mm/hugetlb: introduce hugetlb_walk()

huge_pte_offset() is the main walker function for hugetlb pgtables.  The
name is not really representing what it does, though.

Instead of renaming it, introduce a wrapper function called hugetlb_walk()
which will use huge_pte_offset() inside.  Assert on the locks when walking
the pgtable.

Note, the vma lock assertion will be a no-op for private mappings.

Document the last special case in the page_vma_mapped_walk() path where we
don't need any more lock to call hugetlb_walk().

Taking vma lock there is not needed because either: (1) potential callers
of hugetlb pvmw holds i_mmap_rwsem already (from one rmap_walk()), or (2)
the caller will not walk a hugetlb vma at all so the hugetlb code path not
reachable (e.g.  in ksm or uprobe paths).

It's slightly implicit for future page_vma_mapped_walk() callers on that
lock requirement.  But anyway, when one day this rule breaks, one will get
a straightforward warning in hugetlb_walk() with lockdep, then there'll be
a way out.

[akpm@linux-foundation.org: coding-style cleanups]
Link: https://lkml.kernel.org/r/20221216155229.2043750-1-peterx@redhat.comSigned-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: James Houghton <jthoughton@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

fs/hugetlbfs/inode.c

@@ -388,9 +388,7 @@ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma,
 {
 	pte_t *ptep, pte;
 
-	ptep = huge_pte_offset(vma->vm_mm, addr,
-			huge_page_size(hstate_vma(vma)));
-
+	ptep = hugetlb_walk(vma, addr, huge_page_size(hstate_vma(vma)));
 	if (!ptep)
 		return false;
 

fs/userfaultfd.c

@@ -252,14 +252,12 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
 					 unsigned long flags,
 					 unsigned long reason)
 {
-	struct mm_struct *mm = ctx->mm;
 	pte_t *ptep, pte;
 	bool ret = true;
 
-	mmap_assert_locked(mm);
-
-	ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
+	mmap_assert_locked(ctx->mm);
 
+	ptep = hugetlb_walk(vma, address, vma_mmu_pagesize(vma));
 	if (!ptep)
 		goto out;
 

include/linux/hugetlb.h

@@ -2,6 +2,7 @@
 #ifndef _LINUX_HUGETLB_H
 #define _LINUX_HUGETLB_H
 
+#include <linux/mm.h>
 #include <linux/mm_types.h>
 #include <linux/mmdebug.h>
 #include <linux/fs.h>
@@ -196,6 +197,11 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
  * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE.
  * Returns the pte_t* if found, or NULL if the address is not mapped.
  *
+ * IMPORTANT: we should normally not directly call this function, instead
+ * this is only a common interface to implement arch-specific
+ * walker. Please use hugetlb_walk() instead, because that will attempt to
+ * verify the locking for you.
+ *
  * Since this function will walk all the pgtable pages (including not only
  * high-level pgtable page, but also PUD entry that can be unshared
  * concurrently for VM_SHARED), the caller of this function should be
@@ -1229,4 +1235,35 @@ bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr);
 #define flush_hugetlb_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
 #endif
 
+static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
+{
+	return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
+}
+
+/*
+ * Safe version of huge_pte_offset() to check the locks.  See comments
+ * above huge_pte_offset().
+ */
+static inline pte_t *
+hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz)
+{
+#if defined(CONFIG_HUGETLB_PAGE) && \
+	defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && defined(CONFIG_LOCKDEP)
+	struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
+
+	/*
+	 * If pmd sharing possible, locking needed to safely walk the
+	 * hugetlb pgtables.  More information can be found at the comment
+	 * above huge_pte_offset() in the same file.
+	 *
+	 * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP.
+	 */
+	if (__vma_shareable_lock(vma))
+		WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) &&
+			     !lockdep_is_held(
+				 &vma->vm_file->f_mapping->i_mmap_rwsem));
+#endif
+	return huge_pte_offset(vma->vm_mm, addr, sz);
+}
+
 #endif /* _LINUX_HUGETLB_H */

mm/hugetlb.c

@@ -260,11 +260,6 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
 /*
  * hugetlb vma_lock helper routines
  */
-static bool __vma_shareable_lock(struct vm_area_struct *vma)
-{
-	return vma->vm_flags & VM_MAYSHARE && vma->vm_private_data;
-}
-
 void hugetlb_vma_lock_read(struct vm_area_struct *vma)
 {
 	if (__vma_shareable_lock(vma)) {
@@ -4980,7 +4975,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	} else {
 		/*
 		 * For shared mappings the vma lock must be held before
-		 * calling huge_pte_offset in the src vma. Otherwise, the
+		 * calling hugetlb_walk() in the src vma. Otherwise, the
 		 * returned ptep could go away if part of a shared pmd and
 		 * another thread calls huge_pmd_unshare.
 		 */
@@ -4990,7 +4985,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	last_addr_mask = hugetlb_mask_last_page(h);
 	for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) {
 		spinlock_t *src_ptl, *dst_ptl;
-		src_pte = huge_pte_offset(src, addr, sz);
+		src_pte = hugetlb_walk(src_vma, addr, sz);
 		if (!src_pte) {
 			addr |= last_addr_mask;
 			continue;
@@ -5197,7 +5192,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 	hugetlb_vma_lock_write(vma);
 	i_mmap_lock_write(mapping);
 	for (; old_addr < old_end; old_addr += sz, new_addr += sz) {
-		src_pte = huge_pte_offset(mm, old_addr, sz);
+		src_pte = hugetlb_walk(vma, old_addr, sz);
 		if (!src_pte) {
 			old_addr |= last_addr_mask;
 			new_addr |= last_addr_mask;
@@ -5260,7 +5255,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 	last_addr_mask = hugetlb_mask_last_page(h);
 	address = start;
 	for (; address < end; address += sz) {
-		ptep = huge_pte_offset(mm, address, sz);
+		ptep = hugetlb_walk(vma, address, sz);
 		if (!ptep) {
 			address |= last_addr_mask;
 			continue;
@@ -5573,7 +5568,7 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 			hugetlb_vma_lock_read(vma);
 			spin_lock(ptl);
-			ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
+			ptep = hugetlb_walk(vma, haddr, huge_page_size(h));
 			if (likely(ptep &&
 				   pte_same(huge_ptep_get(ptep), pte)))
 				goto retry_avoidcopy;
@@ -5611,7 +5606,7 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * before the page tables are altered
 	 */
 	spin_lock(ptl);
-	ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
+	ptep = hugetlb_walk(vma, haddr, huge_page_size(h));
 	if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) {
 		/* Break COW or unshare */
 		huge_ptep_clear_flush(vma, haddr, ptep);
@@ -6397,7 +6392,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
 		return NULL;
 
 	hugetlb_vma_lock_read(vma);
-	pte = huge_pte_offset(mm, haddr, huge_page_size(h));
+	pte = hugetlb_walk(vma, haddr, huge_page_size(h));
 	if (!pte)
 		goto out_unlock;
 
@@ -6462,8 +6457,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 *
 		 * Note that page table lock is not held when pte is null.
 		 */
-		pte = huge_pte_offset(mm, vaddr & huge_page_mask(h),
-				      huge_page_size(h));
+		pte = hugetlb_walk(vma, vaddr & huge_page_mask(h),
+				   huge_page_size(h));
 		if (pte)
 			ptl = huge_pte_lock(h, mm, pte);
 		absent = !pte || huge_pte_none(huge_ptep_get(pte));
@@ -6654,7 +6649,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	last_addr_mask = hugetlb_mask_last_page(h);
 	for (; address < end; address += psize) {
 		spinlock_t *ptl;
-		ptep = huge_pte_offset(mm, address, psize);
+		ptep = hugetlb_walk(vma, address, psize);
 		if (!ptep) {
 			if (!uffd_wp) {
 				address |= last_addr_mask;
@@ -7064,8 +7059,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
 
 		saddr = page_table_shareable(svma, vma, addr, idx);
 		if (saddr) {
-			spte = huge_pte_offset(svma->vm_mm, saddr,
-					       vma_mmu_pagesize(svma));
+			spte = hugetlb_walk(svma, saddr,
+					    vma_mmu_pagesize(svma));
 			if (spte) {
 				get_page(virt_to_page(spte));
 				break;
@@ -7377,7 +7372,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 	hugetlb_vma_lock_write(vma);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
 	for (address = start; address < end; address += PUD_SIZE) {
-		ptep = huge_pte_offset(mm, address, sz);
+		ptep = hugetlb_walk(vma, address, sz);
 		if (!ptep)
 			continue;
 		ptl = huge_pte_lock(h, mm, ptep);

mm/page_vma_mapped.c

@@ -168,9 +168,12 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 		/* The only possible mapping was handled on last iteration */
 		if (pvmw->pte)
 			return not_found(pvmw);
-
-		/* when pud is not present, pte will be NULL */
-		pvmw->pte = huge_pte_offset(mm, pvmw->address, size);
+		/*
+		 * All callers that get here will already hold the
+		 * i_mmap_rwsem.  Therefore, no additional locks need to be
+		 * taken before calling hugetlb_walk().
+		 */
+		pvmw->pte = hugetlb_walk(vma, pvmw->address, size);
 		if (!pvmw->pte)
 			return false;
 

mm/pagewalk.c

@@ -305,13 +305,11 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end,
 	hugetlb_vma_lock_read(vma);
 	do {
 		next = hugetlb_entry_end(h, addr, end);
-		pte = huge_pte_offset(walk->mm, addr & hmask, sz);
-
+		pte = hugetlb_walk(vma, addr & hmask, sz);
 		if (pte)
 			err = ops->hugetlb_entry(pte, hmask, addr, next, walk);
 		else if (ops->pte_hole)
 			err = ops->pte_hole(addr, next, -1, walk);
-
 		if (err)
 			break;
 	} while (addr = next, addr != end);