From 2813893f8b197a14f1e1ddb04d99bce46817c84a Mon Sep 17 00:00:00 2001 From: Iulia Manda Date: Wed, 15 Apr 2015 16:16:41 -0700 Subject: kernel: conditionally support non-root users, groups and capabilities There are a lot of embedded systems that run most or all of their functionality in init, running as root:root. For these systems, supporting multiple users is not necessary. This patch adds a new symbol, CONFIG_MULTIUSER, that makes support for non-root users, non-root groups, and capabilities optional. It is enabled under CONFIG_EXPERT menu. When this symbol is not defined, UID and GID are zero in any possible case and processes always have all capabilities. The following syscalls are compiled out: setuid, setregid, setgid, setreuid, setresuid, getresuid, setresgid, getresgid, setgroups, getgroups, setfsuid, setfsgid, capget, capset. Also, groups.c is compiled out completely. In kernel/capability.c, capable function was moved in order to avoid adding two ifdef blocks. This change saves about 25 KB on a defconfig build. The most minimal kernels have total text sizes in the high hundreds of kB rather than low MB. (The 25k goes down a bit with allnoconfig, but not that much. The kernel was booted in Qemu. All the common functionalities work. Adding users/groups is not possible, failing with -ENOSYS. Bloat-o-meter output: add/remove: 7/87 grow/shrink: 19/397 up/down: 1675/-26325 (-24650) [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Iulia Manda Reviewed-by: Josh Triplett Acked-by: Geert Uytterhoeven Tested-by: Paul E. McKenney Reviewed-by: Paul E. McKenney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index a03d9cd23ed7..3be344902316 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -325,6 +325,7 @@ out_unlock: * SMP: There are not races, the GIDs are checked only by filesystem * operations (as far as semantic preservation is concerned). */ +#ifdef CONFIG_MULTIUSER SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) { struct user_namespace *ns = current_user_ns(); @@ -815,6 +816,7 @@ change_okay: commit_creds(new); return old_fsgid; } +#endif /* CONFIG_MULTIUSER */ /** * sys_getpid - return the thread group id of the current process -- cgit v1.2.3 From 6e399cd144d8500ffb5d40fa6848890e2580a80a Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 16 Apr 2015 12:47:59 -0700 Subject: prctl: avoid using mmap_sem for exe_file serialization Oleg cleverly suggested using xchg() to set the new mm->exe_file instead of calling set_mm_exe_file() which requires some form of serialization -- mmap_sem in this case. For archs that do not have atomic rmw instructions we still fallback to a spinlock alternative, so this should always be safe. As such, we only need the mmap_sem for looking up the backing vm_file, which can be done sharing the lock. Naturally, this means we need to manually deal with both the new and old file reference counting, and we need not worry about the MMF_EXE_FILE_CHANGED bits, which can probably be deleted in the future anyway. Signed-off-by: Davidlohr Bueso Suggested-by: Oleg Nesterov Acked-by: Oleg Nesterov Reviewed-by: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys.c | 47 ++++++++++++++++++++++++++++------------------- 1 file changed, 28 insertions(+), 19 deletions(-) (limited to 'kernel/sys.c') diff --git a/kernel/sys.c b/kernel/sys.c index 3be344902316..a4e372b798a5 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1649,14 +1649,13 @@ SYSCALL_DEFINE1(umask, int, mask) return mask; } -static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd) +static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) { struct fd exe; + struct file *old_exe, *exe_file; struct inode *inode; int err; - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); - exe = fdget(fd); if (!exe.file) return -EBADF; @@ -1680,15 +1679,22 @@ static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd) /* * Forbid mm->exe_file change if old file still mapped. */ + exe_file = get_mm_exe_file(mm); err = -EBUSY; - if (mm->exe_file) { + if (exe_file) { struct vm_area_struct *vma; - for (vma = mm->mmap; vma; vma = vma->vm_next) - if (vma->vm_file && - path_equal(&vma->vm_file->f_path, - &mm->exe_file->f_path)) - goto exit; + down_read(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (!vma->vm_file) + continue; + if (path_equal(&vma->vm_file->f_path, + &exe_file->f_path)) + goto exit_err; + } + + up_read(&mm->mmap_sem); + fput(exe_file); } /* @@ -1702,10 +1708,18 @@ static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd) goto exit; err = 0; - set_mm_exe_file(mm, exe.file); /* this grabs a reference to exe.file */ + /* set the new file, lockless */ + get_file(exe.file); + old_exe = xchg(&mm->exe_file, exe.file); + if (old_exe) + fput(old_exe); exit: fdput(exe); return err; +exit_err: + up_read(&mm->mmap_sem); + fput(exe_file); + goto exit; } #ifdef CONFIG_CHECKPOINT_RESTORE @@ -1840,10 +1854,9 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL; } - down_write(&mm->mmap_sem); if (prctl_map.exe_fd != (u32)-1) - error = prctl_set_mm_exe_file_locked(mm, prctl_map.exe_fd); - downgrade_write(&mm->mmap_sem); + error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd); + down_read(&mm->mmap_sem); if (error) goto out; @@ -1909,12 +1922,8 @@ static int prctl_set_mm(int opt, unsigned long addr, if (!capable(CAP_SYS_RESOURCE)) return -EPERM; - if (opt == PR_SET_MM_EXE_FILE) { - down_write(&mm->mmap_sem); - error = prctl_set_mm_exe_file_locked(mm, (unsigned int)addr); - up_write(&mm->mmap_sem); - return error; - } + if (opt == PR_SET_MM_EXE_FILE) + return prctl_set_mm_exe_file(mm, (unsigned int)addr); if (addr >= TASK_SIZE || addr < mmap_min_addr) return -EINVAL; -- cgit v1.2.3