[dpdk-dev] [PATCH v2] bus/pci: forbid VA as IOVA mode if IOMMU address width too small

Zhang, Qi Z qi.z.zhang at intel.com
Fri Jan 12 04:56:03 CET 2018



> -----Original Message-----
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Maxime Coquelin
> Sent: Tuesday, January 9, 2018 9:18 PM
> To: dev at dpdk.org; stable at dpdk.org; Tan, Jianfeng <jianfeng.tan at intel.com>;
> santosh.shukla at caviumnetworks.com; Burakov, Anatoly
> <anatoly.burakov at intel.com>; thomas at monjalon.net;
> stephen at networkplumber.org
> Cc: peterx at redhat.com; Maxime Coquelin <maxime.coquelin at redhat.com>
> Subject: [dpdk-dev] [PATCH v2] bus/pci: forbid VA as IOVA mode if IOMMU
> address width too small
> 
> Intel VT-d supports different address widths for the IOVAs, from
> 39 bits to 56 bits.
> 
> While recent processors support at least 48 bits, VT-d emulation currently
> only supports 39 bits. It makes DMA mapping to fail in this case when using
> VA as IOVA mode, as user-space virtual addresses uses up to 47 bits (see
> kernel's Documentation/x86/x86_64/mm.txt).
> 
> This patch parses VT-d CAP register value available in sysfs, and forbid VA as
> IOVA mode if the GAW is 39 bits or unknown.
> 
> Fixes: f37dfab21c98 ("drivers/net: enable IOVA mode for Intel PMDs")
> 
> Cc: stable at dpdk.org
> Signed-off-by: Maxime Coquelin <maxime.coquelin at redhat.com>
> ---
> 
> Changes in v2:
> ==============
> - Rework pci_one_device_iommu_support_va #ifdefery (Stephen)
> - Don't inline introduced functions (Stephen)
> 
>  drivers/bus/pci/linux/pci.c | 108
> ++++++++++++++++++++++++++++++++++++++++----
>  1 file changed, 99 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/bus/pci/linux/pci.c b/drivers/bus/pci/linux/pci.c index
> 25f907e04..0a43c4b89 100644
> --- a/drivers/bus/pci/linux/pci.c
> +++ b/drivers/bus/pci/linux/pci.c
> @@ -547,6 +547,100 @@ pci_one_device_has_iova_va(void)
>  	return 0;
>  }
> 
> +#if defined(RTE_ARCH_X86)
> +static bool
> +pci_one_device_iommu_support_va(struct rte_pci_device *dev) {
> +#define VTD_CAP_SAGAW_SHIFT         8
> +#define VTD_CAP_SAGAW_MASK          (0x1fULL <<
> VTD_CAP_SAGAW_SHIFT)
> +#define X86_VA_WIDTH 47 /* From Documentation/x86/x86_64/mm.txt
> */
> +	struct rte_pci_addr *addr = &dev->addr;
> +	char filename[PATH_MAX];
> +	FILE *fp;
> +	uint64_t sagaw, vtd_cap_reg = 0;
> +	int guest_addr_width = 0;
> +
> +	snprintf(filename, sizeof(filename),
> +		 "%s/" PCI_PRI_FMT "/iommu/intel-iommu/cap",
> +		 rte_pci_get_sysfs_path(), addr->domain, addr->bus, addr->devid,
> +		 addr->function);
> +	if (access(filename, F_OK) == -1) {
> +		/* We don't have an Intel IOMMU, assume VA supported*/
> +		return true;
> +	}
> +
> +	/* We have an intel IOMMU */
> +	fp = fopen(filename, "r");
> +	if (fp == NULL) {
> +		RTE_LOG(ERR, EAL, "%s(): can't open %s\n", __func__, filename);
> +		return false;
> +	}
> +
> +	if (fscanf(fp, "%lx", &vtd_cap_reg) != 1) {
> +		RTE_LOG(ERR, EAL, "%s(): can't read %s\n", __func__, filename);
> +		fclose(fp);
> +		return false;
> +	}
> +
> +	fclose(fp);
> +
> +	sagaw = (vtd_cap_reg & VTD_CAP_SAGAW_MASK) >>
> VTD_CAP_SAGAW_SHIFT;

Base on previous test, sagaw is not the MAX VA address

Below should be the correct cap decode from kernel driver include/linux/intel-iommu.h
#define cap_mgaw(c)	((((c) >> 16) & 0x3f) + 1)

Regards
Qi

> +
> +	switch (sagaw) {
> +	case 2:
> +		guest_addr_width = 39;
> +		break;
> +	case 4:
> +		guest_addr_width = 48;
> +		break;
> +	case 6:
> +		guest_addr_width = 56;
> +		break;
> +	default:
> +		RTE_LOG(ERR, EAL, "Unkwown Intel IOMMU SAGAW value (%lx)\n",
> +				sagaw);
> +		break;
> +	}
> +
> +	if (guest_addr_width < X86_VA_WIDTH)
> +		return false;
> +
> +	return true;
> +}
> +#elif defined(RTE_ARCH_PPC_64)
> +static bool
> +pci_one_device_iommu_support_va(struct rte_pci_device *dev) {
> +	return false;
> +}
> +#else
> +static bool
> +pci_one_device_iommu_support_va(struct rte_pci_device *dev) {
> +	return true;
> +}
> +#endif
> +
> +/*
> + * All devices IOMMUs support VA as IOVA  */ static bool
> +pci_devices_iommu_support_va(void)
> +{
> +	struct rte_pci_device *dev = NULL;
> +	struct rte_pci_driver *drv = NULL;
> +
> +	FOREACH_DRIVER_ON_PCIBUS(drv) {
> +		FOREACH_DEVICE_ON_PCIBUS(dev) {
> +			if (!rte_pci_match(drv, dev))
> +				continue;
> +			if (!pci_one_device_iommu_support_va(dev))
> +				return false;
> +		}
> +	}
> +	return true;
> +}
> +
>  /*
>   * Get iommu class of PCI devices on the bus.
>   */
> @@ -557,12 +651,7 @@ rte_pci_get_iommu_class(void)
>  	bool is_vfio_noiommu_enabled = true;
>  	bool has_iova_va;
>  	bool is_bound_uio;
> -	bool spapr_iommu =
> -#if defined(RTE_ARCH_PPC_64)
> -		true;
> -#else
> -		false;
> -#endif
> +	bool iommu_no_va;
> 
>  	is_bound = pci_one_device_is_bound();
>  	if (!is_bound)
> @@ -570,13 +659,14 @@ rte_pci_get_iommu_class(void)
> 
>  	has_iova_va = pci_one_device_has_iova_va();
>  	is_bound_uio = pci_one_device_bound_uio();
> +	iommu_no_va = !pci_devices_iommu_support_va();
>  #ifdef VFIO_PRESENT
>  	is_vfio_noiommu_enabled = rte_vfio_noiommu_is_enabled() == true ?
>  					true : false;
>  #endif
> 
>  	if (has_iova_va && !is_bound_uio && !is_vfio_noiommu_enabled &&
> -			!spapr_iommu)
> +			!iommu_no_va)
>  		return RTE_IOVA_VA;
> 
>  	if (has_iova_va) {
> @@ -585,8 +675,8 @@ rte_pci_get_iommu_class(void)
>  			RTE_LOG(WARNING, EAL, "vfio-noiommu mode
> configured\n");
>  		if (is_bound_uio)
>  			RTE_LOG(WARNING, EAL, "few device bound to UIO\n");
> -		if (spapr_iommu)
> -			RTE_LOG(WARNING, EAL, "sPAPR IOMMU does not support
> IOVA as VA\n");
> +		if (iommu_no_va)
> +			RTE_LOG(WARNING, EAL, "IOMMU does not support IOVA as
> VA\n");
>  	}
> 
>  	return RTE_IOVA_PA;
> --
> 2.14.3



More information about the dev mailing list