1 files changed, 81 insertions, 10 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index add5228a7d97..41741b9c351a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2366,6 +2366,64 @@ out:
 }
 EXPORT_SYMBOL(filemap_get_folios_tag);
 
+/**
+ * filemap_get_folios_dirty - Get a batch of dirty folios
+ * @mapping:	The address_space to search
+ * @start:	The starting folio index
+ * @end:	The final folio index (inclusive)
+ * @fbatch:	The batch to fill
+ *
+ * filemap_get_folios_dirty() works exactly like filemap_get_folios(), except
+ * the returned folios are presumed to be dirty or undergoing writeback. Dirty
+ * state is presumed because we don't block on folio lock nor want to miss
+ * folios. Callers that need to can recheck state upon locking the folio.
+ *
+ * This may not return all dirty folios if the batch gets filled up.
+ *
+ * Return: The number of folios found.
+ * Also update @start to be positioned for traversal of the next folio.
+ */
+unsigned filemap_get_folios_dirty(struct address_space *mapping, pgoff_t *start,
+			pgoff_t end, struct folio_batch *fbatch)
+{
+	XA_STATE(xas, &mapping->i_pages, *start);
+	struct folio *folio;
+
+	rcu_read_lock();
+	while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) {
+		if (xa_is_value(folio))
+			continue;
+		if (folio_trylock(folio)) {
+			bool clean = !folio_test_dirty(folio) &&
+				     !folio_test_writeback(folio);
+			folio_unlock(folio);
+			if (clean) {
+				folio_put(folio);
+				continue;
+			}
+		}
+		if (!folio_batch_add(fbatch, folio)) {
+			unsigned long nr = folio_nr_pages(folio);
+			*start = folio->index + nr;
+			goto out;
+		}
+	}
+	/*
+	 * We come here when there is no folio beyond @end. We take care to not
+	 * overflow the index @start as it confuses some of the callers. This
+	 * breaks the iteration when there is a folio at index -1 but that is
+	 * already broke anyway.
+	 */
+	if (end == (pgoff_t)-1)
+		*start = (pgoff_t)-1;
+	else
+		*start = end + 1;
+out:
+	rcu_read_unlock();
+
+	return folio_batch_count(fbatch);
+}
+
 /*
  * CD/DVDs are error prone. When a medium error occurs, the driver may fail
  * a _large_ part of the i/o request. Imagine the worst scenario:
@@ -3681,8 +3739,10 @@ skip:
 static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 			struct folio *folio, unsigned long start,
 			unsigned long addr, unsigned int nr_pages,
-			unsigned long *rss, unsigned short *mmap_miss)
+			unsigned long *rss, unsigned short *mmap_miss,
+			pgoff_t file_end)
 {
+	struct address_space *mapping = folio->mapping;
 	unsigned int ref_from_caller = 1;
 	vm_fault_t ret = 0;
 	struct page *page = folio_page(folio, start);
@@ -3691,12 +3751,16 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 	unsigned long addr0;
 
 	/*
-	 * Map the large folio fully where possible.
+	 * Map the large folio fully where possible:
 	 *
-	 * The folio must not cross VMA or page table boundary.
+	 *  - The folio is fully within size of the file or belong
+	 *    to shmem/tmpfs;
+	 *  - The folio doesn't cross VMA boundary;
+	 *  - The folio doesn't cross page table boundary;
 	 */
 	addr0 = addr - start * PAGE_SIZE;
-	if (folio_within_vma(folio, vmf->vma) &&
+	if ((file_end >= folio_next_index(folio) || shmem_mapping(mapping)) &&
+	    folio_within_vma(folio, vmf->vma) &&
 	    (addr0 & PMD_MASK) == ((addr0 + folio_size(folio) - 1) & PMD_MASK)) {
 		vmf->pte -= start;
 		page -= start;
@@ -3817,7 +3881,18 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	if (!folio)
 		goto out;
 
-	if (filemap_map_pmd(vmf, folio, start_pgoff)) {
+	file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1;
+	end_pgoff = min(end_pgoff, file_end);
+
+	/*
+	 * Do not allow to map with PMD across i_size to preserve
+	 * SIGBUS semantics.
+	 *
+	 * Make an exception for shmem/tmpfs that for long time
+	 * intentionally mapped with PMDs across i_size.
+	 */
+	if ((file_end >= folio_next_index(folio) || shmem_mapping(mapping)) &&
+	    filemap_map_pmd(vmf, folio, start_pgoff)) {
 		ret = VM_FAULT_NOPAGE;
 		goto out;
 	}
@@ -3830,10 +3905,6 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		goto out;
 	}
 
-	file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1;
-	if (end_pgoff > file_end)
-		end_pgoff = file_end;
-
 	folio_type = mm_counter_file(folio);
 	do {
 		unsigned long end;
@@ -3850,7 +3921,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		else
 			ret |= filemap_map_folio_range(vmf, folio,
 					xas.xa_index - folio->index, addr,
-					nr_pages, &rss, &mmap_miss);
+					nr_pages, &rss, &mmap_miss, file_end);
 
 		folio_unlock(folio);
 	} while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL);