diff options
Diffstat (limited to 'fs/overlayfs')
| -rw-r--r-- | fs/overlayfs/Kconfig | 1 | ||||
| -rw-r--r-- | fs/overlayfs/Makefile | 2 | ||||
| -rw-r--r-- | fs/overlayfs/copy_up.c | 249 | ||||
| -rw-r--r-- | fs/overlayfs/dir.c | 217 | ||||
| -rw-r--r-- | fs/overlayfs/export.c | 83 | ||||
| -rw-r--r-- | fs/overlayfs/file.c | 306 | ||||
| -rw-r--r-- | fs/overlayfs/inode.c | 169 | ||||
| -rw-r--r-- | fs/overlayfs/namei.c | 99 | ||||
| -rw-r--r-- | fs/overlayfs/overlayfs.h | 106 | ||||
| -rw-r--r-- | fs/overlayfs/ovl_entry.h | 9 | ||||
| -rw-r--r-- | fs/overlayfs/params.c | 6 | ||||
| -rw-r--r-- | fs/overlayfs/readdir.c | 32 | ||||
| -rw-r--r-- | fs/overlayfs/super.c | 212 | ||||
| -rw-r--r-- | fs/overlayfs/util.c | 179 | ||||
| -rw-r--r-- | fs/overlayfs/xattrs.c | 271 |
15 files changed, 1162 insertions, 779 deletions
diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index fec5020c3495..2ac67e04a6fb 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config OVERLAY_FS tristate "Overlay filesystem support" + select FS_STACK select EXPORTFS help An overlay filesystem combines two filesystems - an 'upper' filesystem diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile index 4e173d56b11f..5648954f8588 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 params.o + copy_up.o export.o params.o xattrs.o diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index ada3fcc9c6d5..a00af67cee98 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -114,13 +114,13 @@ int ovl_copy_xattr(struct super_block *sb, const struct path *oldpath, struct de if (ovl_is_private_xattr(sb, name)) continue; - error = security_inode_copy_up_xattr(name); - if (error < 0 && error != -EOPNOTSUPP) - break; - if (error == 1) { + error = security_inode_copy_up_xattr(old, name); + if (error == -ECANCELED) { error = 0; continue; /* Discard */ } + if (error < 0 && error != -EOPNOTSUPP) + break; if (is_posix_acl_xattr(name)) { error = ovl_copy_acl(OVL_FS(sb), oldpath, new, name); @@ -230,8 +230,37 @@ static int ovl_copy_fileattr(struct inode *inode, const struct path *old, return ovl_real_fileattr_set(new, &newfa); } +static int ovl_verify_area(loff_t pos, loff_t pos2, loff_t len, loff_t totlen) +{ + loff_t tmp; + + if (pos != pos2) + return -EIO; + if (pos < 0 || len < 0 || totlen < 0) + return -EIO; + if (check_add_overflow(pos, len, &tmp)) + return -EIO; + return 0; +} + +static int ovl_sync_file(struct path *path) +{ + struct file *new_file; + int err; + + new_file = ovl_path_open(path, O_LARGEFILE | O_RDONLY); + if (IS_ERR(new_file)) + return PTR_ERR(new_file); + + err = vfs_fsync(new_file, 0); + fput(new_file); + + return err; +} + static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, - struct file *new_file, loff_t len) + struct file *new_file, loff_t len, + bool datasync) { struct path datapath; struct file *old_file; @@ -244,7 +273,8 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, int error = 0; ovl_path_lowerdata(dentry, &datapath); - if (WARN_ON(datapath.dentry == NULL)) + if (WARN_ON_ONCE(datapath.dentry == NULL) || + WARN_ON_ONCE(len < 0)) return -EIO; old_file = ovl_path_open(&datapath, O_LARGEFILE | O_RDONLY); @@ -252,10 +282,16 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, return PTR_ERR(old_file); /* Try to use clone_file_range to clone up within the same fs */ - cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0); + cloned = vfs_clone_file_range(old_file, 0, new_file, 0, len, 0); if (cloned == len) goto out_fput; + /* Couldn't clone, so now we try to copy the data */ + error = rw_verify_area(READ, old_file, &old_pos, len); + if (!error) + error = rw_verify_area(WRITE, new_file, &new_pos, len); + if (error) + goto out_fput; /* Check if lower fs supports seek operation */ if (old_file->f_mode & FMODE_LSEEK) @@ -263,7 +299,7 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, while (len) { size_t this_len = OVL_COPY_UP_CHUNK_SIZE; - long bytes; + ssize_t bytes; if (len < this_len) this_len = len; @@ -287,8 +323,12 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, * it may not recognize all kind of holes and sometimes * only skips partial of hole area. However, it will be * enough for most of the use cases. + * + * We do not hold upper sb_writers throughout the loop to avert + * lockdep warning with llseek of lower file in nested overlay: + * - upper sb_writers + * -- lower ovl_inode_lock (ovl_llseek) */ - if (skip_hole && data_pos < old_pos) { data_pos = vfs_llseek(old_file, old_pos, SEEK_DATA); if (data_pos > old_pos) { @@ -303,6 +343,10 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, } } + error = ovl_verify_area(old_pos, new_pos, this_len, len); + if (error) + break; + bytes = do_splice_direct(old_file, &old_pos, new_file, &new_pos, this_len, SPLICE_F_MOVE); @@ -314,7 +358,8 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry, len -= bytes; } - if (!error && ovl_should_sync(ofs)) + /* call fsync once, either now or later along with metadata */ + if (!error && ovl_should_sync(ofs) && datasync) error = vfs_fsync(new_file, 0); out_fput: fput(old_file); @@ -371,13 +416,13 @@ int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upperdentry, return err; } -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper) { struct ovl_fh *fh; int fh_type, dwords; int buflen = MAX_HANDLE_SZ; - uuid_t *uuid = &real->d_sb->s_uuid; + uuid_t *uuid = &realinode->i_sb->s_uuid; int err; /* Make sure the real fid stays 32bit aligned */ @@ -394,13 +439,13 @@ struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, * the price or reconnecting the dentry. */ dwords = buflen >> 2; - fh_type = exportfs_encode_fh(real, (void *)fh->fb.fid, &dwords, 0); + fh_type = exportfs_encode_inode_fh(realinode, (void *)fh->fb.fid, + &dwords, NULL, 0); buflen = (dwords << 2); err = -EIO; - if (WARN_ON(fh_type < 0) || - WARN_ON(buflen > MAX_HANDLE_SZ) || - WARN_ON(fh_type == FILEID_INVALID)) + if (fh_type < 0 || fh_type == FILEID_INVALID || + WARN_ON(buflen > MAX_HANDLE_SZ)) goto out_err; fh->fb.version = OVL_FH_VERSION; @@ -426,29 +471,29 @@ out_err: return ERR_PTR(err); } -int ovl_set_origin(struct ovl_fs *ofs, struct dentry *lower, - struct dentry *upper) +struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin) { - const struct ovl_fh *fh = NULL; - int err; - /* * When lower layer doesn't support export operations store a 'null' fh, * so we can use the overlay.origin xattr to distignuish between a copy * up and a pure upper inode. */ - if (ovl_can_decode_fh(lower->d_sb)) { - fh = ovl_encode_real_fh(ofs, lower, false); - if (IS_ERR(fh)) - return PTR_ERR(fh); - } + if (!ovl_can_decode_fh(origin->d_sb)) + return NULL; + + return ovl_encode_real_fh(ofs, d_inode(origin), false); +} + +int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, + struct dentry *upper) +{ + int err; /* * Do not fail when upper doesn't support xattrs. */ err = ovl_check_setxattr(ofs, upper, OVL_XATTR_ORIGIN, fh->buf, fh ? fh->fb.len : 0, 0); - kfree(fh); /* Ignore -EPERM from setting "user.*" on symlink/special */ return err == -EPERM ? 0 : err; @@ -461,7 +506,7 @@ static int ovl_set_upper_fh(struct ovl_fs *ofs, struct dentry *upper, const struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, upper, true); + fh = ovl_encode_real_fh(ofs, d_inode(upper), true); if (IS_ERR(fh)) return PTR_ERR(fh); @@ -476,7 +521,7 @@ static int ovl_set_upper_fh(struct ovl_fs *ofs, struct dentry *upper, * * Caller must hold i_mutex on indexdir. */ -static int ovl_create_index(struct dentry *dentry, struct dentry *origin, +static int ovl_create_index(struct dentry *dentry, const struct ovl_fh *fh, struct dentry *upper) { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); @@ -502,7 +547,7 @@ static int ovl_create_index(struct dentry *dentry, struct dentry *origin, if (WARN_ON(ovl_test_flag(OVL_INDEX, d_inode(dentry)))) return -EIO; - err = ovl_get_index_name(ofs, origin, &name); + err = ovl_get_index_name_fh(fh, &name); if (err) return err; @@ -541,10 +586,12 @@ struct ovl_copy_up_ctx { struct dentry *destdir; struct qstr destname; struct dentry *workdir; + const struct ovl_fh *origin_fh; bool origin; bool indexed; bool metacopy; bool metacopy_digest; + bool metadata_fsync; }; static int ovl_link_up(struct ovl_copy_up_ctx *c) @@ -555,14 +602,16 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c) struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb); struct inode *udir = d_inode(upperdir); + ovl_start_write(c->dentry); + /* Mark parent "impure" because it may now contain non-pure upper */ err = ovl_set_impure(c->parent, upperdir); if (err) - return err; + goto out; err = ovl_set_nlink_lower(c->dentry); if (err) - return err; + goto out; inode_lock_nested(udir, I_MUTEX_PARENT); upper = ovl_lookup_upper(ofs, c->dentry->d_name.name, upperdir, @@ -570,7 +619,6 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c) err = PTR_ERR(upper); if (!IS_ERR(upper)) { err = ovl_do_link(ofs, ovl_dentry_upper(c->dentry), udir, upper); - dput(upper); if (!err) { /* Restore timestamps on parent (best effort) */ @@ -578,13 +626,16 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c) ovl_dentry_set_upper_alias(c->dentry); ovl_dentry_update_reval(c->dentry, upper); } + dput(upper); } inode_unlock(udir); if (err) - return err; + goto out; err = ovl_set_nlink_upper(c->dentry); +out: + ovl_end_write(c->dentry); return err; } @@ -601,7 +652,8 @@ static int ovl_copy_up_data(struct ovl_copy_up_ctx *c, const struct path *temp) if (IS_ERR(new_file)) return PTR_ERR(new_file); - err = ovl_copy_up_file(ofs, c->dentry, new_file, c->stat.size); + err = ovl_copy_up_file(ofs, c->dentry, new_file, c->stat.size, + !c->metadata_fsync); fput(new_file); return err; @@ -637,7 +689,7 @@ static int ovl_copy_up_metadata(struct ovl_copy_up_ctx *c, struct dentry *temp) * hard link. */ if (c->origin) { - err = ovl_set_origin(ofs, c->lowerpath.dentry, temp); + err = ovl_set_origin_fh(ofs, c->origin_fh, temp); if (err) return err; } @@ -668,6 +720,10 @@ static int ovl_copy_up_metadata(struct ovl_copy_up_ctx *c, struct dentry *temp) err = ovl_set_attr(ofs, temp, &c->stat); inode_unlock(temp->d_inode); + /* fsync metadata before moving it into upper dir */ + if (!err && ovl_should_sync(ofs) && c->metadata_fsync) + err = ovl_sync_file(&upperpath); + return err; } @@ -709,7 +765,7 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c) struct inode *inode; struct inode *udir = d_inode(c->destdir), *wdir = d_inode(c->workdir); struct path path = { .mnt = ovl_upper_mnt(ofs) }; - struct dentry *temp, *upper; + struct dentry *temp, *upper, *trap; struct ovl_cu_creds cc; int err; struct ovl_cattr cattr = { @@ -719,21 +775,19 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c) .link = c->link }; - /* workdir and destdir could be the same when copying up to indexdir */ - err = -EIO; - if (lock_rename(c->workdir, c->destdir) != NULL) - goto unlock; - err = ovl_prep_cu_creds(c->dentry, &cc); if (err) - goto unlock; + return err; + ovl_start_write(c->dentry); + inode_lock_nested(wdir, I_MUTEX_PARENT); temp = ovl_create_temp(ofs, c->workdir, &cattr); + inode_unlock(wdir); + ovl_end_write(c->dentry); ovl_revert_cu_creds(&cc); - err = PTR_ERR(temp); if (IS_ERR(temp)) - goto unlock; + return PTR_ERR(temp); /* * Copy up data first and then xattrs. Writing data after @@ -741,15 +795,31 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c) */ path.dentry = temp; err = ovl_copy_up_data(c, &path); - if (err) + /* + * We cannot hold lock_rename() throughout this helper, because of + * lock ordering with sb_writers, which shouldn't be held when calling + * ovl_copy_up_data(), so lock workdir and destdir and make sure that + * temp wasn't moved before copy up completion or cleanup. + */ + ovl_start_write(c->dentry); + trap = lock_rename(c->workdir, c->destdir); + if (trap || temp->d_parent != c->workdir) { + /* temp or workdir moved underneath us? abort without cleanup */ + dput(temp); + err = -EIO; + if (IS_ERR(trap)) + goto out; + goto unlock; + } else if (err) { goto cleanup; + } err = ovl_copy_up_metadata(c, temp); if (err) goto cleanup; if (S_ISDIR(c->stat.mode) && c->indexed) { - err = ovl_create_index(c->dentry, c->lowerpath.dentry, temp); + err = ovl_create_index(c->dentry, c->origin_fh, temp); if (err) goto cleanup; } @@ -779,6 +849,8 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c) ovl_set_flag(OVL_WHITEOUTS, inode); unlock: unlock_rename(c->workdir, c->destdir); +out: + ovl_end_write(c->dentry); return err; @@ -802,22 +874,26 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c) if (err) return err; + ovl_start_write(c->dentry); tmpfile = ovl_do_tmpfile(ofs, c->workdir, c->stat.mode); + ovl_end_write(c->dentry); ovl_revert_cu_creds(&cc); - if (IS_ERR(tmpfile)) return PTR_ERR(tmpfile); temp = tmpfile->f_path.dentry; if (!c->metacopy && c->stat.size) { - err = ovl_copy_up_file(ofs, c->dentry, tmpfile, c->stat.size); + err = ovl_copy_up_file(ofs, c->dentry, tmpfile, c->stat.size, + !c->metadata_fsync); if (err) goto out_fput; } + ovl_start_write(c->dentry); + err = ovl_copy_up_metadata(c, temp); if (err) - goto out_fput; + goto out; inode_lock_nested(udir, I_MUTEX_PARENT); @@ -831,7 +907,7 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c) inode_unlock(udir); if (err) - goto out_fput; + goto out; if (c->metacopy_digest) ovl_set_flag(OVL_HAS_DIGEST, d_inode(c->dentry)); @@ -843,6 +919,8 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c) ovl_set_upperdata(d_inode(c->dentry)); ovl_inode_update(d_inode(c->dentry), dget(temp)); +out: + ovl_end_write(c->dentry); out_fput: fput(tmpfile); return err; @@ -861,6 +939,8 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) { int err; struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb); + struct dentry *origin = c->lowerpath.dentry; + struct ovl_fh *fh = NULL; bool to_index = false; /* @@ -877,25 +957,42 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) to_index = true; } - if (S_ISDIR(c->stat.mode) || c->stat.nlink == 1 || to_index) + if (S_ISDIR(c->stat.mode) || c->stat.nlink == 1 || to_index) { + fh = ovl_get_origin_fh(ofs, origin); + if (IS_ERR(fh)) + return PTR_ERR(fh); + + /* origin_fh may be NULL */ + c->origin_fh = fh; c->origin = true; + } if (to_index) { c->destdir = ovl_indexdir(c->dentry->d_sb); - err = ovl_get_index_name(ofs, c->lowerpath.dentry, &c->destname); + err = ovl_get_index_name(ofs, origin, &c->destname); if (err) - return err; + goto out_free_fh; } else if (WARN_ON(!c->parent)) { /* Disconnected dentry must be copied up to index dir */ - return -EIO; + err = -EIO; + goto out_free_fh; } else { /* + * c->dentry->d_name is stabilzed by ovl_copy_up_start(), + * because if we got here, it means that c->dentry has no upper + * alias and changing ->d_name means going through ovl_rename() + * that will call ovl_copy_up() on source and target dentry. + */ + c->destname = c->dentry->d_name; + /* * Mark parent "impure" because it may now contain non-pure * upper */ + ovl_start_write(c->dentry); err = ovl_set_impure(c->parent, c->destdir); + ovl_end_write(c->dentry); if (err) - return err; + goto out_free_fh; } /* Should we copyup with O_TMPFILE or with workdir? */ @@ -909,6 +1006,7 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) if (c->indexed) ovl_set_flag(OVL_INDEX, d_inode(c->dentry)); + ovl_start_write(c->dentry); if (to_index) { /* Initialize nlink for copy up of disconnected dentry */ err = ovl_set_nlink_upper(c->dentry); @@ -923,10 +1021,13 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) ovl_dentry_set_upper_alias(c->dentry); ovl_dentry_update_reval(c->dentry, ovl_dentry_upper(c->dentry)); } + ovl_end_write(c->dentry); out: if (to_index) kfree(c->destname.name); +out_free_fh: + kfree(fh); return err; } @@ -1011,15 +1112,16 @@ static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c) * Writing to upper file will clear security.capability xattr. We * don't want that to happen for normal copy-up operation. */ + ovl_start_write(c->dentry); if (capability) { err = ovl_do_setxattr(ofs, upperpath.dentry, XATTR_NAME_CAPS, capability, cap_size, 0); - if (err) - goto out_free; } - - - err = ovl_removexattr(ofs, upperpath.dentry, OVL_XATTR_METACOPY); + if (!err) { + err = ovl_removexattr(ofs, upperpath.dentry, + OVL_XATTR_METACOPY); + } + ovl_end_write(c->dentry); if (err) goto out_free; @@ -1057,12 +1159,22 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, !kgid_has_mapping(current_user_ns(), ctx.stat.gid)) return -EOVERFLOW; + /* + * With metacopy disabled, we fsync after final metadata copyup, for + * both regular files and directories to get atomic copyup semantics + * on filesystems that do not use strict metadata ordering (e.g. ubifs). + * + * With metacopy enabled we want to avoid fsync on all meta copyup + * that will hurt performance of workloads such as chown -R, so we + * only fsync on data copyup as legacy behavior. + */ + ctx.metadata_fsync = !OVL_FS(dentry->d_sb)->config.metacopy && + (S_ISREG(ctx.stat.mode) || S_ISDIR(ctx.stat.mode)); ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags); if (parent) { ovl_path_upper(parent, &parentpath); ctx.destdir = parentpath.dentry; - ctx.destname = dentry->d_name; err = vfs_getattr(&parentpath, &ctx.pstat, STATX_ATIME | STATX_MTIME, @@ -1170,17 +1282,10 @@ static bool ovl_open_need_copy_up(struct dentry *dentry, int flags) int ovl_maybe_copy_up(struct dentry *dentry, int flags) { - int err = 0; - - if (ovl_open_need_copy_up(dentry, flags)) { - err = ovl_want_write(dentry); - if (!err) { - err = ovl_copy_up_flags(dentry, flags); - ovl_drop_write(dentry); - } - } + if (!ovl_open_need_copy_up(dentry, flags)) + return 0; - return err; + return ovl_copy_up_flags(dentry, flags); } int ovl_copy_up_with_data(struct dentry *dentry) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 54602f0bed8b..ab65e98a1def 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -14,6 +14,7 @@ #include <linux/posix_acl_xattr.h> #include <linux/atomic.h> #include <linux/ratelimit.h> +#include <linux/backing-file.h> #include "overlayfs.h" static unsigned short ovl_redirect_max = 256; @@ -260,14 +261,13 @@ static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry) * may not use to instantiate the new dentry. */ static int ovl_instantiate(struct dentry *dentry, struct inode *inode, - struct dentry *newdentry, bool hardlink) + struct dentry *newdentry, bool hardlink, struct file *tmpfile) { struct ovl_inode_params oip = { .upperdentry = newdentry, .newinode = inode, }; - ovl_dir_modified(dentry->d_parent, false); ovl_dentry_set_upper_alias(dentry); ovl_dentry_init_reval(dentry, newdentry, NULL); @@ -295,6 +295,9 @@ static int ovl_instantiate(struct dentry *dentry, struct inode *inode, inc_nlink(inode); } + if (tmpfile) + d_mark_tmpfile(tmpfile, inode); + d_instantiate(dentry, inode); if (inode != oip.newinode) { pr_warn_ratelimited("newly created inode found in cache (%pd2)\n", @@ -342,7 +345,8 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode, ovl_set_opaque(dentry, newdentry); } - err = ovl_instantiate(dentry, inode, newdentry, !!attr->hardlink); + ovl_dir_modified(dentry->d_parent, false); + err = ovl_instantiate(dentry, inode, newdentry, !!attr->hardlink, NULL); if (err) goto out_cleanup; out_unlock: @@ -474,7 +478,7 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, goto out_unlock; err = -ESTALE; - if (d_is_negative(upper) || !IS_WHITEOUT(d_inode(upper))) + if (d_is_negative(upper) || !ovl_upper_is_whiteout(ofs, upper)) goto out_dput; newdentry = ovl_create_temp(ofs, workdir, cattr); @@ -526,7 +530,8 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, if (err) goto out_cleanup; } - err = ovl_instantiate(dentry, inode, newdentry, hardlink); + ovl_dir_modified(dentry->d_parent, false); + err = ovl_instantiate(dentry, inode, newdentry, hardlink, NULL); if (err) { ovl_cleanup(ofs, udir, newdentry); dput(newdentry); @@ -548,18 +553,37 @@ out_cleanup: goto out_dput; } +static int ovl_setup_cred_for_create(struct dentry *dentry, struct inode *inode, + umode_t mode, const struct cred *old_cred) +{ + int err; + struct cred *override_cred; + + override_cred = prepare_creds(); + if (!override_cred) + return -ENOMEM; + + override_cred->fsuid = inode->i_uid; + override_cred->fsgid = inode->i_gid; + err = security_dentry_create_files_as(dentry, mode, &dentry->d_name, + old_cred, override_cred); + if (err) { + put_cred(override_cred); + return err; + } + put_cred(override_creds(override_cred)); + put_cred(override_cred); + + return 0; +} + static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, struct ovl_cattr *attr, bool origin) { int err; const struct cred *old_cred; - struct cred *override_cred; struct dentry *parent = dentry->d_parent; - err = ovl_copy_up(parent); - if (err) - return err; - old_cred = ovl_override_creds(dentry->d_sb); /* @@ -573,10 +597,6 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, } if (!attr->hardlink) { - err = -ENOMEM; - override_cred = prepare_creds(); - if (!override_cred) - goto out_revert_creds; /* * In the creation cases(create, mkdir, mknod, symlink), * ovl should transfer current's fs{u,g}id to underlying @@ -590,17 +610,9 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, * create a new inode, so just use the ovl mounter's * fs{u,g}id. */ - override_cred->fsuid = inode->i_uid; - override_cred->fsgid = inode->i_gid; - err = security_dentry_create_files_as(dentry, - attr->mode, &dentry->d_name, old_cred, - override_cred); - if (err) { - put_cred(override_cred); + err = ovl_setup_cred_for_create(dentry, inode, attr->mode, old_cred); + if (err) goto out_revert_creds; - } - put_cred(override_creds(override_cred)); - put_cred(override_cred); } if (!ovl_dentry_is_whiteout(dentry)) @@ -623,6 +635,10 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev, .link = link, }; + err = ovl_copy_up(dentry->d_parent); + if (err) + return err; + err = ovl_want_write(dentry); if (err) goto out; @@ -697,28 +713,24 @@ static int ovl_link(struct dentry *old, struct inode *newdir, int err; struct inode *inode; - err = ovl_want_write(old); + err = ovl_copy_up(old); if (err) goto out; - err = ovl_copy_up(old); + err = ovl_copy_up(new->d_parent); if (err) - goto out_drop_write; + goto out; - err = ovl_copy_up(new->d_parent); + err = ovl_nlink_start(old); if (err) - goto out_drop_write; + goto out; if (ovl_is_metacopy_dentry(old)) { err = ovl_set_link_redirect(old); if (err) - goto out_drop_write; + goto out_nlink_end; } - err = ovl_nlink_start(old); - if (err) - goto out_drop_write; - inode = d_inode(old); ihold(inode); @@ -728,9 +740,8 @@ static int ovl_link(struct dentry *old, struct inode *newdir, if (err) iput(inode); +out_nlink_end: ovl_nlink_end(old); -out_drop_write: - ovl_drop_write(old); out: return err; } @@ -888,17 +899,13 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir) goto out; } - err = ovl_want_write(dentry); - if (err) - goto out; - err = ovl_copy_up(dentry->d_parent); if (err) - goto out_drop_write; + goto out; err = ovl_nlink_start(dentry); if (err) - goto out_drop_write; + goto out; old_cred = ovl_override_creds(dentry->d_sb); if (!lower_positive) @@ -923,8 +930,6 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir) if (ovl_dentry_upper(dentry)) ovl_copyattr(d_inode(dentry)); -out_drop_write: - ovl_drop_write(dentry); out: ovl_cache_free(&list); return err; @@ -1128,29 +1133,32 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir, } } - err = ovl_want_write(old); - if (err) - goto out; - err = ovl_copy_up(old); if (err) - goto out_drop_write; + goto out; err = ovl_copy_up(new->d_parent); if (err) - goto out_drop_write; + goto out; if (!overwrite) { err = ovl_copy_up(new); if (err) - goto out_drop_write; + goto out; } else if (d_inode(new)) { err = ovl_nlink_start(new); if (err) - goto out_drop_write; + goto out; update_nlink = true; } + if (!update_nlink) { + /* ovl_nlink_start() took ovl_want_write() */ + err = ovl_want_write(old); + if (err) + goto out; + } + old_cred = ovl_override_creds(old->d_sb); if (!list_empty(&list)) { @@ -1185,6 +1193,10 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir, } trap = lock_rename(new_upperdir, old_upperdir); + if (IS_ERR(trap)) { + err = PTR_ERR(trap); + goto out_revert_creds; + } olddentry = ovl_lookup_upper(ofs, old->d_name.name, old_upperdir, old->d_name.len); @@ -1216,7 +1228,7 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir, } } else { if (!d_is_negative(newdentry)) { - if (!new_opaque || !ovl_is_whiteout(newdentry)) + if (!new_opaque || !ovl_upper_is_whiteout(ofs, newdentry)) goto out_dput; } else { if (flags & RENAME_EXCHANGE) @@ -1283,14 +1295,108 @@ out_revert_creds: revert_creds(old_cred); if (update_nlink) ovl_nlink_end(new); -out_drop_write: - ovl_drop_write(old); + else + ovl_drop_write(old); out: dput(opaquedir); ovl_cache_free(&list); return err; } +static int ovl_create_tmpfile(struct file *file, struct dentry *dentry, + struct inode *inode, umode_t mode) +{ + const struct cred *old_cred; + struct path realparentpath; + struct file *realfile; + struct dentry *newdentry; + /* It's okay to set O_NOATIME, since the owner will be current fsuid */ + int flags = file->f_flags | OVL_OPEN_FLAGS; + int err; + + old_cred = ovl_override_creds(dentry->d_sb); + err = ovl_setup_cred_for_create(dentry, inode, mode, old_cred); + if (err) + goto out_revert_creds; + + ovl_path_upper(dentry->d_parent, &realparentpath); + realfile = backing_tmpfile_open(&file->f_path, flags, &realparentpath, + mode, current_cred()); + err = PTR_ERR_OR_ZERO(realfile); + pr_debug("tmpfile/open(%pd2, 0%o) = %i\n", realparentpath.dentry, mode, err); + if (err) + goto out_revert_creds; + + /* ovl_instantiate() consumes the newdentry reference on success */ + newdentry = dget(realfile->f_path.dentry); + err = ovl_instantiate(dentry, inode, newdentry, false, file); + if (!err) { + file->private_data = realfile; + } else { + dput(newdentry); + fput(realfile); + } +out_revert_creds: + revert_creds(old_cred); + return err; +} + +static int ovl_dummy_open(struct inode *inode, struct file *file) +{ + return 0; +} + +static int ovl_tmpfile(struct mnt_idmap *idmap, struct inode *dir, + struct file *file, umode_t mode) +{ + int err; + struct dentry *dentry = file->f_path.dentry; + struct inode *inode; + + if (!OVL_FS(dentry->d_sb)->tmpfile) + return -EOPNOTSUPP; + + err = ovl_copy_up(dentry->d_parent); + if (err) + return err; + + err = ovl_want_write(dentry); + if (err) + return err; + + err = -ENOMEM; + inode = ovl_new_inode(dentry->d_sb, mode, 0); + if (!inode) + goto drop_write; + + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); + err = ovl_create_tmpfile(file, dentry, inode, inode->i_mode); + if (err) + goto put_inode; + + /* + * Check if the preallocated inode was actually used. Having something + * else assigned to the dentry shouldn't happen as that would indicate + * that the backing tmpfile "leaked" out of overlayfs. + */ + err = -EIO; + if (WARN_ON(inode != d_inode(dentry))) + goto put_realfile; + + /* inode reference was transferred to dentry */ + inode = NULL; + err = finish_open(file, dentry, ovl_dummy_open); +put_realfile: + /* Without FMODE_OPENED ->release() won't be called on @file */ + if (!(file->f_mode & FMODE_OPENED)) + fput(file->private_data); +put_inode: + iput(inode); +drop_write: + ovl_drop_write(dentry); + return err; +} + const struct inode_operations ovl_dir_inode_operations = { .lookup = ovl_lookup, .mkdir = ovl_mkdir, @@ -1311,4 +1417,5 @@ const struct inode_operations ovl_dir_inode_operations = { .update_time = ovl_update_time, .fileattr_get = ovl_fileattr_get, .fileattr_set = ovl_fileattr_set, + .tmpfile = ovl_tmpfile, }; diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 611ff567a1aa..444aeeccb6da 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -23,12 +23,7 @@ static int ovl_encode_maybe_copy_up(struct dentry *dentry) if (ovl_dentry_upper(dentry)) return 0; - err = ovl_want_write(dentry); - if (!err) { - err = ovl_copy_up(dentry); - ovl_drop_write(dentry); - } - + err = ovl_copy_up(dentry); if (err) { pr_warn_ratelimited("failed to copy up on encode (%pd2, err=%i)\n", dentry, err); @@ -181,35 +176,37 @@ static int ovl_connect_layer(struct dentry *dentry) * * Return 0 for upper file handle, > 0 for lower file handle or < 0 on error. */ -static int ovl_check_encode_origin(struct dentry *dentry) +static int ovl_check_encode_origin(struct inode *inode) { - struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + struct ovl_fs *ofs = OVL_FS(inode->i_sb); bool decodable = ofs->config.nfs_export; + struct dentry *dentry; + int err; /* No upper layer? */ if (!ovl_upper_mnt(ofs)) return 1; /* Lower file handle for non-upper non-decodable */ - if (!ovl_dentry_upper(dentry) && !decodable) + if (!ovl_inode_upper(inode) && !decodable) return 1; /* Upper file handle for pure upper */ - if (!ovl_dentry_lower(dentry)) + if (!ovl_inode_lower(inode)) return 0; /* * Root is never indexed, so if there's an upper layer, encode upper for * root. */ - if (dentry == dentry->d_sb->s_root) + if (inode == d_inode(inode->i_sb->s_root)) return 0; /* * Upper decodable file handle for non-indexed upper. */ - if (ovl_dentry_upper(dentry) && decodable && - !ovl_test_flag(OVL_INDEX, d_inode(dentry))) + if (ovl_inode_upper(inode) && decodable && + !ovl_test_flag(OVL_INDEX, inode)) return 0; /* @@ -218,14 +215,23 @@ static int ovl_check_encode_origin(struct dentry *dentry) * ovl_connect_layer() will try to make origin's layer "connected" by * copying up a "connectable" ancestor. */ - if (d_is_dir(dentry) && decodable) - return ovl_connect_layer(dentry); + if (!decodable || !S_ISDIR(inode->i_mode)) + return 1; + + dentry = d_find_any_alias(inode); + if (!dentry) + return -ENOENT; + + err = ovl_connect_layer(dentry); + dput(dentry); + if (err < 0) + return err; /* Lower file handle for indexed and non-upper dir/non-dir */ return 1; } -static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, +static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct inode *inode, u32 *fid, int buflen) { struct ovl_fh *fh = NULL; @@ -236,13 +242,13 @@ static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, * Check if we should encode a lower or upper file handle and maybe * copy up an ancestor to make lower file handle connectable. */ - err = enc_lower = ovl_check_encode_origin(dentry); + err = enc_lower = ovl_check_encode_origin(inode); if (enc_lower < 0) goto fail; /* Encode an upper or lower file handle */ - fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_dentry_lower(dentry) : - ovl_dentry_upper(dentry), !enc_lower); + fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_inode_lower(inode) : + ovl_inode_upper(inode), !enc_lower); if (IS_ERR(fh)) return PTR_ERR(fh); @@ -256,8 +262,8 @@ out: return err; fail: - pr_warn_ratelimited("failed to encode file handle (%pd2, err=%i)\n", - dentry, err); + pr_warn_ratelimited("failed to encode file handle (ino=%lu, err=%i)\n", + inode->i_ino, err); goto out; } @@ -265,19 +271,13 @@ static int ovl_encode_fh(struct inode *inode, u32 *fid, int *max_len, struct inode *parent) { struct ovl_fs *ofs = OVL_FS(inode->i_sb); - struct dentry *dentry; int bytes, buflen = *max_len << 2; /* TODO: encode connectable file handles */ if (parent) return FILEID_INVALID; - dentry = d_find_any_alias(inode); - if (!dentry) - return FILEID_INVALID; - - bytes = ovl_dentry_to_fid(ofs, dentry, fid, buflen); - dput(dentry); + bytes = ovl_dentry_to_fid(ofs, inode, fid, buflen); if (bytes <= 0) return FILEID_INVALID; @@ -298,7 +298,6 @@ 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 = NULL; struct ovl_entry *oe; struct ovl_inode_params oip = { @@ -329,27 +328,7 @@ static struct dentry *ovl_obtain_alias(struct super_block *sb, if (upper) ovl_set_flag(OVL_UPPERDATA, inode); - dentry = d_find_any_alias(inode); - if (dentry) - goto out_iput; - - dentry = d_alloc_anon(inode->i_sb); - if (unlikely(!dentry)) - goto nomem; - - if (upper_alias) - ovl_dentry_set_upper_alias(dentry); - - ovl_dentry_init_reval(dentry, upper, OVL_I_E(inode)); - - return d_instantiate_anon(dentry, inode); - -nomem: - dput(dentry); - dentry = ERR_PTR(-ENOMEM); -out_iput: - iput(inode); - return dentry; + return d_obtain_alias(inode); } /* Get the upper or lower dentry in stack whose on layer @idx */ @@ -469,7 +448,7 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb, * For decoded lower dir file handle, lookup index by origin to check * if lower dir was copied up and and/or removed. */ - if (!this && layer->idx && ofs->indexdir && !WARN_ON(!d_is_dir(real))) { + if (!this && layer->idx && ovl_indexdir(sb) && !WARN_ON(!d_is_dir(real))) { index = ovl_lookup_index(ofs, NULL, real, false); if (IS_ERR(index)) return index; @@ -742,7 +721,7 @@ static struct dentry *ovl_lower_fh_to_d(struct super_block *sb, } /* Then lookup indexed upper/whiteout by origin fh */ - if (ofs->indexdir) { + if (ovl_indexdir(sb)) { index = ovl_get_index_fh(ofs, fh); err = PTR_ERR(index); if (IS_ERR(index)) { diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 8be4dc050d1e..94095058da34 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -9,20 +9,11 @@ #include <linux/xattr.h> #include <linux/uio.h> #include <linux/uaccess.h> -#include <linux/splice.h> #include <linux/security.h> -#include <linux/mm.h> #include <linux/fs.h> +#include <linux/backing-file.h> #include "overlayfs.h" -struct ovl_aio_req { - struct kiocb iocb; - refcount_t ref; - struct kiocb *orig_iocb; -}; - -static struct kmem_cache *ovl_aio_request_cachep; - static char ovl_whatisit(struct inode *inode, struct inode *realinode) { if (realinode != ovl_inode_upper(inode)) @@ -33,9 +24,6 @@ static char ovl_whatisit(struct inode *inode, struct inode *realinode) return 'm'; } -/* No atime modification on underlying */ -#define OVL_OPEN_FLAGS (O_NOATIME) - static struct file *ovl_open_realfile(const struct file *file, const struct path *realpath) { @@ -60,8 +48,8 @@ static struct file *ovl_open_realfile(const struct file *file, if (!inode_owner_or_capable(real_idmap, realinode)) flags &= ~O_NOATIME; - realfile = backing_file_open(&file->f_path, flags, realpath, - current_cred()); + realfile = backing_file_open(file_user_path((struct file *) file), + flags, realpath, current_cred()); } revert_creds(old_cred); @@ -105,11 +93,11 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real, bool allow_meta) { struct dentry *dentry = file_dentry(file); + struct file *realfile = file->private_data; struct path realpath; int err; - real->flags = 0; - real->file = file->private_data; + real->word = (unsigned long)realfile; if (allow_meta) { ovl_path_real(dentry, &realpath); @@ -125,16 +113,17 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real, return -EIO; /* Has it been copied up since we'd opened it? */ - if (unlikely(file_inode(real->file) != d_inode(realpath.dentry))) { - real->flags = FDPUT_FPUT; - real->file = ovl_open_realfile(file, &realpath); - - return PTR_ERR_OR_ZERO(real->file); + if (unlikely(file_inode(realfile) != d_inode(realpath.dentry))) { + struct file *f = ovl_open_realfile(file, &realpath); + if (IS_ERR(f)) + return PTR_ERR(f); + real->word = (unsigned long)f | FDPUT_FPUT; + return 0; } /* Did the flags change since open? */ - if (unlikely((file->f_flags ^ real->file->f_flags) & ~OVL_OPEN_FLAGS)) - return ovl_change_flags(real->file, file->f_flags); + if (unlikely((file->f_flags ^ realfile->f_flags) & ~OVL_OPEN_FLAGS)) + return ovl_change_flags(realfile, file->f_flags); return 0; } @@ -142,10 +131,11 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real, static int ovl_real_fdget(const struct file *file, struct fd *real) { if (d_is_dir(file_dentry(file))) { - real->flags = 0; - real->file = ovl_dir_real_file(file, false); - - return PTR_ERR_OR_ZERO(real->file); + struct file *f = ovl_dir_real_file(file, false); + if (IS_ERR(f)) + return PTR_ERR(f); + real->word = (unsigned long)f; + return 0; } return ovl_real_fdget_meta(file, real, false); @@ -221,13 +211,13 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence) * files, so we use the real file to perform seeks. */ ovl_inode_lock(inode); - real.file->f_pos = file->f_pos; + fd_file(real)->f_pos = file->f_pos; old_cred = ovl_override_creds(inode->i_sb); - ret = vfs_llseek(real.file, offset, whence); + ret = vfs_llseek(fd_file(real), offset, whence); revert_creds(old_cred); - file->f_pos = real.file->f_pos; + file->f_pos = fd_file(real)->f_pos; ovl_inode_unlock(inode); fdput(real); @@ -235,10 +225,22 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence) return ret; } +static void ovl_file_modified(struct file *file) +{ + /* Update size/mtime */ + ovl_copyattr(file_inode(file)); +} + +static void ovl_file_end_write(struct file *file, loff_t pos, ssize_t ret) +{ + ovl_file_modified(file); +} + static void ovl_file_accessed(struct file *file) { struct inode *inode, *upperinode; struct timespec64 ctime, uctime; + struct timespec64 mtime, umtime; if (file->f_flags & O_NOATIME) return; @@ -251,71 +253,27 @@ static void ovl_file_accessed(struct file *file) ctime = inode_get_ctime(inode); uctime = inode_get_ctime(upperinode); - if ((!timespec64_equal(&inode->i_mtime, &upperinode->i_mtime) || - !timespec64_equal(&ctime, &uctime))) { - inode->i_mtime = upperinode->i_mtime; + mtime = inode_get_mtime(inode); + umtime = inode_get_mtime(upperinode); + if ((!timespec64_equal(&mtime, &umtime)) || + !timespec64_equal(&ctime, &uctime)) { + inode_set_mtime_to_ts(inode, inode_get_mtime(upperinode)); inode_set_ctime_to_ts(inode, uctime); } touch_atime(&file->f_path); } -static rwf_t ovl_iocb_to_rwf(int ifl) -{ - rwf_t flags = 0; - - if (ifl & IOCB_NOWAIT) - flags |= RWF_NOWAIT; - if (ifl & IOCB_HIPRI) - flags |= RWF_HIPRI; - if (ifl & IOCB_DSYNC) - flags |= RWF_DSYNC; - if (ifl & IOCB_SYNC) - flags |= RWF_SYNC; - - return flags; -} - -static inline void ovl_aio_put(struct ovl_aio_req *aio_req) -{ - if (refcount_dec_and_test(&aio_req->ref)) { - fput(aio_req->iocb.ki_filp); - kmem_cache_free(ovl_aio_request_cachep, aio_req); - } -} - -static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req) -{ - struct kiocb *iocb = &aio_req->iocb; - struct kiocb *orig_iocb = aio_req->orig_iocb; - - if (iocb->ki_flags & IOCB_WRITE) { - struct inode *inode = file_inode(orig_iocb->ki_filp); - - kiocb_end_write(iocb); - ovl_copyattr(inode); - } - - orig_iocb->ki_pos = iocb->ki_pos; - ovl_aio_put(aio_req); -} - -static void ovl_aio_rw_complete(struct kiocb *iocb, long res) -{ - struct ovl_aio_req *aio_req = container_of(iocb, - struct ovl_aio_req, iocb); - struct kiocb *orig_iocb = aio_req->orig_iocb; - - ovl_aio_cleanup_handler(aio_req); - orig_iocb->ki_complete(orig_iocb, res); -} - static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct fd real; - const struct cred *old_cred; ssize_t ret; + struct backing_file_ctx ctx = { + .cred = ovl_creds(file_inode(file)->i_sb), + .user_file = file, + .accessed = ovl_file_accessed, + }; if (!iov_iter_count(iter)) return 0; @@ -324,36 +282,8 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (ret) return ret; - ret = -EINVAL; - if (iocb->ki_flags & IOCB_DIRECT && - !(real.file->f_mode & FMODE_CAN_ODIRECT)) - goto out_fdput; - - old_cred = ovl_override_creds(file_inode(file)->i_sb); - if (is_sync_kiocb(iocb)) { - ret = vfs_iter_read(real.file, iter, &iocb->ki_pos, - ovl_iocb_to_rwf(iocb->ki_flags)); - } else { - struct ovl_aio_req *aio_req; - - ret = -ENOMEM; - aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL); - if (!aio_req) - goto out; - - aio_req->orig_iocb = iocb; - kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); - aio_req->iocb.ki_complete = ovl_aio_rw_complete; - refcount_set(&aio_req->ref, 2); - ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter); - ovl_aio_put(aio_req); - if (ret != -EIOCBQUEUED) - ovl_aio_cleanup_handler(aio_req); - } -out: - revert_creds(old_cred); - ovl_file_accessed(file); -out_fdput: + ret = backing_file_read_iter(fd_file(real), iter, iocb, iocb->ki_flags, + &ctx); fdput(real); return ret; @@ -364,9 +294,13 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct fd real; - const struct cred *old_cred; ssize_t ret; int ifl = iocb->ki_flags; + struct backing_file_ctx ctx = { + .cred = ovl_creds(inode->i_sb), + .user_file = file, + .end_write = ovl_file_end_write, + }; if (!iov_iter_count(iter)) return 0; @@ -374,19 +308,11 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) inode_lock(inode); /* Update mode */ ovl_copyattr(inode); - ret = file_remove_privs(file); - if (ret) - goto out_unlock; ret = ovl_real_fdget(file, &real); if (ret) goto out_unlock; - ret = -EINVAL; - if (iocb->ki_flags & IOCB_DIRECT && - !(real.file->f_mode & FMODE_CAN_ODIRECT)) - goto out_fdput; - if (!ovl_should_sync(OVL_FS(inode->i_sb))) ifl &= ~(IOCB_DSYNC | IOCB_SYNC); @@ -395,37 +321,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) * this property in case it is set by the issuer. */ ifl &= ~IOCB_DIO_CALLER_COMP; - - old_cred = ovl_override_creds(file_inode(file)->i_sb); - if (is_sync_kiocb(iocb)) { - file_start_write(real.file); - ret = vfs_iter_write(real.file, iter, &iocb->ki_pos, - ovl_iocb_to_rwf(ifl)); - file_end_write(real.file); - /* Update size */ - ovl_copyattr(inode); - } else { - struct ovl_aio_req *aio_req; - - ret = -ENOMEM; - aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL); - if (!aio_req) - goto out; - - aio_req->orig_iocb = iocb; - kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); - aio_req->iocb.ki_flags = ifl; - aio_req->iocb.ki_complete = ovl_aio_rw_complete; - refcount_set(&aio_req->ref, 2); - kiocb_start_write(&aio_req->iocb); - ret = vfs_iocb_iter_write(real.file, &aio_req->iocb, iter); - ovl_aio_put(aio_req); - if (ret != -EIOCBQUEUED) - ovl_aio_cleanup_handler(aio_req); - } -out: - revert_creds(old_cred); -out_fdput: + ret = backing_file_write_iter(fd_file(real), iter, iocb, ifl, &ctx); fdput(real); out_unlock: @@ -438,27 +334,28 @@ static ssize_t ovl_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { - const struct cred *old_cred; struct fd real; ssize_t ret; + struct backing_file_ctx ctx = { + .cred = ovl_creds(file_inode(in)->i_sb), + .user_file = in, + .accessed = ovl_file_accessed, + }; ret = ovl_real_fdget(in, &real); if (ret) return ret; - old_cred = ovl_override_creds(file_inode(in)->i_sb); - ret = vfs_splice_read(real.file, ppos, pipe, len, flags); - revert_creds(old_cred); - ovl_file_accessed(in); - + ret = backing_file_splice_read(fd_file(real), ppos, pipe, len, flags, &ctx); fdput(real); + return ret; } /* * Calling iter_file_splice_write() directly from overlay's f_op may deadlock * due to lock order inversion between pipe->mutex in iter_file_splice_write() - * and file_start_write(real.file) in ovl_write_iter(). + * and file_start_write(fd_file(real)) in ovl_write_iter(). * * So do everything ovl_write_iter() does and call iter_file_splice_write() on * the real file. @@ -467,30 +364,23 @@ static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { struct fd real; - const struct cred *old_cred; struct inode *inode = file_inode(out); ssize_t ret; + struct backing_file_ctx ctx = { + .cred = ovl_creds(inode->i_sb), + .user_file = out, + .end_write = ovl_file_end_write, + }; inode_lock(inode); /* Update mode */ ovl_copyattr(inode); - ret = file_remove_privs(out); - if (ret) - goto out_unlock; ret = ovl_real_fdget(out, &real); if (ret) goto out_unlock; - old_cred = ovl_override_creds(inode->i_sb); - file_start_write(real.file); - - ret = iter_file_splice_write(pipe, real.file, ppos, len, flags); - - file_end_write(real.file); - /* Update size */ - ovl_copyattr(inode); - revert_creds(old_cred); + ret = backing_file_splice_write(pipe, fd_file(real), ppos, len, flags, &ctx); fdput(real); out_unlock: @@ -514,9 +404,9 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) return ret; /* Don't sync lower file for fear of receiving EROFS error */ - if (file_inode(real.file) == ovl_inode_upper(file_inode(file))) { + if (file_inode(fd_file(real)) == ovl_inode_upper(file_inode(file))) { old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = vfs_fsync_range(real.file, start, end, datasync); + ret = vfs_fsync_range(fd_file(real), start, end, datasync); revert_creds(old_cred); } @@ -528,23 +418,13 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) static int ovl_mmap(struct file *file, struct vm_area_struct *vma) { struct file *realfile = file->private_data; - const struct cred *old_cred; - int ret; - - if (!realfile->f_op->mmap) - return -ENODEV; - - if (WARN_ON(file != vma->vm_file)) - return -EIO; - - vma_set_file(vma, realfile); - - old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = call_mmap(vma->vm_file, vma); - revert_creds(old_cred); - ovl_file_accessed(file); + struct backing_file_ctx ctx = { + .cred = ovl_creds(file_inode(file)->i_sb), + .user_file = file, + .accessed = ovl_file_accessed, + }; - return ret; + return backing_file_mmap(realfile, vma, &ctx); } static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len) @@ -566,11 +446,11 @@ static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len goto out_unlock; old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = vfs_fallocate(real.file, mode, offset, len); + ret = vfs_fallocate(fd_file(real), mode, offset, len); revert_creds(old_cred); /* Update size */ - ovl_copyattr(inode); + ovl_file_modified(file); fdput(real); @@ -591,7 +471,7 @@ static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice) return ret; old_cred = ovl_override_creds(file_inode(file)->i_sb); - ret = vfs_fadvise(real.file, offset, len, advice); + ret = vfs_fadvise(fd_file(real), offset, len, advice); revert_creds(old_cred); fdput(real); @@ -636,25 +516,25 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, old_cred = ovl_override_creds(file_inode(file_out)->i_sb); switch (op) { case OVL_COPY: - ret = vfs_copy_file_range(real_in.file, pos_in, - real_out.file, pos_out, len, flags); + ret = vfs_copy_file_range(fd_file(real_in), pos_in, + fd_file(real_out), pos_out, len, flags); break; case OVL_CLONE: - ret = vfs_clone_file_range(real_in.file, pos_in, - real_out.file, pos_out, len, flags); + ret = vfs_clone_file_range(fd_file(real_in), pos_in, + fd_file(real_out), pos_out, len, flags); break; case OVL_DEDUPE: - ret = vfs_dedupe_file_range_one(real_in.file, pos_in, - real_out.file, pos_out, len, + ret = vfs_dedupe_file_range_one(fd_file(real_in), pos_in, + fd_file(real_out), pos_out, len, flags); break; } revert_creds(old_cred); /* Update size */ - ovl_copyattr(inode_out); + ovl_file_modified(file_out); fdput(real_in); fdput(real_out); @@ -710,9 +590,9 @@ static int ovl_flush(struct file *file, fl_owner_t id) if (err) return err; - if (real.file->f_op->flush) { + if (fd_file(real)->f_op->flush) { old_cred = ovl_override_creds(file_inode(file)->i_sb); - err = real.file->f_op->flush(real.file, id); + err = fd_file(real)->f_op->flush(fd_file(real), id); revert_creds(old_cred); } fdput(real); @@ -737,19 +617,3 @@ const struct file_operations ovl_file_operations = { .copy_file_range = ovl_copy_file_range, .remap_file_range = ovl_remap_file_range, }; - -int __init ovl_aio_request_cache_init(void) -{ - ovl_aio_request_cachep = kmem_cache_create("ovl_aio_req", - sizeof(struct ovl_aio_req), - 0, SLAB_HWCACHE_ALIGN, NULL); - if (!ovl_aio_request_cachep) - return -ENOMEM; - - return 0; -} - -void ovl_aio_request_cache_destroy(void) -{ - kmem_cache_destroy(ovl_aio_request_cachep); -} diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 9c42a30317d5..baa54c718bd7 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -8,7 +8,6 @@ #include <linux/slab.h> #include <linux/cred.h> #include <linux/xattr.h> -#include <linux/posix_acl.h> #include <linux/ratelimit.h> #include <linux/fiemap.h> #include <linux/fileattr.h> @@ -32,10 +31,6 @@ int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (err) return err; - err = ovl_want_write(dentry); - if (err) - goto out; - if (attr->ia_valid & ATTR_SIZE) { /* Truncate should trigger data copy up as well */ full_copy_up = true; @@ -54,7 +49,7 @@ int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry, winode = d_inode(upperdentry); err = get_write_access(winode); if (err) - goto out_drop_write; + goto out; } if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) @@ -78,6 +73,10 @@ int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry, */ attr->ia_valid &= ~ATTR_OPEN; + err = ovl_want_write(dentry); + if (err) + goto out_put_write; + inode_lock(upperdentry->d_inode); old_cred = ovl_override_creds(dentry->d_sb); err = ovl_do_notify_change(ofs, upperdentry, attr); @@ -85,12 +84,12 @@ int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (!err) ovl_copyattr(dentry->d_inode); inode_unlock(upperdentry->d_inode); + ovl_drop_write(dentry); +out_put_write: if (winode) put_write_access(winode); } -out_drop_write: - ovl_drop_write(dentry); out: return err; } @@ -339,130 +338,6 @@ static const char *ovl_get_link(struct dentry *dentry, return p; } -bool ovl_is_private_xattr(struct super_block *sb, const char *name) -{ - struct ovl_fs *ofs = OVL_FS(sb); - - if (ofs->config.userxattr) - return strncmp(name, OVL_XATTR_USER_PREFIX, - sizeof(OVL_XATTR_USER_PREFIX) - 1) == 0; - else - return strncmp(name, OVL_XATTR_TRUSTED_PREFIX, - sizeof(OVL_XATTR_TRUSTED_PREFIX) - 1) == 0; -} - -int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, - const void *value, size_t size, int flags) -{ - int err; - struct ovl_fs *ofs = OVL_FS(dentry->d_sb); - struct dentry *upperdentry = ovl_i_dentry_upper(inode); - struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry); - struct path realpath; - const struct cred *old_cred; - - err = ovl_want_write(dentry); - if (err) - goto out; - - if (!value && !upperdentry) { - ovl_path_lower(dentry, &realpath); - old_cred = ovl_override_creds(dentry->d_sb); - err = vfs_getxattr(mnt_idmap(realpath.mnt), realdentry, name, NULL, 0); - revert_creds(old_cred); - if (err < 0) - goto out_drop_write; - } - - if (!upperdentry) { - err = ovl_copy_up(dentry); - if (err) - goto out_drop_write; - - realdentry = ovl_dentry_upper(dentry); - } - - old_cred = ovl_override_creds(dentry->d_sb); - if (value) { - err = ovl_do_setxattr(ofs, realdentry, name, value, size, - flags); - } else { - WARN_ON(flags != XATTR_REPLACE); - err = ovl_do_removexattr(ofs, realdentry, name); - } - revert_creds(old_cred); - - /* copy c/mtime */ - ovl_copyattr(inode); - -out_drop_write: - ovl_drop_write(dentry); -out: - return err; -} - -int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, - void *value, size_t size) -{ - ssize_t res; - const struct cred *old_cred; - struct path realpath; - - ovl_i_path_real(inode, &realpath); - old_cred = ovl_override_creds(dentry->d_sb); - res = vfs_getxattr(mnt_idmap(realpath.mnt), realpath.dentry, name, value, size); - revert_creds(old_cred); - return res; -} - -static bool ovl_can_list(struct super_block *sb, const char *s) -{ - /* Never list private (.overlay) */ - if (ovl_is_private_xattr(sb, s)) - return false; - - /* List all non-trusted xattrs */ - if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0) - return true; - - /* list other trusted for superuser only */ - return ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); -} - -ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) -{ - struct dentry *realdentry = ovl_dentry_real(dentry); - ssize_t res; - size_t len; - char *s; - const struct cred *old_cred; - - old_cred = ovl_override_creds(dentry->d_sb); - res = vfs_listxattr(realdentry, list, size); - revert_creds(old_cred); - if (res <= 0 || size == 0) - return res; - - /* filter out private xattrs */ - for (s = list, len = res; len;) { - size_t slen = strnlen(s, len) + 1; - - /* underlying fs providing us with an broken xattr list? */ - if (WARN_ON(slen > len)) - return -EIO; - - len -= slen; - if (!ovl_can_list(dentry->d_sb, s)) { - res -= slen; - memmove(s, s + slen, len); - } else { - s += slen; - } - } - - return res; -} - #ifdef CONFIG_FS_POSIX_ACL /* * Apply the idmapping of the layer to POSIX ACLs. The caller must pass a clone @@ -611,10 +486,6 @@ static int ovl_set_or_remove_acl(struct dentry *dentry, struct inode *inode, struct dentry *upperdentry = ovl_dentry_upper(dentry); struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry); - err = ovl_want_write(dentry); - if (err) - return err; - /* * If ACL is to be removed from a lower file, check if it exists in * the first place before copying it up. @@ -630,7 +501,7 @@ static int ovl_set_or_remove_acl(struct dentry *dentry, struct inode *inode, revert_creds(old_cred); if (IS_ERR(real_acl)) { err = PTR_ERR(real_acl); - goto out_drop_write; + goto out; } posix_acl_release(real_acl); } @@ -638,23 +509,26 @@ static int ovl_set_or_remove_acl(struct dentry *dentry, struct inode *inode, if (!upperdentry) { err = ovl_copy_up(dentry); if (err) - goto out_drop_write; + goto out; realdentry = ovl_dentry_upper(dentry); } + err = ovl_want_write(dentry); + if (err) + goto out; + old_cred = ovl_override_creds(dentry->d_sb); if (acl) err = ovl_do_set_acl(ofs, realdentry, acl_name, acl); else err = ovl_do_remove_acl(ofs, realdentry, acl_name); revert_creds(old_cred); + ovl_drop_write(dentry); /* copy c/mtime */ ovl_copyattr(inode); - -out_drop_write: - ovl_drop_write(dentry); +out: return err; } @@ -704,7 +578,8 @@ int ovl_update_time(struct inode *inode, int flags) if (upperpath.dentry) { touch_atime(&upperpath); - inode->i_atime = d_inode(upperpath.dentry)->i_atime; + inode_set_atime_to_ts(inode, + inode_get_atime(d_inode(upperpath.dentry))); } } return 0; @@ -782,14 +657,14 @@ int ovl_fileattr_set(struct mnt_idmap *idmap, unsigned int flags; int err; - err = ovl_want_write(dentry); - if (err) - goto out; - err = ovl_copy_up(dentry); if (!err) { ovl_path_real(dentry, &upperpath); + err = ovl_want_write(dentry); + if (err) + goto out; + old_cred = ovl_override_creds(inode->i_sb); /* * Store immutable/append-only flags in xattr and clear them @@ -802,6 +677,7 @@ int ovl_fileattr_set(struct mnt_idmap *idmap, if (!err) err = ovl_real_fileattr_set(&upperpath, fa); revert_creds(old_cred); + ovl_drop_write(dentry); /* * Merge real inode flags with inode flags read from @@ -816,7 +692,6 @@ int ovl_fileattr_set(struct mnt_idmap *idmap, /* Update ctime */ ovl_copyattr(inode); } - ovl_drop_write(dentry); out: return err; } diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 80391c687c2a..42b73ae5ba01 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -18,10 +18,11 @@ struct ovl_lookup_data { struct super_block *sb; - struct vfsmount *mnt; + const struct ovl_layer *layer; struct qstr name; bool is_dir; bool opaque; + bool xwhiteouts; bool stop; bool last; char *redirect; @@ -201,17 +202,13 @@ struct dentry *ovl_decode_real_fh(struct ovl_fs *ofs, struct ovl_fh *fh, return real; } -static bool ovl_is_opaquedir(struct ovl_fs *ofs, const struct path *path) -{ - return ovl_path_check_dir_xattr(ofs, path, OVL_XATTR_OPAQUE); -} - static struct dentry *ovl_lookup_positive_unlocked(struct ovl_lookup_data *d, const char *name, struct dentry *base, int len, bool drop_negative) { - struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->mnt), name, base, len); + struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->layer->mnt), name, + base, len); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { if (drop_negative && ret->d_lockref.count == 1) { @@ -232,10 +229,13 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, size_t prelen, const char *post, struct dentry **ret, bool drop_negative) { + struct ovl_fs *ofs = OVL_FS(d->sb); struct dentry *this; struct path path; int err; bool last_element = !post[0]; + bool is_upper = d->layer->idx == 0; + char val; this = ovl_lookup_positive_unlocked(d, name, base, namelen, drop_negative); if (IS_ERR(this)) { @@ -251,7 +251,10 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, err = -EREMOTE; goto out_err; } - if (ovl_is_whiteout(this)) { + + path.dentry = this; + path.mnt = d->layer->mnt; + if (ovl_path_is_whiteout(ofs, &path)) { d->stop = d->opaque = true; goto put_and_out; } @@ -264,14 +267,12 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, goto put_and_out; } - path.dentry = this; - path.mnt = d->mnt; if (!d_can_lookup(this)) { if (d->is_dir || !last_element) { d->stop = true; goto put_and_out; } - err = ovl_check_metacopy_xattr(OVL_FS(d->sb), &path, NULL); + err = ovl_check_metacopy_xattr(ofs, &path, NULL); if (err < 0) goto out_err; @@ -291,7 +292,12 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, if (d->last) goto out; - if (ovl_is_opaquedir(OVL_FS(d->sb), &path)) { + /* overlay.opaque=x means xwhiteouts directory */ + val = ovl_get_opaquedir_val(ofs, &path); + if (last_element && !is_upper && val == 'x') { + d->xwhiteouts = true; + ovl_layer_set_xwhiteouts(ofs, d->layer); + } else if (val == 'y') { d->stop = true; if (last_element) d->opaque = true; @@ -438,7 +444,7 @@ int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected, else if (IS_ERR(origin)) return PTR_ERR(origin); - if (upperdentry && !ovl_is_whiteout(upperdentry) && + if (upperdentry && !ovl_upper_is_whiteout(ofs, upperdentry) && inode_wrong_type(d_inode(upperdentry), d_inode(origin)->i_mode)) goto invalid; @@ -507,6 +513,19 @@ static int ovl_verify_fh(struct ovl_fs *ofs, struct dentry *dentry, return err; } +int ovl_verify_set_fh(struct ovl_fs *ofs, struct dentry *dentry, + enum ovl_xattr ox, const struct ovl_fh *fh, + bool is_upper, bool set) +{ + int err; + + err = ovl_verify_fh(ofs, dentry, ox, fh); + if (set && err == -ENODATA) + err = ovl_setxattr(ofs, dentry, ox, fh->buf, fh->fb.len); + + return err; +} + /* * Verify that @real dentry matches the file handle stored in xattr @name. * @@ -515,24 +534,22 @@ static int ovl_verify_fh(struct ovl_fs *ofs, struct dentry *dentry, * * Return 0 on match, -ESTALE on mismatch, -ENODATA on no xattr, < 0 on error. */ -int ovl_verify_set_fh(struct ovl_fs *ofs, struct dentry *dentry, - enum ovl_xattr ox, struct dentry *real, bool is_upper, - bool set) +int ovl_verify_origin_xattr(struct ovl_fs *ofs, struct dentry *dentry, + enum ovl_xattr ox, struct dentry *real, + bool is_upper, bool set) { struct inode *inode; struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, real, is_upper); + fh = ovl_encode_real_fh(ofs, d_inode(real), is_upper); err = PTR_ERR(fh); if (IS_ERR(fh)) { fh = NULL; goto fail; } - err = ovl_verify_fh(ofs, dentry, ox, fh); - if (set && err == -ENODATA) - err = ovl_setxattr(ofs, dentry, ox, fh->buf, fh->fb.len); + err = ovl_verify_set_fh(ofs, dentry, ox, fh, is_upper, set); if (err) goto fail; @@ -548,6 +565,7 @@ fail: goto out; } + /* Get upper dentry from index */ struct dentry *ovl_index_upper(struct ovl_fs *ofs, struct dentry *index, bool connected) @@ -684,7 +702,7 @@ orphan: goto out; } -static int ovl_get_index_name_fh(struct ovl_fh *fh, struct qstr *name) +int ovl_get_index_name_fh(const struct ovl_fh *fh, struct qstr *name) { char *n, *s; @@ -720,7 +738,7 @@ int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin, struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, origin, false); + fh = ovl_encode_real_fh(ofs, d_inode(origin), false); if (IS_ERR(fh)) return PTR_ERR(fh); @@ -741,7 +759,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh) if (err) return ERR_PTR(err); - index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len); + index = lookup_positive_unlocked(name.name, ofs->workdir, name.len); kfree(name.name); if (IS_ERR(index)) { if (PTR_ERR(index) == -ENOENT) @@ -774,7 +792,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, return ERR_PTR(err); index = lookup_one_positive_unlocked(ovl_upper_mnt_idmap(ofs), name.name, - ofs->indexdir, name.len); + ofs->workdir, name.len); if (IS_ERR(index)) { err = PTR_ERR(index); if (err == -ENOENT) { @@ -850,7 +868,8 @@ fail: * Returns next layer in stack starting from top. * Returns -1 if this is the last layer. */ -int ovl_path_next(int idx, struct dentry *dentry, struct path *path) +int ovl_path_next(int idx, struct dentry *dentry, struct path *path, + const struct ovl_layer **layer) { struct ovl_entry *oe = OVL_E(dentry); struct ovl_path *lowerstack = ovl_lowerstack(oe); @@ -858,13 +877,16 @@ int ovl_path_next(int idx, struct dentry *dentry, struct path *path) BUG_ON(idx < 0); if (idx == 0) { ovl_path_upper(dentry, path); - if (path->dentry) + if (path->dentry) { + *layer = &OVL_FS(dentry->d_sb)->layers[0]; return ovl_numlower(oe) ? 1 : -1; + } idx++; } BUG_ON(idx > ovl_numlower(oe)); path->dentry = lowerstack[idx - 1].dentry; - path->mnt = lowerstack[idx - 1].layer->mnt; + *layer = lowerstack[idx - 1].layer; + path->mnt = (*layer)->mnt; return (idx < ovl_numlower(oe)) ? idx + 1 : -1; } @@ -873,20 +895,27 @@ int ovl_path_next(int idx, struct dentry *dentry, struct path *path) static int ovl_fix_origin(struct ovl_fs *ofs, struct dentry *dentry, struct dentry *lower, struct dentry *upper) { + const struct ovl_fh *fh; int err; if (ovl_check_origin_xattr(ofs, upper)) return 0; + fh = ovl_get_origin_fh(ofs, lower); + if (IS_ERR(fh)) + return PTR_ERR(fh); + err = ovl_want_write(dentry); if (err) - return err; + goto out; - err = ovl_set_origin(ofs, lower, upper); + err = ovl_set_origin_fh(ofs, fh, upper); if (!err) err = ovl_set_impure(dentry->d_parent, upper->d_parent); ovl_drop_write(dentry); +out: + kfree(fh); return err; } @@ -1035,7 +1064,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, old_cred = ovl_override_creds(dentry->d_sb); upperdir = ovl_dentry_upper(dentry->d_parent); if (upperdir) { - d.mnt = ovl_upper_mnt(ofs); + d.layer = &ofs->layers[0]; err = ovl_lookup_layer(upperdir, &d, &upperdentry, true); if (err) goto out; @@ -1091,7 +1120,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, else if (d.is_dir || !ofs->numdatalayer) d.last = lower.layer->idx == ovl_numlower(roe); - d.mnt = lower.layer->mnt; + d.layer = lower.layer; err = ovl_lookup_layer(lower.dentry, &d, &this, false); if (err) goto out_put; @@ -1258,6 +1287,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, if (upperopaque) ovl_dentry_set_opaque(dentry); + if (d.xwhiteouts) + ovl_dentry_set_xwhiteouts(dentry); if (upperdentry) ovl_dentry_set_upper_alias(dentry); @@ -1383,7 +1414,11 @@ bool ovl_lower_positive(struct dentry *dentry) break; } } else { - positive = !ovl_is_whiteout(this); + struct path path = { + .dentry = this, + .mnt = parentpath->layer->mnt, + }; + positive = !ovl_path_is_whiteout(OVL_FS(dentry->d_sb), &path); done = true; dput(this); } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 09ca82ed0f8c..500a9634ad53 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -28,7 +28,16 @@ enum ovl_path_type { #define OVL_XATTR_NAMESPACE "overlay." #define OVL_XATTR_TRUSTED_PREFIX XATTR_TRUSTED_PREFIX OVL_XATTR_NAMESPACE +#define OVL_XATTR_TRUSTED_PREFIX_LEN (sizeof(OVL_XATTR_TRUSTED_PREFIX) - 1) #define OVL_XATTR_USER_PREFIX XATTR_USER_PREFIX OVL_XATTR_NAMESPACE +#define OVL_XATTR_USER_PREFIX_LEN (sizeof(OVL_XATTR_USER_PREFIX) - 1) + +#define OVL_XATTR_ESCAPE_PREFIX OVL_XATTR_NAMESPACE +#define OVL_XATTR_ESCAPE_PREFIX_LEN (sizeof(OVL_XATTR_ESCAPE_PREFIX) - 1) +#define OVL_XATTR_ESCAPE_TRUSTED_PREFIX OVL_XATTR_TRUSTED_PREFIX OVL_XATTR_ESCAPE_PREFIX +#define OVL_XATTR_ESCAPE_TRUSTED_PREFIX_LEN (sizeof(OVL_XATTR_ESCAPE_TRUSTED_PREFIX) - 1) +#define OVL_XATTR_ESCAPE_USER_PREFIX OVL_XATTR_USER_PREFIX OVL_XATTR_ESCAPE_PREFIX +#define OVL_XATTR_ESCAPE_USER_PREFIX_LEN (sizeof(OVL_XATTR_ESCAPE_USER_PREFIX) - 1) enum ovl_xattr { OVL_XATTR_OPAQUE, @@ -40,6 +49,7 @@ enum ovl_xattr { OVL_XATTR_UUID, OVL_XATTR_METACOPY, OVL_XATTR_PROTATTR, + OVL_XATTR_XWHITEOUT, }; enum ovl_inode_flag { @@ -59,6 +69,8 @@ enum ovl_entry_flag { OVL_E_UPPER_ALIAS, OVL_E_OPAQUE, OVL_E_CONNECTED, + /* Lower stack may contain xwhiteout entries */ + OVL_E_XWHITEOUTS, }; enum { @@ -163,6 +175,9 @@ static inline int ovl_metadata_digest_size(const struct ovl_metacopy *metacopy) return (int)metacopy->len - OVL_METACOPY_MIN_SIZE; } +/* No atime modification on underlying */ +#define OVL_OPEN_FLAGS (O_NOATIME) + extern const char *const ovl_xattr_table[][2]; static inline const char *ovl_xattr(struct ovl_fs *ofs, enum ovl_xattr ox) { @@ -406,10 +421,20 @@ static inline int ovl_do_getattr(const struct path *path, struct kstat *stat, } /* util.c */ +int ovl_get_write_access(struct dentry *dentry); +void ovl_put_write_access(struct dentry *dentry); +void ovl_start_write(struct dentry *dentry); +void ovl_end_write(struct dentry *dentry); int ovl_want_write(struct dentry *dentry); void ovl_drop_write(struct dentry *dentry); struct dentry *ovl_workdir(struct dentry *dentry); const struct cred *ovl_override_creds(struct super_block *sb); + +static inline const struct cred *ovl_creds(struct super_block *sb) +{ + return OVL_FS(sb)->creator_cred; +} + int ovl_can_decode_fh(struct super_block *sb); struct dentry *ovl_indexdir(struct super_block *sb); bool ovl_index_all(struct super_block *sb); @@ -456,6 +481,10 @@ bool ovl_dentry_test_flag(unsigned long flag, struct dentry *dentry); bool ovl_dentry_is_opaque(struct dentry *dentry); bool ovl_dentry_is_whiteout(struct dentry *dentry); void ovl_dentry_set_opaque(struct dentry *dentry); +bool ovl_dentry_has_xwhiteouts(struct dentry *dentry); +void ovl_dentry_set_xwhiteouts(struct dentry *dentry); +void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs, + const struct ovl_layer *layer); bool ovl_dentry_has_upper_alias(struct dentry *dentry); void ovl_dentry_set_upper_alias(struct dentry *dentry); bool ovl_dentry_needs_data_copy_up(struct dentry *dentry, int flags); @@ -468,16 +497,28 @@ void ovl_inode_update(struct inode *inode, struct dentry *upperdentry); void ovl_dir_modified(struct dentry *dentry, bool impurity); u64 ovl_inode_version_get(struct inode *inode); bool ovl_is_whiteout(struct dentry *dentry); +bool ovl_path_is_whiteout(struct ovl_fs *ofs, const struct path *path); struct file *ovl_path_open(const struct path *path, int flags); int ovl_copy_up_start(struct dentry *dentry, int flags); void ovl_copy_up_end(struct dentry *dentry); bool ovl_already_copied_up(struct dentry *dentry, int flags); -bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path, - enum ovl_xattr ox); +char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path, + enum ovl_xattr ox); bool ovl_path_check_origin_xattr(struct ovl_fs *ofs, const struct path *path); +bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path); bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs, const struct path *upperpath); +static inline bool ovl_upper_is_whiteout(struct ovl_fs *ofs, + struct dentry *upperdentry) +{ + struct path upperpath = { + .dentry = upperdentry, + .mnt = ovl_upper_mnt(ofs), + }; + return ovl_path_is_whiteout(ofs, &upperpath); +} + static inline bool ovl_check_origin_xattr(struct ovl_fs *ofs, struct dentry *upperdentry) { @@ -506,8 +547,6 @@ int ovl_set_metacopy_xattr(struct ovl_fs *ofs, struct dentry *d, bool ovl_is_metacopy_dentry(struct dentry *dentry); char *ovl_get_redirect_xattr(struct ovl_fs *ofs, const struct path *path, int padding); int ovl_ensure_verity_loaded(struct path *path); -int ovl_get_verity_xattr(struct ovl_fs *ofs, const struct path *path, - u8 *digest_buf, int *buf_length); int ovl_validate_verity(struct ovl_fs *ofs, struct path *metapath, struct path *datapath); @@ -539,7 +578,13 @@ static inline bool ovl_is_impuredir(struct super_block *sb, .mnt = ovl_upper_mnt(ofs), }; - return ovl_path_check_dir_xattr(ofs, &upperpath, OVL_XATTR_IMPURE); + return ovl_get_dir_xattr_val(ofs, &upperpath, OVL_XATTR_IMPURE) == 'y'; +} + +static inline char ovl_get_opaquedir_val(struct ovl_fs *ofs, + const struct path *path) +{ + return ovl_get_dir_xattr_val(ofs, path, OVL_XATTR_OPAQUE); } static inline bool ovl_redirect_follow(struct ovl_fs *ofs) @@ -632,33 +677,45 @@ struct dentry *ovl_decode_real_fh(struct ovl_fs *ofs, struct ovl_fh *fh, int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected, struct dentry *upperdentry, struct ovl_path **stackp); int ovl_verify_set_fh(struct ovl_fs *ofs, struct dentry *dentry, - enum ovl_xattr ox, struct dentry *real, bool is_upper, - bool set); + enum ovl_xattr ox, const struct ovl_fh *fh, + bool is_upper, bool set); +int ovl_verify_origin_xattr(struct ovl_fs *ofs, struct dentry *dentry, + enum ovl_xattr ox, struct dentry *real, + bool is_upper, bool set); struct dentry *ovl_index_upper(struct ovl_fs *ofs, struct dentry *index, bool connected); int ovl_verify_index(struct ovl_fs *ofs, struct dentry *index); +int ovl_get_index_name_fh(const struct ovl_fh *fh, struct qstr *name); int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin, struct qstr *name); struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh); struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, struct dentry *origin, bool verify); -int ovl_path_next(int idx, struct dentry *dentry, struct path *path); +int ovl_path_next(int idx, struct dentry *dentry, struct path *path, + const struct ovl_layer **layer); int ovl_verify_lowerdata(struct dentry *dentry); struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); bool ovl_lower_positive(struct dentry *dentry); +static inline int ovl_verify_origin_fh(struct ovl_fs *ofs, struct dentry *upper, + const struct ovl_fh *fh, bool set) +{ + return ovl_verify_set_fh(ofs, upper, OVL_XATTR_ORIGIN, fh, false, set); +} + static inline int ovl_verify_origin(struct ovl_fs *ofs, struct dentry *upper, struct dentry *origin, bool set) { - return ovl_verify_set_fh(ofs, upper, OVL_XATTR_ORIGIN, origin, - false, set); + return ovl_verify_origin_xattr(ofs, upper, OVL_XATTR_ORIGIN, origin, + false, set); } static inline int ovl_verify_upper(struct ovl_fs *ofs, struct dentry *index, struct dentry *upper, bool set) { - return ovl_verify_set_fh(ofs, index, OVL_XATTR_UPPER, upper, true, set); + return ovl_verify_origin_xattr(ofs, index, OVL_XATTR_UPPER, upper, + true, set); } /* readdir.c */ @@ -692,17 +749,8 @@ int ovl_set_nlink_lower(struct dentry *dentry); unsigned int ovl_get_nlink(struct ovl_fs *ofs, struct dentry *lowerdentry, struct dentry *upperdentry, unsigned int fallback); -int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry, - struct iattr *attr); -int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, - struct kstat *stat, u32 request_mask, unsigned int flags); int ovl_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); -int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, - const void *value, size_t size, int flags); -int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, - void *value, size_t size); -ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *do_ovl_get_acl(struct mnt_idmap *idmap, @@ -807,8 +855,6 @@ struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir, /* file.c */ extern const struct file_operations ovl_file_operations; -int __init ovl_aio_request_cache_init(void); -void ovl_aio_request_cache_destroy(void); int ovl_real_fileattr_get(const struct path *realpath, struct fileattr *fa); int ovl_real_fileattr_set(const struct path *realpath, struct fileattr *fa); int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa); @@ -821,10 +867,11 @@ int ovl_copy_up_with_data(struct dentry *dentry); int ovl_maybe_copy_up(struct dentry *dentry, int flags); int ovl_copy_xattr(struct super_block *sb, const struct path *path, struct dentry *new); int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upper, struct kstat *stat); -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper); -int ovl_set_origin(struct ovl_fs *ofs, struct dentry *lower, - struct dentry *upper); +struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin); +int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, + struct dentry *upper); /* export.c */ extern const struct export_operations ovl_export_operations; @@ -838,3 +885,12 @@ static inline bool ovl_force_readonly(struct ovl_fs *ofs) { return (!ovl_upper_mnt(ofs) || !ofs->workdir); } + +/* xattr.c */ + +const struct xattr_handler * const *ovl_xattr_handlers(struct ovl_fs *ofs); +int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr); +int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags); +ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index d82d2a043da2..cb449ab310a7 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -40,6 +40,8 @@ struct ovl_layer { int idx; /* One fsid per unique underlying sb (upper fsid == 0) */ int fsid; + /* xwhiteouts were found on this layer */ + bool has_xwhiteouts; }; struct ovl_path { @@ -59,14 +61,12 @@ struct ovl_fs { unsigned int numfs; /* Number of data-only lower layers */ unsigned int numdatalayer; - const struct ovl_layer *layers; + struct ovl_layer *layers; struct ovl_sb *fs; /* workbasedir is the path at workdir= mount option */ struct dentry *workbasedir; - /* workdir is the 'work' directory under workbasedir */ + /* workdir is the 'work' or 'index' directory under workbasedir */ struct dentry *workdir; - /* index directory listing overlay inodes by origin file handle */ - struct dentry *indexdir; long namelen; /* pathnames of lower and upper dirs, for show_options */ struct ovl_config config; @@ -81,7 +81,6 @@ struct ovl_fs { /* Traps in ovl inode cache */ struct inode *workbasedir_trap; struct inode *workdir_trap; - struct inode *indexdir_trap; /* -1: disabled, 0: same fs, 1..32: number of unused ino bits */ int xino_mode; /* For allocation of non-persistent inode numbers */ diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index 21d31aaef95d..e42546c6c5df 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -139,10 +139,6 @@ static int ovl_verity_mode_def(void) return OVL_VERITY_OFF; } -#define fsparam_string_empty(NAME, OPT) \ - __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) - - const struct fs_parameter_spec ovl_parameter_spec[] = { fsparam_string_empty("lowerdir", Opt_lowerdir), fsparam_string("lowerdir+", Opt_lowerdir_add), @@ -724,10 +720,8 @@ void ovl_free_fs(struct ovl_fs *ofs) unsigned i; iput(ofs->workbasedir_trap); - iput(ofs->indexdir_trap); iput(ofs->workdir_trap); dput(ofs->whiteout); - dput(ofs->indexdir); dput(ofs->workdir); if (ofs->workdir_locked) ovl_inuse_unlock(ofs->workbasedir); diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index de39e067ae65..0ca8af060b0c 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -25,6 +25,7 @@ struct ovl_cache_entry { struct ovl_cache_entry *next_maybe_whiteout; bool is_upper; bool is_whiteout; + bool check_xwhiteout; char name[]; }; @@ -47,6 +48,7 @@ struct ovl_readdir_data { int err; bool is_upper; bool d_type_supported; + bool in_xwhiteouts_dir; }; struct ovl_dir_file { @@ -162,6 +164,8 @@ static struct ovl_cache_entry *ovl_cache_entry_new(struct ovl_readdir_data *rdd, p->ino = 0; p->is_upper = rdd->is_upper; p->is_whiteout = false; + /* Defer check for overlay.whiteout to ovl_iterate() */ + p->check_xwhiteout = rdd->in_xwhiteouts_dir && d_type == DT_REG; if (d_type == DT_CHR) { p->next_maybe_whiteout = rdd->first_maybe_whiteout; @@ -353,10 +357,13 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list, .is_lowest = false, }; int idx, next; + const struct ovl_layer *layer; for (idx = 0; idx != -1; idx = next) { - next = ovl_path_next(idx, dentry, &realpath); + next = ovl_path_next(idx, dentry, &realpath, &layer); rdd.is_upper = ovl_dentry_upper(dentry) == realpath.dentry; + rdd.in_xwhiteouts_dir = layer->has_xwhiteouts && + ovl_dentry_has_xwhiteouts(dentry); if (next != -1) { err = ovl_dir_read(&realpath, &rdd); @@ -447,7 +454,7 @@ static u64 ovl_remap_lower_ino(u64 ino, int xinobits, int fsid, } /* - * Set d_ino for upper entries. Non-upper entries should always report + * Set d_ino for upper entries if needed. Non-upper entries should always report * the uppermost real inode ino and should not call this function. * * When not all layer are on same fs, report real ino also for upper. @@ -455,8 +462,11 @@ static u64 ovl_remap_lower_ino(u64 ino, int xinobits, int fsid, * When all layers are on the same fs, and upper has a reference to * copy up origin, call vfs_getattr() on the overlay entry to make * sure that d_ino will be consistent with st_ino from stat(2). + * + * Also checks the overlay.whiteout xattr by doing a full lookup which will return + * negative in this case. */ -static int ovl_cache_update_ino(const struct path *path, struct ovl_cache_entry *p) +static int ovl_cache_update(const struct path *path, struct ovl_cache_entry *p, bool update_ino) { struct dentry *dir = path->dentry; @@ -467,7 +477,7 @@ static int ovl_cache_update_ino(const struct path *path, struct ovl_cache_entry int xinobits = ovl_xino_bits(ofs); int err = 0; - if (!ovl_same_dev(ofs)) + if (!ovl_same_dev(ofs) && !p->check_xwhiteout) goto out; if (p->name[0] == '.') { @@ -481,6 +491,7 @@ static int ovl_cache_update_ino(const struct path *path, struct ovl_cache_entry goto get; } } + /* This checks also for xwhiteouts */ this = lookup_one(mnt_idmap(path->mnt), p->name, dir, p->len); if (IS_ERR_OR_NULL(this) || !this->d_inode) { /* Mark a stale entry */ @@ -494,6 +505,9 @@ static int ovl_cache_update_ino(const struct path *path, struct ovl_cache_entry } get: + if (!ovl_same_dev(ofs) || !update_ino) + goto out; + type = ovl_path_type(this); if (OVL_TYPE_ORIGIN(type)) { struct kstat stat; @@ -572,7 +586,7 @@ static int ovl_dir_read_impure(const struct path *path, struct list_head *list, list_for_each_entry_safe(p, n, list, l_node) { if (strcmp(p->name, ".") != 0 && strcmp(p->name, "..") != 0) { - err = ovl_cache_update_ino(path, p); + err = ovl_cache_update(path, p, true); if (err) return err; } @@ -778,13 +792,13 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx) while (od->cursor != &od->cache->entries) { p = list_entry(od->cursor, struct ovl_cache_entry, l_node); if (!p->is_whiteout) { - if (!p->ino) { - err = ovl_cache_update_ino(&file->f_path, p); + if (!p->ino || p->check_xwhiteout) { + err = ovl_cache_update(&file->f_path, p, !p->ino); if (err) goto out; } } - /* ovl_cache_update_ino() sets is_whiteout on stale entry */ + /* ovl_cache_update() sets is_whiteout on stale entry */ if (!p->is_whiteout) { if (!dir_emit(ctx, p->name, p->len, p->ino, p->type)) break; @@ -1156,7 +1170,7 @@ int ovl_workdir_cleanup(struct ovl_fs *ofs, struct inode *dir, int ovl_indexdir_cleanup(struct ovl_fs *ofs) { int err; - struct dentry *indexdir = ofs->indexdir; + struct dentry *indexdir = ofs->workdir; struct dentry *index = NULL; struct inode *dir = indexdir->d_inode; struct path path = { .mnt = ovl_upper_mnt(ofs), .dentry = indexdir }; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 2c056d737c27..87a36c6eea5f 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -28,33 +28,38 @@ MODULE_LICENSE("GPL"); struct ovl_dir_cache; -static struct dentry *ovl_d_real(struct dentry *dentry, - const struct inode *inode) +static struct dentry *ovl_d_real(struct dentry *dentry, enum d_real_type type) { - struct dentry *real = NULL, *lower; + struct dentry *upper, *lower; int err; - /* It's an overlay file */ - if (inode && d_inode(dentry) == inode) - return dentry; + switch (type) { + case D_REAL_DATA: + case D_REAL_METADATA: + break; + default: + goto bug; + } if (!d_is_reg(dentry)) { - if (!inode || inode == d_inode(dentry)) - return dentry; - goto bug; + /* d_real_inode() is only relevant for regular files */ + return dentry; } - real = ovl_dentry_upper(dentry); - if (real && (inode == d_inode(real))) - return real; + upper = ovl_dentry_upper(dentry); + if (upper && (type == D_REAL_METADATA || + ovl_has_upperdata(d_inode(dentry)))) + return upper; - if (real && !inode && ovl_has_upperdata(d_inode(dentry))) - return real; + if (type == D_REAL_METADATA) { + lower = ovl_dentry_lower(dentry); + goto real_lower; + } /* - * Best effort lazy lookup of lowerdata for !inode case to return + * Best effort lazy lookup of lowerdata for D_REAL_DATA case to return * the real lowerdata dentry. The only current caller of d_real() with - * NULL inode is d_real_inode() from trace_uprobe and this caller is + * D_REAL_DATA is d_real_inode() from trace_uprobe and this caller is * likely going to be followed reading from the file, before placing * uprobes on offset within the file, so lowerdata should be available * when setting the uprobe. @@ -65,18 +70,13 @@ static struct dentry *ovl_d_real(struct dentry *dentry, lower = ovl_dentry_lowerdata(dentry); if (!lower) goto bug; - real = lower; - /* Handle recursion */ - real = d_real(real, inode); +real_lower: + /* Handle recursion into stacked lower fs */ + return d_real(lower, type); - if (!inode || inode == d_inode(real)) - return real; bug: - WARN(1, "%s(%pd4, %s:%lu): real dentry (%p/%lu) not found\n", - __func__, dentry, inode ? inode->i_sb->s_id : "NULL", - inode ? inode->i_ino : 0, real, - real && d_inode(real) ? d_inode(real)->i_ino : 0); + WARN(1, "%s(%pd4, %d): real dentry not found\n", __func__, dentry, type); return dentry; } @@ -202,15 +202,9 @@ static int ovl_sync_fs(struct super_block *sb, int wait) int ret; ret = ovl_sync_status(ofs); - /* - * We have to always set the err, because the return value isn't - * checked in syncfs, and instead indirectly return an error via - * the sb's writeback errseq, which VFS inspects after this call. - */ - if (ret < 0) { - errseq_set(&sb->s_wb_err, -EIO); + + if (ret < 0) return -EIO; - } if (!ret) return ret; @@ -431,74 +425,14 @@ static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir) bool ok = false; if (workdir != upperdir) { - ok = (lock_rename(workdir, upperdir) == NULL); - unlock_rename(workdir, upperdir); + struct dentry *trap = lock_rename(workdir, upperdir); + if (!IS_ERR(trap)) + unlock_rename(workdir, upperdir); + ok = (trap == NULL); } return ok; } -static int ovl_own_xattr_get(const struct xattr_handler *handler, - struct dentry *dentry, struct inode *inode, - const char *name, void *buffer, size_t size) -{ - return -EOPNOTSUPP; -} - -static int ovl_own_xattr_set(const struct xattr_handler *handler, - struct mnt_idmap *idmap, - struct dentry *dentry, struct inode *inode, - const char *name, const void *value, - size_t size, int flags) -{ - return -EOPNOTSUPP; -} - -static int ovl_other_xattr_get(const struct xattr_handler *handler, - struct dentry *dentry, struct inode *inode, - const char *name, void *buffer, size_t size) -{ - return ovl_xattr_get(dentry, inode, name, buffer, size); -} - -static int ovl_other_xattr_set(const struct xattr_handler *handler, - struct mnt_idmap *idmap, - struct dentry *dentry, struct inode *inode, - const char *name, const void *value, - size_t size, int flags) -{ - return ovl_xattr_set(dentry, inode, name, value, size, flags); -} - -static const struct xattr_handler ovl_own_trusted_xattr_handler = { - .prefix = OVL_XATTR_TRUSTED_PREFIX, - .get = ovl_own_xattr_get, - .set = ovl_own_xattr_set, -}; - -static const struct xattr_handler ovl_own_user_xattr_handler = { - .prefix = OVL_XATTR_USER_PREFIX, - .get = ovl_own_xattr_get, - .set = ovl_own_xattr_set, -}; - -static const struct xattr_handler ovl_other_xattr_handler = { - .prefix = "", /* catch all */ - .get = ovl_other_xattr_get, - .set = ovl_other_xattr_set, -}; - -static const struct xattr_handler *ovl_trusted_xattr_handlers[] = { - &ovl_own_trusted_xattr_handler, - &ovl_other_xattr_handler, - NULL -}; - -static const struct xattr_handler *ovl_user_xattr_handlers[] = { - &ovl_own_user_xattr_handler, - &ovl_other_xattr_handler, - NULL -}; - static int ovl_setup_trap(struct super_block *sb, struct dentry *dir, struct inode **ptrap, const char *name) { @@ -639,7 +573,7 @@ static int ovl_check_rename_whiteout(struct ovl_fs *ofs) if (IS_ERR(whiteout)) goto cleanup_temp; - err = ovl_is_whiteout(whiteout); + err = ovl_upper_is_whiteout(ofs, whiteout); /* Best effort cleanup of whiteout and temp file */ if (err) @@ -879,15 +813,20 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs, { struct vfsmount *mnt = ovl_upper_mnt(ofs); struct dentry *indexdir; + struct dentry *origin = ovl_lowerstack(oe)->dentry; + const struct ovl_fh *fh; int err; + fh = ovl_get_origin_fh(ofs, origin); + if (IS_ERR(fh)) + return PTR_ERR(fh); + err = mnt_want_write(mnt); if (err) - return err; + goto out_free_fh; /* Verify lower root is upper root origin */ - err = ovl_verify_origin(ofs, upperpath->dentry, - ovl_lowerstack(oe)->dentry, true); + err = ovl_verify_origin_fh(ofs, upperpath->dentry, fh, true); if (err) { pr_err("failed to verify upper root origin\n"); goto out; @@ -902,10 +841,8 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs, if (IS_ERR(indexdir)) { err = PTR_ERR(indexdir); } else if (indexdir) { - ofs->indexdir = indexdir; - ofs->workdir = dget(indexdir); - - err = ovl_setup_trap(sb, ofs->indexdir, &ofs->indexdir_trap, + ofs->workdir = indexdir; + err = ovl_setup_trap(sb, indexdir, &ofs->workdir_trap, "indexdir"); if (err) goto out; @@ -918,15 +855,15 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs, * ".overlay.upper" to indicate that index may have * directory entries. */ - if (ovl_check_origin_xattr(ofs, ofs->indexdir)) { - err = ovl_verify_set_fh(ofs, ofs->indexdir, - OVL_XATTR_ORIGIN, - upperpath->dentry, true, false); + if (ovl_check_origin_xattr(ofs, indexdir)) { + err = ovl_verify_origin_xattr(ofs, indexdir, + OVL_XATTR_ORIGIN, + upperpath->dentry, true, + false); if (err) pr_err("failed to verify index dir 'origin' xattr\n"); } - err = ovl_verify_upper(ofs, ofs->indexdir, upperpath->dentry, - true); + err = ovl_verify_upper(ofs, indexdir, upperpath->dentry, true); if (err) pr_err("failed to verify index dir 'upper' xattr\n"); @@ -934,11 +871,13 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs, if (!err) err = ovl_indexdir_cleanup(ofs); } - if (err || !ofs->indexdir) + if (err || !indexdir) pr_warn("try deleting index dir or mounting with '-o index=off' to disable inodes index.\n"); out: mnt_drop_write(mnt); +out_free_fh: + kfree(fh); return err; } @@ -1180,6 +1119,11 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb, return ERR_PTR(-EINVAL); } + if (ctx->nr == ctx->nr_data) { + pr_err("at least one non-data lowerdir is required\n"); + return ERR_PTR(-EINVAL); + } + err = -EINVAL; for (i = 0; i < ctx->nr; i++) { l = &ctx->lower[i]; @@ -1296,6 +1240,7 @@ static struct dentry *ovl_get_root(struct super_block *sb, struct ovl_entry *oe) { struct dentry *root; + struct ovl_fs *ofs = OVL_FS(sb); struct ovl_path *lowerpath = ovl_lowerstack(oe); unsigned long ino = d_inode(lowerpath->dentry)->i_ino; int fsid = lowerpath->layer->fsid; @@ -1317,6 +1262,20 @@ static struct dentry *ovl_get_root(struct super_block *sb, ovl_set_flag(OVL_IMPURE, d_inode(root)); } + /* Look for xwhiteouts marker except in the lowermost layer */ + for (int i = 0; i < ovl_numlower(oe) - 1; i++, lowerpath++) { + struct path path = { + .mnt = lowerpath->layer->mnt, + .dentry = lowerpath->dentry, + }; + + /* overlay.opaque=x means xwhiteouts directory */ + if (ovl_get_opaquedir_val(ofs, &path) == 'x') { + ovl_layer_set_xwhiteouts(ofs, lowerpath->layer); + ovl_dentry_set_xwhiteouts(root); + } + } + /* Root is always merge -> can have whiteouts */ ovl_set_flag(OVL_WHITEOUTS, d_inode(root)); ovl_dentry_set_flag(OVL_E_CONNECTED, root); @@ -1452,7 +1411,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) goto out_free_oe; /* Force r/o mount with no index dir */ - if (!ofs->indexdir) + if (!ofs->workdir) sb->s_flags |= SB_RDONLY; } @@ -1461,7 +1420,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) goto out_free_oe; /* Show index=off in /proc/mounts for forced r/o mount */ - if (!ofs->indexdir) { + if (!ofs->workdir) { ofs->config.index = false; if (ovl_upper_mnt(ofs) && ofs->config.nfs_export) { pr_warn("NFS export requires an index dir, falling back to nfs_export=off.\n"); @@ -1488,11 +1447,19 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) cap_lower(cred->cap_effective, CAP_SYS_RESOURCE); sb->s_magic = OVERLAYFS_SUPER_MAGIC; - sb->s_xattr = ofs->config.userxattr ? ovl_user_xattr_handlers : - ovl_trusted_xattr_handlers; + sb->s_xattr = ovl_xattr_handlers(ofs); sb->s_fs_info = ofs; +#ifdef CONFIG_FS_POSIX_ACL sb->s_flags |= SB_POSIXACL; +#endif sb->s_iflags |= SB_I_SKIP_SYNC; + /* + * Ensure that umask handling is done by the filesystems used + * for the the upper layer instead of overlayfs as that would + * lead to unexpected results. + */ + sb->s_iflags |= SB_I_NOUMASK; + sb->s_iflags |= SB_I_EVM_HMAC_UNSUPPORTED; err = -ENOMEM; root_dentry = ovl_get_root(sb, ctx->upper.dentry, oe); @@ -1535,19 +1502,15 @@ static int __init ovl_init(void) ovl_inode_cachep = kmem_cache_create("ovl_inode", sizeof(struct ovl_inode), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_ACCOUNT), + SLAB_ACCOUNT), ovl_inode_init_once); if (ovl_inode_cachep == NULL) return -ENOMEM; - err = ovl_aio_request_cache_init(); - if (!err) { - err = register_filesystem(&ovl_fs_type); - if (!err) - return 0; + err = register_filesystem(&ovl_fs_type); + if (!err) + return 0; - ovl_aio_request_cache_destroy(); - } kmem_cache_destroy(ovl_inode_cachep); return err; @@ -1563,7 +1526,6 @@ static void __exit ovl_exit(void) */ rcu_barrier(); kmem_cache_destroy(ovl_inode_cachep); - ovl_aio_request_cache_destroy(); } module_init(ovl_init); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 0bf3ffcd072f..99571de665dd 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -17,12 +17,38 @@ #include <linux/ratelimit.h> #include "overlayfs.h" +/* Get write access to upper mnt - may fail if upper sb was remounted ro */ +int ovl_get_write_access(struct dentry *dentry) +{ + struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + return mnt_get_write_access(ovl_upper_mnt(ofs)); +} + +/* Get write access to upper sb - may block if upper sb is frozen */ +void ovl_start_write(struct dentry *dentry) +{ + struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + sb_start_write(ovl_upper_mnt(ofs)->mnt_sb); +} + int ovl_want_write(struct dentry *dentry) { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); return mnt_want_write(ovl_upper_mnt(ofs)); } +void ovl_put_write_access(struct dentry *dentry) +{ + struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + mnt_put_write_access(ovl_upper_mnt(ofs)); +} + +void ovl_end_write(struct dentry *dentry) +{ + struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + sb_end_write(ovl_upper_mnt(ofs)->mnt_sb); +} + void ovl_drop_write(struct dentry *dentry) { struct ovl_fs *ofs = OVL_FS(dentry->d_sb); @@ -55,7 +81,7 @@ int ovl_can_decode_fh(struct super_block *sb) if (!capable(CAP_DAC_READ_SEARCH)) return 0; - if (!sb->s_export_op || !sb->s_export_op->fh_to_dentry) + if (!exportfs_can_decode_fh(sb->s_export_op)) return 0; return sb->s_export_op->encode_fh ? -1 : FILEID_INO32_GEN; @@ -65,7 +91,7 @@ struct dentry *ovl_indexdir(struct super_block *sb) { struct ovl_fs *ofs = OVL_FS(sb); - return ofs->indexdir; + return ofs->config.index ? ofs->workdir : NULL; } /* Index all files on copy up. For now only enabled for NFS export */ @@ -274,7 +300,9 @@ enum ovl_path_type ovl_path_realdata(struct dentry *dentry, struct path *path) struct dentry *ovl_dentry_upper(struct dentry *dentry) { - return ovl_upperdentry_dereference(OVL_I(d_inode(dentry))); + struct inode *inode = d_inode(dentry); + + return inode ? ovl_upperdentry_dereference(OVL_I(inode)) : NULL; } struct dentry *ovl_dentry_lower(struct dentry *dentry) @@ -438,6 +466,33 @@ void ovl_dentry_set_opaque(struct dentry *dentry) ovl_dentry_set_flag(OVL_E_OPAQUE, dentry); } +bool ovl_dentry_has_xwhiteouts(struct dentry *dentry) +{ + return ovl_dentry_test_flag(OVL_E_XWHITEOUTS, dentry); +} + +void ovl_dentry_set_xwhiteouts(struct dentry *dentry) +{ + ovl_dentry_set_flag(OVL_E_XWHITEOUTS, dentry); +} + +/* + * ovl_layer_set_xwhiteouts() is called before adding the overlay dir + * dentry to dcache, while readdir of that same directory happens after + * the overlay dir dentry is in dcache, so if some cpu observes that + * ovl_dentry_is_xwhiteouts(), it will also observe layer->has_xwhiteouts + * for the layers where xwhiteouts marker was found in that merge dir. + */ +void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs, + const struct ovl_layer *layer) +{ + if (layer->has_xwhiteouts) + return; + + /* Write once to read-mostly layer properties */ + ofs->layers[layer->idx].has_xwhiteouts = true; +} + /* * For hard links and decoded file handles, it's possible for ovl_dentry_upper() * to return positive, while there's no actual upper alias for the inode. @@ -578,6 +633,16 @@ bool ovl_is_whiteout(struct dentry *dentry) return inode && IS_WHITEOUT(inode); } +/* + * Use this over ovl_is_whiteout for upper and lower files, as it also + * handles overlay.whiteout xattr whiteout files. + */ +bool ovl_path_is_whiteout(struct ovl_fs *ofs, const struct path *path) +{ + return ovl_is_whiteout(path->dentry) || + ovl_path_check_xwhiteout_xattr(ofs, path); +} + struct file *ovl_path_open(const struct path *path, int flags) { struct inode *inode = d_inode(path->dentry); @@ -647,22 +712,36 @@ bool ovl_already_copied_up(struct dentry *dentry, int flags) return false; } +/* + * The copy up "transaction" keeps an elevated mnt write count on upper mnt, + * but leaves taking freeze protection on upper sb to lower level helpers. + */ int ovl_copy_up_start(struct dentry *dentry, int flags) { struct inode *inode = d_inode(dentry); int err; err = ovl_inode_lock_interruptible(inode); - if (!err && ovl_already_copied_up_locked(dentry, flags)) { + if (err) + return err; + + if (ovl_already_copied_up_locked(dentry, flags)) err = 1; /* Already copied up */ - ovl_inode_unlock(inode); - } + else + err = ovl_get_write_access(dentry); + if (err) + goto out_unlock; + + return 0; +out_unlock: + ovl_inode_unlock(inode); return err; } void ovl_copy_up_end(struct dentry *dentry) { + ovl_put_write_access(dentry); ovl_inode_unlock(d_inode(dentry)); } @@ -679,6 +758,19 @@ bool ovl_path_check_origin_xattr(struct ovl_fs *ofs, const struct path *path) return false; } +bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path) +{ + struct dentry *dentry = path->dentry; + int res; + + /* xattr.whiteout must be a zero size regular file */ + if (!d_is_reg(dentry) || i_size_read(d_inode(dentry)) != 0) + return false; + + res = ovl_path_getxattr(ofs, path, OVL_XATTR_XWHITEOUT, NULL, 0); + return res >= 0; +} + /* * Load persistent uuid from xattr into s_uuid if found, or store a new * random generated value in s_uuid and in xattr. @@ -687,13 +779,14 @@ bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs, const struct path *upperpath) { bool set = false; + uuid_t uuid; int res; /* Try to load existing persistent uuid */ - res = ovl_path_getxattr(ofs, upperpath, OVL_XATTR_UUID, sb->s_uuid.b, + res = ovl_path_getxattr(ofs, upperpath, OVL_XATTR_UUID, uuid.b, UUID_SIZE); if (res == UUID_SIZE) - return true; + goto set_uuid; if (res != -ENODATA) goto fail; @@ -721,37 +814,37 @@ bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs, } /* Generate overlay instance uuid */ - uuid_gen(&sb->s_uuid); + uuid_gen(&uuid); /* Try to store persistent uuid */ set = true; - res = ovl_setxattr(ofs, upperpath->dentry, OVL_XATTR_UUID, sb->s_uuid.b, + res = ovl_setxattr(ofs, upperpath->dentry, OVL_XATTR_UUID, uuid.b, UUID_SIZE); - if (res == 0) - return true; + if (res) + goto fail; + +set_uuid: + super_set_uuid(sb, uuid.b, sizeof(uuid)); + return true; fail: - memset(sb->s_uuid.b, 0, UUID_SIZE); ofs->config.uuid = OVL_UUID_NULL; pr_warn("failed to %s uuid (%pd2, err=%i); falling back to uuid=null.\n", set ? "set" : "get", upperpath->dentry, res); return false; } -bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path, - enum ovl_xattr ox) +char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path, + enum ovl_xattr ox) { int res; char val; if (!d_is_dir(path->dentry)) - return false; + return 0; res = ovl_path_getxattr(ofs, path, ox, &val, 1); - if (res == 1 && val == 'y') - return true; - - return false; + return res == 1 ? val : 0; } #define OVL_XATTR_OPAQUE_POSTFIX "opaque" @@ -763,6 +856,7 @@ bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path, #define OVL_XATTR_UUID_POSTFIX "uuid" #define OVL_XATTR_METACOPY_POSTFIX "metacopy" #define OVL_XATTR_PROTATTR_POSTFIX "protattr" +#define OVL_XATTR_XWHITEOUT_POSTFIX "whiteout" #define OVL_XATTR_TAB_ENTRY(x) \ [x] = { [false] = OVL_XATTR_TRUSTED_PREFIX x ## _POSTFIX, \ @@ -778,6 +872,7 @@ const char *const ovl_xattr_table[][2] = { OVL_XATTR_TAB_ENTRY(OVL_XATTR_UUID), OVL_XATTR_TAB_ENTRY(OVL_XATTR_METACOPY), OVL_XATTR_TAB_ENTRY(OVL_XATTR_PROTATTR), + OVL_XATTR_TAB_ENTRY(OVL_XATTR_XWHITEOUT), }; int ovl_check_setxattr(struct ovl_fs *ofs, struct dentry *upperdentry, @@ -901,7 +996,7 @@ int ovl_set_protattr(struct inode *inode, struct dentry *upper, return 0; } -/** +/* * Caller must hold a reference to inode to prevent it from being freed while * it is marked inuse. */ @@ -976,12 +1071,18 @@ static void ovl_cleanup_index(struct dentry *dentry) struct dentry *index = NULL; struct inode *inode; struct qstr name = { }; + bool got_write = false; int err; err = ovl_get_index_name(ofs, lowerdentry, &name); if (err) goto fail; + err = ovl_want_write(dentry); + if (err) + goto fail; + + got_write = true; inode = d_inode(upperdentry); if (!S_ISDIR(inode->i_mode) && inode->i_nlink != 1) { pr_warn_ratelimited("cleanup linked index (%pd2, ino=%lu, nlink=%u)\n", @@ -1019,6 +1120,8 @@ static void ovl_cleanup_index(struct dentry *dentry) goto fail; out: + if (got_write) + ovl_drop_write(dentry); kfree(name.name); dput(index); return; @@ -1065,8 +1168,12 @@ int ovl_nlink_start(struct dentry *dentry) if (err) return err; + err = ovl_want_write(dentry); + if (err) + goto out_unlock; + if (d_is_dir(dentry) || !ovl_test_flag(OVL_INDEX, inode)) - goto out; + return 0; old_cred = ovl_override_creds(dentry->d_sb); /* @@ -1077,10 +1184,15 @@ int ovl_nlink_start(struct dentry *dentry) */ err = ovl_set_nlink_upper(dentry); revert_creds(old_cred); - -out: if (err) - ovl_inode_unlock(inode); + goto out_drop_write; + + return 0; + +out_drop_write: + ovl_drop_write(dentry); +out_unlock: + ovl_inode_unlock(inode); return err; } @@ -1089,6 +1201,8 @@ void ovl_nlink_end(struct dentry *dentry) { struct inode *inode = d_inode(dentry); + ovl_drop_write(dentry); + if (ovl_test_flag(OVL_INDEX, inode) && inode->i_nlink == 0) { const struct cred *old_cred; @@ -1102,12 +1216,17 @@ void ovl_nlink_end(struct dentry *dentry) int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir) { + struct dentry *trap; + /* Workdir should not be the same as upperdir */ if (workdir == upperdir) goto err; /* Workdir should not be subdir of upperdir and vice versa */ - if (lock_rename(workdir, upperdir) != NULL) + trap = lock_rename(workdir, upperdir); + if (IS_ERR(trap)) + goto err; + if (trap) goto err_unlock; return 0; @@ -1262,7 +1381,7 @@ int ovl_ensure_verity_loaded(struct path *datapath) * If this inode was not yet opened, the verity info hasn't been * loaded yet, so we need to do that here to force it into memory. */ - filp = kernel_file_open(datapath, O_RDONLY, inode, current_cred()); + filp = kernel_file_open(datapath, O_RDONLY, current_cred()); if (IS_ERR(filp)) return PTR_ERR(filp); fput(filp); @@ -1406,14 +1525,16 @@ void ovl_copyattr(struct inode *inode) realinode = ovl_i_path_real(inode, &realpath); real_idmap = mnt_idmap(realpath.mnt); + spin_lock(&inode->i_lock); vfsuid = i_uid_into_vfsuid(real_idmap, realinode); vfsgid = i_gid_into_vfsgid(real_idmap, realinode); inode->i_uid = vfsuid_into_kuid(vfsuid); inode->i_gid = vfsgid_into_kgid(vfsgid); inode->i_mode = realinode->i_mode; - inode->i_atime = realinode->i_atime; - inode->i_mtime = realinode->i_mtime; + inode_set_atime_to_ts(inode, inode_get_atime(realinode)); + inode_set_mtime_to_ts(inode, inode_get_mtime(realinode)); inode_set_ctime_to_ts(inode, inode_get_ctime(realinode)); i_size_write(inode, i_size_read(realinode)); + spin_unlock(&inode->i_lock); } diff --git a/fs/overlayfs/xattrs.c b/fs/overlayfs/xattrs.c new file mode 100644 index 000000000000..383978e4663c --- /dev/null +++ b/fs/overlayfs/xattrs.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/fs.h> +#include <linux/xattr.h> +#include "overlayfs.h" + +static bool ovl_is_escaped_xattr(struct super_block *sb, const char *name) +{ + struct ovl_fs *ofs = sb->s_fs_info; + + if (ofs->config.userxattr) + return strncmp(name, OVL_XATTR_ESCAPE_USER_PREFIX, + OVL_XATTR_ESCAPE_USER_PREFIX_LEN) == 0; + else + return strncmp(name, OVL_XATTR_ESCAPE_TRUSTED_PREFIX, + OVL_XATTR_ESCAPE_TRUSTED_PREFIX_LEN - 1) == 0; +} + +static bool ovl_is_own_xattr(struct super_block *sb, const char *name) +{ + struct ovl_fs *ofs = OVL_FS(sb); + + if (ofs->config.userxattr) + return strncmp(name, OVL_XATTR_USER_PREFIX, + OVL_XATTR_USER_PREFIX_LEN) == 0; + else + return strncmp(name, OVL_XATTR_TRUSTED_PREFIX, + OVL_XATTR_TRUSTED_PREFIX_LEN) == 0; +} + +bool ovl_is_private_xattr(struct super_block *sb, const char *name) +{ + return ovl_is_own_xattr(sb, name) && !ovl_is_escaped_xattr(sb, name); +} + +static int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + int err; + struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + struct dentry *upperdentry = ovl_i_dentry_upper(inode); + struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry); + struct path realpath; + const struct cred *old_cred; + + if (!value && !upperdentry) { + ovl_path_lower(dentry, &realpath); + old_cred = ovl_override_creds(dentry->d_sb); + err = vfs_getxattr(mnt_idmap(realpath.mnt), realdentry, name, NULL, 0); + revert_creds(old_cred); + if (err < 0) + goto out; + } + + if (!upperdentry) { + err = ovl_copy_up(dentry); + if (err) + goto out; + + realdentry = ovl_dentry_upper(dentry); + } + + err = ovl_want_write(dentry); + if (err) + goto out; + + old_cred = ovl_override_creds(dentry->d_sb); + if (value) { + err = ovl_do_setxattr(ofs, realdentry, name, value, size, + flags); + } else { + WARN_ON(flags != XATTR_REPLACE); + err = ovl_do_removexattr(ofs, realdentry, name); + } + revert_creds(old_cred); + ovl_drop_write(dentry); + + /* copy c/mtime */ + ovl_copyattr(inode); +out: + return err; +} + +static int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, + void *value, size_t size) +{ + ssize_t res; + const struct cred *old_cred; + struct path realpath; + + ovl_i_path_real(inode, &realpath); + old_cred = ovl_override_creds(dentry->d_sb); + res = vfs_getxattr(mnt_idmap(realpath.mnt), realpath.dentry, name, value, size); + revert_creds(old_cred); + return res; +} + +static bool ovl_can_list(struct super_block *sb, const char *s) +{ + /* Never list private (.overlay) */ + if (ovl_is_private_xattr(sb, s)) + return false; + + /* List all non-trusted xattrs */ + if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0) + return true; + + /* list other trusted for superuser only */ + return ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); +} + +ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) +{ + struct dentry *realdentry = ovl_dentry_real(dentry); + struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + ssize_t res; + size_t len; + char *s; + const struct cred *old_cred; + size_t prefix_len, name_len; + + old_cred = ovl_override_creds(dentry->d_sb); + res = vfs_listxattr(realdentry, list, size); + revert_creds(old_cred); + if (res <= 0 || size == 0) + return res; + + prefix_len = ofs->config.userxattr ? + OVL_XATTR_USER_PREFIX_LEN : OVL_XATTR_TRUSTED_PREFIX_LEN; + + /* filter out private xattrs */ + for (s = list, len = res; len;) { + size_t slen = strnlen(s, len) + 1; + + /* underlying fs providing us with an broken xattr list? */ + if (WARN_ON(slen > len)) + return -EIO; + + len -= slen; + if (!ovl_can_list(dentry->d_sb, s)) { + res -= slen; + memmove(s, s + slen, len); + } else if (ovl_is_escaped_xattr(dentry->d_sb, s)) { + res -= OVL_XATTR_ESCAPE_PREFIX_LEN; + name_len = slen - prefix_len - OVL_XATTR_ESCAPE_PREFIX_LEN; + s += prefix_len; + memmove(s, s + OVL_XATTR_ESCAPE_PREFIX_LEN, name_len + len); + s += name_len; + } else { + s += slen; + } + } + + return res; +} + +static char *ovl_xattr_escape_name(const char *prefix, const char *name) +{ + size_t prefix_len = strlen(prefix); + size_t name_len = strlen(name); + size_t escaped_len; + char *escaped, *s; + + escaped_len = prefix_len + OVL_XATTR_ESCAPE_PREFIX_LEN + name_len; + if (escaped_len > XATTR_NAME_MAX) + return ERR_PTR(-EOPNOTSUPP); + + escaped = kmalloc(escaped_len + 1, GFP_KERNEL); + if (escaped == NULL) + return ERR_PTR(-ENOMEM); + + s = escaped; + memcpy(s, prefix, prefix_len); + s += prefix_len; + memcpy(s, OVL_XATTR_ESCAPE_PREFIX, OVL_XATTR_ESCAPE_PREFIX_LEN); + s += OVL_XATTR_ESCAPE_PREFIX_LEN; + memcpy(s, name, name_len + 1); + + return escaped; +} + +static int ovl_own_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + char *escaped; + int r; + + escaped = ovl_xattr_escape_name(handler->prefix, name); + if (IS_ERR(escaped)) + return PTR_ERR(escaped); + + r = ovl_xattr_get(dentry, inode, escaped, buffer, size); + + kfree(escaped); + + return r; +} + +static int ovl_own_xattr_set(const struct xattr_handler *handler, + struct mnt_idmap *idmap, + struct dentry *dentry, struct inode *inode, + const char *name, const void *value, + size_t size, int flags) +{ + char *escaped; + int r; + + escaped = ovl_xattr_escape_name(handler->prefix, name); + if (IS_ERR(escaped)) + return PTR_ERR(escaped); + + r = ovl_xattr_set(dentry, inode, escaped, value, size, flags); + + kfree(escaped); + + return r; +} + +static int ovl_other_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + return ovl_xattr_get(dentry, inode, name, buffer, size); +} + +static int ovl_other_xattr_set(const struct xattr_handler *handler, + struct mnt_idmap *idmap, + struct dentry *dentry, struct inode *inode, + const char *name, const void *value, + size_t size, int flags) +{ + return ovl_xattr_set(dentry, inode, name, value, size, flags); +} + +static const struct xattr_handler ovl_own_trusted_xattr_handler = { + .prefix = OVL_XATTR_TRUSTED_PREFIX, + .get = ovl_own_xattr_get, + .set = ovl_own_xattr_set, +}; + +static const struct xattr_handler ovl_own_user_xattr_handler = { + .prefix = OVL_XATTR_USER_PREFIX, + .get = ovl_own_xattr_get, + .set = ovl_own_xattr_set, +}; + +static const struct xattr_handler ovl_other_xattr_handler = { + .prefix = "", /* catch all */ + .get = ovl_other_xattr_get, + .set = ovl_other_xattr_set, +}; + +static const struct xattr_handler * const ovl_trusted_xattr_handlers[] = { + &ovl_own_trusted_xattr_handler, + &ovl_other_xattr_handler, + NULL +}; + +static const struct xattr_handler * const ovl_user_xattr_handlers[] = { + &ovl_own_user_xattr_handler, + &ovl_other_xattr_handler, + NULL +}; + +const struct xattr_handler * const *ovl_xattr_handlers(struct ovl_fs *ofs) +{ + return ofs->config.userxattr ? ovl_user_xattr_handlers : + ovl_trusted_xattr_handlers; +} + |