diff options
Diffstat (limited to 'fs/nfsd/vfs.c')
| -rw-r--r-- | fs/nfsd/vfs.c | 972 |
1 files changed, 408 insertions, 564 deletions
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 184938fcff0..140c496f612 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1,4 +1,3 @@ -#define MSNFS /* HACK HACK */ /* * File operations used by nfsd. Some of these have been ripped from * other parts of the kernel because they weren't exported, others @@ -29,14 +28,15 @@ #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 <linux/nfs4_acl.h> -#include <linux/nfsd_idmap.h> +#include "acl.h" +#include "idmap.h" #endif /* CONFIG_NFSD_V4 */ #include "nfsd.h" @@ -88,8 +88,9 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, .dentry = dget(dentry)}; int err = 0; - while (d_mountpoint(path.dentry) && follow_down(&path)) - ; + err = follow_down(&path); + if (err < 0) + goto out; exp2 = rqst_exp_get_by_name(rqstp, &path); if (IS_ERR(exp2)) { @@ -168,6 +169,8 @@ 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; @@ -181,16 +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, NFSD_MAY_EXEC); - if (err) - return err; - dparent = fhp->fh_dentry; exp = fhp->fh_export; exp_get(exp); @@ -210,7 +207,12 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_nfserr; } } 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)) @@ -254,6 +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; @@ -291,41 +296,12 @@ commit_metadata(struct svc_fh *fhp) } /* - * Set various file attributes. - * N.B. After this call fhp needs an fh_put + * Go over the attributes and take care of the small differences between + * NFS semantics and what Linux expects. */ -__be32 -nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, - int check_guard, time_t guardtime) +static void +nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) { - struct dentry *dentry; - struct inode *inode; - int accmode = NFSD_MAY_SATTR; - int ftype = 0; - __be32 err; - int host_err; - int size_change = 0; - - 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; - - /* Get inode */ - err = fh_verify(rqstp, fhp, ftype, accmode); - if (err) - goto out; - - 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; - /* * NFSv2 does not differentiate between "set-[ac]time-to-now" * which only requires access, and "set-[ac]time-to-X" which @@ -335,8 +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) @@ -362,40 +337,6 @@ 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, - 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. - */ - host_err = break_lease(inode, O_WRONLY | 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; - } - } /* sanitize the mode change */ if (iap->ia_valid & ATTR_MODE) { @@ -405,8 +346,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, /* 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_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 */ @@ -418,181 +358,171 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, iap->ia_valid |= (ATTR_KILL_SUID | 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) - commit_metadata(fhp); -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; - ssize_t ret; - - buflen = vfs_getxattr(dentry, key, NULL, 0); - if (buflen <= 0) - return 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; - *buf = kmalloc(buflen, GFP_KERNEL); - if (!*buf) - return -ENOMEM; + 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; - ret = vfs_getxattr(dentry, key, *buf, buflen); - if (ret < 0) - kfree(*buf); - return ret; -} -#endif + /* Callers that do fh_verify should do the fh_want_write: */ + get_write_count = !fhp->fh_dentry; -#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); + } + + dentry = fhp->fh_dentry; + inode = dentry->d_inode; - len = posix_acl_to_xattr(pacl, buf, buflen); - if (len < 0) { - error = len; + /* 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; } - error = vfs_setxattr(dentry, key, buf, len, 0); + iap->ia_valid |= ATTR_CTIME; + + if (check_guard && guardtime != inode->i_ctime.tv_sec) { + err = nfserr_notsync; + goto out_put_write_access; + } + + 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 */, 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); + 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); } - -static struct posix_acl * -_get_posix_acl(struct dentry *dentry, char *key) +#else +__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct xdr_netobj *label) { - 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; -} - -int -nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_acl **acl) -{ - 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_NFSD_V4) */ @@ -698,18 +628,27 @@ 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; @@ -721,19 +660,28 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, * 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 | NFSD_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 & NFSD_MAY_WRITE)) + if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE)) goto out; /* * We must ignore files (but only files) which might have mandatory @@ -746,29 +694,29 @@ 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. - */ - if (!(access & NFSD_MAY_NOT_BREAK_LEASE)) - host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? O_WRONLY : 0)); - if (host_err == -EWOULDBLOCK) - host_err = -ETIMEDOUT; + host_err = nfsd_open_break_lease(inode, may_flags); if (host_err) /* NOMEM or WOULDBLOCK */ goto out_nfserr; - if (access & NFSD_MAY_WRITE) { - if (access & NFSD_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; } - *filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_path.mnt), - flags, current_cred()); - if (IS_ERR(*filp)) + *filp = dentry_open(&path, flags, current_cred()); + if (IS_ERR(*filp)) { host_err = PTR_ERR(*filp); - else - host_err = ima_file_check(*filp, access); + *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: @@ -809,7 +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; @@ -842,30 +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; @@ -879,66 +820,54 @@ 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 -} - -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; - mm_segment_t oldfs; - __be32 err; - int host_err; - - err = nfserr_perm; - inode = file->f_path.dentry->d_inode; - - if (svc_msnfs(fhp) && !lock_may_read(inode, offset, *count)) - goto out; - - 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); - host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset); - set_fs(oldfs); - } - if (host_err >= 0) { nfsdstats.io_read += host_err; *count = host_err; - err = 0; fsnotify_access(file); + return 0; } else - err = nfserrno(host_err); -out: - return err; + return nfserrno(host_err); } -static void kill_suid(struct dentry *dentry) +int nfsd_splice_read(struct svc_rqst *rqstp, + struct file *file, loff_t offset, unsigned long *count) { - struct iattr ia; - ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; + struct splice_desc sd = { + .len = 0, + .total_len = *count, + .pos = offset, + .u.data = rqstp, + }; + int host_err; - mutex_lock(&dentry->d_inode->i_mutex); - notify_change(dentry, &ia); - mutex_unlock(&dentry->d_inode->i_mutex); + 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); +} + +int nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen, + unsigned long *count) +{ + mm_segment_t oldfs; + int host_err; + + 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); +} + +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); } /* @@ -957,7 +886,7 @@ static void kill_suid(struct dentry *dentry) */ static int wait_for_concurrent_writes(struct file *file) { - struct inode *inode = file->f_path.dentry->d_inode; + struct inode *inode = file_inode(file); static ino_t last_ino; static dev_t last_dev; int err = 0; @@ -991,45 +920,30 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, 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 NFSv2 gathered writes have been configured for this volume, - * flushing the data to disk is handled separately below. - */ use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp); - if (!file->f_op->fsync) {/* COMMIT3 cannot work */ - stable = 2; - *stablep = 2; /* FILE_SYNC */ - } - if (!EX_ISSYNC(exp)) stable = 0; - if (stable && !use_wgather) { - spin_lock(&file->f_lock); - file->f_flags |= O_SYNC; - spin_unlock(&file->f_lock); - } /* Write the data. */ oldfs = get_fs(); set_fs(KERNEL_DS); - host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset); + host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos); set_fs(oldfs); if (host_err < 0) goto out_nfserr; @@ -1037,12 +951,12 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, nfsdstats.io_write += host_err; fsnotify_modify(file); - /* clear setuid/setgid flag after write */ - if (inode->i_mode & (S_ISUID | S_ISGID)) - kill_suid(dentry); - - if (stable && use_wgather) - host_err = wait_for_concurrent_writes(file); + 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); @@ -1050,37 +964,33 @@ out_nfserr: err = 0; else err = nfserrno(host_err); -out: + if (rqstp->rq_local) + tsk_restore_flags(current, pflags, PF_LESS_THROTTLE); return err; } -/* - * 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, - loff_t offset, struct kvec *vec, int vlen, unsigned long *count) +__be32 nfsd_get_tmp_read_open(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct file **file, struct raparms **ra) { - struct file *file; struct inode *inode; - struct raparms *ra; __be32 err; - err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file); + err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, file); if (err) return err; - inode = file->f_path.dentry->d_inode; + 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; + *ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino); - err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count); + 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]; @@ -1090,28 +1000,29 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, ra->p_count--; spin_unlock(&rab->pb_lock); } - nfsd_close(file); - return err; } -/* As above, but use the provided file descriptor. */ -__be32 -nfsd_read_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, - loff_t offset, struct kvec *vec, int vlen, - unsigned long *count) +/* + * 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, + 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, - NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE); - if (err) - goto out; - err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count); - } else /* Note file may still be NULL in NFSv4 special stateid case: */ - err = nfsd_read(rqstp, fhp, offset, vec, vlen, count); -out: return err; } @@ -1206,7 +1117,7 @@ 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); @@ -1269,6 +1180,10 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, * 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); @@ -1284,9 +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; } @@ -1296,8 +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; } @@ -1312,17 +1226,14 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, 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 = 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; @@ -1336,10 +1247,8 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev); break; } - if (host_err < 0) { - mnt_drop_write(fhp->fh_export->ex_path.mnt); + if (host_err < 0) goto out_nfserr; - } err = nfsd_create_setattr(rqstp, resfhp, iap); @@ -1351,7 +1260,6 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, err2 = nfserrno(commit_metadata(fhp)); if (err2) err = err2; - mnt_drop_write(fhp->fh_export->ex_path.mnt); /* * Update the file handle to get the new inode info. */ @@ -1368,14 +1276,21 @@ 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; @@ -1391,7 +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, NFSD_MAY_CREATE); + err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC); if (err) goto out; @@ -1403,6 +1318,11 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, err = nfserr_notdir; 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); /* @@ -1413,11 +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 @@ -1428,16 +1355,13 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, v_atime = verifier[1]&0x7fffffff; } - host_err = mnt_want_write(fhp->fh_export->ex_path.mnt); - if (host_err) - goto out_nfserr; if (dchild->d_inode) { err = 0; 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 @@ -1456,19 +1380,30 @@ 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; } - mnt_drop_write(fhp->fh_export->ex_path.mnt); + fh_drop_write(fhp); goto out; } - host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL); + host_err = vfs_create(dirp, dchild, iap->ia_mode, true); if (host_err < 0) { - mnt_drop_write(fhp->fh_export->ex_path.mnt); + fh_drop_write(fhp); goto out_nfserr; } if (created) @@ -1476,7 +1411,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, 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; @@ -1496,7 +1431,6 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, if (!err) err = nfserrno(commit_metadata(fhp)); - mnt_drop_write(fhp->fh_export->ex_path.mnt); /* * Update the filehandle to get the new inode info. */ @@ -1507,6 +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: @@ -1523,30 +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, 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->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) @@ -1586,6 +1522,11 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, 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); @@ -1593,10 +1534,6 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, if (IS_ERR(dnew)) goto out_nfserr; - 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) @@ -1614,7 +1551,7 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, err = nfserrno(commit_metadata(fhp)); fh_unlock(fhp); - mnt_drop_write(fhp->fh_export->ex_path.mnt); + fh_drop_write(fhp); cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp); dput(dnew); @@ -1643,10 +1580,12 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_CREATE); if (err) goto out; - err = fh_verify(rqstp, tfhp, -S_IFDIR, NFSD_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; @@ -1654,6 +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; @@ -1665,12 +1610,10 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, dold = tfhp->fh_dentry; - host_err = mnt_want_write(tfhp->fh_export->ex_path.mnt); - if (host_err) { - err = nfserrno(host_err); + err = nfserr_noent; + if (!dold->d_inode) goto out_dput; - } - host_err = vfs_link(dold, dirp, dnew); + host_err = vfs_link(dold, dirp, dnew, NULL); if (!host_err) { err = nfserrno(commit_metadata(ffhp)); if (!err) @@ -1681,11 +1624,11 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, else err = nfserrno(host_err); } - mnt_drop_write(tfhp->fh_export->ex_path.mnt); out_dput: dput(dnew); out_unlock: fh_unlock(ffhp); + fh_drop_write(tfhp); out: return err; @@ -1720,14 +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); @@ -1755,44 +1700,34 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (ndentry == trap) goto out_dput_new; - if (svc_msnfs(ffhp) && - ((atomic_read(&odentry->d_count) > 1) - || (atomic_read(&ndentry->d_count) > 1))) { - 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) + 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); + host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0); if (!host_err) { host_err = commit_metadata(tfhp); if (!host_err) host_err = commit_metadata(ffhp); } - - mnt_drop_write(ffhp->fh_export->ex_path.mnt); - 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; @@ -1818,6 +1753,10 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, 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; @@ -1836,28 +1775,14 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, 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)) { - 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); - } - - dput(rdentry); - if (!host_err) host_err = commit_metadata(fhp); + dput(rdentry); - mnt_drop_write(fhp->fh_export->ex_path.mnt); out_nfserr: err = nfserrno(host_err); out: @@ -1880,6 +1805,7 @@ struct buffered_dirent { }; struct readdir_data { + struct dir_context ctx; char *dirent; size_t used; int full; @@ -1911,27 +1837,29 @@ static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen, 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; + struct readdir_data buf = { + .ctx.actor = nfsd_buffered_filldir, + .dirent = (void *)__get_free_page(GFP_KERNEL) + }; - 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; + 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 = vfs_readdir(file, nfsd_buffered_filldir, &buf); + host_err = iterate_dir(file, &buf.ctx); if (buf.full) host_err = 0; @@ -1995,12 +1923,17 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, __be32 err; struct file *file; loff_t offset = *offsetp; + int may_flags = NFSD_MAY_READ; - err = nfsd_open(rqstp, fhp, S_IFDIR, NFSD_MAY_READ, &file); + /* 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_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; @@ -2052,7 +1985,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, struct inode *inode = dentry->d_inode; int err; - if (acc == NFSD_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", @@ -2112,7 +2045,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, * with NFSv3. */ if ((acc & NFSD_MAY_OWNER_OVERRIDE) && - inode->i_uid == current_fsuid()) + uid_eq(inode->i_uid, current_fsuid())) return 0; /* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */ @@ -2120,7 +2053,8 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, /* Allow read access to binaries even when mode 111 */ if (err == -EACCES && S_ISREG(inode->i_mode) && - acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE)) + (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; @@ -2186,93 +2120,3 @@ out_nomem: nfsd_racache_shutdown(); return -ENOMEM; } - -#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->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; - - 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 { - 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; - } - } - mnt_drop_write(fhp->fh_export->ex_path.mnt); - -getout: - kfree(value); - return error; -} -#endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ |