kernel.git/drivers/net/hyperv/netvsc.c, branch linux-3.17.y

hyperv: Fix a bug in netvsc_send()

2014-10-15T10:29:23Z

[ Upstream commit 3a67c9ccad926a168d8b7891537a452018368a5b ] After the packet is successfully sent, we should not touch the packet as it may have been freed. This patch is based on the work done by Long Li . David, please queue this up for stable. Signed-off-by: K. Y. Srinivasan Reported-by: Sitsofe Wheeler Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman

Drivers: net-next: hyperv: Increase the size of the sendbuf region

2014-08-04T22:07:14Z

Intel did some benchmarking on our network throughput when Linux on Hyper-V is as used as a gateway. This fix gave us almost a 1 Gbps additional throughput on about 5Gbps base throughput we hadi, prior to increasing the sendbuf size. The sendbuf mechanism is a copy based transport that we have which is clearly more optimal than the copy-free page flipping mechanism (for small packets). In the forwarding scenario, we deal only with MTU sized packets, and increasing the size of the senbuf area gave us the additional performance. For what it is worth, Windows guests on Hyper-V, I am told use similar sendbuf size as well. The exact value of sendbuf I think is less important than the fact that it needs to be larger than what Linux can allocate as physically contiguous memory. Thus the change over to allocating via vmalloc(). We currently allocate 16MB receive buffer and we use vmalloc there for allocation. Also the low level channel code has already been modified to deal with physically dis-contiguous memory in the ringbuffer setup. Based on experimentation Intel did, they say there was some improvement in throughput as the sendbuf size was increased up to 16MB and there was no effect on throughput beyond 16MB. Thus I have chosen 16MB here. Increasing the sendbuf value makes a material difference in small packet handling In this version of the patch, based on David's feedback, I have added additional details in the commit log. Signed-off-by: K. Y. Srinivasan Signed-off-by: David S. Miller

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

2014-07-30T20:25:49Z

Signed-off-by: David S. Miller

hyperv: Fix error return code in netvsc_init_buf()

2014-07-23T21:55:47Z

Fix to return -ENOMEM from the kalloc error handling case instead of 0. Signed-off-by: Wei Yongjun Reviewed-by: Haiyang Zhang Signed-off-by: David S. Miller

drivers/net/hyperv/netvsc.c: remove unnecessary null test before kfree

2014-07-03T01:22:25Z

Fix checkpatch warning: WARNING: kfree(NULL) is safe this check is probably not required Cc: Haiyang Zhang Cc: netdev@vger.kernel.org Signed-off-by: Fabian Frederick Signed-off-by: David S. Miller

hyperv: fix apparent cut-n-paste error in send path teardown

2014-06-17T04:36:13Z

c25aaf814a63: "hyperv: Enable sendbuf mechanism on the send path" added some teardown code that looks like it was copied from the recieve path above, but missed a variable name replacement. Signed-off-by: Dave Jones Signed-off-by: David S. Miller

hyperv: Enable sendbuf mechanism on the send path

2014-04-30T17:48:46Z

We send packets using a copy-free mechanism (this is the Guest to Host transport via VMBUS). While this is obviously optimal for large packets, it may not be optimal for small packets. Hyper-V host supports a second mechanism for sending packets that is "copy based". We implement that mechanism in this patch. In this version of the patch I have addressed a comment from David Miller. With this patch (and all of the other offload and VRSS patches), we are now able to almost saturate a 10G interface between Linux VMs on Hyper-V on different hosts - close to 9 Gbps as measured via iperf. Signed-off-by: K. Y. Srinivasan Reviewed-by: Haiyang Zhang Signed-off-by: David S. Miller

hyperv: Simplify the send_completion variables

2014-04-23T18:48:39Z

The union contains only one member now, so we use the variables in it directly. Signed-off-by: Haiyang Zhang Reviewed-by: K. Y. Srinivasan Signed-off-by: David S. Miller

hyperv: Remove recv_pkt_list and lock

2014-04-23T18:48:39Z

Removed recv_pkt_list and lock, and updated related code, so that the locking overhead is reduced especially when multiple channels are in use. The recv_pkt_list isn't actually necessary because the packets are processed sequentially in each channel. It has been replaced by a local variable, and the related lock for this list is also removed. The is_data_pkt field is not used in receive path, so its assignment is cleaned up. Signed-off-by: Haiyang Zhang Reviewed-by: K. Y. Srinivasan Signed-off-by: David S. Miller

hyperv: Add support for virtual Receive Side Scaling (vRSS)

2014-04-21T17:32:29Z

This feature allows multiple channels to be used by each virtual NIC. It is available on Hyper-V host 2012 R2. Signed-off-by: Haiyang Zhang Reviewed-by: K. Y. Srinivasan Signed-off-by: David S. Miller