Date:   Thu, 20 Sep 2018 10:21:14 -0700
From:   Jacob Pan <jacob.jun.pan@...ux.intel.com>
To:     Eric Auger <eric.auger@...hat.com>
Cc:     eric.auger.pro@...il.com, iommu@...ts.linux-foundation.org,
        linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
        kvmarm@...ts.cs.columbia.edu, joro@...tes.org,
        alex.williamson@...hat.com, yi.l.liu@...ux.intel.com,
        jean-philippe.brucker@....com, will.deacon@....com,
        robin.murphy@....com, tianyu.lan@...el.com, ashok.raj@...el.com,
        marc.zyngier@....com, christoffer.dall@....com,
        peter.maydell@...aro.org, jacob.jun.pan@...ux.intel.com
Subject: Re: [RFC v2 01/20] iommu: Introduce bind_pasid_table API

On Tue, 18 Sep 2018 16:24:38 +0200
Eric Auger <eric.auger@...hat.com> wrote:

> From: Jacob Pan <jacob.jun.pan@...ux.intel.com>
> 
> In virtualization use case, when a guest is assigned
> a PCI host device, protected by a virtual IOMMU on a guest,
> the physical IOMMU must be programmed to be consistent with
> the guest mappings. If the physical IOMMU supports two
> translation stages it makes sense to program guest mappings
> onto the first stage/level (ARM/VTD terminology) while to host
> owns the stage/level 2.
> 
> In that case, it is mandated to trap on guest configuration
> settings and pass those to the physical iommu driver.
> 
> This patch adds a new API to the iommu subsystem that allows
> to bind and unbind the guest configuration data to the host.
> 
> A generic iommu_pasid_table_config struct is introduced in
> a new iommu.h uapi header. This is going to be used by the VFIO
> user API. We foresee at least two specializations of this struct,
> for PASID table passing and ARM SMMUv3.
> 
> Signed-off-by: Jean-Philippe Brucker <jean-philippe.brucker@....com>
> Signed-off-by: Liu, Yi L <yi.l.liu@...ux.intel.com>
> Signed-off-by: Ashok Raj <ashok.raj@...el.com>
> Signed-off-by: Jacob Pan <jacob.jun.pan@...ux.intel.com>
> Signed-off-by: Eric Auger <eric.auger@...hat.com>
> 
> ---
> 
> In practice, I think it would be simpler to have a single
> set_pasid_table function instead of bind/unbind. The "bypass" field
> tells the stage 1 is bypassed (equivalent to the unbind actually).
> On userspace we have notifications that the device context has
> changed. Calling either bind or unbind requires to have an understand
> of what was the previous state and call different notifiers. So to me
> the bind/unbind complexifies the user integration while not bring much
> benefits.
> 
I don't have strong preference and I think having a single function
makes sense. In VT-d2, the bind/unbind operation is a result of PASID
cache invalidation from the guest. So there is no symmetrical
bind/unbin user calls.

> This patch generalizes the API introduced by Jacob & co-authors in
> https://lwn.net/Articles/754331/
> 
> v1 -> v2:
> - restore the original pasid table name
> - remove the struct device * parameter in the API
> - reworked iommu_pasid_smmuv3
> ---
>  drivers/iommu/iommu.c      | 19 ++++++++++++++
>  include/linux/iommu.h      | 21 +++++++++++++++
>  include/uapi/linux/iommu.h | 52
> ++++++++++++++++++++++++++++++++++++++ 3 files changed, 92
> insertions(+) create mode 100644 include/uapi/linux/iommu.h
> 
> diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
> index 8c15c5980299..db2c7c9502ae 100644
> --- a/drivers/iommu/iommu.c
> +++ b/drivers/iommu/iommu.c
> @@ -1362,6 +1362,25 @@ int iommu_attach_device(struct iommu_domain
> *domain, struct device *dev) }
>  EXPORT_SYMBOL_GPL(iommu_attach_device);
>  
> +int iommu_bind_pasid_table(struct iommu_domain *domain,
> +			   struct iommu_pasid_table_config *cfg)
> +{
> +	if (unlikely(!domain->ops->bind_pasid_table))
> +		return -ENODEV;
> +
> +	return domain->ops->bind_pasid_table(domain, cfg);
> +}
> +EXPORT_SYMBOL_GPL(iommu_bind_pasid_table);
> +
> +void iommu_unbind_pasid_table(struct iommu_domain *domain)
> +{
> +	if (unlikely(!domain->ops->unbind_pasid_table))
> +		return;
> +
> +	domain->ops->unbind_pasid_table(domain);
> +}
> +EXPORT_SYMBOL_GPL(iommu_unbind_pasid_table);
> +
>  static void __iommu_detach_device(struct iommu_domain *domain,
>  				  struct device *dev)
>  {
> diff --git a/include/linux/iommu.h b/include/linux/iommu.h
> index 87994c265bf5..e56cad4863f7 100644
> --- a/include/linux/iommu.h
> +++ b/include/linux/iommu.h
> @@ -25,6 +25,7 @@
>  #include <linux/errno.h>
>  #include <linux/err.h>
>  #include <linux/of.h>
> +#include <uapi/linux/iommu.h>
>  
>  #define IOMMU_READ	(1 << 0)
>  #define IOMMU_WRITE	(1 << 1)
> @@ -185,6 +186,8 @@ struct iommu_resv_region {
>   * @domain_get_windows: Return the number of windows for a domain
>   * @of_xlate: add OF master IDs to iommu grouping
>   * @pgsize_bitmap: bitmap of all possible supported page sizes
> + * @bind_pasid_table: bind pasid table
> + * @unbind_pasid_table: unbind pasid table and restore defaults
>   */
>  struct iommu_ops {
>  	bool (*capable)(enum iommu_cap);
> @@ -231,6 +234,10 @@ struct iommu_ops {
>  	int (*of_xlate)(struct device *dev, struct of_phandle_args
> *args); bool (*is_attach_deferred)(struct iommu_domain *domain,
> struct device *dev); 
> +	int (*bind_pasid_table)(struct iommu_domain *domain,
> +				struct iommu_pasid_table_config
> *cfg);
> +	void (*unbind_pasid_table)(struct iommu_domain *domain);
> +
>  	unsigned long pgsize_bitmap;
>  };
>  
> @@ -292,6 +299,9 @@ extern int iommu_attach_device(struct
> iommu_domain *domain, struct device *dev);
>  extern void iommu_detach_device(struct iommu_domain *domain,
>  				struct device *dev);
> +extern int iommu_bind_pasid_table(struct iommu_domain *domain,
> +				  struct iommu_pasid_table_config
> *cfg); +extern void iommu_unbind_pasid_table(struct iommu_domain
> *domain); extern struct iommu_domain *iommu_get_domain_for_dev(struct
> device *dev); extern int iommu_map(struct iommu_domain *domain,
> unsigned long iova, phys_addr_t paddr, size_t size, int prot);
> @@ -684,6 +694,17 @@ const struct iommu_ops
> *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) return NULL;
>  }
>  
> +static inline
> +int iommu_bind_pasid_table(struct iommu_domain *domain,
> +			   struct iommu_pasid_table_config *cfg)
> +{
> +	return -ENODEV;
> +}
> +static inline
> +void iommu_unbind_pasid_table(struct iommu_domain *domain)
> +{
> +}
> +
>  #endif /* CONFIG_IOMMU_API */
>  
>  #ifdef CONFIG_IOMMU_DEBUGFS
> diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h
> new file mode 100644
> index 000000000000..babec91ae7e1
> --- /dev/null
> +++ b/include/uapi/linux/iommu.h
> @@ -0,0 +1,52 @@
> +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
> +/*
> + * IOMMU user API definitions
> + *
> + *
> + * This program is free software; you can redistribute it and/or
> modify
> + * it under the terms of the GNU General Public License version 2 as
> + * published by the Free Software Foundation.
> + */
> +
> +#ifndef _UAPI_IOMMU_H
> +#define _UAPI_IOMMU_H
> +
> +#include <linux/types.h>
> +
> +/**
> + * SMMUv3 Stream Table Entry stage 1 related information
> + * @s1contextptr: Context Descriptor Table GPA
> + * @abort: shall the STE lead to abort
> + * @s1fmt: STE s1fmt field as set by the guest
> + * @s1cdmax: STE s1cdmax as set by the guest
> + * @s1dss: STE s1dss as set by the guest
> + * All field names match the smmu 3.0/3.1 spec (ARM IHI 0070A)
> + */
> +struct iommu_pasid_smmuv3 {
> +	__u64 s1contextptr;
> +	__u8 bypass;
> +	__u8 abort;
> +	__u8 s1fmt;
> +	__u8 s1cdmax;
> +	__u8 s1dss;
> +};
> +
> +/**
> + * PASID table data used to bind guest PASID table to the host IOMMU
> + * Note PASID table corresponds to the Context Table on ARM SMMUv3.
> + *
> + * @version: API version to prepare for future extensions
> + * @format: format of the PASID table
> + *
> + */
> +struct iommu_pasid_table_config {
don;t you need some vendor neutral data such as 
 * @base_ptr:	PASID table pointer
 * @pasid_bits:	number of bits supported in the guest PASID table, must be less
 *		or equal than the host supported PASID size.


> +#define PASID_TABLE_CFG_VERSION_1 1
> +	__u32 version;
> +#define IOMMU_PASID_FORMAT_SMMUV3	(1 << 0)
> +	__u32 format;
> +	union {
> +		struct iommu_pasid_smmuv3 smmuv3;
> +	};
> +};
> +
> +#endif /* _UAPI_IOMMU_H */

Powered by blists - more mailing lists