// SPDX-License-Identifier: GPL-2.0-only/* * linux/fs/open.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/string.h>#include <linux/mm.h>#include <linux/file.h>#include <linux/fdtable.h>#include <linux/fsnotify.h>#include <linux/module.h>#include <linux/tty.h>#include <linux/namei.h>#include <linux/backing-dev.h>#include <linux/capability.h>#include <linux/securebits.h>#include <linux/security.h>#include <linux/mount.h>#include <linux/fcntl.h>#include <linux/slab.h>#include <linux/uaccess.h>#include <linux/fs.h>#include <linux/personality.h>#include <linux/pagemap.h>#include <linux/syscalls.h>#include <linux/rcupdate.h>#include <linux/audit.h>#include <linux/falloc.h>#include <linux/fs_struct.h>#include <linux/dnotify.h>#include <linux/compat.h>#include <linux/mnt_idmapping.h>#include <linux/filelock.h> #include "internal.h" int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry, loff_t length, unsigned int time_attrs, struct file *filp){ int ret; struct iattr newattrs; /* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */ if (length < 0) return -EINVAL; newattrs.ia_size = length; newattrs.ia_valid = ATTR_SIZE | time_attrs; if (filp) { newattrs.ia_file = filp; newattrs.ia_valid |= ATTR_FILE; } /* Remove suid, sgid, and file capabilities on truncate too */ ret = dentry_needs_remove_privs(idmap, dentry); if (ret < 0) return ret; if (ret) newattrs.ia_valid |= ret | ATTR_FORCE; ret = inode_lock_killable(dentry->d_inode); if (ret) return ret; /* Note any delegations or leases have already been broken: */ ret = notify_change(idmap, dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret;} int vfs_truncate(const struct path *path, loff_t length){ struct mnt_idmap *idmap; struct inode *inode; int error; inode = path->dentry->d_inode; /* For directories it's -EISDIR, for other non-regulars - -EINVAL */ if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode)) return -EINVAL; idmap = mnt_idmap(path->mnt); error = inode_permission(idmap, inode, MAY_WRITE); if (error) return error; error = fsnotify_truncate_perm(path, length); if (error) return error; error = mnt_want_write(path->mnt); if (error) return error; error = -EPERM; if (IS_APPEND(inode)) goto mnt_drop_write_and_out; error = get_write_access(inode); if (error) goto mnt_drop_write_and_out; /* * Make sure that there are no leases. get_write_access() protects * against the truncate racing with a lease-granting setlease(). */ error = break_lease(inode, O_WRONLY); if (error) goto put_write_and_out; error = security_path_truncate(path); if (!error) error = do_truncate(idmap, path->dentry, length, 0, NULL); put_write_and_out: put_write_access(inode);mnt_drop_write_and_out: mnt_drop_write(path->mnt); return error;}EXPORT_SYMBOL_GPL(vfs_truncate); int ksys_truncate(const char __user *pathname, loff_t length){ unsigned int lookup_flags = LOOKUP_FOLLOW; struct path path; int error; if (length < 0) /* sorry, but loff_t says... */ return -EINVAL; CLASS(filename, name)(pathname);retry: error = filename_lookup(AT_FDCWD, name, lookup_flags, &path, NULL); if (!error) { error = vfs_truncate(&path, length); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error;} SYSCALL_DEFINE2(truncate, const char __user *, path, long, length){ return ksys_truncate(path, length);} #ifdef CONFIG_COMPATCOMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length){ return ksys_truncate(path, length);}#endif int do_ftruncate(struct file *file, loff_t length, unsigned int flags){ struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; int error; if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE)) return -EINVAL; /* * Cannot ftruncate over 2^31 bytes without large file support, either * through opening with O_LARGEFILE or by using ftruncate64(). */ if (length > MAX_NON_LFS && !(file->f_flags & O_LARGEFILE) && !(flags & FTRUNCATE_LFS)) return -EINVAL; /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(file))) return -EPERM; error = security_file_truncate(file); if (error) return error; error = fsnotify_truncate_perm(&file->f_path, length); if (error) return error; scoped_guard(super_write, inode->i_sb) return do_truncate(file_mnt_idmap(file), dentry, length, ATTR_MTIME | ATTR_CTIME, file);} int ksys_ftruncate(unsigned int fd, loff_t length, unsigned int flags){ if (length < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return do_ftruncate(fd_file(f), length, flags);} SYSCALL_DEFINE2(ftruncate, unsigned int, fd, off_t, length){ return ksys_ftruncate(fd, length, 0);} #ifdef CONFIG_COMPATCOMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_off_t, length){ return ksys_ftruncate(fd, length, 0);}#endif /* LFS versions of truncate are only needed on 32 bit machines */#if BITS_PER_LONG == 32SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length){ return ksys_truncate(path, length);} SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length){ return ksys_ftruncate(fd, length, FTRUNCATE_LFS);}#endif /* BITS_PER_LONG == 32 */ #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_TRUNCATE64)COMPAT_SYSCALL_DEFINE3(truncate64, const char __user *, pathname, compat_arg_u64_dual(length)){ return ksys_truncate(pathname, compat_arg_u64_glue(length));}#endif #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FTRUNCATE64)COMPAT_SYSCALL_DEFINE3(ftruncate64, unsigned int, fd, compat_arg_u64_dual(length)){ return ksys_ftruncate(fd, compat_arg_u64_glue(length), FTRUNCATE_LFS);}#endif int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len){ struct inode *inode = file_inode(file); int ret; loff_t sum; if (offset < 0 || len <= 0) return -EINVAL; if (mode & ~(FALLOC_FL_MODE_MASK | FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; /* * Modes are exclusive, even if that is not obvious from the encoding * as bit masks and the mix with the flag in the same namespace. * * To make things even more complicated, FALLOC_FL_ALLOCATE_RANGE is * encoded as no bit set. */ switch (mode & FALLOC_FL_MODE_MASK) { case FALLOC_FL_ALLOCATE_RANGE: case FALLOC_FL_UNSHARE_RANGE: case FALLOC_FL_ZERO_RANGE: break; case FALLOC_FL_PUNCH_HOLE: if (!(mode & FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; break; case FALLOC_FL_COLLAPSE_RANGE: case FALLOC_FL_INSERT_RANGE: case FALLOC_FL_WRITE_ZEROES: if (mode & FALLOC_FL_KEEP_SIZE) return -EOPNOTSUPP; break; default: return -EOPNOTSUPP; } if (!(file->f_mode & FMODE_WRITE)) return -EBADF; /* * On append-only files only space preallocation is supported. */ if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode)) return -EPERM; if (IS_IMMUTABLE(inode)) return -EPERM; /* * We cannot allow any fallocate operation on an active swapfile */ if (IS_SWAPFILE(inode)) return -ETXTBSY; /* * Revalidate the write permissions, in case security policy has * changed since the files were opened. */ ret = security_file_permission(file, MAY_WRITE); if (ret) return ret; ret = fsnotify_file_area_perm(file, MAY_WRITE, &offset, len); if (ret) return ret; if (S_ISFIFO(inode->i_mode)) return -ESPIPE; if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -ENODEV; /* Check for wraparound */ if (check_add_overflow(offset, len, &sum)) return -EFBIG; if (sum > inode->i_sb->s_maxbytes) return -EFBIG; if (!file->f_op->fallocate) return -EOPNOTSUPP; file_start_write(file); ret = file->f_op->fallocate(file, mode, offset, len); /* * Create inotify and fanotify events. * * To keep the logic simple always create events if fallocate succeeds. * This implies that events are even created if the file size remains * unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE. */ if (ret == 0) fsnotify_modify(file); file_end_write(file); return ret;}EXPORT_SYMBOL_GPL(vfs_fallocate); int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len){ CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_fallocate(fd_file(f), mode, offset, len);} SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len){ return ksys_fallocate(fd, mode, offset, len);} #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FALLOCATE)COMPAT_SYSCALL_DEFINE6(fallocate, int, fd, int, mode, compat_arg_u64_dual(offset), compat_arg_u64_dual(len)){ return ksys_fallocate(fd, mode, compat_arg_u64_glue(offset), compat_arg_u64_glue(len));}#endif /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and * switching the fsuid/fsgid around to the real ones. * * Creating new credentials is expensive, so we try to skip doing it, * which we can if the result would match what we already got. */static bool access_need_override_creds(int flags){ const struct cred *cred; if (flags & AT_EACCESS) return false; cred = current_cred(); if (!uid_eq(cred->fsuid, cred->uid) || !gid_eq(cred->fsgid, cred->gid)) return true; if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(cred->user_ns, 0); if (!uid_eq(cred->uid, root_uid)) { if (!cap_isclear(cred->cap_effective)) return true; } else { if (!cap_isidentical(cred->cap_effective, cred->cap_permitted)) return true; } } return false;} static const struct cred *access_override_creds(void){ struct cred *override_cred; override_cred = prepare_creds(); if (!override_cred) return NULL; /* * XXX access_need_override_creds performs checks in hopes of skipping * this work. Make sure it stays in sync if making any changes in this * routine. */ override_cred->fsuid = override_cred->uid; override_cred->fsgid = override_cred->gid; if (!issecure(SECURE_NO_SETUID_FIXUP)) { /* Clear the capabilities if we switch to a non-root user */ kuid_t root_uid = make_kuid(override_cred->user_ns, 0); if (!uid_eq(override_cred->uid, root_uid)) cap_clear(override_cred->cap_effective); else override_cred->cap_effective = override_cred->cap_permitted; } /* * The new set of credentials can *only* be used in * task-synchronous circumstances, and does not need * RCU freeing, unless somebody then takes a separate * reference to it. * * NOTE! This is _only_ true because this credential * is used purely for override_creds() that installs * it as the subjective cred. Other threads will be * accessing ->real_cred, not the subjective cred. * * If somebody _does_ make a copy of this (using the * 'get_current_cred()' function), that will clear the * non_rcu field, because now that other user may be * expecting RCU freeing. But normal thread-synchronous * cred accesses will keep things non-racy to avoid RCU * freeing. */ override_cred->non_rcu = 1; return override_creds(override_cred);} static int do_faccessat(int dfd, const char __user *filename, int mode, int flags){ struct path path; struct inode *inode; int res; unsigned int lookup_flags = LOOKUP_FOLLOW; const struct cred *old_cred = NULL; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) return -EINVAL; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (access_need_override_creds(flags)) { old_cred = access_override_creds(); if (!old_cred) return -ENOMEM; } CLASS(filename_uflags, name)(filename, flags);retry: res = filename_lookup(dfd, name, lookup_flags, &path, NULL); if (res) goto out; inode = d_backing_inode(path.dentry); if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { /* * MAY_EXEC on regular files is denied if the fs is mounted * with the "noexec" flag. */ res = -EACCES; if (path_noexec(&path))Lines 1–500 of 1634. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/open.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fsnotify.h> #include <linux/module.h> #include <linux/tty.h> #include <linux/namei.h> #include <linux/backing-dev.h> #include <linux/capability.h> #include <linux/securebits.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/rcupdate.h> #include <linux/audit.h> #include <linux/falloc.h> #include <linux/fs_struct.h> #include <linux/dnotify.h> #include <linux/compat.h> #include <linux/mnt_idmapping.h> #include <linux/filelock.h> #include "internal.h" int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry, loff_t length, unsigned int time_attrs, struct file *filp) { int ret; struct iattr newattrs; /* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */ if (length < 0) return -EINVAL; newattrs.ia_size = length; newattrs.ia_valid = ATTR_SIZE | time_attrs; if (filp) { newattrs.ia_file = filp; newattrs.ia_valid |= ATTR_FILE; } /* Remove suid, sgid, and file capabilities on truncate too */ ret = dentry_needs_remove_privs(idmap, dentry); if (ret < 0) return ret; if (ret) newattrs.ia_valid |= ret | ATTR_FORCE; ret = inode_lock_killable(dentry->d_inode); if (ret) return ret; /* Note any delegations or leases have already been broken: */ ret = notify_change(idmap, dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret; } int vfs_truncate(const struct path *path, loff_t length) { struct mnt_idmap *idmap; struct inode *inode; int error; inode = path->dentry->d_inode; /* For directories it's -EISDIR, for other non-regulars - -EINVAL */ if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode)) return -EINVAL; idmap = mnt_idmap(path->mnt); error = inode_permission(idmap, inode, MAY_WRITE); if (error) return error; error = fsnotify_truncate_perm(path, length); if (error) return error; error = mnt_want_write(path->mnt); if (error) return error; error = -EPERM; if (IS_APPEND(inode)) goto mnt_drop_write_and_out; error = get_write_access(inode); if (error) goto mnt_drop_write_and_out; /* * Make sure that there are no leases. get_write_access() protects * against the truncate racing with a lease-granting setlease(). */ error = break_lease(inode, O_WRONLY); if (error) goto put_write_and_out; error = security_path_truncate(path); if (!error) error = do_truncate(idmap, path->dentry, length, 0, NULL); put_write_and_out: put_write_access(inode); mnt_drop_write_and_out: mnt_drop_write(path->mnt); return error; } EXPORT_SYMBOL_GPL(vfs_truncate); int ksys_truncate(const char __user *pathname, loff_t length) { unsigned int lookup_flags = LOOKUP_FOLLOW; struct path path; int error; if (length < 0) /* sorry, but loff_t says... */ return -EINVAL; CLASS(filename, name)(pathname); retry: error = filename_lookup(AT_FDCWD, name, lookup_flags, &path, NULL); if (!error) { error = vfs_truncate(&path, length); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE2(truncate, const char __user *, path, long, length) { return ksys_truncate(path, length); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length) { return ksys_truncate(path, length); } #endif int do_ftruncate(struct file *file, loff_t length, unsigned int flags) { struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; int error; if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE)) return -EINVAL; /* * Cannot ftruncate over 2^31 bytes without large file support, either * through opening with O_LARGEFILE or by using ftruncate64(). */ if (length > MAX_NON_LFS && !(file->f_flags & O_LARGEFILE) && !(flags & FTRUNCATE_LFS)) return -EINVAL; /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(file))) return -EPERM; error = security_file_truncate(file); if (error) return error; error = fsnotify_truncate_perm(&file->f_path, length); if (error) return error; scoped_guard(super_write, inode->i_sb) return do_truncate(file_mnt_idmap(file), dentry, length, ATTR_MTIME | ATTR_CTIME, file); } int ksys_ftruncate(unsigned int fd, loff_t length, unsigned int flags) { if (length < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return do_ftruncate(fd_file(f), length, flags); } SYSCALL_DEFINE2(ftruncate, unsigned int, fd, off_t, length) { return ksys_ftruncate(fd, length, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_off_t, length) { return ksys_ftruncate(fd, length, 0); } #endif /* LFS versions of truncate are only needed on 32 bit machines */ #if BITS_PER_LONG == 32 SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length) { return ksys_truncate(path, length); } SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length) { return ksys_ftruncate(fd, length, FTRUNCATE_LFS); } #endif /* BITS_PER_LONG == 32 */ #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_TRUNCATE64) COMPAT_SYSCALL_DEFINE3(truncate64, const char __user *, pathname, compat_arg_u64_dual(length)) { return ksys_truncate(pathname, compat_arg_u64_glue(length)); } #endif #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FTRUNCATE64) COMPAT_SYSCALL_DEFINE3(ftruncate64, unsigned int, fd, compat_arg_u64_dual(length)) { return ksys_ftruncate(fd, compat_arg_u64_glue(length), FTRUNCATE_LFS); } #endif int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); int ret; loff_t sum; if (offset < 0 || len <= 0) return -EINVAL; if (mode & ~(FALLOC_FL_MODE_MASK | FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; /* * Modes are exclusive, even if that is not obvious from the encoding * as bit masks and the mix with the flag in the same namespace. * * To make things even more complicated, FALLOC_FL_ALLOCATE_RANGE is * encoded as no bit set. */ switch (mode & FALLOC_FL_MODE_MASK) { case FALLOC_FL_ALLOCATE_RANGE: case FALLOC_FL_UNSHARE_RANGE: case FALLOC_FL_ZERO_RANGE: break; case FALLOC_FL_PUNCH_HOLE: if (!(mode & FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; break; case FALLOC_FL_COLLAPSE_RANGE: case FALLOC_FL_INSERT_RANGE: case FALLOC_FL_WRITE_ZEROES: if (mode & FALLOC_FL_KEEP_SIZE) return -EOPNOTSUPP; break; default: return -EOPNOTSUPP; } if (!(file->f_mode & FMODE_WRITE)) return -EBADF; /* * On append-only files only space preallocation is supported. */ if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode)) return -EPERM; if (IS_IMMUTABLE(inode)) return -EPERM; /* * We cannot allow any fallocate operation on an active swapfile */ if (IS_SWAPFILE(inode)) return -ETXTBSY; /* * Revalidate the write permissions, in case security policy has * changed since the files were opened. */ ret = security_file_permission(file, MAY_WRITE); if (ret) return ret; ret = fsnotify_file_area_perm(file, MAY_WRITE, &offset, len); if (ret) return ret; if (S_ISFIFO(inode->i_mode)) return -ESPIPE; if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -ENODEV; /* Check for wraparound */ if (check_add_overflow(offset, len, &sum)) return -EFBIG; if (sum > inode->i_sb->s_maxbytes) return -EFBIG; if (!file->f_op->fallocate) return -EOPNOTSUPP; file_start_write(file); ret = file->f_op->fallocate(file, mode, offset, len); /* * Create inotify and fanotify events. * * To keep the logic simple always create events if fallocate succeeds. * This implies that events are even created if the file size remains * unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE. */ if (ret == 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL_GPL(vfs_fallocate); int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_fallocate(fd_file(f), mode, offset, len); } SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) { return ksys_fallocate(fd, mode, offset, len); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FALLOCATE) COMPAT_SYSCALL_DEFINE6(fallocate, int, fd, int, mode, compat_arg_u64_dual(offset), compat_arg_u64_dual(len)) { return ksys_fallocate(fd, mode, compat_arg_u64_glue(offset), compat_arg_u64_glue(len)); } #endif /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and * switching the fsuid/fsgid around to the real ones. * * Creating new credentials is expensive, so we try to skip doing it, * which we can if the result would match what we already got. */ static bool access_need_override_creds(int flags) { const struct cred *cred; if (flags & AT_EACCESS) return false; cred = current_cred(); if (!uid_eq(cred->fsuid, cred->uid) || !gid_eq(cred->fsgid, cred->gid)) return true; if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(cred->user_ns, 0); if (!uid_eq(cred->uid, root_uid)) { if (!cap_isclear(cred->cap_effective)) return true; } else { if (!cap_isidentical(cred->cap_effective, cred->cap_permitted)) return true; } } return false; } static const struct cred *access_override_creds(void) { struct cred *override_cred; override_cred = prepare_creds(); if (!override_cred) return NULL; /* * XXX access_need_override_creds performs checks in hopes of skipping * this work. Make sure it stays in sync if making any changes in this * routine. */ override_cred->fsuid = override_cred->uid; override_cred->fsgid = override_cred->gid; if (!issecure(SECURE_NO_SETUID_FIXUP)) { /* Clear the capabilities if we switch to a non-root user */ kuid_t root_uid = make_kuid(override_cred->user_ns, 0); if (!uid_eq(override_cred->uid, root_uid)) cap_clear(override_cred->cap_effective); else override_cred->cap_effective = override_cred->cap_permitted; } /* * The new set of credentials can *only* be used in * task-synchronous circumstances, and does not need * RCU freeing, unless somebody then takes a separate * reference to it. * * NOTE! This is _only_ true because this credential * is used purely for override_creds() that installs * it as the subjective cred. Other threads will be * accessing ->real_cred, not the subjective cred. * * If somebody _does_ make a copy of this (using the * 'get_current_cred()' function), that will clear the * non_rcu field, because now that other user may be * expecting RCU freeing. But normal thread-synchronous * cred accesses will keep things non-racy to avoid RCU * freeing. */ override_cred->non_rcu = 1; return override_creds(override_cred); } static int do_faccessat(int dfd, const char __user *filename, int mode, int flags) { struct path path; struct inode *inode; int res; unsigned int lookup_flags = LOOKUP_FOLLOW; const struct cred *old_cred = NULL; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) return -EINVAL; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (access_need_override_creds(flags)) { old_cred = access_override_creds(); if (!old_cred) return -ENOMEM; } CLASS(filename_uflags, name)(filename, flags); retry: res = filename_lookup(dfd, name, lookup_flags, &path, NULL); if (res) goto out; inode = d_backing_inode(path.dentry); if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { /* * MAY_EXEC on regular files is denied if the fs is mounted * with the "noexec" flag. */ res = -EACCES; if (path_noexec(&path))