* [net PATCH 0/5] virtio_net XDP fixes and ajust_header xupport
From: John Fastabend @ 2017-01-12 21:43 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
This has a fix to handle small buffer free logic correctly and then
also adds adjust head support.
I pushed adjust head at net (even though its rc3) to avoid having
to push another exception case into virtio_net to catch if the
program uses adjust_head and then block it. If there are any strong
objections to this we can push it at net-next and use a patch from
Jakub to add the exception handling but then user space has to deal
with it either via try/fail logic or via kernel version checks. Granted
we already have some cases that need to be configured to enable XDP
but I don't see any reason to have yet another one when we can fix it
now vs delaying a kernel version.
---
John Fastabend (5):
virtio_net: use dev_kfree_skb for small buffer XDP receive
net: virtio: wrap rtnl_lock in test for calling with lock already held
virtio_net: factor out xdp handler for readability
virtio_net: remove duplicate queue pair binding in XDP
virtio_net: XDP support for adjust_head
drivers/net/virtio_net.c | 251 ++++++++++++++++++++++++++++++++--------------
drivers/virtio/virtio.c | 9 +-
include/linux/virtio.h | 3 +
3 files changed, 183 insertions(+), 80 deletions(-)
^ permalink raw reply
* [net PATCH 1/5] virtio_net: use dev_kfree_skb for small buffer XDP receive
From: John Fastabend @ 2017-01-12 21:43 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170112213919.3039.54165.stgit@john-Precision-Tower-5810>
In the small buffer case during driver unload we currently use
put_page instead of dev_kfree_skb. Resolve this by adding a check
for virtnet mode when checking XDP queue type. Also name the
function so that the code reads correctly to match the additional
check.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
drivers/net/virtio_net.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 4a10500..d97bb71 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1890,8 +1890,12 @@ static void free_receive_page_frags(struct virtnet_info *vi)
put_page(vi->rq[i].alloc_frag.page);
}
-static bool is_xdp_queue(struct virtnet_info *vi, int q)
+static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
{
+ /* For small receive mode always use kfree_skb variants */
+ if (!vi->mergeable_rx_bufs)
+ return false;
+
if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
return false;
else if (q < vi->curr_queue_pairs)
@@ -1908,7 +1912,7 @@ static void free_unused_bufs(struct virtnet_info *vi)
for (i = 0; i < vi->max_queue_pairs; i++) {
struct virtqueue *vq = vi->sq[i].vq;
while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
- if (!is_xdp_queue(vi, i))
+ if (!is_xdp_raw_buffer_queue(vi, i))
dev_kfree_skb(buf);
else
put_page(virt_to_head_page(buf));
^ permalink raw reply related
* [net PATCH 2/5] net: virtio: wrap rtnl_lock in test for calling with lock already held
From: John Fastabend @ 2017-01-12 21:44 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170112213919.3039.54165.stgit@john-Precision-Tower-5810>
For XDP use case and to allow ethtool reset tests it is useful to be
able to use reset routines from contexts where rtnl lock is already
held.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
drivers/net/virtio_net.c | 16 +++++++++-------
1 file changed, 9 insertions(+), 7 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d97bb71..43cb2e0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1864,12 +1864,13 @@ static void virtnet_free_queues(struct virtnet_info *vi)
kfree(vi->sq);
}
-static void free_receive_bufs(struct virtnet_info *vi)
+static void free_receive_bufs(struct virtnet_info *vi, bool need_lock)
{
struct bpf_prog *old_prog;
int i;
- rtnl_lock();
+ if (need_lock)
+ rtnl_lock();
for (i = 0; i < vi->max_queue_pairs; i++) {
while (vi->rq[i].pages)
__free_pages(get_a_page(&vi->rq[i], GFP_KERNEL), 0);
@@ -1879,7 +1880,8 @@ static void free_receive_bufs(struct virtnet_info *vi)
if (old_prog)
bpf_prog_put(old_prog);
}
- rtnl_unlock();
+ if (need_lock)
+ rtnl_unlock();
}
static void free_receive_page_frags(struct virtnet_info *vi)
@@ -2351,14 +2353,14 @@ static int virtnet_probe(struct virtio_device *vdev)
return err;
}
-static void remove_vq_common(struct virtnet_info *vi)
+static void remove_vq_common(struct virtnet_info *vi, bool lock)
{
vi->vdev->config->reset(vi->vdev);
/* Free unused buffers in both send and recv, if any. */
free_unused_bufs(vi);
- free_receive_bufs(vi);
+ free_receive_bufs(vi, lock);
free_receive_page_frags(vi);
@@ -2376,7 +2378,7 @@ static void virtnet_remove(struct virtio_device *vdev)
unregister_netdev(vi->dev);
- remove_vq_common(vi);
+ remove_vq_common(vi, true);
free_percpu(vi->stats);
free_netdev(vi->dev);
@@ -2401,7 +2403,7 @@ static int virtnet_freeze(struct virtio_device *vdev)
napi_disable(&vi->rq[i].napi);
}
- remove_vq_common(vi);
+ remove_vq_common(vi, true);
return 0;
}
^ permalink raw reply related
* [net PATCH 3/5] virtio_net: factor out xdp handler for readability
From: John Fastabend @ 2017-01-12 21:44 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170112213919.3039.54165.stgit@john-Precision-Tower-5810>
At this point the do_xdp_prog is mostly if/else branches handling
the different modes of virtio_net. So remove it and handle running
the program in the per mode handlers.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
drivers/net/virtio_net.c | 76 +++++++++++++++++-----------------------------
1 file changed, 28 insertions(+), 48 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 43cb2e0..ec54644 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -388,49 +388,6 @@ static void virtnet_xdp_xmit(struct virtnet_info *vi,
virtqueue_kick(sq->vq);
}
-static u32 do_xdp_prog(struct virtnet_info *vi,
- struct receive_queue *rq,
- struct bpf_prog *xdp_prog,
- void *data, int len)
-{
- int hdr_padded_len;
- struct xdp_buff xdp;
- void *buf;
- unsigned int qp;
- u32 act;
-
- if (vi->mergeable_rx_bufs) {
- hdr_padded_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
- xdp.data = data + hdr_padded_len;
- xdp.data_end = xdp.data + (len - vi->hdr_len);
- buf = data;
- } else { /* small buffers */
- struct sk_buff *skb = data;
-
- xdp.data = skb->data;
- xdp.data_end = xdp.data + len;
- buf = skb->data;
- }
-
- act = bpf_prog_run_xdp(xdp_prog, &xdp);
- switch (act) {
- case XDP_PASS:
- return XDP_PASS;
- case XDP_TX:
- qp = vi->curr_queue_pairs -
- vi->xdp_queue_pairs +
- smp_processor_id();
- xdp.data = buf;
- virtnet_xdp_xmit(vi, rq, &vi->sq[qp], &xdp, data);
- return XDP_TX;
- default:
- bpf_warn_invalid_xdp_action(act);
- case XDP_ABORTED:
- case XDP_DROP:
- return XDP_DROP;
- }
-}
-
static struct sk_buff *receive_small(struct net_device *dev,
struct virtnet_info *vi,
struct receive_queue *rq,
@@ -446,19 +403,30 @@ static struct sk_buff *receive_small(struct net_device *dev,
xdp_prog = rcu_dereference(rq->xdp_prog);
if (xdp_prog) {
struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
+ struct xdp_buff xdp;
+ unsigned int qp;
u32 act;
if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags))
goto err_xdp;
- act = do_xdp_prog(vi, rq, xdp_prog, skb, len);
+
+ xdp.data = skb->data;
+ xdp.data_end = xdp.data + len;
+ act = bpf_prog_run_xdp(xdp_prog, &xdp);
switch (act) {
case XDP_PASS:
break;
case XDP_TX:
+ qp = vi->curr_queue_pairs -
+ vi->xdp_queue_pairs +
+ smp_processor_id();
+ virtnet_xdp_xmit(vi, rq, &vi->sq[qp], &xdp, skb);
rcu_read_unlock();
goto xdp_xmit;
- case XDP_DROP:
default:
+ bpf_warn_invalid_xdp_action(act);
+ case XDP_ABORTED:
+ case XDP_DROP:
goto err_xdp;
}
}
@@ -575,7 +543,11 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
rcu_read_lock();
xdp_prog = rcu_dereference(rq->xdp_prog);
if (xdp_prog) {
+ int desc_room = sizeof(struct virtio_net_hdr_mrg_rxbuf);
struct page *xdp_page;
+ struct xdp_buff xdp;
+ unsigned int qp;
+ void *data;
u32 act;
/* This happens when rx buffer size is underestimated */
@@ -598,8 +570,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
if (unlikely(hdr->hdr.gso_type))
goto err_xdp;
- act = do_xdp_prog(vi, rq, xdp_prog,
- page_address(xdp_page) + offset, len);
+ data = page_address(xdp_page) + offset;
+ xdp.data = data + desc_room;
+ xdp.data_end = xdp.data + (len - vi->hdr_len);
+ act = bpf_prog_run_xdp(xdp_prog, &xdp);
switch (act) {
case XDP_PASS:
/* We can only create skb based on xdp_page. */
@@ -613,13 +587,19 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
}
break;
case XDP_TX:
+ qp = vi->curr_queue_pairs -
+ vi->xdp_queue_pairs +
+ smp_processor_id();
+ virtnet_xdp_xmit(vi, rq, &vi->sq[qp], &xdp, data);
ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
if (unlikely(xdp_page != page))
goto err_xdp;
rcu_read_unlock();
goto xdp_xmit;
- case XDP_DROP:
default:
+ bpf_warn_invalid_xdp_action(act);
+ case XDP_ABORTED:
+ case XDP_DROP:
if (unlikely(xdp_page != page))
__free_pages(xdp_page, 0);
ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
^ permalink raw reply related
* [net PATCH 4/5] virtio_net: remove duplicate queue pair binding in XDP
From: John Fastabend @ 2017-01-12 21:44 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170112213919.3039.54165.stgit@john-Precision-Tower-5810>
Factor out qp assignment.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
drivers/net/virtio_net.c | 18 +++++++-----------
1 file changed, 7 insertions(+), 11 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ec54644..6041828 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -332,15 +332,19 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
static void virtnet_xdp_xmit(struct virtnet_info *vi,
struct receive_queue *rq,
- struct send_queue *sq,
struct xdp_buff *xdp,
void *data)
{
struct virtio_net_hdr_mrg_rxbuf *hdr;
unsigned int num_sg, len;
+ struct send_queue *sq;
+ unsigned int qp;
void *xdp_sent;
int err;
+ qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
+ sq = &vi->sq[qp];
+
/* Free up any pending old buffers before queueing new ones. */
while ((xdp_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) {
if (vi->mergeable_rx_bufs) {
@@ -404,7 +408,6 @@ static struct sk_buff *receive_small(struct net_device *dev,
if (xdp_prog) {
struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
struct xdp_buff xdp;
- unsigned int qp;
u32 act;
if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags))
@@ -417,10 +420,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
case XDP_PASS:
break;
case XDP_TX:
- qp = vi->curr_queue_pairs -
- vi->xdp_queue_pairs +
- smp_processor_id();
- virtnet_xdp_xmit(vi, rq, &vi->sq[qp], &xdp, skb);
+ virtnet_xdp_xmit(vi, rq, &xdp, skb);
rcu_read_unlock();
goto xdp_xmit;
default:
@@ -546,7 +546,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
int desc_room = sizeof(struct virtio_net_hdr_mrg_rxbuf);
struct page *xdp_page;
struct xdp_buff xdp;
- unsigned int qp;
void *data;
u32 act;
@@ -587,10 +586,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
}
break;
case XDP_TX:
- qp = vi->curr_queue_pairs -
- vi->xdp_queue_pairs +
- smp_processor_id();
- virtnet_xdp_xmit(vi, rq, &vi->sq[qp], &xdp, data);
+ virtnet_xdp_xmit(vi, rq, &xdp, data);
ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
if (unlikely(xdp_page != page))
goto err_xdp;
^ permalink raw reply related
* [net PATCH 5/5] virtio_net: XDP support for adjust_head
From: John Fastabend @ 2017-01-12 21:45 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170112213919.3039.54165.stgit@john-Precision-Tower-5810>
Add support for XDP adjust head by allocating a 256B header region
that XDP programs can grow into. This is only enabled when a XDP
program is loaded.
In order to ensure that we do not have to unwind queue headroom push
queue setup below bpf_prog_add. It reads better to do a prog ref
unwind vs another queue setup call.
At the moment this code must do a full reset to ensure old buffers
without headroom on program add or with headroom on program removal
are not used incorrectly in the datapath. Ideally we would only
have to disable/enable the RX queues being updated but there is no
API to do this at the moment in virtio so use the big hammer. In
practice it is likely not that big of a problem as this will only
happen when XDP is enabled/disabled changing programs does not
require the reset. There is some risk that the driver may either
have an allocation failure or for some reason fail to correctly
negotiate with the underlying backend in this case the driver will
be left uninitialized. I have not seen this ever happen on my test
systems and for what its worth this same failure case can occur
from probe and other contexts in virtio framework.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
drivers/net/virtio_net.c | 155 ++++++++++++++++++++++++++++++++++++++++------
drivers/virtio/virtio.c | 9 ++-
include/linux/virtio.h | 3 +
3 files changed, 144 insertions(+), 23 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 6041828..8b897e7 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -28,6 +28,7 @@
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/average.h>
+#include <linux/pci.h>
#include <net/busy_poll.h>
static int napi_weight = NAPI_POLL_WEIGHT;
@@ -159,6 +160,9 @@ struct virtnet_info {
/* Ethtool settings */
u8 duplex;
u32 speed;
+
+ /* Headroom allocated in RX Queue */
+ unsigned int headroom;
};
struct padded_vnet_hdr {
@@ -359,6 +363,7 @@ static void virtnet_xdp_xmit(struct virtnet_info *vi,
}
if (vi->mergeable_rx_bufs) {
+ xdp->data -= sizeof(struct virtio_net_hdr_mrg_rxbuf);
/* Zero header and leave csum up to XDP layers */
hdr = xdp->data;
memset(hdr, 0, vi->hdr_len);
@@ -375,7 +380,9 @@ static void virtnet_xdp_xmit(struct virtnet_info *vi,
num_sg = 2;
sg_init_table(sq->sg, 2);
sg_set_buf(sq->sg, hdr, vi->hdr_len);
- skb_to_sgvec(skb, sq->sg + 1, 0, skb->len);
+ skb_to_sgvec(skb, sq->sg + 1,
+ xdp->data - xdp->data_hard_start,
+ xdp->data_end - xdp->data);
}
err = virtqueue_add_outbuf(sq->vq, sq->sg, num_sg,
data, GFP_ATOMIC);
@@ -401,7 +408,6 @@ static struct sk_buff *receive_small(struct net_device *dev,
struct bpf_prog *xdp_prog;
len -= vi->hdr_len;
- skb_trim(skb, len);
rcu_read_lock();
xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -413,11 +419,15 @@ static struct sk_buff *receive_small(struct net_device *dev,
if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags))
goto err_xdp;
- xdp.data = skb->data;
+ xdp.data_hard_start = skb->data;
+ xdp.data = skb->data + vi->headroom;
xdp.data_end = xdp.data + len;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
switch (act) {
case XDP_PASS:
+ /* Recalculate length in case bpf program changed it */
+ len = xdp.data_end - xdp.data;
+ __skb_pull(skb, xdp.data - xdp.data_hard_start);
break;
case XDP_TX:
virtnet_xdp_xmit(vi, rq, &xdp, skb);
@@ -432,6 +442,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
}
rcu_read_unlock();
+ skb_trim(skb, len);
return skb;
err_xdp:
@@ -569,7 +580,11 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
if (unlikely(hdr->hdr.gso_type))
goto err_xdp;
+ /* Allow consuming headroom but reserve enough space to push
+ * the descriptor on if we get an XDP_TX return code.
+ */
data = page_address(xdp_page) + offset;
+ xdp.data_hard_start = data - vi->headroom + desc_room;
xdp.data = data + desc_room;
xdp.data_end = xdp.data + (len - vi->hdr_len);
act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -748,20 +763,21 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
gfp_t gfp)
{
+ int headroom = GOOD_PACKET_LEN + vi->headroom;
struct sk_buff *skb;
struct virtio_net_hdr_mrg_rxbuf *hdr;
int err;
- skb = __netdev_alloc_skb_ip_align(vi->dev, GOOD_PACKET_LEN, gfp);
+ skb = __netdev_alloc_skb_ip_align(vi->dev, headroom, gfp);
if (unlikely(!skb))
return -ENOMEM;
- skb_put(skb, GOOD_PACKET_LEN);
+ skb_put(skb, headroom);
hdr = skb_vnet_hdr(skb);
sg_init_table(rq->sg, 2);
sg_set_buf(rq->sg, hdr, vi->hdr_len);
- skb_to_sgvec(skb, rq->sg + 1, 0, skb->len);
+ skb_to_sgvec(skb, rq->sg + 1, vi->headroom, skb->len - vi->headroom);
err = virtqueue_add_inbuf(rq->vq, rq->sg, 2, skb, gfp);
if (err < 0)
@@ -829,24 +845,27 @@ static unsigned int get_mergeable_buf_len(struct ewma_pkt_len *avg_pkt_len)
return ALIGN(len, MERGEABLE_BUFFER_ALIGN);
}
-static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
+static int add_recvbuf_mergeable(struct virtnet_info *vi,
+ struct receive_queue *rq, gfp_t gfp)
{
struct page_frag *alloc_frag = &rq->alloc_frag;
+ unsigned int headroom = vi->headroom;
char *buf;
unsigned long ctx;
int err;
unsigned int len, hole;
len = get_mergeable_buf_len(&rq->mrg_avg_pkt_len);
- if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp)))
+ if (unlikely(!skb_page_frag_refill(len + headroom, alloc_frag, gfp)))
return -ENOMEM;
buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
+ buf += headroom; /* advance address leaving hole at front of pkt */
ctx = mergeable_buf_to_ctx(buf, len);
get_page(alloc_frag->page);
- alloc_frag->offset += len;
+ alloc_frag->offset += len + headroom;
hole = alloc_frag->size - alloc_frag->offset;
- if (hole < len) {
+ if (hole < len + headroom) {
/* To avoid internal fragmentation, if there is very likely not
* enough space for another buffer, add the remaining space to
* the current buffer. This extra space is not included in
@@ -880,7 +899,7 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
gfp |= __GFP_COLD;
do {
if (vi->mergeable_rx_bufs)
- err = add_recvbuf_mergeable(rq, gfp);
+ err = add_recvbuf_mergeable(vi, rq, gfp);
else if (vi->big_packets)
err = add_recvbuf_big(vi, rq, gfp);
else
@@ -1675,12 +1694,90 @@ static void virtnet_init_settings(struct net_device *dev)
.set_settings = virtnet_set_settings,
};
+#define VIRTIO_XDP_HEADROOM 256
+
+static int init_vqs(struct virtnet_info *vi);
+static void remove_vq_common(struct virtnet_info *vi, bool lock);
+
+/* Reset virtio device with RTNL held this is very similar to the
+ * freeze()/restore() logic except we need to ensure locking. It is
+ * possible that this routine may fail and leave the driver in a
+ * failed state. However assuming the driver negotiated correctly
+ * at probe time we _should_ be able to (re)negotiate driver again.
+ */
+static int virtnet_xdp_reset(struct virtnet_info *vi)
+{
+ struct virtio_device *vdev = vi->vdev;
+ unsigned int status;
+ int i, ret;
+
+ /* Disable and unwind rings */
+ virtio_config_disable(vdev);
+ vdev->failed = vdev->config->get_status(vdev) & VIRTIO_CONFIG_S_FAILED;
+
+ netif_device_detach(vi->dev);
+ cancel_delayed_work_sync(&vi->refill);
+ if (netif_running(vi->dev)) {
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ napi_disable(&vi->rq[i].napi);
+ }
+
+ remove_vq_common(vi, false);
+
+ /* Do a reset per virtio spec recommendation */
+ vdev->config->reset(vdev);
+
+ /* Acknowledge that we've seen the device. */
+ status = vdev->config->get_status(vdev);
+ vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+ /* Notify driver is up and finalize features per specification. The
+ * error code from finalize features is checked here but should not
+ * fail because we assume features were previously synced successfully.
+ */
+ status = vdev->config->get_status(vdev);
+ vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_DRIVER);
+ ret = virtio_finalize_features(vdev);
+ if (ret) {
+ netdev_warn(vi->dev, "virtio_finalize_features failed during reset aborting\n");
+ goto err;
+ }
+
+ ret = init_vqs(vi);
+ if (ret) {
+ netdev_warn(vi->dev, "init_vqs failed during reset aborting\n");
+ goto err;
+ }
+ virtio_device_ready(vi->vdev);
+
+ if (netif_running(vi->dev)) {
+ for (i = 0; i < vi->curr_queue_pairs; i++)
+ if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
+ schedule_delayed_work(&vi->refill, 0);
+
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ virtnet_napi_enable(&vi->rq[i]);
+ }
+ netif_device_attach(vi->dev);
+ /* Finally, tell the device we're all set */
+ status = vdev->config->get_status(vdev);
+ vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_DRIVER_OK);
+ virtio_config_enable(vdev);
+
+ return 0;
+err:
+ status = vdev->config->get_status(vdev);
+ vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_FAILED);
+ return ret;
+}
+
static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
{
unsigned long int max_sz = PAGE_SIZE - sizeof(struct padded_vnet_hdr);
struct virtnet_info *vi = netdev_priv(dev);
struct bpf_prog *old_prog;
u16 xdp_qp = 0, curr_qp;
+ unsigned int old_hr;
int i, err;
if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) ||
@@ -1712,18 +1809,31 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
return -ENOMEM;
}
- err = virtnet_set_queues(vi, curr_qp + xdp_qp);
- if (err) {
- dev_warn(&dev->dev, "XDP Device queue allocation failure.\n");
- return err;
- }
-
+ old_hr = vi->headroom;
if (prog) {
prog = bpf_prog_add(prog, vi->max_queue_pairs - 1);
- if (IS_ERR(prog)) {
- virtnet_set_queues(vi, curr_qp);
+ if (IS_ERR(prog))
return PTR_ERR(prog);
- }
+ vi->headroom = VIRTIO_XDP_HEADROOM;
+ } else {
+ vi->headroom = 0;
+ }
+
+ /* Changing the headroom in buffers is a disruptive operation because
+ * existing buffers must be flushed and reallocated. This will happen
+ * when a xdp program is initially added or xdp is disabled by removing
+ * the xdp program.
+ */
+ if (old_hr != vi->headroom) {
+ err = virtnet_xdp_reset(vi);
+ if (err)
+ goto err_reset;
+ }
+
+ err = virtnet_set_queues(vi, curr_qp + xdp_qp);
+ if (err) {
+ dev_warn(&dev->dev, "XDP Device queue allocation failure.\n");
+ goto err_reset;
}
vi->xdp_queue_pairs = xdp_qp;
@@ -1737,6 +1847,11 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
}
return 0;
+err_reset:
+ if (prog)
+ bpf_prog_sub(prog, vi->max_queue_pairs - 1);
+ vi->headroom = old_hr;
+ return err;
}
static bool virtnet_xdp_query(struct net_device *dev)
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 7062bb0..0e922b9 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -145,14 +145,15 @@ void virtio_config_changed(struct virtio_device *dev)
}
EXPORT_SYMBOL_GPL(virtio_config_changed);
-static void virtio_config_disable(struct virtio_device *dev)
+void virtio_config_disable(struct virtio_device *dev)
{
spin_lock_irq(&dev->config_lock);
dev->config_enabled = false;
spin_unlock_irq(&dev->config_lock);
}
+EXPORT_SYMBOL_GPL(virtio_config_disable);
-static void virtio_config_enable(struct virtio_device *dev)
+void virtio_config_enable(struct virtio_device *dev)
{
spin_lock_irq(&dev->config_lock);
dev->config_enabled = true;
@@ -161,8 +162,9 @@ static void virtio_config_enable(struct virtio_device *dev)
dev->config_change_pending = false;
spin_unlock_irq(&dev->config_lock);
}
+EXPORT_SYMBOL_GPL(virtio_config_enable);
-static int virtio_finalize_features(struct virtio_device *dev)
+int virtio_finalize_features(struct virtio_device *dev)
{
int ret = dev->config->finalize_features(dev);
unsigned status;
@@ -182,6 +184,7 @@ static int virtio_finalize_features(struct virtio_device *dev)
}
return 0;
}
+EXPORT_SYMBOL_GPL(virtio_finalize_features);
static int virtio_dev_probe(struct device *_d)
{
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index d5eb547..eac8f05 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -137,6 +137,9 @@ static inline struct virtio_device *dev_to_virtio(struct device *_dev)
void virtio_break_device(struct virtio_device *dev);
+void virtio_config_disable(struct virtio_device *dev);
+void virtio_config_enable(struct virtio_device *dev);
+int virtio_finalize_features(struct virtio_device *dev);
void virtio_config_changed(struct virtio_device *dev);
#ifdef CONFIG_PM_SLEEP
int virtio_device_freeze(struct virtio_device *dev);
^ permalink raw reply related
* Re: [PATCH] tcp: fix tcp_fastopen unaligned access complaints on sparc
From: David Miller @ 2017-01-12 21:47 UTC (permalink / raw)
To: eric.dumazet
Cc: shannon.nelson, rob.gardner, netdev, sparclinux, linux-kernel
In-Reply-To: <1484256990.13165.6.camel@edumazet-glaptop3.roam.corp.google.com>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 12 Jan 2017 13:36:30 -0800
> val should be an union, so that proper alignment is enforced by one
> member.
Sure, annotating the type so that it is aligned correctly makes
sense.
^ permalink raw reply
* Re: [PATCH net-next] ipmr: improve hash scalability
From: David Miller @ 2017-01-12 21:48 UTC (permalink / raw)
To: nikolay; +Cc: netdev, roopa, sharpd
In-Reply-To: <1484232813-11473-1-git-send-email-nikolay@cumulusnetworks.com>
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Thu, 12 Jan 2017 15:53:33 +0100
> Recently we started using ipmr with thousands of entries and easily hit
> soft lockups on smaller devices. The reason is that the hash function
> uses the high order bits from the src and dst, but those don't change in
> many common cases, also the hash table is only 64 elements so with
> thousands it doesn't scale at all.
> This patch migrates the hash table to rhashtable, and in particular the
> rhl interface which allows for duplicate elements to be chained because
> of the MFC_PROXY support (*,G; *,*,oif cases) which allows for multiple
> duplicate entries to be added with different interfaces (IMO wrong, but
> it's been in for a long time).
>
> And here are some results from tests I've run in a VM:
> mr_table size (default, allocated for all namespaces):
> Before After
> 49304 bytes 2400 bytes
>
> Add 65000 routes (the diff is much larger on smaller devices):
> Before After
> 1m42s 58s
>
> Forwarding 256 byte packets with 65000 routes (test done in a VM):
> Before After
> 3 Mbps / ~1465 pps 122 Mbps / ~59000 pps
>
> As a bonus we no longer see the soft lockups on smaller devices which
> showed up even with 2000 entries before.
>
> Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Looks really nice, applied, thanks!
^ permalink raw reply
* Re: Marvell Phy (1510) issue since v4.7 kernel
From: Andrew Lunn @ 2017-01-12 21:49 UTC (permalink / raw)
To: Kwok, WingMan
Cc: rmk+kernel@arm.linux.org.uk, Karicheri, Muralidharan,
netdev@vger.kernel.org
In-Reply-To: <230CBA6E4B6B6B418E8730AC28E6FC7E15354EB0@DFLE11.ent.ti.com>
> But our problem is caused by the read_status function:
>
> if ((phydev->supported & SUPPORTED_FIBRE)) {
> err = phy_write(phydev, MII_MARVELL_PHY_PAGE, MII_M1111_FIBER);
> if (err < 0)
> goto error;
>
> err = marvell_read_status_page(phydev, MII_M1111_FIBER);
> if (err < 0)
> goto error;
>
> /* If the fiber link is up, it is the selected and used link.
> * In this case, we need to stay in the fiber page.
> * Please to be careful about that, avoid to restore Copper page
> * in other functions which could break the behaviour
> * for some fiber phy like 88E1512.
> * */
> if (phydev->link)
> return 0;
>
> which keeps the fiber page if phydev->link is true (for some
> reason this is the case even though we are not using fiber)
How are you using the PHY. What phy-mode do you have set? Do you
happen to be using it as an RGMII to SERDES/SGMII bridge? This is what
Russell King is doing, i think.
Have you tried the patch Russell submitted recently.
Author: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue Jan 10 23:13:45 2017 +0000
net: phy: marvell: fix Marvell 88E1512 used in SGMII mode
When an Marvell 88E1512 PHY is connected to a nic in SGMII mode, the
fiber page is used for the SGMII host-side connection. The PHY driver
notices that SUPPORTED_FIBRE is set, so it tries reading the fiber page
for the link status, and ends up reading the MAC-side status instead of
the outgoing (copper) link. This leads to incorrect results reported
via ethtool.
If the PHY is connected via SGMII to the host, ignore the fiber page.
However, continue to allow the existing power management code to
suspend and resume the fiber page.
> However, this causes a problem in kernel reboot because neither
> the suspend/resume is called to restore the copper page and
> u-boot marvell phy driver does not support 1510 fiber, which
> will then result in writing to the wrong phy regs and causes
> a sgmii auto-nego time out.
This is still a u-boot bug. It should not assume the PHY is in a sane
state. It should reset it and configure it as needed. So far, i don't
think you have reported any issues with Linux usage of the PHY. There
clearly are bugs, but your real problem is u-boot.
> In addition to fixing the ! in suspend/resume, my suggestion
> would be to change also the read_status function to
> always restore the copper page after doing the fiber stuffs:
Nope. This is done deliberately, as the comment suggests:
> /* If the fiber link is up, it is the selected and used link.
> * In this case, we need to stay in the fiber page.
> * Please to be careful about that, avoid to restore Copper page
> * in other functions which could break the behaviour
> * for some fiber phy like 88E1512.
> * */
> if (phydev->link)
> return 0;
The point is, the phylib will continue polling the PHY registers,
reading them. If the FIBRE is up, we want to read the FIBRE values,
not the copper.
> Another issue is that, as of now, FIBER is enabled regardless
> of the specific 88e151x. But I believe there is 88e151x chip(s)
> that does not support fiber. Should fiber be enabled only for
> those that do support fiber?
Yes, we should look at register 30, page 18 any set SUPPORTED_FIBRE
based on that.
Andrew
^ permalink raw reply
* Re: [PATCH] net: thunderx: acpi: fix LMAC initialization
From: David Miller @ 2017-01-12 21:50 UTC (permalink / raw)
To: Vadim.Lomovtsev
Cc: linux-arm-kernel, netdev, linux-kernel, sgoutham, rric,
Radha.Chintakuntla
In-Reply-To: <1484234886-22172-1-git-send-email-Vadim.Lomovtsev@caviumnetworks.com>
From: Vadim Lomovtsev <Vadim.Lomovtsev@caviumnetworks.com>
Date: Thu, 12 Jan 2017 07:28:06 -0800
> While probing BGX we requesting appropriate QLM for it's configuration
> and get LMAC count by that request. Then, while reading configured
> MAC values from SSDT table we need to save them in proper mapping:
> BGX[i]->lmac[j].mac = <MAC value>
> to later provide for initialization stuff. In order to fill
> such mapping properly we need to add lmac index to be used while
> acpi initialization since at this moment bgx->lmac_count already contains
> actual value.
>
> Signed-off-by: Vadim Lomovtsev <Vadim.Lomovtsev@caviumnetworks.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next] liquidio: replace skb_tx_hash with fallback
From: David Miller @ 2017-01-12 21:51 UTC (permalink / raw)
To: eric.dumazet
Cc: felix.manlunas, netdev, raghu.vatsavayi, derek.chickles,
satananda.burla
In-Reply-To: <1484248218.3321.1.camel@edumazet-glaptop3.roam.corp.google.com>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 12 Jan 2017 11:10:18 -0800
> Why are you keeping these functions then ?
>
> Remove them completely, and remove .ndo_select_queue from your ops.
>
> Core networking stack will fallback automatically.
Agreed, if all the queue selection function is doing is invoking the
fallback, get rid of it.
^ permalink raw reply
* Re: [PATCH net-next] ipv6: sr: static percpu allocation for hmac_ring
From: David Miller @ 2017-01-12 21:53 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev, david.lebrun
In-Reply-To: <1484239810.15816.47.camel@edumazet-glaptop3.roam.corp.google.com>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 12 Jan 2017 08:50:10 -0800
> From: Eric Dumazet <edumazet@google.com>
>
> Current allocations are not NUMA aware, and lack proper
> cleanup in case of error.
>
> It is perfectly fine to use static per cpu allocations for 256 bytes
> per cpu.
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Cc: David Lebrun <david.lebrun@uclouvain.be>
Applied.
^ permalink raw reply
* Re: [PATCH] tcp: fix tcp_fastopen unaligned access complaints on sparc
From: Shannon Nelson @ 2017-01-12 21:58 UTC (permalink / raw)
To: David Miller, eric.dumazet; +Cc: rob.gardner, netdev, sparclinux, linux-kernel
In-Reply-To: <20170112.164731.720625943370044951.davem@davemloft.net>
On 1/12/2017 1:47 PM, David Miller wrote:
> From: Eric Dumazet <eric.dumazet@gmail.com>
> Date: Thu, 12 Jan 2017 13:36:30 -0800
>
>> val should be an union, so that proper alignment is enforced by one
>> member.
>
> Sure, annotating the type so that it is aligned correctly makes
> sense.
>
... and we should change the offending pointer assignment as well. I
can use this and respin a v2 if we're happy with this solution.
sln
^ permalink raw reply
* Re: [PATCH] tcp: fix tcp_fastopen unaligned access complaints on sparc
From: David Miller @ 2017-01-12 21:58 UTC (permalink / raw)
To: shannon.nelson
Cc: eric.dumazet, rob.gardner, netdev, sparclinux, linux-kernel
In-Reply-To: <a24f1f0e-457b-0316-b545-fe1362bd7dbe@oracle.com>
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Thu, 12 Jan 2017 13:58:10 -0800
>
>
> On 1/12/2017 1:47 PM, David Miller wrote:
>> From: Eric Dumazet <eric.dumazet@gmail.com>
>> Date: Thu, 12 Jan 2017 13:36:30 -0800
>>
>>> val should be an union, so that proper alignment is enforced by one
>>> member.
>>
>> Sure, annotating the type so that it is aligned correctly makes
>> sense.
>>
>
> ... and we should change the offending pointer assignment as well. I
> can use this and respin a v2 if we're happy with this solution.
I am.
^ permalink raw reply
* Re: [net-next PATCH 1/3] Revert "icmp: avoid allocating large struct on stack"
From: Cong Wang @ 2017-01-12 22:21 UTC (permalink / raw)
To: Eric Dumazet
Cc: Jesper Dangaard Brouer, David Miller,
Linux Kernel Network Developers
In-Reply-To: <1484084891.21472.44.camel@edumazet-glaptop3.roam.corp.google.com>
On Tue, Jan 10, 2017 at 1:48 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> On Tue, 2017-01-10 at 21:08 +0100, Jesper Dangaard Brouer wrote:
>> On Tue, 10 Jan 2017 10:44:59 -0800 Cong Wang <xiyou.wangcong@gmail.com> wrote:
>>
>> > On Tue, Jan 10, 2017 at 10:12 AM, David Miller <davem@davemloft.net> wrote:
>> [...]
>> > > You can keep showing us how expertly you can deflect the real
>> > > issue we are discussion here, but that won't improve the situation
>> > > at all I am afraid.
>> >
>> > Of course, there are just too many people too lazy to do a google search:
>> >
>> > https://lists.debian.org/debian-kernel/2013/05/msg00500.html
>>
>> My analysis of the problem shown in above link is not related to using
>> all the stack space, but instead that skb->cb was not cleared. This
>> can cause the ip_options_echo() call in icmp_send() to access garbage
>> as this is: __ip_options_echo(dopt, skb, &IPCB(skb)->opt).
>>
>> Fixed by commit a622260254ee ("ip_tunnel: fix kernel panic with icmp_dest_unreach")
>> https://git.kernel.org/torvalds/c/a622260254ee
>>
>> Thus, it is (likely) the __ip_options_echo() call that violates stack
>> access, as it is passed in a pointer to the stack, and advance this
>> based on garbage "optlen".
>>
>
> I totally agree.
I can't agree, iptunnel or ipgre symbols are not in the above stack trace
at all. Although I do agree that the above stack usage is not aggressive,
especially when compared with the other I sent.
My vague memory told me the original problem I fixed is related to vxlan
but after trying to search all netdev archives in 2013 May/Jun, I still can't
find it, perhaps it was reported to LKML or somewhere else rather than
netdev. It was certainly a real problem.
Even though the irq stack is 16K, but it is too easy to stack netdevices
and stack qdisc's too, so for TX path I am not surprised at all if 16K could
be exhausted eventually. Yeah, it is hard to blame one of them in the call
chain, but 112 bytes _alone_ are aggressive for such a function deeply
in the call stack. That's my whole point.
^ permalink raw reply
* Re: [net PATCH 5/5] virtio_net: XDP support for adjust_head
From: Michael S. Tsirkin @ 2017-01-12 22:22 UTC (permalink / raw)
To: John Fastabend
Cc: jasowang, john.r.fastabend, netdev, alexei.starovoitov, daniel
In-Reply-To: <20170112214519.3039.27879.stgit@john-Precision-Tower-5810>
On Thu, Jan 12, 2017 at 01:45:19PM -0800, John Fastabend wrote:
> Add support for XDP adjust head by allocating a 256B header region
> that XDP programs can grow into. This is only enabled when a XDP
> program is loaded.
>
> In order to ensure that we do not have to unwind queue headroom push
> queue setup below bpf_prog_add. It reads better to do a prog ref
> unwind vs another queue setup call.
>
> At the moment this code must do a full reset to ensure old buffers
> without headroom on program add or with headroom on program removal
> are not used incorrectly in the datapath. Ideally we would only
> have to disable/enable the RX queues being updated but there is no
> API to do this at the moment in virtio so use the big hammer. In
> practice it is likely not that big of a problem as this will only
> happen when XDP is enabled/disabled changing programs does not
> require the reset. There is some risk that the driver may either
> have an allocation failure or for some reason fail to correctly
> negotiate with the underlying backend in this case the driver will
> be left uninitialized. I have not seen this ever happen on my test
> systems and for what its worth this same failure case can occur
> from probe and other contexts in virtio framework.
Could you explain about this a bit more?
Thanks!
> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
> ---
> drivers/net/virtio_net.c | 155 ++++++++++++++++++++++++++++++++++++++++------
> drivers/virtio/virtio.c | 9 ++-
> include/linux/virtio.h | 3 +
> 3 files changed, 144 insertions(+), 23 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 6041828..8b897e7 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -28,6 +28,7 @@
> #include <linux/slab.h>
> #include <linux/cpu.h>
> #include <linux/average.h>
> +#include <linux/pci.h>
> #include <net/busy_poll.h>
>
> static int napi_weight = NAPI_POLL_WEIGHT;
> @@ -159,6 +160,9 @@ struct virtnet_info {
> /* Ethtool settings */
> u8 duplex;
> u32 speed;
> +
> + /* Headroom allocated in RX Queue */
> + unsigned int headroom;
> };
>
> struct padded_vnet_hdr {
> @@ -359,6 +363,7 @@ static void virtnet_xdp_xmit(struct virtnet_info *vi,
> }
>
> if (vi->mergeable_rx_bufs) {
> + xdp->data -= sizeof(struct virtio_net_hdr_mrg_rxbuf);
> /* Zero header and leave csum up to XDP layers */
> hdr = xdp->data;
> memset(hdr, 0, vi->hdr_len);
> @@ -375,7 +380,9 @@ static void virtnet_xdp_xmit(struct virtnet_info *vi,
> num_sg = 2;
> sg_init_table(sq->sg, 2);
> sg_set_buf(sq->sg, hdr, vi->hdr_len);
> - skb_to_sgvec(skb, sq->sg + 1, 0, skb->len);
> + skb_to_sgvec(skb, sq->sg + 1,
> + xdp->data - xdp->data_hard_start,
> + xdp->data_end - xdp->data);
> }
> err = virtqueue_add_outbuf(sq->vq, sq->sg, num_sg,
> data, GFP_ATOMIC);
> @@ -401,7 +408,6 @@ static struct sk_buff *receive_small(struct net_device *dev,
> struct bpf_prog *xdp_prog;
>
> len -= vi->hdr_len;
> - skb_trim(skb, len);
>
> rcu_read_lock();
> xdp_prog = rcu_dereference(rq->xdp_prog);
> @@ -413,11 +419,15 @@ static struct sk_buff *receive_small(struct net_device *dev,
> if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags))
> goto err_xdp;
>
> - xdp.data = skb->data;
> + xdp.data_hard_start = skb->data;
> + xdp.data = skb->data + vi->headroom;
> xdp.data_end = xdp.data + len;
> act = bpf_prog_run_xdp(xdp_prog, &xdp);
> switch (act) {
> case XDP_PASS:
> + /* Recalculate length in case bpf program changed it */
> + len = xdp.data_end - xdp.data;
> + __skb_pull(skb, xdp.data - xdp.data_hard_start);
> break;
> case XDP_TX:
> virtnet_xdp_xmit(vi, rq, &xdp, skb);
> @@ -432,6 +442,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
> }
> rcu_read_unlock();
>
> + skb_trim(skb, len);
> return skb;
>
> err_xdp:
> @@ -569,7 +580,11 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
> if (unlikely(hdr->hdr.gso_type))
> goto err_xdp;
>
> + /* Allow consuming headroom but reserve enough space to push
> + * the descriptor on if we get an XDP_TX return code.
> + */
> data = page_address(xdp_page) + offset;
> + xdp.data_hard_start = data - vi->headroom + desc_room;
> xdp.data = data + desc_room;
> xdp.data_end = xdp.data + (len - vi->hdr_len);
> act = bpf_prog_run_xdp(xdp_prog, &xdp);
> @@ -748,20 +763,21 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
> static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
> gfp_t gfp)
> {
> + int headroom = GOOD_PACKET_LEN + vi->headroom;
> struct sk_buff *skb;
> struct virtio_net_hdr_mrg_rxbuf *hdr;
> int err;
>
> - skb = __netdev_alloc_skb_ip_align(vi->dev, GOOD_PACKET_LEN, gfp);
> + skb = __netdev_alloc_skb_ip_align(vi->dev, headroom, gfp);
> if (unlikely(!skb))
> return -ENOMEM;
>
> - skb_put(skb, GOOD_PACKET_LEN);
> + skb_put(skb, headroom);
>
> hdr = skb_vnet_hdr(skb);
> sg_init_table(rq->sg, 2);
> sg_set_buf(rq->sg, hdr, vi->hdr_len);
> - skb_to_sgvec(skb, rq->sg + 1, 0, skb->len);
> + skb_to_sgvec(skb, rq->sg + 1, vi->headroom, skb->len - vi->headroom);
>
> err = virtqueue_add_inbuf(rq->vq, rq->sg, 2, skb, gfp);
> if (err < 0)
> @@ -829,24 +845,27 @@ static unsigned int get_mergeable_buf_len(struct ewma_pkt_len *avg_pkt_len)
> return ALIGN(len, MERGEABLE_BUFFER_ALIGN);
> }
>
> -static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
> +static int add_recvbuf_mergeable(struct virtnet_info *vi,
> + struct receive_queue *rq, gfp_t gfp)
> {
> struct page_frag *alloc_frag = &rq->alloc_frag;
> + unsigned int headroom = vi->headroom;
> char *buf;
> unsigned long ctx;
> int err;
> unsigned int len, hole;
>
> len = get_mergeable_buf_len(&rq->mrg_avg_pkt_len);
> - if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp)))
> + if (unlikely(!skb_page_frag_refill(len + headroom, alloc_frag, gfp)))
> return -ENOMEM;
>
> buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
> + buf += headroom; /* advance address leaving hole at front of pkt */
> ctx = mergeable_buf_to_ctx(buf, len);
> get_page(alloc_frag->page);
> - alloc_frag->offset += len;
> + alloc_frag->offset += len + headroom;
> hole = alloc_frag->size - alloc_frag->offset;
> - if (hole < len) {
> + if (hole < len + headroom) {
> /* To avoid internal fragmentation, if there is very likely not
> * enough space for another buffer, add the remaining space to
> * the current buffer. This extra space is not included in
> @@ -880,7 +899,7 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
> gfp |= __GFP_COLD;
> do {
> if (vi->mergeable_rx_bufs)
> - err = add_recvbuf_mergeable(rq, gfp);
> + err = add_recvbuf_mergeable(vi, rq, gfp);
> else if (vi->big_packets)
> err = add_recvbuf_big(vi, rq, gfp);
> else
> @@ -1675,12 +1694,90 @@ static void virtnet_init_settings(struct net_device *dev)
> .set_settings = virtnet_set_settings,
> };
>
> +#define VIRTIO_XDP_HEADROOM 256
> +
> +static int init_vqs(struct virtnet_info *vi);
> +static void remove_vq_common(struct virtnet_info *vi, bool lock);
> +
> +/* Reset virtio device with RTNL held this is very similar to the
> + * freeze()/restore() logic except we need to ensure locking. It is
> + * possible that this routine may fail and leave the driver in a
> + * failed state. However assuming the driver negotiated correctly
> + * at probe time we _should_ be able to (re)negotiate driver again.
> + */
> +static int virtnet_xdp_reset(struct virtnet_info *vi)
> +{
> + struct virtio_device *vdev = vi->vdev;
> + unsigned int status;
> + int i, ret;
> +
> + /* Disable and unwind rings */
> + virtio_config_disable(vdev);
> + vdev->failed = vdev->config->get_status(vdev) & VIRTIO_CONFIG_S_FAILED;
> +
> + netif_device_detach(vi->dev);
> + cancel_delayed_work_sync(&vi->refill);
> + if (netif_running(vi->dev)) {
> + for (i = 0; i < vi->max_queue_pairs; i++)
> + napi_disable(&vi->rq[i].napi);
> + }
> +
> + remove_vq_common(vi, false);
> +
> + /* Do a reset per virtio spec recommendation */
> + vdev->config->reset(vdev);
> +
> + /* Acknowledge that we've seen the device. */
> + status = vdev->config->get_status(vdev);
> + vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_ACKNOWLEDGE);
> +
> + /* Notify driver is up and finalize features per specification. The
> + * error code from finalize features is checked here but should not
> + * fail because we assume features were previously synced successfully.
> + */
> + status = vdev->config->get_status(vdev);
> + vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_DRIVER);
> + ret = virtio_finalize_features(vdev);
> + if (ret) {
> + netdev_warn(vi->dev, "virtio_finalize_features failed during reset aborting\n");
> + goto err;
> + }
> +
> + ret = init_vqs(vi);
> + if (ret) {
> + netdev_warn(vi->dev, "init_vqs failed during reset aborting\n");
> + goto err;
> + }
> + virtio_device_ready(vi->vdev);
> +
> + if (netif_running(vi->dev)) {
> + for (i = 0; i < vi->curr_queue_pairs; i++)
> + if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
> + schedule_delayed_work(&vi->refill, 0);
> +
> + for (i = 0; i < vi->max_queue_pairs; i++)
> + virtnet_napi_enable(&vi->rq[i]);
> + }
> + netif_device_attach(vi->dev);
> + /* Finally, tell the device we're all set */
> + status = vdev->config->get_status(vdev);
> + vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_DRIVER_OK);
> + virtio_config_enable(vdev);
> +
> + return 0;
> +err:
> + status = vdev->config->get_status(vdev);
> + vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_FAILED);
> + return ret;
> +}
> +
> static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
> {
> unsigned long int max_sz = PAGE_SIZE - sizeof(struct padded_vnet_hdr);
> struct virtnet_info *vi = netdev_priv(dev);
> struct bpf_prog *old_prog;
> u16 xdp_qp = 0, curr_qp;
> + unsigned int old_hr;
> int i, err;
>
> if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) ||
> @@ -1712,18 +1809,31 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
> return -ENOMEM;
> }
>
> - err = virtnet_set_queues(vi, curr_qp + xdp_qp);
> - if (err) {
> - dev_warn(&dev->dev, "XDP Device queue allocation failure.\n");
> - return err;
> - }
> -
> + old_hr = vi->headroom;
> if (prog) {
> prog = bpf_prog_add(prog, vi->max_queue_pairs - 1);
> - if (IS_ERR(prog)) {
> - virtnet_set_queues(vi, curr_qp);
> + if (IS_ERR(prog))
> return PTR_ERR(prog);
> - }
> + vi->headroom = VIRTIO_XDP_HEADROOM;
> + } else {
> + vi->headroom = 0;
> + }
> +
> + /* Changing the headroom in buffers is a disruptive operation because
> + * existing buffers must be flushed and reallocated. This will happen
> + * when a xdp program is initially added or xdp is disabled by removing
> + * the xdp program.
> + */
> + if (old_hr != vi->headroom) {
> + err = virtnet_xdp_reset(vi);
> + if (err)
> + goto err_reset;
> + }
> +
> + err = virtnet_set_queues(vi, curr_qp + xdp_qp);
> + if (err) {
> + dev_warn(&dev->dev, "XDP Device queue allocation failure.\n");
> + goto err_reset;
> }
>
> vi->xdp_queue_pairs = xdp_qp;
> @@ -1737,6 +1847,11 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
> }
>
> return 0;
> +err_reset:
> + if (prog)
> + bpf_prog_sub(prog, vi->max_queue_pairs - 1);
> + vi->headroom = old_hr;
> + return err;
> }
>
> static bool virtnet_xdp_query(struct net_device *dev)
> diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
> index 7062bb0..0e922b9 100644
> --- a/drivers/virtio/virtio.c
> +++ b/drivers/virtio/virtio.c
> @@ -145,14 +145,15 @@ void virtio_config_changed(struct virtio_device *dev)
> }
> EXPORT_SYMBOL_GPL(virtio_config_changed);
>
> -static void virtio_config_disable(struct virtio_device *dev)
> +void virtio_config_disable(struct virtio_device *dev)
> {
> spin_lock_irq(&dev->config_lock);
> dev->config_enabled = false;
> spin_unlock_irq(&dev->config_lock);
> }
> +EXPORT_SYMBOL_GPL(virtio_config_disable);
>
> -static void virtio_config_enable(struct virtio_device *dev)
> +void virtio_config_enable(struct virtio_device *dev)
> {
> spin_lock_irq(&dev->config_lock);
> dev->config_enabled = true;
> @@ -161,8 +162,9 @@ static void virtio_config_enable(struct virtio_device *dev)
> dev->config_change_pending = false;
> spin_unlock_irq(&dev->config_lock);
> }
> +EXPORT_SYMBOL_GPL(virtio_config_enable);
>
> -static int virtio_finalize_features(struct virtio_device *dev)
> +int virtio_finalize_features(struct virtio_device *dev)
> {
> int ret = dev->config->finalize_features(dev);
> unsigned status;
> @@ -182,6 +184,7 @@ static int virtio_finalize_features(struct virtio_device *dev)
> }
> return 0;
> }
> +EXPORT_SYMBOL_GPL(virtio_finalize_features);
>
> static int virtio_dev_probe(struct device *_d)
> {
> diff --git a/include/linux/virtio.h b/include/linux/virtio.h
> index d5eb547..eac8f05 100644
> --- a/include/linux/virtio.h
> +++ b/include/linux/virtio.h
> @@ -137,6 +137,9 @@ static inline struct virtio_device *dev_to_virtio(struct device *_dev)
>
> void virtio_break_device(struct virtio_device *dev);
>
> +void virtio_config_disable(struct virtio_device *dev);
> +void virtio_config_enable(struct virtio_device *dev);
> +int virtio_finalize_features(struct virtio_device *dev);
> void virtio_config_changed(struct virtio_device *dev);
> #ifdef CONFIG_PM_SLEEP
> int virtio_device_freeze(struct virtio_device *dev);
^ permalink raw reply
* [PATCH v2] tcp: fix tcp_fastopen unaligned access complaints on sparc
From: Shannon Nelson @ 2017-01-12 22:24 UTC (permalink / raw)
To: netdev, davem
Cc: sparclinux, linux-kernel, eric.dumazet, rob.gardner,
Shannon Nelson
Fix up a data alignment issue on sparc by swapping the order
of the cookie byte array field with the length field in
struct tcp_fastopen_cookie, and making it a proper union
to clean up the typecasting.
This addresses log complaints like these:
log_unaligned: 113 callbacks suppressed
Kernel unaligned access at TPC[976490] tcp_try_fastopen+0x2d0/0x360
Kernel unaligned access at TPC[9764ac] tcp_try_fastopen+0x2ec/0x360
Kernel unaligned access at TPC[9764c8] tcp_try_fastopen+0x308/0x360
Kernel unaligned access at TPC[9764e4] tcp_try_fastopen+0x324/0x360
Kernel unaligned access at TPC[976490] tcp_try_fastopen+0x2d0/0x360
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
---
v2: Use Eric's suggestion for a union in the struct
include/linux/tcp.h | 7 ++++++-
net/ipv4/tcp_fastopen.c | 2 +-
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index fc5848d..c93f4b3 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -62,8 +62,13 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb)
/* TCP Fast Open Cookie as stored in memory */
struct tcp_fastopen_cookie {
+ union {
+ u8 val[TCP_FASTOPEN_COOKIE_MAX];
+#if IS_ENABLED(CONFIG_IPV6)
+ struct in6_addr addr;
+#endif
+ };
s8 len;
- u8 val[TCP_FASTOPEN_COOKIE_MAX];
bool exp; /* In RFC6994 experimental option format */
};
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 4e777a3..f519195 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -113,7 +113,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
struct tcp_fastopen_cookie tmp;
if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
- struct in6_addr *buf = (struct in6_addr *) tmp.val;
+ struct in6_addr *buf = &tmp.addr;
int i;
for (i = 0; i < 4; i++)
--
1.7.1
^ permalink raw reply related
* Re: [PATCH 2/2] ARM: dts: dra72-evm-revc: enable irqs for dp83867 eth phys
From: Tony Lindgren @ 2017-01-12 22:27 UTC (permalink / raw)
To: Grygorii Strashko; +Cc: Mugunthan V N, linux-omap, Sekhar Nori, netdev
In-Reply-To: <cd8cdb56-ca47-6e17-43b4-daedc7889612@ti.com>
* Grygorii Strashko <grygorii.strashko@ti.com> [170109 11:26]:
>
>
> On 01/06/2017 03:54 PM, Tony Lindgren wrote:
> > * Grygorii Strashko <grygorii.strashko@ti.com> [170106 12:56]:
> > > TI DRA72-EVM Rev C has two DP83867 ethernet phys which support IRQ
> > > generation in case of phy/link status changes. The INT/PWDN lines from both
> > > DP83867 phys are wired to DRA7 gpio6.16, so reflect the same in DT.
> >
> > Hmm not seeing the patch 1/2 here.. Can this one be queued separately?
> > Is it for v4.11 or a fix?
>
> This is for next (v4.11) and there is just a mistake in subj, Sry.
OK applying into omap-for-v4.11/dt thanks.
Tony
^ permalink raw reply
* Re: Marvell Phy (1510) issue since v4.7 kernel
From: Russell King - ARM Linux @ 2017-01-12 22:31 UTC (permalink / raw)
To: Andrew Lunn
Cc: Kwok, WingMan, Karicheri, Muralidharan, netdev@vger.kernel.org
In-Reply-To: <20170112214941.GE10203@lunn.ch>
On Thu, Jan 12, 2017 at 10:49:41PM +0100, Andrew Lunn wrote:
> How are you using the PHY. What phy-mode do you have set? Do you
> happen to be using it as an RGMII to SERDES/SGMII bridge? This is what
> Russell King is doing, i think.
No - the 88E1512 here is connected to the ethernet host via SGMII.
Armada 8040 ----SGMII----> 88E1512 ----> RJ45
The problem that my commit fixes is that when the 88E1512 is used in
this mode, the copper page reflects the status of the RJ45-side link,
and the fiber page reflects the Armada 8040 side of the link.
Without my patch, the 88E1512 read_status function spots that the fiber
page reports its link is up (because the Armada 8040 side is indeed up)
and decides to report that as the link settings, rather than the
(correct) copper side.
> The point is, the phylib will continue polling the PHY registers,
> reading them. If the FIBRE is up, we want to read the FIBRE values,
> not the copper.
... but only if we aren't connected in SGMII mode to the ethernet host!
The 88E1512 has the RGMII pins, and it has the Serdes pins. The Serdes
pins are used for the optical transceiver, or they're used for a SGMII
connection to an ethernet host. So they can't do both.
--
RMK's Patch system: http://www.armlinux.org.uk/developer/patches/
FTTC broadband for 0.8mile line: currently at 9.6Mbps down 400kbps up
according to speedtest.net.
^ permalink raw reply
* [next-queue v4 PATCH 0/7]i40e: Add VF Port Representator support for SR-IOV VFs
From: Sridhar Samudrala @ 2017-01-12 22:35 UTC (permalink / raw)
To: alexander.h.duyck, john.r.fastabend, anjali.singhai,
jakub.kicinski, davem, scott.d.peterson, gerlitz.or, jiri,
intel-wired-lan, netdev
This patchset is against dev-queue branch of Jeff Kirsher's next-queue git tree.
- Patch 1 introduces devlink interface to get/set the mode of SRIOV switch.
- Patch 2 adds support to create VF port representor(VFPR) netdevs associated
with SR-IOV VFs that can be used to control/configure VFs from PF name space.
- Patch 3 enables syncing link state between VFs and VFPRs.
- Patch 4 adds a new type to metadata_dst to allow passing VF id to lower device.
- Patch 5 adds TX and RX support to VFPR netdevs.
- Patch 6 enables HW and SW VFPR statistics to be exposed via netlink on VFPR
netdevs.
- Patch 7 adds support to get switch id and port number for VFPR netdevs.
v4:
- Make VFPR ndo_get_stats64 a void function to match with recent upstream
change.
v3:
- misc. error handling fixes suggested by Scott Peterson
- introduce switchdev_ops and add support to get switch id and port no.
for VFPR netdevs. Suggested by Or Gerlitz
v2:
- handle i40e_alloc_vfpr_netdev() failures.
- minor comment/commit msg updates.
Jakub Kicinski (1):
net: store port/representator id in metadata_dst
Sridhar Samudrala (6):
i40e: Introduce devlink interface.
i40e: Introduce VF Port Representator(VFPR) netdevs.
i40e: Sync link state between VFs and VFPRs
i40e: Add TX and RX support in switchdev mode.
i40e: Add support for exposing VF port statistics via VFPR netdev on
the host.
i40e: Add support to get switch id and port number for VFPR netdevs
drivers/net/ethernet/intel/Kconfig | 1 +
drivers/net/ethernet/intel/i40e/i40e.h | 5 +
drivers/net/ethernet/intel/i40e/i40e_main.c | 131 +++++++-
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 146 +++++++-
drivers/net/ethernet/intel/i40e/i40e_txrx.h | 2 +
drivers/net/ethernet/intel/i40e/i40e_type.h | 3 +
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 368 ++++++++++++++++++++-
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h | 25 ++
include/net/dst_metadata.h | 41 ++-
net/core/dst.c | 15 +-
net/core/filter.c | 1 +
net/ipv4/ip_tunnel_core.c | 6 +-
net/openvswitch/flow_netlink.c | 4 +-
13 files changed, 713 insertions(+), 35 deletions(-)
--
2.5.5
^ permalink raw reply
* [next-queue v4 PATCH 1/7] i40e: Introduce devlink interface.
From: Sridhar Samudrala @ 2017-01-12 22:35 UTC (permalink / raw)
To: alexander.h.duyck, john.r.fastabend, anjali.singhai,
jakub.kicinski, davem, scott.d.peterson, gerlitz.or, jiri,
intel-wired-lan, netdev
In-Reply-To: <1484260510-9162-1-git-send-email-sridhar.samudrala@intel.com>
Add initial devlink support to get/set the mode of SRIOV switch.
This patch sets the default mode as 'legacy' and enables getting the mode
and and setting it to 'legacy'.
The switch mode can be get/set via following 'devlink' commands.
# devlink dev eswitch show pci/0000:05:00.0
pci/0000:05:00.0: mode legacy
# devlink dev eswitch set pci/0000:05:00.0 mode switchdev
devlink answers: Operation not supported
# devlink dev eswitch set pci/0000:05:00.0 mode legacy
# devlink dev eswitch show pci/0000:05:00.0
pci/0000:05:00.0: mode legacy
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
drivers/net/ethernet/intel/Kconfig | 1 +
drivers/net/ethernet/intel/i40e/i40e.h | 3 ++
drivers/net/ethernet/intel/i40e/i40e_main.c | 80 ++++++++++++++++++++++++++---
3 files changed, 76 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 1349b45..0dbb87e 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -215,6 +215,7 @@ config I40E
tristate "Intel(R) Ethernet Controller XL710 Family support"
imply PTP_1588_CLOCK
depends on PCI
+ depends on MAY_USE_DEVLINK
---help---
This driver supports Intel(R) Ethernet Controller XL710 Family of
devices. For more information on how to identify your adapter, go
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 9b51026..331a1e0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -54,6 +54,8 @@
#include <linux/clocksource.h>
#include <linux/net_tstamp.h>
#include <linux/ptp_clock_kernel.h>
+#include <net/devlink.h>
+
#include "i40e_type.h"
#include "i40e_prototype.h"
#ifdef I40E_FCOE
@@ -476,6 +478,7 @@ struct i40e_pf {
u32 ioremap_len;
u32 fd_inv;
u16 phy_led_val;
+ enum devlink_eswitch_mode eswitch_mode;
};
/**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b685b55..ac49f89 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11294,6 +11294,57 @@ static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf)
}
/**
+ * i40e_devlink_eswitch_mode_get
+ *
+ * @devlink: pointer to devlink struct
+ * @mode: sr-iov switch mode pointer
+ *
+ * Returns the switch mode of the associated PF in the @mode pointer.
+ */
+static int i40e_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+ struct i40e_pf *pf = devlink_priv(devlink);
+
+ *mode = pf->eswitch_mode;
+
+ return 0;
+}
+
+/**
+ * i40e_devlink_eswitch_mode_set
+ *
+ * @devlink: pointer to devlink struct
+ * @mode: sr-iov switch mode
+ *
+ * Set the switch mode of the associated PF.
+ * Returns 0 on success and -EOPNOTSUPP on error.
+ */
+static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
+{
+ struct i40e_pf *pf = devlink_priv(devlink);
+ int err = 0;
+
+ if (mode == pf->eswitch_mode)
+ goto done;
+
+ switch (mode) {
+ case DEVLINK_ESWITCH_MODE_LEGACY:
+ pf->eswitch_mode = mode;
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ break;
+ }
+done:
+ return err;
+}
+
+static const struct devlink_ops i40e_devlink_ops = {
+ .eswitch_mode_get = i40e_devlink_eswitch_mode_get,
+ .eswitch_mode_set = i40e_devlink_eswitch_mode_set,
+};
+
+/**
* i40e_probe - Device initialization routine
* @pdev: PCI device information struct
* @ent: entry in i40e_pci_tbl
@@ -11310,6 +11361,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
struct i40e_pf *pf;
struct i40e_hw *hw;
static u16 pfs_found;
+ struct devlink *devlink;
u16 wol_nvm_bits;
u16 link_status;
int err;
@@ -11343,20 +11395,28 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
pci_enable_pcie_error_reporting(pdev);
pci_set_master(pdev);
+ devlink = devlink_alloc(&i40e_devlink_ops, sizeof(*pf));
+ if (!devlink) {
+ dev_err(&pdev->dev, "devlink_alloc failed\n");
+ err = -ENOMEM;
+ goto err_devlink_alloc;
+ }
+
/* Now that we have a PCI connection, we need to do the
* low level device setup. This is primarily setting up
* the Admin Queue structures and then querying for the
* device's current profile information.
*/
- pf = kzalloc(sizeof(*pf), GFP_KERNEL);
- if (!pf) {
- err = -ENOMEM;
- goto err_pf_alloc;
- }
+ pf = devlink_priv(devlink);
pf->next_vsi = 0;
pf->pdev = pdev;
set_bit(__I40E_DOWN, &pf->state);
+ pf->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+ err = devlink_register(devlink, &pdev->dev);
+ if (err)
+ goto err_devlink_register;
+
hw = &pf->hw;
hw->back = pf;
@@ -11830,8 +11890,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
err_pf_reset:
iounmap(hw->hw_addr);
err_ioremap:
- kfree(pf);
-err_pf_alloc:
+ devlink_unregister(devlink);
+err_devlink_register:
+ devlink_free(devlink);
+err_devlink_alloc:
pci_disable_pcie_error_reporting(pdev);
pci_release_mem_regions(pdev);
err_pci_reg:
@@ -11853,6 +11915,7 @@ static void i40e_remove(struct pci_dev *pdev)
{
struct i40e_pf *pf = pci_get_drvdata(pdev);
struct i40e_hw *hw = &pf->hw;
+ struct devlink *devlink = priv_to_devlink(pf);
i40e_status ret_code;
int i;
@@ -11941,7 +12004,8 @@ static void i40e_remove(struct pci_dev *pdev)
kfree(pf->vsi);
iounmap(hw->hw_addr);
- kfree(pf);
+ devlink_unregister(devlink);
+ devlink_free(devlink);
pci_release_mem_regions(pdev);
pci_disable_pcie_error_reporting(pdev);
--
2.5.5
^ permalink raw reply related
* [next-queue v4 PATCH 2/7] i40e: Introduce VF Port Representator(VFPR) netdevs.
From: Sridhar Samudrala @ 2017-01-12 22:35 UTC (permalink / raw)
To: alexander.h.duyck, john.r.fastabend, anjali.singhai,
jakub.kicinski, davem, scott.d.peterson, gerlitz.or, jiri,
intel-wired-lan, netdev
In-Reply-To: <1484260510-9162-1-git-send-email-sridhar.samudrala@intel.com>
VF Port Representator netdevs are created for each VF if the switch mode
is set to 'switchdev'. These netdevs can be used to control and configure
VFs from PFs namespace. They enable exposing VF statistics, configure and
monitor link state, mtu, filters, fdb/vlan entries etc. of VFs.
Broadcast filters are not enabled in switchdev mode.
VFPR netdevs inherit the mac address from the PF.
Sample script to create VF port representors
# rmmod i40e; modprobe i40e
# devlink dev eswitch set pci/0000:05:00.0 mode switchdev
# echo 2 > /sys/class/net/enp5s0f0/device/sriov_numvfs
# ip l show
297: enp5s0f0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop portid 6805ca2e7268 state DOWN mode DEFAULT group default qlen 1000
link/ether 68:05:ca:2e:72:68 brd ff:ff:ff:ff:ff:ff
vf 0 MAC 00:00:00:00:00:00, spoof checking on, link-state auto, trust off
vf 1 MAC 00:00:00:00:00:00, spoof checking on, link-state auto, trust off
299: enp5s0f0-vf0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000
link/ether 68:05:ca:2e:72:68 brd ff:ff:ff:ff:ff:ff
300: enp5s0f0-vf1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000
link/ether 68:05:ca:2e:72:68 brd ff:ff:ff:ff:ff:ff
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 21 ++-
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 153 ++++++++++++++++++++-
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h | 14 ++
3 files changed, 182 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index ac49f89..53a0618 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11322,13 +11322,32 @@ static int i40e_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
{
struct i40e_pf *pf = devlink_priv(devlink);
- int err = 0;
+ struct i40e_vf *vf;
+ int i, j, err = 0;
if (mode == pf->eswitch_mode)
goto done;
switch (mode) {
case DEVLINK_ESWITCH_MODE_LEGACY:
+ for (i = 0; i < pf->num_alloc_vfs; i++) {
+ vf = &pf->vf[i];
+ i40e_free_vfpr_netdev(vf);
+ }
+ pf->eswitch_mode = mode;
+ break;
+ case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+ for (i = 0; i < pf->num_alloc_vfs; i++) {
+ vf = &pf->vf[i];
+ err = i40e_alloc_vfpr_netdev(vf, i);
+ if (err) {
+ for (j = 0; j < i; j++) {
+ vf = &pf->vf[j];
+ i40e_free_vfpr_netdev(vf);
+ }
+ goto done;
+ }
+ }
pf->eswitch_mode = mode;
break;
default:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index cbbf864..f9927dc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -696,11 +696,15 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
"Could not add MAC filter %pM for VF %d\n",
vf->default_lan_addr.addr, vf->vf_id);
}
- eth_broadcast_addr(broadcast);
- f = i40e_add_mac_filter(vsi, broadcast);
- if (!f)
- dev_info(&pf->pdev->dev,
- "Could not allocate VF broadcast filter\n");
+
+ /* Add VF broadcast filter only in 'legacy' mode */
+ if (vsi->back->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY) {
+ eth_broadcast_addr(broadcast);
+ f = i40e_add_mac_filter(vsi, broadcast);
+ if (!f)
+ dev_info(&pf->pdev->dev,
+ "Could not allocate VF broadcast filter\n");
+ }
spin_unlock_bh(&vsi->mac_filter_hash_lock);
i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id),
(u32)hena);
@@ -1018,6 +1022,137 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
}
/**
+ * i40e_vfpr_netdev_open
+ * @dev: network interface device structure
+ *
+ * Called when vfpr netdevice is brought up.
+ **/
+static int i40e_vfpr_netdev_open(struct net_device *dev)
+{
+ return 0;
+}
+
+/**
+ * i40e_vfpr_netdev_stop
+ * @dev: network interface device structure
+ *
+ * Called when vfpr netdevice is brought down.
+ **/
+static int i40e_vfpr_netdev_stop(struct net_device *dev)
+{
+ return 0;
+}
+
+static const struct net_device_ops i40e_vfpr_netdev_ops = {
+ .ndo_open = i40e_vfpr_netdev_open,
+ .ndo_stop = i40e_vfpr_netdev_stop,
+};
+
+/**
+ * i40e_update_vf_broadcast_filter
+ * @vf: pointer to the VF structure
+ * @enable: boolean flag indicating add/delete
+ *
+ * add/delete VFs broadcast filter
+ **/
+void i40e_update_vf_broadcast_filter(struct i40e_vf *vf, bool enable)
+{
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx];
+ u8 broadcast[ETH_ALEN];
+ int err;
+
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+ eth_broadcast_addr(broadcast);
+ if (enable)
+ i40e_add_mac_filter(vsi, broadcast);
+ else
+ i40e_del_mac_filter(vsi, broadcast);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
+
+ /* update broadcast filter */
+ err = i40e_sync_vsi_filters(vsi);
+ if (err)
+ dev_err(&pf->pdev->dev, "Unable to program bcast filter\n");
+}
+
+/**
+ * i40e_alloc_vfpr_netdev
+ * @vf: pointer to the VF structure
+ * @vf_num: VF number
+ *
+ * Create VF Port representor netdev
+ **/
+int i40e_alloc_vfpr_netdev(struct i40e_vf *vf, u16 vf_num)
+{
+ struct net_device *vfpr_netdev;
+ char netdev_name[IFNAMSIZ];
+ struct i40e_vfpr_netdev_priv *priv;
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+ int err;
+
+ snprintf(netdev_name, IFNAMSIZ, "%s-vf%d", vsi->netdev->name, vf_num);
+ vfpr_netdev = alloc_netdev(sizeof(struct i40e_vfpr_netdev_priv),
+ netdev_name, NET_NAME_UNKNOWN, ether_setup);
+ if (!vfpr_netdev) {
+ dev_err(&pf->pdev->dev, "alloc_netdev failed for vf:%d\n",
+ vf_num);
+ return -ENOMEM;
+ }
+
+ pf->vf[vf_num].vfpr_netdev = vfpr_netdev;
+
+ priv = netdev_priv(vfpr_netdev);
+ priv->vf = &pf->vf[vf_num];
+
+ vfpr_netdev->netdev_ops = &i40e_vfpr_netdev_ops;
+ eth_hw_addr_inherit(vfpr_netdev, vsi->netdev);
+
+ netif_carrier_off(vfpr_netdev);
+ netif_tx_disable(vfpr_netdev);
+
+ err = register_netdev(vfpr_netdev);
+ if (err) {
+ dev_err(&pf->pdev->dev, "register_netdev failed for vf: %s\n",
+ vf->vfpr_netdev->name);
+ free_netdev(vfpr_netdev);
+ return err;
+ }
+
+ dev_info(&pf->pdev->dev, "VF Port representor(%s) created for VF %d\n",
+ vf->vfpr_netdev->name, vf_num);
+
+ /* Delete broadcast filter for VF */
+ i40e_update_vf_broadcast_filter(vf, false);
+
+ return 0;
+}
+
+/**
+ * i40e_free_vfpr_netdev
+ * @vf: pointer to the VF structure
+ *
+ * Free VF Port representor netdev
+ **/
+void i40e_free_vfpr_netdev(struct i40e_vf *vf)
+{
+ struct i40e_pf *pf = vf->pf;
+
+ if (!vf->vfpr_netdev)
+ return;
+
+ dev_info(&pf->pdev->dev, "Freeing VF Port representor(%s)\n",
+ vf->vfpr_netdev->name);
+
+ unregister_netdev(vf->vfpr_netdev);
+ free_netdev(vf->vfpr_netdev);
+
+ /* Add broadcast filter to VF */
+ i40e_update_vf_broadcast_filter(vf, true);
+}
+
+/**
* i40e_free_vfs
* @pf: pointer to the PF structure
*
@@ -1058,6 +1193,9 @@ void i40e_free_vfs(struct i40e_pf *pf)
i40e_free_vf_res(&pf->vf[i]);
/* disable qp mappings */
i40e_disable_vf_mappings(&pf->vf[i]);
+
+ if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+ i40e_free_vfpr_netdev(&pf->vf[i]);
}
kfree(pf->vf);
@@ -1125,6 +1263,11 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
/* VF resources get allocated during reset */
i40e_reset_vf(&vfs[i], false);
+ if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) {
+ ret = i40e_alloc_vfpr_netdev(&vfs[i], i);
+ if (ret)
+ goto err_alloc;
+ }
}
pf->num_alloc_vfs = num_alloc_vfs;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 4012d06..25ce93c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -72,10 +72,21 @@ enum i40e_vf_capabilities {
I40E_VIRTCHNL_VF_CAP_IWARP,
};
+/* VF Port representator netdev private structure */
+struct i40e_vfpr_netdev_priv {
+ struct i40e_vf *vf;
+};
+
/* VF information structure */
struct i40e_vf {
struct i40e_pf *pf;
+ /* VF Port representator netdev that allows control and configuration
+ * of VFs from the host. Enables returning VF stats, configuring link
+ * state, mtu, fdb/vlans etc.
+ */
+ struct net_device *vfpr_netdev;
+
/* VF id in the PF space */
s16 vf_id;
/* all VF vsis connect to the same parent */
@@ -142,4 +153,7 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable);
void i40e_vc_notify_link_state(struct i40e_pf *pf);
void i40e_vc_notify_reset(struct i40e_pf *pf);
+int i40e_alloc_vfpr_netdev(struct i40e_vf *vf, u16 vf_num);
+void i40e_free_vfpr_netdev(struct i40e_vf *vf);
+
#endif /* _I40E_VIRTCHNL_PF_H_ */
--
2.5.5
^ permalink raw reply related
* [next-queue v4 PATCH 3/7] i40e: Sync link state between VFs and VFPRs
From: Sridhar Samudrala @ 2017-01-12 22:35 UTC (permalink / raw)
To: alexander.h.duyck, john.r.fastabend, anjali.singhai,
jakub.kicinski, davem, scott.d.peterson, gerlitz.or, jiri,
intel-wired-lan, netdev
In-Reply-To: <1484260510-9162-1-git-send-email-sridhar.samudrala@intel.com>
This patch enables
- reflecting the link state of VFPR based on VF admin state & link state
of VF based on admin state of VFPR.
- bringing up/down the VFPR sends a notification to update VF link state.
- bringing up/down the VF will cause the link state update of VFPR.
- enable/disable VF link state via ndo_set_vf_link_state will update the
admin state of associated VFPR.
PF: enp5s0f0, VFs: enp5s2,enp5s2f1 VFPRs:enp5s0f0-vf0, enp5s0f0-vf1
# rmmod i40e; modprobe i40e
# devlink dev eswitch set pci/0000:05:00.0 mode switchdev
# echo 2 > /sys/class/net/enp5s0f0/device/sriov_numvfs
# ip link set enp5s2 up
# ip link set enp5s0f0-vf0 up
# ip link set enp5s0f0-vf1 up
/* enp5s2 UP -> enp5s0f0-vf0 CARRIER ON */
# ip link show enp5s0f0-vf0
215: enp5s0f0-vf0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel state UP mode DEFAULT group default qlen 1000
link/ether 68:05:ca:2e:72:68 brd ff:ff:ff:ff:ff:ff
/* enp5s0f0-vf0 UP -> enp5s2 CARRIER ON */
# ip link show enp5s2
218: enp5s2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000
link/ether ea:4d:60:bc:6f:85 brd ff:ff:ff:ff:ff:ff
/* enp5s2f1 DOWN -> enp5s0f0-vf1 NO-CARRIER */
# ip link show enp5s0f0-vf1
216: enp5s0f0-vf1: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc fq_codel state DOWN mode DEFAULT group default qlen 1000
link/ether 68:05:ca:2e:72:68 brd ff:ff:ff:ff:ff:ff
# ip link set enp5s0f0-vf0 down
# ip link set enp5s2f1 up
/* enp5s0-vf0 DOWN -> enp5s2 NO_CARRIER */
# ip link show enp5s2
218: enp5s2: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc mq state DOWN mode DEFAULT group default qlen 1000
link/ether ea:4d:60:bc:6f:85 brd ff:ff:ff:ff:ff:ff
# ip -d link show enp5s0f0
213: enp5s0f0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop portid 6805ca27268 state DOWN mode DEFAULT group default qlen 1000
link/ether 68:05:ca:2e:72:68 brd ff:ff:ff:ff:ff:ff promiscuity 0 addrgenmode eui64
vf 0 MAC 00:00:00:00:00:00, spoof checking on, link-state disable, trust off
vf 1 MAC 00:00:00:00:00:00, spoof checking on, link-state enable, trust off
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 54 ++++++++++++++++++++++
1 file changed, 54 insertions(+)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index f9927dc..275113c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1029,6 +1029,13 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
**/
static int i40e_vfpr_netdev_open(struct net_device *dev)
{
+ struct i40e_vfpr_netdev_priv *priv = netdev_priv(dev);
+ struct i40e_vf *vf = priv->vf;
+
+ vf->link_forced = true;
+ vf->link_up = true;
+ i40e_vc_notify_vf_link_state(vf);
+
return 0;
}
@@ -1040,6 +1047,13 @@ static int i40e_vfpr_netdev_open(struct net_device *dev)
**/
static int i40e_vfpr_netdev_stop(struct net_device *dev)
{
+ struct i40e_vfpr_netdev_priv *priv = netdev_priv(dev);
+ struct i40e_vf *vf = priv->vf;
+
+ vf->link_forced = true;
+ vf->link_up = false;
+ i40e_vc_notify_vf_link_state(vf);
+
return 0;
}
@@ -1126,6 +1140,13 @@ int i40e_alloc_vfpr_netdev(struct i40e_vf *vf, u16 vf_num)
/* Delete broadcast filter for VF */
i40e_update_vf_broadcast_filter(vf, false);
+ /* Reset VF link as we are changing the mode to 'switchdev'. VFPR netdev
+ * needs to be brought up to enable VF link.
+ */
+ vf->link_forced = true;
+ vf->link_up = false;
+ i40e_vc_notify_vf_link_state(vf);
+
return 0;
}
@@ -1150,6 +1171,10 @@ void i40e_free_vfpr_netdev(struct i40e_vf *vf)
/* Add broadcast filter to VF */
i40e_update_vf_broadcast_filter(vf, true);
+
+ /* In legacy mode, VF link is not controlled by VFPR */
+ vf->link_forced = false;
+ i40e_vc_notify_vf_link_state(vf);
}
/**
@@ -1907,8 +1932,17 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
goto error_param;
}
+ if (vf->link_forced && !vf->link_up) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx]))
aq_ret = I40E_ERR_TIMEOUT;
+
+ if ((aq_ret == 0) && vf->vfpr_netdev)
+ netif_carrier_on(vf->vfpr_netdev);
+
error_param:
/* send the response to the VF */
return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_ENABLE_QUEUES,
@@ -1946,8 +1980,16 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
goto error_param;
}
+ if (vf->link_forced && vf->link_up) {
+ aq_ret = I40E_ERR_PARAM;
+ goto error_param;
+ }
+
i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
+ if ((aq_ret == 0) && vf->vfpr_netdev)
+ netif_carrier_off(vf->vfpr_netdev);
+
error_param:
/* send the response to the VF */
return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_DISABLE_QUEUES,
@@ -3183,6 +3225,7 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_pf *pf = np->vsi->back;
struct i40e_virtchnl_pf_event pfe;
+ struct net_device *vfpr_netdev;
struct i40e_hw *hw = &pf->hw;
struct i40e_vf *vf;
int abs_vf_id;
@@ -3225,6 +3268,17 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
ret = -EINVAL;
goto error_out;
}
+
+ vfpr_netdev = vf->vfpr_netdev;
+ if (vfpr_netdev) {
+ unsigned int flags = vfpr_netdev->flags;
+
+ if (vf->link_up)
+ dev_change_flags(vfpr_netdev, flags | IFF_UP);
+ else
+ dev_change_flags(vfpr_netdev, flags & ~IFF_UP);
+ }
+
/* Notify the VF of its new link state */
i40e_aq_send_msg_to_vf(hw, abs_vf_id, I40E_VIRTCHNL_OP_EVENT,
0, (u8 *)&pfe, sizeof(pfe), NULL);
--
2.5.5
^ permalink raw reply related
* [next-queue v4 PATCH 4/7] net: store port/representator id in metadata_dst
From: Sridhar Samudrala @ 2017-01-12 22:35 UTC (permalink / raw)
To: alexander.h.duyck, john.r.fastabend, anjali.singhai,
jakub.kicinski, davem, scott.d.peterson, gerlitz.or, jiri,
intel-wired-lan, netdev
In-Reply-To: <1484260510-9162-1-git-send-email-sridhar.samudrala@intel.com>
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Switches and modern SR-IOV enabled NICs may multiplex traffic from Port
representators and control messages over single set of hardware queues.
Control messages and muxed traffic may need ordered delivery.
Those requirements make it hard to comfortably use TC infrastructure today
unless we have a way of attaching metadata to skbs at the upper device.
Because single set of queues is used for many netdevs stopping TC/sched queues
of all of them reliably is impossible and lower device has to retreat to
returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath.
This patch attempts to enable port/representative devs to attach metadata to
skbs which carry port id. This way representatives can be queueless and all
queuing can be performed at the lower netdev in the usual way.
Traffic arriving on the port/representative interfaces will be have metadata
attached and will subsequently be queued to the lower device for transmission.
The lower device should recognize the metadata and translate it to HW specific
format which is most likely either a special header inserted before the network
headers or descriptor/metadata fields.
Metadata is associated with the lower device by storing the netdev pointer along
with port id so that if TC decides to redirect or mirror the new netdev will not
try to interpret it.
This is mostly for SR-IOV devices since switches don't have lower netdevs today.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
include/net/dst_metadata.h | 41 ++++++++++++++++++++++++++++++++---------
net/core/dst.c | 15 ++++++++++-----
net/core/filter.c | 1 +
net/ipv4/ip_tunnel_core.c | 6 ++++--
net/openvswitch/flow_netlink.c | 4 +++-
5 files changed, 50 insertions(+), 17 deletions(-)
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 701fc81..a803129 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -5,10 +5,22 @@
#include <net/ip_tunnels.h>
#include <net/dst.h>
+enum metadata_type {
+ METADATA_IP_TUNNEL,
+ METADATA_HW_PORT_MUX,
+};
+
+struct hw_port_info {
+ struct net_device *lower_dev;
+ u32 port_id;
+};
+
struct metadata_dst {
struct dst_entry dst;
+ enum metadata_type type;
union {
struct ip_tunnel_info tun_info;
+ struct hw_port_info port_info;
} u;
};
@@ -27,7 +39,7 @@ static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb)
struct metadata_dst *md_dst = skb_metadata_dst(skb);
struct dst_entry *dst;
- if (md_dst)
+ if (md_dst && md_dst->type == METADATA_IP_TUNNEL)
return &md_dst->u.tun_info;
dst = skb_dst(skb);
@@ -55,22 +67,33 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a,
a = (const struct metadata_dst *) skb_dst(skb_a);
b = (const struct metadata_dst *) skb_dst(skb_b);
- if (!a != !b || a->u.tun_info.options_len != b->u.tun_info.options_len)
+ if (!a != !b || a->type != b->type)
return 1;
- return memcmp(&a->u.tun_info, &b->u.tun_info,
- sizeof(a->u.tun_info) + a->u.tun_info.options_len);
+ switch (a->type) {
+ case METADATA_HW_PORT_MUX:
+ return memcmp(&a->u.port_info, &b->u.port_info,
+ sizeof(a->u.port_info));
+ case METADATA_IP_TUNNEL:
+ return memcmp(&a->u.tun_info, &b->u.tun_info,
+ sizeof(a->u.tun_info) +
+ a->u.tun_info.options_len);
+ default:
+ return 1;
+ }
}
void metadata_dst_free(struct metadata_dst *);
-struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
-struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags);
+struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type,
+ gfp_t flags);
+struct metadata_dst __percpu *
+metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags);
static inline struct metadata_dst *tun_rx_dst(int md_size)
{
struct metadata_dst *tun_dst;
- tun_dst = metadata_dst_alloc(md_size, GFP_ATOMIC);
+ tun_dst = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC);
if (!tun_dst)
return NULL;
@@ -85,11 +108,11 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb)
int md_size;
struct metadata_dst *new_md;
- if (!md_dst)
+ if (!md_dst || md_dst->type != METADATA_IP_TUNNEL)
return ERR_PTR(-EINVAL);
md_size = md_dst->u.tun_info.options_len;
- new_md = metadata_dst_alloc(md_size, GFP_ATOMIC);
+ new_md = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC);
if (!new_md)
return ERR_PTR(-ENOMEM);
diff --git a/net/core/dst.c b/net/core/dst.c
index b5cbbe0..62dd4e4 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -367,7 +367,9 @@ static int dst_md_discard(struct sk_buff *skb)
return 0;
}
-static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen)
+static void __metadata_dst_init(struct metadata_dst *md_dst,
+ enum metadata_type type, u8 optslen)
+
{
struct dst_entry *dst;
@@ -379,9 +381,11 @@ static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen)
dst->output = dst_md_discard_out;
memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
+ md_dst->type = type;
}
-struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags)
+struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type,
+ gfp_t flags)
{
struct metadata_dst *md_dst;
@@ -389,7 +393,7 @@ struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags)
if (!md_dst)
return NULL;
- __metadata_dst_init(md_dst, optslen);
+ __metadata_dst_init(md_dst, type, optslen);
return md_dst;
}
@@ -403,7 +407,8 @@ void metadata_dst_free(struct metadata_dst *md_dst)
kfree(md_dst);
}
-struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags)
+struct metadata_dst __percpu *
+metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags)
{
int cpu;
struct metadata_dst __percpu *md_dst;
@@ -414,7 +419,7 @@ struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags)
return NULL;
for_each_possible_cpu(cpu)
- __metadata_dst_init(per_cpu_ptr(md_dst, cpu), optslen);
+ __metadata_dst_init(per_cpu_ptr(md_dst, cpu), type, optslen);
return md_dst;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 1969b3f..617ca0c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2521,6 +2521,7 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which)
* that is holding verifier mutex.
*/
md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX,
+ METADATA_IP_TUNNEL,
GFP_KERNEL);
if (!md_dst)
return NULL;
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 5476110..4544b35 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -134,10 +134,12 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
struct metadata_dst *res;
struct ip_tunnel_info *dst, *src;
- if (!md || md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
+ if (!md || md->type != METADATA_IP_TUNNEL ||
+ md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
+
return NULL;
- res = metadata_dst_alloc(0, flags);
+ res = metadata_dst_alloc(0, METADATA_IP_TUNNEL, flags);
if (!res)
return NULL;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index c87d359..164b4f1 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2105,7 +2105,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
if (start < 0)
return start;
- tun_dst = metadata_dst_alloc(key.tun_opts_len, GFP_KERNEL);
+ tun_dst = metadata_dst_alloc(key.tun_opts_len, METADATA_IP_TUNNEL,
+ GFP_KERNEL);
+
if (!tun_dst)
return -ENOMEM;
--
2.5.5
^ permalink raw reply related
* [next-queue v4 PATCH 5/7] i40e: Add TX and RX support in switchdev mode.
From: Sridhar Samudrala @ 2017-01-12 22:35 UTC (permalink / raw)
To: alexander.h.duyck, john.r.fastabend, anjali.singhai,
jakub.kicinski, davem, scott.d.peterson, gerlitz.or, jiri,
intel-wired-lan, netdev
In-Reply-To: <1484260510-9162-1-git-send-email-sridhar.samudrala@intel.com>
In switchdev mode, broadcast filter is not enabled on VFs. The broadcasts
and unknown frames from VFs are received by the PF and passed to
corresponding VF port representator netdev.
A host based switching entity like a linux bridge or OVS redirects these
frames to the right VFs via VFPR netdevs. Any frames sent via VFPR netdevs
are sent as directed transmits to the corresponding VFs. To enable directed
transmit, skb metadata dst is used to pass the VF id and the frame is
requeued to call the PFs transmit routine.
Small script to demonstrate inter VF pings in switchdev mode.
PF: enp5s0f0, VFs: enp5s2,enp5s2f1 VFPRs:enp5s0f0-vf0, enp5s0f0-vf1
# rmmod i40e; modprobe i40e
# devlink dev eswitch set pci/0000:05:00.0 mode switchdev
# echo 2 > /sys/class/net/enp5s0f0/device/sriov_numvfs
# ip link set enp5s0f0 vf 0 mac 00:11:22:33:44:55
# ip link set enp5s0f0 vf 1 mac 00:11:22:33:44:56
# rmmod i40evf; modprobe i40evf
/* Create 2 namespaces and move the VFs to the corresponding ns. */
# ip netns add ns0
# ip link set enp5s2 netns ns0
# ip netns exec ns0 ip addr add 192.168.1.10/24 dev enp5s2
# ip netns exec ns0 ip link set enp5s2 up
# ip netns add ns1
# ip link set enp5s2f1 netns ns1
# ip netns exec ns1 ip addr add 192.168.1.11/24 dev enp5s2f1
# ip netns exec ns1 ip link set enp5s2f1 up
/* bring up pf and vfpr netdevs */
# ip link set enp5s0f0 up
# ip link set enp5s0f0-vf0 up
# ip link set enp5s0f0-vf1 up
/* Create a linux bridge and add vfpr netdevs to it. */
# ip link add vfpr-br type bridge
# ip link set enp5s0f0-vf0 master vfpr-br
# ip link set enp5s0f0-vf1 master vfpr-br
# ip addr add 192.168.1.1/24 dev vfpr-br
# ip link set vfpr-br up
# ip netns exec ns0 ping -c3 192.168.1.11
# ip netns exec ns1 ping -c3 192.168.1.10
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e.h | 1 +
drivers/net/ethernet/intel/i40e/i40e_main.c | 4 +
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 106 ++++++++++++++++++++-
drivers/net/ethernet/intel/i40e/i40e_txrx.h | 2 +
drivers/net/ethernet/intel/i40e/i40e_type.h | 3 +
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 17 +++-
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h | 1 +
7 files changed, 127 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 331a1e0..95cfe46 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -55,6 +55,7 @@
#include <linux/net_tstamp.h>
#include <linux/ptp_clock_kernel.h>
#include <net/devlink.h>
+#include <net/dst_metadata.h>
#include "i40e_type.h"
#include "i40e_prototype.h"
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 53a0618..9212656 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11322,6 +11322,7 @@ static int i40e_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
{
struct i40e_pf *pf = devlink_priv(devlink);
+ struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
struct i40e_vf *vf;
int i, j, err = 0;
@@ -11335,6 +11336,8 @@ static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
i40e_free_vfpr_netdev(vf);
}
pf->eswitch_mode = mode;
+ vsi->netdev->priv_flags |=
+ (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM);
break;
case DEVLINK_ESWITCH_MODE_SWITCHDEV:
for (i = 0; i < pf->num_alloc_vfs; i++) {
@@ -11349,6 +11352,7 @@ static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
}
}
pf->eswitch_mode = mode;
+ netif_keep_dst(vsi->netdev);
break;
default:
err = -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 0291ed4..f43d1df 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1283,16 +1283,39 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
* @rx_ring: rx ring in play
* @skb: packet to send up
* @vlan_tag: vlan tag for packet
+ * @lpbk: is it a loopback frame?
**/
static void i40e_receive_skb(struct i40e_ring *rx_ring,
- struct sk_buff *skb, u16 vlan_tag)
+ struct sk_buff *skb, u16 vlan_tag, bool lpbk)
{
struct i40e_q_vector *q_vector = rx_ring->q_vector;
+ struct i40e_pf *pf = rx_ring->vsi->back;
+ struct i40e_vf *vf;
+ struct ethhdr *eth;
+ int vf_id;
if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
(vlan_tag & VLAN_VID_MASK))
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
+ if ((pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY) || !lpbk)
+ goto gro_receive;
+
+ /* If a loopback packet is received from a VF in switchdev mode, pass
+ * the frame to the corresponding VFPR netdev based on the source MAC
+ * in the frame.
+ */
+ eth = (struct ethhdr *)skb_mac_header(skb);
+ for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) {
+ vf = &pf->vf[vf_id];
+ if (ether_addr_equal(eth->h_source,
+ vf->default_lan_addr.addr)) {
+ skb->dev = vf->vfpr_netdev;
+ break;
+ }
+ }
+
+gro_receive:
napi_gro_receive(&q_vector->napi, skb);
}
@@ -1501,6 +1524,7 @@ static inline void i40e_rx_hash(struct i40e_ring *ring,
* @rx_desc: pointer to the EOP Rx descriptor
* @skb: pointer to current skb being populated
* @rx_ptype: the packet type decoded by hardware
+ * @lpbk: is it a loopback frame?
*
* This function checks the ring, descriptor, and packet information in
* order to populate the hash, checksum, VLAN, protocol, and
@@ -1509,7 +1533,7 @@ static inline void i40e_rx_hash(struct i40e_ring *ring,
static inline
void i40e_process_skb_fields(struct i40e_ring *rx_ring,
union i40e_rx_desc *rx_desc, struct sk_buff *skb,
- u8 rx_ptype)
+ u8 rx_ptype, bool *lpbk)
{
u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
u32 rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>
@@ -1518,6 +1542,9 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring,
u32 tsyn = (rx_status & I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >>
I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT;
+ *lpbk = !!((rx_status & I40E_RXD_QW1_STATUS_LPBK_MASK) >>
+ I40E_RXD_QW1_STATUS_LPBK_SHIFT);
+
if (unlikely(tsynvalid))
i40e_ptp_rx_hwtstamp(rx_ring->vsi->back, skb, tsyn);
@@ -2045,6 +2072,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
u8 rx_ptype;
u64 qword;
unsigned int xdp_consumed_bytes = 0;
+ bool lpbk;
/* return some buffers to hardware, one at a time is too slow */
if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
@@ -2113,7 +2141,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
I40E_RXD_QW1_PTYPE_SHIFT;
/* populate checksum, VLAN, and protocol */
- i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
+ i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype, &lpbk);
#ifdef I40E_FCOE
if (unlikely(
@@ -2127,7 +2155,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0;
- i40e_receive_skb(rx_ring, skb, vlan_tag);
+ i40e_receive_skb(rx_ring, skb, vlan_tag, lpbk);
skb = NULL;
/* update budget accounting */
@@ -2692,6 +2720,27 @@ static int i40e_tso(struct i40e_tx_buffer *first, u8 *hdr_len,
}
/**
+ * i40e_tvsi - set up the target vsi in TX context descriptor
+ * @tx_ring: ptr to the target vsi
+ * @cd_type_cmd_tso_mss: Quad Word 1
+ *
+ * Returns 0
+ **/
+static int i40e_tvsi(struct i40e_vsi *tvsi, u64 *cd_type_cmd_tso_mss)
+{
+ u64 cd_cmd, cd_tvsi;
+
+ cd_cmd = I40E_TX_CTX_DESC_SWTCH_VSI;
+ cd_tvsi = tvsi->id;
+ cd_tvsi = (cd_tvsi << I40E_TXD_CTX_QW1_VSI_SHIFT) &
+ I40E_TXD_CTX_QW1_VSI_MASK;
+ *cd_type_cmd_tso_mss |= (cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) |
+ cd_tvsi;
+
+ return 0;
+}
+
+/**
* i40e_tsyn - set up the tsyn context descriptor
* @tx_ring: ptr to the ring to send
* @skb: ptr to the skb we're sending
@@ -3223,8 +3272,12 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
struct i40e_ring *tx_ring)
{
u64 cd_type_cmd_tso_mss = I40E_TX_DESC_DTYPE_CONTEXT;
+ struct metadata_dst *md_dst = skb_metadata_dst(skb);
u32 cd_tunneling = 0, cd_l2tag2 = 0;
struct i40e_tx_buffer *first;
+ struct i40e_vsi *t_vsi = NULL;
+ struct i40e_vf *t_vf;
+ struct i40e_pf *pf;
u32 td_offset = 0;
u32 tx_flags = 0;
__be16 protocol;
@@ -3276,7 +3329,26 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
else if (protocol == htons(ETH_P_IPV6))
tx_flags |= I40E_TX_FLAGS_IPV6;
- tso = i40e_tso(first, &hdr_len, &cd_type_cmd_tso_mss);
+ /* If skb metadata dst points to a VF id, do a directed transmit to
+ * that VSI. TSO is mutually exclusive with this option. So TSO is not
+ * enabled when doing a directed transmit.
+ */
+ if (md_dst && (md_dst->type == METADATA_HW_PORT_MUX)) {
+ pf = tx_ring->vsi->back;
+ if (md_dst->u.port_info.port_id >= pf->num_alloc_vfs) {
+ WARN_ONCE(1, "Unexpected port_id: %d num_vfs:%d\n",
+ md_dst->u.port_info.port_id,
+ pf->num_alloc_vfs);
+ goto out_drop;
+ }
+ t_vf = &pf->vf[md_dst->u.port_info.port_id];
+ t_vsi = pf->vsi[t_vf->lan_vsi_idx];
+ }
+
+ if (t_vsi)
+ tso = i40e_tvsi(t_vsi, &cd_type_cmd_tso_mss);
+ else
+ tso = i40e_tso(first, &hdr_len, &cd_type_cmd_tso_mss);
if (tso < 0)
goto out_drop;
@@ -3340,3 +3412,27 @@ netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
return i40e_xmit_frame_ring(skb, tx_ring);
}
+
+/**
+ * i40e_vfpr_netdev_start_xmit
+ * @skb: send buffer
+ * @netdev: network interface device structure
+ *
+ * Sets skb->dev to PF netdev, VF id in the skb->dst and requeues
+ * skb via dev_queue_xmit()
+ **/
+netdev_tx_t i40e_vfpr_netdev_start_xmit(struct sk_buff *skb,
+ struct net_device *netdev)
+{
+ struct i40e_vfpr_netdev_priv *priv = netdev_priv(netdev);
+ struct i40e_vf *vf = priv->vf;
+ struct i40e_pf *pf = vf->pf;
+ struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+
+ skb_dst_drop(skb);
+ dst_hold(&priv->vfpr_dst->dst);
+ skb_dst_set(skb, &priv->vfpr_dst->dst);
+ skb->dev = vsi->netdev;
+
+ return dev_queue_xmit(skb);
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 3250be7..5e24aef 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -393,6 +393,8 @@ struct i40e_ring_container {
bool i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
+netdev_tx_t i40e_vfpr_netdev_start_xmit(struct sk_buff *skb,
+ struct net_device *netdev);
void i40e_clean_tx_ring(struct i40e_ring *tx_ring);
void i40e_clean_rx_ring(struct i40e_ring *rx_ring);
int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 939f9fd..251f57e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -729,6 +729,9 @@ enum i40e_rx_desc_status_bits {
#define I40E_RXD_QW1_STATUS_TSYNVALID_SHIFT I40E_RX_DESC_STATUS_TSYNVALID_SHIFT
#define I40E_RXD_QW1_STATUS_TSYNVALID_MASK \
BIT_ULL(I40E_RXD_QW1_STATUS_TSYNVALID_SHIFT)
+#define I40E_RXD_QW1_STATUS_LPBK_SHIFT I40E_RX_DESC_STATUS_LPBK_SHIFT
+#define I40E_RXD_QW1_STATUS_LPBK_MASK \
+ BIT_ULL(I40E_RXD_QW1_STATUS_LPBK_SHIFT)
enum i40e_rx_desc_fltstat_values {
I40E_RX_DESC_FLTSTAT_NO_DATA = 0,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 275113c..7211fba 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1060,6 +1060,7 @@ static int i40e_vfpr_netdev_stop(struct net_device *dev)
static const struct net_device_ops i40e_vfpr_netdev_ops = {
.ndo_open = i40e_vfpr_netdev_open,
.ndo_stop = i40e_vfpr_netdev_stop,
+ .ndo_start_xmit = i40e_vfpr_netdev_start_xmit,
};
/**
@@ -1119,6 +1120,10 @@ int i40e_alloc_vfpr_netdev(struct i40e_vf *vf, u16 vf_num)
priv = netdev_priv(vfpr_netdev);
priv->vf = &pf->vf[vf_num];
+ priv->vfpr_dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
+ GFP_KERNEL);
+ priv->vfpr_dst->u.port_info.lower_dev = vsi->netdev;
+ priv->vfpr_dst->u.port_info.port_id = vf->vf_id;
vfpr_netdev->netdev_ops = &i40e_vfpr_netdev_ops;
eth_hw_addr_inherit(vfpr_netdev, vsi->netdev);
@@ -1130,6 +1135,7 @@ int i40e_alloc_vfpr_netdev(struct i40e_vf *vf, u16 vf_num)
if (err) {
dev_err(&pf->pdev->dev, "register_netdev failed for vf: %s\n",
vf->vfpr_netdev->name);
+ dst_release((struct dst_entry *)priv->vfpr_dst);
free_netdev(vfpr_netdev);
return err;
}
@@ -1158,6 +1164,7 @@ int i40e_alloc_vfpr_netdev(struct i40e_vf *vf, u16 vf_num)
**/
void i40e_free_vfpr_netdev(struct i40e_vf *vf)
{
+ struct i40e_vfpr_netdev_priv *priv;
struct i40e_pf *pf = vf->pf;
if (!vf->vfpr_netdev)
@@ -1166,6 +1173,8 @@ void i40e_free_vfpr_netdev(struct i40e_vf *vf)
dev_info(&pf->pdev->dev, "Freeing VF Port representor(%s)\n",
vf->vfpr_netdev->name);
+ priv = netdev_priv(vf->vfpr_netdev);
+ dst_release((struct dst_entry *)priv->vfpr_dst);
unregister_netdev(vf->vfpr_netdev);
free_netdev(vf->vfpr_netdev);
@@ -1940,8 +1949,10 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx]))
aq_ret = I40E_ERR_TIMEOUT;
- if ((aq_ret == 0) && vf->vfpr_netdev)
+ if ((aq_ret == 0) && vf->vfpr_netdev) {
+ netif_tx_start_all_queues(vf->vfpr_netdev);
netif_carrier_on(vf->vfpr_netdev);
+ }
error_param:
/* send the response to the VF */
@@ -1987,8 +1998,10 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
- if ((aq_ret == 0) && vf->vfpr_netdev)
+ if ((aq_ret == 0) && vf->vfpr_netdev) {
+ netif_tx_stop_all_queues(vf->vfpr_netdev);
netif_carrier_off(vf->vfpr_netdev);
+ }
error_param:
/* send the response to the VF */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 25ce93c..3dea207 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -74,6 +74,7 @@ enum i40e_vf_capabilities {
/* VF Port representator netdev private structure */
struct i40e_vfpr_netdev_priv {
+ struct metadata_dst *vfpr_dst;
struct i40e_vf *vf;
};
--
2.5.5
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox