linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Will Deacon <will.deacon@arm.com>
To: Robin Murphy <robin.murphy@arm.com>
Cc: joro@8bytes.org, thunder.leizhen@huawei.com,
	iommu@lists.linux-foundation.org,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, linuxarm@huawei.com,
	guohanjun@huawei.com, huawei.libin@huawei.com,
	john.garry@huawei.com
Subject: Re: [PATCH v7 4/6] iommu: Add bootup option "iommu.non_strict"
Date: Tue, 18 Sep 2018 18:10:13 +0100	[thread overview]
Message-ID: <20180918171013.GK16498@arm.com> (raw)
In-Reply-To: <41f81c46348db4acd9a542184f10e7ca24f6c219.1536935328.git.robin.murphy@arm.com>

On Fri, Sep 14, 2018 at 03:30:22PM +0100, Robin Murphy wrote:
> From: Zhen Lei <thunder.leizhen@huawei.com>
> 
> Add a bootup option to make the system manager can choose which mode to
> be used. The default mode is strict.
> 
> Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
> [rm: move handling out of SMMUv3 driver]
> Signed-off-by: Robin Murphy <robin.murphy@arm.com>
> ---
>  .../admin-guide/kernel-parameters.txt         | 13 ++++++++++
>  drivers/iommu/iommu.c                         | 26 +++++++++++++++++++
>  2 files changed, 39 insertions(+)
> 
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index 9871e649ffef..406b91759b62 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -1749,6 +1749,19 @@
>  		nobypass	[PPC/POWERNV]
>  			Disable IOMMU bypass, using IOMMU for PCI devices.
>  
> +	iommu.non_strict=	[ARM64]
> +			Format: { "0" | "1" }
> +			0 - strict mode, default.
> +			    Release IOVAs after the related TLBs are invalid
> +			    completely.
> +			1 - non-strict mode.
> +			    Put off TLBs invalidation and release memory first.
> +			    It's good for scatter-gather performance but lacks
> +			    full isolation, an untrusted device can access the
> +			    reused memory because the TLBs may still valid.
> +			    Please take	full consideration before choosing this
> +			    mode. Note that, VFIO will always use strict mode.

This text needs help. How about something like:

	0 - strict mode, default.
	    Invalidate the TLB of the IOMMU hardware as part of every
	    unmap() operation.
	1 - lazy mode.
	    Defer TLB invalidation so that the TLB of the IOMMU hardware
	    is invalidated periodically, rather than as part of every
	    unmap() operation.

(generally, I think I'd s/non strict/lazy/ in this patch to avoid the double
negatives)

> +
>  	iommu.passthrough=
>  			[ARM64] Configure DMA to bypass the IOMMU by default.
>  			Format: { "0" | "1" }
> diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
> index 8c15c5980299..2cabd0c0a4f3 100644
> --- a/drivers/iommu/iommu.c
> +++ b/drivers/iommu/iommu.c
> @@ -41,6 +41,7 @@ static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY;
>  #else
>  static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA;
>  #endif
> +static bool iommu_dma_non_strict __read_mostly;
>  
>  struct iommu_callback_data {
>  	const struct iommu_ops *ops;
> @@ -131,6 +132,24 @@ static int __init iommu_set_def_domain_type(char *str)
>  }
>  early_param("iommu.passthrough", iommu_set_def_domain_type);
>  
> +static int __init iommu_dma_setup(char *str)
> +{
> +	int ret;
> +
> +	ret = kstrtobool(str, &iommu_dma_non_strict);
> +	if (ret)
> +		return ret;
> +
> +	if (iommu_dma_non_strict) {
> +		pr_warn("WARNING: iommu non-strict mode is chosen.\n"
> +			"It's good for scatter-gather performance but lacks full isolation\n");

Hmm, not sure about this message either and tainting is probably over the
top. Maybe drop the taint and just pr_info something like "IOMMU DMA ops
using lazy TLB invalidation: unable to protect against malicious devices"

> +		add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
> +	}
> +
> +	return 0;
> +}
> +early_param("iommu.non_strict", iommu_dma_setup);
> +
>  static ssize_t iommu_group_attr_show(struct kobject *kobj,
>  				     struct attribute *__attr, char *buf)
>  {
> @@ -1072,6 +1091,13 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
>  		group->default_domain = dom;
>  		if (!group->domain)
>  			group->domain = dom;
> +
> +		if (dom && iommu_dma_non_strict) {
> +			int attr = 1;
> +			iommu_domain_set_attr(dom,
> +					      DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE,
> +					      &attr);
> +		}

Hmm, I don't think we can guarantee that we're working with the DMA domain
here. Does this all fall out in the wash for the identity domain?

Will

  reply	other threads:[~2018-09-18 17:09 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-14 14:30 [PATCH v7 0/6] Add non-strict mode support for iommu-dma Robin Murphy
2018-09-14 14:30 ` [PATCH v7 1/6] iommu/arm-smmu-v3: Implement flush_iotlb_all hook Robin Murphy
2018-09-14 14:30 ` [PATCH v7 2/6] iommu/dma: Add support for non-strict mode Robin Murphy
2018-09-18 17:10   ` Will Deacon
2018-09-18 18:52     ` Robin Murphy
2018-09-14 14:30 ` [PATCH v7 3/6] iommu/io-pgtable-arm: " Robin Murphy
2018-09-14 14:30 ` [PATCH v7 4/6] iommu: Add bootup option "iommu.non_strict" Robin Murphy
2018-09-18 17:10   ` Will Deacon [this message]
2018-09-18 19:01     ` Robin Murphy
2018-09-14 14:30 ` [PATCH v7 5/6] iommu/arm-smmu-v3: Add support for non-strict mode Robin Murphy
2018-09-18 17:10   ` Will Deacon
2018-09-18 19:09     ` Robin Murphy
2018-09-14 14:30 ` [PATCH v7 6/6] iommu/arm-smmu: Support " Robin Murphy
2018-09-18 17:10   ` Will Deacon
2018-09-18 19:22     ` Robin Murphy
2018-09-18 17:10 ` [PATCH v7 0/6] Add non-strict mode support for iommu-dma Will Deacon
2018-09-18 18:28   ` Robin Murphy

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=20180918171013.GK16498@arm.com \
    --to=will.deacon@arm.com \
    --cc=guohanjun@huawei.com \
    --cc=huawei.libin@huawei.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=john.garry@huawei.com \
    --cc=joro@8bytes.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxarm@huawei.com \
    --cc=robin.murphy@arm.com \
    --cc=thunder.leizhen@huawei.com \
    --subject='Re: [PATCH v7 4/6] iommu: Add bootup option "iommu.non_strict"' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).