diff options
Diffstat (limited to 'fs/namei.c')
| -rw-r--r-- | fs/namei.c | 2940 |
1 files changed, 1574 insertions, 1366 deletions
diff --git a/fs/namei.c b/fs/namei.c index db6565c99825..578c2110df02 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -22,6 +22,7 @@ #include <linux/fs.h> #include <linux/namei.h> #include <linux/pagemap.h> +#include <linux/sched/mm.h> #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/security.h> @@ -204,6 +205,14 @@ getname_flags(const char __user *filename, int flags, int *empty) } struct filename * +getname_uflags(const char __user *filename, int uflags) +{ + int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0; + + return getname_flags(filename, flags, NULL); +} + +struct filename * getname(const char __user * filename) { return getname_flags(filename, 0, NULL); @@ -247,6 +256,9 @@ getname_kernel(const char * filename) void putname(struct filename *name) { + if (IS_ERR(name)) + return; + BUG_ON(name->refcnt <= 0); if (--name->refcnt > 0) @@ -259,7 +271,24 @@ void putname(struct filename *name) __putname(name); } -static int check_acl(struct inode *inode, int mask) +/** + * check_acl - perform ACL permission checking + * @mnt_userns: user namespace of the mount the inode was found from + * @inode: inode to check permissions on + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) + * + * This function performs the ACL permission checking. Since this function + * retrieve POSIX acls it needs to know whether it is called from a blocking or + * non-blocking context and thus cares about the MAY_NOT_BLOCK bit. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +static int check_acl(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *acl; @@ -271,14 +300,14 @@ static int check_acl(struct inode *inode, int mask) /* no ->get_acl() calls in RCU mode... */ if (is_uncached_acl(acl)) return -ECHILD; - return posix_acl_permission(inode, acl, mask & ~MAY_NOT_BLOCK); + return posix_acl_permission(mnt_userns, inode, acl, mask); } acl = get_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { - int error = posix_acl_permission(inode, acl, mask); + int error = posix_acl_permission(mnt_userns, inode, acl, mask); posix_acl_release(acl); return error; } @@ -287,38 +316,67 @@ static int check_acl(struct inode *inode, int mask) return -EAGAIN; } -/* - * This does the basic permission checking +/** + * acl_permission_check - perform basic UNIX permission checking + * @mnt_userns: user namespace of the mount the inode was found from + * @inode: inode to check permissions on + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) + * + * This function performs the basic UNIX permission checking. Since this + * function may retrieve POSIX acls it needs to know whether it is called from a + * blocking or non-blocking context and thus cares about the MAY_NOT_BLOCK bit. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. */ -static int acl_permission_check(struct inode *inode, int mask) +static int acl_permission_check(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { unsigned int mode = inode->i_mode; + kuid_t i_uid; - if (likely(uid_eq(current_fsuid(), inode->i_uid))) + /* Are we the owner? If so, ACL's don't matter */ + i_uid = i_uid_into_mnt(mnt_userns, inode); + if (likely(uid_eq(current_fsuid(), i_uid))) { + mask &= 7; mode >>= 6; - else { - if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { - int error = check_acl(inode, mask); - if (error != -EAGAIN) - return error; - } + return (mask & ~mode) ? -EACCES : 0; + } - if (in_group_p(inode->i_gid)) - mode >>= 3; + /* Do we have ACL's? */ + if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { + int error = check_acl(mnt_userns, inode, mask); + if (error != -EAGAIN) + return error; } + /* Only RWX matters for group/other mode bits */ + mask &= 7; + /* - * If the DACs are ok we don't need any capability check. + * Are the group permissions different from + * the other permissions in the bits we care + * about? Need to check group ownership if so. */ - if ((mask & ~mode & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0) - return 0; - return -EACCES; + if (mask & (mode ^ (mode >> 3))) { + kgid_t kgid = i_gid_into_mnt(mnt_userns, inode); + if (in_group_p(kgid)) + mode >>= 3; + } + + /* Bits in 'mode' clear that we require? */ + return (mask & ~mode) ? -EACCES : 0; } /** * generic_permission - check for access rights on a Posix-like filesystem + * @mnt_userns: user namespace of the mount the inode was found from * @inode: inode to check access rights for - * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...) + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, + * %MAY_NOT_BLOCK ...) * * Used to check for read/write/execute permissions on a file. * We use "fsuid" for this, letting us set arbitrary permissions @@ -328,25 +386,33 @@ static int acl_permission_check(struct inode *inode, int mask) * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk * request cannot be satisfied (eg. requires blocking or too much complexity). * It would then be called again in ref-walk mode. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. */ -int generic_permission(struct inode *inode, int mask) +int generic_permission(struct user_namespace *mnt_userns, struct inode *inode, + int mask) { int ret; /* * Do the basic permission checks. */ - ret = acl_permission_check(inode, mask); + ret = acl_permission_check(mnt_userns, inode, mask); if (ret != -EACCES) return ret; if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ if (!(mask & MAY_WRITE)) - if (capable_wrt_inode_uidgid(inode, + if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_DAC_READ_SEARCH)) return 0; - if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) + if (capable_wrt_inode_uidgid(mnt_userns, inode, + CAP_DAC_OVERRIDE)) return 0; return -EACCES; } @@ -356,7 +422,8 @@ int generic_permission(struct inode *inode, int mask) */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) - if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) + if (capable_wrt_inode_uidgid(mnt_userns, inode, + CAP_DAC_READ_SEARCH)) return 0; /* * Read/write DACs are always overridable. @@ -364,31 +431,38 @@ int generic_permission(struct inode *inode, int mask) * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) - if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) + if (capable_wrt_inode_uidgid(mnt_userns, inode, + CAP_DAC_OVERRIDE)) return 0; return -EACCES; } EXPORT_SYMBOL(generic_permission); -/* +/** + * do_inode_permission - UNIX permission checking + * @mnt_userns: user namespace of the mount the inode was found from + * @inode: inode to check permissions on + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) + * * We _really_ want to just do "generic_permission()" without * even looking at the inode->i_op values. So we keep a cache * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ -static inline int do_inode_permission(struct inode *inode, int mask) +static inline int do_inode_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { if (likely(inode->i_op->permission)) - return inode->i_op->permission(inode, mask); + return inode->i_op->permission(mnt_userns, inode, mask); /* This gets set once for the inode lifetime */ spin_lock(&inode->i_lock); inode->i_opflags |= IOP_FASTPERM; spin_unlock(&inode->i_lock); } - return generic_permission(inode, mask); + return generic_permission(mnt_userns, inode, mask); } /** @@ -413,8 +487,9 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) /** * inode_permission - Check for access rights to a given inode - * @inode: Inode to check permission on - * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) + * @mnt_userns: User namespace of the mount the inode was found from + * @inode: Inode to check permission on + * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Check for read/write/execute permissions on an inode. We use fs[ug]id for * this, letting us set arbitrary permissions for filesystem access without @@ -422,7 +497,8 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ -int inode_permission(struct inode *inode, int mask) +int inode_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) { int retval; @@ -442,11 +518,11 @@ int inode_permission(struct inode *inode, int mask) * written back improperly if their true value is unknown * to the vfs. */ - if (HAS_UNMAPPED_ID(inode)) + if (HAS_UNMAPPED_ID(mnt_userns, inode)) return -EACCES; } - retval = do_inode_permission(inode, mask); + retval = do_inode_permission(mnt_userns, inode, mask); if (retval) return retval; @@ -490,8 +566,8 @@ struct nameidata { struct qstr last; struct path root; struct inode *inode; /* path.dentry.d_inode */ - unsigned int flags; - unsigned seq, m_seq, r_seq; + unsigned int flags, state; + unsigned seq, next_seq, m_seq, r_seq; int last_type; unsigned depth; int total_link_count; @@ -503,22 +579,41 @@ struct nameidata { } *stack, internal[EMBEDDED_LEVELS]; struct filename *name; struct nameidata *saved; - struct inode *link_inode; unsigned root_seq; int dfd; + kuid_t dir_uid; + umode_t dir_mode; } __randomize_layout; -static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) +#define ND_ROOT_PRESET 1 +#define ND_ROOT_GRABBED 2 +#define ND_JUMPED 4 + +static void __set_nameidata(struct nameidata *p, int dfd, struct filename *name) { struct nameidata *old = current->nameidata; p->stack = p->internal; + p->depth = 0; p->dfd = dfd; p->name = name; + p->path.mnt = NULL; + p->path.dentry = NULL; p->total_link_count = old ? old->total_link_count : 0; p->saved = old; current->nameidata = p; } +static inline void set_nameidata(struct nameidata *p, int dfd, struct filename *name, + const struct path *root) +{ + __set_nameidata(p, dfd, name); + p->state = 0; + if (unlikely(root)) { + p->state = ND_ROOT_PRESET; + p->root = *root; + } +} + static void restore_nameidata(void) { struct nameidata *now = current->nameidata, *old = now->saved; @@ -530,52 +625,34 @@ static void restore_nameidata(void) kfree(now->stack); } -static int __nd_alloc_stack(struct nameidata *nd) +static bool nd_alloc_stack(struct nameidata *nd) { struct saved *p; - if (nd->flags & LOOKUP_RCU) { - p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved), - GFP_ATOMIC); - if (unlikely(!p)) - return -ECHILD; - } else { - p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved), - GFP_KERNEL); - if (unlikely(!p)) - return -ENOMEM; - } + p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved), + nd->flags & LOOKUP_RCU ? GFP_ATOMIC : GFP_KERNEL); + if (unlikely(!p)) + return false; memcpy(p, nd->internal, sizeof(nd->internal)); nd->stack = p; - return 0; + return true; } /** - * path_connected - Verify that a path->dentry is below path->mnt.mnt_root - * @path: nameidate to verify + * path_connected - Verify that a dentry is below mnt.mnt_root * * Rename can sometimes move a file or directory outside of a bind * mount, path_connected allows those cases to be detected. */ -static bool path_connected(const struct path *path) +static bool path_connected(struct vfsmount *mnt, struct dentry *dentry) { - struct vfsmount *mnt = path->mnt; struct super_block *sb = mnt->mnt_sb; - /* Bind mounts and multi-root filesystems can have disconnected paths */ - if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root)) + /* Bind mounts can have disconnected paths */ + if (mnt->mnt_root == sb->s_root) return true; - return is_subdir(path->dentry, mnt->mnt_root); -} - -static inline int nd_alloc_stack(struct nameidata *nd) -{ - if (likely(nd->depth != EMBEDDED_LEVELS)) - return 0; - if (likely(nd->stack != nd->internal)) - return 0; - return __nd_alloc_stack(nd); + return is_subdir(dentry, mnt->mnt_root); } static void drop_links(struct nameidata *nd) @@ -588,6 +665,13 @@ static void drop_links(struct nameidata *nd) } } +static void leave_rcu(struct nameidata *nd) +{ + nd->flags &= ~LOOKUP_RCU; + nd->seq = nd->next_seq = 0; + rcu_read_unlock(); +} + static void terminate_walk(struct nameidata *nd) { drop_links(nd); @@ -596,22 +680,22 @@ static void terminate_walk(struct nameidata *nd) path_put(&nd->path); for (i = 0; i < nd->depth; i++) path_put(&nd->stack[i].link); - if (nd->flags & LOOKUP_ROOT_GRABBED) { + if (nd->state & ND_ROOT_GRABBED) { path_put(&nd->root); - nd->flags &= ~LOOKUP_ROOT_GRABBED; + nd->state &= ~ND_ROOT_GRABBED; } } else { - nd->flags &= ~LOOKUP_RCU; - rcu_read_unlock(); + leave_rcu(nd); } nd->depth = 0; + nd->path.mnt = NULL; + nd->path.dentry = NULL; } /* path_put is needed afterwards regardless of success or failure */ -static bool legitimize_path(struct nameidata *nd, - struct path *path, unsigned seq) +static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq) { - int res = __legitimize_mnt(path->mnt, nd->m_seq); + int res = __legitimize_mnt(path->mnt, mseq); if (unlikely(res)) { if (res > 0) path->mnt = NULL; @@ -625,9 +709,20 @@ static bool legitimize_path(struct nameidata *nd, return !read_seqcount_retry(&path->dentry->d_seq, seq); } +static inline bool legitimize_path(struct nameidata *nd, + struct path *path, unsigned seq) +{ + return __legitimize_path(path, seq, nd->m_seq); +} + static bool legitimize_links(struct nameidata *nd) { int i; + if (unlikely(nd->flags & LOOKUP_CACHED)) { + drop_links(nd); + nd->depth = 0; + return false; + } for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { @@ -641,17 +736,10 @@ static bool legitimize_links(struct nameidata *nd) static bool legitimize_root(struct nameidata *nd) { - /* - * For scoped-lookups (where nd->root has been zeroed), we need to - * restart the whole lookup from scratch -- because set_root() is wrong - * for these lookups (nd->dfd is the root, not the filesystem root). - */ - if (!nd->root.mnt && (nd->flags & LOOKUP_IS_SCOPED)) - return false; /* Nothing to do if nd->root is zero or is managed by the VFS user. */ - if (!nd->root.mnt || (nd->flags & LOOKUP_ROOT)) + if (!nd->root.mnt || (nd->state & ND_ROOT_PRESET)) return true; - nd->flags |= LOOKUP_ROOT_GRABBED; + nd->state |= ND_ROOT_GRABBED; return legitimize_path(nd, &nd->root, nd->root_seq); } @@ -667,63 +755,65 @@ static bool legitimize_root(struct nameidata *nd) */ /** - * unlazy_walk - try to switch to ref-walk mode. + * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data - * Returns: 0 on success, -ECHILD on failure + * Returns: true on success, false on failure * - * unlazy_walk attempts to legitimize the current nd->path and nd->root + * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. - * Nothing should touch nameidata between unlazy_walk() failure and + * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ -static int unlazy_walk(struct nameidata *nd) +static bool try_to_unlazy(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; BUG_ON(!(nd->flags & LOOKUP_RCU)); - nd->flags &= ~LOOKUP_RCU; if (unlikely(!legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) goto out; if (unlikely(!legitimize_root(nd))) goto out; - rcu_read_unlock(); + leave_rcu(nd); BUG_ON(nd->inode != parent->d_inode); - return 0; + return true; out1: nd->path.mnt = NULL; nd->path.dentry = NULL; out: - rcu_read_unlock(); - return -ECHILD; + leave_rcu(nd); + return false; } /** - * unlazy_child - try to switch to ref-walk mode. + * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data - * @dentry: child of nd->path.dentry - * @seq: seq number to check dentry against - * Returns: 0 on success, -ECHILD on failure + * @dentry: next dentry to step into + * Returns: true on success, false on failure * - * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry - * for ref-walk mode. @dentry must be a path found by a do_lookup call on - * @nd. Must be called from rcu-walk context. - * Nothing should touch nameidata between unlazy_child() failure and + * Similar to try_to_unlazy(), but here we have the next dentry already + * picked by rcu-walk and want to legitimize that in addition to the current + * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. + * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ -static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq) +static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry) { + int res; BUG_ON(!(nd->flags & LOOKUP_RCU)); - nd->flags &= ~LOOKUP_RCU; if (unlikely(!legitimize_links(nd))) goto out2; - if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq))) - goto out2; + res = __legitimize_mnt(nd->path.mnt, nd->m_seq); + if (unlikely(res)) { + if (res > 0) + goto out2; + goto out1; + } if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref))) goto out1; @@ -736,7 +826,7 @@ static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned se */ if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) goto out; - if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) + if (read_seqcount_retry(&dentry->d_seq, nd->next_seq)) goto out_dput; /* * Sequence counts matched. Now make sure that the root is @@ -744,20 +834,20 @@ static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned se */ if (unlikely(!legitimize_root(nd))) goto out_dput; - rcu_read_unlock(); - return 0; + leave_rcu(nd); + return true; out2: nd->path.mnt = NULL; out1: nd->path.dentry = NULL; out: - rcu_read_unlock(); - return -ECHILD; + leave_rcu(nd); + return false; out_dput: - rcu_read_unlock(); + leave_rcu(nd); dput(dentry); - return -ECHILD; + return false; } static inline int d_revalidate(struct dentry *dentry, unsigned int flags) @@ -788,9 +878,11 @@ static int complete_walk(struct nameidata *nd) * We don't want to zero nd->root for scoped-lookups or * externally-managed nd->root. */ - if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED))) - nd->root.mnt = NULL; - if (unlikely(unlazy_walk(nd))) + if (!(nd->state & ND_ROOT_PRESET)) + if (!(nd->flags & LOOKUP_IS_SCOPED)) + nd->root.mnt = NULL; + nd->flags &= ~LOOKUP_CACHED; + if (!try_to_unlazy(nd)) return -ECHILD; } @@ -815,7 +907,7 @@ static int complete_walk(struct nameidata *nd) return -EXDEV; } - if (likely(!(nd->flags & LOOKUP_JUMPED))) + if (likely(!(nd->state & ND_JUMPED))) return 0; if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE))) @@ -853,30 +945,11 @@ static int set_root(struct nameidata *nd) } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_root(fs, &nd->root); - nd->flags |= LOOKUP_ROOT_GRABBED; + nd->state |= ND_ROOT_GRABBED; } return 0; } -static void path_put_conditional(struct path *path, struct nameidata *nd) -{ - dput(path->dentry); - if (path->mnt != nd->path.mnt) - mntput(path->mnt); -} - -static inline void path_to_nameidata(const struct path *path, - struct nameidata *nd) -{ - if (!(nd->flags & LOOKUP_RCU)) { - dput(nd->path.dentry); - if (nd->path.mnt != path->mnt) - mntput(nd->path.mnt); - } - nd->path.mnt = path->mnt; - nd->path.dentry = path->dentry; -} - static int nd_jump_root(struct nameidata *nd) { if (unlikely(nd->flags & LOOKUP_BENEATH)) @@ -897,7 +970,7 @@ static int nd_jump_root(struct nameidata *nd) d = nd->path.dentry; nd->inode = d->d_inode; nd->seq = nd->root_seq; - if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq))) + if (read_seqcount_retry(&d->d_seq, nd->seq)) return -ECHILD; } else { path_put(&nd->path); @@ -905,7 +978,7 @@ static int nd_jump_root(struct nameidata *nd) path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } - nd->flags |= LOOKUP_JUMPED; + nd->state |= ND_JUMPED; return 0; } @@ -913,7 +986,7 @@ static int nd_jump_root(struct nameidata *nd) * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ -int nd_jump_link(struct path *path) +int nd_jump_link(const struct path *path) { int error = -ELOOP; struct nameidata *nd = current->nameidata; @@ -933,7 +1006,7 @@ int nd_jump_link(struct path *path) path_put(&nd->path); nd->path = *path; nd->inode = nd->path.dentry->d_inode; - nd->flags |= LOOKUP_JUMPED; + nd->state |= ND_JUMPED; return 0; err: @@ -949,10 +1022,60 @@ static inline void put_link(struct nameidata *nd) path_put(&last->link); } -int sysctl_protected_symlinks __read_mostly = 0; -int sysctl_protected_hardlinks __read_mostly = 0; -int sysctl_protected_fifos __read_mostly; -int sysctl_protected_regular __read_mostly; +static int sysctl_protected_symlinks __read_mostly; +static int sysctl_protected_hardlinks __read_mostly; +static int sysctl_protected_fifos __read_mostly; +static int sysctl_protected_regular __read_mostly; + +#ifdef CONFIG_SYSCTL +static struct ctl_table namei_sysctls[] = { + { + .procname = "protected_symlinks", + .data = &sysctl_protected_symlinks, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "protected_hardlinks", + .data = &sysctl_protected_hardlinks, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "protected_fifos", + .data = &sysctl_protected_fifos, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { + .procname = "protected_regular", + .data = &sysctl_protected_regular, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { } +}; + +static int __init init_fs_namei_sysctls(void) +{ + register_sysctl_init("fs", namei_sysctls); + return 0; +} +fs_initcall(init_fs_namei_sysctls); + +#endif /* CONFIG_SYSCTL */ /** * may_follow_link - Check symlink following for unsafe situations @@ -969,28 +1092,26 @@ int sysctl_protected_regular __read_mostly; * * Returns 0 if following the symlink is allowed, -ve on error. */ -static inline int may_follow_link(struct nameidata *nd) +static inline int may_follow_link(struct nameidata *nd, const struct inode *inode) { - const struct inode *inode; - const struct inode *parent; - kuid_t puid; + struct user_namespace *mnt_userns; + kuid_t i_uid; if (!sysctl_protected_symlinks) return 0; + mnt_userns = mnt_user_ns(nd->path.mnt); + i_uid = i_uid_into_mnt(mnt_userns, inode); /* Allowed if owner and follower match. */ - inode = nd->link_inode; - if (uid_eq(current_cred()->fsuid, inode->i_uid)) + if (uid_eq(current_cred()->fsuid, i_uid)) return 0; /* Allowed if parent directory not sticky and world-writable. */ - parent = nd->inode; - if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH)) + if ((nd->dir_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH)) return 0; /* Allowed if parent directory and link owner match. */ - puid = parent->i_uid; - if (uid_valid(puid) && uid_eq(puid, inode->i_uid)) + if (uid_valid(nd->dir_uid) && uid_eq(nd->dir_uid, i_uid)) return 0; if (nd->flags & LOOKUP_RCU) @@ -1003,6 +1124,7 @@ static inline int may_follow_link(struct nameidata *nd) /** * safe_hardlink_source - Check for safe hardlink conditions + * @mnt_userns: user namespace of the mount the inode was found from * @inode: the source inode to hardlink from * * Return false if at least one of the following conditions: @@ -1013,7 +1135,8 @@ static inline int may_follow_link(struct nameidata *nd) * * Otherwise returns true. */ -static bool safe_hardlink_source(struct inode *inode) +static bool safe_hardlink_source(struct user_namespace *mnt_userns, + struct inode *inode) { umode_t mode = inode->i_mode; @@ -1030,7 +1153,7 @@ static bool safe_hardlink_source(struct inode *inode) return false; /* Hardlinking to unreadable or unwritable sources is dangerous. */ - if (inode_permission(inode, MAY_READ | MAY_WRITE)) + if (inode_permission(mnt_userns, inode, MAY_READ | MAY_WRITE)) return false; return true; @@ -1038,6 +1161,7 @@ static bool safe_hardlink_source(struct inode *inode) /** * may_linkat - Check permissions for creating a hardlink + * @mnt_userns: user namespace of the mount the inode was found from * @link: the source to hardlink from * * Block hardlink when all of: @@ -1046,14 +1170,21 @@ static bool safe_hardlink_source(struct inode *inode) * - hardlink source is unsafe (see safe_hardlink_source() above) * - not CAP_FOWNER in a namespace with the inode owner uid mapped * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + * * Returns 0 if successful, -ve on error. */ -static int may_linkat(struct path *link) +int may_linkat(struct user_namespace *mnt_userns, const struct path *link) { struct inode *inode = link->dentry->d_inode; /* Inode writeback is not safe when the uid or gid are invalid. */ - if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) + if (!uid_valid(i_uid_into_mnt(mnt_userns, inode)) || + !gid_valid(i_gid_into_mnt(mnt_userns, inode))) return -EOVERFLOW; if (!sysctl_protected_hardlinks) @@ -1062,7 +1193,8 @@ static int may_linkat(struct path *link) /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ - if (safe_hardlink_source(inode) || inode_owner_or_capable(inode)) + if (safe_hardlink_source(mnt_userns, inode) || + inode_owner_or_capable(mnt_userns, inode)) return 0; audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); @@ -1073,8 +1205,8 @@ static int may_linkat(struct path *link) * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. - * @dir_mode: mode bits of directory - * @dir_uid: owner of directory + * @mnt_userns: user namespace of the mount the inode was found from + * @nd: nameidata pathwalk data * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: @@ -1088,16 +1220,25 @@ static int may_linkat(struct path *link) * the directory doesn't have to be world writable: being group writable will * be enough. * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + * * Returns 0 if the open is allowed, -ve on error. */ -static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid, - struct inode * const inode) +static int may_create_in_sticky(struct user_namespace *mnt_userns, + struct nameidata *nd, struct inode *const inode) { + umode_t dir_mode = nd->dir_mode; + kuid_t dir_uid = nd->dir_uid; + if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) || (!sysctl_protected_regular && S_ISREG(inode->i_mode)) || likely(!(dir_mode & S_ISVTX)) || - uid_eq(inode->i_uid, dir_uid) || - uid_eq(current_fsuid(), inode->i_uid)) + uid_eq(i_uid_into_mnt(mnt_userns, inode), dir_uid) || + uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode))) return 0; if (likely(dir_mode & 0002) || @@ -1113,63 +1254,6 @@ static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid, return 0; } -static __always_inline -const char *get_link(struct nameidata *nd) -{ - struct saved *last = nd->stack + nd->depth - 1; - struct dentry *dentry = last->link.dentry; - struct inode *inode = nd->link_inode; - int error; - const char *res; - - if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS)) - return ERR_PTR(-ELOOP); - - if (!(nd->flags & LOOKUP_RCU)) { - touch_atime(&last->link); - cond_resched(); - } else if (atime_needs_update(&last->link, inode)) { - if (unlikely(unlazy_walk(nd))) - return ERR_PTR(-ECHILD); - touch_atime(&last->link); - } - - error = security_inode_follow_link(dentry, inode, - nd->flags & LOOKUP_RCU); - if (unlikely(error)) - return ERR_PTR(error); - - nd->last_type = LAST_BIND; - res = READ_ONCE(inode->i_link); - if (!res) { - const char * (*get)(struct dentry *, struct inode *, - struct delayed_call *); - get = inode->i_op->get_link; - if (nd->flags & LOOKUP_RCU) { - res = get(NULL, inode, &last->done); - if (res == ERR_PTR(-ECHILD)) { - if (unlikely(unlazy_walk(nd))) - return ERR_PTR(-ECHILD); - res = get(dentry, inode, &last->done); - } - } else { - res = get(dentry, inode, &last->done); - } - if (IS_ERR_OR_NULL(res)) - return res; - } - if (*res == '/') { - error = nd_jump_root(nd); - if (unlikely(error)) - return ERR_PTR(error); - while (unlikely(*++res == '/')) - ; - } - if (!*res) - res = NULL; - return res; -} - /* * follow_up - Find the mountpoint of path's vfsmount * @@ -1203,19 +1287,59 @@ int follow_up(struct path *path) } EXPORT_SYMBOL(follow_up); +static bool choose_mountpoint_rcu(struct mount *m, const struct path *root, + struct path *path, unsigned *seqp) +{ + while (mnt_has_parent(m)) { + struct dentry *mountpoint = m->mnt_mountpoint; + + m = m->mnt_parent; + if (unlikely(root->dentry == mountpoint && + root->mnt == &m->mnt)) + break; + if (mountpoint != m->mnt.mnt_root) { + path->mnt = &m->mnt; + path->dentry = mountpoint; + *seqp = read_seqcount_begin(&mountpoint->d_seq); + return true; + } + } + return false; +} + +static bool choose_mountpoint(struct mount *m, const struct path *root, + struct path *path) +{ + bool found; + + rcu_read_lock(); + while (1) { + unsigned seq, mseq = read_seqbegin(&mount_lock); + + found = choose_mountpoint_rcu(m, root, path, &seq); + if (unlikely(!found)) { + if (!read_seqretry(&mount_lock, mseq)) + break; + } else { + if (likely(__legitimize_path(path, seq, mseq))) + break; + rcu_read_unlock(); + path_put(path); + rcu_read_lock(); + } + } + rcu_read_unlock(); + return found; +} + /* * Perform an automount * - return -EISDIR to tell follow_managed() to stop and return the path we * were called with. */ -static int follow_automount(struct path *path, struct nameidata *nd, - bool *need_mntput) +static int follow_automount(struct path *path, int *count, unsigned lookup_flags) { - struct vfsmount *mnt; - int err; - - if (!path->dentry->d_op || !path->dentry->d_op->d_automount) - return -EREMOTE; + struct dentry *dentry = path->dentry; /* We don't want to mount if someone's just doing a stat - * unless they're stat'ing a directory and appended a '/' to @@ -1228,138 +1352,91 @@ static int follow_automount(struct path *path, struct nameidata *nd, * as being automount points. These will need the attentions * of the daemon to instantiate them before they can be used. */ - if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | + if (!(lookup_flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && - path->dentry->d_inode) + dentry->d_inode) return -EISDIR; - nd->total_link_count++; - if (nd->total_link_count >= 40) + if (count && (*count)++ >= MAXSYMLINKS) return -ELOOP; - mnt = path->dentry->d_op->d_automount(path); - if (IS_ERR(mnt)) { - /* - * The filesystem is allowed to return -EISDIR here to indicate - * it doesn't want to automount. For instance, autofs would do - * this so that its userspace daemon can mount on this dentry. - * - * However, we can only permit this if it's a terminal point in - * the path being looked up; if it wasn't then the remainder of - * the path is inaccessible and we should say so. - */ - if (PTR_ERR(mnt) == -EISDIR && (nd->flags & LOOKUP_PARENT)) - return -EREMOTE; - return PTR_ERR(mnt); - } - - if (!mnt) /* mount collision */ - return 0; - - if (!*need_mntput) { - /* lock_mount() may release path->mnt on error */ - mntget(path->mnt); - *need_mntput = true; - } - err = finish_automount(mnt, path); - - switch (err) { - case -EBUSY: - /* Someone else made a mount here whilst we were busy */ - return 0; - case 0: - path_put(path); - path->mnt = mnt; - path->dentry = dget(mnt->mnt_root); - return 0; - default: - return err; - } - + return finish_automount(dentry->d_op->d_automount(path), path); } /* - * Handle a dentry that is managed in some way. - * - Flagged for transit management (autofs) - * - Flagged as mountpoint - * - Flagged as automount point - * - * This may only be called in refwalk mode. - * On success path->dentry is known positive. - * - * Serialization is taken care of in namespace.c + * mount traversal - out-of-line part. One note on ->d_flags accesses - + * dentries are pinned but not locked here, so negative dentry can go + * positive right under us. Use of smp_load_acquire() provides a barrier + * sufficient for ->d_inode and ->d_flags consistency. */ -static int follow_managed(struct path *path, struct nameidata *nd) +static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped, + int *count, unsigned lookup_flags) { - struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */ - unsigned flags; + struct vfsmount *mnt = path->mnt; bool need_mntput = false; int ret = 0; - /* Given that we're not holding a lock here, we retain the value in a - * local variable for each dentry as we look at it so that we don't see - * the components of that value change under us */ - while (flags = smp_load_acquire(&path->dentry->d_flags), - unlikely(flags & DCACHE_MANAGED_DENTRY)) { + while (flags & DCACHE_MANAGED_DENTRY) { /* Allow the filesystem to manage the transit without i_mutex * being held. */ if (flags & DCACHE_MANAGE_TRANSIT) { - BUG_ON(!path->dentry->d_op); - BUG_ON(!path->dentry->d_op->d_manage); ret = path->dentry->d_op->d_manage(path, false); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } - /* Transit to a mounted filesystem. */ - if (flags & DCACHE_MOUNTED) { + if (flags & DCACHE_MOUNTED) { // something's mounted on it.. struct vfsmount *mounted = lookup_mnt(path); - if (mounted) { + if (mounted) { // ... in our namespace dput(path->dentry); if (need_mntput) mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); + // here we know it's positive + flags = path->dentry->d_flags; need_mntput = true; continue; } - - /* Something is mounted on this dentry in another - * namespace and/or whatever was mounted there in this - * namespace got unmounted before lookup_mnt() could - * get it */ } - /* Handle an automount point */ - if (flags & DCACHE_NEED_AUTOMOUNT) { - ret = follow_automount(path, nd, &need_mntput); - if (ret < 0) - break; - continue; - } + if (!(flags & DCACHE_NEED_AUTOMOUNT)) + break; - /* We didn't change the current path point */ - break; + // uncovered automount point + ret = follow_automount(path, count, lookup_flags); + flags = smp_load_acquire(&path->dentry->d_flags); + if (ret < 0) + break; } - if (need_mntput) { - if (path->mnt == mnt) - mntput(path->mnt); - if (unlikely(nd->flags & LOOKUP_NO_XDEV)) - ret = -EXDEV; - else - nd->flags |= LOOKUP_JUMPED; - } - if (ret == -EISDIR || !ret) - ret = 1; - if (ret > 0 && unlikely(d_flags_negative(flags))) + if (ret == -EISDIR) + ret = 0; + // possible if you race with several mount --move + if (need_mntput && path->mnt == mnt) + mntput(path->mnt); + if (!ret && unlikely(d_flags_negative(flags))) ret = -ENOENT; - if (unlikely(ret < 0)) - path_put_conditional(path, nd); + *jumped = need_mntput; return ret; } +static inline int traverse_mounts(struct path *path, bool *jumped, + int *count, unsigned lookup_flags) +{ + unsigned flags = smp_load_acquire(&path->dentry->d_flags); + + /* fastpath */ + if (likely(!(flags & DCACHE_MANAGED_DENTRY))) { + *jumped = false; + if (unlikely(d_flags_negative(flags))) + return -ENOENT; + return 0; + } + return __traverse_mounts(path, flags, jumped, count, lookup_flags); +} + int follow_down_one(struct path *path) { struct vfsmount *mounted; @@ -1376,217 +1453,103 @@ int follow_down_one(struct path *path) } EXPORT_SYMBOL(follow_down_one); -static inline int managed_dentry_rcu(const struct path *path) +/* + * Follow down to the covering mount currently visible to userspace. At each + * point, the filesystem owning that dentry may be queried as to whether the + * caller is permitted to proceed or not. + */ +int follow_down(struct path *path) { - return (path->dentry->d_flags & DCACHE_MANAGE_TRANSIT) ? - path->dentry->d_op->d_manage(path, true) : 0; + struct vfsmount *mnt = path->mnt; + bool jumped; + int ret = traverse_mounts(path, &jumped, NULL, 0); + + if (path->mnt != mnt) + mntput(mnt); + return ret; } +EXPORT_SYMBOL(follow_down); /* * Try to skip to top of mountpoint pile in rcuwalk mode. Fail if * we meet a managed dentry that would need blocking. */ -static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, - struct inode **inode, unsigned *seqp) +static bool __follow_mount_rcu(struct nameidata *nd, struct path *path) { + struct dentry *dentry = path->dentry; + unsigned int flags = dentry->d_flags; + + if (likely(!(flags & DCACHE_MANAGED_DENTRY))) + return true; + + if (unlikely(nd->flags & LOOKUP_NO_XDEV)) + return false; + for (;;) { - struct mount *mounted; /* * Don't forget we might have a non-mountpoint managed dentry * that wants to block transit. */ - switch (managed_dentry_rcu(path)) { - case -ECHILD: - default: - return false; - case -EISDIR: - return true; - case 0: - break; - } - - if (!d_mountpoint(path->dentry)) - return !(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT); - - mounted = __lookup_mnt(path->mnt, path->dentry); - if (!mounted) - break; - if (unlikely(nd->flags & LOOKUP_NO_XDEV)) - return false; - path->mnt = &mounted->mnt; - path->dentry = mounted->mnt.mnt_root; - nd->flags |= LOOKUP_JUMPED; - *seqp = read_seqcount_begin(&path->dentry->d_seq); - /* - * Update the inode too. We don't need to re-check the - * dentry sequence number here after this d_inode read, - * because a mount-point is always pinned. - */ - *inode = path->dentry->d_inode; - } - return !read_seqretry(&mount_lock, nd->m_seq) && - !(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT); -} - -static int follow_dotdot_rcu(struct nameidata *nd) -{ - struct inode *inode = nd->inode; - - while (1) { - if (path_equal(&nd->path, &nd->root)) { - if (unlikely(nd->flags & LOOKUP_BENEATH)) - return -ECHILD; - break; + if (unlikely(flags & DCACHE_MANAGE_TRANSIT)) { + int res = dentry->d_op->d_manage(path, true); + if (res) + return res == -EISDIR; + flags = dentry->d_flags; } - if (nd->path.dentry != nd->path.mnt->mnt_root) { - struct dentry *old = nd->path.dentry; - struct dentry *parent = old->d_parent; - unsigned seq; - inode = parent->d_inode; - seq = read_seqcount_begin(&parent->d_seq); - if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq))) - return -ECHILD; - nd->path.dentry = parent; - nd->seq = seq; - if (unlikely(!path_connected(&nd->path))) - return -ECHILD; - break; - } else { - struct mount *mnt = real_mount(nd->path.mnt); - struct mount *mparent = mnt->mnt_parent; - struct dentry *mountpoint = mnt->mnt_mountpoint; - struct inode *inode2 = mountpoint->d_inode; - unsigned seq = read_seqcount_begin(&mountpoint->d_seq); - if (unlikely(read_seqretry(&mount_lock, nd->m_seq))) - return -ECHILD; - if (&mparent->mnt == nd->path.mnt) - break; - if (unlikely(nd->flags & LOOKUP_NO_XDEV)) - return -ECHILD; - /* we know that mountpoint was pinned */ - nd->path.dentry = mountpoint; - nd->path.mnt = &mparent->mnt; - inode = inode2; - nd->seq = seq; + if (flags & DCACHE_MOUNTED) { + struct mount *mounted = __lookup_mnt(path->mnt, dentry); + if (mounted) { + path->mnt = &mounted->mnt; + dentry = path->dentry = mounted->mnt.mnt_root; + nd->state |= ND_JUMPED; + nd->next_seq = read_seqcount_begin(&dentry->d_seq); + flags = dentry->d_flags; + // makes sure that non-RCU pathwalk could reach + // this state. + if (read_seqretry(&mount_lock, nd->m_seq)) + return false; + continue; + } + if (read_seqretry(&mount_lock, nd->m_seq)) + return false; } + return !(flags & DCACHE_NEED_AUTOMOUNT); } - while (unlikely(d_mountpoint(nd->path.dentry))) { - struct mount *mounted; - mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry); - if (unlikely(read_seqretry(&mount_lock, nd->m_seq))) - return -ECHILD; - if (!mounted) - break; - if (unlikely(nd->flags & LOOKUP_NO_XDEV)) - return -ECHILD; - nd->path.mnt = &mounted->mnt; - nd->path.dentry = mounted->mnt.mnt_root; - inode = nd->path.dentry->d_inode; - nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); - } - nd->inode = inode; - return 0; } -/* - * Follow down to the covering mount currently visible to userspace. At each - * point, the filesystem owning that dentry may be queried as to whether the - * caller is permitted to proceed or not. - */ -int follow_down(struct path *path) +static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, + struct path *path) { - unsigned managed; + bool jumped; int ret; - while (managed = READ_ONCE(path->dentry->d_flags), - unlikely(managed & DCACHE_MANAGED_DENTRY)) { - /* Allow the filesystem to manage the transit without i_mutex - * being held. - * - * We indicate to the filesystem if someone is trying to mount - * something here. This gives autofs the chance to deny anyone - * other than its daemon the right to mount on its - * superstructure. - * - * The filesystem may sleep at this point. - */ - if (managed & DCACHE_MANAGE_TRANSIT) { - BUG_ON(!path->dentry->d_op); - BUG_ON(!path->dentry->d_op->d_manage); - ret = path->dentry->d_op->d_manage(path, false); - if (ret < 0) - return ret == -EISDIR ? 0 : ret; - } - - /* Transit to a mounted filesystem. */ - if (managed & DCACHE_MOUNTED) { - struct vfsmount *mounted = lookup_mnt(path); - if (!mounted) - break; - dput(path->dentry); - mntput(path->mnt); - path->mnt = mounted; - path->dentry = dget(mounted->mnt_root); - continue; - } - - /* Don't handle automount points here */ - break; - } - return 0; -} -EXPORT_SYMBOL(follow_down); - -/* - * Skip to top of mountpoint pile in refwalk mode for follow_dotdot() - */ -static void follow_mount(struct path *path) -{ - while (d_mountpoint(path->dentry)) { - struct vfsmount *mounted = lookup_mnt(path); - if (!mounted) - break; - dput(path->dentry); - mntput(path->mnt); - path->mnt = mounted; - path->dentry = dget(mounted->mnt_root); + path->mnt = nd->path.mnt; + path->dentry = dentry; + if (nd->flags & LOOKUP_RCU) { + unsigned int seq = nd->next_seq; + if (likely(__follow_mount_rcu(nd, path))) + return 0; + // *path and nd->next_seq might've been clobbered + path->mnt = nd->path.mnt; + path->dentry = dentry; + nd->next_seq = seq; + if (!try_to_unlazy_next(nd, dentry)) + return -ECHILD; } -} - -static int path_parent_directory(struct path *path) -{ - struct dentry *old = path->dentry; - /* rare case of legitimate dget_parent()... */ - path->dentry = dget_parent(path->dentry); - dput(old); - if (unlikely(!path_connected(path))) - return -ENOENT; - return 0; -} - -static int follow_dotdot(struct nameidata *nd) -{ - while (1) { - if (path_equal(&nd->path, &nd->root)) { - if (unlikely(nd->flags & LOOKUP_BENEATH)) - return -EXDEV; - break; - } - if (nd->path.dentry != nd->path.mnt->mnt_root) { - int ret = path_parent_directory(&nd->path); - if (ret) - return ret; - break; - } - if (!follow_up(&nd->path)) - break; + ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags); + if (jumped) { if (unlikely(nd->flags & LOOKUP_NO_XDEV)) - return -EXDEV; + ret = -EXDEV; + else + nd->state |= ND_JUMPED; } - follow_mount(&nd->path); - nd->inode = nd->path.dentry->d_inode; - return 0; + if (unlikely(ret)) { + dput(path->dentry); + if (path->mnt != nd->path.mnt) + mntput(path->mnt); + } + return ret; } /* @@ -1643,14 +1606,10 @@ static struct dentry *__lookup_hash(const struct qstr *name, return dentry; } -static int lookup_fast(struct nameidata *nd, - struct path *path, struct inode **inode, - unsigned *seqp) +static struct dentry *lookup_fast(struct nameidata *nd) { - struct vfsmount *mnt = nd->path.mnt; struct dentry *dentry, *parent = nd->path.dentry; int status = 1; - int err; /* * Rename seqlock is not required here because in the off chance @@ -1658,72 +1617,41 @@ static int lookup_fast(struct nameidata *nd, * going to fall back to non-racy lookup. */ if (nd->flags & LOOKUP_RCU) { - unsigned seq; - bool negative; - dentry = __d_lookup_rcu(parent, &nd->last, &seq); + dentry = __d_lookup_rcu(parent, &nd->last, &nd->next_seq); if (unlikely(!dentry)) { - if (unlazy_walk(nd)) - return -ECHILD; - return 0; + if (!try_to_unlazy(nd)) + return ERR_PTR(-ECHILD); + return NULL; } /* - * This sequence count validates that the inode matches - * the dentry name information from lookup. - */ - *inode = d_backing_inode(dentry); - negative = d_is_negative(dentry); - if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) - return -ECHILD; - - /* * This sequence count validates that the parent had no * changes while we did the lookup of the dentry above. - * - * The memory barrier in read_seqcount_begin of child is - * enough, we can use __read_seqcount_retry here. */ - if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq))) - return -ECHILD; + if (read_seqcount_retry(&parent->d_seq, nd->seq)) + return ERR_PTR(-ECHILD); - *seqp = seq; status = d_revalidate(dentry, nd->flags); - if (likely(status > 0)) { - /* - * Note: do negative dentry check after revalidation in - * case that drops it. - */ - if (unlikely(negative)) - return -ENOENT; - path->mnt = mnt; - path->dentry = dentry; - if (likely(__follow_mount_rcu(nd, path, inode, seqp))) - return 1; - } - if (unlazy_child(nd, dentry, seq)) - return -ECHILD; - if (unlikely(status == -ECHILD)) + if (likely(status > 0)) + return dentry; + if (!try_to_unlazy_next(nd, dentry)) + return ERR_PTR(-ECHILD); + if (status == -ECHILD) /* we'd been told to redo it in non-rcu mode */ status = d_revalidate(dentry, nd->flags); } else { dentry = __d_lookup(parent, &nd->last); if (unlikely(!dentry)) - return 0; + return NULL; status = d_revalidate(dentry, nd->flags); } if (unlikely(status <= 0)) { if (!status) d_invalidate(dentry); dput(dentry); - return status; + return ERR_PTR(status); } - - path->mnt = mnt; - path->dentry = dentry; - err = follow_managed(path, nd); - if (likely(err > 0)) - *inode = d_backing_inode(path->dentry); - return err; + return dentry; } /* Fast lookup failed, do it the slow way */ @@ -1776,157 +1704,299 @@ static struct dentry *lookup_slow(const struct qstr *name, return res; } -static inline int may_lookup(struct nameidata *nd) +static inline int may_lookup(struct user_namespace *mnt_userns, + struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { - int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); - if (err != -ECHILD) + int err = inode_permission(mnt_userns, nd->inode, MAY_EXEC|MAY_NOT_BLOCK); + if (err != -ECHILD || !try_to_unlazy(nd)) return err; - if (unlazy_walk(nd)) - return -ECHILD; } - return inode_permission(nd->inode, MAY_EXEC); + return inode_permission(mnt_userns, nd->inode, MAY_EXEC); } -static inline int handle_dots(struct nameidata *nd, int type) +static int reserve_stack(struct nameidata *nd, struct path *link) { - if (type == LAST_DOTDOT) { - int error = 0; + if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) + return -ELOOP; - if (!nd->root.mnt) { - error = set_root(nd); - if (error) - return error; - } - if (nd->flags & LOOKUP_RCU) - error = follow_dotdot_rcu(nd); - else - error = follow_dotdot(nd); - if (error) - return error; + if (likely(nd->depth != EMBEDDED_LEVELS)) + return 0; + if (likely(nd->stack != nd->internal)) + return 0; + if (likely(nd_alloc_stack(nd))) + return 0; - if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { - /* - * If there was a racing rename or mount along our - * path, then we can't be sure that ".." hasn't jumped - * above nd->root (and so userspace should retry or use - * some fallback). - */ - smp_rmb(); - if (unlikely(__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq))) - return -EAGAIN; - if (unlikely(__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq))) - return -EAGAIN; - } + if (nd->flags & LOOKUP_RCU) { + // we need to grab link before we do unlazy. And we can't skip + // unlazy even if we fail to grab the link - cleanup needs it + bool grabbed_link = legitimize_path(nd, link, nd->next_seq); + + if (!try_to_unlazy(nd) || !grabbed_link) + return -ECHILD; + + if (nd_alloc_stack(nd)) + return 0; } - return 0; + return -ENOMEM; } -static int pick_link(struct nameidata *nd, struct path *link, - struct inode *inode, unsigned seq) +enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4}; + +static const char *pick_link(struct nameidata *nd, struct path *link, + struct inode *inode, int flags) { - int error; struct saved *last; - if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) { - path_to_nameidata(link, nd); - return -ELOOP; - } - if (!(nd->flags & LOOKUP_RCU)) { - if (link->mnt == nd->path.mnt) - mntget(link->mnt); - } - error = nd_alloc_stack(nd); + const char *res; + int error = reserve_stack(nd, link); + if (unlikely(error)) { - if (error == -ECHILD) { - if (unlikely(!legitimize_path(nd, link, seq))) { - drop_links(nd); - nd->depth = 0; - nd->flags &= ~LOOKUP_RCU; - nd->path.mnt = NULL; - nd->path.dentry = NULL; - rcu_read_unlock(); - } else if (likely(unlazy_walk(nd)) == 0) - error = nd_alloc_stack(nd); - } - if (error) { + if (!(nd->flags & LOOKUP_RCU)) path_put(link); - return error; - } + return ERR_PTR(error); } - last = nd->stack + nd->depth++; last->link = *link; clear_delayed_call(&last->done); - nd->link_inode = inode; - last->seq = seq; - return 1; -} + last->seq = nd->next_seq; -enum {WALK_FOLLOW = 1, WALK_MORE = 2}; + if (flags & WALK_TRAILING) { + error = may_follow_link(nd, inode); + if (unlikely(error)) + return ERR_PTR(error); + } + + if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) || + unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW)) + return ERR_PTR(-ELOOP); + + if (!(nd->flags & LOOKUP_RCU)) { + touch_atime(&last->link); + cond_resched(); + } else if (atime_needs_update(&last->link, inode)) { + if (!try_to_unlazy(nd)) + return ERR_PTR(-ECHILD); + touch_atime(&last->link); + } + + error = security_inode_follow_link(link->dentry, inode, + nd->flags & LOOKUP_RCU); + if (unlikely(error)) + return ERR_PTR(error); + + res = READ_ONCE(inode->i_link); + if (!res) { + const char * (*get)(struct dentry *, struct inode *, + struct delayed_call *); + get = inode->i_op->get_link; + if (nd->flags & LOOKUP_RCU) { + res = get(NULL, inode, &last->done); + if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd)) + res = get(link->dentry, inode, &last->done); + } else { + res = get(link->dentry, inode, &last->done); + } + if (!res) + goto all_done; + if (IS_ERR(res)) + return res; + } + if (*res == '/') { + error = nd_jump_root(nd); + if (unlikely(error)) + return ERR_PTR(error); + while (unlikely(*++res == '/')) + ; + } + if (*res) + return res; +all_done: // pure jump + put_link(nd); + return NULL; +} /* * Do we need to follow links? We _really_ want to be able * to do this check without having to look at inode->i_op, * so we keep a cache of "no, this doesn't need follow_link" * for the common case. + * + * NOTE: dentry must be what nd->next_seq had been sampled from. */ -static inline int step_into(struct nameidata *nd, struct path *path, - int flags, struct inode *inode, unsigned seq) +static const char *step_into(struct nameidata *nd, int flags, + struct dentry *dentry) { - if (!(flags & WALK_MORE) && nd->depth) - put_link(nd); - if (likely(!d_is_symlink(path->dentry)) || - !(flags & WALK_FOLLOW || nd->flags & LOOKUP_FOLLOW)) { + struct path path; + struct inode *inode; + int err = handle_mounts(nd, dentry, &path); + + if (err < 0) + return ERR_PTR(err); + inode = path.dentry->d_inode; + if (likely(!d_is_symlink(path.dentry)) || + ((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) || + (flags & WALK_NOFOLLOW)) { /* not a symlink or should not follow */ - path_to_nameidata(path, nd); + if (nd->flags & LOOKUP_RCU) { + if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq)) + return ERR_PTR(-ECHILD); + if (unlikely(!inode)) + return ERR_PTR(-ENOENT); + } else { + dput(nd->path.dentry); + if (nd->path.mnt != path.mnt) + mntput(nd->path.mnt); + } + nd->path = path; nd->inode = inode; - nd->seq = seq; - return 0; + nd->seq = nd->next_seq; + return NULL; } - /* make sure that d_is_symlink above matches inode */ if (nd->flags & LOOKUP_RCU) { - if (read_seqcount_retry(&path->dentry->d_seq, seq)) - return -ECHILD; + /* make sure that d_is_symlink above matches inode */ + if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq)) + return ERR_PTR(-ECHILD); + } else { + if (path.mnt == nd->path.mnt) + mntget(path.mnt); } - return pick_link(nd, path, inode, seq); + return pick_link(nd, &path, inode, flags); } -static int walk_component(struct nameidata *nd, int flags) +static struct dentry *follow_dotdot_rcu(struct nameidata *nd) { - struct path path; - struct inode *inode; - unsigned seq; - int err; + struct dentry *parent, *old; + + if (path_equal(&nd->path, &nd->root)) + goto in_root; + if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { + struct path path; + unsigned seq; + if (!choose_mountpoint_rcu(real_mount(nd->path.mnt), + &nd->root, &path, &seq)) + goto in_root; + if (unlikely(nd->flags & LOOKUP_NO_XDEV)) + return ERR_PTR(-ECHILD); + nd->path = path; + nd->inode = path.dentry->d_inode; + nd->seq = seq; + // makes sure that non-RCU pathwalk could reach this state + if (read_seqretry(&mount_lock, nd->m_seq)) + return ERR_PTR(-ECHILD); + /* we know that mountpoint was pinned */ + } + old = nd->path.dentry; + parent = old->d_parent; + nd->next_seq = read_seqcount_begin(&parent->d_seq); + // makes sure that non-RCU pathwalk could reach this state + if (read_seqcount_retry(&old->d_seq, nd->seq)) + return ERR_PTR(-ECHILD); + if (unlikely(!path_connected(nd->path.mnt, parent))) + return ERR_PTR(-ECHILD); + return parent; +in_root: + if (read_seqretry(&mount_lock, nd->m_seq)) + return ERR_PTR(-ECHILD); + if (unlikely(nd->flags & LOOKUP_BENEATH)) + return ERR_PTR(-ECHILD); + nd->next_seq = nd->seq; + return nd->path.dentry; +} + +static struct dentry *follow_dotdot(struct nameidata *nd) +{ + struct dentry *parent; + + if (path_equal(&nd->path, &nd->root)) + goto in_root; + if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { + struct path path; + + if (!choose_mountpoint(real_mount(nd->path.mnt), + &nd->root, &path)) + goto in_root; + path_put(&nd->path); + nd->path = path; + nd->inode = path.dentry->d_inode; + if (unlikely(nd->flags & LOOKUP_NO_XDEV)) + return ERR_PTR(-EXDEV); + } + /* rare case of legitimate dget_parent()... */ + parent = dget_parent(nd->path.dentry); + if (unlikely(!path_connected(nd->path.mnt, parent))) { + dput(parent); + return ERR_PTR(-ENOENT); + } + return parent; + +in_root: + if (unlikely(nd->flags & LOOKUP_BENEATH)) + return ERR_PTR(-EXDEV); + return dget(nd->path.dentry); +} + +static const char *handle_dots(struct nameidata *nd, int type) +{ + if (type == LAST_DOTDOT) { + const char *error = NULL; + struct dentry *parent; + + if (!nd->root.mnt) { + error = ERR_PTR(set_root(nd)); + if (error) + return error; + } + if (nd->flags & LOOKUP_RCU) + parent = follow_dotdot_rcu(nd); + else + parent = follow_dotdot(nd); + if (IS_ERR(parent)) + return ERR_CAST(parent); + error = step_into(nd, WALK_NOFOLLOW, parent); + if (unlikely(error)) + return error; + + if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { + /* + * If there was a racing rename or mount along our + * path, then we can't be sure that ".." hasn't jumped + * above nd->root (and so userspace should retry or use + * some fallback). + */ + smp_rmb(); + if (__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq)) + return ERR_PTR(-EAGAIN); + if (__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq)) + return ERR_PTR(-EAGAIN); + } + } + return NULL; +} + +static const char *walk_component(struct nameidata *nd, int flags) +{ + struct dentry *dentry; /* * "." and ".." are special - ".." especially so because it has * to be able to know about the current root directory and * parent relationships. */ if (unlikely(nd->last_type != LAST_NORM)) { - err = handle_dots(nd, nd->last_type); if (!(flags & WALK_MORE) && nd->depth) put_link(nd); - return err; + return handle_dots(nd, nd->last_type); } - err = lookup_fast(nd, &path, &inode, &seq); - if (unlikely(err <= 0)) { - if (err < 0) - return err; - path.dentry = lookup_slow(&nd->last, nd->path.dentry, - nd->flags); - if (IS_ERR(path.dentry)) - return PTR_ERR(path.dentry); - - path.mnt = nd->path.mnt; - err = follow_managed(&path, nd); - if (unlikely(err < 0)) - return err; - - seq = 0; /* we are already out of RCU mode */ - inode = d_backing_inode(path.dentry); + dentry = lookup_fast(nd); + if (IS_ERR(dentry)) + return ERR_CAST(dentry); + if (unlikely(!dentry)) { + dentry = lookup_slow(&nd->last, nd->path.dentry, nd->flags); + if (IS_ERR(dentry)) + return ERR_CAST(dentry); } - - return step_into(nd, &path, flags, inode, seq); + if (!(flags & WALK_MORE) && nd->depth) + put_link(nd); + return step_into(nd, flags, dentry); } /* @@ -2167,21 +2237,29 @@ static inline u64 hash_name(const void *salt, const char *name) */ static int link_path_walk(const char *name, struct nameidata *nd) { + int depth = 0; // depth <= nd->depth int err; + nd->last_type = LAST_ROOT; + nd->flags |= LOOKUP_PARENT; if (IS_ERR(name)) return PTR_ERR(name); while (*name=='/') name++; - if (!*name) + if (!*name) { + nd->dir_mode = 0; // short-circuit the 'hardening' idiocy return 0; + } /* At this point we know we have a real path component. */ for(;;) { + struct user_namespace *mnt_userns; + const char *link; u64 hash_len; int type; - err = may_lookup(nd); + mnt_userns = mnt_user_ns(nd->path.mnt); + err = may_lookup(mnt_userns, nd); if (err) return err; @@ -2192,7 +2270,7 @@ static int link_path_walk(const char *name, struct nameidata *nd) case 2: if (name[1] == '.') { type = LAST_DOTDOT; - nd->flags |= LOOKUP_JUMPED; + nd->state |= ND_JUMPED; } break; case 1: @@ -2200,7 +2278,7 @@ static int link_path_walk(const char *name, struct nameidata *nd) } if (likely(type == LAST_NORM)) { struct dentry *parent = nd->path.dentry; - nd->flags &= ~LOOKUP_JUMPED; + nd->state &= ~ND_JUMPED; if (unlikely(parent->d_flags & DCACHE_OP_HASH)) { struct qstr this = { { .hash_len = hash_len }, .name = name }; err = parent->d_op->d_hash(parent, &this); @@ -2227,40 +2305,31 @@ static int link_path_walk(const char *name, struct nameidata *nd) } while (unlikely(*name == '/')); if (unlikely(!*name)) { OK: - /* pathname body, done */ - if (!nd->depth) - return 0; - name = nd->stack[nd->depth - 1].name; - /* trailing symlink, done */ - if (!name) + /* pathname or trailing symlink, done */ + if (!depth) { + nd->dir_uid = i_uid_into_mnt(mnt_userns, nd->inode); + nd->dir_mode = nd->inode->i_mode; + nd->flags &= ~LOOKUP_PARENT; return 0; + } /* last component of nested symlink */ - err = walk_component(nd, WALK_FOLLOW); + name = nd->stack[--depth].name; + link = walk_component(nd, 0); } else { /* not the last component */ - err = walk_component(nd, WALK_FOLLOW | WALK_MORE); + link = walk_component(nd, WALK_MORE); } - if (err < 0) - return err; - - if (err) { - const char *s = get_link(nd); - - if (IS_ERR(s)) - return PTR_ERR(s); - err = 0; - if (unlikely(!s)) { - /* jumped */ - put_link(nd); - } else { - nd->stack[nd->depth - 1].name = name; - name = s; - continue; - } + if (unlikely(link)) { + if (IS_ERR(link)) + return PTR_ERR(link); + /* a symlink to follow */ + nd->stack[depth++].name = name; + name = link; + continue; } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { - if (unlazy_walk(nd)) + if (!try_to_unlazy(nd)) return -ECHILD; } return -ENOTDIR; @@ -2274,20 +2343,25 @@ static const char *path_init(struct nameidata *nd, unsigned flags) int error; const char *s = nd->name->name; + /* LOOKUP_CACHED requires RCU, ask caller to retry */ + if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED) + return ERR_PTR(-EAGAIN); + if (!*s) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) rcu_read_lock(); + else + nd->seq = nd->next_seq = 0; - nd->last_type = LAST_ROOT; /* if there are only slashes... */ - nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT; - nd->depth = 0; + nd->flags = flags; + nd->state |= ND_JUMPED; nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount); nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount); smp_rmb(); - if (flags & LOOKUP_ROOT) { + if (nd->state & ND_ROOT_PRESET) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; if (*s && unlikely(!d_can_lookup(root))) @@ -2304,8 +2378,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags) } nd->root.mnt = NULL; - nd->path.mnt = NULL; - nd->path.dentry = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) { @@ -2364,60 +2436,26 @@ static const char *path_init(struct nameidata *nd, unsigned flags) nd->root_seq = nd->seq; } else { path_get(&nd->root); - nd->flags |= LOOKUP_ROOT_GRABBED; + nd->state |= ND_ROOT_GRABBED; } } return s; } -static const char *trailing_symlink(struct nameidata *nd) -{ - const char *s; - int error = may_follow_link(nd); - if (unlikely(error)) - return ERR_PTR(error); - nd->flags |= LOOKUP_PARENT; - nd->stack[0].name = NULL; - s = get_link(nd); - return s ? s : ""; -} - -static inline int lookup_last(struct nameidata *nd) +static inline const char *lookup_last(struct nameidata *nd) { if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; - nd->flags &= ~LOOKUP_PARENT; - return walk_component(nd, 0); + return walk_component(nd, WALK_TRAILING); } static int handle_lookup_down(struct nameidata *nd) { - struct path path = nd->path; - struct inode *inode = nd->inode; - unsigned seq = nd->seq; - int err; - - if (nd->flags & LOOKUP_RCU) { - /* - * don't bother with unlazy_walk on failure - we are - * at the very beginning of walk, so we lose nothing - * if we simply redo everything in non-RCU mode - */ - if (unlikely(!__follow_mount_rcu(nd, &path, &inode, &seq))) - return -ECHILD; - } else { - dget(path.dentry); - err = follow_managed(&path, nd); - if (unlikely(err < 0)) - return err; - inode = d_backing_inode(path.dentry); - seq = 0; - } - path_to_nameidata(&path, nd); - nd->inode = inode; - nd->seq = seq; - return 0; + if (!(nd->flags & LOOKUP_RCU)) + dget(nd->path.dentry); + nd->next_seq = nd->seq; + return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry)); } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ @@ -2432,9 +2470,12 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path s = ERR_PTR(err); } - while (!(err = link_path_walk(s, nd)) - && ((err = lookup_last(nd)) > 0)) { - s = trailing_symlink(nd); + while (!(err = link_path_walk(s, nd)) && + (s = lookup_last(nd)) != NULL) + ; + if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) { + err = handle_lookup_down(nd); + nd->state &= ~ND_JUMPED; // no d_weak_revalidate(), please... } if (!err) err = complete_walk(nd); @@ -2458,11 +2499,7 @@ int filename_lookup(int dfd, struct filename *name, unsigned flags, struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); - if (unlikely(root)) { - nd.root = *root; - flags |= LOOKUP_ROOT; - } - set_nameidata(&nd, dfd, name); + set_nameidata(&nd, dfd, name, root); retval = path_lookupat(&nd, flags | LOOKUP_RCU, path); if (unlikely(retval == -ECHILD)) retval = path_lookupat(&nd, flags, path); @@ -2470,9 +2507,9 @@ int filename_lookup(int dfd, struct filename *name, unsigned flags, retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path); if (likely(!retval)) - audit_inode(name, path->dentry, 0); + audit_inode(name, path->dentry, + flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0); restore_nameidata(); - putname(name); return retval; } @@ -2493,16 +2530,17 @@ static int path_parentat(struct nameidata *nd, unsigned flags, return err; } -static struct filename *filename_parentat(int dfd, struct filename *name, - unsigned int flags, struct path *parent, - struct qstr *last, int *type) +/* Note: this does not consume "name" */ +static int filename_parentat(int dfd, struct filename *name, + unsigned int flags, struct path *parent, + struct qstr *last, int *type) { int retval; struct nameidata nd; if (IS_ERR(name)) - return name; - set_nameidata(&nd, dfd, name); + return PTR_ERR(name); + set_nameidata(&nd, dfd, name, NULL); retval = path_parentat(&nd, flags | LOOKUP_RCU, parent); if (unlikely(retval == -ECHILD)) retval = path_parentat(&nd, flags, parent); @@ -2512,29 +2550,23 @@ static struct filename *filename_parentat(int dfd, struct filename *name, *last = nd.last; *type = nd.last_type; audit_inode(name, parent->dentry, AUDIT_INODE_PARENT); - } else { - putname(name); - name = ERR_PTR(retval); } restore_nameidata(); - return name; + return retval; } /* does lookup, returns the object with parent locked */ -struct dentry *kern_path_locked(const char *name, struct path *path) +static struct dentry *__kern_path_locked(struct filename *name, struct path *path) { - struct filename *filename; struct dentry *d; struct qstr last; - int type; + int type, error; - filename = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path, - &last, &type); - if (IS_ERR(filename)) - return ERR_CAST(filename); + error = filename_parentat(AT_FDCWD, name, 0, path, &last, &type); + if (error) + return ERR_PTR(error); if (unlikely(type != LAST_NORM)) { path_put(path); - putname(filename); return ERR_PTR(-EINVAL); } inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); @@ -2543,14 +2575,26 @@ struct dentry *kern_path_locked(const char *name, struct path *path) inode_unlock(path->dentry->d_inode); path_put(path); } - putname(filename); return d; } +struct dentry *kern_path_locked(const char *name, struct path *path) +{ + struct filename *filename = getname_kernel(name); + struct dentry *res = __kern_path_locked(filename, path); + + putname(filename); + return res; +} + int kern_path(const char *name, unsigned int flags, struct path *path) { - return filename_lookup(AT_FDCWD, getname_kernel(name), - flags, path, NULL); + struct filename *filename = getname_kernel(name); + int ret = filename_lookup(AT_FDCWD, filename, flags, path, NULL); + + putname(filename); + return ret; + } EXPORT_SYMBOL(kern_path); @@ -2566,15 +2610,21 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { + struct filename *filename; struct path root = {.mnt = mnt, .dentry = dentry}; + int ret; + + filename = getname_kernel(name); /* the first argument of filename_lookup() is ignored with root */ - return filename_lookup(AT_FDCWD, getname_kernel(name), - flags , path, &root); + ret = filename_lookup(AT_FDCWD, filename, flags, path, &root); + putname(filename); + return ret; } EXPORT_SYMBOL(vfs_path_lookup); -static int lookup_one_len_common(const char *name, struct dentry *base, - int len, struct qstr *this) +static int lookup_one_common(struct user_namespace *mnt_userns, + const char *name, struct dentry *base, int len, + struct qstr *this) { this->name = name; this->len = len; @@ -2602,7 +2652,7 @@ static int lookup_one_len_common(const char *name, struct dentry *base, return err; } - return inode_permission(base->d_inode, MAY_EXEC); + return inode_permission(mnt_userns, base->d_inode, MAY_EXEC); } /** @@ -2626,7 +2676,7 @@ struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len WARN_ON_ONCE(!inode_is_locked(base->d_inode)); - err = lookup_one_len_common(name, base, len, &this); + err = lookup_one_common(&init_user_ns, name, base, len, &this); if (err) return ERR_PTR(err); @@ -2653,7 +2703,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) WARN_ON_ONCE(!inode_is_locked(base->d_inode)); - err = lookup_one_len_common(name, base, len, &this); + err = lookup_one_common(&init_user_ns, name, base, len, &this); if (err) return ERR_PTR(err); @@ -2663,7 +2713,38 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) EXPORT_SYMBOL(lookup_one_len); /** - * lookup_one_len_unlocked - filesystem helper to lookup single pathname component + * lookup_one - filesystem helper to lookup single pathname component + * @mnt_userns: user namespace of the mount the lookup is performed from + * @name: pathname component to lookup + * @base: base directory to lookup from + * @len: maximum length @len should be interpreted to + * + * Note that this routine is purely a helper for filesystem usage and should + * not be called by generic code. + * + * The caller must hold base->i_mutex. + */ +struct dentry *lookup_one(struct user_namespace *mnt_userns, const char *name, + struct dentry *base, int len) +{ + struct dentry *dentry; + struct qstr this; + int err; + + WARN_ON_ONCE(!inode_is_locked(base->d_inode)); + + err = lookup_one_common(mnt_userns, name, base, len, &this); + if (err) + return ERR_PTR(err); + + dentry = lookup_dcache(&this, base, 0); + return dentry ? dentry : __lookup_slow(&this, base, 0); +} +EXPORT_SYMBOL(lookup_one); + +/** + * lookup_one_unlocked - filesystem helper to lookup single pathname component + * @mnt_userns: idmapping of the mount the lookup is performed from * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to @@ -2674,14 +2755,15 @@ EXPORT_SYMBOL(lookup_one_len); * Unlike lookup_one_len, it should be called without the parent * i_mutex held, and will take the i_mutex itself if necessary. */ -struct dentry *lookup_one_len_unlocked(const char *name, - struct dentry *base, int len) +struct dentry *lookup_one_unlocked(struct user_namespace *mnt_userns, + const char *name, struct dentry *base, + int len) { struct qstr this; int err; struct dentry *ret; - err = lookup_one_len_common(name, base, len, &this); + err = lookup_one_common(mnt_userns, name, base, len, &this); if (err) return ERR_PTR(err); @@ -2690,6 +2772,59 @@ struct dentry *lookup_one_len_unlocked(const char *name, ret = lookup_slow(&this, base, 0); return ret; } +EXPORT_SYMBOL(lookup_one_unlocked); + +/** + * lookup_one_positive_unlocked - filesystem helper to lookup single + * pathname component + * @mnt_userns: idmapping of the mount the lookup is performed from + * @name: pathname component to lookup + * @base: base directory to lookup from + * @len: maximum length @len should be interpreted to + * + * This helper will yield ERR_PTR(-ENOENT) on negatives. The helper returns + * known positive or ERR_PTR(). This is what most of the users want. + * + * Note that pinned negative with unlocked parent _can_ become positive at any + * time, so callers of lookup_one_unlocked() need to be very careful; pinned + * positives have >d_inode stable, so this one avoids such problems. + * + * Note that this routine is purely a helper for filesystem usage and should + * not be called by generic code. + * + * The helper should be called without i_mutex held. + */ +struct dentry *lookup_one_positive_unlocked(struct user_namespace *mnt_userns, + const char *name, + struct dentry *base, int len) +{ + struct dentry *ret = lookup_one_unlocked(mnt_userns, name, base, len); + + if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { + dput(ret); + ret = ERR_PTR(-ENOENT); + } + return ret; +} +EXPORT_SYMBOL(lookup_one_positive_unlocked); + +/** + * lookup_one_len_unlocked - filesystem helper to lookup single pathname component + * @name: pathname component to lookup + * @base: base directory to lookup from + * @len: maximum length @len should be interpreted to + * + * Note that this routine is purely a helper for filesystem usage and should + * not be called by generic code. + * + * Unlike lookup_one_len, it should be called without the parent + * i_mutex held, and will take the i_mutex itself if necessary. + */ +struct dentry *lookup_one_len_unlocked(const char *name, + struct dentry *base, int len) +{ + return lookup_one_unlocked(&init_user_ns, name, base, len); +} EXPORT_SYMBOL(lookup_one_len_unlocked); /* @@ -2703,12 +2838,7 @@ EXPORT_SYMBOL(lookup_one_len_unlocked); struct dentry *lookup_positive_unlocked(const char *name, struct dentry *base, int len) { - struct dentry *ret = lookup_one_len_unlocked(name, base, len); - if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { - dput(ret); - ret = ERR_PTR(-ENOENT); - } - return ret; + return lookup_one_positive_unlocked(&init_user_ns, name, base, len); } EXPORT_SYMBOL(lookup_positive_unlocked); @@ -2718,24 +2848,23 @@ int path_pts(struct path *path) /* Find something mounted on "pts" in the same directory as * the input path. */ - struct dentry *child, *parent; - struct qstr this; - int ret; - - ret = path_parent_directory(path); - if (ret) - return ret; + struct dentry *parent = dget_parent(path->dentry); + struct dentry *child; + struct qstr this = QSTR_INIT("pts", 3); - parent = path->dentry; - this.name = "pts"; - this.len = 3; + if (unlikely(!path_connected(path->mnt, parent))) { + dput(parent); + return -ENOENT; + } + dput(path->dentry); + path->dentry = parent; child = d_hash_and_lookup(parent, &this); if (!child) return -ENOENT; path->dentry = child; dput(parent); - follow_mount(path); + follow_down(path); return 0; } #endif @@ -2743,102 +2872,24 @@ int path_pts(struct path *path) int user_path_at_empty(int dfd, const char __user *name, unsigned flags, struct path *path, int *empty) { - return filename_lookup(dfd, getname_flags(name, flags, empty), - flags, path, NULL); -} -EXPORT_SYMBOL(user_path_at_empty); + struct filename *filename = getname_flags(name, flags, empty); + int ret = filename_lookup(dfd, filename, flags, path, NULL); -/** - * path_mountpoint - look up a path to be umounted - * @nd: lookup context - * @flags: lookup flags - * @path: pointer to container for result - * - * Look up the given name, but don't attempt to revalidate the last component. - * Returns 0 and "path" will be valid on success; Returns error otherwise. - */ -static int -path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path) -{ - const char *s = path_init(nd, flags); - int err; - - while (!(err = link_path_walk(s, nd)) && - (err = lookup_last(nd)) > 0) { - s = trailing_symlink(nd); - } - if (!err && (nd->flags & LOOKUP_RCU)) - err = unlazy_walk(nd); - if (!err) - err = handle_lookup_down(nd); - if (!err) { - *path = nd->path; - nd->path.mnt = NULL; - nd->path.dentry = NULL; - } - terminate_walk(nd); - return err; -} - -static int -filename_mountpoint(int dfd, struct filename *name, struct path *path, - unsigned int flags) -{ - struct nameidata nd; - int error; - if (IS_ERR(name)) - return PTR_ERR(name); - set_nameidata(&nd, dfd, name); - error = path_mountpoint(&nd, flags | LOOKUP_RCU, path); - if (unlikely(error == -ECHILD)) - error = path_mountpoint(&nd, flags, path); - if (unlikely(error == -ESTALE)) - error = path_mountpoint(&nd, flags | LOOKUP_REVAL, path); - if (likely(!error)) - audit_inode(name, path->dentry, AUDIT_INODE_NOEVAL); - restore_nameidata(); - putname(name); - return error; -} - -/** - * user_path_mountpoint_at - lookup a path from userland in order to umount it - * @dfd: directory file descriptor - * @name: pathname from userland - * @flags: lookup flags - * @path: pointer to container to hold result - * - * A umount is a special case for path walking. We're not actually interested - * in the inode in this situation, and ESTALE errors can be a problem. We - * simply want track down the dentry and vfsmount attached at the mountpoint - * and avoid revalidating the last component. - * - * Returns 0 and populates "path" on success. - */ -int -user_path_mountpoint_at(int dfd, const char __user *name, unsigned int flags, - struct path *path) -{ - return filename_mountpoint(dfd, getname(name), path, flags); -} - -int -kern_path_mountpoint(int dfd, const char *name, struct path *path, - unsigned int flags) -{ - return filename_mountpoint(dfd, getname_kernel(name), path, flags); + putname(filename); + return ret; } -EXPORT_SYMBOL(kern_path_mountpoint); +EXPORT_SYMBOL(user_path_at_empty); -int __check_sticky(struct inode *dir, struct inode *inode) +int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir, + struct inode *inode) { kuid_t fsuid = current_fsuid(); - if (uid_eq(inode->i_uid, fsuid)) + if (uid_eq(i_uid_into_mnt(mnt_userns, inode), fsuid)) return 0; - if (uid_eq(dir->i_uid, fsuid)) + if (uid_eq(i_uid_into_mnt(mnt_userns, dir), fsuid)) return 0; - return !capable_wrt_inode_uidgid(inode, CAP_FOWNER); + return !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FOWNER); } EXPORT_SYMBOL(__check_sticky); @@ -2862,7 +2913,8 @@ EXPORT_SYMBOL(__check_sticky); * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ -static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) +static int may_delete(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); int error; @@ -2874,19 +2926,21 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) BUG_ON(victim->d_parent->d_inode != dir); /* Inode writeback is not safe when the uid or gid are invalid. */ - if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) + if (!uid_valid(i_uid_into_mnt(mnt_userns, inode)) || + !gid_valid(i_gid_into_mnt(mnt_userns, inode))) return -EOVERFLOW; audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); - error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; - if (check_sticky(dir, inode) || IS_APPEND(inode) || - IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(inode)) + if (check_sticky(mnt_userns, dir, inode) || IS_APPEND(inode) || + IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || + HAS_UNMAPPED_ID(mnt_userns, inode)) return -EPERM; if (isdir) { if (!d_is_dir(victim)) @@ -2911,19 +2965,18 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ -static inline int may_create(struct inode *dir, struct dentry *child) +static inline int may_create(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *child) { - struct user_namespace *s_user_ns; audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); if (child->d_inode) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; - s_user_ns = dir->i_sb->s_user_ns; - if (!kuid_has_mapping(s_user_ns, current_fsuid()) || - !kgid_has_mapping(s_user_ns, current_fsgid())) + if (!fsuidgid_has_mapping(dir->i_sb, mnt_userns)) return -EOVERFLOW; - return inode_permission(dir, MAY_WRITE | MAY_EXEC); + + return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); } /* @@ -2970,21 +3023,96 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) } EXPORT_SYMBOL(unlock_rename); -int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool want_excl) +/** + * mode_strip_umask - handle vfs umask stripping + * @dir: parent directory of the new inode + * @mode: mode of the new inode to be created in @dir + * + * Umask stripping depends on whether or not the filesystem supports POSIX + * ACLs. If the filesystem doesn't support it umask stripping is done directly + * in here. If the filesystem does support POSIX ACLs umask stripping is + * deferred until the filesystem calls posix_acl_create(). + * + * Returns: mode + */ +static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) +{ + if (!IS_POSIXACL(dir)) + mode &= ~current_umask(); + return mode; +} + +/** + * vfs_prepare_mode - prepare the mode to be used for a new inode + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: parent directory of the new inode + * @mode: mode of the new inode + * @mask_perms: allowed permission by the vfs + * @type: type of file to be created + * + * This helper consolidates and enforces vfs restrictions on the @mode of a new + * object to be created. + * + * Umask stripping depends on whether the filesystem supports POSIX ACLs (see + * the kernel documentation for mode_strip_umask()). Moving umask stripping + * after setgid stripping allows the same ordering for both non-POSIX ACL and + * POSIX ACL supporting filesystems. + * + * Note that it's currently valid for @type to be 0 if a directory is created. + * Filesystems raise that flag individually and we need to check whether each + * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a + * non-zero type. + * + * Returns: mode to be passed to the filesystem + */ +static inline umode_t vfs_prepare_mode(struct user_namespace *mnt_userns, + const struct inode *dir, umode_t mode, + umode_t mask_perms, umode_t type) +{ + mode = mode_strip_sgid(mnt_userns, dir, mode); + mode = mode_strip_umask(dir, mode); + + /* + * Apply the vfs mandated allowed permission mask and set the type of + * file to be created before we call into the filesystem. + */ + mode &= (mask_perms & ~S_IFMT); + mode |= (type & S_IFMT); + + return mode; +} + +/** + * vfs_create - create new file + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: inode of @dentry + * @dentry: pointer to dentry of the base directory + * @mode: mode of the new file + * @want_excl: whether the file must not yet exist + * + * Create a new file. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +int vfs_create(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, bool want_excl) { - int error = may_create(dir, dentry); + int error = may_create(mnt_userns, dir, dentry); if (error) return error; if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ - mode &= S_IALLUGO; - mode |= S_IFREG; + + mode = vfs_prepare_mode(mnt_userns, dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; - error = dir->i_op->create(dir, dentry, mode, want_excl); + error = dir->i_op->create(mnt_userns, dir, dentry, mode, want_excl); if (!error) fsnotify_create(dir, dentry); return error; @@ -2996,7 +3124,7 @@ int vfs_mkobj(struct dentry *dentry, umode_t mode, void *arg) { struct inode *dir = dentry->d_parent->d_inode; - int error = may_create(dir, dentry); + int error = may_create(&init_user_ns, dir, dentry); if (error) return error; @@ -3018,7 +3146,8 @@ bool may_open_dev(const struct path *path) !(path->mnt->mnt_sb->s_iflags & SB_I_NODEV); } -static int may_open(const struct path *path, int acc_mode, int flag) +static int may_open(struct user_namespace *mnt_userns, const struct path *path, + int acc_mode, int flag) { struct dentry *dentry = path->dentry; struct inode *inode = dentry->d_inode; @@ -3033,19 +3162,27 @@ static int may_open(const struct path *path, int acc_mode, int flag) case S_IFDIR: if (acc_mode & MAY_WRITE) return -EISDIR; + if (acc_mode & MAY_EXEC) + return -EACCES; break; case S_IFBLK: case S_IFCHR: if (!may_open_dev(path)) return -EACCES; - /*FALLTHRU*/ + fallthrough; case S_IFIFO: case S_IFSOCK: + if (acc_mode & MAY_EXEC) + return -EACCES; flag &= ~O_TRUNC; break; + case S_IFREG: + if ((acc_mode & MAY_EXEC) && path_noexec(path)) + return -EACCES; + break; } - error = inode_permission(inode, MAY_OPEN | acc_mode); + error = inode_permission(mnt_userns, inode, MAY_OPEN | acc_mode); if (error) return error; @@ -3060,27 +3197,23 @@ static int may_open(const struct path *path, int acc_mode, int flag) } /* O_NOATIME can only be set by the owner or superuser */ - if (flag & O_NOATIME && !inode_owner_or_capable(inode)) + if (flag & O_NOATIME && !inode_owner_or_capable(mnt_userns, inode)) return -EPERM; return 0; } -static int handle_truncate(struct file *filp) +static int handle_truncate(struct user_namespace *mnt_userns, struct file *filp) { const struct path *path = &filp->f_path; struct inode *inode = path->dentry->d_inode; int error = get_write_access(inode); if (error) return error; - /* - * Refuse to truncate files with mandatory locks held on them. - */ - error = locks_verify_locked(filp); - if (!error) - error = security_path_truncate(path); + + error = security_path_truncate(path); if (!error) { - error = do_truncate(path->dentry, 0, + error = do_truncate(mnt_userns, path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } @@ -3095,19 +3228,19 @@ static inline int open_to_namei_flags(int flag) return flag; } -static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode) +static int may_o_create(struct user_namespace *mnt_userns, + const struct path *dir, struct dentry *dentry, + umode_t mode) { - struct user_namespace *s_user_ns; int error = security_path_mknod(dir, dentry, mode, 0); if (error) return error; - s_user_ns = dir->dentry->d_sb->s_user_ns; - if (!kuid_has_mapping(s_user_ns, current_fsuid()) || - !kgid_has_mapping(s_user_ns, current_fsgid())) + if (!fsuidgid_has_mapping(dir->dentry->d_sb, mnt_userns)) return -EOVERFLOW; - error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); + error = inode_permission(mnt_userns, dir->dentry->d_inode, + MAY_WRITE | MAY_EXEC); if (error) return error; @@ -3127,18 +3260,14 @@ static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t m * * Returns an error code otherwise. */ -static int atomic_open(struct nameidata *nd, struct dentry *dentry, - struct path *path, struct file *file, - const struct open_flags *op, - int open_flag, umode_t mode) +static struct dentry *atomic_open(struct nameidata *nd, struct dentry *dentry, + struct file *file, + int open_flag, umode_t mode) { struct dentry *const DENTRY_NOT_SET = (void *) -1UL; struct inode *dir = nd->path.dentry->d_inode; int error; - if (!(~open_flag & (O_EXCL | O_CREAT))) /* both O_EXCL and O_CREAT */ - open_flag &= ~O_TRUNC; - if (nd->flags & LOOKUP_DIRECTORY) open_flag |= O_DIRECTORY; @@ -3149,19 +3278,10 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, d_lookup_done(dentry); if (!error) { if (file->f_mode & FMODE_OPENED) { - /* - * We didn't have the inode before the open, so check open - * permission here. - */ - int acc_mode = op->acc_mode; - if (file->f_mode & FMODE_CREATED) { - WARN_ON(!(open_flag & O_CREAT)); - fsnotify_create(dir, dentry); - acc_mode = 0; + if (unlikely(dentry != file->f_path.dentry)) { + dput(dentry); + dentry = dget(file->f_path.dentry); } - error = may_open(&file->f_path, acc_mode, open_flag); - if (WARN_ON(error > 0)) - error = -EINVAL; } else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { error = -EIO; } else { @@ -3169,19 +3289,15 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, dput(dentry); dentry = file->f_path.dentry; } - if (file->f_mode & FMODE_CREATED) - fsnotify_create(dir, dentry); - if (unlikely(d_is_negative(dentry))) { + if (unlikely(d_is_negative(dentry))) error = -ENOENT; - } else { - path->dentry = dentry; - path->mnt = nd->path.mnt; - return 0; - } } } - dput(dentry); - return error; + if (error) { + dput(dentry); + dentry = ERR_PTR(error); + } + return dentry; } /* @@ -3199,11 +3315,11 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, * * An error code is returned on failure. */ -static int lookup_open(struct nameidata *nd, struct path *path, - struct file *file, - const struct open_flags *op, - bool got_write) +static struct dentry *lookup_open(struct nameidata *nd, struct file *file, + const struct open_flags *op, + bool got_write) { + struct user_namespace *mnt_userns; struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; int open_flag = op->open_flag; @@ -3213,7 +3329,7 @@ static int lookup_open(struct nameidata *nd, struct path *path, DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); if (unlikely(IS_DEADDIR(dir_inode))) - return -ENOENT; + return ERR_PTR(-ENOENT); file->f_mode &= ~FMODE_CREATED; dentry = d_lookup(dir, &nd->last); @@ -3221,7 +3337,7 @@ static int lookup_open(struct nameidata *nd, struct path *path, if (!dentry) { dentry = d_alloc_parallel(dir, &nd->last, &wq); if (IS_ERR(dentry)) - return PTR_ERR(dentry); + return dentry; } if (d_in_lookup(dentry)) break; @@ -3237,7 +3353,7 @@ static int lookup_open(struct nameidata *nd, struct path *path, } if (dentry->d_inode) { /* Cached positive dentry: will open in f_op->open */ - goto out_no_open; + return dentry; } /* @@ -3249,41 +3365,28 @@ static int lookup_open(struct nameidata *nd, struct path *path, * Another problem is returing the "right" error value (e.g. for an * O_EXCL open we want to return EEXIST not EROFS). */ + if (unlikely(!got_write)) + open_flag &= ~O_TRUNC; + mnt_userns = mnt_user_ns(nd->path.mnt); if (open_flag & O_CREAT) { - if (!IS_POSIXACL(dir->d_inode)) - mode &= ~current_umask(); - if (unlikely(!got_write)) { + if (open_flag & O_EXCL) + open_flag &= ~O_TRUNC; + mode = vfs_prepare_mode(mnt_userns, dir->d_inode, mode, mode, mode); + if (likely(got_write)) + create_error = may_o_create(mnt_userns, &nd->path, + dentry, mode); + else create_error = -EROFS; - open_flag &= ~O_CREAT; - if (open_flag & (O_EXCL | O_TRUNC)) - goto no_open; - /* No side effects, safe to clear O_CREAT */ - } else { - create_error = may_o_create(&nd->path, dentry, mode); - if (create_error) { - open_flag &= ~O_CREAT; - if (open_flag & O_EXCL) - goto no_open; - } - } - } else if ((open_flag & (O_TRUNC|O_WRONLY|O_RDWR)) && - unlikely(!got_write)) { - /* - * No O_CREATE -> atomicity not a requirement -> fall - * back to lookup + open - */ - goto no_open; } - + if (create_error) + open_flag &= ~O_CREAT; if (dir_inode->i_op->atomic_open) { - error = atomic_open(nd, dentry, path, file, op, open_flag, - mode); - if (unlikely(error == -ENOENT) && create_error) - error = create_error; - return error; + dentry = atomic_open(nd, dentry, file, open_flag, mode); + if (unlikely(create_error) && dentry == ERR_PTR(-ENOENT)) + dentry = ERR_PTR(create_error); + return dentry; } -no_open: if (d_in_lookup(dentry)) { struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry, nd->flags); @@ -3306,88 +3409,65 @@ no_open: error = -EACCES; goto out_dput; } - error = dir_inode->i_op->create(dir_inode, dentry, mode, - open_flag & O_EXCL); + + error = dir_inode->i_op->create(mnt_userns, dir_inode, dentry, + mode, open_flag & O_EXCL); if (error) goto out_dput; - fsnotify_create(dir_inode, dentry); } if (unlikely(create_error) && !dentry->d_inode) { error = create_error; goto out_dput; } -out_no_open: - path->dentry = dentry; - path->mnt = nd->path.mnt; - return 0; + return dentry; out_dput: dput(dentry); - return error; + return ERR_PTR(error); } -/* - * Handle the last step of open() - */ -static int do_last(struct nameidata *nd, +static const char *open_last_lookups(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct dentry *dir = nd->path.dentry; - kuid_t dir_uid = nd->inode->i_uid; - umode_t dir_mode = nd->inode->i_mode; int open_flag = op->open_flag; - bool will_truncate = (open_flag & O_TRUNC) != 0; bool got_write = false; - int acc_mode = op->acc_mode; - unsigned seq; - struct inode *inode; - struct path path; - int error; + struct dentry *dentry; + const char *res; - nd->flags &= ~LOOKUP_PARENT; nd->flags |= op->intent; if (nd->last_type != LAST_NORM) { - error = handle_dots(nd, nd->last_type); - if (unlikely(error)) - return error; - goto finish_open; + if (nd->depth) + put_link(nd); + return handle_dots(nd, nd->last_type); } if (!(open_flag & O_CREAT)) { if (nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; /* we _can_ be in RCU mode here */ - error = lookup_fast(nd, &path, &inode, &seq); - if (likely(error > 0)) + dentry = lookup_fast(nd); + if (IS_ERR(dentry)) + return ERR_CAST(dentry); + if (likely(dentry)) goto finish_lookup; - if (error < 0) - return error; - - BUG_ON(nd->inode != dir->d_inode); BUG_ON(nd->flags & LOOKUP_RCU); } else { /* create side of things */ - /* - * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED - * has been cleared when we got to the last component we are - * about to look up - */ - error = complete_walk(nd); - if (error) - return error; - + if (nd->flags & LOOKUP_RCU) { + if (!try_to_unlazy(nd)) + return ERR_PTR(-ECHILD); + } audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* trailing slashes? */ if (unlikely(nd->last.name[nd->last.len])) - return -EISDIR; + return ERR_PTR(-EISDIR); } if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { - error = mnt_want_write(nd->path.mnt); - if (!error) - got_write = true; + got_write = !mnt_want_write(nd->path.mnt); /* * do _not_ fail yet - we might not need that or fail with * a different error; let lookup_open() decide; we'll be @@ -3398,176 +3478,199 @@ static int do_last(struct nameidata *nd, inode_lock(dir->d_inode); else inode_lock_shared(dir->d_inode); - error = lookup_open(nd, &path, file, op, got_write); + dentry = lookup_open(nd, file, op, got_write); + if (!IS_ERR(dentry) && (file->f_mode & FMODE_CREATED)) + fsnotify_create(dir->d_inode, dentry); if (open_flag & O_CREAT) inode_unlock(dir->d_inode); else inode_unlock_shared(dir->d_inode); - if (error) - goto out; - - if (file->f_mode & FMODE_OPENED) { - if ((file->f_mode & FMODE_CREATED) || - !S_ISREG(file_inode(file)->i_mode)) - will_truncate = false; - - audit_inode(nd->name, file->f_path.dentry, 0); - goto opened; - } + if (got_write) + mnt_drop_write(nd->path.mnt); - if (file->f_mode & FMODE_CREATED) { - /* Don't check for write permission, don't truncate */ - open_flag &= ~O_TRUNC; - will_truncate = false; - acc_mode = 0; - path_to_nameidata(&path, nd); - goto finish_open_created; - } + if (IS_ERR(dentry)) + return ERR_CAST(dentry); - /* - * If atomic_open() acquired write access it is dropped now due to - * possible mount and symlink following (this might be optimized away if - * necessary...) - */ - if (got_write) { - mnt_drop_write(nd->path.mnt); - got_write = false; + if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) { + dput(nd->path.dentry); + nd->path.dentry = dentry; + return NULL; } - error = follow_managed(&path, nd); - if (unlikely(error < 0)) - return error; +finish_lookup: + if (nd->depth) + put_link(nd); + res = step_into(nd, WALK_TRAILING, dentry); + if (unlikely(res)) + nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); + return res; +} - /* - * create/update audit record if it already exists. - */ - audit_inode(nd->name, path.dentry, 0); +/* + * Handle the last step of open() + */ +static int do_open(struct nameidata *nd, + struct file *file, const struct open_flags *op) +{ + struct user_namespace *mnt_userns; + int open_flag = op->open_flag; + bool do_truncate; + int acc_mode; + int error; - if (unlikely((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))) { - path_to_nameidata(&path, nd); - return -EEXIST; + if (!(file->f_mode & (FMODE_OPENED | FMODE_CREATED))) { + error = complete_walk(nd); + if (error) + return error; } - - seq = 0; /* out of RCU mode, so the value doesn't matter */ - inode = d_backing_inode(path.dentry); -finish_lookup: - error = step_into(nd, &path, 0, inode, seq); - if (unlikely(error)) - return error; -finish_open: - /* Why this, you ask? _Now_ we might have grown LOOKUP_JUMPED... */ - error = complete_walk(nd); - if (error) - return error; - audit_inode(nd->name, nd->path.dentry, 0); + if (!(file->f_mode & FMODE_CREATED)) + audit_inode(nd->name, nd->path.dentry, 0); + mnt_userns = mnt_user_ns(nd->path.mnt); if (open_flag & O_CREAT) { - error = -EISDIR; + if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED)) + return -EEXIST; if (d_is_dir(nd->path.dentry)) - goto out; - error = may_create_in_sticky(dir_mode, dir_uid, + return -EISDIR; + error = may_create_in_sticky(mnt_userns, nd, d_backing_inode(nd->path.dentry)); if (unlikely(error)) - goto out; + return error; } - error = -ENOTDIR; if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) - goto out; - if (!d_is_reg(nd->path.dentry)) - will_truncate = false; + return -ENOTDIR; - if (will_truncate) { + do_truncate = false; + acc_mode = op->acc_mode; + if (file->f_mode & FMODE_CREATED) { + /* Don't check for write permission, don't truncate */ + open_flag &= ~O_TRUNC; + acc_mode = 0; + } else if (d_is_reg(nd->path.dentry) && open_flag & O_TRUNC) { error = mnt_want_write(nd->path.mnt); if (error) - goto out; - got_write = true; + return error; + do_truncate = true; } -finish_open_created: - error = may_open(&nd->path, acc_mode, open_flag); - if (error) - goto out; - BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */ - error = vfs_open(&nd->path, file); - if (error) - goto out; -opened: - error = ima_file_check(file, op->acc_mode); - if (!error && will_truncate) - error = handle_truncate(file); -out: + error = may_open(mnt_userns, &nd->path, acc_mode, open_flag); + if (!error && !(file->f_mode & FMODE_OPENED)) + error = vfs_open(&nd->path, file); + if (!error) + error = ima_file_check(file, op->acc_mode); + if (!error && do_truncate) + error = handle_truncate(mnt_userns, file); if (unlikely(error > 0)) { WARN_ON(1); error = -EINVAL; } - if (got_write) + if (do_truncate) mnt_drop_write(nd->path.mnt); return error; } -struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) +/** + * vfs_tmpfile - create tmpfile + * @mnt_userns: user namespace of the mount the inode was found from + * @dentry: pointer to dentry of the base directory + * @mode: mode of the new tmpfile + * @open_flag: flags + * + * Create a temporary file. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +static int vfs_tmpfile(struct user_namespace *mnt_userns, + const struct path *parentpath, + struct file *file, umode_t mode) { - struct dentry *child = NULL; - struct inode *dir = dentry->d_inode; + struct dentry *child; + struct inode *dir = d_inode(parentpath->dentry); struct inode *inode; int error; /* we want directory to be writable */ - error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); if (error) - goto out_err; - error = -EOPNOTSUPP; + return error; if (!dir->i_op->tmpfile) - goto out_err; - error = -ENOMEM; - child = d_alloc(dentry, &slash_name); + return -EOPNOTSUPP; + child = d_alloc(parentpath->dentry, &slash_name); if (unlikely(!child)) - goto out_err; - error = dir->i_op->tmpfile(dir, child, mode); + return -ENOMEM; + file->f_path.mnt = parentpath->mnt; + file->f_path.dentry = child; + mode = vfs_prepare_mode(mnt_userns, dir, mode, mode, mode); + error = dir->i_op->tmpfile(mnt_userns, dir, file, mode); + dput(child); if (error) - goto out_err; - error = -ENOENT; - inode = child->d_inode; - if (unlikely(!inode)) - goto out_err; - if (!(open_flag & O_EXCL)) { + return error; + /* Don't check for other permissions, the inode was just created */ + error = may_open(mnt_userns, &file->f_path, 0, file->f_flags); + if (error) + return error; + inode = file_inode(file); + if (!(file->f_flags & O_EXCL)) { spin_lock(&inode->i_lock); inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); } - ima_post_create_tmpfile(inode); - return child; + ima_post_create_tmpfile(mnt_userns, inode); + return 0; +} -out_err: - dput(child); - return ERR_PTR(error); +/** + * vfs_tmpfile_open - open a tmpfile for kernel internal use + * @mnt_userns: user namespace of the mount the inode was found from + * @parentpath: path of the base directory + * @mode: mode of the new tmpfile + * @open_flag: flags + * @cred: credentials for open + * + * Create and open a temporary file. The file is not accounted in nr_files, + * hence this is only for kernel internal use, and must not be installed into + * file tables or such. + */ +struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns, + const struct path *parentpath, + umode_t mode, int open_flag, const struct cred *cred) +{ + struct file *file; + int error; + + file = alloc_empty_file_noaccount(open_flag, cred); + if (!IS_ERR(file)) { + error = vfs_tmpfile(mnt_userns, parentpath, file, mode); + if (error) { + fput(file); + file = ERR_PTR(error); + } + } + return file; } -EXPORT_SYMBOL(vfs_tmpfile); +EXPORT_SYMBOL(vfs_tmpfile_open); static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file) { - struct dentry *child; + struct user_namespace *mnt_userns; struct path path; int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path); + if (unlikely(error)) return error; error = mnt_want_write(path.mnt); if (unlikely(error)) goto out; - child = vfs_tmpfile(path.dentry, op->mode, op->open_flag); - error = PTR_ERR(child); - if (IS_ERR(child)) - goto out2; - dput(path.dentry); - path.dentry = child; - audit_inode(nd->name, child, 0); - /* Don't check for other permissions, the inode was just created */ - error = may_open(&path, 0, op->open_flag); + mnt_userns = mnt_user_ns(path.mnt); + error = vfs_tmpfile(mnt_userns, &path, file, op->mode); if (error) goto out2; - file->f_path.mnt = path.mnt; - error = finish_open(file, child, NULL); + audit_inode(nd->name, file->f_path.dentry, 0); out2: mnt_drop_write(path.mnt); out: @@ -3604,10 +3707,10 @@ static struct file *path_openat(struct nameidata *nd, } else { const char *s = path_init(nd, flags); while (!(error = link_path_walk(s, nd)) && - (error = do_last(nd, file, op)) > 0) { - nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); - s = trailing_symlink(nd); - } + (s = open_last_lookups(nd, file, op)) != NULL) + ; + if (!error) + error = do_open(nd, file, op); terminate_walk(nd); } if (likely(!error)) { @@ -3633,7 +3736,7 @@ struct file *do_filp_open(int dfd, struct filename *pathname, int flags = op->lookup_flags; struct file *filp; - set_nameidata(&nd, dfd, pathname); + set_nameidata(&nd, dfd, pathname, NULL); filp = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(filp == ERR_PTR(-ECHILD))) filp = path_openat(&nd, op, flags); @@ -3643,25 +3746,22 @@ struct file *do_filp_open(int dfd, struct filename *pathname, return filp; } -struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt, +struct file *do_file_open_root(const struct path *root, const char *name, const struct open_flags *op) { struct nameidata nd; struct file *file; struct filename *filename; - int flags = op->lookup_flags | LOOKUP_ROOT; - - nd.root.mnt = mnt; - nd.root.dentry = dentry; + int flags = op->lookup_flags; - if (d_is_symlink(dentry) && op->intent & LOOKUP_OPEN) + if (d_is_symlink(root->dentry) && op->intent & LOOKUP_OPEN) return ERR_PTR(-ELOOP); filename = getname_kernel(name); if (IS_ERR(filename)) return ERR_CAST(filename); - set_nameidata(&nd, -1, filename); + set_nameidata(&nd, -1, filename, root); file = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(file == ERR_PTR(-ECHILD))) file = path_openat(&nd, op, flags); @@ -3673,24 +3773,20 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt, } static struct dentry *filename_create(int dfd, struct filename *name, - struct path *path, unsigned int lookup_flags) + struct path *path, unsigned int lookup_flags) { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; + bool want_dir = lookup_flags & LOOKUP_DIRECTORY; + unsigned int reval_flag = lookup_flags & LOOKUP_REVAL; + unsigned int create_flags = LOOKUP_CREATE | LOOKUP_EXCL; int type; int err2; int error; - bool is_dir = (lookup_flags & LOOKUP_DIRECTORY); - /* - * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any - * other flags passed in are ignored! - */ - lookup_flags &= LOOKUP_REVAL; - - name = filename_parentat(dfd, name, lookup_flags, path, &last, &type); - if (IS_ERR(name)) - return ERR_CAST(name); + error = filename_parentat(dfd, name, reval_flag, path, &last, &type); + if (error) + return ERR_PTR(error); /* * Yucky last component or no last component at all? @@ -3702,11 +3798,13 @@ static struct dentry *filename_create(int dfd, struct filename *name, /* don't fail immediately if it's r/o, at least try to report other errors */ err2 = mnt_want_write(path->mnt); /* - * Do the final lookup. + * Do the final lookup. Suppress 'create' if there is a trailing + * '/', and a directory wasn't requested. */ - lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL; + if (last.name[last.len] && !want_dir) + create_flags = 0; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path->dentry, lookup_flags); + dentry = __lookup_hash(&last, path->dentry, reval_flag | create_flags); if (IS_ERR(dentry)) goto unlock; @@ -3720,7 +3818,7 @@ static struct dentry *filename_create(int dfd, struct filename *name, * all is fine. Let's be bastards - you had / on the end, you've * been asking for (non-existent) directory. -ENOENT for you. */ - if (unlikely(!is_dir && last.name[last.len])) { + if (unlikely(!create_flags)) { error = -ENOENT; goto fail; } @@ -3728,7 +3826,6 @@ static struct dentry *filename_create(int dfd, struct filename *name, error = err2; goto fail; } - putname(name); return dentry; fail: dput(dentry); @@ -3739,15 +3836,17 @@ unlock: mnt_drop_write(path->mnt); out: path_put(path); - putname(name); return dentry; } struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, unsigned int lookup_flags) { - return filename_create(dfd, getname_kernel(pathname), - path, lookup_flags); + struct filename *filename = getname_kernel(pathname); + struct dentry *res = filename_create(dfd, filename, path, lookup_flags); + + putname(filename); + return res; } EXPORT_SYMBOL(kern_path_create); @@ -3763,23 +3862,47 @@ EXPORT_SYMBOL(done_path_create); inline struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, unsigned int lookup_flags) { - return filename_create(dfd, getname(pathname), path, lookup_flags); + struct filename *filename = getname(pathname); + struct dentry *res = filename_create(dfd, filename, path, lookup_flags); + + putname(filename); + return res; } EXPORT_SYMBOL(user_path_create); -int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) +/** + * vfs_mknod - create device node or file + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: inode of @dentry + * @dentry: pointer to dentry of the base directory + * @mode: mode of the new device node or file + * @dev: device number of device to create + * + * Create a device node or file. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +int vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode, dev_t dev) { - int error = may_create(dir, dentry); + bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; + int error = may_create(mnt_userns, dir, dentry); if (error) return error; - if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD)) + if ((S_ISCHR(mode) || S_ISBLK(mode)) && !is_whiteout && + !capable(CAP_MKNOD)) return -EPERM; if (!dir->i_op->mknod) return -EPERM; + mode = vfs_prepare_mode(mnt_userns, dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; @@ -3788,7 +3911,7 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) if (error) return error; - error = dir->i_op->mknod(dir, dentry, mode, dev); + error = dir->i_op->mknod(mnt_userns, dir, dentry, mode, dev); if (!error) fsnotify_create(dir, dentry); return error; @@ -3812,9 +3935,10 @@ static int may_mknod(umode_t mode) } } -long do_mknodat(int dfd, const char __user *filename, umode_t mode, +static int do_mknodat(int dfd, struct filename *name, umode_t mode, unsigned int dev) { + struct user_namespace *mnt_userns; struct dentry *dentry; struct path path; int error; @@ -3822,54 +3946,76 @@ long do_mknodat(int dfd, const char __user *filename, umode_t mode, error = may_mknod(mode); if (error) - return error; + goto out1; retry: - dentry = user_path_create(dfd, filename, &path, lookup_flags); + dentry = filename_create(dfd, name, &path, lookup_flags); + error = PTR_ERR(dentry); if (IS_ERR(dentry)) - return PTR_ERR(dentry); + goto out1; - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); - error = security_path_mknod(&path, dentry, mode, dev); + error = security_path_mknod(&path, dentry, + mode_strip_umask(path.dentry->d_inode, mode), dev); if (error) - goto out; + goto out2; + + mnt_userns = mnt_user_ns(path.mnt); switch (mode & S_IFMT) { case 0: case S_IFREG: - error = vfs_create(path.dentry->d_inode,dentry,mode,true); + error = vfs_create(mnt_userns, path.dentry->d_inode, + dentry, mode, true); if (!error) - ima_post_path_mknod(dentry); + ima_post_path_mknod(mnt_userns, dentry); break; case S_IFCHR: case S_IFBLK: - error = vfs_mknod(path.dentry->d_inode,dentry,mode, - new_decode_dev(dev)); + error = vfs_mknod(mnt_userns, path.dentry->d_inode, + dentry, mode, new_decode_dev(dev)); break; case S_IFIFO: case S_IFSOCK: - error = vfs_mknod(path.dentry->d_inode,dentry,mode,0); + error = vfs_mknod(mnt_userns, path.dentry->d_inode, + dentry, mode, 0); break; } -out: +out2: done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } +out1: + putname(name); return error; } SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, dev) { - return do_mknodat(dfd, filename, mode, dev); + return do_mknodat(dfd, getname(filename), mode, dev); } SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev) { - return do_mknodat(AT_FDCWD, filename, mode, dev); + return do_mknodat(AT_FDCWD, getname(filename), mode, dev); } -int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +/** + * vfs_mkdir - create directory + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: inode of @dentry + * @dentry: pointer to dentry of the base directory + * @mode: mode of the new directory + * + * Create a directory. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +int vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { - int error = may_create(dir, dentry); + int error = may_create(mnt_userns, dir, dentry); unsigned max_links = dir->i_sb->s_max_links; if (error) @@ -3878,7 +4024,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (!dir->i_op->mkdir) return -EPERM; - mode &= (S_IRWXUGO|S_ISVTX); + mode = vfs_prepare_mode(mnt_userns, dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) return error; @@ -3886,14 +4032,14 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (max_links && dir->i_nlink >= max_links) return -EMLINK; - error = dir->i_op->mkdir(dir, dentry, mode); + error = dir->i_op->mkdir(mnt_userns, dir, dentry, mode); if (!error) fsnotify_mkdir(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkdir); -long do_mkdirat(int dfd, const char __user *pathname, umode_t mode) +int do_mkdirat(int dfd, struct filename *name, umode_t mode) { struct dentry *dentry; struct path path; @@ -3901,36 +4047,57 @@ long do_mkdirat(int dfd, const char __user *pathname, umode_t mode) unsigned int lookup_flags = LOOKUP_DIRECTORY; retry: - dentry = user_path_create(dfd, pathname, &path, lookup_flags); + dentry = filename_create(dfd, name, &path, lookup_flags); + error = PTR_ERR(dentry); if (IS_ERR(dentry)) - return PTR_ERR(dentry); + goto out_putname; - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); - error = security_path_mkdir(&path, dentry, mode); - if (!error) - error = vfs_mkdir(path.dentry->d_inode, dentry, mode); + error = security_path_mkdir(&path, dentry, + mode_strip_umask(path.dentry->d_inode, mode)); + if (!error) { + struct user_namespace *mnt_userns; + mnt_userns = mnt_user_ns(path.mnt); + error = vfs_mkdir(mnt_userns, path.dentry->d_inode, dentry, + mode); + } done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } +out_putname: + putname(name); return error; } SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) { - return do_mkdirat(dfd, pathname, mode); + return do_mkdirat(dfd, getname(pathname), mode); } SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) { - return do_mkdirat(AT_FDCWD, pathname, mode); + return do_mkdirat(AT_FDCWD, getname(pathname), mode); } -int vfs_rmdir(struct inode *dir, struct dentry *dentry) +/** + * vfs_rmdir - remove directory + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: inode of @dentry + * @dentry: pointer to dentry of the base directory + * + * Remove a directory. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry) { - int error = may_delete(dir, dentry, 1); + int error = may_delete(mnt_userns, dir, dentry, 1); if (error) return error; @@ -3942,7 +4109,8 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) inode_lock(dentry->d_inode); error = -EBUSY; - if (is_local_mountpoint(dentry)) + if (is_local_mountpoint(dentry) || + (dentry->d_inode->i_flags & S_KERNEL_FILE)) goto out; error = security_inode_rmdir(dir, dentry); @@ -3957,83 +4125,84 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); - fsnotify_rmdir(dir, dentry); out: inode_unlock(dentry->d_inode); dput(dentry); if (!error) - d_delete(dentry); + d_delete_notify(dir, dentry); return error; } EXPORT_SYMBOL(vfs_rmdir); -long do_rmdir(int dfd, const char __user *pathname) +int do_rmdir(int dfd, struct filename *name) { - int error = 0; - struct filename *name; + struct user_namespace *mnt_userns; + int error; struct dentry *dentry; struct path path; struct qstr last; int type; unsigned int lookup_flags = 0; retry: - name = filename_parentat(dfd, getname(pathname), lookup_flags, - &path, &last, &type); - if (IS_ERR(name)) - return PTR_ERR(name); + error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); + if (error) + goto exit1; switch (type) { case LAST_DOTDOT: error = -ENOTEMPTY; - goto exit1; + goto exit2; case LAST_DOT: error = -EINVAL; - goto exit1; + goto exit2; case LAST_ROOT: error = -EBUSY; - goto exit1; + goto exit2; } error = mnt_want_write(path.mnt); if (error) - goto exit1; + goto exit2; inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) - goto exit2; + goto exit3; if (!dentry->d_inode) { error = -ENOENT; - goto exit3; + goto exit4; } error = security_path_rmdir(&path, dentry); if (error) - goto exit3; - error = vfs_rmdir(path.dentry->d_inode, dentry); -exit3: + goto exit4; + mnt_userns = mnt_user_ns(path.mnt); + error = vfs_rmdir(mnt_userns, path.dentry->d_inode, dentry); +exit4: dput(dentry); -exit2: +exit3: inode_unlock(path.dentry->d_inode); mnt_drop_write(path.mnt); -exit1: +exit2: path_put(&path); - putname(name); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } +exit1: + putname(name); return error; } SYSCALL_DEFINE1(rmdir, const char __user *, pathname) { - return do_rmdir(AT_FDCWD, pathname); + return do_rmdir(AT_FDCWD, getname(pathname)); } /** * vfs_unlink - unlink a filesystem object + * @mnt_userns: user namespace of the mount the inode was found from * @dir: parent directory * @dentry: victim * @delegated_inode: returns victim inode, if the inode is delegated. @@ -4049,11 +4218,18 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname) * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. */ -int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) +int vfs_unlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, struct inode **delegated_inode) { struct inode *target = dentry->d_inode; - int error = may_delete(dir, dentry, 0); + int error = may_delete(mnt_userns, dir, dentry, 0); if (error) return error; @@ -4062,7 +4238,9 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate return -EPERM; inode_lock(target); - if (is_local_mountpoint(dentry)) + if (IS_SWAPFILE(target)) + error = -EPERM; + else if (is_local_mountpoint(dentry)) error = -EBUSY; else { error = security_inode_unlink(dir, dentry); @@ -4074,7 +4252,6 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate if (!error) { dont_mount(dentry); detach_mounts(dentry); - fsnotify_unlink(dir, dentry); } } } @@ -4082,9 +4259,11 @@ out: inode_unlock(target); /* We don't d_delete() NFS sillyrenamed files--they still exist. */ - if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) { + if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) { + fsnotify_unlink(dir, dentry); + } else if (!error) { fsnotify_link_count(target); - d_delete(dentry); + d_delete_notify(dir, dentry); } return error; @@ -4097,7 +4276,7 @@ EXPORT_SYMBOL(vfs_unlink); * writeout happening, and we don't want to prevent access to the directory * while waiting on the I/O. */ -long do_unlinkat(int dfd, struct filename *name) +int do_unlinkat(int dfd, struct filename *name) { int error; struct dentry *dentry; @@ -4108,22 +4287,24 @@ long do_unlinkat(int dfd, struct filename *name) struct inode *delegated_inode = NULL; unsigned int lookup_flags = 0; retry: - name = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); - if (IS_ERR(name)) - return PTR_ERR(name); + error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); + if (error) + goto exit1; error = -EISDIR; if (type != LAST_NORM) - goto exit1; + goto exit2; error = mnt_want_write(path.mnt); if (error) - goto exit1; + goto exit2; retry_deleg: inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { + struct user_namespace *mnt_userns; + /* Why not before? Because we want correct error value */ if (last.name[last.len]) goto slashes; @@ -4133,9 +4314,11 @@ retry_deleg: ihold(inode); error = security_path_unlink(&path, dentry); if (error) - goto exit2; - error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode); -exit2: + goto exit3; + mnt_userns = mnt_user_ns(path.mnt); + error = vfs_unlink(mnt_userns, path.dentry->d_inode, dentry, + &delegated_inode); +exit3: dput(dentry); } inode_unlock(path.dentry->d_inode); @@ -4148,13 +4331,14 @@ exit2: goto retry_deleg; } mnt_drop_write(path.mnt); -exit1: +exit2: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; inode = NULL; goto retry; } +exit1: putname(name); return error; @@ -4165,7 +4349,7 @@ slashes: error = -EISDIR; else error = -ENOTDIR; - goto exit2; + goto exit3; } SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag) @@ -4174,8 +4358,7 @@ SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag) return -EINVAL; if (flag & AT_REMOVEDIR) - return do_rmdir(dfd, pathname); - + return do_rmdir(dfd, getname(pathname)); return do_unlinkat(dfd, getname(pathname)); } @@ -4184,9 +4367,25 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname) return do_unlinkat(AT_FDCWD, getname(pathname)); } -int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) +/** + * vfs_symlink - create symlink + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: inode of @dentry + * @dentry: pointer to dentry of the base directory + * @oldname: name of the file to link to + * + * Create a symlink. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. + */ +int vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, const char *oldname) { - int error = may_create(dir, dentry); + int error = may_create(mnt_userns, dir, dentry); if (error) return error; @@ -4198,40 +4397,45 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) if (error) return error; - error = dir->i_op->symlink(dir, dentry, oldname); + error = dir->i_op->symlink(mnt_userns, dir, dentry, oldname); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_symlink); -long do_symlinkat(const char __user *oldname, int newdfd, - const char __user *newname) +int do_symlinkat(struct filename *from, int newdfd, struct filename *to) { int error; - struct filename *from; struct dentry *dentry; struct path path; unsigned int lookup_flags = 0; - from = getname(oldname); - if (IS_ERR(from)) - return PTR_ERR(from); + if (IS_ERR(from)) { + error = PTR_ERR(from); + goto out_putnames; + } retry: - dentry = user_path_create(newdfd, newname, &path, lookup_flags); + dentry = filename_create(newdfd, to, &path, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) - goto out_putname; + goto out_putnames; error = security_path_symlink(&path, dentry, from->name); - if (!error) - error = vfs_symlink(path.dentry->d_inode, dentry, from->name); + if (!error) { + struct user_namespace *mnt_userns; + + mnt_userns = mnt_user_ns(path.mnt); + error = vfs_symlink(mnt_userns, path.dentry->d_inode, dentry, + from->name); + } done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } -out_putname: +out_putnames: + putname(to); putname(from); return error; } @@ -4239,17 +4443,18 @@ out_putname: SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname) { - return do_symlinkat(oldname, newdfd, newname); + return do_symlinkat(getname(oldname), newdfd, getname(newname)); } SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname) { - return do_symlinkat(oldname, AT_FDCWD, newname); + return do_symlinkat(getname(oldname), AT_FDCWD, getname(newname)); } /** * vfs_link - create a new link * @old_dentry: object to be linked + * @mnt_userns: the user namespace of the mount * @dir: new parent * @new_dentry: where to create the new link * @delegated_inode: returns inode needing a delegation break @@ -4265,8 +4470,16 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. + * + * If the inode has been found through an idmapped mount the user namespace of + * the vfsmount must be passed through @mnt_userns. This function will then take + * care to map the inode according to @mnt_userns before checking permissions. + * On non-idmapped mounts or if permission checking is to be performed on the + * raw inode simply passs init_user_ns. */ -int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) +int vfs_link(struct dentry *old_dentry, struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *new_dentry, + struct inode **delegated_inode) { struct inode *inode = old_dentry->d_inode; unsigned max_links = dir->i_sb->s_max_links; @@ -4275,7 +4488,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de if (!inode) return -ENOENT; - error = may_create(dir, new_dentry); + error = may_create(mnt_userns, dir, new_dentry); if (error) return error; @@ -4292,7 +4505,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de * be writen back improperly if their true value is unknown to * the vfs. */ - if (HAS_UNMAPPED_ID(inode)) + if (HAS_UNMAPPED_ID(mnt_userns, inode)) return -EPERM; if (!dir->i_op->link) return -EPERM; @@ -4336,51 +4549,55 @@ EXPORT_SYMBOL(vfs_link); * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ -int do_linkat(int olddfd, const char __user *oldname, int newdfd, - const char __user *newname, int flags) +int do_linkat(int olddfd, struct filename *old, int newdfd, + struct filename *new, int flags) { + struct user_namespace *mnt_userns; struct dentry *new_dentry; struct path old_path, new_path; struct inode *delegated_inode = NULL; int how = 0; int error; - if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) - return -EINVAL; + if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) { + error = -EINVAL; + goto out_putnames; + } /* * To use null names we require CAP_DAC_READ_SEARCH * This ensures that not everyone will be able to create * handlink using the passed filedescriptor. */ - if (flags & AT_EMPTY_PATH) { - if (!capable(CAP_DAC_READ_SEARCH)) - return -ENOENT; - how = LOOKUP_EMPTY; + if (flags & AT_EMPTY_PATH && !capable(CAP_DAC_READ_SEARCH)) { + error = -ENOENT; + goto out_putnames; } if (flags & AT_SYMLINK_FOLLOW) how |= LOOKUP_FOLLOW; retry: - error = user_path_at(olddfd, oldname, how, &old_path); + error = filename_lookup(olddfd, old, how, &old_path, NULL); if (error) - return error; + goto out_putnames; - new_dentry = user_path_create(newdfd, newname, &new_path, + new_dentry = filename_create(newdfd, new, &new_path, (how & LOOKUP_REVAL)); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) - goto out; + goto out_putpath; error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; - error = may_linkat(&old_path); + mnt_userns = mnt_user_ns(new_path.mnt); + error = may_linkat(mnt_userns, &old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; - error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode); + error = vfs_link(old_path.dentry, mnt_userns, new_path.dentry->d_inode, + new_dentry, &delegated_inode); out_dput: done_path_create(&new_path, new_dentry); if (delegated_inode) { @@ -4395,8 +4612,11 @@ out_dput: how |= LOOKUP_REVAL; goto retry; } -out: +out_putpath: path_put(&old_path); +out_putnames: + putname(old); + putname(new); return error; } @@ -4404,22 +4624,18 @@ out: SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags) { - return do_linkat(olddfd, oldname, newdfd, newname, flags); + return do_linkat(olddfd, getname_uflags(oldname, flags), + newdfd, getname(newname), flags); } SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname) { - return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); + return do_linkat(AT_FDCWD, getname(oldname), AT_FDCWD, getname(newname), 0); } /** * vfs_rename - rename a filesystem object - * @old_dir: parent of source - * @old_dentry: source - * @new_dir: parent of destination - * @new_dentry: destination - * @delegated_inode: returns an inode needing a delegation break - * @flags: rename flags + * @rd: pointer to &struct renamedata info * * The caller must hold multiple mutexes--see lock_rename()). * @@ -4462,11 +4678,14 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ -int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - struct inode **delegated_inode, unsigned int flags) +int vfs_rename(struct renamedata *rd) { int error; + struct inode *old_dir = rd->old_dir, *new_dir = rd->new_dir; + struct dentry *old_dentry = rd->old_dentry; + struct dentry *new_dentry = rd->new_dentry; + struct inode **delegated_inode = rd->delegated_inode; + unsigned int flags = rd->flags; bool is_dir = d_is_dir(old_dentry); struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; @@ -4477,19 +4696,21 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (source == target) return 0; - error = may_delete(old_dir, old_dentry, is_dir); + error = may_delete(rd->old_mnt_userns, old_dir, old_dentry, is_dir); if (error) return error; if (!target) { - error = may_create(new_dir, new_dentry); + error = may_create(rd->new_mnt_userns, new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) - error = may_delete(new_dir, new_dentry, is_dir); + error = may_delete(rd->new_mnt_userns, new_dir, + new_dentry, is_dir); else - error = may_delete(new_dir, new_dentry, new_is_dir); + error = may_delete(rd->new_mnt_userns, new_dir, + new_dentry, new_is_dir); } if (error) return error; @@ -4503,12 +4724,14 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, */ if (new_dir != old_dir) { if (is_dir) { - error = inode_permission(source, MAY_WRITE); + error = inode_permission(rd->old_mnt_userns, source, + MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { - error = inode_permission(target, MAY_WRITE); + error = inode_permission(rd->new_mnt_userns, target, + MAY_WRITE); if (error) return error; } @@ -4526,6 +4749,10 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, else if (target) inode_lock(target); + error = -EPERM; + if (IS_SWAPFILE(source) || (target && IS_SWAPFILE(target))) + goto out; + error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) goto out; @@ -4548,8 +4775,8 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (error) goto out; } - error = old_dir->i_op->rename(old_dir, old_dentry, - new_dir, new_dentry, flags); + error = old_dir->i_op->rename(rd->new_mnt_userns, old_dir, old_dentry, + new_dir, new_dentry, flags); if (error) goto out; @@ -4587,48 +4814,40 @@ out: } EXPORT_SYMBOL(vfs_rename); -static int do_renameat2(int olddfd, const char __user *oldname, int newdfd, - const char __user *newname, unsigned int flags) +int do_renameat2(int olddfd, struct filename *from, int newdfd, + struct filename *to, unsigned int flags) { + struct renamedata rd; struct dentry *old_dentry, *new_dentry; struct dentry *trap; struct path old_path, new_path; struct qstr old_last, new_last; int old_type, new_type; struct inode *delegated_inode = NULL; - struct filename *from; - struct filename *to; unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET; bool should_retry = false; - int error; + int error = -EINVAL; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) - return -EINVAL; + goto put_names; if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && (flags & RENAME_EXCHANGE)) - return -EINVAL; - - if ((flags & RENAME_WHITEOUT) && !capable(CAP_MKNOD)) - return -EPERM; + goto put_names; if (flags & RENAME_EXCHANGE) target_flags = 0; retry: - from = filename_parentat(olddfd, getname(oldname), lookup_flags, - &old_path, &old_last, &old_type); - if (IS_ERR(from)) { - error = PTR_ERR(from); - goto exit; - } + error = filename_parentat(olddfd, from, lookup_flags, &old_path, + &old_last, &old_type); + if (error) + goto put_names; - to = filename_parentat(newdfd, getname(newname), lookup_flags, - &new_path, &new_last, &new_type); - if (IS_ERR(to)) { - error = PTR_ERR(to); + error = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last, + &new_type); + if (error) goto exit1; - } error = -EXDEV; if (old_path.mnt != new_path.mnt) @@ -4698,9 +4917,16 @@ retry_deleg: &new_path, new_dentry, flags); if (error) goto exit5; - error = vfs_rename(old_path.dentry->d_inode, old_dentry, - new_path.dentry->d_inode, new_dentry, - &delegated_inode, flags); + + rd.old_dir = old_path.dentry->d_inode; + rd.old_dentry = old_dentry; + rd.old_mnt_userns = mnt_user_ns(old_path.mnt); + rd.new_dir = new_path.dentry->d_inode; + rd.new_dentry = new_dentry; + rd.new_mnt_userns = mnt_user_ns(new_path.mnt); + rd.delegated_inode = &delegated_inode; + rd.flags = flags; + error = vfs_rename(&rd); exit5: dput(new_dentry); exit4: @@ -4717,49 +4943,38 @@ exit2: if (retry_estale(error, lookup_flags)) should_retry = true; path_put(&new_path); - putname(to); exit1: path_put(&old_path); - putname(from); if (should_retry) { should_retry = false; lookup_flags |= LOOKUP_REVAL; goto retry; } -exit: +put_names: + putname(from); + putname(to); return error; } SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags) { - return do_renameat2(olddfd, oldname, newdfd, newname, flags); + return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), + flags); } SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname) { - return do_renameat2(olddfd, oldname, newdfd, newname, 0); + return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), + 0); } SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { - return do_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0); -} - -int vfs_whiteout(struct inode *dir, struct dentry *dentry) -{ - int error = may_create(dir, dentry); - if (error) - return error; - - if (!dir->i_op->mknod) - return -EPERM; - - return dir->i_op->mknod(dir, dentry, - S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); + return do_renameat2(AT_FDCWD, getname(oldname), AT_FDCWD, + getname(newname), 0); } -EXPORT_SYMBOL(vfs_whiteout); int readlink_copy(char __user *buffer, int buflen, const char *link) { @@ -4889,28 +5104,28 @@ int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) } EXPORT_SYMBOL(page_readlink); -/* - * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS - */ -int __page_symlink(struct inode *inode, const char *symname, int len, int nofs) +int page_symlink(struct inode *inode, const char *symname, int len) { struct address_space *mapping = inode->i_mapping; + const struct address_space_operations *aops = mapping->a_ops; + bool nofs = !mapping_gfp_constraint(mapping, __GFP_FS); struct page *page; - void *fsdata; + void *fsdata = NULL; int err; - unsigned int flags = 0; - if (nofs) - flags |= AOP_FLAG_NOFS; + unsigned int flags; retry: - err = pagecache_write_begin(NULL, mapping, 0, len-1, - flags, &page, &fsdata); + if (nofs) + flags = memalloc_nofs_save(); + err = aops->write_begin(NULL, mapping, 0, len-1, &page, &fsdata); + if (nofs) + memalloc_nofs_restore(flags); if (err) goto fail; memcpy(page_address(page), symname, len-1); - err = pagecache_write_end(NULL, mapping, 0, len-1, len-1, + err = aops->write_end(NULL, mapping, 0, len-1, len-1, page, fsdata); if (err < 0) goto fail; @@ -4922,13 +5137,6 @@ retry: fail: return err; } -EXPORT_SYMBOL(__page_symlink); - -int page_symlink(struct inode *inode, const char *symname, int len) -{ - return __page_symlink(inode, symname, len, - !mapping_gfp_constraint(inode->i_mapping, __GFP_FS)); -} EXPORT_SYMBOL(page_symlink); const struct inode_operations page_symlink_inode_operations = { |