numam-spdk/lib/env_dpdk
Jim Harris 4d8c6a8440 env_dpdk: handle RTE_BAD_IOVA correctly in vtophys_get_paddr_pagemap
We've had cases (especially with vhost) in the past where we have
a valid vaddr but the backing page was not assigned yet.  DPDK used
to return 0 as the phys addr in these cases but now it returns
RTE_BAD_IOVA.  Unfortunately we don't have any tests currently
in the test pool that hit this condition, but at least one user
has an environment which hits it and this patch fixes their
problem.

Make sure we still work with older versions of DPDK as well.

Fixes issue #260.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ie3c0ef54a3e34153bd0850ecfb2be4fcb92455b1

Reviewed-on: https://review.gerrithub.io/410071
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2018-05-17 17:07:44 +00:00
..
env_internal.h env_dpdk: track PCI devices internally for vtophys 2018-04-02 14:03:05 -04:00
env.c env: Explicitly fail calls to spdk_malloc with flags of 0 2018-05-11 16:16:38 +00:00
env.mk env_dpdk: remove hard-coded library paths 2018-02-23 11:07:38 -05:00
init.c app: pci_black/whitelist on global config and command line option 2018-04-30 17:25:41 +00:00
Makefile env: add pci_virtio.c 2017-09-26 14:28:24 -04:00
memory.c env: bump max virtual address map from 128tb to 256tb 2018-01-25 11:05:59 -05:00
pci_ioat.c env: register PMDs on associated first probe 2017-03-06 12:44:34 -07:00
pci_nvme.c env: register PMDs on associated first probe 2017-03-06 12:44:34 -07:00
pci_virtio.c bdev/virtio: added vhost-blk initiator 2018-03-02 13:41:38 -05:00
pci.c env: remove deprecated spdk_pci_get_device() 2018-05-10 19:40:22 +00:00
threads.c env_dpdk: add an assert check for last core 2018-02-22 10:43:59 -05:00
vtophys.c env_dpdk: handle RTE_BAD_IOVA correctly in vtophys_get_paddr_pagemap 2018-05-17 17:07:44 +00:00