Received-SPF: pass (google.com: domain of linux-kernel+bounces-174632-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
Message-ID: <34f29631-af45-462a-a168-e9f4bb4451cf@samsung.com>
Date: Thu, 9 May 2024 17:27:31 +0200
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH] dma: fix DMA sync for drivers not calling
 dma_set_mask*()
To: Alexander Lobakin <aleksander.lobakin@intel.com>, Christoph Hellwig
	<hch@lst.de>
Cc: Eric Dumazet <edumazet@google.com>, Jakub Kicinski <kuba@kernel.org>,
	Steven Price <steven.price@arm.com>, Robin Murphy <robin.murphy@arm.com>,
	Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>, "Rafael J.
 Wysocki" <rafael@kernel.org>, Magnus Karlsson <magnus.karlsson@intel.com>,
	nex.sw.ncis.osdt.itp.upstreaming@intel.com, bpf@vger.kernel.org,
	netdev@vger.kernel.org, iommu@lists.linux.dev, linux-kernel@vger.kernel.org
Content-Language: en-US
From: Marek Szyprowski <m.szyprowski@samsung.com>
In-Reply-To: <20240509144616.938519-1-aleksander.lobakin@intel.com>
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset="utf-8"
CMS-TYPE: 201P
References: <CGME20240509144704eucas1p2fe6bfb07a9b39f548e7db0f24e47eb0a@eucas1p2.samsung.com>
	<20240509144616.938519-1-aleksander.lobakin@intel.com>

On 09.05.2024 16:46, Alexander Lobakin wrote:
> There are several reports that the DMA sync shortcut broke non-coherent
> devices.
> dev->dma_need_sync is false after the &device allocation and if a driver
> didn't call dma_set_mask*(), it will still be false even if the device
> is not DMA-coherent and thus needs synchronizing. Due to historical
> reasons, there's still a lot of drivers not calling it.
> Invert the boolean, so that the sync will be performed by default and
> the shortcut will be enabled only when calling dma_set_mask*().
>
> Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
> Closes: https://lore.kernel.org/lkml/46160534-5003-4809-a408-6b3a3f4921e9@samsung.com
> Reported-by: Steven Price <steven.price@arm.com>
> Closes: https://lore.kernel.org/lkml/010686f5-3049-46a1-8230-7752a1b433ff@arm.com
> Fixes: 32ba8b823252 ("dma: avoid redundant calls for sync operations")
> Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
> ---
>   include/linux/device.h      |  4 ++--
>   include/linux/dma-map-ops.h |  4 ++--
>   include/linux/dma-mapping.h |  2 +-
>   kernel/dma/mapping.c        | 10 +++++-----
>   kernel/dma/swiotlb.c        |  2 +-
>   5 files changed, 11 insertions(+), 11 deletions(-)
>
> diff --git a/include/linux/device.h b/include/linux/device.h
> index ed95b829f05b..d4b50accff26 100644
> --- a/include/linux/device.h
> +++ b/include/linux/device.h
> @@ -691,7 +691,7 @@ struct device_physical_location {
>    *		and optionall (if the coherent mask is large enough) also
>    *		for dma allocations.  This flag is managed by the dma ops
>    *		instance from ->dma_supported.
> - * @dma_need_sync: The device needs performing DMA sync operations.
> + * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers.
>    *
>    * At the lowest level, every device in a Linux system is represented by an
>    * instance of struct device. The device structure contains the information
> @@ -805,7 +805,7 @@ struct device {
>   	bool			dma_ops_bypass : 1;
>   #endif
>   #ifdef CONFIG_DMA_NEED_SYNC
> -	bool			dma_need_sync:1;
> +	bool			dma_skip_sync:1;
>   #endif
>   };
>   
> diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
> index 4893cb89cb52..5217b922d29f 100644
> --- a/include/linux/dma-map-ops.h
> +++ b/include/linux/dma-map-ops.h
> @@ -280,8 +280,8 @@ static inline void dma_reset_need_sync(struct device *dev)
>   {
>   #ifdef CONFIG_DMA_NEED_SYNC
>   	/* Reset it only once so that the function can be called on hotpath */
> -	if (unlikely(!dev->dma_need_sync))
> -		dev->dma_need_sync = true;
> +	if (unlikely(dev->dma_skip_sync))
> +		dev->dma_skip_sync = false;
>   #endif
>   }
>   
> diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
> index eb4e15893b6c..f693aafe221f 100644
> --- a/include/linux/dma-mapping.h
> +++ b/include/linux/dma-mapping.h
> @@ -295,7 +295,7 @@ bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr);
>   static inline bool dma_dev_need_sync(const struct device *dev)
>   {
>   	/* Always call DMA sync operations when debugging is enabled */
> -	return dev->dma_need_sync || IS_ENABLED(CONFIG_DMA_API_DEBUG);
> +	return !dev->dma_skip_sync || IS_ENABLED(CONFIG_DMA_API_DEBUG);
>   }
>   
>   static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
> diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
> index 3524bc92c37f..3f77c3f8d16d 100644
> --- a/kernel/dma/mapping.c
> +++ b/kernel/dma/mapping.c
> @@ -392,7 +392,7 @@ bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr)
>   
>   	if (dma_map_direct(dev, ops))
>   		/*
> -		 * dma_need_sync could've been reset on first SWIOTLB buffer
> +		 * dma_skip_sync could've been reset on first SWIOTLB buffer
>   		 * mapping, but @dma_addr is not necessary an SWIOTLB buffer.
>   		 * In this case, fall back to more granular check.
>   		 */
> @@ -407,20 +407,20 @@ static void dma_setup_need_sync(struct device *dev)
>   
>   	if (dma_map_direct(dev, ops) || (ops->flags & DMA_F_CAN_SKIP_SYNC))
>   		/*
> -		 * dma_need_sync will be reset to %true on first SWIOTLB buffer
> +		 * dma_skip_sync will be reset to %false on first SWIOTLB buffer
>   		 * mapping, if any. During the device initialization, it's
>   		 * enough to check only for the DMA coherence.
>   		 */
> -		dev->dma_need_sync = !dev_is_dma_coherent(dev);
> +		dev->dma_skip_sync = dev_is_dma_coherent(dev);
>   	else if (!ops->sync_single_for_device && !ops->sync_single_for_cpu &&
>   		 !ops->sync_sg_for_device && !ops->sync_sg_for_cpu)
>   		/*
>   		 * Synchronization is not possible when none of DMA sync ops
>   		 * is set.
>   		 */
> -		dev->dma_need_sync = false;
> +		dev->dma_skip_sync = true;
>   	else
> -		dev->dma_need_sync = true;
> +		dev->dma_skip_sync = false;
>   }
>   #else /* !CONFIG_DMA_NEED_SYNC */
>   static inline void dma_setup_need_sync(struct device *dev) { }
> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
> index ae3e593eaadb..068134697cf1 100644
> --- a/kernel/dma/swiotlb.c
> +++ b/kernel/dma/swiotlb.c
> @@ -1409,7 +1409,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
>   	}
>   
>   	/*
> -	 * If dma_need_sync wasn't set, reset it on first SWIOTLB buffer
> +	 * If dma_skip_sync was set, reset it on first SWIOTLB buffer
>   	 * mapping to always sync SWIOTLB buffers.
>   	 */
>   	dma_reset_need_sync(dev);

Best regards
-- 
Marek Szyprowski, PhD
Samsung R&D Institute Poland