[PATCH v3 3/3] iommu/arm-smmu-v3: Allow ATS to be always on

[Nirmoy Das]

On 07.03.26 00:41, Nicolin Chen wrote:
> When a device's default substream attaches to an identity domain, the SMMU
> driver currently sets the device's STE between two modes:
>
>    Mode 1: Cfg=Translate, S1DSS=Bypass, EATS=1
>    Mode 2: Cfg=bypass (EATS is ignored by HW)
>
> When there is an active PASID (non-default substream), mode 1 is used. And
> when there is no PASID support or no active PASID, mode 2 is used.
>
> The driver will also downgrade an STE from mode 1 to mode 2, when the last
> active substream becomes inactive.
>
> However, there are PCIe devices that demand ATS to be always on. For these
> devices, their STEs have to use the mode 1 as HW ignores EATS with mode 2.
>
> Change the driver accordingly:
>    - always use the mode 1
>    - never downgrade to mode 2
>    - allocate and retain a CD table (see note below)
>
> Note that these devices might not support PASID, i.e. doing non-PASID ATS.
> In such a case, the ssid_bits is set to 0. However, s1cdmax must be set to
> a !0 value in order to keep the S1DSS field effective. Thus, when a master
> requires ats_always_on, set its s1cdmax to minimal 1, meaning the CD table
> will have a dummy entry (SSID=1) that will be never used.
>
> Now, for these device, arm_smmu_cdtab_allocated() will always return true,
> v.s. false prior to this change. When its default substream is attached to
> an IDENTITY domain, its first CD is NULL in the table, which is a totally
> valid case. Thus, add "!master->ats_always_on" to the condition.
>
> Reviewed-by: Jonathan Cameron <jonathan.cameron at huawei.com>
> Signed-off-by: Nicolin Chen <nicolinc at nvidia.com>

Tested-by: Nirmoy Das <nirmoyd at nvidia.com>

Acked-by: Nirmoy Das <nirmoyd at nvidia.com>


> ---
>   drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  1 +
>   drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 72 ++++++++++++++++++---
>   2 files changed, 65 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
> index 3c6d65d36164f..f966d474b61fd 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
> @@ -848,6 +848,7 @@ struct arm_smmu_master {
>   	bool				ats_enabled : 1;
>   	bool				ste_ats_enabled : 1;
>   	bool				stall_enabled;
> +	bool				ats_always_on;
>   	unsigned int			ssid_bits;
>   	unsigned int			iopf_refcount;
>   };
> 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 4d00d796f0783..ef98e79b4e75d 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> @@ -1482,8 +1482,11 @@ void arm_smmu_clear_cd(struct arm_smmu_master *master, ioasid_t ssid)
>   	if (!arm_smmu_cdtab_allocated(&master->cd_table))
>   		return;
>   	cdptr = arm_smmu_get_cd_ptr(master, ssid);
> -	if (WARN_ON(!cdptr))
> +	if (!cdptr) {
> +		/* Only ats_always_on allows a NULL CD on default substream */
> +		WARN_ON(!master->ats_always_on || ssid);
>   		return;
> +	}
>   	arm_smmu_write_cd_entry(master, ssid, cdptr, &target);
>   }
>   
> @@ -1496,6 +1499,22 @@ static int arm_smmu_alloc_cd_tables(struct arm_smmu_master *master)
>   	struct arm_smmu_ctx_desc_cfg *cd_table = &master->cd_table;
>   
>   	cd_table->s1cdmax = master->ssid_bits;
> +
> +	/*
> +	 * When a device doesn't support PASID (non default SSID), ssid_bits is
> +	 * set to 0. This also sets S1CDMAX to 0, which disables the substreams
> +	 * and ignores the S1DSS field.
> +	 *
> +	 * On the other hand, if a device demands ATS to be always on even when
> +	 * its default substream is IOMMU bypassed, it has to use EATS that is
> +	 * only effective with an STE (CFG=S1translate, S1DSS=Bypass). For such
> +	 * use cases, S1CDMAX has to be !0, in order to make use of S1DSS/EATS.
> +	 *
> +	 * Set S1CDMAX no lower than 1. This would add a dummy substream in the
> +	 * CD table but it should never be used by an actual CD.
> +	 */
> +	if (master->ats_always_on)
> +		cd_table->s1cdmax = max_t(u8, cd_table->s1cdmax, 1);
>   	max_contexts = 1 << cd_table->s1cdmax;
>   
>   	if (!(smmu->features & ARM_SMMU_FEAT_2_LVL_CDTAB) ||
> @@ -3250,7 +3269,8 @@ static int arm_smmu_blocking_set_dev_pasid(struct iommu_domain *new_domain,
>   	 * When the last user of the CD table goes away downgrade the STE back
>   	 * to a non-cd_table one, by re-attaching its sid_domain.
>   	 */
> -	if (!arm_smmu_ssids_in_use(&master->cd_table)) {
> +	if (!master->ats_always_on &&
> +	    !arm_smmu_ssids_in_use(&master->cd_table)) {
>   		struct iommu_domain *sid_domain =
>   			iommu_driver_get_domain_for_dev(master->dev);
>   
> @@ -3274,6 +3294,8 @@ static void arm_smmu_attach_dev_ste(struct iommu_domain *domain,
>   		.old_domain = old_domain,
>   		.ssid = IOMMU_NO_PASID,
>   	};
> +	bool ats_always_on = master->ats_always_on &&
> +			     s1dss != STRTAB_STE_1_S1DSS_TERMINATE;
>   
>   	/*
>   	 * Do not allow any ASID to be changed while are working on the STE,
> @@ -3285,7 +3307,7 @@ static void arm_smmu_attach_dev_ste(struct iommu_domain *domain,
>   	 * If the CD table is not in use we can use the provided STE, otherwise
>   	 * we use a cdtable STE with the provided S1DSS.
>   	 */
> -	if (arm_smmu_ssids_in_use(&master->cd_table)) {
> +	if (ats_always_on || arm_smmu_ssids_in_use(&master->cd_table)) {
>   		/*
>   		 * If a CD table has to be present then we need to run with ATS
>   		 * on because we have to assume a PASID is using ATS. For
> @@ -3581,6 +3603,40 @@ static void arm_smmu_remove_master(struct arm_smmu_master *master)
>   	kfree(master->streams);
>   }
>   
> +static int arm_smmu_master_prepare_ats(struct arm_smmu_master *master)
> +{
> +	bool s1p = master->smmu->features & ARM_SMMU_FEAT_TRANS_S1;
> +	unsigned int stu = __ffs(master->smmu->pgsize_bitmap);
> +	struct pci_dev *pdev = to_pci_dev(master->dev);
> +	int ret;
> +
> +	if (!arm_smmu_ats_supported(master))
> +		return 0;
> +
> +	if (!pci_ats_always_on(pdev))
> +		goto out_prepare;
> +
> +	/*
> +	 * S1DSS is required for ATS to be always on for identity domain cases.
> +	 * However, the S1DSS field is ignored if !IDR0_S1P or !IDR1_SSIDSIZE.
> +	 */
> +	if (!s1p || !master->smmu->ssid_bits) {
> +		dev_info_once(master->dev,
> +			      "SMMU doesn't support ATS to be always on\n");
> +		goto out_prepare;
> +	}
> +
> +	master->ats_always_on = true;
> +
> +	ret = arm_smmu_alloc_cd_tables(master);
> +	if (ret)
> +		return ret;
> +
> +out_prepare:
> +	pci_prepare_ats(pdev, stu);
> +	return 0;
> +}
> +
>   static struct iommu_device *arm_smmu_probe_device(struct device *dev)
>   {
>   	int ret;
> @@ -3629,14 +3685,14 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
>   	    smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
>   		master->stall_enabled = true;
>   
> -	if (dev_is_pci(dev)) {
> -		unsigned int stu = __ffs(smmu->pgsize_bitmap);
> -
> -		pci_prepare_ats(to_pci_dev(dev), stu);
> -	}
> +	ret = arm_smmu_master_prepare_ats(master);
> +	if (ret)
> +		goto err_disable_pasid;
>   
>   	return &smmu->iommu;
>   
> +err_disable_pasid:
> +	arm_smmu_disable_pasid(master);
>   err_free_master:
>   	kfree(master);
>   	return ERR_PTR(ret);