mm: pass page directly instead of using folio_page

In commit_anon_folio_batch(), we iterate over all pages pointed to by the
PTE batch.  Therefore we need to know the first page of the batch;
currently we derive that via folio_page(folio, 0), but, that takes us to
the first (head) page of the folio instead - our PTE batch may lie in the
middle of the folio, leading to incorrectness.

Bite the bullet and throw away the micro-optimization of reusing the folio
in favour of code simplicity.  Derive the page and the folio in
change_pte_range, and pass the page too to commit_anon_folio_batch to fix
the aforementioned issue.

Link: https://lkml.kernel.org/r/[email protected]
Fixes: cac1db8 ("mm: optimize mprotect() by PTE batching")
Reported-by: [email protected]
Signed-off-by: Dev Jain <[email protected]>
Reviewed-by: Lorenzo Stoakes <[email protected]>
Debugged-by: David Hildenbrand <[email protected]>
Acked-by: David Hildenbrand <[email protected]>
Cc: Anshuman Khandual <[email protected]>
Cc: Barry Song <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Christophe Leroy <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Jann Horn <[email protected]>
Cc: Joey Gouly <[email protected]>
Cc: Kevin Brodsky <[email protected]>
Cc: Lance Yang <[email protected]>
Cc: Liam Howlett <[email protected]>
Cc: Matthew Wilcox (Oracle) <[email protected]>
Cc: Peter Xu <[email protected]>
Cc: Ryan Roberts <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Yang Shi <[email protected]>
Cc: Yicong Yang <[email protected]>
Cc: Zhenhua Huang <[email protected]>
Cc: Zi Yan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: Dev Jain

mm/mprotect.c

@@ -120,9 +120,8 @@ static int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep,
 
 static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr,
 			   pte_t oldpte, pte_t *pte, int target_node,
-			   struct folio **foliop)
+			   struct folio *folio)
 {
-	struct folio *folio = NULL;
 	bool ret = true;
 	bool toptier;
 	int nid;
@@ -131,7 +130,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr,
 	if (pte_protnone(oldpte))
 		goto skip;
 
-	folio = vm_normal_folio(vma, addr, oldpte);
 	if (!folio)
 		goto skip;
 
@@ -173,7 +171,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr,
 		folio_xchg_access_time(folio, jiffies_to_msecs(jiffies));
 
 skip:
-	*foliop = folio;
 	return ret;
 }
 
@@ -231,10 +228,9 @@ static int page_anon_exclusive_sub_batch(int start_idx, int max_len,
  * retrieve sub-batches.
  */
 static void commit_anon_folio_batch(struct vm_area_struct *vma,
-		struct folio *folio, unsigned long addr, pte_t *ptep,
+		struct folio *folio, struct page *first_page, unsigned long addr, pte_t *ptep,
 		pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb)
 {
-	struct page *first_page = folio_page(folio, 0);
 	bool expected_anon_exclusive;
 	int sub_batch_idx = 0;
 	int len;
@@ -251,7 +247,7 @@ static void commit_anon_folio_batch(struct vm_area_struct *vma,
 }
 
 static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma,
-		struct folio *folio, unsigned long addr, pte_t *ptep,
+		struct folio *folio, struct page *page, unsigned long addr, pte_t *ptep,
 		pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb)
 {
 	bool set_write;
@@ -270,7 +266,7 @@ static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma,
 				       /* idx = */ 0, set_write, tlb);
 		return;
 	}
-	commit_anon_folio_batch(vma, folio, addr, ptep, oldpte, ptent, nr_ptes, tlb);
+	commit_anon_folio_batch(vma, folio, page, addr, ptep, oldpte, ptent, nr_ptes, tlb);
 }
 
 static long change_pte_range(struct mmu_gather *tlb,
@@ -305,15 +301,19 @@ static long change_pte_range(struct mmu_gather *tlb,
 			const fpb_t flags = FPB_RESPECT_SOFT_DIRTY | FPB_RESPECT_WRITE;
 			int max_nr_ptes = (end - addr) >> PAGE_SHIFT;
 			struct folio *folio = NULL;
+			struct page *page;
 			pte_t ptent;
 
+			page = vm_normal_page(vma, addr, oldpte);
+			if (page)
+				folio = page_folio(page);
 			/*
 			 * Avoid trapping faults against the zero or KSM
 			 * pages. See similar comment in change_huge_pmd.
 			 */
 			if (prot_numa) {
 				int ret = prot_numa_skip(vma, addr, oldpte, pte,
-							 target_node, &folio);
+							 target_node, folio);
 				if (ret) {
 
 					/* determine batch to skip */
@@ -323,9 +323,6 @@ static long change_pte_range(struct mmu_gather *tlb,
 				}
 			}
 
-			if (!folio)
-				folio = vm_normal_folio(vma, addr, oldpte);
-
 			nr_ptes = mprotect_folio_pte_batch(folio, pte, oldpte, max_nr_ptes, flags);
 
 			oldpte = modify_prot_start_ptes(vma, addr, pte, nr_ptes);
@@ -351,7 +348,7 @@ static long change_pte_range(struct mmu_gather *tlb,
 			 */
 			if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) &&
 			     !pte_write(ptent))
-				set_write_prot_commit_flush_ptes(vma, folio,
+				set_write_prot_commit_flush_ptes(vma, folio, page,
 				addr, pte, oldpte, ptent, nr_ptes, tlb);
 			else
 				prot_commit_flush_ptes(vma, addr, pte, oldpte, ptent,