[dpdk-dev] [PATCH v7 3/9] linuxapp/eal_pci: get iommu class

[Burakov, Anatoly]

> From: Santosh Shukla [mailto:santosh.shukla at caviumnetworks.com]
> Sent: Thursday, August 31, 2017 4:26 AM
> To: dev at dpdk.org
> Cc: thomas at monjalon.net; jerin.jacob at caviumnetworks.com;
> hemant.agrawal at nxp.com; olivier.matz at 6wind.com;
> maxime.coquelin at redhat.com; Gonzalez Monroy, Sergio
> <sergio.gonzalez.monroy at intel.com>; Richardson, Bruce
> <bruce.richardson at intel.com>; shreyansh.jain at nxp.com;
> gaetan.rivet at 6wind.com; Burakov, Anatoly <anatoly.burakov at intel.com>;
> stephen at networkplumber.org; aconole at redhat.com; Santosh Shukla
> <santosh.shukla at caviumnetworks.com>
> Subject: [PATCH v7 3/9] linuxapp/eal_pci: get iommu class
> 
> Get iommu class of PCI device on the bus and returns preferred iova
> mapping mode for that bus.
> 
> Patch also introduces RTE_PCI_DRV_IOVA_AS_VA drv flag.
> Flag used when driver needs to operate in iova=va mode.
> 
> Algorithm for iova scheme selection for PCI bus:
> 0. If no device bound then return with RTE_IOVA_DC mapping mode, else
> goto 1).
> 1. Look for device attached to vfio kdrv and has .drv_flag set to
> RTE_PCI_DRV_IOVA_AS_VA.
> 2. Look for any device attached to UIO class of driver.
> 3. Check for vfio-noiommu mode enabled.
> 
> If 2) & 3) is false and 1) is true then select mapping scheme as RTE_IOVA_VA.
> Otherwise use default mapping scheme (RTE_IOVA_PA).
> 
> Signed-off-by: Santosh Shukla <santosh.shukla at caviumnetworks.com>
> Signed-off-by: Jerin Jacob <jerin.jacob at caviumnetworks.com>
> Reviewed-by: Maxime Coquelin <maxime.coquelin at redhat.com>
> Acked-by: Hemant Agrawal <hemant.agrawal at nxp.com>
> ---
> v6 --> v7:
> - squashed v6 series patch no [01/12] & [05/12]..
>   i.e.. moved RTE_PCI_DRV_IOVA_AS_VA flag into this patch. (Aaron
> comment).
> 
>  lib/librte_eal/common/include/rte_pci.h         |  2 +
>  lib/librte_eal/linuxapp/eal/eal_pci.c           | 95
> +++++++++++++++++++++++++
>  lib/librte_eal/linuxapp/eal/eal_vfio.c          | 19 +++++
>  lib/librte_eal/linuxapp/eal/eal_vfio.h          |  4 ++
>  lib/librte_eal/linuxapp/eal/rte_eal_version.map |  1 +
>  5 files changed, 121 insertions(+)
> 
> diff --git a/lib/librte_eal/common/include/rte_pci.h
> b/lib/librte_eal/common/include/rte_pci.h
> index 0e36de093..a67d77f22 100644
> --- a/lib/librte_eal/common/include/rte_pci.h
> +++ b/lib/librte_eal/common/include/rte_pci.h
> @@ -202,6 +202,8 @@ struct rte_pci_bus {  #define
> RTE_PCI_DRV_INTR_RMV 0x0010
>  /** Device driver needs to keep mapped resources if unsupported dev
> detected */  #define RTE_PCI_DRV_KEEP_MAPPED_RES 0x0020
> +/** Device driver supports iova as va */ #define
> RTE_PCI_DRV_IOVA_AS_VA
> +0X0040
> 
>  /**
>   * A structure describing a PCI mapping.
> diff --git a/lib/librte_eal/linuxapp/eal/eal_pci.c
> b/lib/librte_eal/linuxapp/eal/eal_pci.c
> index 8951ce742..9725fd493 100644
> --- a/lib/librte_eal/linuxapp/eal/eal_pci.c
> +++ b/lib/librte_eal/linuxapp/eal/eal_pci.c
> @@ -45,6 +45,7 @@
>  #include "eal_filesystem.h"
>  #include "eal_private.h"
>  #include "eal_pci_init.h"
> +#include "eal_vfio.h"
> 
>  /**
>   * @file
> @@ -487,6 +488,100 @@ rte_pci_scan(void)
>  	return -1;
>  }
> 
> +/*
> + * Is pci device bound to any kdrv
> + */
> +static inline int
> +pci_device_is_bound(void)
> +{
> +	struct rte_pci_device *dev = NULL;
> +	int ret = 0;
> +
> +	FOREACH_DEVICE_ON_PCIBUS(dev) {
> +		if (dev->kdrv == RTE_KDRV_UNKNOWN ||
> +		    dev->kdrv == RTE_KDRV_NONE) {
> +			continue;
> +		} else {
> +			ret = 1;
> +			break;
> +		}
> +	}
> +	return ret;
> +}
> +
> +/*
> + * Any one of the device bound to uio
> + */
> +static inline int
> +pci_device_bound_uio(void)
> +{
> +	struct rte_pci_device *dev = NULL;
> +
> +	FOREACH_DEVICE_ON_PCIBUS(dev) {
> +		if (dev->kdrv == RTE_KDRV_IGB_UIO ||
> +		   dev->kdrv == RTE_KDRV_UIO_GENERIC) {
> +			return 1;
> +		}
> +	}
> +	return 0;
> +}
> +
> +/*
> + * Any one of the device has iova as va  */ static inline int
> +pci_device_has_iova_va(void)
> +{
> +	struct rte_pci_device *dev = NULL;
> +	struct rte_pci_driver *drv = NULL;
> +
> +	FOREACH_DRIVER_ON_PCIBUS(drv) {
> +		if (drv && drv->drv_flags & RTE_PCI_DRV_IOVA_AS_VA) {
> +			FOREACH_DEVICE_ON_PCIBUS(dev) {
> +				if (dev->kdrv == RTE_KDRV_VFIO &&
> +				    rte_pci_match(drv, dev))
> +					return 1;
> +			}
> +		}
> +	}
> +	return 0;
> +}
> +
> +/*
> + * Get iommu class of PCI devices on the bus.
> + */
> +enum rte_iova_mode
> +rte_pci_get_iommu_class(void)
> +{
> +	bool is_bound;
> +	bool is_vfio_noiommu_enabled = true;
> +	bool has_iova_va;
> +	bool is_bound_uio;
> +
> +	is_bound = pci_device_is_bound();
> +	if (!is_bound)
> +		return RTE_IOVA_DC;
> +
> +	has_iova_va = pci_device_has_iova_va();
> +	is_bound_uio = pci_device_bound_uio(); #ifdef VFIO_PRESENT
> +	is_vfio_noiommu_enabled = vfio_noiommu_is_enabled() == 1 ? 1 :
> 0;

If you specify is_vfio_noiommu_enabled as bool, you should probably treat it as such, and assign true/false.

Other than that, I'm curious why is it always set to "true" by default? If we don't have VFIO compiled, it seems like the error message would always complain about vfio-noiommu mode being enabled, which is confusing.

Thanks,
Anatoly