Re: [PATCH v1 2/3] powerpc/powernv: Support PCI error injection

[Michael Neuling <mikey@neuling.org>]

On Mon, 2014-06-23 at 12:14 +1000, Gavin Shan wrote:
> The patch implements one OPAL firmware sysfs file to support PCI error
> injection: "/sys/firmware/opal/errinjct", which will be used like the
> way described as follows.
>=20
> According to PAPR spec, there are 3 RTAS calls related to error injection=
:
> "ibm,open-errinjct": allocate token prior to doing error injection.
> "ibm,close-errinjct": release the token allocated from "ibm,open-errinjct=
".
> "ibm,errinjct": do error injection.
>=20
> Sysfs file /sys/firmware/opal/errinjct accepts strings that have fixed
> format "ei_token ...". For now, we only support 32-bits and 64-bits
> PCI error injection and they should have following strings written to
> /sys/firmware/opal/errinjct as follows. We don't have corresponding
> sysfs files for "ibm,open-errinjct" and "ibm,close-errinjct", which
> means that we rely on userland to maintain the token by itself.

This sounds cool. =20

Can you document the sysfs interface in Documentation/powerpc?

Mikey

>=20
> 32-bits PCI error: "7:addr:mask:iommu_group_id:function".
> 64-bits PCI error: "8:addr:mask:iommu_group_id:function".
>=20
> The above "7" and "8" represent 32-bits and 64-bits PCI error seperately
> and "function" is one of the specific PCI errors (e.g. MMIO access addres=
s
> parity error), which are defined by PAPR spec.
>=20
> Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
> ---
>  arch/powerpc/include/asm/opal.h                |   1 +
>  arch/powerpc/platforms/powernv/Makefile        |   2 +-
>  arch/powerpc/platforms/powernv/opal-errinjct.c | 184 +++++++++++++++++++=
++++++
>  arch/powerpc/platforms/powernv/opal.c          |   2 +
>  4 files changed, 188 insertions(+), 1 deletion(-)
>  create mode 100644 arch/powerpc/platforms/powernv/opal-errinjct.c
>=20
> diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/o=
pal.h
> index d982bb8..bf280d9 100644
> --- a/arch/powerpc/include/asm/opal.h
> +++ b/arch/powerpc/include/asm/opal.h
> @@ -985,6 +985,7 @@ extern int opal_elog_init(void);
>  extern void opal_platform_dump_init(void);
>  extern void opal_sys_param_init(void);
>  extern void opal_msglog_init(void);
> +extern void opal_errinjct_init(void);
> =20
>  extern int opal_machine_check(struct pt_regs *regs);
>  extern bool opal_mce_check_early_recovery(struct pt_regs *regs);
> diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platf=
orms/powernv/Makefile
> index 63cebb9..4711de8 100644
> --- a/arch/powerpc/platforms/powernv/Makefile
> +++ b/arch/powerpc/platforms/powernv/Makefile
> @@ -1,7 +1,7 @@
>  obj-y			+=3D setup.o opal-takeover.o opal-wrappers.o opal.o opal-async.o
>  obj-y			+=3D opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
>  obj-y			+=3D rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
> -obj-y			+=3D opal-msglog.o
> +obj-y			+=3D opal-msglog.o opal-errinjct.o
> =20
>  obj-$(CONFIG_SMP)	+=3D smp.o
>  obj-$(CONFIG_PCI)	+=3D pci.o pci-p5ioc2.o pci-ioda.o
> diff --git a/arch/powerpc/platforms/powernv/opal-errinjct.c b/arch/powerp=
c/platforms/powernv/opal-errinjct.c
> new file mode 100644
> index 0000000..29c9e83
> --- /dev/null
> +++ b/arch/powerpc/platforms/powernv/opal-errinjct.c
> @@ -0,0 +1,184 @@
> +/*
> + * The file supports error injection, which works based on OPAL API.
> + * For now, we only support PCI error injection. We need support
> + * injecting other types of errors in future.
> + *
> + * Copyright Gavin Shan, IBM Corporation 2014.
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published by
> + * the Free Software Foundation; either version 2 of the License, or
> + * (at your option) any later version.
> + */
> +
> +#include <linux/kernel.h>
> +#include <linux/init.h>
> +#include <linux/msi.h>
> +#include <linux/pci.h>
> +#include <linux/iommu.h>
> +#include <linux/random.h>
> +#include <linux/slab.h>
> +#include <linux/sysfs.h>
> +#include <linux/fs.h>
> +#include <linux/fcntl.h>
> +#include <linux/kobject.h>
> +
> +#include <asm/msi_bitmap.h>
> +#include <asm/iommu.h>
> +#include <asm/pci-bridge.h>
> +#include <asm/ppc-pci.h>
> +#include <asm/opal.h>
> +
> +#include "powernv.h"
> +#include "pci.h"
> +
> +static DEFINE_MUTEX(errinjct_mutex);
> +
> +static int errinjct_iommu_group_to_phb_and_pe(uint32_t iommu_grp_id,
> +					      uint64_t *phb_id,
> +					      uint32_t *pe_num)
> +{
> +#ifdef CONFIG_IOMMU_API
> +	struct iommu_group *iommu_grp;
> +	struct iommu_table *tbl;
> +	struct pnv_ioda_pe *pe;
> +
> +	iommu_grp =3D iommu_group_get_by_id(iommu_grp_id);
> +	if (!iommu_grp)
> +		return -ENODEV;
> +
> +	tbl =3D iommu_group_get_iommudata(iommu_grp);
> +	if (!tbl)
> +		return -ENODEV;
> +
> +	pe =3D container_of(tbl, struct pnv_ioda_pe, tce32_table);
> +	if (!pe->phb)
> +		return -ENODEV;
> +
> +	*phb_id =3D pe->phb->opal_id;
> +	*pe_num =3D pe->pe_number;
> +
> +	return 0;
> +#endif
> +
> +	return -ENXIO;
> +}
> +
> +static int errinjct_ioa_bus_error(const char *buf, struct OpalErrinjct *=
ei)
> +{
> +	uint32_t iommu_grp_id;
> +	int ret;
> +
> +	/* Extract parameters */
> +	ret =3D sscanf(buf, "%x:%x:%x:%x:%x",
> +		     &ei->type, &ei->ioa.addr,
> +		     &ei->ioa.mask, &iommu_grp_id, ei->ioa.function);
> +	if (ret !=3D 5)
> +		return -EINVAL;
> +
> +	/* Invalid function ? */
> +	if (ei->ioa.function < OpalEitIoaLoadMemAddr ||
> +	    ei->ioa.function > OpalEitIoaDmaWriteMemTarget)
> +		return -ERANGE;
> +
> +	/* Retrieve PHB ID and PE number */
> +	ret =3D errinjct_iommu_group_to_phb_and_pe(iommu_grp_id,
> +						 &ei->ioa.phb_id,
> +						 &ei->ioa.pe);
> +	if (ret)
> +		return ret;
> +
> +	return 0;
> +}
> +
> +static int errinjct_ioa_bus_error64(const char *buf, struct OpalErrinjct=
 *ei)
> +{
> +	uint32_t iommu_grp_id;
> +	int ret;
> +
> +	/* Extract parameter */
> +	ret =3D sscanf(buf, "%x:%llx:%llx:%x:%x",
> +		     &ei->type, &ei->ioa64.addr,
> +		     &ei->ioa64.mask, &iommu_grp_id, &ei->ioa64.function);
> +	if (ret !=3D 5)
> +		return -EINVAL;
> +
> +	/* Invalid function ? */
> +	if (ei->ioa64.function < OpalEitIoaLoadMemAddr ||
> +	    ei->ioa64.function > OpalEitIoaDmaWriteMemTarget)
> +		return -ERANGE;
> +
> +	/* Retrieve PHB ID and PE number */
> +	ret =3D errinjct_iommu_group_to_phb_and_pe(iommu_grp_id,
> +						 &ei->ioa64.phb_id,
> +						 &ei->ioa64.pe);
> +	if (ret)
> +		return ret;
> +
> +	return 0;
> +}
> +
> +static ssize_t errinjct_store(struct kobject *kobj,
> +			      struct kobj_attribute *attr,
> +			      const char *buf, size_t count)
> +{
> +	struct OpalErrinjct ei;
> +	int ret;
> +	long rc;
> +
> +	/* Extract common parameters */
> +	ret =3D sscanf(buf, "%x", &ei.type);
> +	if (ret !=3D 1)
> +		return -EINVAL;
> +
> +	/* Error injection might be in progress */
> +	if (!mutex_trylock(&errinjct_mutex))
> +		return -EAGAIN;
> +
> +	switch (ei.type) {
> +	case OpalErrinjctTypeIoaBusError:
> +		ret =3D errinjct_ioa_bus_error(buf, &ei);
> +		break;
> +	case OpalErrinjctTypeIoaBusError64:
> +		ret =3D errinjct_ioa_bus_error64(buf, &ei);
> +		break;
> +	default:
> +		ret =3D -ERANGE;
> +	}
> +
> +	/* Invalid parameters ? */
> +	if (ret)
> +		goto mutex_unlock_exit;
> +
> +	/* OPAL call */
> +	rc =3D opal_err_injct(&ei);
> +	if (rc =3D=3D OPAL_SUCCESS)
> +		ret =3D count;
> +	else
> +		ret =3D -EIO;
> +
> +mutex_unlock_exit:
> +	mutex_unlock(&errinjct_mutex);
> +	return ret;
> +}
> +
> +static struct kobj_attribute errinjct_attr =3D
> +	__ATTR(errinjct, 0600, NULL, errinjct_store);
> +
> +void __init opal_errinjct_init(void)
> +{
> +	int ret;
> +
> +	/* Make sure /sys/firmware/opal directory is created */
> +	if (!opal_kobj) {
> +		pr_warn("%s: opal kobject is not available\n",
> +			__func__);
> +		return;
> +	}
> +
> +	/* Create the sysfs files */
> +	ret =3D sysfs_create_file(opal_kobj, &errinjct_attr.attr);
> +	if (ret)
> +		pr_warn("%s: Cannot create sysfs file (%d)\n",
> +			__func__, ret);
> +}
> diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platfor=
ms/powernv/opal.c
> index 360ad80c..cb29bb5 100644
> --- a/arch/powerpc/platforms/powernv/opal.c
> +++ b/arch/powerpc/platforms/powernv/opal.c
> @@ -604,6 +604,8 @@ static int __init opal_init(void)
>  		opal_sys_param_init();
>  		/* Setup message log interface. */
>  		opal_msglog_init();
> +		/* Setup error injection interface */
> +		opal_errinjct_init();
>  	}
> =20
>  	return 0;