#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.
* Zerocpy NFS support (C) 2002 Hirokazu Takahashi <taka@valinux.co.jp>
*/
-#include <linux/string.h>
-#include <linux/time.h>
-#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
-#include <linux/mount.h>
-#include <linux/major.h>
#include <linux/splice.h>
-#include <linux/proc_fs.h>
-#include <linux/stat.h>
#include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/pagemap.h>
-#include <linux/in.h>
-#include <linux/module.h>
#include <linux/namei.h>
-#include <linux/vfs.h>
#include <linux/delay.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#ifdef CONFIG_NFSD_V3
-#include <linux/nfs3.h>
-#include <linux/nfsd/xdr3.h>
-#endif /* CONFIG_NFSD_V3 */
-#include <linux/nfsd/nfsfh.h>
-#include <linux/quotaops.h>
#include <linux/fsnotify.h>
-#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#include <linux/xattr.h>
+#include <linux/jhash.h>
+#include <linux/ima.h>
+#include <linux/slab.h>
+#include <asm/uaccess.h>
+#include <linux/exportfs.h>
+#include <linux/writeback.h>
+
+#ifdef CONFIG_NFSD_V3
+#include "xdr3.h"
+#endif /* CONFIG_NFSD_V3 */
+
#ifdef CONFIG_NFSD_V4
-#include <linux/nfs4.h>
#include <linux/nfs4_acl.h>
#include <linux/nfsd_idmap.h>
-#include <linux/security.h>
#endif /* CONFIG_NFSD_V4 */
-#include <linux/jhash.h>
-#include <linux/ima.h>
-#include <asm/uaccess.h>
+#include "nfsd.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_FILEOP
.dentry = dget(dentry)};
int err = 0;
- while (follow_down(&path.mnt, &path.dentry) &&
- d_mountpoint(path.dentry))
+ while (d_mountpoint(path.dentry) && follow_down(&path))
;
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;
}
- if ((exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) {
+ if (nfsd_v4client(rqstp) ||
+ (exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) {
/* successfully crossed mount point */
/*
* This is subtle: path.dentry is *not* on path.mnt
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;
+}
+
+/*
+ * For nfsd purposes, we treat V4ROOT exports as though there was an
+ * export at *every* directory.
+ */
+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,
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 */
- 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.mnt, &path.dentry))
- ;
- 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);
/*
* 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;
return err;
}
+/*
+ * Commit metadata changes to stable storage.
+ */
+static int
+commit_metadata(struct svc_fh *fhp)
+{
+ struct inode *inode = fhp->fh_dentry->d_inode;
+ const struct export_operations *export_ops = inode->i_sb->s_export_op;
+ int error = 0;
+
+ if (!EX_ISSYNC(fhp->fh_export))
+ return 0;
+
+ if (export_ops->commit_metadata) {
+ error = export_ops->commit_metadata(inode);
+ } else {
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = 0, /* metadata only */
+ };
+
+ error = sync_inode(inode, &wbc);
+ }
+
+ return error;
+}
/*
* Set various file attributes.
* If we are changing the size of the file, then
* we need to break all leases.
*/
- host_err = break_lease(inode, FMODE_WRITE | O_NONBLOCK);
+ host_err = break_lease(inode, O_WRONLY | O_NONBLOCK);
if (host_err == -EWOULDBLOCK)
host_err = -ETIMEDOUT;
if (host_err) /* ENOMEM or EWOULDBLOCK */
put_write_access(inode);
goto out_nfserr;
}
- vfs_dq_init(inode);
}
/* sanitize the mode change */
if (size_change)
put_write_access(inode);
if (!err)
- if (EX_ISSYNC(fhp->fh_export))
- write_inode_now(inode, 1);
+ commit_metadata(fhp);
out:
return err;
nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
int access, struct file **filp)
{
- const struct cred *cred = current_cred();
struct dentry *dentry;
struct inode *inode;
int flags = O_RDONLY|O_LARGEFILE;
__be32 err;
- int host_err;
+ int host_err = 0;
+
+ validate_process_creds();
/*
* If we get here, then the client has already done an "open",
* Check to see if there are any leases on this file.
* This may block while leases are broken.
*/
- host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? FMODE_WRITE : 0));
+ if (!(access & NFSD_MAY_NOT_BREAK_LEASE))
+ host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? O_WRONLY : 0));
if (host_err == -EWOULDBLOCK)
host_err = -ETIMEDOUT;
if (host_err) /* NOMEM or WOULDBLOCK */
flags = O_RDWR|O_LARGEFILE;
else
flags = O_WRONLY|O_LARGEFILE;
-
- vfs_dq_init(inode);
}
*filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_path.mnt),
- flags, cred);
+ flags, current_cred());
if (IS_ERR(*filp))
host_err = PTR_ERR(*filp);
else
- ima_counts_get(*filp);
+ host_err = ima_file_check(*filp, access);
out_nfserr:
err = nfserrno(host_err);
out:
+ validate_process_creds();
return err;
}
}
/*
- * Sync a file
- * As this calls fsync (not fdatasync) there is no need for a write_inode
- * after it.
- */
-static inline int nfsd_dosync(struct file *filp, struct dentry *dp,
- const struct file_operations *fop)
-{
- struct inode *inode = dp->d_inode;
- int (*fsync) (struct file *, struct dentry *, int);
- int err;
-
- err = filemap_fdatawrite(inode->i_mapping);
- if (err == 0 && fop && (fsync = fop->fsync))
- err = fsync(filp, dp, 0);
- if (err == 0)
- err = filemap_fdatawait(inode->i_mapping);
-
- return err;
-}
-
-static int
-nfsd_sync(struct file *filp)
-{
- int err;
- struct inode *inode = filp->f_path.dentry->d_inode;
- dprintk("nfsd: sync file %s\n", filp->f_path.dentry->d_name.name);
- mutex_lock(&inode->i_mutex);
- err=nfsd_dosync(filp, filp->f_path.dentry, filp->f_op);
- mutex_unlock(&inode->i_mutex);
-
- return err;
-}
-
-int
-nfsd_sync_dir(struct dentry *dp)
-{
- return nfsd_dosync(NULL, dp, dp->d_inode->i_fop);
-}
-
-/*
* Obtain the readahead parameters for the file
* specified by (dev, ino).
*/
mutex_unlock(&dentry->d_inode->i_mutex);
}
+/*
+ * Gathered writes: If another process is currently writing to the file,
+ * there's a high chance this is another nfsd (triggered by a bulk write
+ * from a client's biod). Rather than syncing the file with each write
+ * request, we sleep for 10 msec.
+ *
+ * I don't know if this roughly approximates C. Juszak's idea of
+ * gathered writes, but it's a nice and simple solution (IMHO), and it
+ * seems to work:-)
+ *
+ * Note: we do this only in the NFSv2 case, since v3 and higher have a
+ * better tool (separate unstable writes and commits) for solving this
+ * problem.
+ */
+static int wait_for_concurrent_writes(struct file *file)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ static ino_t last_ino;
+ static dev_t last_dev;
+ int err = 0;
+
+ if (atomic_read(&inode->i_writecount) > 1
+ || (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) {
+ dprintk("nfsd: write defer %d\n", task_pid_nr(current));
+ msleep(10);
+ dprintk("nfsd: write resume %d\n", task_pid_nr(current));
+ }
+
+ if (inode->i_state & I_DIRTY) {
+ dprintk("nfsd: write sync %d\n", task_pid_nr(current));
+ err = vfs_fsync(file, 0);
+ }
+ last_ino = inode->i_ino;
+ last_dev = inode->i_sb->s_dev;
+ return err;
+}
+
static __be32
nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
loff_t offset, struct kvec *vec, int vlen,
__be32 err = 0;
int host_err;
int stable = *stablep;
+ int use_wgather;
#ifdef MSNFS
err = nfserr_perm;
* - the sync export option has been set, or
* - the client requested O_SYNC behavior (NFSv3 feature).
* - The file system doesn't support fsync().
- * When gathered writes have been configured for this volume,
+ * When NFSv2 gathered writes have been configured for this volume,
* flushing the data to disk is handled separately below.
*/
+ use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
if (!file->f_op->fsync) {/* COMMIT3 cannot work */
stable = 2;
if (!EX_ISSYNC(exp))
stable = 0;
- if (stable && !EX_WGATHER(exp)) {
+ if (stable && !use_wgather) {
spin_lock(&file->f_lock);
file->f_flags |= O_SYNC;
spin_unlock(&file->f_lock);
oldfs = get_fs(); set_fs(KERNEL_DS);
host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset);
set_fs(oldfs);
- if (host_err >= 0) {
- *cnt = host_err;
- nfsdstats.io_write += host_err;
- fsnotify_modify(file->f_path.dentry);
- }
+ if (host_err < 0)
+ goto out_nfserr;
+ *cnt = host_err;
+ nfsdstats.io_write += host_err;
+ fsnotify_modify(file->f_path.dentry);
/* clear setuid/setgid flag after write */
- if (host_err >= 0 && (inode->i_mode & (S_ISUID | S_ISGID)))
+ if (inode->i_mode & (S_ISUID | S_ISGID))
kill_suid(dentry);
- if (host_err >= 0 && stable) {
- static ino_t last_ino;
- static dev_t last_dev;
-
- /*
- * Gathered writes: If another process is currently
- * writing to the file, there's a high chance
- * this is another nfsd (triggered by a bulk write
- * from a client's biod). Rather than syncing the
- * file with each write request, we sleep for 10 msec.
- *
- * I don't know if this roughly approximates
- * C. Juszak's idea of gathered writes, but it's a
- * nice and simple solution (IMHO), and it seems to
- * work:-)
- */
- if (EX_WGATHER(exp)) {
- if (atomic_read(&inode->i_writecount) > 1
- || (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) {
- dprintk("nfsd: write defer %d\n", task_pid_nr(current));
- msleep(10);
- dprintk("nfsd: write resume %d\n", task_pid_nr(current));
- }
-
- if (inode->i_state & I_DIRTY) {
- dprintk("nfsd: write sync %d\n", task_pid_nr(current));
- host_err=nfsd_sync(file);
- }
-#if 0
- wake_up(&inode->i_wait);
-#endif
- }
- last_ino = inode->i_ino;
- last_dev = inode->i_sb->s_dev;
- }
+ if (stable && use_wgather)
+ host_err = wait_for_concurrent_writes(file);
+out_nfserr:
dprintk("nfsd: write complete host_err=%d\n", host_err);
if (host_err >= 0)
err = 0;
#ifdef CONFIG_NFSD_V3
/*
* Commit all pending writes to stable storage.
- * Strictly speaking, we could sync just the indicated file region here,
- * but there's currently no way we can ask the VFS to do so.
+ *
+ * Note: we only guarantee that data that lies within the range specified
+ * by the 'offset' and 'count' parameters will be synced.
*
* Unfortunately we cannot lock the file to make sure we return full WCC
* data to the client, as locking happens lower down in the filesystem.
loff_t offset, unsigned long count)
{
struct file *file;
- __be32 err;
+ loff_t end = LLONG_MAX;
+ __be32 err = nfserr_inval;
- if ((u64)count > ~(u64)offset)
- return nfserr_inval;
+ if (offset < 0)
+ goto out;
+ if (count != 0) {
+ end = offset + (loff_t)count - 1;
+ if (end < offset)
+ goto out;
+ }
- err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
+ err = nfsd_open(rqstp, fhp, S_IFREG,
+ NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &file);
if (err)
- return err;
+ goto out;
if (EX_ISSYNC(fhp->fh_export)) {
- if (file->f_op && file->f_op->fsync) {
- err = nfserrno(nfsd_sync(file));
- } else {
+ int err2 = vfs_fsync_range(file, offset, end, 0);
+
+ if (err2 != -EINVAL)
+ err = nfserrno(err2);
+ else
err = nfserr_notsupp;
- }
}
nfsd_close(file);
+out:
return err;
}
#endif /* CONFIG_NFSD_V3 */
goto out_nfserr;
}
- if (EX_ISSYNC(fhp->fh_export)) {
- err = nfserrno(nfsd_sync_dir(dentry));
- write_inode_now(dchild->d_inode, 1);
- }
+ err = nfsd_create_setattr(rqstp, resfhp, iap);
- err2 = nfsd_create_setattr(rqstp, resfhp, iap);
+ /*
+ * nfsd_setattr already committed the child. Transactional filesystems
+ * had a chance to commit changes for both parent and child
+ * simultaneously making the following commit_metadata a noop.
+ */
+ err2 = nfserrno(commit_metadata(fhp));
if (err2)
err = err2;
mnt_drop_write(fhp->fh_export->ex_path.mnt);
struct dentry *dentry, *dchild = NULL;
struct inode *dirp;
__be32 err;
- __be32 err2;
int host_err;
__u32 v_mtime=0, v_atime=0;
if (created)
*created = 1;
- if (EX_ISSYNC(fhp->fh_export)) {
- err = nfserrno(nfsd_sync_dir(dentry));
- /* setattr will sync the child (or not) */
- }
-
nfsd_check_ignore_resizing(iap);
if (createmode == NFS3_CREATE_EXCLUSIVE) {
}
set_attr:
- err2 = nfsd_create_setattr(rqstp, resfhp, iap);
- if (err2)
- err = err2;
+ err = nfsd_create_setattr(rqstp, resfhp, iap);
+
+ /*
+ * nfsd_setattr already committed the child (and possibly also the parent).
+ */
+ if (!err)
+ err = nfserrno(commit_metadata(fhp));
mnt_drop_write(fhp->fh_export->ex_path.mnt);
/*
}
} else
host_err = vfs_symlink(dentry->d_inode, dnew, path);
-
- if (!host_err) {
- if (EX_ISSYNC(fhp->fh_export))
- host_err = nfsd_sync_dir(dentry);
- }
err = nfserrno(host_err);
+ if (!err)
+ err = nfserrno(commit_metadata(fhp));
fh_unlock(fhp);
mnt_drop_write(fhp->fh_export->ex_path.mnt);
}
host_err = vfs_link(dold, dirp, dnew);
if (!host_err) {
- if (EX_ISSYNC(ffhp->fh_export)) {
- err = nfserrno(nfsd_sync_dir(ddir));
- write_inode_now(dest, 1);
- }
- err = 0;
+ err = nfserrno(commit_metadata(ffhp));
+ if (!err)
+ err = nfserrno(commit_metadata(tfhp));
} else {
if (host_err == -EXDEV && rqstp->rq_vers == 2)
err = nfserr_acces;
goto out_dput_new;
host_err = vfs_rename(fdir, odentry, tdir, ndentry);
- if (!host_err && EX_ISSYNC(tfhp->fh_export)) {
- host_err = nfsd_sync_dir(tdentry);
+ if (!host_err) {
+ host_err = commit_metadata(tfhp);
if (!host_err)
- host_err = nfsd_sync_dir(fdentry);
+ host_err = commit_metadata(ffhp);
}
mnt_drop_write(ffhp->fh_export->ex_path.mnt);
dput(rdentry);
- if (host_err)
- goto out_drop;
- if (EX_ISSYNC(fhp->fh_export))
- host_err = nfsd_sync_dir(dentry);
+ if (!host_err)
+ host_err = commit_metadata(fhp);
-out_drop:
mnt_drop_write(fhp->fh_export->ex_path.mnt);
out_nfserr:
err = nfserrno(host_err);
*/
path.mnt = exp->ex_path.mnt;
path.dentry = dentry;
- err = ima_path_check(&path, acc & (MAY_READ | MAY_WRITE | MAY_EXEC),
- IMA_COUNT_LEAVE);
nfsd_out:
return err? nfserrno(err) : 0;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff