Re: [dpdk-dev] dpdk16.07 and virtio "Cannot mmap IO port resource"

2016-12-11 Thread Gopakumar Choorakkot Edakkunni
nevermind .. I saw the hew ARCH_X86 flag which I dint realise I have to add in my config file when I moved from dpdk2.0 On Sun, Dec 11, 2016 at 12:29 AM, Gopakumar Choorakkot Edakkunni < gopakumar@gmail.com> wrote: > Somewhere I read that the "offset" parameter for sysfs mmap() needs to be >

Re: [dpdk-dev] dpdk16.07 and virtio "Cannot mmap IO port resource"

2016-12-11 Thread Gopakumar Choorakkot Edakkunni
Somewhere I read that the "offset" parameter for sysfs mmap() needs to be the start address of the resource, so I tried the below diff, and mmap still fails .. Still scratching my head diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_uio.c b/lib/librte_eal/linuxapp/eal/eal_pci_uio.c index 1786b75.

Re: [dpdk-dev] dpdk16.07 and virtio "Cannot mmap IO port resource"

2016-12-10 Thread Gopakumar Choorakkot Edakkunni
Hi Oliver, Looking at the kernel code pci_mmap_resource()--->pci_mmap_fits(), it looks like pci_mmap_fits() expects that the "number of pages" requested to map is no larger than the actual size of the pci resource. But in pci_uio_ioport_map() what is passed as the requested size is the end_addr of

[dpdk-dev] dpdk16.07 and virtio "Cannot mmap IO port resource"

2016-12-09 Thread Gopakumar Choorakkot Edakkunni
I tried to load up dpdk (bound to uio_pci_generic, tried igb_uio also!) on a virtio interface. Dpdk exits with the "Cannot mmap IO port resource" complaint - the call chain is legacy_virtio_resource_init()-->pci_uio_ioport_map(). If anyone can give any clues/pointers as to what might be wrong, tha