Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...

5 files changed, 32 insertions, 16 deletions

diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index b68f47541169..a6935af2235c 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -453,3 +453,4 @@
 448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
 449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
 450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
+451  common	cachestat		sys_cachestat			sys_cachestat
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index cb2ee06df286..3c62d1b218b1 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -294,6 +294,8 @@ again:
 
 	rc = -ENXIO;
 	ptep = get_locked_pte(gmap->mm, uaddr, &ptelock);
+	if (!ptep)
+		goto out;
 	if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) {
 		page = pte_page(*ptep);
 		rc = -EAGAIN;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index da6dac36e959..9bd0a873f3b1 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2777,7 +2777,7 @@ static struct page *get_map_page(struct kvm *kvm, u64 uaddr)
 
 	mmap_read_lock(kvm->mm);
 	get_user_pages_remote(kvm->mm, uaddr, 1, FOLL_WRITE,
-			      &page, NULL, NULL);
+			      &page, NULL);
 	mmap_read_unlock(kvm->mm);
 	return page;
 }
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index dc90d1eb0d55..f4b6fc746fce 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -895,12 +895,12 @@ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr,
 
 /**
  * gmap_pte_op_end - release the page table lock
- * @ptl: pointer to the spinlock pointer
+ * @ptep: pointer to the locked pte
+ * @ptl: pointer to the page table spinlock
  */
-static void gmap_pte_op_end(spinlock_t *ptl)
+static void gmap_pte_op_end(pte_t *ptep, spinlock_t *ptl)
 {
-	if (ptl)
-		spin_unlock(ptl);
+	pte_unmap_unlock(ptep, ptl);
 }
 
 /**
@@ -1011,7 +1011,7 @@ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
 {
 	int rc;
 	pte_t *ptep;
-	spinlock_t *ptl = NULL;
+	spinlock_t *ptl;
 	unsigned long pbits = 0;
 
 	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
@@ -1025,7 +1025,7 @@ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
 	pbits |= (bits & GMAP_NOTIFY_SHADOW) ? PGSTE_VSIE_BIT : 0;
 	/* Protect and unlock. */
 	rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, pbits);
-	gmap_pte_op_end(ptl);
+	gmap_pte_op_end(ptep, ptl);
 	return rc;
 }
 
@@ -1154,7 +1154,7 @@ int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val)
 				/* Do *NOT* clear the _PAGE_INVALID bit! */
 				rc = 0;
 			}
-			gmap_pte_op_end(ptl);
+			gmap_pte_op_end(ptep, ptl);
 		}
 		if (!rc)
 			break;
@@ -1248,7 +1248,7 @@ static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr,
 			if (!rc)
 				gmap_insert_rmap(sg, vmaddr, rmap);
 			spin_unlock(&sg->guest_table_lock);
-			gmap_pte_op_end(ptl);
+			gmap_pte_op_end(ptep, ptl);
 		}
 		radix_tree_preload_end();
 		if (rc) {
@@ -2156,7 +2156,7 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte)
 			tptep = (pte_t *) gmap_table_walk(sg, saddr, 0);
 			if (!tptep) {
 				spin_unlock(&sg->guest_table_lock);
-				gmap_pte_op_end(ptl);
+				gmap_pte_op_end(sptep, ptl);
 				radix_tree_preload_end();
 				break;
 			}
@@ -2167,7 +2167,7 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte)
 				rmap = NULL;
 				rc = 0;
 			}
-			gmap_pte_op_end(ptl);
+			gmap_pte_op_end(sptep, ptl);
 			spin_unlock(&sg->guest_table_lock);
 		}
 		radix_tree_preload_end();
@@ -2495,7 +2495,7 @@ void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4],
 				continue;
 			if (ptep_test_and_clear_uc(gmap->mm, vmaddr, ptep))
 				set_bit(i, bitmap);
-			spin_unlock(ptl);
+			pte_unmap_unlock(ptep, ptl);
 		}
 	}
 	gmap_pmd_op_end(gmap, pmdp);
@@ -2537,7 +2537,12 @@ static inline void thp_split_mm(struct mm_struct *mm)
  * Remove all empty zero pages from the mapping for lazy refaulting
  * - This must be called after mm->context.has_pgste is set, to avoid
  *   future creation of zero pages
- * - This must be called after THP was enabled
+ * - This must be called after THP was disabled.
+ *
+ * mm contracts with s390, that even if mm were to remove a page table,
+ * racing with the loop below and so causing pte_offset_map_lock() to fail,
+ * it will never insert a page table containing empty zero pages once
+ * mm_forbids_zeropage(mm) i.e. mm->context.has_pgste is set.
  */
 static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
 			   unsigned long end, struct mm_walk *walk)
@@ -2549,6 +2554,8 @@ static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
 		spinlock_t *ptl;
 
 		ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+		if (!ptep)
+			break;
 		if (is_zero_pfn(pte_pfn(*ptep)))
 			ptep_xchg_direct(walk->mm, addr, ptep, __pte(_PAGE_INVALID));
 		pte_unmap_unlock(ptep, ptl);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 6effb24de6d9..3bd2ab2a9a34 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -829,7 +829,7 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	default:
 		return -EFAULT;
 	}
-
+again:
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
@@ -850,6 +850,8 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	spin_unlock(ptl);
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!ptep)
+		goto again;
 	new = old = pgste_get_lock(ptep);
 	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
 			    PGSTE_ACC_BITS | PGSTE_FP_BIT);
@@ -938,7 +940,7 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 	default:
 		return -EFAULT;
 	}
-
+again:
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
@@ -955,6 +957,8 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 	spin_unlock(ptl);
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!ptep)
+		goto again;
 	new = old = pgste_get_lock(ptep);
 	/* Reset guest reference bit only */
 	pgste_val(new) &= ~PGSTE_GR_BIT;
@@ -1000,7 +1004,7 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	default:
 		return -EFAULT;
 	}
-
+again:
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
@@ -1017,6 +1021,8 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	spin_unlock(ptl);
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!ptep)
+		goto again;
 	pgste = pgste_get_lock(ptep);
 	*key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
 	paddr = pte_val(*ptep) & PAGE_MASK;