[dpdk-dev] [PATCH v2 0/4] fix the issue that DPDK takes over virtio device blindly
On Tue, Jan 12, 2016 at 10:46 AM, Xie, Huawei wrote: > On 1/12/2016 12:24 PM, Santosh Shukla wrote: >> On Tue, Jan 12, 2016 at 8:32 AM, Xie, Huawei wrote: >>> On 1/5/2016 1:25 AM, Stephen Hemminger wrote: On Mon, 4 Jan 2016 01:56:09 +0800 Huawei Xie wrote: > v2 changes: > Remove unnecessary assignment of NULL to dev->data->mac_addrs > Ajust one comment's position > change LOG level from ERR to INFO > > virtio PMD doesn't set RTE_PCI_DRV_NEED_MAPPING in drv_flags of its > eth_driver. It will try igb_uio and PORT IO in turn to configure > virtio device. Even user in guest VM doesn't want to use virtio for > DPDK, virtio PMD will take over the device blindly. > > The more serious problem is kernel driver is still manipulating the > device, which causes driver conflict. > > This patch checks if there is any kernel driver manipulating the > virtio device before virtio PMD uses port IO to configure the device. > > Huawei Xie (4): > eal: make the comment more accurate > eal: set kdrv to RTE_KDRV_NONE if kernel driver isn't manipulating the > device. > virtio: return 1 to tell the kernel we don't take over this device > virtio: check if any kernel driver is manipulating the virtio device > > drivers/net/virtio/virtio_ethdev.c | 16 ++-- > lib/librte_eal/common/eal_common_pci.c | 8 > lib/librte_eal/linuxapp/eal/eal_pci.c | 2 +- > 3 files changed, 19 insertions(+), 7 deletions(-) > Overall looks good, thanks for addressing this. It would be good to note that VFIO no-IOMMU mode should work for this as well. >>> It isn't implemented yet in virtio PMD. I could add a note in the commit >>> message. Do you plan to implement this? >>> >> I can send vfio-noiommu patches for this one, as I am looking at >> vfio-noiommu for virtio for my arm v4 patch series. Stephen, let me >> know if you already started working on this? >> >> Also for some reason I can't find [3/4] patch, could you point me to >> patch link? Thanks. > Thanks. Here is the patch: http://www.dpdk.org/dev/patchwork/patch/9720/ > Thanks, I am rebasing my v4 series on top of this patch, although I couldn't see current series creating issue for vfio-noiommu case. We'll post feedback in v4 cover-letter.
[dpdk-dev] [PATCH v2 0/4] fix the issue that DPDK takes over virtio device blindly
On Tue, Jan 12, 2016 at 8:32 AM, Xie, Huawei wrote: > > On 1/5/2016 1:25 AM, Stephen Hemminger wrote: > > On Mon, 4 Jan 2016 01:56:09 +0800 > > Huawei Xie wrote: > > > >> v2 changes: > >> Remove unnecessary assignment of NULL to dev->data->mac_addrs > >> Ajust one comment's position > >> change LOG level from ERR to INFO > >> > >> virtio PMD doesn't set RTE_PCI_DRV_NEED_MAPPING in drv_flags of its > >> eth_driver. It will try igb_uio and PORT IO in turn to configure > >> virtio device. Even user in guest VM doesn't want to use virtio for > >> DPDK, virtio PMD will take over the device blindly. > >> > >> The more serious problem is kernel driver is still manipulating the > >> device, which causes driver conflict. > >> > >> This patch checks if there is any kernel driver manipulating the > >> virtio device before virtio PMD uses port IO to configure the device. > >> > >> Huawei Xie (4): > >> eal: make the comment more accurate > >> eal: set kdrv to RTE_KDRV_NONE if kernel driver isn't manipulating the > >> device. > >> virtio: return 1 to tell the kernel we don't take over this device > >> virtio: check if any kernel driver is manipulating the virtio device > >> > >> drivers/net/virtio/virtio_ethdev.c | 16 ++-- > >> lib/librte_eal/common/eal_common_pci.c | 8 > >> lib/librte_eal/linuxapp/eal/eal_pci.c | 2 +- > >> 3 files changed, 19 insertions(+), 7 deletions(-) > >> > > Overall looks good, thanks for addressing this. > > > > It would be good to note that VFIO no-IOMMU mode should work for this > > as well. > > It isn't implemented yet in virtio PMD. I could add a note in the commit > message. Do you plan to implement this? > I can send vfio-noiommu patches for this one, as I am looking at vfio-noiommu for virtio for my arm v4 patch series. Stephen, let me know if you already started working on this? Also for some reason I can't find [3/4] patch, could you point me to patch link? Thanks. > > > >
[dpdk-dev] [PATCH v2 0/4] fix the issue that DPDK takes over virtio device blindly
On 1/12/2016 12:24 PM, Santosh Shukla wrote: > On Tue, Jan 12, 2016 at 8:32 AM, Xie, Huawei wrote: >> On 1/5/2016 1:25 AM, Stephen Hemminger wrote: >>> On Mon, 4 Jan 2016 01:56:09 +0800 >>> Huawei Xie wrote: >>> v2 changes: Remove unnecessary assignment of NULL to dev->data->mac_addrs Ajust one comment's position change LOG level from ERR to INFO virtio PMD doesn't set RTE_PCI_DRV_NEED_MAPPING in drv_flags of its eth_driver. It will try igb_uio and PORT IO in turn to configure virtio device. Even user in guest VM doesn't want to use virtio for DPDK, virtio PMD will take over the device blindly. The more serious problem is kernel driver is still manipulating the device, which causes driver conflict. This patch checks if there is any kernel driver manipulating the virtio device before virtio PMD uses port IO to configure the device. Huawei Xie (4): eal: make the comment more accurate eal: set kdrv to RTE_KDRV_NONE if kernel driver isn't manipulating the device. virtio: return 1 to tell the kernel we don't take over this device virtio: check if any kernel driver is manipulating the virtio device drivers/net/virtio/virtio_ethdev.c | 16 ++-- lib/librte_eal/common/eal_common_pci.c | 8 lib/librte_eal/linuxapp/eal/eal_pci.c | 2 +- 3 files changed, 19 insertions(+), 7 deletions(-) >>> Overall looks good, thanks for addressing this. >>> >>> It would be good to note that VFIO no-IOMMU mode should work for this >>> as well. >> It isn't implemented yet in virtio PMD. I could add a note in the commit >> message. Do you plan to implement this? >> > I can send vfio-noiommu patches for this one, as I am looking at > vfio-noiommu for virtio for my arm v4 patch series. Stephen, let me > know if you already started working on this? > > Also for some reason I can't find [3/4] patch, could you point me to > patch link? Thanks. Thanks. Here is the patch: http://www.dpdk.org/dev/patchwork/patch/9720/
[dpdk-dev] [PATCH v2 0/4] fix the issue that DPDK takes over virtio device blindly
On 1/5/2016 1:25 AM, Stephen Hemminger wrote: > On Mon, 4 Jan 2016 01:56:09 +0800 > Huawei Xie wrote: > >> v2 changes: >> Remove unnecessary assignment of NULL to dev->data->mac_addrs >> Ajust one comment's position >> change LOG level from ERR to INFO >> >> virtio PMD doesn't set RTE_PCI_DRV_NEED_MAPPING in drv_flags of its >> eth_driver. It will try igb_uio and PORT IO in turn to configure >> virtio device. Even user in guest VM doesn't want to use virtio for >> DPDK, virtio PMD will take over the device blindly. >> >> The more serious problem is kernel driver is still manipulating the >> device, which causes driver conflict. >> >> This patch checks if there is any kernel driver manipulating the >> virtio device before virtio PMD uses port IO to configure the device. >> >> Huawei Xie (4): >> eal: make the comment more accurate >> eal: set kdrv to RTE_KDRV_NONE if kernel driver isn't manipulating the >> device. >> virtio: return 1 to tell the kernel we don't take over this device >> virtio: check if any kernel driver is manipulating the virtio device >> >> drivers/net/virtio/virtio_ethdev.c | 16 ++-- >> lib/librte_eal/common/eal_common_pci.c | 8 >> lib/librte_eal/linuxapp/eal/eal_pci.c | 2 +- >> 3 files changed, 19 insertions(+), 7 deletions(-) >> > Overall looks good, thanks for addressing this. > > It would be good to note that VFIO no-IOMMU mode should work for this > as well. It isn't implemented yet in virtio PMD. I could add a note in the commit message. Do you plan to implement this? >
[dpdk-dev] [PATCH v2 0/4] fix the issue that DPDK takes over virtio device blindly
On Mon, 4 Jan 2016 01:56:09 +0800 Huawei Xie wrote: > v2 changes: > Remove unnecessary assignment of NULL to dev->data->mac_addrs > Ajust one comment's position > change LOG level from ERR to INFO > > virtio PMD doesn't set RTE_PCI_DRV_NEED_MAPPING in drv_flags of its > eth_driver. It will try igb_uio and PORT IO in turn to configure > virtio device. Even user in guest VM doesn't want to use virtio for > DPDK, virtio PMD will take over the device blindly. > > The more serious problem is kernel driver is still manipulating the > device, which causes driver conflict. > > This patch checks if there is any kernel driver manipulating the > virtio device before virtio PMD uses port IO to configure the device. > > Huawei Xie (4): > eal: make the comment more accurate > eal: set kdrv to RTE_KDRV_NONE if kernel driver isn't manipulating the > device. > virtio: return 1 to tell the kernel we don't take over this device > virtio: check if any kernel driver is manipulating the virtio device > > drivers/net/virtio/virtio_ethdev.c | 16 ++-- > lib/librte_eal/common/eal_common_pci.c | 8 > lib/librte_eal/linuxapp/eal/eal_pci.c | 2 +- > 3 files changed, 19 insertions(+), 7 deletions(-) > Overall looks good, thanks for addressing this. It would be good to note that VFIO no-IOMMU mode should work for this as well.
[dpdk-dev] [PATCH v2 0/4] fix the issue that DPDK takes over virtio device blindly
v2 changes: Remove unnecessary assignment of NULL to dev->data->mac_addrs Ajust one comment's position change LOG level from ERR to INFO virtio PMD doesn't set RTE_PCI_DRV_NEED_MAPPING in drv_flags of its eth_driver. It will try igb_uio and PORT IO in turn to configure virtio device. Even user in guest VM doesn't want to use virtio for DPDK, virtio PMD will take over the device blindly. The more serious problem is kernel driver is still manipulating the device, which causes driver conflict. This patch checks if there is any kernel driver manipulating the virtio device before virtio PMD uses port IO to configure the device. Huawei Xie (4): eal: make the comment more accurate eal: set kdrv to RTE_KDRV_NONE if kernel driver isn't manipulating the device. virtio: return 1 to tell the kernel we don't take over this device virtio: check if any kernel driver is manipulating the virtio device drivers/net/virtio/virtio_ethdev.c | 16 ++-- lib/librte_eal/common/eal_common_pci.c | 8 lib/librte_eal/linuxapp/eal/eal_pci.c | 2 +- 3 files changed, 19 insertions(+), 7 deletions(-) -- 1.8.1.4