Return-Path: From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Mikulas Patocka , Heinz Mauelshagen , NeilBrown Subject: [PATCH 3.18 18/39] md/raid5: fix another livelock caused by non-aligned writes. Date: Mon, 9 Feb 2015 16:34:01 +0800 Message-Id: <20150209083329.638725464@linuxfoundation.org> In-Reply-To: <20150209083328.753647350@linuxfoundation.org> References: <20150209083328.753647350@linuxfoundation.org> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15 Sender: linux-kernel-owner@vger.kernel.org List-ID: 3.18-stable review patch. If anyone has any objections, please let me know. ------------------ From: NeilBrown commit b1b02fe97f75b12ab34b2303bfd4e3526d903a58 upstream. If a non-page-aligned write is destined for a device which is missing/faulty, we can deadlock. As the target device is missing, a read-modify-write cycle is not possible. As the write is not for a full-page, a recontruct-write cycle is not possible. This should be handled by logic in fetch_block() which notices there is a non-R5_OVERWRITE write to a missing device, and so loads all blocks. However since commit 67f455486d2ea2, that code requires STRIPE_PREREAD_ACTIVE before it will active, and those circumstances never set STRIPE_PREREAD_ACTIVE. So: in handle_stripe_dirtying, if neither rmw or rcw was possible, set STRIPE_DELAYED, which will cause STRIPE_PREREAD_ACTIVE be set after a suitable delay. Fixes: 67f455486d2ea20b2d94d6adf5b9b783d079e321 Reported-by: Mikulas Patocka Tested-by: Heinz Mauelshagen Signed-off-by: NeilBrown Signed-off-by: Greg Kroah-Hartman --- drivers/md/raid5.c | 5 +++++ 1 file changed, 5 insertions(+) --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3195,6 +3195,11 @@ static void handle_stripe_dirtying(struc (unsigned long long)sh->sector, rcw, qread, test_bit(STRIPE_DELAYED, &sh->state)); } + + if (rcw > disks && rmw > disks && + !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + set_bit(STRIPE_DELAYED, &sh->state); + /* now if nothing is locked, and if we have enough data, * we can start a write request */