[PATCH net-next] netvsc: Use the new in-place consumption APIs in the rx path

Use the new APIs for eliminating a copy on the receive path. These new APIs also
help in minimizing the number of memory barriers we end up issuing (in the
ringbuffer code) since we can better control when we want to expose the ring
state to the host.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Tested-by: Dexuan Cui <decui@microsoft.com>
Tested-by: Simon Xiao <redacted>
---
 drivers/net/hyperv/netvsc.c |   88 +++++++++++++++++++++++++++++--------------
 1 files changed, 59 insertions(+), 29 deletions(-)

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 719cb35..8cd4c19 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c

@@ -1141,6 +1141,39 @@ static inline void netvsc_receive_inband(struct hv_device *hdev,
 	}
 }
 
+static void netvsc_process_raw_pkt(struct hv_device *device,
+				   struct vmbus_channel *channel,
+				   struct netvsc_device *net_device,
+				   struct net_device *ndev,
+				   u64 request_id,
+				   struct vmpacket_descriptor *desc)
+{
+	struct nvsp_message *nvmsg;
+
+	nvmsg = (struct nvsp_message *)((unsigned long)
+		desc + (desc->offset8 << 3));
+
+	switch (desc->type) {
+	case VM_PKT_COMP:
+		netvsc_send_completion(net_device, channel, device, desc);
+		break;
+
+	case VM_PKT_DATA_USING_XFER_PAGES:
+		netvsc_receive(net_device, channel, device, desc);
+		break;
+
+	case VM_PKT_DATA_INBAND:
+		netvsc_receive_inband(device, net_device, nvmsg);
+		break;
+
+	default:
+		netdev_err(ndev, "unhandled packet type %d, tid %llx\n",
+			   desc->type, request_id);
+		break;
+	}
+}
+
+
 void netvsc_channel_cb(void *context)
 {
 	int ret;

@@ -1153,7 +1186,7 @@ void netvsc_channel_cb(void *context)
 	unsigned char *buffer;
 	int bufferlen = NETVSC_PACKET_SIZE;
 	struct net_device *ndev;
-	struct nvsp_message *nvmsg;
+	bool need_to_commit = false;
 
 	if (channel->primary_channel != NULL)
 		device = channel->primary_channel->device_obj;

@@ -1167,39 +1200,36 @@ void netvsc_channel_cb(void *context)
 	buffer = get_per_channel_state(channel);
 
 	do {
+		desc = get_next_pkt_raw(channel);
+		if (desc != NULL) {
+			netvsc_process_raw_pkt(device,
+					       channel,
+					       net_device,
+					       ndev,
+					       desc->trans_id,
+					       desc);
+
+			put_pkt_raw(channel, desc);
+			need_to_commit = true;
+			continue;
+		}
+		if (need_to_commit) {
+			need_to_commit = false;
+			commit_rd_index(channel);
+		}
+
 		ret = vmbus_recvpacket_raw(channel, buffer, bufferlen,
 					   &bytes_recvd, &request_id);
 		if (ret == 0) {
 			if (bytes_recvd > 0) {
 				desc = (struct vmpacket_descriptor *)buffer;
-				nvmsg = (struct nvsp_message *)((unsigned long)
-					 desc + (desc->offset8 << 3));
-				switch (desc->type) {
-				case VM_PKT_COMP:
-					netvsc_send_completion(net_device,
-								channel,
-								device, desc);
-					break;
-
-				case VM_PKT_DATA_USING_XFER_PAGES:
-					netvsc_receive(net_device, channel,
-						       device, desc);
-					break;
-
-				case VM_PKT_DATA_INBAND:
-					netvsc_receive_inband(device,
-							      net_device,
-							      nvmsg);
-					break;
-
-				default:
-					netdev_err(ndev,
-						   "unhandled packet type %d, "
-						   "tid %llx len %d\n",
-						   desc->type, request_id,
-						   bytes_recvd);
-					break;
-				}
+				netvsc_process_raw_pkt(device,
+						       channel,
+						       net_device,
+						       ndev,
+						       request_id,
+						       desc);
+
 
 			} else {
 				/*

-- 
1.7.4.1

-----Original Message-----
From: Linus Torvalds [mailto:torvalds@linux-foundation.org]
Sent: Thursday, June 9, 2016 5:12 PM
To: KY Srinivasan <kys@microsoft.com>
Cc: davem@davemloft.net; netdev@vger.kernel.org; lkml <linux-
kernel@vger.kernel.org>; devel@linuxdriverproject.org; olaf@aepfle.de;
apw@canonical.com; jasowang@redhat.com;
leann.ogasawara@canonical.com
Subject: Re: [PATCH net-next] netvsc: Use the new in-place consumption APIs in
the rx path

Srinivasan,

 these are all sent through linuxonhyperv.com, and fail DMARC because
they have a microsoft.com address but no valid DKIM.

Please fix your email setup.  You need to go through the real
microsoft smtp servers if you use a microsoft.com address. Or you need
to get linuxonhyperv.com fixed as a smtp server with the proper MS
email signing.

               Linus

Thanks Linus, we will fix our email setup.

Regards,

K. Y

On Thu, Jun 9, 2016 at 6:34 PM, K. Y. Srinivasan [off-list ref] wrote:

quoted

Use the new APIs for eliminating a copy on the receive path. These new APIs

also

quoted

help in minimizing the number of memory barriers we end up issuing (in the
ringbuffer code) since we can better control when we want to expose the ring
state to the host.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Tested-by: Dexuan Cui <decui@microsoft.com>
Tested-by: Simon Xiao <redacted>
---
 drivers/net/hyperv/netvsc.c |   88 +++++++++++++++++++++++++++++---------

-----

quoted

 1 files changed, 59 insertions(+), 29 deletions(-)

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 719cb35..8cd4c19 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c

@@ -1141,6 +1141,39 @@ static inline void netvsc_receive_inband(struct

hv_device *hdev,

quoted

        }
 }

+static void netvsc_process_raw_pkt(struct hv_device *device,
+                                  struct vmbus_channel *channel,
+                                  struct netvsc_device *net_device,
+                                  struct net_device *ndev,
+                                  u64 request_id,
+                                  struct vmpacket_descriptor *desc)
+{
+       struct nvsp_message *nvmsg;
+
+       nvmsg = (struct nvsp_message *)((unsigned long)
+               desc + (desc->offset8 << 3));
+
+       switch (desc->type) {
+       case VM_PKT_COMP:
+               netvsc_send_completion(net_device, channel, device, desc);
+               break;
+
+       case VM_PKT_DATA_USING_XFER_PAGES:
+               netvsc_receive(net_device, channel, device, desc);
+               break;
+
+       case VM_PKT_DATA_INBAND:
+               netvsc_receive_inband(device, net_device, nvmsg);
+               break;
+
+       default:
+               netdev_err(ndev, "unhandled packet type %d, tid %llx\n",
+                          desc->type, request_id);
+               break;
+       }
+}
+
+
 void netvsc_channel_cb(void *context)
 {
        int ret;

@@ -1153,7 +1186,7 @@ void netvsc_channel_cb(void *context)
        unsigned char *buffer;
        int bufferlen = NETVSC_PACKET_SIZE;
        struct net_device *ndev;
-       struct nvsp_message *nvmsg;
+       bool need_to_commit = false;

        if (channel->primary_channel != NULL)
                device = channel->primary_channel->device_obj;

@@ -1167,39 +1200,36 @@ void netvsc_channel_cb(void *context)
        buffer = get_per_channel_state(channel);

        do {
+               desc = get_next_pkt_raw(channel);
+               if (desc != NULL) {
+                       netvsc_process_raw_pkt(device,
+                                              channel,
+                                              net_device,
+                                              ndev,
+                                              desc->trans_id,
+                                              desc);
+
+                       put_pkt_raw(channel, desc);
+                       need_to_commit = true;
+                       continue;
+               }
+               if (need_to_commit) {
+                       need_to_commit = false;
+                       commit_rd_index(channel);
+               }
+
                ret = vmbus_recvpacket_raw(channel, buffer, bufferlen,
                                           &bytes_recvd, &request_id);
                if (ret == 0) {
                        if (bytes_recvd > 0) {
                                desc = (struct vmpacket_descriptor *)buffer;
-                               nvmsg = (struct nvsp_message *)((unsigned long)
-                                        desc + (desc->offset8 << 3));
-                               switch (desc->type) {
-                               case VM_PKT_COMP:
-                                       netvsc_send_completion(net_device,
-                                                               channel,
-                                                               device, desc);
-                                       break;
-
-                               case VM_PKT_DATA_USING_XFER_PAGES:
-                                       netvsc_receive(net_device, channel,
-                                                      device, desc);
-                                       break;
-
-                               case VM_PKT_DATA_INBAND:
-                                       netvsc_receive_inband(device,
-                                                             net_device,
-                                                             nvmsg);
-                                       break;
-
-                               default:
-                                       netdev_err(ndev,
-                                                  "unhandled packet type %d, "
-                                                  "tid %llx len %d\n",
-                                                  desc->type, request_id,
-                                                  bytes_recvd);
-                                       break;
-                               }
+                               netvsc_process_raw_pkt(device,
+                                                      channel,
+                                                      net_device,
+                                                      ndev,
+                                                      request_id,
+                                                      desc);
+

                        } else {
                                /*
--

1.7.4.1

Srinivasan,

 these are all sent through linuxonhyperv.com, and fail DMARC because
they have a microsoft.com address but no valid DKIM.

Please fix your email setup.  You need to go through the real
microsoft smtp servers if you use a microsoft.com address. Or you need
to get linuxonhyperv.com fixed as a smtp server with the proper MS
email signing.

               Linus

On Thu, Jun 9, 2016 at 6:34 PM, K. Y. Srinivasan [off-list ref] wrote:

-----Original Message-----
From: KY Srinivasan
Sent: Thursday, June 9, 2016 5:16 PM
To: 'Linus Torvalds' <torvalds@linux-foundation.org>
Cc: davem@davemloft.net; netdev@vger.kernel.org; lkml <linux-
kernel@vger.kernel.org>; devel@linuxdriverproject.org; olaf@aepfle.de;
apw@canonical.com; jasowang@redhat.com;
leann.ogasawara@canonical.com
Subject: RE: [PATCH net-next] netvsc: Use the new in-place consumption APIs in
the rx path

quoted

-----Original Message-----
From: Linus Torvalds [mailto:torvalds@linux-foundation.org]
Sent: Thursday, June 9, 2016 5:12 PM
To: KY Srinivasan <kys@microsoft.com>
Cc: davem@davemloft.net; netdev@vger.kernel.org; lkml <linux-
kernel@vger.kernel.org>; devel@linuxdriverproject.org; olaf@aepfle.de;
apw@canonical.com; jasowang@redhat.com;
leann.ogasawara@canonical.com
Subject: Re: [PATCH net-next] netvsc: Use the new in-place consumption APIs

in

quoted

the rx path

Srinivasan,

 these are all sent through linuxonhyperv.com, and fail DMARC because
they have a microsoft.com address but no valid DKIM.

Please fix your email setup.  You need to go through the real
microsoft smtp servers if you use a microsoft.com address. Or you need
to get linuxonhyperv.com fixed as a smtp server with the proper MS
email signing.

               Linus

Thanks Linus, we will fix our email setup.

We have now addressed this issue (kind of). We will continue to send our patches from
linuxonhyperv.com; however the "from" address will be example@exchange.microsoft.com.
We are working on the longer term solution that won't need this weird "from" address.

David, based on this comment from Linus, you have deferred this patch - 
as far as I know there were no other comments for me to address.
Should I resend the patch.

Regards,

K. Y
  

Regards,

K. Y

quoted

On Thu, Jun 9, 2016 at 6:34 PM, K. Y. Srinivasan [off-list ref] wrote:

quoted

Use the new APIs for eliminating a copy on the receive path. These new

APIs

quoted

also

quoted

help in minimizing the number of memory barriers we end up issuing (in

the

quoted

quoted

ringbuffer code) since we can better control when we want to expose the

ring

quoted

quoted

state to the host.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Tested-by: Dexuan Cui <decui@microsoft.com>
Tested-by: Simon Xiao <redacted>
---
 drivers/net/hyperv/netvsc.c |   88 +++++++++++++++++++++++++++++-------

--

quoted

-----

quoted

 1 files changed, 59 insertions(+), 29 deletions(-)

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 719cb35..8cd4c19 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c

@@ -1141,6 +1141,39 @@ static inline void netvsc_receive_inband(struct

hv_device *hdev,

quoted

        }
 }

+static void netvsc_process_raw_pkt(struct hv_device *device,
+                                  struct vmbus_channel *channel,
+                                  struct netvsc_device *net_device,
+                                  struct net_device *ndev,
+                                  u64 request_id,
+                                  struct vmpacket_descriptor *desc)
+{
+       struct nvsp_message *nvmsg;
+
+       nvmsg = (struct nvsp_message *)((unsigned long)
+               desc + (desc->offset8 << 3));
+
+       switch (desc->type) {
+       case VM_PKT_COMP:
+               netvsc_send_completion(net_device, channel, device, desc);
+               break;
+
+       case VM_PKT_DATA_USING_XFER_PAGES:
+               netvsc_receive(net_device, channel, device, desc);
+               break;
+
+       case VM_PKT_DATA_INBAND:
+               netvsc_receive_inband(device, net_device, nvmsg);
+               break;
+
+       default:
+               netdev_err(ndev, "unhandled packet type %d, tid %llx\n",
+                          desc->type, request_id);
+               break;
+       }
+}
+
+
 void netvsc_channel_cb(void *context)
 {
        int ret;

@@ -1153,7 +1186,7 @@ void netvsc_channel_cb(void *context)
        unsigned char *buffer;
        int bufferlen = NETVSC_PACKET_SIZE;
        struct net_device *ndev;
-       struct nvsp_message *nvmsg;
+       bool need_to_commit = false;

        if (channel->primary_channel != NULL)
                device = channel->primary_channel->device_obj;

@@ -1167,39 +1200,36 @@ void netvsc_channel_cb(void *context)
        buffer = get_per_channel_state(channel);

        do {
+               desc = get_next_pkt_raw(channel);
+               if (desc != NULL) {
+                       netvsc_process_raw_pkt(device,
+                                              channel,
+                                              net_device,
+                                              ndev,
+                                              desc->trans_id,
+                                              desc);
+
+                       put_pkt_raw(channel, desc);
+                       need_to_commit = true;
+                       continue;
+               }
+               if (need_to_commit) {
+                       need_to_commit = false;
+                       commit_rd_index(channel);
+               }
+
                ret = vmbus_recvpacket_raw(channel, buffer, bufferlen,
                                           &bytes_recvd, &request_id);
                if (ret == 0) {
                        if (bytes_recvd > 0) {
                                desc = (struct vmpacket_descriptor *)buffer;
-                               nvmsg = (struct nvsp_message *)((unsigned long)
-                                        desc + (desc->offset8 << 3));
-                               switch (desc->type) {
-                               case VM_PKT_COMP:
-                                       netvsc_send_completion(net_device,
-                                                               channel,
-                                                               device, desc);
-                                       break;
-
-                               case VM_PKT_DATA_USING_XFER_PAGES:
-                                       netvsc_receive(net_device, channel,
-                                                      device, desc);
-                                       break;
-
-                               case VM_PKT_DATA_INBAND:
-                                       netvsc_receive_inband(device,
-                                                             net_device,
-                                                             nvmsg);
-                                       break;
-
-                               default:
-                                       netdev_err(ndev,
-                                                  "unhandled packet type %d, "
-                                                  "tid %llx len %d\n",
-                                                  desc->type, request_id,
-                                                  bytes_recvd);
-                                       break;
-                               }
+                               netvsc_process_raw_pkt(device,
+                                                      channel,
+                                                      net_device,
+                                                      ndev,
+                                                      request_id,
+                                                      desc);
+

                        } else {
                                /*
--

1.7.4.1