aboutsummaryrefslogtreecommitdiff
path: root/fs/nfsd/vfs.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfsd/vfs.c')
-rw-r--r--fs/nfsd/vfs.c1710
1 files changed, 887 insertions, 823 deletions
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 46f59d5365a..140c496f612 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1,7 +1,4 @@
-#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.
@@ -16,47 +13,34 @@
* 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>
-#ifdef CONFIG_NFSD_V4
-#include <linux/nfs4.h>
-#include <linux/nfs4_acl.h>
-#include <linux/nfsd_idmap.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>
#include <linux/security.h>
+
+#ifdef CONFIG_NFSD_V3
+#include "xdr3.h"
+#endif /* CONFIG_NFSD_V3 */
+
+#ifdef CONFIG_NFSD_V4
+#include "acl.h"
+#include "idmap.h"
#endif /* CONFIG_NFSD_V4 */
-#include <linux/jhash.h>
-#include <asm/uaccess.h>
+#include "nfsd.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_FILEOP
@@ -83,7 +67,6 @@ struct raparm_hbucket {
spinlock_t pb_lock;
} ____cacheline_aligned_in_smp;
-static struct raparms * raparml;
#define RAPARM_HASH_BITS 4
#define RAPARM_HASH_SIZE (1<<RAPARM_HASH_BITS)
#define RAPARM_HASH_MASK (RAPARM_HASH_SIZE-1)
@@ -101,35 +84,98 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
{
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));
+ err = follow_down(&path);
+ if (err < 0)
+ goto out;
- 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 (nfsd4_is_junction(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,
@@ -138,16 +184,10 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct svc_export *exp;
struct dentry *dparent;
struct dentry *dentry;
- __be32 err;
int host_err;
dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
- /* Obtain dentry and export. */
- err = fh_verify(rqstp, fhp, S_IFDIR, MAY_EXEC);
- if (err)
- return err;
-
dparent = fhp->fh_dentry;
exp = fhp->fh_export;
exp_get(exp);
@@ -158,37 +198,21 @@ 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 */
- 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);
+ /*
+ * In the nfsd4_open() case, this may be held across
+ * subsequent open and delegation acquisition which may
+ * need to take the child's i_mutex:
+ */
+ fh_lock_nested(fhp, I_MUTEX_PARENT);
dentry = lookup_one_len(name, dparent, len);
host_err = PTR_ERR(dentry);
if (IS_ERR(dentry))
@@ -196,7 +220,7 @@ 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;
@@ -232,6 +256,9 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
struct dentry *dentry;
__be32 err;
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
+ if (err)
+ return err;
err = nfsd_lookup_dentry(rqstp, fhp, name, len, &exp, &dentry);
if (err)
return err;
@@ -251,44 +278,30 @@ out:
return err;
}
-
/*
- * Set various file attributes.
- * N.B. After this call fhp needs an fh_put
+ * Commit metadata changes to stable storage.
*/
-__be32
-nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
- int check_guard, time_t guardtime)
+static int
+commit_metadata(struct svc_fh *fhp)
{
- struct dentry *dentry;
- struct inode *inode;
- int accmode = MAY_SATTR;
- int ftype = 0;
- int imode;
- __be32 err;
- int host_err;
- int size_change = 0;
-
- if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
- accmode |= MAY_WRITE|MAY_OWNER_OVERRIDE;
- if (iap->ia_valid & ATTR_SIZE)
- ftype = S_IFREG;
-
- /* Get inode */
- err = fh_verify(rqstp, fhp, ftype, accmode);
- if (err)
- goto out;
-
- dentry = fhp->fh_dentry;
- inode = dentry->d_inode;
+ struct inode *inode = fhp->fh_dentry->d_inode;
+ const struct export_operations *export_ops = inode->i_sb->s_export_op;
- /* Ignore any mode updates on symlinks */
- if (S_ISLNK(inode->i_mode))
- iap->ia_valid &= ~ATTR_MODE;
+ if (!EX_ISSYNC(fhp->fh_export))
+ return 0;
- if (!iap->ia_valid)
- goto out;
+ if (export_ops->commit_metadata)
+ return export_ops->commit_metadata(inode);
+ return sync_inode_metadata(inode, 1);
+}
+/*
+ * Go over the attributes and take care of the small differences between
+ * NFS semantics and what Linux expects.
+ */
+static void
+nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
+{
/*
* NFSv2 does not differentiate between "set-[ac]time-to-now"
* which only requires access, and "set-[ac]time-to-X" which
@@ -298,8 +311,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
* convert to "set to now" instead of "set to explicit time"
*
* We only call inode_change_ok as the last test as technically
- * it is not an interface that we should be using. It is only
- * valid if the filesystem does not define it's own i_op->setattr.
+ * it is not an interface that we should be using.
*/
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define MAX_TOUCH_TIME_ERROR (30*60)
@@ -325,235 +337,194 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
iap->ia_valid &= ~BOTH_TIME_SET;
}
}
-
- /*
- * The size case is special.
- * It changes the file as well as the attributes.
- */
- if (iap->ia_valid & ATTR_SIZE) {
- if (iap->ia_size < inode->i_size) {
- err = nfsd_permission(rqstp, fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE);
- if (err)
- goto out;
- }
-
- /*
- * 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);
- if (host_err == -EWOULDBLOCK)
- host_err = -ETIMEDOUT;
- if (host_err) /* ENOMEM or EWOULDBLOCK */
- goto out_nfserr;
-
- host_err = get_write_access(inode);
- if (host_err)
- goto out_nfserr;
-
- size_change = 1;
- host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
- if (host_err) {
- put_write_access(inode);
- goto out_nfserr;
- }
- DQUOT_INIT(inode);
- }
- imode = inode->i_mode;
+ /* sanitize the mode change */
if (iap->ia_valid & ATTR_MODE) {
iap->ia_mode &= S_IALLUGO;
- imode = iap->ia_mode |= (imode & ~S_IALLUGO);
- /* if changing uid/gid revoke setuid/setgid in mode */
- if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) {
- iap->ia_valid |= ATTR_KILL_PRIV;
+ iap->ia_mode |= (inode->i_mode & ~S_IALLUGO);
+ }
+
+ /* Revoke setuid/setgid on chown */
+ if (!S_ISDIR(inode->i_mode) &&
+ ((iap->ia_valid & ATTR_UID) || (iap->ia_valid & ATTR_GID))) {
+ iap->ia_valid |= ATTR_KILL_PRIV;
+ if (iap->ia_valid & ATTR_MODE) {
+ /* we're setting mode too, just clear the s*id bits */
iap->ia_mode &= ~S_ISUID;
+ if (iap->ia_mode & S_IXGRP)
+ iap->ia_mode &= ~S_ISGID;
+ } else {
+ /* set ATTR_KILL_* bits and let VFS handle it */
+ iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID);
}
- if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)
- iap->ia_mode &= ~S_ISGID;
- } else {
- /*
- * Revoke setuid/setgid bit on chown/chgrp
- */
- if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid)
- iap->ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV;
- if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)
- iap->ia_valid |= ATTR_KILL_SGID;
}
+}
- /* Change the attributes. */
+static __be32
+nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct iattr *iap)
+{
+ struct inode *inode = fhp->fh_dentry->d_inode;
+ int host_err;
- iap->ia_valid |= ATTR_CTIME;
+ if (iap->ia_size < inode->i_size) {
+ __be32 err;
- err = nfserr_notsync;
- if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
- fh_lock(fhp);
- host_err = notify_change(dentry, iap);
- err = nfserrno(host_err);
- fh_unlock(fhp);
+ err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
+ NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE);
+ if (err)
+ return err;
}
- if (size_change)
- put_write_access(inode);
- if (!err)
- if (EX_ISSYNC(fhp->fh_export))
- write_inode_now(inode, 1);
-out:
- return err;
-out_nfserr:
- err = nfserrno(host_err);
- goto out;
+ host_err = get_write_access(inode);
+ if (host_err)
+ goto out_nfserrno;
+
+ host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
+ if (host_err)
+ goto out_put_write_access;
+ return 0;
+
+out_put_write_access:
+ put_write_access(inode);
+out_nfserrno:
+ return nfserrno(host_err);
}
-#if defined(CONFIG_NFSD_V2_ACL) || \
- defined(CONFIG_NFSD_V3_ACL) || \
- defined(CONFIG_NFSD_V4)
-static ssize_t nfsd_getxattr(struct dentry *dentry, char *key, void **buf)
+/*
+ * Set various file attributes. After this call fhp needs an fh_put.
+ */
+__be32
+nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
+ int check_guard, time_t guardtime)
{
- ssize_t buflen;
+ struct dentry *dentry;
+ struct inode *inode;
+ int accmode = NFSD_MAY_SATTR;
+ umode_t ftype = 0;
+ __be32 err;
+ int host_err;
+ bool get_write_count;
+ int size_change = 0;
- buflen = vfs_getxattr(dentry, key, NULL, 0);
- if (buflen <= 0)
- return buflen;
+ if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
+ accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
+ if (iap->ia_valid & ATTR_SIZE)
+ ftype = S_IFREG;
- *buf = kmalloc(buflen, GFP_KERNEL);
- if (!*buf)
- return -ENOMEM;
+ /* Callers that do fh_verify should do the fh_want_write: */
+ get_write_count = !fhp->fh_dentry;
- return vfs_getxattr(dentry, key, *buf, buflen);
-}
-#endif
-
-#if defined(CONFIG_NFSD_V4)
-static int
-set_nfsv4_acl_one(struct dentry *dentry, struct posix_acl *pacl, char *key)
-{
- int len;
- size_t buflen;
- char *buf = NULL;
- int error = 0;
-
- buflen = posix_acl_xattr_size(pacl->a_count);
- buf = kmalloc(buflen, GFP_KERNEL);
- error = -ENOMEM;
- if (buf == NULL)
+ /* Get inode */
+ err = fh_verify(rqstp, fhp, ftype, accmode);
+ if (err)
goto out;
+ if (get_write_count) {
+ host_err = fh_want_write(fhp);
+ if (host_err)
+ return nfserrno(host_err);
+ }
- len = posix_acl_to_xattr(pacl, buf, buflen);
- if (len < 0) {
- error = len;
+ dentry = fhp->fh_dentry;
+ inode = dentry->d_inode;
+
+ /* Ignore any mode updates on symlinks */
+ if (S_ISLNK(inode->i_mode))
+ iap->ia_valid &= ~ATTR_MODE;
+
+ if (!iap->ia_valid)
goto out;
+
+ nfsd_sanitize_attrs(inode, iap);
+
+ /*
+ * The size case is special, it changes the file in addition to the
+ * attributes.
+ */
+ if (iap->ia_valid & ATTR_SIZE) {
+ err = nfsd_get_write_access(rqstp, fhp, iap);
+ if (err)
+ goto out;
+ size_change = 1;
+ }
+
+ iap->ia_valid |= ATTR_CTIME;
+
+ if (check_guard && guardtime != inode->i_ctime.tv_sec) {
+ err = nfserr_notsync;
+ goto out_put_write_access;
}
- error = vfs_setxattr(dentry, key, buf, len, 0);
+ fh_lock(fhp);
+ host_err = notify_change(dentry, iap, NULL);
+ fh_unlock(fhp);
+ err = nfserrno(host_err);
+
+out_put_write_access:
+ if (size_change)
+ put_write_access(inode);
+ if (!err)
+ commit_metadata(fhp);
out:
- kfree(buf);
- return error;
+ return err;
}
-__be32
-nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
- struct nfs4_acl *acl)
+#if defined(CONFIG_NFSD_V4)
+/*
+ * NFS junction information is stored in an extended attribute.
+ */
+#define NFSD_JUNCTION_XATTR_NAME XATTR_TRUSTED_PREFIX "junction.nfs"
+
+/**
+ * nfsd4_is_junction - Test if an object could be an NFS junction
+ *
+ * @dentry: object to test
+ *
+ * Returns 1 if "dentry" appears to contain NFS junction information.
+ * Otherwise 0 is returned.
+ */
+int nfsd4_is_junction(struct dentry *dentry)
+{
+ struct inode *inode = dentry->d_inode;
+
+ if (inode == NULL)
+ return 0;
+ if (inode->i_mode & S_IXUGO)
+ return 0;
+ if (!(inode->i_mode & S_ISVTX))
+ return 0;
+ if (vfs_getxattr(dentry, NFSD_JUNCTION_XATTR_NAME, NULL, 0) <= 0)
+ return 0;
+ return 1;
+}
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct xdr_netobj *label)
{
__be32 error;
int host_error;
struct dentry *dentry;
- struct inode *inode;
- struct posix_acl *pacl = NULL, *dpacl = NULL;
- unsigned int flags = 0;
- /* Get inode */
- error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, MAY_SATTR);
+ error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, NFSD_MAY_SATTR);
if (error)
return error;
dentry = fhp->fh_dentry;
- inode = dentry->d_inode;
- if (S_ISDIR(inode->i_mode))
- flags = NFS4_ACL_DIR;
- host_error = nfs4_acl_nfsv4_to_posix(acl, &pacl, &dpacl, flags);
- if (host_error == -EINVAL) {
- return nfserr_attrnotsupp;
- } else if (host_error < 0)
- goto out_nfserr;
-
- host_error = set_nfsv4_acl_one(dentry, pacl, POSIX_ACL_XATTR_ACCESS);
- if (host_error < 0)
- goto out_release;
-
- if (S_ISDIR(inode->i_mode))
- host_error = set_nfsv4_acl_one(dentry, dpacl, POSIX_ACL_XATTR_DEFAULT);
-
-out_release:
- posix_acl_release(pacl);
- posix_acl_release(dpacl);
-out_nfserr:
- if (host_error == -EOPNOTSUPP)
- return nfserr_attrnotsupp;
- else
- return nfserrno(host_error);
-}
-
-static struct posix_acl *
-_get_posix_acl(struct dentry *dentry, char *key)
-{
- void *buf = NULL;
- struct posix_acl *pacl = NULL;
- int buflen;
-
- buflen = nfsd_getxattr(dentry, key, &buf);
- if (!buflen)
- buflen = -ENODATA;
- if (buflen <= 0)
- return ERR_PTR(buflen);
-
- pacl = posix_acl_from_xattr(buf, buflen);
- kfree(buf);
- return pacl;
+ mutex_lock(&dentry->d_inode->i_mutex);
+ host_error = security_inode_setsecctx(dentry, label->data, label->len);
+ mutex_unlock(&dentry->d_inode->i_mutex);
+ return nfserrno(host_error);
}
-
-int
-nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_acl **acl)
+#else
+__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct xdr_netobj *label)
{
- struct inode *inode = dentry->d_inode;
- int error = 0;
- struct posix_acl *pacl = NULL, *dpacl = NULL;
- unsigned int flags = 0;
-
- pacl = _get_posix_acl(dentry, POSIX_ACL_XATTR_ACCESS);
- if (IS_ERR(pacl) && PTR_ERR(pacl) == -ENODATA)
- pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
- if (IS_ERR(pacl)) {
- error = PTR_ERR(pacl);
- pacl = NULL;
- goto out;
- }
-
- if (S_ISDIR(inode->i_mode)) {
- dpacl = _get_posix_acl(dentry, POSIX_ACL_XATTR_DEFAULT);
- if (IS_ERR(dpacl) && PTR_ERR(dpacl) == -ENODATA)
- dpacl = NULL;
- else if (IS_ERR(dpacl)) {
- error = PTR_ERR(dpacl);
- dpacl = NULL;
- goto out;
- }
- flags = NFS4_ACL_DIR;
- }
-
- *acl = nfs4_acl_posix_to_nfsv4(pacl, dpacl, flags);
- if (IS_ERR(*acl)) {
- error = PTR_ERR(*acl);
- *acl = NULL;
- }
- out:
- posix_acl_release(pacl);
- posix_acl_release(dpacl);
- return error;
+ return nfserr_notsupp;
}
+#endif
-#endif /* defined(CONFIG_NFS_V4) */
+#endif /* defined(CONFIG_NFSD_V4) */
#ifdef CONFIG_NFSD_V3
/*
@@ -564,20 +535,20 @@ struct accessmap {
int how;
};
static struct accessmap nfs3_regaccess[] = {
- { NFS3_ACCESS_READ, MAY_READ },
- { NFS3_ACCESS_EXECUTE, MAY_EXEC },
- { NFS3_ACCESS_MODIFY, MAY_WRITE|MAY_TRUNC },
- { NFS3_ACCESS_EXTEND, MAY_WRITE },
+ { NFS3_ACCESS_READ, NFSD_MAY_READ },
+ { NFS3_ACCESS_EXECUTE, NFSD_MAY_EXEC },
+ { NFS3_ACCESS_MODIFY, NFSD_MAY_WRITE|NFSD_MAY_TRUNC },
+ { NFS3_ACCESS_EXTEND, NFSD_MAY_WRITE },
{ 0, 0 }
};
static struct accessmap nfs3_diraccess[] = {
- { NFS3_ACCESS_READ, MAY_READ },
- { NFS3_ACCESS_LOOKUP, MAY_EXEC },
- { NFS3_ACCESS_MODIFY, MAY_EXEC|MAY_WRITE|MAY_TRUNC },
- { NFS3_ACCESS_EXTEND, MAY_EXEC|MAY_WRITE },
- { NFS3_ACCESS_DELETE, MAY_REMOVE },
+ { NFS3_ACCESS_READ, NFSD_MAY_READ },
+ { NFS3_ACCESS_LOOKUP, NFSD_MAY_EXEC },
+ { NFS3_ACCESS_MODIFY, NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC},
+ { NFS3_ACCESS_EXTEND, NFSD_MAY_EXEC|NFSD_MAY_WRITE },
+ { NFS3_ACCESS_DELETE, NFSD_MAY_REMOVE },
{ 0, 0 }
};
@@ -590,10 +561,10 @@ static struct accessmap nfs3_anyaccess[] = {
* mainly at mode bits, and we make sure to ignore read-only
* filesystem checks
*/
- { NFS3_ACCESS_READ, MAY_READ },
- { NFS3_ACCESS_EXECUTE, MAY_EXEC },
- { NFS3_ACCESS_MODIFY, MAY_WRITE|MAY_LOCAL_ACCESS },
- { NFS3_ACCESS_EXTEND, MAY_WRITE|MAY_LOCAL_ACCESS },
+ { NFS3_ACCESS_READ, NFSD_MAY_READ },
+ { NFS3_ACCESS_EXECUTE, NFSD_MAY_EXEC },
+ { NFS3_ACCESS_MODIFY, NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS },
+ { NFS3_ACCESS_EXTEND, NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS },
{ 0, 0 }
};
@@ -607,7 +578,7 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor
u32 query, result = 0, sresult = 0;
__be32 error;
- error = fh_verify(rqstp, fhp, 0, MAY_NOP);
+ error = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP);
if (error)
goto out;
@@ -657,40 +628,60 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor
}
#endif /* CONFIG_NFSD_V3 */
+static int nfsd_open_break_lease(struct inode *inode, int access)
+{
+ unsigned int mode;
+ if (access & NFSD_MAY_NOT_BREAK_LEASE)
+ return 0;
+ mode = (access & NFSD_MAY_WRITE) ? O_WRONLY : O_RDONLY;
+ return break_lease(inode, mode | O_NONBLOCK);
+}
/*
* Open an existing file or directory.
- * The access argument indicates the type of open (read/write/lock)
+ * The may_flags argument indicates the type of open (read/write/lock)
+ * and additional flags.
* N.B. After this call fhp needs an fh_put
*/
__be32
-nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
- int access, struct file **filp)
+nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
+ int may_flags, struct file **filp)
{
- struct dentry *dentry;
+ struct path path;
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",
* and (hopefully) checked permission - so allow OWNER_OVERRIDE
* in case a chmod has now revoked permission.
+ *
+ * Arguably we should also allow the owner override for
+ * directories, but we never have and it doesn't seem to have
+ * caused anyone a problem. If we were to change this, note
+ * also that our filldir callbacks would need a variant of
+ * lookup_one_len that doesn't check permissions.
*/
- err = fh_verify(rqstp, fhp, type, access | MAY_OWNER_OVERRIDE);
+ if (type == S_IFREG)
+ may_flags |= NFSD_MAY_OWNER_OVERRIDE;
+ err = fh_verify(rqstp, fhp, type, may_flags);
if (err)
goto out;
- dentry = fhp->fh_dentry;
- inode = dentry->d_inode;
+ path.mnt = fhp->fh_export->ex_path.mnt;
+ path.dentry = fhp->fh_dentry;
+ inode = path.dentry->d_inode;
/* Disallow write access to files with the append-only bit set
* or any access when mandatory locking enabled
*/
err = nfserr_perm;
- if (IS_APPEND(inode) && (access & MAY_WRITE))
+ if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE))
goto out;
/*
* We must ignore files (but only files) which might have mandatory
@@ -703,31 +694,33 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
if (!inode->i_fop)
goto out;
- /*
- * 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 & MAY_WRITE) ? FMODE_WRITE : 0));
- if (host_err == -EWOULDBLOCK)
- host_err = -ETIMEDOUT;
+ host_err = nfsd_open_break_lease(inode, may_flags);
if (host_err) /* NOMEM or WOULDBLOCK */
goto out_nfserr;
- if (access & MAY_WRITE) {
- if (access & MAY_READ)
+ if (may_flags & NFSD_MAY_WRITE) {
+ if (may_flags & NFSD_MAY_READ)
flags = O_RDWR|O_LARGEFILE;
else
flags = O_WRONLY|O_LARGEFILE;
-
- DQUOT_INIT(inode);
}
- *filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_path.mnt),
- flags);
- if (IS_ERR(*filp))
+ *filp = dentry_open(&path, flags, current_cred());
+ if (IS_ERR(*filp)) {
host_err = PTR_ERR(*filp);
+ *filp = NULL;
+ } else {
+ host_err = ima_file_check(*filp, may_flags);
+
+ if (may_flags & NFSD_MAY_64BIT_COOKIE)
+ (*filp)->f_mode |= FMODE_64BITHASH;
+ else
+ (*filp)->f_mode |= FMODE_32BITHASH;
+ }
+
out_nfserr:
err = nfserrno(host_err);
out:
+ validate_process_creds();
return err;
}
@@ -741,47 +734,6 @@ nfsd_close(struct file *filp)
}
/*
- * 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).
*/
@@ -805,7 +757,7 @@ nfsd_get_raparms(dev_t dev, ino_t ino)
if (ra->p_count == 0)
frap = rap;
}
- depth = nfsdstats.ra_size*11/10;
+ depth = nfsdstats.ra_size;
if (!frap) {
spin_unlock(&rab->pb_lock);
return NULL;
@@ -838,30 +790,23 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
struct splice_desc *sd)
{
struct svc_rqst *rqstp = sd->u.data;
- struct page **pp = rqstp->rq_respages + rqstp->rq_resused;
+ struct page **pp = rqstp->rq_next_page;
struct page *page = buf->page;
size_t size;
- int ret;
-
- ret = buf->ops->confirm(pipe, buf);
- if (unlikely(ret))
- return ret;
size = sd->len;
if (rqstp->rq_res.page_len == 0) {
get_page(page);
- put_page(*pp);
- *pp = page;
- rqstp->rq_resused++;
+ put_page(*rqstp->rq_next_page);
+ *(rqstp->rq_next_page++) = page;
rqstp->rq_res.page_base = buf->offset;
rqstp->rq_res.page_len = size;
} else if (page != pp[-1]) {
get_page(page);
- if (*pp)
- put_page(*pp);
- *pp = page;
- rqstp->rq_resused++;
+ if (*rqstp->rq_next_page)
+ put_page(*rqstp->rq_next_page);
+ *(rqstp->rq_next_page++) = page;
rqstp->rq_res.page_len += size;
} else
rqstp->rq_res.page_len += size;
@@ -875,89 +820,97 @@ static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe,
return __splice_from_pipe(pipe, sd, nfsd_splice_actor);
}
-static inline int svc_msnfs(struct svc_fh *ffhp)
+__be32 nfsd_finish_read(struct file *file, unsigned long *count, int host_err)
{
-#ifdef MSNFS
- return (ffhp->fh_export->ex_flags & NFSEXP_MSNFS);
-#else
- return 0;
-#endif
+ if (host_err >= 0) {
+ nfsdstats.io_read += host_err;
+ *count = host_err;
+ fsnotify_access(file);
+ return 0;
+ } else
+ return nfserrno(host_err);
}
-static __be32
-nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
- loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
+int nfsd_splice_read(struct svc_rqst *rqstp,
+ struct file *file, loff_t offset, unsigned long *count)
{
- struct inode *inode;
- struct raparms *ra;
- mm_segment_t oldfs;
- __be32 err;
- int host_err;
-
- err = nfserr_perm;
- inode = file->f_path.dentry->d_inode;
+ struct splice_desc sd = {
+ .len = 0,
+ .total_len = *count,
+ .pos = offset,
+ .u.data = rqstp,
+ };
+ int host_err;
+
+ rqstp->rq_next_page = rqstp->rq_respages + 1;
+ host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
+ return nfsd_finish_read(file, count, host_err);
+}
- if (svc_msnfs(fhp) && !lock_may_read(inode, offset, *count))
- goto out;
+int nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen,
+ unsigned long *count)
+{
+ mm_segment_t oldfs;
+ int host_err;
- /* Get readahead parameters */
- ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
+ oldfs = get_fs();
+ set_fs(KERNEL_DS);
+ host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
+ set_fs(oldfs);
+ return nfsd_finish_read(file, count, host_err);
+}
- if (ra && ra->p_set)
- file->f_ra = ra->p_ra;
+static __be32
+nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file,
+ loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
+{
+ if (file->f_op->splice_read && rqstp->rq_splice_ok)
+ return nfsd_splice_read(rqstp, file, offset, count);
+ else
+ return nfsd_readv(file, offset, vec, vlen, count);
+}
- if (file->f_op->splice_read && rqstp->rq_splice_ok) {
- struct splice_desc sd = {
- .len = 0,
- .total_len = *count,
- .pos = offset,
- .u.data = rqstp,
- };
+/*
+ * 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_inode(file);
+ static ino_t last_ino;
+ static dev_t last_dev;
+ int err = 0;
- rqstp->rq_resused = 1;
- host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
- } else {
- oldfs = get_fs();
- set_fs(KERNEL_DS);
- host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
- set_fs(oldfs);
+ 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));
}
- /* Write back readahead params */
- if (ra) {
- struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex];
- spin_lock(&rab->pb_lock);
- ra->p_ra = file->f_ra;
- ra->p_set = 1;
- ra->p_count--;
- spin_unlock(&rab->pb_lock);
+ if (inode->i_state & I_DIRTY) {
+ dprintk("nfsd: write sync %d\n", task_pid_nr(current));
+ err = vfs_fsync(file, 0);
}
-
- if (host_err >= 0) {
- nfsdstats.io_read += host_err;
- *count = host_err;
- err = 0;
- fsnotify_access(file->f_path.dentry);
- } else
- err = nfserrno(host_err);
-out:
+ last_ino = inode->i_ino;
+ last_dev = inode->i_sb->s_dev;
return err;
}
-static void kill_suid(struct dentry *dentry)
-{
- struct iattr ia;
- ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
-
- mutex_lock(&dentry->d_inode->i_mutex);
- notify_change(dentry, &ia);
- mutex_unlock(&dentry->d_inode->i_mutex);
-}
-
static __be32
nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
loff_t offset, struct kvec *vec, int vlen,
- unsigned long cnt, int *stablep)
+ unsigned long *cnt, int *stablep)
{
struct svc_export *exp;
struct dentry *dentry;
@@ -966,122 +919,110 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
__be32 err = 0;
int host_err;
int stable = *stablep;
+ int use_wgather;
+ loff_t pos = offset;
+ unsigned int pflags = current->flags;
-#ifdef MSNFS
- err = nfserr_perm;
-
- if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
- (!lock_may_write(file->f_path.dentry->d_inode, offset, cnt)))
- goto out;
-#endif
+ if (rqstp->rq_local)
+ /*
+ * We want less throttling in balance_dirty_pages()
+ * and shrink_inactive_list() so that nfs to
+ * localhost doesn't cause nfsd to lock up due to all
+ * the client's dirty pages or its congested queue.
+ */
+ current->flags |= PF_LESS_THROTTLE;
dentry = file->f_path.dentry;
inode = dentry->d_inode;
exp = fhp->fh_export;
- /*
- * Request sync writes if
- * - 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,
- * flushing the data to disk is handled separately below.
- */
-
- if (file->f_op->fsync == 0) {/* COMMIT3 cannot work */
- stable = 2;
- *stablep = 2; /* FILE_SYNC */
- }
+ use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
if (!EX_ISSYNC(exp))
stable = 0;
- if (stable && !EX_WGATHER(exp))
- file->f_flags |= O_SYNC;
/* Write the data. */
oldfs = get_fs(); set_fs(KERNEL_DS);
- host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset);
+ host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos);
set_fs(oldfs);
- if (host_err >= 0) {
- nfsdstats.io_write += cnt;
- fsnotify_modify(file->f_path.dentry);
- }
-
- /* clear setuid/setgid flag after write */
- if (host_err >= 0 && (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 (host_err < 0)
+ goto out_nfserr;
+ *cnt = host_err;
+ nfsdstats.io_write += host_err;
+ fsnotify_modify(file);
- 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) {
+ if (use_wgather)
+ host_err = wait_for_concurrent_writes(file);
+ else
+ host_err = vfs_fsync_range(file, offset, offset+*cnt, 0);
}
+out_nfserr:
dprintk("nfsd: write complete host_err=%d\n", host_err);
if (host_err >= 0)
err = 0;
- else
+ else
err = nfserrno(host_err);
-out:
+ if (rqstp->rq_local)
+ tsk_restore_flags(current, pflags, PF_LESS_THROTTLE);
return err;
}
+__be32 nfsd_get_tmp_read_open(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct file **file, struct raparms **ra)
+{
+ struct inode *inode;
+ __be32 err;
+
+ err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, file);
+ if (err)
+ return err;
+
+ inode = file_inode(*file);
+
+ /* Get readahead parameters */
+ *ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
+
+ if (*ra && (*ra)->p_set)
+ (*file)->f_ra = (*ra)->p_ra;
+ return nfs_ok;
+}
+
+void nfsd_put_tmp_read_open(struct file *file, struct raparms *ra)
+{
+ /* Write back readahead params */
+ if (ra) {
+ struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex];
+ spin_lock(&rab->pb_lock);
+ ra->p_ra = file->f_ra;
+ ra->p_set = 1;
+ ra->p_count--;
+ spin_unlock(&rab->pb_lock);
+ }
+ nfsd_close(file);
+}
+
/*
* Read data from a file. count must contain the requested read count
* on entry. On return, *count contains the number of bytes actually read.
* N.B. After this call fhp needs an fh_put
*/
-__be32
-nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
- loff_t offset, struct kvec *vec, int vlen,
- unsigned long *count)
+__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
{
- __be32 err;
+ struct file *file;
+ struct raparms *ra;
+ __be32 err;
+
+ err = nfsd_get_tmp_read_open(rqstp, fhp, &file, &ra);
+ if (err)
+ return err;
+
+ err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count);
+
+ nfsd_put_tmp_read_open(file, ra);
- if (file) {
- err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
- MAY_READ|MAY_OWNER_OVERRIDE);
- if (err)
- goto out;
- err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
- } else {
- err = nfsd_open(rqstp, fhp, S_IFREG, MAY_READ, &file);
- if (err)
- goto out;
- err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
- nfsd_close(file);
- }
-out:
return err;
}
@@ -1092,20 +1033,20 @@ out:
*/
__be32
nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
- loff_t offset, struct kvec *vec, int vlen, unsigned long cnt,
+ loff_t offset, struct kvec *vec, int vlen, unsigned long *cnt,
int *stablep)
{
__be32 err = 0;
if (file) {
err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
- MAY_WRITE|MAY_OWNER_OVERRIDE);
+ NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE);
if (err)
goto out;
err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt,
stablep);
} else {
- err = nfsd_open(rqstp, fhp, S_IFREG, MAY_WRITE, &file);
+ err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
if (err)
goto out;
@@ -1121,8 +1062,9 @@ out:
#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.
@@ -1132,27 +1074,37 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
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;
+ }
- if ((err = nfsd_open(rqstp, fhp, S_IFREG, MAY_WRITE, &file)) != 0)
- return err;
+ err = nfsd_open(rqstp, fhp, S_IFREG,
+ NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &file);
+ if (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 */
-__be32
+static __be32
nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp,
struct iattr *iap)
{
@@ -1165,13 +1117,28 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp,
* send along the gid on create when it tries to implement
* setgid directories via NFS:
*/
- if (current->fsuid != 0)
+ if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID))
iap->ia_valid &= ~(ATTR_UID|ATTR_GID);
if (iap->ia_valid)
return nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
return 0;
}
+/* HPUX client sometimes creates a file in mode 000, and sets size to 0.
+ * setting size to 0 may fail for some specific file systems by the permission
+ * checking which requires WRITE permission but the mode is 000.
+ * we ignore the resizing(to 0) on the just new created file, since the size is
+ * 0 after file created.
+ *
+ * call this only after vfs_create() is called.
+ * */
+static void
+nfsd_check_ignore_resizing(struct iattr *iap)
+{
+ if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0))
+ iap->ia_valid &= ~ATTR_SIZE;
+}
+
/*
* Create a file (regular, directory, device, fifo); UNIX sockets
* not yet implemented.
@@ -1198,7 +1165,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (isdotent(fname, flen))
goto out;
- err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
if (err)
goto out;
@@ -1206,13 +1173,17 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
dirp = dentry->d_inode;
err = nfserr_notdir;
- if(!dirp->i_op || !dirp->i_op->lookup)
+ if (!dirp->i_op->lookup)
goto out;
/*
* Check whether the response file handle has been verified yet.
* If it has, the parent directory should already be locked.
*/
if (!resfhp->fh_dentry) {
+ host_err = fh_want_write(fhp);
+ if (host_err)
+ goto out_nfserr;
+
/* called from nfsd_proc_mkdir, or possibly nfsd3_proc_create */
fh_lock_nested(fhp, I_MUTEX_PARENT);
dchild = lookup_one_len(fname, dentry, flen);
@@ -1228,9 +1199,8 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (!fhp->fh_locked) {
/* not actually possible */
printk(KERN_ERR
- "nfsd_create: parent %s/%s not locked!\n",
- dentry->d_parent->d_name.name,
- dentry->d_name.name);
+ "nfsd_create: parent %pd2 not locked!\n",
+ dentry);
err = nfserr_io;
goto out;
}
@@ -1240,8 +1210,8 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
*/
err = nfserr_exist;
if (dchild->d_inode) {
- dprintk("nfsd_create: dentry %s/%s not negative!\n",
- dentry->d_name.name, dchild->d_name.name);
+ dprintk("nfsd_create: dentry %pd/%pd not negative!\n",
+ dentry, dchild);
goto out;
}
@@ -1249,13 +1219,23 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
iap->ia_mode = 0;
iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type;
+ err = nfserr_inval;
+ if (!S_ISREG(type) && !S_ISDIR(type) && !special_file(type)) {
+ printk(KERN_WARNING "nfsd: bad file type %o in nfsd_create\n",
+ type);
+ goto out;
+ }
+
/*
* Get the dir op function pointer.
*/
err = 0;
+ host_err = 0;
switch (type) {
case S_IFREG:
- host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
+ host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
+ if (!host_err)
+ nfsd_check_ignore_resizing(iap);
break;
case S_IFDIR:
host_err = vfs_mkdir(dirp, dchild, iap->ia_mode);
@@ -1266,20 +1246,18 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
case S_IFSOCK:
host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev);
break;
- default:
- printk("nfsd: bad file type %o in nfsd_create\n", type);
- host_err = -EINVAL;
}
if (host_err < 0)
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;
/*
@@ -1298,19 +1276,25 @@ out_nfserr:
}
#ifdef CONFIG_NFSD_V3
+
+static inline int nfsd_create_is_exclusive(int createmode)
+{
+ return createmode == NFS3_CREATE_EXCLUSIVE
+ || createmode == NFS4_CREATE_EXCLUSIVE4_1;
+}
+
/*
- * NFSv3 version of nfsd_create
+ * NFSv3 and NFSv4 version of nfsd_create
*/
__be32
-nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
+do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
char *fname, int flen, struct iattr *iap,
struct svc_fh *resfhp, int createmode, u32 *verifier,
- int *truncp, int *created)
+ bool *truncp, bool *created)
{
struct dentry *dentry, *dchild = NULL;
struct inode *dirp;
__be32 err;
- __be32 err2;
int host_err;
__u32 v_mtime=0, v_atime=0;
@@ -1322,7 +1306,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
goto out;
if (!(iap->ia_valid & ATTR_MODE))
iap->ia_mode = 0;
- err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
if (err)
goto out;
@@ -1332,8 +1316,13 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
/* Get all the sanity checks out of the way before
* we lock the parent. */
err = nfserr_notdir;
- if(!dirp->i_op || !dirp->i_op->lookup)
+ if (!dirp->i_op->lookup)
goto out;
+
+ host_err = fh_want_write(fhp);
+ if (host_err)
+ goto out_nfserr;
+
fh_lock_nested(fhp, I_MUTEX_PARENT);
/*
@@ -1344,11 +1333,18 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (IS_ERR(dchild))
goto out_nfserr;
+ /* If file doesn't exist, check for permissions to create one */
+ if (!dchild->d_inode) {
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
+ if (err)
+ goto out;
+ }
+
err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
if (err)
goto out;
- if (createmode == NFS3_CREATE_EXCLUSIVE) {
+ if (nfsd_create_is_exclusive(createmode)) {
/* solaris7 gets confused (bugid 4218508) if these have
* the high bit set, so just clear the high bits. If this is
* ever changed to use different attrs for storing the
@@ -1365,7 +1361,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
switch (createmode) {
case NFS3_CREATE_UNCHECKED:
if (! S_ISREG(dchild->d_inode->i_mode))
- err = nfserr_exist;
+ goto out;
else if (truncp) {
/* in nfsv4, we need to treat this case a little
* differently. we don't want to truncate the
@@ -1384,27 +1380,38 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
case NFS3_CREATE_EXCLUSIVE:
if ( dchild->d_inode->i_mtime.tv_sec == v_mtime
&& dchild->d_inode->i_atime.tv_sec == v_atime
- && dchild->d_inode->i_size == 0 )
+ && dchild->d_inode->i_size == 0 ) {
+ if (created)
+ *created = 1;
break;
+ }
+ case NFS4_CREATE_EXCLUSIVE4_1:
+ if ( dchild->d_inode->i_mtime.tv_sec == v_mtime
+ && dchild->d_inode->i_atime.tv_sec == v_atime
+ && dchild->d_inode->i_size == 0 ) {
+ if (created)
+ *created = 1;
+ goto set_attr;
+ }
/* fallthru */
case NFS3_CREATE_GUARDED:
err = nfserr_exist;
}
+ fh_drop_write(fhp);
goto out;
}
- host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
- if (host_err < 0)
+ host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
+ if (host_err < 0) {
+ fh_drop_write(fhp);
goto out_nfserr;
+ }
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) {
+ if (nfsd_create_is_exclusive(createmode)) {
/* Cram the verifier into atime/mtime */
iap->ia_valid = ATTR_MTIME|ATTR_ATIME
| ATTR_MTIME_SET|ATTR_ATIME_SET;
@@ -1416,9 +1423,13 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
}
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));
/*
* Update the filehandle to get the new inode info.
@@ -1430,6 +1441,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
fh_unlock(fhp);
if (dchild && !IS_ERR(dchild))
dput(dchild);
+ fh_drop_write(fhp);
return err;
out_nfserr:
@@ -1446,30 +1458,31 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
__be32
nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp)
{
- struct dentry *dentry;
struct inode *inode;
mm_segment_t oldfs;
__be32 err;
int host_err;
+ struct path path;
- err = fh_verify(rqstp, fhp, S_IFLNK, MAY_NOP);
+ err = fh_verify(rqstp, fhp, S_IFLNK, NFSD_MAY_NOP);
if (err)
goto out;
- dentry = fhp->fh_dentry;
- inode = dentry->d_inode;
+ path.mnt = fhp->fh_export->ex_path.mnt;
+ path.dentry = fhp->fh_dentry;
+ inode = path.dentry->d_inode;
err = nfserr_inval;
- if (!inode->i_op || !inode->i_op->readlink)
+ if (!inode->i_op->readlink)
goto out;
- touch_atime(fhp->fh_export->ex_path.mnt, dentry);
+ touch_atime(&path);
/* N.B. Why does this call need a get_fs()??
* Remove the set_fs and watch the fireworks:-) --okir
*/
oldfs = get_fs(); set_fs(KERNEL_DS);
- host_err = inode->i_op->readlink(dentry, buf, *lenp);
+ host_err = inode->i_op->readlink(path.dentry, (char __user *)buf, *lenp);
set_fs(oldfs);
if (host_err < 0)
@@ -1498,7 +1511,6 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct dentry *dentry, *dnew;
__be32 err, cerr;
int host_err;
- umode_t mode;
err = nfserr_noent;
if (!flen || !plen)
@@ -1507,9 +1519,14 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (isdotent(fname, flen))
goto out;
- err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
if (err)
goto out;
+
+ host_err = fh_want_write(fhp);
+ if (host_err)
+ goto out_nfserr;
+
fh_lock(fhp);
dentry = fhp->fh_dentry;
dnew = lookup_one_len(fname, dentry, flen);
@@ -1517,11 +1534,6 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
if (IS_ERR(dnew))
goto out_nfserr;
- mode = S_IALLUGO;
- /* Only the MODE ATTRibute is even vaguely meaningful */
- if (iap && (iap->ia_valid & ATTR_MODE))
- mode = iap->ia_mode & S_IALLUGO;
-
if (unlikely(path[plen] != 0)) {
char *path_alloced = kmalloc(plen+1, GFP_KERNEL);
if (path_alloced == NULL)
@@ -1529,19 +1541,18 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
else {
strncpy(path_alloced, path, plen);
path_alloced[plen] = 0;
- host_err = vfs_symlink(dentry->d_inode, dnew, path_alloced, mode);
+ host_err = vfs_symlink(dentry->d_inode, dnew, path_alloced);
kfree(path_alloced);
}
} else
- host_err = vfs_symlink(dentry->d_inode, dnew, path, mode);
-
- if (!host_err) {
- if (EX_ISSYNC(fhp->fh_export))
- host_err = nfsd_sync_dir(dentry);
- }
+ host_err = vfs_symlink(dentry->d_inode, dnew, path);
err = nfserrno(host_err);
+ if (!err)
+ err = nfserrno(commit_metadata(fhp));
fh_unlock(fhp);
+ fh_drop_write(fhp);
+
cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp);
dput(dnew);
if (err==0) err = cerr;
@@ -1562,17 +1573,19 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
char *name, int len, struct svc_fh *tfhp)
{
struct dentry *ddir, *dnew, *dold;
- struct inode *dirp, *dest;
+ struct inode *dirp;
__be32 err;
int host_err;
- err = fh_verify(rqstp, ffhp, S_IFDIR, MAY_CREATE);
+ err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_CREATE);
if (err)
goto out;
- err = fh_verify(rqstp, tfhp, -S_IFDIR, MAY_NOP);
+ err = fh_verify(rqstp, tfhp, 0, NFSD_MAY_NOP);
if (err)
goto out;
-
+ err = nfserr_isdir;
+ if (S_ISDIR(tfhp->fh_dentry->d_inode->i_mode))
+ goto out;
err = nfserr_perm;
if (!len)
goto out;
@@ -1580,6 +1593,12 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
if (isdotent(name, len))
goto out;
+ host_err = fh_want_write(tfhp);
+ if (host_err) {
+ err = nfserrno(host_err);
+ goto out;
+ }
+
fh_lock_nested(ffhp, I_MUTEX_PARENT);
ddir = ffhp->fh_dentry;
dirp = ddir->d_inode;
@@ -1590,25 +1609,26 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
goto out_nfserr;
dold = tfhp->fh_dentry;
- dest = dold->d_inode;
- host_err = vfs_link(dold, dirp, dnew);
+ err = nfserr_noent;
+ if (!dold->d_inode)
+ goto out_dput;
+ host_err = vfs_link(dold, dirp, dnew, NULL);
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;
else
err = nfserrno(host_err);
}
-
+out_dput:
dput(dnew);
out_unlock:
fh_unlock(ffhp);
+ fh_drop_write(tfhp);
out:
return err;
@@ -1630,10 +1650,10 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
__be32 err;
int host_err;
- err = fh_verify(rqstp, ffhp, S_IFDIR, MAY_REMOVE);
+ err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_REMOVE);
if (err)
goto out;
- err = fh_verify(rqstp, tfhp, S_IFDIR, MAY_CREATE);
+ err = fh_verify(rqstp, tfhp, S_IFDIR, NFSD_MAY_CREATE);
if (err)
goto out;
@@ -1643,14 +1663,16 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
tdentry = tfhp->fh_dentry;
tdir = tdentry->d_inode;
- err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev;
- if (ffhp->fh_export != tfhp->fh_export)
- goto out;
-
err = nfserr_perm;
if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen))
goto out;
+ host_err = fh_want_write(ffhp);
+ if (host_err) {
+ err = nfserrno(host_err);
+ goto out;
+ }
+
/* cannot use fh_lock as we need deadlock protective ordering
* so do it by hand */
trap = lock_rename(tdentry, fdentry);
@@ -1678,35 +1700,34 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
if (ndentry == trap)
goto out_dput_new;
-#ifdef MSNFS
- if ((ffhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
- ((atomic_read(&odentry->d_count) > 1)
- || (atomic_read(&ndentry->d_count) > 1))) {
- host_err = -EPERM;
- } else
-#endif
- host_err = vfs_rename(fdir, odentry, tdir, ndentry);
- if (!host_err && EX_ISSYNC(tfhp->fh_export)) {
- host_err = nfsd_sync_dir(tdentry);
+ host_err = -EXDEV;
+ if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt)
+ goto out_dput_new;
+ if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
+ goto out_dput_new;
+
+ host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0);
+ if (!host_err) {
+ host_err = commit_metadata(tfhp);
if (!host_err)
- host_err = nfsd_sync_dir(fdentry);
+ host_err = commit_metadata(ffhp);
}
-
out_dput_new:
dput(ndentry);
out_dput_old:
dput(odentry);
out_nfserr:
err = nfserrno(host_err);
-
- /* we cannot reply on fh_unlock on the two filehandles,
+ /*
+ * We cannot rely on fh_unlock on the two filehandles,
* as that would do the wrong thing if the two directories
- * were the same, so again we do it by hand
+ * were the same, so again we do it by hand.
*/
fill_post_wcc(ffhp);
fill_post_wcc(tfhp);
unlock_rename(tdentry, fdentry);
ffhp->fh_locked = tfhp->fh_locked = 0;
+ fh_drop_write(ffhp);
out:
return err;
@@ -1728,10 +1749,14 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
err = nfserr_acces;
if (!flen || isdotent(fname, flen))
goto out;
- err = fh_verify(rqstp, fhp, S_IFDIR, MAY_REMOVE);
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_REMOVE);
if (err)
goto out;
+ host_err = fh_want_write(fhp);
+ if (host_err)
+ goto out_nfserr;
+
fh_lock_nested(fhp, I_MUTEX_PARENT);
dentry = fhp->fh_dentry;
dirp = dentry->d_inode;
@@ -1750,25 +1775,14 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
if (!type)
type = rdentry->d_inode->i_mode & S_IFMT;
- if (type != S_IFDIR) { /* It's UNLINK */
-#ifdef MSNFS
- if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
- (atomic_read(&rdentry->d_count) > 1)) {
- host_err = -EPERM;
- } else
-#endif
- host_err = vfs_unlink(dirp, rdentry);
- } else { /* It's RMDIR */
+ if (type != S_IFDIR)
+ host_err = vfs_unlink(dirp, rdentry, NULL);
+ else
host_err = vfs_rmdir(dirp, rdentry);
- }
-
+ if (!host_err)
+ host_err = commit_metadata(fhp);
dput(rdentry);
- if (host_err)
- goto out_nfserr;
- if (EX_ISSYNC(fhp->fh_export))
- host_err = nfsd_sync_dir(dentry);
-
out_nfserr:
err = nfserrno(host_err);
out:
@@ -1776,6 +1790,129 @@ out:
}
/*
+ * We do this buffering because we must not call back into the file
+ * system's ->lookup() method from the filldir callback. That may well
+ * deadlock a number of file systems.
+ *
+ * This is based heavily on the implementation of same in XFS.
+ */
+struct buffered_dirent {
+ u64 ino;
+ loff_t offset;
+ int namlen;
+ unsigned int d_type;
+ char name[];
+};
+
+struct readdir_data {
+ struct dir_context ctx;
+ char *dirent;
+ size_t used;
+ int full;
+};
+
+static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type)
+{
+ struct readdir_data *buf = __buf;
+ struct buffered_dirent *de = (void *)(buf->dirent + buf->used);
+ unsigned int reclen;
+
+ reclen = ALIGN(sizeof(struct buffered_dirent) + namlen, sizeof(u64));
+ if (buf->used + reclen > PAGE_SIZE) {
+ buf->full = 1;
+ return -EINVAL;
+ }
+
+ de->namlen = namlen;
+ de->offset = offset;
+ de->ino = ino;
+ de->d_type = d_type;
+ memcpy(de->name, name, namlen);
+ buf->used += reclen;
+
+ return 0;
+}
+
+static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func,
+ struct readdir_cd *cdp, loff_t *offsetp)
+{
+ struct buffered_dirent *de;
+ int host_err;
+ int size;
+ loff_t offset;
+ struct readdir_data buf = {
+ .ctx.actor = nfsd_buffered_filldir,
+ .dirent = (void *)__get_free_page(GFP_KERNEL)
+ };
+
+ if (!buf.dirent)
+ return nfserrno(-ENOMEM);
+
+ offset = *offsetp;
+
+ while (1) {
+ struct inode *dir_inode = file_inode(file);
+ unsigned int reclen;
+
+ cdp->err = nfserr_eof; /* will be cleared on successful read */
+ buf.used = 0;
+ buf.full = 0;
+
+ host_err = iterate_dir(file, &buf.ctx);
+ if (buf.full)
+ host_err = 0;
+
+ if (host_err < 0)
+ break;
+
+ size = buf.used;
+
+ 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))
+ break;
+
+ if (cdp->err != nfs_ok)
+ 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);
+ }
+
+ free_page((unsigned long)(buf.dirent));
+
+ if (host_err)
+ return nfserrno(host_err);
+
+ *offsetp = offset;
+ return cdp->err;
+}
+
+/*
* Read entries from a directory.
* The NFSv3/4 verifier we ignore for now.
*/
@@ -1784,35 +1921,25 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp,
struct readdir_cd *cdp, filldir_t func)
{
__be32 err;
- int host_err;
struct file *file;
loff_t offset = *offsetp;
+ int may_flags = NFSD_MAY_READ;
+
+ /* NFSv2 only supports 32 bit cookies */
+ if (rqstp->rq_vers > 2)
+ may_flags |= NFSD_MAY_64BIT_COOKIE;
- err = nfsd_open(rqstp, fhp, S_IFDIR, MAY_READ, &file);
+ err = nfsd_open(rqstp, fhp, S_IFDIR, may_flags, &file);
if (err)
goto out;
- offset = vfs_llseek(file, offset, 0);
+ offset = vfs_llseek(file, offset, SEEK_SET);
if (offset < 0) {
err = nfserrno((int)offset);
goto out_close;
}
- /*
- * Read the directory entries. This silly loop is necessary because
- * readdir() is not guaranteed to fill up the entire buffer, but
- * may choose to do less.
- */
-
- do {
- cdp->err = nfserr_eof; /* will be cleared on successful read */
- host_err = vfs_readdir(file, func, cdp);
- } while (host_err >=0 && cdp->err == nfs_ok);
- if (host_err)
- err = nfserrno(host_err);
- else
- err = cdp->err;
- *offsetp = vfs_llseek(file, 0, 1);
+ err = nfsd_buffered_readdir(file, func, cdp, offsetp);
if (err == nfserr_eof || err == nfserr_toosmall)
err = nfs_ok; /* can still be found in ->err */
@@ -1827,11 +1954,19 @@ out:
* N.B. After this call fhp needs an fh_put
*/
__be32
-nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat)
+nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat, int access)
{
- __be32 err = fh_verify(rqstp, fhp, 0, MAY_NOP);
- if (!err && vfs_statfs(fhp->fh_dentry,stat))
- err = nfserr_io;
+ __be32 err;
+
+ err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP | access);
+ if (!err) {
+ struct path path = {
+ .mnt = fhp->fh_export->ex_path.mnt,
+ .dentry = fhp->fh_dentry,
+ };
+ if (vfs_statfs(&path, stat))
+ err = nfserr_io;
+ }
return err;
}
@@ -1850,41 +1985,42 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
struct inode *inode = dentry->d_inode;
int err;
- if (acc == MAY_NOP)
+ if ((acc & NFSD_MAY_MASK) == NFSD_MAY_NOP)
return 0;
#if 0
dprintk("nfsd: permission 0x%x%s%s%s%s%s%s%s mode 0%o%s%s%s\n",
acc,
- (acc & MAY_READ)? " read" : "",
- (acc & MAY_WRITE)? " write" : "",
- (acc & MAY_EXEC)? " exec" : "",
- (acc & MAY_SATTR)? " sattr" : "",
- (acc & MAY_TRUNC)? " trunc" : "",
- (acc & MAY_LOCK)? " lock" : "",
- (acc & MAY_OWNER_OVERRIDE)? " owneroverride" : "",
+ (acc & NFSD_MAY_READ)? " read" : "",
+ (acc & NFSD_MAY_WRITE)? " write" : "",
+ (acc & NFSD_MAY_EXEC)? " exec" : "",
+ (acc & NFSD_MAY_SATTR)? " sattr" : "",
+ (acc & NFSD_MAY_TRUNC)? " trunc" : "",
+ (acc & NFSD_MAY_LOCK)? " lock" : "",
+ (acc & NFSD_MAY_OWNER_OVERRIDE)? " owneroverride" : "",
inode->i_mode,
IS_IMMUTABLE(inode)? " immut" : "",
IS_APPEND(inode)? " append" : "",
- IS_RDONLY(inode)? " ro" : "");
+ __mnt_is_readonly(exp->ex_path.mnt)? " ro" : "");
dprintk(" owner %d/%d user %d/%d\n",
- inode->i_uid, inode->i_gid, current->fsuid, current->fsgid);
+ inode->i_uid, inode->i_gid, current_fsuid(), current_fsgid());
#endif
/* Normally we reject any write/sattr etc access on a read-only file
* system. But if it is IRIX doing check on write-access for a
* device special file, we ignore rofs.
*/
- if (!(acc & MAY_LOCAL_ACCESS))
- if (acc & (MAY_WRITE | MAY_SATTR | MAY_TRUNC)) {
- if (exp_rdonly(rqstp, exp) || IS_RDONLY(inode))
+ if (!(acc & NFSD_MAY_LOCAL_ACCESS))
+ if (acc & (NFSD_MAY_WRITE | NFSD_MAY_SATTR | NFSD_MAY_TRUNC)) {
+ if (exp_rdonly(rqstp, exp) ||
+ __mnt_is_readonly(exp->ex_path.mnt))
return nfserr_rofs;
- if (/* (acc & MAY_WRITE) && */ IS_IMMUTABLE(inode))
+ if (/* (acc & NFSD_MAY_WRITE) && */ IS_IMMUTABLE(inode))
return nfserr_perm;
}
- if ((acc & MAY_TRUNC) && IS_APPEND(inode))
+ if ((acc & NFSD_MAY_TRUNC) && IS_APPEND(inode))
return nfserr_perm;
- if (acc & MAY_LOCK) {
+ if (acc & NFSD_MAY_LOCK) {
/* If we cannot rely on authentication in NLM requests,
* just allow locks, otherwise require read permission, or
* ownership
@@ -1892,7 +2028,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
if (exp->ex_flags & NFSEXP_NOAUTHNLM)
return 0;
else
- acc = MAY_READ | MAY_OWNER_OVERRIDE;
+ acc = NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE;
}
/*
* The file owner always gets access permission for accesses that
@@ -1908,16 +2044,18 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
* We must trust the client to do permission checking - using "ACCESS"
* with NFSv3.
*/
- if ((acc & MAY_OWNER_OVERRIDE) &&
- inode->i_uid == current->fsuid)
+ if ((acc & NFSD_MAY_OWNER_OVERRIDE) &&
+ uid_eq(inode->i_uid, current_fsuid()))
return 0;
- err = permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC), NULL);
+ /* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */
+ err = inode_permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC));
/* Allow read access to binaries even when mode 111 */
if (err == -EACCES && S_ISREG(inode->i_mode) &&
- acc == (MAY_READ | MAY_OWNER_OVERRIDE))
- err = permission(inode, MAY_EXEC, NULL);
+ (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) ||
+ acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC)))
+ err = inode_permission(inode, MAY_EXEC);
return err? nfserrno(err) : 0;
}
@@ -1925,11 +2063,20 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
void
nfsd_racache_shutdown(void)
{
- if (!raparml)
- return;
+ struct raparms *raparm, *last_raparm;
+ unsigned int i;
+
dprintk("nfsd: freeing readahead buffers.\n");
- kfree(raparml);
- raparml = NULL;
+
+ for (i = 0; i < RAPARM_HASH_SIZE; i++) {
+ raparm = raparm_hash[i].pb_head;
+ while(raparm) {
+ last_raparm = raparm;
+ raparm = raparm->p_next;
+ kfree(last_raparm);
+ }
+ raparm_hash[i].pb_head = NULL;
+ }
}
/*
* Initialize readahead param cache
@@ -1940,119 +2087,36 @@ nfsd_racache_init(int cache_size)
int i;
int j = 0;
int nperbucket;
+ struct raparms **raparm = NULL;
- if (raparml)
+ if (raparm_hash[0].pb_head)
return 0;
- if (cache_size < 2*RAPARM_HASH_SIZE)
- cache_size = 2*RAPARM_HASH_SIZE;
- raparml = kcalloc(cache_size, sizeof(struct raparms), GFP_KERNEL);
-
- if (!raparml) {
- printk(KERN_WARNING
- "nfsd: Could not allocate memory read-ahead cache.\n");
- return -ENOMEM;
- }
+ nperbucket = DIV_ROUND_UP(cache_size, RAPARM_HASH_SIZE);
+ if (nperbucket < 2)
+ nperbucket = 2;
+ cache_size = nperbucket * RAPARM_HASH_SIZE;
dprintk("nfsd: allocating %d readahead buffers.\n", cache_size);
- for (i = 0 ; i < RAPARM_HASH_SIZE ; i++) {
- raparm_hash[i].pb_head = NULL;
+
+ for (i = 0; i < RAPARM_HASH_SIZE; i++) {
spin_lock_init(&raparm_hash[i].pb_lock);
- }
- nperbucket = DIV_ROUND_UP(cache_size, RAPARM_HASH_SIZE);
- for (i = 0; i < cache_size - 1; i++) {
- if (i % nperbucket == 0)
- raparm_hash[j++].pb_head = raparml + i;
- if (i % nperbucket < nperbucket-1)
- raparml[i].p_next = raparml + i + 1;
+
+ raparm = &raparm_hash[i].pb_head;
+ for (j = 0; j < nperbucket; j++) {
+ *raparm = kzalloc(sizeof(struct raparms), GFP_KERNEL);
+ if (!*raparm)
+ goto out_nomem;
+ raparm = &(*raparm)->p_next;
+ }
+ *raparm = NULL;
}
nfsdstats.ra_size = cache_size;
return 0;
-}
-
-#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
-struct posix_acl *
-nfsd_get_posix_acl(struct svc_fh *fhp, int type)
-{
- struct inode *inode = fhp->fh_dentry->d_inode;
- char *name;
- void *value = NULL;
- ssize_t size;
- struct posix_acl *acl;
-
- if (!IS_POSIXACL(inode))
- return ERR_PTR(-EOPNOTSUPP);
-
- switch (type) {
- case ACL_TYPE_ACCESS:
- name = POSIX_ACL_XATTR_ACCESS;
- break;
- case ACL_TYPE_DEFAULT:
- name = POSIX_ACL_XATTR_DEFAULT;
- break;
- default:
- return ERR_PTR(-EOPNOTSUPP);
- }
- size = nfsd_getxattr(fhp->fh_dentry, name, &value);
- if (size < 0)
- return ERR_PTR(size);
-
- acl = posix_acl_from_xattr(value, size);
- kfree(value);
- return acl;
-}
-
-int
-nfsd_set_posix_acl(struct svc_fh *fhp, int type, struct posix_acl *acl)
-{
- struct inode *inode = fhp->fh_dentry->d_inode;
- char *name;
- void *value = NULL;
- size_t size;
- int error;
-
- if (!IS_POSIXACL(inode) || !inode->i_op ||
- !inode->i_op->setxattr || !inode->i_op->removexattr)
- return -EOPNOTSUPP;
- switch(type) {
- case ACL_TYPE_ACCESS:
- name = POSIX_ACL_XATTR_ACCESS;
- break;
- case ACL_TYPE_DEFAULT:
- name = POSIX_ACL_XATTR_DEFAULT;
- break;
- default:
- return -EOPNOTSUPP;
- }
-
- if (acl && acl->a_count) {
- size = posix_acl_xattr_size(acl->a_count);
- value = kmalloc(size, GFP_KERNEL);
- if (!value)
- return -ENOMEM;
- error = posix_acl_to_xattr(acl, value, size);
- if (error < 0)
- goto getout;
- size = error;
- } else
- size = 0;
-
- if (size)
- error = vfs_setxattr(fhp->fh_dentry, name, value, size, 0);
- else {
- if (!S_ISDIR(inode->i_mode) && type == ACL_TYPE_DEFAULT)
- error = 0;
- else {
- error = vfs_removexattr(fhp->fh_dentry, name);
- if (error == -ENODATA)
- error = 0;
- }
- }
-
-getout:
- kfree(value);
- return error;
+out_nomem:
+ dprintk("nfsd: kmalloc failed, freeing readahead buffers\n");
+ nfsd_racache_shutdown();
+ return -ENOMEM;
}
-#endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 03:38:37 +0000