Date:   Sun, 31 Jul 2022 20:55:04 +0800
From:   Yi Liu <yi.l.liu@...el.com>
To:     Lu Baolu <baolu.lu@...ux.intel.com>,
        Joerg Roedel <joro@...tes.org>,
        "Jason Gunthorpe" <jgg@...dia.com>,
        Christoph Hellwig <hch@...radead.org>,
        Kevin Tian <kevin.tian@...el.com>,
        Ashok Raj <ashok.raj@...el.com>, Will Deacon <will@...nel.org>,
        Robin Murphy <robin.murphy@....com>,
        Jean-Philippe Brucker <jean-philippe@...aro.com>,
        Dave Jiang <dave.jiang@...el.com>,
        Vinod Koul <vkoul@...nel.org>
CC:     Eric Auger <eric.auger@...hat.com>,
        Jacob jun Pan <jacob.jun.pan@...el.com>,
        Zhangfei Gao <zhangfei.gao@...aro.org>,
        Zhu Tony <tony.zhu@...el.com>, <iommu@...ts.linux.dev>,
        <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v10 08/12] iommu/sva: Refactoring
 iommu_sva_bind/unbind_device()

On 2022/7/5 13:07, Lu Baolu wrote:
> The existing iommu SVA interfaces are implemented by calling the SVA
> specific iommu ops provided by the IOMMU drivers. There's no need for
> any SVA specific ops in iommu_ops vector anymore as we can achieve
> this through the generic attach/detach_dev_pasid domain ops.
> 
> This refactors the IOMMU SVA interfaces implementation by using the
> set/block_pasid_dev ops and align them with the concept of the SVA
> iommu domain. Put the new SVA code in the sva related file in order
> to make it self-contained.
> 
> Signed-off-by: Lu Baolu <baolu.lu@...ux.intel.com>
> Tested-by: Zhangfei Gao <zhangfei.gao@...aro.org>
> Tested-by: Tony Zhu <tony.zhu@...el.com>
> ---
>   include/linux/iommu.h         |  67 +++++++++++--------
>   drivers/iommu/iommu-sva-lib.c |  98 ++++++++++++++++++++++++++++
>   drivers/iommu/iommu.c         | 119 ++++++++--------------------------
>   3 files changed, 165 insertions(+), 119 deletions(-)
> 
> diff --git a/include/linux/iommu.h b/include/linux/iommu.h
> index 42f0418dc22c..f59b0ecd3995 100644
> --- a/include/linux/iommu.h
> +++ b/include/linux/iommu.h
> @@ -39,7 +39,6 @@ struct device;
>   struct iommu_domain;
>   struct iommu_domain_ops;
>   struct notifier_block;
> -struct iommu_sva;
>   struct iommu_fault_event;
>   struct iommu_dma_cookie;
>   
> @@ -57,6 +56,14 @@ struct iommu_domain_geometry {
>   	bool force_aperture;       /* DMA only allowed in mappable range? */
>   };
>   
> +/**
> + * struct iommu_sva - handle to a device-mm bond
> + */
> +struct iommu_sva {
> +	struct device		*dev;
> +	refcount_t		users;
> +};
> +
>   /* Domain feature flags */
>   #define __IOMMU_DOMAIN_PAGING	(1U << 0)  /* Support for iommu_map/unmap */
>   #define __IOMMU_DOMAIN_DMA_API	(1U << 1)  /* Domain for use in DMA-API
> @@ -105,6 +112,7 @@ struct iommu_domain {
>   		};
>   		struct {	/* IOMMU_DOMAIN_SVA */
>   			struct mm_struct *mm;
> +			struct iommu_sva bond;
>   		};
>   	};
>   };
> @@ -638,13 +646,6 @@ struct iommu_fwspec {
>   /* ATS is supported */
>   #define IOMMU_FWSPEC_PCI_RC_ATS			(1 << 0)
>   
> -/**
> - * struct iommu_sva - handle to a device-mm bond
> - */
> -struct iommu_sva {
> -	struct device			*dev;
> -};
> -
>   int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
>   		      const struct iommu_ops *ops);
>   void iommu_fwspec_free(struct device *dev);
> @@ -685,11 +686,6 @@ int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f);
>   int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f);
>   bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f);
>   
> -struct iommu_sva *iommu_sva_bind_device(struct device *dev,
> -					struct mm_struct *mm);
> -void iommu_sva_unbind_device(struct iommu_sva *handle);
> -u32 iommu_sva_get_pasid(struct iommu_sva *handle);
> -
>   int iommu_device_use_default_domain(struct device *dev);
>   void iommu_device_unuse_default_domain(struct device *dev);
>   
> @@ -703,6 +699,8 @@ int iommu_attach_device_pasid(struct iommu_domain *domain, struct device *dev,
>   			      ioasid_t pasid);
>   void iommu_detach_device_pasid(struct iommu_domain *domain, struct device *dev,
>   			       ioasid_t pasid);
> +struct iommu_domain *
> +iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid);
>   #else /* CONFIG_IOMMU_API */
>   
>   struct iommu_ops {};
> @@ -1033,21 +1031,6 @@ iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
>   	return -ENODEV;
>   }
>   
> -static inline struct iommu_sva *
> -iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
> -{
> -	return NULL;
> -}
> -
> -static inline void iommu_sva_unbind_device(struct iommu_sva *handle)
> -{
> -}
> -
> -static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
> -{
> -	return IOMMU_PASID_INVALID;
> -}
> -
>   static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev)
>   {
>   	return NULL;
> @@ -1093,6 +1076,12 @@ static inline void iommu_detach_device_pasid(struct iommu_domain *domain,
>   					     struct device *dev, ioasid_t pasid)
>   {
>   }
> +
> +static inline struct iommu_domain *
> +iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid)
> +{
> +	return NULL;
> +}
>   #endif /* CONFIG_IOMMU_API */
>   
>   /**
> @@ -1118,4 +1107,26 @@ void iommu_debugfs_setup(void);
>   static inline void iommu_debugfs_setup(void) {}
>   #endif
>   
> +#ifdef CONFIG_IOMMU_SVA
> +struct iommu_sva *iommu_sva_bind_device(struct device *dev,
> +					struct mm_struct *mm);
> +void iommu_sva_unbind_device(struct iommu_sva *handle);
> +u32 iommu_sva_get_pasid(struct iommu_sva *handle);
> +#else
> +static inline struct iommu_sva *
> +iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
> +{
> +	return NULL;
> +}
> +
> +static inline void iommu_sva_unbind_device(struct iommu_sva *handle)
> +{
> +}
> +
> +static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
> +{
> +	return IOMMU_PASID_INVALID;
> +}
> +#endif /* CONFIG_IOMMU_SVA */
> +
>   #endif /* __LINUX_IOMMU_H */
> diff --git a/drivers/iommu/iommu-sva-lib.c b/drivers/iommu/iommu-sva-lib.c
> index 106506143896..751366980232 100644
> --- a/drivers/iommu/iommu-sva-lib.c
> +++ b/drivers/iommu/iommu-sva-lib.c
> @@ -4,6 +4,7 @@
>    */
>   #include <linux/mutex.h>
>   #include <linux/sched/mm.h>
> +#include <linux/iommu.h>
>   
>   #include "iommu-sva-lib.h"
>   
> @@ -69,3 +70,100 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid)
>   	return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero);
>   }
>   EXPORT_SYMBOL_GPL(iommu_sva_find);
> +
> +/**
> + * iommu_sva_bind_device() - Bind a process address space to a device
> + * @dev: the device
> + * @mm: the mm to bind, caller must hold a reference to mm_users
> + *
> + * Create a bond between device and address space, allowing the device to access
> + * the mm using the returned PASID. If a bond already exists between @device and
> + * @mm, it is returned and an additional reference is taken. Caller must call
> + * iommu_sva_unbind_device() to release each reference.
> + *
> + * iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) must be called first, to
> + * initialize the required SVA features.
> + *
> + * On error, returns an ERR_PTR value.
> + */
> +struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
> +{
> +	struct iommu_domain *domain;
> +	ioasid_t max_pasids;
> +	int ret = -EINVAL;
> +
> +	max_pasids = dev->iommu->max_pasids;
> +	if (!max_pasids)
> +		return ERR_PTR(-EOPNOTSUPP);
> +
> +	/* Allocate mm->pasid if necessary. */
> +	ret = iommu_sva_alloc_pasid(mm, 1, max_pasids - 1);

do we want to call mmgrab() before iomu_sva_alloc_pasid() to
avoid using mm without any reference? In your current code,
mmgrab() is called in iommu_sva_domain_alloc().

> +	if (ret)
> +		return ERR_PTR(ret);
> +
> +	mutex_lock(&iommu_sva_lock);
> +	/* Search for an existing domain. */
> +	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid);
> +	if (domain) {
> +		refcount_inc(&domain->bond.users);
> +		goto out_success;
> +	}
> +
> +	/* Allocate a new domain and set it on device pasid. */
> +	domain = iommu_sva_domain_alloc(dev, mm);
> +	if (!domain) {
> +		ret = -ENOMEM;
> +		goto out_unlock;
> +	}
> +
> +	ret = iommu_attach_device_pasid(domain, dev, mm->pasid);
> +	if (ret)
> +		goto out_free_domain;
> +	domain->bond.dev = dev;
> +	refcount_set(&domain->bond.users, 1);
> +
> +out_success:
> +	mutex_unlock(&iommu_sva_lock);
> +	return &domain->bond;
> +
> +out_free_domain:
> +	iommu_domain_free(domain);
> +out_unlock:
> +	mutex_unlock(&iommu_sva_lock);
> +
> +	return ERR_PTR(ret);
> +}
> +EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
> +
> +/**
> + * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device
> + * @handle: the handle returned by iommu_sva_bind_device()
> + *
> + * Put reference to a bond between device and address space. The device should
> + * not be issuing any more transaction for this PASID. All outstanding page
> + * requests for this PASID must have been flushed to the IOMMU.
> + */
> +void iommu_sva_unbind_device(struct iommu_sva *handle)
> +{
> +	struct device *dev = handle->dev;
> +	struct iommu_domain *domain =
> +			container_of(handle, struct iommu_domain, bond);
> +	ioasid_t pasid = iommu_sva_get_pasid(handle);
> +
> +	mutex_lock(&iommu_sva_lock);
> +	if (refcount_dec_and_test(&domain->bond.users)) {
> +		iommu_detach_device_pasid(domain, dev, pasid);
> +		iommu_domain_free(domain);
> +	}
> +	mutex_unlock(&iommu_sva_lock);
> +}
> +EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
> +
> +u32 iommu_sva_get_pasid(struct iommu_sva *handle)
> +{
> +	struct iommu_domain *domain =
> +			container_of(handle, struct iommu_domain, bond);
> +
> +	return domain->mm->pasid;
> +}
> +EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
> diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
> index 10479c5e4d23..e1491eb3c7b6 100644
> --- a/drivers/iommu/iommu.c
> +++ b/drivers/iommu/iommu.c
> @@ -2789,97 +2789,6 @@ bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat)
>   }
>   EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
>   
> -/**
> - * iommu_sva_bind_device() - Bind a process address space to a device
> - * @dev: the device
> - * @mm: the mm to bind, caller must hold a reference to it
> - *
> - * Create a bond between device and address space, allowing the device to access
> - * the mm using the returned PASID. If a bond already exists between @device and
> - * @mm, it is returned and an additional reference is taken. Caller must call
> - * iommu_sva_unbind_device() to release each reference.
> - *
> - * iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) must be called first, to
> - * initialize the required SVA features.
> - *
> - * On error, returns an ERR_PTR value.
> - */
> -struct iommu_sva *
> -iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
> -{
> -	struct iommu_group *group;
> -	struct iommu_sva *handle = ERR_PTR(-EINVAL);
> -	const struct iommu_ops *ops = dev_iommu_ops(dev);
> -
> -	if (!ops->sva_bind)
> -		return ERR_PTR(-ENODEV);
> -
> -	group = iommu_group_get(dev);
> -	if (!group)
> -		return ERR_PTR(-ENODEV);
> -
> -	/* Ensure device count and domain don't change while we're binding */
> -	mutex_lock(&group->mutex);
> -
> -	/*
> -	 * To keep things simple, SVA currently doesn't support IOMMU groups
> -	 * with more than one device. Existing SVA-capable systems are not
> -	 * affected by the problems that required IOMMU groups (lack of ACS
> -	 * isolation, device ID aliasing and other hardware issues).
> -	 */
> -	if (iommu_group_device_count(group) != 1)
> -		goto out_unlock;
> -
> -	handle = ops->sva_bind(dev, mm);
> -
> -out_unlock:
> -	mutex_unlock(&group->mutex);
> -	iommu_group_put(group);
> -
> -	return handle;
> -}
> -EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
> -
> -/**
> - * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device
> - * @handle: the handle returned by iommu_sva_bind_device()
> - *
> - * Put reference to a bond between device and address space. The device should
> - * not be issuing any more transaction for this PASID. All outstanding page
> - * requests for this PASID must have been flushed to the IOMMU.
> - */
> -void iommu_sva_unbind_device(struct iommu_sva *handle)
> -{
> -	struct iommu_group *group;
> -	struct device *dev = handle->dev;
> -	const struct iommu_ops *ops = dev_iommu_ops(dev);
> -
> -	if (!ops->sva_unbind)
> -		return;
> -
> -	group = iommu_group_get(dev);
> -	if (!group)
> -		return;
> -
> -	mutex_lock(&group->mutex);
> -	ops->sva_unbind(handle);
> -	mutex_unlock(&group->mutex);
> -
> -	iommu_group_put(group);
> -}
> -EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
> -
> -u32 iommu_sva_get_pasid(struct iommu_sva *handle)
> -{
> -	const struct iommu_ops *ops = dev_iommu_ops(handle->dev);
> -
> -	if (!ops->sva_get_pasid)
> -		return IOMMU_PASID_INVALID;
> -
> -	return ops->sva_get_pasid(handle);
> -}
> -EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
> -
>   /*
>    * Changes the default domain of an iommu group that has *only* one device
>    *
> @@ -3366,3 +3275,31 @@ void iommu_detach_device_pasid(struct iommu_domain *domain, struct device *dev,
>   
>   	iommu_group_put(group);
>   }
> +
> +/*
> + * This is a variant of iommu_get_domain_for_dev(). It returns the existing
> + * domain attached to pasid of a device. It's only for internal use of the
> + * IOMMU subsystem. The caller must take care to avoid any possible
> + * use-after-free case.
> + */
> +struct iommu_domain *
> +iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid)
> +{
> +	struct iommu_domain *domain;
> +	struct iommu_group *group;
> +
> +	if (!pasid_valid(pasid))
> +		return NULL;
> +
> +	group = iommu_group_get(dev);
> +	if (!group)
> +		return NULL;
> +	/*
> +	 * The xarray protects its internal state with RCU. Hence the domain
> +	 * obtained is either NULL or fully formed.
> +	 */
> +	domain = xa_load(&group->pasid_array, pasid);
> +	iommu_group_put(group);
> +
> +	return domain;
> +}

-- 
Regards,
Yi Liu

Powered by blists - more mailing lists