[3.11.y.z,extended,stable] Patch "mm: numa: serialise parallel get_user_page against THP migration" has been added to staging queue

diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index dd74e46..0596e8e 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -83,6 +83,12 @@  static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		pte_t pte = gup_get_pte(ptep);
 		struct page *page;

+		/* Similar to the PMD case, NUMA hinting must take slow path */
+		if (pte_numa(pte)) {
+			pte_unmap(ptep);
+			return 0;
+		}
+
 		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
 			pte_unmap(ptep);
 			return 0;
@@ -167,6 +173,13 @@  static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd))) {
+			/*
+			 * NUMA hinting faults need to be handled in the GUP
+			 * slowpath for accounting purposes and so that they
+			 * can be serialised against THP migration.
+			 */
+			if (pmd_numa(pmd))
+				return 0;
 			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
 				return 0;
 		} else {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 12acb0b..72da10d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1252,6 +1252,10 @@  struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
 		return ERR_PTR(-EFAULT);

+	/* Full NUMA hinting faults to serialise migration in fault paths */
+	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+		goto out;
+
 	page = pmd_page(*pmd);
 	VM_BUG_ON(!PageHead(page));
 	if (flags & FOLL_TOUCH) {
@@ -1318,23 +1322,27 @@  int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* If the page was locked, there are no parallel migrations */
 		if (page_locked)
 			goto clear_pmdnuma;
+	}

-		/*
-		 * Otherwise wait for potential migrations and retry. We do
-		 * relock and check_same as the page may no longer be mapped.
-		 * As the fault is being retried, do not account for it.
-		 */
+	/*
+	 * If there are potential migrations, wait for completion and retry. We
+	 * do not relock and check_same as the page may no longer be mapped.
+	 * Furtermore, even if the page is currently misplaced, there is no
+	 * guarantee it is still misplaced after the migration completes.
+	 */
+	if (!page_locked) {
 		spin_unlock(&mm->page_table_lock);
 		wait_on_page_locked(page);
 		page_nid = -1;
 		goto out;
 	}

-	/* Page is misplaced, serialise migrations and parallel THP splits */
+	/*
+	 * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
+	 * to serialises splits
+	 */
 	get_page(page);
 	spin_unlock(&mm->page_table_lock);
-	if (!page_locked)
-		lock_page(page);
 	anon_vma = page_lock_anon_vma_read(page);

 	/* Confirm the PTE did not while locked */
diff --git a/mm/migrate.c b/mm/migrate.c
index d22f6f0..b3ffb81 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1658,6 +1658,7 @@  int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	struct page *new_page = NULL;
 	struct mem_cgroup *memcg = NULL;
 	int page_lru = page_is_file_cache(page);
+	pmd_t orig_entry;

 	/*
 	 * Don't migrate pages that are mapped in multiple processes.
@@ -1699,7 +1700,8 @@  int migrate_misplaced_transhuge_page(struct mm_struct *mm,

 	/* Recheck the target PMD */
 	spin_lock(&mm->page_table_lock);
-	if (unlikely(!pmd_same(*pmd, entry))) {
+	if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) {
+fail_putback:
 		spin_unlock(&mm->page_table_lock);

 		/* Reverse changes made by migrate_page_copy() */
@@ -1729,16 +1731,34 @@  int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	 */
 	mem_cgroup_prepare_migration(page, new_page, &memcg);

+	orig_entry = *pmd;
 	entry = mk_pmd(new_page, vma->vm_page_prot);
-	entry = pmd_mknonnuma(entry);
-	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 	entry = pmd_mkhuge(entry);
+	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);

+	/*
+	 * Clear the old entry under pagetable lock and establish the new PTE.
+	 * Any parallel GUP will either observe the old page blocking on the
+	 * page lock, block on the page table lock or observe the new page.
+	 * The SetPageUptodate on the new page and page_add_new_anon_rmap
+	 * guarantee the copy is visible before the pagetable update.
+	 */
+	flush_cache_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+	page_add_new_anon_rmap(new_page, vma, haddr);
 	pmdp_clear_flush(vma, haddr, pmd);
 	set_pmd_at(mm, haddr, pmd, entry);
-	page_add_new_anon_rmap(new_page, vma, haddr);
 	update_mmu_cache_pmd(vma, address, &entry);
+
+	if (page_count(page) != 2) {
+		set_pmd_at(mm, haddr, pmd, orig_entry);
+		flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+		update_mmu_cache_pmd(vma, address, &entry);
+		page_remove_rmap(new_page);
+		goto fail_putback;
+	}
+
 	page_remove_rmap(page);
+
 	/*
 	 * Finish the charge transaction under the page table lock to
 	 * prevent split_huge_page() from dividing up the charge
@@ -1763,9 +1783,13 @@  int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 out_fail:
 	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 out_dropref:
-	entry = pmd_mknonnuma(entry);
-	set_pmd_at(mm, haddr, pmd, entry);
-	update_mmu_cache_pmd(vma, address, &entry);
+	spin_lock(&mm->page_table_lock);
+	if (pmd_same(*pmd, entry)) {
+		entry = pmd_mknonnuma(entry);
+		set_pmd_at(mm, haddr, pmd, entry);
+		update_mmu_cache_pmd(vma, address, &entry);
+	}
+	spin_unlock(&mm->page_table_lock);

 	unlock_page(page);
 	put_page(page);