diff options
| -rw-r--r-- | Documentation/filesystems/overlayfs.rst | 44 | ||||
| -rw-r--r-- | MAINTAINERS | 1 | ||||
| -rw-r--r-- | fs/overlayfs/Makefile | 2 | ||||
| -rw-r--r-- | fs/overlayfs/copy_up.c | 11 | ||||
| -rw-r--r-- | fs/overlayfs/dir.c | 9 | ||||
| -rw-r--r-- | fs/overlayfs/export.c | 41 | ||||
| -rw-r--r-- | fs/overlayfs/file.c | 21 | ||||
| -rw-r--r-- | fs/overlayfs/inode.c | 73 | ||||
| -rw-r--r-- | fs/overlayfs/namei.c | 201 | ||||
| -rw-r--r-- | fs/overlayfs/overlayfs.h | 106 | ||||
| -rw-r--r-- | fs/overlayfs/ovl_entry.h | 91 | ||||
| -rw-r--r-- | fs/overlayfs/params.c | 389 | ||||
| -rw-r--r-- | fs/overlayfs/readdir.c | 19 | ||||
| -rw-r--r-- | fs/overlayfs/super.c | 907 | ||||
| -rw-r--r-- | fs/overlayfs/util.c | 179 |
15 files changed, 1390 insertions, 704 deletions
diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst index 4c76fda07645..eb7d2c88ddec 100644 --- a/Documentation/filesystems/overlayfs.rst +++ b/Documentation/filesystems/overlayfs.rst @@ -231,12 +231,11 @@ Mount options: Redirects are enabled. - "redirect_dir=follow": Redirects are not created, but followed. -- "redirect_dir=off": - Redirects are not created and only followed if "redirect_always_follow" - feature is enabled in the kernel/module config. - "redirect_dir=nofollow": - Redirects are not created and not followed (equivalent to "redirect_dir=off" - if "redirect_always_follow" feature is not enabled). + Redirects are not created and not followed. +- "redirect_dir=off": + If "redirect_always_follow" is enabled in the kernel/module config, + this "off" traslates to "follow", otherwise it translates to "nofollow". When the NFS export feature is enabled, every copied up directory is indexed by the file handle of the lower inode and a file handle of the @@ -371,6 +370,41 @@ conflict with metacopy=on, and will result in an error. [*] redirect_dir=follow only conflicts with metacopy=on if upperdir=... is given. + +Data-only lower layers +---------------------- + +With "metacopy" feature enabled, an overlayfs regular file may be a composition +of information from up to three different layers: + + 1) metadata from a file in the upper layer + + 2) st_ino and st_dev object identifier from a file in a lower layer + + 3) data from a file in another lower layer (further below) + +The "lower data" file can be on any lower layer, except from the top most +lower layer. + +Below the top most lower layer, any number of lower most layers may be defined +as "data-only" lower layers, using double colon ("::") separators. +A normal lower layer is not allowed to be below a data-only layer, so single +colon separators are not allowed to the right of double colon ("::") separators. + + +For example: + + mount -t overlay overlay -olowerdir=/l1:/l2:/l3::/do1::/do2 /merged + +The paths of files in the "data-only" lower layers are not visible in the +merged overlayfs directories and the metadata and st_ino/st_dev of files +in the "data-only" lower layers are not visible in overlayfs inodes. + +Only the data of the files in the "data-only" lower layers may be visible +when a "metacopy" file in one of the lower layers above it, has a "redirect" +to the absolute path of the "lower data" file in the "data-only" lower layer. + + Sharing and copying layers -------------------------- diff --git a/MAINTAINERS b/MAINTAINERS index efdcc8fef84a..06285577795e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15937,6 +15937,7 @@ F: include/media/i2c/ov2659.h OVERLAY FILESYSTEM M: Miklos Szeredi <miklos@szeredi.hu> +M: Amir Goldstein <amir73il@gmail.com> L: linux-unionfs@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs.git diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile index 9164c585eb2f..4e173d56b11f 100644 --- a/fs/overlayfs/Makefile +++ b/fs/overlayfs/Makefile @@ -6,4 +6,4 @@ obj-$(CONFIG_OVERLAY_FS) += overlay.o overlay-objs := super.o namei.o util.o inode.o file.o dir.o readdir.o \ - copy_up.o export.o + copy_up.o export.o params.o diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index f658cc8ea492..568f743a5584 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -575,6 +575,7 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c) /* Restore timestamps on parent (best effort) */ ovl_set_timestamps(ofs, upperdir, &c->pstat); ovl_dentry_set_upper_alias(c->dentry); + ovl_dentry_update_reval(c->dentry, upper); } } inode_unlock(udir); @@ -894,6 +895,7 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) inode_unlock(udir); ovl_dentry_set_upper_alias(c->dentry); + ovl_dentry_update_reval(c->dentry, ovl_dentry_upper(c->dentry)); } out: @@ -1071,6 +1073,15 @@ static int ovl_copy_up_flags(struct dentry *dentry, int flags) if (WARN_ON(disconnected && d_is_dir(dentry))) return -EIO; + /* + * We may not need lowerdata if we are only doing metacopy up, but it is + * not very important to optimize this case, so do lazy lowerdata lookup + * before any copy up, so we can do it before taking ovl_inode_lock(). + */ + err = ovl_maybe_lookup_lowerdata(dentry); + if (err) + return err; + old_cred = ovl_override_creds(dentry->d_sb); while (!err) { struct dentry *next; diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index fc25fb95d5fc..033fc0458a3d 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -83,7 +83,7 @@ static struct dentry *ovl_whiteout(struct ovl_fs *ofs) ofs->whiteout = whiteout; } - if (ofs->share_whiteout) { + if (!ofs->no_shared_whiteout) { whiteout = ovl_lookup_temp(ofs, workdir); if (IS_ERR(whiteout)) goto out; @@ -95,7 +95,7 @@ static struct dentry *ovl_whiteout(struct ovl_fs *ofs) if (err != -EMLINK) { pr_warn("Failed to link whiteout - disabling whiteout inode sharing(nlink=%u, err=%i)\n", ofs->whiteout->d_inode->i_nlink, err); - ofs->share_whiteout = false; + ofs->no_shared_whiteout = true; } dput(whiteout); } @@ -269,8 +269,7 @@ static int ovl_instantiate(struct dentry *dentry, struct inode *inode, ovl_dir_modified(dentry->d_parent, false); ovl_dentry_set_upper_alias(dentry); - ovl_dentry_update_reval(dentry, newdentry, - DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE); + ovl_dentry_init_reval(dentry, newdentry, NULL); if (!hardlink) { /* @@ -953,7 +952,7 @@ static bool ovl_type_merge_or_lower(struct dentry *dentry) static bool ovl_can_move(struct dentry *dentry) { - return ovl_redirect_dir(dentry->d_sb) || + return ovl_redirect_dir(OVL_FS(dentry->d_sb)) || !d_is_dir(dentry) || !ovl_type_merge_or_lower(dentry); } diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index defd4e231ad2..35680b6e175b 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -80,7 +80,7 @@ static int ovl_connectable_layer(struct dentry *dentry) /* We can get overlay root from root of any layer */ if (dentry == dentry->d_sb->s_root) - return oe->numlower; + return ovl_numlower(oe); /* * If it's an unindexed merge dir, then it's not connectable with any @@ -91,7 +91,7 @@ static int ovl_connectable_layer(struct dentry *dentry) return 0; /* We can get upper/overlay path from indexed/lower dentry */ - return oe->lowerstack[0].layer->idx; + return ovl_lowerstack(oe)->layer->idx; } /* @@ -105,6 +105,7 @@ static int ovl_connectable_layer(struct dentry *dentry) static int ovl_connect_layer(struct dentry *dentry) { struct dentry *next, *parent = NULL; + struct ovl_entry *oe = OVL_E(dentry); int origin_layer; int err = 0; @@ -112,7 +113,7 @@ static int ovl_connect_layer(struct dentry *dentry) WARN_ON(!ovl_dentry_lower(dentry))) return -EIO; - origin_layer = OVL_E(dentry)->lowerstack[0].layer->idx; + origin_layer = ovl_lowerstack(oe)->layer->idx; if (ovl_dentry_test_flag(OVL_E_CONNECTED, dentry)) return origin_layer; @@ -285,21 +286,29 @@ static struct dentry *ovl_obtain_alias(struct super_block *sb, struct dentry *lower = lowerpath ? lowerpath->dentry : NULL; struct dentry *upper = upper_alias ?: index; struct dentry *dentry; - struct inode *inode; + struct inode *inode = NULL; struct ovl_entry *oe; struct ovl_inode_params oip = { - .lowerpath = lowerpath, .index = index, - .numlower = !!lower }; /* We get overlay directory dentries with ovl_lookup_real() */ if (d_is_dir(upper ?: lower)) return ERR_PTR(-EIO); + oe = ovl_alloc_entry(!!lower); + if (!oe) + return ERR_PTR(-ENOMEM); + oip.upperdentry = dget(upper); + if (lower) { + ovl_lowerstack(oe)->dentry = dget(lower); + ovl_lowerstack(oe)->layer = lowerpath->layer; + } + oip.oe = oe; inode = ovl_get_inode(sb, &oip); if (IS_ERR(inode)) { + ovl_free_entry(oe); dput(upper); return ERR_CAST(inode); } @@ -314,20 +323,11 @@ static struct dentry *ovl_obtain_alias(struct super_block *sb, dentry = d_alloc_anon(inode->i_sb); if (unlikely(!dentry)) goto nomem; - oe = ovl_alloc_entry(lower ? 1 : 0); - if (!oe) - goto nomem; - if (lower) { - oe->lowerstack->dentry = dget(lower); - oe->lowerstack->layer = lowerpath->layer; - } - dentry->d_fsdata = oe; if (upper_alias) ovl_dentry_set_upper_alias(dentry); - ovl_dentry_update_reval(dentry, upper, - DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE); + ovl_dentry_init_reval(dentry, upper, OVL_I_E(inode)); return d_instantiate_anon(dentry, inode); @@ -342,15 +342,16 @@ out_iput: /* Get the upper or lower dentry in stack whose on layer @idx */ static struct dentry *ovl_dentry_real_at(struct dentry *dentry, int idx) { - struct ovl_entry *oe = dentry->d_fsdata; + struct ovl_entry *oe = OVL_E(dentry); + struct ovl_path *lowerstack = ovl_lowerstack(oe); int i; if (!idx) return ovl_dentry_upper(dentry); - for (i = 0; i < oe->numlower; i++) { - if (oe->lowerstack[i].layer->idx == idx) - return oe->lowerstack[i].dentry; + for (i = 0; i < ovl_numlower(oe); i++) { + if (lowerstack[i].layer->idx == idx) + return lowerstack[i].dentry; } return NULL; diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 1f93a3ae113e..21245b00722a 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -107,14 +107,23 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real, { struct dentry *dentry = file_dentry(file); struct path realpath; + int err; real->flags = 0; real->file = file->private_data; - if (allow_meta) + if (allow_meta) { ovl_path_real(dentry, &realpath); - else + } else { + /* lazy lookup of lowerdata */ + err = ovl_maybe_lookup_lowerdata(dentry); + if (err) + return err; + ovl_path_realdata(dentry, &realpath); + } + if (!realpath.dentry) + return -EIO; /* Has it been copied up since we'd opened it? */ if (unlikely(file_inode(real->file) != d_inode(realpath.dentry))) { @@ -150,6 +159,11 @@ static int ovl_open(struct inode *inode, struct file *file) struct path realpath; int err; + /* lazy lookup of lowerdata */ + err = ovl_maybe_lookup_lowerdata(dentry); + if (err) + return err; + err = ovl_maybe_copy_up(dentry, file->f_flags); if (err) return err; @@ -158,6 +172,9 @@ static int ovl_open(struct inode *inode, struct file *file) file->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); ovl_path_realdata(dentry, &realpath); + if (!realpath.dentry) + return -EIO; + realfile = ovl_open_realfile(file, &realpath); if (IS_ERR(realfile)) return PTR_ERR(realfile); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 541cf3717fc2..a63e57447be9 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -97,8 +97,9 @@ out: static void ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid) { - bool samefs = ovl_same_fs(dentry->d_sb); - unsigned int xinobits = ovl_xino_bits(dentry->d_sb); + struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + bool samefs = ovl_same_fs(ofs); + unsigned int xinobits = ovl_xino_bits(ofs); unsigned int xinoshift = 64 - xinobits; if (samefs) { @@ -123,7 +124,7 @@ static void ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid) stat->ino |= ((u64)fsid) << (xinoshift + 1); stat->dev = dentry->d_sb->s_dev; return; - } else if (ovl_xino_warn(dentry->d_sb)) { + } else if (ovl_xino_warn(ofs)) { pr_warn_ratelimited("inode number too big (%pd2, ino=%llu, xinobits=%d)\n", dentry, stat->ino, xinobits); } @@ -149,7 +150,7 @@ static void ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid) * is unique per underlying fs, so we use the unique anonymous * bdev assigned to the underlying fs. */ - stat->dev = OVL_FS(dentry->d_sb)->fs[fsid].pseudo_dev; + stat->dev = ofs->fs[fsid].pseudo_dev; } } @@ -186,7 +187,7 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, * If lower filesystem supports NFS file handles, this also guaranties * persistent st_ino across mount cycle. */ - if (!is_dir || ovl_same_dev(dentry->d_sb)) { + if (!is_dir || ovl_same_dev(OVL_FS(dentry->d_sb))) { if (!OVL_TYPE_UPPER(type)) { fsid = ovl_layer_lower(dentry)->fsid; } else if (OVL_TYPE_ORIGIN(type)) { @@ -240,15 +241,22 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, /* * If lower is not same as lowerdata or if there was * no origin on upper, we can end up here. + * With lazy lowerdata lookup, guess lowerdata blocks + * from size to avoid lowerdata lookup on stat(2). */ struct kstat lowerdatastat; u32 lowermask = STATX_BLOCKS; ovl_path_lowerdata(dentry, &realpath); - err = vfs_getattr(&realpath, &lowerdatastat, - lowermask, flags); - if (err) - goto out; + if (realpath.dentry) { + err = vfs_getattr(&realpath, &lowerdatastat, + lowermask, flags); + if (err) + goto out; + } else { + lowerdatastat.blocks = + round_up(stat->size, stat->blksize) >> 9; + } stat->blocks = lowerdatastat.blocks; } } @@ -288,8 +296,8 @@ int ovl_permission(struct mnt_idmap *idmap, int err; /* Careful in RCU walk mode */ - ovl_i_path_real(inode, &realpath); - if (!realpath.dentry) { + realinode = ovl_i_path_real(inode, &realpath); + if (!realinode) { WARN_ON(!(mask & MAY_NOT_BLOCK)); return -ECHILD; } @@ -302,7 +310,6 @@ int ovl_permission(struct mnt_idmap *idmap, if (err) return err; - realinode = d_inode(realpath.dentry); old_cred = ovl_override_creds(inode->i_sb); if (!upperinode && !special_file(realinode->i_mode) && mask & MAY_WRITE) { @@ -559,20 +566,20 @@ struct posix_acl *do_ovl_get_acl(struct mnt_idmap *idmap, struct inode *inode, int type, bool rcu, bool noperm) { - struct inode *realinode = ovl_inode_real(inode); + struct inode *realinode; struct posix_acl *acl; struct path realpath; - if (!IS_POSIXACL(realinode)) - return NULL; - /* Careful in RCU walk mode */ - ovl_i_path_real(inode, &realpath); - if (!realpath.dentry) { + realinode = ovl_i_path_real(inode, &realpath); + if (!realinode) { WARN_ON(!rcu); return ERR_PTR(-ECHILD); } + if (!IS_POSIXACL(realinode)) + return NULL; + if (rcu) { /* * If the layer is idmapped drop out of RCU path walk @@ -710,6 +717,9 @@ static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, struct inode *realinode = ovl_inode_realdata(inode); const struct cred *old_cred; + if (!realinode) + return -EIO; + if (!realinode->i_op->fiemap) return -EOPNOTSUPP; @@ -952,7 +962,7 @@ static inline void ovl_lockdep_annotate_inode_mutex_key(struct inode *inode) static void ovl_next_ino(struct inode *inode) { - struct ovl_fs *ofs = inode->i_sb->s_fs_info; + struct ovl_fs *ofs = OVL_FS(inode->i_sb); inode->i_ino = atomic_long_inc_return(&ofs->last_ino); if (unlikely(!inode->i_ino)) @@ -961,7 +971,8 @@ static void ovl_next_ino(struct inode *inode) static void ovl_map_ino(struct inode *inode, unsigned long ino, int fsid) { - int xinobits = ovl_xino_bits(inode->i_sb); + struct ovl_fs *ofs = OVL_FS(inode->i_sb); + int xinobits = ovl_xino_bits(ofs); unsigned int xinoshift = 64 - xinobits; /* @@ -972,7 +983,7 @@ static void ovl_map_ino(struct inode *inode, unsigned long ino, int fsid) * with d_ino also causes nfsd readdirplus to fail. */ inode->i_ino = ino; - if (ovl_same_fs(inode->i_sb)) { + if (ovl_same_fs(ofs)) { return; } else if (xinobits && likely(!(ino >> xinoshift))) { inode->i_ino |= (unsigned long)fsid << (xinoshift + 1); @@ -1003,14 +1014,10 @@ void ovl_inode_init(struct inode *inode, struct ovl_inode_params *oip, struct inode *realinode; struct ovl_inode *oi = OVL_I(inode); - if (oip->upperdentry) - oi->__upperdentry = oip->upperdentry; - if (oip->lowerpath && oip->lowerpath->dentry) { - oi->lowerpath.dentry = dget(oip->lowerpath->dentry); - oi->lowerpath.layer = oip->lowerpath->layer; - } - if (oip->lowerdata) - oi->lowerdata = igrab(d_inode(oip->lowerdata)); + oi->__upperdentry = oip->upperdentry; + oi->oe = oip->oe; + oi->redirect = oip->redirect; + oi->lowerdata_redirect = oip->lowerdata_redirect; realinode = ovl_inode_real(inode); ovl_copyattr(inode); @@ -1325,7 +1332,7 @@ struct inode *ovl_get_inode(struct super_block *sb, { struct ovl_fs *ofs = OVL_FS(sb); struct dentry *upperdentry = oip->upperdentry; - struct ovl_path *lowerpath = oip->lowerpath; + struct ovl_path *lowerpath = ovl_lowerpath(oip->oe); struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL; struct inode *inode; struct dentry *lowerdentry = lowerpath ? lowerpath->dentry : NULL; @@ -1369,7 +1376,9 @@ struct inode *ovl_get_inode(struct super_block *sb, } dput(upperdentry); + ovl_free_entry(oip->oe); kfree(oip->redirect); + kfree(oip->lowerdata_redirect); goto out; } @@ -1398,14 +1407,12 @@ struct inode *ovl_get_inode(struct super_block *sb, if (oip->index) ovl_set_flag(OVL_INDEX, inode); - OVL_I(inode)->redirect = oip->redirect; - if (bylower) ovl_set_flag(OVL_CONST_INO, inode); /* Check for non-merge dir that may have whiteouts */ if (is_dir) { - if (((upperdentry && lowerdentry) || oip->numlower > 1) || + if (((upperdentry && lowerdentry) || ovl_numlower(oip->oe) > 1) || ovl_path_check_origin_xattr(ofs, &realpath)) { ovl_set_flag(OVL_WHITEOUTS, inode); } diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index cfb3420b7df0..57adf911735f 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -14,6 +14,8 @@ #include <linux/exportfs.h> #include "overlayfs.h" +#include "../internal.h" /* for vfs_path_lookup */ + struct ovl_lookup_data { struct super_block *sb; struct vfsmount *mnt; @@ -24,6 +26,8 @@ struct ovl_lookup_data { bool last; char *redirect; bool metacopy; + /* Referring to last redirect xattr */ + bool absolute_redirect; }; static int ovl_check_redirect(const struct path *path, struct ovl_lookup_data *d, @@ -33,11 +37,13 @@ static int ovl_check_redirect(const struct path *path, struct ovl_lookup_data *d char *buf; struct ovl_fs *ofs = OVL_FS(d->sb); + d->absolute_redirect = false; buf = ovl_get_redirect_xattr(ofs, path, prelen + strlen(post)); if (IS_ERR_OR_NULL(buf)) return PTR_ERR(buf); if (buf[0] == '/') { + d->absolute_redirect = true; /* * One of the ancestor path elements in an absolute path * lookup in ovl_lookup_layer() could have been opaque and @@ -349,6 +355,61 @@ static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d, return 0; } +static int ovl_lookup_data_layer(struct dentry *dentry, const char *redirect, + const struct ovl_layer *layer, + struct path *datapath) +{ + int err; + + err = vfs_path_lookup(layer->mnt->mnt_root, layer->mnt, redirect, + LOOKUP_BENEATH | LOOKUP_NO_SYMLINKS | LOOKUP_NO_XDEV, + datapath); + pr_debug("lookup lowerdata (%pd2, redirect=\"%s\", layer=%d, err=%i)\n", + dentry, redirect, layer->idx, err); + + if (err) + return err; + + err = -EREMOTE; + if (ovl_dentry_weird(datapath->dentry)) + goto out_path_put; + + err = -ENOENT; + /* Only regular file is acceptable as lower data */ + if (!d_is_reg(datapath->dentry)) + goto out_path_put; + + return 0; + +out_path_put: + path_put(datapath); + + return err; +} + +/* Lookup in data-only layers by absolute redirect to layer root */ +static int ovl_lookup_data_layers(struct dentry *dentry, const char *redirect, + struct ovl_path *lowerdata) +{ + struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + const struct ovl_layer *layer; + struct path datapath; + int err = -ENOENT; + int i; + + layer = &ofs->layers[ofs->numlayer - ofs->numdatalayer]; + for (i = 0; i < ofs->numdatalayer; i++, layer++) { + err = ovl_lookup_data_layer(dentry, redirect, layer, &datapath); + if (!err) { + mntput(datapath.mnt); + lowerdata->dentry = datapath.dentry; + lowerdata->layer = layer; + return 0; + } + } + + return err; +} int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected, struct dentry *upperdentry, struct ovl_path **stackp) @@ -356,7 +417,7 @@ int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected, struct dentry *origin = NULL; int i; - for (i = 1; i < ofs->numlayer; i++) { + for (i = 1; i <= ovl_numlowerlayer(ofs); i++) { /* * If lower fs uuid is not unique among lower fs we cannot match * fh->uuid to layer. @@ -790,20 +851,21 @@ fail: */ int ovl_path_next(int idx, struct dentry *dentry, struct path *path) { - struct ovl_entry *oe = dentry->d_fsdata; + struct ovl_entry *oe = OVL_E(dentry); + struct ovl_path *lowerstack = ovl_lowerstack(oe); BUG_ON(idx < 0); if (idx == 0) { ovl_path_upper(dentry, path); if (path->dentry) - return oe->numlower ? 1 : -1; + return ovl_numlower(oe) ? 1 : -1; idx++; } - BUG_ON(idx > oe->numlower); - path->dentry = oe->lowerstack[idx - 1].dentry; - path->mnt = oe->lowerstack[idx - 1].layer->mnt; + BUG_ON(idx > ovl_numlower(oe)); + path->dentry = lowerstack[idx - 1].dentry; + path->mnt = lowerstack[idx - 1].layer->mnt; - return (idx < oe->numlower) ? idx + 1 : -1; + return (idx < ovl_numlower(oe)) ? idx + 1 : -1; } /* Fix missing 'origin' xattr */ @@ -827,14 +889,60 @@ static int ovl_fix_origin(struct ovl_fs *ofs, struct dentry *dentry, return err; } +/* Lazy lookup of lowerdata */ +int ovl_maybe_lookup_lowerdata(struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + const char *redirect = ovl_lowerdata_redirect(inode); + struct ovl_path datapath = {}; + const struct cred *old_cred; + int err; + + if (!redirect || ovl_dentry_lowerdata(dentry)) + return 0; + + if (redirect[0] != '/') + return -EIO; + + err = ovl_inode_lock_interruptible(inode); + if (err) + return err; + + err = 0; + /* Someone got here before us? */ + if (ovl_dentry_lowerdata(dentry)) + goto out; + + old_cred = ovl_override_creds(dentry->d_sb); + err = ovl_lookup_data_layers(dentry, redirect, &datapath); + revert_creds(old_cred); + if (err) + goto out_err; + + err = ovl_dentry_set_lowerdata(dentry, &datapath); + if (err) + goto out_err; + +out: + ovl_inode_unlock(inode); + dput(datapath.dentry); + + return err; + +out_err: + pr_warn_ratelimited("lazy lowerdata lookup failed (%pd2, err=%i)\n", + dentry, err); + goto out; +} + struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - struct ovl_entry *oe; + struct ovl_entry *oe = NULL; const struct cred *old_cred; struct ovl_fs *ofs = dentry->d_sb->s_fs_info; - struct ovl_entry *poe = dentry->d_parent->d_fsdata; - struct ovl_entry *roe = dentry->d_sb->s_root->d_fsdata; + struct ovl_entry *poe = OVL_E(dentry->d_parent); + struct ovl_entry *roe = OVL_E(dentry->d_sb->s_root); struct ovl_path *stack = NULL, *origin_path = NULL; struct dentry *upperdir, *upperdentry = NULL; struct dentry *origin = NULL; @@ -853,7 +961,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, .is_dir = false, .opaque = false, .stop = false, - .last = ofs->config.redirect_follow ? false : !poe->numlower, + .last = ovl_redirect_follow(ofs) ? false : !ovl_numlower(poe), .redirect = NULL, .metacopy = false, }; @@ -904,21 +1012,20 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, upperopaque = d.opaque; } - if (!d.stop && poe->numlower) { + if (!d.stop && ovl_numlower(poe)) { err = -ENOMEM; - stack = kcalloc(ofs->numlayer - 1, sizeof(struct ovl_path), - GFP_KERNEL); + stack = ovl_stack_alloc(ofs->numlayer - 1); if (!stack) goto out_put_upper; } - for (i = 0; !d.stop && i < poe->numlower; i++) { - struct ovl_path lower = poe->lowerstack[i]; + for (i = 0; !d.stop && i < ovl_numlower(poe); i++) { + struct ovl_path lower = ovl_lowerstack(poe)[i]; - if (!ofs->config.redirect_follow) - d.last = i == poe->numlower - 1; - else - d.last = lower.layer->idx == roe->numlower; + if (!ovl_redirect_follow(ofs)) + d.last = i == ovl_numlower(poe) - 1; + else if (d.is_dir || !ofs->numdatalayer) + d.last = lower.layer->idx == ovl_numlower(roe); d.mnt = lower.layer->mnt; err = ovl_lookup_layer(lower.dentry, &d, &this, false); @@ -995,7 +1102,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, * this attack vector when not necessary. */ err = -EPERM; - if (d.redirect && !ofs->config.redirect_follow) { + if (d.redirect && !ovl_redirect_follow(ofs)) { pr_warn_ratelimited("refusing to follow redirect for (%pd2)\n", dentry); goto out_put; @@ -1011,6 +1118,12 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, } } + /* Defer lookup of lowerdata in data-only layers to first access */ + if (d.metacopy && ctr && ofs->numdatalayer && d.absolute_redirect) { + d.metacopy = false; + ctr++; + } + /* * For regular non-metacopy upper dentries, there is no lower * path based lookup, hence ctr will be zero. If a dentry is found @@ -1067,13 +1180,14 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, } } - oe = ovl_alloc_entry(ctr); - err = -ENOMEM; - if (!oe) - goto out_put; + if (ctr) { + oe = ovl_alloc_entry(ctr); + err = -ENOMEM; + if (!oe) + goto out_put; - memcpy(oe->lowerstack, stack, sizeof(struct ovl_path) * ctr); - dentry->d_fsdata = oe; + ovl_stack_cpy(ovl_lowerstack(oe), stack, ctr); + } if (upperopaque) ovl_dentry_set_opaque(dentry); @@ -1106,14 +1220,16 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, if (upperdentry || ctr) { struct ovl_inode_params oip = { .upperdentry = upperdentry, - .lowerpath = stack, + .oe = oe, .index = index, - .numlower = ctr, .redirect = upperredirect, - .lowerdata = (ctr > 1 && !d.is_dir) ? - stack[ctr - 1].dentry : NULL, }; + /* Store lowerdata redirect for lazy lookup */ + if (ctr > 1 && !d.is_dir && !stack[ctr - 1].dentry) { + oip.lowerdata_redirect = d.redirect; + d.redirect = NULL; + } inode = ovl_get_inode(dentry->d_sb, &oip); err = PTR_ERR(inode); if (IS_ERR(inode)) @@ -1122,8 +1238,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, ovl_set_flag(OVL_UPPERDATA, inode); } - ovl_dentry_update_reval(dentry, upperdentry, - DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE); + ovl_dentry_init_reval(dentry, upperdentry, OVL_I_E(inode)); revert_creds(old_cred); if (origin_path) { @@ -1131,18 +1246,15 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, kfree(origin_path); } dput(index); - kfree(stack); + ovl_stack_free(stack, ctr); kfree(d.redirect); return d_splice_alias(inode, dentry); out_free_oe: - dentry->d_fsdata = NULL; - kfree(oe); + ovl_free_entry(oe); out_put: dput(index); - for (i = 0; i < ctr; i++) - dput(stack[i].dentry); - kfree(stack); + ovl_stack_free(stack, ctr); out_put_upper: if (origin_path) { dput(origin_path->dentry); @@ -1158,7 +1270,7 @@ out: bool ovl_lower_positive(struct dentry *dentry) { - struct ovl_entry *poe = dentry->d_parent->d_fsdata; + struct ovl_entry *poe = OVL_E(dentry->d_parent); const struct qstr *name = &dentry->d_name; const struct cred *old_cred; unsigned int i; @@ -1178,12 +1290,13 @@ bool ovl_lower_positive(struct dentry *dentry) old_cred = ovl_override_creds(dentry->d_sb); /* Positive upper -> have to look up lower to see whether it exists */ - for (i = 0; !done && !positive && i < poe->numlower; i++) { + for (i = 0; !done && !positive && i < ovl_numlower(poe); i++) { struct dentry *this; - struct dentry *lowerdir = poe->lowerstack[i].dentry; + struct ovl_path *parentpath = &ovl_lowerstack(poe)[i]; - this = lookup_one_positive_unlocked(mnt_idmap(poe->lowerstack[i].layer->mnt), - name->name, lowerdir, name->len); + this = lookup_one_positive_unlocked( + mnt_idmap(parentpath->layer->mnt), + name->name, parentpath->dentry, name->len); if (IS_ERR(this)) { switch (PTR_ERR(this)) { case -ENOENT: diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 23686e8a06c4..4142d1a457ff 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -58,11 +58,26 @@ enum ovl_entry_flag { }; enum { + OVL_REDIRECT_OFF, /* "off" mode is never used. In effect */ + OVL_REDIRECT_FOLLOW, /* ...it translates to either "follow" */ + OVL_REDIRECT_NOFOLLOW, /* ...or "nofollow". */ + OVL_REDIRECT_ON, +}; + +enum { OVL_XINO_OFF, OVL_XINO_AUTO, OVL_XINO_ON, }; +/* The set of options that user requested explicitly via mount options */ +struct ovl_opt_set { + bool metacopy; + bool redirect; + bool nfs_export; + bool index; +}; + /* * The tuple (fh,uuid) is a universal unique identifier for a copy up origin, * where: @@ -353,17 +368,29 @@ static inline bool ovl_open_flags_need_copy_up(int flags) return ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC)); } -static inline bool ovl_allow_offline_changes(struct ovl_fs *ofs) -{ - /* - * To avoid regressions in existing setups with overlay lower offline - * changes, we allow lower changes only if none of the new features - * are used. - */ - return (!ofs->config.index && !ofs->config.metacopy && - !ofs->config.redirect_dir && ofs->config.xino != OVL_XINO_ON); -} +/* params.c */ +#define OVL_MAX_STACK 500 + +struct ovl_fs_context_layer { + char *name; + struct path path; +}; + +struct ovl_fs_context { + struct path upper; + struct path work; + size_t capacity; + size_t nr; /* includes nr_data */ + size_t nr_data; + struct ovl_opt_set set; + struct ovl_fs_context_layer *lower; +}; + +int ovl_parse_param_upperdir(const char *name, struct fs_context *fc, + bool workdir); +int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc); +void ovl_parse_param_drop_lowerdir(struct ovl_fs_context *ctx); /* util.c */ int ovl_want_write(struct dentry *dentry); @@ -3 |