mm: close theoretical race where stale TLB entries could linger

Commit 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a
parallel reclaim leaving stale TLB entries") described a theoretical race
as such:

"""
Nadav Amit identified a theoretical race between page reclaim and mprotect
due to TLB flushes being batched outside of the PTL being held.

He described the race as follows:

	CPU0                            CPU1
	----                            ----
					user accesses memory using RW PTE
					[PTE now cached in TLB]
	try_to_unmap_one()
	==> ptep_get_and_clear()
	==> set_tlb_ubc_flush_pending()
					mprotect(addr, PROT_READ)
					==> change_pte_range()
					==> [ PTE non-present - no flush ]

					user writes using cached RW PTE
	...

	try_to_unmap_flush()

The same type of race exists for reads when protecting for PROT_NONE and
also exists for operations that can leave an old TLB entry behind such as
munmap, mremap and madvise.
"""

The solution was to introduce flush_tlb_batched_pending() and call it
under the PTL from mprotect/madvise/munmap/mremap to complete any pending
tlb flushes.

However, while madvise_free_pte_range() and
madvise_cold_or_pageout_pte_range() were both retro-fitted to call
flush_tlb_batched_pending() immediately after initially acquiring the PTL,
they both temporarily release the PTL to split a large folio if they
stumble upon one.  In this case, where re-acquiring the PTL
flush_tlb_batched_pending() must be called again, but it previously was
not.  Let's fix that.

There are 2 Fixes: tags here: the first is the commit that fixed
madvise_free_pte_range().  The second is the commit that added
madvise_cold_or_pageout_pte_range(), which looks like it copy/pasted the
faulty pattern from madvise_free_pte_range().

This is a theoretical bug discovered during code review.

Link: https://lkml.kernel.org/r/20250606092809.4194056-1-ryan.roberts@arm.com
Fixes: 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries")
Fixes: 9c276cc65a58 ("mm: introduce MADV_COLD")
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Jann Horn <jannh@google.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Mel Gorman <mgorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/madvise.c b/mm/madvise.c
index 5f7a66a1617e39e3a9c133990fcdebd13e1fe654..1d44a35ae85cf104c1c34fdd800ba6723491bda1 100644 (file)
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -508,6 +508,7 @@ restart:
                                        pte_offset_map_lock(mm, pmd, addr, &ptl);
                                if (!start_pte)
                                        break;
+                               flush_tlb_batched_pending(mm);
                                arch_enter_lazy_mmu_mode();
                                if (!err)
                                        nr = 0;
@@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
                                start_pte = pte;
                                if (!start_pte)
                                        break;
+                               flush_tlb_batched_pending(mm);
                                arch_enter_lazy_mmu_mode();
                                if (!err)
                                        nr = 0;