Linux IOMMU Development
 help / color / mirror / Atom feed
From: Robin Murphy <robin.murphy@arm.com>
To: Daniel Mentz <danielmentz@google.com>, iommu@lists.linux.dev
Cc: Nicolin Chen <nicolinc@nvidia.com>,
	linux-arm-kernel@lists.infradead.org,
	Will Deacon <will@kernel.org>,
	Mostafa Saleh <smostafa@google.com>
Subject: Re: [PATCH] iommu/arm-smmu-v3: Skip prefetch cmd for MMU-600, MMU-700
Date: Wed, 15 May 2024 16:29:45 +0100	[thread overview]
Message-ID: <b348ee57-c461-4546-94dc-1cbdbaf33145@arm.com> (raw)
In-Reply-To: <20240513215420.408374-1-danielmentz@google.com>

Hi Daniel,

On 2024-05-13 10:54 pm, Daniel Mentz wrote:
> Arm CoreLink MMU-600 and MMU-700 both silently ignore the
> CMD_PREFETCH_CONFIG command. Let's not waste cycles adding this command to
> the command queue if it is ignored anyway.

It is true that our implementations don't do anything with prefetch 
commands so far, however this is a valid architectural behaviour, and 
the intent of the quirk is really for buggy implementations where the 
commands erroneously fault.

TBH if saving cycles in arm_smmu_attach_dev() matters to you, then 
you're probably not going to like what's now queued in next that makes 
it absurdly overcomplicated with loads of indirect function calls...

Thanks,
Robin.

> Signed-off-by: Daniel Mentz <danielmentz@google.com>
> ---
>   drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 4 ++++
>   1 file changed, 4 insertions(+)
> 
> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> index aa62f0ecd053..98f1c4b44ef3 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> @@ -3684,6 +3684,8 @@ static void arm_smmu_device_iidr_probe(struct arm_smmu_device *smmu)
>   	case IIDR_IMPLEMENTER_ARM:
>   		switch (productid) {
>   		case IIDR_PRODUCTID_ARM_MMU_600:
> +			/* MMU-600 silently ignores CMD_PREFETCH_CONFIG */
> +			smmu->options |= ARM_SMMU_OPT_SKIP_PREFETCH;
>   			/* Arm erratum 1076982 */
>   			if (variant == 0 && revision <= 2)
>   				smmu->features &= ~ARM_SMMU_FEAT_SEV;
> @@ -3692,6 +3694,8 @@ static void arm_smmu_device_iidr_probe(struct arm_smmu_device *smmu)
>   				smmu->features &= ~ARM_SMMU_FEAT_NESTING;
>   			break;
>   		case IIDR_PRODUCTID_ARM_MMU_700:
> +			/* MMU-700 silently ignores CMD_PREFETCH_CONFIG */
> +			smmu->options |= ARM_SMMU_OPT_SKIP_PREFETCH;
>   			/* Arm erratum 2812531 */
>   			smmu->features &= ~ARM_SMMU_FEAT_BTM;
>   			smmu->options |= ARM_SMMU_OPT_CMDQ_FORCE_SYNC;

  reply	other threads:[~2024-05-15 15:29 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-13 21:54 [PATCH] iommu/arm-smmu-v3: Skip prefetch cmd for MMU-600, MMU-700 Daniel Mentz
2024-05-15 15:29 ` Robin Murphy [this message]
2024-05-21 17:49   ` Daniel Mentz

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=b348ee57-c461-4546-94dc-1cbdbaf33145@arm.com \
    --to=robin.murphy@arm.com \
    --cc=danielmentz@google.com \
    --cc=iommu@lists.linux.dev \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=nicolinc@nvidia.com \
    --cc=smostafa@google.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