Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - A few misc subsystems: kthread, scripts, ntfs, ocfs2, block, and vfs

 - Most the MM patches which precede the patches in Willy's tree: kasan,
   pagecache, gup, swap, shmem, memcg, selftests, pagemap, mremap,
   sparsemem, vmalloc, pagealloc, memory-failure, mlock, hugetlb,
   userfaultfd, vmscan, compaction, mempolicy, oom-kill, migration, thp,
   cma, autonuma, psi, ksm, page-poison, madvise, memory-hotplug, rmap,
   zswap, uaccess, ioremap, highmem, cleanups, kfence, hmm, and damon.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (227 commits)
  mm/damon/sysfs: remove repeat container_of() in damon_sysfs_kdamond_release()
  Docs/ABI/testing: add DAMON sysfs interface ABI document
  Docs/admin-guide/mm/damon/usage: document DAMON sysfs interface
  selftests/damon: add a test for DAMON sysfs interface
  mm/damon/sysfs: support DAMOS stats
  mm/damon/sysfs: support DAMOS watermarks
  mm/damon/sysfs: support schemes prioritization
  mm/damon/sysfs: support DAMOS quotas
  mm/damon/sysfs: support DAMON-based Operation Schemes
  mm/damon/sysfs: support the physical address space monitoring
  mm/damon/sysfs: link DAMON for virtual address spaces monitoring
  mm/damon: implement a minimal stub for sysfs-based DAMON interface
  mm/damon/core: add number of each enum type values
  mm/damon/core: allow non-exclusive DAMON start/stop
  Docs/damon: update outdated term 'regions update interval'
  Docs/vm/damon/design: update DAMON-Idle Page Tracking interference handling
  Docs/vm/damon: call low level monitoring primitives the operations
  mm/damon: remove unnecessary CONFIG_DAMON option
  mm/damon/paddr,vaddr: remove damon_{p,v}a_{target_valid,set_operations}()
  mm/damon/dbgfs-test: fix is_target_id() change
  ...

1 files changed, 58 insertions, 44 deletions

diff --git a/mm/memory.c b/mm/memory.c
index c125c4969913..e0f3410fa70c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1309,22 +1309,34 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
  * Parameter block passed down to zap_pte_range in exceptional cases.
  */
 struct zap_details {
-	struct address_space *zap_mapping;	/* Check page->mapping if set */
 	struct folio *single_folio;	/* Locked folio to be unmapped */
+	bool even_cows;			/* Zap COWed private pages too? */
 };
 
-/*
- * We set details->zap_mapping when we want to unmap shared but keep private
- * pages. Return true if skip zapping this page, false otherwise.
- */
-static inline bool
-zap_skip_check_mapping(struct zap_details *details, struct page *page)
+/* Whether we should zap all COWed (private) pages too */
+static inline bool should_zap_cows(struct zap_details *details)
 {
-	if (!details || !page)
-		return false;
+	/* By default, zap all pages */
+	if (!details)
+		return true;
 
-	return details->zap_mapping &&
-		(details->zap_mapping != page_rmapping(page));
+	/* Or, we zap COWed pages only if the caller wants to */
+	return details->even_cows;
+}
+
+/* Decides whether we should zap this page with the page pointer specified */
+static inline bool should_zap_page(struct zap_details *details, struct page *page)
+{
+	/* If we can make a decision without *page.. */
+	if (should_zap_cows(details))
+		return true;
+
+	/* E.g. the caller passes NULL for the case of a zero page */
+	if (!page)
+		return true;
+
+	/* Otherwise we should only zap non-anon pages */
+	return !PageAnon(page);
 }
 
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
@@ -1349,6 +1361,8 @@ again:
 	arch_enter_lazy_mmu_mode();
 	do {
 		pte_t ptent = *pte;
+		struct page *page;
+
 		if (pte_none(ptent))
 			continue;
 
@@ -1356,10 +1370,8 @@ again:
 			break;
 
 		if (pte_present(ptent)) {
-			struct page *page;
-
 			page = vm_normal_page(vma, addr, ptent);
-			if (unlikely(zap_skip_check_mapping(details, page)))
+			if (unlikely(!should_zap_page(details, page)))
 				continue;
 			ptent = ptep_get_and_clear_full(mm, addr, pte,
 							tlb->fullmm);
@@ -1391,34 +1403,32 @@ again:
 		entry = pte_to_swp_entry(ptent);
 		if (is_device_private_entry(entry) ||
 		    is_device_exclusive_entry(entry)) {
-			struct page *page = pfn_swap_entry_to_page(entry);
-
-			if (unlikely(zap_skip_check_mapping(details, page)))
+			page = pfn_swap_entry_to_page(entry);
+			if (unlikely(!should_zap_page(details, page)))
 				continue;
-			pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
 			rss[mm_counter(page)]--;
-
 			if (is_device_private_entry(entry))
 				page_remove_rmap(page, false);
-
 			put_page(page);
-			continue;
-		}
-
-		/* If details->check_mapping, we leave swap entries. */
-		if (unlikely(details))
-			continue;
-
-		if (!non_swap_entry(entry))
+		} else if (!non_swap_entry(entry)) {
+			/* Genuine swap entry, hence a private anon page */
+			if (!should_zap_cows(details))
+				continue;
 			rss[MM_SWAPENTS]--;
-		else if (is_migration_entry(entry)) {
-			struct page *page;
-
+			if (unlikely(!free_swap_and_cache(entry)))
+				print_bad_pte(vma, addr, ptent, NULL);
+		} else if (is_migration_entry(entry)) {
 			page = pfn_swap_entry_to_page(entry);
+			if (!should_zap_page(details, page))
+				continue;
 			rss[mm_counter(page)]--;
+		} else if (is_hwpoison_entry(entry)) {
+			if (!should_zap_cows(details))
+				continue;
+		} else {
+			/* We should have covered all the swap entry types */
+			WARN_ON_ONCE(1);
 		}
-		if (unlikely(!free_swap_and_cache(entry)))
-			print_bad_pte(vma, addr, ptent, NULL);
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
@@ -1705,7 +1715,7 @@ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long addr
 void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size)
 {
-	if (address < vma->vm_start || address + size > vma->vm_end ||
+	if (!range_in_vma(vma, address, address + size) ||
 	    		!(vma->vm_flags & VM_PFNMAP))
 		return;
 
@@ -3340,12 +3350,8 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root,
 	vma_interval_tree_foreach(vma, root, first_index, last_index) {
 		vba = vma->vm_pgoff;
 		vea = vba + vma_pages(vma) - 1;
-		zba = first_index;
-		if (zba < vba)
-			zba = vba;
-		zea = last_index;
-		if (zea > vea)
-			zea = vea;
+		zba = max(first_index, vba);
+		zea = min(last_index, vea);
 
 		unmap_mapping_range_vma(vma,
 			((zba - vba) << PAGE_SHIFT) + vma->vm_start,
@@ -3377,7 +3383,7 @@ void unmap_mapping_folio(struct folio *folio)
 	first_index = folio->index;
 	last_index = folio->index + folio_nr_pages(folio) - 1;
 
-	details.zap_mapping = mapping;
+	details.even_cows = false;
 	details.single_folio = folio;
 
 	i_mmap_lock_write(mapping);
@@ -3406,7 +3412,7 @@ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start,
 	pgoff_t	first_index = start;
 	pgoff_t	last_index = start + nr - 1;
 
-	details.zap_mapping = even_cows ? NULL : mapping;
+	details.even_cows = even_cows;
 	if (last_index < first_index)
 		last_index = ULONG_MAX;
 
@@ -3871,11 +3877,16 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
 		return ret;
 
 	if (unlikely(PageHWPoison(vmf->page))) {
-		if (ret & VM_FAULT_LOCKED)
+		vm_fault_t poisonret = VM_FAULT_HWPOISON;
+		if (ret & VM_FAULT_LOCKED) {
+			/* Retry if a clean page was removed from the cache. */
+			if (invalidate_inode_page(vmf->page))
+				poisonret = 0;
 			unlock_page(vmf->page);
+		}
 		put_page(vmf->page);
 		vmf->page = NULL;
-		return VM_FAULT_HWPOISON;
+		return poisonret;
 	}
 
 	if (unlikely(!(ret & VM_FAULT_LOCKED)))
@@ -4622,6 +4633,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 	struct vm_fault vmf = {
 		.vma = vma,
 		.address = address & PAGE_MASK,
+		.real_address = address,
 		.flags = flags,
 		.pgoff = linear_page_index(vma, address),
 		.gfp_mask = __get_fault_gfp_mask(vma),
@@ -5444,6 +5456,8 @@ long copy_huge_page_from_user(struct page *dst_page,
 		if (rc)
 			break;
 
+		flush_dcache_page(subpage);
+
 		cond_resched();
 	}
 	return ret_val;