[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <AM0PR04MB6004C29F992ACA290E63E687E717A@AM0PR04MB6004.eurprd04.prod.outlook.com>
Date: Mon, 14 Aug 2023 06:36:03 +0000
From: Gaurav Jain <gaurav.jain@....com>
To: Meenakshi Aggarwal <meenakshi.aggarwal@....com>,
Horia Geanta <horia.geanta@....com>,
Varun Sethi <V.Sethi@....com>,
Pankaj Gupta <pankaj.gupta@....com>,
"herbert@...dor.apana.org.au" <herbert@...dor.apana.org.au>,
"davem@...emloft.net" <davem@...emloft.net>,
"linux-crypto@...r.kernel.org" <linux-crypto@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
CC: Iuliana Prodan <iuliana.prodan@....com>
Subject: RE: [PATCH] crypto: caam - increase the domain of write memory
barrier to full system
Reviewed-by: Gaurav Jain <gaurav.jain@....com>
> -----Original Message-----
> From: Meenakshi Aggarwal <meenakshi.aggarwal@....com>
> Sent: Tuesday, August 8, 2023 4:25 PM
> To: Horia Geanta <horia.geanta@....com>; Varun Sethi <V.Sethi@....com>;
> Pankaj Gupta <pankaj.gupta@....com>; Gaurav Jain <gaurav.jain@....com>;
> herbert@...dor.apana.org.au; davem@...emloft.net; linux-
> crypto@...r.kernel.org; linux-kernel@...r.kernel.org
> Cc: Iuliana Prodan <iuliana.prodan@....com>; Meenakshi Aggarwal
> <meenakshi.aggarwal@....com>
> Subject: [PATCH] crypto: caam - increase the domain of write memory barrier to
> full system
>
> From: Iuliana Prodan <iuliana.prodan@....com>
>
> In caam_jr_enqueue, under heavy DDR load, smp_wmb() or dma_wmb() fail to
> make the input ring be updated before the CAAM starts reading it. So, CAAM will
> process, again, an old descriptor address and will put it in the output ring. This
> will make caam_jr_dequeue() to fail, since this old descriptor is not in the
> software ring.
> To fix this, use wmb() which works on the full system instead of inner/outer
> shareable domains.
>
> Signed-off-by: Iuliana Prodan <iuliana.prodan@....com>
> Signed-off-by: Meenakshi Aggarwal <meenakshi.aggarwal@....com>
> ---
> drivers/crypto/caam/jr.c | 10 +++++++++-
> 1 file changed, 9 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c index
> 767fbf052536..5507d5d34a4c 100644
> --- a/drivers/crypto/caam/jr.c
> +++ b/drivers/crypto/caam/jr.c
> @@ -464,8 +464,16 @@ int caam_jr_enqueue(struct device *dev, u32 *desc,
> * Guarantee that the descriptor's DMA address has been written to
> * the next slot in the ring before the write index is updated, since
> * other cores may update this index independently.
> + *
> + * Under heavy DDR load, smp_wmb() or dma_wmb() fail to make the
> input
> + * ring be updated before the CAAM starts reading it. So, CAAM will
> + * process, again, an old descriptor address and will put it in the
> + * output ring. This will make caam_jr_dequeue() to fail, since this
> + * old descriptor is not in the software ring.
> + * To fix this, use wmb() which works on the full system instead of
> + * inner/outer shareable domains.
> */
> - smp_wmb();
> + wmb();
>
> jrp->head = (head + 1) & (JOBR_DEPTH - 1);
>
> --
> 2.25.1
Powered by blists - more mailing lists