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;
From:   Sanket Parmar <sparmar@cadence.com>
To:     Peter Chen <peter.chen@kernel.org>
CC:     Pawel Laszczak <pawell@cadence.com>,
        "a-govindraju@ti.com" <a-govindraju@ti.com>,
        "linux-usb@vger.kernel.org" <linux-usb@vger.kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        Rahul Kumar <kurahul@cadence.com>,
        "gregkh@linuxfoundation.org" <gregkh@linuxfoundation.org>,
        "kishon@ti.com" <kishon@ti.com>,
        "hch@infradead.org" <hch@infradead.org>
Subject: RE: [PATCH v2] usb: cdns3: Optimize DMA request buffer allocation
Thread-Topic: [PATCH v2] usb: cdns3: Optimize DMA request buffer allocation
Thread-Index: AQHXG2HVTwRhsyf3N0aVH9FwBZjdNqqMmo+AgAM6/uA=
Date:   Mon, 22 Mar 2021 10:30:53 +0000
Message-ID: <BY5PR07MB8119561FE06198D12F1771D0B0659@BY5PR07MB8119.namprd07.prod.outlook.com>
References: <1616008439-15494-1-git-send-email-sparmar@cadence.com>
 <20210320090858.GB28364@b29397-desktop>
In-Reply-To: <20210320090858.GB28364@b29397-desktop>
Accept-Language: en-US
Content-Language: en-US
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: d9bfae40-eb5b-4239-1242-08d8ed1d9293
X-MS-Exchange-CrossTenant-originalarrivaltime: 22 Mar 2021 10:30:53.9890
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: d36035c5-6ce6-4662-a3dc-e762e61ae4c9
X-MS-Exchange-CrossTenant-mailboxtype: HOSTED
X-MS-Exchange-CrossTenant-userprincipalname: LvQJMu/M2lvfj28dV48HN/6QznTSmtbQb9ercGaJEzkJVUjZrsBCAvfDdSCS8LSMqPQfKKcOVGKeyVHu3HNzWUv5dkKUHUITuKvGtGpR/r0=
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BYAPR07MB6327
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.369,18.0.761
 definitions=2021-03-22_04:2021-03-22,2021-03-22 signatures=0
X-Proofpoint-Spam-Details: rule=outbound_check_notspam policy=outbound_check score=0 adultscore=0
 phishscore=0 mlxlogscore=803 clxscore=1015 impostorscore=0 suspectscore=0
 mlxscore=0 spamscore=0 malwarescore=0 priorityscore=1501
 lowpriorityscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx
 scancount=1 engine=8.12.0-2009150000 definitions=main-2103220074
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Hi Peter,

> On 21-03-17 20:13:59, Sanket Parmar wrote:
> > dma_alloc_coherent() might fail on the platform with a small
> > DMA region.
> >
> > To avoid such failure in cdns3_prepare_aligned_request_buf(),
> > dma_alloc_coherent() is replaced with dma_alloc_noncoherent()
> > to allocate aligned request buffer of dynamic length.
> >
> > Reported-by: Aswath Govindraju <a-govindraju@ti.com>
> > Signed-off-by: Sanket Parmar <sparmar@cadence.com>
> > ---
> >
> > Changelog:
> > v2:
> > - used dma_*_noncoherent() APIs
> > - changed the commit log
> >
> >  drivers/usb/cdns3/cdns3-gadget.c | 30 ++++++++++++++++++++++++-----
> -
> >  drivers/usb/cdns3/cdns3-gadget.h |  2 ++
> >  2 files changed, 26 insertions(+), 6 deletions(-)
> >
> > diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3=
-
> gadget.c
> > index 0b892a2..126087b 100644
> > --- a/drivers/usb/cdns3/cdns3-gadget.c
> > +++ b/drivers/usb/cdns3/cdns3-gadget.c
> > @@ -819,9 +819,15 @@ void cdns3_gadget_giveback(struct
> cdns3_endpoint *priv_ep,
> >  					priv_ep->dir);
> >
> >  	if ((priv_req->flags & REQUEST_UNALIGNED) &&
> > -	    priv_ep->dir =3D=3D USB_DIR_OUT && !request->status)
> > +	    priv_ep->dir =3D=3D USB_DIR_OUT && !request->status) {
> > +		/* Make DMA buffer CPU accessible */
> > +		dma_sync_single_for_cpu(priv_dev->sysdev,
> > +			priv_req->aligned_buf->dma,
> > +			priv_req->aligned_buf->size,
> > +			priv_req->aligned_buf->dir);
> >  		memcpy(request->buf, priv_req->aligned_buf->buf,
> >  		       request->length);
> > +	}
> >
> >  	priv_req->flags &=3D ~(REQUEST_PENDING | REQUEST_UNALIGNED);
> >  	/* All TRBs have finished, clear the counter */
> > @@ -883,8 +889,8 @@ static void cdns3_free_aligned_request_buf(struct
> work_struct *work)
> >  			 * interrupts.
> >  			 */
> >  			spin_unlock_irqrestore(&priv_dev->lock, flags);
> > -			dma_free_coherent(priv_dev->sysdev, buf->size,
> > -					  buf->buf, buf->dma);
> > +			dma_free_noncoherent(priv_dev->sysdev, buf-
> >size,
> > +					  buf->buf, buf->dma, buf->dir);
> >  			kfree(buf);
> >  			spin_lock_irqsave(&priv_dev->lock, flags);
> >  		}
> > @@ -911,10 +917,13 @@ static int
> cdns3_prepare_aligned_request_buf(struct cdns3_request *priv_req)
> >  			return -ENOMEM;
> >
> >  		buf->size =3D priv_req->request.length;
> > +		buf->dir =3D usb_endpoint_dir_in(priv_ep->endpoint.desc) ?
> > +			DMA_TO_DEVICE : DMA_FROM_DEVICE;
> >
> > -		buf->buf =3D dma_alloc_coherent(priv_dev->sysdev,
> > +		buf->buf =3D dma_alloc_noncoherent(priv_dev->sysdev,
> >  					      buf->size,
> >  					      &buf->dma,
> > +					      buf->dir,
> >  					      GFP_ATOMIC);
> >  		if (!buf->buf) {
> >  			kfree(buf);
> > @@ -936,10 +945,18 @@ static int
> cdns3_prepare_aligned_request_buf(struct cdns3_request *priv_req)
> >  	}
> >
> >  	if (priv_ep->dir =3D=3D USB_DIR_IN) {
> > +		/* Make DMA buffer CPU accessible */
> > +		dma_sync_single_for_cpu(priv_dev->sysdev,
> > +			buf->dma, buf->size, buf->dir);
> >  		memcpy(buf->buf, priv_req->request.buf,
> >  		       priv_req->request.length);
> >  	}
> >
> > +	/* Transfer DMA buffer ownership back to device */
> > +	dma_sync_single_for_device(priv_dev->sysdev,
> > +			buf->dma, buf->size, buf->dir);
> > +
> > +
>=20
> One more blank line.
>=20
> Otherwise, it seems OK for me.

I have remove this blank line. New patch has been posted already.

>=20
> >  	priv_req->flags |=3D REQUEST_UNALIGNED;
> >  	trace_cdns3_prepare_aligned_request(priv_req);
> >
> > @@ -3088,9 +3105,10 @@ static void cdns3_gadget_exit(struct cdns *cdns)
> >  		struct cdns3_aligned_buf *buf;
> >
> >  		buf =3D cdns3_next_align_buf(&priv_dev->aligned_buf_list);
> > -		dma_free_coherent(priv_dev->sysdev, buf->size,
> > +		dma_free_noncoherent(priv_dev->sysdev, buf->size,
> >  				  buf->buf,
> > -				  buf->dma);
> > +				  buf->dma,
> > +				  buf->dir);
> >
> >  		list_del(&buf->list);
> >  		kfree(buf);
> > diff --git a/drivers/usb/cdns3/cdns3-gadget.h b/drivers/usb/cdns3/cdns3=
-
> gadget.h
> > index ecf9b91..c5660f2 100644
> > --- a/drivers/usb/cdns3/cdns3-gadget.h
> > +++ b/drivers/usb/cdns3/cdns3-gadget.h
> > @@ -12,6 +12,7 @@
> >  #ifndef __LINUX_CDNS3_GADGET
> >  #define __LINUX_CDNS3_GADGET
> >  #include <linux/usb/gadget.h>
> > +#include <linux/dma-direction.h>
> >
> >  /*
> >   * USBSS-DEV register interface.
> > @@ -1205,6 +1206,7 @@ struct cdns3_aligned_buf {
> >  	void			*buf;
> >  	dma_addr_t		dma;
> >  	u32			size;
> > +	enum dma_data_direction dir;
> >  	unsigned		in_use:1;
> >  	struct list_head	list;
> >  };
> > --
> > 2.4.5
> >
>=20
> --
>=20
> Thanks,
> Peter Chen

Thanks,
Sanket