lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date:   Tue, 10 Jul 2018 13:56:42 +0300
From:   Leon Romanovsky <leon@...nel.org>
To:     Jan Dakinevich <jan.dakinevich@...tuozzo.com>
Cc:     Yishai Hadas <yishaih@...lanox.com>,
        Doug Ledford <dledford@...hat.com>,
        Jason Gunthorpe <jgg@...pe.ca>,
        Tariq Toukan <tariqt@...lanox.com>,
        "David S. Miller" <davem@...emloft.net>,
        linux-rdma@...r.kernel.org, linux-kernel@...r.kernel.org,
        netdev@...r.kernel.org, Denis Lunev <den@...tuozzo.com>,
        Konstantin Khorenko <khorenko@...tuozzo.com>
Subject: Re: [PATCH] ib/mlx4: adjust gfp flags for DMA allocations

On Mon, Jul 09, 2018 at 04:51:13PM +0300, Jan Dakinevich wrote:
> For most cases it is enough to use common GFP_KERNEL flag. However,
> there is one place with defined fallback path on unsuccessful allocation.
> In this case it would be preferred to append on first allocation attempt
> __GFP_NOWARN and __GFP_NORETRY flags to suppress possible warnings and
> to shorten the path to the fallback in a case of memory pressure.
>
> Signed-off-by: Jan Dakinevich <jan.dakinevich@...tuozzo.com>
> ---
>  drivers/infiniband/hw/mlx4/cq.c            |  2 +-
>  drivers/infiniband/hw/mlx4/qp.c            |  6 ++++--
>  drivers/infiniband/hw/mlx4/srq.c           |  2 +-
>  drivers/net/ethernet/mellanox/mlx4/alloc.c | 12 ++++++------
>  include/linux/mlx4/device.h                |  2 +-
>  5 files changed, 13 insertions(+), 11 deletions(-)
>

Thanks for the patch, however we are working on the patch to avoid
second call to mlx4_buf_alloc() and it will eliminate the annoying
WARN splat.

Because it is in latest stages of internal review, NAK.

Thanks

Download attachment "signature.asc" of type "application/pgp-signature" (802 bytes)

Powered by blists - more mailing lists