kernel-ark/arch/x86/ia32/ia32_aout.c
David Howells a6f76f23d2 CRED: Make execve() take advantage of copy-on-write credentials
Make execve() take advantage of copy-on-write credentials, allowing it to set
up the credentials in advance, and then commit the whole lot after the point
of no return.

This patch and the preceding patches have been tested with the LTP SELinux
testsuite.

This patch makes several logical sets of alteration:

 (1) execve().

     The credential bits from struct linux_binprm are, for the most part,
     replaced with a single credentials pointer (bprm->cred).  This means that
     all the creds can be calculated in advance and then applied at the point
     of no return with no possibility of failure.

     I would like to replace bprm->cap_effective with:

	cap_isclear(bprm->cap_effective)

     but this seems impossible due to special behaviour for processes of pid 1
     (they always retain their parent's capability masks where normally they'd
     be changed - see cap_bprm_set_creds()).

     The following sequence of events now happens:

     (a) At the start of do_execve, the current task's cred_exec_mutex is
     	 locked to prevent PTRACE_ATTACH from obsoleting the calculation of
     	 creds that we make.

     (a) prepare_exec_creds() is then called to make a copy of the current
     	 task's credentials and prepare it.  This copy is then assigned to
     	 bprm->cred.

  	 This renders security_bprm_alloc() and security_bprm_free()
     	 unnecessary, and so they've been removed.

     (b) The determination of unsafe execution is now performed immediately
     	 after (a) rather than later on in the code.  The result is stored in
     	 bprm->unsafe for future reference.

     (c) prepare_binprm() is called, possibly multiple times.

     	 (i) This applies the result of set[ug]id binaries to the new creds
     	     attached to bprm->cred.  Personality bit clearance is recorded,
     	     but now deferred on the basis that the exec procedure may yet
     	     fail.

         (ii) This then calls the new security_bprm_set_creds().  This should
	     calculate the new LSM and capability credentials into *bprm->cred.

	     This folds together security_bprm_set() and parts of
	     security_bprm_apply_creds() (these two have been removed).
	     Anything that might fail must be done at this point.

         (iii) bprm->cred_prepared is set to 1.

	     bprm->cred_prepared is 0 on the first pass of the security
	     calculations, and 1 on all subsequent passes.  This allows SELinux
	     in (ii) to base its calculations only on the initial script and
	     not on the interpreter.

     (d) flush_old_exec() is called to commit the task to execution.  This
     	 performs the following steps with regard to credentials:

	 (i) Clear pdeath_signal and set dumpable on certain circumstances that
	     may not be covered by commit_creds().

         (ii) Clear any bits in current->personality that were deferred from
             (c.i).

     (e) install_exec_creds() [compute_creds() as was] is called to install the
     	 new credentials.  This performs the following steps with regard to
     	 credentials:

         (i) Calls security_bprm_committing_creds() to apply any security
             requirements, such as flushing unauthorised files in SELinux, that
             must be done before the credentials are changed.

	     This is made up of bits of security_bprm_apply_creds() and
	     security_bprm_post_apply_creds(), both of which have been removed.
	     This function is not allowed to fail; anything that might fail
	     must have been done in (c.ii).

         (ii) Calls commit_creds() to apply the new credentials in a single
             assignment (more or less).  Possibly pdeath_signal and dumpable
             should be part of struct creds.

	 (iii) Unlocks the task's cred_replace_mutex, thus allowing
	     PTRACE_ATTACH to take place.

         (iv) Clears The bprm->cred pointer as the credentials it was holding
             are now immutable.

         (v) Calls security_bprm_committed_creds() to apply any security
             alterations that must be done after the creds have been changed.
             SELinux uses this to flush signals and signal handlers.

     (f) If an error occurs before (d.i), bprm_free() will call abort_creds()
     	 to destroy the proposed new credentials and will then unlock
     	 cred_replace_mutex.  No changes to the credentials will have been
     	 made.

 (2) LSM interface.

     A number of functions have been changed, added or removed:

     (*) security_bprm_alloc(), ->bprm_alloc_security()
     (*) security_bprm_free(), ->bprm_free_security()

     	 Removed in favour of preparing new credentials and modifying those.

     (*) security_bprm_apply_creds(), ->bprm_apply_creds()
     (*) security_bprm_post_apply_creds(), ->bprm_post_apply_creds()

     	 Removed; split between security_bprm_set_creds(),
     	 security_bprm_committing_creds() and security_bprm_committed_creds().

     (*) security_bprm_set(), ->bprm_set_security()

     	 Removed; folded into security_bprm_set_creds().

     (*) security_bprm_set_creds(), ->bprm_set_creds()

     	 New.  The new credentials in bprm->creds should be checked and set up
     	 as appropriate.  bprm->cred_prepared is 0 on the first call, 1 on the
     	 second and subsequent calls.

     (*) security_bprm_committing_creds(), ->bprm_committing_creds()
     (*) security_bprm_committed_creds(), ->bprm_committed_creds()

     	 New.  Apply the security effects of the new credentials.  This
     	 includes closing unauthorised files in SELinux.  This function may not
     	 fail.  When the former is called, the creds haven't yet been applied
     	 to the process; when the latter is called, they have.

 	 The former may access bprm->cred, the latter may not.

 (3) SELinux.

     SELinux has a number of changes, in addition to those to support the LSM
     interface changes mentioned above:

     (a) The bprm_security_struct struct has been removed in favour of using
     	 the credentials-under-construction approach.

     (c) flush_unauthorized_files() now takes a cred pointer and passes it on
     	 to inode_has_perm(), file_has_perm() and dentry_open().

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 10:39:24 +11:00

545 lines
14 KiB
C

/*
* a.out loader for x86-64
*
* Copyright (C) 1991, 1992, 1996 Linus Torvalds
* Hacked together by Andi Kleen
*/
#include <linux/module.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/a.out.h>
#include <linux/errno.h>
#include <linux/signal.h>
#include <linux/string.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/ptrace.h>
#include <linux/user.h>
#include <linux/slab.h>
#include <linux/binfmts.h>
#include <linux/personality.h>
#include <linux/init.h>
#include <linux/jiffies.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/cacheflush.h>
#include <asm/user32.h>
#include <asm/ia32.h>
#undef WARN_OLD
#undef CORE_DUMP /* probably broken */
static int load_aout_binary(struct linux_binprm *, struct pt_regs *regs);
static int load_aout_library(struct file *);
#ifdef CORE_DUMP
static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
unsigned long limit);
/*
* fill in the user structure for a core dump..
*/
static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
{
u32 fs, gs;
/* changed the size calculations - should hopefully work better. lbt */
dump->magic = CMAGIC;
dump->start_code = 0;
dump->start_stack = regs->sp & ~(PAGE_SIZE - 1);
dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
dump->u_dsize = ((unsigned long)
(current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
dump->u_dsize -= dump->u_tsize;
dump->u_ssize = 0;
dump->u_debugreg[0] = current->thread.debugreg0;
dump->u_debugreg[1] = current->thread.debugreg1;
dump->u_debugreg[2] = current->thread.debugreg2;
dump->u_debugreg[3] = current->thread.debugreg3;
dump->u_debugreg[4] = 0;
dump->u_debugreg[5] = 0;
dump->u_debugreg[6] = current->thread.debugreg6;
dump->u_debugreg[7] = current->thread.debugreg7;
if (dump->start_stack < 0xc0000000) {
unsigned long tmp;
tmp = (unsigned long) (0xc0000000 - dump->start_stack);
dump->u_ssize = tmp >> PAGE_SHIFT;
}
dump->regs.bx = regs->bx;
dump->regs.cx = regs->cx;
dump->regs.dx = regs->dx;
dump->regs.si = regs->si;
dump->regs.di = regs->di;
dump->regs.bp = regs->bp;
dump->regs.ax = regs->ax;
dump->regs.ds = current->thread.ds;
dump->regs.es = current->thread.es;
savesegment(fs, fs);
dump->regs.fs = fs;
savesegment(gs, gs);
dump->regs.gs = gs;
dump->regs.orig_ax = regs->orig_ax;
dump->regs.ip = regs->ip;
dump->regs.cs = regs->cs;
dump->regs.flags = regs->flags;
dump->regs.sp = regs->sp;
dump->regs.ss = regs->ss;
#if 1 /* FIXME */
dump->u_fpvalid = 0;
#else
dump->u_fpvalid = dump_fpu(regs, &dump->i387);
#endif
}
#endif
static struct linux_binfmt aout_format = {
.module = THIS_MODULE,
.load_binary = load_aout_binary,
.load_shlib = load_aout_library,
#ifdef CORE_DUMP
.core_dump = aout_core_dump,
#endif
.min_coredump = PAGE_SIZE
};
static void set_brk(unsigned long start, unsigned long end)
{
start = PAGE_ALIGN(start);
end = PAGE_ALIGN(end);
if (end <= start)
return;
down_write(&current->mm->mmap_sem);
do_brk(start, end - start);
up_write(&current->mm->mmap_sem);
}
#ifdef CORE_DUMP
/*
* These are the only things you should do on a core-file: use only these
* macros to write out all the necessary info.
*/
static int dump_write(struct file *file, const void *addr, int nr)
{
return file->f_op->write(file, addr, nr, &file->f_pos) == nr;
}
#define DUMP_WRITE(addr, nr) \
if (!dump_write(file, (void *)(addr), (nr))) \
goto end_coredump;
#define DUMP_SEEK(offset) \
if (file->f_op->llseek) { \
if (file->f_op->llseek(file, (offset), 0) != (offset)) \
goto end_coredump; \
} else \
file->f_pos = (offset)
#define START_DATA() (u.u_tsize << PAGE_SHIFT)
#define START_STACK(u) (u.start_stack)
/*
* Routine writes a core dump image in the current directory.
* Currently only a stub-function.
*
* Note that setuid/setgid files won't make a core-dump if the uid/gid
* changed due to the set[u|g]id. It's enforced by the "current->mm->dumpable"
* field, which also makes sure the core-dumps won't be recursive if the
* dumping of the process results in another error..
*/
static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
unsigned long limit)
{
mm_segment_t fs;
int has_dumped = 0;
unsigned long dump_start, dump_size;
struct user32 dump;
fs = get_fs();
set_fs(KERNEL_DS);
has_dumped = 1;
current->flags |= PF_DUMPCORE;
strncpy(dump.u_comm, current->comm, sizeof(current->comm));
dump.u_ar0 = offsetof(struct user32, regs);
dump.signal = signr;
dump_thread32(regs, &dump);
/*
* If the size of the dump file exceeds the rlimit, then see
* what would happen if we wrote the stack, but not the data
* area.
*/
if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > limit)
dump.u_dsize = 0;
/* Make sure we have enough room to write the stack and data areas. */
if ((dump.u_ssize + 1) * PAGE_SIZE > limit)
dump.u_ssize = 0;
/* make sure we actually have a data and stack area to dump */
set_fs(USER_DS);
if (!access_ok(VERIFY_READ, (void *) (unsigned long)START_DATA(dump),
dump.u_dsize << PAGE_SHIFT))
dump.u_dsize = 0;
if (!access_ok(VERIFY_READ, (void *) (unsigned long)START_STACK(dump),
dump.u_ssize << PAGE_SHIFT))
dump.u_ssize = 0;
set_fs(KERNEL_DS);
/* struct user */
DUMP_WRITE(&dump, sizeof(dump));
/* Now dump all of the user data. Include malloced stuff as well */
DUMP_SEEK(PAGE_SIZE);
/* now we start writing out the user space info */
set_fs(USER_DS);
/* Dump the data area */
if (dump.u_dsize != 0) {
dump_start = START_DATA(dump);
dump_size = dump.u_dsize << PAGE_SHIFT;
DUMP_WRITE(dump_start, dump_size);
}
/* Now prepare to dump the stack area */
if (dump.u_ssize != 0) {
dump_start = START_STACK(dump);
dump_size = dump.u_ssize << PAGE_SHIFT;
DUMP_WRITE(dump_start, dump_size);
}
/*
* Finally dump the task struct. Not be used by gdb, but
* could be useful
*/
set_fs(KERNEL_DS);
DUMP_WRITE(current, sizeof(*current));
end_coredump:
set_fs(fs);
return has_dumped;
}
#endif
/*
* create_aout_tables() parses the env- and arg-strings in new user
* memory and creates the pointer tables from them, and puts their
* addresses on the "stack", returning the new stack pointer value.
*/
static u32 __user *create_aout_tables(char __user *p, struct linux_binprm *bprm)
{
u32 __user *argv, *envp, *sp;
int argc = bprm->argc, envc = bprm->envc;
sp = (u32 __user *) ((-(unsigned long)sizeof(u32)) & (unsigned long) p);
sp -= envc+1;
envp = sp;
sp -= argc+1;
argv = sp;
put_user((unsigned long) envp, --sp);
put_user((unsigned long) argv, --sp);
put_user(argc, --sp);
current->mm->arg_start = (unsigned long) p;
while (argc-- > 0) {
char c;
put_user((u32)(unsigned long)p, argv++);
do {
get_user(c, p++);
} while (c);
}
put_user(0, argv);
current->mm->arg_end = current->mm->env_start = (unsigned long) p;
while (envc-- > 0) {
char c;
put_user((u32)(unsigned long)p, envp++);
do {
get_user(c, p++);
} while (c);
}
put_user(0, envp);
current->mm->env_end = (unsigned long) p;
return sp;
}
/*
* These are the functions used to load a.out style executables and shared
* libraries. There is no binary dependent code anywhere else.
*/
static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
{
unsigned long error, fd_offset, rlim;
struct exec ex;
int retval;
ex = *((struct exec *) bprm->buf); /* exec-header */
if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC &&
N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) ||
N_TRSIZE(ex) || N_DRSIZE(ex) ||
i_size_read(bprm->file->f_path.dentry->d_inode) <
ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
return -ENOEXEC;
}
fd_offset = N_TXTOFF(ex);
/* Check initial limits. This avoids letting people circumvent
* size limits imposed on them by creating programs with large
* arrays in the data or bss.
*/
rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur;
if (rlim >= RLIM_INFINITY)
rlim = ~0;
if (ex.a_data + ex.a_bss > rlim)
return -ENOMEM;
/* Flush all traces of the currently running executable */
retval = flush_old_exec(bprm);
if (retval)
return retval;
regs->cs = __USER32_CS;
regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 =
regs->r13 = regs->r14 = regs->r15 = 0;
/* OK, This is the point of no return */
set_personality(PER_LINUX);
set_thread_flag(TIF_IA32);
clear_thread_flag(TIF_ABI_PENDING);
current->mm->end_code = ex.a_text +
(current->mm->start_code = N_TXTADDR(ex));
current->mm->end_data = ex.a_data +
(current->mm->start_data = N_DATADDR(ex));
current->mm->brk = ex.a_bss +
(current->mm->start_brk = N_BSSADDR(ex));
current->mm->free_area_cache = TASK_UNMAPPED_BASE;
current->mm->cached_hole_size = 0;
current->mm->mmap = NULL;
install_exec_creds(bprm);
current->flags &= ~PF_FORKNOEXEC;
if (N_MAGIC(ex) == OMAGIC) {
unsigned long text_addr, map_size;
loff_t pos;
text_addr = N_TXTADDR(ex);
pos = 32;
map_size = ex.a_text+ex.a_data;
down_write(&current->mm->mmap_sem);
error = do_brk(text_addr & PAGE_MASK, map_size);
up_write(&current->mm->mmap_sem);
if (error != (text_addr & PAGE_MASK)) {
send_sig(SIGKILL, current, 0);
return error;
}
error = bprm->file->f_op->read(bprm->file,
(char __user *)text_addr,
ex.a_text+ex.a_data, &pos);
if ((signed long)error < 0) {
send_sig(SIGKILL, current, 0);
return error;
}
flush_icache_range(text_addr, text_addr+ex.a_text+ex.a_data);
} else {
#ifdef WARN_OLD
static unsigned long error_time, error_time2;
if ((ex.a_text & 0xfff || ex.a_data & 0xfff) &&
(N_MAGIC(ex) != NMAGIC) &&
time_after(jiffies, error_time2 + 5*HZ)) {
printk(KERN_NOTICE "executable not page aligned\n");
error_time2 = jiffies;
}
if ((fd_offset & ~PAGE_MASK) != 0 &&
time_after(jiffies, error_time + 5*HZ)) {
printk(KERN_WARNING
"fd_offset is not page aligned. Please convert "
"program: %s\n",
bprm->file->f_path.dentry->d_name.name);
error_time = jiffies;
}
#endif
if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) {
loff_t pos = fd_offset;
down_write(&current->mm->mmap_sem);
do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
up_write(&current->mm->mmap_sem);
bprm->file->f_op->read(bprm->file,
(char __user *)N_TXTADDR(ex),
ex.a_text+ex.a_data, &pos);
flush_icache_range((unsigned long) N_TXTADDR(ex),
(unsigned long) N_TXTADDR(ex) +
ex.a_text+ex.a_data);
goto beyond_if;
}
down_write(&current->mm->mmap_sem);
error = do_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
PROT_READ | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
MAP_EXECUTABLE | MAP_32BIT,
fd_offset);
up_write(&current->mm->mmap_sem);
if (error != N_TXTADDR(ex)) {
send_sig(SIGKILL, current, 0);
return error;
}
down_write(&current->mm->mmap_sem);
error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
MAP_EXECUTABLE | MAP_32BIT,
fd_offset + ex.a_text);
up_write(&current->mm->mmap_sem);
if (error != N_DATADDR(ex)) {
send_sig(SIGKILL, current, 0);
return error;
}
}
beyond_if:
set_binfmt(&aout_format);
set_brk(current->mm->start_brk, current->mm->brk);
retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
if (retval < 0) {
/* Someone check-me: is this error path enough? */
send_sig(SIGKILL, current, 0);
return retval;
}
current->mm->start_stack =
(unsigned long)create_aout_tables((char __user *)bprm->p, bprm);
/* start thread */
loadsegment(fs, 0);
loadsegment(ds, __USER32_DS);
loadsegment(es, __USER32_DS);
load_gs_index(0);
(regs)->ip = ex.a_entry;
(regs)->sp = current->mm->start_stack;
(regs)->flags = 0x200;
(regs)->cs = __USER32_CS;
(regs)->ss = __USER32_DS;
regs->r8 = regs->r9 = regs->r10 = regs->r11 =
regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
set_fs(USER_DS);
return 0;
}
static int load_aout_library(struct file *file)
{
struct inode *inode;
unsigned long bss, start_addr, len, error;
int retval;
struct exec ex;
inode = file->f_path.dentry->d_inode;
retval = -ENOEXEC;
error = kernel_read(file, 0, (char *) &ex, sizeof(ex));
if (error != sizeof(ex))
goto out;
/* We come in here for the regular a.out style of shared libraries */
if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) ||
N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) ||
i_size_read(inode) <
ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
goto out;
}
if (N_FLAGS(ex))
goto out;
/* For QMAGIC, the starting address is 0x20 into the page. We mask
this off to get the starting address for the page */
start_addr = ex.a_entry & 0xfffff000;
if ((N_TXTOFF(ex) & ~PAGE_MASK) != 0) {
loff_t pos = N_TXTOFF(ex);
#ifdef WARN_OLD
static unsigned long error_time;
if (time_after(jiffies, error_time + 5*HZ)) {
printk(KERN_WARNING
"N_TXTOFF is not page aligned. Please convert "
"library: %s\n",
file->f_path.dentry->d_name.name);
error_time = jiffies;
}
#endif
down_write(&current->mm->mmap_sem);
do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
up_write(&current->mm->mmap_sem);
file->f_op->read(file, (char __user *)start_addr,
ex.a_text + ex.a_data, &pos);
flush_icache_range((unsigned long) start_addr,
(unsigned long) start_addr + ex.a_text +
ex.a_data);
retval = 0;
goto out;
}
/* Now use mmap to map the library into memory. */
down_write(&current->mm->mmap_sem);
error = do_mmap(file, start_addr, ex.a_text + ex.a_data,
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_32BIT,
N_TXTOFF(ex));
up_write(&current->mm->mmap_sem);
retval = error;
if (error != start_addr)
goto out;
len = PAGE_ALIGN(ex.a_text + ex.a_data);
bss = ex.a_text + ex.a_data + ex.a_bss;
if (bss > len) {
down_write(&current->mm->mmap_sem);
error = do_brk(start_addr + len, bss - len);
up_write(&current->mm->mmap_sem);
retval = error;
if (error != start_addr + len)
goto out;
}
retval = 0;
out:
return retval;
}
static int __init init_aout_binfmt(void)
{
return register_binfmt(&aout_format);
}
static void __exit exit_aout_binfmt(void)
{
unregister_binfmt(&aout_format);
}
module_init(init_aout_binfmt);
module_exit(exit_aout_binfmt);
MODULE_LICENSE("GPL");