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, 74 insertions, 69 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 8b4f93e84868..551834cd5299 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -33,22 +33,9 @@ typedef struct { unsigned long pd; } hugepd_t;
 /*
  * For HugeTLB page, there are more metadata to save in the struct page. But
  * the head struct page cannot meet our needs, so we have to abuse other tail
- * struct page to store the metadata. In order to avoid conflicts caused by
- * subsequent use of more tail struct pages, we gather these discrete indexes
- * of tail struct page here.
+ * struct page to store the metadata.
  */
-enum {
-	SUBPAGE_INDEX_SUBPOOL = 1,	/* reuse page->private */
-#ifdef CONFIG_CGROUP_HUGETLB
-	SUBPAGE_INDEX_CGROUP,		/* reuse page->private */
-	SUBPAGE_INDEX_CGROUP_RSVD,	/* reuse page->private */
-	__MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD,
-#endif
-#ifdef CONFIG_MEMORY_FAILURE
-	SUBPAGE_INDEX_HWPOISON,
-#endif
-	__NR_USED_SUBPAGE,
-};
+#define __NR_USED_SUBPAGE 3
 
 struct hugepage_subpool {
 	spinlock_t lock;
@@ -149,6 +136,8 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 			     unsigned long len);
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *,
 			    struct vm_area_struct *, struct vm_area_struct *);
+struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
+				unsigned long address, unsigned int flags);
 long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
 			 struct page **, struct vm_area_struct **,
 			 unsigned long *, unsigned long *, long, unsigned int,
@@ -181,10 +170,11 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
 int isolate_hugetlb(struct page *page, struct list_head *list);
-int get_hwpoison_huge_page(struct page *page, bool *hugetlb);
-int get_huge_page_for_hwpoison(unsigned long pfn, int flags);
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison);
+int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+				bool *migratable_cleared);
 void putback_active_hugepage(struct page *page);
-void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
+void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason);
 void free_huge_page(struct page *page);
 void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
@@ -209,17 +199,6 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pte_t *ptep);
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end);
-struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
-			      int write);
-struct page *follow_huge_pd(struct vm_area_struct *vma,
-			    unsigned long address, hugepd_t hpd,
-			    int flags, int pdshift);
-struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address,
-				 int flags);
-struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
-				pud_t *pud, int flags);
-struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
-			     pgd_t *pgd, int flags);
 
 void hugetlb_vma_lock_read(struct vm_area_struct *vma);
 void hugetlb_vma_unlock_read(struct vm_area_struct *vma);
@@ -272,6 +251,12 @@ static inline void adjust_range_if_pmd_sharing_possible(
 {
 }
 
+static inline struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
+				unsigned long address, unsigned int flags)
+{
+	BUILD_BUG(); /* should never be compiled in if !CONFIG_HUGETLB_PAGE*/
+}
+
 static inline long follow_hugetlb_page(struct mm_struct *mm,
 			struct vm_area_struct *vma, struct page **pages,
 			struct vm_area_struct **vmas, unsigned long *position,
@@ -282,12 +267,6 @@ static inline long follow_hugetlb_page(struct mm_struct *mm,
 	return 0;
 }
 
-static inline struct page *follow_huge_addr(struct mm_struct *mm,
-					unsigned long address, int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 static inline int copy_hugetlb_page_range(struct mm_struct *dst,
 					  struct mm_struct *src,
 					  struct vm_area_struct *dst_vma,
@@ -320,31 +299,6 @@ static inline void hugetlb_show_meminfo_node(int nid)
 {
 }
 
-static inline struct page *follow_huge_pd(struct vm_area_struct *vma,
-				unsigned long address, hugepd_t hpd, int flags,
-				int pdshift)
-{
-	return NULL;
-}
-
-static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma,
-				unsigned long address, int flags)
-{
-	return NULL;
-}
-
-static inline struct page *follow_huge_pud(struct mm_struct *mm,
-				unsigned long address, pud_t *pud, int flags)
-{
-	return NULL;
-}
-
-static inline struct page *follow_huge_pgd(struct mm_struct *mm,
-				unsigned long address, pgd_t *pgd, int flags)
-{
-	return NULL;
-}
-
 static inline int prepare_hugepage_range(struct file *file,
 				unsigned long addr, unsigned long len)
 {
@@ -425,12 +379,13 @@ static inline int isolate_hugetlb(struct page *page, struct list_head *list)
 	return -EBUSY;
 }
 
-static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison)
 {
 	return 0;
 }
 
-static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+					bool *migratable_cleared)
 {
 	return 0;
 }
@@ -439,8 +394,8 @@ static inline void putback_active_hugepage(struct page *page)
 {
 }
 
-static inline void move_hugetlb_state(struct page *oldpage,
-					struct page *newpage, int reason)
+static inline void move_hugetlb_state(struct folio *old_folio,
+					struct folio *new_folio, int reason)
 {
 }
 
@@ -623,26 +578,50 @@ enum hugetlb_page_flags {
  */
 #ifdef CONFIG_HUGETLB_PAGE
 #define TESTHPAGEFLAG(uname, flname)				\
+static __always_inline						\
+bool folio_test_hugetlb_##flname(struct folio *folio)		\
+	{	void *private = &folio->private;		\
+		return test_bit(HPG_##flname, private);		\
+	}							\
 static inline int HPage##uname(struct page *page)		\
 	{ return test_bit(HPG_##flname, &(page->private)); }
 
 #define SETHPAGEFLAG(uname, flname)				\
+static __always_inline						\
+void folio_set_hugetlb_##flname(struct folio *folio)		\
+	{	void *private = &folio->private;		\
+		set_bit(HPG_##flname, private);			\
+	}							\
 static inline void SetHPage##uname(struct page *page)		\
 	{ set_bit(HPG_##flname, &(page->private)); }
 
 #define CLEARHPAGEFLAG(uname, flname)				\
+static __always_inline						\
+void folio_clear_hugetlb_##flname(struct folio *folio)		\
+	{	void *private = &folio->private;		\
+		clear_bit(HPG_##flname, private);		\
+	}							\
 static inline void ClearHPage##uname(struct page *page)		\
 	{ clear_bit(HPG_##flname, &(page->private)); }
 #else
 #define TESTHPAGEFLAG(uname, flname)				\
+static inline bool						\
+folio_test_hugetlb_##flname(struct folio *folio)		\
+	{ return 0; }						\
 static inline int HPage##uname(struct page *page)		\
 	{ return 0; }
 
 #define SETHPAGEFLAG(uname, flname)				\
+static inline void						\
+folio_set_hugetlb_##flname(struct folio *folio) 		\
+	{ }							\
 static inline void SetHPage##uname(struct page *page)		\
 	{ }
 
 #define CLEARHPAGEFLAG(uname, flname)				\
+static inline void						\
+folio_clear_hugetlb_##flname(struct folio *folio)		\
+	{ }							\
 static inline void ClearHPage##uname(struct page *page)		\
 	{ }
 #endif
@@ -728,18 +707,29 @@ extern unsigned int default_hstate_idx;
 
 #define default_hstate (hstates[default_hstate_idx])
 
+static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio)
+{
+	return folio->_hugetlb_subpool;
+}
+
 /*
- * hugetlb page subpool pointer located in hpage[1].private
+ * hugetlb page subpool pointer located in hpage[2].hugetlb_subpool
  */
 static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
 {
-	return (void *)page_private(hpage + SUBPAGE_INDEX_SUBPOOL);
+	return hugetlb_folio_subpool(page_folio(hpage));
+}
+
+static inline void hugetlb_set_folio_subpool(struct folio *folio,
+					struct hugepage_subpool *subpool)
+{
+	folio->_hugetlb_subpool = subpool;
 }
 
 static inline void hugetlb_set_page_subpool(struct page *hpage,
 					struct hugepage_subpool *subpool)
 {
-	set_page_private(hpage + SUBPAGE_INDEX_SUBPOOL, (unsigned long)subpool);
+	hugetlb_set_folio_subpool(page_folio(hpage), subpool);
 }
 
 static inline struct hstate *hstate_file(struct file *f)
@@ -823,10 +813,15 @@ static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift,
 }
 #endif
 
+static inline struct hstate *folio_hstate(struct folio *folio)
+{
+	VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+	return size_to_hstate(folio_size(folio));
+}
+
 static inline struct hstate *page_hstate(struct page *page)
 {
-	VM_BUG_ON_PAGE(!PageHuge(page), page);
-	return size_to_hstate(page_size(page));
+	return folio_hstate(page_folio(page));
 }
 
 static inline unsigned hstate_index_to_shift(unsigned index)
@@ -983,6 +978,11 @@ void hugetlb_unregister_node(struct node *node);
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
+static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio)
+{
+	return NULL;
+}
+
 static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
 {
 	return NULL;
@@ -1035,6 +1035,11 @@ static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
 	return NULL;
 }
 
+static inline struct hstate *folio_hstate(struct folio *folio)
+{
+	return NULL;
+}
+
 static inline struct hstate *page_hstate(struct page *page)
 {
 	return NULL;