Merge tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - More userfaultfs work from Peter Xu

 - Several convert-to-folios series from Sidhartha Kumar and Huang Ying

 - Some filemap cleanups from Vishal Moola

 - David Hildenbrand added the ability to selftest anon memory COW
   handling

 - Some cpuset simplifications from Liu Shixin

 - Addition of vmalloc tracing support by Uladzislau Rezki

 - Some pagecache folioifications and simplifications from Matthew
   Wilcox

 - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use
   it

 - Miguel Ojeda contributed some cleanups for our use of the
   __no_sanitize_thread__ gcc keyword.

   This series should have been in the non-MM tree, my bad

 - Naoya Horiguchi improved the interaction between memory poisoning and
   memory section removal for huge pages

 - DAMON cleanups and tuneups from SeongJae Park

 - Tony Luck fixed the handling of COW faults against poisoned pages

 - Peter Xu utilized the PTE marker code for handling swapin errors

 - Hugh Dickins reworked compound page mapcount handling, simplifying it
   and making it more efficient

 - Removal of the autonuma savedwrite infrastructure from Nadav Amit and
   David Hildenbrand

 - zram support for multiple compression streams from Sergey Senozhatsky

 - David Hildenbrand reworked the GUP code's R/O long-term pinning so
   that drivers no longer need to use the FOLL_FORCE workaround which
   didn't work very well anyway

 - Mel Gorman altered the page allocator so that local IRQs can remnain
   enabled during per-cpu page allocations

 - Vishal Moola removed the try_to_release_page() wrapper

 - Stefan Roesch added some per-BDI sysfs tunables which are used to
   prevent network block devices from dirtying excessive amounts of
   pagecache

 - David Hildenbrand did some cleanup and repair work on KSM COW
   breaking

 - Nhat Pham and Johannes Weiner have implemented writeback in zswap's
   zsmalloc backend

 - Brian Foster has fixed a longstanding corner-case oddity in
   file[map]_write_and_wait_range()

 - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang
   Chen

 - Shiyang Ruan has done some work on fsdax, to make its reflink mode
   work better under xfstests. Better, but still not perfect

 - Christoph Hellwig has removed the .writepage() method from several
   filesystems. They only need .writepages()

 - Yosry Ahmed wrote a series which fixes the memcg reclaim target
   beancounting

 - David Hildenbrand has fixed some of our MM selftests for 32-bit
   machines

 - Many singleton patches, as usual

* tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (313 commits)
  mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio
  mm: mmu_gather: allow more than one batch of delayed rmaps
  mm: fix typo in struct pglist_data code comment
  kmsan: fix memcpy tests
  mm: add cond_resched() in swapin_walk_pmd_entry()
  mm: do not show fs mm pc for VM_LOCKONFAULT pages
  selftests/vm: ksm_functional_tests: fixes for 32bit
  selftests/vm: cow: fix compile warning on 32bit
  selftests/vm: madv_populate: fix missing MADV_POPULATE_(READ|WRITE) definitions
  mm/gup_test: fix PIN_LONGTERM_TEST_READ with highmem
  mm,thp,rmap: fix races between updates of subpages_mapcount
  mm: memcg: fix swapcached stat accounting
  mm: add nodes= arg to memory.reclaim
  mm: disable top-tier fallback to reclaim on proactive reclaim
  selftests: cgroup: make sure reclaim target memcg is unprotected
  selftests: cgroup: refactor proactive reclaim code to reclaim_until()
  mm: memcg: fix stale protection of reclaim target memcg
  mm/mmap: properly unaccount memory on mas_preallocate() failure
  omfs: remove ->writepage
  jfs: remove ->writepage
  ...

1 files changed, 34 insertions, 20 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 202ec3156d04..c301487be5fb 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -237,11 +237,17 @@ static const struct inode_operations shmem_inode_operations;
 static const struct inode_operations shmem_dir_inode_operations;
 static const struct inode_operations shmem_special_inode_operations;
 static const struct vm_operations_struct shmem_vm_ops;
+static const struct vm_operations_struct shmem_anon_vm_ops;
 static struct file_system_type shmem_fs_type;
 
+bool vma_is_anon_shmem(struct vm_area_struct *vma)
+{
+	return vma->vm_ops == &shmem_anon_vm_ops;
+}
+
 bool vma_is_shmem(struct vm_area_struct *vma)
 {
-	return vma->vm_ops == &shmem_vm_ops;
+	return vma_is_anon_shmem(vma) || vma->vm_ops == &shmem_vm_ops;
 }
 
 static LIST_HEAD(shmem_swaplist);
@@ -922,21 +928,18 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 
 	folio_batch_init(&fbatch);
 	index = start;
-	while (index < end && find_lock_entries(mapping, index, end - 1,
+	while (index < end && find_lock_entries(mapping, &index, end - 1,
 			&fbatch, indices)) {
 		for (i = 0; i < folio_batch_count(&fbatch); i++) {
 			folio = fbatch.folios[i];
 
-			index = indices[i];
-
 			if (xa_is_value(folio)) {
 				if (unfalloc)
 					continue;
 				nr_swaps_freed += !shmem_free_swap(mapping,
-								index, folio);
+							indices[i], folio);
 				continue;
 			}
-			index += folio_nr_pages(folio) - 1;
 
 			if (!unfalloc || !folio_test_uptodate(folio))
 				truncate_inode_folio(mapping, folio);
@@ -945,7 +948,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		folio_batch_remove_exceptionals(&fbatch);
 		folio_batch_release(&fbatch);
 		cond_resched();
-		index++;
 	}
 
 	/*
@@ -988,7 +990,7 @@ whole_folios:
 	while (index < end) {
 		cond_resched();
 
-		if (!find_get_entries(mapping, index, end - 1, &fbatch,
+		if (!find_get_entries(mapping, &index, end - 1, &fbatch,
 				indices)) {
 			/* If all gone or hole-punch or unfalloc, we're done */
 			if (index == start || end != -1)
@@ -1000,13 +1002,12 @@ whole_folios:
 		for (i = 0; i < folio_batch_count(&fbatch); i++) {
 			folio = fbatch.folios[i];
 
-			index = indices[i];
 			if (xa_is_value(folio)) {
 				if (unfalloc)
 					continue;
-				if (shmem_free_swap(mapping, index, folio)) {
+				if (shmem_free_swap(mapping, indices[i], folio)) {
 					/* Swap was replaced by page: retry */
-					index--;
+					index = indices[i];
 					break;
 				}
 				nr_swaps_freed++;
@@ -1019,19 +1020,17 @@ whole_folios:
 				if (folio_mapping(folio) != mapping) {
 					/* Page was replaced by swap: retry */
 					folio_unlock(folio);
-					index--;
+					index = indices[i];
 					break;
 				}
 				VM_BUG_ON_FOLIO(folio_test_writeback(folio),
 						folio);
 				truncate_inode_folio(mapping, folio);
 			}
-			index = folio->index + folio_nr_pages(folio) - 1;
 			folio_unlock(folio);
 		}
 		folio_batch_remove_exceptionals(&fbatch);
 		folio_batch_release(&fbatch);
-		index++;
 	}
 
 	spin_lock_irq(&info->lock);
@@ -1700,7 +1699,7 @@ static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index,
 	swp_entry_t swapin_error;
 	void *old;
 
-	swapin_error = make_swapin_error_entry(&folio->page);
+	swapin_error = make_swapin_error_entry();
 	old = xa_cmpxchg_irq(&mapping->i_pages, index,
 			     swp_to_radix_entry(swap),
 			     swp_to_radix_entry(swapin_error), 0);
@@ -1844,7 +1843,7 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index,
 	struct shmem_sb_info *sbinfo;
 	struct mm_struct *charge_mm;
 	struct folio *folio;
-	pgoff_t hindex = index;
+	pgoff_t hindex;
 	gfp_t huge_gfp;
 	int error;
 	int once = 0;
@@ -1882,7 +1881,6 @@ repeat:
 	}
 
 	if (folio) {
-		hindex = folio->index;
 		if (sgp == SGP_WRITE)
 			folio_mark_accessed(folio);
 		if (folio_test_uptodate(folio))
@@ -2282,7 +2280,8 @@ out_nomem:
 
 static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	struct shmem_inode_info *info = SHMEM_I(file_inode(file));
+	struct inode *inode = file_inode(file);
+	struct shmem_inode_info *info = SHMEM_I(inode);
 	int ret;
 
 	ret = seal_check_future_write(info->seals, vma);
@@ -2293,7 +2292,11 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 	vma->vm_flags |= VM_MTE_ALLOWED;
 
 	file_accessed(file);
-	vma->vm_ops = &shmem_vm_ops;
+	/* This is anonymous shared memory if it is unlinked at the time of mmap */
+	if (inode->i_nlink)
+		vma->vm_ops = &shmem_vm_ops;
+	else
+		vma->vm_ops = &shmem_anon_vm_ops;
 	return 0;
 }
 
@@ -3921,6 +3924,7 @@ EXPORT_SYMBOL(shmem_aops);
 
 static const struct file_operations shmem_file_operations = {
 	.mmap		= shmem_mmap,
+	.open		= generic_file_open,
 	.get_unmapped_area = shmem_get_unmapped_area,
 #ifdef CONFIG_TMPFS
 	.llseek		= shmem_file_llseek,
@@ -4006,6 +4010,15 @@ static const struct vm_operations_struct shmem_vm_ops = {
 #endif
 };
 
+static const struct vm_operations_struct shmem_anon_vm_ops = {
+	.fault		= shmem_fault,
+	.map_pages	= filemap_map_pages,
+#ifdef CONFIG_NUMA
+	.set_policy     = shmem_set_policy,
+	.get_policy     = shmem_get_policy,
+#endif
+};
+
 int shmem_init_fs_context(struct fs_context *fc)
 {
 	struct shmem_options *ctx;
@@ -4181,6 +4194,7 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
 #define shmem_vm_ops				generic_file_vm_ops
+#define shmem_anon_vm_ops			generic_file_vm_ops
 #define shmem_file_operations			ramfs_file_operations
 #define shmem_get_inode(sb, dir, mode, dev, flags)	ramfs_get_inode(sb, dir, mode, dev)
 #define shmem_acct_size(flags, size)		0
@@ -4286,7 +4300,7 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	vma->vm_file = file;
-	vma->vm_ops = &shmem_vm_ops;
+	vma->vm_ops = &shmem_anon_vm_ops;
 
 	return 0;
 }