[PATCH v2] mm: don't expose page to fast gup prematurely

[Yu Zhao]

We don't want to expose page to fast gup running on a remote CPU
before all local non-atomic ops on page flags are visible first.

For anon page that isn't in swap cache, we need to make sure all
prior non-atomic ops, especially __SetPageSwapBacked() in
page_add_new_anon_rmap(), are order before set_pte_at() to prevent
the following race:

	CPU 1				CPU1
set_pte_at()			get_user_pages_fast()
page_add_new_anon_rmap()		gup_pte_range()
	__SetPageSwapBacked()			SetPageReferenced()

This demonstrates a non-fatal scenario. Though I haven't directly
observed any fatal ones, they can exist, e.g., PG_lock set by fast
gup caller and then overwritten by __SetPageSwapBacked().

For anon page that is in swap cache and file page including tmpfs,
we don't need smp_wmb() before set_pte_at(). We've already exposed
them after adding them to swap and file caches. xas_lock_irq() and
xas_unlock_irq() are used during the process, which guarantees
__SetPageUptodate() and other non-atomic ops are ordered before
set_pte_at(). (Using non-atomic ops thereafter is a bug, obviously).

The smp_wmb() is open-coded rather than inserted at the bottom of
page_add_new_anon_rmap() because there is one place that calls the
function doesn't need the barrier (do_huge_pmd_wp_page_fallback()).

Alternatively, we can use atomic ops instead. There seems at least
as many __SetPageUptodate() and __SetPageSwapBacked() to change.

Signed-off-by: Yu Zhao <yuzhao@xxxxxxxxxx>
---
 kernel/events/uprobes.c |  2 ++
 mm/huge_memory.c        |  4 ++++
 mm/khugepaged.c         |  2 ++
 mm/memory.c             | 10 +++++++++-
 mm/migrate.c            |  2 ++
 mm/swapfile.c           |  6 ++++--
 mm/userfaultfd.c        |  2 ++
 7 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 84fa00497c49..7069785e2e52 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -194,6 +194,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	flush_cache_page(vma, addr, pte_pfn(*pvmw.pte));
 	ptep_clear_flush_notify(vma, addr, pvmw.pte);
+	/* commit non-atomic ops before exposing to fast gup */
+	smp_wmb();
 	set_pte_at_notify(mm, addr, pvmw.pte,
 			mk_pte(new_page, vma->vm_page_prot));
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index de1f15969e27..0be8cee94a5b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -616,6 +616,8 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 		mem_cgroup_commit_charge(page, memcg, false, true);
 		lru_cache_add_active_or_unevictable(page, vma);
 		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
+		/* commit non-atomic ops before exposing to fast gup */
+		smp_wmb();
 		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
 		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		mm_inc_nr_ptes(vma->vm_mm);
@@ -1423,6 +1425,8 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 		page_add_new_anon_rmap(new_page, vma, haddr, true);
 		mem_cgroup_commit_charge(new_page, memcg, false, true);
 		lru_cache_add_active_or_unevictable(new_page, vma);
+		/* commit non-atomic ops before exposing to fast gup */
+		smp_wmb();
 		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
 		update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
 		if (!page) {
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index eaaa21b23215..c703e4b7c9be 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1081,6 +1081,8 @@ static void collapse_huge_page(struct mm_struct *mm,
 	count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1);
 	lru_cache_add_active_or_unevictable(new_page, vma);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
+	/* commit non-atomic ops before exposing to fast gup */
+	smp_wmb();
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
 	spin_unlock(pmd_ptl);
diff --git a/mm/memory.c b/mm/memory.c
index ea3c74855b23..e56d7df0a206 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2363,6 +2363,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		 * mmu page tables (such as kvm shadow page tables), we want the
 		 * new page to be mapped directly into the secondary page table.
 		 */
+		/* commit non-atomic ops before exposing to fast gup */
+		smp_wmb();
 		set_pte_at_notify(mm, vmf->address, vmf->pte, entry);
 		update_mmu_cache(vma, vmf->address, vmf->pte);
 		if (old_page) {
@@ -2873,7 +2875,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	flush_icache_page(vma, page);
 	if (pte_swp_soft_dirty(vmf->orig_pte))
 		pte = pte_mksoft_dirty(pte);
-	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
 	arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte);
 	vmf->orig_pte = pte;
 
@@ -2882,12 +2883,15 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		page_add_new_anon_rmap(page, vma, vmf->address, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(page, vma);
+		/* commit non-atomic ops before exposing to fast gup */
+		smp_wmb();
 	} else {
 		do_page_add_anon_rmap(page, vma, vmf->address, exclusive);
 		mem_cgroup_commit_charge(page, memcg, true, false);
 		activate_page(page);
 	}
 
+	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
 	swap_free(entry);
 	if (mem_cgroup_swap_full(page) ||
 	    (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
@@ -3030,6 +3034,8 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	page_add_new_anon_rmap(page, vma, vmf->address, false);
 	mem_cgroup_commit_charge(page, memcg, false, false);
 	lru_cache_add_active_or_unevictable(page, vma);
+	/* commit non-atomic ops before exposing to fast gup */
+	smp_wmb();
 setpte:
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
 
@@ -3293,6 +3299,8 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 		page_add_new_anon_rmap(page, vma, vmf->address, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(page, vma);
+		/* commit non-atomic ops before exposing to fast gup */
+		smp_wmb();
 	} else {
 		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
 		page_add_file_rmap(page, false);
diff --git a/mm/migrate.c b/mm/migrate.c
index a42858d8e00b..ebfd58d2d606 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2689,6 +2689,8 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 		lru_cache_add_active_or_unevictable(page, vma);
 	get_page(page);
 
+	/* commit non-atomic ops before exposing to fast gup */
+	smp_wmb();
 	if (flush) {
 		flush_cache_page(vma, addr, pte_pfn(*ptep));
 		ptep_clear_flush_notify(vma, addr, ptep);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 0789a762ce2f..8e2c8ba9f793 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1880,8 +1880,6 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
 	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
 	get_page(page);
-	set_pte_at(vma->vm_mm, addr, pte,
-		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
 	if (page == swapcache) {
 		page_add_anon_rmap(page, vma, addr, false);
 		mem_cgroup_commit_charge(page, memcg, true, false);
@@ -1889,7 +1887,11 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		page_add_new_anon_rmap(page, vma, addr, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(page, vma);
+		/* commit non-atomic ops before exposing to fast gup */
+		smp_wmb();
 	}
+	set_pte_at(vma->vm_mm, addr, pte,
+		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
 	swap_free(entry);
 	/*
 	 * Move the page to the active list so it is not
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index c7ae74ce5ff3..4f92913242a1 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -92,6 +92,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 	mem_cgroup_commit_charge(page, memcg, false, false);
 	lru_cache_add_active_or_unevictable(page, dst_vma);
 
+	/* commit non-atomic ops before exposing to fast gup */
+	smp_wmb();
 	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
 
 	/* No need to invalidate - it was non-present before */
-- 
2.23.0.237.gc6a4ce50a0-goog