Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...

1 files changed, 39 insertions, 137 deletions

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index c5a51481bbb9..5063b482e34f 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -94,14 +94,22 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
 #define pte_offset_kernel pte_offset_kernel
 #endif
 
-#if defined(CONFIG_HIGHPTE)
-#define pte_offset_map(dir, address)				\
-	((pte_t *)kmap_atomic(pmd_page(*(dir))) +		\
-	 pte_index((address)))
-#define pte_unmap(pte) kunmap_atomic((pte))
+#ifdef CONFIG_HIGHPTE
+#define __pte_map(pmd, address) \
+	((pte_t *)kmap_local_page(pmd_page(*(pmd))) + pte_index((address)))
+#define pte_unmap(pte)	do {	\
+	kunmap_local((pte));	\
+	/* rcu_read_unlock() to be added later */	\
+} while (0)
 #else
-#define pte_offset_map(dir, address)	pte_offset_kernel((dir), (address))
-#define pte_unmap(pte) ((void)(pte))	/* NOP */
+static inline pte_t *__pte_map(pmd_t *pmd, unsigned long address)
+{
+	return pte_offset_kernel(pmd, address);
+}
+static inline void pte_unmap(pte_t *pte)
+{
+	/* rcu_read_unlock() to be added later */
+}
 #endif
 
 /* Find an entry in the second-level page table.. */
@@ -204,12 +212,26 @@ static inline int pudp_set_access_flags(struct vm_area_struct *vma,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
+#ifndef ptep_get
+static inline pte_t ptep_get(pte_t *ptep)
+{
+	return READ_ONCE(*ptep);
+}
+#endif
+
+#ifndef pmdp_get
+static inline pmd_t pmdp_get(pmd_t *pmdp)
+{
+	return READ_ONCE(*pmdp);
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address,
 					    pte_t *ptep)
 {
-	pte_t pte = *ptep;
+	pte_t pte = ptep_get(ptep);
 	int r = 1;
 	if (!pte_young(pte))
 		r = 0;
@@ -296,7 +318,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long address,
 				       pte_t *ptep)
 {
-	pte_t pte = *ptep;
+	pte_t pte = ptep_get(ptep);
 	pte_clear(mm, address, ptep);
 	page_table_check_pte_clear(mm, address, pte);
 	return pte;
@@ -309,20 +331,6 @@ static inline void ptep_clear(struct mm_struct *mm, unsigned long addr,
 	ptep_get_and_clear(mm, addr, ptep);
 }
 
-#ifndef ptep_get
-static inline pte_t ptep_get(pte_t *ptep)
-{
-	return READ_ONCE(*ptep);
-}
-#endif
-
-#ifndef pmdp_get
-static inline pmd_t pmdp_get(pmd_t *pmdp)
-{
-	return READ_ONCE(*pmdp);
-}
-#endif
-
 #ifdef CONFIG_GUP_GET_PXX_LOW_HIGH
 /*
  * For walking the pagetables without holding any locks.  Some architectures
@@ -511,7 +519,7 @@ extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma,
 struct mm_struct;
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
 {
-	pte_t old_pte = *ptep;
+	pte_t old_pte = ptep_get(ptep);
 	set_pte_at(mm, address, ptep, pte_wrprotect(old_pte));
 }
 #endif
@@ -591,6 +599,10 @@ extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 #endif
 
+#ifndef arch_needs_pgtable_deposit
+#define arch_needs_pgtable_deposit() (false)
+#endif
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
  * This is an implementation of pmdp_establish() that is only suitable for an
@@ -1292,9 +1304,10 @@ static inline int pud_trans_huge(pud_t pud)
 }
 #endif
 
-/* See pmd_none_or_trans_huge_or_clear_bad for discussion. */
-static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud)
+static inline int pud_trans_unstable(pud_t *pud)
 {
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
+	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 	pud_t pudval = READ_ONCE(*pud);
 
 	if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval))
@@ -1303,121 +1316,10 @@ static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud)
 		pud_clear_bad(pud);
 		return 1;
 	}
-	return 0;
-}
-
-/* See pmd_trans_unstable for discussion. */
-static inline int pud_trans_unstable(pud_t *pud)
-{
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
-	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
-	return pud_none_or_trans_huge_or_dev_or_clear_bad(pud);
-#else
-	return 0;
-#endif
-}
-
-#ifndef arch_needs_pgtable_deposit
-#define arch_needs_pgtable_deposit() (false)
-#endif
-/*
- * This function is meant to be used by sites walking pagetables with
- * the mmap_lock held in read mode to protect against MADV_DONTNEED and
- * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd
- * into a null pmd and the transhuge page fault can convert a null pmd
- * into an hugepmd or into a regular pmd (if the hugepage allocation
- * fails). While holding the mmap_lock in read mode the pmd becomes
- * stable and stops changing under us only if it's not null and not a
- * transhuge pmd. When those races occurs and this function makes a
- * difference vs the standard pmd_none_or_clear_bad, the result is
- * undefined so behaving like if the pmd was none is safe (because it
- * can return none anyway). The compiler level barrier() is critically
- * important to compute the two checks atomically on the same pmdval.
- *
- * For 32bit kernels with a 64bit large pmd_t this automatically takes
- * care of reading the pmd atomically to avoid SMP race conditions
- * against pmd_populate() when the mmap_lock is hold for reading by the
- * caller (a special atomic read not done by "gcc" as in the generic
- * version above, is also needed when THP is disabled because the page
- * fault can populate the pmd from under us).
- */
-static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
-{
-	pmd_t pmdval = pmdp_get_lockless(pmd);
-	/*
-	 * The barrier will stabilize the pmdval in a register or on
-	 * the stack so that it will stop changing under the code.
-	 *
-	 * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE,
-	 * pmdp_get_lockless is allowed to return a not atomic pmdval
-	 * (for example pointing to an hugepage that has never been
-	 * mapped in the pmd). The below checks will only care about
-	 * the low part of the pmd with 32bit PAE x86 anyway, with the
-	 * exception of pmd_none(). So the important thing is that if
-	 * the low part of the pmd is found null, the high part will
-	 * be also null or the pmd_none() check below would be
-	 * confused.
-	 */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	barrier();
 #endif
-	/*
-	 * !pmd_present() checks for pmd migration entries
-	 *
-	 * The complete check uses is_pmd_migration_entry() in linux/swapops.h
-	 * But using that requires moving current function and pmd_trans_unstable()
-	 * to linux/swapops.h to resolve dependency, which is too much code move.
-	 *
-	 * !pmd_present() is equivalent to is_pmd_migration_entry() currently,
-	 * because !pmd_present() pages can only be under migration not swapped
-	 * out.
-	 *
-	 * pmd_none() is preserved for future condition checks on pmd migration
-	 * entries and not confusing with this function name, although it is
-	 * redundant with !pmd_present().
-	 */
-	if (pmd_none(pmdval) || pmd_trans_huge(pmdval) ||
-		(IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) && !pmd_present(pmdval)))
-		return 1;
-	if (unlikely(pmd_bad(pmdval))) {
-		pmd_clear_bad(pmd);
-		return 1;
-	}
 	return 0;
 }
 
-/*
- * This is a noop if Transparent Hugepage Support is not built into
- * the kernel. Otherwise it is equivalent to
- * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in
- * places that already verified the pmd is not none and they want to
- * walk ptes while holding the mmap sem in read mode (write mode don't
- * need this). If THP is not enabled, the pmd can't go away under the
- * code even if MADV_DONTNEED runs, but if THP is enabled we need to
- * run a pmd_trans_unstable before walking the ptes after
- * split_huge_pmd returns (because it may have run when the pmd become
- * null, but then a page fault can map in a THP and not a regular page).
- */
-static inline int pmd_trans_unstable(pmd_t *pmd)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	return pmd_none_or_trans_huge_or_clear_bad(pmd);
-#else
-	return 0;
-#endif
-}
-
-/*
- * the ordering of these checks is important for pmds with _page_devmap set.
- * if we check pmd_trans_unstable() first we will trip the bad_pmd() check
- * inside of pmd_none_or_trans_huge_or_clear_bad(). this will end up correctly
- * returning 1 but not before it spams dmesg with the pmd_clear_bad() output.
- */
-static inline int pmd_devmap_trans_unstable(pmd_t *pmd)
-{
-	return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
-}
-
 #ifndef CONFIG_NUMA_BALANCING
 /*
  * Technically a PTE can be PROTNONE even when not doing NUMA balancing but