X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fnfsd%2Fvfs.c;h=8afdba5082e883e254d3852cea99d34e16361d30;hb=8d75da8afd068fa58b35e69c7c8c46770d9e7a98;hp=9609eb51d727147ac745f4d89f3e2110dae222ae;hpb=6c6a426fdcb374b7641d7cf9eea88410828b9d9a;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 9609eb5..8afdba5 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1,7 +1,5 @@ #define MSNFS /* HACK HACK */ /* - * linux/fs/nfsd/vfs.c - * * File operations used by nfsd. Some of these have been ripped from * other parts of the kernel because they weren't exported, others * are partial duplicates with added or changed functionality. @@ -16,47 +14,33 @@ * Zerocpy NFS support (C) 2002 Hirokazu Takahashi */ -#include -#include -#include #include #include -#include -#include #include -#include -#include #include -#include -#include -#include -#include -#include -#include #include -#include #include -#include -#include -#ifdef CONFIG_NFSD_V3 -#include -#include -#endif /* CONFIG_NFSD_V3 */ -#include #include #include -#include #include #include +#include +#include +#include +#include +#include + +#ifdef CONFIG_NFSD_V3 +#include "xdr3.h" +#endif /* CONFIG_NFSD_V3 */ + #ifdef CONFIG_NFSD_V4 -#include #include #include -#include #endif /* CONFIG_NFSD_V4 */ -#include -#include +#include "nfsd.h" +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_FILEOP @@ -100,35 +84,95 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, { struct svc_export *exp = *expp, *exp2 = NULL; struct dentry *dentry = *dpp; - struct vfsmount *mnt = mntget(exp->ex_path.mnt); - struct dentry *mounts = dget(dentry); + struct path path = {.mnt = mntget(exp->ex_path.mnt), + .dentry = dget(dentry)}; int err = 0; - while (follow_down(&mnt,&mounts)&&d_mountpoint(mounts)); + while (d_mountpoint(path.dentry) && follow_down(&path)) + ; - exp2 = rqst_exp_get_by_name(rqstp, mnt, mounts); + exp2 = rqst_exp_get_by_name(rqstp, &path); if (IS_ERR(exp2)) { - if (PTR_ERR(exp2) != -ENOENT) - err = PTR_ERR(exp2); - dput(mounts); - mntput(mnt); + err = PTR_ERR(exp2); + /* + * We normally allow NFS clients to continue + * "underneath" a mountpoint that is not exported. + * The exception is V4ROOT, where no traversal is ever + * allowed without an explicit export of the new + * directory. + */ + if (err == -ENOENT && !(exp->ex_flags & NFSEXP_V4ROOT)) + err = 0; + path_put(&path); goto out; } - if ((exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) { + if (nfsd_v4client(rqstp) || + (exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) { /* successfully crossed mount point */ - exp_put(exp); + /* + * This is subtle: path.dentry is *not* on path.mnt + * at this point. The only reason we are safe is that + * original mnt is pinned down by exp, so we should + * put path *before* putting exp + */ + *dpp = path.dentry; + path.dentry = dentry; *expp = exp2; - dput(dentry); - *dpp = mounts; - } else { - exp_put(exp2); - dput(mounts); + exp2 = exp; } - mntput(mnt); + path_put(&path); + exp_put(exp2); out: return err; } +static void follow_to_parent(struct path *path) +{ + struct dentry *dp; + + while (path->dentry == path->mnt->mnt_root && follow_up(path)) + ; + dp = dget_parent(path->dentry); + dput(path->dentry); + path->dentry = dp; +} + +static int nfsd_lookup_parent(struct svc_rqst *rqstp, struct dentry *dparent, struct svc_export **exp, struct dentry **dentryp) +{ + struct svc_export *exp2; + struct path path = {.mnt = mntget((*exp)->ex_path.mnt), + .dentry = dget(dparent)}; + + follow_to_parent(&path); + + exp2 = rqst_exp_parent(rqstp, &path); + if (PTR_ERR(exp2) == -ENOENT) { + *dentryp = dget(dparent); + } else if (IS_ERR(exp2)) { + path_put(&path); + return PTR_ERR(exp2); + } else { + *dentryp = dget(path.dentry); + exp_put(*exp); + *exp = exp2; + } + path_put(&path); + return 0; +} + +/* + * For nfsd purposes, we treat V4ROOT exports as though there was an + * export at *every* directory. + */ +int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp) +{ + if (d_mountpoint(dentry)) + return 1; + if (!(exp->ex_flags & NFSEXP_V4ROOT)) + return 0; + return dentry->d_inode != NULL; +} + __be32 nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, unsigned int len, @@ -157,34 +201,13 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, dentry = dget(dparent); else if (dparent != exp->ex_path.dentry) dentry = dget_parent(dparent); - else if (!EX_NOHIDE(exp)) + else if (!EX_NOHIDE(exp) && !nfsd_v4client(rqstp)) dentry = dget(dparent); /* .. == . just like at / */ else { /* checking mountpoint crossing is very different when stepping up */ - struct svc_export *exp2 = NULL; - struct dentry *dp; - struct vfsmount *mnt = mntget(exp->ex_path.mnt); - dentry = dget(dparent); - while(dentry == mnt->mnt_root && follow_up(&mnt, &dentry)) - ; - dp = dget_parent(dentry); - dput(dentry); - dentry = dp; - - exp2 = rqst_exp_parent(rqstp, mnt, dentry); - if (PTR_ERR(exp2) == -ENOENT) { - dput(dentry); - dentry = dget(dparent); - } else if (IS_ERR(exp2)) { - host_err = PTR_ERR(exp2); - dput(dentry); - mntput(mnt); + host_err = nfsd_lookup_parent(rqstp, dparent, &exp, &dentry); + if (host_err) goto out_nfserr; - } else { - exp_put(exp); - exp = exp2; - } - mntput(mnt); } } else { fh_lock(fhp); @@ -195,7 +218,7 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, /* * check if we have crossed a mount point ... */ - if (d_mountpoint(dentry)) { + if (nfsd_mountpoint(dentry, exp)) { if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) { dput(dentry); goto out_nfserr; @@ -250,6 +273,32 @@ out: return err; } +/* + * Commit metadata changes to stable storage. + */ +static int +commit_metadata(struct svc_fh *fhp) +{ + struct inode *inode = fhp->fh_dentry->d_inode; + const struct export_operations *export_ops = inode->i_sb->s_export_op; + int error = 0; + + if (!EX_ISSYNC(fhp->fh_export)) + return 0; + + if (export_ops->commit_metadata) { + error = export_ops->commit_metadata(inode); + } else { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, /* metadata only */ + }; + + error = sync_inode(inode, &wbc); + } + + return error; +} /* * Set various file attributes. @@ -356,7 +405,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, put_write_access(inode); goto out_nfserr; } - DQUOT_INIT(inode); + vfs_dq_init(inode); } /* sanitize the mode change */ @@ -366,8 +415,9 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, } /* Revoke setuid/setgid on chown */ - if (((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) || - ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)) { + 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 */ @@ -677,6 +727,8 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, __be32 err; int host_err; + validate_process_creds(); + /* * If we get here, then the client has already done an "open", * and (hopefully) checked permission - so allow OWNER_OVERRIDE @@ -722,15 +774,16 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, else flags = O_WRONLY|O_LARGEFILE; - DQUOT_INIT(inode); + vfs_dq_init(inode); } *filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_path.mnt), - flags); + flags, current_cred()); if (IS_ERR(*filp)) host_err = PTR_ERR(*filp); out_nfserr: err = nfserrno(host_err); out: + validate_process_creds(); return err; } @@ -744,47 +797,6 @@ nfsd_close(struct file *filp) } /* - * Sync a file - * As this calls fsync (not fdatasync) there is no need for a write_inode - * after it. - */ -static inline int nfsd_dosync(struct file *filp, struct dentry *dp, - const struct file_operations *fop) -{ - struct inode *inode = dp->d_inode; - int (*fsync) (struct file *, struct dentry *, int); - int err; - - err = filemap_fdatawrite(inode->i_mapping); - if (err == 0 && fop && (fsync = fop->fsync)) - err = fsync(filp, dp, 0); - if (err == 0) - err = filemap_fdatawait(inode->i_mapping); - - return err; -} - - -static int -nfsd_sync(struct file *filp) -{ - int err; - struct inode *inode = filp->f_path.dentry->d_inode; - dprintk("nfsd: sync file %s\n", filp->f_path.dentry->d_name.name); - mutex_lock(&inode->i_mutex); - err=nfsd_dosync(filp, filp->f_path.dentry, filp->f_op); - mutex_unlock(&inode->i_mutex); - - return err; -} - -int -nfsd_sync_dir(struct dentry *dp) -{ - return nfsd_dosync(NULL, dp, dp->d_inode->i_fop); -} - -/* * Obtain the readahead parameters for the file * specified by (dev, ino). */ @@ -957,10 +969,47 @@ static void kill_suid(struct dentry *dentry) mutex_unlock(&dentry->d_inode->i_mutex); } +/* + * Gathered writes: If another process is currently writing to the file, + * there's a high chance this is another nfsd (triggered by a bulk write + * from a client's biod). Rather than syncing the file with each write + * request, we sleep for 10 msec. + * + * I don't know if this roughly approximates C. Juszak's idea of + * gathered writes, but it's a nice and simple solution (IMHO), and it + * seems to work:-) + * + * Note: we do this only in the NFSv2 case, since v3 and higher have a + * better tool (separate unstable writes and commits) for solving this + * problem. + */ +static int wait_for_concurrent_writes(struct file *file) +{ + struct inode *inode = file->f_path.dentry->d_inode; + static ino_t last_ino; + static dev_t last_dev; + int err = 0; + + if (atomic_read(&inode->i_writecount) > 1 + || (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) { + dprintk("nfsd: write defer %d\n", task_pid_nr(current)); + msleep(10); + dprintk("nfsd: write resume %d\n", task_pid_nr(current)); + } + + if (inode->i_state & I_DIRTY) { + dprintk("nfsd: write sync %d\n", task_pid_nr(current)); + err = vfs_fsync(file, file->f_path.dentry, 0); + } + last_ino = inode->i_ino; + last_dev = inode->i_sb->s_dev; + return err; +} + static __be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, struct kvec *vec, int vlen, - unsigned long cnt, int *stablep) + unsigned long *cnt, int *stablep) { struct svc_export *exp; struct dentry *dentry; @@ -969,12 +1018,13 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, __be32 err = 0; int host_err; int stable = *stablep; + int use_wgather; #ifdef MSNFS err = nfserr_perm; if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) && - (!lock_may_write(file->f_path.dentry->d_inode, offset, cnt))) + (!lock_may_write(file->f_path.dentry->d_inode, offset, *cnt))) goto out; #endif @@ -987,9 +1037,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, * - the sync export option has been set, or * - the client requested O_SYNC behavior (NFSv3 feature). * - The file system doesn't support fsync(). - * When gathered writes have been configured for this volume, + * When NFSv2 gathered writes have been configured for this volume, * flushing the data to disk is handled separately below. */ + use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp); if (!file->f_op->fsync) {/* COMMIT3 cannot work */ stable = 2; @@ -998,62 +1049,34 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (!EX_ISSYNC(exp)) stable = 0; - if (stable && !EX_WGATHER(exp)) + if (stable && !use_wgather) { + spin_lock(&file->f_lock); file->f_flags |= O_SYNC; + spin_unlock(&file->f_lock); + } /* Write the data. */ oldfs = get_fs(); set_fs(KERNEL_DS); host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset); set_fs(oldfs); - if (host_err >= 0) { - nfsdstats.io_write += cnt; - fsnotify_modify(file->f_path.dentry); - } + if (host_err < 0) + goto out_nfserr; + *cnt = host_err; + nfsdstats.io_write += host_err; + fsnotify_modify(file->f_path.dentry); /* clear setuid/setgid flag after write */ - if (host_err >= 0 && (inode->i_mode & (S_ISUID | S_ISGID))) + if (inode->i_mode & (S_ISUID | S_ISGID)) kill_suid(dentry); - if (host_err >= 0 && stable) { - static ino_t last_ino; - static dev_t last_dev; - - /* - * Gathered writes: If another process is currently - * writing to the file, there's a high chance - * this is another nfsd (triggered by a bulk write - * from a client's biod). Rather than syncing the - * file with each write request, we sleep for 10 msec. - * - * I don't know if this roughly approximates - * C. Juszak's idea of gathered writes, but it's a - * nice and simple solution (IMHO), and it seems to - * work:-) - */ - if (EX_WGATHER(exp)) { - if (atomic_read(&inode->i_writecount) > 1 - || (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) { - dprintk("nfsd: write defer %d\n", task_pid_nr(current)); - msleep(10); - dprintk("nfsd: write resume %d\n", task_pid_nr(current)); - } - - if (inode->i_state & I_DIRTY) { - dprintk("nfsd: write sync %d\n", task_pid_nr(current)); - host_err=nfsd_sync(file); - } -#if 0 - wake_up(&inode->i_wait); -#endif - } - last_ino = inode->i_ino; - last_dev = inode->i_sb->s_dev; - } + if (stable && use_wgather) + host_err = wait_for_concurrent_writes(file); +out_nfserr: dprintk("nfsd: write complete host_err=%d\n", host_err); if (host_err >= 0) err = 0; - else + else err = nfserrno(host_err); out: return err; @@ -1095,7 +1118,7 @@ out: */ __be32 nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, - loff_t offset, struct kvec *vec, int vlen, unsigned long cnt, + loff_t offset, struct kvec *vec, int vlen, unsigned long *cnt, int *stablep) { __be32 err = 0; @@ -1124,8 +1147,9 @@ out: #ifdef CONFIG_NFSD_V3 /* * Commit all pending writes to stable storage. - * Strictly speaking, we could sync just the indicated file region here, - * but there's currently no way we can ask the VFS to do so. + * + * Note: we only guarantee that data that lies within the range specified + * by the 'offset' and 'count' parameters will be synced. * * Unfortunately we cannot lock the file to make sure we return full WCC * data to the client, as locking happens lower down in the filesystem. @@ -1135,23 +1159,32 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset, unsigned long count) { struct file *file; - __be32 err; + loff_t end = LLONG_MAX; + __be32 err = nfserr_inval; - if ((u64)count > ~(u64)offset) - return nfserr_inval; + if (offset < 0) + goto out; + if (count != 0) { + end = offset + (loff_t)count - 1; + if (end < offset) + goto out; + } err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file); if (err) - return err; + goto out; if (EX_ISSYNC(fhp->fh_export)) { - if (file->f_op && file->f_op->fsync) { - err = nfserrno(nfsd_sync(file)); - } else { + int err2 = vfs_fsync_range(file, file->f_path.dentry, + offset, end, 0); + + if (err2 != -EINVAL) + err = nfserrno(err2); + else err = nfserr_notsupp; - } } nfsd_close(file); +out: return err; } #endif /* CONFIG_NFSD_V3 */ @@ -1169,13 +1202,28 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp, * send along the gid on create when it tries to implement * setgid directories via NFS: */ - if (current->fsuid != 0) + if (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. @@ -1210,7 +1258,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, dirp = dentry->d_inode; err = nfserr_notdir; - if(!dirp->i_op || !dirp->i_op->lookup) + if (!dirp->i_op->lookup) goto out; /* * Check whether the response file handle has been verified yet. @@ -1271,6 +1319,8 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, switch (type) { case S_IFREG: host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL); + if (!host_err) + nfsd_check_ignore_resizing(iap); break; case S_IFDIR: host_err = vfs_mkdir(dirp, dchild, iap->ia_mode); @@ -1287,12 +1337,14 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_nfserr; } - if (EX_ISSYNC(fhp->fh_export)) { - err = nfserrno(nfsd_sync_dir(dentry)); - write_inode_now(dchild->d_inode, 1); - } + err = nfsd_create_setattr(rqstp, resfhp, iap); - err2 = nfsd_create_setattr(rqstp, resfhp, iap); + /* + * nfsd_setattr already committed the child. Transactional filesystems + * had a chance to commit changes for both parent and child + * simultaneously making the following commit_metadata a noop. + */ + err2 = nfserrno(commit_metadata(fhp)); if (err2) err = err2; mnt_drop_write(fhp->fh_export->ex_path.mnt); @@ -1324,7 +1376,6 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, struct dentry *dentry, *dchild = NULL; struct inode *dirp; __be32 err; - __be32 err2; int host_err; __u32 v_mtime=0, v_atime=0; @@ -1346,7 +1397,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, /* Get all the sanity checks out of the way before * we lock the parent. */ err = nfserr_notdir; - if(!dirp->i_op || !dirp->i_op->lookup) + if (!dirp->i_op->lookup) goto out; fh_lock_nested(fhp, I_MUTEX_PARENT); @@ -1419,10 +1470,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, 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 */ @@ -1436,9 +1484,13 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, } set_attr: - err2 = nfsd_create_setattr(rqstp, resfhp, iap); - if (err2) - err = err2; + err = nfsd_create_setattr(rqstp, resfhp, iap); + + /* + * nfsd_setattr already committed the child (and possibly also the parent). + */ + if (!err) + err = nfserrno(commit_metadata(fhp)); mnt_drop_write(fhp->fh_export->ex_path.mnt); /* @@ -1481,7 +1533,7 @@ nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp) 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_path.mnt, dentry); @@ -1553,12 +1605,9 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, } } else host_err = vfs_symlink(dentry->d_inode, dnew, path); - - if (!host_err) { - if (EX_ISSYNC(fhp->fh_export)) - host_err = nfsd_sync_dir(dentry); - } err = nfserrno(host_err); + if (!err) + err = nfserrno(commit_metadata(fhp)); fh_unlock(fhp); mnt_drop_write(fhp->fh_export->ex_path.mnt); @@ -1620,11 +1669,9 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, } host_err = vfs_link(dold, dirp, dnew); if (!host_err) { - if (EX_ISSYNC(ffhp->fh_export)) { - err = nfserrno(nfsd_sync_dir(ddir)); - write_inode_now(dest, 1); - } - err = 0; + err = nfserrno(commit_metadata(ffhp)); + if (!err) + err = nfserrno(commit_metadata(tfhp)); } else { if (host_err == -EXDEV && rqstp->rq_vers == 2) err = nfserr_acces; @@ -1720,10 +1767,10 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, goto out_dput_new; host_err = vfs_rename(fdir, odentry, tdir, ndentry); - if (!host_err && EX_ISSYNC(tfhp->fh_export)) { - host_err = nfsd_sync_dir(tdentry); + if (!host_err) { + host_err = commit_metadata(tfhp); if (!host_err) - host_err = nfsd_sync_dir(fdentry); + host_err = commit_metadata(ffhp); } mnt_drop_write(ffhp->fh_export->ex_path.mnt); @@ -1804,12 +1851,9 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, dput(rdentry); - if (host_err) - goto out_drop; - if (EX_ISSYNC(fhp->fh_export)) - host_err = nfsd_sync_dir(dentry); + if (!host_err) + host_err = commit_metadata(fhp); -out_drop: mnt_drop_write(fhp->fh_export->ex_path.mnt); out_nfserr: err = nfserrno(host_err); @@ -1818,6 +1862,126 @@ out: } /* + * We do this buffering because we must not call back into the file + * system's ->lookup() method from the filldir callback. That may well + * deadlock a number of file systems. + * + * This is based heavily on the implementation of same in XFS. + */ +struct buffered_dirent { + u64 ino; + loff_t offset; + int namlen; + unsigned int d_type; + char name[]; +}; + +struct readdir_data { + 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. */ @@ -1826,7 +1990,6 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, struct readdir_cd *cdp, filldir_t func) { __be32 err; - int host_err; struct file *file; loff_t offset = *offsetp; @@ -1840,21 +2003,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, goto out_close; } - /* - * Read the directory entries. This silly loop is necessary because - * readdir() is not guaranteed to fill up the entire buffer, but - * may choose to do less. - */ - - do { - cdp->err = nfserr_eof; /* will be cleared on successful read */ - host_err = vfs_readdir(file, func, cdp); - } while (host_err >=0 && cdp->err == nfs_ok); - if (host_err) - err = nfserrno(host_err); - else - err = cdp->err; - *offsetp = vfs_llseek(file, 0, 1); + err = nfsd_buffered_readdir(file, func, cdp, offsetp); if (err == nfserr_eof || err == nfserr_toosmall) err = nfs_ok; /* can still be found in ->err */ @@ -1890,6 +2039,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, struct dentry *dentry, int acc) { struct inode *inode = dentry->d_inode; + struct path path; int err; if (acc == NFSD_MAY_NOP) @@ -1909,7 +2059,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, IS_APPEND(inode)? " append" : "", __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 @@ -1952,7 +2102,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, * with NFSv3. */ if ((acc & NFSD_MAY_OWNER_OVERRIDE) && - inode->i_uid == current->fsuid) + inode->i_uid == current_fsuid()) return 0; /* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */ @@ -1962,7 +2112,16 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, if (err == -EACCES && S_ISREG(inode->i_mode) && acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE)) err = inode_permission(inode, MAY_EXEC); + if (err) + goto nfsd_out; + /* Do integrity (permission) checking now, but defer incrementing + * IMA counts to the actual file open. + */ + path.mnt = exp->ex_path.mnt; + path.dentry = dentry; + err = ima_path_check(&path, acc & (MAY_READ | MAY_WRITE | MAY_EXEC)); +nfsd_out: return err? nfserrno(err) : 0; } @@ -2069,7 +2228,7 @@ nfsd_set_posix_acl(struct svc_fh *fhp, int type, struct posix_acl *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) {