From: Tom Herbert
Date: Thu, 14 Jan 2016 13:44:24 -0800
> The fact that we can negatively affect the output of Toeplitz so
> predictably is actually a liability and not a benefit. This sort of
> thing can be the basis of a DOS attack and is why we kicked out XOR
> hash in favor of Jenkins.
+1
T
From: Haiyang Zhang
Date: Wed, 13 Jan 2016 23:10:57 +
> I have done a comparison of the Toeplitz v.s. Jenkins Hash algorithms,
> and found that the Toeplitz provides much better distribution of the
> connections into send-indirection-table entries.
This fails to take into consideration how
From: Vitaly Kuznetsov
Date: Thu, 7 Jan 2016 10:33:09 +0100
> Recent changes to 'struct flow_keys' (e.g commit d34af823ff40 ("net: Add
> VLAN ID to flow_keys")) introduced a performance regression in netvsc
> driver. Is problem is, however, not the above mentioned commit but the
> fact that net
From: Dexuan Cui
Date: Thu, 24 Dec 2015 06:14:36 -0800
> +#define HV_RINGBUFFER_READ_FLAG_RAW (1 << 0)
> +#define HV_RINGBUFFER_READ_FLAG_HVSOCK (1 << 1)
Please use BIT().
___
devel mailing list
de...@linuxdriverproject.org
http:
From: Haiyang Zhang
Date: Wed, 16 Dec 2015 19:20:44 +
> In our test, we have bisected and found the following patch introduced big
> overhead into skb_flow_dissect_flow_keys(), and caused performance
> regression:
> commit: d34af823
> net: Add VLAN ID to flow_keys
NEVER _EVER_ work around
From: Haiyang Zhang
Date: Thu, 10 Dec 2015 12:19:35 -0800
> In commit 2a04ae8acb14 ("hv_netvsc: remove locking in netvsc_send()"), the
> locking for MSD (Multi-Send Data) field was removed. This could cause a
> race condition between RNDIS control messages and data packets processing,
> because t
From: "K. Y. Srinivasan"
Date: Tue, 1 Dec 2015 16:42:58 -0800
> In an attempt to avoid having to allocate memory on the send path, the netvsc
> driver was requesting additional head room so that both rndis header and the
> netvsc packet (the state that had to persist) could be placed in the skb.
From: "K. Y. Srinivasan"
Date: Sat, 28 Nov 2015 12:20:36 -0800
> +#elseif defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25)
The correct CPP directive is "#elif".
___
devel mailing list
de...@linuxdriverproject.org
http://driverdev.linuxdriverproject.org/
From: Vitaly Kuznetsov
Date: Fri, 27 Nov 2015 11:39:55 +0100
> There are several issues in hv_netvsc driver with regards to link status
> change handling:
> - RNDIS_STATUS_NETWORK_CHANGE results in calling userspace helper doing
> '/etc/init.d/network restart' and this is inappropriate and brok
From: Dexuan Cui
Date: Mon, 9 Nov 2015 03:11:35 +
>> -Original Message-
>> From: David Miller [mailto:da...@davemloft.net]
>> Sent: Monday, November 9, 2015 10:53
>> To: Dexuan Cui
>> Cc: eric.duma...@gmail.com; d...@cumulusnetworks.com; Simon Xi
From: Dexuan Cui
Date: Mon, 9 Nov 2015 02:39:24 +
>> Throughput on a single TCP flow for a 40G NIC can be tricky to tune.
> Why is a single TCP flow trickier than multiple TCP flows?
> IMO it should be easier to analyze the issue of a single TCP flow?
Because a single TCP flow can only use o
From: Dexuan Cui
Date: Tue, 28 Jul 2015 05:35:30 -0700
> In the SMP guest case, when the per-channel callback hvsock_events() is
> running on virtual CPU A, if the guest tries to close the connection on
> virtual CPU B: we invoke vmbus_close() -> vmbus_close_internal(),
> then we can have trouble
From: Dexuan Cui
Date: Tue, 28 Jul 2015 05:35:23 -0700
> +/* hvsock_release() can be invoked in 2 paths:
> + * 1. on process termination:
> + * hvsock_sk_destruct+0x1a/0x20
> + * __sk_free+0x1d/0x130
> + * sk_free+0x19/0x20
> + * hvsock_release+0x138/0x160
> + * sock_release+0x1f/0x90
>
From: Dexuan Cui
Date: Tue, 28 Jul 2015 05:35:11 -0700
> With the 2 APIs supplied by the VMBus driver, the coming net/hvsock driver
> can register 2 callbacks and can know when a new hvsock connection is
> offered by the host, and when a hvsock connection is being closed by the
> host.
>
> Signe
From: Haiyang Zhang
Date: Fri, 24 Jul 2015 10:08:40 -0700
> This patch adds data structures and handlers for messages related
> to SRIOV Virtual Function.
>
> Signed-off-by: Haiyang Zhang
> Reviewed-by: K. Y. Srinivasan
Applied.
___
devel mailing li
From: "K. Y. Srinivasan"
Date: Wed, 22 Jul 2015 11:42:32 -0700
> The current code returns from probe without waiting for the proper handling
> of subchannels that may be requested. If the netvsc driver were to be rapidly
> loaded/unloaded, we can trigger a panic as the unload will be tearing
> d
From: Dexuan Cui
Date: Tue, 14 Jul 2015 03:00:48 -0700
> + pr_debug("hvsock_sk_destruct: called\n");
Debug logging just to state that a function is called is not appropriate,
we have very sophisticated tracing facilities in the kernel that can do
that transparently, and more.
PLease remove
From: Dexuan Cui
Date: Tue, 14 Jul 2015 02:58:56 -0700
> +int vmbus_sendpacket_hvsock(struct vmbus_channel *channel, void *buf, u32
> len)
> +{
> + struct vmpacket_descriptor desc;
> + struct vmpipe_proto_header pipe_hdr;
> + u32 packetlen;
> + u32 packetlen_aligned;
> + stru
From: Dexuan Cui
Date: Tue, 14 Jul 2015 02:58:03 -0700
> A helper function is also added.
>
> Signed-off-by: Dexuan Cui
> ---
> include/linux/hyperv.h | 7 +++
> 1 file changed, 7 insertions(+)
>
> diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
> index 30d3a1f..aa21814 10064
From: Haiyang Zhang
Date: Mon, 13 Jul 2015 13:09:16 -0700
> The current change mtu call only stops tx before removing RNDIS filter.
> In case ringbufer is not empty, the rndis_filter_device_remove() may
> hang on removing the buffers.
>
> This patch adds close of RNDIS filter before removing it,
From: Haiyang Zhang
Date: Mon, 6 Jul 2015 14:11:37 -0700
> When packet encapsulation is in use, the MTU needs to be reduced for
> headroom reservation.
> The existing code takes the updated MTU value only from the host side.
> But vSwitch extensions, such as Open vSwitch, require the flexibility
From: Dan Carpenter
Date: Fri, 3 Jul 2015 14:28:47 +0300
> On Thu, Jul 02, 2015 at 01:17:35PM -0700, Haiyang Zhang wrote:
>> When packet encapsulation is in use, the MTU needs to be reduced for
>> headroom reservation.
>> The existing code takes the updated MTU value only from the host side.
>> B
icitly included
> and that tends to hide places where vmalloc() et al are added to files
> but the include of vmalloc.h is forgotten.
>
...
> Suggested-by: David Miller
> Signed-off-by: Stephen Rothwell
With the follow-on allnoconfig fixes:
Acked-by: David S. Miller
From: "K. Y. Srinivasan"
Date: Thu, 28 May 2015 17:07:44 -0700
> Allocate both receive buffer and send buffer from the NUMA node assigned to
> the
> primary channel.
Series applied, thanks.
___
devel mailing list
de...@linuxdriverproject.org
http://dr
From: "K. Y. Srinivasan"
Date: Wed, 27 May 2015 13:16:57 -0700
> The current algorithm for deciding on the number of VRSS channels is
> not optimal since we open up the min of number of CPUs online and the
> number of VRSS channels the host is offering. So on a 32 VCPU guest
> we could potentiall
From: "K. Y. Srinivasan"
Date: Tue, 26 May 2015 16:21:09 -0700
> The current algorithm for deciding on the number of VRSS channels is
> not optimal since we open up the min of number of CPUs online and the
> number of VRSS channels the host is offering. So on a 32 VCPU guest
> we could potentiall
From: Simon Xiao
Date: Fri, 15 May 2015 02:33:03 -0700
> Currently the struct netvsc_stats has a member s_sync
> of type u64_stats_sync.
> This definition will break kernel build as the macro
> netdev_alloc_pcpu_stats requires this member name to be syncp.
> (see netdev_alloc_pcpu_stats definitio
From: Simon Xiao
Date: Thu, 14 May 2015 01:00:25 -0700
> Current code does not lock anything when calculating the TX and RX stats.
> As a result, the RX and TX data reported by ifconfig are not accuracy in a
> system with high network throughput and multiple CPUs (in my test,
> RX/TX = 83% betwee
From: six...@microsoft.com
Date: Tue, 12 May 2015 15:50:02 -0700
> From: Simon Xiao
>
> Current code does not lock anything when calculating the TX and RX stats.
> As a result, the RX and TX data reported by ifconfig are not accuracy in a
> system with high network throughput and multiple CPUs (
From: "K. Y. Srinivasan"
Date: Mon, 11 May 2015 15:39:46 -0700
> Based on the information given to this driver (via the xmit_more skb flag),
> we can defer signaling the host if more packets are on the way. This will help
> make the host more efficient since it can potentially process a larger ba
From: KY Srinivasan
Date: Mon, 11 May 2015 08:59:53 +
>
>
>> -Original Message-
>> From: Joe Perches [mailto:j...@perches.com]
>> Sent: Sunday, May 10, 2015 10:58 PM
>> To: KY Srinivasan
>> Cc: da...@davemloft.net; net...@vger.kernel.org; linux-
>> ker...@vger.kernel.org; de...@linu
From: "K. Y. Srinivasan"
Date: Wed, 6 May 2015 15:29:05 -0700
> - ret = vmbus_sendpacket_pagebuffer(out_channel,
> - pgbuf,
> - packet->page_buf_cnt,
> -
From: Jerry Snitselaar
Date: Mon, 4 May 2015 10:57:16 -0700
> With commit b56fc3c53654 ("hv_netvsc: Fix a bug in netvsc_start_xmit()"),
> skb variable is no longer used in netvsc_send. Remove variable and dead
> code that depended on it.
>
> Cc: Haiyang Zhang
> Cc: K. Y. Srinivasan
> Signed-o
From: "K. Y. Srinivasan"
Date: Wed, 29 Apr 2015 15:33:42 -0700
> @@ -772,19 +773,21 @@ static inline int netvsc_send_pkt(
> if (packet->page_buf_cnt) {
> pgbuf = packet->cp_partial ? packet->page_buf +
> packet->rmsg_pgcnt : packet->page_buf;
> -
From: "K. Y. Srinivasan"
Date: Tue, 28 Apr 2015 17:59:48 -0700
> Commit b08cc79155fc26d0d112b1470d1ece5034651a4b eliminated memory
> allocation in the packet send path:
>
> "hv_netvsc: Eliminate memory allocation in the packet send path
>
> The network protocol used to communicate with
From: six...@microsoft.com
Date: Tue, 28 Apr 2015 01:05:17 -0700
> From: Simon Xiao
>
> 1. Introduce netif-msg to netvsc to control debug logging output
> and keep msg_enable in netvsc_device_context so that it is
> kept persistently.
> 2. Only call dump_rndis_message() when NETIF_MSG_RX_ERR or
From: "K. Y. Srinivasan"
Date: Mon, 27 Apr 2015 18:14:50 -0700
> Commit commit b08cc79155fc26d0d112b1470d1ece5034651a4b eliminated memory
> allocation in the packet send path. This commit introduced a bug since it
> did not account for the case if the skb was cloned. Fix this bug by
> using the p
From: six...@microsoft.com
Date: Fri, 24 Apr 2015 11:34:48 -0700
> + net_device_ctx->msg_enable = netif_msg_init(debug, default_msg);
> + if (netif_msg_probe(net_device_ctx))
> + netdev_dbg(net, "netvsc msg_enable: %d",
> +net_device_ctx->msg_enable);
>
From: Simon Xiao
Date: Tue, 21 Apr 2015 22:14:14 +
> In current netvsc driver, for each packet received, it will call
> dump_rndis_message() to try to dump the rndis packet information by
> netdev_dbg(). In non-debug mode, dump_rndis_message() will not dump
> anything but it still initialize
From: six...@microsoft.com
Date: Tue, 21 Apr 2015 15:58:05 -0700
> From: Simon Xiao
>
> Signed-off-by: Simon Xiao
> Reviewed-by: K. Y. Srinivasan
> Reviewed-by: Haiyang Zhang
I just gave you feedback on this patch in response to your
original submission, do not ignore it.
___
From: Haiyang Zhang
Date: Mon, 13 Apr 2015 16:34:35 -0700
> If remaining space in a send buffer slot is too small for the whole message,
> we only copy the RNDIS header and PPI data into send buffer, so we can batch
> one more packet each time. It reduces the vmbus per-message overhead.
>
> Sign
From: Vitaly Kuznetsov
Date: Wed, 8 Apr 2015 17:54:04 +0200
> This patch series fixes the same issue which was fixed in Xen with commit
> 97a6d1bb2b658ac85ed88205ccd1ab809899884d ("xen-netfront: Fix handling packets
> on
> compound pages with skb_linearize").
This patch series only applies on
From: Haiyang Zhang
Date: Mon, 6 Apr 2015 15:22:54 -0700
> In the two places changed, we now use netvsc_xmit_completion() which properly
> frees hv_netvsc_packet in or not in skb headroom.
>
> Signed-off-by: Haiyang Zhang
> Reviewed-by: K. Y. Srinivasan
Applied.
_
From: Haiyang Zhang
Date: Mon, 6 Apr 2015 15:22:53 -0700
> The sum of RNDIS msg and PPI struct sizes is used in multiple places, so we
> define
> a macro for them.
>
> Signed-off-by: Haiyang Zhang
> Reviewed-by: K. Y. Srinivasan
Applied.
___
devel
From: Haiyang Zhang
Date: Mon, 6 Apr 2015 15:22:52 -0700
> Signed-off-by: Haiyang Zhang
> Reviewed-by: K. Y. Srinivasan
Applied.
___
devel mailing list
de...@linuxdriverproject.org
http://driverdev.linuxdriverproject.org/mailman/listinfo/driverdev-d
From: "K. Y. Srinivasan"
Date: Sun, 29 Mar 2015 21:07:58 -0700
> The network protocol used to communicate with the host is the remote ndis
> (rndis)
> protocol. We need to decorate each outgoing packet with a rndis header and
> additional rndis state (rndis per-packet state). To manage this stat
From: Haiyang Zhang
Date: Thu, 26 Mar 2015 16:20:58 -0700
> The vmbus_are_subchannels_present() also involves opening the channels, which
> may be too early at this point. Checking for subchannels is not necessary
> here.
> So this patch removes it. Subchannels will be opened when offer messages
From: Haiyang Zhang
Date: Thu, 26 Mar 2015 09:03:37 -0700
> With this patch, we can send out multiple RNDIS data packets in one send
> buffer
> slot and one VMBus message. It reduces the overhead associated with VMBus
> messages.
>
> Signed-off-by: Haiyang Zhang
> Reviewed-by: K. Y. Srinivasa
From: KY Srinivasan
Date: Tue, 17 Mar 2015 20:07:10 +
> I pulled down the net-next tree and the issue is with the first patch:
> 0001-Drivers-hv-vmbus-Export-the-vmbus_sendpacket_pagebuf.patch
>
> The net-next tree is not current with Greg's tree and this patch is on code
> that
> is in Gre
From: "K. Y. Srinivasan"
Date: Tue, 17 Mar 2015 09:02:25 -0700
> Take into consideration the xmit_more flag in skb to decide if we should
> notify the host as we place packets in VMBUS.
>
> The VMBUS API that would give us this control is already in Greg's tree, in
> this
> patch-set, that API
From: Andrew Schwartzmeyer
Date: Thu, 26 Feb 2015 16:27:14 -0800
> This adds support for reporting the actual and maximum combined channels
> count of the hv_netvsc driver via 'ethtool --show-channels'.
>
> This required adding 'max_chn' to 'struct netvsc_device', and assigning
> it 'rsscap.num_
From: Lad Prabhakar
Date: Thu, 5 Feb 2015 15:06:33 +
> From: "Lad, Prabhakar"
>
> this patch fixes following sparse warnings:
>
> netvsc.c:688:5: warning: symbol 'netvsc_copy_to_send_buf' was not declared.
> Should it be static?
> rndis_filter.c:627:5: warning: symbol 'rndis_filter_set_o
From: Haiyang Zhang
Date: Thu, 29 Jan 2015 12:34:49 -0800
> The existing code frees the skb in EAGAIN case, in which the skb will be
> retried from upper layer and used again.
> Also, the existing code doesn't free send buffer slot in error case, because
> there is no completion message for unsen
From: Nicholas Mc Guire
Date: Sun, 25 Jan 2015 19:08:37 +0100
> As the if completes with a unconditional goto the else branch
> is not needed here.
>
> Signed-off-by: Nicholas Mc Guire
> ---
>
> v2: added missing subsystem string in subject line - patch unchanged
The feedback you were given w
From: Haiyang Zhang
Date: Fri, 19 Dec 2014 18:25:18 -0800
> The changed names are union fields with the same size, so the existing code
> still works. But, we now update these variables to the correct names.
>
> Signed-off-by: Haiyang Zhang
> Reviewed-by: K. Y. Srinivasan
Applied.
___
From: Haiyang Zhang
Date: Mon, 1 Dec 2014 13:28:39 -0800
> This patch adds proper handling of the vNIC hot removal event, which includes
> a rescind-channel-offer message from the host side that triggers vNIC close
> and
> removal. In this case, the notices to the host during close and removal
From: SF Markus Elfring
Date: Tue, 25 Nov 2014 22:55:34 +0100
> From: Markus Elfring
> Date: Tue, 25 Nov 2014 22:33:45 +0100
>
> The vfree() function performs also input parameter validation.
> Thus the test around the call is not needed.
>
> This issue was detected by using the Coccinelle sof
From: SF Markus Elfring
Date: Sun, 23 Nov 2014 08:18:31 +0100
>> Whereas if you learn how to base your changes cleanly on the correct
>> base now, all of your future submissions will go quickly and smoothly
>> into my tree.
>
> My reluctance to work with more Linux repositories will evolve
> ove
From: SF Markus Elfring
Date: Sun, 23 Nov 2014 01:51:24 +0100
>> This has nothing to do with me asking you to frame your patches
>> against the correct tree.
>
> I imagine than someone other can also pick up this update suggestion
> (a simple change of two lines) quicker before I might try anoth
From: SF Markus Elfring
Date: Fri, 21 Nov 2014 23:15:42 +0100
>> This does not apply to the net-next tree, please respin.
>
> Thanks for your reply.
>
> How do you think about to try out the scripts which I published
> in March to get more constructive feedback?
This has nothing to do with me
From: SF Markus Elfring
Date: Thu, 20 Nov 2014 15:25:27 +0100
> From: Markus Elfring
> Date: Thu, 20 Nov 2014 15:15:21 +0100
>
> The vfree() function performs also input parameter validation. Thus the test
> around the call is not needed.
>
> This issue was detected by using the Coccinelle sof
From: Haiyang Zhang
Date: Wed, 12 Nov 2014 14:07:44 -0800
> If the host uses packet encapsulation feature, the MTU may be reduced by the
> host due to headroom reservation for encapsulation. This patch handles this
> new MTU value.
>
> Signed-off-by: Haiyang Zhang
Applied, thanks for adding th
From: Haiyang Zhang
Date: Wed, 12 Nov 2014 20:02:11 +
> The Hyper-V host doesn't support MTU below 1500. If we try setting MTU to a
> value < 1500, the host will use 1500 automatically and return 1500 in the
> RNDIS_OID_GEN_MAXIMUM_FRAME_SIZE query and guest will also use it. That's
> why
From: Haiyang Zhang
Date: Tue, 11 Nov 2014 15:27:52 -0800
> - if (mtu < 68 || mtu > limit)
> + if (mtu < ETH_DATA_LEN || mtu > limit)
> return -EINVAL;
This is not correct.
The test is against the minimally supported MTU, which should
be 68 not ETH_DATA_LEN which is 1500.
From: Haiyang Zhang
Date: Thu, 30 Oct 2014 14:07:17 -0700
> This will allow the workload spreading via vRSS for IPv6.
>
> Signed-off-by: Haiyang Zhang
> Reviewed-by: K. Y. Srinivasan
Applied.
___
devel mailing list
de...@linuxdriverproject.org
http:
From: Haiyang Zhang
Date: Wed, 22 Oct 2014 13:47:18 -0700
> total_data_buflen is used by netvsc_send() to decide if a packet can be put
> into send buffer. It should also include the size of RNDIS message before the
> Ethernet frame. Otherwise, a messge with total size bigger than
> send_section
From: Haiyang Zhang
Date: Thu, 16 Oct 2014 14:47:58 -0700
> In case that the IP header has optional field at the end, this patch will
> get the port numbers after that field, and compute the hash. The general
> parser skb_flow_dissect() is used here.
>
> Signed-off-by: Haiyang Zhang
> Reviewed-
From: Haiyang Zhang
Date: Tue, 14 Oct 2014 20:05:17 +
> In case that the IP header has optional field at the end, this patch will
> get the port numbers after that field, and compute the hash.
>
> Signed-off-by: Haiyang Zhang
> Reviewed-by: K. Y. Srinivasan
This isn't even close to what I
From: Haiyang Zhang
Date: Tue, 14 Oct 2014 15:16:28 -0700
> In case that the IP header has optional field at the end, this patch will
> get the port numbers after that field, and compute the hash.
>
> Signed-off-by: Haiyang Zhang
> Reviewed-by: K. Y. Srinivasan
Instead of adding hack after ha
From: "K. Y. Srinivasan"
Date: Sun, 5 Oct 2014 10:42:51 -0700
> 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. Srinivasa
From: "K. Y. Srinivasan"
Date: Sun, 28 Sep 2014 22:16:43 -0700
> After the packet is successfully sent, we should not touch the skb
> as it may have been freed. This patch is based on the work done by
> Long Li .
>
> In this version of the patch I have fixed issues pointed out by David.
> Davi
From: "K. Y. Srinivasan"
Date: Sun, 28 Sep 2014 19:49:51 -0700
> After the packet is successfully sent, we should not touch the skb as it may
> have been freed. This patch is based on the work done by
> Long Li .
>
> Signed-off-by: K. Y. Srinivasan
> Tested-by: Long Li
> Cc:
You hyperv guys
From: Dan Carpenter
Date: Thu, 4 Sep 2014 14:11:23 +0300
> We try to call free_netvsc_device(net_device) when "net_device" is NULL.
> It leads to an Oops.
>
> Fixes: f90251c8a6d0 ('hyperv: Increase the buffer length for
> netvsc_channel_cb()')
> Signed-off-by: Dan Carpenter
Applied, thanks Da
From: Haiyang Zhang
Date: Fri, 15 Aug 2014 19:18:19 +
> When the buffer is too small for a packet from VMBus, a bigger buffer will be
> allocated in netvsc_channel_cb() and retry reading the packet from VMBus.
> Increasing this buffer size will reduce the retry overhead.
>
> Signed-off-by: H
From: Haiyang Zhang
Date: Tue, 19 Aug 2014 20:53:55 +
> @@ -200,12 +202,18 @@ static bool netvsc_set_hash(u32 *hash, struct sk_buff
> *skb)
> iphdr = ip_hdr(skb);
>
> if (iphdr->version == 4) {
> - if (iphdr->protocol == IPPROTO_TCP)
> + data = (u8 *)&ip
From: Haiyang Zhang
Date: Wed, 13 Aug 2014 18:03:44 +
> When the buffer is too small for a packet from VMBus, a bigger buffer will be
> allocated in netvsc_channel_cb() and retry reading the packet from VMBus.
> Increasing this buffer size will reduce the retry overhead.
>
> Signed-off-by: H
From: "K. Y. Srinivasan"
Date: Wed, 6 Aug 2014 11:11:00 -0700
> WS2008R2 is a supported platform and it turns out that the maximum sendbuf
> size that ws2008R2 can support is only 15MB. Make the necessary
> adjustment.
>
> Signed-off-by: K. Y. Srinivasan
Applied, thanks.
_
From: Haiyang Zhang
Date: Fri, 1 Aug 2014 15:55:30 +
> When the buffer is too small for a packet from VMBus, a bigger buffer will be
> allocated in netvsc_channel_cb() and retry reading the packet from VMBus.
> Increasing this buffer size will reduce the retry overhead.
>
> Signed-off-by: H
From: Haiyang Zhang
Date: Mon, 4 Aug 2014 12:33:45 -0700
> When the buffer is too small for a packet from VMBus, a bigger buffer will be
> allocated in netvsc_channel_cb() and retry reading the packet from VMBus.
> Increasing this buffer size will reduce the retry overhead.
>
> Signed-off-by: H
From: "K. Y. Srinivasan"
Date: Sat, 2 Aug 2014 10:42:02 -0700
> 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 sendb
Don't explain things to me in this thread.
Instead, tell the whole world and everyone who would ever see this
commit, in the commit log message.
___
devel mailing list
de...@linuxdriverproject.org
http://driverdev.linuxdriverproject.org/mailman/listinfo
From: "K. Y. Srinivasan"
Date: Wed, 30 Jul 2014 18:35:49 -0700
> For forwarding scenarios, it will be useful to allocate larger
> sendbuf. Make the necessary adjustments to permit this.
>
> Signed-off-by: K. Y. Srinivasan
This needs more information.
You're increasing the size by 16 times, 1M
From: "K. Y. Srinivasan"
Date: Wed, 30 Jul 2014 18:20:16 -0700
> For forwarding scenarios, it will be useful to allocate larger
> sendbuf. Make the necessary adjustments to permit this.
>
> Signed-off-by: K. Y. Srinivasan
Please submit this with a proper Subject line, something like
"[PATCH 1/
From: weiyj...@163.com
Date: Wed, 23 Jul 2014 09:00:35 +0800
> From: Wei Yongjun
>
> Fix to return -ENOMEM from the kalloc error handling
> case instead of 0.
>
> Signed-off-by: Wei Yongjun
Applied, thank you.
___
devel mailing list
de...@linuxdrive
From: Olaf Hering
Date: Mon, 21 Jul 2014 11:18:51 +0200
> On Mon, Jul 21, Richard Weinberger wrote:
>
>> My concern is that 10 seconds is maybe not a the right choice.
>> (As we cannot know all implementations)
>
> Until someone reports an issue with it, 10 is fine. Just like 20 or 666.
Wrong,
From: Benoit Taine
Date: Fri, 18 Jul 2014 17:26:47 +0200
> We should prefer `const struct pci_device_id` over
> `DEFINE_PCI_DEVICE_TABLE` to meet kernel coding style guidelines.
> This issue was reported by checkpatch.
>
> A simplified version of the semantic patch that makes this change is as
>
From: Richard Weinberger
Date: Wed, 9 Jul 2014 16:23:59 +0200
> In order to have at least a netconsole to debug kernel issues on
> Windows Azure this patch implements netpoll support.
> Sending packets is easy, netvsc_start_xmit() does already everything
> needed.
>
> Signed-off-by: Richard Wei
From: Joe Perches
Date: Mon, 23 Jun 2014 06:41:28 -0700
> Adding the helper reduces object code size as well as overall
> source size line count.
>
> It's also consistent with all the various zalloc mechanisms
> in the kernel.
>
> Done with a simple cocci script and some typing.
For networking
From: Greg KH
Date: Mon, 23 Jun 2014 12:29:11 -0400
> Given that this change will fail on all future distro releases, and
> almost all of the community distros today, I don't see how this is
> acceptable at all. Nor would it be any better if you switch to a
> systemd command line script as well.
From: Haiyang Zhang
Date: Mon, 23 Jun 2014 16:09:59 +
> So, what's the equivalent or similar command to "network restart" on SLES12?
> Could
> you update the command line for the usermodehelper when porting this patch to
> SLES
> 12?
No, you are not going to keep the usermodehelper invocat
From: Olaf Hering
Date: Mon, 23 Jun 2014 15:17:23 +0200
> On Mon, Jun 23, Haiyang Zhang wrote:
>
>> > I think its reasonable to expect guest config changes on this new kind
>> > of host. Would a link-down/link-up event work? I'm sure it will, there
>> > is enough code floating around in the gues
From: Haiyang Zhang
Date: Thu, 19 Jun 2014 18:34:36 -0700
> The RNDIS_STATUS_NETWORK_CHANGE event is received after the Hyper-V host
> sleep or hibernation. We refresh network at this time.
> MS-TFS: 135162
>
> Signed-off-by: Haiyang Zhang
> Reviewed-by: K. Y. Srinivasan
Applied, thanks.
From: Stephen Hemminger
Date: Tue, 3 Jun 2014 08:38:15 -0700
> The uuid structure could be managed as a const in several places.
>
> Signed-off-by: Stephen Hemminger
Applied, thanks.
___
devel mailing list
de...@linuxdriverproject.org
http://driverde
From: Haiyang Zhang
Date: Wed, 21 May 2014 12:55:39 -0700
> It passes the hash value as the RNDIS Per-packet info to the Hyper-V host,
> so that the send completion notices can be spread across multiple channels.
> MS-TFS: 140273
>
> Signed-off-by: Haiyang Zhang
Applied, but please craft your
From: Wilfried Klaebe
Date: Sun, 11 May 2014 00:12:32 +
> net: get rid of SET_ETHTOOL_OPS
>
> Dave Miller mentioned he'd like to see SET_ETHTOOL_OPS gone.
> This does that.
>
> Mostly done via coccinelle script:
> @@
> struct ethtool_ops *ops;
> struct net_device *dev;
> @@
> - SET_ET
From: Haiyang Zhang
Date: Thu, 8 May 2014 15:14:10 -0700
> This change ensures the driver can be built successfully without the
> CONFIG_SYSFS flag.
> MS-TFS: 182270
>
> Signed-off-by: Haiyang Zhang
> Reviewed-by: K. Y. Srinivasan
Applied, thanks.
From: Haiyang Zhang
Date: Thu, 8 May 2014 13:41:33 -0700
> +static inline void netvsc_record_rx_queue(struct sk_buff *skb,
> + struct hv_netvsc_packet *packet,
> + struct net_device *ndev)
> +{
> +#ifdef CONFIG_SYSFS
> +
From: Haiyang Zhang
Date: Fri, 2 May 2014 14:42:06 +
> real_num_rx_queues is defined in "include/linux/netdevice.h":
> It requires CONFIG_SYSFS flag, which is enabled by default, but not set in
> your config file.
>
> Could you use default config and add hyperv drivers, then try again?
You
n this version of the patch I have addressed comments from
> David Miller.
>
> This patch fixes a bug that is exposed in gateway scenarios.
>
> Signed-off-by: K. Y. Srinivasan
> Reviewed-by: Haiyang Zhang
Applied and queued up for -stable, t hanks.
_
st 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 ar
201 - 300 of 355 matches
Mail list logo
