Received-SPF: pass (google.com: domain of linux-wireless-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
Date:   Fri, 25 Mar 2022 16:25:08 +0100
From:   Halil Pasic <pasic@linux.ibm.com>
To:     Robin Murphy <robin.murphy@arm.com>
Cc:     Linus Torvalds <torvalds@linux-foundation.org>,
        Oleksandr Natalenko <oleksandr@natalenko.name>,
        Christoph Hellwig <hch@lst.de>,
        Marek Szyprowski <m.szyprowski@samsung.com>,
        Toke =?UTF-8?B?SMO4aWxhbmQtSsO4?= =?UTF-8?B?cmdlbnNlbg==?= 
        <toke@toke.dk>, Kalle Valo <kvalo@kernel.org>,
        "David S. Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        Olha Cherevyk <olha.cherevyk@gmail.com>,
        iommu <iommu@lists.linux-foundation.org>,
        linux-wireless <linux-wireless@vger.kernel.org>,
        Netdev <netdev@vger.kernel.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        stable <stable@vger.kernel.org>,
        Halil Pasic <pasic@linux.ibm.com>
Subject: Re: [REGRESSION] Recent swiotlb DMA_FROM_DEVICE fixes break
 ath9k-based AP
Message-ID: <20220325162508.3273e0db.pasic@linux.ibm.com>
In-Reply-To: <20220324190216.0efa067f.pasic@linux.ibm.com>
References: <1812355.tdWV9SEqCh@natalenko.name>
        <CAHk-=wiwz+Z2MaP44h086jeniG-OpK3c=FywLsCwXV7Crvadrg@mail.gmail.com>
        <27b5a287-7a33-9a8b-ad6d-04746735fb0c@arm.com>
        <CAHk-=wip7TCD_+2STTepuEZvGMg6wcz+o=kyFUvHjuKziTMixw@mail.gmail.com>
        <f88ca616-96d1-82dc-1bc8-b17480e937dd@arm.com>
        <20220324190216.0efa067f.pasic@linux.ibm.com>
Organization: IBM
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 8bit
Precedence: bulk

On Thu, 24 Mar 2022 19:02:16 +0100
Halil Pasic <pasic@linux.ibm.com> wrote:

> > I'll admit I still never quite grasped the reason for also adding the 
> > override to swiotlb_sync_single_for_device() in aa6f8dcbab47, but I 
> > think by that point we were increasingly tired and confused and starting 
> > to second-guess ourselves (well, I was, at least).  
> 
> I raised the question, do we need to do the same for
> swiotlb_sync_single_for_device(). Did that based on my understanding of the
> DMA API documentation. I had the following scenario in mind
> 
> SWIOTLB without the snyc_single:
>                                   Memory      Bounce buffer      Owner
> --------------------------------------------------------------------------
> start                             12345678    xxxxxxxx             C
> dma_map(DMA_FROM_DEVICE)          12345678 -> 12345678             C->D
> device writes partial data        12345678    12ABC678 <- ABC      D
> sync_for_cpu(DMA_FROM_DEVICE)     12ABC678 <- 12ABC678             D->C
> cpu modifies buffer               66666666    12ABC678             C
> sync_for_device(DMA_FROM_DEVICE)  66666666    12ABC678             C->D
> device writes partial data        66666666    1EFGC678 <-EFG       D
> dma_unmap(DMA_FROM_DEVICE)        1EFGC678 <- 1EFGC678             D->C
> 
> Legend: in Owner column C stands for cpu and D for device.
> 
> Without swiotlb, I believe we should have arrived at 6EFG6666. To get the
> same result, IMHO, we need to do a sync in sync_for_device().
> And aa6f8dcbab47 is an imperfect solution to that (because of size).
> 

@Robin, Christoph: Do we consider this a valid scenario?

Regards,
Halil