RE: [PATCH v2 3/4] iommu/arm-smmu-v3: Add support for dirty tracking in domain alloc

[Shameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com>]

> -----Original Message-----
> From: Joao Martins <joao.m.martins@oracle.com>
> Sent: Thursday, February 22, 2024 11:04 AM
> To: Shameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com>
> Cc: joro@8bytes.org; jgg@nvidia.com; kevin.tian@intel.com;
> nicolinc@nvidia.com; iommu@lists.linux.dev; mshavit@google.com;
> robin.murphy@arm.com; will@kernel.org; jiangkunkun
> <jiangkunkun@huawei.com>; zhukeqian <zhukeqian1@huawei.com>;
> Linuxarm <linuxarm@huawei.com>; linux-arm-kernel@lists.infradead.org
> Subject: Re: [PATCH v2 3/4] iommu/arm-smmu-v3: Add support for dirty
> tracking in domain alloc
> 
> On 22/02/2024 09:49, Shameer Kolothum wrote:
> > From: Joao Martins <joao.m.martins@oracle.com>
> >
> > This provides all the infrastructure to enable dirty tracking if the
> > hardware has the capability and domain alloc request for it.
> >
> > Please note, we still report no support for IOMMU_CAP_DIRTY_TRACKING
> > as it will finally be enabled in a subsequent patch.
> >
> > Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
> > Signed-off-by: Shameer Kolothum
> <shameerali.kolothum.thodi@huawei.com>
> > ---
> >  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 95
> ++++++++++++++++-----
> >  include/linux/io-pgtable.h                  |  4 +
> >  2 files changed, 77 insertions(+), 22 deletions(-)
> >
> > 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 bd30739e3588..058bbb0dbe2e 100644
> > --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> > +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> > @@ -43,6 +43,7 @@ MODULE_PARM_DESC(disable_msipolling,
> >  	"Disable MSI-based polling for CMD_SYNC completion.");
> >
> >  static struct iommu_ops arm_smmu_ops;
> > +static struct iommu_dirty_ops arm_smmu_dirty_ops;
> >
> >  enum arm_smmu_msi_index {
> >  	EVTQ_MSI_INDEX,
> > @@ -86,7 +87,8 @@ static struct arm_smmu_option_prop
> > arm_smmu_options[] = {
> >
> >  static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device
> > *smmu);  static int arm_smmu_domain_finalise(struct arm_smmu_domain
> *smmu_domain,
> > -				    struct arm_smmu_device *smmu);
> > +				    struct arm_smmu_device *smmu,
> > +				    bool enable_dirty);
> >  static int arm_smmu_alloc_cd_tables(struct arm_smmu_master *master);
> > static void arm_smmu_tlb_inv_all_s2(struct arm_smmu_domain
> > *smmu_domain);
> >
> > @@ -2378,7 +2380,7 @@ static struct iommu_domain
> *arm_smmu_domain_alloc_paging(struct device *dev)
> >  		struct arm_smmu_master *master =
> dev_iommu_priv_get(dev);
> >  		int ret;
> >
> > -		ret = arm_smmu_domain_finalise(smmu_domain, master-
> >smmu);
> > +		ret = arm_smmu_domain_finalise(smmu_domain, master-
> >smmu, false);
> >  		if (ret) {
> >  			kfree(smmu_domain);
> >  			return ERR_PTR(ret);
> > @@ -2445,10 +2447,11 @@ static void arm_smmu_domain_free(struct
> > iommu_domain *domain)  }
> >
> >  static int arm_smmu_domain_finalise(struct arm_smmu_domain
> *smmu_domain,
> > -				    struct arm_smmu_device *smmu)
> > +				    struct arm_smmu_device *smmu,
> > +				    bool enable_dirty)
> >  {
> >  	int ret;
> > -	unsigned long ias, oas;
> > +	unsigned long ias;
> >  	enum io_pgtable_fmt fmt;
> >  	struct io_pgtable_cfg pgtbl_cfg;
> >  	struct io_pgtable_ops *pgtbl_ops;
> > @@ -2459,31 +2462,31 @@ static int arm_smmu_domain_finalise(struct
> arm_smmu_domain *smmu_domain,
> >  	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S2))
> >  		smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
> >
> > +	pgtbl_cfg = (struct io_pgtable_cfg) {
> > +		.pgsize_bitmap	= smmu->pgsize_bitmap,
> > +		.coherent_walk	= smmu->features &
> ARM_SMMU_FEAT_COHERENCY,
> > +		.tlb		= &arm_smmu_flush_ops,
> > +		.iommu_dev	= smmu->dev,
> > +	};
> > +
> >  	switch (smmu_domain->stage) {
> >  	case ARM_SMMU_DOMAIN_S1:
> >  		ias = (smmu->features & ARM_SMMU_FEAT_VAX) ? 52 : 48;
> > -		ias = min_t(unsigned long, ias, VA_BITS);
> > -		oas = smmu->ias;
> > +		pgtbl_cfg.ias = min_t(unsigned long, ias, VA_BITS);
> > +		pgtbl_cfg.oas = smmu->ias;
> > +		if (enable_dirty)
> > +			pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_ARM_HD;
> >  		fmt = ARM_64_LPAE_S1;
> >  		break;
> >  	case ARM_SMMU_DOMAIN_S2:
> > -		ias = smmu->ias;
> > -		oas = smmu->oas;
> > +		pgtbl_cfg.ias = smmu->ias;
> > +		pgtbl_cfg.oas = smmu->oas;
> >  		fmt = ARM_64_LPAE_S2;
> >  		break;
> >  	default:
> >  		return -EINVAL;
> >  	}
> >
> > -	pgtbl_cfg = (struct io_pgtable_cfg) {
> > -		.pgsize_bitmap	= smmu->pgsize_bitmap,
> > -		.ias		= ias,
> > -		.oas		= oas,
> > -		.coherent_walk	= smmu->features &
> ARM_SMMU_FEAT_COHERENCY,
> > -		.tlb		= &arm_smmu_flush_ops,
> > -		.iommu_dev	= smmu->dev,
> > -	};
> > -
> >  	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
> >  	if (!pgtbl_ops)
> >  		return -ENOMEM;
> > @@ -2491,7 +2494,8 @@ static int arm_smmu_domain_finalise(struct
> arm_smmu_domain *smmu_domain,
> >  	smmu_domain->domain.pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
> >  	smmu_domain->domain.geometry.aperture_end = (1UL <<
> pgtbl_cfg.ias) - 1;
> >  	smmu_domain->domain.geometry.force_aperture = true;
> > -
> > +	if (enable_dirty && smmu_domain->stage ==
> ARM_SMMU_DOMAIN_S1)
> > +		smmu_domain->domain.dirty_ops =
> &arm_smmu_dirty_ops;
> >  	ret = arm_smmu_domain_alloc_id(smmu, smmu_domain);
> >  	if (ret < 0) {
> >  		free_io_pgtable_ops(pgtbl_ops);
> > @@ -2811,7 +2815,7 @@ static int arm_smmu_attach_dev(struct
> iommu_domain *domain, struct device *dev)
> >  	mutex_lock(&smmu_domain->init_mutex);
> >
> >  	if (!smmu_domain->smmu) {
> > -		ret = arm_smmu_domain_finalise(smmu_domain, smmu);
> > +		ret = arm_smmu_domain_finalise(smmu_domain, smmu,
> false);
> >  	} else if (smmu_domain->smmu != smmu)
> >  		ret = -EINVAL;
> >
> 
> 
> I think we are missing the domain attach_dev check for dirty tracking.
> 
> Something like:
> 
> if (domain->dirty_ops && !arm_smmu_dbm_capable(smmu))
> 	return -EINVAL;
> 
> But that helper is only introduced in the last patch, so maybe:
> 
> if (domain->dirty_ops &&
>     !device_iommu_capable(dev, IOMMU_CAP_DIRTY_TRACKING))
> 	return -EINVAL;

Ok. But do we really need to check this in attach()? As dirty_ops are added only
if it is requested in alloc_user() and there we return err when hardware doesn't 
have the capability.  So not sure how this matters in attach() path. May be I am 
missing something.

Thanks,
Shameer