Re: [PATCH v3 2/4] iommu: Add PASID support for DMA mapping API users

[Jacob Pan <jacob.jun.pan@linux.intel.com>]

Hi Jason,

On Tue, 10 May 2022 20:28:04 -0300, Jason Gunthorpe <jgg@nvidia.com> wrote:

> On Tue, May 10, 2022 at 02:07:02PM -0700, Jacob Pan wrote:
> > DMA mapping API is the de facto standard for in-kernel DMA. It operates
> > on a per device/RID basis which is not PASID-aware.
> > 
> > Some modern devices such as Intel Data Streaming Accelerator, PASID is
> > required for certain work submissions. To allow such devices use DMA
> > mapping API, we need the following functionalities:
> > 1. Provide device a way to retrieve a PASID for work submission within
> > the kernel
> > 2. Enable the kernel PASID on the IOMMU for the device
> > 3. Attach the kernel PASID to the device's default DMA domain, let it
> > be IOVA or physical address in case of pass-through.
> > 
> > This patch introduces a driver facing API that enables DMA API
> > PASID usage. Once enabled, device drivers can continue to use DMA APIs
> > as is. There is no difference in dma_handle between without PASID and
> > with PASID.
> > 
> > Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
> >  drivers/iommu/dma-iommu.c | 107 ++++++++++++++++++++++++++++++++++++++
> >  include/linux/dma-iommu.h |   3 ++
> >  include/linux/iommu.h     |   2 +
> >  3 files changed, 112 insertions(+)
> > 
> > diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> > index 1ca85d37eeab..5984f3129fa2 100644
> > +++ b/drivers/iommu/dma-iommu.c
> > @@ -34,6 +34,8 @@ struct iommu_dma_msi_page {
> >  	phys_addr_t		phys;
> >  };
> >  
> > +static DECLARE_IOASID_SET(iommu_dma_pasid);
> > +
> >  enum iommu_dma_cookie_type {
> >  	IOMMU_DMA_IOVA_COOKIE,
> >  	IOMMU_DMA_MSI_COOKIE,
> > @@ -370,6 +372,111 @@ void iommu_put_dma_cookie(struct iommu_domain
> > *domain) domain->iova_cookie = NULL;
> >  }
> >  
> > +/**
> > + * iommu_attach_dma_pasid --Attach a PASID for in-kernel DMA. Use the
> > device's
> > + * DMA domain.
> > + * @dev: Device to be enabled
> > + * @pasid: The returned kernel PASID to be used for DMA
> > + *
> > + * DMA request with PASID will be mapped the same way as the legacy
> > DMA.
> > + * If the device is in pass-through, PASID will also pass-through. If
> > the
> > + * device is in IOVA, the PASID will point to the same IOVA page table.
> > + *
> > + * @return err code or 0 on success
> > + */
> > +int iommu_attach_dma_pasid(struct device *dev, ioasid_t *pasid)
> > +{
> > +	struct iommu_domain *dom;
> > +	ioasid_t id, max;
> > +	int ret = 0;
> > +
> > +	dom = iommu_get_domain_for_dev(dev);
> > +	if (!dom || !dom->ops || !dom->ops->attach_dev_pasid)
> > +		return -ENODEV;
> > +
> > +	/* Only support domain types that DMA API can be used */
> > +	if (dom->type == IOMMU_DOMAIN_UNMANAGED ||
> > +	    dom->type == IOMMU_DOMAIN_BLOCKED) {
> > +		dev_warn(dev, "Invalid domain type %d", dom->type);  
> 
> This should be a WARN_ON
> 
will do, thanks

> > +		return -EPERM;
> > +	}
> > +
> > +	id = dom->pasid;
> > +	if (!id) {
> > +		/*
> > +		 * First device to use PASID in its DMA domain,
> > allocate
> > +		 * a single PASID per DMA domain is all we need, it is
> > also
> > +		 * good for performance when it comes down to IOTLB
> > flush.
> > +		 */
> > +		max = 1U << dev->iommu->pasid_bits;
> > +		if (!max)
> > +			return -EINVAL;
> > +
> > +		id = ioasid_alloc(&iommu_dma_pasid, 1, max, dev);
> > +		if (id == INVALID_IOASID)
> > +			return -ENOMEM;
> > +
> > +		dom->pasid = id;
> > +		atomic_set(&dom->pasid_users, 1);  
> 
> All of this needs proper locking.
> 
good catch, will add a mutex for domain updates, detach as well.

> > +	}
> > +
> > +	ret = dom->ops->attach_dev_pasid(dom, dev, id);
> > +	if (!ret) {
> > +		*pasid = id;
> > +		atomic_inc(&dom->pasid_users);
> > +		return 0;
> > +	}
> > +
> > +	if (atomic_dec_and_test(&dom->pasid_users)) {
> > +		ioasid_free(id);
> > +		dom->pasid = 0;
> > +	}
> > +
> > +	return ret;
> > +}
> > +EXPORT_SYMBOL(iommu_attach_dma_pasid);
> > +
> > +/**
> > + * iommu_detach_dma_pasid --Disable in-kernel DMA request with PASID
> > + * @dev:	Device's PASID DMA to be disabled
> > + *
> > + * It is the device driver's responsibility to ensure no more incoming
> > DMA
> > + * requests with the kernel PASID before calling this function. IOMMU
> > driver
> > + * ensures PASID cache, IOTLBs related to the kernel PASID are cleared
> > and
> > + * drained.
> > + *
> > + */
> > +void iommu_detach_dma_pasid(struct device *dev)
> > +{
> > +	struct iommu_domain *dom;
> > +	ioasid_t pasid;
> > +
> > +	dom = iommu_get_domain_for_dev(dev);
> > +	if (!dom || !dom->ops || !dom->ops->detach_dev_pasid) {
> > +		dev_warn(dev, "No ops for detaching PASID %u", pasid);
> > +		return;
> > +	}
> > +	/* Only support DMA API managed domain type */
> > +	if (dom->type == IOMMU_DOMAIN_UNMANAGED ||
> > +	    dom->type == IOMMU_DOMAIN_BLOCKED) {
> > +		dev_err(dev, "Invalid domain type %d to detach DMA
> > PASID %u\n",
> > +			 dom->type, pasid);
> > +		return;
> > +	}
> > +	pasid = dom->pasid;
> > +	if (!pasid) {
> > +		dev_err(dev, "No DMA PASID attached\n");
> > +		return;
> > +	}  
> 
> All WARN_ON's too
> 
will do.

> > +	dom->ops->detach_dev_pasid(dom, dev, pasid);
> > +	if (atomic_dec_and_test(&dom->pasid_users)) {
> > +		ioasid_free(pasid);
> > +		dom->pasid = 0;
> > +	}
> > +}
> > +EXPORT_SYMBOL(iommu_detach_dma_pasid);
> > +
> >  /**
> >   * iommu_dma_get_resv_regions - Reserved region driver helper
> >   * @dev: Device from iommu_get_resv_regions()
> > diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
> > index 24607dc3c2ac..538650b9cb75 100644
> > +++ b/include/linux/dma-iommu.h
> > @@ -18,6 +18,9 @@ int iommu_get_dma_cookie(struct iommu_domain *domain);
> >  int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base);
> >  void iommu_put_dma_cookie(struct iommu_domain *domain);
> >  
> > +int iommu_attach_dma_pasid(struct device *dev, ioasid_t *pasid);
> > +void iommu_detach_dma_pasid(struct device *dev);
> > +
> >  /* Setup call for arch DMA mapping code */
> >  void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64
> > dma_limit); int iommu_dma_init_fq(struct iommu_domain *domain);
> > diff --git a/include/linux/iommu.h b/include/linux/iommu.h
> > index 1164524814cb..281a87fdce77 100644
> > +++ b/include/linux/iommu.h
> > @@ -105,6 +105,8 @@ struct iommu_domain {
> >  	enum iommu_page_response_code (*iopf_handler)(struct
> > iommu_fault *fault, void *data);
> >  	void *fault_data;
> > +	ioasid_t pasid;		/* Used for DMA requests with
> > PASID */
> > +	atomic_t pasid_users;  
> 
> These are poorly named, this is really the DMA API global PASID and
> shouldn't be used for other things.
> 
I was hoping it can be generic since sva_cookie also has a pasid field but
it looks like sva uses mm->pasid now.

Shall we call it dma_api_pasid, dma_pasid, or something else?

> Jason


Thanks,

Jacob