From: "Kirill A. Shutemov" <kirill@shutemov.name>
To: Matthew Wilcox <willy@infradead.org>
Cc: Qian Cai <cai@lca.pw>,
akpm@linux-foundation.org, elver@google.com, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH -next] mm/filemap: fix a data race in filemap_fault()
Date: Mon, 10 Feb 2020 21:05:46 +0300 [thread overview]
Message-ID: <20200210180546.vt7yhdjav5oinij7@box> (raw)
In-Reply-To: <20200210172511.GL8731@bombadil.infradead.org>
On Mon, Feb 10, 2020 at 09:25:11AM -0800, Matthew Wilcox wrote:
> On Mon, Feb 10, 2020 at 12:00:29PM -0500, Qian Cai wrote:
> > @@ -2622,7 +2622,7 @@ void filemap_map_pages(struct vm_fault *vmf,
> > if (page->index >= max_idx)
> > goto unlock;
> >
> > - if (file->f_ra.mmap_miss > 0)
> > + if (data_race(file->f_ra.mmap_miss > 0))
> > file->f_ra.mmap_miss--;
>
> How is this safe? Two threads can each see 1, and then both decrement the
> in-memory copy, causing it to end up at -1.
Right, it is bogus.
Below is my completely untested attempt on fix this. It still allows
races, but they will only lead to missed accounting, but not underflow.
diff --git a/mm/filemap.c b/mm/filemap.c
index 1784478270e1..1919d37c646a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2365,6 +2365,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
struct address_space *mapping = file->f_mapping;
struct file *fpin = NULL;
pgoff_t offset = vmf->pgoff;
+ unsigned mmap_miss;
/* If we don't want any read-ahead, don't bother */
if (vmf->vma->vm_flags & VM_RAND_READ)
@@ -2380,14 +2381,15 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
}
/* 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 fpin;
/*
@@ -2413,13 +2415,15 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
struct file_ra_state *ra = &file->f_ra;
struct address_space *mapping = file->f_mapping;
struct file *fpin = NULL;
+ unsigned int mmap_miss;
pgoff_t offset = vmf->pgoff;
/* If we don't want any read-ahead, don't bother */
if (vmf->vma->vm_flags & VM_RAND_READ)
return fpin;
- 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)) {
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
page_cache_async_readahead(mapping, ra, file,
@@ -2586,7 +2590,9 @@ void filemap_map_pages(struct vm_fault *vmf,
unsigned long max_idx;
XA_STATE(xas, &mapping->i_pages, start_pgoff);
struct page *page;
+ unsigned long mmap_miss;
+ mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
rcu_read_lock();
xas_for_each(&xas, page, end_pgoff) {
if (xas_retry(&xas, page))
@@ -2622,8 +2628,8 @@ 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 += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
if (vmf->pte)
@@ -2643,6 +2649,7 @@ 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);
--
Kirill A. Shutemov
next prev parent reply other threads:[~2020-02-10 18:05 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-10 17:00 [PATCH -next] mm/filemap: fix a data race in filemap_fault() Qian Cai
2020-02-10 17:25 ` Matthew Wilcox
2020-02-10 18:05 ` Kirill A. Shutemov [this message]
2020-02-10 19:58 ` Qian Cai
2020-02-10 21:21 ` Kirill A. Shutemov
2020-02-10 19:20 ` Qian Cai
2020-02-10 19:21 ` Matthew Wilcox
2020-02-10 20:28 ` Qian Cai
2020-02-10 20:44 ` Marco Elver
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200210180546.vt7yhdjav5oinij7@box \
--to=kirill@shutemov.name \
--cc=akpm@linux-foundation.org \
--cc=cai@lca.pw \
--cc=elver@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).