* Zerocpy NFS support (C) 2002 Hirokazu Takahashi <taka@valinux.co.jp>
*/
-#include <linux/config.h>
#include <linux/string.h>
#include <linux/time.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/major.h>
-#include <linux/ext2_fs.h>
+#include <linux/splice.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/nfsd_idmap.h>
#include <linux/security.h>
#endif /* CONFIG_NFSD_V4 */
+#include <linux/jhash.h>
#include <asm/uaccess.h>
#define NFSDDBG_FACILITY NFSDDBG_FILEOP
-#define NFSD_PARANOIA
-/* We must ignore files (but only files) which might have mandatory
- * locks on them because there is no way to know if the accesser has
- * the lock.
- */
-#define IS_ISMNDLK(i) (S_ISREG((i)->i_mode) && MANDATORY_LOCK(i))
-
/*
* This is a cache of readahead params that help us choose the proper
* readahead strategy. Initially, we set all readahead parameters to 0
dev_t p_dev;
int p_set;
struct file_ra_state p_ra;
+ unsigned int p_hindex;
};
-static struct raparms * raparml;
-static struct raparms * raparm_cache;
+struct raparm_hbucket {
+ struct raparms *pb_head;
+ spinlock_t pb_lock;
+} ____cacheline_aligned_in_smp;
+
+#define RAPARM_HASH_BITS 4
+#define RAPARM_HASH_SIZE (1<<RAPARM_HASH_BITS)
+#define RAPARM_HASH_MASK (RAPARM_HASH_SIZE-1)
+static struct raparm_hbucket raparm_hash[RAPARM_HASH_SIZE];
/*
* Called from nfsd_lookup and encode_dirent. Check if we have crossed
* a mount point.
- * Returns -EAGAIN leaving *dpp and *expp unchanged,
+ * Returns -EAGAIN or -ETIMEDOUT leaving *dpp and *expp unchanged,
* or nfs_ok having possibly changed *dpp and *expp
*/
int
{
struct svc_export *exp = *expp, *exp2 = NULL;
struct dentry *dentry = *dpp;
- struct vfsmount *mnt = mntget(exp->ex_mnt);
+ struct vfsmount *mnt = mntget(exp->ex_path.mnt);
struct dentry *mounts = dget(dentry);
- int err = nfs_ok;
+ int err = 0;
while (follow_down(&mnt,&mounts)&&d_mountpoint(mounts));
- exp2 = exp_get_by_name(exp->ex_client, mnt, mounts, &rqstp->rq_chandle);
+ exp2 = rqst_exp_get_by_name(rqstp, mnt, mounts);
if (IS_ERR(exp2)) {
- err = PTR_ERR(exp2);
+ if (PTR_ERR(exp2) != -ENOENT)
+ err = PTR_ERR(exp2);
dput(mounts);
mntput(mnt);
goto out;
}
- if (exp2 && ((exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2))) {
+ if ((exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) {
/* successfully crossed mount point */
- exp_put(exp);
- *expp = exp2;
+ /*
+ * This is subtle: dentry is *not* under mnt at this point.
+ * The only reason we are safe is that original mnt is pinned
+ * down by exp, so we should dput before putting exp.
+ */
dput(dentry);
*dpp = mounts;
+ exp_put(exp);
+ *expp = exp2;
} else {
- if (exp2) exp_put(exp2);
+ exp_put(exp2);
dput(mounts);
}
mntput(mnt);
return err;
}
-/*
- * Look up one component of a pathname.
- * N.B. After this call _both_ fhp and resfh need an fh_put
- *
- * If the lookup would cross a mountpoint, and the mounted filesystem
- * is exported to the client with NFSEXP_NOHIDE, then the lookup is
- * accepted as it stands and the mounted directory is
- * returned. Otherwise the covered directory is returned.
- * NOTE: this mountpoint crossing is not supported properly by all
- * clients and is explicitly disallowed for NFSv3
- * NeilBrown <neilb@cse.unsw.edu.au>
- */
-int
-nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
- int len, struct svc_fh *resfh)
+__be32
+nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ const char *name, unsigned int len,
+ struct svc_export **exp_ret, struct dentry **dentry_ret)
{
struct svc_export *exp;
struct dentry *dparent;
struct dentry *dentry;
- int err;
+ __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);
+ err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
if (err)
return err;
exp = fhp->fh_export;
exp_get(exp);
- err = nfserr_acces;
-
/* Lookup the name, but don't follow links */
if (isdotent(name, len)) {
if (len==1)
dentry = dget(dparent);
- else if (dparent != exp->ex_dentry) {
+ else if (dparent != exp->ex_path.dentry)
dentry = dget_parent(dparent);
- } else if (!EX_NOHIDE(exp))
+ else if (!EX_NOHIDE(exp))
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_mnt);
+ struct vfsmount *mnt = mntget(exp->ex_path.mnt);
dentry = dget(dparent);
while(dentry == mnt->mnt_root && follow_up(&mnt, &dentry))
;
dput(dentry);
dentry = dp;
- exp2 = exp_parent(exp->ex_client, mnt, dentry,
- &rqstp->rq_chandle);
- if (IS_ERR(exp2)) {
- err = PTR_ERR(exp2);
+ 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);
goto out_nfserr;
- }
- if (!exp2) {
- dput(dentry);
- dentry = dget(dparent);
} else {
exp_put(exp);
exp = exp2;
} else {
fh_lock(fhp);
dentry = lookup_one_len(name, dparent, len);
- err = PTR_ERR(dentry);
+ host_err = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out_nfserr;
/*
* check if we have crossed a mount point ...
*/
if (d_mountpoint(dentry)) {
- if ((err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
+ if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
dput(dentry);
goto out_nfserr;
}
}
}
+ *dentry_ret = dentry;
+ *exp_ret = exp;
+ return 0;
+
+out_nfserr:
+ exp_put(exp);
+ return nfserrno(host_err);
+}
+
+/*
+ * Look up one component of a pathname.
+ * N.B. After this call _both_ fhp and resfh need an fh_put
+ *
+ * If the lookup would cross a mountpoint, and the mounted filesystem
+ * is exported to the client with NFSEXP_NOHIDE, then the lookup is
+ * accepted as it stands and the mounted directory is
+ * returned. Otherwise the covered directory is returned.
+ * NOTE: this mountpoint crossing is not supported properly by all
+ * clients and is explicitly disallowed for NFSv3
+ * NeilBrown <neilb@cse.unsw.edu.au>
+ */
+__be32
+nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
+ unsigned int len, struct svc_fh *resfh)
+{
+ struct svc_export *exp;
+ struct dentry *dentry;
+ __be32 err;
+
+ err = nfsd_lookup_dentry(rqstp, fhp, name, len, &exp, &dentry);
+ if (err)
+ return err;
+ err = check_nfsd_access(exp, rqstp);
+ if (err)
+ goto out;
/*
* Note: we compose the file handle now, but as the
* dentry may be negative, it may need to be updated.
err = fh_compose(resfh, exp, dentry, fhp);
if (!err && !dentry->d_inode)
err = nfserr_noent;
- dput(dentry);
out:
+ dput(dentry);
exp_put(exp);
return err;
-
-out_nfserr:
- err = nfserrno(err);
- goto out;
}
+
/*
* Set various file attributes.
* N.B. After this call fhp needs an fh_put
*/
-int
+__be32
nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
int check_guard, time_t guardtime)
{
struct dentry *dentry;
struct inode *inode;
- int accmode = MAY_SATTR;
+ int accmode = NFSD_MAY_SATTR;
int ftype = 0;
- int imode;
- int err;
+ __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;
+ accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
if (iap->ia_valid & ATTR_SIZE)
ftype = S_IFREG;
if (!iap->ia_valid)
goto out;
- /* NFSv2 does not differentiate between "set-[ac]time-to-now"
+ /*
+ * NFSv2 does not differentiate between "set-[ac]time-to-now"
* which only requires access, and "set-[ac]time-to-X" which
* requires ownership.
* So if it looks like it might be "set both to the same time which
*/
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define MAX_TOUCH_TIME_ERROR (30*60)
- if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET
- && iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec
- ) {
- /* Looks probable. Now just make sure time is in the right ballpark.
- * Solaris, at least, doesn't seem to care what the time request is.
- * We require it be within 30 minutes of now.
- */
- time_t delta = iap->ia_atime.tv_sec - get_seconds();
- if (delta<0) delta = -delta;
- if (delta < MAX_TOUCH_TIME_ERROR &&
- inode_change_ok(inode, iap) != 0) {
- /* turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME
- * this will cause notify_change to set these times to "now"
+ if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET &&
+ iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) {
+ /*
+ * Looks probable.
+ *
+ * Now just make sure time is in the right ballpark.
+ * Solaris, at least, doesn't seem to care what the time
+ * request is. We require it be within 30 minutes of now.
*/
- iap->ia_valid &= ~BOTH_TIME_SET;
- }
+ time_t delta = iap->ia_atime.tv_sec - get_seconds();
+ if (delta < 0)
+ delta = -delta;
+ if (delta < MAX_TOUCH_TIME_ERROR &&
+ inode_change_ok(inode, iap) != 0) {
+ /*
+ * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME.
+ * This will cause notify_change to set these times
+ * to "now"
+ */
+ iap->ia_valid &= ~BOTH_TIME_SET;
+ }
}
- /* The size case is special. It changes the file as well as the attributes. */
+ /*
+ * 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(fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE);
+ err = nfsd_permission(rqstp, fhp->fh_export, dentry,
+ NFSD_MAY_TRUNC|NFSD_MAY_OWNER_OVERRIDE);
if (err)
goto out;
}
* If we are changing the size of the file, then
* we need to break all leases.
*/
- err = break_lease(inode, FMODE_WRITE | O_NONBLOCK);
- if (err == -EWOULDBLOCK)
- err = -ETIMEDOUT;
- if (err) /* ENOMEM or EWOULDBLOCK */
+ 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;
- err = get_write_access(inode);
- if (err)
+ host_err = get_write_access(inode);
+ if (host_err)
goto out_nfserr;
size_change = 1;
- err = locks_verify_truncate(inode, NULL, iap->ia_size);
- if (err) {
+ host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
+ if (host_err) {
put_write_access(inode);
goto out_nfserr;
}
- DQUOT_INIT(inode);
+ vfs_dq_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);
+ iap->ia_mode |= (inode->i_mode & ~S_IALLUGO);
}
- /* 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;
- if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)
- iap->ia_valid |= ATTR_KILL_SGID;
+ /* Revoke setuid/setgid on chown */
+ if (!S_ISDIR(inode->i_mode) &&
+ (((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) ||
+ ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_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);
+ }
+ }
/* Change the attributes. */
err = nfserr_notsync;
if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
fh_lock(fhp);
- err = notify_change(dentry, iap);
- err = nfserrno(err);
+ host_err = notify_change(dentry, iap);
+ err = nfserrno(host_err);
fh_unlock(fhp);
}
if (size_change)
return err;
out_nfserr:
- err = nfserrno(err);
+ err = nfserrno(host_err);
goto out;
}
static ssize_t nfsd_getxattr(struct dentry *dentry, char *key, void **buf)
{
ssize_t buflen;
- int error;
+ ssize_t ret;
buflen = vfs_getxattr(dentry, key, NULL, 0);
if (buflen <= 0)
if (!*buf)
return -ENOMEM;
- error = vfs_getxattr(dentry, key, *buf, buflen);
- if (error < 0)
- return error;
- return buflen;
+ ret = vfs_getxattr(dentry, key, *buf, buflen);
+ if (ret < 0)
+ kfree(*buf);
+ return ret;
}
#endif
return error;
}
-int
+__be32
nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct nfs4_acl *acl)
{
- int error;
+ __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)
- goto out;
+ return error;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
if (S_ISDIR(inode->i_mode))
flags = NFS4_ACL_DIR;
- error = nfs4_acl_nfsv4_to_posix(acl, &pacl, &dpacl, flags);
- if (error == -EINVAL) {
- error = nfserr_attrnotsupp;
- goto out;
- } else if (error < 0)
+ 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;
- if (pacl) {
- error = set_nfsv4_acl_one(dentry, pacl, POSIX_ACL_XATTR_ACCESS);
- if (error < 0)
- goto out_nfserr;
- }
-
- if (dpacl) {
- error = set_nfsv4_acl_one(dentry, dpacl, POSIX_ACL_XATTR_DEFAULT);
- if (error < 0)
- goto out_nfserr;
- }
+ host_error = set_nfsv4_acl_one(dentry, pacl, POSIX_ACL_XATTR_ACCESS);
+ if (host_error < 0)
+ goto out_release;
- error = nfs_ok;
+ if (S_ISDIR(inode->i_mode))
+ host_error = set_nfsv4_acl_one(dentry, dpacl, POSIX_ACL_XATTR_DEFAULT);
-out:
+out_release:
posix_acl_release(pacl);
posix_acl_release(dpacl);
- return (error);
out_nfserr:
- error = nfserrno(error);
- goto out;
+ if (host_error == -EOPNOTSUPP)
+ return nfserr_attrnotsupp;
+ else
+ return nfserrno(host_error);
}
static struct posix_acl *
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 }
};
* 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 }
};
-int
+__be32
nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *supported)
{
struct accessmap *map;
struct svc_export *export;
struct dentry *dentry;
u32 query, result = 0, sresult = 0;
- unsigned int error;
+ __be32 error;
- error = fh_verify(rqstp, fhp, 0, MAY_NOP);
+ error = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP);
if (error)
goto out;
query = *access;
for (; map->access; map++) {
if (map->access & query) {
- unsigned int err2;
+ __be32 err2;
sresult |= map->access;
- err2 = nfsd_permission(export, dentry, map->how);
+ err2 = nfsd_permission(rqstp, export, dentry, map->how);
switch (err2) {
case nfs_ok:
result |= map->access;
* The access argument indicates the type of open (read/write/lock)
* N.B. After this call fhp needs an fh_put
*/
-int
+__be32
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, err;
+ int flags = O_RDONLY|O_LARGEFILE;
+ __be32 err;
+ int host_err;
/*
* 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.
*/
- err = fh_verify(rqstp, fhp, type, access | MAY_OWNER_OVERRIDE);
+ err = fh_verify(rqstp, fhp, type, access | NFSD_MAY_OWNER_OVERRIDE);
if (err)
goto out;
* or any access when mandatory locking enabled
*/
err = nfserr_perm;
- if (IS_APPEND(inode) && (access & MAY_WRITE))
+ if (IS_APPEND(inode) && (access & NFSD_MAY_WRITE))
goto out;
- if (IS_ISMNDLK(inode))
+ /*
+ * We must ignore files (but only files) which might have mandatory
+ * locks on them because there is no way to know if the accesser has
+ * the lock.
+ */
+ if (S_ISREG((inode)->i_mode) && mandatory_lock(inode))
goto out;
if (!inode->i_fop)
* Check to see if there are any leases on this file.
* This may block while leases are broken.
*/
- err = break_lease(inode, O_NONBLOCK | ((access & MAY_WRITE) ? FMODE_WRITE : 0));
- if (err == -EWOULDBLOCK)
- err = -ETIMEDOUT;
- if (err) /* NOMEM or WOULDBLOCK */
+ host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? FMODE_WRITE : 0));
+ if (host_err == -EWOULDBLOCK)
+ host_err = -ETIMEDOUT;
+ if (host_err) /* NOMEM or WOULDBLOCK */
goto out_nfserr;
- if (access & MAY_WRITE) {
- flags = O_WRONLY|O_LARGEFILE;
+ if (access & NFSD_MAY_WRITE) {
+ if (access & NFSD_MAY_READ)
+ flags = O_RDWR|O_LARGEFILE;
+ else
+ flags = O_WRONLY|O_LARGEFILE;
- DQUOT_INIT(inode);
+ vfs_dq_init(inode);
}
- *filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_mnt), flags);
+ *filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_path.mnt),
+ flags, cred);
if (IS_ERR(*filp))
- err = PTR_ERR(*filp);
+ host_err = PTR_ERR(*filp);
out_nfserr:
- if (err)
- err = nfserrno(err);
+ err = nfserrno(host_err);
out:
return err;
}
return err;
}
-
static int
nfsd_sync(struct file *filp)
{
int err;
- struct inode *inode = filp->f_dentry->d_inode;
- dprintk("nfsd: sync file %s\n", filp->f_dentry->d_name.name);
+ 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_dentry, filp->f_op);
+ err=nfsd_dosync(filp, filp->f_path.dentry, filp->f_op);
mutex_unlock(&inode->i_mutex);
return err;
* Obtain the readahead parameters for the file
* specified by (dev, ino).
*/
-static DEFINE_SPINLOCK(ra_lock);
static inline struct raparms *
nfsd_get_raparms(dev_t dev, ino_t ino)
{
struct raparms *ra, **rap, **frap = NULL;
int depth = 0;
+ unsigned int hash;
+ struct raparm_hbucket *rab;
- spin_lock(&ra_lock);
- for (rap = &raparm_cache; (ra = *rap); rap = &ra->p_next) {
+ hash = jhash_2words(dev, ino, 0xfeedbeef) & RAPARM_HASH_MASK;
+ rab = &raparm_hash[hash];
+
+ spin_lock(&rab->pb_lock);
+ for (rap = &rab->pb_head; (ra = *rap); rap = &ra->p_next) {
if (ra->p_ino == ino && ra->p_dev == dev)
goto found;
depth++;
}
depth = nfsdstats.ra_size*11/10;
if (!frap) {
- spin_unlock(&ra_lock);
+ spin_unlock(&rab->pb_lock);
return NULL;
}
rap = frap;
ra->p_dev = dev;
ra->p_ino = ino;
ra->p_set = 0;
+ ra->p_hindex = hash;
found:
- if (rap != &raparm_cache) {
+ if (rap != &rab->pb_head) {
*rap = ra->p_next;
- ra->p_next = raparm_cache;
- raparm_cache = ra;
+ ra->p_next = rab->pb_head;
+ rab->pb_head = ra;
}
ra->p_count++;
nfsdstats.ra_depth[depth*10/nfsdstats.ra_size]++;
- spin_unlock(&ra_lock);
+ spin_unlock(&rab->pb_lock);
return ra;
}
/*
- * Grab and keep cached pages assosiated with a file in the svc_rqst
- * so that they can be passed to the netowork sendmsg/sendpage routines
- * directrly. They will be released after the sending has completed.
+ * Grab and keep cached pages associated with a file in the svc_rqst
+ * so that they can be passed to the network sendmsg/sendpage routines
+ * directly. They will be released after the sending has completed.
*/
static int
-nfsd_read_actor(read_descriptor_t *desc, struct page *page, unsigned long offset , unsigned long size)
+nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
+ struct splice_desc *sd)
{
- unsigned long count = desc->count;
- struct svc_rqst *rqstp = desc->arg.data;
+ struct svc_rqst *rqstp = sd->u.data;
+ struct page **pp = rqstp->rq_respages + rqstp->rq_resused;
+ struct page *page = buf->page;
+ size_t size;
+ int ret;
- if (size > count)
- size = count;
+ ret = buf->ops->confirm(pipe, buf);
+ if (unlikely(ret))
+ return ret;
+
+ size = sd->len;
if (rqstp->rq_res.page_len == 0) {
get_page(page);
- rqstp->rq_respages[rqstp->rq_resused++] = page;
- rqstp->rq_res.page_base = offset;
+ put_page(*pp);
+ *pp = page;
+ rqstp->rq_resused++;
+ rqstp->rq_res.page_base = buf->offset;
rqstp->rq_res.page_len = size;
- } else if (page != rqstp->rq_respages[rqstp->rq_resused-1]) {
+ } else if (page != pp[-1]) {
get_page(page);
- rqstp->rq_respages[rqstp->rq_resused++] = page;
+ if (*pp)
+ put_page(*pp);
+ *pp = page;
+ rqstp->rq_resused++;
rqstp->rq_res.page_len += size;
- } else {
+ } else
rqstp->rq_res.page_len += size;
- }
- desc->count = count - size;
- desc->written += size;
return size;
}
-static int
+static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe,
+ struct splice_desc *sd)
+{
+ return __splice_from_pipe(pipe, sd, nfsd_splice_actor);
+}
+
+static inline int svc_msnfs(struct svc_fh *ffhp)
+{
+#ifdef MSNFS
+ return (ffhp->fh_export->ex_flags & NFSEXP_MSNFS);
+#else
+ return 0;
+#endif
+}
+
+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)
{
struct inode *inode;
struct raparms *ra;
mm_segment_t oldfs;
- int err;
+ __be32 err;
+ int host_err;
err = nfserr_perm;
- inode = file->f_dentry->d_inode;
-#ifdef MSNFS
- if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
- (!lock_may_read(inode, offset, *count)))
+ inode = file->f_path.dentry->d_inode;
+
+ if (svc_msnfs(fhp) && !lock_may_read(inode, offset, *count))
goto out;
-#endif
/* 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;
- if (file->f_op->sendfile) {
- svc_pushback_unused_pages(rqstp);
- err = file->f_op->sendfile(file, &offset, *count,
- nfsd_read_actor, rqstp);
+ if (file->f_op->splice_read && rqstp->rq_splice_ok) {
+ struct splice_desc sd = {
+ .len = 0,
+ .total_len = *count,
+ .pos = offset,
+ .u.data = rqstp,
+ };
+
+ rqstp->rq_resused = 1;
+ host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
} else {
oldfs = get_fs();
set_fs(KERNEL_DS);
- err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
+ host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
set_fs(oldfs);
}
/* Write back readahead params */
if (ra) {
- spin_lock(&ra_lock);
+ 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(&ra_lock);
+ spin_unlock(&rab->pb_lock);
}
- if (err >= 0) {
- nfsdstats.io_read += err;
- *count = err;
+ if (host_err >= 0) {
+ nfsdstats.io_read += host_err;
+ *count = host_err;
err = 0;
- fsnotify_access(file->f_dentry);
+ fsnotify_access(file->f_path.dentry);
} else
- err = nfserrno(err);
+ err = nfserrno(host_err);
out:
return err;
}
static void kill_suid(struct dentry *dentry)
{
struct iattr ia;
- ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID;
+ 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 int
+/*
+ * 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,
- unsigned long cnt, int *stablep)
+ unsigned long *cnt, int *stablep)
{
struct svc_export *exp;
struct dentry *dentry;
struct inode *inode;
mm_segment_t oldfs;
- int err = 0;
+ __be32 err = 0;
+ int host_err;
int stable = *stablep;
+ int use_wgather;
#ifdef MSNFS
err = nfserr_perm;
if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
- (!lock_may_write(file->f_dentry->d_inode, offset, cnt)))
+ (!lock_may_write(file->f_path.dentry->d_inode, offset, *cnt)))
goto out;
#endif
- dentry = file->f_dentry;
+ dentry = file->f_path.dentry;
inode = dentry->d_inode;
exp = fhp->fh_export;
* - 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 == 0) {/* COMMIT3 cannot work */
+ if (!file->f_op->fsync) {/* COMMIT3 cannot work */
stable = 2;
*stablep = 2; /* FILE_SYNC */
}
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);
- err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset);
+ host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset);
set_fs(oldfs);
- if (err >= 0) {
- nfsdstats.io_write += cnt;
- fsnotify_modify(file->f_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 (err >= 0 && (inode->i_mode & (S_ISUID | S_ISGID)))
+ if (inode->i_mode & (S_ISUID | S_ISGID))
kill_suid(dentry);
- if (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", current->pid);
- msleep(10);
- dprintk("nfsd: write resume %d\n", current->pid);
- }
-
- if (inode->i_state & I_DIRTY) {
- dprintk("nfsd: write sync %d\n", current->pid);
- 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);
- dprintk("nfsd: write complete err=%d\n", err);
- if (err >= 0)
+out_nfserr:
+ dprintk("nfsd: write complete host_err=%d\n", host_err);
+ if (host_err >= 0)
err = 0;
- else
- err = nfserrno(err);
+ else
+ err = nfserrno(host_err);
out:
return err;
}
* on entry. On return, *count contains the number of bytes actually read.
* N.B. After this call fhp needs an fh_put
*/
-int
+__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)
{
- int err;
+ __be32 err;
if (file) {
- err = nfsd_permission(fhp->fh_export, fhp->fh_dentry,
- MAY_READ|MAY_OWNER_OVERRIDE);
+ err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
+ NFSD_MAY_READ|NFSD_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);
+ err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
if (err)
goto out;
err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
* The stable flag requests synchronous writes.
* N.B. After this call fhp needs an fh_put
*/
-int
+__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)
{
- int err = 0;
+ __be32 err = 0;
if (file) {
- err = nfsd_permission(fhp->fh_export, fhp->fh_dentry,
- MAY_WRITE|MAY_OWNER_OVERRIDE);
+ err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
+ 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;
* 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.
*/
-int
+__be32
nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
loff_t offset, unsigned long count)
{
struct file *file;
- int err;
+ __be32 err;
if ((u64)count > ~(u64)offset)
return nfserr_inval;
- if ((err = nfsd_open(rqstp, fhp, S_IFREG, MAY_WRITE, &file)) != 0)
+ err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
+ if (err)
return err;
if (EX_ISSYNC(fhp->fh_export)) {
if (file->f_op && file->f_op->fsync) {
}
#endif /* CONFIG_NFSD_V3 */
+static __be32
+nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp,
+ struct iattr *iap)
+{
+ /*
+ * Mode has already been set earlier in create:
+ */
+ iap->ia_valid &= ~ATTR_MODE;
+ /*
+ * Setting uid/gid works only for root. Irix appears to
+ * send along the gid on create when it tries to implement
+ * setgid directories via NFS:
+ */
+ if (current_fsuid() != 0)
+ 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.
*
* N.B. Every call to nfsd_create needs an fh_put for _both_ fhp and resfhp
*/
-int
+__be32
nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
char *fname, int flen, struct iattr *iap,
int type, dev_t rdev, struct svc_fh *resfhp)
{
struct dentry *dentry, *dchild = NULL;
struct inode *dirp;
- int err;
+ __be32 err;
+ __be32 err2;
+ int host_err;
err = nfserr_perm;
if (!flen)
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;
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 (!resfhp->fh_dentry) {
/* called from nfsd_proc_mkdir, or possibly nfsd3_proc_create */
- fh_lock(fhp);
+ fh_lock_nested(fhp, I_MUTEX_PARENT);
dchild = lookup_one_len(fname, dentry, flen);
- err = PTR_ERR(dchild);
+ host_err = PTR_ERR(dchild);
if (IS_ERR(dchild))
goto out_nfserr;
err = fh_compose(resfhp, fhp->fh_export, dchild, 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;
+ }
+
+ host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+ if (host_err)
+ goto out_nfserr;
+
/*
* Get the dir op function pointer.
*/
- err = nfserr_perm;
+ err = 0;
switch (type) {
case S_IFREG:
- err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
+ host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
+ if (!host_err)
+ nfsd_check_ignore_resizing(iap);
break;
case S_IFDIR:
- err = vfs_mkdir(dirp, dchild, iap->ia_mode);
+ host_err = vfs_mkdir(dirp, dchild, iap->ia_mode);
break;
case S_IFCHR:
case S_IFBLK:
case S_IFIFO:
case S_IFSOCK:
- err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev);
+ host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev);
break;
- default:
- printk("nfsd: bad file type %o in nfsd_create\n", type);
- err = -EINVAL;
}
- if (err < 0)
+ if (host_err < 0) {
+ mnt_drop_write(fhp->fh_export->ex_path.mnt);
goto out_nfserr;
+ }
if (EX_ISSYNC(fhp->fh_export)) {
err = nfserrno(nfsd_sync_dir(dentry));
write_inode_now(dchild->d_inode, 1);
}
-
- /* Set file attributes. Mode has already been set and
- * setting uid/gid works only for root. Irix appears to
- * send along the gid when it tries to implement setgid
- * directories via NFS.
- */
- if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0) {
- int err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
- if (err2)
- err = err2;
- }
+ err2 = nfsd_create_setattr(rqstp, resfhp, iap);
+ if (err2)
+ err = err2;
+ mnt_drop_write(fhp->fh_export->ex_path.mnt);
/*
* Update the file handle to get the new inode info.
*/
return err;
out_nfserr:
- err = nfserrno(err);
+ err = nfserrno(host_err);
goto out;
}
/*
* NFSv3 version of nfsd_create
*/
-int
+__be32
nfsd_create_v3(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 *truncp, int *created)
{
struct dentry *dentry, *dchild = NULL;
struct inode *dirp;
- int err;
+ __be32 err;
+ __be32 err2;
+ int host_err;
__u32 v_mtime=0, v_atime=0;
- int v_mode=0;
err = nfserr_perm;
if (!flen)
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_CREATE);
if (err)
goto out;
/* 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;
- fh_lock(fhp);
+ fh_lock_nested(fhp, I_MUTEX_PARENT);
/*
* Compose the response file handle.
*/
dchild = lookup_one_len(fname, dentry, flen);
- err = PTR_ERR(dchild);
+ host_err = PTR_ERR(dchild);
if (IS_ERR(dchild))
goto out_nfserr;
goto out;
if (createmode == NFS3_CREATE_EXCLUSIVE) {
- /* while the verifier would fit in mtime+atime,
- * solaris7 gets confused (bugid 4218508) if these have
- * the high bit set, so we use the mode as well
+ /* 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
+ * verifier, then do_open_lookup() will also need to be fixed
+ * accordingly.
*/
v_mtime = verifier[0]&0x7fffffff;
v_atime = verifier[1]&0x7fffffff;
- v_mode = S_IFREG
- | ((verifier[0]&0x80000000) >> (32-7)) /* u+x */
- | ((verifier[1]&0x80000000) >> (32-9)) /* u+r */
- ;
}
+ host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+ if (host_err)
+ goto out_nfserr;
if (dchild->d_inode) {
err = 0;
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_mode == v_mode
&& dchild->d_inode->i_size == 0 )
break;
/* fallthru */
case NFS3_CREATE_GUARDED:
err = nfserr_exist;
}
+ mnt_drop_write(fhp->fh_export->ex_path.mnt);
goto out;
}
- err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
- if (err < 0)
+ host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
+ if (host_err < 0) {
+ mnt_drop_write(fhp->fh_export->ex_path.mnt);
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) {
- /* Cram the verifier into atime/mtime/mode */
+ /* Cram the verifier into atime/mtime */
iap->ia_valid = ATTR_MTIME|ATTR_ATIME
- | ATTR_MTIME_SET|ATTR_ATIME_SET
- | ATTR_MODE;
+ | ATTR_MTIME_SET|ATTR_ATIME_SET;
/* XXX someone who knows this better please fix it for nsec */
iap->ia_mtime.tv_sec = v_mtime;
iap->ia_atime.tv_sec = v_atime;
iap->ia_mtime.tv_nsec = 0;
iap->ia_atime.tv_nsec = 0;
- iap->ia_mode = v_mode;
}
- /* Set file attributes.
- * Mode has already been set but we might need to reset it
- * for CREATE_EXCLUSIVE
- * Irix appears to send along the gid when it tries to
- * implement setgid directories via NFS. Clear out all that cruft.
- */
set_attr:
- if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID)) != 0) {
- int err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
- if (err2)
- err = err2;
- }
+ err2 = nfsd_create_setattr(rqstp, resfhp, iap);
+ if (err2)
+ err = err2;
+ mnt_drop_write(fhp->fh_export->ex_path.mnt);
/*
* Update the filehandle to get the new inode info.
*/
return err;
out_nfserr:
- err = nfserrno(err);
+ err = nfserrno(host_err);
goto out;
}
#endif /* CONFIG_NFSD_V3 */
* fits into the buffer. On return, it contains the true length.
* N.B. After this call fhp needs an fh_put
*/
-int
+__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;
- int err;
+ __be32 err;
+ int host_err;
- err = fh_verify(rqstp, fhp, S_IFLNK, MAY_NOP);
+ err = fh_verify(rqstp, fhp, S_IFLNK, NFSD_MAY_NOP);
if (err)
goto out;
inode = 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_mnt, dentry);
+ touch_atime(fhp->fh_export->ex_path.mnt, dentry);
/* 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);
- err = inode->i_op->readlink(dentry, buf, *lenp);
+ host_err = inode->i_op->readlink(dentry, buf, *lenp);
set_fs(oldfs);
- if (err < 0)
+ if (host_err < 0)
goto out_nfserr;
- *lenp = err;
+ *lenp = host_err;
err = 0;
out:
return err;
out_nfserr:
- err = nfserrno(err);
+ err = nfserrno(host_err);
goto out;
}
* Create a symlink and look up its inode
* N.B. After this call _both_ fhp and resfhp need an fh_put
*/
-int
+__be32
nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
char *fname, int flen,
char *path, int plen,
struct iattr *iap)
{
struct dentry *dentry, *dnew;
- int err, cerr;
- umode_t mode;
+ __be32 err, cerr;
+ int host_err;
err = nfserr_noent;
if (!flen || !plen)
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;
fh_lock(fhp);
dentry = fhp->fh_dentry;
dnew = lookup_one_len(fname, dentry, flen);
- err = PTR_ERR(dnew);
+ host_err = PTR_ERR(dnew);
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;
+ host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+ if (host_err)
+ goto out_nfserr;
if (unlikely(path[plen] != 0)) {
char *path_alloced = kmalloc(plen+1, GFP_KERNEL);
if (path_alloced == NULL)
- err = -ENOMEM;
+ host_err = -ENOMEM;
else {
strncpy(path_alloced, path, plen);
path_alloced[plen] = 0;
- err = vfs_symlink(dentry->d_inode, dnew, path_alloced, mode);
+ host_err = vfs_symlink(dentry->d_inode, dnew, path_alloced);
kfree(path_alloced);
}
} else
- err = vfs_symlink(dentry->d_inode, dnew, path, mode);
+ host_err = vfs_symlink(dentry->d_inode, dnew, path);
- if (!err)
+ if (!host_err) {
if (EX_ISSYNC(fhp->fh_export))
- err = nfsd_sync_dir(dentry);
- if (err)
- err = nfserrno(err);
+ host_err = nfsd_sync_dir(dentry);
+ }
+ err = nfserrno(host_err);
fh_unlock(fhp);
+ mnt_drop_write(fhp->fh_export->ex_path.mnt);
+
cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp);
dput(dnew);
if (err==0) err = cerr;
return err;
out_nfserr:
- err = nfserrno(err);
+ err = nfserrno(host_err);
goto out;
}
* Create a hardlink
* N.B. After this call _both_ ffhp and tfhp need an fh_put
*/
-int
+__be32
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;
- int err;
+ __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, -S_IFDIR, NFSD_MAY_NOP);
if (err)
goto out;
if (isdotent(name, len))
goto out;
- fh_lock(ffhp);
+ fh_lock_nested(ffhp, I_MUTEX_PARENT);
ddir = ffhp->fh_dentry;
dirp = ddir->d_inode;
dnew = lookup_one_len(name, ddir, len);
- err = PTR_ERR(dnew);
+ host_err = PTR_ERR(dnew);
if (IS_ERR(dnew))
goto out_nfserr;
dold = tfhp->fh_dentry;
dest = dold->d_inode;
- err = vfs_link(dold, dirp, dnew);
- if (!err) {
+ host_err = mnt_want_write(tfhp->fh_export->ex_path.mnt);
+ if (host_err) {
+ err = nfserrno(host_err);
+ goto out_dput;
+ }
+ 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;
} else {
- if (err == -EXDEV && rqstp->rq_vers == 2)
+ if (host_err == -EXDEV && rqstp->rq_vers == 2)
err = nfserr_acces;
else
- err = nfserrno(err);
+ err = nfserrno(host_err);
}
-
- fh_unlock(ffhp);
+ mnt_drop_write(tfhp->fh_export->ex_path.mnt);
+out_dput:
dput(dnew);
+out_unlock:
+ fh_unlock(ffhp);
out:
return err;
out_nfserr:
- err = nfserrno(err);
- goto out;
+ err = nfserrno(host_err);
+ goto out_unlock;
}
/*
* Rename a file
* N.B. After this call _both_ ffhp and tfhp need an fh_put
*/
-int
+__be32
nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
struct svc_fh *tfhp, char *tname, int tlen)
{
struct dentry *fdentry, *tdentry, *odentry, *ndentry, *trap;
struct inode *fdir, *tdir;
- int err;
+ __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;
tdir = tdentry->d_inode;
err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev;
- if (fdir->i_sb != tdir->i_sb)
+ if (ffhp->fh_export != tfhp->fh_export)
goto out;
err = nfserr_perm;
fill_pre_wcc(tfhp);
odentry = lookup_one_len(fname, fdentry, flen);
- err = PTR_ERR(odentry);
+ host_err = PTR_ERR(odentry);
if (IS_ERR(odentry))
goto out_nfserr;
- err = -ENOENT;
+ host_err = -ENOENT;
if (!odentry->d_inode)
goto out_dput_old;
- err = -EINVAL;
+ host_err = -EINVAL;
if (odentry == trap)
goto out_dput_old;
ndentry = lookup_one_len(tname, tdentry, tlen);
- err = PTR_ERR(ndentry);
+ host_err = PTR_ERR(ndentry);
if (IS_ERR(ndentry))
goto out_dput_old;
- err = -ENOTEMPTY;
+ host_err = -ENOTEMPTY;
if (ndentry == trap)
goto out_dput_new;
-#ifdef MSNFS
- if ((ffhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
+ if (svc_msnfs(ffhp) &&
((atomic_read(&odentry->d_count) > 1)
|| (atomic_read(&ndentry->d_count) > 1))) {
- err = -EPERM;
- } else
-#endif
- err = vfs_rename(fdir, odentry, tdir, ndentry);
- if (!err && EX_ISSYNC(tfhp->fh_export)) {
- err = nfsd_sync_dir(tdentry);
- if (!err)
- err = nfsd_sync_dir(fdentry);
+ host_err = -EPERM;
+ goto out_dput_new;
}
+ host_err = -EXDEV;
+ if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt)
+ goto out_dput_new;
+ host_err = mnt_want_write(ffhp->fh_export->ex_path.mnt);
+ if (host_err)
+ 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 = nfsd_sync_dir(fdentry);
+ }
+
+ mnt_drop_write(ffhp->fh_export->ex_path.mnt);
+
out_dput_new:
dput(ndentry);
out_dput_old:
dput(odentry);
out_nfserr:
- if (err)
- err = nfserrno(err);
+ err = nfserrno(host_err);
/* we cannot reply on fh_unlock on the two filehandles,
* as that would do the wrong thing if the two directories
* Unlink a file or directory
* N.B. After this call fhp needs an fh_put
*/
-int
+__be32
nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
char *fname, int flen)
{
struct dentry *dentry, *rdentry;
struct inode *dirp;
- int err;
+ __be32 err;
+ int host_err;
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;
- fh_lock(fhp);
+ fh_lock_nested(fhp, I_MUTEX_PARENT);
dentry = fhp->fh_dentry;
dirp = dentry->d_inode;
rdentry = lookup_one_len(fname, dentry, flen);
- err = PTR_ERR(rdentry);
+ host_err = PTR_ERR(rdentry);
if (IS_ERR(rdentry))
goto out_nfserr;
if (!type)
type = rdentry->d_inode->i_mode & S_IFMT;
+ host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+ if (host_err)
+ goto out_nfserr;
+
if (type != S_IFDIR) { /* It's UNLINK */
#ifdef MSNFS
if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
(atomic_read(&rdentry->d_count) > 1)) {
- err = -EPERM;
+ host_err = -EPERM;
} else
#endif
- err = vfs_unlink(dirp, rdentry);
+ host_err = vfs_unlink(dirp, rdentry);
} else { /* It's RMDIR */
- err = vfs_rmdir(dirp, rdentry);
+ host_err = vfs_rmdir(dirp, rdentry);
}
dput(rdentry);
- if (err == 0 &&
- EX_ISSYNC(fhp->fh_export))
- err = nfsd_sync_dir(dentry);
+ if (host_err)
+ goto out_drop;
+ if (EX_ISSYNC(fhp->fh_export))
+ host_err = nfsd_sync_dir(dentry);
+out_drop:
+ mnt_drop_write(fhp->fh_export->ex_path.mnt);
out_nfserr:
- err = nfserrno(err);
+ err = nfserrno(host_err);
out:
return err;
}
/*
+ * 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 {
+ 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 readdir_data buf;
+ struct buffered_dirent *de;
+ int host_err;
+ int size;
+ loff_t offset;
+
+ buf.dirent = (void *)__get_free_page(GFP_KERNEL);
+ if (!buf.dirent)
+ 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 */
+ buf.used = 0;
+ buf.full = 0;
+
+ host_err = vfs_readdir(file, nfsd_buffered_filldir, &buf);
+ 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.
*/
-int
+__be32
nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp,
- struct readdir_cd *cdp, encode_dent_fn func)
+ struct readdir_cd *cdp, filldir_t func)
{
- int err;
+ __be32 err;
struct file *file;
loff_t offset = *offsetp;
- err = nfsd_open(rqstp, fhp, S_IFDIR, MAY_READ, &file);
+ err = nfsd_open(rqstp, fhp, S_IFDIR, NFSD_MAY_READ, &file);
if (err)
goto out;
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 */
- err = vfs_readdir(file, (filldir_t) func, cdp);
- } while (err >=0 && cdp->err == nfs_ok);
- if (err)
- err = nfserrno(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 */
* Get file system stats
* N.B. After this call fhp needs an fh_put
*/
-int
-nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat)
+__be32
+nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat, int access)
{
- int err = fh_verify(rqstp, fhp, 0, MAY_NOP);
- if (!err && vfs_statfs(fhp->fh_dentry->d_inode->i_sb,stat))
+ __be32 err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP | access);
+ if (!err && vfs_statfs(fhp->fh_dentry,stat))
err = nfserr_io;
return err;
}
+static int exp_rdonly(struct svc_rqst *rqstp, struct svc_export *exp)
+{
+ return nfsexp_flags(rqstp, exp) & NFSEXP_READONLY;
+}
+
/*
* Check for a user's access permissions to this inode.
*/
-int
-nfsd_permission(struct svc_export *exp, struct dentry *dentry, int acc)
+__be32
+nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
+ struct dentry *dentry, int acc)
{
struct inode *inode = dentry->d_inode;
int err;
- if (acc == MAY_NOP)
+ if (acc == 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 (EX_RDONLY(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
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
* 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) &&
+ 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))
+ err = inode_permission(inode, MAY_EXEC);
return err? nfserrno(err) : 0;
}
void
nfsd_racache_shutdown(void)
{
- if (!raparm_cache)
- return;
+ struct raparms *raparm, *last_raparm;
+ unsigned int i;
+
dprintk("nfsd: freeing readahead buffers.\n");
- kfree(raparml);
- raparm_cache = 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
nfsd_racache_init(int cache_size)
{
int i;
+ int j = 0;
+ int nperbucket;
+ struct raparms **raparm = NULL;
+
- if (raparm_cache)
+ if (raparm_hash[0].pb_head)
return 0;
- raparml = kmalloc(sizeof(struct raparms) * cache_size, GFP_KERNEL);
-
- if (raparml != NULL) {
- dprintk("nfsd: allocating %d readahead buffers.\n",
- cache_size);
- memset(raparml, 0, sizeof(struct raparms) * cache_size);
- for (i = 0; i < cache_size - 1; i++) {
- raparml[i].p_next = raparml + i + 1;
+ 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++) {
+ spin_lock_init(&raparm_hash[i].pb_lock);
+
+ 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_cache = raparml;
- } else {
- printk(KERN_WARNING
- "nfsd: Could not allocate memory read-ahead cache.\n");
- return -ENOMEM;
+ *raparm = NULL;
}
+
nfsdstats.ra_size = cache_size;
return 0;
+
+out_nomem:
+ dprintk("nfsd: kmalloc failed, freeing readahead buffers\n");
+ nfsd_racache_shutdown();
+ return -ENOMEM;
}
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
size_t size;
int error;
- if (!IS_POSIXACL(inode) || !inode->i_op ||
+ if (!IS_POSIXACL(inode) ||
!inode->i_op->setxattr || !inode->i_op->removexattr)
return -EOPNOTSUPP;
switch(type) {
value = kmalloc(size, GFP_KERNEL);
if (!value)
return -ENOMEM;
- size = posix_acl_to_xattr(acl, value, size);
- if (size < 0) {
- error = size;
+ error = posix_acl_to_xattr(acl, value, size);
+ if (error < 0)
goto getout;
- }
+ size = error;
} else
size = 0;
+ error = mnt_want_write(fhp->fh_export->ex_path.mnt);
+ if (error)
+ goto getout;
if (size)
error = vfs_setxattr(fhp->fh_dentry, name, value, size, 0);
else {
error = 0;
}
}
+ mnt_drop_write(fhp->fh_export->ex_path.mnt);
getout:
kfree(value);