From 23c2fe376a7438568022845b0374c195e1db9c4e Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Mon, 9 Dec 2024 17:28:02 +0800 Subject: [PATCH] mm: pgtable: fix UAF of ptdesc->ptl The syzbot reported the following BUG: ================================================================== BUG: KASAN: slab-use-after-free in __lock_acquire+0x78/0x2100 kernel/locking/lockdep.c:5089 Read of size 8 at addr ffff888034718978 by task syz-executor352/6070 CPU: 0 UID: 0 PID: 6070 Comm: syz-executor352 Not tainted 6.13.0-rc1-next-20241205-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0x169/0x550 mm/kasan/report.c:489 kasan_report+0x143/0x180 mm/kasan/report.c:602 __lock_acquire+0x78/0x2100 kernel/locking/lockdep.c:5089 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5849 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154 spin_lock include/linux/spinlock.h:351 [inline] move_pages_pte+0x8aa/0x3400 mm/userfaultfd.c:1248 move_pages+0xe75/0x16a0 mm/userfaultfd.c:1754 userfaultfd_move fs/userfaultfd.c:1899 [inline] userfaultfd_ioctl+0x5221/0x6840 fs/userfaultfd.c:2022 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:906 [inline] __se_sys_ioctl+0xf5/0x170 fs/ioctl.c:892 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fed8de85af9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 18 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fed8de40238 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fed8df10328 RCX: 00007fed8de85af9 RDX: 0000000020000080 RSI: 00000000c028aa05 RDI: 0000000000000003 RBP: 00007fed8df10320 R08: 00007fed8de406c0 R09: 00007fed8de406c0 R10: 00007fed8de406c0 R11: 0000000000000246 R12: 00007fed8dedd334 R13: 0000000000000010 R14: 00007ffc241241e0 R15: 00007ffc241242c8 Allocated by task 6070: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 unpoison_slab_object mm/kasan/common.c:319 [inline] __kasan_slab_alloc+0x66/0x80 mm/kasan/common.c:345 kasan_slab_alloc include/linux/kasan.h:250 [inline] slab_post_alloc_hook mm/slub.c:4104 [inline] slab_alloc_node mm/slub.c:4153 [inline] kmem_cache_alloc_noprof+0x1d9/0x380 mm/slub.c:4160 ptlock_alloc+0x20/0x70 mm/memory.c:7026 ptlock_init include/linux/mm.h:2971 [inline] pagetable_pte_ctor include/linux/mm.h:2998 [inline] __pte_alloc_one_noprof include/asm-generic/pgalloc.h:73 [inline] pte_alloc_one+0xd3/0x510 arch/x86/mm/pgtable.c:41 __do_huge_pmd_anonymous_page mm/huge_memory.c:1229 [inline] do_huge_pmd_anonymous_page+0x2fb/0xb30 mm/huge_memory.c:1374 create_huge_pmd mm/memory.c:5737 [inline] __handle_mm_fault mm/memory.c:5986 [inline] handle_mm_fault+0x15a7/0x1bb0 mm/memory.c:6183 do_user_addr_fault arch/x86/mm/fault.c:1338 [inline] handle_page_fault arch/x86/mm/fault.c:1481 [inline] exc_page_fault+0x459/0x8b0 arch/x86/mm/fault.c:1539 asm_exc_page_fault+0x26/0x30 arch/x86/include/asm/idtentry.h:623 Freed by task 6071: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:576 poison_slab_object mm/kasan/common.c:247 [inline] __kasan_slab_free+0x59/0x70 mm/kasan/common.c:264 kasan_slab_free include/linux/kasan.h:233 [inline] slab_free_hook mm/slub.c:2338 [inline] slab_free mm/slub.c:4598 [inline] kmem_cache_free+0x195/0x410 mm/slub.c:4700 pagetable_pte_dtor include/linux/mm.h:3009 [inline] ___pte_free_tlb+0x2b/0x140 arch/x86/mm/pgtable.c:63 __pte_free_tlb arch/x86/include/asm/pgalloc.h:61 [inline] free_pte+0x142/0x190 mm/pt_reclaim.c:31 zap_pte_range mm/memory.c:1780 [inline] zap_pmd_range mm/memory.c:1822 [inline] zap_pud_range mm/memory.c:1851 [inline] zap_p4d_range mm/memory.c:1872 [inline] unmap_page_range+0x4062/0x48d0 mm/memory.c:1893 zap_page_range_single+0x45c/0x630 mm/memory.c:2018 madvise_dontneed_single_vma mm/madvise.c:859 [inline] madvise_dontneed_free mm/madvise.c:940 [inline] madvise_vma_behavior mm/madvise.c:1270 [inline] madvise_walk_vmas mm/madvise.c:1502 [inline] do_madvise+0x2774/0x4d90 mm/madvise.c:1689 __do_sys_madvise mm/madvise.c:1705 [inline] __se_sys_madvise mm/madvise.c:1703 [inline] __x64_sys_madvise+0xa6/0xc0 mm/madvise.c:1703 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f To fix it, free ptdesc->ptl by RCU. Reported-by: syzbot+1c58afed1cfd2f57efee@syzkaller.appspotmail.com Signed-off-by: Qi Zheng --- include/linux/mm.h | 2 +- include/linux/mm_types.h | 9 ++++++++- mm/memory.c | 22 ++++++++++++++++------ mm/userfaultfd.c | 4 ++-- 4 files changed, 27 insertions(+), 10 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 95bfaf5b85d90..b532415ef5841 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2988,7 +2988,7 @@ 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) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d0e720ccecd71..7b94ea4d0d26a 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -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. @@ -478,7 +485,7 @@ struct ptdesc { union { unsigned long _pt_pad_2; #if ALLOC_SPLIT_PTLOCKS - spinlock_t *ptl; + struct pt_lock *ptl; #else spinlock_t ptl; #endif diff --git a/mm/memory.c b/mm/memory.c index 83fd35c034d7a..802dae0602b32 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -7022,24 +7022,34 @@ 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 diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index bc9a66ec6a6e4..4527c385935be 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1185,8 +1185,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, } /* Sanity checks before the operation */ - if (WARN_ON_ONCE(pmd_none(*dst_pmd)) || WARN_ON_ONCE(pmd_none(*src_pmd)) || - WARN_ON_ONCE(pmd_trans_huge(*dst_pmd)) || WARN_ON_ONCE(pmd_trans_huge(*src_pmd))) { + if (pmd_none(*dst_pmd) || pmd_none(*src_pmd) || + pmd_trans_huge(*dst_pmd) || pmd_trans_huge(*src_pmd)) { err = -EINVAL; goto out; } -- 2.20.1