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, 38 insertions, 23 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index d03e149ffe6e..a56a6d17e201 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -95,9 +95,6 @@ struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma)
 {
 	mmap_assert_locked(vma->vm_mm);
 
-	if (vma->vm_file)
-		return NULL;
-
 	return vma->anon_name;
 }
 
@@ -183,7 +180,7 @@ success:
 	 * vm_flags is protected by the mmap_lock held in write mode.
 	 */
 	vma->vm_flags = new_flags;
-	if (!vma->vm_file) {
+	if (!vma->vm_file || vma_is_anon_shmem(vma)) {
 		error = replace_anon_vma_name(vma, anon_name);
 		if (error)
 			return error;
@@ -226,6 +223,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 			put_page(page);
 	}
 	swap_read_unplug(splug);
+	cond_resched();
 
 	return 0;
 }
@@ -321,6 +319,21 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	return 0;
 }
 
+static inline bool can_do_file_pageout(struct vm_area_struct *vma)
+{
+	if (!vma->vm_file)
+		return false;
+	/*
+	 * paging out pagecache only for non-anonymous mappings that correspond
+	 * to the files the calling process could (if tried) open for writing;
+	 * otherwise we'd be including shared non-exclusive mappings, which
+	 * opens a side channel.
+	 */
+	return inode_owner_or_capable(&init_user_ns,
+				      file_inode(vma->vm_file)) ||
+	       file_permission(vma->vm_file, MAY_WRITE) == 0;
+}
+
 static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 				unsigned long addr, unsigned long end,
 				struct mm_walk *walk)
@@ -334,10 +347,14 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 	spinlock_t *ptl;
 	struct page *page = NULL;
 	LIST_HEAD(page_list);
+	bool pageout_anon_only_filter;
 
 	if (fatal_signal_pending(current))
 		return -EINTR;
 
+	pageout_anon_only_filter = pageout && !vma_is_anonymous(vma) &&
+					!can_do_file_pageout(vma);
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	if (pmd_trans_huge(*pmd)) {
 		pmd_t orig_pmd;
@@ -364,6 +381,9 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 		if (page_mapcount(page) != 1)
 			goto huge_unlock;
 
+		if (pageout_anon_only_filter && !PageAnon(page))
+			goto huge_unlock;
+
 		if (next - addr != HPAGE_PMD_SIZE) {
 			int err;
 
@@ -432,6 +452,8 @@ regular_page:
 		if (PageTransCompound(page)) {
 			if (page_mapcount(page) != 1)
 				break;
+			if (pageout_anon_only_filter && !PageAnon(page))
+				break;
 			get_page(page);
 			if (!trylock_page(page)) {
 				put_page(page);
@@ -459,6 +481,9 @@ regular_page:
 		if (!PageLRU(page) || page_mapcount(page) != 1)
 			continue;
 
+		if (pageout_anon_only_filter && !PageAnon(page))
+			continue;
+
 		VM_BUG_ON_PAGE(PageTransCompound(page), page);
 
 		if (pte_young(ptent)) {
@@ -553,23 +578,6 @@ static void madvise_pageout_page_range(struct mmu_gather *tlb,
 	tlb_end_vma(tlb, vma);
 }
 
-static inline bool can_do_pageout(struct vm_area_struct *vma)
-{
-	if (vma_is_anonymous(vma))
-		return true;
-	if (!vma->vm_file)
-		return false;
-	/*
-	 * paging out pagecache only for non-anonymous mappings that correspond
-	 * to the files the calling process could (if tried) open for writing;
-	 * otherwise we'd be including shared non-exclusive mappings, which
-	 * opens a side channel.
-	 */
-	return inode_owner_or_capable(&init_user_ns,
-				      file_inode(vma->vm_file)) ||
-	       file_permission(vma->vm_file, MAY_WRITE) == 0;
-}
-
 static long madvise_pageout(struct vm_area_struct *vma,
 			struct vm_area_struct **prev,
 			unsigned long start_addr, unsigned long end_addr)
@@ -581,7 +589,14 @@ static long madvise_pageout(struct vm_area_struct *vma,
 	if (!can_madv_lru_vma(vma))
 		return -EINVAL;
 
-	if (!can_do_pageout(vma))
+	/*
+	 * If the VMA belongs to a private file mapping, there can be private
+	 * dirty pages which can be paged out if even this process is neither
+	 * owner nor write capable of the file. We allow private file mappings
+	 * further to pageout dirty anon pages.
+	 */
+	if (!vma_is_anonymous(vma) && (!can_do_file_pageout(vma) &&
+				(vma->vm_flags & VM_MAYSHARE)))
 		return 0;
 
 	lru_add_drain();
@@ -1273,7 +1288,7 @@ static int madvise_vma_anon_name(struct vm_area_struct *vma,
 	int error;
 
 	/* Only anonymous mappings can be named */
-	if (vma->vm_file)
+	if (vma->vm_file && !vma_is_anon_shmem(vma))
 		return -EBADF;
 
 	error = madvise_update_vma(vma, prev, start, end, vma->vm_flags,