Linux IOMMU Development
 help / color / mirror / Atom feed
From: Damien Le Moal via iommu <iommu@lists.linux-foundation.org>
To: John Garry <john.garry@huawei.com>,
	joro@8bytes.org, will@kernel.org, jejb@linux.ibm.com,
	martin.petersen@oracle.com, hch@lst.de, m.szyprowski@samsung.com,
	robin.murphy@arm.com
Cc: linux-scsi@vger.kernel.org, linux-doc@vger.kernel.org,
	linuxarm@huawei.com, iommu@lists.linux.dev,
	linux-kernel@vger.kernel.org, linux-ide@vger.kernel.org,
	iommu@lists.linux-foundation.org
Subject: Re: [PATCH v5 4/5] scsi: scsi_transport_sas: Cap shost max_sectors according to DMA optimal limit
Date: Fri, 1 Jul 2022 08:49:36 +0900	[thread overview]
Message-ID: <2e6475e5-4899-1e3a-1418-918b9510ec6d@opensource.wdc.com> (raw)
In-Reply-To: <1656590892-42307-5-git-send-email-john.garry@huawei.com>

On 6/30/22 21:08, John Garry wrote:
> Streaming DMA mappings may be considerably slower when mappings go through
> an IOMMU and the total mapping length is somewhat long. This is because the
> IOMMU IOVA code allocates and free an IOVA for each mapping, which may
> affect performance.
> 
> For performance reasons set the request queue max_sectors from
> dma_opt_mapping_size(), which knows this mapping limit.
> 
> Signed-off-by: John Garry <john.garry@huawei.com>
> ---
>  drivers/scsi/scsi_transport_sas.c | 6 ++++++
>  1 file changed, 6 insertions(+)
> 
> diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
> index 12bff64dade6..1b45248748e0 100644
> --- a/drivers/scsi/scsi_transport_sas.c
> +++ b/drivers/scsi/scsi_transport_sas.c
> @@ -225,6 +225,7 @@ static int sas_host_setup(struct transport_container *tc, struct device *dev,
>  {
>  	struct Scsi_Host *shost = dev_to_shost(dev);
>  	struct sas_host_attrs *sas_host = to_sas_host_attrs(shost);
> +	struct device *dma_dev = shost->dma_dev;
>  
>  	INIT_LIST_HEAD(&sas_host->rphy_list);
>  	mutex_init(&sas_host->lock);
> @@ -236,6 +237,11 @@ static int sas_host_setup(struct transport_container *tc, struct device *dev,
>  		dev_printk(KERN_ERR, dev, "fail to a bsg device %d\n",
>  			   shost->host_no);
>  
> +	if (dma_dev) {
> +		shost->max_sectors = min_t(unsigned int, shost->max_sectors,
> +				dma_opt_mapping_size(dma_dev) >> SECTOR_SHIFT);
> +	}

Hmm... shost->max_sectors becomes the max_hw_sectors limit for the block
dev. So using dma_max_mapping_size(dma_dev) for that limit makes sense.
Shouldn't dma_opt_mapping_size(dma_dev) be used to limit only the default
"soft" limit (queue max_sectors limit) instead of the hard limit ?

> +
>  	return 0;
>  }
>  
-- 
Damien Le Moal
Western Digital Research
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

WARNING: multiple messages have this Message-ID (diff)
From: Damien Le Moal <damien.lemoal@opensource.wdc.com>
To: John Garry <john.garry@huawei.com>,
	joro@8bytes.org, will@kernel.org, jejb@linux.ibm.com,
	martin.petersen@oracle.com, hch@lst.de, m.szyprowski@samsung.com,
	robin.murphy@arm.com
Cc: linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-ide@vger.kernel.org, iommu@lists.linux-foundation.org,
	iommu@lists.linux.dev, linux-scsi@vger.kernel.org,
	linuxarm@huawei.com
Subject: Re: [PATCH v5 4/5] scsi: scsi_transport_sas: Cap shost max_sectors according to DMA optimal limit
Date: Fri, 1 Jul 2022 08:49:36 +0900	[thread overview]
Message-ID: <2e6475e5-4899-1e3a-1418-918b9510ec6d@opensource.wdc.com> (raw)
Message-ID: <20220630234936.9L5dD3yyIWlBweV_gtq-_PCkiADdT33R9tiV2KLepls@z> (raw)
In-Reply-To: <1656590892-42307-5-git-send-email-john.garry@huawei.com>

On 6/30/22 21:08, John Garry wrote:
> Streaming DMA mappings may be considerably slower when mappings go through
> an IOMMU and the total mapping length is somewhat long. This is because the
> IOMMU IOVA code allocates and free an IOVA for each mapping, which may
> affect performance.
> 
> For performance reasons set the request queue max_sectors from
> dma_opt_mapping_size(), which knows this mapping limit.
> 
> Signed-off-by: John Garry <john.garry@huawei.com>
> ---
>  drivers/scsi/scsi_transport_sas.c | 6 ++++++
>  1 file changed, 6 insertions(+)
> 
> diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
> index 12bff64dade6..1b45248748e0 100644
> --- a/drivers/scsi/scsi_transport_sas.c
> +++ b/drivers/scsi/scsi_transport_sas.c
> @@ -225,6 +225,7 @@ static int sas_host_setup(struct transport_container *tc, struct device *dev,
>  {
>  	struct Scsi_Host *shost = dev_to_shost(dev);
>  	struct sas_host_attrs *sas_host = to_sas_host_attrs(shost);
> +	struct device *dma_dev = shost->dma_dev;
>  
>  	INIT_LIST_HEAD(&sas_host->rphy_list);
>  	mutex_init(&sas_host->lock);
> @@ -236,6 +237,11 @@ static int sas_host_setup(struct transport_container *tc, struct device *dev,
>  		dev_printk(KERN_ERR, dev, "fail to a bsg device %d\n",
>  			   shost->host_no);
>  
> +	if (dma_dev) {
> +		shost->max_sectors = min_t(unsigned int, shost->max_sectors,
> +				dma_opt_mapping_size(dma_dev) >> SECTOR_SHIFT);
> +	}

Hmm... shost->max_sectors becomes the max_hw_sectors limit for the block
dev. So using dma_max_mapping_size(dma_dev) for that limit makes sense.
Shouldn't dma_opt_mapping_size(dma_dev) be used to limit only the default
"soft" limit (queue max_sectors limit) instead of the hard limit ?

> +
>  	return 0;
>  }
>  
-- 
Damien Le Moal
Western Digital Research

  parent reply	other threads:[~2022-06-30 23:49 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-30 12:08 [PATCH v5 0/5] DMA mapping changes for SCSI core John Garry via iommu
2022-06-30 12:08 ` John Garry
2022-06-30 12:08 ` [PATCH v5 1/5] dma-mapping: Add dma_opt_mapping_size() John Garry via iommu
2022-06-30 12:08   ` John Garry
2022-06-30 12:08 ` [PATCH v5 2/5] dma-iommu: Add iommu_dma_opt_mapping_size() John Garry via iommu
2022-06-30 12:08   ` John Garry
2022-06-30 12:08 ` [PATCH v5 3/5] scsi: core: Cap shost max_sectors according to DMA limits only once John Garry via iommu
2022-06-30 12:08   ` John Garry
2022-06-30 23:41   ` Damien Le Moal via iommu
2022-06-30 23:41     ` Damien Le Moal
2022-07-01  8:02     ` John Garry via iommu
2022-07-01  8:02       ` John Garry
2022-06-30 12:08 ` [PATCH v5 4/5] scsi: scsi_transport_sas: Cap shost max_sectors according to DMA optimal limit John Garry via iommu
2022-06-30 12:08   ` John Garry
2022-06-30 23:49   ` Damien Le Moal via iommu [this message]
2022-06-30 23:49     ` Damien Le Moal
2022-07-01  8:46     ` John Garry via iommu
2022-07-01  8:46       ` John Garry
2022-06-30 12:08 ` [PATCH v5 5/5] ata: libata-scsi: Cap ata_device->max_sectors according to shost->max_sectors John Garry via iommu
2022-06-30 12:08   ` John Garry
2022-07-06 13:40 ` [PATCH v5 0/5] DMA mapping changes for SCSI core John Garry via iommu
2022-07-06 13:40   ` John Garry
2022-07-06 13:44   ` Christoph Hellwig
2022-07-06 13:44     ` Christoph Hellwig
2022-07-07 20:35     ` Martin K. Petersen
2022-07-08 16:17       ` John Garry
2022-07-10 23:08         ` Damien Le Moal
2022-07-11  7:36           ` John Garry
2022-07-11 10:40             ` Damien Le Moal
2022-07-11 14:49               ` John Garry
2022-07-14  3:10         ` Martin K. Petersen
2022-07-14  7:52           ` John Garry

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=2e6475e5-4899-1e3a-1418-918b9510ec6d@opensource.wdc.com \
    --to=iommu@lists.linux-foundation.org \
    --cc=damien.lemoal@opensource.wdc.com \
    --cc=hch@lst.de \
    --cc=iommu@lists.linux.dev \
    --cc=jejb@linux.ibm.com \
    --cc=john.garry@huawei.com \
    --cc=joro@8bytes.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-ide@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=linuxarm@huawei.com \
    --cc=m.szyprowski@samsung.com \
    --cc=martin.petersen@oracle.com \
    --cc=robin.murphy@arm.com \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox