Message-ID: <c9adfbda-b78a-405a-a691-9f99d7dc2a26@arm.com>
Date:   Tue, 5 Mar 2019 14:56:50 +0000
From:   Jean-Philippe Brucker <jean-philippe.brucker@....com>
To:     Eric Auger <eric.auger@...hat.com>, 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, jacob.jun.pan@...ux.intel.com,
        yi.l.liu@...ux.intel.com, will.deacon@....com, robin.murphy@....com
Cc:     marc.zyngier@....com, peter.maydell@...aro.org,
        kevin.tian@...el.com, ashok.raj@...el.com, christoffer.dall@....com
Subject: Re: [PATCH v4 02/22] iommu: introduce device fault data

On 18/02/2019 13:54, Eric Auger wrote:
> From: Jacob Pan <jacob.jun.pan@...ux.intel.com>
> 
> Device faults detected by IOMMU can be reported outside the IOMMU
> subsystem for further processing. This patch introduces
> a generic device fault data structure.
> 
> The fault can be either an unrecoverable fault or a page request,
> also referred to as a recoverable fault.
> 
> We only care about non internal faults that are likely to be reported
> to an external subsystem.
> 
> Signed-off-by: Jacob Pan <jacob.jun.pan@...ux.intel.com>
> 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: Eric Auger <eric.auger@...hat.com>
> 
> ---
> 
> v3 -> v4:
> - use a union containing aither an unrecoverable fault or a page
>   request message. Move the device private data in the page request
>   structure. Reshuffle the fields and use flags.
> - move fault perm attributes to the uapi
> - remove a bunch of iommu_fault_reason enum values that were related
>   to internal errors
> ---
>  include/linux/iommu.h      |  47 +++++++++++++++
>  include/uapi/linux/iommu.h | 115 +++++++++++++++++++++++++++++++++++++
>  2 files changed, 162 insertions(+)
>  create mode 100644 include/uapi/linux/iommu.h
> 
> diff --git a/include/linux/iommu.h b/include/linux/iommu.h
> index e90da6b6f3d1..032d33894723 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)
> @@ -48,6 +49,7 @@ struct bus_type;
>  struct device;
>  struct iommu_domain;
>  struct notifier_block;
> +struct iommu_fault_event;
>  
>  /* iommu fault flags */
>  #define IOMMU_FAULT_READ	0x0
> @@ -55,6 +57,7 @@ struct notifier_block;
>  
>  typedef int (*iommu_fault_handler_t)(struct iommu_domain *,
>  			struct device *, unsigned long, int, void *);
> +typedef int (*iommu_dev_fault_handler_t)(struct iommu_fault_event *, void *);
>  
>  struct iommu_domain_geometry {
>  	dma_addr_t aperture_start; /* First address that can be mapped    */
> @@ -243,6 +246,49 @@ struct iommu_device {
>  	struct device *dev;
>  };
>  
> +/**
> + * struct iommu_fault_event - Generic per device fault data
> + *
> + * - PCI and non-PCI devices
> + * - Recoverable faults (e.g. page request), information based on PCI ATS
> + *   and PASID spec.

"for example information based on PCI PRI and PASID extensions"? ATS+PRI
have been integrated into the main spec, and only PRI is relevant here.

> + * - Un-recoverable faults of device interest

"of interest to device drivers"?

> + * - DMA remapping and IRQ remapping faults
> + *
> + * @fault: fault descriptor
> + * @iommu_private: used by the IOMMU driver for storing fault-specific
> + *                 data. Users should not modify this field before
> + *                 sending the fault response.
> + */
> +struct iommu_fault_event {
> +	struct iommu_fault fault;
> +	u64 iommu_private;
> +};
> +
> +/**
> + * struct iommu_fault_param - per-device IOMMU fault data
> + * @dev_fault_handler: Callback function to handle IOMMU faults at device level
> + * @data: handler private data
> + *
> + */
> +struct iommu_fault_param {
> +	iommu_dev_fault_handler_t handler;
> +	void *data;
> +};
> +
> +/**
> + * struct iommu_param - collection of per-device IOMMU data
> + *
> + * @fault_param: IOMMU detected device fault reporting data
> + *
> + * TODO: migrate other per device data pointers under iommu_dev_data, e.g.
> + *	struct iommu_group	*iommu_group;
> + *	struct iommu_fwspec	*iommu_fwspec;
> + */
> +struct iommu_param {
> +	struct iommu_fault_param *fault_param;
> +};
> +
>  int  iommu_device_register(struct iommu_device *iommu);
>  void iommu_device_unregister(struct iommu_device *iommu);
>  int  iommu_device_sysfs_add(struct iommu_device *iommu,
> @@ -418,6 +464,7 @@ struct iommu_ops {};
>  struct iommu_group {};
>  struct iommu_fwspec {};
>  struct iommu_device {};
> +struct iommu_fault_param {};
>  
>  static inline bool iommu_present(struct bus_type *bus)
>  {
> diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h
> new file mode 100644
> index 000000000000..7ebf23ed6ccb
> --- /dev/null
> +++ b/include/uapi/linux/iommu.h
> @@ -0,0 +1,115 @@
> +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
> +/*
> + * IOMMU user API definitions
> + */
> +
> +#ifndef _UAPI_IOMMU_H
> +#define _UAPI_IOMMU_H
> +
> +#include <linux/types.h>
> +
> +/*  Generic fault types, can be expanded IRQ remapping fault */
> +enum iommu_fault_type {
> +	IOMMU_FAULT_DMA_UNRECOV = 1,	/* unrecoverable fault */
> +	IOMMU_FAULT_PAGE_REQ,		/* page request fault */
> +};
> +
> +enum iommu_fault_reason {
> +	IOMMU_FAULT_REASON_UNKNOWN = 0,
> +
> +	/* Could not access the PASID table (fetch caused external abort) */
> +	IOMMU_FAULT_REASON_PASID_FETCH,
> +
> +	/* pasid entry is invalid or has configuration errors */
> +	IOMMU_FAULT_REASON_BAD_PASID_ENTRY,
> +
> +	/*
> +	 * PASID is out of range (e.g. exceeds the maximum PASID
> +	 * supported by the IOMMU) or disabled.
> +	 */
> +	IOMMU_FAULT_REASON_PASID_INVALID,
> +
> +	/*
> +	 * An external abort occurred fetching (or updating) a translation
> +	 * table descriptor
> +	 */
> +	IOMMU_FAULT_REASON_WALK_EABT,
> +
> +	/*
> +	 * Could not access the page table entry (Bad address),
> +	 * actual translation fault
> +	 */
> +	IOMMU_FAULT_REASON_PTE_FETCH,
> +
> +	/* Protection flag check failed */
> +	IOMMU_FAULT_REASON_PERMISSION,
> +
> +	/* access flag check failed */
> +	IOMMU_FAULT_REASON_ACCESS,
> +
> +	/* Output address of a translation stage caused Address Size fault */
> +	IOMMU_FAULT_REASON_OOR_ADDRESS,
> +};
> +
> +/**
> + * Unrecoverable fault data
> + * @reason: reason of the fault
> + * @addr: offending page address
> + * @fetch_addr: address that caused a fetch abort, if any
> + * @pasid: contains process address space ID, used in shared virtual memory
> + * @perm: Requested permission access using by the incoming transaction
> + *	IOMMU_FAULT_READ, IOMMU_FAULT_WRITE

Stale comment

> + */
> +struct iommu_fault_unrecoverable {
> +	__u32	reason; /* enum iommu_fault_reason */
> +#define IOMMU_FAULT_UNRECOV_PASID_VALID		(1 << 0)
> +#define IOMMU_FAULT_UNRECOV_PERM_VALID		(1 << 1)

Not needed, since @perm is already a bitfield

> +#define IOMMU_FAULT_UNRECOV_ADDR_VALID		(1 << 2)
> +#define IOMMU_FAULT_UNRECOV_FETCH_ADDR_VALID	(1 << 3)
> +	__u32	flags;
> +	__u32	pasid;
> +#define IOMMU_FAULT_PERM_WRITE	(1 << 0) /* write */
> +#define IOMMU_FAULT_PERM_EXEC	(1 << 1) /* exec */
> +#define IOMMU_FAULT_PERM_PRIV	(1 << 2) /* priviledged */

typo "privileged"

> +#define IOMMU_FAULT_PERM_INST	(1 << 3) /* instruction */

Could you move these outside the struct definition? They are shared with
the other struct. And it would be less confusing, from the device driver
point of view, to merge those with the existing IOMMU_FAULT_* defines
(but moving them to UAPI and making them bits)

> +	__u32	perm;
> +	__u64	addr;
> +	__u64	fetch_addr;
> +};
> +
> +/*
> + * Page Request data (aka. recoverable fault data)
> + * @flags : encodes whether the pasid is valid and whether this
> + * is the last page in group
> + * @pasid: pasid
> + * @grpid: page request group index
> + * @perm: requested page permissions
> + * @addr: page address
> + */
> +struct iommu_fault_page_request {
> +#define IOMMU_FAULT_PAGE_REQUEST_PASID_PRESENT	(1 << 0)

PASID_VALID, to be consistent with the other set of flags?

> +#define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE	(1 << 1)
> +#define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA	(1 << 2)
> +	__u32   flags;
> +	__u32	pasid;
> +	__u32	grpid;
> +	__u32	perm;
> +	__u64	addr;

Given that we'll be reporting stall faults using this struct, it would
be good to have the fetch_addr field and flag here as well.

> +	__u64	private_data[2];
> +};
> +
> +/**
> + * struct iommu_fault - Generic fault data
> + *
> + * @type contains fault type
> + */
> +
> +struct iommu_fault {
> +	__u32	type;   /* enum iommu_fault_type */
> +	__u32	reserved;
> +	union {
> +		struct iommu_fault_unrecoverable event;
> +		struct iommu_fault_page_request prm;

What's the 'm' in "prm"? Maybe just "pr"?

Thanks,
Jean

> +	};
> +};
> +#endif /* _UAPI_IOMMU_H */
> 

Powered by blists - more mailing lists