[PATCHv3 1/2] mm/memory: Do not populate page table entries beyond i_size

[Kiryl Shutsemau <kirill@shutemov.name>]

From: Kiryl Shutsemau <kas@kernel.org>

Accesses within VMA, but beyond i_size rounded up to PAGE_SIZE are
supposed to generate SIGBUS.

Recent changes attempted to fault in full folio where possible. They did
not respect i_size, which led to populating PTEs beyond i_size and
breaking SIGBUS semantics.

Darrick reported generic/749 breakage because of this.

However, the problem existed before the recent changes. With huge=always
tmpfs, any write to a file leads to PMD-size allocation. Following the
fault-in of the folio will install PMD mapping regardless of i_size.

Fix filemap_map_pages() and finish_fault() to not install:
  - PTEs beyond i_size;
  - PMD mappings across i_size;

Make an exception for shmem/tmpfs that for long time intentionally
mapped with PMDs across i_size.

Signed-off-by: Kiryl Shutsemau <kas@kernel.org>
Fixes: 19773df031bc ("mm/fault: try to map the entire file folio in finish_fault()")
Fixes: 357b92761d94 ("mm/filemap: map entire large folio faultaround")
Fixes: 01c70267053d ("fs: add a filesystem flag for THPs")
Reported-by: "Darrick J. Wong" <djwong@kernel.org>
---
 mm/filemap.c | 28 ++++++++++++++++++++--------
 mm/memory.c  | 20 +++++++++++++++++++-
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index b7b297c1ad4f..ff75bd89b68c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3690,7 +3690,8 @@ static struct folio *next_uptodate_folio(struct xa_state *xas,
 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,
+			bool can_map_large)
 {
 	unsigned int ref_from_caller = 1;
 	vm_fault_t ret = 0;
@@ -3705,7 +3706,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 	 * The folio must not cross VMA or page table boundary.
 	 */
 	addr0 = addr - start * PAGE_SIZE;
-	if (folio_within_vma(folio, vmf->vma) &&
+	if (can_map_large && folio_within_vma(folio, vmf->vma) &&
 	    (addr0 & PMD_MASK) == ((addr0 + folio_size(folio) - 1) & PMD_MASK)) {
 		vmf->pte -= start;
 		page -= start;
@@ -3820,13 +3821,27 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	unsigned long rss = 0;
 	unsigned int nr_pages = 0, folio_type;
 	unsigned short mmap_miss = 0, mmap_miss_saved;
+	bool can_map_large;
 
 	rcu_read_lock();
 	folio = next_uptodate_folio(&xas, mapping, end_pgoff);
 	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 PTEs beyond i_size and 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.
+	 */
+	can_map_large = shmem_mapping(mapping) ||
+		file_end >= folio_next_index(folio);
+
+	if (can_map_large && filemap_map_pmd(vmf, folio, start_pgoff)) {
 		ret = VM_FAULT_NOPAGE;
 		goto out;
 	}
@@ -3839,10 +3854,6 @@ 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;
@@ -3859,7 +3870,8 @@ 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,
+					can_map_large);
 
 		folio_unlock(folio);
 	} while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL);
diff --git a/mm/memory.c b/mm/memory.c
index 39e21688e74b..1a3eb070f8df 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -77,6 +77,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/pgalloc.h>
 #include <linux/uaccess.h>
+#include <linux/shmem_fs.h>
 
 #include <trace/events/kmem.h>
 
@@ -5545,8 +5546,25 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 			return ret;
 	}
 
+	if (!needs_fallback && vma->vm_file) {
+		struct address_space *mapping = vma->vm_file->f_mapping;
+		pgoff_t file_end;
+
+		file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
+
+		/*
+		 * Do not allow to map with PTEs beyond i_size and 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.
+		 */
+		needs_fallback = !shmem_mapping(mapping) &&
+			file_end < folio_next_index(folio);
+	}
+
 	if (pmd_none(*vmf->pmd)) {
-		if (folio_test_pmd_mappable(folio)) {
+		if (!needs_fallback && folio_test_pmd_mappable(folio)) {
 			ret = do_set_pmd(vmf, folio, page);
 			if (ret != VM_FAULT_FALLBACK)
 				return ret;
-- 
2.50.1