David Marchand b76fafb174 eal: fix IOVA mode selection as VA for PCI drivers ... The incriminated commit broke the use of RTE_PCI_DRV_IOVA_AS_VA which was intended to mean "driver only supports VA" but had been understood as "driver supports both PA and VA" by most net drivers and used to let dpdk processes to run as non root (which do not have access to physical addresses on recent kernels). The check on physical addresses actually closed the gap for those drivers. We don't need to mark them with RTE_PCI_DRV_IOVA_AS_VA and this flag can retain its intended meaning. Document explicitly its meaning. We can check that a driver requirement wrt to IOVA mode is fulfilled before trying to probe a device. Finally, document the heuristic used to select the IOVA mode and hope that we won't break it again. Fixes: 703458e19c ("bus/pci: consider only usable devices for IOVA mode") Signed-off-by: David Marchand <david.marchand@redhat.com> Reviewed-by: Jerin Jacob <jerinj@marvell.com> Tested-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>		2019-07-22 17:45:52 +02:00
..
nfpcore	net/nfp: fix memory leak	2019-04-12 11:02:02 +02:00
Makefile	net/nfp: check hugepage IOVA based on DMA mask	2018-10-28 22:06:51 +01:00
meson.build	drivers: add reasons for components being disabled	2019-07-02 23:21:11 +02:00
nfp_net_ctrl.h	drivers/net: fix shifting 32-bit signed variable 31 times	2019-03-01 18:17:36 +01:00
nfp_net_logs.h	net/nfp: add CPP bridge as service	2019-01-14 22:57:33 +01:00
nfp_net_pmd.h	net: add rte prefix to ether defines	2019-05-24 13:34:45 +02:00
nfp_net.c	eal: fix IOVA mode selection as VA for PCI drivers	2019-07-22 17:45:52 +02:00
rte_pmd_nfp_version.map	nfp: introduce driver initialization	2015-12-08 03:00:42 +01:00