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, 21 insertions, 24 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5b663eca1f29..e245191e6b04 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -6,16 +6,16 @@
  * High level machine check handler. Handles pages reported by the
  * hardware as being corrupted usually due to a multi-bit ECC memory or cache
  * failure.
- * 
+ *
  * In addition there is a "soft offline" entry point that allows stop using
  * not-yet-corrupted-by-suspicious pages without killing anything.
  *
  * Handles page cache pages in various states.	The tricky part
- * here is that we can access any page asynchronously in respect to 
- * other VM users, because memory failures could happen anytime and 
- * anywhere. This could violate some of their assumptions. This is why 
- * this code has to be extremely careful. Generally it tries to use 
- * normal locking rules, as in get the standard locks, even if that means 
+ * here is that we can access any page asynchronously in respect to
+ * other VM users, because memory failures could happen anytime and
+ * anywhere. This could violate some of their assumptions. This is why
+ * this code has to be extremely careful. Generally it tries to use
+ * normal locking rules, as in get the standard locks, even if that means
  * the error handling takes potentially a long time.
  *
  * It can be very tempting to add handling for obscure cases here.
@@ -25,12 +25,12 @@
  *   https://git.kernel.org/cgit/utils/cpu/mce/mce-test.git/
  * - The case actually shows up as a frequent (top 10) page state in
  *   tools/mm/page-types when running a real workload.
- * 
+ *
  * There are several operations here with exponential complexity because
- * of unsuitable VM data structures. For example the operation to map back 
- * from RMAP chains to processes has to walk the complete process list and 
+ * of unsuitable VM data structures. For example the operation to map back
+ * from RMAP chains to processes has to walk the complete process list and
  * has non linear complexity with the number. But since memory corruptions
- * are rare we hope to get away with this. This avoids impacting the core 
+ * are rare we hope to get away with this. This avoids impacting the core
  * VM.
  */
 
@@ -123,7 +123,6 @@ const struct attribute_group memory_failure_attr_group = {
 	.attrs = memory_failure_attr,
 };
 
-#ifdef CONFIG_SYSCTL
 static struct ctl_table memory_failure_table[] = {
 	{
 		.procname	= "memory_failure_early_kill",
@@ -146,14 +145,6 @@ static struct ctl_table memory_failure_table[] = {
 	{ }
 };
 
-static int __init memory_failure_sysctl_init(void)
-{
-	register_sysctl_init("vm", memory_failure_table);
-	return 0;
-}
-late_initcall(memory_failure_sysctl_init);
-#endif /* CONFIG_SYSCTL */
-
 /*
  * Return values:
  *   1:   the page is dissolved (if needed) and taken off from buddy,
@@ -395,6 +386,7 @@ static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma,
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
+	pte_t ptent;
 
 	VM_BUG_ON_VMA(address == -EFAULT, vma);
 	pgd = pgd_offset(vma->vm_mm, address);
@@ -414,7 +406,10 @@ static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma,
 	if (pmd_devmap(*pmd))
 		return PMD_SHIFT;
 	pte = pte_offset_map(pmd, address);
-	if (pte_present(*pte) && pte_devmap(*pte))
+	if (!pte)
+		return 0;
+	ptent = ptep_get(pte);
+	if (pte_present(ptent) && pte_devmap(ptent))
 		ret = PAGE_SHIFT;
 	pte_unmap(pte);
 	return ret;
@@ -800,13 +795,13 @@ static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr,
 		goto out;
 	}
 
-	if (pmd_trans_unstable(pmdp))
-		goto out;
-
 	mapped_pte = ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp,
 						addr, &ptl);
+	if (!ptep)
+		goto out;
+
 	for (; addr != end; ptep++, addr += PAGE_SIZE) {
-		ret = check_hwpoisoned_entry(*ptep, addr, PAGE_SHIFT,
+		ret = check_hwpoisoned_entry(ptep_get(ptep), addr, PAGE_SHIFT,
 					     hwp->pfn, &hwp->tk);
 		if (ret == 1)
 			break;
@@ -2441,6 +2436,8 @@ static int __init memory_failure_init(void)
 		INIT_WORK(&mf_cpu->work, memory_failure_work_func);
 	}
 
+	register_sysctl_init("vm", memory_failure_table);
+
 	return 0;
 }
 core_initcall(memory_failure_init);