![Robin Holt](/assets/img/avatar_default.png)
There is a race condition between mmu_notifier_unregister() and __mmu_notifier_release(). Assume two tasks, one calling mmu_notifier_unregister() as a result of a filp_close() ->flush() callout (task A), and the other calling mmu_notifier_release() from an mmput() (task B). A B t1 srcu_read_lock() t2 if (!hlist_unhashed()) t3 srcu_read_unlock() t4 srcu_read_lock() t5 hlist_del_init_rcu() t6 synchronize_srcu() t7 srcu_read_unlock() t8 hlist_del_rcu() <--- NULL pointer deref. Additionally, the list traversal in __mmu_notifier_release() is not protected by the by the mmu_notifier_mm->hlist_lock which can result in callouts to the ->release() notifier from both mmu_notifier_unregister() and __mmu_notifier_release(). -stable suggestions: The stable trees prior to 3.7.y need commits21a92735f6
and70400303ce
cherry-picked in that order prior to cherry-picking this commit. The 3.7.y tree already has those two commits. Signed-off-by: Robin Holt <holt@sgi.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Cc: Avi Kivity <avi@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Sagi Grimberg <sagig@mellanox.co.il> Cc: Haggai Eran <haggaie@mellanox.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
339 lines
9.3 KiB
C
339 lines
9.3 KiB
C
/*
|
|
* linux/mm/mmu_notifier.c
|
|
*
|
|
* Copyright (C) 2008 Qumranet, Inc.
|
|
* Copyright (C) 2008 SGI
|
|
* Christoph Lameter <clameter@sgi.com>
|
|
*
|
|
* This work is licensed under the terms of the GNU GPL, version 2. See
|
|
* the COPYING file in the top-level directory.
|
|
*/
|
|
|
|
#include <linux/rculist.h>
|
|
#include <linux/mmu_notifier.h>
|
|
#include <linux/export.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/err.h>
|
|
#include <linux/srcu.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/slab.h>
|
|
|
|
/* global SRCU for all MMs */
|
|
static struct srcu_struct srcu;
|
|
|
|
/*
|
|
* This function can't run concurrently against mmu_notifier_register
|
|
* because mm->mm_users > 0 during mmu_notifier_register and exit_mmap
|
|
* runs with mm_users == 0. Other tasks may still invoke mmu notifiers
|
|
* in parallel despite there being no task using this mm any more,
|
|
* through the vmas outside of the exit_mmap context, such as with
|
|
* vmtruncate. This serializes against mmu_notifier_unregister with
|
|
* the mmu_notifier_mm->lock in addition to SRCU and it serializes
|
|
* against the other mmu notifiers with SRCU. struct mmu_notifier_mm
|
|
* can't go away from under us as exit_mmap holds an mm_count pin
|
|
* itself.
|
|
*/
|
|
void __mmu_notifier_release(struct mm_struct *mm)
|
|
{
|
|
struct mmu_notifier *mn;
|
|
int id;
|
|
|
|
/*
|
|
* srcu_read_lock() here will block synchronize_srcu() in
|
|
* mmu_notifier_unregister() until all registered
|
|
* ->release() callouts this function makes have
|
|
* returned.
|
|
*/
|
|
id = srcu_read_lock(&srcu);
|
|
spin_lock(&mm->mmu_notifier_mm->lock);
|
|
while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
|
|
mn = hlist_entry(mm->mmu_notifier_mm->list.first,
|
|
struct mmu_notifier,
|
|
hlist);
|
|
|
|
/*
|
|
* Unlink. This will prevent mmu_notifier_unregister()
|
|
* from also making the ->release() callout.
|
|
*/
|
|
hlist_del_init_rcu(&mn->hlist);
|
|
spin_unlock(&mm->mmu_notifier_mm->lock);
|
|
|
|
/*
|
|
* Clear sptes. (see 'release' description in mmu_notifier.h)
|
|
*/
|
|
if (mn->ops->release)
|
|
mn->ops->release(mn, mm);
|
|
|
|
spin_lock(&mm->mmu_notifier_mm->lock);
|
|
}
|
|
spin_unlock(&mm->mmu_notifier_mm->lock);
|
|
|
|
/*
|
|
* All callouts to ->release() which we have done are complete.
|
|
* Allow synchronize_srcu() in mmu_notifier_unregister() to complete
|
|
*/
|
|
srcu_read_unlock(&srcu, id);
|
|
|
|
/*
|
|
* mmu_notifier_unregister() may have unlinked a notifier and may
|
|
* still be calling out to it. Additionally, other notifiers
|
|
* may have been active via vmtruncate() et. al. Block here
|
|
* to ensure that all notifier callouts for this mm have been
|
|
* completed and the sptes are really cleaned up before returning
|
|
* to exit_mmap().
|
|
*/
|
|
synchronize_srcu(&srcu);
|
|
}
|
|
|
|
/*
|
|
* If no young bitflag is supported by the hardware, ->clear_flush_young can
|
|
* unmap the address and return 1 or 0 depending if the mapping previously
|
|
* existed or not.
|
|
*/
|
|
int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
|
|
unsigned long address)
|
|
{
|
|
struct mmu_notifier *mn;
|
|
struct hlist_node *n;
|
|
int young = 0, id;
|
|
|
|
id = srcu_read_lock(&srcu);
|
|
hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
|
|
if (mn->ops->clear_flush_young)
|
|
young |= mn->ops->clear_flush_young(mn, mm, address);
|
|
}
|
|
srcu_read_unlock(&srcu, id);
|
|
|
|
return young;
|
|
}
|
|
|
|
int __mmu_notifier_test_young(struct mm_struct *mm,
|
|
unsigned long address)
|
|
{
|
|
struct mmu_notifier *mn;
|
|
struct hlist_node *n;
|
|
int young = 0, id;
|
|
|
|
id = srcu_read_lock(&srcu);
|
|
hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
|
|
if (mn->ops->test_young) {
|
|
young = mn->ops->test_young(mn, mm, address);
|
|
if (young)
|
|
break;
|
|
}
|
|
}
|
|
srcu_read_unlock(&srcu, id);
|
|
|
|
return young;
|
|
}
|
|
|
|
void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
|
|
pte_t pte)
|
|
{
|
|
struct mmu_notifier *mn;
|
|
struct hlist_node *n;
|
|
int id;
|
|
|
|
id = srcu_read_lock(&srcu);
|
|
hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
|
|
if (mn->ops->change_pte)
|
|
mn->ops->change_pte(mn, mm, address, pte);
|
|
}
|
|
srcu_read_unlock(&srcu, id);
|
|
}
|
|
|
|
void __mmu_notifier_invalidate_page(struct mm_struct *mm,
|
|
unsigned long address)
|
|
{
|
|
struct mmu_notifier *mn;
|
|
struct hlist_node *n;
|
|
int id;
|
|
|
|
id = srcu_read_lock(&srcu);
|
|
hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
|
|
if (mn->ops->invalidate_page)
|
|
mn->ops->invalidate_page(mn, mm, address);
|
|
}
|
|
srcu_read_unlock(&srcu, id);
|
|
}
|
|
|
|
void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
struct mmu_notifier *mn;
|
|
struct hlist_node *n;
|
|
int id;
|
|
|
|
id = srcu_read_lock(&srcu);
|
|
hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
|
|
if (mn->ops->invalidate_range_start)
|
|
mn->ops->invalidate_range_start(mn, mm, start, end);
|
|
}
|
|
srcu_read_unlock(&srcu, id);
|
|
}
|
|
|
|
void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
struct mmu_notifier *mn;
|
|
struct hlist_node *n;
|
|
int id;
|
|
|
|
id = srcu_read_lock(&srcu);
|
|
hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
|
|
if (mn->ops->invalidate_range_end)
|
|
mn->ops->invalidate_range_end(mn, mm, start, end);
|
|
}
|
|
srcu_read_unlock(&srcu, id);
|
|
}
|
|
|
|
static int do_mmu_notifier_register(struct mmu_notifier *mn,
|
|
struct mm_struct *mm,
|
|
int take_mmap_sem)
|
|
{
|
|
struct mmu_notifier_mm *mmu_notifier_mm;
|
|
int ret;
|
|
|
|
BUG_ON(atomic_read(&mm->mm_users) <= 0);
|
|
|
|
/*
|
|
* Verify that mmu_notifier_init() already run and the global srcu is
|
|
* initialized.
|
|
*/
|
|
BUG_ON(!srcu.per_cpu_ref);
|
|
|
|
ret = -ENOMEM;
|
|
mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
|
|
if (unlikely(!mmu_notifier_mm))
|
|
goto out;
|
|
|
|
if (take_mmap_sem)
|
|
down_write(&mm->mmap_sem);
|
|
ret = mm_take_all_locks(mm);
|
|
if (unlikely(ret))
|
|
goto out_clean;
|
|
|
|
if (!mm_has_notifiers(mm)) {
|
|
INIT_HLIST_HEAD(&mmu_notifier_mm->list);
|
|
spin_lock_init(&mmu_notifier_mm->lock);
|
|
|
|
mm->mmu_notifier_mm = mmu_notifier_mm;
|
|
mmu_notifier_mm = NULL;
|
|
}
|
|
atomic_inc(&mm->mm_count);
|
|
|
|
/*
|
|
* Serialize the update against mmu_notifier_unregister. A
|
|
* side note: mmu_notifier_release can't run concurrently with
|
|
* us because we hold the mm_users pin (either implicitly as
|
|
* current->mm or explicitly with get_task_mm() or similar).
|
|
* We can't race against any other mmu notifier method either
|
|
* thanks to mm_take_all_locks().
|
|
*/
|
|
spin_lock(&mm->mmu_notifier_mm->lock);
|
|
hlist_add_head(&mn->hlist, &mm->mmu_notifier_mm->list);
|
|
spin_unlock(&mm->mmu_notifier_mm->lock);
|
|
|
|
mm_drop_all_locks(mm);
|
|
out_clean:
|
|
if (take_mmap_sem)
|
|
up_write(&mm->mmap_sem);
|
|
kfree(mmu_notifier_mm);
|
|
out:
|
|
BUG_ON(atomic_read(&mm->mm_users) <= 0);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Must not hold mmap_sem nor any other VM related lock when calling
|
|
* this registration function. Must also ensure mm_users can't go down
|
|
* to zero while this runs to avoid races with mmu_notifier_release,
|
|
* so mm has to be current->mm or the mm should be pinned safely such
|
|
* as with get_task_mm(). If the mm is not current->mm, the mm_users
|
|
* pin should be released by calling mmput after mmu_notifier_register
|
|
* returns. mmu_notifier_unregister must be always called to
|
|
* unregister the notifier. mm_count is automatically pinned to allow
|
|
* mmu_notifier_unregister to safely run at any time later, before or
|
|
* after exit_mmap. ->release will always be called before exit_mmap
|
|
* frees the pages.
|
|
*/
|
|
int mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
|
|
{
|
|
return do_mmu_notifier_register(mn, mm, 1);
|
|
}
|
|
EXPORT_SYMBOL_GPL(mmu_notifier_register);
|
|
|
|
/*
|
|
* Same as mmu_notifier_register but here the caller must hold the
|
|
* mmap_sem in write mode.
|
|
*/
|
|
int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
|
|
{
|
|
return do_mmu_notifier_register(mn, mm, 0);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__mmu_notifier_register);
|
|
|
|
/* this is called after the last mmu_notifier_unregister() returned */
|
|
void __mmu_notifier_mm_destroy(struct mm_struct *mm)
|
|
{
|
|
BUG_ON(!hlist_empty(&mm->mmu_notifier_mm->list));
|
|
kfree(mm->mmu_notifier_mm);
|
|
mm->mmu_notifier_mm = LIST_POISON1; /* debug */
|
|
}
|
|
|
|
/*
|
|
* This releases the mm_count pin automatically and frees the mm
|
|
* structure if it was the last user of it. It serializes against
|
|
* running mmu notifiers with SRCU and against mmu_notifier_unregister
|
|
* with the unregister lock + SRCU. All sptes must be dropped before
|
|
* calling mmu_notifier_unregister. ->release or any other notifier
|
|
* method may be invoked concurrently with mmu_notifier_unregister,
|
|
* and only after mmu_notifier_unregister returned we're guaranteed
|
|
* that ->release or any other method can't run anymore.
|
|
*/
|
|
void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
|
|
{
|
|
BUG_ON(atomic_read(&mm->mm_count) <= 0);
|
|
|
|
spin_lock(&mm->mmu_notifier_mm->lock);
|
|
if (!hlist_unhashed(&mn->hlist)) {
|
|
int id;
|
|
|
|
/*
|
|
* Ensure we synchronize up with __mmu_notifier_release().
|
|
*/
|
|
id = srcu_read_lock(&srcu);
|
|
|
|
hlist_del_rcu(&mn->hlist);
|
|
spin_unlock(&mm->mmu_notifier_mm->lock);
|
|
|
|
if (mn->ops->release)
|
|
mn->ops->release(mn, mm);
|
|
|
|
/*
|
|
* Allow __mmu_notifier_release() to complete.
|
|
*/
|
|
srcu_read_unlock(&srcu, id);
|
|
} else
|
|
spin_unlock(&mm->mmu_notifier_mm->lock);
|
|
|
|
/*
|
|
* Wait for any running method to finish, including ->release() if it
|
|
* was run by __mmu_notifier_release() instead of us.
|
|
*/
|
|
synchronize_srcu(&srcu);
|
|
|
|
BUG_ON(atomic_read(&mm->mm_count) <= 0);
|
|
|
|
mmdrop(mm);
|
|
}
|
|
EXPORT_SYMBOL_GPL(mmu_notifier_unregister);
|
|
|
|
static int __init mmu_notifier_init(void)
|
|
{
|
|
return init_srcu_struct(&srcu);
|
|
}
|
|
|
|
module_init(mmu_notifier_init);
|