Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Tue, 5 Oct 2021 15:22:00 -0300
From:   Jason Gunthorpe <jgg@nvidia.com>
To:     Logan Gunthorpe <logang@deltatee.com>
Cc:     Doug Ledford <dledford@redhat.com>, linux-rdma@vger.kernel.org,
        linux-kernel@vger.kernel.org,
        Zheng Yongjun <zhengyongjun3@huawei.com>,
        Wenpeng Liang <liangwenpeng@huawei.com>,
        Leon Romanovsky <leon@kernel.org>,
        Weihang Li <liweihang@huawei.com>,
        Mark Bloch <mbloch@nvidia.com>
Subject: Re: [PATCH] RDMA/rw: switch to dma_map_sgtable()
Message-ID: <20211005182200.GA2677974@nvidia.com>
References: <20211001213215.3761-1-logang@deltatee.com>
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20211001213215.3761-1-logang@deltatee.com>
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?4ZjUpcb7XaFIq4IY2o9MnCKG+iSs3/6Ue4BxwFmCuC40apCRRK0EoT04B0q+?=
 =?us-ascii?Q?NG0NFahBroRE/InhWeK53PGcKlWy4vyhGPtp+gEDAkYTPKbzQBr6kTS9NqQH?=
 =?us-ascii?Q?WkvvlENmKO5FLSQZLzEDccJjHtgmpRjJRKE+Enfhug4au6r4aRt2Ur5g08m3?=
 =?us-ascii?Q?lLP60E/Qka/GUUzh4mkMuQwS0mIeQejnI1TSrpZPr9vd2sM6yN+Q8pXDV4Pw?=
 =?us-ascii?Q?A1gWXyG1DIprvzd4xIn4RsHoC7Fix2SQqSXWiERC+l1dZ9vzHgUDndkRMkfN?=
 =?us-ascii?Q?xApEoXg6n7QPcCA2JiV1ZGgynmehOaXT0uSKLun4b+H/SkG1wRmtZ6B8qeyg?=
 =?us-ascii?Q?LK8DVpS/pf8FedhNFb8fMatBTCLeSV/ZPtRYNUOoKNGQkcrVpy2TmvdqXN8x?=
 =?us-ascii?Q?wbRHkXPTBspPGLpp2VG6wqvOPvUr35BPvaNGHAs11vXU5yHQ0nZuhKb2MMFX?=
 =?us-ascii?Q?Dg2+g/qpocbt23o9vhtp1axqBzY41TlhytJErQjte2wYNyc9s4SPiLObU18w?=
 =?us-ascii?Q?g7v9LZH4kqlviSiC5e0VuJkKuUBn+OqzuSJxGxCniYUQMcv3bgMETwnvT94r?=
 =?us-ascii?Q?cRodIgdyth2N0zBqItBlonKV77A8NqarDM5v1vkKFgz4CJVqqXUjeEIP/OXx?=
 =?us-ascii?Q?biui/YB0mqqzpu0RUfzLWo2MwKNiMDSrahDx/1mXZ0YewnvMsp3543M0xpTv?=
 =?us-ascii?Q?E4cbDv8452B6ZTFHfXTqBtUKGZbz0FHwsb24kjC8i5ViML3LMM7EMcQMtlc4?=
 =?us-ascii?Q?IaUKxOfiuFPKkw1oq3ER8srMNiX6FwzO4d3v9jpqeeMDnRzRcLlCI46Y3YSa?=
 =?us-ascii?Q?VhAh5JmBFj1FbrHIzCb+jBr0lFaS/W2IOqBJRg7nw1tFxMFzV98beaUVFgRY?=
 =?us-ascii?Q?JxmgCWlUJ4noRBbKKiVkJzupYm759k4sFca6UrZl8GxtAFVTi2ONpp5ee0JZ?=
 =?us-ascii?Q?hmUYWWKuqxYS59/9LYDeklscbB2x90V5xOwzPMnIQ7dc4nW/nKuyI4laKOrH?=
 =?us-ascii?Q?mHuuUu1T+wDeCFH3/2gt9qD9F4LpjpNewleyCC1ARMMNS7mC04c+VpnwCmw7?=
 =?us-ascii?Q?wAM70qkte3uRHIDDs8rLxDYBWKo//uTCDrxPnLB5QC5RyX6qY9sMipRpWuys?=
 =?us-ascii?Q?uwdcILgeN7gwpymXh0Efzpk0JQgKvXWmUt7/6nDX7L+oi+tGLbmxxONmkgAn?=
 =?us-ascii?Q?0QS9iLVG8HhBO7l7TP4WlIc2EjpaXsBGGhik0JyvAXb7yz3BRbLq72Olg2Hv?=
 =?us-ascii?Q?U5wiEkTU+axtcvkeAt5GQ6J44PKiKZ346ye4LVgxW4TG9vNd/UJLktZCPRHI?=
 =?us-ascii?Q?DO80mMUdffar+4WcHBGu20nC2r4XJNYrnzRfXV47CJw7OQ=3D=3D?=
X-OriginatorOrg: Nvidia.com
X-MS-Exchange-CrossTenant-Network-Message-Id: e0cb2a0a-e5f3-434f-9c88-08d9882d069d
X-MS-Exchange-CrossTenant-AuthSource: BL0PR12MB5506.namprd12.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 05 Oct 2021 18:22:01.8053
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: Pl6uD0BWMcKTLHXQkIFxEJE4aGKJ/tahRD62wHj3J4K8IAyM/02Nr4ogCFU+GoPG
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BL0PR12MB5553
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Fri, Oct 01, 2021 at 03:32:15PM -0600, Logan Gunthorpe wrote:
> There are a couple of subtle error path bugs related to mapping the
> sgls:
> 
> - In rdma_rw_ctx_init(), dma_unmap would be called with an sg that
>   could have been incremented from the original call, as well as an
>   nents that was not the original number of nents called when mapped.
> - Similarly in rdma_rw_ctx_signature_init, both sg and prot_sg were
>   unmapped with the incorrect number of nents.
> 
> To fix this, switch to the sgtable interface for mapping which
> conveniently stores the original nents for unmapping. This will get
> cleaned up further once the dma mapping interface supports P2PDMA and
> pci_p2pdma_map_sg() can be removed. At that point the sgtable interface
> will be preferred as it offers better error reporting for P2PDMA pages.
> 
> Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
 ---
>  drivers/infiniband/core/rw.c | 66 ++++++++++++++++++++++--------------
>  1 file changed, 41 insertions(+), 25 deletions(-)

Applied to for-next, thanks

Jason