#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 <asm/uaccess.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 <asm/uaccess.h>
+#include "nfsd.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_FILEOP
{
struct svc_export *exp = *expp, *exp2 = NULL;
struct dentry *dentry = *dpp;
- struct vfsmount *mnt = mntget(exp->ex_path.mnt);
- struct dentry *mounts = dget(dentry);
+ struct path path = {.mnt = mntget(exp->ex_path.mnt),
+ .dentry = dget(dentry)};
int err = 0;
- while (follow_down(&mnt,&mounts)&&d_mountpoint(mounts));
+ while (d_mountpoint(path.dentry) && follow_down(&path))
+ ;
- exp2 = rqst_exp_get_by_name(rqstp, mnt, mounts);
+ exp2 = rqst_exp_get_by_name(rqstp, &path);
if (IS_ERR(exp2)) {
- if (PTR_ERR(exp2) != -ENOENT)
- err = PTR_ERR(exp2);
- dput(mounts);
- mntput(mnt);
+ 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 */
- exp_put(exp);
+ /*
+ * This is subtle: path.dentry is *not* on path.mnt
+ * at this point. The only reason we are safe is that
+ * original mnt is pinned down by exp, so we should
+ * put path *before* putting exp
+ */
+ *dpp = path.dentry;
+ path.dentry = dentry;
*expp = exp2;
- dput(dentry);
- *dpp = mounts;
- } else {
- exp_put(exp2);
- dput(mounts);
+ exp2 = exp;
}
- mntput(mnt);
+ path_put(&path);
+ exp_put(exp2);
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;
+}
+
+/*
+ * 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 vfsmount *mnt = mntget(exp->ex_path.mnt);
- dentry = dget(dparent);
- while(dentry == mnt->mnt_root && follow_up(&mnt, &dentry))
- ;
- dp = dget_parent(dentry);
- dput(dentry);
- dentry = dp;
-
- exp2 = rqst_exp_parent(rqstp, mnt, dentry);
- if (PTR_ERR(exp2) == -ENOENT) {
- dput(dentry);
- dentry = dget(dparent);
- } else if (IS_ERR(exp2)) {
- host_err = PTR_ERR(exp2);
- dput(dentry);
- mntput(mnt);
+ host_err = nfsd_lookup_parent(rqstp, dparent, &exp, &dentry);
+ if (host_err)
goto out_nfserr;
- } else {
- exp_put(exp);
- exp = exp2;
- }
- mntput(mnt);
}
} 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;
put_write_access(inode);
goto out_nfserr;
}
- DQUOT_INIT(inode);
+ vfs_dq_init(inode);
}
/* sanitize the mode change */
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;
+ validate_process_creds();
+
/*
* If we get here, then the client has already done an "open",
* and (hopefully) checked permission - so allow OWNER_OVERRIDE
else
flags = O_WRONLY|O_LARGEFILE;
- DQUOT_INIT(inode);
+ 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);
out_nfserr:
err = nfserrno(host_err);
out:
+ validate_process_creds();
return err;
}
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 = nfsd_sync(file);
+ }
+ 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);
+ }
/* Write the data. */
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) {
- 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) {
+ if (host_err >= 0)
err = 0;
- *cnt = host_err;
- } else
+ else
err = nfserrno(host_err);
out:
return err;
return 0;
}
-static int nfsd_buffered_readdir(struct file *file, filldir_t func,
- struct readdir_cd *cdp, loff_t *offsetp)
+static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func,
+ struct readdir_cd *cdp, loff_t *offsetp)
{
struct readdir_data buf;
struct buffered_dirent *de;
buf.dirent = (void *)__get_free_page(GFP_KERNEL);
if (!buf.dirent)
- return -ENOMEM;
+ return nfserrno(-ENOMEM);
offset = *offsetp;
while (1) {
+ struct inode *dir_inode = file->f_path.dentry->d_inode;
unsigned int reclen;
cdp->err = nfserr_eof; /* will be cleared on successful read */
if (!size)
break;
+ /*
+ * Various filldir functions may end up calling back into
+ * lookup_one_len() and the file system's ->lookup() method.
+ * These expect i_mutex to be held, as it would within readdir.
+ */
+ host_err = mutex_lock_killable(&dir_inode->i_mutex);
+ if (host_err)
+ break;
+
de = (struct buffered_dirent *)buf.dirent;
while (size > 0) {
offset = de->offset;
if (func(cdp, de->name, de->namlen, de->offset,
de->ino, de->d_type))
- goto done;
+ break;
if (cdp->err != nfs_ok)
- goto done;
+ break;
reclen = ALIGN(sizeof(*de) + de->namlen,
sizeof(u64));
size -= reclen;
de = (struct buffered_dirent *)((char *)de + reclen);
}
+ mutex_unlock(&dir_inode->i_mutex);
+ if (size > 0) /* We bailed out early */
+ break;
+
offset = vfs_llseek(file, 0, SEEK_CUR);
}
- done:
free_page((unsigned long)(buf.dirent));
if (host_err)
struct dentry *dentry, int acc)
{
struct inode *inode = dentry->d_inode;
+ struct path path;
int err;
if (acc == NFSD_MAY_NOP)
if (err == -EACCES && S_ISREG(inode->i_mode) &&
acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE))
err = inode_permission(inode, MAY_EXEC);
+ if (err)
+ goto nfsd_out;
+ /* Do integrity (permission) checking now, but defer incrementing
+ * IMA counts to the actual file open.
+ */
+ 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;
}