Newer
Older
/*
* linux/fs/exec.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/*
* #!-checking implemented by tytso.
*/
/*
* Demand-loading implemented 01.12.91 - no need to read anything but
* the header into memory. The inode of the executable is put into
* "current->executable", and page faults do the actual loading. Clean.
*
* Once more I can proudly say that linux stood up to being changed: it
* was less than 2 hours work to get demand-loading completely implemented.
*
* Demand loading changed July 1993 by Eric Youngdale. Use mmap instead,
* current->executable is only used by the procfs. This allows a dispatch
* table to check for several different types of binary formats. We keep
* trying until we recognize the file or we run out of supported binary
* formats.
*/
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/smp_lock.h>

Neil Horman
committed
#include <linux/string.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/key.h>
#include <linux/personality.h>
#include <linux/binfmts.h>
#include <linux/utsname.h>
#include <linux/pid_namespace.h>
#include <linux/module.h>
#include <linux/namei.h>
#include <linux/proc_fs.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/tsacct_kern.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#ifdef CONFIG_KMOD
#include <linux/kmod.h>
#endif
#ifdef __alpha__
/* for /sbin/loader handling in search_binary_handler() */
#include <linux/a.out.h>
#endif

Dan Aloni
committed
char core_pattern[CORENAME_MAX_SIZE] = "core";
/* The maximal length of core_pattern is also specified in sysctl.c */
static DEFINE_RWLOCK(binfmt_lock);
int register_binfmt(struct linux_binfmt * fmt)
{
if (!fmt)
return -EINVAL;
write_lock(&binfmt_lock);
write_unlock(&binfmt_lock);
return 0;
}
EXPORT_SYMBOL(register_binfmt);
void unregister_binfmt(struct linux_binfmt * fmt)
write_unlock(&binfmt_lock);
}
EXPORT_SYMBOL(unregister_binfmt);
static inline void put_binfmt(struct linux_binfmt * fmt)
{
module_put(fmt->module);
}
/*
* Note that a shared library must be both readable and executable due to
* security reasons.
*
* Also note that we take the address to load from from the file itself.
*/
asmlinkage long sys_uselib(const char __user * library)
{
char *tmp = getname(library);
int error = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
error = path_lookup_open(AT_FDCWD, tmp,
LOOKUP_FOLLOW, &nd,
FMODE_READ|FMODE_EXEC);
putname(tmp);
}
if (!S_ISREG(nd.path.dentry->d_inode->i_mode))
error = -EACCES;
if (nd.path.mnt->mnt_flags & MNT_NOEXEC)
goto exit;
error = vfs_permission(&nd, MAY_READ | MAY_EXEC | MAY_OPEN);
file = nameidata_to_filp(&nd, O_RDONLY|O_LARGEFILE);
error = PTR_ERR(file);
if (IS_ERR(file))
goto out;
error = -ENOEXEC;
if(file->f_op) {
struct linux_binfmt * fmt;
read_lock(&binfmt_lock);
list_for_each_entry(fmt, &formats, lh) {
if (!fmt->load_shlib)
continue;
if (!try_module_get(fmt->module))
continue;
read_unlock(&binfmt_lock);
error = fmt->load_shlib(file);
read_lock(&binfmt_lock);
put_binfmt(fmt);
if (error != -ENOEXEC)
break;
}
read_unlock(&binfmt_lock);
}
fput(file);
out:
return error;
exit:
release_open_intent(&nd);
#ifdef CONFIG_MMU
static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
int write)
{
struct page *page;
int ret;
#ifdef CONFIG_STACK_GROWSUP
if (write) {
ret = expand_stack_downwards(bprm->vma, pos);
if (ret < 0)
return NULL;
}
#endif
ret = get_user_pages(current, bprm->mm, pos,
1, write, 1, &page, NULL);
if (ret <= 0)
return NULL;
if (write) {
unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
struct rlimit *rlim;
/*
* We've historically supported up to 32 pages (ARG_MAX)
* of argument strings even with small stacks
*/
if (size <= ARG_MAX)
return page;
* Limit to 1/4-th the stack size for the argv+env strings.
* This ensures that:
* - the remaining binfmt code will not run out of stack space,
* - the program will have a reasonable amount of stack left
* to work from.
*/
rlim = current->signal->rlim;
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
if (size > rlim[RLIMIT_STACK].rlim_cur / 4) {
put_page(page);
return NULL;
}
}
return page;
}
static void put_arg_page(struct page *page)
{
put_page(page);
}
static void free_arg_page(struct linux_binprm *bprm, int i)
{
}
static void free_arg_pages(struct linux_binprm *bprm)
{
}
static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos,
struct page *page)
{
flush_cache_page(bprm->vma, pos, page_to_pfn(page));
}
static int __bprm_mm_init(struct linux_binprm *bprm)
{
int err = -ENOMEM;
struct vm_area_struct *vma = NULL;
struct mm_struct *mm = bprm->mm;
bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
if (!vma)
goto err;
down_write(&mm->mmap_sem);
vma->vm_mm = mm;
/*
* Place the stack at the largest stack address the architecture
* supports. Later, we'll move this to an appropriate place. We don't
* use STACK_TOP because that can depend on attributes which aren't
* configured yet.
*/
vma->vm_end = STACK_TOP_MAX;
vma->vm_start = vma->vm_end - PAGE_SIZE;
vma->vm_flags = VM_STACK_FLAGS;
vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
err = insert_vm_struct(mm, vma);
if (err) {
up_write(&mm->mmap_sem);
goto err;
}
mm->stack_vm = mm->total_vm = 1;
up_write(&mm->mmap_sem);
bprm->p = vma->vm_end - sizeof(void *);
return 0;
err:
if (vma) {
bprm->vma = NULL;
kmem_cache_free(vm_area_cachep, vma);
}
return err;
}
static bool valid_arg_len(struct linux_binprm *bprm, long len)
{
return len <= MAX_ARG_STRLEN;
}
#else
static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
int write)
{
struct page *page;
page = bprm->page[pos / PAGE_SIZE];
if (!page && write) {
page = alloc_page(GFP_HIGHUSER|__GFP_ZERO);
if (!page)
return NULL;
bprm->page[pos / PAGE_SIZE] = page;
}
return page;
}
static void put_arg_page(struct page *page)
{
}
static void free_arg_page(struct linux_binprm *bprm, int i)
{
if (bprm->page[i]) {
__free_page(bprm->page[i]);
bprm->page[i] = NULL;
}
}
static void free_arg_pages(struct linux_binprm *bprm)
{
int i;
for (i = 0; i < MAX_ARG_PAGES; i++)
free_arg_page(bprm, i);
}
static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos,
struct page *page)
{
}
static int __bprm_mm_init(struct linux_binprm *bprm)
{
bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *);
return 0;
}
static bool valid_arg_len(struct linux_binprm *bprm, long len)
{
return len <= bprm->p;
}
#endif /* CONFIG_MMU */
/*
* Create a new mm_struct and populate it with a temporary stack
* vm_area_struct. We don't have enough context at this point to set the stack
* flags, permissions, and offset, so we use temporary values. We'll update
* them later in setup_arg_pages().
*/
int bprm_mm_init(struct linux_binprm *bprm)
{
int err;
struct mm_struct *mm = NULL;
bprm->mm = mm = mm_alloc();
err = -ENOMEM;
if (!mm)
goto err;
err = init_new_context(current, mm);
if (err)
goto err;
err = __bprm_mm_init(bprm);
if (err)
goto err;
return 0;
err:
if (mm) {
bprm->mm = NULL;
mmdrop(mm);
}
return err;
}
/*
* count() counts the number of strings in array ARGV.
*/
static int count(char __user * __user * argv, int max)
{
int i = 0;
if (argv != NULL) {
for (;;) {
char __user * p;
if (get_user(p, argv))
return -EFAULT;
if (!p)
break;
argv++;
if(++i > max)
return -E2BIG;
cond_resched();
}
}
return i;
}
/*
* 'copy_strings()' copies argument/environment strings from the old
* processes's memory to the new process's stack. The call to get_user_pages()
* ensures the destination page is created and not swapped out.
static int copy_strings(int argc, char __user * __user * argv,
struct linux_binprm *bprm)
{
struct page *kmapped_page = NULL;
char *kaddr = NULL;
int ret;
while (argc-- > 0) {
char __user *str;
int len;
unsigned long pos;
if (get_user(str, argv+argc) ||
!(len = strnlen_user(str, MAX_ARG_STRLEN))) {
/* We're going to work our way backwords. */
while (len > 0) {
int offset, bytes_to_copy;
offset = pos % PAGE_SIZE;
if (offset == 0)
offset = PAGE_SIZE;
bytes_to_copy = offset;
if (bytes_to_copy > len)
bytes_to_copy = len;
offset -= bytes_to_copy;
pos -= bytes_to_copy;
str -= bytes_to_copy;
len -= bytes_to_copy;
if (!kmapped_page || kpos != (pos & PAGE_MASK)) {
struct page *page;
page = get_arg_page(bprm, pos, 1);
if (kmapped_page) {
flush_kernel_dcache_page(kmapped_page);
kpos = pos & PAGE_MASK;
flush_arg_page(bprm, kpos, kmapped_page);
if (copy_from_user(kaddr+offset, str, bytes_to_copy)) {
ret = -EFAULT;
goto out;
}
}
}
ret = 0;
out:
if (kmapped_page) {
flush_kernel_dcache_page(kmapped_page);
return ret;
}
/*
* Like copy_strings, but get argv and its values from kernel memory.
*/
int copy_strings_kernel(int argc,char ** argv, struct linux_binprm *bprm)
{
int r;
mm_segment_t oldfs = get_fs();
set_fs(KERNEL_DS);
r = copy_strings(argc, (char __user * __user *)argv, bprm);
set_fs(oldfs);
return r;
}
EXPORT_SYMBOL(copy_strings_kernel);
#ifdef CONFIG_MMU
* During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX. Once
* the binfmt code determines where the new stack should reside, we shift it to
* its final location. The process proceeds as follows:
* 1) Use shift to calculate the new vma endpoints.
* 2) Extend vma to cover both the old and new ranges. This ensures the
* arguments passed to subsequent functions are consistent.
* 3) Move vma's page tables to the new range.
* 4) Free up any cleared pgd range.
* 5) Shrink the vma to cover only the new range.
static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
unsigned long old_start = vma->vm_start;
unsigned long old_end = vma->vm_end;
unsigned long length = old_end - old_start;
unsigned long new_start = old_start - shift;
unsigned long new_end = old_end - shift;
struct mmu_gather *tlb;
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
/*
* ensure there are no vmas between where we want to go
* and where we are
*/
if (vma != find_vma(mm, new_start))
return -EFAULT;
/*
* cover the whole range: [new_start, old_end)
*/
vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL);
/*
* move the page tables downwards, on failure we rely on
* process cleanup to remove whatever mess we made.
*/
if (length != move_page_tables(vma, old_start,
vma, new_start, length))
return -ENOMEM;
lru_add_drain();
tlb = tlb_gather_mmu(mm, 0);
if (new_end > old_start) {
/*
* when the old and new regions overlap clear from new_end.
*/
free_pgd_range(tlb, new_end, old_end, new_end,
vma->vm_next ? vma->vm_next->vm_start : 0);
} else {
/*
* otherwise, clean from old_start; this is done to not touch
* the address space in [new_end, old_start) some architectures
* have constraints on va-space that make this illegal (IA64) -
* for the others its just a little faster.
*/
free_pgd_range(tlb, old_start, old_end, new_end,
vma->vm_next ? vma->vm_next->vm_start : 0);
tlb_finish_mmu(tlb, new_end, old_end);
/*
* shrink the vma to just the new range.
*/
vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL);
return 0;
}
#define EXTRA_STACK_VM_PAGES 20 /* random */
/*
* Finalizes the stack vm_area_struct. The flags and permissions are updated,
* the stack is optionally relocated, and some extra space is added.
*/
int setup_arg_pages(struct linux_binprm *bprm,
unsigned long stack_top,
int executable_stack)
{
unsigned long ret;
unsigned long stack_shift;
struct vm_area_struct *vma = bprm->vma;
struct vm_area_struct *prev = NULL;
unsigned long vm_flags;
unsigned long stack_base;
#ifdef CONFIG_STACK_GROWSUP
/* Limit stack size to 1GB */
stack_base = current->signal->rlim[RLIMIT_STACK].rlim_max;
if (stack_base > (1 << 30))
stack_base = 1 << 30;
/* Make sure we didn't let the argument array grow too large. */
if (vma->vm_end - vma->vm_start > stack_base)
return -ENOMEM;
stack_base = PAGE_ALIGN(stack_top - stack_base);
stack_shift = vma->vm_start - stack_base;
mm->arg_start = bprm->p - stack_shift;
bprm->p = vma->vm_end - stack_shift;
stack_top = arch_align_stack(stack_top);
stack_top = PAGE_ALIGN(stack_top);
stack_shift = vma->vm_end - stack_top;
bprm->p -= stack_shift;
mm->arg_start = bprm->p;
#endif
if (bprm->loader)
bprm->loader -= stack_shift;
bprm->exec -= stack_shift;
vm_flags = VM_STACK_FLAGS;
/*
* Adjust stack execute permissions; explicitly enable for
* EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X and leave alone
* (arch default) otherwise.
*/
if (unlikely(executable_stack == EXSTACK_ENABLE_X))
vm_flags |= VM_EXEC;
else if (executable_stack == EXSTACK_DISABLE_X)
vm_flags &= ~VM_EXEC;
vm_flags |= mm->def_flags;
ret = mprotect_fixup(vma, &prev, vma->vm_start, vma->vm_end,
vm_flags);
if (ret)
goto out_unlock;
BUG_ON(prev != vma);
/* Move stack pages down in memory. */
if (stack_shift) {
ret = shift_arg_pages(vma, stack_shift);
if (ret) {
up_write(&mm->mmap_sem);
return ret;
}
}
#ifdef CONFIG_STACK_GROWSUP
stack_base = vma->vm_end + EXTRA_STACK_VM_PAGES * PAGE_SIZE;
#else
stack_base = vma->vm_start - EXTRA_STACK_VM_PAGES * PAGE_SIZE;
#endif
ret = expand_stack(vma, stack_base);
if (ret)
ret = -EFAULT;
out_unlock:
up_write(&mm->mmap_sem);
return 0;
}
EXPORT_SYMBOL(setup_arg_pages);
#endif /* CONFIG_MMU */
struct file *open_exec(const char *name)
{
struct nameidata nd;
struct file *file;
err = path_lookup_open(AT_FDCWD, name, LOOKUP_FOLLOW, &nd,
FMODE_READ|FMODE_EXEC);
if (err)
goto out;
err = -EACCES;
if (!S_ISREG(nd.path.dentry->d_inode->i_mode))
goto out_path_put;
if (nd.path.mnt->mnt_flags & MNT_NOEXEC)
goto out_path_put;
err = vfs_permission(&nd, MAY_EXEC | MAY_OPEN);
if (err)
goto out_path_put;
file = nameidata_to_filp(&nd, O_RDONLY|O_LARGEFILE);
if (IS_ERR(file))
return file;
err = deny_write_access(file);
if (err) {
fput(file);
goto out;
return file;
out_path_put:
release_open_intent(&nd);
path_put(&nd.path);
out:
return ERR_PTR(err);
}
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
EXPORT_SYMBOL(open_exec);
int kernel_read(struct file *file, unsigned long offset,
char *addr, unsigned long count)
{
mm_segment_t old_fs;
loff_t pos = offset;
int result;
old_fs = get_fs();
set_fs(get_ds());
/* The cast to a user pointer is valid due to the set_fs() */
result = vfs_read(file, (void __user *)addr, count, &pos);
set_fs(old_fs);
return result;
}
EXPORT_SYMBOL(kernel_read);
static int exec_mmap(struct mm_struct *mm)
{
struct task_struct *tsk;
struct mm_struct * old_mm, *active_mm;
/* Notify parent that we're no longer interested in the old VM */
tsk = current;
old_mm = current->mm;
mm_release(tsk, old_mm);
if (old_mm) {
/*
* Make sure that if there is a core dump in progress
* for the old mm, we get out and die instead of going
* through with the exec. We must hold mmap_sem around
* checking core_state and changing tsk->mm.
if (unlikely(old_mm->core_state)) {
up_read(&old_mm->mmap_sem);
return -EINTR;
}
}
task_lock(tsk);
active_mm = tsk->active_mm;
tsk->mm = mm;
tsk->active_mm = mm;
activate_mm(active_mm, mm);
task_unlock(tsk);
arch_pick_mmap_layout(mm);
if (old_mm) {
up_read(&old_mm->mmap_sem);
mm_update_next_owner(old_mm);
mmput(old_mm);
return 0;
}
mmdrop(active_mm);
return 0;
}
/*
* This function makes sure the current process has its own signal table,
* so that flush_signal_handlers can later reset the handlers without
* disturbing other processes. (Other processes might share the signal
* table via the CLONE_SIGHAND option to clone().)
*/
static int de_thread(struct task_struct *tsk)
struct sighand_struct *oldsighand = tsk->sighand;
struct task_struct *leader = NULL;
goto no_thread_group;
/*
* Kill all other threads in the thread group.
*/
spin_lock_irq(lock);
if (signal_group_exit(sig)) {
/*
* Another group action in progress, just
* return so that the signal is processed.
*/
spin_unlock_irq(lock);
return -EAGAIN;
}
sig->group_exit_task = tsk;
/* Account for the thread group leader hanging around: */
count = thread_group_leader(tsk) ? 1 : 2;
sig->notify_count = count;
while (atomic_read(&sig->count) > count) {
__set_current_state(TASK_UNINTERRUPTIBLE);
spin_unlock_irq(lock);
schedule();
spin_lock_irq(lock);
}
spin_unlock_irq(lock);
/*
* At this point all other threads have exited, all we have to
* do is to wait for the thread group leader to become inactive,
* and to assume its PID:
*/
if (!thread_group_leader(tsk)) {
leader = tsk->group_leader;
sig->notify_count = -1; /* for exit_notify() */
for (;;) {
write_lock_irq(&tasklist_lock);
if (likely(leader->exit_state))
break;
__set_current_state(TASK_UNINTERRUPTIBLE);
write_unlock_irq(&tasklist_lock);
schedule();
}
if (unlikely(task_child_reaper(tsk) == leader))
task_active_pid_ns(tsk)->child_reaper = tsk;

Roland McGrath
committed
/*
* The only record we have of the real-time age of a
* process, regardless of execs it's done, is start_time.
* All the past CPU time is accumulated in signal_struct
* from sister threads now dead. But in this non-leader
* exec, nothing survives from the original leader thread,
* whose birth marks the true age of this process now.
* When we take on its identity by switching to its PID, we
* also take its birthdate (always earlier than our own).
*/
tsk->start_time = leader->start_time;

Roland McGrath
committed
BUG_ON(!same_thread_group(leader, tsk));
BUG_ON(has_group_leader_pid(tsk));
/*
* An exec() starts a new thread group with the
* TGID of the previous thread group. Rehash the
* two threads with a switched PID, and release
* the former thread group leader:
*/
/* Become a process group leader with the old leader's pid.
* The old leader becomes a thread of the this thread group.
* Note: The old leader also uses this pid until release_task
* is called. Odd but simple and correct.
*/
detach_pid(tsk, PIDTYPE_PID);
tsk->pid = leader->pid;
attach_pid(tsk, PIDTYPE_PID, task_pid(leader));
transfer_pid(leader, tsk, PIDTYPE_PGID);
transfer_pid(leader, tsk, PIDTYPE_SID);
list_replace_rcu(&leader->tasks, &tsk->tasks);
tsk->group_leader = tsk;
leader->group_leader = tsk;
BUG_ON(leader->exit_state != EXIT_ZOMBIE);
leader->exit_state = EXIT_DEAD;
sig->group_exit_task = NULL;
sig->notify_count = 0;
if (leader)
release_task(leader);
if (atomic_read(&oldsighand->count) != 1) {
struct sighand_struct *newsighand;
* This ->sighand is shared with the CLONE_SIGHAND
* but not CLONE_THREAD task, switch to the new one.
newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
if (!newsighand)
return -ENOMEM;
atomic_set(&newsighand->count, 1);
memcpy(newsighand->action, oldsighand->action,
sizeof(newsighand->action));
write_lock_irq(&tasklist_lock);
spin_lock(&oldsighand->siglock);
rcu_assign_pointer(tsk->sighand, newsighand);
spin_unlock(&oldsighand->siglock);
write_unlock_irq(&tasklist_lock);
BUG_ON(!thread_group_leader(tsk));
/*
* These functions flushes out all traces of the currently running executable
* so that a new one can be started
*/
static void flush_old_files(struct files_struct * files)
spin_lock(&files->file_lock);
for (;;) {
unsigned long set, i;
j++;
i = j * __NFDBITS;
if (i >= fdt->max_fds)
set = fdt->close_on_exec->fds_bits[j];
fdt->close_on_exec->fds_bits[j] = 0;
spin_unlock(&files->file_lock);
for ( ; set ; i++,set >>= 1) {
if (set & 1) {
sys_close(i);
}
}
spin_lock(&files->file_lock);
}
spin_unlock(&files->file_lock);
}
char *get_task_comm(char *buf, struct task_struct *tsk)
{
/* buf must be at least sizeof(tsk->comm) in size */
task_lock(tsk);
strncpy(buf, tsk->comm, sizeof(tsk->comm));
task_unlock(tsk);
}
void set_task_comm(struct task_struct *tsk, char *buf)
{
task_lock(tsk);
strlcpy(tsk->comm, buf, sizeof(tsk->comm));
task_unlock(tsk);
}
int flush_old_exec(struct linux_binprm * bprm)
{
char * name;
int i, ch, retval;
char tcomm[sizeof(current->comm)];
/*
* Make sure we have a private signal table and that
* we are unassociated from the previous thread group.
*/
retval = de_thread(current);
if (retval)
goto out;
/*
* Release all of the old mmap stuff
*/
retval = exec_mmap(bprm->mm);
if (retval)
goto out;
bprm->mm = NULL; /* We're using it now */
/* This is the point of no return */
current->sas_ss_sp = current->sas_ss_size = 0;
if (current->euid == current->uid && current->egid == current->gid)
set_dumpable(current->mm, 1);
set_dumpable(current->mm, suid_dumpable);
/* Copies the binary name from after last slash */
for (i=0; (ch = *(name++)) != '\0';) {
if (ch == '/')
i = 0; /* overwrite what we wrote */
else
if (i < (sizeof(tcomm) - 1))
tcomm[i++] = ch;
}
tcomm[i] = '\0';
set_task_comm(current, tcomm);
current->flags &= ~PF_RANDOMIZE;
flush_thread();
/* Set the new mm task size. We have to do that late because it may
* depend on TIF_32BIT which is only updated in flush_thread() on
* some architectures like powerpc
*/
current->mm->task_size = TASK_SIZE;
if (bprm->e_uid != current->euid || bprm->e_gid != current->egid) {
suid_keys(current);
set_dumpable(current->mm, suid_dumpable);
current->pdeath_signal = 0;
} else if (file_permission(bprm->file, MAY_READ) ||
(bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) {
set_dumpable(current->mm, suid_dumpable);
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
}
/* An exec changes our domain. We are no longer part of the thread
group */
current->self_exec_id++;
flush_signal_handlers(current, 0);
flush_old_files(current->files);
return 0;
out:
return retval;
}
EXPORT_SYMBOL(flush_old_exec);
/*
* Fill the binprm structure from the inode.
* Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
*/
int prepare_binprm(struct linux_binprm *bprm)
{
int mode;
struct inode * inode = bprm->file->f_path.dentry->d_inode;
int retval;
mode = inode->i_mode;
if (bprm->file->f_op == NULL)
return -EACCES;
bprm->e_uid = current->euid;
bprm->e_gid = current->egid;
if(!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) {
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
/* Set-uid? */
if (mode & S_ISUID) {
current->personality &= ~PER_CLEAR_ON_SETID;
bprm->e_uid = inode->i_uid;
}
/* Set-gid? */
/*
* If setgid is set but no group execute bit then this
* is a candidate for mandatory locking, not a setgid
* executable.
*/
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
current->personality &= ~PER_CLEAR_ON_SETID;
bprm->e_gid = inode->i_gid;
}
}
/* fill in binprm security blob */
retval = security_bprm_set(bprm);
if (retval)
return retval;
memset(bprm->buf,0,BINPRM_BUF_SIZE);
return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE);
}
EXPORT_SYMBOL(prepare_binprm);
static int unsafe_exec(struct task_struct *p)
if (atomic_read(&p->fs->count) > 1 ||
atomic_read(&p->files->count) > 1 ||
atomic_read(&p->sighand->count) > 1)
unsafe |= LSM_UNSAFE_SHARE;
return unsafe;
}
void compute_creds(struct linux_binprm *bprm)
{
int unsafe;
if (bprm->e_uid != current->uid) {
current->pdeath_signal = 0;
}
exec_keys(current);
task_lock(current);
unsafe = unsafe_exec(current);
security_bprm_apply_creds(bprm, unsafe);
task_unlock(current);
security_bprm_post_apply_creds(bprm);
}
EXPORT_SYMBOL(compute_creds);
/*
* Arguments are '\0' separated strings found at the location bprm->p
* points to; chop off the first by relocating brpm->p to right after
* the first '\0' encountered.
*/
int remove_arg_zero(struct linux_binprm *bprm)
int ret = 0;
unsigned long offset;
char *kaddr;
struct page *page;
do {
offset = bprm->p & ~PAGE_MASK;
page = get_arg_page(bprm, bprm->p, 0);
if (!page) {
ret = -EFAULT;
goto out;
}
kaddr = kmap_atomic(page, KM_USER0);
for (; offset < PAGE_SIZE && kaddr[offset];
offset++, bprm->p++)
;
kunmap_atomic(kaddr, KM_USER0);
put_arg_page(page);
if (offset == PAGE_SIZE)
free_arg_page(bprm, (bprm->p >> PAGE_SHIFT) - 1);
} while (offset == PAGE_SIZE);
bprm->p++;
bprm->argc--;
ret = 0;
}
EXPORT_SYMBOL(remove_arg_zero);
/*
* cycle the list of binary formats handler, until one recognizes the image
*/
int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
{
int try,retval;
struct linux_binfmt *fmt;
/* handle /sbin/loader.. */
{
struct exec * eh = (struct exec *) bprm->buf;
if (!bprm->loader && eh->fh.f_magic == 0x183 &&
(eh->fh.f_flags & 0x3000) == 0x3000)
{
struct file * file;
unsigned long loader;
allow_write_access(bprm->file);
fput(bprm->file);
bprm->file = NULL;
loader = bprm->vma->vm_end - sizeof(void *);
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
file = open_exec("/sbin/loader");
retval = PTR_ERR(file);
if (IS_ERR(file))
return retval;
/* Remember if the application is TASO. */
bprm->sh_bang = eh->ah.entry < 0x100000000UL;
bprm->file = file;
bprm->loader = loader;
retval = prepare_binprm(bprm);
if (retval<0)
return retval;
/* should call search_binary_handler recursively here,
but it does not matter */
}
}
#endif
retval = security_bprm_check(bprm);
if (retval)
return retval;
/* kernel module loader fixup */
/* so we don't try to load run modprobe in kernel space. */
set_fs(USER_DS);
retval = audit_bprm(bprm);
if (retval)
return retval;
retval = -ENOENT;
for (try=0; try<2; try++) {
read_lock(&binfmt_lock);
list_for_each_entry(fmt, &formats, lh) {
int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary;
if (!fn)
continue;
if (!try_module_get(fmt->module))
continue;
read_unlock(&binfmt_lock);
retval = fn(bprm, regs);
if (retval >= 0) {
put_binfmt(fmt);
allow_write_access(bprm->file);
if (bprm->file)
fput(bprm->file);
bprm->file = NULL;
current->did_exec = 1;
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
return retval;
}
read_lock(&binfmt_lock);
put_binfmt(fmt);
if (retval != -ENOEXEC || bprm->mm == NULL)
break;
if (!bprm->file) {
read_unlock(&binfmt_lock);
return retval;
}
}
read_unlock(&binfmt_lock);
if (retval != -ENOEXEC || bprm->mm == NULL) {
break;
#ifdef CONFIG_KMOD
}else{
#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
if (printable(bprm->buf[0]) &&
printable(bprm->buf[1]) &&
printable(bprm->buf[2]) &&
printable(bprm->buf[3]))
break; /* -ENOEXEC */
request_module("binfmt-%04x", *(unsigned short *)(&bprm->buf[2]));
#endif
}
}
return retval;
}
EXPORT_SYMBOL(search_binary_handler);
void free_bprm(struct linux_binprm *bprm)
{
free_arg_pages(bprm);
kfree(bprm);
}
/*
* sys_execve() executes a new program.
*/
int do_execve(char * filename,
char __user *__user *argv,
char __user *__user *envp,
struct pt_regs * regs)
{
struct linux_binprm *bprm;
struct file *file;
struct files_struct *displaced;
retval = unshare_files(&displaced);
if (retval)
goto out_ret;
bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
goto out_files;
file = open_exec(filename);
retval = PTR_ERR(file);
if (IS_ERR(file))
goto out_kfree;
sched_exec();
bprm->file = file;
bprm->filename = filename;
bprm->interp = filename;
retval = bprm_mm_init(bprm);
if (retval)
goto out_file;
bprm->argc = count(argv, MAX_ARG_STRINGS);
if ((retval = bprm->argc) < 0)
goto out_mm;
bprm->envc = count(envp, MAX_ARG_STRINGS);
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
if ((retval = bprm->envc) < 0)
goto out_mm;
retval = security_bprm_alloc(bprm);
if (retval)
goto out;
retval = prepare_binprm(bprm);
if (retval < 0)
goto out;
retval = copy_strings_kernel(1, &bprm->filename, bprm);
if (retval < 0)
goto out;
bprm->exec = bprm->p;
retval = copy_strings(bprm->envc, envp, bprm);
if (retval < 0)
goto out;
retval = copy_strings(bprm->argc, argv, bprm);
if (retval < 0)
goto out;
retval = search_binary_handler(bprm,regs);
if (retval >= 0) {
/* execve success */
security_bprm_free(bprm);
acct_update_integrals(current);
if (displaced)
put_files_struct(displaced);
return retval;
}
out:
if (bprm->security)
security_bprm_free(bprm);
out_mm:
if (bprm->mm)
out_file:
if (bprm->file) {
allow_write_access(bprm->file);
fput(bprm->file);
}
out_kfree:
out_files:
if (displaced)
reset_files_struct(displaced);
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
out_ret:
return retval;
}
int set_binfmt(struct linux_binfmt *new)
{
struct linux_binfmt *old = current->binfmt;
if (new) {
if (!try_module_get(new->module))
return -1;
}
current->binfmt = new;
if (old)
module_put(old->module);
return 0;
}
EXPORT_SYMBOL(set_binfmt);
/* format_corename will inspect the pattern parameter, and output a
* name into corename, which must have space for at least
* CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
*/
static int format_corename(char *corename, int nr_threads, long signr)
const char *pat_ptr = core_pattern;
int ispipe = (*pat_ptr == '|');
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
char *out_ptr = corename;
char *const out_end = corename + CORENAME_MAX_SIZE;
int rc;
int pid_in_pattern = 0;
/* Repeat as long as we have more pattern to process and more output
space */
while (*pat_ptr) {
if (*pat_ptr != '%') {
if (out_ptr == out_end)
goto out;
*out_ptr++ = *pat_ptr++;
} else {
switch (*++pat_ptr) {
case 0:
goto out;
/* Double percent, output one percent */
case '%':
if (out_ptr == out_end)
goto out;
*out_ptr++ = '%';
break;
/* pid */
case 'p':
pid_in_pattern = 1;
rc = snprintf(out_ptr, out_end - out_ptr,
"%d", task_tgid_vnr(current));
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
if (rc > out_end - out_ptr)
goto out;
out_ptr += rc;
break;
/* uid */
case 'u':
rc = snprintf(out_ptr, out_end - out_ptr,
"%d", current->uid);
if (rc > out_end - out_ptr)
goto out;
out_ptr += rc;
break;
/* gid */
case 'g':
rc = snprintf(out_ptr, out_end - out_ptr,
"%d", current->gid);
if (rc > out_end - out_ptr)
goto out;
out_ptr += rc;
break;
/* signal that caused the coredump */
case 's':
rc = snprintf(out_ptr, out_end - out_ptr,
"%ld", signr);
if (rc > out_end - out_ptr)
goto out;
out_ptr += rc;
break;
/* UNIX time of coredump */
case 't': {
struct timeval tv;
do_gettimeofday(&tv);
rc = snprintf(out_ptr, out_end - out_ptr,
"%lu", tv.tv_sec);
if (rc > out_end - out_ptr)
goto out;
out_ptr += rc;
break;
}
/* hostname */
case 'h':
down_read(&uts_sem);
rc = snprintf(out_ptr, out_end - out_ptr,
"%s", utsname()->nodename);
up_read(&uts_sem);
if (rc > out_end - out_ptr)
goto out;
out_ptr += rc;
break;
/* executable */
case 'e':
rc = snprintf(out_ptr, out_end - out_ptr,
"%s", current->comm);
if (rc > out_end - out_ptr)
goto out;
out_ptr += rc;
break;

Neil Horman
committed
/* core limit size */
case 'c':
rc = snprintf(out_ptr, out_end - out_ptr,
"%lu", current->signal->rlim[RLIMIT_CORE].rlim_cur);
if (rc > out_end - out_ptr)
goto out;
out_ptr += rc;
break;
default:
break;
}
++pat_ptr;
}
}
/* Backward compatibility with core_uses_pid:
*
* If core_pattern does not include a %p (as is the default)
* and core_uses_pid is set, then .%pid will be appended to
* the filename. Do not do this for piped commands. */
if (!ispipe && !pid_in_pattern
&& (core_uses_pid || nr_threads)) {
".%d", task_tgid_vnr(current));
if (rc > out_end - out_ptr)
goto out;
out_ptr += rc;
}
return ispipe;
static int zap_process(struct task_struct *start)
{
struct task_struct *t;
start->signal->flags = SIGNAL_GROUP_EXIT;
start->signal->group_stop_count = 0;
t = start;
do {
if (t != current && t->mm) {
sigaddset(&t->pending.signal, SIGKILL);
signal_wake_up(t, 1);
} while_each_thread(start, t);
static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
struct core_state *core_state, int exit_code)
int nr = -EAGAIN;
spin_lock_irq(&tsk->sighand->siglock);
if (!signal_group_exit(tsk->signal)) {
mm->core_state = core_state;
tsk->signal->group_exit_code = exit_code;
nr = zap_process(tsk);
spin_unlock_irq(&tsk->sighand->siglock);
if (unlikely(nr < 0))
return nr;
if (atomic_read(&mm->mm_users) == nr + 1)
/*
* We should find and kill all tasks which use this mm, and we should
* count them correctly into ->nr_threads. We don't take tasklist
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
* lock, but this is safe wrt:
*
* fork:
* None of sub-threads can fork after zap_process(leader). All
* processes which were created before this point should be
* visible to zap_threads() because copy_process() adds the new
* process to the tail of init_task.tasks list, and lock/unlock
* of ->siglock provides a memory barrier.
*
* do_exit:
* The caller holds mm->mmap_sem. This means that the task which
* uses this mm can't pass exit_mm(), so it can't exit or clear
* its ->mm.
*
* de_thread:
* It does list_replace_rcu(&leader->tasks, ¤t->tasks),
* we must see either old or new leader, this does not matter.
* However, it can change p->sighand, so lock_task_sighand(p)
* must be used. Since p->mm != NULL and we hold ->mmap_sem
* it can't fail.
*
* Note also that "g" can be the old leader with ->mm == NULL
* and already unhashed and thus removed from ->thread_group.
* This is OK, __unhash_process()->list_del_rcu() does not
* clear the ->next pointer, we will find the new leader via
* next_thread().
*/
if (g == tsk->group_leader)
continue;
if (g->flags & PF_KTHREAD)
continue;
p = g;
do {
if (p->mm) {
if (unlikely(p->mm == mm)) {
lock_task_sighand(p, &flags);
nr += zap_process(p);
unlock_task_sighand(p, &flags);
}
} while_each_thread(g, p);
atomic_set(&core_state->nr_threads, nr);
static int coredump_wait(int exit_code, struct core_state *core_state)
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
struct completion *vfork_done;
init_completion(&core_state->startup);
core_state->dumper.task = tsk;
core_state->dumper.next = NULL;
core_waiters = zap_threads(tsk, mm, core_state, exit_code);
if (unlikely(core_waiters < 0))
goto fail;
/*
* Make sure nobody is waiting for us to release the VM,
* otherwise we can deadlock when we wait on each other
*/
vfork_done = tsk->vfork_done;
if (vfork_done) {
tsk->vfork_done = NULL;
complete(vfork_done);
}
wait_for_completion(&core_state->startup);
fail:
return core_waiters;
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
static void coredump_finish(struct mm_struct *mm)
{
struct core_thread *curr, *next;
struct task_struct *task;
next = mm->core_state->dumper.next;
while ((curr = next) != NULL) {
next = curr->next;
task = curr->task;
/*
* see exit_mm(), curr->task must not see
* ->task == NULL before we read ->next.
*/
smp_mb();
curr->task = NULL;
wake_up_process(task);
}
mm->core_state = NULL;
}
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
/*
* set_dumpable converts traditional three-value dumpable to two flags and
* stores them into mm->flags. It modifies lower two bits of mm->flags, but
* these bits are not changed atomically. So get_dumpable can observe the
* intermediate state. To avoid doing unexpected behavior, get get_dumpable
* return either old dumpable or new one by paying attention to the order of
* modifying the bits.
*
* dumpable | mm->flags (binary)
* old new | initial interim final
* ---------+-----------------------
* 0 1 | 00 01 01
* 0 2 | 00 10(*) 11
* 1 0 | 01 00 00
* 1 2 | 01 11 11
* 2 0 | 11 10(*) 00
* 2 1 | 11 11 01
*
* (*) get_dumpable regards interim value of 10 as 11.
*/
void set_dumpable(struct mm_struct *mm, int value)
{
switch (value) {
case 0:
clear_bit(MMF_DUMPABLE, &mm->flags);
smp_wmb();
clear_bit(MMF_DUMP_SECURELY, &mm->flags);
break;
case 1:
set_bit(MMF_DUMPABLE, &mm->flags);
smp_wmb();
clear_bit(MMF_DUMP_SECURELY, &mm->flags);
break;
case 2:
set_bit(MMF_DUMP_SECURELY, &mm->flags);
smp_wmb();
set_bit(MMF_DUMPABLE, &mm->flags);
break;
}
}
int get_dumpable(struct mm_struct *mm)
{
int ret;
ret = mm->flags & 0x3;
return (ret >= 2) ? 2 : ret;
}
int do_coredump(long signr, int exit_code, struct pt_regs * regs)
{
struct core_state core_state;
char corename[CORENAME_MAX_SIZE + 1];
struct mm_struct *mm = current->mm;
struct linux_binfmt * binfmt;
struct inode * inode;
struct file * file;
int retval = 0;
int ispipe = 0;
unsigned long core_limit = current->signal->rlim[RLIMIT_CORE].rlim_cur;

Neil Horman
committed
char **helper_argv = NULL;
int helper_argc = 0;
char *delimit;
binfmt = current->binfmt;
if (!binfmt || !binfmt->core_dump)
goto fail;
down_write(&mm->mmap_sem);
/*
* If another thread got here first, or we are not dumpable, bail out.
*/
if (mm->core_state || !get_dumpable(mm)) {
/*
* We cannot trust fsuid as being the "true" uid of the
* process nor do we know its entire history. We only know it
* was tainted so we dump it as root in mode 2.
*/
if (get_dumpable(mm) == 2) { /* Setuid core dump mode */
flag = O_EXCL; /* Stop rewrite attacks */
current->fsuid = 0; /* Dump root private */
}
retval = coredump_wait(exit_code, &core_state);
/*
* Clear any false indication of pending signals that might
* be seen by the filesystem code called to write the core file.
*/
clear_thread_flag(TIF_SIGPENDING);
/*
* lock_kernel() because format_corename() is controlled by sysctl, which
* uses lock_kernel()
*/
lock_kernel();
ispipe = format_corename(corename, retval, signr);
/*
* Don't bother to check the RLIMIT_CORE value if core_pattern points
* to a pipe. Since we're not writing directly to the filesystem
* RLIMIT_CORE doesn't really apply, as no actual core file will be
* created unless the pipe reader choses to write out the core file
* at which point file size limits and permissions will be imposed
* as it does with any other process
*/

Neil Horman
committed
if ((!ispipe) && (core_limit < binfmt->min_coredump))
goto fail_unlock;
if (ispipe) {

Neil Horman
committed
helper_argv = argv_split(GFP_KERNEL, corename+1, &helper_argc);
/* Terminate the string before the first option */
delimit = strchr(corename, ' ');
if (delimit)
*delimit = '\0';
delimit = strrchr(helper_argv[0], '/');
if (delimit)
delimit++;
else
delimit = helper_argv[0];
if (!strcmp(delimit, current->comm)) {
printk(KERN_NOTICE "Recursive core dump detected, "
"aborting\n");
goto fail_unlock;
}
core_limit = RLIM_INFINITY;
/* SIGPIPE can happen, but it's just never processed */
if (call_usermodehelper_pipe(corename+1, helper_argv, NULL,
&file)) {
printk(KERN_INFO "Core dump to %s pipe failed\n",
corename);
goto fail_unlock;
}
} else
file = filp_open(corename,
O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
0600);
inode = file->f_path.dentry->d_inode;
if (inode->i_nlink > 1)
goto close_fail; /* multiple links - don't dump */
if (!ispipe && d_unhashed(file->f_path.dentry))
/* AK: actually i see no reason to not allow this for named pipes etc.,
but keep the previous behaviour for now. */
if (!ispipe && !S_ISREG(inode->i_mode))
/*
* Dont allow local users get cute and trick others to coredump
* into their pre-created files:
*/
if (inode->i_uid != current->fsuid)
goto close_fail;
if (!file->f_op)
goto close_fail;
if (!file->f_op->write)
goto close_fail;
if (!ispipe && do_truncate(file->f_path.dentry, 0, 0, file) != 0)
retval = binfmt->core_dump(signr, regs, file, core_limit);
if (retval)
current->signal->group_exit_code |= 0x80;
close_fail:
filp_close(file, NULL);
fail_unlock:

Neil Horman
committed
if (helper_argv)
argv_free(helper_argv);