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, 51 insertions, 204 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 98aac6201e1b..f212d571b563 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -545,42 +545,13 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
 			 (FOLL_PIN | FOLL_GET)))
 		return ERR_PTR(-EINVAL);
-
-	/*
-	 * Considering PTE level hugetlb, like continuous-PTE hugetlb on
-	 * ARM64 architecture.
-	 */
-	if (is_vm_hugetlb_page(vma)) {
-		page = follow_huge_pmd_pte(vma, address, flags);
-		if (page)
-			return page;
-		return no_page_table(vma, flags);
-	}
-
-retry:
 	if (unlikely(pmd_bad(*pmd)))
 		return no_page_table(vma, flags);
 
 	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
 	pte = *ptep;
-	if (!pte_present(pte)) {
-		swp_entry_t entry;
-		/*
-		 * KSM's break_ksm() relies upon recognizing a ksm page
-		 * even while it is being migrated, so for that case we
-		 * need migration_entry_wait().
-		 */
-		if (likely(!(flags & FOLL_MIGRATION)))
-			goto no_page;
-		if (pte_none(pte))
-			goto no_page;
-		entry = pte_to_swp_entry(pte);
-		if (!is_migration_entry(entry))
-			goto no_page;
-		pte_unmap_unlock(ptep, ptl);
-		migration_entry_wait(mm, pmd, address);
-		goto retry;
-	}
+	if (!pte_present(pte))
+		goto no_page;
 	if (pte_protnone(pte) && !gup_can_follow_protnone(flags))
 		goto no_page;
 
@@ -623,7 +594,7 @@ retry:
 		}
 	}
 
-	if (!pte_write(pte) && gup_must_unshare(flags, page)) {
+	if (!pte_write(pte) && gup_must_unshare(vma, flags, page)) {
 		page = ERR_PTR(-EMLINK);
 		goto out;
 	}
@@ -690,42 +661,8 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	pmdval = READ_ONCE(*pmd);
 	if (pmd_none(pmdval))
 		return no_page_table(vma, flags);
-	if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) {
-		page = follow_huge_pmd_pte(vma, address, flags);
-		if (page)
-			return page;
+	if (!pmd_present(pmdval))
 		return no_page_table(vma, flags);
-	}
-	if (is_hugepd(__hugepd(pmd_val(pmdval)))) {
-		page = follow_huge_pd(vma, address,
-				      __hugepd(pmd_val(pmdval)), flags,
-				      PMD_SHIFT);
-		if (page)
-			return page;
-		return no_page_table(vma, flags);
-	}
-retry:
-	if (!pmd_present(pmdval)) {
-		/*
-		 * Should never reach here, if thp migration is not supported;
-		 * Otherwise, it must be a thp migration entry.
-		 */
-		VM_BUG_ON(!thp_migration_supported() ||
-				  !is_pmd_migration_entry(pmdval));
-
-		if (likely(!(flags & FOLL_MIGRATION)))
-			return no_page_table(vma, flags);
-
-		pmd_migration_entry_wait(mm, pmd);
-		pmdval = READ_ONCE(*pmd);
-		/*
-		 * MADV_DONTNEED may convert the pmd to null because
-		 * mmap_lock is held in read mode
-		 */
-		if (pmd_none(pmdval))
-			return no_page_table(vma, flags);
-		goto retry;
-	}
 	if (pmd_devmap(pmdval)) {
 		ptl = pmd_lock(mm, pmd);
 		page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
@@ -739,18 +676,10 @@ retry:
 	if (pmd_protnone(pmdval) && !gup_can_follow_protnone(flags))
 		return no_page_table(vma, flags);
 
-retry_locked:
 	ptl = pmd_lock(mm, pmd);
-	if (unlikely(pmd_none(*pmd))) {
-		spin_unlock(ptl);
-		return no_page_table(vma, flags);
-	}
 	if (unlikely(!pmd_present(*pmd))) {
 		spin_unlock(ptl);
-		if (likely(!(flags & FOLL_MIGRATION)))
-			return no_page_table(vma, flags);
-		pmd_migration_entry_wait(mm, pmd);
-		goto retry_locked;
+		return no_page_table(vma, flags);
 	}
 	if (unlikely(!pmd_trans_huge(*pmd))) {
 		spin_unlock(ptl);
@@ -793,20 +722,6 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 	pud = pud_offset(p4dp, address);
 	if (pud_none(*pud))
 		return no_page_table(vma, flags);
-	if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) {
-		page = follow_huge_pud(mm, address, pud, flags);
-		if (page)
-			return page;
-		return no_page_table(vma, flags);
-	}
-	if (is_hugepd(__hugepd(pud_val(*pud)))) {
-		page = follow_huge_pd(vma, address,
-				      __hugepd(pud_val(*pud)), flags,
-				      PUD_SHIFT);
-		if (page)
-			return page;
-		return no_page_table(vma, flags);
-	}
 	if (pud_devmap(*pud)) {
 		ptl = pud_lock(mm, pud);
 		page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap);
@@ -826,7 +741,6 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
 				    struct follow_page_context *ctx)
 {
 	p4d_t *p4d;
-	struct page *page;
 
 	p4d = p4d_offset(pgdp, address);
 	if (p4d_none(*p4d))
@@ -835,14 +749,6 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
 	if (unlikely(p4d_bad(*p4d)))
 		return no_page_table(vma, flags);
 
-	if (is_hugepd(__hugepd(p4d_val(*p4d)))) {
-		page = follow_huge_pd(vma, address,
-				      __hugepd(p4d_val(*p4d)), flags,
-				      P4D_SHIFT);
-		if (page)
-			return page;
-		return no_page_table(vma, flags);
-	}
 	return follow_pud_mask(vma, address, p4d, flags, ctx);
 }
 
@@ -880,10 +786,18 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
 
 	ctx->page_mask = 0;
 
-	/* make this handle hugepd */
-	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
-	if (!IS_ERR(page)) {
-		WARN_ON_ONCE(flags & (FOLL_GET | FOLL_PIN));
+	/*
+	 * Call hugetlb_follow_page_mask for hugetlb vmas as it will use
+	 * special hugetlb page table walking code.  This eliminates the
+	 * need to check for hugetlb entries in the general walking code.
+	 *
+	 * hugetlb_follow_page_mask is only for follow_page() handling here.
+	 * Ordinary GUP uses follow_hugetlb_page for hugetlb processing.
+	 */
+	if (is_vm_hugetlb_page(vma)) {
+		page = hugetlb_follow_page_mask(vma, address, flags);
+		if (!page)
+			page = no_page_table(vma, flags);
 		return page;
 	}
 
@@ -892,21 +806,6 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
 		return no_page_table(vma, flags);
 
-	if (pgd_huge(*pgd)) {
-		page = follow_huge_pgd(mm, address, pgd, flags);
-		if (page)
-			return page;
-		return no_page_table(vma, flags);
-	}
-	if (is_hugepd(__hugepd(pgd_val(*pgd)))) {
-		page = follow_huge_pd(vma, address,
-				      __hugepd(pgd_val(*pgd)), flags,
-				      PGDIR_SHIFT);
-		if (page)
-			return page;
-		return no_page_table(vma, flags);
-	}
-
 	return follow_p4d_mask(vma, address, pgd, flags, ctx);
 }
 
@@ -1077,6 +976,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 		if (!(vm_flags & VM_WRITE)) {
 			if (!(gup_flags & FOLL_FORCE))
 				return -EFAULT;
+			/* hugetlb does not support FOLL_FORCE|FOLL_WRITE. */
+			if (is_vm_hugetlb_page(vma))
+				return -EFAULT;
 			/*
 			 * We used to let the write,force case do COW in a
 			 * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could
@@ -2117,14 +2019,19 @@ static long __gup_longterm_locked(struct mm_struct *mm,
 				  unsigned long nr_pages,
 				  struct page **pages,
 				  struct vm_area_struct **vmas,
+				  int *locked,
 				  unsigned int gup_flags)
 {
+	bool must_unlock = false;
 	unsigned int flags;
 	long rc, nr_pinned_pages;
 
+	if (locked && WARN_ON_ONCE(!*locked))
+		return -EINVAL;
+
 	if (!(gup_flags & FOLL_LONGTERM))
 		return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
-					       NULL, gup_flags);
+					       locked, gup_flags);
 
 	/*
 	 * If we get to this point then FOLL_LONGTERM is set, and FOLL_LONGTERM
@@ -2138,8 +2045,13 @@ static long __gup_longterm_locked(struct mm_struct *mm,
 		return -EINVAL;
 	flags = memalloc_pin_save();
 	do {
+		if (locked && !*locked) {
+			mmap_read_lock(mm);
+			must_unlock = true;
+			*locked = 1;
+		}
 		nr_pinned_pages = __get_user_pages_locked(mm, start, nr_pages,
-							  pages, vmas, NULL,
+							  pages, vmas, locked,
 							  gup_flags);
 		if (nr_pinned_pages <= 0) {
 			rc = nr_pinned_pages;
@@ -2149,6 +2061,10 @@ static long __gup_longterm_locked(struct mm_struct *mm,
 	} while (rc == -EAGAIN);
 	memalloc_pin_restore(flags);
 
+	if (locked && *locked && must_unlock) {
+		mmap_read_unlock(mm);
+		*locked = 0;
+	}
 	return rc ? rc : nr_pinned_pages;
 }
 
@@ -2172,35 +2088,6 @@ static bool is_valid_gup_flags(unsigned int gup_flags)
 }
 
 #ifdef CONFIG_MMU
-static long __get_user_pages_remote(struct mm_struct *mm,
-				    unsigned long start, unsigned long nr_pages,
-				    unsigned int gup_flags, struct page **pages,
-				    struct vm_area_struct **vmas, int *locked)
-{
-	/*
-	 * Parts of FOLL_LONGTERM behavior are incompatible with
-	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
-	 * vmas. However, this only comes up if locked is set, and there are
-	 * callers that do request FOLL_LONGTERM, but do not set locked. So,
-	 * allow what we can.
-	 */
-	if (gup_flags & FOLL_LONGTERM) {
-		if (WARN_ON_ONCE(locked))
-			return -EINVAL;
-		/*
-		 * This will check the vmas (even if our vmas arg is NULL)
-		 * and return -ENOTSUPP if DAX isn't allowed in this case:
-		 */
-		return __gup_longterm_locked(mm, start, nr_pages, pages,
-					     vmas, gup_flags | FOLL_TOUCH |
-					     FOLL_REMOTE);
-	}
-
-	return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
-				       locked,
-				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
-}
-
 /**
  * get_user_pages_remote() - pin user pages in memory
  * @mm:		mm_struct of target mm
@@ -2269,8 +2156,8 @@ long get_user_pages_remote(struct mm_struct *mm,
 	if (!is_valid_gup_flags(gup_flags))
 		return -EINVAL;
 
-	return __get_user_pages_remote(mm, start, nr_pages, gup_flags,
-				       pages, vmas, locked);
+	return __gup_longterm_locked(mm, start, nr_pages, pages, vmas, locked,
+				     gup_flags | FOLL_TOUCH | FOLL_REMOTE);
 }
 EXPORT_SYMBOL(get_user_pages_remote);
 
@@ -2282,14 +2169,6 @@ long get_user_pages_remote(struct mm_struct *mm,
 {
 	return 0;
 }
-
-static long __get_user_pages_remote(struct mm_struct *mm,
-				    unsigned long start, unsigned long nr_pages,
-				    unsigned int gup_flags, struct page **pages,
-				    struct vm_area_struct **vmas, int *locked)
-{
-	return 0;
-}
 #endif /* !CONFIG_MMU */
 
 /**
@@ -2316,7 +2195,7 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
 		return -EINVAL;
 
 	return __gup_longterm_locked(current->mm, start, nr_pages,
-				     pages, vmas, gup_flags | FOLL_TOUCH);
+				     pages, vmas, NULL, gup_flags | FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages);
 
@@ -2342,18 +2221,9 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 	int locked = 1;
 	long ret;
 
-	/*
-	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
-	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
-	 * vmas.  As there are no users of this flag in this call we simply
-	 * disallow this option for now.
-	 */
-	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
-		return -EINVAL;
-
 	mmap_read_lock(mm);
-	ret = __get_user_pages_locked(mm, start, nr_pages, pages, NULL,
-				      &locked, gup_flags | FOLL_TOUCH);
+	ret = __gup_longterm_locked(mm, start, nr_pages, pages, NULL, &locked,
+				    gup_flags | FOLL_TOUCH);
 	if (locked)
 		mmap_read_unlock(mm);
 	return ret;
@@ -2480,7 +2350,7 @@ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 			goto pte_unmap;
 		}
 
-		if (!pte_write(pte) && gup_must_unshare(flags, page)) {
+		if (!pte_write(pte) && gup_must_unshare(NULL, flags, page)) {
 			gup_put_folio(folio, 1, flags);
 			goto pte_unmap;
 		}
@@ -2672,7 +2542,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 		return 0;
 	}
 
-	if (!pte_write(pte) && gup_must_unshare(flags, &folio->page)) {
+	if (!pte_write(pte) && gup_must_unshare(NULL, flags, &folio->page)) {
 		gup_put_folio(folio, refs, flags);
 		return 0;
 	}
@@ -2738,7 +2608,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return 0;
 	}
 
-	if (!pmd_write(orig) && gup_must_unshare(flags, &folio->page)) {
+	if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) {
 		gup_put_folio(folio, refs, flags);
 		return 0;
 	}
@@ -2778,7 +2648,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return 0;
 	}
 
-	if (!pud_write(orig) && gup_must_unshare(flags, &folio->page)) {
+	if (!pud_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) {
 		gup_put_folio(folio, refs, flags);
 		return 0;
 	}
@@ -2953,29 +2823,6 @@ static bool gup_fast_permitted(unsigned long start, unsigned long end)
 }
 #endif
 
-static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
-				   unsigned int gup_flags, struct page **pages)
-{
-	int ret;
-
-	/*
-	 * FIXME: FOLL_LONGTERM does not work with
-	 * get_user_pages_unlocked() (see comments in that function)
-	 */
-	if (gup_flags & FOLL_LONGTERM) {
-		mmap_read_lock(current->mm);
-		ret = __gup_longterm_locked(current->mm,
-					    start, nr_pages,
-					    pages, NULL, gup_flags);
-		mmap_read_unlock(current->mm);
-	} else {
-		ret = get_user_pages_unlocked(start, nr_pages,
-					      pages, gup_flags);
-	}
-
-	return ret;
-}
-
 static unsigned long lockless_pages_from_mm(unsigned long start,
 					    unsigned long end,
 					    unsigned int gup_flags,
@@ -3060,8 +2907,8 @@ static int internal_get_user_pages_fast(unsigned long start,
 	/* Slow path: try to get the remaining pages with get_user_pages */
 	start += nr_pinned << PAGE_SHIFT;
 	pages += nr_pinned;
-	ret = __gup_longterm_unlocked(start, nr_pages - nr_pinned, gup_flags,
-				      pages);
+	ret = get_user_pages_unlocked(start, nr_pages - nr_pinned, pages,
+				      gup_flags);
 	if (ret < 0) {
 		/*
 		 * The caller has to unpin the pages we already pinned so
@@ -3260,9 +3107,9 @@ long pin_user_pages_remote(struct mm_struct *mm,
 	if (WARN_ON_ONCE(!pages))
 		return -EINVAL;
 
-	gup_flags |= FOLL_PIN;
-	return __get_user_pages_remote(mm, start, nr_pages, gup_flags,
-				       pages, vmas, locked);
+	return __gup_longterm_locked(mm, start, nr_pages, pages, vmas, locked,
+				     gup_flags | FOLL_PIN | FOLL_TOUCH |
+					     FOLL_REMOTE);
 }
 EXPORT_SYMBOL(pin_user_pages_remote);
 
@@ -3296,7 +3143,7 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages,
 
 	gup_flags |= FOLL_PIN;
 	return __gup_longterm_locked(current->mm, start, nr_pages,
-				     pages, vmas, gup_flags);
+				     pages, vmas, NULL, gup_flags);
 }
 EXPORT_SYMBOL(pin_user_pages);