New subject: [PATCH kernel-4.19 2/3] page_alloc: consider highatomic reserve in watermark fast

3 Sep 2021

From: "Kirill A. Shutemov" kirill@shutemov.name
mainline inclusion
from mainline-v5.9-rc1
commit e630bfac79456d3acd22c9286b50e83aafb7a07c
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: Kirill A. Shutemov kirill@shutemov.name
Signed-off-by: Qian Cai cai@lca.pw
Signed-off-by: Andrew Morton akpm@linux-foundation.org
Tested-by: Qian Cai cai@lca.pw
Reviewed-by: Matthew Wilcox (Oracle) willy@infradead.org
Cc: Marco Elver elver@google.com
Link: http://lkml.kernel.org/r/20200211030134.1847-1-cai@lca.pw
Signed-off-by: Linus Torvalds torvalds@linux-foundation.org
Conflicts:
    mm/filemap.c
[Peng Liu: cherry-pick from e630bfac79456d3acd22c9286b50e83aafb7a07c]
Signed-off-by: Peng Liu liupeng256@huawei.com
Reviewed-by: tong tiangen tongtiangen@huawei.com
Signed-off-by: Yang Yingliang yangyingliang@huawei.com
---
 mm/filemap.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 5c33c40e80192..4cf4b096d5b63 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2528,6 +2528,7 @@ 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)
@@ -2542,14 +2543,15 @@ 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;
/*
@@ -2572,12 +2574,14 @@ 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);
@@ -2737,6 +2741,7 @@ 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) {
@@ -2784,8 +2789,8 @@ 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)
@@ -2807,6 +2812,7 @@ 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);
-- 
2.25.1

    

[PATCH kernel-4.19 1/3] mm/filemap.c: fix a data race in filemap_fault()