mm: pgtable: make ptlock be freed by RCU

If ALLOC_SPLIT_PTLOCKS is enabled, the ptdesc->ptl will be a pointer and a
ptlock will be allocated for it, and it will be freed immediately before
the PTE page is freed.  Once we support empty PTE page reclaimation, it
may result in the following use-after-free problem:

	CPU 0				CPU 1

					pte_offset_map_rw_nolock(&ptlock)
					--> rcu_read_lock()
	madvise(MADV_DONTNEED)
	--> ptlock_free (free ptlock immediately!)
	    free PTE page via RCU
					/* UAF!! */
					spin_lock(ptlock)

To avoid this problem, make ptlock also be freed by RCU.

Link: https://lkml.kernel.org/r/20241210084431.91414-1-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Reported-by: syzbot+1c58afed1cfd2f57efee@syzkaller.appspotmail.com
Tested-by: syzbot+1c58afed1cfd2f57efee@syzkaller.appspotmail.com
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Cc: Zach O'Keefe <zokeefe@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Qi Zheng 2024-12-10 16:44:31 +08:00 committed by Andrew Morton
parent 62e76fb4ff
commit f1fdbec3ff
3 changed files with 25 additions and 8 deletions

View File

@ -2925,7 +2925,7 @@ void ptlock_free(struct ptdesc *ptdesc);
static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc)
{
return ptdesc->ptl;
return &(ptdesc->ptl->ptl);
}
#else /* ALLOC_SPLIT_PTLOCKS */
static inline void ptlock_cache_init(void)

View File

@ -434,6 +434,13 @@ FOLIO_MATCH(flags, _flags_2a);
FOLIO_MATCH(compound_head, _head_2a);
#undef FOLIO_MATCH
#if ALLOC_SPLIT_PTLOCKS
struct pt_lock {
spinlock_t ptl;
struct rcu_head rcu;
};
#endif
/**
* struct ptdesc - Memory descriptor for page tables.
* @__page_flags: Same as page flags. Powerpc only.
@ -482,7 +489,7 @@ struct ptdesc {
union {
unsigned long _pt_pad_2;
#if ALLOC_SPLIT_PTLOCKS
spinlock_t *ptl;
struct pt_lock *ptl;
#else
spinlock_t ptl;
#endif

View File

@ -7013,24 +7013,34 @@ static struct kmem_cache *page_ptl_cachep;
void __init ptlock_cache_init(void)
{
page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0,
page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(struct pt_lock), 0,
SLAB_PANIC, NULL);
}
bool ptlock_alloc(struct ptdesc *ptdesc)
{
spinlock_t *ptl;
struct pt_lock *pt_lock;
ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL);
if (!ptl)
pt_lock = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL);
if (!pt_lock)
return false;
ptdesc->ptl = ptl;
ptdesc->ptl = pt_lock;
return true;
}
static void ptlock_free_rcu(struct rcu_head *head)
{
struct pt_lock *pt_lock;
pt_lock = container_of(head, struct pt_lock, rcu);
kmem_cache_free(page_ptl_cachep, pt_lock);
}
void ptlock_free(struct ptdesc *ptdesc)
{
kmem_cache_free(page_ptl_cachep, ptdesc->ptl);
struct pt_lock *pt_lock = ptdesc->ptl;
call_rcu(&pt_lock->rcu, ptlock_free_rcu);
}
#endif