linux_dsm_epyc7002/fs/nfs/nfs3proc.c

969 lines
24 KiB
C
Raw Normal View History

/*
* linux/fs/nfs/nfs3proc.c
*
* Client-side NFSv3 procedures stubs.
*
* Copyright (C) 1997, Olaf Kirch
*/
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/sunrpc/clnt.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/nfs.h>
#include <linux/nfs3.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/lockd/bind.h>
#include <linux/nfs_mount.h>
#include <linux/freezer.h>
#include <linux/xattr.h>
#include "iostat.h"
#include "internal.h"
#include "nfs3_fs.h"
#define NFSDBG_FACILITY NFSDBG_PROC
/* A wrapper to handle the EJUKEBOX error messages */
static int
nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
{
int res;
do {
res = rpc_call_sync(clnt, msg, flags);
if (res != -EJUKEBOX)
break;
freezable_schedule_timeout_killable_unsafe(NFS_JUKEBOX_RETRY_TIME);
res = -ERESTARTSYS;
} while (!fatal_signal_pending(current));
return res;
}
#define rpc_call_sync(clnt, msg, flags) nfs3_rpc_wrapper(clnt, msg, flags)
static int
nfs3_async_handle_jukebox(struct rpc_task *task, struct inode *inode)
{
if (task->tk_status != -EJUKEBOX)
return 0;
if (task->tk_status == -EJUKEBOX)
nfs_inc_stats(inode, NFSIOS_DELAY);
task->tk_status = 0;
rpc_restart_call(task);
rpc_delay(task, NFS_JUKEBOX_RETRY_TIME);
return 1;
}
static int
do_proc_get_root(struct rpc_clnt *client, struct nfs_fh *fhandle,
struct nfs_fsinfo *info)
{
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_FSINFO],
.rpc_argp = fhandle,
.rpc_resp = info,
};
int status;
dprintk("%s: call fsinfo\n", __func__);
nfs_fattr_init(info->fattr);
status = rpc_call_sync(client, &msg, 0);
dprintk("%s: reply fsinfo: %d\n", __func__, status);
if (status == 0 && !(info->fattr->valid & NFS_ATTR_FATTR)) {
msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR];
msg.rpc_resp = info->fattr;
status = rpc_call_sync(client, &msg, 0);
dprintk("%s: reply getattr: %d\n", __func__, status);
}
return status;
}
/*
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 07:06:13 +07:00
* Bare-bones access to getattr: this is for nfs_get_root/nfs_get_sb
*/
static int
nfs3_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fsinfo *info)
{
int status;
status = do_proc_get_root(server->client, fhandle, info);
if (status && server->nfs_client->cl_rpcclient != server->client)
status = do_proc_get_root(server->nfs_client->cl_rpcclient, fhandle, info);
return status;
}
/*
* One function for each procedure in the NFS protocol.
*/
static int
nfs3_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fattr *fattr, struct nfs4_label *label)
{
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR],
.rpc_argp = fhandle,
.rpc_resp = fattr,
};
int status;
dprintk("NFS call getattr\n");
nfs_fattr_init(fattr);
status = rpc_call_sync(server->client, &msg, 0);
dprintk("NFS reply getattr: %d\n", status);
return status;
}
static int
nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
struct iattr *sattr)
{
struct inode *inode = d_inode(dentry);
struct nfs3_sattrargs arg = {
.fh = NFS_FH(inode),
.sattr = sattr,
};
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_SETATTR],
.rpc_argp = &arg,
.rpc_resp = fattr,
};
int status;
dprintk("NFS call setattr\n");
if (sattr->ia_valid & ATTR_FILE)
msg.rpc_cred = nfs_file_cred(sattr->ia_file);
nfs_fattr_init(fattr);
status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
if (status == 0)
nfs_setattr_update_inode(inode, sattr, fattr);
dprintk("NFS reply setattr: %d\n", status);
return status;
}
static int
nfs3_proc_lookup(struct inode *dir, const struct qstr *name,
struct nfs_fh *fhandle, struct nfs_fattr *fattr,
struct nfs4_label *label)
{
struct nfs3_diropargs arg = {
.fh = NFS_FH(dir),
.name = name->name,
.len = name->len
};
struct nfs3_diropres res = {
.fh = fhandle,
.fattr = fattr
};
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_LOOKUP],
.rpc_argp = &arg,
.rpc_resp = &res,
};
int status;
dprintk("NFS call lookup %s\n", name->name);
res.dir_attr = nfs_alloc_fattr();
if (res.dir_attr == NULL)
return -ENOMEM;
nfs_fattr_init(fattr);
status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
nfs_refresh_inode(dir, res.dir_attr);
if (status >= 0 && !(fattr->valid & NFS_ATTR_FATTR)) {
msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR];
msg.rpc_argp = fhandle;
msg.rpc_resp = fattr;
status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
}
nfs_free_fattr(res.dir_attr);
dprintk("NFS reply lookup: %d\n", status);
return status;
}
static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
{
struct nfs3_accessargs arg = {
.fh = NFS_FH(inode),
};
struct nfs3_accessres res;
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_ACCESS],
.rpc_argp = &arg,
.rpc_resp = &res,
.rpc_cred = entry->cred,
};
int mode = entry->mask;
int status = -ENOMEM;
dprintk("NFS call access\n");
if (mode & MAY_READ)
arg.access |= NFS3_ACCESS_READ;
if (S_ISDIR(inode->i_mode)) {
if (mode & MAY_WRITE)
arg.access |= NFS3_ACCESS_MODIFY | NFS3_ACCESS_EXTEND | NFS3_ACCESS_DELETE;
if (mode & MAY_EXEC)
arg.access |= NFS3_ACCESS_LOOKUP;
} else {
if (mode & MAY_WRITE)
arg.access |= NFS3_ACCESS_MODIFY | NFS3_ACCESS_EXTEND;
if (mode & MAY_EXEC)
arg.access |= NFS3_ACCESS_EXECUTE;
}
res.fattr = nfs_alloc_fattr();
if (res.fattr == NULL)
goto out;
status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
nfs_refresh_inode(inode, res.fattr);
if (status == 0) {
entry->mask = 0;
if (res.access & NFS3_ACCESS_READ)
entry->mask |= MAY_READ;
if (res.access & (NFS3_ACCESS_MODIFY | NFS3_ACCESS_EXTEND | NFS3_ACCESS_DELETE))
entry->mask |= MAY_WRITE;
if (res.access & (NFS3_ACCESS_LOOKUP|NFS3_ACCESS_EXECUTE))
entry->mask |= MAY_EXEC;
}
nfs_free_fattr(res.fattr);
out:
dprintk("NFS reply access: %d\n", status);
return status;
}
static int nfs3_proc_readlink(struct inode *inode, struct page *page,
unsigned int pgbase, unsigned int pglen)
{
struct nfs_fattr *fattr;
struct nfs3_readlinkargs args = {
.fh = NFS_FH(inode),
.pgbase = pgbase,
.pglen = pglen,
.pages = &page
};
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_READLINK],
.rpc_argp = &args,
};
int status = -ENOMEM;
dprintk("NFS call readlink\n");
fattr = nfs_alloc_fattr();
if (fattr == NULL)
goto out;
msg.rpc_resp = fattr;
status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
nfs_refresh_inode(inode, fattr);
nfs_free_fattr(fattr);
out:
dprintk("NFS reply readlink: %d\n", status);
return status;
}
struct nfs3_createdata {
struct rpc_message msg;
union {
struct nfs3_createargs create;
struct nfs3_mkdirargs mkdir;
struct nfs3_symlinkargs symlink;
struct nfs3_mknodargs mknod;
} arg;
struct nfs3_diropres res;
struct nfs_fh fh;
struct nfs_fattr fattr;
struct nfs_fattr dir_attr;
};
static struct nfs3_createdata *nfs3_alloc_createdata(void)
{
struct nfs3_createdata *data;
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (data != NULL) {
data->msg.rpc_argp = &data->arg;
data->msg.rpc_resp = &data->res;
data->res.fh = &data->fh;
data->res.fattr = &data->fattr;
data->res.dir_attr = &data->dir_attr;
nfs_fattr_init(data->res.fattr);
nfs_fattr_init(data->res.dir_attr);
}
return data;
}
static int nfs3_do_create(struct inode *dir, struct dentry *dentry, struct nfs3_createdata *data)
{
int status;
status = rpc_call_sync(NFS_CLIENT(dir), &data->msg, 0);
nfs_post_op_update_inode(dir, data->res.dir_attr);
if (status == 0)
status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL);
return status;
}
static void nfs3_free_createdata(struct nfs3_createdata *data)
{
kfree(data);
}
/*
* Create a regular file.
*/
static int
nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
int flags)
{
struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
int status = -ENOMEM;
dprintk("NFS call create %pd\n", dentry);
data = nfs3_alloc_createdata();
if (data == NULL)
goto out;
data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_CREATE];
data->arg.create.fh = NFS_FH(dir);
data->arg.create.name = dentry->d_name.name;
data->arg.create.len = dentry->d_name.len;
data->arg.create.sattr = sattr;
data->arg.create.createmode = NFS3_CREATE_UNCHECKED;
if (flags & O_EXCL) {
data->arg.create.createmode = NFS3_CREATE_EXCLUSIVE;
data->arg.create.verifier[0] = cpu_to_be32(jiffies);
data->arg.create.verifier[1] = cpu_to_be32(current->pid);
}
status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl);
if (status)
goto out;
for (;;) {
status = nfs3_do_create(dir, dentry, data);
if (status != -ENOTSUPP)
break;
/* If the server doesn't support the exclusive creation
* semantics, try again with simple 'guarded' mode. */
switch (data->arg.create.createmode) {
case NFS3_CREATE_EXCLUSIVE:
data->arg.create.createmode = NFS3_CREATE_GUARDED;
break;
case NFS3_CREATE_GUARDED:
data->arg.create.createmode = NFS3_CREATE_UNCHECKED;
break;
case NFS3_CREATE_UNCHECKED:
goto out;
}
nfs_fattr_init(data->res.dir_attr);
nfs_fattr_init(data->res.fattr);
}
if (status != 0)
goto out_release_acls;
/* When we created the file with exclusive semantics, make
* sure we set the attributes afterwards. */
if (data->arg.create.createmode == NFS3_CREATE_EXCLUSIVE) {
dprintk("NFS call setattr (post-create)\n");
if (!(sattr->ia_valid & ATTR_ATIME_SET))
sattr->ia_valid |= ATTR_ATIME;
if (!(sattr->ia_valid & ATTR_MTIME_SET))
sattr->ia_valid |= ATTR_MTIME;
/* Note: we could use a guarded setattr here, but I'm
* not sure this buys us anything (and I'd have
* to revamp the NFSv3 XDR code) */
status = nfs3_proc_setattr(dentry, data->res.fattr, sattr);
nfs_post_op_update_inode(d_inode(dentry), data->res.fattr);
dprintk("NFS reply setattr (post-create): %d\n", status);
if (status != 0)
goto out_release_acls;
}
status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl);
out_release_acls:
posix_acl_release(acl);
posix_acl_release(default_acl);
out:
nfs3_free_createdata(data);
dprintk("NFS reply create: %d\n", status);
return status;
}
static int
nfs3_proc_remove(struct inode *dir, const struct qstr *name)
{
struct nfs_removeargs arg = {
.fh = NFS_FH(dir),
.name = *name,
};
struct nfs_removeres res;
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_REMOVE],
.rpc_argp = &arg,
.rpc_resp = &res,
};
int status = -ENOMEM;
dprintk("NFS call remove %s\n", name->name);
res.dir_attr = nfs_alloc_fattr();
if (res.dir_attr == NULL)
goto out;
status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
nfs_post_op_update_inode(dir, res.dir_attr);
nfs_free_fattr(res.dir_attr);
out:
dprintk("NFS reply remove: %d\n", status);
return status;
}
static void
nfs3_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
{
msg->rpc_proc = &nfs3_procedures[NFS3PROC_REMOVE];
}
static void nfs3_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
{
rpc_call_start(task);
}
static int
nfs3_proc_unlink_done(struct rpc_task *task, struct inode *dir)
{
struct nfs_removeres *res;
if (nfs3_async_handle_jukebox(task, dir))
return 0;
res = task->tk_msg.rpc_resp;
nfs_post_op_update_inode(dir, res->dir_attr);
return 1;
}
static void
nfs3_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
{
msg->rpc_proc = &nfs3_procedures[NFS3PROC_RENAME];
}
static void nfs3_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data)
{
rpc_call_start(task);
}
static int
nfs3_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
struct inode *new_dir)
{
struct nfs_renameres *res;
if (nfs3_async_handle_jukebox(task, old_dir))
return 0;
res = task->tk_msg.rpc_resp;
nfs_post_op_update_inode(old_dir, res->old_fattr);
nfs_post_op_update_inode(new_dir, res->new_fattr);
return 1;
}
static int
nfs3_proc_link(struct inode *inode, struct inode *dir, const struct qstr *name)
{
struct nfs3_linkargs arg = {
.fromfh = NFS_FH(inode),
.tofh = NFS_FH(dir),
.toname = name->name,
.tolen = name->len
};
struct nfs3_linkres res;
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_LINK],
.rpc_argp = &arg,
.rpc_resp = &res,
};
int status = -ENOMEM;
dprintk("NFS call link %s\n", name->name);
res.fattr = nfs_alloc_fattr();
res.dir_attr = nfs_alloc_fattr();
if (res.fattr == NULL || res.dir_attr == NULL)
goto out;
status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
nfs_post_op_update_inode(dir, res.dir_attr);
nfs_post_op_update_inode(inode, res.fattr);
out:
nfs_free_fattr(res.dir_attr);
nfs_free_fattr(res.fattr);
dprintk("NFS reply link: %d\n", status);
return status;
}
static int
nfs3_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
unsigned int len, struct iattr *sattr)
{
struct nfs3_createdata *data;
int status = -ENOMEM;
if (len > NFS3_MAXPATHLEN)
return -ENAMETOOLONG;
dprintk("NFS call symlink %pd\n", dentry);
data = nfs3_alloc_createdata();
if (data == NULL)
goto out;
data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_SYMLINK];
data->arg.symlink.fromfh = NFS_FH(dir);
data->arg.symlink.fromname = dentry->d_name.name;
data->arg.symlink.fromlen = dentry->d_name.len;
data->arg.symlink.pages = &page;
data->arg.symlink.pathlen = len;
data->arg.symlink.sattr = sattr;
status = nfs3_do_create(dir, dentry, data);
nfs3_free_createdata(data);
out:
dprintk("NFS reply symlink: %d\n", status);
return status;
}
static int
nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr)
{
struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
int status = -ENOMEM;
dprintk("NFS call mkdir %pd\n", dentry);
data = nfs3_alloc_createdata();
if (data == NULL)
goto out;
status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl);
if (status)
goto out;
data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_MKDIR];
data->arg.mkdir.fh = NFS_FH(dir);
data->arg.mkdir.name = dentry->d_name.name;
data->arg.mkdir.len = dentry->d_name.len;
data->arg.mkdir.sattr = sattr;
status = nfs3_do_create(dir, dentry, data);
if (status != 0)
goto out_release_acls;
status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl);
out_release_acls:
posix_acl_release(acl);
posix_acl_release(default_acl);
out:
nfs3_free_createdata(data);
dprintk("NFS reply mkdir: %d\n", status);
return status;
}
static int
nfs3_proc_rmdir(struct inode *dir, const struct qstr *name)
{
struct nfs_fattr *dir_attr;
struct nfs3_diropargs arg = {
.fh = NFS_FH(dir),
.name = name->name,
.len = name->len
};
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_RMDIR],
.rpc_argp = &arg,
};
int status = -ENOMEM;
dprintk("NFS call rmdir %s\n", name->name);
dir_attr = nfs_alloc_fattr();
if (dir_attr == NULL)
goto out;
msg.rpc_resp = dir_attr;
status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
nfs_post_op_update_inode(dir, dir_attr);
nfs_free_fattr(dir_attr);
out:
dprintk("NFS reply rmdir: %d\n", status);
return status;
}
/*
* The READDIR implementation is somewhat hackish - we pass the user buffer
* to the encode function, which installs it in the receive iovec.
* The decode function itself doesn't perform any decoding, it just makes
* sure the reply is syntactically correct.
*
* Also note that this implementation handles both plain readdir and
* readdirplus.
*/
static int
nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
u64 cookie, struct page **pages, unsigned int count, int plus)
{
struct inode *dir = d_inode(dentry);
__be32 *verf = NFS_I(dir)->cookieverf;
struct nfs3_readdirargs arg = {
.fh = NFS_FH(dir),
.cookie = cookie,
.verf = {verf[0], verf[1]},
.plus = plus,
.count = count,
.pages = pages
};
struct nfs3_readdirres res = {
.verf = verf,
.plus = plus
};
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_READDIR],
.rpc_argp = &arg,
.rpc_resp = &res,
.rpc_cred = cred
};
int status = -ENOMEM;
if (plus)
msg.rpc_proc = &nfs3_procedures[NFS3PROC_READDIRPLUS];
dprintk("NFS call readdir%s %d\n",
plus? "plus" : "", (unsigned int) cookie);
res.dir_attr = nfs_alloc_fattr();
if (res.dir_attr == NULL)
goto out;
status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
nfs_invalidate_atime(dir);
nfs_refresh_inode(dir, res.dir_attr);
nfs_free_fattr(res.dir_attr);
out:
dprintk("NFS reply readdir%s: %d\n",
plus? "plus" : "", status);
return status;
}
static int
nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
dev_t rdev)
{
struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
int status = -ENOMEM;
dprintk("NFS call mknod %pd %u:%u\n", dentry,
MAJOR(rdev), MINOR(rdev));
data = nfs3_alloc_createdata();
if (data == NULL)
goto out;
status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl);
if (status)
goto out;
data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_MKNOD];
data->arg.mknod.fh = NFS_FH(dir);
data->arg.mknod.name = dentry->d_name.name;
data->arg.mknod.len = dentry->d_name.len;
data->arg.mknod.sattr = sattr;
data->arg.mknod.rdev = rdev;
switch (sattr->ia_mode & S_IFMT) {
case S_IFBLK:
data->arg.mknod.type = NF3BLK;
break;
case S_IFCHR:
data->arg.mknod.type = NF3CHR;
break;
case S_IFIFO:
data->arg.mknod.type = NF3FIFO;
break;
case S_IFSOCK:
data->arg.mknod.type = NF3SOCK;
break;
default:
status = -EINVAL;
goto out;
}
status = nfs3_do_create(dir, dentry, data);
if (status != 0)
goto out_release_acls;
status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl);
out_release_acls:
posix_acl_release(acl);
posix_acl_release(default_acl);
out:
nfs3_free_createdata(data);
dprintk("NFS reply mknod: %d\n", status);
return status;
}
static int
nfs3_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fsstat *stat)
{
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_FSSTAT],
.rpc_argp = fhandle,
.rpc_resp = stat,
};
int status;
dprintk("NFS call fsstat\n");
nfs_fattr_init(stat->fattr);
status = rpc_call_sync(server->client, &msg, 0);
dprintk("NFS reply fsstat: %d\n", status);
return status;
}
static int
do_proc_fsinfo(struct rpc_clnt *client, struct nfs_fh *fhandle,
struct nfs_fsinfo *info)
{
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_FSINFO],
.rpc_argp = fhandle,
.rpc_resp = info,
};
int status;
dprintk("NFS call fsinfo\n");
nfs_fattr_init(info->fattr);
status = rpc_call_sync(client, &msg, 0);
dprintk("NFS reply fsinfo: %d\n", status);
return status;
}
/*
* Bare-bones access to fsinfo: this is for nfs_get_root/nfs_get_sb via
* nfs_create_server
*/
static int
nfs3_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fsinfo *info)
{
int status;
status = do_proc_fsinfo(server->client, fhandle, info);
if (status && server->nfs_client->cl_rpcclient != server->client)
status = do_proc_fsinfo(server->nfs_client->cl_rpcclient, fhandle, info);
return status;
}
static int
nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_pathconf *info)
{
struct rpc_message msg = {
.rpc_proc = &nfs3_procedures[NFS3PROC_PATHCONF],
.rpc_argp = fhandle,
.rpc_resp = info,
};
int status;
dprintk("NFS call pathconf\n");
nfs_fattr_init(info->fattr);
status = rpc_call_sync(server->client, &msg, 0);
dprintk("NFS reply pathconf: %d\n", status);
return status;
}
static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
{
struct inode *inode = hdr->inode;
if (hdr->pgio_done_cb != NULL)
return hdr->pgio_done_cb(task, hdr);
if (nfs3_async_handle_jukebox(task, inode))
return -EAGAIN;
nfs_invalidate_atime(inode);
nfs_refresh_inode(inode, &hdr->fattr);
return 0;
}
static void nfs3_proc_read_setup(struct nfs_pgio_header *hdr,
struct rpc_message *msg)
{
msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ];
}
static int nfs3_proc_pgio_rpc_prepare(struct rpc_task *task,
struct nfs_pgio_header *hdr)
{
rpc_call_start(task);
NFSv4: Don't try to recover NFSv4 locks when they are lost. When an NFSv4 client loses contact with the server it can lose any locks that it holds. Currently when it reconnects to the server it simply tries to reclaim those locks. This might succeed even though some other client has held and released a lock in the mean time. So the first client might think the file is unchanged, but it isn't. This isn't good. If, when recovery happens, the locks cannot be claimed because some other client still holds the lock, then we get a message in the kernel logs, but the client can still write. So two clients can both think they have a lock and can both write at the same time. This is equally not good. There was a patch a while ago http://comments.gmane.org/gmane.linux.nfs/41917 which tried to address some of this, but it didn't seem to go anywhere. That patch would also send a signal to the process. That might be useful but for now this patch just causes writes to fail. For NFSv4 (unlike v2/v3) there is a strong link between the lock and the write request so we can fairly easily fail any IO of the lock is gone. While some applications might not expect this, it is still safer than allowing the write to succeed. Because this is a fairly big change in behaviour a module parameter, "recover_locks", is introduced which defaults to true (the current behaviour) but can be set to "false" to tell the client not to try to recover things that were lost. Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2013-09-04 14:04:49 +07:00
return 0;
}
static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
{
struct inode *inode = hdr->inode;
if (hdr->pgio_done_cb != NULL)
return hdr->pgio_done_cb(task, hdr);
if (nfs3_async_handle_jukebox(task, inode))
return -EAGAIN;
if (task->tk_status >= 0)
nfs_writeback_update_inode(hdr);
return 0;
}
static void nfs3_proc_write_setup(struct nfs_pgio_header *hdr,
struct rpc_message *msg)
{
msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE];
}
static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
{
rpc_call_start(task);
}
static int nfs3_commit_done(struct rpc_task *task, struct nfs_commit_data *data)
{
if (data->commit_done_cb != NULL)
return data->commit_done_cb(task, data);
if (nfs3_async_handle_jukebox(task, data->inode))
return -EAGAIN;
nfs_refresh_inode(data->inode, data->res.fattr);
return 0;
}
static void nfs3_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg)
{
msg->rpc_proc = &nfs3_procedures[NFS3PROC_COMMIT];
}
static int
nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
{
struct inode *inode = file_inode(filp);
return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl);
}
static int nfs3_have_delegation(struct inode *inode, fmode_t flags)
{
return 0;
}
static int nfs3_return_delegation(struct inode *inode)
{
nfs_wb_all(inode);
return 0;
}
static const struct inode_operations nfs3_dir_inode_operations = {
.create = nfs_create,
.lookup = nfs_lookup,
.link = nfs_link,
.unlink = nfs_unlink,
.symlink = nfs_symlink,
.mkdir = nfs_mkdir,
.rmdir = nfs_rmdir,
.mknod = nfs_mknod,
.rename = nfs_rename,
.permission = nfs_permission,
.getattr = nfs_getattr,
.setattr = nfs_setattr,
#ifdef CONFIG_NFS_V3_ACL
.listxattr = nfs3_listxattr,
.get_acl = nfs3_get_acl,
.set_acl = nfs3_set_acl,
#endif
};
static const struct inode_operations nfs3_file_inode_operations = {
.permission = nfs_permission,
.getattr = nfs_getattr,
.setattr = nfs_setattr,
#ifdef CONFIG_NFS_V3_ACL
.listxattr = nfs3_listxattr,
.get_acl = nfs3_get_acl,
.set_acl = nfs3_set_acl,
#endif
};
const struct nfs_rpc_ops nfs_v3_clientops = {
.version = 3, /* protocol version */
.dentry_ops = &nfs_dentry_operations,
.dir_inode_ops = &nfs3_dir_inode_operations,
.file_inode_ops = &nfs3_file_inode_operations,
.file_ops = &nfs_file_operations,
.getroot = nfs3_proc_get_root,
.submount = nfs_submount,
.try_mount = nfs_try_mount,
.getattr = nfs3_proc_getattr,
.setattr = nfs3_proc_setattr,
.lookup = nfs3_proc_lookup,
.access = nfs3_proc_access,
.readlink = nfs3_proc_readlink,
.create = nfs3_proc_create,
.remove = nfs3_proc_remove,
.unlink_setup = nfs3_proc_unlink_setup,
.unlink_rpc_prepare = nfs3_proc_unlink_rpc_prepare,
.unlink_done = nfs3_proc_unlink_done,
.rename_setup = nfs3_proc_rename_setup,
.rename_rpc_prepare = nfs3_proc_rename_rpc_prepare,
.rename_done = nfs3_proc_rename_done,
.link = nfs3_proc_link,
.symlink = nfs3_proc_symlink,
.mkdir = nfs3_proc_mkdir,
.rmdir = nfs3_proc_rmdir,
.readdir = nfs3_proc_readdir,
.mknod = nfs3_proc_mknod,
.statfs = nfs3_proc_statfs,
.fsinfo = nfs3_proc_fsinfo,
.pathconf = nfs3_proc_pathconf,
.decode_dirent = nfs3_decode_dirent,
.pgio_rpc_prepare = nfs3_proc_pgio_rpc_prepare,
.read_setup = nfs3_proc_read_setup,
.read_done = nfs3_read_done,
.write_setup = nfs3_proc_write_setup,
.write_done = nfs3_write_done,
.commit_setup = nfs3_proc_commit_setup,
.commit_rpc_prepare = nfs3_proc_commit_rpc_prepare,
.commit_done = nfs3_commit_done,
.lock = nfs3_proc_lock,
.clear_acl_cache = forget_all_cached_acls,
.close_context = nfs_close_context,
.have_delegation = nfs3_have_delegation,
.return_delegation = nfs3_return_delegation,
.alloc_client = nfs_alloc_client,
.init_client = nfs_init_client,
.free_client = nfs_free_client,
.create_server = nfs3_create_server,
.clone_server = nfs3_clone_server,
};