seconds). + + Note: If is invalid, say the string "0", then a negative + entry is created, which will cause the kernel to treat the hostname + as having no valid DNS translation. + + + + +A basic sample /sbin/nfs_cache_getent +===================================== + +#!/bin/bash +# +ttl=600 +# +cut=/usr/bin/cut +getent=/usr/bin/getent +rpc_pipefs=/var/lib/nfs/rpc_pipefs +# +die() +{ + echo "Usage: $0 cache_name entry_name" + exit 1 +} + +[ $# -lt 2 ] && die +cachename="$1" +cache_path=${rpc_pipefs}/cache/${cachename}/channel + +case "${cachename}" in + dns_resolve) + name="$2" + result="$(${getent} hosts ${name} | ${cut} -f1 -d\ )" + [ -z "${result}" ] && result="0" + ;; + *) + die + ;; +esac +echo "${result} ${name} ${ttl}" >${cache_path} + diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt new file mode 100644 index 00000000000..1bd0d0c0517 --- /dev/null +++ b/Documentation/filesystems/nfs/nfs41-server.txt @@ -0,0 +1,222 @@ +NFSv4.1 Server Implementation + +Server support for minorversion 1 can be controlled using the +/proc/fs/nfsd/versions control file. The string output returned +by reading this file will contain either "+4.1" or "-4.1" +correspondingly. + +Currently, server support for minorversion 1 is disabled by default. +It can be enabled at run time by writing the string "+4.1" to +the /proc/fs/nfsd/versions control file. Note that to write this +control file, the nfsd service must be taken down. Use your user-mode +nfs-utils to set this up; see rpc.nfsd(8) + +(Warning: older servers will interpret "+4.1" and "-4.1" as "+4" and +"-4", respectively. Therefore, code meant to work on both new and old +kernels must turn 4.1 on or off *before* turning support for version 4 +on or off; rpc.nfsd does this correctly.) + +The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based +on the latest NFSv4.1 Internet Draft: +http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29 + +From the many new features in NFSv4.1 the current implementation +focuses on the mandatory-to-implement NFSv4.1 Sessions, providing +"exactly once" semantics and better control and throttling of the +resources allocated for each client. + +Other NFSv4.1 features, Parallel NFS operations in particular, +are still under development out of tree. +See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design +for more information. + +The current implementation is intended for developers only: while it +does support ordinary file operations on clients we have tested against +(including the linux client), it is incomplete in ways which may limit +features unexpectedly, cause known bugs in rare cases, or cause +interoperability problems with future clients. Known issues: + + - gss support is questionable: currently mounts with kerberos + from a linux client are possible, but we aren't really + conformant with the spec (for example, we don't use kerberos + on the backchannel correctly). + - no trunking support: no clients currently take advantage of + trunking, but this is a mandatory feature, and its use is + recommended to clients in a number of places. (E.g. to ensure + timely renewal in case an existing connection's retry timeouts + have gotten too long; see section 8.3 of the draft.) + Therefore, lack of this feature may cause future clients to + fail. + - Incomplete backchannel support: incomplete backchannel gss + support and no support for BACKCHANNEL_CTL mean that + callbacks (hence delegations and layouts) may not be + available and clients confused by the incomplete + implementation may fail. + - Server reboot recovery is unsupported; if the server reboots, + clients may fail. + - We do not support SSV, which provides security for shared + client-server state (thus preventing unauthorized tampering + with locks and opens, for example). It is mandatory for + servers to support this, though no clients use it yet. + - Mandatory operations which we do not support, such as + DESTROY_CLIENTID, FREE_STATEID, SECINFO_NO_NAME, and + TEST_STATEID, are not currently used by clients, but will be + (and the spec recommends their uses in common cases), and + clients should not be expected to know how to recover from the + case where they are not supported. This will eventually cause + interoperability failures. + +In addition, some limitations are inherited from the current NFSv4 +implementation: + + - Incomplete delegation enforcement: if a file is renamed or + unlinked, a client holding a delegation may continue to + indefinitely allow opens of the file under the old name. + +The table below, taken from the NFSv4.1 document, lists +the operations that are mandatory to implement (REQ), optional +(OPT), and NFSv4.0 operations that are required not to implement (MNI) +in minor version 1. The first column indicates the operations that +are not supported yet by the linux server implementation. + +The OPTIONAL features identified and their abbreviations are as follows: + pNFS Parallel NFS + FDELG File Delegations + DDELG Directory Delegations + +The following abbreviations indicate the linux server implementation status. + I Implemented NFSv4.1 operations. + NS Not Supported. + NS* unimplemented optional feature. + P pNFS features implemented out of tree. + PNS pNFS features that are not supported yet (out of tree). + +Operations + + +----------------------+------------+--------------+----------------+ + | Operation | REQ, REC, | Feature | Definition | + | | OPT, or | (REQ, REC, | | + | | MNI | or OPT) | | + +----------------------+------------+--------------+----------------+ + | ACCESS | REQ | | Section 18.1 | +NS | BACKCHANNEL_CTL | REQ | | Section 18.33 | +NS | BIND_CONN_TO_SESSION | REQ | | Section 18.34 | + | CLOSE | REQ | | Section 18.2 | + | COMMIT | REQ | | Section 18.3 | + | CREATE | REQ | | Section 18.4 | +I | CREATE_SESSION | REQ | | Section 18.36 | +NS*| DELEGPURGE | OPT | FDELG (REQ) | Section 18.5 | + | DELEGRETURN | OPT | FDELG, | Section 18.6 | + | | | DDELG, pNFS | | + | | | (REQ) | | +NS | DESTROY_CLIENTID | REQ | | Section 18.50 | +I | DESTROY_SESSION | REQ | | Section 18.37 | +I | EXCHANGE_ID | REQ | | Section 18.35 | +NS | FREE_STATEID | REQ | | Section 18.38 | + | GETATTR | REQ | | Section 18.7 | +P | GETDEVICEINFO | OPT | pNFS (REQ) | Section 18.40 | +P | GETDEVICELIST | OPT | pNFS (OPT) | Section 18.41 | + | GETFH | REQ | | Section 18.8 | +NS*| GET_DIR_DELEGATION | OPT | DDELG (REQ) | Section 18.39 | +P | LAYOUTCOMMIT | OPT | pNFS (REQ) | Section 18.42 | +P | LAYOUTGET | OPT | pNFS (REQ) | Section 18.43 | +P | LAYOUTRETURN | OPT | pNFS (REQ) | Section 18.44 | + | LINK | OPT | | Section 18.9 | + | LOCK | REQ | | Section 18.10 | + | LOCKT | REQ | | Section 18.11 | + | LOCKU | REQ | | Section 18.12 | + | LOOKUP | REQ | | Section 18.13 | + | LOOKUPP | REQ | | Section 18.14 | + | NVERIFY | REQ | | Section 18.15 | + | OPEN | REQ | | Section 18.16 | +NS*| OPENATTR | OPT | | Section 18.17 | + | OPEN_CONFIRM | MNI | | N/A | + | OPEN_DOWNGRADE | REQ | | Section 18.18 | + | PUTFH | REQ | | Section 18.19 | + | PUTPUBFH | REQ | | Section 18.20 | + | PUTROOTFH | REQ | | Section 18.21 | + | READ | REQ | | Section 18.22 | + | READDIR | REQ | | Section 18.23 | + | READLINK | OPT | | Section 18.24 | +NS | RECLAIM_COMPLETE | REQ | | Section 18.51 | + | RELEASE_LOCKOWNER | MNI | | N/A | + | REMOVE | REQ | | Section 18.25 | + | RENAME | REQ | | Section 18.26 | + | RENEW | MNI | | N/A | + | RESTOREFH | REQ | | Section 18.27 | + | SAVEFH | REQ | | Section 18.28 | + | SECINFO | REQ | | Section 18.29 | +NS | SECINFO_NO_NAME | REC | pNFS files | Section 18.45, | + | | | layout (REQ) | Section 13.12 | +I | SEQUENCE | REQ | | Section 18.46 | + | SETATTR | REQ | | Section 18.30 | + | SETCLIENTID | MNI | | N/A | + | SETCLIENTID_CONFIRM | MNI | | N/A | +NS | SET_SSV | REQ | | Section 18.47 | +NS | TEST_STATEID | REQ | | Section 18.48 | + | VERIFY | REQ | | Section 18.31 | +NS*| WANT_DELEGATION | OPT | FDELG (OPT) | Section 18.49 | + | WRITE | REQ | | Section 18.32 | + +Callback Operations + + +-------------------------+-----------+-------------+---------------+ + | Operation | REQ, REC, | Feature | Definition | + | | OPT, or | (REQ, REC, | | + | | MNI | or OPT) | | + +-------------------------+-----------+-------------+---------------+ + | CB_GETATTR | OPT | FDELG (REQ) | Section 20.1 | +P | CB_LAYOUTRECALL | OPT | pNFS (REQ) | Section 20.3 | +NS*| CB_NOTIFY | OPT | DDELG (REQ) | Section 20.4 | +P | CB_NOTIFY_DEVICEID | OPT | pNFS (OPT) | Section 20.12 | +NS*| CB_NOTIFY_LOCK | OPT | | Section 20.11 | +NS*| CB_PUSH_DELEG | OPT | FDELG (OPT) | Section 20.5 | + | CB_RECALL | OPT | FDELG, | Section 20.2 | + | | | DDELG, pNFS | | + | | | (REQ) | | +NS*| CB_RECALL_ANY | OPT | FDELG, | Section 20.6 | + | | | DDELG, pNFS | | + | | | (REQ) | | +NS | CB_RECALL_SLOT | REQ | | Section 20.8 | +NS*| CB_RECALLABLE_OBJ_AVAIL | OPT | DDELG, pNFS | Section 20.7 | + | | | (REQ) | | +I | CB_SEQUENCE | OPT | FDELG, | Section 20.9 | + | | | DDELG, pNFS | | + | | | (REQ) | | +NS*| CB_WANTS_CANCELLED | OPT | FDELG, | Section 20.10 | + | | | DDELG, pNFS | | + | | | (REQ) | | + +-------------------------+-----------+-------------+---------------+ + +Implementation notes: + +DELEGPURGE: +* mandatory only for servers that support CLAIM_DELEGATE_PREV and/or + CLAIM_DELEG_PREV_FH (which allows clients to keep delegations that + persist across client reboots). Thus we need not implement this for + now. + +EXCHANGE_ID: +* only SP4_NONE state protection supported +* implementation ids are ignored + +CREATE_SESSION: +* backchannel attributes are ignored +* backchannel security parameters are ignored + +SEQUENCE: +* no support for dynamic slot table renegotiation (optional) + +nfsv4.1 COMPOUND rules: +The following cases aren't supported yet: +* Enforcing of NFS4ERR_NOT_ONLY_OP for: BIND_CONN_TO_SESSION, CREATE_SESSION, + DESTROY_CLIENTID, DESTROY_SESSION, EXCHANGE_ID. +* DESTROY_SESSION MUST be the final operation in the COMPOUND request. + +Nonstandard compound limitations: +* No support for a sessions fore channel RPC compound that requires both a + ca_maxrequestsize request and a ca_maxresponsesize reply, so we may + fail to live up to the promise we made in CREATE_SESSION fore channel + negotiation. +* No more than one IO operation (read, write, readdir) allowed per + compound. diff --git a/Documentation/filesystems/nfs/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt new file mode 100644 index 00000000000..3ba0b945aaf --- /dev/null +++ b/Documentation/filesystems/nfs/nfsroot.txt @@ -0,0 +1,270 @@ +Mounting the root filesystem via NFS (nfsroot) +=============================================== + +Written 1996 by Gero Kuhlmann +Updated 1997 by Martin Mares +Updated 2006 by Nico Schottelius +Updated 2006 by Horms + + + +In order to use a diskless system, such as an X-terminal or printer server +for example, it is necessary for the root filesystem to be present on a +non-disk device. This may be an initramfs (see Documentation/filesystems/ +ramfs-rootfs-initramfs.txt), a ramdisk (see Documentation/initrd.txt) or a +filesystem mounted via NFS. The following text describes on how to use NFS +for the root filesystem. For the rest of this text 'client' means the +diskless system, and 'server' means the NFS server. + + + + +1.) Enabling nfsroot capabilities + ----------------------------- + +In order to use nfsroot, NFS client support needs to be selected as +built-in during configuration. Once this has been selected, the nfsroot +option will become available, which should also be selected. + +In the networking options, kernel level autoconfiguration can be selected, +along with the types of autoconfiguration to support. Selecting all of +DHCP, BOOTP and RARP is safe. + + + + +2.) Kernel command line + ------------------- + +When the kernel has been loaded by a boot loader (see below) it needs to be +told what root fs device to use. And in the case of nfsroot, where to find +both the server and the name of the directory on the server to mount as root. +This can be established using the following kernel command line parameters: + + +root=/dev/nfs + + This is necessary to enable the pseudo-NFS-device. Note that it's not a + real device but just a synonym to tell the kernel to use NFS instead of + a real device. + + +nfsroot=[:][,] + + If the `nfsroot' parameter is NOT given on the command line, + the default "/tftpboot/%s" will be used. + + Specifies the IP address of the NFS server. + The default address is determined by the `ip' parameter + (see below). This parameter allows the use of different + servers for IP autoconfiguration and NFS. + + Name of the directory on the server to mount as root. + If there is a "%s" token in the string, it will be + replaced by the ASCII-representation of the client's + IP address. + + Standard NFS options. All options are separated by commas. + The following defaults are used: + port = as given by server portmap daemon + rsize = 4096 + wsize = 4096 + timeo = 7 + retrans = 3 + acregmin = 3 + acregmax = 60 + acdirmin = 30 + acdirmax = 60 + flags = hard, nointr, noposix, cto, ac + + +ip=:::::: + + This parameter tells the kernel how to configure IP addresses of devices + and also how to set up the IP routing table. It was originally called + `nfsaddrs', but now the boot-time IP configuration works independently of + NFS, so it was renamed to `ip' and the old name remained as an alias for + compatibility reasons. + + If this parameter is missing from the kernel command line, all fields are + assumed to be empty, and the defaults mentioned below apply. In general + this means that the kernel tries to configure everything using + autoconfiguration. + + The parameter can appear alone as the value to the `ip' + parameter (without all the ':' characters before). If the value is + "ip=off" or "ip=none", no autoconfiguration will take place, otherwise + autoconfiguration will take place. The most common way to use this + is "ip=dhcp". + + IP address of the client. + + Default: Determined using autoconfiguration. + + IP address of the NFS server. If RARP is used to determine + the client address and this parameter is NOT empty only + replies from the specified server are accepted. + + Only required for NFS root. That is autoconfiguration + will not be triggered if it is missing and NFS root is not + in operation. + + Default: Determined using autoconfiguration. + The address of the autoconfiguration server is used. + + IP address of a gateway if the server is on a different subnet. + + Default: Determined using autoconfiguration. + + Netmask for local network interface. If unspecified + the netmask is derived from the client IP address assuming + classful addressing. + + Default: Determined using autoconfiguration. + + Name of the client. May be supplied by autoconfiguration, + but its absence will not trigger autoconfiguration. + + Default: Client IP address is used in ASCII notation. + + Name of network device to use. + + Default: If the host only has one device, it is used. + Otherwise the device is determined using + autoconfiguration. This is done by sending + autoconfiguration requests out of all devices, + and using the device that received the first reply. + + Method to use for autoconfiguration. In the case of options + which specify multiple autoconfiguration protocols, + requests are sent using all protocols, and the first one + to reply is used. + + Only autoconfiguration protocols that have been compiled + into the kernel will be used, regardless of the value of + this option. + + off or none: don't use autoconfiguration + (do static IP assignment instead) + on or any: use any protocol available in the kernel + (default) + dhcp: use DHCP + bootp: use BOOTP + rarp: use RARP + both: use both BOOTP and RARP but not DHCP + (old option kept for backwards compatibility) + + Default: any + + + + +3.) Boot Loader + ---------- + +To get the kernel into memory different approaches can be used. +They depend on various facilities being available: + + +3.1) Booting from a floppy using syslinux + + When building kernels, an easy way to create a boot floppy that uses + syslinux is to use the zdisk or bzdisk make targets which use zimage + and bzimage images respectively. Both targets accept the + FDARGS parameter which can be used to set the kernel command line. + + e.g. + make bzdisk FDARGS="root=/dev/nfs" + + Note that the user running this command will need to have + access to the floppy drive device, /dev/fd0 + + For more information on syslinux, including how to create bootdisks + for prebuilt kernels, see http://syslinux.zytor.com/ + + N.B: Previously it was possible to write a kernel directly to + a floppy using dd, configure the boot device using rdev, and + boot using the resulting floppy. Linux no longer supports this + method of booting. + +3.2) Booting from a cdrom using isolinux + + When building kernels, an easy way to create a bootable cdrom that + uses isolinux is to use the isoimage target which uses a bzimage + image. Like zdisk and bzdisk, this target accepts the FDARGS + parameter which can be used to set the kernel command line. + + e.g. + make isoimage FDARGS="root=/dev/nfs" + + The resulting iso image will be arch//boot/image.iso + This can be written to a cdrom using a variety of tools including + cdrecord. + + e.g. + cdrecord dev=ATAPI:1,0,0 arch/i386/boot/image.iso + + For more information on isolinux, including how to create bootdisks + for prebuilt kernels, see http://syslinux.zytor.com/ + +3.2) Using LILO + When using LILO all the necessary command line parameters may be + specified using the 'append=' directive in the LILO configuration + file. + + However, to use the 'root=' directive you also need to create + a dummy root device, which may be removed after LILO is run. + + mknod /dev/boot255 c 0 255 + + For information on configuring LILO, please refer to its documentation. + +3.3) Using GRUB + When using GRUB, kernel parameter are simply appended after the kernel + specification: kernel + +3.4) Using loadlin + loadlin may be used to boot Linux from a DOS command prompt without + requiring a local hard disk to mount as root. This has not been + thoroughly tested by the authors of this document, but in general + it should be possible configure the kernel command line similarly + to the configuration of LILO. + + Please refer to the loadlin documentation for further information. + +3.5) Using a boot ROM + This is probably the most elegant way of booting a diskless client. + With a boot ROM the kernel is loaded using the TFTP protocol. The + authors of this document are not aware of any no commercial boot + ROMs that support booting Linux over the network. However, there + are two free implementations of a boot ROM, netboot-nfs and + etherboot, both of which are available on sunsite.unc.edu, and both + of which contain everything you need to boot a diskless Linux client. + +3.6) Using pxelinux + Pxelinux may be used to boot linux using the PXE boot loader + which is present on many modern network cards. + + When using pxelinux, the kernel image is specified using + "kernel ". The nfsroot parameters + are passed to the kernel by adding them to the "append" line. + It is common to use serial console in conjunction with pxeliunx, + see Documentation/serial-console.txt for more information. + + For more information on isolinux, including how to create bootdisks + for prebuilt kernels, see http://syslinux.zytor.com/ + + + + +4.) Credits + ------- + + The nfsroot code in the kernel and the RARP support have been written + by Gero Kuhlmann . + + The rest of the IP layer autoconfiguration code has been written + by Martin Mares . + + In order to write the initial version of nfsroot I would like to thank + Jens-Uwe Mager for his help. diff --git a/Documentation/filesystems/nfs41-server.txt b/Documentation/filesystems/nfs41-server.txt deleted file mode 100644 index 1bd0d0c0517..00000000000 --- a/Documentation/filesystems/nfs41-server.txt +++ /dev/null @@ -1,222 +0,0 @@ -NFSv4.1 Server Implementation - -Server support for minorversion 1 can be controlled using the -/proc/fs/nfsd/versions control file. The string output returned -by reading this file will contain either "+4.1" or "-4.1" -correspondingly. - -Currently, server support for minorversion 1 is disabled by default. -It can be enabled at run time by writing the string "+4.1" to -the /proc/fs/nfsd/versions control file. Note that to write this -control file, the nfsd service must be taken down. Use your user-mode -nfs-utils to set this up; see rpc.nfsd(8) - -(Warning: older servers will interpret "+4.1" and "-4.1" as "+4" and -"-4", respectively. Therefore, code meant to work on both new and old -kernels must turn 4.1 on or off *before* turning support for version 4 -on or off; rpc.nfsd does this correctly.) - -The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based -on the latest NFSv4.1 Internet Draft: -http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29 - -From the many new features in NFSv4.1 the current implementation -focuses on the mandatory-to-implement NFSv4.1 Sessions, providing -"exactly once" semantics and better control and throttling of the -resources allocated for each client. - -Other NFSv4.1 features, Parallel NFS operations in particular, -are still under development out of tree. -See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design -for more information. - -The current implementation is intended for developers only: while it -does support ordinary file operations on clients we have tested against -(including the linux client), it is incomplete in ways which may limit -features unexpectedly, cause known bugs in rare cases, or cause -interoperability problems with future clients. Known issues: - - - gss support is questionable: currently mounts with kerberos - from a linux client are possible, but we aren't really - conformant with the spec (for example, we don't use kerberos - on the backchannel correctly). - - no trunking support: no clients currently take advantage of - trunking, but this is a mandatory feature, and its use is - recommended to clients in a number of places. (E.g. to ensure - timely renewal in case an existing connection's retry timeouts - have gotten too long; see section 8.3 of the draft.) - Therefore, lack of this feature may cause future clients to - fail. - - Incomplete backchannel support: incomplete backchannel gss - support and no support for BACKCHANNEL_CTL mean that - callbacks (hence delegations and layouts) may not be - available and clients confused by the incomplete - implementation may fail. - - Server reboot recovery is unsupported; if the server reboots, - clients may fail. - - We do not support SSV, which provides security for shared - client-server state (thus preventing unauthorized tampering - with locks and opens, for example). It is mandatory for - servers to support this, though no clients use it yet. - - Mandatory operations which we do not support, such as - DESTROY_CLIENTID, FREE_STATEID, SECINFO_NO_NAME, and - TEST_STATEID, are not currently used by clients, but will be - (and the spec recommends their uses in common cases), and - clients should not be expected to know how to recover from the - case where they are not supported. This will eventually cause - interoperability failures. - -In addition, some limitations are inherited from the current NFSv4 -implementation: - - - Incomplete delegation enforcement: if a file is renamed or - unlinked, a client holding a delegation may continue to - indefinitely allow opens of the file under the old name. - -The table below, taken from the NFSv4.1 document, lists -the operations that are mandatory to implement (REQ), optional -(OPT), and NFSv4.0 operations that are required not to implement (MNI) -in minor version 1. The first column indicates the operations that -are not supported yet by the linux server implementation. - -The OPTIONAL features identified and their abbreviations are as follows: - pNFS Parallel NFS - FDELG File Delegations - DDELG Directory Delegations - -The following abbreviations indicate the linux server implementation status. - I Implemented NFSv4.1 operations. - NS Not Supported. - NS* unimplemented optional feature. - P pNFS features implemented out of tree. - PNS pNFS features that are not supported yet (out of tree). - -Operations - - +----------------------+------------+--------------+----------------+ - | Operation | REQ, REC, | Feature | Definition | - | | OPT, or | (REQ, REC, | | - | | MNI | or OPT) | | - +----------------------+------------+--------------+----------------+ - | ACCESS | REQ | | Section 18.1 | -NS | BACKCHANNEL_CTL | REQ | | Section 18.33 | -NS | BIND_CONN_TO_SESSION | REQ | | Section 18.34 | - | CLOSE | REQ | | Section 18.2 | - | COMMIT | REQ | | Section 18.3 | - | CREATE | REQ | | Section 18.4 | -I | CREATE_SESSION | REQ | | Section 18.36 | -NS*| DELEGPURGE | OPT | FDELG (REQ) | Section 18.5 | - | DELEGRETURN | OPT | FDELG, | Section 18.6 | - | | | DDELG, pNFS | | - | | | (REQ) | | -NS | DESTROY_CLIENTID | REQ | | Section 18.50 | -I | DESTROY_SESSION | REQ | | Section 18.37 | -I | EXCHANGE_ID | REQ | | Section 18.35 | -NS | FREE_STATEID | REQ | | Section 18.38 | - | GETATTR | REQ | | Section 18.7 | -P | GETDEVICEINFO | OPT | pNFS (REQ) | Section 18.40 | -P | GETDEVICELIST | OPT | pNFS (OPT) | Section 18.41 | - | GETFH | REQ | | Section 18.8 | -NS*| GET_DIR_DELEGATION | OPT | DDELG (REQ) | Section 18.39 | -P | LAYOUTCOMMIT | OPT | pNFS (REQ) | Section 18.42 | -P | LAYOUTGET | OPT | pNFS (REQ) | Section 18.43 | -P | LAYOUTRETURN | OPT | pNFS (REQ) | Section 18.44 | - | LINK | OPT | | Section 18.9 | - | LOCK | REQ | | Section 18.10 | - | LOCKT | REQ | | Section 18.11 | - | LOCKU | REQ | | Section 18.12 | - | LOOKUP | REQ | | Section 18.13 | - | LOOKUPP | REQ | | Section 18.14 | - | NVERIFY | REQ | | Section 18.15 | - | OPEN | REQ | | Section 18.16 | -NS*| OPENATTR | OPT | | Section 18.17 | - | OPEN_CONFIRM | MNI | | N/A | - | OPEN_DOWNGRADE | REQ | | Section 18.18 | - | PUTFH | REQ | | Section 18.19 | - | PUTPUBFH | REQ | | Section 18.20 | - | PUTROOTFH | REQ | | Section 18.21 | - | READ | REQ | | Section 18.22 | - | READDIR | REQ | | Section 18.23 | - | READLINK | OPT | | Section 18.24 | -NS | RECLAIM_COMPLETE | REQ | | Section 18.51 | - | RELEASE_LOCKOWNER | MNI | | N/A | - | REMOVE | REQ | | Section 18.25 | - | RENAME | REQ | | Section 18.26 | - | RENEW | MNI | | N/A | - | RESTOREFH | REQ | | Section 18.27 | - | SAVEFH | REQ | | Section 18.28 | - | SECINFO | REQ | | Section 18.29 | -NS | SECINFO_NO_NAME | REC | pNFS files | Section 18.45, | - | | | layout (REQ) | Section 13.12 | -I | SEQUENCE | REQ | | Section 18.46 | - | SETATTR | REQ | | Section 18.30 | - | SETCLIENTID | MNI | | N/A | - | SETCLIENTID_CONFIRM | MNI | | N/A | -NS | SET_SSV | REQ | | Section 18.47 | -NS | TEST_STATEID | REQ | | Section 18.48 | - | VERIFY | REQ | | Section 18.31 | -NS*| WANT_DELEGATION | OPT | FDELG (OPT) | Section 18.49 | - | WRITE | REQ | | Section 18.32 | - -Callback Operations - - +-------------------------+-----------+-------------+---------------+ - | Operation | REQ, REC, | Feature | Definition | - | | OPT, or | (REQ, REC, | | - | | MNI | or OPT) | | - +-------------------------+-----------+-------------+---------------+ - | CB_GETATTR | OPT | FDELG (REQ) | Section 20.1 | -P | CB_LAYOUTRECALL | OPT | pNFS (REQ) | Section 20.3 | -NS*| CB_NOTIFY | OPT | DDELG (REQ) | Section 20.4 | -P | CB_NOTIFY_DEVICEID | OPT | pNFS (OPT) | Section 20.12 | -NS*| CB_NOTIFY_LOCK | OPT | | Section 20.11 | -NS*| CB_PUSH_DELEG | OPT | FDELG (OPT) | Section 20.5 | - | CB_RECALL | OPT | FDELG, | Section 20.2 | - | | | DDELG, pNFS | | - | | | (REQ) | | -NS*| CB_RECALL_ANY | OPT | FDELG, | Section 20.6 | - | | | DDELG, pNFS | | - | | | (REQ) | | -NS | CB_RECALL_SLOT | REQ | | Section 20.8 | -NS*| CB_RECALLABLE_OBJ_AVAIL | OPT | DDELG, pNFS | Section 20.7 | - | | | (REQ) | | -I | CB_SEQUENCE | OPT | FDELG, | Section 20.9 | - | | | DDELG, pNFS | | - | | | (REQ) | | -NS*| CB_WANTS_CANCELLED | OPT | FDELG, | Section 20.10 | - | | | DDELG, pNFS | | - | | | (REQ) | | - +-------------------------+-----------+-------------+---------------+ - -Implementation notes: - -DELEGPURGE: -* mandatory only for servers that support CLAIM_DELEGATE_PREV and/or - CLAIM_DELEG_PREV_FH (which allows clients to keep delegations that - persist across client reboots). Thus we need not implement this for - now. - -EXCHANGE_ID: -* only SP4_NONE state protection supported -* implementation ids are ignored - -CREATE_SESSION: -* backchannel attributes are ignored -* backchannel security parameters are ignored - -SEQUENCE: -* no support for dynamic slot table renegotiation (optional) - -nfsv4.1 COMPOUND rules: -The following cases aren't supported yet: -* Enforcing of NFS4ERR_NOT_ONLY_OP for: BIND_CONN_TO_SESSION, CREATE_SESSION, - DESTROY_CLIENTID, DESTROY_SESSION, EXCHANGE_ID. -* DESTROY_SESSION MUST be the final operation in the COMPOUND request. - -Nonstandard compound limitations: -* No support for a sessions fore channel RPC compound that requires both a - ca_maxrequestsize request and a ca_maxresponsesize reply, so we may - fail to live up to the promise we made in CREATE_SESSION fore channel - negotiation. -* No more than one IO operation (read, write, readdir) allowed per - compound. diff --git a/Documentation/filesystems/nfsroot.txt b/Documentation/filesystems/nfsroot.txt deleted file mode 100644 index 3ba0b945aaf..00000000000 --- a/Documentation/filesystems/nfsroot.txt +++ /dev/null @@ -1,270 +0,0 @@ -Mounting the root filesystem via NFS (nfsroot) -=============================================== - -Written 1996 by Gero Kuhlmann -Updated 1997 by Martin Mares -Updated 2006 by Nico Schottelius -Updated 2006 by Horms - - - -In order to use a diskless system, such as an X-terminal or printer server -for example, it is necessary for the root filesystem to be present on a -non-disk device. This may be an initramfs (see Documentation/filesystems/ -ramfs-rootfs-initramfs.txt), a ramdisk (see Documentation/initrd.txt) or a -filesystem mounted via NFS. The following text describes on how to use NFS -for the root filesystem. For the rest of this text 'client' means the -diskless system, and 'server' means the NFS server. - - - - -1.) Enabling nfsroot capabilities - ----------------------------- - -In order to use nfsroot, NFS client support needs to be selected as -built-in during configuration. Once this has been selected, the nfsroot -option will become available, which should also be selected. - -In the networking options, kernel level autoconfiguration can be selected, -along with the types of autoconfiguration to support. Selecting all of -DHCP, BOOTP and RARP is safe. - - - - -2.) Kernel command line - ------------------- - -When the kernel has been loaded by a boot loader (see below) it needs to be -told what root fs device to use. And in the case of nfsroot, where to find -both the server and the name of the directory on the server to mount as root. -This can be established using the following kernel command line parameters: - - -root=/dev/nfs - - This is necessary to enable the pseudo-NFS-device. Note that it's not a - real device but just a synonym to tell the kernel to use NFS instead of - a real device. - - -nfsroot=[:][,] - - If the `nfsroot' parameter is NOT given on the command line, - the default "/tftpboot/%s" will be used. - - Specifies the IP address of the NFS server. - The default address is determined by the `ip' parameter - (see below). This parameter allows the use of different - servers for IP autoconfiguration and NFS. - - Name of the directory on the server to mount as root. - If there is a "%s" token in the string, it will be - replaced by the ASCII-representation of the client's - IP address. - - Standard NFS options. All options are separated by commas. - The following defaults are used: - port = as given by server portmap daemon - rsize = 4096 - wsize = 4096 - timeo = 7 - retrans = 3 - acregmin = 3 - acregmax = 60 - acdirmin = 30 - acdirmax = 60 - flags = hard, nointr, noposix, cto, ac - - -ip=:::::: - - This parameter tells the kernel how to configure IP addresses of devices - and also how to set up the IP routing table. It was originally called - `nfsaddrs', but now the boot-time IP configuration works independently of - NFS, so it was renamed to `ip' and the old name remained as an alias for - compatibility reasons. - - If this parameter is missing from the kernel command line, all fields are - assumed to be empty, and the defaults mentioned below apply. In general - this means that the kernel tries to configure everything using - autoconfiguration. - - The parameter can appear alone as the value to the `ip' - parameter (without all the ':' characters before). If the value is - "ip=off" or "ip=none", no autoconfiguration will take place, otherwise - autoconfiguration will take place. The most common way to use this - is "ip=dhcp". - - IP address of the client. - - Default: Determined using autoconfiguration. - - IP address of the NFS server. If RARP is used to determine - the client address and this parameter is NOT empty only - replies from the specified server are accepted. - - Only required for NFS root. That is autoconfiguration - will not be triggered if it is missing and NFS root is not - in operation. - - Default: Determined using autoconfiguration. - The address of the autoconfiguration server is used. - - IP address of a gateway if the server is on a different subnet. - - Default: Determined using autoconfiguration. - - Netmask for local network interface. If unspecified - the netmask is derived from the client IP address assuming - classful addressing. - - Default: Determined using autoconfiguration. - - Name of the client. May be supplied by autoconfiguration, - but its absence will not trigger autoconfiguration. - - Default: Client IP address is used in ASCII notation. - - Name of network device to use. - - Default: If the host only has one device, it is used. - Otherwise the device is determined using - autoconfiguration. This is done by sending - autoconfiguration requests out of all devices, - and using the device that received the first reply. - - Method to use for autoconfiguration. In the case of options - which specify multiple autoconfiguration protocols, - requests are sent using all protocols, and the first one - to reply is used. - - Only autoconfiguration protocols that have been compiled - into the kernel will be used, regardless of the value of - this option. - - off or none: don't use autoconfiguration - (do static IP assignment instead) - on or any: use any protocol available in the kernel - (default) - dhcp: use DHCP - bootp: use BOOTP - rarp: use RARP - both: use both BOOTP and RARP but not DHCP - (old option kept for backwards compatibility) - - Default: any - - - - -3.) Boot Loader - ---------- - -To get the kernel into memory different approaches can be used. -They depend on various facilities being available: - - -3.1) Booting from a floppy using syslinux - - When building kernels, an easy way to create a boot floppy that uses - syslinux is to use the zdisk or bzdisk make targets which use zimage - and bzimage images respectively. Both targets accept the - FDARGS parameter which can be used to set the kernel command line. - - e.g. - make bzdisk FDARGS="root=/dev/nfs" - - Note that the user running this command will need to have - access to the floppy drive device, /dev/fd0 - - For more information on syslinux, including how to create bootdisks - for prebuilt kernels, see http://syslinux.zytor.com/ - - N.B: Previously it was possible to write a kernel directly to - a floppy using dd, configure the boot device using rdev, and - boot using the resulting floppy. Linux no longer supports this - method of booting. - -3.2) Booting from a cdrom using isolinux - - When building kernels, an easy way to create a bootable cdrom that - uses isolinux is to use the isoimage target which uses a bzimage - image. Like zdisk and bzdisk, this target accepts the FDARGS - parameter which can be used to set the kernel command line. - - e.g. - make isoimage FDARGS="root=/dev/nfs" - - The resulting iso image will be arch//boot/image.iso - This can be written to a cdrom using a variety of tools including - cdrecord. - - e.g. - cdrecord dev=ATAPI:1,0,0 arch/i386/boot/image.iso - - For more information on isolinux, including how to create bootdisks - for prebuilt kernels, see http://syslinux.zytor.com/ - -3.2) Using LILO - When using LILO all the necessary command line parameters may be - specified using the 'append=' directive in the LILO configuration - file. - - However, to use the 'root=' directive you also need to create - a dummy root device, which may be removed after LILO is run. - - mknod /dev/boot255 c 0 255 - - For information on configuring LILO, please refer to its documentation. - -3.3) Using GRUB - When using GRUB, kernel parameter are simply appended after the kernel - specification: kernel - -3.4) Using loadlin - loadlin may be used to boot Linux from a DOS command prompt without - requiring a local hard disk to mount as root. This has not been - thoroughly tested by the authors of this document, but in general - it should be possible configure the kernel command line similarly - to the configuration of LILO. - - Please refer to the loadlin documentation for further information. - -3.5) Using a boot ROM - This is probably the most elegant way of booting a diskless client. - With a boot ROM the kernel is loaded using the TFTP protocol. The - authors of this document are not aware of any no commercial boot - ROMs that support booting Linux over the network. However, there - are two free implementations of a boot ROM, netboot-nfs and - etherboot, both of which are available on sunsite.unc.edu, and both - of which contain everything you need to boot a diskless Linux client. - -3.6) Using pxelinux - Pxelinux may be used to boot linux using the PXE boot loader - which is present on many modern network cards. - - When using pxelinux, the kernel image is specified using - "kernel ". The nfsroot parameters - are passed to the kernel by adding them to the "append" line. - It is common to use serial console in conjunction with pxeliunx, - see Documentation/serial-console.txt for more information. - - For more information on isolinux, including how to create bootdisks - for prebuilt kernels, see http://syslinux.zytor.com/ - - - - -4.) Credits - ------- - - The nfsroot code in the kernel and the RARP support have been written - by Gero Kuhlmann . - - The rest of the IP layer autoconfiguration code has been written - by Martin Mares . - - In order to write the initial version of nfsroot I would like to thank - Jens-Uwe Mager for his help. diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 92b888d540a..a7e9746ee7e 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -140,7 +140,7 @@ Callers of notify_change() need ->i_mutex now. New super_block field "struct export_operations *s_export_op" for explicit support for exporting, e.g. via NFS. The structure is fully documented at its declaration in include/linux/fs.h, and in -Documentation/filesystems/Exporting. +Documentation/filesystems/nfs/Exporting. Briefly it allows for the definition of decode_fh and encode_fh operations to encode and decode filehandles, and allows the filesystem to use diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 9107b387e91..dab0f04b426 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1017,7 +1017,7 @@ and is between 256 and 4096 characters. It is defined in the file No delay ip= [IP_PNP] - See Documentation/filesystems/nfsroot.txt. + See Documentation/filesystems/nfs/nfsroot.txt. ip2= [HW] Set IO/IRQ pairs for up to 4 IntelliPort boards See comment before ip2_setup() in @@ -1538,10 +1538,10 @@ and is between 256 and 4096 characters. It is defined in the file going to be removed in 2.6.29. nfsaddrs= [NFS] - See Documentation/filesystems/nfsroot.txt. + See Documentation/filesystems/nfs/nfsroot.txt. nfsroot= [NFS] nfs root filesystem for disk-less boxes. - See Documentation/filesystems/nfsroot.txt. + See Documentation/filesystems/nfs/nfsroot.txt. nfs.callback_tcpport= [NFS] set the TCP port on which the NFSv4 callback diff --git a/fs/cifs/export.c b/fs/cifs/export.c index 75949d6a5f1..6177f7cca16 100644 --- a/fs/cifs/export.c +++ b/fs/cifs/export.c @@ -24,7 +24,7 @@ */ /* - * See Documentation/filesystems/Exporting + * See Documentation/filesystems/nfs/Exporting * and examples in fs/exportfs * * Since cifs is a network file system, an "fsid" must be included for diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 197c7db583c..e9e175949a6 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -6,7 +6,7 @@ * and for mapping back from file handles to dentries. * * For details on why we do all the strange and hairy things in here - * take a look at Documentation/filesystems/Exporting. + * take a look at Documentation/filesystems/nfs/Exporting. */ #include #include diff --git a/fs/isofs/export.c b/fs/isofs/export.c index e81a30593ba..ed752cb3847 100644 --- a/fs/isofs/export.c +++ b/fs/isofs/export.c @@ -9,7 +9,7 @@ * * The following files are helpful: * - * Documentation/filesystems/Exporting + * Documentation/filesystems/nfs/Exporting * fs/exportfs/expfs.c. */ diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 2a77bc25d5a..59e5673b459 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -90,7 +90,7 @@ config ROOT_NFS If you want your system to mount its root file system via NFS, choose Y here. This is common practice for managing systems without local permanent storage. For details, read - . + . Most people say N here. diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 27e772cefb6..dc12f416a49 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -97,7 +97,7 @@ struct fid { * @get_name: find the name for a given inode in a given directory * @get_parent: find the parent of a given directory * - * See Documentation/filesystems/Exporting for details on how to use + * See Documentation/filesystems/nfs/Exporting for details on how to use * this interface correctly. * * encode_fh: diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 70491d9035e..0c94a1ac294 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -166,7 +166,7 @@ config IP_PNP_DHCP If unsure, say Y. Note that if you want to use DHCP, a DHCP server must be operating on your network. Read - for details. + for details. config IP_PNP_BOOTP bool "IP: BOOTP support" @@ -181,7 +181,7 @@ config IP_PNP_BOOTP does BOOTP itself, providing all necessary information on the kernel command line, you can say N here. If unsure, say Y. Note that if you want to use BOOTP, a BOOTP server must be operating on your network. - Read for details. + Read for details. config IP_PNP_RARP bool "IP: RARP support" @@ -194,7 +194,7 @@ config IP_PNP_RARP older protocol which is being obsoleted by BOOTP and DHCP), say Y here. Note that if you want to use RARP, a RARP server must be operating on your network. Read - for details. + for details. # not yet ready.. # bool ' IP: ARP support' CONFIG_IP_PNP_ARP diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index f8d04c25645..7dcbf470609 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1447,7 +1447,7 @@ late_initcall(ip_auto_config); /* * Decode any IP configuration options in the "ip=" or "nfsaddrs=" kernel - * command line parameter. See Documentation/filesystems/nfsroot.txt. + * command line parameter. See Documentation/filesystems/nfs/nfsroot.txt. */ static int __init ic_proto_name(char *name) { -- cgit v1.2.3-18-g5258 From dd829c45640ff14d7a039af40b3b3975f1b2e484 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Wed, 21 Oct 2009 17:54:13 -0400 Subject: nfsd4.1: fix session memory use calculation Unbalanced calculations on creation and destruction of sessions could cause our estimate of cache memory used to become negative, sometimes resulting in spurious SERVERFAULT returns to client CREATE_SESSION requests. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index fcb9817881a..c1713711041 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -629,10 +629,13 @@ void free_session(struct kref *kref) { struct nfsd4_session *ses; + int mem; ses = container_of(kref, struct nfsd4_session, se_ref); spin_lock(&nfsd_drc_lock); - nfsd_drc_mem_used -= ses->se_fchannel.maxreqs * NFSD_SLOT_CACHE_SIZE; + mem = ses->se_fchannel.maxreqs + * (ses->se_fchannel.maxresp_cached - NFSD_MIN_HDR_SEQ_SZ); + nfsd_drc_mem_used -= mem; spin_unlock(&nfsd_drc_lock); free_session_slots(ses); kfree(ses); -- cgit v1.2.3-18-g5258 From efe0cb6d5a1f20ad4df045a055048afed4c5e660 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sat, 24 Oct 2009 20:52:16 -0400 Subject: nfsd4.1: common slot allocation size calculation We do the same calculation in a couple places; use a helper function, and add a little documentation, in the hopes of preventing bugs like that fixed in the last patch. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c1713711041..42dab9587af 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -524,6 +524,15 @@ free_session_slots(struct nfsd4_session *ses) kfree(ses->se_slots[i]); } +/* + * We don't actually need to cache the rpc and session headers, so we + * can allocate a little less for each slot: + */ +static inline int slot_bytes(struct nfsd4_channel_attrs *ca) +{ + return ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; +} + static int alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp, struct nfsd4_create_session *cses) @@ -555,7 +564,7 @@ alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp, memcpy(new, &tmp, sizeof(*new)); /* allocate each struct nfsd4_slot and data cache in one piece */ - cachesize = new->se_fchannel.maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; + cachesize = slot_bytes(&new->se_fchannel); for (i = 0; i < new->se_fchannel.maxreqs; i++) { sp = kzalloc(sizeof(*sp) + cachesize, GFP_KERNEL); if (!sp) @@ -633,8 +642,7 @@ free_session(struct kref *kref) ses = container_of(kref, struct nfsd4_session, se_ref); spin_lock(&nfsd_drc_lock); - mem = ses->se_fchannel.maxreqs - * (ses->se_fchannel.maxresp_cached - NFSD_MIN_HDR_SEQ_SZ); + mem = ses->se_fchannel.maxreqs * slot_bytes(&ses->se_fchannel); nfsd_drc_mem_used -= mem; spin_unlock(&nfsd_drc_lock); free_session_slots(ses); -- cgit v1.2.3-18-g5258 From dc83d6e27fa80babe31c80aa8568f125f72edf57 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 20 Oct 2009 18:51:34 -0400 Subject: nfsd4: don't try to map gid's in generic rpc code For nfsd we provide users the option of mapping uid's to server-side supplementary group lists. That makes sense for nfsd, but not necessarily for other rpc users (such as the callback client). So move that lookup to svcauth_unix_set_client, which is a program-specific method. Signed-off-by: J. Bruce Fields --- net/sunrpc/svcauth_unix.c | 53 +++++++++++++++++++++++++++-------------------- 1 file changed, 30 insertions(+), 23 deletions(-) diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 117f68a8aa4..97cc3de7432 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -655,23 +655,25 @@ static struct unix_gid *unix_gid_lookup(uid_t uid) return NULL; } -static int unix_gid_find(uid_t uid, struct group_info **gip, - struct svc_rqst *rqstp) +static struct group_info *unix_gid_find(uid_t uid, struct svc_rqst *rqstp) { - struct unix_gid *ug = unix_gid_lookup(uid); + struct unix_gid *ug; + struct group_info *gi; + int ret; + + ug = unix_gid_lookup(uid); if (!ug) - return -EAGAIN; - switch (cache_check(&unix_gid_cache, &ug->h, &rqstp->rq_chandle)) { + return ERR_PTR(-EAGAIN); + ret = cache_check(&unix_gid_cache, &ug->h, &rqstp->rq_chandle); + switch (ret) { case -ENOENT: - *gip = NULL; - return 0; + return ERR_PTR(-ENOENT); case 0: - *gip = ug->gi; - get_group_info(*gip); + gi = get_group_info(ug->gi); cache_put(&ug->h, &unix_gid_cache); - return 0; + return gi; default: - return -EAGAIN; + return ERR_PTR(-EAGAIN); } } @@ -681,6 +683,8 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) struct sockaddr_in *sin; struct sockaddr_in6 *sin6, sin6_storage; struct ip_map *ipm; + struct group_info *gi; + struct svc_cred *cred = &rqstp->rq_cred; switch (rqstp->rq_addr.ss_family) { case AF_INET: @@ -722,6 +726,17 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) ip_map_cached_put(rqstp, ipm); break; } + + gi = unix_gid_find(cred->cr_uid, rqstp); + switch (PTR_ERR(gi)) { + case -EAGAIN: + return SVC_DROP; + case -ENOENT: + break; + default: + put_group_info(cred->cr_group_info); + cred->cr_group_info = gi; + } return SVC_OK; } @@ -818,19 +833,11 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) slen = svc_getnl(argv); /* gids length */ if (slen > 16 || (len -= (slen + 2)*4) < 0) goto badcred; - if (unix_gid_find(cred->cr_uid, &cred->cr_group_info, rqstp) - == -EAGAIN) + cred->cr_group_info = groups_alloc(slen); + if (cred->cr_group_info == NULL) return SVC_DROP; - if (cred->cr_group_info == NULL) { - cred->cr_group_info = groups_alloc(slen); - if (cred->cr_group_info == NULL) - return SVC_DROP; - for (i = 0; i < slen; i++) - GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv); - } else { - for (i = 0; i < slen ; i++) - svc_getnl(argv); - } + for (i = 0; i < slen; i++) + GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv); if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { *authp = rpc_autherr_badverf; return SVC_DENIED; -- cgit v1.2.3-18-g5258 From aba24d71580180dfdf6a1a83a5858a1c048fd785 Mon Sep 17 00:00:00 2001 From: Frank Filz Date: Wed, 21 Oct 2009 16:45:02 -0700 Subject: nfsd: Fix sort_pacl in fs/nfsd/nf4acl.c to actually sort groups We have been doing some extensive testing of Linux support for ACLs on NFDS v4. We have noticed that the server rejects ACLs where the groups are out of order, for example, the following ACL is rejected: A::OWNER@:rwaxtTcCy A::user101@domain:rwaxtcy A::GROUP@:rwaxtcy A:g:group102@domain:rwaxtcy A:g:group101@domain:rwaxtcy A::EVERYONE@:rwaxtcy Examining the server code, I found that after converting an NFS v4 ACL to POSIX, sort_pacl is called to sort the user ACEs and group ACEs. Unfortunately, a minor bug causes the group sort to be skipped. Signed-off-by: Frank Filz Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4acl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index 725d02f210e..6d9c6aabc85 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -389,7 +389,7 @@ sort_pacl(struct posix_acl *pacl) sort_pacl_range(pacl, 1, i-1); BUG_ON(pacl->a_entries[i].e_tag != ACL_GROUP_OBJ); - j = i++; + j = ++i; while (pacl->a_entries[j].e_tag == ACL_GROUP) j++; sort_pacl_range(pacl, i, j-1); -- cgit v1.2.3-18-g5258 From 1b7e0403c6a72d18bebd4f2a6858b6c69c4bd428 Mon Sep 17 00:00:00 2001 From: Peter Staubach Date: Mon, 2 Nov 2009 16:59:07 -0500 Subject: nfsd: register NFS_ACL with rpcbind Modify the NFS server to register the NFS_ACL services with the rpcbind daemon. This allows the client to ping for the existence of the NFS_ACL support via commands such as "rpcinfo -t nfs_acl". This patch also modifies the NFS_ACL support so that responses to version 2 NULLPROC requests can be made. The changelog for the patch which turned off this functionality mentioned something about not registering the NFS_ACL as being part of some tradition. I can't find this tradition and the only other implementation which supports NFS_ACL does register them with the rpcbind daemon. Signed-off-by: Peter Staubach Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs2acl.c | 13 +++++++++++-- fs/nfsd/nfs3acl.c | 2 +- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 4e3219e8411..e2a17f0a96a 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -217,6 +217,16 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, * XDR encode functions */ +/* + * There must be an encoding function for void results so svc_process + * will work properly. + */ +int +nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) +{ + return xdr_ressize_check(rqstp, p); +} + /* GETACL */ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_getaclres *resp) @@ -308,7 +318,6 @@ static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p, } #define nfsaclsvc_decode_voidargs NULL -#define nfsaclsvc_encode_voidres NULL #define nfsaclsvc_release_void NULL #define nfsd3_fhandleargs nfsd_fhandle #define nfsd3_attrstatres nfsd_attrstat @@ -346,5 +355,5 @@ struct svc_version nfsd_acl_version2 = { .vs_proc = nfsd_acl_procedures2, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS3_SVC_XDRSIZE, - .vs_hidden = 1, + .vs_hidden = 0, }; diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 9981dbb377a..ff73596eb55 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -264,6 +264,6 @@ struct svc_version nfsd_acl_version3 = { .vs_proc = nfsd_acl_procedures3, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS3_SVC_XDRSIZE, - .vs_hidden = 1, + .vs_hidden = 0, }; -- cgit v1.2.3-18-g5258 From 8c10cbdb4af642d9a2efb45ea89251aaab905360 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Mon, 19 Oct 2009 12:04:53 +0200 Subject: nfsd: use STATEID_FMT and STATEID_VAL for printing stateids Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 46 ++++++++++++++++------------------------------ include/linux/nfsd/state.h | 7 +++++++ 2 files changed, 23 insertions(+), 30 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 42dab9587af..c8b621a120c 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2416,11 +2416,8 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta memcpy(&open->op_delegate_stateid, &dp->dl_stateid, sizeof(dp->dl_stateid)); - dprintk("NFSD: delegation stateid=(%08x/%08x/%08x/%08x)\n\n", - dp->dl_stateid.si_boot, - dp->dl_stateid.si_stateownerid, - dp->dl_stateid.si_fileid, - dp->dl_stateid.si_generation); + dprintk("NFSD: delegation stateid=" STATEID_FMT "\n", + STATEID_VAL(&dp->dl_stateid)); out: if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS && flag == NFS4_OPEN_DELEGATE_NONE @@ -2510,9 +2507,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf status = nfs_ok; - dprintk("nfs4_process_open2: stateid=(%08x/%08x/%08x/%08x)\n", - stp->st_stateid.si_boot, stp->st_stateid.si_stateownerid, - stp->st_stateid.si_fileid, stp->st_stateid.si_generation); + dprintk("%s: stateid=" STATEID_FMT "\n", __func__, + STATEID_VAL(&stp->st_stateid)); out: if (fp) put_nfs4_file(fp); @@ -2678,9 +2674,8 @@ STALE_STATEID(stateid_t *stateid) { if (time_after((unsigned long)boot_time, (unsigned long)stateid->si_boot)) { - dprintk("NFSD: stale stateid (%08x/%08x/%08x/%08x)!\n", - stateid->si_boot, stateid->si_stateownerid, - stateid->si_fileid, stateid->si_generation); + dprintk("NFSD: stale stateid " STATEID_FMT "!\n", + STATEID_VAL(stateid)); return 1; } return 0; @@ -2692,9 +2687,8 @@ EXPIRED_STATEID(stateid_t *stateid) if (time_before((unsigned long)boot_time, ((unsigned long)stateid->si_boot)) && time_before((unsigned long)(stateid->si_boot + lease_time), get_seconds())) { - dprintk("NFSD: expired stateid (%08x/%08x/%08x/%08x)!\n", - stateid->si_boot, stateid->si_stateownerid, - stateid->si_fileid, stateid->si_generation); + dprintk("NFSD: expired stateid " STATEID_FMT "!\n", + STATEID_VAL(stateid)); return 1; } return 0; @@ -2708,9 +2702,8 @@ stateid_error_map(stateid_t *stateid) if (EXPIRED_STATEID(stateid)) return nfserr_expired; - dprintk("NFSD: bad stateid (%08x/%08x/%08x/%08x)!\n", - stateid->si_boot, stateid->si_stateownerid, - stateid->si_fileid, stateid->si_generation); + dprintk("NFSD: bad stateid " STATEID_FMT "!\n", + STATEID_VAL(stateid)); return nfserr_bad_stateid; } @@ -2896,10 +2889,8 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, struct svc_fh *current_fh = &cstate->current_fh; __be32 status; - dprintk("NFSD: preprocess_seqid_op: seqid=%d " - "stateid = (%08x/%08x/%08x/%08x)\n", seqid, - stateid->si_boot, stateid->si_stateownerid, stateid->si_fileid, - stateid->si_generation); + dprintk("NFSD: %s: seqid=%d stateid = " STATEID_FMT "\n", __func__, + seqid, STATEID_VAL(stateid)); *stpp = NULL; *sopp = NULL; @@ -3031,12 +3022,8 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, sop->so_confirmed = 1; update_stateid(&stp->st_stateid); memcpy(&oc->oc_resp_stateid, &stp->st_stateid, sizeof(stateid_t)); - dprintk("NFSD: nfsd4_open_confirm: success, seqid=%d " - "stateid=(%08x/%08x/%08x/%08x)\n", oc->oc_seqid, - stp->st_stateid.si_boot, - stp->st_stateid.si_stateownerid, - stp->st_stateid.si_fileid, - stp->st_stateid.si_generation); + dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n", + __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stateid)); nfsd4_create_clid_dir(sop->so_client); out: @@ -3295,9 +3282,8 @@ find_delegation_stateid(struct inode *ino, stateid_t *stid) struct nfs4_file *fp; struct nfs4_delegation *dl; - dprintk("NFSD:find_delegation_stateid stateid=(%08x/%08x/%08x/%08x)\n", - stid->si_boot, stid->si_stateownerid, - stid->si_fileid, stid->si_generation); + dprintk("NFSD: %s: stateid=" STATEID_FMT "\n", __func__, + STATEID_VAL(stid)); fp = find_file(ino); if (!fp) diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index b38d1132418..5aadf8aa3a9 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -60,6 +60,13 @@ typedef struct { #define si_stateownerid si_opaque.so_stateownerid #define si_fileid si_opaque.so_fileid +#define STATEID_FMT "(%08x/%08x/%08x/%08x)" +#define STATEID_VAL(s) \ + (s)->si_boot, \ + (s)->si_stateownerid, \ + (s)->si_fileid, \ + (s)->si_generation + struct nfsd4_cb_sequence { /* args/res */ u32 cbs_minorversion; -- cgit v1.2.3-18-g5258 From ea4878a24d7e6a467d369b962bab95bd6a12cbe0 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 6 Nov 2009 13:59:43 -0500 Subject: nfs: move more to Documentation/filesystems/nfs Oops: I missed two files in the first commit that created this directory. Signed-off-by: J. Bruce Fields --- Documentation/filesystems/00-INDEX | 2 - Documentation/filesystems/knfsd-stats.txt | 159 -------------------- Documentation/filesystems/nfs/00-INDEX | 4 + Documentation/filesystems/nfs/knfsd-stats.txt | 159 ++++++++++++++++++++ Documentation/filesystems/nfs/rpc-cache.txt | 202 ++++++++++++++++++++++++++ Documentation/filesystems/rpc-cache.txt | 202 -------------------------- 6 files changed, 365 insertions(+), 363 deletions(-) delete mode 100644 Documentation/filesystems/knfsd-stats.txt create mode 100644 Documentation/filesystems/nfs/knfsd-stats.txt create mode 100644 Documentation/filesystems/nfs/rpc-cache.txt delete mode 100644 Documentation/filesystems/rpc-cache.txt diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index 482151c883a..658154f5255 100644 --- a/Documentation/filesystems/00-INDEX +++ b/Documentation/filesystems/00-INDEX @@ -84,8 +84,6 @@ relay.txt - info on relay, for efficient streaming from kernel to user space. romfs.txt - description of the ROMFS filesystem. -rpc-cache.txt - - introduction to the caching mechanisms in the sunrpc layer. seq_file.txt - how to use the seq_file API sharedsubtree.txt diff --git a/Documentation/filesystems/knfsd-stats.txt b/Documentation/filesystems/knfsd-stats.txt deleted file mode 100644 index 64ced5149d3..00000000000 --- a/Documentation/filesystems/knfsd-stats.txt +++ /dev/null @@ -1,159 +0,0 @@ - -Kernel NFS Server Statistics -============================ - -This document describes the format and semantics of the statistics -which the kernel NFS server makes available to userspace. These -statistics are available in several text form pseudo files, each of -which is described separately below. - -In most cases you don't need to know these formats, as the nfsstat(8) -program from the nfs-utils distribution provides a helpful command-line -interface for extracting and printing them. - -All the files described here are formatted as a sequence of text lines, -separated by newline '\n' characters. Lines beginning with a hash -'#' character are comments intended for humans and should be ignored -by parsing routines. All other lines contain a sequence of fields -separated by whitespace. - -/proc/fs/nfsd/pool_stats ------------------------- - -This file is available in kernels from 2.6.30 onwards, if the -/proc/fs/nfsd filesystem is mounted (it almost always should be). - -The first line is a comment which describes the fields present in -all the other lines. The other lines present the following data as -a sequence of unsigned decimal numeric fields. One line is shown -for each NFS thread pool. - -All counters are 64 bits wide and wrap naturally. There is no way -to zero these counters, instead applications should do their own -rate conversion. - -pool - The id number of the NFS thread pool to which this line applies. - This number does not change. - - Thread pool ids are a contiguous set of small integers starting - at zero. The maximum value depends on the thread pool mode, but - currently cannot be larger than the number of CPUs in the system. - Note that in the default case there will be a single thread pool - which contains all the nfsd threads and all the CPUs in the system, - and thus this file will have a single line with a pool id of "0". - -packets-arrived - Counts how many NFS packets have arrived. More precisely, this - is the number of times that the network stack has notified the - sunrpc server layer that new data may be available on a transport - (e.g. an NFS or UDP socket or an NFS/RDMA endpoint). - - Depending on the NFS workload patterns and various network stack - effects (such as Large Receive Offload) which can combine packets - on the wire, this may be either more or less than the number - of NFS calls received (which statistic is available elsewhere). - However this is a more accurate and less workload-dependent measure - of how much CPU load is being placed on the sunrpc server layer - due to NFS network traffic. - -sockets-enqueued - Counts how many times an NFS transport is enqueued to wait for - an nfsd thread to service it, i.e. no nfsd thread was considered - available. - - The circumstance this statistic tracks indicates that there was NFS - network-facing work to be done but it couldn't be done immediately, - thus introducing a small delay in servicing NFS calls. The ideal - rate of change for this counter is zero; significantly non-zero - values may indicate a performance limitation. - - This can happen either because there are too few nfsd threads in the - thread pool for the NFS workload (the workload is thread-limited), - or because the NFS workload needs more CPU time than is available in - the thread pool (the workload is CPU-limited). In the former case, - configuring more nfsd threads will probably improve the performance - of the NFS workload. In the latter case, the sunrpc server layer is - already choosing not to wake idle nfsd threads because there are too - many nfsd threads which want to run but cannot, so configuring more - nfsd threads will make no difference whatsoever. The overloads-avoided - statistic (see below) can be used to distinguish these cases. - -threads-woken - Counts how many times an idle nfsd thread is woken to try to - receive some data from an NFS transport. - - This statistic tracks the circumstance where incoming - network-facing NFS work is being handled quickly, which is a good - thing. The ideal rate of change for this counter will be close - to but less than the rate of change of the packets-arrived counter. - -overloads-avoided - Counts how many times the sunrpc server layer chose not to wake an - nfsd thread, despite the presence of idle nfsd threads, because - too many nfsd threads had been recently woken but could not get - enough CPU time to actually run. - - This statistic counts a circumstance where the sunrpc layer - heuristically avoids overloading the CPU scheduler with too many - runnable nfsd threads. The ideal rate of change for this counter - is zero. Significant non-zero values indicate that the workload - is CPU limited. Usually this is associated with heavy CPU usage - on all the CPUs in the nfsd thread pool. - - If a sustained large overloads-avoided rate is detected on a pool, - the top(1) utility should be used to check for the following - pattern of CPU usage on all the CPUs associated with the given - nfsd thread pool. - - - %us ~= 0 (as you're *NOT* running applications on your NFS server) - - - %wa ~= 0 - - - %id ~= 0 - - - %sy + %hi + %si ~= 100 - - If this pattern is seen, configuring more nfsd threads will *not* - improve the performance of the workload. If this patten is not - seen, then something more subtle is wrong. - -threads-timedout - Counts how many times an nfsd thread triggered an idle timeout, - i.e. was not woken to handle any incoming network packets for - some time. - - This statistic counts a circumstance where there are more nfsd - threads configured than can be used by the NFS workload. This is - a clue that the number of nfsd threads can be reduced without - affecting performance. Unfortunately, it's only a clue and not - a strong indication, for a couple of reasons: - - - Currently the rate at which the counter is incremented is quite - slow; the idle timeout is 60 minutes. Unless the NFS workload - remains constant for hours at a time, this counter is unlikely - to be providing information that is still useful. - - - It is usually a wise policy to provide some slack, - i.e. configure a few more nfsds than are currently needed, - to allow for future spikes in load. - - -Note that incoming packets on NFS transports will be dealt with in -one of three ways. An nfsd thread can be woken (threads-woken counts -this case), or the transport can be enqueued for later attention -(sockets-enqueued counts this case), or the packet can be temporarily -deferred because the transport is currently being used by an nfsd -thread. This last case is not very interesting and is not explicitly -counted, but can be inferred from the other counters thus: - -packets-deferred = packets-arrived - ( sockets-enqueued + threads-woken ) - - -More ----- -Descriptions of the other statistics file should go here. - - -Greg Banks -26 Mar 2009 diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX index 6ff3d212027..2f68cd68876 100644 --- a/Documentation/filesystems/nfs/00-INDEX +++ b/Documentation/filesystems/nfs/00-INDEX @@ -2,6 +2,8 @@ - this file (nfs-related documentation). Exporting - explanation of how to make filesystems exportable. +knfsd-stats.txt + - statistics which the NFS server makes available to user space. nfs.txt - nfs client, and DNS resolution for fs_locations. nfs41-server.txt @@ -10,3 +12,5 @@ nfs-rdma.txt - how to install and setup the Linux NFS/RDMA client and server software nfsroot.txt - short guide on setting up a diskless box with NFS root filesystem. +rpc-cache.txt + - introduction to the caching mechanisms in the sunrpc layer. diff --git a/Documentation/filesystems/nfs/knfsd-stats.txt b/Documentation/filesystems/nfs/knfsd-stats.txt new file mode 100644 index 00000000000..64ced5149d3 --- /dev/null +++ b/Documentation/filesystems/nfs/knfsd-stats.txt @@ -0,0 +1,159 @@ + +Kernel NFS Server Statistics +============================ + +This document describes the format and semantics of the statistics +which the kernel NFS server makes available to userspace. These +statistics are available in several text form pseudo files, each of +which is described separately below. + +In most cases you don't need to know these formats, as the nfsstat(8) +program from the nfs-utils distribution provides a helpful command-line +interface for extracting and printing them. + +All the files described here are formatted as a sequence of text lines, +separated by newline '\n' characters. Lines beginning with a hash +'#' character are comments intended for humans and should be ignored +by parsing routines. All other lines contain a sequence of fields +separated by whitespace. + +/proc/fs/nfsd/pool_stats +------------------------ + +This file is available in kernels from 2.6.30 onwards, if the +/proc/fs/nfsd filesystem is mounted (it almost always should be). + +The first line is a comment which describes the fields present in +all the other lines. The other lines present the following data as +a sequence of unsigned decimal numeric fields. One line is shown +for each NFS thread pool. + +All counters are 64 bits wide and wrap naturally. There is no way +to zero these counters, instead applications should do their own +rate conversion. + +pool + The id number of the NFS thread pool to which this line applies. + This number does not change. + + Thread pool ids are a contiguous set of small integers starting + at zero. The maximum value depends on the thread pool mode, but + currently cannot be larger than the number of CPUs in the system. + Note that in the default case there will be a single thread pool + which contains all the nfsd threads and all the CPUs in the system, + and thus this file will have a single line with a pool id of "0". + +packets-arrived + Counts how many NFS packets have arrived. More precisely, this + is the number of times that the network stack has notified the + sunrpc server layer that new data may be available on a transport + (e.g. an NFS or UDP socket or an NFS/RDMA endpoint). + + Depending on the NFS workload patterns and various network stack + effects (such as Large Receive Offload) which can combine packets + on the wire, this may be either more or less than the number + of NFS calls received (which statistic is available elsewhere). + However this is a more accurate and less workload-dependent measure + of how much CPU load is being placed on the sunrpc server layer + due to NFS network traffic. + +sockets-enqueued + Counts how many times an NFS transport is enqueued to wait for + an nfsd thread to service it, i.e. no nfsd thread was considered + available. + + The circumstance this statistic tracks indicates that there was NFS + network-facing work to be done but it couldn't be done immediately, + thus introducing a small delay in servicing NFS calls. The ideal + rate of change for this counter is zero; significantly non-zero + values may indicate a performance limitation. + + This can happen either because there are too few nfsd threads in the + thread pool for the NFS workload (the workload is thread-limited), + or because the NFS workload needs more CPU time than is available in + the thread pool (the workload is CPU-limited). In the former case, + configuring more nfsd threads will probably improve the performance + of the NFS workload. In the latter case, the sunrpc server layer is + already choosing not to wake idle nfsd threads because there are too + many nfsd threads which want to run but cannot, so configuring more + nfsd threads will make no difference whatsoever. The overloads-avoided + statistic (see below) can be used to distinguish these cases. + +threads-woken + Counts how many times an idle nfsd thread is woken to try to + receive some data from an NFS transport. + + This statistic tracks the circumstance where incoming + network-facing NFS work is being handled quickly, which is a good + thing. The ideal rate of change for this counter will be close + to but less than the rate of change of the packets-arrived counter. + +overloads-avoided + Counts how many times the sunrpc server layer chose not to wake an + nfsd thread, despite the presence of idle nfsd threads, because + too many nfsd threads had been recently woken but could not get + enough CPU time to actually run. + + This statistic counts a circumstance where the sunrpc layer + heuristically avoids overloading the CPU scheduler with too many + runnable nfsd threads. The ideal rate of change for this counter + is zero. Significant non-zero values indicate that the workload + is CPU limited. Usually this is associated with heavy CPU usage + on all the CPUs in the nfsd thread pool. + + If a sustained large overloads-avoided rate is detected on a pool, + the top(1) utility should be used to check for the following + pattern of CPU usage on all the CPUs associated with the given + nfsd thread pool. + + - %us ~= 0 (as you're *NOT* running applications on your NFS server) + + - %wa ~= 0 + + - %id ~= 0 + + - %sy + %hi + %si ~= 100 + + If this pattern is seen, configuring more nfsd threads will *not* + improve the performance of the workload. If this patten is not + seen, then something more subtle is wrong. + +threads-timedout + Counts how many times an nfsd thread triggered an idle timeout, + i.e. was not woken to handle any incoming network packets for + some time. + + This statistic counts a circumstance where there are more nfsd + threads configured than can be used by the NFS workload. This is + a clue that the number of nfsd threads can be reduced without + affecting performance. Unfortunately, it's only a clue and not + a strong indication, for a couple of reasons: + + - Currently the rate at which the counter is incremented is quite + slow; the idle timeout is 60 minutes. Unless the NFS workload + remains constant for hours at a time, this counter is unlikely + to be providing information that is still useful. + + - It is usually a wise policy to provide some slack, + i.e. configure a few more nfsds than are currently needed, + to allow for future spikes in load. + + +Note that incoming packets on NFS transports will be dealt with in +one of three ways. An nfsd thread can be woken (threads-woken counts +this case), or the transport can be enqueued for later attention +(sockets-enqueued counts this case), or the packet can be temporarily +deferred because the transport is currently being used by an nfsd +thread. This last case is not very interesting and is not explicitly +counted, but can be inferred from the other counters thus: + +packets-deferred = packets-arrived - ( sockets-enqueued + threads-woken ) + + +More +---- +Descriptions of the other statistics file should go here. + + +Greg Banks +26 Mar 2009 diff --git a/Documentation/filesystems/nfs/rpc-cache.txt b/Documentation/filesystems/nfs/rpc-cache.txt new file mode 100644 index 00000000000..8a382bea680 --- /dev/null +++ b/Documentation/filesystems/nfs/rpc-cache.txt @@ -0,0 +1,202 @@ + This document gives a brief introduction to the caching +mechanisms in the sunrpc layer that is used, in particular, +for NFS authentication. + +CACHES +====== +The caching replaces the old exports table and allows for +a wide variety of values to be caches. + +There are a number of caches that are similar in structure though +quite possibly very different in content and use. There is a corpus +of common code for managing these caches. + +Examples of caches that are likely to be needed are: + - mapping from IP address to client name + - mapping from client name and filesystem to export options + - mapping from UID to list of GIDs, to work around NFS's limitation + of 16 gids. + - mappings between local UID/GID and remote UID/GID for sites that + do not have uniform uid assignment + - mapping from network identify to public key for crypto authentication. + +The common code handles such things as: + - general cache lookup with correct locking + - supporting 'NEGATIVE' as well as positive entries + - allowing an EXPIRED time on cache items, and removing + items after they expire, and are no longer in-use. + - making requests to user-space to fill in cache entries + - allowing user-space to directly set entries in the cache + - delaying RPC requests that depend on as-yet incomplete + cache entries, and replaying those requests when the cache entry + is complete. + - clean out old entries as they expire. + +Creating a Cache +---------------- + +1/ A cache needs a datum to store. This is in the form of a + structure definition that must contain a + struct cache_head + as an element, usually the first. + It will also contain a key and some content. + Each cache element is reference counted and contains + expiry and update times for use in cache management. +2/ A cache needs a "cache_detail" structure that + describes the cache. This stores the hash table, some + parameters for cache management, and some operations detailing how + to work with particular cache items. + The operations requires are: + struct cache_head *alloc(void) + This simply allocates appropriate memory and returns + a pointer to the cache_detail embedded within the + structure + void cache_put(struct kref *) + This is called when the last reference to an item is + dropped. The pointer passed is to the 'ref' field + in the cache_head. cache_put should release any + references create by 'cache_init' and, if CACHE_VALID + is set, any references created by cache_update. + It should then release the memory allocated by + 'alloc'. + int match(struct cache_head *orig, struct cache_head *new) + test if the keys in the two structures match. Return + 1 if they do, 0 if they don't. + void init(struct cache_head *orig, struct cache_head *new) + Set the 'key' fields in 'new' from 'orig'. This may + include taking references to shared objects. + void update(struct cache_head *orig, struct cache_head *new) + Set the 'content' fileds in 'new' from 'orig'. + int cache_show(struct seq_file *m, struct cache_detail *cd, + struct cache_head *h) + Optional. Used to provide a /proc file that lists the + contents of a cache. This should show one item, + usually on just one line. + int cache_request(struct cache_detail *cd, struct cache_head *h, + char **bpp, int *blen) + Format a request to be send to user-space for an item + to be instantiated. *bpp is a buffer of size *blen. + bpp should be moved forward over the encoded message, + and *blen should be reduced to show how much free + space remains. Return 0 on success or <0 if not + enough room or other problem. + int cache_parse(struct cache_detail *cd, char *buf, int len) + A message from user space has arrived to fill out a + cache entry. It is in 'buf' of length 'len'. + cache_parse should parse this, find the item in the + cache with sunrpc_cache_lookup, and update the item + with sunrpc_cache_update. + + +3/ A cache needs to be registered using cache_register(). This + includes it on a list of caches that will be regularly + cleaned to discard old data. + +Using a cache +------------- + +To find a value in a cache, call sunrpc_cache_lookup passing a pointer +to the cache_head in a sample item with the 'key' fields filled in. +This will be passed to ->match to identify the target entry. If no +entry is found, a new entry will be create, added to the cache, and +marked as not containing valid data. + +The item returned is typically passed to cache_check which will check +if the data is valid, and may initiate an up-call to get fresh data. +cache_check will return -ENOENT in the entry is negative or if an up +call is needed but not possible, -EAGAIN if an upcall is pending, +or 0 if the data is valid; + +cache_check can be passed a "struct cache_req *". This structure is +typically embedded in the actual request and can be used to create a +deferred copy of the request (struct cache_deferred_req). This is +done when the found cache item is not uptodate, but the is reason to +believe that userspace might provide information soon. When the cache +item does become valid, the deferred copy of the request will be +revisited (->revisit). It is expected that this method will +reschedule the request for processing. + +The value returned by sunrpc_cache_lookup can also be passed to +sunrpc_cache_update to set the content for the item. A second item is +passed which should hold the content. If the item found by _lookup +has valid data, then it is discarded and a new item is created. This +saves any user of an item from worrying about content changing while +it is being inspected. If the item found by _lookup does not contain +valid data, then the content is copied across and CACHE_VALID is set. + +Populating a cache +------------------ + +Each cache has a name, and when the cache is registered, a directory +with that name is created in /proc/net/rpc + +This directory contains a file called 'channel' which is a channel +for communicating between kernel and user for populating the cache. +This directory may later contain other files of interacting +with the cache. + +The 'channel' works a bit like a datagram socket. Each 'write' is +passed as a whole to the cache for parsing and interpretation. +Each cache can treat the write requests differently, but it is +expected that a message written will contain: + - a key + - an expiry time + - a content. +with the intention that an item in the cache with the give key +should be create or updated to have the given content, and the +expiry time should be set on that item. + +Reading from a channel is a bit more interesting. When a cache +lookup fails, or when it succeeds but finds an entry that may soon +expire, a request is lodged for that cache item to be updated by +user-space. These requests appear in the channel file. + +Successive reads will return successive requests. +If there are no more requests to return, read will return EOF, but a +select or poll for read will block waiting for another request to be +added. + +Thus a user-space helper is likely to: + open the channel. + select for readable + read a request + write a response + loop. + +If it dies and needs to be restarted, any requests that have not been +answered will still appear in the file and will be read by the new +instance of the helper. + +Each cache should define a "cache_parse" method which takes a message +written from user-space and processes it. It should return an error +(which propagates back to the write syscall) or 0. + +Each cache should also define a "cache_request" method which +takes a cache item and encodes a request into the buffer +provided. + +Note: If a cache has no active readers on the channel, and has had not +active readers for more than 60 seconds, further requests will not be +added to the channel but instead all lookups that do not find a valid +entry will fail. This is partly for backward compatibility: The +previous nfs exports table was deemed to be authoritative and a +failed lookup meant a definite 'no'. + +request/response format +----------------------- + +While each cache is free to use it's own format for requests +and responses over channel, the following is recommended as +appropriate and support routines are available to help: +Each request or response record should be printable ASCII +with precisely one newline character which should be at the end. +Fields within the record should be separated by spaces, normally one. +If spaces, newlines, or nul characters are needed in a field they +much be quoted. two mechanisms are available: +1/ If a field begins '\x' then it must contain an even number of + hex digits, and pairs of these digits provide the bytes in the + field. +2/ otherwise a \ in the field must be followed by 3 octal digits + which give the code for a byte. Other characters are treated + as them selves. At the very least, space, newline, nul, and + '\' must be quoted in this way. diff --git a/Documentation/filesystems/rpc-cache.txt b/Documentation/filesystems/rpc-cache.txt deleted file mode 100644 index 8a382bea680..00000000000 --- a/Documentation/filesystems/rpc-cache.txt +++ /dev/null @@ -1,202 +0,0 @@ - This document gives a brief introduction to the caching -mechanisms in the sunrpc layer that is used, in particular, -for NFS authentication. - -CACHES -====== -The caching replaces the old exports table and allows for -a wide variety of values to be caches. - -There are a number of caches that are similar in structure though -quite possibly very different in content and use. There is a corpus -of common code for managing these caches. - -Examples of caches that are likely to be needed are: - - mapping from IP address to client name - - mapping from client name and filesystem to export options - - mapping from UID to list of GIDs, to work around NFS's limitation - of 16 gids. - - mappings between local UID/GID and remote UID/GID for sites that - do not have uniform uid assignment - - mapping from network identify to public key for crypto authentication. - -The common code handles such things as: - - general cache lookup with correct locking - - supporting 'NEGATIVE' as well as positive entries - - allowing an EXPIRED time on cache items, and removing - items after they expire, and are no longer in-use. - - making requests to user-space to fill in cache entries - - allowing user-space to directly set entries in the cache - - delaying RPC requests that depend on as-yet incomplete - cache entries, and replaying those requests when the cache entry - is complete. - - clean out old entries as they expire. - -Creating a Cache ----------------- - -1/ A cache needs a datum to store. This is in the form of a - structure definition that must contain a - struct cache_head - as an element, usually the first. - It will also contain a key and some content. - Each cache element is reference counted and contains - expiry and update times for use in cache management. -2/ A cache needs a "cache_detail" structure that - describes the cache. This stores the hash table, some - parameters for cache management, and some operations detailing how - to work with particular cache items. - The operations requires are: - struct cache_head *alloc(void) - This simply allocates appropriate memory and returns - a pointer to the cache_detail embedded within the - structure - void cache_put(struct kref *) - This is called when the last reference to an item is - dropped. The pointer passed is to the 'ref' field - in the cache_head. cache_put should release any - references create by 'cache_init' and, if CACHE_VALID - is set, any references created by cache_update. - It should then release the memory allocated by - 'alloc'. - int match(struct cache_head *orig, struct cache_head *new) - test if the keys in the two structures match. Return - 1 if they do, 0 if they don't. - void init(struct cache_head *orig, struct cache_head *new) - Set the 'key' fields in 'new' from 'orig'. This may - include taking references to shared objects. - void update(struct cache_head *orig, struct cache_head *new) - Set the 'content' fileds in 'new' from 'orig'. - int cache_show(struct seq_file *m, struct cache_detail *cd, - struct cache_head *h) - Optional. Used to provide a /proc file that lists the - contents of a cache. This should show one item, - usually on just one line. - int cache_request(struct cache_detail *cd, struct cache_head *h, - char **bpp, int *blen) - Format a request to be send to user-space for an item - to be instantiated. *bpp is a buffer of size *blen. - bpp should be moved forward over the encoded message, - and *blen should be reduced to show how much free - space remains. Return 0 on success or <0 if not - enough room or other problem. - int cache_parse(struct cache_detail *cd, char *buf, int len) - A message from user space has arrived to fill out a - cache entry. It is in 'buf' of length 'len'. - cache_parse should parse this, find the item in the - cache with sunrpc_cache_lookup, and update the item - with sunrpc_cache_update. - - -3/ A cache needs to be registered using cache_register(). This - includes it on a list of caches that will be regularly - cleaned to discard old data. - -Using a cache -------------- - -To find a value in a cache, call sunrpc_cache_lookup passing a pointer -to the cache_head in a sample item with the 'key' fields filled in. -This will be passed to ->match to identify the target entry. If no -entry is found, a new entry will be create, added to the cache, and -marked as not containing valid data. - -The item returned is typically passed to cache_check which will check -if the data is valid, and may initiate an up-call to get fresh data. -cache_check will return -ENOENT in the entry is negative or if an up -call is needed but not possible, -EAGAIN if an upcall is pending, -or 0 if the data is valid; - -cache_check can be passed a "struct cache_req *". This structure is -typically embedded in the actual request and can be used to create a -deferred copy of the request (struct cache_deferred_req). This is -done when the found cache item is not uptodate, but the is reason to -believe that userspace might provide information soon. When the cache -item does become valid, the deferred copy of the request will be -revisited (->revisit). It is expected that this method will -reschedule the request for processing. - -The value returned by sunrpc_cache_lookup can also be passed to -sunrpc_cache_update to set the content for the item. A second item is -passed which should hold the content. If the item found by _lookup -has valid data, then it is discarded and a new item is created. This -saves any user of an item from worrying about content changing while -it is being inspected. If the item found by _lookup does not contain -valid data, then the content is copied across and CACHE_VALID is set. - -Populating a cache ------------------- - -Each cache has a name, and when the cache is registered, a directory -with that name is created in /proc/net/rpc - -This directory contains a file called 'channel' which is a channel -for communicating between kernel and user for populating the cache. -This directory may later contain other files of interacting -with the cache. - -The 'channel' works a bit like a datagram socket. Each 'write' is -passed as a whole to the cache for parsing and interpretation. -Each cache can treat the write requests differently, but it is -expected that a message written will contain: - - a key - - an expiry time - - a content. -with the intention that an item in the cache with the give key -should be create or updated to have the given content, and the -expiry time should be set on that item. - -Reading from a channel is a bit more interesting. When a cache -lookup fails, or when it succeeds but finds an entry that may soon -expire, a request is lodged for that cache item to be updated by -user-space. These requests appear in the channel file. - -Successive reads will return successive requests. -If there are no more requests to return, read will return EOF, but a -select or poll for read will block waiting for another request to be -added. - -Thus a user-space helper is likely to: - open the channel. - select for readable - read a request - write a response - loop. - -If it dies and needs to be restarted, any requests that have not been -answered will still appear in the file and will be read by the new -instance of the helper. - -Each cache should define a "cache_parse" method which takes a message -written from user-space and processes it. It should return an error -(which propagates back to the write syscall) or 0. - -Each cache should also define a "cache_request" method which -takes a cache item and encodes a request into the buffer -provided. - -Note: If a cache has no active readers on the channel, and has had not -active readers for more than 60 seconds, further requests will not be -added to the channel but instead all lookups that do not find a valid -entry will fail. This is partly for backward compatibility: The -previous nfs exports table was deemed to be authoritative and a -failed lookup meant a definite 'no'. - -request/response format ------------------------ - -While each cache is free to use it's own format for requests -and responses over channel, the following is recommended as -appropriate and support routines are available to help: -Each request or response record should be printable ASCII -with precisely one newline character which should be at the end. -Fields within the record should be separated by spaces, normally one. -If spaces, newlines, or nul characters are needed in a field they -much be quoted. two mechanisms are available: -1/ If a field begins '\x' then it must contain an even number of - hex digits, and pairs of these digits provide the bytes in the - field. -2/ otherwise a \ in the field must be followed by 3 octal digits - which give the code for a byte. Other characters are treated - as them selves. At the very least, space, newline, nul, and - '\' must be quoted in this way. -- cgit v1.2.3-18-g5258 From 0a3adadee42f2865bb867b8c5f4955b7def9baad Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Wed, 4 Nov 2009 18:12:35 -0500 Subject: nfsd: make fs/nfsd/vfs.h for common includes None of this stuff is used outside nfsd, so move it out of the common linux include directory. Actually, probably none of the stuff in include/linux/nfsd/nfsd.h really belongs there, so later we may remove that file entirely. Signed-off-by: J. Bruce Fields --- fs/nfsd/lockd.c | 1 + fs/nfsd/nfs2acl.c | 1 + fs/nfsd/nfs3acl.c | 1 + fs/nfsd/nfs3proc.c | 1 + fs/nfsd/nfs4proc.c | 1 + fs/nfsd/nfs4recover.c | 1 + fs/nfsd/nfs4state.c | 1 + fs/nfsd/nfs4xdr.c | 1 + fs/nfsd/nfsfh.c | 1 + fs/nfsd/nfsproc.c | 1 + fs/nfsd/nfssvc.c | 1 + fs/nfsd/vfs.c | 1 + fs/nfsd/vfs.h | 98 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfsd/nfsd.h | 87 +---------------------------------------- 14 files changed, 111 insertions(+), 86 deletions(-) create mode 100644 fs/nfsd/vfs.h diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index b2786a5f9af..812bc64874f 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -16,6 +16,7 @@ #include #include #include +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_LOCKD diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index e2a17f0a96a..38c883d48b0 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -14,6 +14,7 @@ #include #include #include +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC #define RETURN_STATUS(st) { resp->status = (st); return (st); } diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index ff73596eb55..526d85a65f7 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -13,6 +13,7 @@ #include #include #include +#include "vfs.h" #define RETURN_STATUS(st) { resp->status = (st); return (st); } diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index a713c418a92..1a259d313e1 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -25,6 +25,7 @@ #include #include #include +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index bebc0c2e1b0..60a93cdefef 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -48,6 +48,7 @@ #include #include #include +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index b5348405046..c7a6b245c7a 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -47,6 +47,7 @@ #include #include #include +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c8b621a120c..850960e5d62 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -56,6 +56,7 @@ #include #include #include +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 0fbd50cee1f..db0fc55670b 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -57,6 +57,7 @@ #include #include #include +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_XDR diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 01965b2f3a7..d0d8a217a3e 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -22,6 +22,7 @@ #include #include #include +#include "vfs.h" #include "auth.h" #define NFSDDBG_FACILITY NFSDDBG_FH diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index c5393d1b895..6c967e1ba37 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -24,6 +24,7 @@ #include #include #include +#include "vfs.h" typedef struct svc_rqst svc_rqst; typedef struct svc_buf svc_buf; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 67ea83eedd4..2944b31dcbe 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -35,6 +35,7 @@ #include #include #include +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_SVC diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 638573968dc..a7038ede671 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -56,6 +56,7 @@ #endif /* CONFIG_NFSD_V4 */ #include #include +#include "vfs.h" #include diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h new file mode 100644 index 00000000000..b8011fd2fca --- /dev/null +++ b/fs/nfsd/vfs.h @@ -0,0 +1,98 @@ +/* + * Copyright (C) 1995-1997 Olaf Kirch + */ + +#ifndef LINUX_NFSD_VFS_H +#define LINUX_NFSD_VFS_H + +/* + * Flags for nfsd_permission + */ +#define NFSD_MAY_NOP 0 +#define NFSD_MAY_EXEC 1 /* == MAY_EXEC */ +#define NFSD_MAY_WRITE 2 /* == MAY_WRITE */ +#define NFSD_MAY_READ 4 /* == MAY_READ */ +#define NFSD_MAY_SATTR 8 +#define NFSD_MAY_TRUNC 16 +#define NFSD_MAY_LOCK 32 +#define NFSD_MAY_OWNER_OVERRIDE 64 +#define NFSD_MAY_LOCAL_ACCESS 128 /* IRIX doing local access check on device special file*/ +#define NFSD_MAY_BYPASS_GSS_ON_ROOT 256 + +#define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE) +#define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC) + +/* + * Callback function for readdir + */ +typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int); + +/* nfsd/vfs.c */ +int fh_lock_parent(struct svc_fh *, struct dentry *); +int nfsd_racache_init(int); +void nfsd_racache_shutdown(void); +int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, + struct svc_export **expp); +__be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *, + const char *, unsigned int, struct svc_fh *); +__be32 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *, + const char *, unsigned int, + struct svc_export **, struct dentry **); +__be32 nfsd_setattr(struct svc_rqst *, struct svc_fh *, + struct iattr *, int, time_t); +#ifdef CONFIG_NFSD_V4 +__be32 nfsd4_set_nfs4_acl(struct svc_rqst *, struct svc_fh *, + struct nfs4_acl *); +int nfsd4_get_nfs4_acl(struct svc_rqst *, struct dentry *, struct nfs4_acl **); +#endif /* CONFIG_NFSD_V4 */ +__be32 nfsd_create(struct svc_rqst *, struct svc_fh *, + char *name, int len, struct iattr *attrs, + int type, dev_t rdev, struct svc_fh *res); +#ifdef CONFIG_NFSD_V3 +__be32 nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *); +__be32 nfsd_create_v3(struct svc_rqst *, struct svc_fh *, + char *name, int len, struct iattr *attrs, + struct svc_fh *res, int createmode, + u32 *verifier, int *truncp, int *created); +__be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, + loff_t, unsigned long); +#endif /* CONFIG_NFSD_V3 */ +__be32 nfsd_open(struct svc_rqst *, struct svc_fh *, int, + int, struct file **); +void nfsd_close(struct file *); +__be32 nfsd_read(struct svc_rqst *, struct svc_fh *, struct file *, + loff_t, struct kvec *, int, unsigned long *); +__be32 nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *, + loff_t, struct kvec *,int, unsigned long *, int *); +__be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, + char *, int *); +__be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, + char *name, int len, char *path, int plen, + struct svc_fh *res, struct iattr *); +__be32 nfsd_link(struct svc_rqst *, struct svc_fh *, + char *, int, struct svc_fh *); +__be32 nfsd_rename(struct svc_rqst *, + struct svc_fh *, char *, int, + struct svc_fh *, char *, int); +__be32 nfsd_remove(struct svc_rqst *, + struct svc_fh *, char *, int); +__be32 nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type, + char *name, int len); +int nfsd_truncate(struct svc_rqst *, struct svc_fh *, + unsigned long size); +__be32 nfsd_readdir(struct svc_rqst *, struct svc_fh *, + loff_t *, struct readdir_cd *, filldir_t); +__be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *, + struct kstatfs *, int access); + +int nfsd_notify_change(struct inode *, struct iattr *); +__be32 nfsd_permission(struct svc_rqst *, struct svc_export *, + struct dentry *, int); +int nfsd_sync_dir(struct dentry *dp); + +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) +struct posix_acl *nfsd_get_posix_acl(struct svc_fh *, int); +int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *); +#endif + +#endif /* LINUX_NFSD_VFS_H */ diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 510ffdd5020..e4518d090a8 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -25,30 +25,10 @@ */ #define NFSD_SUPPORTED_MINOR_VERSION 1 -/* - * Flags for nfsd_permission - */ -#define NFSD_MAY_NOP 0 -#define NFSD_MAY_EXEC 1 /* == MAY_EXEC */ -#define NFSD_MAY_WRITE 2 /* == MAY_WRITE */ -#define NFSD_MAY_READ 4 /* == MAY_READ */ -#define NFSD_MAY_SATTR 8 -#define NFSD_MAY_TRUNC 16 -#define NFSD_MAY_LOCK 32 -#define NFSD_MAY_OWNER_OVERRIDE 64 -#define NFSD_MAY_LOCAL_ACCESS 128 /* IRIX doing local access check on device special file*/ -#define NFSD_MAY_BYPASS_GSS_ON_ROOT 256 - -#define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE) -#define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC) - -/* - * Callback function for readdir - */ struct readdir_cd { __be32 err; /* 0, nfserr, or nfserr_eof */ }; -typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int); + extern struct svc_program nfsd_program; extern struct svc_version nfsd_version2, nfsd_version3, @@ -73,69 +53,6 @@ int nfsd_nrpools(void); int nfsd_get_nrthreads(int n, int *); int nfsd_set_nrthreads(int n, int *); -/* nfsd/vfs.c */ -int fh_lock_parent(struct svc_fh *, struct dentry *); -int nfsd_racache_init(int); -void nfsd_racache_shutdown(void); -int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, - struct svc_export **expp); -__be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *, - const char *, unsigned int, struct svc_fh *); -__be32 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *, - const char *, unsigned int, - struct svc_export **, struct dentry **); -__be32 nfsd_setattr(struct svc_rqst *, struct svc_fh *, - struct iattr *, int, time_t); -#ifdef CONFIG_NFSD_V4 -__be32 nfsd4_set_nfs4_acl(struct svc_rqst *, struct svc_fh *, - struct nfs4_acl *); -int nfsd4_get_nfs4_acl(struct svc_rqst *, struct dentry *, struct nfs4_acl **); -#endif /* CONFIG_NFSD_V4 */ -__be32 nfsd_create(struct svc_rqst *, struct svc_fh *, - char *name, int len, struct iattr *attrs, - int type, dev_t rdev, struct svc_fh *res); -#ifdef CONFIG_NFSD_V3 -__be32 nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *); -__be32 nfsd_create_v3(struct svc_rqst *, struct svc_fh *, - char *name, int len, struct iattr *attrs, - struct svc_fh *res, int createmode, - u32 *verifier, int *truncp, int *created); -__be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, - loff_t, unsigned long); -#endif /* CONFIG_NFSD_V3 */ -__be32 nfsd_open(struct svc_rqst *, struct svc_fh *, int, - int, struct file **); -void nfsd_close(struct file *); -__be32 nfsd_read(struct svc_rqst *, struct svc_fh *, struct file *, - loff_t, struct kvec *, int, unsigned long *); -__be32 nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *, - loff_t, struct kvec *,int, unsigned long *, int *); -__be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, - char *, int *); -__be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, - char *name, int len, char *path, int plen, - struct svc_fh *res, struct iattr *); -__be32 nfsd_link(struct svc_rqst *, struct svc_fh *, - char *, int, struct svc_fh *); -__be32 nfsd_rename(struct svc_rqst *, - struct svc_fh *, char *, int, - struct svc_fh *, char *, int); -__be32 nfsd_remove(struct svc_rqst *, - struct svc_fh *, char *, int); -__be32 nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type, - char *name, int len); -int nfsd_truncate(struct svc_rqst *, struct svc_fh *, - unsigned long size); -__be32 nfsd_readdir(struct svc_rqst *, struct svc_fh *, - loff_t *, struct readdir_cd *, filldir_t); -__be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *, - struct kstatfs *, int access); - -int nfsd_notify_change(struct inode *, struct iattr *); -__be32 nfsd_permission(struct svc_rqst *, struct svc_export *, - struct dentry *, int); -int nfsd_sync_dir(struct dentry *dp); - #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) #ifdef CONFIG_NFSD_V2_ACL extern struct svc_version nfsd_acl_version2; @@ -147,8 +64,6 @@ extern struct svc_version nfsd_acl_version3; #else #define nfsd_acl_version3 NULL #endif -struct posix_acl *nfsd_get_posix_acl(struct svc_fh *, int); -int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *); #endif enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; -- cgit v1.2.3-18-g5258 From 78c210efdefe07131f91ed512a3308b15bb14e2f Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 6 Aug 2009 15:41:34 -0400 Subject: Revert "knfsd: avoid overloading the CPU scheduler with enormous load averages" This reverts commit 59a252ff8c0f2fa32c896f69d56ae33e641ce7ad. This helps in an entirely cached workload but not necessarily in workloads that require waiting on disk. Conflicts: include/linux/sunrpc/svc.h net/sunrpc/svc_xprt.c Reported-by: Simon Kirby Tested-by: Jesper Krogh Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 3 --- net/sunrpc/svc_xprt.c | 31 +++++++++---------------------- 2 files changed, 9 insertions(+), 25 deletions(-) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 52e8cb0a756..d1567d62755 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -29,7 +29,6 @@ struct svc_pool_stats { unsigned long packets; unsigned long sockets_queued; unsigned long threads_woken; - unsigned long overloads_avoided; unsigned long threads_timedout; }; @@ -50,7 +49,6 @@ struct svc_pool { struct list_head sp_sockets; /* pending sockets */ unsigned int sp_nrthreads; /* # of threads in pool */ struct list_head sp_all_threads; /* all server threads */ - int sp_nwaking; /* number of threads woken but not yet active */ struct svc_pool_stats sp_stats; /* statistics on pool operation */ } ____cacheline_aligned_in_smp; @@ -284,7 +282,6 @@ struct svc_rqst { * cache pages */ wait_queue_head_t rq_wait; /* synchronization */ struct task_struct *rq_task; /* service thread */ - int rq_waking; /* 1 if thread is being woken */ }; /* diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index df124f78ee4..2c58b75a236 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -16,8 +16,6 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT -#define SVC_MAX_WAKING 5 - static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); @@ -306,7 +304,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) struct svc_pool *pool; struct svc_rqst *rqstp; int cpu; - int thread_avail; if (!(xprt->xpt_flags & ((1<sp_lock); + if (!list_empty(&pool->sp_threads) && + !list_empty(&pool->sp_sockets)) + printk(KERN_ERR + "svc_xprt_enqueue: " + "threads and transports both waiting??\n"); + if (test_bit(XPT_DEAD, &xprt->xpt_flags)) { /* Don't enqueue dead transports */ dprintk("svc: transport %p is dead, not enqueued\n", xprt); @@ -358,15 +361,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) } process: - /* Work out whether threads are available */ - thread_avail = !list_empty(&pool->sp_threads); /* threads are asleep */ - if (pool->sp_nwaking >= SVC_MAX_WAKING) { - /* too many threads are runnable and trying to wake up */ - thread_avail = 0; - pool->sp_stats.overloads_avoided++; - } - - if (thread_avail) { + if (!list_empty(&pool->sp_threads)) { rqstp = list_entry(pool->sp_threads.next, struct svc_rqst, rq_list); @@ -381,8 +376,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) svc_xprt_get(xprt); rqstp->rq_reserved = serv->sv_max_mesg; atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); - rqstp->rq_waking = 1; - pool->sp_nwaking++; pool->sp_stats.threads_woken++; BUG_ON(xprt->xpt_pool != pool); wake_up(&rqstp->rq_wait); @@ -651,11 +644,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) return -EINTR; spin_lock_bh(&pool->sp_lock); - if (rqstp->rq_waking) { - rqstp->rq_waking = 0; - pool->sp_nwaking--; - BUG_ON(pool->sp_nwaking < 0); - } xprt = svc_xprt_dequeue(pool); if (xprt) { rqstp->rq_xprt = xprt; @@ -1204,16 +1192,15 @@ static int svc_pool_stats_show(struct seq_file *m, void *p) struct svc_pool *pool = p; if (p == SEQ_START_TOKEN) { - seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken overloads-avoided threads-timedout\n"); + seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken threads-timedout\n"); return 0; } - seq_printf(m, "%u %lu %lu %lu %lu %lu\n", + seq_printf(m, "%u %lu %lu %lu %lu\n", pool->sp_id, pool->sp_stats.packets, pool->sp_stats.sockets_queued, pool->sp_stats.threads_woken, - pool->sp_stats.overloads_avoided, pool->sp_stats.threads_timedout); return 0; -- cgit v1.2.3-18-g5258 From 864f0f61f829bac5f150a903aad9619322a25424 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Wed, 25 Nov 2009 17:42:05 -0500 Subject: nfsd: simplify fh_verify access checks All nfsd security depends on the security checks in fh_verify, and especially on nfsd_setuser(). It therefore bothers me that the nfsd_setuser call may be made from three different places, depending on whether the filehandle has already been mapped to a dentry, and on whether subtreechecking is in force. Instead, make an unconditional call in fh_verify(), so it's trivial to verify that the call always occurs. That leaves us with a redundant nfsd_setuser() call in the subtreecheck case--it needs the correct user set earlier in order to check execute permissions on the path to this filehandle--but I'm willing to accept that minor inefficiency in the subtreecheck case in return for more straightforward permission checking. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfsfh.c | 50 +++++++++++++++++++++----------------------------- 1 file changed, 21 insertions(+), 29 deletions(-) diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index d0d8a217a3e..a77efb8c224 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -233,14 +233,6 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) goto out; } - if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) { - error = nfsd_setuser_and_check_port(rqstp, exp); - if (error) { - dput(dentry); - goto out; - } - } - if (S_ISDIR(dentry->d_inode->i_mode) && (dentry->d_flags & DCACHE_DISCONNECTED)) { printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %s/%s\n", @@ -295,28 +287,28 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) error = nfsd_set_fh_dentry(rqstp, fhp); if (error) goto out; - dentry = fhp->fh_dentry; - exp = fhp->fh_export; - } else { - /* - * just rechecking permissions - * (e.g. nfsproc_create calls fh_verify, then nfsd_create - * does as well) - */ - dprintk("nfsd: fh_verify - just checking\n"); - dentry = fhp->fh_dentry; - exp = fhp->fh_export; - /* - * Set user creds for this exportpoint; necessary even - * in the "just checking" case because this may be a - * filehandle that was created by fh_compose, and that - * is about to be used in another nfsv4 compound - * operation. - */ - error = nfsd_setuser_and_check_port(rqstp, exp); - if (error) - goto out; } + dentry = fhp->fh_dentry; + exp = fhp->fh_export; + /* + * We still have to do all these permission checks, even when + * fh_dentry is already set: + * - fh_verify may be called multiple times with different + * "access" arguments (e.g. nfsd_proc_create calls + * fh_verify(...,NFSD_MAY_EXEC) first, then later (in + * nfsd_create) calls fh_verify(...,NFSD_MAY_CREATE). + * - in the NFSv4 case, the filehandle may have been filled + * in by fh_compose, and given a dentry, but further + * compound operations performed with that filehandle + * still need permissions checks. In the worst case, a + * mountpoint crossing may have changed the export + * options, and we may now need to use a different uid + * (for example, if different id-squashing options are in + * effect on the new filesystem). + */ + error = nfsd_setuser_and_check_port(rqstp, exp); + if (error) + goto out; error = nfsd_mode_check(rqstp, dentry->d_inode->i_mode, type); if (error) -- cgit v1.2.3-18-g5258 From 57ecb34febc4c133ca0ccc7817796605a78a01d3 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 1 Dec 2009 19:42:57 -0500 Subject: nfsd4: fix share mode permissions NFSv4 opens may function as locks denying other NFSv4 users the rights to open a file. We're requiring a user to have write permissions before they can deny write. We're *not* requiring a user to have write permissions to deny read, which is if anything a more drastic denial. What was intended was to require write permissions for DENY_READ. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 60a93cdefef..a468224a118 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -171,7 +171,7 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs accmode |= NFSD_MAY_READ; if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) accmode |= (NFSD_MAY_WRITE | NFSD_MAY_TRUNC); - if (open->op_share_deny & NFS4_SHARE_DENY_WRITE) + if (open->op_share_deny & NFS4_SHARE_DENY_READ) accmode |= NFSD_MAY_WRITE; status = fh_verify(rqstp, current_fh, S_IFREG, accmode); -- cgit v1.2.3-18-g5258 From 4056c9a344d60ee96471a5f3b0a3c8a90371c8fd Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:28:04 +0200 Subject: nfsd: Remove unused dprintk This doesn't appear to be useful. Signed-off-by: Boaz Harrosh Signed-off-by: J. Bruce Fields --- include/linux/nfsd/nfsfh.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index 8f641c90845..2973e113534 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -20,7 +20,6 @@ # include #endif #include -#include /* * This is the old "dentry style" Linux NFSv2 file handle. @@ -329,9 +328,6 @@ fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) struct dentry *dentry = fhp->fh_dentry; struct inode *inode; - dfprintk(FILEOP, "nfsd: fh_lock(%s) locked = %d\n", - SVCFH_fmt(fhp), fhp->fh_locked); - BUG_ON(!dentry); if (fhp->fh_locked) { -- cgit v1.2.3-18-g5258 From a600ffcbb3743cf1296bee2a41d4824c719d7181 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:28:35 +0200 Subject: sunrpc: Clean never used include files Remove include of two headers never used by this file. Doing so exposed a missing #include in include/linux/sunrpc/rpc_rdma.h. I did not see any other users dependency but if exist they should be fixed since these headers are totally irrelevant to here. Signed-off-by: Boaz Harrosh Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/debug.h | 3 --- include/linux/sunrpc/rpc_rdma.h | 2 ++ 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h index 10709cbe96f..c2786f20016 100644 --- a/include/linux/sunrpc/debug.h +++ b/include/linux/sunrpc/debug.h @@ -28,9 +28,6 @@ #ifdef __KERNEL__ -#include -#include - /* * Enable RPC debugging/profiling. */ diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index 87b895d5c78..b78f16b1dea 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -40,6 +40,8 @@ #ifndef _LINUX_SUNRPC_RPC_RDMA_H #define _LINUX_SUNRPC_RPC_RDMA_H +#include + struct rpcrdma_segment { __be32 rs_handle; /* Registered memory handle */ __be32 rs_length; /* Length of the chunk in bytes */ -- cgit v1.2.3-18-g5258 From d703158229329af7152d159753f849aa7bd55ee6 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:28:47 +0200 Subject: nfsd: Fix independence of a few nfsd related headers An header should be compilation independent, .i.e pull in any header who's declarations are directly used by this header. And not let users re-include all it's dependencies all over again. [At the end of the day what's the use of a header if it does not have more then one user?] Signed-off-by: Boaz Harrosh Signed-off-by: J. Bruce Fields --- include/linux/nfs_xdr.h | 1 + include/linux/nfsacl.h | 1 + 2 files changed, 2 insertions(+) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 62f63fb0c4c..00a0c817081 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -2,6 +2,7 @@ #define _LINUX_NFS_XDR_H #include +#include /* * To change the maximum rsize and wsize supported by the NFS client, adjust diff --git a/include/linux/nfsacl.h b/include/linux/nfsacl.h index 43011b69297..f321b578ede 100644 --- a/include/linux/nfsacl.h +++ b/include/linux/nfsacl.h @@ -29,6 +29,7 @@ #ifdef __KERNEL__ #include +#include /* Maximum number of ACL entries over NFS */ #define NFS_ACL_MAX_ENTRIES 1024 -- cgit v1.2.3-18-g5258 From 72579ac9cd68081108277c31781b127d0f420d61 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:28:59 +0200 Subject: nfsd: Headers Independence and include cleanups * Add includes that are directly used by headers * Remove includes that are not needed These are the changes made: [xdr.h] struct nfsd_readdirres has an embedded struct readdir_cd from nfsd.h fixing that we can drop other includes [xdr4.h] embedded types defined both at state.h and nfsd.h [syscall.h] After export.h fix none of these stuff is needed. fix extra space in # include <> statement [stats.h] does not need but was export to user-mode so I don't touch it [state.h] embedded types from nfsfh.h like struct knfsd_fh. bringing that eliminates the need for all other includes [nfsfh.h] directly manipulating types from sunrpc/svc.h. Removed Other unused headers. [nfsd.h] removed unused headers include [export.h] lots of sunrpc/svc.h types and a single prototype declaration with pointer from nfsfh.h, but all users of export.h do need nfsfh.h any way. remove now un-needed include. [const.h] Unfixed (not independent) [cache.h] could do with a forward declaration of "struct svc_rqst;" from sunrpc/svc.h but all users absolutely will need sunrpc/svc.h it is easier overall this way. Signed-off-by: Boaz Harrosh Signed-off-by: J. Bruce Fields --- include/linux/nfsd/cache.h | 3 +-- include/linux/nfsd/export.h | 2 +- include/linux/nfsd/nfsd.h | 4 ---- include/linux/nfsd/nfsfh.h | 3 +-- include/linux/nfsd/state.h | 4 +--- include/linux/nfsd/syscall.h | 8 +------- include/linux/nfsd/xdr.h | 3 +-- include/linux/nfsd/xdr4.h | 3 ++- 8 files changed, 8 insertions(+), 22 deletions(-) diff --git a/include/linux/nfsd/cache.h b/include/linux/nfsd/cache.h index 3a3f58934f5..a165425dea4 100644 --- a/include/linux/nfsd/cache.h +++ b/include/linux/nfsd/cache.h @@ -10,8 +10,7 @@ #ifndef NFSCACHE_H #define NFSCACHE_H -#include -#include +#include /* * Representation of a reply cache entry. diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index a6d9ef2bb34..ef3d416fcf6 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -12,7 +12,7 @@ # include #ifdef __KERNEL__ -# include +# include #endif /* diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index e4518d090a8..74f67c2aca3 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -11,13 +11,9 @@ #define LINUX_NFSD_NFSD_H #include -#include -#include -#include #include #include -#include #include #include /* diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index 2973e113534..49523edbc51 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -16,8 +16,7 @@ # include #ifdef __KERNEL__ -# include -# include +# include #endif #include diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 5aadf8aa3a9..2af75686e0d 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -37,9 +37,7 @@ #ifndef _NFSD4_STATE_H #define _NFSD4_STATE_H -#include -#include -#include +#include typedef struct { u32 cl_boot; diff --git a/include/linux/nfsd/syscall.h b/include/linux/nfsd/syscall.h index 7a3b565b898..812bc1e160d 100644 --- a/include/linux/nfsd/syscall.h +++ b/include/linux/nfsd/syscall.h @@ -9,14 +9,8 @@ #ifndef NFSD_SYSCALL_H #define NFSD_SYSCALL_H -# include -#ifdef __KERNEL__ -# include -#endif -#include -#include +#include #include -#include /* * Version of the syscall interface diff --git a/include/linux/nfsd/xdr.h b/include/linux/nfsd/xdr.h index a0132ef58f2..58f824d854c 100644 --- a/include/linux/nfsd/xdr.h +++ b/include/linux/nfsd/xdr.h @@ -7,9 +7,8 @@ #ifndef LINUX_NFSD_H #define LINUX_NFSD_H -#include #include -#include +#include struct nfsd_fhandle { struct svc_fh fh; diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 73164c2b3d2..1bf266239c7 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -39,7 +39,8 @@ #ifndef _LINUX_NFSD_XDR4_H #define _LINUX_NFSD_XDR4_H -#include +#include +#include #define NFSD4_MAX_TAGLEN 128 #define XDR_LEN(n) (((n) + 3) & ~3) -- cgit v1.2.3-18-g5258 From 341eb184469f8e4a6841fc49a57ad4a27e51c335 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:29:12 +0200 Subject: nfsd: Source files #include cleanups Now that the headers are fixed and carry their own wait, all fs/nfsd/ source files can include a minimal set of headers. and still compile just fine. This patch should improve the compilation speed of the nfsd module. Signed-off-by: Boaz Harrosh Signed-off-by: J. Bruce Fields --- fs/nfsd/auth.c | 4 ---- fs/nfsd/export.c | 15 --------------- fs/nfsd/lockd.c | 5 ----- fs/nfsd/nfs2acl.c | 4 ---- fs/nfsd/nfs3acl.c | 3 --- fs/nfsd/nfs3proc.c | 13 ------------- fs/nfsd/nfs3xdr.c | 11 ----------- fs/nfsd/nfs4acl.c | 8 -------- fs/nfsd/nfs4callback.c | 13 ------------- fs/nfsd/nfs4idmap.c | 15 +-------------- fs/nfsd/nfs4proc.c | 10 ---------- fs/nfsd/nfs4recover.c | 8 -------- fs/nfsd/nfs4state.c | 15 --------------- fs/nfsd/nfs4xdr.c | 12 +----------- fs/nfsd/nfscache.c | 8 -------- fs/nfsd/nfsctl.c | 25 ------------------------- fs/nfsd/nfsfh.c | 9 --------- fs/nfsd/nfsproc.c | 13 ------------- fs/nfsd/nfssvc.c | 15 --------------- fs/nfsd/nfsxdr.c | 8 -------- fs/nfsd/stats.c | 5 ----- fs/nfsd/vfs.c | 20 -------------------- 22 files changed, 2 insertions(+), 237 deletions(-) diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 36fcabbf518..ad354d284cf 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -4,12 +4,8 @@ * Copyright (C) 1995, 1996 Olaf Kirch */ -#include #include -#include -#include #include -#include #include "auth.h" int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp) diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index b73baba3fb9..68e63f44144 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -14,27 +14,12 @@ * Copyright (C) 1995, 1996 Olaf Kirch, */ -#include -#include -#include -#include -#include -#include -#include -#include #include -#include -#include #include #include -#include #include -#include #include -#include -#include -#include #include #define NFSDDBG_FACILITY NFSDDBG_EXPORT diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 812bc64874f..801ef7104ff 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -8,12 +8,7 @@ * Copyright (C) 1996, Olaf Kirch */ -#include -#include #include -#include -#include -#include #include #include #include "vfs.h" diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 38c883d48b0..a54628de771 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -6,13 +6,9 @@ * Copyright (C) 2002-2003 Andreas Gruenbacher */ -#include -#include #include #include -#include #include -#include #include #include "vfs.h" diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 526d85a65f7..2f5c61bea90 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -6,12 +6,9 @@ * Copyright (C) 2002-2003 Andreas Gruenbacher */ -#include -#include #include #include #include -#include #include #include "vfs.h" diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 1a259d313e1..b694b430454 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -6,25 +6,12 @@ * Copyright (C) 1996, 1997, 1998 Olaf Kirch */ -#include -#include -#include #include #include -#include -#include -#include -#include -#include -#include -#include #include -#include -#include #include #include -#include #include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index d0a2ce1b432..623e13aa625 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -8,18 +8,7 @@ * 2003-08-09 Jamie Lokier: Use htonl() for nanoseconds, not htons()! */ -#include -#include -#include -#include -#include -#include #include -#include -#include -#include -#include -#include #include #include "auth.h" diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index 6d9c6aabc85..d6f0cea4bab 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -36,15 +36,7 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -#include -#include -#include -#include -#include -#include #include -#include -#include #include diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 24e8d78f8dd..4fe396071b6 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -33,22 +33,9 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -#include -#include -#include -#include -#include -#include -#include -#include -#include #include -#include #include #include -#include -#include -#include #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index ba2c199592f..8e518cd5ac1 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -35,22 +35,9 @@ */ #include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include #include -#include -#include #include -#include +#include /* * Cache entry diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a468224a118..61f682c77e7 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -34,20 +34,10 @@ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ - -#include -#include -#include #include -#include -#include #include -#include -#include #include -#include -#include #include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index c7a6b245c7a..48742f243c2 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -33,20 +33,12 @@ * */ -#include -#include #include -#include #include -#include -#include #include #include -#include -#include #include #include -#include #include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 850960e5d62..1fe6e29fd50 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -34,26 +34,11 @@ * */ -#include -#include -#include - -#include -#include -#include #include -#include -#include #include -#include -#include -#include #include #include #include -#include -#include -#include #include #include #include "vfs.h" diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index db0fc55670b..2fa96821f5b 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -40,22 +40,12 @@ * at the end of nfs4svc_decode_compoundargs. */ -#include -#include -#include #include -#include +#include #include -#include -#include -#include -#include -#include #include #include -#include #include -#include #include #include "vfs.h" diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 4638635c5d8..96694b8345e 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -10,14 +10,6 @@ * Copyright (C) 1995, 1996 Olaf Kirch */ -#include -#include -#include -#include -#include -#include - -#include #include #include diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 5c01fc148ce..e4f49fd6af4 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -6,42 +6,17 @@ * Copyright (C) 1995, 1996 Olaf Kirch */ -#include - -#include -#include -#include -#include #include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include #include -#include #include -#include -#include #include #include #include -#include #include #include #include -#include -#include - /* * We have a single directory with 9 nodes in it. */ diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index a77efb8c224..73994816503 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -9,17 +9,8 @@ * ... and again Southern-Winter 2001 to support export_operations */ -#include -#include -#include -#include -#include -#include #include -#include -#include -#include #include #include #include "vfs.h" diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 6c967e1ba37..b6bd9e0d7cd 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -7,21 +7,8 @@ * Copyright (C) 1995-1997 Olaf Kirch */ -#include -#include -#include -#include -#include -#include -#include -#include #include -#include -#include -#include -#include -#include #include #include #include "vfs.h" diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 2944b31dcbe..b2d7ffac035 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -8,30 +8,15 @@ * Copyright (C) 1995, 1996, 1997 Olaf Kirch */ -#include #include -#include -#include -#include -#include -#include -#include -#include -#include #include #include -#include #include -#include #include -#include #include -#include #include -#include #include -#include #include #include #include diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index afd08e2c90a..5e0603da39e 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -6,15 +6,7 @@ * Copyright (C) 1995, 1996 Olaf Kirch */ -#include -#include -#include -#include -#include -#include -#include #include -#include #include "auth.h" #define NFSDDBG_FACILITY NFSDDBG_XDR diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 71944cddf68..e3e411e9fe4 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -23,14 +23,9 @@ * Copyright (C) 1995, 1996, 1997 Olaf Kirch */ -#include -#include -#include #include -#include #include -#include #include #include #include diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index a7038ede671..81ce108c114 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -16,43 +16,23 @@ * Zerocpy NFS support (C) 2002 Hirokazu Takahashi */ -#include -#include -#include #include #include -#include -#include #include -#include -#include #include -#include -#include -#include -#include -#include -#include #include -#include #include -#include #include #ifdef CONFIG_NFSD_V3 -#include #include #endif /* CONFIG_NFSD_V3 */ -#include #include #include -#include #include #include #ifdef CONFIG_NFSD_V4 -#include #include #include -#include #endif /* CONFIG_NFSD_V4 */ #include #include -- cgit v1.2.3-18-g5258 From 370d560017c9c269a1351ba19e91b206bd5816c8 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:29:27 +0200 Subject: compat.c: Remove dependence on nfsd private headers Two nfsd related headers where included but never actually used. The linux/nfsd/nfsd.h file will eventually be moved to fs/nfsd directory as it is only needed by nfsd itself. There are 3 more compat.c files in the Kernel at other ARCHs that wrongly #include nfsd headers. Once these are fixed the headers can be moved. Signed-off-by: Boaz Harrosh Signed-off-by: J. Bruce Fields --- fs/compat.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/compat.c b/fs/compat.c index 6c19040ffee..00d90c2e66f 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -38,8 +38,6 @@ #include #include #include -#include -#include #include #include #include -- cgit v1.2.3-18-g5258 From ec346449eb75474df27db945377c7a5b56b7c8cc Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:29:39 +0200 Subject: parsic: remove un-used nfsd #includes Some un-used includes removed. This patch is in an effort to cleanup nfsd headers and move private definitions to source directory. Signed-off-by: Boaz Harrosh Tested-by: Grant Grundler Acked-by: Helge Deller Signed-off-by: J. Bruce Fields --- arch/parisc/kernel/sys_parisc32.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index 561388b17c9..4a8ca634dcc 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -26,13 +26,7 @@ #include #include #include -#include #include -#include -#include -#include -#include -#include #include #include #include -- cgit v1.2.3-18-g5258 From 40ede4a8cf8af6faac23462ba1b48bc4d074f0bb Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:29:54 +0200 Subject: sparc: remove un-used nfsd #includes Some un-used includes removed. In an effort to cleanup nfsd headers and move private definitions to source directory. Signed-off-by: Boaz Harrosh Signed-off-by: J. Bruce Fields --- arch/sparc/kernel/sys_sparc32.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index 04e28b2671c..0a68fdf3e87 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -26,11 +26,6 @@ #include #include #include -#include -#include -#include -#include -#include #include #include #include -- cgit v1.2.3-18-g5258 From 399643f25eb93374e27e06ec85f0e8958298af2e Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:30:05 +0200 Subject: s390: remove un-used nfsd #includes Some un-used includes removed. This patch is in an effort to cleanup nfsd headers and move private definitions to source directory. Signed-off-by: Boaz Harrosh Signed-off-by: J. Bruce Fields --- arch/s390/kernel/compat_linux.c | 6 ------ arch/s390/kernel/compat_linux.h | 4 ---- 2 files changed, 10 deletions(-) diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 0debcec23a3..29a2f34b955 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -31,14 +31,8 @@ #include #include #include -#include #include #include -#include -#include -#include -#include -#include #include #include #include diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index c07f9ca05ad..81d6ee826ff 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -4,10 +4,6 @@ #include #include #include -#include -#include -#include -#include /* Macro that masks the high order bit of an 32 bit pointer and converts it*/ /* to a 64 bit pointer */ -- cgit v1.2.3-18-g5258 From 0296f55f98368219af772f54d3bf18a9ad859399 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:30:27 +0200 Subject: lockd: Remove un-used nfsd headers #includes In what history where these ever needed? Well not any more. Signed-off-by: Boaz Harrosh Signed-off-by: J. Bruce Fields --- fs/lockd/svc4proc.c | 4 ---- fs/lockd/svcproc.c | 4 ---- 2 files changed, 8 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index bd173a6ca3b..a7966eed3c1 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -11,10 +11,6 @@ #include #include #include -#include -#include -#include -#include #include #include diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index e1d28ddd216..56c9519d900 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -11,10 +11,6 @@ #include #include #include -#include -#include -#include -#include #include #include -- cgit v1.2.3-18-g5258 From 68590c382b875cc9a76b06097f3dff6730d787c1 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:30:43 +0200 Subject: vfs: nfsctl.c un-used nfsd #includes Only linux/nfsd/syscall.h is actually used. Remove the other nfsd #includes, so they can be moved to source directory. Signed-off-by: Boaz Harrosh Signed-off-by: J. Bruce Fields --- fs/nfsctl.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/nfsctl.c b/fs/nfsctl.c index 8f9a20556f7..d3854d94b7c 100644 --- a/fs/nfsctl.c +++ b/fs/nfsctl.c @@ -7,8 +7,6 @@ #include #include #include -#include -#include #include #include #include -- cgit v1.2.3-18-g5258 From 9a74af21330c8d46efa977d088a62cc1bfa954e9 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 3 Dec 2009 20:30:56 +0200 Subject: nfsd: Move private headers to source directory Lots of include/linux/nfsd/* headers are only used by nfsd module. Move them to the source directory Signed-off-by: Boaz Harrosh Signed-off-by: J. Bruce Fields --- fs/nfsd/auth.c | 2 +- fs/nfsd/cache.h | 85 +++++++ fs/nfsd/export.c | 3 +- fs/nfsd/lockd.c | 2 +- fs/nfsd/nfs2acl.c | 7 +- fs/nfsd/nfs3acl.c | 7 +- fs/nfsd/nfs3proc.c | 4 +- fs/nfsd/nfs3xdr.c | 2 +- fs/nfsd/nfs4callback.c | 4 +- fs/nfsd/nfs4proc.c | 4 +- fs/nfsd/nfs4recover.c | 5 +- fs/nfsd/nfs4state.c | 2 +- fs/nfsd/nfs4xdr.c | 3 +- fs/nfsd/nfscache.c | 4 +- fs/nfsd/nfsctl.c | 5 +- fs/nfsd/nfsd.h | 335 +++++++++++++++++++++++++++ fs/nfsd/nfsfh.c | 2 +- fs/nfsd/nfsproc.c | 4 +- fs/nfsd/nfssvc.c | 4 +- fs/nfsd/nfsxdr.c | 2 +- fs/nfsd/state.h | 409 ++++++++++++++++++++++++++++++++ fs/nfsd/stats.c | 4 +- fs/nfsd/vfs.c | 18 +- fs/nfsd/xdr.h | 176 ++++++++++++++ fs/nfsd/xdr3.h | 346 +++++++++++++++++++++++++++ fs/nfsd/xdr4.h | 564 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfsd/cache.h | 85 ------- include/linux/nfsd/nfsd.h | 335 --------------------------- include/linux/nfsd/state.h | 409 -------------------------------- include/linux/nfsd/xdr.h | 176 -------------- include/linux/nfsd/xdr3.h | 346 --------------------------- include/linux/nfsd/xdr4.h | 564 --------------------------------------------- 32 files changed, 1963 insertions(+), 1955 deletions(-) create mode 100644 fs/nfsd/cache.h create mode 100644 fs/nfsd/nfsd.h create mode 100644 fs/nfsd/state.h create mode 100644 fs/nfsd/xdr.h create mode 100644 fs/nfsd/xdr3.h create mode 100644 fs/nfsd/xdr4.h delete mode 100644 include/linux/nfsd/cache.h delete mode 100644 include/linux/nfsd/nfsd.h delete mode 100644 include/linux/nfsd/state.h delete mode 100644 include/linux/nfsd/xdr.h delete mode 100644 include/linux/nfsd/xdr3.h delete mode 100644 include/linux/nfsd/xdr4.h diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index ad354d284cf..71209d4993d 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -5,7 +5,7 @@ */ #include -#include +#include "nfsd.h" #include "auth.h" int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp) diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h new file mode 100644 index 00000000000..a165425dea4 --- /dev/null +++ b/fs/nfsd/cache.h @@ -0,0 +1,85 @@ +/* + * include/linux/nfsd/cache.h + * + * Request reply cache. This was heavily inspired by the + * implementation in 4.3BSD/4.4BSD. + * + * Copyright (C) 1995, 1996 Olaf Kirch + */ + +#ifndef NFSCACHE_H +#define NFSCACHE_H + +#include + +/* + * Representation of a reply cache entry. + */ +struct svc_cacherep { + struct hlist_node c_hash; + struct list_head c_lru; + + unsigned char c_state, /* unused, inprog, done */ + c_type, /* status, buffer */ + c_secure : 1; /* req came from port < 1024 */ + struct sockaddr_in c_addr; + __be32 c_xid; + u32 c_prot; + u32 c_proc; + u32 c_vers; + unsigned long c_timestamp; + union { + struct kvec u_vec; + __be32 u_status; + } c_u; +}; + +#define c_replvec c_u.u_vec +#define c_replstat c_u.u_status + +/* cache entry states */ +enum { + RC_UNUSED, + RC_INPROG, + RC_DONE +}; + +/* return values */ +enum { + RC_DROPIT, + RC_REPLY, + RC_DOIT, + RC_INTR +}; + +/* + * Cache types. + * We may want to add more types one day, e.g. for diropres and + * attrstat replies. Using cache entries with fixed length instead + * of buffer pointers may be more efficient. + */ +enum { + RC_NOCACHE, + RC_REPLSTAT, + RC_REPLBUFF, +}; + +/* + * If requests are retransmitted within this interval, they're dropped. + */ +#define RC_DELAY (HZ/5) + +int nfsd_reply_cache_init(void); +void nfsd_reply_cache_shutdown(void); +int nfsd_cache_lookup(struct svc_rqst *, int); +void nfsd_cache_update(struct svc_rqst *, int, __be32 *); + +#ifdef CONFIG_NFSD_V4 +void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp); +#else /* CONFIG_NFSD_V4 */ +static inline void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp) +{ +} +#endif /* CONFIG_NFSD_V4 */ + +#endif /* NFSCACHE_H */ diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 68e63f44144..cb3dae2fcd8 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -18,10 +18,11 @@ #include #include -#include #include #include +#include "nfsd.h" + #define NFSDDBG_FACILITY NFSDDBG_EXPORT typedef struct auth_domain svc_client; diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 801ef7104ff..6f12777ed22 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -9,8 +9,8 @@ */ #include -#include #include +#include "nfsd.h" #include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_LOCKD diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index a54628de771..874e2a94bf4 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -6,10 +6,11 @@ * Copyright (C) 2002-2003 Andreas Gruenbacher */ -#include -#include -#include +#include "nfsd.h" +/* FIXME: nfsacl.h is a broken header */ #include +#include "cache.h" +#include "xdr3.h" #include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 2f5c61bea90..c6011ddbadc 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -6,10 +6,11 @@ * Copyright (C) 2002-2003 Andreas Gruenbacher */ -#include -#include -#include +#include "nfsd.h" +/* FIXME: nfsacl.h is a broken header */ #include +#include "cache.h" +#include "xdr3.h" #include "vfs.h" #define RETURN_STATUS(st) { resp->status = (st); return (st); } diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index b694b430454..90b19ca75b3 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -10,8 +10,8 @@ #include #include -#include -#include +#include "cache.h" +#include "xdr3.h" #include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 623e13aa625..c523bb88c10 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -9,7 +9,7 @@ */ #include -#include +#include "xdr3.h" #include "auth.h" #define NFSDDBG_FACILITY NFSDDBG_XDR diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 4fe396071b6..f7a31582763 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -34,8 +34,8 @@ */ #include -#include -#include +#include "nfsd.h" +#include "state.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 61f682c77e7..e2b5666f25d 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -36,8 +36,8 @@ */ #include -#include -#include +#include "cache.h" +#include "xdr4.h" #include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 48742f243c2..6744e7f2da0 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -33,12 +33,13 @@ * */ -#include -#include #include #include #include #include + +#include "nfsd.h" +#include "state.h" #include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 1fe6e29fd50..2923e6c1da1 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -36,11 +36,11 @@ #include #include -#include #include #include #include #include +#include "xdr4.h" #include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 2fa96821f5b..cab97803110 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -43,10 +43,11 @@ #include #include #include -#include #include #include #include + +#include "xdr4.h" #include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_XDR diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 96694b8345e..18aa9729a38 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -10,8 +10,8 @@ * Copyright (C) 1995, 1996 Olaf Kirch */ -#include -#include +#include "nfsd.h" +#include "cache.h" /* Size of reply cache. Common values are: * 4.3BSD: 128 diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index e4f49fd6af4..0415680d3f5 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -11,12 +11,13 @@ #include #include -#include -#include #include #include #include +#include "nfsd.h" +#include "cache.h" + /* * We have a single directory with 9 nodes in it. */ diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h new file mode 100644 index 00000000000..74f67c2aca3 --- /dev/null +++ b/fs/nfsd/nfsd.h @@ -0,0 +1,335 @@ +/* + * linux/include/linux/nfsd/nfsd.h + * + * Hodge-podge collection of knfsd-related stuff. + * I will sort this out later. + * + * Copyright (C) 1995-1997 Olaf Kirch + */ + +#ifndef LINUX_NFSD_NFSD_H +#define LINUX_NFSD_NFSD_H + +#include +#include + +#include +#include +#include +/* + * nfsd version + */ +#define NFSD_SUPPORTED_MINOR_VERSION 1 + +struct readdir_cd { + __be32 err; /* 0, nfserr, or nfserr_eof */ +}; + + +extern struct svc_program nfsd_program; +extern struct svc_version nfsd_version2, nfsd_version3, + nfsd_version4; +extern u32 nfsd_supported_minorversion; +extern struct mutex nfsd_mutex; +extern struct svc_serv *nfsd_serv; +extern spinlock_t nfsd_drc_lock; +extern unsigned int nfsd_drc_max_mem; +extern unsigned int nfsd_drc_mem_used; + +extern const struct seq_operations nfs_exports_op; + +/* + * Function prototypes. + */ +int nfsd_svc(unsigned short port, int nrservs); +int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp); + +int nfsd_nrthreads(void); +int nfsd_nrpools(void); +int nfsd_get_nrthreads(int n, int *); +int nfsd_set_nrthreads(int n, int *); + +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) +#ifdef CONFIG_NFSD_V2_ACL +extern struct svc_version nfsd_acl_version2; +#else +#define nfsd_acl_version2 NULL +#endif +#ifdef CONFIG_NFSD_V3_ACL +extern struct svc_version nfsd_acl_version3; +#else +#define nfsd_acl_version3 NULL +#endif +#endif + +enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; +int nfsd_vers(int vers, enum vers_op change); +int nfsd_minorversion(u32 minorversion, enum vers_op change); +void nfsd_reset_versions(void); +int nfsd_create_serv(void); + +extern int nfsd_max_blksize; + +/* + * NFSv4 State + */ +#ifdef CONFIG_NFSD_V4 +extern unsigned int max_delegations; +int nfs4_state_init(void); +void nfsd4_free_slabs(void); +int nfs4_state_start(void); +void nfs4_state_shutdown(void); +time_t nfs4_lease_time(void); +void nfs4_reset_lease(time_t leasetime); +int nfs4_reset_recoverydir(char *recdir); +#else +static inline int nfs4_state_init(void) { return 0; } +static inline void nfsd4_free_slabs(void) { } +static inline int nfs4_state_start(void) { return 0; } +static inline void nfs4_state_shutdown(void) { } +static inline time_t nfs4_lease_time(void) { return 0; } +static inline void nfs4_reset_lease(time_t leasetime) { } +static inline int nfs4_reset_recoverydir(char *recdir) { return 0; } +#endif + +/* + * lockd binding + */ +void nfsd_lockd_init(void); +void nfsd_lockd_shutdown(void); + + +/* + * These macros provide pre-xdr'ed values for faster operation. + */ +#define nfs_ok cpu_to_be32(NFS_OK) +#define nfserr_perm cpu_to_be32(NFSERR_PERM) +#define nfserr_noent cpu_to_be32(NFSERR_NOENT) +#define nfserr_io cpu_to_be32(NFSERR_IO) +#define nfserr_nxio cpu_to_be32(NFSERR_NXIO) +#define nfserr_eagain cpu_to_be32(NFSERR_EAGAIN) +#define nfserr_acces cpu_to_be32(NFSERR_ACCES) +#define nfserr_exist cpu_to_be32(NFSERR_EXIST) +#define nfserr_xdev cpu_to_be32(NFSERR_XDEV) +#define nfserr_nodev cpu_to_be32(NFSERR_NODEV) +#define nfserr_notdir cpu_to_be32(NFSERR_NOTDIR) +#define nfserr_isdir cpu_to_be32(NFSERR_ISDIR) +#define nfserr_inval cpu_to_be32(NFSERR_INVAL) +#define nfserr_fbig cpu_to_be32(NFSERR_FBIG) +#define nfserr_nospc cpu_to_be32(NFSERR_NOSPC) +#define nfserr_rofs cpu_to_be32(NFSERR_ROFS) +#define nfserr_mlink cpu_to_be32(NFSERR_MLINK) +#define nfserr_opnotsupp cpu_to_be32(NFSERR_OPNOTSUPP) +#define nfserr_nametoolong cpu_to_be32(NFSERR_NAMETOOLONG) +#define nfserr_notempty cpu_to_be32(NFSERR_NOTEMPTY) +#define nfserr_dquot cpu_to_be32(NFSERR_DQUOT) +#define nfserr_stale cpu_to_be32(NFSERR_STALE) +#define nfserr_remote cpu_to_be32(NFSERR_REMOTE) +#define nfserr_wflush cpu_to_be32(NFSERR_WFLUSH) +#define nfserr_badhandle cpu_to_be32(NFSERR_BADHANDLE) +#define nfserr_notsync cpu_to_be32(NFSERR_NOT_SYNC) +#define nfserr_badcookie cpu_to_be32(NFSERR_BAD_COOKIE) +#define nfserr_notsupp cpu_to_be32(NFSERR_NOTSUPP) +#define nfserr_toosmall cpu_to_be32(NFSERR_TOOSMALL) +#define nfserr_serverfault cpu_to_be32(NFSERR_SERVERFAULT) +#define nfserr_badtype cpu_to_be32(NFSERR_BADTYPE) +#define nfserr_jukebox cpu_to_be32(NFSERR_JUKEBOX) +#define nfserr_denied cpu_to_be32(NFSERR_DENIED) +#define nfserr_deadlock cpu_to_be32(NFSERR_DEADLOCK) +#define nfserr_expired cpu_to_be32(NFSERR_EXPIRED) +#define nfserr_bad_cookie cpu_to_be32(NFSERR_BAD_COOKIE) +#define nfserr_same cpu_to_be32(NFSERR_SAME) +#define nfserr_clid_inuse cpu_to_be32(NFSERR_CLID_INUSE) +#define nfserr_stale_clientid cpu_to_be32(NFSERR_STALE_CLIENTID) +#define nfserr_resource cpu_to_be32(NFSERR_RESOURCE) +#define nfserr_moved cpu_to_be32(NFSERR_MOVED) +#define nfserr_nofilehandle cpu_to_be32(NFSERR_NOFILEHANDLE) +#define nfserr_minor_vers_mismatch cpu_to_be32(NFSERR_MINOR_VERS_MISMATCH) +#define nfserr_share_denied cpu_to_be32(NFSERR_SHARE_DENIED) +#define nfserr_stale_stateid cpu_to_be32(NFSERR_STALE_STATEID) +#define nfserr_old_stateid cpu_to_be32(NFSERR_OLD_STATEID) +#define nfserr_bad_stateid cpu_to_be32(NFSERR_BAD_STATEID) +#define nfserr_bad_seqid cpu_to_be32(NFSERR_BAD_SEQID) +#define nfserr_symlink cpu_to_be32(NFSERR_SYMLINK) +#define nfserr_not_same cpu_to_be32(NFSERR_NOT_SAME) +#define nfserr_restorefh cpu_to_be32(NFSERR_RESTOREFH) +#define nfserr_attrnotsupp cpu_to_be32(NFSERR_ATTRNOTSUPP) +#define nfserr_bad_xdr cpu_to_be32(NFSERR_BAD_XDR) +#define nfserr_openmode cpu_to_be32(NFSERR_OPENMODE) +#define nfserr_locks_held cpu_to_be32(NFSERR_LOCKS_HELD) +#define nfserr_op_illegal cpu_to_be32(NFSERR_OP_ILLEGAL) +#define nfserr_grace cpu_to_be32(NFSERR_GRACE) +#define nfserr_no_grace cpu_to_be32(NFSERR_NO_GRACE) +#define nfserr_reclaim_bad cpu_to_be32(NFSERR_RECLAIM_BAD) +#define nfserr_badname cpu_to_be32(NFSERR_BADNAME) +#define nfserr_cb_path_down cpu_to_be32(NFSERR_CB_PATH_DOWN) +#define nfserr_locked cpu_to_be32(NFSERR_LOCKED) +#define nfserr_wrongsec cpu_to_be32(NFSERR_WRONGSEC) +#define nfserr_badiomode cpu_to_be32(NFS4ERR_BADIOMODE) +#define nfserr_badlayout cpu_to_be32(NFS4ERR_BADLAYOUT) +#define nfserr_bad_session_digest cpu_to_be32(NFS4ERR_BAD_SESSION_DIGEST) +#define nfserr_badsession cpu_to_be32(NFS4ERR_BADSESSION) +#define nfserr_badslot cpu_to_be32(NFS4ERR_BADSLOT) +#define nfserr_complete_already cpu_to_be32(NFS4ERR_COMPLETE_ALREADY) +#define nfserr_conn_not_bound_to_session cpu_to_be32(NFS4ERR_CONN_NOT_BOUND_TO_SESSION) +#define nfserr_deleg_already_wanted cpu_to_be32(NFS4ERR_DELEG_ALREADY_WANTED) +#define nfserr_back_chan_busy cpu_to_be32(NFS4ERR_BACK_CHAN_BUSY) +#define nfserr_layouttrylater cpu_to_be32(NFS4ERR_LAYOUTTRYLATER) +#define nfserr_layoutunavailable cpu_to_be32(NFS4ERR_LAYOUTUNAVAILABLE) +#define nfserr_nomatching_layout cpu_to_be32(NFS4ERR_NOMATCHING_LAYOUT) +#define nfserr_recallconflict cpu_to_be32(NFS4ERR_RECALLCONFLICT) +#define nfserr_unknown_layouttype cpu_to_be32(NFS4ERR_UNKNOWN_LAYOUTTYPE) +#define nfserr_seq_misordered cpu_to_be32(NFS4ERR_SEQ_MISORDERED) +#define nfserr_sequence_pos cpu_to_be32(NFS4ERR_SEQUENCE_POS) +#define nfserr_req_too_big cpu_to_be32(NFS4ERR_REQ_TOO_BIG) +#define nfserr_rep_too_big cpu_to_be32(NFS4ERR_REP_TOO_BIG) +#define nfserr_rep_too_big_to_cache cpu_to_be32(NFS4ERR_REP_TOO_BIG_TO_CACHE) +#define nfserr_retry_uncached_rep cpu_to_be32(NFS4ERR_RETRY_UNCACHED_REP) +#define nfserr_unsafe_compound cpu_to_be32(NFS4ERR_UNSAFE_COMPOUND) +#define nfserr_too_many_ops cpu_to_be32(NFS4ERR_TOO_MANY_OPS) +#define nfserr_op_not_in_session cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION) +#define nfserr_hash_alg_unsupp cpu_to_be32(NFS4ERR_HASH_ALG_UNSUPP) +#define nfserr_clientid_busy cpu_to_be32(NFS4ERR_CLIENTID_BUSY) +#define nfserr_pnfs_io_hole cpu_to_be32(NFS4ERR_PNFS_IO_HOLE) +#define nfserr_seq_false_retry cpu_to_be32(NFS4ERR_SEQ_FALSE_RETRY) +#define nfserr_bad_high_slot cpu_to_be32(NFS4ERR_BAD_HIGH_SLOT) +#define nfserr_deadsession cpu_to_be32(NFS4ERR_DEADSESSION) +#define nfserr_encr_alg_unsupp cpu_to_be32(NFS4ERR_ENCR_ALG_UNSUPP) +#define nfserr_pnfs_no_layout cpu_to_be32(NFS4ERR_PNFS_NO_LAYOUT) +#define nfserr_not_only_op cpu_to_be32(NFS4ERR_NOT_ONLY_OP) +#define nfserr_wrong_cred cpu_to_be32(NFS4ERR_WRONG_CRED) +#define nfserr_wrong_type cpu_to_be32(NFS4ERR_WRONG_TYPE) +#define nfserr_dirdeleg_unavail cpu_to_be32(NFS4ERR_DIRDELEG_UNAVAIL) +#define nfserr_reject_deleg cpu_to_be32(NFS4ERR_REJECT_DELEG) +#define nfserr_returnconflict cpu_to_be32(NFS4ERR_RETURNCONFLICT) +#define nfserr_deleg_revoked cpu_to_be32(NFS4ERR_DELEG_REVOKED) + +/* error codes for internal use */ +/* if a request fails due to kmalloc failure, it gets dropped. + * Client should resend eventually + */ +#define nfserr_dropit cpu_to_be32(30000) +/* end-of-file indicator in readdir */ +#define nfserr_eof cpu_to_be32(30001) +/* replay detected */ +#define nfserr_replay_me cpu_to_be32(11001) +/* nfs41 replay detected */ +#define nfserr_replay_cache cpu_to_be32(11002) + +/* Check for dir entries '.' and '..' */ +#define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.')) + +/* + * Time of server startup + */ +extern struct timeval nfssvc_boot; + +#ifdef CONFIG_NFSD_V4 + +/* before processing a COMPOUND operation, we have to check that there + * is enough space in the buffer for XDR encode to succeed. otherwise, + * we might process an operation with side effects, and be unable to + * tell the client that the operation succeeded. + * + * COMPOUND_SLACK_SPACE - this is the minimum bytes of buffer space + * needed to encode an "ordinary" _successful_ operation. (GETATTR, + * READ, READDIR, and READLINK have their own buffer checks.) if we + * fall below this level, we fail the next operation with NFS4ERR_RESOURCE. + * + * COMPOUND_ERR_SLACK_SPACE - this is the minimum bytes of buffer space + * needed to encode an operation which has failed with NFS4ERR_RESOURCE. + * care is taken to ensure that we never fall below this level for any + * reason. + */ +#define COMPOUND_SLACK_SPACE 140 /* OP_GETFH */ +#define COMPOUND_ERR_SLACK_SPACE 12 /* OP_SETATTR */ + +#define NFSD_LEASE_TIME (nfs4_lease_time()) +#define NFSD_LAUNDROMAT_MINTIMEOUT 10 /* seconds */ + +/* + * The following attributes are currently not supported by the NFSv4 server: + * ARCHIVE (deprecated anyway) + * HIDDEN (unlikely to be supported any time soon) + * MIMETYPE (unlikely to be supported any time soon) + * QUOTA_* (will be supported in a forthcoming patch) + * SYSTEM (unlikely to be supported any time soon) + * TIME_BACKUP (unlikely to be supported any time soon) + * TIME_CREATE (unlikely to be supported any time soon) + */ +#define NFSD4_SUPPORTED_ATTRS_WORD0 \ +(FATTR4_WORD0_SUPPORTED_ATTRS | FATTR4_WORD0_TYPE | FATTR4_WORD0_FH_EXPIRE_TYPE \ + | FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE | FATTR4_WORD0_LINK_SUPPORT \ + | FATTR4_WORD0_SYMLINK_SUPPORT | FATTR4_WORD0_NAMED_ATTR | FATTR4_WORD0_FSID \ + | FATTR4_WORD0_UNIQUE_HANDLES | FATTR4_WORD0_LEASE_TIME | FATTR4_WORD0_RDATTR_ERROR \ + | FATTR4_WORD0_ACLSUPPORT | FATTR4_WORD0_CANSETTIME | FATTR4_WORD0_CASE_INSENSITIVE \ + | FATTR4_WORD0_CASE_PRESERVING | FATTR4_WORD0_CHOWN_RESTRICTED \ + | FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FILEID | FATTR4_WORD0_FILES_AVAIL \ + | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_HOMOGENEOUS \ + | FATTR4_WORD0_MAXFILESIZE | FATTR4_WORD0_MAXLINK | FATTR4_WORD0_MAXNAME \ + | FATTR4_WORD0_MAXREAD | FATTR4_WORD0_MAXWRITE | FATTR4_WORD0_ACL) + +#define NFSD4_SUPPORTED_ATTRS_WORD1 \ +(FATTR4_WORD1_MODE | FATTR4_WORD1_NO_TRUNC | FATTR4_WORD1_NUMLINKS \ + | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP | FATTR4_WORD1_RAWDEV \ + | FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL \ + | FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS | FATTR4_WORD1_TIME_ACCESS_SET \ + | FATTR4_WORD1_TIME_DELTA | FATTR4_WORD1_TIME_METADATA \ + | FATTR4_WORD1_TIME_MODIFY | FATTR4_WORD1_TIME_MODIFY_SET | FATTR4_WORD1_MOUNTED_ON_FILEID) + +#define NFSD4_SUPPORTED_ATTRS_WORD2 0 + +#define NFSD4_1_SUPPORTED_ATTRS_WORD0 \ + NFSD4_SUPPORTED_ATTRS_WORD0 + +#define NFSD4_1_SUPPORTED_ATTRS_WORD1 \ + NFSD4_SUPPORTED_ATTRS_WORD1 + +#define NFSD4_1_SUPPORTED_ATTRS_WORD2 \ + (NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT) + +static inline u32 nfsd_suppattrs0(u32 minorversion) +{ + return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0 + : NFSD4_SUPPORTED_ATTRS_WORD0; +} + +static inline u32 nfsd_suppattrs1(u32 minorversion) +{ + return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD1 + : NFSD4_SUPPORTED_ATTRS_WORD1; +} + +static inline u32 nfsd_suppattrs2(u32 minorversion) +{ + return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD2 + : NFSD4_SUPPORTED_ATTRS_WORD2; +} + +/* These will return ERR_INVAL if specified in GETATTR or READDIR. */ +#define NFSD_WRITEONLY_ATTRS_WORD1 \ +(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) + +/* These are the only attrs allowed in CREATE/OPEN/SETATTR. */ +#define NFSD_WRITEABLE_ATTRS_WORD0 \ +(FATTR4_WORD0_SIZE | FATTR4_WORD0_ACL ) +#define NFSD_WRITEABLE_ATTRS_WORD1 \ +(FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP \ + | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) +#define NFSD_WRITEABLE_ATTRS_WORD2 0 + +#define NFSD_SUPPATTR_EXCLCREAT_WORD0 \ + NFSD_WRITEABLE_ATTRS_WORD0 +/* + * we currently store the exclusive create verifier in the v_{a,m}time + * attributes so the client can't set these at create time using EXCLUSIVE4_1 + */ +#define NFSD_SUPPATTR_EXCLCREAT_WORD1 \ + (NFSD_WRITEABLE_ATTRS_WORD1 & \ + ~(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)) +#define NFSD_SUPPATTR_EXCLCREAT_WORD2 \ + NFSD_WRITEABLE_ATTRS_WORD2 + +#endif /* CONFIG_NFSD_V4 */ + +#endif /* LINUX_NFSD_NFSD_H */ diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 73994816503..0eb1c59f5ab 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -12,7 +12,7 @@ #include #include -#include +#include "nfsd.h" #include "vfs.h" #include "auth.h" diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index b6bd9e0d7cd..21a5f793c3d 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -9,8 +9,8 @@ #include -#include -#include +#include "cache.h" +#include "xdr.h" #include "vfs.h" typedef struct svc_rqst svc_rqst; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index b2d7ffac035..b520ce10bd1 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -15,11 +15,11 @@ #include #include -#include -#include #include #include #include +#include "nfsd.h" +#include "cache.h" #include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_SVC diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 5e0603da39e..3bec831704a 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -6,7 +6,7 @@ * Copyright (C) 1995, 1996 Olaf Kirch */ -#include +#include "xdr.h" #include "auth.h" #define NFSDDBG_FACILITY NFSDDBG_XDR diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h new file mode 100644 index 00000000000..2af75686e0d --- /dev/null +++ b/fs/nfsd/state.h @@ -0,0 +1,409 @@ +/* + * linux/include/nfsd/state.h + * + * Copyright (c) 2001 The Regents of the University of Michigan. + * All rights reserved. + * + * Kendrick Smith + * Andy Adamson + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ + +#ifndef _NFSD4_STATE_H +#define _NFSD4_STATE_H + +#include + +typedef struct { + u32 cl_boot; + u32 cl_id; +} clientid_t; + +typedef struct { + u32 so_boot; + u32 so_stateownerid; + u32 so_fileid; +} stateid_opaque_t; + +typedef struct { + u32 si_generation; + stateid_opaque_t si_opaque; +} stateid_t; +#define si_boot si_opaque.so_boot +#define si_stateownerid si_opaque.so_stateownerid +#define si_fileid si_opaque.so_fileid + +#define STATEID_FMT "(%08x/%08x/%08x/%08x)" +#define STATEID_VAL(s) \ + (s)->si_boot, \ + (s)->si_stateownerid, \ + (s)->si_fileid, \ + (s)->si_generation + +struct nfsd4_cb_sequence { + /* args/res */ + u32 cbs_minorversion; + struct nfs4_client *cbs_clp; +}; + +struct nfs4_delegation { + struct list_head dl_perfile; + struct list_head dl_perclnt; + struct list_head dl_recall_lru; /* delegation recalled */ + atomic_t dl_count; /* ref count */ + struct nfs4_client *dl_client; + struct nfs4_file *dl_file; + struct file_lock *dl_flock; + struct file *dl_vfs_file; + u32 dl_type; + time_t dl_time; +/* For recall: */ + u32 dl_ident; + stateid_t dl_stateid; + struct knfsd_fh dl_fh; + int dl_retries; +}; + +/* client delegation callback info */ +struct nfs4_cb_conn { + /* SETCLIENTID info */ + struct sockaddr_storage cb_addr; + size_t cb_addrlen; + u32 cb_prog; + u32 cb_minorversion; + u32 cb_ident; /* minorversion 0 only */ + /* RPC client info */ + atomic_t cb_set; /* successful CB_NULL call */ + struct rpc_clnt * cb_client; +}; + +/* Maximum number of slots per session. 160 is useful for long haul TCP */ +#define NFSD_MAX_SLOTS_PER_SESSION 160 +/* Maximum number of operations per session compound */ +#define NFSD_MAX_OPS_PER_COMPOUND 16 +/* Maximum session per slot cache size */ +#define NFSD_SLOT_CACHE_SIZE 1024 +/* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */ +#define NFSD_CACHE_SIZE_SLOTS_PER_SESSION 32 +#define NFSD_MAX_MEM_PER_SESSION \ + (NFSD_CACHE_SIZE_SLOTS_PER_SESSION * NFSD_SLOT_CACHE_SIZE) + +struct nfsd4_slot { + bool sl_inuse; + bool sl_cachethis; + u16 sl_opcnt; + u32 sl_seqid; + __be32 sl_status; + u32 sl_datalen; + char sl_data[]; +}; + +struct nfsd4_channel_attrs { + u32 headerpadsz; + u32 maxreq_sz; + u32 maxresp_sz; + u32 maxresp_cached; + u32 maxops; + u32 maxreqs; + u32 nr_rdma_attrs; + u32 rdma_attrs; +}; + +struct nfsd4_create_session { + clientid_t clientid; + struct nfs4_sessionid sessionid; + u32 seqid; + u32 flags; + struct nfsd4_channel_attrs fore_channel; + struct nfsd4_channel_attrs back_channel; + u32 callback_prog; + u32 uid; + u32 gid; +}; + +/* The single slot clientid cache structure */ +struct nfsd4_clid_slot { + u32 sl_seqid; + __be32 sl_status; + struct nfsd4_create_session sl_cr_ses; +}; + +struct nfsd4_session { + struct kref se_ref; + struct list_head se_hash; /* hash by sessionid */ + struct list_head se_perclnt; + u32 se_flags; + struct nfs4_client *se_client; /* for expire_client */ + struct nfs4_sessionid se_sessionid; + struct nfsd4_channel_attrs se_fchannel; + struct nfsd4_channel_attrs se_bchannel; + struct nfsd4_slot *se_slots[]; /* forward channel slots */ +}; + +static inline void +nfsd4_put_session(struct nfsd4_session *ses) +{ + extern void free_session(struct kref *kref); + kref_put(&ses->se_ref, free_session); +} + +static inline void +nfsd4_get_session(struct nfsd4_session *ses) +{ + kref_get(&ses->se_ref); +} + +/* formatted contents of nfs4_sessionid */ +struct nfsd4_sessionid { + clientid_t clientid; + u32 sequence; + u32 reserved; +}; + +#define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */ + +/* + * struct nfs4_client - one per client. Clientids live here. + * o Each nfs4_client is hashed by clientid. + * + * o Each nfs4_clients is also hashed by name + * (the opaque quantity initially sent by the client to identify itself). + * + * o cl_perclient list is used to ensure no dangling stateowner references + * when we expire the nfs4_client + */ +struct nfs4_client { + struct list_head cl_idhash; /* hash by cl_clientid.id */ + struct list_head cl_strhash; /* hash by cl_name */ + struct list_head cl_openowners; + struct list_head cl_delegations; + struct list_head cl_lru; /* tail queue */ + struct xdr_netobj cl_name; /* id generated by client */ + char cl_recdir[HEXDIR_LEN]; /* recovery dir */ + nfs4_verifier cl_verifier; /* generated by client */ + time_t cl_time; /* time of last lease renewal */ + struct sockaddr_storage cl_addr; /* client ipaddress */ + u32 cl_flavor; /* setclientid pseudoflavor */ + char *cl_principal; /* setclientid principal name */ + struct svc_cred cl_cred; /* setclientid principal */ + clientid_t cl_clientid; /* generated by server */ + nfs4_verifier cl_confirm; /* generated by server */ + struct nfs4_cb_conn cl_cb_conn; /* callback info */ + atomic_t cl_count; /* ref count */ + u32 cl_firststate; /* recovery dir creation */ + + /* for nfs41 */ + struct list_head cl_sessions; + struct nfsd4_clid_slot cl_cs_slot; /* create_session slot */ + u32 cl_exchange_flags; + struct nfs4_sessionid cl_sessionid; + + /* for nfs41 callbacks */ + /* We currently support a single back channel with a single slot */ + unsigned long cl_cb_slot_busy; + u32 cl_cb_seq_nr; + struct svc_xprt *cl_cb_xprt; /* 4.1 callback transport */ + struct rpc_wait_queue cl_cb_waitq; /* backchannel callers may */ + /* wait here for slots */ +}; + +/* struct nfs4_client_reset + * one per old client. Populates reset_str_hashtbl. Filled from conf_id_hashtbl + * upon lease reset, or from upcall to state_daemon (to read in state + * from non-volitile storage) upon reboot. + */ +struct nfs4_client_reclaim { + struct list_head cr_strhash; /* hash by cr_name */ + char cr_recdir[HEXDIR_LEN]; /* recover dir */ +}; + +static inline void +update_stateid(stateid_t *stateid) +{ + stateid->si_generation++; +} + +/* A reasonable value for REPLAY_ISIZE was estimated as follows: + * The OPEN response, typically the largest, requires + * 4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) + 8(verifier) + + * 4(deleg. type) + 8(deleg. stateid) + 4(deleg. recall flag) + + * 20(deleg. space limit) + ~32(deleg. ace) = 112 bytes + */ + +#define NFSD4_REPLAY_ISIZE 112 + +/* + * Replay buffer, where the result of the last seqid-mutating operation + * is cached. + */ +struct nfs4_replay { + __be32 rp_status; + unsigned int rp_buflen; + char *rp_buf; + unsigned intrp_allocated; + struct knfsd_fh rp_openfh; + char rp_ibuf[NFSD4_REPLAY_ISIZE]; +}; + +/* +* nfs4_stateowner can either be an open_owner, or a lock_owner +* +* so_idhash: stateid_hashtbl[] for open owner, lockstateid_hashtbl[] +* for lock_owner +* so_strhash: ownerstr_hashtbl[] for open_owner, lock_ownerstr_hashtbl[] +* for lock_owner +* so_perclient: nfs4_client->cl_perclient entry - used when nfs4_client +* struct is reaped. +* so_perfilestate: heads the list of nfs4_stateid (either open or lock) +* and is used to ensure no dangling nfs4_stateid references when we +* release a stateowner. +* so_perlockowner: (open) nfs4_stateid->st_perlockowner entry - used when +* close is called to reap associated byte-range locks +* so_close_lru: (open) stateowner is placed on this list instead of being +* reaped (when so_perfilestate is empty) to hold the last close replay. +* reaped by laundramat thread after lease period. +*/ +struct nfs4_stateowner { + struct kref so_ref; + struct list_head so_idhash; /* hash by so_id */ + struct list_head so_strhash; /* hash by op_name */ + struct list_head so_perclient; + struct list_head so_stateids; + struct list_head so_perstateid; /* for lockowners only */ + struct list_head so_close_lru; /* tail queue */ + time_t so_time; /* time of placement on so_close_lru */ + int so_is_open_owner; /* 1=openowner,0=lockowner */ + u32 so_id; + struct nfs4_client * so_client; + /* after increment in ENCODE_SEQID_OP_TAIL, represents the next + * sequence id expected from the client: */ + u32 so_seqid; + struct xdr_netobj so_owner; /* open owner name */ + int so_confirmed; /* successful OPEN_CONFIRM? */ + struct nfs4_replay so_replay; +}; + +/* +* nfs4_file: a file opened by some number of (open) nfs4_stateowners. +* o fi_perfile list is used to search for conflicting +* share_acces, share_deny on the file. +*/ +struct nfs4_file { + atomic_t fi_ref; + struct list_head fi_hash; /* hash by "struct inode *" */ + struct list_head fi_stateids; + struct list_head fi_delegations; + struct inode *fi_inode; + u32 fi_id; /* used with stateowner->so_id + * for stateid_hashtbl hash */ + bool fi_had_conflict; +}; + +/* +* nfs4_stateid can either be an open stateid or (eventually) a lock stateid +* +* (open)nfs4_stateid: one per (open)nfs4_stateowner, nfs4_file +* +* st_hash: stateid_hashtbl[] entry or lockstateid_hashtbl entry +* st_perfile: file_hashtbl[] entry. +* st_perfile_state: nfs4_stateowner->so_perfilestate +* st_perlockowner: (open stateid) list of lock nfs4_stateowners +* st_access_bmap: used only for open stateid +* st_deny_bmap: used only for open stateid +* st_openstp: open stateid lock stateid was derived from +* +* XXX: open stateids and lock stateids have diverged sufficiently that +* we should consider defining separate structs for the two cases. +*/ + +struct nfs4_stateid { + struct list_head st_hash; + struct list_head st_perfile; + struct list_head st_perstateowner; + struct list_head st_lockowners; + struct nfs4_stateowner * st_stateowner; + struct nfs4_file * st_file; + stateid_t st_stateid; + struct file * st_vfs_file; + unsigned long st_access_bmap; + unsigned long st_deny_bmap; + struct nfs4_stateid * st_openstp; +}; + +/* flags for preprocess_seqid_op() */ +#define HAS_SESSION 0x00000001 +#define CONFIRM 0x00000002 +#define OPEN_STATE 0x00000004 +#define LOCK_STATE 0x00000008 +#define RD_STATE 0x00000010 +#define WR_STATE 0x00000020 +#define CLOSE_STATE 0x00000040 + +#define seqid_mutating_err(err) \ + (((err) != nfserr_stale_clientid) && \ + ((err) != nfserr_bad_seqid) && \ + ((err) != nfserr_stale_stateid) && \ + ((err) != nfserr_bad_stateid)) + +struct nfsd4_compound_state; + +extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, + stateid_t *stateid, int flags, struct file **filp); +extern void nfs4_lock_state(void); +extern void nfs4_unlock_state(void); +extern int nfs4_in_grace(void); +extern __be32 nfs4_check_open_reclaim(clientid_t *clid); +extern void put_nfs4_client(struct nfs4_client *clp); +extern void nfs4_free_stateowner(struct kref *kref); +extern int set_callback_cred(void); +extern void nfsd4_probe_callback(struct nfs4_client *clp); +extern void nfsd4_cb_recall(struct nfs4_delegation *dp); +extern void nfs4_put_delegation(struct nfs4_delegation *dp); +extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname); +extern void nfsd4_init_recdir(char *recdir_name); +extern int nfsd4_recdir_load(void); +extern void nfsd4_shutdown_recdir(void); +extern int nfs4_client_to_reclaim(const char *name); +extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id); +extern void nfsd4_recdir_purge_old(void); +extern int nfsd4_create_clid_dir(struct nfs4_client *clp); +extern void nfsd4_remove_clid_dir(struct nfs4_client *clp); + +static inline void +nfs4_put_stateowner(struct nfs4_stateowner *so) +{ + kref_put(&so->so_ref, nfs4_free_stateowner); +} + +static inline void +nfs4_get_stateowner(struct nfs4_stateowner *so) +{ + kref_get(&so->so_ref); +} + +#endif /* NFSD4_STATE_H */ diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index e3e411e9fe4..3fc69dfd309 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -25,11 +25,11 @@ #include #include - #include -#include #include +#include "nfsd.h" + struct nfsd_stats nfsdstats; struct svc_stat nfsd_svcstats = { .program = &nfsd_program, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 81ce108c114..04bdba12d21 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -22,23 +22,25 @@ #include #include #include -#include -#ifdef CONFIG_NFSD_V3 -#include -#endif /* CONFIG_NFSD_V3 */ #include #include #include #include +#include +#include +#include + +#ifdef CONFIG_NFSD_V3 +#include "xdr3.h" +#endif /* CONFIG_NFSD_V3 */ + #ifdef CONFIG_NFSD_V4 #include #include #endif /* CONFIG_NFSD_V4 */ -#include -#include -#include "vfs.h" -#include +#include "nfsd.h" +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_FILEOP diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h new file mode 100644 index 00000000000..235ee5c3be5 --- /dev/null +++ b/fs/nfsd/xdr.h @@ -0,0 +1,176 @@ +/* + * linux/include/linux/nfsd/xdr.h + * + * XDR types for nfsd. This is mainly a typing exercise. + */ + +#ifndef LINUX_NFSD_H +#define LINUX_NFSD_H + +#include +#include "nfsd.h" + +struct nfsd_fhandle { + struct svc_fh fh; +}; + +struct nfsd_sattrargs { + struct svc_fh fh; + struct iattr attrs; +}; + +struct nfsd_diropargs { + struct svc_fh fh; + char * name; + unsigned int len; +}; + +struct nfsd_readargs { + struct svc_fh fh; + __u32 offset; + __u32 count; + int vlen; +}; + +struct nfsd_writeargs { + svc_fh fh; + __u32 offset; + int len; + int vlen; +}; + +struct nfsd_createargs { + struct svc_fh fh; + char * name; + unsigned int len; + struct iattr attrs; +}; + +struct nfsd_renameargs { + struct svc_fh ffh; + char * fname; + unsigned int flen; + struct svc_fh tfh; + char * tname; + unsigned int tlen; +}; + +struct nfsd_readlinkargs { + struct svc_fh fh; + char * buffer; +}; + +struct nfsd_linkargs { + struct svc_fh ffh; + struct svc_fh tfh; + char * tname; + unsigned int tlen; +}; + +struct nfsd_symlinkargs { + struct svc_fh ffh; + char * fname; + unsigned int flen; + char * tname; + unsigned int tlen; + struct iattr attrs; +}; + +struct nfsd_readdirargs { + struct svc_fh fh; + __u32 cookie; + __u32 count; + __be32 * buffer; +}; + +struct nfsd_attrstat { + struct svc_fh fh; + struct kstat stat; +}; + +struct nfsd_diropres { + struct svc_fh fh; + struct kstat stat; +}; + +struct nfsd_readlinkres { + int len; +}; + +struct nfsd_readres { + struct svc_fh fh; + unsigned long count; + struct kstat stat; +}; + +struct nfsd_readdirres { + int count; + + struct readdir_cd common; + __be32 * buffer; + int buflen; + __be32 * offset; +}; + +struct nfsd_statfsres { + struct kstatfs stats; +}; + +/* + * Storage requirements for XDR arguments and results. + */ +union nfsd_xdrstore { + struct nfsd_sattrargs sattr; + struct nfsd_diropargs dirop; + struct nfsd_readargs read; + struct nfsd_writeargs write; + struct nfsd_createargs create; + struct nfsd_renameargs rename; + struct nfsd_linkargs link; + struct nfsd_symlinkargs symlink; + struct nfsd_readdirargs readdir; +}; + +#define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore) + + +int nfssvc_decode_void(struct svc_rqst *, __be32 *, void *); +int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); +int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *, + struct nfsd_sattrargs *); +int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *, + struct nfsd_diropargs *); +int nfssvc_decode_readargs(struct svc_rqst *, __be32 *, + struct nfsd_readargs *); +int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *, + struct nfsd_writeargs *); +int nfssvc_decode_createargs(struct svc_rqst *, __be32 *, + struct nfsd_createargs *); +int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *, + struct nfsd_renameargs *); +int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *, + struct nfsd_readlinkargs *); +int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *, + struct nfsd_linkargs *); +int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *, + struct nfsd_symlinkargs *); +int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *, + struct nfsd_readdirargs *); +int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *); +int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *); +int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *); +int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd_readlinkres *); +int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *); +int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *); +int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *); + +int nfssvc_encode_entry(void *, const char *name, + int namlen, loff_t offset, u64 ino, unsigned int); + +int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); + +/* Helper functions for NFSv2 ACL code */ +__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp); +__be32 *nfs2svc_decode_fh(__be32 *p, struct svc_fh *fhp); + +#endif /* LINUX_NFSD_H */ diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h new file mode 100644 index 00000000000..b330756973c --- /dev/null +++ b/fs/nfsd/xdr3.h @@ -0,0 +1,346 @@ +/* + * linux/include/linux/nfsd/xdr3.h + * + * XDR types for NFSv3 in nfsd. + * + * Copyright (C) 1996-1998, Olaf Kirch + */ + +#ifndef _LINUX_NFSD_XDR3_H +#define _LINUX_NFSD_XDR3_H + +#include "xdr.h" + +struct nfsd3_sattrargs { + struct svc_fh fh; + struct iattr attrs; + int check_guard; + time_t guardtime; +}; + +struct nfsd3_diropargs { + struct svc_fh fh; + char * name; + unsigned int len; +}; + +struct nfsd3_accessargs { + struct svc_fh fh; + unsigned int access; +}; + +struct nfsd3_readargs { + struct svc_fh fh; + __u64 offset; + __u32 count; + int vlen; +}; + +struct nfsd3_writeargs { + svc_fh fh; + __u64 offset; + __u32 count; + int stable; + __u32 len; + int vlen; +}; + +struct nfsd3_createargs { + struct svc_fh fh; + char * name; + unsigned int len; + int createmode; + struct iattr attrs; + __be32 * verf; +}; + +struct nfsd3_mknodargs { + struct svc_fh fh; + char * name; + unsigned int len; + __u32 ftype; + __u32 major, minor; + struct iattr attrs; +}; + +struct nfsd3_renameargs { + struct svc_fh ffh; + char * fname; + unsigned int flen; + struct svc_fh tfh; + char * tname; + unsigned int tlen; +}; + +struct nfsd3_readlinkargs { + struct svc_fh fh; + char * buffer; +}; + +struct nfsd3_linkargs { + struct svc_fh ffh; + struct svc_fh tfh; + char * tname; + unsigned int tlen; +}; + +struct nfsd3_symlinkargs { + struct svc_fh ffh; + char * fname; + unsigned int flen; + char * tname; + unsigned int tlen; + struct iattr attrs; +}; + +struct nfsd3_readdirargs { + struct svc_fh fh; + __u64 cookie; + __u32 dircount; + __u32 count; + __be32 * verf; + __be32 * buffer; +}; + +struct nfsd3_commitargs { + struct svc_fh fh; + __u64 offset; + __u32 count; +}; + +struct nfsd3_getaclargs { + struct svc_fh fh; + int mask; +}; + +struct posix_acl; +struct nfsd3_setaclargs { + struct svc_fh fh; + int mask; + struct posix_acl *acl_access; + struct posix_acl *acl_default; +}; + +struct nfsd3_attrstat { + __be32 status; + struct svc_fh fh; + struct kstat stat; +}; + +/* LOOKUP, CREATE, MKDIR, SYMLINK, MKNOD */ +struct nfsd3_diropres { + __be32 status; + struct svc_fh dirfh; + struct svc_fh fh; +}; + +struct nfsd3_accessres { + __be32 status; + struct svc_fh fh; + __u32 access; +}; + +struct nfsd3_readlinkres { + __be32 status; + struct svc_fh fh; + __u32 len; +}; + +struct nfsd3_readres { + __be32 status; + struct svc_fh fh; + unsigned long count; + int eof; +}; + +struct nfsd3_writeres { + __be32 status; + struct svc_fh fh; + unsigned long count; + int committed; +}; + +struct nfsd3_renameres { + __be32 status; + struct svc_fh ffh; + struct svc_fh tfh; +}; + +struct nfsd3_linkres { + __be32 status; + struct svc_fh tfh; + struct svc_fh fh; +}; + +struct nfsd3_readdirres { + __be32 status; + struct svc_fh fh; + int count; + __be32 verf[2]; + + struct readdir_cd common; + __be32 * buffer; + int buflen; + __be32 * offset; + __be32 * offset1; + struct svc_rqst * rqstp; + +}; + +struct nfsd3_fsstatres { + __be32 status; + struct kstatfs stats; + __u32 invarsec; +}; + +struct nfsd3_fsinfores { + __be32 status; + __u32 f_rtmax; + __u32 f_rtpref; + __u32 f_rtmult; + __u32 f_wtmax; + __u32 f_wtpref; + __u32 f_wtmult; + __u32 f_dtpref; + __u64 f_maxfilesize; + __u32 f_properties; +}; + +struct nfsd3_pathconfres { + __be32 status; + __u32 p_link_max; + __u32 p_name_max; + __u32 p_no_trunc; + __u32 p_chown_restricted; + __u32 p_case_insensitive; + __u32 p_case_preserving; +}; + +struct nfsd3_commitres { + __be32 status; + struct svc_fh fh; +}; + +struct nfsd3_getaclres { + __be32 status; + struct svc_fh fh; + int mask; + struct posix_acl *acl_access; + struct posix_acl *acl_default; +}; + +/* dummy type for release */ +struct nfsd3_fhandle_pair { + __u32 dummy; + struct svc_fh fh1; + struct svc_fh fh2; +}; + +/* + * Storage requirements for XDR arguments and results. + */ +union nfsd3_xdrstore { + struct nfsd3_sattrargs sattrargs; + struct nfsd3_diropargs diropargs; + struct nfsd3_readargs readargs; + struct nfsd3_writeargs writeargs; + struct nfsd3_createargs createargs; + struct nfsd3_renameargs renameargs; + struct nfsd3_linkargs linkargs; + struct nfsd3_symlinkargs symlinkargs; + struct nfsd3_readdirargs readdirargs; + struct nfsd3_diropres diropres; + struct nfsd3_accessres accessres; + struct nfsd3_readlinkres readlinkres; + struct nfsd3_readres readres; + struct nfsd3_writeres writeres; + struct nfsd3_renameres renameres; + struct nfsd3_linkres linkres; + struct nfsd3_readdirres readdirres; + struct nfsd3_fsstatres fsstatres; + struct nfsd3_fsinfores fsinfores; + struct nfsd3_pathconfres pathconfres; + struct nfsd3_commitres commitres; + struct nfsd3_getaclres getaclres; +}; + +#define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore) + +int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); +int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *, + struct nfsd3_sattrargs *); +int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *, + struct nfsd3_diropargs *); +int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *, + struct nfsd3_accessargs *); +int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *, + struct nfsd3_readargs *); +int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *, + struct nfsd3_writeargs *); +int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *, + struct nfsd3_createargs *); +int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *, + struct nfsd3_createargs *); +int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *, + struct nfsd3_mknodargs *); +int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *, + struct nfsd3_renameargs *); +int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *, + struct nfsd3_readlinkargs *); +int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *, + struct nfsd3_linkargs *); +int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *, + struct nfsd3_symlinkargs *); +int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *, + struct nfsd3_readdirargs *); +int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *, + struct nfsd3_readdirargs *); +int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *, + struct nfsd3_commitargs *); +int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *); +int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *, + struct nfsd3_attrstat *); +int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *, + struct nfsd3_attrstat *); +int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *, + struct nfsd3_diropres *); +int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *, + struct nfsd3_accessres *); +int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *, + struct nfsd3_readlinkres *); +int nfs3svc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd3_readres *); +int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *, struct nfsd3_writeres *); +int nfs3svc_encode_createres(struct svc_rqst *, __be32 *, + struct nfsd3_diropres *); +int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *, + struct nfsd3_renameres *); +int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *, + struct nfsd3_linkres *); +int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *, + struct nfsd3_readdirres *); +int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *, + struct nfsd3_fsstatres *); +int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *, + struct nfsd3_fsinfores *); +int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *, + struct nfsd3_pathconfres *); +int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *, + struct nfsd3_commitres *); + +int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *, + struct nfsd3_attrstat *); +int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *, + struct nfsd3_fhandle_pair *); +int nfs3svc_encode_entry(void *, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int); +int nfs3svc_encode_entry_plus(void *, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int); +/* Helper functions for NFSv3 ACL code */ +__be32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, + struct svc_fh *fhp); +__be32 *nfs3svc_decode_fh(__be32 *p, struct svc_fh *fhp); + + +#endif /* _LINUX_NFSD_XDR3_H */ diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h new file mode 100644 index 00000000000..83202a1cf07 --- /dev/null +++ b/fs/nfsd/xdr4.h @@ -0,0 +1,564 @@ +/* + * include/linux/nfsd/xdr4.h + * + * Server-side types for NFSv4. + * + * Copyright (c) 2002 The Regents of the University of Michigan. + * All rights reserved. + * + * Kendrick Smith + * Andy Adamson + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR + * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ + +#ifndef _LINUX_NFSD_XDR4_H +#define _LINUX_NFSD_XDR4_H + +#include "state.h" +#include "nfsd.h" + +#define NFSD4_MAX_TAGLEN 128 +#define XDR_LEN(n) (((n) + 3) & ~3) + +struct nfsd4_compound_state { + struct svc_fh current_fh; + struct svc_fh save_fh; + struct nfs4_stateowner *replay_owner; + /* For sessions DRC */ + struct nfsd4_session *session; + struct nfsd4_slot *slot; + __be32 *datap; + size_t iovlen; + u32 minorversion; + u32 status; +}; + +static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs) +{ + return cs->slot != NULL; +} + +struct nfsd4_change_info { + u32 atomic; + bool change_supported; + u32 before_ctime_sec; + u32 before_ctime_nsec; + u64 before_change; + u32 after_ctime_sec; + u32 after_ctime_nsec; + u64 after_change; +}; + +struct nfsd4_access { + u32 ac_req_access; /* request */ + u32 ac_supported; /* response */ + u32 ac_resp_access; /* response */ +}; + +struct nfsd4_close { + u32 cl_seqid; /* request */ + stateid_t cl_stateid; /* request+response */ + struct nfs4_stateowner * cl_stateowner; /* response */ +}; + +struct nfsd4_commit { + u64 co_offset; /* request */ + u32 co_count; /* request */ + nfs4_verifier co_verf; /* response */ +}; + +struct nfsd4_create { + u32 cr_namelen; /* request */ + char * cr_name; /* request */ + u32 cr_type; /* request */ + union { /* request */ + struct { + u32 namelen; + char *name; + } link; /* NF4LNK */ + struct { + u32 specdata1; + u32 specdata2; + } dev; /* NF4BLK, NF4CHR */ + } u; + u32 cr_bmval[3]; /* request */ + struct iattr cr_iattr; /* request */ + struct nfsd4_change_info cr_cinfo; /* response */ + struct nfs4_acl *cr_acl; +}; +#define cr_linklen u.link.namelen +#define cr_linkname u.link.name +#define cr_specdata1 u.dev.specdata1 +#define cr_specdata2 u.dev.specdata2 + +struct nfsd4_delegreturn { + stateid_t dr_stateid; +}; + +struct nfsd4_getattr { + u32 ga_bmval[3]; /* request */ + struct svc_fh *ga_fhp; /* response */ +}; + +struct nfsd4_link { + u32 li_namelen; /* request */ + char * li_name; /* request */ + struct nfsd4_change_info li_cinfo; /* response */ +}; + +struct nfsd4_lock_denied { + clientid_t ld_clientid; + struct nfs4_stateowner *ld_sop; + u64 ld_start; + u64 ld_length; + u32 ld_type; +}; + +struct nfsd4_lock { + /* request */ + u32 lk_type; + u32 lk_reclaim; /* boolean */ + u64 lk_offset; + u64 lk_length; + u32 lk_is_new; + union { + struct { + u32 open_seqid; + stateid_t open_stateid; + u32 lock_seqid; + clientid_t clientid; + struct xdr_netobj owner; + } new; + struct { + stateid_t lock_stateid; + u32 lock_seqid; + } old; + } v; + + /* response */ + union { + struct { + stateid_t stateid; + } ok; + struct nfsd4_lock_denied denied; + } u; + /* The lk_replay_owner is the open owner in the open_to_lock_owner + * case and the lock owner otherwise: */ + struct nfs4_stateowner *lk_replay_owner; +}; +#define lk_new_open_seqid v.new.open_seqid +#define lk_new_open_stateid v.new.open_stateid +#define lk_new_lock_seqid v.new.lock_seqid +#define lk_new_clientid v.new.clientid +#define lk_new_owner v.new.owner +#define lk_old_lock_stateid v.old.lock_stateid +#define lk_old_lock_seqid v.old.lock_seqid + +#define lk_rflags u.ok.rflags +#define lk_resp_stateid u.ok.stateid +#define lk_denied u.denied + + +struct nfsd4_lockt { + u32 lt_type; + clientid_t lt_clientid; + struct xdr_netobj lt_owner; + u64 lt_offset; + u64 lt_length; + struct nfs4_stateowner * lt_stateowner; + struct nfsd4_lock_denied lt_denied; +}; + + +struct nfsd4_locku { + u32 lu_type; + u32 lu_seqid; + stateid_t lu_stateid; + u64 lu_offset; + u64 lu_length; + struct nfs4_stateowner *lu_stateowner; +}; + + +struct nfsd4_lookup { + u32 lo_len; /* request */ + char * lo_name; /* request */ +}; + +struct nfsd4_putfh { + u32 pf_fhlen; /* request */ + char *pf_fhval; /* request */ +}; + +struct nfsd4_open { + u32 op_claim_type; /* request */ + struct xdr_netobj op_fname; /* request - everything but CLAIM_PREV */ + u32 op_delegate_type; /* request - CLAIM_PREV only */ + stateid_t op_delegate_stateid; /* request - response */ + u32 op_create; /* request */ + u32 op_createmode; /* request */ + u32 op_bmval[3]; /* request */ + struct iattr iattr; /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */ + nfs4_verifier verf; /* EXCLUSIVE4 */ + clientid_t op_clientid; /* request */ + struct xdr_netobj op_owner; /* request */ + u32 op_seqid; /* request */ + u32 op_share_access; /* request */ + u32 op_share_deny; /* request */ + stateid_t op_stateid; /* response */ + u32 op_recall; /* recall */ + struct nfsd4_change_info op_cinfo; /* response */ + u32 op_rflags; /* response */ + int op_truncate; /* used during processing */ + struct nfs4_stateowner *op_stateowner; /* used during processing */ + struct nfs4_acl *op_acl; +}; +#define op_iattr iattr +#define op_verf verf + +struct nfsd4_open_confirm { + stateid_t oc_req_stateid /* request */; + u32 oc_seqid /* request */; + stateid_t oc_resp_stateid /* response */; + struct nfs4_stateowner * oc_stateowner; /* response */ +}; + +struct nfsd4_open_downgrade { + stateid_t od_stateid; + u32 od_seqid; + u32 od_share_access; + u32 od_share_deny; + struct nfs4_stateowner *od_stateowner; +}; + + +struct nfsd4_read { + stateid_t rd_stateid; /* request */ + u64 rd_offset; /* request */ + u32 rd_length; /* request */ + int rd_vlen; + struct file *rd_filp; + + struct svc_rqst *rd_rqstp; /* response */ + struct svc_fh * rd_fhp; /* response */ +}; + +struct nfsd4_readdir { + u64 rd_cookie; /* request */ + nfs4_verifier rd_verf; /* request */ + u32 rd_dircount; /* request */ + u32 rd_maxcount; /* request */ + u32 rd_bmval[3]; /* request */ + struct svc_rqst *rd_rqstp; /* response */ + struct svc_fh * rd_fhp; /* response */ + + struct readdir_cd common; + __be32 * buffer; + int buflen; + __be32 * offset; +}; + +struct nfsd4_release_lockowner { + clientid_t rl_clientid; + struct xdr_netobj rl_owner; +}; +struct nfsd4_readlink { + struct svc_rqst *rl_rqstp; /* request */ + struct svc_fh * rl_fhp; /* request */ +}; + +struct nfsd4_remove { + u32 rm_namelen; /* request */ + char * rm_name; /* request */ + struct nfsd4_change_info rm_cinfo; /* response */ +}; + +struct nfsd4_rename { + u32 rn_snamelen; /* request */ + char * rn_sname; /* request */ + u32 rn_tnamelen; /* request */ + char * rn_tname; /* request */ + struct nfsd4_change_info rn_sinfo; /* response */ + struct nfsd4_change_info rn_tinfo; /* response */ +}; + +struct nfsd4_secinfo { + u32 si_namelen; /* request */ + char *si_name; /* request */ + struct svc_export *si_exp; /* response */ +}; + +struct nfsd4_setattr { + stateid_t sa_stateid; /* request */ + u32 sa_bmval[3]; /* request */ + struct iattr sa_iattr; /* request */ + struct nfs4_acl *sa_acl; +}; + +struct nfsd4_setclientid { + nfs4_verifier se_verf; /* request */ + u32 se_namelen; /* request */ + char * se_name; /* request */ + u32 se_callback_prog; /* request */ + u32 se_callback_netid_len; /* request */ + char * se_callback_netid_val; /* request */ + u32 se_callback_addr_len; /* request */ + char * se_callback_addr_val; /* request */ + u32 se_callback_ident; /* request */ + clientid_t se_clientid; /* response */ + nfs4_verifier se_confirm; /* response */ +}; + +struct nfsd4_setclientid_confirm { + clientid_t sc_clientid; + nfs4_verifier sc_confirm; +}; + +/* also used for NVERIFY */ +struct nfsd4_verify { + u32 ve_bmval[3]; /* request */ + u32 ve_attrlen; /* request */ + char * ve_attrval; /* request */ +}; + +struct nfsd4_write { + stateid_t wr_stateid; /* request */ + u64 wr_offset; /* request */ + u32 wr_stable_how; /* request */ + u32 wr_buflen; /* request */ + int wr_vlen; + + u32 wr_bytes_written; /* response */ + u32 wr_how_written; /* response */ + nfs4_verifier wr_verifier; /* response */ +}; + +struct nfsd4_exchange_id { + nfs4_verifier verifier; + struct xdr_netobj clname; + u32 flags; + clientid_t clientid; + u32 seqid; + int spa_how; +}; + +struct nfsd4_sequence { + struct nfs4_sessionid sessionid; /* request/response */ + u32 seqid; /* request/response */ + u32 slotid; /* request/response */ + u32 maxslots; /* request/response */ + u32 cachethis; /* request */ +#if 0 + u32 target_maxslots; /* response */ + u32 status_flags; /* response */ +#endif /* not yet */ +}; + +struct nfsd4_destroy_session { + struct nfs4_sessionid sessionid; +}; + +struct nfsd4_op { + int opnum; + __be32 status; + union { + struct nfsd4_access access; + struct nfsd4_close close; + struct nfsd4_commit commit; + struct nfsd4_create create; + struct nfsd4_delegreturn delegreturn; + struct nfsd4_getattr getattr; + struct svc_fh * getfh; + struct nfsd4_link link; + struct nfsd4_lock lock; + struct nfsd4_lockt lockt; + struct nfsd4_locku locku; + struct nfsd4_lookup lookup; + struct nfsd4_verify nverify; + struct nfsd4_open open; + struct nfsd4_open_confirm open_confirm; + struct nfsd4_open_downgrade open_downgrade; + struct nfsd4_putfh putfh; + struct nfsd4_read read; + struct nfsd4_readdir readdir; + struct nfsd4_readlink readlink; + struct nfsd4_remove remove; + struct nfsd4_rename rename; + clientid_t renew; + struct nfsd4_secinfo secinfo; + struct nfsd4_setattr setattr; + struct nfsd4_setclientid setclientid; + struct nfsd4_setclientid_confirm setclientid_confirm; + struct nfsd4_verify verify; + struct nfsd4_write write; + struct nfsd4_release_lockowner release_lockowner; + + /* NFSv4.1 */ + struct nfsd4_exchange_id exchange_id; + struct nfsd4_create_session create_session; + struct nfsd4_destroy_session destroy_session; + struct nfsd4_sequence sequence; + } u; + struct nfs4_replay * replay; +}; + +struct nfsd4_compoundargs { + /* scratch variables for XDR decode */ + __be32 * p; + __be32 * end; + struct page ** pagelist; + int pagelen; + __be32 tmp[8]; + __be32 * tmpp; + struct tmpbuf { + struct tmpbuf *next; + void (*release)(const void *); + void *buf; + } *to_free; + + struct svc_rqst *rqstp; + + u32 taglen; + char * tag; + u32 minorversion; + u32 opcnt; + struct nfsd4_op *ops; + struct nfsd4_op iops[8]; +}; + +struct nfsd4_compoundres { + /* scratch variables for XDR encode */ + __be32 * p; + __be32 * end; + struct xdr_buf * xbuf; + struct svc_rqst * rqstp; + + u32 taglen; + char * tag; + u32 opcnt; + __be32 * tagp; /* tag, opcount encode location */ + struct nfsd4_compound_state cstate; +}; + +static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp) +{ + struct nfsd4_compoundargs *args = resp->rqstp->rq_argp; + return resp->opcnt == 1 && args->ops[0].opnum == OP_SEQUENCE; +} + +static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp) +{ + return !resp->cstate.slot->sl_cachethis || nfsd4_is_solo_sequence(resp); +} + +#define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) + +static inline void +set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) +{ + BUG_ON(!fhp->fh_pre_saved || !fhp->fh_post_saved); + cinfo->atomic = 1; + cinfo->change_supported = IS_I_VERSION(fhp->fh_dentry->d_inode); + if (cinfo->change_supported) { + cinfo->before_change = fhp->fh_pre_change; + cinfo->after_change = fhp->fh_post_change; + } else { + cinfo->before_ctime_sec = fhp->fh_pre_ctime.tv_sec; + cinfo->before_ctime_nsec = fhp->fh_pre_ctime.tv_nsec; + cinfo->after_ctime_sec = fhp->fh_post_attr.ctime.tv_sec; + cinfo->after_ctime_nsec = fhp->fh_post_attr.ctime.tv_nsec; + } +} + +int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *); +int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *, + struct nfsd4_compoundargs *); +int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, + struct nfsd4_compoundres *); +void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); +void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op); +__be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, + struct dentry *dentry, __be32 *buffer, int *countp, + u32 *bmval, struct svc_rqst *, int ignore_crossmnt); +extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, + struct nfsd4_setclientid *setclid); +extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, + struct nfsd4_setclientid_confirm *setclientid_confirm); +extern void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp); +extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, + struct nfsd4_sequence *seq); +extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, +struct nfsd4_exchange_id *); + extern __be32 nfsd4_create_session(struct svc_rqst *, + struct nfsd4_compound_state *, + struct nfsd4_create_session *); +extern __be32 nfsd4_sequence(struct svc_rqst *, + struct nfsd4_compound_state *, + struct nfsd4_sequence *); +extern __be32 nfsd4_destroy_session(struct svc_rqst *, + struct nfsd4_compound_state *, + struct nfsd4_destroy_session *); +extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *, + struct nfsd4_open *open); +extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, + struct svc_fh *current_fh, struct nfsd4_open *open); +extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, struct nfsd4_open_confirm *oc); +extern __be32 nfsd4_close(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, + struct nfsd4_close *close); +extern __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, + struct nfsd4_open_downgrade *od); +extern __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + struct nfsd4_lock *lock); +extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, + struct nfsd4_lockt *lockt); +extern __be32 nfsd4_locku(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, + struct nfsd4_locku *locku); +extern __be32 +nfsd4_release_lockowner(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, + struct nfsd4_release_lockowner *rlockowner); +extern void nfsd4_release_compoundargs(struct nfsd4_compoundargs *); +extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr); +extern __be32 nfsd4_renew(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, clientid_t *clid); +#endif + +/* + * Local variables: + * c-basic-offset: 8 + * End: + */ diff --git a/include/linux/nfsd/cache.h b/include/linux/nfsd/cache.h deleted file mode 100644 index a165425dea4..00000000000 --- a/include/linux/nfsd/cache.h +++ /dev/null @@ -1,85 +0,0 @@ -/* - * include/linux/nfsd/cache.h - * - * Request reply cache. This was heavily inspired by the - * implementation in 4.3BSD/4.4BSD. - * - * Copyright (C) 1995, 1996 Olaf Kirch - */ - -#ifndef NFSCACHE_H -#define NFSCACHE_H - -#include - -/* - * Representation of a reply cache entry. - */ -struct svc_cacherep { - struct hlist_node c_hash; - struct list_head c_lru; - - unsigned char c_state, /* unused, inprog, done */ - c_type, /* status, buffer */ - c_secure : 1; /* req came from port < 1024 */ - struct sockaddr_in c_addr; - __be32 c_xid; - u32 c_prot; - u32 c_proc; - u32 c_vers; - unsigned long c_timestamp; - union { - struct kvec u_vec; - __be32 u_status; - } c_u; -}; - -#define c_replvec c_u.u_vec -#define c_replstat c_u.u_status - -/* cache entry states */ -enum { - RC_UNUSED, - RC_INPROG, - RC_DONE -}; - -/* return values */ -enum { - RC_DROPIT, - RC_REPLY, - RC_DOIT, - RC_INTR -}; - -/* - * Cache types. - * We may want to add more types one day, e.g. for diropres and - * attrstat replies. Using cache entries with fixed length instead - * of buffer pointers may be more efficient. - */ -enum { - RC_NOCACHE, - RC_REPLSTAT, - RC_REPLBUFF, -}; - -/* - * If requests are retransmitted within this interval, they're dropped. - */ -#define RC_DELAY (HZ/5) - -int nfsd_reply_cache_init(void); -void nfsd_reply_cache_shutdown(void); -int nfsd_cache_lookup(struct svc_rqst *, int); -void nfsd_cache_update(struct svc_rqst *, int, __be32 *); - -#ifdef CONFIG_NFSD_V4 -void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp); -#else /* CONFIG_NFSD_V4 */ -static inline void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp) -{ -} -#endif /* CONFIG_NFSD_V4 */ - -#endif /* NFSCACHE_H */ diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h deleted file mode 100644 index 74f67c2aca3..00000000000 --- a/include/linux/nfsd/nfsd.h +++ /dev/null @@ -1,335 +0,0 @@ -/* - * linux/include/linux/nfsd/nfsd.h - * - * Hodge-podge collection of knfsd-related stuff. - * I will sort this out later. - * - * Copyright (C) 1995-1997 Olaf Kirch - */ - -#ifndef LINUX_NFSD_NFSD_H -#define LINUX_NFSD_NFSD_H - -#include -#include - -#include -#include -#include -/* - * nfsd version - */ -#define NFSD_SUPPORTED_MINOR_VERSION 1 - -struct readdir_cd { - __be32 err; /* 0, nfserr, or nfserr_eof */ -}; - - -extern struct svc_program nfsd_program; -extern struct svc_version nfsd_version2, nfsd_version3, - nfsd_version4; -extern u32 nfsd_supported_minorversion; -extern struct mutex nfsd_mutex; -extern struct svc_serv *nfsd_serv; -extern spinlock_t nfsd_drc_lock; -extern unsigned int nfsd_drc_max_mem; -extern unsigned int nfsd_drc_mem_used; - -extern const struct seq_operations nfs_exports_op; - -/* - * Function prototypes. - */ -int nfsd_svc(unsigned short port, int nrservs); -int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp); - -int nfsd_nrthreads(void); -int nfsd_nrpools(void); -int nfsd_get_nrthreads(int n, int *); -int nfsd_set_nrthreads(int n, int *); - -#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) -#ifdef CONFIG_NFSD_V2_ACL -extern struct svc_version nfsd_acl_version2; -#else -#define nfsd_acl_version2 NULL -#endif -#ifdef CONFIG_NFSD_V3_ACL -extern struct svc_version nfsd_acl_version3; -#else -#define nfsd_acl_version3 NULL -#endif -#endif - -enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; -int nfsd_vers(int vers, enum vers_op change); -int nfsd_minorversion(u32 minorversion, enum vers_op change); -void nfsd_reset_versions(void); -int nfsd_create_serv(void); - -extern int nfsd_max_blksize; - -/* - * NFSv4 State - */ -#ifdef CONFIG_NFSD_V4 -extern unsigned int max_delegations; -int nfs4_state_init(void); -void nfsd4_free_slabs(void); -int nfs4_state_start(void); -void nfs4_state_shutdown(void); -time_t nfs4_lease_time(void); -void nfs4_reset_lease(time_t leasetime); -int nfs4_reset_recoverydir(char *recdir); -#else -static inline int nfs4_state_init(void) { return 0; } -static inline void nfsd4_free_slabs(void) { } -static inline int nfs4_state_start(void) { return 0; } -static inline void nfs4_state_shutdown(void) { } -static inline time_t nfs4_lease_time(void) { return 0; } -static inline void nfs4_reset_lease(time_t leasetime) { } -static inline int nfs4_reset_recoverydir(char *recdir) { return 0; } -#endif - -/* - * lockd binding - */ -void nfsd_lockd_init(void); -void nfsd_lockd_shutdown(void); - - -/* - * These macros provide pre-xdr'ed values for faster operation. - */ -#define nfs_ok cpu_to_be32(NFS_OK) -#define nfserr_perm cpu_to_be32(NFSERR_PERM) -#define nfserr_noent cpu_to_be32(NFSERR_NOENT) -#define nfserr_io cpu_to_be32(NFSERR_IO) -#define nfserr_nxio cpu_to_be32(NFSERR_NXIO) -#define nfserr_eagain cpu_to_be32(NFSERR_EAGAIN) -#define nfserr_acces cpu_to_be32(NFSERR_ACCES) -#define nfserr_exist cpu_to_be32(NFSERR_EXIST) -#define nfserr_xdev cpu_to_be32(NFSERR_XDEV) -#define nfserr_nodev cpu_to_be32(NFSERR_NODEV) -#define nfserr_notdir cpu_to_be32(NFSERR_NOTDIR) -#define nfserr_isdir cpu_to_be32(NFSERR_ISDIR) -#define nfserr_inval cpu_to_be32(NFSERR_INVAL) -#define nfserr_fbig cpu_to_be32(NFSERR_FBIG) -#define nfserr_nospc cpu_to_be32(NFSERR_NOSPC) -#define nfserr_rofs cpu_to_be32(NFSERR_ROFS) -#define nfserr_mlink cpu_to_be32(NFSERR_MLINK) -#define nfserr_opnotsupp cpu_to_be32(NFSERR_OPNOTSUPP) -#define nfserr_nametoolong cpu_to_be32(NFSERR_NAMETOOLONG) -#define nfserr_notempty cpu_to_be32(NFSERR_NOTEMPTY) -#define nfserr_dquot cpu_to_be32(NFSERR_DQUOT) -#define nfserr_stale cpu_to_be32(NFSERR_STALE) -#define nfserr_remote cpu_to_be32(NFSERR_REMOTE) -#define nfserr_wflush cpu_to_be32(NFSERR_WFLUSH) -#define nfserr_badhandle cpu_to_be32(NFSERR_BADHANDLE) -#define nfserr_notsync cpu_to_be32(NFSERR_NOT_SYNC) -#define nfserr_badcookie cpu_to_be32(NFSERR_BAD_COOKIE) -#define nfserr_notsupp cpu_to_be32(NFSERR_NOTSUPP) -#define nfserr_toosmall cpu_to_be32(NFSERR_TOOSMALL) -#define nfserr_serverfault cpu_to_be32(NFSERR_SERVERFAULT) -#define nfserr_badtype cpu_to_be32(NFSERR_BADTYPE) -#define nfserr_jukebox cpu_to_be32(NFSERR_JUKEBOX) -#define nfserr_denied cpu_to_be32(NFSERR_DENIED) -#define nfserr_deadlock cpu_to_be32(NFSERR_DEADLOCK) -#define nfserr_expired cpu_to_be32(NFSERR_EXPIRED) -#define nfserr_bad_cookie cpu_to_be32(NFSERR_BAD_COOKIE) -#define nfserr_same cpu_to_be32(NFSERR_SAME) -#define nfserr_clid_inuse cpu_to_be32(NFSERR_CLID_INUSE) -#define nfserr_stale_clientid cpu_to_be32(NFSERR_STALE_CLIENTID) -#define nfserr_resource cpu_to_be32(NFSERR_RESOURCE) -#define nfserr_moved cpu_to_be32(NFSERR_MOVED) -#define nfserr_nofilehandle cpu_to_be32(NFSERR_NOFILEHANDLE) -#define nfserr_minor_vers_mismatch cpu_to_be32(NFSERR_MINOR_VERS_MISMATCH) -#define nfserr_share_denied cpu_to_be32(NFSERR_SHARE_DENIED) -#define nfserr_stale_stateid cpu_to_be32(NFSERR_STALE_STATEID) -#define nfserr_old_stateid cpu_to_be32(NFSERR_OLD_STATEID) -#define nfserr_bad_stateid cpu_to_be32(NFSERR_BAD_STATEID) -#define nfserr_bad_seqid cpu_to_be32(NFSERR_BAD_SEQID) -#define nfserr_symlink cpu_to_be32(NFSERR_SYMLINK) -#define nfserr_not_same cpu_to_be32(NFSERR_NOT_SAME) -#define nfserr_restorefh cpu_to_be32(NFSERR_RESTOREFH) -#define nfserr_attrnotsupp cpu_to_be32(NFSERR_ATTRNOTSUPP) -#define nfserr_bad_xdr cpu_to_be32(NFSERR_BAD_XDR) -#define nfserr_openmode cpu_to_be32(NFSERR_OPENMODE) -#define nfserr_locks_held cpu_to_be32(NFSERR_LOCKS_HELD) -#define nfserr_op_illegal cpu_to_be32(NFSERR_OP_ILLEGAL) -#define nfserr_grace cpu_to_be32(NFSERR_GRACE) -#define nfserr_no_grace cpu_to_be32(NFSERR_NO_GRACE) -#define nfserr_reclaim_bad cpu_to_be32(NFSERR_RECLAIM_BAD) -#define nfserr_badname cpu_to_be32(NFSERR_BADNAME) -#define nfserr_cb_path_down cpu_to_be32(NFSERR_CB_PATH_DOWN) -#define nfserr_locked cpu_to_be32(NFSERR_LOCKED) -#define nfserr_wrongsec cpu_to_be32(NFSERR_WRONGSEC) -#define nfserr_badiomode cpu_to_be32(NFS4ERR_BADIOMODE) -#define nfserr_badlayout cpu_to_be32(NFS4ERR_BADLAYOUT) -#define nfserr_bad_session_digest cpu_to_be32(NFS4ERR_BAD_SESSION_DIGEST) -#define nfserr_badsession cpu_to_be32(NFS4ERR_BADSESSION) -#define nfserr_badslot cpu_to_be32(NFS4ERR_BADSLOT) -#define nfserr_complete_already cpu_to_be32(NFS4ERR_COMPLETE_ALREADY) -#define nfserr_conn_not_bound_to_session cpu_to_be32(NFS4ERR_CONN_NOT_BOUND_TO_SESSION) -#define nfserr_deleg_already_wanted cpu_to_be32(NFS4ERR_DELEG_ALREADY_WANTED) -#define nfserr_back_chan_busy cpu_to_be32(NFS4ERR_BACK_CHAN_BUSY) -#define nfserr_layouttrylater cpu_to_be32(NFS4ERR_LAYOUTTRYLATER) -#define nfserr_layoutunavailable cpu_to_be32(NFS4ERR_LAYOUTUNAVAILABLE) -#define nfserr_nomatching_layout cpu_to_be32(NFS4ERR_NOMATCHING_LAYOUT) -#define nfserr_recallconflict cpu_to_be32(NFS4ERR_RECALLCONFLICT) -#define nfserr_unknown_layouttype cpu_to_be32(NFS4ERR_UNKNOWN_LAYOUTTYPE) -#define nfserr_seq_misordered cpu_to_be32(NFS4ERR_SEQ_MISORDERED) -#define nfserr_sequence_pos cpu_to_be32(NFS4ERR_SEQUENCE_POS) -#define nfserr_req_too_big cpu_to_be32(NFS4ERR_REQ_TOO_BIG) -#define nfserr_rep_too_big cpu_to_be32(NFS4ERR_REP_TOO_BIG) -#define nfserr_rep_too_big_to_cache cpu_to_be32(NFS4ERR_REP_TOO_BIG_TO_CACHE) -#define nfserr_retry_uncached_rep cpu_to_be32(NFS4ERR_RETRY_UNCACHED_REP) -#define nfserr_unsafe_compound cpu_to_be32(NFS4ERR_UNSAFE_COMPOUND) -#define nfserr_too_many_ops cpu_to_be32(NFS4ERR_TOO_MANY_OPS) -#define nfserr_op_not_in_session cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION) -#define nfserr_hash_alg_unsupp cpu_to_be32(NFS4ERR_HASH_ALG_UNSUPP) -#define nfserr_clientid_busy cpu_to_be32(NFS4ERR_CLIENTID_BUSY) -#define nfserr_pnfs_io_hole cpu_to_be32(NFS4ERR_PNFS_IO_HOLE) -#define nfserr_seq_false_retry cpu_to_be32(NFS4ERR_SEQ_FALSE_RETRY) -#define nfserr_bad_high_slot cpu_to_be32(NFS4ERR_BAD_HIGH_SLOT) -#define nfserr_deadsession cpu_to_be32(NFS4ERR_DEADSESSION) -#define nfserr_encr_alg_unsupp cpu_to_be32(NFS4ERR_ENCR_ALG_UNSUPP) -#define nfserr_pnfs_no_layout cpu_to_be32(NFS4ERR_PNFS_NO_LAYOUT) -#define nfserr_not_only_op cpu_to_be32(NFS4ERR_NOT_ONLY_OP) -#define nfserr_wrong_cred cpu_to_be32(NFS4ERR_WRONG_CRED) -#define nfserr_wrong_type cpu_to_be32(NFS4ERR_WRONG_TYPE) -#define nfserr_dirdeleg_unavail cpu_to_be32(NFS4ERR_DIRDELEG_UNAVAIL) -#define nfserr_reject_deleg cpu_to_be32(NFS4ERR_REJECT_DELEG) -#define nfserr_returnconflict cpu_to_be32(NFS4ERR_RETURNCONFLICT) -#define nfserr_deleg_revoked cpu_to_be32(NFS4ERR_DELEG_REVOKED) - -/* error codes for internal use */ -/* if a request fails due to kmalloc failure, it gets dropped. - * Client should resend eventually - */ -#define nfserr_dropit cpu_to_be32(30000) -/* end-of-file indicator in readdir */ -#define nfserr_eof cpu_to_be32(30001) -/* replay detected */ -#define nfserr_replay_me cpu_to_be32(11001) -/* nfs41 replay detected */ -#define nfserr_replay_cache cpu_to_be32(11002) - -/* Check for dir entries '.' and '..' */ -#define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.')) - -/* - * Time of server startup - */ -extern struct timeval nfssvc_boot; - -#ifdef CONFIG_NFSD_V4 - -/* before processing a COMPOUND operation, we have to check that there - * is enough space in the buffer for XDR encode to succeed. otherwise, - * we might process an operation with side effects, and be unable to - * tell the client that the operation succeeded. - * - * COMPOUND_SLACK_SPACE - this is the minimum bytes of buffer space - * needed to encode an "ordinary" _successful_ operation. (GETATTR, - * READ, READDIR, and READLINK have their own buffer checks.) if we - * fall below this level, we fail the next operation with NFS4ERR_RESOURCE. - * - * COMPOUND_ERR_SLACK_SPACE - this is the minimum bytes of buffer space - * needed to encode an operation which has failed with NFS4ERR_RESOURCE. - * care is taken to ensure that we never fall below this level for any - * reason. - */ -#define COMPOUND_SLACK_SPACE 140 /* OP_GETFH */ -#define COMPOUND_ERR_SLACK_SPACE 12 /* OP_SETATTR */ - -#define NFSD_LEASE_TIME (nfs4_lease_time()) -#define NFSD_LAUNDROMAT_MINTIMEOUT 10 /* seconds */ - -/* - * The following attributes are currently not supported by the NFSv4 server: - * ARCHIVE (deprecated anyway) - * HIDDEN (unlikely to be supported any time soon) - * MIMETYPE (unlikely to be supported any time soon) - * QUOTA_* (will be supported in a forthcoming patch) - * SYSTEM (unlikely to be supported any time soon) - * TIME_BACKUP (unlikely to be supported any time soon) - * TIME_CREATE (unlikely to be supported any time soon) - */ -#define NFSD4_SUPPORTED_ATTRS_WORD0 \ -(FATTR4_WORD0_SUPPORTED_ATTRS | FATTR4_WORD0_TYPE | FATTR4_WORD0_FH_EXPIRE_TYPE \ - | FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE | FATTR4_WORD0_LINK_SUPPORT \ - | FATTR4_WORD0_SYMLINK_SUPPORT | FATTR4_WORD0_NAMED_ATTR | FATTR4_WORD0_FSID \ - | FATTR4_WORD0_UNIQUE_HANDLES | FATTR4_WORD0_LEASE_TIME | FATTR4_WORD0_RDATTR_ERROR \ - | FATTR4_WORD0_ACLSUPPORT | FATTR4_WORD0_CANSETTIME | FATTR4_WORD0_CASE_INSENSITIVE \ - | FATTR4_WORD0_CASE_PRESERVING | FATTR4_WORD0_CHOWN_RESTRICTED \ - | FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FILEID | FATTR4_WORD0_FILES_AVAIL \ - | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_HOMOGENEOUS \ - | FATTR4_WORD0_MAXFILESIZE | FATTR4_WORD0_MAXLINK | FATTR4_WORD0_MAXNAME \ - | FATTR4_WORD0_MAXREAD | FATTR4_WORD0_MAXWRITE | FATTR4_WORD0_ACL) - -#define NFSD4_SUPPORTED_ATTRS_WORD1 \ -(FATTR4_WORD1_MODE | FATTR4_WORD1_NO_TRUNC | FATTR4_WORD1_NUMLINKS \ - | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP | FATTR4_WORD1_RAWDEV \ - | FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL \ - | FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS | FATTR4_WORD1_TIME_ACCESS_SET \ - | FATTR4_WORD1_TIME_DELTA | FATTR4_WORD1_TIME_METADATA \ - | FATTR4_WORD1_TIME_MODIFY | FATTR4_WORD1_TIME_MODIFY_SET | FATTR4_WORD1_MOUNTED_ON_FILEID) - -#define NFSD4_SUPPORTED_ATTRS_WORD2 0 - -#define NFSD4_1_SUPPORTED_ATTRS_WORD0 \ - NFSD4_SUPPORTED_ATTRS_WORD0 - -#define NFSD4_1_SUPPORTED_ATTRS_WORD1 \ - NFSD4_SUPPORTED_ATTRS_WORD1 - -#define NFSD4_1_SUPPORTED_ATTRS_WORD2 \ - (NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT) - -static inline u32 nfsd_suppattrs0(u32 minorversion) -{ - return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0 - : NFSD4_SUPPORTED_ATTRS_WORD0; -} - -static inline u32 nfsd_suppattrs1(u32 minorversion) -{ - return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD1 - : NFSD4_SUPPORTED_ATTRS_WORD1; -} - -static inline u32 nfsd_suppattrs2(u32 minorversion) -{ - return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD2 - : NFSD4_SUPPORTED_ATTRS_WORD2; -} - -/* These will return ERR_INVAL if specified in GETATTR or READDIR. */ -#define NFSD_WRITEONLY_ATTRS_WORD1 \ -(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) - -/* These are the only attrs allowed in CREATE/OPEN/SETATTR. */ -#define NFSD_WRITEABLE_ATTRS_WORD0 \ -(FATTR4_WORD0_SIZE | FATTR4_WORD0_ACL ) -#define NFSD_WRITEABLE_ATTRS_WORD1 \ -(FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP \ - | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) -#define NFSD_WRITEABLE_ATTRS_WORD2 0 - -#define NFSD_SUPPATTR_EXCLCREAT_WORD0 \ - NFSD_WRITEABLE_ATTRS_WORD0 -/* - * we currently store the exclusive create verifier in the v_{a,m}time - * attributes so the client can't set these at create time using EXCLUSIVE4_1 - */ -#define NFSD_SUPPATTR_EXCLCREAT_WORD1 \ - (NFSD_WRITEABLE_ATTRS_WORD1 & \ - ~(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)) -#define NFSD_SUPPATTR_EXCLCREAT_WORD2 \ - NFSD_WRITEABLE_ATTRS_WORD2 - -#endif /* CONFIG_NFSD_V4 */ - -#endif /* LINUX_NFSD_NFSD_H */ diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h deleted file mode 100644 index 2af75686e0d..00000000000 --- a/include/linux/nfsd/state.h +++ /dev/null @@ -1,409 +0,0 @@ -/* - * linux/include/nfsd/state.h - * - * Copyright (c) 2001 The Regents of the University of Michigan. - * All rights reserved. - * - * Kendrick Smith - * Andy Adamson - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the University nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - */ - -#ifndef _NFSD4_STATE_H -#define _NFSD4_STATE_H - -#include - -typedef struct { - u32 cl_boot; - u32 cl_id; -} clientid_t; - -typedef struct { - u32 so_boot; - u32 so_stateownerid; - u32 so_fileid; -} stateid_opaque_t; - -typedef struct { - u32 si_generation; - stateid_opaque_t si_opaque; -} stateid_t; -#define si_boot si_opaque.so_boot -#define si_stateownerid si_opaque.so_stateownerid -#define si_fileid si_opaque.so_fileid - -#define STATEID_FMT "(%08x/%08x/%08x/%08x)" -#define STATEID_VAL(s) \ - (s)->si_boot, \ - (s)->si_stateownerid, \ - (s)->si_fileid, \ - (s)->si_generation - -struct nfsd4_cb_sequence { - /* args/res */ - u32 cbs_minorversion; - struct nfs4_client *cbs_clp; -}; - -struct nfs4_delegation { - struct list_head dl_perfile; - struct list_head dl_perclnt; - struct list_head dl_recall_lru; /* delegation recalled */ - atomic_t dl_count; /* ref count */ - struct nfs4_client *dl_client; - struct nfs4_file *dl_file; - struct file_lock *dl_flock; - struct file *dl_vfs_file; - u32 dl_type; - time_t dl_time; -/* For recall: */ - u32 dl_ident; - stateid_t dl_stateid; - struct knfsd_fh dl_fh; - int dl_retries; -}; - -/* client delegation callback info */ -struct nfs4_cb_conn { - /* SETCLIENTID info */ - struct sockaddr_storage cb_addr; - size_t cb_addrlen; - u32 cb_prog; - u32 cb_minorversion; - u32 cb_ident; /* minorversion 0 only */ - /* RPC client info */ - atomic_t cb_set; /* successful CB_NULL call */ - struct rpc_clnt * cb_client; -}; - -/* Maximum number of slots per session. 160 is useful for long haul TCP */ -#define NFSD_MAX_SLOTS_PER_SESSION 160 -/* Maximum number of operations per session compound */ -#define NFSD_MAX_OPS_PER_COMPOUND 16 -/* Maximum session per slot cache size */ -#define NFSD_SLOT_CACHE_SIZE 1024 -/* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */ -#define NFSD_CACHE_SIZE_SLOTS_PER_SESSION 32 -#define NFSD_MAX_MEM_PER_SESSION \ - (NFSD_CACHE_SIZE_SLOTS_PER_SESSION * NFSD_SLOT_CACHE_SIZE) - -struct nfsd4_slot { - bool sl_inuse; - bool sl_cachethis; - u16 sl_opcnt; - u32 sl_seqid; - __be32 sl_status; - u32 sl_datalen; - char sl_data[]; -}; - -struct nfsd4_channel_attrs { - u32 headerpadsz; - u32 maxreq_sz; - u32 maxresp_sz; - u32 maxresp_cached; - u32 maxops; - u32 maxreqs; - u32 nr_rdma_attrs; - u32 rdma_attrs; -}; - -struct nfsd4_create_session { - clientid_t clientid; - struct nfs4_sessionid sessionid; - u32 seqid; - u32 flags; - struct nfsd4_channel_attrs fore_channel; - struct nfsd4_channel_attrs back_channel; - u32 callback_prog; - u32 uid; - u32 gid; -}; - -/* The single slot clientid cache structure */ -struct nfsd4_clid_slot { - u32 sl_seqid; - __be32 sl_status; - struct nfsd4_create_session sl_cr_ses; -}; - -struct nfsd4_session { - struct kref se_ref; - struct list_head se_hash; /* hash by sessionid */ - struct list_head se_perclnt; - u32 se_flags; - struct nfs4_client *se_client; /* for expire_client */ - struct nfs4_sessionid se_sessionid; - struct nfsd4_channel_attrs se_fchannel; - struct nfsd4_channel_attrs se_bchannel; - struct nfsd4_slot *se_slots[]; /* forward channel slots */ -}; - -static inline void -nfsd4_put_session(struct nfsd4_session *ses) -{ - extern void free_session(struct kref *kref); - kref_put(&ses->se_ref, free_session); -} - -static inline void -nfsd4_get_session(struct nfsd4_session *ses) -{ - kref_get(&ses->se_ref); -} - -/* formatted contents of nfs4_sessionid */ -struct nfsd4_sessionid { - clientid_t clientid; - u32 sequence; - u32 reserved; -}; - -#define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */ - -/* - * struct nfs4_client - one per client. Clientids live here. - * o Each nfs4_client is hashed by clientid. - * - * o Each nfs4_clients is also hashed by name - * (the opaque quantity initially sent by the client to identify itself). - * - * o cl_perclient list is used to ensure no dangling stateowner references - * when we expire the nfs4_client - */ -struct nfs4_client { - struct list_head cl_idhash; /* hash by cl_clientid.id */ - struct list_head cl_strhash; /* hash by cl_name */ - struct list_head cl_openowners; - struct list_head cl_delegations; - struct list_head cl_lru; /* tail queue */ - struct xdr_netobj cl_name; /* id generated by client */ - char cl_recdir[HEXDIR_LEN]; /* recovery dir */ - nfs4_verifier cl_verifier; /* generated by client */ - time_t cl_time; /* time of last lease renewal */ - struct sockaddr_storage cl_addr; /* client ipaddress */ - u32 cl_flavor; /* setclientid pseudoflavor */ - char *cl_principal; /* setclientid principal name */ - struct svc_cred cl_cred; /* setclientid principal */ - clientid_t cl_clientid; /* generated by server */ - nfs4_verifier cl_confirm; /* generated by server */ - struct nfs4_cb_conn cl_cb_conn; /* callback info */ - atomic_t cl_count; /* ref count */ - u32 cl_firststate; /* recovery dir creation */ - - /* for nfs41 */ - struct list_head cl_sessions; - struct nfsd4_clid_slot cl_cs_slot; /* create_session slot */ - u32 cl_exchange_flags; - struct nfs4_sessionid cl_sessionid; - - /* for nfs41 callbacks */ - /* We currently support a single back channel with a single slot */ - unsigned long cl_cb_slot_busy; - u32 cl_cb_seq_nr; - struct svc_xprt *cl_cb_xprt; /* 4.1 callback transport */ - struct rpc_wait_queue cl_cb_waitq; /* backchannel callers may */ - /* wait here for slots */ -}; - -/* struct nfs4_client_reset - * one per old client. Populates reset_str_hashtbl. Filled from conf_id_hashtbl - * upon lease reset, or from upcall to state_daemon (to read in state - * from non-volitile storage) upon reboot. - */ -struct nfs4_client_reclaim { - struct list_head cr_strhash; /* hash by cr_name */ - char cr_recdir[HEXDIR_LEN]; /* recover dir */ -}; - -static inline void -update_stateid(stateid_t *stateid) -{ - stateid->si_generation++; -} - -/* A reasonable value for REPLAY_ISIZE was estimated as follows: - * The OPEN response, typically the largest, requires - * 4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) + 8(verifier) + - * 4(deleg. type) + 8(deleg. stateid) + 4(deleg. recall flag) + - * 20(deleg. space limit) + ~32(deleg. ace) = 112 bytes - */ - -#define NFSD4_REPLAY_ISIZE 112 - -/* - * Replay buffer, where the result of the last seqid-mutating operation - * is cached. - */ -struct nfs4_replay { - __be32 rp_status; - unsigned int rp_buflen; - char *rp_buf; - unsigned intrp_allocated; - struct knfsd_fh rp_openfh; - char rp_ibuf[NFSD4_REPLAY_ISIZE]; -}; - -/* -* nfs4_stateowner can either be an open_owner, or a lock_owner -* -* so_idhash: stateid_hashtbl[] for open owner, lockstateid_hashtbl[] -* for lock_owner -* so_strhash: ownerstr_hashtbl[] for open_owner, lock_ownerstr_hashtbl[] -* for lock_owner -* so_perclient: nfs4_client->cl_perclient entry - used when nfs4_client -* struct is reaped. -* so_perfilestate: heads the list of nfs4_stateid (either open or lock) -* and is used to ensure no dangling nfs4_stateid references when we -* release a stateowner. -* so_perlockowner: (open) nfs4_stateid->st_perlockowner entry - used when -* close is called to reap associated byte-range locks -* so_close_lru: (open) stateowner is placed on this list instead of being -* reaped (when so_perfilestate is empty) to hold the last close replay. -* reaped by laundramat thread after lease period. -*/ -struct nfs4_stateowner { - struct kref so_ref; - struct list_head so_idhash; /* hash by so_id */ - struct list_head so_strhash; /* hash by op_name */ - struct list_head so_perclient; - struct list_head so_stateids; - struct list_head so_perstateid; /* for lockowners only */ - struct list_head so_close_lru; /* tail queue */ - time_t so_time; /* time of placement on so_close_lru */ - int so_is_open_owner; /* 1=openowner,0=lockowner */ - u32 so_id; - struct nfs4_client * so_client; - /* after increment in ENCODE_SEQID_OP_TAIL, represents the next - * sequence id expected from the client: */ - u32 so_seqid; - struct xdr_netobj so_owner; /* open owner name */ - int so_confirmed; /* successful OPEN_CONFIRM? */ - struct nfs4_replay so_replay; -}; - -/* -* nfs4_file: a file opened by some number of (open) nfs4_stateowners. -* o fi_perfile list is used to search for conflicting -* share_acces, share_deny on the file. -*/ -struct nfs4_file { - atomic_t fi_ref; - struct list_head fi_hash; /* hash by "struct inode *" */ - struct list_head fi_stateids; - struct list_head fi_delegations; - struct inode *fi_inode; - u32 fi_id; /* used with stateowner->so_id - * for stateid_hashtbl hash */ - bool fi_had_conflict; -}; - -/* -* nfs4_stateid can either be an open stateid or (eventually) a lock stateid -* -* (open)nfs4_stateid: one per (open)nfs4_stateowner, nfs4_file -* -* st_hash: stateid_hashtbl[] entry or lockstateid_hashtbl entry -* st_perfile: file_hashtbl[] entry. -* st_perfile_state: nfs4_stateowner->so_perfilestate -* st_perlockowner: (open stateid) list of lock nfs4_stateowners -* st_access_bmap: used only for open stateid -* st_deny_bmap: used only for open stateid -* st_openstp: open stateid lock stateid was derived from -* -* XXX: open stateids and lock stateids have diverged sufficiently that -* we should consider defining separate structs for the two cases. -*/ - -struct nfs4_stateid { - struct list_head st_hash; - struct list_head st_perfile; - struct list_head st_perstateowner; - struct list_head st_lockowners; - struct nfs4_stateowner * st_stateowner; - struct nfs4_file * st_file; - stateid_t st_stateid; - struct file * st_vfs_file; - unsigned long st_access_bmap; - unsigned long st_deny_bmap; - struct nfs4_stateid * st_openstp; -}; - -/* flags for preprocess_seqid_op() */ -#define HAS_SESSION 0x00000001 -#define CONFIRM 0x00000002 -#define OPEN_STATE 0x00000004 -#define LOCK_STATE 0x00000008 -#define RD_STATE 0x00000010 -#define WR_STATE 0x00000020 -#define CLOSE_STATE 0x00000040 - -#define seqid_mutating_err(err) \ - (((err) != nfserr_stale_clientid) && \ - ((err) != nfserr_bad_seqid) && \ - ((err) != nfserr_stale_stateid) && \ - ((err) != nfserr_bad_stateid)) - -struct nfsd4_compound_state; - -extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, - stateid_t *stateid, int flags, struct file **filp); -extern void nfs4_lock_state(void); -extern void nfs4_unlock_state(void); -extern int nfs4_in_grace(void); -extern __be32 nfs4_check_open_reclaim(clientid_t *clid); -extern void put_nfs4_client(struct nfs4_client *clp); -extern void nfs4_free_stateowner(struct kref *kref); -extern int set_callback_cred(void); -extern void nfsd4_probe_callback(struct nfs4_client *clp); -extern void nfsd4_cb_recall(struct nfs4_delegation *dp); -extern void nfs4_put_delegation(struct nfs4_delegation *dp); -extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname); -extern void nfsd4_init_recdir(char *recdir_name); -extern int nfsd4_recdir_load(void); -extern void nfsd4_shutdown_recdir(void); -extern int nfs4_client_to_reclaim(const char *name); -extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id); -extern void nfsd4_recdir_purge_old(void); -extern int nfsd4_create_clid_dir(struct nfs4_client *clp); -extern void nfsd4_remove_clid_dir(struct nfs4_client *clp); - -static inline void -nfs4_put_stateowner(struct nfs4_stateowner *so) -{ - kref_put(&so->so_ref, nfs4_free_stateowner); -} - -static inline void -nfs4_get_stateowner(struct nfs4_stateowner *so) -{ - kref_get(&so->so_ref); -} - -#endif /* NFSD4_STATE_H */ diff --git a/include/linux/nfsd/xdr.h b/include/linux/nfsd/xdr.h deleted file mode 100644 index 58f824d854c..00000000000 --- a/include/linux/nfsd/xdr.h +++ /dev/null @@ -1,176 +0,0 @@ -/* - * linux/include/linux/nfsd/xdr.h - * - * XDR types for nfsd. This is mainly a typing exercise. - */ - -#ifndef LINUX_NFSD_H -#define LINUX_NFSD_H - -#include -#include - -struct nfsd_fhandle { - struct svc_fh fh; -}; - -struct nfsd_sattrargs { - struct svc_fh fh; - struct iattr attrs; -}; - -struct nfsd_diropargs { - struct svc_fh fh; - char * name; - unsigned int len; -}; - -struct nfsd_readargs { - struct svc_fh fh; - __u32 offset; - __u32 count; - int vlen; -}; - -struct nfsd_writeargs { - svc_fh fh; - __u32 offset; - int len; - int vlen; -}; - -struct nfsd_createargs { - struct svc_fh fh; - char * name; - unsigned int len; - struct iattr attrs; -}; - -struct nfsd_renameargs { - struct svc_fh ffh; - char * fname; - unsigned int flen; - struct svc_fh tfh; - char * tname; - unsigned int tlen; -}; - -struct nfsd_readlinkargs { - struct svc_fh fh; - char * buffer; -}; - -struct nfsd_linkargs { - struct svc_fh ffh; - struct svc_fh tfh; - char * tname; - unsigned int tlen; -}; - -struct nfsd_symlinkargs { - struct svc_fh ffh; - char * fname; - unsigned int flen; - char * tname; - unsigned int tlen; - struct iattr attrs; -}; - -struct nfsd_readdirargs { - struct svc_fh fh; - __u32 cookie; - __u32 count; - __be32 * buffer; -}; - -struct nfsd_attrstat { - struct svc_fh fh; - struct kstat stat; -}; - -struct nfsd_diropres { - struct svc_fh fh; - struct kstat stat; -}; - -struct nfsd_readlinkres { - int len; -}; - -struct nfsd_readres { - struct svc_fh fh; - unsigned long count; - struct kstat stat; -}; - -struct nfsd_readdirres { - int count; - - struct readdir_cd common; - __be32 * buffer; - int buflen; - __be32 * offset; -}; - -struct nfsd_statfsres { - struct kstatfs stats; -}; - -/* - * Storage requirements for XDR arguments and results. - */ -union nfsd_xdrstore { - struct nfsd_sattrargs sattr; - struct nfsd_diropargs dirop; - struct nfsd_readargs read; - struct nfsd_writeargs write; - struct nfsd_createargs create; - struct nfsd_renameargs rename; - struct nfsd_linkargs link; - struct nfsd_symlinkargs symlink; - struct nfsd_readdirargs readdir; -}; - -#define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore) - - -int nfssvc_decode_void(struct svc_rqst *, __be32 *, void *); -int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); -int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *, - struct nfsd_sattrargs *); -int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *, - struct nfsd_diropargs *); -int nfssvc_decode_readargs(struct svc_rqst *, __be32 *, - struct nfsd_readargs *); -int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *, - struct nfsd_writeargs *); -int nfssvc_decode_createargs(struct svc_rqst *, __be32 *, - struct nfsd_createargs *); -int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *, - struct nfsd_renameargs *); -int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *, - struct nfsd_readlinkargs *); -int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *, - struct nfsd_linkargs *); -int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *, - struct nfsd_symlinkargs *); -int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *, - struct nfsd_readdirargs *); -int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *); -int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *); -int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *); -int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd_readlinkres *); -int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *); -int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *); -int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *); - -int nfssvc_encode_entry(void *, const char *name, - int namlen, loff_t offset, u64 ino, unsigned int); - -int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); - -/* Helper functions for NFSv2 ACL code */ -__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp); -__be32 *nfs2svc_decode_fh(__be32 *p, struct svc_fh *fhp); - -#endif /* LINUX_NFSD_H */ diff --git a/include/linux/nfsd/xdr3.h b/include/linux/nfsd/xdr3.h deleted file mode 100644 index 421eddd65a2..00000000000 --- a/include/linux/nfsd/xdr3.h +++ /dev/null @@ -1,346 +0,0 @@ -/* - * linux/include/linux/nfsd/xdr3.h - * - * XDR types for NFSv3 in nfsd. - * - * Copyright (C) 1996-1998, Olaf Kirch - */ - -#ifndef _LINUX_NFSD_XDR3_H -#define _LINUX_NFSD_XDR3_H - -#include - -struct nfsd3_sattrargs { - struct svc_fh fh; - struct iattr attrs; - int check_guard; - time_t guardtime; -}; - -struct nfsd3_diropargs { - struct svc_fh fh; - char * name; - unsigned int len; -}; - -struct nfsd3_accessargs { - struct svc_fh fh; - unsigned int access; -}; - -struct nfsd3_readargs { - struct svc_fh fh; - __u64 offset; - __u32 count; - int vlen; -}; - -struct nfsd3_writeargs { - svc_fh fh; - __u64 offset; - __u32 count; - int stable; - __u32 len; - int vlen; -}; - -struct nfsd3_createargs { - struct svc_fh fh; - char * name; - unsigned int len; - int createmode; - struct iattr attrs; - __be32 * verf; -}; - -struct nfsd3_mknodargs { - struct svc_fh fh; - char * name; - unsigned int len; - __u32 ftype; - __u32 major, minor; - struct iattr attrs; -}; - -struct nfsd3_renameargs { - struct svc_fh ffh; - char * fname; - unsigned int flen; - struct svc_fh tfh; - char * tname; - unsigned int tlen; -}; - -struct nfsd3_readlinkargs { - struct svc_fh fh; - char * buffer; -}; - -struct nfsd3_linkargs { - struct svc_fh ffh; - struct svc_fh tfh; - char * tname; - unsigned int tlen; -}; - -struct nfsd3_symlinkargs { - struct svc_fh ffh; - char * fname; - unsigned int flen; - char * tname; - unsigned int tlen; - struct iattr attrs; -}; - -struct nfsd3_readdirargs { - struct svc_fh fh; - __u64 cookie; - __u32 dircount; - __u32 count; - __be32 * verf; - __be32 * buffer; -}; - -struct nfsd3_commitargs { - struct svc_fh fh; - __u64 offset; - __u32 count; -}; - -struct nfsd3_getaclargs { - struct svc_fh fh; - int mask; -}; - -struct posix_acl; -struct nfsd3_setaclargs { - struct svc_fh fh; - int mask; - struct posix_acl *acl_access; - struct posix_acl *acl_default; -}; - -struct nfsd3_attrstat { - __be32 status; - struct svc_fh fh; - struct kstat stat; -}; - -/* LOOKUP, CREATE, MKDIR, SYMLINK, MKNOD */ -struct nfsd3_diropres { - __be32 status; - struct svc_fh dirfh; - struct svc_fh fh; -}; - -struct nfsd3_accessres { - __be32 status; - struct svc_fh fh; - __u32 access; -}; - -struct nfsd3_readlinkres { - __be32 status; - struct svc_fh fh; - __u32 len; -}; - -struct nfsd3_readres { - __be32 status; - struct svc_fh fh; - unsigned long count; - int eof; -}; - -struct nfsd3_writeres { - __be32 status; - struct svc_fh fh; - unsigned long count; - int committed; -}; - -struct nfsd3_renameres { - __be32 status; - struct svc_fh ffh; - struct svc_fh tfh; -}; - -struct nfsd3_linkres { - __be32 status; - struct svc_fh tfh; - struct svc_fh fh; -}; - -struct nfsd3_readdirres { - __be32 status; - struct svc_fh fh; - int count; - __be32 verf[2]; - - struct readdir_cd common; - __be32 * buffer; - int buflen; - __be32 * offset; - __be32 * offset1; - struct svc_rqst * rqstp; - -}; - -struct nfsd3_fsstatres { - __be32 status; - struct kstatfs stats; - __u32 invarsec; -}; - -struct nfsd3_fsinfores { - __be32 status; - __u32 f_rtmax; - __u32 f_rtpref; - __u32 f_rtmult; - __u32 f_wtmax; - __u32 f_wtpref; - __u32 f_wtmult; - __u32 f_dtpref; - __u64 f_maxfilesize; - __u32 f_properties; -}; - -struct nfsd3_pathconfres { - __be32 status; - __u32 p_link_max; - __u32 p_name_max; - __u32 p_no_trunc; - __u32 p_chown_restricted; - __u32 p_case_insensitive; - __u32 p_case_preserving; -}; - -struct nfsd3_commitres { - __be32 status; - struct svc_fh fh; -}; - -struct nfsd3_getaclres { - __be32 status; - struct svc_fh fh; - int mask; - struct posix_acl *acl_access; - struct posix_acl *acl_default; -}; - -/* dummy type for release */ -struct nfsd3_fhandle_pair { - __u32 dummy; - struct svc_fh fh1; - struct svc_fh fh2; -}; - -/* - * Storage requirements for XDR arguments and results. - */ -union nfsd3_xdrstore { - struct nfsd3_sattrargs sattrargs; - struct nfsd3_diropargs diropargs; - struct nfsd3_readargs readargs; - struct nfsd3_writeargs writeargs; - struct nfsd3_createargs createargs; - struct nfsd3_renameargs renameargs; - struct nfsd3_linkargs linkargs; - struct nfsd3_symlinkargs symlinkargs; - struct nfsd3_readdirargs readdirargs; - struct nfsd3_diropres diropres; - struct nfsd3_accessres accessres; - struct nfsd3_readlinkres readlinkres; - struct nfsd3_readres readres; - struct nfsd3_writeres writeres; - struct nfsd3_renameres renameres; - struct nfsd3_linkres linkres; - struct nfsd3_readdirres readdirres; - struct nfsd3_fsstatres fsstatres; - struct nfsd3_fsinfores fsinfores; - struct nfsd3_pathconfres pathconfres; - struct nfsd3_commitres commitres; - struct nfsd3_getaclres getaclres; -}; - -#define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore) - -int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); -int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *, - struct nfsd3_sattrargs *); -int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *, - struct nfsd3_diropargs *); -int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *, - struct nfsd3_accessargs *); -int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *, - struct nfsd3_readargs *); -int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *, - struct nfsd3_writeargs *); -int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *, - struct nfsd3_createargs *); -int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *, - struct nfsd3_createargs *); -int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *, - struct nfsd3_mknodargs *); -int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *, - struct nfsd3_renameargs *); -int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *, - struct nfsd3_readlinkargs *); -int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *, - struct nfsd3_linkargs *); -int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *, - struct nfsd3_symlinkargs *); -int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *, - struct nfsd3_readdirargs *); -int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *, - struct nfsd3_readdirargs *); -int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *, - struct nfsd3_commitargs *); -int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *); -int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *, - struct nfsd3_diropres *); -int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *, - struct nfsd3_accessres *); -int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *, - struct nfsd3_readlinkres *); -int nfs3svc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd3_readres *); -int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *, struct nfsd3_writeres *); -int nfs3svc_encode_createres(struct svc_rqst *, __be32 *, - struct nfsd3_diropres *); -int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *, - struct nfsd3_renameres *); -int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *, - struct nfsd3_linkres *); -int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *, - struct nfsd3_readdirres *); -int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *, - struct nfsd3_fsstatres *); -int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *, - struct nfsd3_fsinfores *); -int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *, - struct nfsd3_pathconfres *); -int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *, - struct nfsd3_commitres *); - -int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *, - struct nfsd3_fhandle_pair *); -int nfs3svc_encode_entry(void *, const char *name, - int namlen, loff_t offset, u64 ino, - unsigned int); -int nfs3svc_encode_entry_plus(void *, const char *name, - int namlen, loff_t offset, u64 ino, - unsigned int); -/* Helper functions for NFSv3 ACL code */ -__be32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, - struct svc_fh *fhp); -__be32 *nfs3svc_decode_fh(__be32 *p, struct svc_fh *fhp); - - -#endif /* _LINUX_NFSD_XDR3_H */ diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h deleted file mode 100644 index 1bf266239c7..00000000000 --- a/include/linux/nfsd/xdr4.h +++ /dev/null @@ -1,564 +0,0 @@ -/* - * include/linux/nfsd/xdr4.h - * - * Server-side types for NFSv4. - * - * Copyright (c) 2002 The Regents of the University of Michigan. - * All rights reserved. - * - * Kendrick Smith - * Andy Adamson - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the University nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - */ - -#ifndef _LINUX_NFSD_XDR4_H -#define _LINUX_NFSD_XDR4_H - -#include -#include - -#define NFSD4_MAX_TAGLEN 128 -#define XDR_LEN(n) (((n) + 3) & ~3) - -struct nfsd4_compound_state { - struct svc_fh current_fh; - struct svc_fh save_fh; - struct nfs4_stateowner *replay_owner; - /* For sessions DRC */ - struct nfsd4_session *session; - struct nfsd4_slot *slot; - __be32 *datap; - size_t iovlen; - u32 minorversion; - u32 status; -}; - -static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs) -{ - return cs->slot != NULL; -} - -struct nfsd4_change_info { - u32 atomic; - bool change_supported; - u32 before_ctime_sec; - u32 before_ctime_nsec; - u64 before_change; - u32 after_ctime_sec; - u32 after_ctime_nsec; - u64 after_change; -}; - -struct nfsd4_access { - u32 ac_req_access; /* request */ - u32 ac_supported; /* response */ - u32 ac_resp_access; /* response */ -}; - -struct nfsd4_close { - u32 cl_seqid; /* request */ - stateid_t cl_stateid; /* request+response */ - struct nfs4_stateowner * cl_stateowner; /* response */ -}; - -struct nfsd4_commit { - u64 co_offset; /* request */ - u32 co_count; /* request */ - nfs4_verifier co_verf; /* response */ -}; - -struct nfsd4_create { - u32 cr_namelen; /* request */ - char * cr_name; /* request */ - u32 cr_type; /* request */ - union { /* request */ - struct { - u32 namelen; - char *name; - } link; /* NF4LNK */ - struct { - u32 specdata1; - u32 specdata2; - } dev; /* NF4BLK, NF4CHR */ - } u; - u32 cr_bmval[3]; /* request */ - struct iattr cr_iattr; /* request */ - struct nfsd4_change_info cr_cinfo; /* response */ - struct nfs4_acl *cr_acl; -}; -#define cr_linklen u.link.namelen -#define cr_linkname u.link.name -#define cr_specdata1 u.dev.specdata1 -#define cr_specdata2 u.dev.specdata2 - -struct nfsd4_delegreturn { - stateid_t dr_stateid; -}; - -struct nfsd4_getattr { - u32 ga_bmval[3]; /* request */ - struct svc_fh *ga_fhp; /* response */ -}; - -struct nfsd4_link { - u32 li_namelen; /* request */ - char * li_name; /* request */ - struct nfsd4_change_info li_cinfo; /* response */ -}; - -struct nfsd4_lock_denied { - clientid_t ld_clientid; - struct nfs4_stateowner *ld_sop; - u64 ld_start; - u64 ld_length; - u32 ld_type; -}; - -struct nfsd4_lock { - /* request */ - u32 lk_type; - u32 lk_reclaim; /* boolean */ - u64 lk_offset; - u64 lk_length; - u32 lk_is_new; - union { - struct { - u32 open_seqid; - stateid_t open_stateid; - u32 lock_seqid; - clientid_t clientid; - struct xdr_netobj owner; - } new; - struct { - stateid_t lock_stateid; - u32 lock_seqid; - } old; - } v; - - /* response */ - union { - struct { - stateid_t stateid; - } ok; - struct nfsd4_lock_denied denied; - } u; - /* The lk_replay_owner is the open owner in the open_to_lock_owner - * case and the lock owner otherwise: */ - struct nfs4_stateowner *lk_replay_owner; -}; -#define lk_new_open_seqid v.new.open_seqid -#define lk_new_open_stateid v.new.open_stateid -#define lk_new_lock_seqid v.new.lock_seqid -#define lk_new_clientid v.new.clientid -#define lk_new_owner v.new.owner -#define lk_old_lock_stateid v.old.lock_stateid -#define lk_old_lock_seqid v.old.lock_seqid - -#define lk_rflags u.ok.rflags -#define lk_resp_stateid u.ok.stateid -#define lk_denied u.denied - - -struct nfsd4_lockt { - u32 lt_type; - clientid_t lt_clientid; - struct xdr_netobj lt_owner; - u64 lt_offset; - u64 lt_length; - struct nfs4_stateowner * lt_stateowner; - struct nfsd4_lock_denied lt_denied; -}; - - -struct nfsd4_locku { - u32 lu_type; - u32 lu_seqid; - stateid_t lu_stateid; - u64 lu_offset; - u64 lu_length; - struct nfs4_stateowner *lu_stateowner; -}; - - -struct nfsd4_lookup { - u32 lo_len; /* request */ - char * lo_name; /* request */ -}; - -struct nfsd4_putfh { - u32 pf_fhlen; /* request */ - char *pf_fhval; /* request */ -}; - -struct nfsd4_open { - u32 op_claim_type; /* request */ - struct xdr_netobj op_fname; /* request - everything but CLAIM_PREV */ - u32 op_delegate_type; /* request - CLAIM_PREV only */ - stateid_t op_delegate_stateid; /* request - response */ - u32 op_create; /* request */ - u32 op_createmode; /* request */ - u32 op_bmval[3]; /* request */ - struct iattr iattr; /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */ - nfs4_verifier verf; /* EXCLUSIVE4 */ - clientid_t op_clientid; /* request */ - struct xdr_netobj op_owner; /* request */ - u32 op_seqid; /* request */ - u32 op_share_access; /* request */ - u32 op_share_deny; /* request */ - stateid_t op_stateid; /* response */ - u32 op_recall; /* recall */ - struct nfsd4_change_info op_cinfo; /* response */ - u32 op_rflags; /* response */ - int op_truncate; /* used during processing */ - struct nfs4_stateowner *op_stateowner; /* used during processing */ - struct nfs4_acl *op_acl; -}; -#define op_iattr iattr -#define op_verf verf - -struct nfsd4_open_confirm { - stateid_t oc_req_stateid /* request */; - u32 oc_seqid /* request */; - stateid_t oc_resp_stateid /* response */; - struct nfs4_stateowner * oc_stateowner; /* response */ -}; - -struct nfsd4_open_downgrade { - stateid_t od_stateid; - u32 od_seqid; - u32 od_share_access; - u32 od_share_deny; - struct nfs4_stateowner *od_stateowner; -}; - - -struct nfsd4_read { - stateid_t rd_stateid; /* request */ - u64 rd_offset; /* request */ - u32 rd_length; /* request */ - int rd_vlen; - struct file *rd_filp; - - struct svc_rqst *rd_rqstp; /* response */ - struct svc_fh * rd_fhp; /* response */ -}; - -struct nfsd4_readdir { - u64 rd_cookie; /* request */ - nfs4_verifier rd_verf; /* request */ - u32 rd_dircount; /* request */ - u32 rd_maxcount; /* request */ - u32 rd_bmval[3]; /* request */ - struct svc_rqst *rd_rqstp; /* response */ - struct svc_fh * rd_fhp; /* response */ - - struct readdir_cd common; - __be32 * buffer; - int buflen; - __be32 * offset; -}; - -struct nfsd4_release_lockowner { - clientid_t rl_clientid; - struct xdr_netobj rl_owner; -}; -struct nfsd4_readlink { - struct svc_rqst *rl_rqstp; /* request */ - struct svc_fh * rl_fhp; /* request */ -}; - -struct nfsd4_remove { - u32 rm_namelen; /* request */ - char * rm_name; /* request */ - struct nfsd4_change_info rm_cinfo; /* response */ -}; - -struct nfsd4_rename { - u32 rn_snamelen; /* request */ - char * rn_sname; /* request */ - u32 rn_tnamelen; /* request */ - char * rn_tname; /* request */ - struct nfsd4_change_info rn_sinfo; /* response */ - struct nfsd4_change_info rn_tinfo; /* response */ -}; - -struct nfsd4_secinfo { - u32 si_namelen; /* request */ - char *si_name; /* request */ - struct svc_export *si_exp; /* response */ -}; - -struct nfsd4_setattr { - stateid_t sa_stateid; /* request */ - u32 sa_bmval[3]; /* request */ - struct iattr sa_iattr; /* request */ - struct nfs4_acl *sa_acl; -}; - -struct nfsd4_setclientid { - nfs4_verifier se_verf; /* request */ - u32 se_namelen; /* request */ - char * se_name; /* request */ - u32 se_callback_prog; /* request */ - u32 se_callback_netid_len; /* request */ - char * se_callback_netid_val; /* request */ - u32 se_callback_addr_len; /* request */ - char * se_callback_addr_val; /* request */ - u32 se_callback_ident; /* request */ - clientid_t se_clientid; /* response */ - nfs4_verifier se_confirm; /* response */ -}; - -struct nfsd4_setclientid_confirm { - clientid_t sc_clientid; - nfs4_verifier sc_confirm; -}; - -/* also used for NVERIFY */ -struct nfsd4_verify { - u32 ve_bmval[3]; /* request */ - u32 ve_attrlen; /* request */ - char * ve_attrval; /* request */ -}; - -struct nfsd4_write { - stateid_t wr_stateid; /* request */ - u64 wr_offset; /* request */ - u32 wr_stable_how; /* request */ - u32 wr_buflen; /* request */ - int wr_vlen; - - u32 wr_bytes_written; /* response */ - u32 wr_how_written; /* response */ - nfs4_verifier wr_verifier; /* response */ -}; - -struct nfsd4_exchange_id { - nfs4_verifier verifier; - struct xdr_netobj clname; - u32 flags; - clientid_t clientid; - u32 seqid; - int spa_how; -}; - -struct nfsd4_sequence { - struct nfs4_sessionid sessionid; /* request/response */ - u32 seqid; /* request/response */ - u32 slotid; /* request/response */ - u32 maxslots; /* request/response */ - u32 cachethis; /* request */ -#if 0 - u32 target_maxslots; /* response */ - u32 status_flags; /* response */ -#endif /* not yet */ -}; - -struct nfsd4_destroy_session { - struct nfs4_sessionid sessionid; -}; - -struct nfsd4_op { - int opnum; - __be32 status; - union { - struct nfsd4_access access; - struct nfsd4_close close; - struct nfsd4_commit commit; - struct nfsd4_create create; - struct nfsd4_delegreturn delegreturn; - struct nfsd4_getattr getattr; - struct svc_fh * getfh; - struct nfsd4_link link; - struct nfsd4_lock lock; - struct nfsd4_lockt lockt; - struct nfsd4_locku locku; - struct nfsd4_lookup lookup; - struct nfsd4_verify nverify; - struct nfsd4_open open; - struct nfsd4_open_confirm open_confirm; - struct nfsd4_open_downgrade open_downgrade; - struct nfsd4_putfh putfh; - struct nfsd4_read read; - struct nfsd4_readdir readdir; - struct nfsd4_readlink readlink; - struct nfsd4_remove remove; - struct nfsd4_rename rename; - clientid_t renew; - struct nfsd4_secinfo secinfo; - struct nfsd4_setattr setattr; - struct nfsd4_setclientid setclientid; - struct nfsd4_setclientid_confirm setclientid_confirm; - struct nfsd4_verify verify; - struct nfsd4_write write; - struct nfsd4_release_lockowner release_lockowner; - - /* NFSv4.1 */ - struct nfsd4_exchange_id exchange_id; - struct nfsd4_create_session create_session; - struct nfsd4_destroy_session destroy_session; - struct nfsd4_sequence sequence; - } u; - struct nfs4_replay * replay; -}; - -struct nfsd4_compoundargs { - /* scratch variables for XDR decode */ - __be32 * p; - __be32 * end; - struct page ** pagelist; - int pagelen; - __be32 tmp[8]; - __be32 * tmpp; - struct tmpbuf { - struct tmpbuf *next; - void (*release)(const void *); - void *buf; - } *to_free; - - struct svc_rqst *rqstp; - - u32 taglen; - char * tag; - u32 minorversion; - u32 opcnt; - struct nfsd4_op *ops; - struct nfsd4_op iops[8]; -}; - -struct nfsd4_compoundres { - /* scratch variables for XDR encode */ - __be32 * p; - __be32 * end; - struct xdr_buf * xbuf; - struct svc_rqst * rqstp; - - u32 taglen; - char * tag; - u32 opcnt; - __be32 * tagp; /* tag, opcount encode location */ - struct nfsd4_compound_state cstate; -}; - -static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp) -{ - struct nfsd4_compoundargs *args = resp->rqstp->rq_argp; - return resp->opcnt == 1 && args->ops[0].opnum == OP_SEQUENCE; -} - -static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp) -{ - return !resp->cstate.slot->sl_cachethis || nfsd4_is_solo_sequence(resp); -} - -#define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) - -static inline void -set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) -{ - BUG_ON(!fhp->fh_pre_saved || !fhp->fh_post_saved); - cinfo->atomic = 1; - cinfo->change_supported = IS_I_VERSION(fhp->fh_dentry->d_inode); - if (cinfo->change_supported) { - cinfo->before_change = fhp->fh_pre_change; - cinfo->after_change = fhp->fh_post_change; - } else { - cinfo->before_ctime_sec = fhp->fh_pre_ctime.tv_sec; - cinfo->before_ctime_nsec = fhp->fh_pre_ctime.tv_nsec; - cinfo->after_ctime_sec = fhp->fh_post_attr.ctime.tv_sec; - cinfo->after_ctime_nsec = fhp->fh_post_attr.ctime.tv_nsec; - } -} - -int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *); -int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *, - struct nfsd4_compoundargs *); -int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, - struct nfsd4_compoundres *); -void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); -void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op); -__be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, - struct dentry *dentry, __be32 *buffer, int *countp, - u32 *bmval, struct svc_rqst *, int ignore_crossmnt); -extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_setclientid *setclid); -extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_setclientid_confirm *setclientid_confirm); -extern void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp); -extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, - struct nfsd4_sequence *seq); -extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, -struct nfsd4_exchange_id *); - extern __be32 nfsd4_create_session(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_create_session *); -extern __be32 nfsd4_sequence(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_sequence *); -extern __be32 nfsd4_destroy_session(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_destroy_session *); -extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *, - struct nfsd4_open *open); -extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, - struct svc_fh *current_fh, struct nfsd4_open *open); -extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_open_confirm *oc); -extern __be32 nfsd4_close(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_close *close); -extern __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_open_downgrade *od); -extern __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *, - struct nfsd4_lock *lock); -extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_lockt *lockt); -extern __be32 nfsd4_locku(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_locku *locku); -extern __be32 -nfsd4_release_lockowner(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_release_lockowner *rlockowner); -extern void nfsd4_release_compoundargs(struct nfsd4_compoundargs *); -extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr); -extern __be32 nfsd4_renew(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, clientid_t *clid); -#endif - -/* - * Local variables: - * c-basic-offset: 8 - * End: - */ -- cgit v1.2.3-18-g5258 From e8e8753f7a32ce4f636771126fc8eba0dc4ad817 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 14 Dec 2009 12:53:32 -0500 Subject: nfsd: new interface to advertise export features Soon we will add the new V4ROOT flag, and allow the INSECURE flag to vary by pseudoflavor. It would be useful for nfs-utils (for example, for improved exportfs error reporting) to be able to know when this happens. Use this new interface for that purpose. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfsctl.c | 21 +++++++++++++++++++++ include/linux/nfsd/export.h | 3 ++- 2 files changed, 23 insertions(+), 1 deletion(-) diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 0415680d3f5..e7051ac4dc7 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -31,6 +31,7 @@ enum { NFSD_Getfd, NFSD_Getfs, NFSD_List, + NFSD_Export_features, NFSD_Fh, NFSD_FO_UnlockIP, NFSD_FO_UnlockFS, @@ -149,6 +150,24 @@ static const struct file_operations exports_operations = { .owner = THIS_MODULE, }; +static int export_features_show(struct seq_file *m, void *v) +{ + seq_printf(m, "0x%x 0x%x\n", NFSEXP_ALLFLAGS, NFSEXP_SECINFO_FLAGS); + return 0; +} + +static int export_features_open(struct inode *inode, struct file *file) +{ + return single_open(file, export_features_show, NULL); +} + +static struct file_operations export_features_operations = { + .open = export_features_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + extern int nfsd_pool_stats_open(struct inode *inode, struct file *file); extern int nfsd_pool_stats_release(struct inode *inode, struct file *file); @@ -1306,6 +1325,8 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent) [NFSD_Getfd] = {".getfd", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Getfs] = {".getfs", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_List] = {"exports", &exports_operations, S_IRUGO}, + [NFSD_Export_features] = {"export_features", + &export_features_operations, S_IRUGO}, [NFSD_FO_UnlockIP] = {"unlock_ip", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_FO_UnlockFS] = {"unlock_filesystem", diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index ef3d416fcf6..4f1df1d7312 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -39,7 +39,8 @@ #define NFSEXP_FSID 0x2000 #define NFSEXP_CROSSMOUNT 0x4000 #define NFSEXP_NOACL 0x8000 /* reserved for possible ACL related use */ -#define NFSEXP_ALLFLAGS 0xFE3F +/* All flags that we claim to support. (Note we don't support NOACL.) */ +#define NFSEXP_ALLFLAGS 0x7E3F /* The flags that may vary depending on security flavor: */ #define NFSEXP_SECINFO_FLAGS (NFSEXP_READONLY | NFSEXP_ROOTSQUASH \ -- cgit v1.2.3-18-g5258 From 12045a6ee9908b38b6d286530c7d816e39071346 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 8 Dec 2009 18:15:52 -0500 Subject: nfsd: let "insecure" flag vary by pseudoflavor This was an oversight; it should be among the export flags that can be allowed to vary by pseudoflavor. This allows an administrator to (for example) allow auth_sys mounts only from low ports, but allow auth_krb5 mounts to use any port. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfsfh.c | 4 +++- include/linux/nfsd/export.h | 4 ++-- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 0eb1c59f5ab..951938d6c49 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -88,8 +88,10 @@ nfsd_mode_check(struct svc_rqst *rqstp, umode_t mode, int type) static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp, struct svc_export *exp) { + int flags = nfsexp_flags(rqstp, exp); + /* Check if the request originated from a secure port. */ - if (!rqstp->rq_secure && EX_SECURE(exp)) { + if (!rqstp->rq_secure && (flags & NFSEXP_INSECURE_PORT)) { RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); dprintk(KERN_WARNING "nfsd: request from insecure port %s!\n", diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 4f1df1d7312..4cafbe1255f 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -44,7 +44,8 @@ /* The flags that may vary depending on security flavor: */ #define NFSEXP_SECINFO_FLAGS (NFSEXP_READONLY | NFSEXP_ROOTSQUASH \ - | NFSEXP_ALLSQUASH) + | NFSEXP_ALLSQUASH \ + | NFSEXP_INSECURE_PORT) #ifdef __KERNEL__ @@ -109,7 +110,6 @@ struct svc_expkey { struct path ek_path; }; -#define EX_SECURE(exp) (!((exp)->ex_flags & NFSEXP_INSECURE_PORT)) #define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC)) #define EX_NOHIDE(exp) ((exp)->ex_flags & NFSEXP_NOHIDE) #define EX_WGATHER(exp) ((exp)->ex_flags & NFSEXP_GATHERED_WRITES) -- cgit v1.2.3-18-g5258 From eb4c86c6a5adec423c9e615d4937fdddd06a16c5 Mon Sep 17 00:00:00 2001 From: Steve Dickson Date: Wed, 9 Sep 2009 14:58:22 -0400 Subject: nfsd: introduce export flag for v4 pseudoroot NFSv4 differs from v2 and v3 in that it presents a single unified filesystem tree, whereas v2 and v3 exported multiple filesystem (whose roots could be found using a separate mount protocol). Our original NFSv4 server implementation asked the administrator to designate a single filesystem as the NFSv4 root, then to mount filesystems they wished to export underneath. (Often using bind mounts of already-existing filesystems.) This was conceptually simple, and allowed easy implementation, but created a serious obstacle to upgrading between v2/v3: since the paths to v4 filesystems were different, administrators would have to adjust all the paths in client-side mount commands when switching to v4. Various workarounds are possible. For example, the administrator could export "/" and designate it as the v4 root. However, the security risks of that approach are obvious, and in any case we shouldn't be requiring the administrator to take extra steps to fix this problem; instead, the server should present consistent paths across different versions by default. These patches take a modified version of that approach: we provide a new export option which exports only a subset of a filesystem. With this flag, it becomes safe for mountd to export "/" by default, with no need for additional configuration. We begin just by defining the new flag. Signed-off-by: Steve Dickson Signed-off-by: J. Bruce Fields --- fs/nfsd/export.c | 1 + include/linux/nfsd/export.h | 10 ++++++++++ 2 files changed, 11 insertions(+) diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index cb3dae2fcd8..c64d55f319b 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -1425,6 +1425,7 @@ static struct flags { { NFSEXP_CROSSMOUNT, {"crossmnt", ""}}, { NFSEXP_NOSUBTREECHECK, {"no_subtree_check", ""}}, { NFSEXP_NOAUTHNLM, {"insecure_locks", ""}}, + { NFSEXP_V4ROOT, {"v4root", ""}}, #ifdef MSNFS { NFSEXP_MSNFS, {"msnfs", ""}}, #endif diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 4cafbe1255f..41f0d4e2537 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -39,6 +39,16 @@ #define NFSEXP_FSID 0x2000 #define NFSEXP_CROSSMOUNT 0x4000 #define NFSEXP_NOACL 0x8000 /* reserved for possible ACL related use */ +/* + * The NFSEXP_V4ROOT flag causes the kernel to give access only to NFSv4 + * clients, and only to the single directory that is the root of the + * export; further lookup and readdir operations are treated as if every + * subdirectory was a mountpoint, and ignored if they are not themselves + * exported. This is used by nfsd and mountd to construct the NFSv4 + * pseudofilesystem, which provides access only to paths leading to each + * exported filesystem. + */ +#define NFSEXP_V4ROOT 0x10000 /* All flags that we claim to support. (Note we don't support NOACL.) */ #define NFSEXP_ALLFLAGS 0x7E3F -- cgit v1.2.3-18-g5258 From 3b6cee7bc4b2f7858e9202293104acda8826bb68 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sun, 25 Oct 2009 21:18:19 -0400 Subject: nfsd4: don't continue "under" mounts in V4ROOT case If /A/mount/point/ has filesystem "B" mounted on top of it, and if "A" is exported, but not "B", then the nfs server has always returned to the client a filehandle for the mountpoint, instead of for the root of "B", allowing the client to see the subtree of "A" that would otherwise be hidden by B. Disable this behavior in the case of V4ROOT exports; we implement the path restrictions of V4ROOT exports by treating *every* directory as if it were a mountpoint, and allowing traversal *only* if the new directory is exported. Signed-off-by: J. Bruce Fields --- fs/nfsd/vfs.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 04bdba12d21..7e2fdd50113 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -99,8 +99,16 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, exp2 = rqst_exp_get_by_name(rqstp, &path); if (IS_ERR(exp2)) { - if (PTR_ERR(exp2) != -ENOENT) - err = PTR_ERR(exp2); + err = PTR_ERR(exp2); + /* + * We normally allow NFS clients to continue + * "underneath" a mountpoint that is not exported. + * The exception is V4ROOT, where no traversal is ever + * allowed without an explicit export of the new + * directory. + */ + if (err == -ENOENT && !(exp->ex_flags & NFSEXP_V4ROOT)) + err = 0; path_put(&path); goto out; } -- cgit v1.2.3-18-g5258 From 82ead7fe41da960ed80652d13d5a1072f85f5aca Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sun, 25 Oct 2009 21:33:15 -0400 Subject: nfsd: filter lookup results in V4ROOT case We treat every object as a mountpoint and pretend it doesn't exist if it isn't exported. Signed-off-by: J. Bruce Fields --- fs/nfsd/vfs.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 7e2fdd50113..eaf2f0dca12 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -166,6 +166,19 @@ static int nfsd_lookup_parent(struct svc_rqst *rqstp, struct dentry *dparent, st return 0; } +/* + * For nfsd purposes, we treat V4ROOT exports as though there was an + * export at *every* directory. + */ +static int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp) +{ + if (d_mountpoint(dentry)) + return 1; + if (!(exp->ex_flags & NFSEXP_V4ROOT)) + return 0; + return dentry->d_inode != NULL; +} + __be32 nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, unsigned int len, @@ -211,7 +224,7 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, /* * check if we have crossed a mount point ... */ - if (d_mountpoint(dentry)) { + if (nfsd_mountpoint(dentry, exp)) { if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) { dput(dentry); goto out_nfserr; -- cgit v1.2.3-18-g5258 From 3227fa41abc191384fa81b3bcf52aa7fccb31536 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sun, 25 Oct 2009 21:43:01 -0400 Subject: nfsd: filter readdir results in V4ROOT case As with lookup, we treat every boject as a mountpoint and pretend it doesn't exist if it isn't exported. The preexisting code here is confusing, but I haven't yet figured out how to make it clearer. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 10 +++++++--- fs/nfsd/vfs.c | 2 +- fs/nfsd/vfs.h | 1 + 3 files changed, 9 insertions(+), 4 deletions(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index cab97803110..a8587e90fd5 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2196,11 +2196,14 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, * we will not follow the cross mount and will fill the attribtutes * directly from the mountpoint dentry. */ - if (d_mountpoint(dentry) && !attributes_need_mount(cd->rd_bmval)) - ignore_crossmnt = 1; - else if (d_mountpoint(dentry)) { + if (nfsd_mountpoint(dentry, exp)) { int err; + if (!(exp->ex_flags & NFSEXP_V4ROOT) + && !attributes_need_mount(cd->rd_bmval)) { + ignore_crossmnt = 1; + goto out_encode; + } /* * Why the heck aren't we just using nfsd_lookup?? * Different "."/".." handling? Something else? @@ -2216,6 +2219,7 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, goto out_put; } +out_encode: nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval, cd->rd_rqstp, ignore_crossmnt); out_put: diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index eaf2f0dca12..a0015a958ae 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -170,7 +170,7 @@ static int nfsd_lookup_parent(struct svc_rqst *rqstp, struct dentry *dparent, st * For nfsd purposes, we treat V4ROOT exports as though there was an * export at *every* directory. */ -static int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp) +int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp) { if (d_mountpoint(dentry)) return 1; diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index b8011fd2fca..f4fa6d351bb 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -40,6 +40,7 @@ __be32 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *, struct svc_export **, struct dentry **); __be32 nfsd_setattr(struct svc_rqst *, struct svc_fh *, struct iattr *, int, time_t); +int nfsd_mountpoint(struct dentry *, struct svc_export *); #ifdef CONFIG_NFSD_V4 __be32 nfsd4_set_nfs4_acl(struct svc_rqst *, struct svc_fh *, struct nfs4_acl *); -- cgit v1.2.3-18-g5258 From f2ca7153ca49a407ea1c7232c9fa7e9849f03f9c Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 12 Nov 2009 17:26:19 -0500 Subject: nfsd: allow exports of symlinks We want to allow exports of symlinks, to allow mountd to communicate to the kernel which symlinks lead to exports, and hence which symlinks need to be visible on the pseudofilesystem. Signed-off-by: J. Bruce Fields --- fs/nfsd/export.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index c64d55f319b..18ac20ffedd 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -358,10 +358,12 @@ static struct svc_export *svc_export_lookup(struct svc_export *); static int check_export(struct inode *inode, int flags, unsigned char *uuid) { - /* We currently export only dirs and regular files. - * This is what umountd does. + /* + * We currently export only dirs, regular files, and (for v4 + * pseudoroot) symlinks. */ if (!S_ISDIR(inode->i_mode) && + !S_ISLNK(inode->i_mode) && !S_ISREG(inode->i_mode)) return -ENOTDIR; -- cgit v1.2.3-18-g5258 From 03a816b46d7eba78da11e4025f0af195b32fa464 Mon Sep 17 00:00:00 2001 From: Steve Dickson Date: Wed, 9 Sep 2009 15:06:05 -0400 Subject: nfsd: restrict filehandles accepted in V4ROOT case On V4ROOT exports, only accept filehandles that are the *root* of some export. This allows mountd to allow or deny access to individual directories and symlinks on the pseudofilesystem. Note that the checks in readdir and lookup are not enough, since a malicious host with access to the network could guess filehandles that they weren't able to obtain through lookup or readdir. Signed-off-by: Steve Dickson Signed-off-by: J. Bruce Fields --- fs/nfsd/nfsd.h | 5 +++++ fs/nfsd/nfsfh.c | 34 ++++++++++++++++++++++++++++++++++ fs/nfsd/vfs.c | 6 ------ 3 files changed, 39 insertions(+), 6 deletions(-) diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 74f67c2aca3..ac121ad1654 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -70,6 +70,11 @@ int nfsd_create_serv(void); extern int nfsd_max_blksize; +static inline int nfsd_v4client(struct svc_rqst *rq) +{ + return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4; +} + /* * NFSv4 State */ diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 951938d6c49..44812c32e51 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -103,6 +103,36 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp, return nfserrno(nfsd_setuser(rqstp, exp)); } +static inline __be32 check_pseudo_root(struct svc_rqst *rqstp, + struct dentry *dentry, struct svc_export *exp) +{ + if (!(exp->ex_flags & NFSEXP_V4ROOT)) + return nfs_ok; + /* + * v2/v3 clients have no need for the V4ROOT export--they use + * the mount protocl instead; also, further V4ROOT checks may be + * in v4-specific code, in which case v2/v3 clients could bypass + * them. + */ + if (!nfsd_v4client(rqstp)) + return nfserr_stale; + /* + * We're exposing only the directories and symlinks that have to be + * traversed on the way to real exports: + */ + if (unlikely(!S_ISDIR(dentry->d_inode->i_mode) && + !S_ISLNK(dentry->d_inode->i_mode))) + return nfserr_stale; + /* + * A pseudoroot export gives permission to access only one + * single directory; the kernel has to make another upcall + * before granting access to anything else under it: + */ + if (unlikely(dentry != exp->ex_path.dentry)) + return nfserr_stale; + return nfs_ok; +} + /* * Use the given filehandle to look up the corresponding export and * dentry. On success, the results are used to set fh_export and @@ -299,6 +329,10 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) * (for example, if different id-squashing options are in * effect on the new filesystem). */ + error = check_pseudo_root(rqstp, dentry, exp); + if (error) + goto out; + error = nfsd_setuser_and_check_port(rqstp, exp); if (error) goto out; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index a0015a958ae..f6ca32b07e1 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -72,12 +72,6 @@ struct raparm_hbucket { #define RAPARM_HASH_MASK (RAPARM_HASH_SIZE-1) static struct raparm_hbucket raparm_hash[RAPARM_HASH_SIZE]; -static inline int -nfsd_v4client(struct svc_rqst *rq) -{ - return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4; -} - /* * Called from nfsd_lookup and encode_dirent. Check if we have crossed * a mount point. -- cgit v1.2.3-18-g5258 From 774b147828e32ec698e49d95d0498fc71da7082d Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sun, 13 Dec 2009 20:21:48 -0500 Subject: nfsd: make V4ROOT exports read-only I can't see any use for writeable V4ROOT exports. Signed-off-by: J. Bruce Fields --- fs/nfsd/export.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 18ac20ffedd..7d5ba1b0ffc 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -355,7 +355,7 @@ static struct svc_export *svc_export_update(struct svc_export *new, struct svc_export *old); static struct svc_export *svc_export_lookup(struct svc_export *); -static int check_export(struct inode *inode, int flags, unsigned char *uuid) +static int check_export(struct inode *inode, int *flags, unsigned char *uuid) { /* @@ -367,6 +367,13 @@ static int check_export(struct inode *inode, int flags, unsigned char *uuid) !S_ISREG(inode->i_mode)) return -ENOTDIR; + /* + * Mountd should never pass down a writeable V4ROOT export, but, + * just to make sure: + */ + if (*flags & NFSEXP_V4ROOT) + *flags |= NFSEXP_READONLY; + /* There are two requirements on a filesystem to be exportable. * 1: We must be able to identify the filesystem from a number. * either a device number (so FS_REQUIRES_DEV needed) @@ -375,7 +382,7 @@ static int check_export(struct inode *inode, int flags, unsigned char *uuid) * This means that s_export_op must be set. */ if (!(inode->i_sb->s_type->fs_flags & FS_REQUIRES_DEV) && - !(flags & NFSEXP_FSID) && + !(*flags & NFSEXP_FSID) && uuid == NULL) { dprintk("exp_export: export of non-dev fs without fsid\n"); return -EINVAL; @@ -590,7 +597,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) goto out4; } - err = check_export(exp.ex_path.dentry->d_inode, exp.ex_flags, + err = check_export(exp.ex_path.dentry->d_inode, &exp.ex_flags, exp.ex_uuid); if (err) goto out4; @@ -1029,7 +1036,7 @@ exp_export(struct nfsctl_export *nxp) goto finish; } - err = check_export(path.dentry->d_inode, nxp->ex_flags, NULL); + err = check_export(path.dentry->d_inode, &nxp->ex_flags, NULL); if (err) goto finish; err = -ENOMEM; -- cgit v1.2.3-18-g5258 From 3d8986c7585457c45fd349b2c542c7c1ecd20843 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 15 Dec 2009 14:09:03 -0500 Subject: nfsd: enable V4ROOT exports With the v4root option now enforced everywhere it should be, it is safe to advertise support for it to mountd. Signed-off-by: J. Bruce Fields --- include/linux/nfsd/export.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 41f0d4e2537..8ae78a61eea 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -50,7 +50,7 @@ */ #define NFSEXP_V4ROOT 0x10000 /* All flags that we claim to support. (Note we don't support NOACL.) */ -#define NFSEXP_ALLFLAGS 0x7E3F +#define NFSEXP_ALLFLAGS 0x17E3F /* The flags that may vary depending on security flavor: */ #define NFSEXP_SECINFO_FLAGS (NFSEXP_READONLY | NFSEXP_ROOTSQUASH \ -- cgit v1.2.3-18-g5258 From c7af6b0895229bd080b86afc91302b66f6df0378 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 4 Dec 2009 18:29:33 -0500 Subject: nfsd: remove unused field rq_reffh This field is never referenced anywhere else. I don't know what it was intended for. Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index d1567d62755..5a3085b9b39 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -273,10 +273,6 @@ struct svc_rqst { struct auth_domain * rq_client; /* RPC peer info */ struct auth_domain * rq_gssclient; /* "gss/"-style peer info */ struct svc_cacherep * rq_cacherep; /* cache info */ - struct knfsd_fh * rq_reffh; /* Referrence filehandle, used to - * determine what device number - * to report (real or virtual) - */ int rq_splice_ok; /* turned off in gss privacy * to prevent encrypting page * cache pages */ -- cgit v1.2.3-18-g5258 From 1557aca7904ed6fadd22cdc3364754070bb3d3c3 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 4 Dec 2009 19:36:06 -0500 Subject: nfsd: move most of nfsfh.h to fs/nfsd Most of this can be trivially moved to a private header as well. Signed-off-by: J. Bruce Fields --- fs/nfsd/export.c | 1 + fs/nfsd/nfsfh.h | 208 +++++++++++++++++++++++++++++++++++++++++++++ fs/nfsd/state.h | 1 + fs/nfsd/vfs.h | 2 + fs/nfsd/xdr.h | 1 + include/linux/nfsd/nfsfh.h | 199 ------------------------------------------- 6 files changed, 213 insertions(+), 199 deletions(-) create mode 100644 fs/nfsd/nfsfh.h diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 7d5ba1b0ffc..b26a3644fbb 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -22,6 +22,7 @@ #include #include "nfsd.h" +#include "nfsfh.h" #define NFSDDBG_FACILITY NFSDDBG_EXPORT diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h new file mode 100644 index 00000000000..cdfb8c6a420 --- /dev/null +++ b/fs/nfsd/nfsfh.h @@ -0,0 +1,208 @@ +/* Copyright (C) 1995, 1996, 1997 Olaf Kirch */ + +#ifndef _LINUX_NFSD_FH_INT_H +#define _LINUX_NFSD_FH_INT_H + +#include + +enum nfsd_fsid { + FSID_DEV = 0, + FSID_NUM, + FSID_MAJOR_MINOR, + FSID_ENCODE_DEV, + FSID_UUID4_INUM, + FSID_UUID8, + FSID_UUID16, + FSID_UUID16_INUM, +}; + +enum fsid_source { + FSIDSOURCE_DEV, + FSIDSOURCE_FSID, + FSIDSOURCE_UUID, +}; +extern enum fsid_source fsid_source(struct svc_fh *fhp); + + +/* This might look a little large to "inline" but in all calls except + * one, 'vers' is constant so moste of the function disappears. + */ +static inline void mk_fsid(int vers, u32 *fsidv, dev_t dev, ino_t ino, + u32 fsid, unsigned char *uuid) +{ + u32 *up; + switch(vers) { + case FSID_DEV: + fsidv[0] = htonl((MAJOR(dev)<<16) | + MINOR(dev)); + fsidv[1] = ino_t_to_u32(ino); + break; + case FSID_NUM: + fsidv[0] = fsid; + break; + case FSID_MAJOR_MINOR: + fsidv[0] = htonl(MAJOR(dev)); + fsidv[1] = htonl(MINOR(dev)); + fsidv[2] = ino_t_to_u32(ino); + break; + + case FSID_ENCODE_DEV: + fsidv[0] = new_encode_dev(dev); + fsidv[1] = ino_t_to_u32(ino); + break; + + case FSID_UUID4_INUM: + /* 4 byte fsid and inode number */ + up = (u32*)uuid; + fsidv[0] = ino_t_to_u32(ino); + fsidv[1] = up[0] ^ up[1] ^ up[2] ^ up[3]; + break; + + case FSID_UUID8: + /* 8 byte fsid */ + up = (u32*)uuid; + fsidv[0] = up[0] ^ up[2]; + fsidv[1] = up[1] ^ up[3]; + break; + + case FSID_UUID16: + /* 16 byte fsid - NFSv3+ only */ + memcpy(fsidv, uuid, 16); + break; + + case FSID_UUID16_INUM: + /* 8 byte inode and 16 byte fsid */ + *(u64*)fsidv = (u64)ino; + memcpy(fsidv+2, uuid, 16); + break; + default: BUG(); + } +} + +static inline int key_len(int type) +{ + switch(type) { + case FSID_DEV: return 8; + case FSID_NUM: return 4; + case FSID_MAJOR_MINOR: return 12; + case FSID_ENCODE_DEV: return 8; + case FSID_UUID4_INUM: return 8; + case FSID_UUID8: return 8; + case FSID_UUID16: return 16; + case FSID_UUID16_INUM: return 24; + default: return 0; + } +} + +/* + * Shorthand for dprintk()'s + */ +extern char * SVCFH_fmt(struct svc_fh *fhp); + +/* + * Function prototypes + */ +__be32 fh_verify(struct svc_rqst *, struct svc_fh *, int, int); +__be32 fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *); +__be32 fh_update(struct svc_fh *); +void fh_put(struct svc_fh *); + +static __inline__ struct svc_fh * +fh_copy(struct svc_fh *dst, struct svc_fh *src) +{ + WARN_ON(src->fh_dentry || src->fh_locked); + + *dst = *src; + return dst; +} + +static inline void +fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src) +{ + dst->fh_size = src->fh_size; + memcpy(&dst->fh_base, &src->fh_base, src->fh_size); +} + +static __inline__ struct svc_fh * +fh_init(struct svc_fh *fhp, int maxsize) +{ + memset(fhp, 0, sizeof(*fhp)); + fhp->fh_maxsize = maxsize; + return fhp; +} + +#ifdef CONFIG_NFSD_V3 +/* + * Fill in the pre_op attr for the wcc data + */ +static inline void +fill_pre_wcc(struct svc_fh *fhp) +{ + struct inode *inode; + + inode = fhp->fh_dentry->d_inode; + if (!fhp->fh_pre_saved) { + fhp->fh_pre_mtime = inode->i_mtime; + fhp->fh_pre_ctime = inode->i_ctime; + fhp->fh_pre_size = inode->i_size; + fhp->fh_pre_change = inode->i_version; + fhp->fh_pre_saved = 1; + } +} + +extern void fill_post_wcc(struct svc_fh *); +#else +#define fill_pre_wcc(ignored) +#define fill_post_wcc(notused) +#endif /* CONFIG_NFSD_V3 */ + + +/* + * Lock a file handle/inode + * NOTE: both fh_lock and fh_unlock are done "by hand" in + * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once + * so, any changes here should be reflected there. + */ + +static inline void +fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) +{ + struct dentry *dentry = fhp->fh_dentry; + struct inode *inode; + + BUG_ON(!dentry); + + if (fhp->fh_locked) { + printk(KERN_WARNING "fh_lock: %s/%s already locked!\n", + dentry->d_parent->d_name.name, dentry->d_name.name); + return; + } + + inode = dentry->d_inode; + mutex_lock_nested(&inode->i_mutex, subclass); + fill_pre_wcc(fhp); + fhp->fh_locked = 1; +} + +static inline void +fh_lock(struct svc_fh *fhp) +{ + fh_lock_nested(fhp, I_MUTEX_NORMAL); +} + +/* + * Unlock a file handle/inode + */ +static inline void +fh_unlock(struct svc_fh *fhp) +{ + BUG_ON(!fhp->fh_dentry); + + if (fhp->fh_locked) { + fill_post_wcc(fhp); + mutex_unlock(&fhp->fh_dentry->d_inode->i_mutex); + fhp->fh_locked = 0; + } +} + +#endif /* _LINUX_NFSD_FH_INT_H */ diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 2af75686e0d..775b8d281d6 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -38,6 +38,7 @@ #define _NFSD4_STATE_H #include +#include "nfsfh.h" typedef struct { u32 cl_boot; diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index f4fa6d351bb..4b1de0a9ea7 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -5,6 +5,8 @@ #ifndef LINUX_NFSD_VFS_H #define LINUX_NFSD_VFS_H +#include "nfsfh.h" + /* * Flags for nfsd_permission */ diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 235ee5c3be5..87fe6f64b8f 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -9,6 +9,7 @@ #include #include "nfsd.h" +#include "nfsfh.h" struct nfsd_fhandle { struct svc_fh fh; diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index 49523edbc51..65e333afaee 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -162,205 +162,6 @@ typedef struct svc_fh { } svc_fh; -enum nfsd_fsid { - FSID_DEV = 0, - FSID_NUM, - FSID_MAJOR_MINOR, - FSID_ENCODE_DEV, - FSID_UUID4_INUM, - FSID_UUID8, - FSID_UUID16, - FSID_UUID16_INUM, -}; - -enum fsid_source { - FSIDSOURCE_DEV, - FSIDSOURCE_FSID, - FSIDSOURCE_UUID, -}; -extern enum fsid_source fsid_source(struct svc_fh *fhp); - - -/* This might look a little large to "inline" but in all calls except - * one, 'vers' is constant so moste of the function disappears. - */ -static inline void mk_fsid(int vers, u32 *fsidv, dev_t dev, ino_t ino, - u32 fsid, unsigned char *uuid) -{ - u32 *up; - switch(vers) { - case FSID_DEV: - fsidv[0] = htonl((MAJOR(dev)<<16) | - MINOR(dev)); - fsidv[1] = ino_t_to_u32(ino); - break; - case FSID_NUM: - fsidv[0] = fsid; - break; - case FSID_MAJOR_MINOR: - fsidv[0] = htonl(MAJOR(dev)); - fsidv[1] = htonl(MINOR(dev)); - fsidv[2] = ino_t_to_u32(ino); - break; - - case FSID_ENCODE_DEV: - fsidv[0] = new_encode_dev(dev); - fsidv[1] = ino_t_to_u32(ino); - break; - - case FSID_UUID4_INUM: - /* 4 byte fsid and inode number */ - up = (u32*)uuid; - fsidv[0] = ino_t_to_u32(ino); - fsidv[1] = up[0] ^ up[1] ^ up[2] ^ up[3]; - break; - - case FSID_UUID8: - /* 8 byte fsid */ - up = (u32*)uuid; - fsidv[0] = up[0] ^ up[2]; - fsidv[1] = up[1] ^ up[3]; - break; - - case FSID_UUID16: - /* 16 byte fsid - NFSv3+ only */ - memcpy(fsidv, uuid, 16); - break; - - case FSID_UUID16_INUM: - /* 8 byte inode and 16 byte fsid */ - *(u64*)fsidv = (u64)ino; - memcpy(fsidv+2, uuid, 16); - break; - default: BUG(); - } -} - -static inline int key_len(int type) -{ - switch(type) { - case FSID_DEV: return 8; - case FSID_NUM: return 4; - case FSID_MAJOR_MINOR: return 12; - case FSID_ENCODE_DEV: return 8; - case FSID_UUID4_INUM: return 8; - case FSID_UUID8: return 8; - case FSID_UUID16: return 16; - case FSID_UUID16_INUM: return 24; - default: return 0; - } -} - -/* - * Shorthand for dprintk()'s - */ -extern char * SVCFH_fmt(struct svc_fh *fhp); - -/* - * Function prototypes - */ -__be32 fh_verify(struct svc_rqst *, struct svc_fh *, int, int); -__be32 fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *); -__be32 fh_update(struct svc_fh *); -void fh_put(struct svc_fh *); - -static __inline__ struct svc_fh * -fh_copy(struct svc_fh *dst, struct svc_fh *src) -{ - WARN_ON(src->fh_dentry || src->fh_locked); - - *dst = *src; - return dst; -} - -static inline void -fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src) -{ - dst->fh_size = src->fh_size; - memcpy(&dst->fh_base, &src->fh_base, src->fh_size); -} - -static __inline__ struct svc_fh * -fh_init(struct svc_fh *fhp, int maxsize) -{ - memset(fhp, 0, sizeof(*fhp)); - fhp->fh_maxsize = maxsize; - return fhp; -} - -#ifdef CONFIG_NFSD_V3 -/* - * Fill in the pre_op attr for the wcc data - */ -static inline void -fill_pre_wcc(struct svc_fh *fhp) -{ - struct inode *inode; - - inode = fhp->fh_dentry->d_inode; - if (!fhp->fh_pre_saved) { - fhp->fh_pre_mtime = inode->i_mtime; - fhp->fh_pre_ctime = inode->i_ctime; - fhp->fh_pre_size = inode->i_size; - fhp->fh_pre_change = inode->i_version; - fhp->fh_pre_saved = 1; - } -} - -extern void fill_post_wcc(struct svc_fh *); -#else -#define fill_pre_wcc(ignored) -#define fill_post_wcc(notused) -#endif /* CONFIG_NFSD_V3 */ - - -/* - * Lock a file handle/inode - * NOTE: both fh_lock and fh_unlock are done "by hand" in - * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once - * so, any changes here should be reflected there. - */ - -static inline void -fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) -{ - struct dentry *dentry = fhp->fh_dentry; - struct inode *inode; - - BUG_ON(!dentry); - - if (fhp->fh_locked) { - printk(KERN_WARNING "fh_lock: %s/%s already locked!\n", - dentry->d_parent->d_name.name, dentry->d_name.name); - return; - } - - inode = dentry->d_inode; - mutex_lock_nested(&inode->i_mutex, subclass); - fill_pre_wcc(fhp); - fhp->fh_locked = 1; -} - -static inline void -fh_lock(struct svc_fh *fhp) -{ - fh_lock_nested(fhp, I_MUTEX_NORMAL); -} - -/* - * Unlock a file handle/inode - */ -static inline void -fh_unlock(struct svc_fh *fhp) -{ - BUG_ON(!fhp->fh_dentry); - - if (fhp->fh_locked) { - fill_post_wcc(fhp); - mutex_unlock(&fhp->fh_dentry->d_inode->i_mutex); - fhp->fh_locked = 0; - } -} #endif /* __KERNEL__ */ -- cgit v1.2.3-18-g5258 From 7663dacd926584093dfc350892792054692b6cb3 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 4 Dec 2009 19:49:00 -0500 Subject: nfsd: remove pointless paths in file headers The new .h files have paths at the top that are now out of date. While we're here, just remove all of those from fs/nfsd; they never served any purpose. Signed-off-by: J. Bruce Fields --- fs/nfsd/auth.c | 6 +----- fs/nfsd/cache.h | 2 -- fs/nfsd/export.c | 2 -- fs/nfsd/lockd.c | 2 -- fs/nfsd/nfs2acl.c | 2 -- fs/nfsd/nfs3acl.c | 2 -- fs/nfsd/nfs3proc.c | 2 -- fs/nfsd/nfs3xdr.c | 2 -- fs/nfsd/nfs4acl.c | 2 -- fs/nfsd/nfs4callback.c | 2 -- fs/nfsd/nfs4idmap.c | 2 -- fs/nfsd/nfs4proc.c | 2 -- fs/nfsd/nfs4recover.c | 2 -- fs/nfsd/nfs4state.c | 2 -- fs/nfsd/nfscache.c | 2 -- fs/nfsd/nfsctl.c | 2 -- fs/nfsd/nfsd.h | 2 -- fs/nfsd/nfsfh.c | 2 -- fs/nfsd/nfsproc.c | 3 --- fs/nfsd/nfssvc.c | 2 -- fs/nfsd/nfsxdr.c | 2 -- fs/nfsd/state.h | 2 -- fs/nfsd/stats.c | 2 -- fs/nfsd/vfs.c | 2 -- fs/nfsd/xdr.h | 6 +----- fs/nfsd/xdr3.h | 2 -- fs/nfsd/xdr4.h | 2 -- 27 files changed, 2 insertions(+), 61 deletions(-) diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 71209d4993d..79717a40dab 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -1,8 +1,4 @@ -/* - * linux/fs/nfsd/auth.c - * - * Copyright (C) 1995, 1996 Olaf Kirch - */ +/* Copyright (C) 1995, 1996 Olaf Kirch */ #include #include "nfsd.h" diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index a165425dea4..d892be61016 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -1,6 +1,4 @@ /* - * include/linux/nfsd/cache.h - * * Request reply cache. This was heavily inspired by the * implementation in 4.3BSD/4.4BSD. * diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index b26a3644fbb..c487810a236 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -1,7 +1,5 @@ #define MSNFS /* HACK HACK */ /* - * linux/fs/nfsd/export.c - * * NFS exporting and validation. * * We maintain a list of clients, each of which has a list of diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 6f12777ed22..0c6d8167013 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/lockd.c - * * This file contains all the stubs needed when communicating with lockd. * This level of indirection is necessary so we can run nfsd+lockd without * requiring the nfs client to be compiled in/loaded, and vice versa. diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 874e2a94bf4..f20589d2ae2 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/nfs2acl.c - * * Process version 2 NFSACL requests. * * Copyright (C) 2002-2003 Andreas Gruenbacher diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index c6011ddbadc..e0c4846bad9 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/nfs3acl.c - * * Process version 3 NFSACL requests. * * Copyright (C) 2002-2003 Andreas Gruenbacher diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 90b19ca75b3..3d68f45a37b 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/nfs3proc.c - * * Process version 3 NFS requests. * * Copyright (C) 1996, 1997, 1998 Olaf Kirch diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index c523bb88c10..2a533a0af2a 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/nfs3xdr.c - * * XDR support for nfsd/protocol version 3. * * Copyright (C) 1995, 1996, 1997 Olaf Kirch diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index d6f0cea4bab..88150685df3 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -1,6 +1,4 @@ /* - * fs/nfs4acl/acl.c - * * Common NFSv4 ACL handling code. * * Copyright (c) 2002, 2003 The Regents of the University of Michigan. diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index f7a31582763..c6eed2a3b09 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/nfs4callback.c - * * Copyright (c) 2001 The Regents of the University of Michigan. * All rights reserved. * diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 8e518cd5ac1..6e2983b27f3 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -1,6 +1,4 @@ /* - * fs/nfsd/nfs4idmap.c - * * Mapping of UID/GIDs to name and vice versa. * * Copyright (c) 2002, 2003 The Regents of the University of diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index e2b5666f25d..37514c46984 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1,6 +1,4 @@ /* - * fs/nfsd/nfs4proc.c - * * Server-side procedures for NFSv4. * * Copyright (c) 2002 The Regents of the University of Michigan. diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 6744e7f2da0..5a754f7b71e 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -1,6 +1,4 @@ /* -* linux/fs/nfsd/nfs4recover.c -* * Copyright (c) 2004 The Regents of the University of Michigan. * All rights reserved. * diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 2923e6c1da1..f19ed866c95 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1,6 +1,4 @@ /* -* linux/fs/nfsd/nfs4state.c -* * Copyright (c) 2001 The Regents of the University of Michigan. * All rights reserved. * diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 18aa9729a38..da08560c481 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/nfscache.c - * * Request reply cache. This is currently a global cache, but this may * change in the future and be a per-client cache. * diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index e7051ac4dc7..2604c3e70ea 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/nfsctl.c - * * Syscall interface to knfsd. * * Copyright (C) 1995, 1996 Olaf Kirch diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index ac121ad1654..e942a1aaac9 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -1,6 +1,4 @@ /* - * linux/include/linux/nfsd/nfsd.h - * * Hodge-podge collection of knfsd-related stuff. * I will sort this out later. * diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 44812c32e51..1c12177b908 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/nfsfh.c - * * NFS server file handle treatment. * * Copyright (C) 1995, 1996 Olaf Kirch diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 21a5f793c3d..a047ad6111e 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -1,7 +1,4 @@ /* - * nfsproc2.c Process version 2 NFS requests. - * linux/fs/nfsd/nfs2proc.c - * * Process version 2 NFS requests. * * Copyright (C) 1995-1997 Olaf Kirch diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index b520ce10bd1..171699eb07c 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/nfssvc.c - * * Central processing for nfsd. * * Authors: Olaf Kirch (okir@monad.swb.de) diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 3bec831704a..4ce005dbf3e 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/nfsxdr.c - * * XDR support for nfsd * * Copyright (C) 1995, 1996 Olaf Kirch diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 775b8d281d6..fefeae27f25 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -1,6 +1,4 @@ /* - * linux/include/nfsd/state.h - * * Copyright (c) 2001 The Regents of the University of Michigan. * All rights reserved. * diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 3fc69dfd309..5232d3e8fb2 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -1,6 +1,4 @@ /* - * linux/fs/nfsd/stats.c - * * procfs-based user access to knfsd statistics * * /proc/net/rpc/nfsd diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index f6ca32b07e1..e3ef3ec0efd 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1,7 +1,5 @@ #define MSNFS /* HACK HACK */ /* - * linux/fs/nfsd/vfs.c - * * File operations used by nfsd. Some of these have been ripped from * other parts of the kernel because they weren't exported, others * are partial duplicates with added or changed functionality. diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 87fe6f64b8f..53b1863dd8f 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -1,8 +1,4 @@ -/* - * linux/include/linux/nfsd/xdr.h - * - * XDR types for nfsd. This is mainly a typing exercise. - */ +/* XDR types for nfsd. This is mainly a typing exercise. */ #ifndef LINUX_NFSD_H #define LINUX_NFSD_H diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index b330756973c..7df980eb056 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -1,6 +1,4 @@ /* - * linux/include/linux/nfsd/xdr3.h - * * XDR types for NFSv3 in nfsd. * * Copyright (C) 1996-1998, Olaf Kirch diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 83202a1cf07..efa33773953 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -1,6 +1,4 @@ /* - * include/linux/nfsd/xdr4.h - * * Server-side types for NFSv4. * * Copyright (c) 2002 The Regents of the University of Michigan. -- cgit v1.2.3-18-g5258