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
  ...

4 files changed, 5 insertions, 121 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index c436d8422654..cb4c67bf45d7 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -401,35 +401,9 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
 #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
 #define pmdp_clear_flush_young pmdp_test_and_clear_young
 
-static inline int __pte_write(pte_t pte)
-{
-	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
-}
-
-#ifdef CONFIG_NUMA_BALANCING
-#define pte_savedwrite pte_savedwrite
-static inline bool pte_savedwrite(pte_t pte)
-{
-	/*
-	 * Saved write ptes are prot none ptes that doesn't have
-	 * privileged bit sit. We mark prot none as one which has
-	 * present and pviliged bit set and RWX cleared. To mark
-	 * protnone which used to have _PAGE_WRITE set we clear
-	 * the privileged bit.
-	 */
-	return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
-}
-#else
-#define pte_savedwrite pte_savedwrite
-static inline bool pte_savedwrite(pte_t pte)
-{
-	return false;
-}
-#endif
-
 static inline int pte_write(pte_t pte)
 {
-	return __pte_write(pte) || pte_savedwrite(pte);
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
 }
 
 static inline int pte_read(pte_t pte)
@@ -441,24 +415,16 @@ static inline int pte_read(pte_t pte)
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-	if (__pte_write(*ptep))
+	if (pte_write(*ptep))
 		pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
-	else if (unlikely(pte_savedwrite(*ptep)))
-		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0);
 }
 
 #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	/*
-	 * We should not find protnone for hugetlb, but this complete the
-	 * interface.
-	 */
-	if (__pte_write(*ptep))
+	if (pte_write(*ptep))
 		pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
-	else if (unlikely(pte_savedwrite(*ptep)))
-		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1);
 }
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
@@ -535,36 +501,6 @@ static inline int pte_protnone(pte_t pte)
 	return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE | _PAGE_RWX)) ==
 		cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE);
 }
-
-#define pte_mk_savedwrite pte_mk_savedwrite
-static inline pte_t pte_mk_savedwrite(pte_t pte)
-{
-	/*
-	 * Used by Autonuma subsystem to preserve the write bit
-	 * while marking the pte PROT_NONE. Only allow this
-	 * on PROT_NONE pte
-	 */
-	VM_BUG_ON((pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_RWX | _PAGE_PRIVILEGED)) !=
-		  cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED));
-	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_PRIVILEGED));
-}
-
-#define pte_clear_savedwrite pte_clear_savedwrite
-static inline pte_t pte_clear_savedwrite(pte_t pte)
-{
-	/*
-	 * Used by KSM subsystem to make a protnone pte readonly.
-	 */
-	VM_BUG_ON(!pte_protnone(pte));
-	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PRIVILEGED));
-}
-#else
-#define pte_clear_savedwrite pte_clear_savedwrite
-static inline pte_t pte_clear_savedwrite(pte_t pte)
-{
-	VM_WARN_ON(1);
-	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_WRITE));
-}
 #endif /* CONFIG_NUMA_BALANCING */
 
 static inline bool pte_hw_valid(pte_t pte)
@@ -641,8 +577,6 @@ static inline unsigned long pte_pfn(pte_t pte)
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-	if (unlikely(pte_savedwrite(pte)))
-		return pte_clear_savedwrite(pte);
 	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_WRITE));
 }
 
@@ -1139,8 +1073,6 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
 #define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
-#define pmd_mk_savedwrite(pmd)	pte_pmd(pte_mk_savedwrite(pmd_pte(pmd)))
-#define pmd_clear_savedwrite(pmd)	pte_pmd(pte_clear_savedwrite(pmd_pte(pmd)))
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 #define pmd_soft_dirty(pmd)    pte_soft_dirty(pmd_pte(pmd))
@@ -1162,8 +1094,6 @@ static inline int pmd_protnone(pmd_t pmd)
 #endif /* CONFIG_NUMA_BALANCING */
 
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
-#define __pmd_write(pmd)	__pte_write(pmd_pte(pmd))
-#define pmd_savedwrite(pmd)	pte_savedwrite(pmd_pte(pmd))
 
 #define pmd_access_permitted pmd_access_permitted
 static inline bool pmd_access_permitted(pmd_t pmd, bool write)
@@ -1241,10 +1171,8 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pmd_t *pmdp)
 {
-	if (__pmd_write((*pmdp)))
+	if (pmd_write(*pmdp))
 		pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
-	else if (unlikely(pmd_savedwrite(*pmdp)))
-		pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED);
 }
 
 /*
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 283f40d05a4d..9972626ddaf6 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -81,13 +81,6 @@ void poking_init(void);
 extern unsigned long ioremap_bot;
 extern const pgprot_t protection_map[16];
 
-/*
- * kern_addr_valid is intended to indicate whether an address is a valid
- * kernel address.  Most 32-bit archs define it as always true (like this)
- * but most 64-bit archs actually perform a test.  What should we do here?
- */
-#define kern_addr_valid(addr)	(1)
-
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_large(pmd)		0
 #endif
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 5a05953ae13f..9182324dbef9 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -265,7 +265,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		}
 		pte = kvmppc_read_update_linux_pte(ptep, writing);
 		if (pte_present(pte) && !pte_protnone(pte)) {
-			if (writing && !__pte_write(pte))
+			if (writing && !pte_write(pte))
 				/* make the actual HPTE be read-only */
 				ptel = hpte_make_readonly(ptel);
 			is_ci = pte_ci(pte);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 5852a86d990d..f1ba8d1e8c1a 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -506,43 +506,6 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 	} while (addr = next, addr != end);
 }
 
-struct page *follow_huge_pd(struct vm_area_struct *vma,
-			    unsigned long address, hugepd_t hpd,
-			    int flags, int pdshift)
-{
-	pte_t *ptep;
-	spinlock_t *ptl;
-	struct page *page = NULL;
-	unsigned long mask;
-	int shift = hugepd_shift(hpd);
-	struct mm_struct *mm = vma->vm_mm;
-
-retry:
-	/*
-	 * hugepage directory entries are protected by mm->page_table_lock
-	 * Use this instead of huge_pte_lockptr
-	 */
-	ptl = &mm->page_table_lock;
-	spin_lock(ptl);
-
-	ptep = hugepte_offset(hpd, address, pdshift);
-	if (pte_present(*ptep)) {
-		mask = (1UL << shift) - 1;
-		page = pte_page(*ptep);
-		page += ((address & mask) >> PAGE_SHIFT);
-		if (flags & FOLL_GET)
-			get_page(page);
-	} else {
-		if (is_hugetlb_entry_migration(*ptep)) {
-			spin_unlock(ptl);
-			__migration_entry_wait(mm, ptep, ptl);
-			goto retry;
-		}
-	}
-	spin_unlock(ptl);
-	return page;
-}
-
 bool __init arch_hugetlb_valid_size(unsigned long size)
 {
 	int shift = __ffs(size);