Skip to contentSkip to conversation

mm-fix-the-race-between-collapse-and-pt_reclaim-under-per-vma-lock.patch removed from -mm tree

merged mm-hotfixes-stable Andrew Morton 1 participant 1 message Aug 5, 2025

lore
Share & tools
lore

Andrew Morton

author tree notice Applied
#0 lore raw

The quilt patch titled
Subject: mm: fix the race between collapse and PT_RECLAIM under per-vma lock
has been removed from the -mm tree. Its filename was
mm-fix-the-race-between-collapse-and-pt_reclaim-under-per-vma-lock.patch

This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

------------------------------------------------------
From: Barry Song <[email protected]>
Subject: mm: fix the race between collapse and PT_RECLAIM under per-vma lock
Date: Tue, 5 Aug 2025 11:54:47 +0800

The check_pmd_still_valid() call during collapse is currently only protected by the mmap_lock in write mode, which was sufficient when pt_reclaim always ran under mmap_lock in read mode. However, since madvise_dontneed can now execute under a per-VMA lock, this assumption is no longer valid. As a result, a race condition can occur between collapse and PT_RECLAIM, potentially leading to a kernel panic.

 [   38.151897] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] SMP KASI
 [   38.153519] KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f]
 [   38.154605] CPU: 0 UID: 0 PID: 721 Comm: repro Not tainted 6.16.0-next-20250801-next-2025080 #1 PREEMPT(voluntary)
 [   38.155929] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org4
 [   38.157418] RIP: 0010:kasan_byte_accessible+0x15/0x30
 [   38.158125] Code: 03 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 0f 1f 00 48 b8 00 00 00 00 00 fc0
 [   38.160461] RSP: 0018:ffff88800feef678 EFLAGS: 00010286
 [   38.161220] RAX: dffffc0000000000 RBX: 0000000000000001 RCX: 1ffffffff0dde60c
 [   38.162232] RDX: 0000000000000000 RSI: ffffffff85da1e18 RDI: dffffc0000000003
 [   38.163176] RBP: ffff88800feef698 R08: 0000000000000001 R09: 0000000000000000
 [   38.164195] R10: 0000000000000000 R11: ffff888016a8ba58 R12: 0000000000000018
 [   38.165189] R13: 0000000000000018 R14: ffffffff85da1e18 R15: 0000000000000000
 [   38.166100] FS:  0000000000000000(0000) GS:ffff8880e3b40000(0000) knlGS:0000000000000000
 [   38.167137] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 [   38.167891] CR2: 00007f97fadfe504 CR3: 0000000007088005 CR4: 0000000000770ef0
 [   38.168812] PKRU: 55555554
 [   38.169275] Call Trace:
 [   38.169647]  <TASK>
 [   38.169975]  ? __kasan_check_byte+0x19/0x50
 [   38.170581]  lock_acquire+0xea/0x310
 [   38.171083]  ? rcu_is_watching+0x19/0xc0
 [   38.171615]  ? __sanitizer_cov_trace_const_cmp4+0x1a/0x20
 [   38.172343]  ? __sanitizer_cov_trace_const_cmp8+0x1c/0x30
 [   38.173130]  _raw_spin_lock+0x38/0x50
 [   38.173707]  ? __pte_offset_map_lock+0x1a2/0x3c0
 [   38.174390]  __pte_offset_map_lock+0x1a2/0x3c0
 [   38.174987]  ? __pfx___pte_offset_map_lock+0x10/0x10
 [   38.175724]  ? __pfx_pud_val+0x10/0x10
 [   38.176308]  ? __sanitizer_cov_trace_const_cmp1+0x1e/0x30
 [   38.177183]  unmap_page_range+0xb60/0x43e0
 [   38.177824]  ? __pfx_unmap_page_range+0x10/0x10
 [   38.178485]  ? mas_next_slot+0x133a/0x1a50
 [   38.179079]  unmap_single_vma.constprop.0+0x15b/0x250
 [   38.179830]  unmap_vmas+0x1fa/0x460
 [   38.180373]  ? __pfx_unmap_vmas+0x10/0x10
 [   38.180994]  ? __sanitizer_cov_trace_const_cmp4+0x1a/0x20
 [   38.181877]  exit_mmap+0x1a2/0xb40
 [   38.182396]  ? lock_release+0x14f/0x2c0
 [   38.182929]  ? __pfx_exit_mmap+0x10/0x10
 [   38.183474]  ? __pfx___mutex_unlock_slowpath+0x10/0x10
 [   38.184188]  ? mutex_unlock+0x16/0x20
 [   38.184704]  mmput+0x132/0x370
 [   38.185208]  do_exit+0x7e7/0x28c0
 [   38.185682]  ? __this_cpu_preempt_check+0x21/0x30
 [   38.186328]  ? do_group_exit+0x1d8/0x2c0
 [   38.186873]  ? __pfx_do_exit+0x10/0x10
 [   38.187401]  ? __this_cpu_preempt_check+0x21/0x30
 [   38.188036]  ? _raw_spin_unlock_irq+0x2c/0x60
 [   38.188634]  ? lockdep_hardirqs_on+0x89/0x110
 [   38.189313]  do_group_exit+0xe4/0x2c0
 [   38.189831]  __x64_sys_exit_group+0x4d/0x60
 [   38.190413]  x64_sys_call+0x2174/0x2180
 [   38.190935]  do_syscall_64+0x6d/0x2e0
 [   38.191449]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

This patch moves the vma_start_write() call to precede check_pmd_still_valid(), ensuring that the check is also properly protected by the per-VMA lock.

Fixes a6fde7add78d ("mm: use per_vma lock for MADV_DONTNEED")
Cc David Hildenbrand <[email protected]>
Cc Lorenzo Stoakes <[email protected]>
Cc Qi Zheng <[email protected]>
Cc Vlastimil Babka <[email protected]>
Cc Jann Horn <[email protected]>
Cc Suren Baghdasaryan <[email protected]>
Cc Lokesh Gidra <[email protected]>
Cc Tangquan Zheng <[email protected]>
Cc Lance Yang <[email protected]>
Cc Zi Yan <[email protected]>
Cc Baolin Wang <[email protected]>
Cc Liam R. Howlett <[email protected]>
Cc Nico Pache <[email protected]>
Cc Ryan Roberts <[email protected]>
Cc Dev Jain <[email protected]>

---

 mm/khugepaged.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
mm/khugepaged.c renamed from mm/khugepaged.c~mm-fix-the-race-between-collapse-and-pt_reclaim-under-per-vma-lock +1 -1
@@ -1172,11 +1172,11 @@ static int collapse_huge_page(struct mm_
 	if (result != SCAN_SUCCEED)
 		goto out_up_write;
 	/* check if the pmd is still valid */
+	vma_start_write(vma);
 	result = check_pmd_still_valid(mm, address, pmd);
 	if (result != SCAN_SUCCEED)
 		goto out_up_write;
 
-	vma_start_write(vma);
 	anon_vma_lock_write(vma->anon_vma);
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address,

_

Patches currently in -mm which might be from [email protected] are