mm/filemap.c: fix a data race in filemap_fault()

mainline inclusion
from mainline-v5.9-rc1
commit e630bfac
category: bugfix
bugzilla: 41542
CVE: NA

-----------------------------------------------

struct file_ra_state ra.mmap_miss could be accessed concurrently during
page faults as noticed by KCSAN,

 BUG: KCSAN: data-race in filemap_fault / filemap_map_pages

 write to 0xffff9b1700a2c1b4 of 4 bytes by task 3292 on cpu 30:
  filemap_fault+0x920/0xfc0
  do_sync_mmap_readahead at mm/filemap.c:2384
  (inlined by) filemap_fault at mm/filemap.c:2486
  __xfs_filemap_fault+0x112/0x3e0 [xfs]
  xfs_filemap_fault+0x74/0x90 [xfs]
  __do_fault+0x9e/0x220
  do_fault+0x4a0/0x920
  __handle_mm_fault+0xc69/0xd00
  handle_mm_fault+0xfc/0x2f0
  do_page_fault+0x263/0x6f9
  page_fault+0x34/0x40

 read to 0xffff9b1700a2c1b4 of 4 bytes by task 3313 on cpu 32:
  filemap_map_pages+0xc2e/0xd80
  filemap_map_pages at mm/filemap.c:2625
  do_fault+0x3da/0x920
  __handle_mm_fault+0xc69/0xd00
  handle_mm_fault+0xfc/0x2f0
  do_page_fault+0x263/0x6f9
  page_fault+0x34/0x40

 Reported by Kernel Concurrency Sanitizer on:
 CPU: 32 PID: 3313 Comm: systemd-udevd Tainted: G        W    L 5.5.0-next-20200210+ #1
 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019

ra.mmap_miss is used to contribute the readahead decisions, a data race
could be undesirable.  Both the read and write is only under non-exclusive
mmap_sem, two concurrent writers could even underflow the counter.  Fix
the underflow by writing to a local variable before committing a final
store to ra.mmap_miss given a small inaccuracy of the counter should be
acceptable.
Signed-off-by: NKirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: NQian Cai <cai@lca.pw>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Tested-by: NQian Cai <cai@lca.pw>
Reviewed-by: NMatthew Wilcox (Oracle) <willy@infradead.org>
Cc: Marco Elver <elver@google.com>
Link: http://lkml.kernel.org/r/20200211030134.1847-1-cai@lca.pwSigned-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
Conflicts:
	mm/filemap.c
[Peng Liu: cherry-pick from e630bfac]
Signed-off-by: NPeng Liu <liupeng256@huawei.com>
Reviewed-by: Ntong tiangen <tongtiangen@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

mm/filemap.c

@@ -2530,6 +2530,7 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
 				   pgoff_t offset)
 {
 	struct address_space *mapping = file->f_mapping;
+	unsigned int mmap_miss;
 
 	/* If we don't want any read-ahead, don't bother */
 	if (vma->vm_flags & VM_RAND_READ)
@@ -2544,14 +2545,15 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
 	}
 
 	/* Avoid banging the cache line if not needed */
-	if (ra->mmap_miss < MMAP_LOTSAMISS * 10)
-		ra->mmap_miss++;
+	mmap_miss = READ_ONCE(ra->mmap_miss);
+	if (mmap_miss < MMAP_LOTSAMISS * 10)
+		WRITE_ONCE(ra->mmap_miss, ++mmap_miss);
 
 	/*
 	 * Do we miss much more than hit in this file? If so,
 	 * stop bothering with read-ahead. It will only hurt.
 	 */
-	if (ra->mmap_miss > MMAP_LOTSAMISS)
+	if (mmap_miss > MMAP_LOTSAMISS)
 		return;
 
 	/*
@@ -2574,12 +2576,14 @@ static void do_async_mmap_readahead(struct vm_area_struct *vma,
 				    pgoff_t offset)
 {
 	struct address_space *mapping = file->f_mapping;
+	unsigned int mmap_miss;
 
 	/* If we don't want any read-ahead, don't bother */
 	if (vma->vm_flags & VM_RAND_READ)
 		return;
-	if (ra->mmap_miss > 0)
-		ra->mmap_miss--;
+	mmap_miss = READ_ONCE(ra->mmap_miss);
+	if (mmap_miss)
+		WRITE_ONCE(ra->mmap_miss, --mmap_miss);
 	if (PageReadahead(page))
 		page_cache_async_readahead(mapping, ra, file,
 					   page, offset, ra->ra_pages);
@@ -2739,6 +2743,7 @@ void filemap_map_pages(struct vm_fault *vmf,
 	pgoff_t last_pgoff = start_pgoff;
 	unsigned long max_idx;
 	struct page *head, *page;
+	unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
 
 	rcu_read_lock();
 	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start_pgoff) {
@@ -2786,8 +2791,8 @@ void filemap_map_pages(struct vm_fault *vmf,
 		if (page->index >= max_idx)
 			goto unlock;
 
-		if (file->f_ra.mmap_miss > 0)
-			file->f_ra.mmap_miss--;
+		if (mmap_miss > 0)
+			mmap_miss--;
 
 		vmf->address += (iter.index - last_pgoff) << PAGE_SHIFT;
 		if (vmf->pte)
@@ -2809,6 +2814,7 @@ void filemap_map_pages(struct vm_fault *vmf,
 			break;
 	}
 	rcu_read_unlock();
+	WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
 }
 EXPORT_SYMBOL(filemap_map_pages);