From nobody Sat Apr 11 15:30:45 2026 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 638A2C19F2D for ; Tue, 9 Aug 2022 19:00:25 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1345229AbiHITAW (ORCPT ); Tue, 9 Aug 2022 15:00:22 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:35862 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1344058AbiHIS7u (ORCPT ); Tue, 9 Aug 2022 14:59:50 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 3A3DD26576 for ; Tue, 9 Aug 2022 11:32:22 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1660069940; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: in-reply-to:in-reply-to:references:references; bh=k+BeaTfVMUnsn/KH0avfSZ9dOxb93xKAhJDQYTFb27o=; b=Pywua4lIm1yom4h8yR2iDxqUBp5ZO3XJeTg43pUAoGTbdvuAKckdkrFPd8xpA2uDR66UaF 0yJWuCe1sPSEaOLNPlqz66owJwnprXAPAvTQpO6bZtYAHG5I4RrXedmTcjq8vqRNsaWQ0m U2ZtztNMHuqvaqZCWOBFfEHymDdlbQQ= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-361-K9PfdN9eOnipk3nuBQkONg-1; Tue, 09 Aug 2022 14:32:17 -0400 X-MC-Unique: K9PfdN9eOnipk3nuBQkONg-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 20F2B3C10226; Tue, 9 Aug 2022 18:32:15 +0000 (UTC) Received: from file01.intranet.prod.int.rdu2.redhat.com (file01.intranet.prod.int.rdu2.redhat.com [10.11.5.7]) by smtp.corp.redhat.com (Postfix) with ESMTPS id CC6B9492C3B; Tue, 9 Aug 2022 18:32:14 +0000 (UTC) Received: from file01.intranet.prod.int.rdu2.redhat.com (localhost [127.0.0.1]) by file01.intranet.prod.int.rdu2.redhat.com (8.14.4/8.14.4) with ESMTP id 279IWE3A015903; Tue, 9 Aug 2022 14:32:14 -0400 Received: from localhost (mpatocka@localhost) by file01.intranet.prod.int.rdu2.redhat.com (8.14.4/8.14.4/Submit) with ESMTP id 279IWDHD015899; Tue, 9 Aug 2022 14:32:14 -0400 X-Authentication-Warning: file01.intranet.prod.int.rdu2.redhat.com: mpatocka owned process doing -bs Date: Tue, 9 Aug 2022 14:32:13 -0400 (EDT) From: Mikulas Patocka X-X-Sender: mpatocka@file01.intranet.prod.int.rdu2.redhat.com To: Matthew Wilcox cc: Linus Torvalds , Will Deacon , "Paul E. McKenney" , Ard Biesheuvel , Alexander Viro , Alan Stern , Andrea Parri , Peter Zijlstra , Boqun Feng , Nicholas Piggin , David Howells , Jade Alglave , Luc Maranget , Akira Yokosawa , Daniel Lustig , Joel Fernandes , Linux Kernel Mailing List , linux-arch , linux-fsdevel@vger.kernel.org Subject: [PATCH v6] add barriers to buffer_uptodate and set_buffer_uptodate In-Reply-To: Message-ID: References: User-Agent: Alpine 2.02 (LRH 1266 2009-07-14) MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.85 on 10.11.54.10 Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Transfer-Encoding: quoted-printable Content-Type: TEXT/PLAIN; charset="utf-8" On Mon, 8 Aug 2022, Matthew Wilcox wrote: > On Mon, Aug 08, 2022 at 10:57:45AM -0400, Mikulas Patocka wrote: > > On Mon, 8 Aug 2022, Matthew Wilcox wrote: > >=20 > > > On Mon, Aug 08, 2022 at 10:26:10AM -0400, Mikulas Patocka wrote: > > > > On Sun, 7 Aug 2022, Matthew Wilcox wrote: > > > > > > +static __always_inline void set_buffer_locked(struct buffer_he= ad *bh) > > > > > > +{ > > > > > > + set_bit(BH_Lock, &bh->b_state); > > > > > > +} > > > > > > + > > > > > > +static __always_inline int buffer_locked(const struct buffer_h= ead *bh) > > > > > > +{ > > > > > > + bool ret =3D test_bit(BH_Lock, &bh->b_state); > > > > > > + /* > > > > > > + * pairs with smp_mb__after_atomic in unlock_buffer > > > > > > + */ > > > > > > + if (!ret) > > > > > > + smp_acquire__after_ctrl_dep(); > > > > > > + return ret; > > > > > > +} > > > > >=20 > > > > > Are there places that think that lock/unlock buffer implies a mem= ory > > > > > barrier? > > > >=20 > > > > There's this in fs/reiserfs: > > > >=20 > > > > if (!buffer_dirty(bh) && !buffer_locked(bh)) { > > > > reiserfs_free_jh(bh); <--- this could be moved before buffer_locked > > >=20 > > > It might be better to think of buffer_locked() as > > > buffer_someone_has_exclusive_access(). I can't see the problem with > > > moving the reads in reiserfs_free_jh() before the read of buffer_lock= ed. > > >=20 > > > > if (buffer_locked((journal->j_header_bh))) { > > > > ... > > > > } > > > > journal->j_last_flush_trans_id =3D trans_id; > > > > journal->j_first_unflushed_offset =3D offset; > > > > jh =3D (struct reiserfs_journal_header *)(journal->j_header_bh->b_d= ata); <--- this could be moved before buffer_locked > > >=20 > > > I don't think b_data is going to be changed while someone else holds > > > the buffer locked. That's initialised by set_bh_page(), which is an > > > initialisation-time thing, before the BH is visible to any other thre= ad. > >=20 > > So, do you think that we don't need a barrier in buffer_locked()? >=20 > That's my feeling. Of course, you might not be the only one confused, > and if fs authors in general have made the mistake of thinking that > buffer_locked is serialising, then it might be better to live up to > that expectation. In my spadfs filesystem, I used lock_buffer/unlock_buffer to prevent the=20 system from seeing or writing back incomplete data. The patterns is lock_buffer(bh); ... do several changes to the buffer that should appear atomically unlock_buffer(bh); mark_buffer_dirty(bh); but it seems to be ok, because both lock_buffer and unlock_buffer have=20 acquire/release semantics. I'm not sure about buffer_locked - perhaps it=20 really doesn't need the barriers - spin_is_locked, mutex_is_locked and=20 rwsem_is_locked also don't have any barriers. Here I'm sending the patch without the change to buffer_locked. Mikulas From: Mikulas Patocka Let's have a look at this piece of code in __bread_slow: get_bh(bh); bh->b_end_io =3D end_buffer_read_sync; submit_bh(REQ_OP_READ, 0, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; Neither wait_on_buffer nor buffer_uptodate contain any memory barrier. Consequently, if someone calls sb_bread and then reads the buffer data, the read of buffer data may be executed before wait_on_buffer(bh) on architectures with weak memory ordering and it may return invalid data. Fix this bug by adding a memory barrier to set_buffer_uptodate and an acquire barrier to buffer_uptodate (in a similar way as folio_test_uptodate and folio_mark_uptodate). Signed-off-by: Mikulas Patocka Cc: stable@vger.kernel.org Index: linux-2.6/include/linux/buffer_head.h =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D Reviewed-by: Matthew Wilcox (Oracle) --- linux-2.6.orig/include/linux/buffer_head.h +++ linux-2.6/include/linux/buffer_head.h @@ -117,7 +117,6 @@ static __always_inline int test_clear_bu * of the form "mark_buffer_foo()". These are higher-level functions which * do something in addition to setting a b_state bit. */ -BUFFER_FNS(Uptodate, uptodate) BUFFER_FNS(Dirty, dirty) TAS_BUFFER_FNS(Dirty, dirty) BUFFER_FNS(Lock, locked) @@ -135,6 +134,30 @@ BUFFER_FNS(Meta, meta) BUFFER_FNS(Prio, prio) BUFFER_FNS(Defer_Completion, defer_completion) =20 +static __always_inline void set_buffer_uptodate(struct buffer_head *bh) +{ + /* + * make it consistent with folio_mark_uptodate + * pairs with smp_load_acquire in buffer_uptodate + */ + smp_mb__before_atomic(); + set_bit(BH_Uptodate, &bh->b_state); +} + +static __always_inline void clear_buffer_uptodate(struct buffer_head *bh) +{ + clear_bit(BH_Uptodate, &bh->b_state); +} + +static __always_inline int buffer_uptodate(const struct buffer_head *bh) +{ + /* + * make it consistent with folio_test_uptodate + * pairs with smp_mb__before_atomic in set_buffer_uptodate + */ + return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) !=3D 0; +} + #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) =20 /* If we *know* page->private refers to buffer_heads */