linux-stable/kernel/futex_compat.c
David Miller 3c5fd9c77d [FUTEX] Fix address computation in compat code.
compat_exit_robust_list() computes a pointer to the
futex entry in userspace as follows:

	(void __user *)entry + futex_offset

'entry' is a 'struct robust_list __user *', and
'futex_offset' is a 'compat_long_t' (typically a 's32').

Things explode if the 32-bit sign bit is set in futex_offset.

Type promotion sign extends futex_offset to a 64-bit value before
adding it to 'entry'.

This triggered a problem on sparc64 running 32-bit applications which
would lock up a cpu looping forever in the fault handling for the
userspace load in handle_futex_death().

Compat userspace runs with address masking (wherein the cpu zeros out
the top 32-bits of every effective address given to a memory operation
instruction) so the sparc64 fault handler accounts for this by
zero'ing out the top 32-bits of the fault address too.

Since the kernel properly uses the compat_uptr interfaces, kernel side
accesses to compat userspace work too since they will only use
addresses with the top 32-bit clear.

Because of this compat futex layer bug we get into the following loop
when executing the get_user() load near the top of handle_futex_death():

1) load from address '0xfffffffff7f16bd8', FAULT
2) fault handler clears upper 32-bits, processes fault
   for address '0xf7f16bd8' which succeeds
3) goto #1

I want to thank Bernd Zeimetz, Josip Rodin, and Fabio Massimo Di Nitto
for their tireless efforts helping me track down this bug.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-11-09 16:13:08 -08:00

185 lines
4.2 KiB
C

/*
* linux/kernel/futex_compat.c
*
* Futex compatibililty routines.
*
* Copyright 2006, Red Hat, Inc., Ingo Molnar
*/
#include <linux/linkage.h>
#include <linux/compat.h>
#include <linux/nsproxy.h>
#include <linux/futex.h>
#include <asm/uaccess.h>
/*
* Fetch a robust-list pointer. Bit 0 signals PI futexes:
*/
static inline int
fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
compat_uptr_t __user *head, int *pi)
{
if (get_user(*uentry, head))
return -EFAULT;
*entry = compat_ptr((*uentry) & ~1);
*pi = (unsigned int)(*uentry) & 1;
return 0;
}
static void __user *futex_uaddr(struct robust_list *entry,
compat_long_t futex_offset)
{
compat_uptr_t base = ptr_to_compat(entry);
void __user *uaddr = compat_ptr(base + futex_offset);
return uaddr;
}
/*
* Walk curr->robust_list (very carefully, it's a userspace list!)
* and mark any locks found there dead, and notify any waiters.
*
* We silently return on any sign of list-walking problem.
*/
void compat_exit_robust_list(struct task_struct *curr)
{
struct compat_robust_list_head __user *head = curr->compat_robust_list;
struct robust_list __user *entry, *next_entry, *pending;
unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
compat_uptr_t uentry, next_uentry, upending;
compat_long_t futex_offset;
int rc;
/*
* Fetch the list head (which was registered earlier, via
* sys_set_robust_list()):
*/
if (fetch_robust_entry(&uentry, &entry, &head->list.next, &pi))
return;
/*
* Fetch the relative futex offset:
*/
if (get_user(futex_offset, &head->futex_offset))
return;
/*
* Fetch any possibly pending lock-add first, and handle it
* if it exists:
*/
if (fetch_robust_entry(&upending, &pending,
&head->list_op_pending, &pip))
return;
next_entry = NULL; /* avoid warning with gcc */
while (entry != (struct robust_list __user *) &head->list) {
/*
* Fetch the next entry in the list before calling
* handle_futex_death:
*/
rc = fetch_robust_entry(&next_uentry, &next_entry,
(compat_uptr_t __user *)&entry->next, &next_pi);
/*
* A pending lock might already be on the list, so
* dont process it twice:
*/
if (entry != pending) {
void __user *uaddr = futex_uaddr(entry, futex_offset);
if (handle_futex_death(uaddr, curr, pi))
return;
}
if (rc)
return;
uentry = next_uentry;
entry = next_entry;
pi = next_pi;
/*
* Avoid excessively long or circular lists:
*/
if (!--limit)
break;
cond_resched();
}
if (pending) {
void __user *uaddr = futex_uaddr(pending, futex_offset);
handle_futex_death(uaddr, curr, pip);
}
}
asmlinkage long
compat_sys_set_robust_list(struct compat_robust_list_head __user *head,
compat_size_t len)
{
if (unlikely(len != sizeof(*head)))
return -EINVAL;
current->compat_robust_list = head;
return 0;
}
asmlinkage long
compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
compat_size_t __user *len_ptr)
{
struct compat_robust_list_head __user *head;
unsigned long ret;
if (!pid)
head = current->compat_robust_list;
else {
struct task_struct *p;
ret = -ESRCH;
read_lock(&tasklist_lock);
p = find_task_by_vpid(pid);
if (!p)
goto err_unlock;
ret = -EPERM;
if ((current->euid != p->euid) && (current->euid != p->uid) &&
!capable(CAP_SYS_PTRACE))
goto err_unlock;
head = p->compat_robust_list;
read_unlock(&tasklist_lock);
}
if (put_user(sizeof(*head), len_ptr))
return -EFAULT;
return put_user(ptr_to_compat(head), head_ptr);
err_unlock:
read_unlock(&tasklist_lock);
return ret;
}
asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val,
struct compat_timespec __user *utime, u32 __user *uaddr2,
u32 val3)
{
struct timespec ts;
ktime_t t, *tp = NULL;
int val2 = 0;
int cmd = op & FUTEX_CMD_MASK;
if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI)) {
if (get_compat_timespec(&ts, utime))
return -EFAULT;
if (!timespec_valid(&ts))
return -EINVAL;
t = timespec_to_ktime(ts);
if (cmd == FUTEX_WAIT)
t = ktime_add(ktime_get(), t);
tp = &t;
}
if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE)
val2 = (int) (unsigned long) utime;
return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
}