Signed-off-by: Huawei Xie
---
config/common_linuxapp |7 +
lib/Makefile |1 +
lib/librte_vhost/Makefile| 48 ++
lib/librte_vhost/eventfd_link/Makefile | 39 +
lib/librte_vhost/eventfd_link/eventfd_link.c
This user space vhost library is based off user space vhost example and aims to
provide same API for different vhost implementations. This implementation
includes user space vhost cuse driver, kernel module for eventfd proxy and
vhost enqueue/dequeue functionalities.
Huawei Xie (1):
vhost
On Sat, Jul 19, 2014 at 12:08:35AM +, Harish Patil wrote:
> Hello dpdk-dev,
> Went thru? couple of documentation but not very clear to me. Does using
> KNI means handing over all the packets received/transmitted by the poll
> mode driver to the linux stack or can it be controlled for the
Hi Stephen,
I have other (inlined) comments on this patch.
> udev->info.version = "0.1";
> udev->info.handler = igbuio_pci_irqhandler;
> udev->info.irqcontrol = igbuio_pci_irqcontrol;
> + udev->info.irq = dev->irq;
[...]
> + /* fall back to MSI */
> case
Hi Stephen,
I cannot merge this part because some lines were removed from the context.
I think I just have to add them but I would like confirmation.
See below.
> @@ -512,36 +499,36 @@
> #endif
> udev->info.priv = udev;
> udev->pdev = dev;
> - udev->mode = 0; /* set the default
Signed-off-by: Huawei Xie
---
config/common_linuxapp | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/config/common_linuxapp b/config/common_linuxapp
index 002ed84..5b58278 100644
--- a/config/common_linuxapp
+++ b/config/common_linuxapp
@@ -391,8 +391,9 @@
Signed-off-by: Huawei Xie
Acked-by: Konstantin Ananyev
Acked-by: Thomos Long
---
config/common_linuxapp |6 +
lib/Makefile |1 +
lib/librte_vhost/Makefile| 48 ++
lib/librte_vhost/eventfd_link/Makefile |
This user space vhost library is based off user space vhost example and aims to
provide same API for different vhost implementations. This implementation
includes user space vhost cuse driver, kernel module for eventfd proxy and
vhost enqueue/dequeue functionalities.
hxie5 (2):
vhost library
> All,
>
> If this was fixed in 1.7 and I missed it I apologize (but it looks from
> source to
> still be broken). I am using DPDK 1.6.0r2 (will be upgrading to
> 1.7.0 soon) on RHEL 6.4. I've converted the functions below to 1.7.0
> names/locations since it looks to still be an issue there.
>
Hi Stephen,
2014-06-06 16:50, Stephen Hemminger:
> Since only one MSI-X entry is ever defined, there is no need to
> put it as an array in the driver private data structure. One msix_entry
> can just be put on the stack and initialized there.
When merging this patch, I realized it's not
improvements for some macro definition about RSS packet
classification types in rte_ethdev.h.
Signed-off-by: Helin Zhang
Acked-by: Cunming Liang
Acked-by: Jijiang Liu
---
lib/librte_ether/rte_ethdev.h | 47 ++-
1 file changed, 24 insertions(+), 23
i40e can support RSS no matter if SR-IOV is enabled or not, while
ixgbe/igb can not support RSS if it is SR-IOV. Code changes are
needed to support i40e RSS if SR-IOV is enabled.
Signed-off-by: Helin Zhang
Acked-by: Jijiang Liu
Acked-by: Cunming Liang
---
app/test-pmd/testpmd.c | 13
Add VF RSS support in Poll Mode Driver, as it is supported by hardware.
Signed-off-by: Helin Zhang
Acked-by: Cunming Liang
Acked-by: Jijiang Liu
---
lib/librte_pmd_i40e/i40e_ethdev.c| 4 +-
lib/librte_pmd_i40e/i40e_ethdev.h| 40 ++-
lib/librte_pmd_i40e/i40e_ethdev_vf.c | 208
As RSS in i40e VF is supported by hardware, these patches enable
it in i40e PMD, and also enable its testing in testpmd.
Helin Zhang (3):
i40evf: add RSS support in VF
app/testpmd: enable RSS support for i40e
ethdev: improvements for some macro definition in head file
Merged two patches in previous patch set into 1.
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Huawei Xie
> Sent: Friday, July 18, 2014 5:56 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH v2] user space vhost driver library
>
> This user space
All,
I've been playing with DPDK recently on a variety of bare metal Linux
installations and so far and have seen wonderful improvements in
performance on both our Westmere and Sandy Bridge based servers.
However when I install ESXi 5.1 (not linked to a vSphere management system
-- stand alone
All,
If this was fixed in 1.7 and I missed it I apologize (but it looks from
source to still be broken). I am using DPDK 1.6.0r2 (will be upgrading to
1.7.0 soon) on RHEL 6.4. I've converted the functions below to 1.7.0
names/locations since it looks to still be an issue there.
tl;dr -- to get
Fix whitespace and other problems reported by checkpatch.
This didi find a real bug in that the setup code was returning
positive value for errors which goes against convention and might have
caused a problem.
Signed-off-by: Stephen Hemminger
--- a/lib/librte_eal/linuxapp/igb_uio/igb_uio.c
Allows msi to be selected as a preferred mode.
Signed-off-by: Stephen Hemminger
--- a/lib/librte_eal/linuxapp/igb_uio/igb_uio.c 2014-07-18 08:47:24.713604900
-0700
+++ b/lib/librte_eal/linuxapp/igb_uio/igb_uio.c 2014-07-18 08:47:24.709604886
-0700
@@ -646,7 +646,7 @@ fail_release_iomem:
Since only one MSI-X entry is ever defined, there is no need to
put it as an array in the driver private data structure. One msix_entry
can just be put on the stack and initialized there.
Also remove the unused backport defines related to MSI-X.
I suspect this code was just inherited from some
It is better style to just use the pci_num_vf directly, rather
than wrapping it with a local (but globally named) function with
the same effect.
Signed-off-by: Stephen Hemminger
--- a/lib/librte_eal/linuxapp/igb_uio/igb_uio.c 2014-06-19 14:29:57.587687790
-0700
+++
Don't put capitialization and space in name since it will show
up in /proc/interrupts. Instead use driver name to follow the
conventions used in the kernel by other drivers.
Signed-off-by: Stephen Hemminger
--- a/lib/librte_eal/linuxapp/igb_uio/igb_uio.c 2014-06-19 14:29:53.775667934
-0700
Use Linux kernel standard coding conventions for console messages.
Bare use of printk() is not desirable and is reported as a style
problem by checkpatch. Instead use pr_info() and dev_info()
to print out log messages where appropriate.
Signed-off-by: Stephen Hemminger
---
Update patches so all are now bisectable, and incorporate comments.
Also fix the checkpatch warnings that are fixable.
*virtio_net_hdr_mem* member within *virtqueue* structure stores a
physical address and is defined as void ptr. When 32bit pmd is used
with 64bit kernel this leads to truncation of 64bit physical address
and pkt i/o does not work.
Changed *virtio_net_hdr_mem* to *phys_addr_t* type and
removed the
25 matches
Mail list logo