* Re: [net PATCH v2 0/5] virtio_net XDP fixes and adjust_header support
From: John Fastabend @ 2017-01-13 2:54 UTC (permalink / raw)
To: jasowang, mst; +Cc: john.r.fastabend, netdev, alexei.starovoitov, daniel
In-Reply-To: <20170113003412.4167.12250.stgit@john-Precision-Tower-5810>
On 17-01-12 04:34 PM, John Fastabend wrote:
> 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.
>
>
> v2: fix spelling error, convert unsigned -> unsigned int
>
> ---
Sorry about the v2 here I got a connection reset by peer error from
git and it seems only 2/5 patches made it to the list. To avoid as much
confusion as possible I just sent a v3 and it seems to have completed
correctly.
Thanks,
John
^ permalink raw reply
* [net PATCH v3 5/5] virtio_net: XDP support for adjust_head
From: John Fastabend @ 2017-01-13 2:52 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170113024908.4535.8835.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
* [net PATCH v3 4/5] virtio_net: remove duplicate queue pair binding in XDP
From: John Fastabend @ 2017-01-13 2:51 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170113024908.4535.8835.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 v3 3/5] virtio_net: factor out xdp handler for readability
From: John Fastabend @ 2017-01-13 2:51 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170113024908.4535.8835.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 v3 2/5] net: virtio: wrap rtnl_lock in test for calling with lock already held
From: John Fastabend @ 2017-01-13 2:51 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170113024908.4535.8835.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 v3 1/5] virtio_net: use dev_kfree_skb for small buffer XDP receive
From: John Fastabend @ 2017-01-13 2:50 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170113024908.4535.8835.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 v3 0/5] virtio_net XDP fixes and adjust_header support
From: John Fastabend @ 2017-01-13 2:50 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.
v2: fix spelling error, convert unsigned -> unsigned int
v3: v2 git crashed during send so retrying sorry for the noise
---
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
* Re: [PATCH net-next v2 00/10] net: dsa: Support for pdata in dsa2
From: Vivien Didelot @ 2017-01-13 2:34 UTC (permalink / raw)
To: Florian Fainelli, netdev
Cc: Florian Fainelli, Jason Cooper, Andrew Lunn,
Sebastian Hesselbarth, Gregory Clement, Russell King,
David S. Miller, moderated list:ARM SUB-ARCHITECTURES, open list,
gregkh
In-Reply-To: <20170112034121.27697-1-f.fainelli@gmail.com>
Hi Florian,
Florian Fainelli <f.fainelli@gmail.com> writes:
> Hi all,
>
> This is not exactly new, and was sent before, although back then, I did not
> have an user of the pre-declared MDIO board information, but now we do. Note
> that I have additional changes queued up to have b53 register platform data for
> MIPS bcm47xx and bcm63xx.
>
> Yes I know that we should have the Orion platforms eventually be converted to
> Device Tree, but until that happens, I don't want any remaining users of the
> old "dsa" platform device (hence the previous DTS submissions for ARM/mvebu)
> and, there will be platforms out there that most likely won't never see DT
> coming their way (BCM47xx is almost 100% sure, BCM63xx maybe not in a distant
> future).
>
> We would probably want the whole series to be merged via David Miller's tree
> to simplify things.
>
> Greg, can you Ack/Nack patch 5 since it touched the core LDD?
>
> Thanks!
I've tested this patchset on my mv88e6xxx (DTS) boards to make sure
nothing was broken, since it touches the driver. Looks good!
Tested-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Thanks,
Vivien
^ permalink raw reply
* Re: [PATCH iproute2] Add support for rt_protos.d
From: David Ahern @ 2017-01-13 2:11 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev
In-Reply-To: <20170112172706.4832fb67@xeon-e3>
On 1/12/17 6:27 PM, Stephen Hemminger wrote:
>> diff --git a/etc/iproute2/rt_protos.d/README b/etc/iproute2/rt_protos.d/README
>> new file mode 100644
>> index 000000000000..723509ce56b6
>> --- /dev/null
>> +++ b/etc/iproute2/rt_protos.d/README
>> @@ -0,0 +1,3 @@
>> +Each file in this directory is an rt_protos configuration file. iproute2
>> +commands scan this directory processing all files that end in '.conf'.
>> +
>
> Applied, but required manual fixup.
>
>
> .git/rebase-apply/patch:15: new blank line at EOF.
> +
> warning: 1 line adds whitespace errors.
>
yes, i noticed that when I applied the patch to our local repo. It's a copy of the rt_tables.d patch and that README has the extra newline too.
^ permalink raw reply
* Re: [PATCH] i40e: Invoke softirqs after napi_reschedule
From: Benjamin Poirier @ 2017-01-13 1:51 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Jeff Kirsher, intel-wired-lan, netdev
In-Reply-To: <1484270130.13165.15.camel@edumazet-glaptop3.roam.corp.google.com>
On 2017/01/12 17:15, Eric Dumazet wrote:
> On Thu, 2017-01-12 at 17:04 -0800, Benjamin Poirier wrote:
> > The following message is logged from time to time when using i40e:
> > NOHZ: local_softirq_pending 08
> >
> > i40e may schedule napi from a workqueue. Afterwards, softirqs are not run
> > in a deterministic time frame. The problem is the same as what was
> > described in commit ec13ee80145c ("virtio_net: invoke softirqs after
> > __napi_schedule") and this patch applies the same fix to i40e.
>
> Yes, I believe mlx4 has a similar problem in mlx4_en_recover_from_oom()
Indeed, I was going to send a patch for mlx4 after this one is accepted.
^ permalink raw reply
* Re: [PATCH iproute2/net-next 0/2] net/sched: cls_flower: Support matching ARP
From: Stephen Hemminger @ 2017-01-13 1:47 UTC (permalink / raw)
To: Simon Horman; +Cc: Dinan Gunawardena, netdev
In-Reply-To: <1484208719-1581-1-git-send-email-simon.horman@netronome.com>
On Thu, 12 Jan 2017 09:11:57 +0100
Simon Horman <simon.horman@netronome.com> wrote:
> Add support for support matching on ARP operation, and hardware and
> protocol addresses for Ethernet hardware and IPv4 protocol addresses.
>
> Changes since RFC:
> * Drop RFC designation; kernel patches are present in net-next
>
> Simon Horman (2):
> tc: flower: update headers for TCA_FLOWER_KEY_ARP*
> tc: flower: Support matching ARP
>
> include/linux/pkt_cls.h | 11 +++
> man/man8/tc-flower.8 | 41 +++++++++-
> tc/f_flower.c | 208 ++++++++++++++++++++++++++++++++++++++++++++----
> 3 files changed, 243 insertions(+), 17 deletions(-)
>
Applied to net-next
^ permalink raw reply
* Re: [PATCH iproute2 v4 3/4] ifstat: Add 64 bits based stats to extended statistics
From: Stephen Hemminger @ 2017-01-13 1:43 UTC (permalink / raw)
To: Nogah Frankel
Cc: netdev, roszenrami, roopa, jiri, idosch, eladr, yotamg, ogerlitz
In-Reply-To: <1484228991-32999-4-git-send-email-nogahf@mellanox.com>
On Thu, 12 Jan 2017 15:49:50 +0200
Nogah Frankel <nogahf@mellanox.com> wrote:
> The default stats for ifstat are 32 bits based.
> The kernel supports 64 bits based stats. (They are returned in struct
> rtnl_link_stats64 which is an exact copy of struct rtnl_link_stats, in
> which the "normal" stats are returned, but with fields of u64 instead of
> u32). This patch adds them as an extended stats.
>
> It is read with filter type IFLA_STATS_LINK_64 and no sub type.
>
> It is under the name 64bits
> (or any shorten of it as "64")
>
> For example:
> ifstat -x 64bit
>
> Signed-off-by: Nogah Frankel <nogahf@mellanox.com>
> Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Other commands (like ip link) always use the 64 bit statistics if available
from the device. I see no reason that ifstat needs to be different.
^ permalink raw reply
* Re: [PATCH iproute2] bridge: fdb: add state filter support
From: Stephen Hemminger @ 2017-01-13 1:39 UTC (permalink / raw)
To: Nikolay Aleksandrov; +Cc: netdev, roopa, purna
In-Reply-To: <1484239659-16565-1-git-send-email-nikolay@cumulusnetworks.com>
On Thu, 12 Jan 2017 17:47:39 +0100
Nikolay Aleksandrov <nikolay@cumulusnetworks.com> wrote:
> This patch adds a new argument to the bridge fdb show command that allows
> to filter by entry state.
> Also update the man page to include all available show arguments.
>
> Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
> ---
Applied. Extra thanks for remembering to update man page.
^ permalink raw reply
* Re: [PATCH iproute2] rttable: Fix invalid range checking when table id is converted to u32
From: Stephen Hemminger @ 2017-01-13 1:36 UTC (permalink / raw)
To: David Ahern; +Cc: netdev, frank.kellermann
In-Reply-To: <1484091235-17749-1-git-send-email-dsa@cumulusnetworks.com>
On Tue, 10 Jan 2017 15:33:55 -0800
David Ahern <dsa@cumulusnetworks.com> wrote:
> Frank reported that table ids for very large numbers are not properly
> detected:
> $ ip li add foobar type vrf table 98765432100123456789
>
> command succeeds and resulting table id is actually:
>
> 21: foobar: <NOARP,MASTER> mtu 65536 qdisc noop state DOWN mode DEFAULT group default qlen 1000
> link/ether da:ea:d4:77:38:2a brd ff:ff:ff:ff:ff:ff promiscuity 0
> vrf table 4294967295 addrgenmode eui64 numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
>
> Make the temp variable 'i' unsigned long and let the typecast to u32
> happen on assignment to id.
>
> Reported-by: Frank Kellermann <frank.kellermann@atos.net>
> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Applied thanks.
^ permalink raw reply
* Re: [PATCH iproute2] ip6tunnel: Align ipv6 tunnel key display with ipv4
From: Stephen Hemminger @ 2017-01-13 1:35 UTC (permalink / raw)
To: David Forster; +Cc: netdev
In-Reply-To: <1484045154-19128-1-git-send-email-dforster@brocade.com>
On Tue, 10 Jan 2017 10:45:54 +0000
David Forster <dforster@brocade.com> wrote:
> Show ipv6 tunnel keys on presence of GRE_KEY flag for tunnel types
> other than GRE. Aligns ipv6 behaviour with ipv4.
>
> Signed-off-by: dforster@brocade.com
Applied thanks.
^ permalink raw reply
* Re: [PATCH iproute2] Add support for rt_protos.d
From: Stephen Hemminger @ 2017-01-13 1:27 UTC (permalink / raw)
To: David Ahern; +Cc: netdev
In-Reply-To: <1484005389-29381-1-git-send-email-dsa@cumulusnetworks.com>
On Mon, 9 Jan 2017 15:43:09 -0800
David Ahern <dsa@cumulusnetworks.com> wrote:
> Add support for reading proto id/name mappings from rt_protos.d
> directory. Allows users to have custom protocol values converted
> to human friendly names.
>
> Each file under rt_protos.d has the 'id name' format used by
> rt_protos. Only .conf files are read and parsed.
>
> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
> ---
> etc/iproute2/rt_protos.d/README | 3 +++
> lib/rt_names.c | 27 +++++++++++++++++++++++++++
> 2 files changed, 30 insertions(+)
> create mode 100644 etc/iproute2/rt_protos.d/README
>
> diff --git a/etc/iproute2/rt_protos.d/README b/etc/iproute2/rt_protos.d/README
> new file mode 100644
> index 000000000000..723509ce56b6
> --- /dev/null
> +++ b/etc/iproute2/rt_protos.d/README
> @@ -0,0 +1,3 @@
> +Each file in this directory is an rt_protos configuration file. iproute2
> +commands scan this directory processing all files that end in '.conf'.
> +
Applied, but required manual fixup.
.git/rebase-apply/patch:15: new blank line at EOF.
+
warning: 1 line adds whitespace errors.
^ permalink raw reply
* Re: [PATCH] i40e: Invoke softirqs after napi_reschedule
From: Eric Dumazet @ 2017-01-13 1:15 UTC (permalink / raw)
To: Benjamin Poirier; +Cc: Jeff Kirsher, intel-wired-lan, netdev
In-Reply-To: <20170113010414.22708-1-bpoirier@suse.com>
On Thu, 2017-01-12 at 17:04 -0800, Benjamin Poirier wrote:
> The following message is logged from time to time when using i40e:
> NOHZ: local_softirq_pending 08
>
> i40e may schedule napi from a workqueue. Afterwards, softirqs are not run
> in a deterministic time frame. The problem is the same as what was
> described in commit ec13ee80145c ("virtio_net: invoke softirqs after
> __napi_schedule") and this patch applies the same fix to i40e.
Yes, I believe mlx4 has a similar problem in mlx4_en_recover_from_oom()
^ permalink raw reply
* Re: [PATCH 5/6] treewide: use kv[mz]alloc* rather than opencoded variants
From: Dilger, Andreas @ 2017-01-13 1:11 UTC (permalink / raw)
To: Michal Hocko
Cc: Andrew Morton, Vlastimil Babka, David Rientjes, Mel Gorman,
Johannes Weiner, Al Viro, linux-mm@kvack.org, LKML, Michal Hocko,
Martin Schwidefsky, Heiko Carstens, Herbert Xu, Anton Vorontsov,
Colin Cross, Kees Cook, Luck, Tony, Rafael J. Wysocki, Ben Skeggs,
Kent Overstreet, Santosh Raspatur, Hariprasad S, Tariq Toukan,
Yishai Hadas, "Will
In-Reply-To: <20170112153717.28943-6-mhocko@kernel.org>
> On Jan 12, 2017, at 08:37, Michal Hocko <mhocko@kernel.org> wrote:
>
> From: Michal Hocko <mhocko@suse.com>
>
> There are many code paths opencoding kvmalloc. Let's use the helper
> instead. The main difference to kvmalloc is that those users are usually
> not considering all the aspects of the memory allocator. E.g. allocation
> requests < 64kB are basically never failing and invoke OOM killer to
> satisfy the allocation. This sounds too disruptive for something that
> has a reasonable fallback - the vmalloc. On the other hand those
> requests might fallback to vmalloc even when the memory allocator would
> succeed after several more reclaim/compaction attempts previously. There
> is no guarantee something like that happens though.
>
> This patch converts many of those places to kv[mz]alloc* helpers because
> they are more conservative.
>
> Signed-off-by: Michal Hocko <mhocko@suse.com>
Lustre part can be
Acked-by: Andreas Dilger <andreas.dilger@intel.com>
[snip]
> diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-mem.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-mem.c
> index a6a76a681ea9..8f638267e704 100644
> --- a/drivers/staging/lustre/lnet/libcfs/linux/linux-mem.c
> +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-mem.c
> @@ -45,15 +45,6 @@ EXPORT_SYMBOL(libcfs_kvzalloc);
> void *libcfs_kvzalloc_cpt(struct cfs_cpt_table *cptab, int cpt, size_t size,
> gfp_t flags)
> {
> - void *ret;
> -
> - ret = kzalloc_node(size, flags | __GFP_NOWARN,
> - cfs_cpt_spread_node(cptab, cpt));
> - if (!ret) {
> - WARN_ON(!(flags & (__GFP_FS | __GFP_HIGH)));
> - ret = vmalloc_node(size, cfs_cpt_spread_node(cptab, cpt));
> - }
> -
> - return ret;
> + return kvzalloc_node(size, flags, cfs_cpt_spread_node(cptab, cpt));
> }
> EXPORT_SYMBOL(libcfs_kvzalloc_cpt);
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* [PATCH] i40e: Invoke softirqs after napi_reschedule
From: Benjamin Poirier @ 2017-01-13 1:04 UTC (permalink / raw)
To: Jeff Kirsher; +Cc: intel-wired-lan, netdev
The following message is logged from time to time when using i40e:
NOHZ: local_softirq_pending 08
i40e may schedule napi from a workqueue. Afterwards, softirqs are not run
in a deterministic time frame. The problem is the same as what was
described in commit ec13ee80145c ("virtio_net: invoke softirqs after
__napi_schedule") and this patch applies the same fix to i40e.
Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index ad4cf63..d65488c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4621,8 +4621,10 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
*/
if ((!tx_pending_hw) && i40e_get_tx_pending(tx_ring, true) &&
(!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) {
+ local_bh_disable();
if (napi_reschedule(&tx_ring->q_vector->napi))
tx_ring->tx_stats.tx_lost_interrupt++;
+ local_bh_enable();
}
}
--
2.10.2
^ permalink raw reply related
* Re: [PATCH v2 7/7] uapi: export all headers under uapi directories
From: Jeff Epler @ 2017-01-13 1:04 UTC (permalink / raw)
To: Nicolas Dichtel
Cc: linux-mips, alsa-devel, linux-ia64, linux-doc, airlied,
linux-fbdev, dri-devel, linux-mtd, sparclinux, linux-arch,
linux-s390, linux-am33-list, linux-c6x-dev, linux-rdma,
linux-hexagon, linux-sh, Christoph Hellwig, coreteam, fcoe-devel,
xen-devel, linux-snps-arc, linux-media, uclinux-h8-devel,
linux-xtensa, arnd, linux-kbuild, adi-buildroot-devel, linux-raid,
linux-m68k, mmarek, linux-metag
In-Reply-To: <9d68af8a-a609-d7b1-58a9-f1155313b077@6wind.com>
On Thu, Jan 12, 2017 at 05:32:09PM +0100, Nicolas Dichtel wrote:
> What I was trying to say is that I export those directories like other are.
> Removing those files is not related to that series.
Perhaps the correct solution is to only copy files matching "*.h" to
reduce the risk of copying files incidentally created by kbuild but
which shouldn't be installed as uapi headers.
jeff
^ permalink raw reply
* [net PATCH v2 2/5] net: virtio: wrap rtnl_lock in test for calling with lock already held
From: John Fastabend @ 2017-01-13 0:35 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170113003412.4167.12250.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 v2 1/5] virtio_net: use dev_kfree_skb for small buffer XDP receive
From: John Fastabend @ 2017-01-13 0:35 UTC (permalink / raw)
To: jasowang, mst
Cc: john.r.fastabend, netdev, john.fastabend, alexei.starovoitov,
daniel
In-Reply-To: <20170113003412.4167.12250.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 v2 0/5] virtio_net XDP fixes and adjust_header support
From: John Fastabend @ 2017-01-13 0:34 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.
v2: fix spelling error, convert unsigned -> unsigned int
---
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
* [PATCH net] openvswitch: maintain correct checksum state in conntrack actions
From: Lance Richardson @ 2017-01-13 0:33 UTC (permalink / raw)
To: netdev, dev
When executing conntrack actions on skbuffs with checksum mode
CHECKSUM_COMPLETE, the checksum must be updated to account for
header pushes and pulls. Otherwise we get "hw csum failure"
logs similar to this (ICMP packet received on geneve tunnel
via ixgbe NIC):
[ 405.740065] genev_sys_6081: hw csum failure
[ 405.740106] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G I 4.10.0-rc3+ #1
[ 405.740108] Call Trace:
[ 405.740110] <IRQ>
[ 405.740113] dump_stack+0x63/0x87
[ 405.740116] netdev_rx_csum_fault+0x3a/0x40
[ 405.740118] __skb_checksum_complete+0xcf/0xe0
[ 405.740120] nf_ip_checksum+0xc8/0xf0
[ 405.740124] icmp_error+0x1de/0x351 [nf_conntrack_ipv4]
[ 405.740132] nf_conntrack_in+0xe1/0x550 [nf_conntrack]
[ 405.740137] ? find_bucket.isra.2+0x62/0x70 [openvswitch]
[ 405.740143] __ovs_ct_lookup+0x95/0x980 [openvswitch]
[ 405.740145] ? netif_rx_internal+0x44/0x110
[ 405.740149] ovs_ct_execute+0x147/0x4b0 [openvswitch]
[ 405.740153] do_execute_actions+0x22e/0xa70 [openvswitch]
[ 405.740157] ovs_execute_actions+0x40/0x120 [openvswitch]
[ 405.740161] ovs_dp_process_packet+0x84/0x120 [openvswitch]
[ 405.740166] ovs_vport_receive+0x73/0xd0 [openvswitch]
[ 405.740168] ? udp_rcv+0x1a/0x20
[ 405.740170] ? ip_local_deliver_finish+0x93/0x1e0
[ 405.740172] ? ip_local_deliver+0x6f/0xe0
[ 405.740174] ? ip_rcv_finish+0x3a0/0x3a0
[ 405.740176] ? ip_rcv_finish+0xdb/0x3a0
[ 405.740177] ? ip_rcv+0x2a7/0x400
[ 405.740180] ? __netif_receive_skb_core+0x970/0xa00
[ 405.740185] netdev_frame_hook+0xd3/0x160 [openvswitch]
[ 405.740187] __netif_receive_skb_core+0x1dc/0xa00
[ 405.740194] ? ixgbe_clean_rx_irq+0x46d/0xa20 [ixgbe]
[ 405.740197] __netif_receive_skb+0x18/0x60
[ 405.740199] netif_receive_skb_internal+0x40/0xb0
[ 405.740201] napi_gro_receive+0xcd/0x120
[ 405.740204] gro_cell_poll+0x57/0x80 [geneve]
[ 405.740206] net_rx_action+0x260/0x3c0
[ 405.740209] __do_softirq+0xc9/0x28c
[ 405.740211] irq_exit+0xd9/0xf0
[ 405.740213] do_IRQ+0x51/0xd0
[ 405.740215] common_interrupt+0x93/0x93
Fixes: 7f8a436eaa2c ("openvswitch: Add conntrack action")
Signed-off-by: Lance Richardson <lrichard@redhat.com>
---
net/openvswitch/conntrack.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 6b78bab..54253ea 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -514,7 +514,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
int hooknum, nh_off, err = NF_ACCEPT;
nh_off = skb_network_offset(skb);
- skb_pull(skb, nh_off);
+ skb_pull_rcsum(skb, nh_off);
/* See HOOK2MANIP(). */
if (maniptype == NF_NAT_MANIP_SRC)
@@ -579,6 +579,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
err = nf_nat_packet(ct, ctinfo, hooknum, skb);
push:
skb_push(skb, nh_off);
+ skb_postpush_rcsum(skb, skb->data, nh_off);
return err;
}
@@ -886,7 +887,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
/* The conntrack module expects to be working at L3. */
nh_ofs = skb_network_offset(skb);
- skb_pull(skb, nh_ofs);
+ skb_pull_rcsum(skb, nh_ofs);
if (key->ip.frag != OVS_FRAG_TYPE_NONE) {
err = handle_fragments(net, key, info->zone.id, skb);
@@ -900,6 +901,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
err = ovs_ct_lookup(net, key, info, skb);
skb_push(skb, nh_ofs);
+ skb_postpush_rcsum(skb, skb->data, nh_ofs);
if (err)
kfree_skb(skb);
return err;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next] liquidio: use fallback for selecting txq
From: Felix Manlunas @ 2017-01-13 0:18 UTC (permalink / raw)
To: davem; +Cc: netdev, raghu.vatsavayi, derek.chickles, satananda.burla
From: Satanand Burla <satananda.burla@cavium.com>
Remove assignment to ndo_select_queue so that fallback is used for
selecting txq. Also remove the now-useless function that used to be
assigned to ndo_select_queue.
Signed-off-by: Satanand Burla <satananda.burla@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: Derek Chickles <derek.chickles@cavium.com>
---
drivers/net/ethernet/cavium/liquidio/lio_main.c | 20 --------------------
drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 21 ---------------------
2 files changed, 41 deletions(-)
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index cc825d5..2b89ec2 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2223,25 +2223,6 @@ static void if_cfg_callback(struct octeon_device *oct,
wake_up_interruptible(&ctx->wc);
}
-/**
- * \brief Select queue based on hash
- * @param dev Net device
- * @param skb sk_buff structure
- * @returns selected queue number
- */
-static u16 select_q(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv __attribute__((unused)),
- select_queue_fallback_t fallback __attribute__((unused)))
-{
- u32 qindex = 0;
- struct lio *lio;
-
- lio = GET_LIO(dev);
- qindex = skb_tx_hash(dev, skb);
-
- return (u16)(qindex % (lio->linfo.num_txpciq));
-}
-
/** Routine to push packets arriving on Octeon interface upto network layer.
* @param oct_id - octeon device id.
* @param skbuff - skbuff struct to be passed to network layer.
@@ -3755,7 +3736,6 @@ static const struct net_device_ops lionetdevops = {
.ndo_set_vf_vlan = liquidio_set_vf_vlan,
.ndo_get_vf_config = liquidio_get_vf_config,
.ndo_set_vf_link_state = liquidio_set_vf_link_state,
- .ndo_select_queue = select_q
};
/** \brief Entry point for the liquidio module
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index ad2e72d..19d88fb 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -1455,26 +1455,6 @@ static void if_cfg_callback(struct octeon_device *oct,
wake_up_interruptible(&ctx->wc);
}
-/**
- * \brief Select queue based on hash
- * @param dev Net device
- * @param skb sk_buff structure
- * @returns selected queue number
- */
-static u16 select_q(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv __attribute__((unused)),
- select_queue_fallback_t fallback __attribute__((unused)))
-{
- struct lio *lio;
- u32 qindex;
-
- lio = GET_LIO(dev);
-
- qindex = skb_tx_hash(dev, skb);
-
- return (u16)(qindex % (lio->linfo.num_txpciq));
-}
-
/** Routine to push packets arriving on Octeon interface upto network layer.
* @param oct_id - octeon device id.
* @param skbuff - skbuff struct to be passed to network layer.
@@ -2717,7 +2697,6 @@ static const struct net_device_ops lionetdevops = {
.ndo_set_features = liquidio_set_features,
.ndo_udp_tunnel_add = liquidio_add_vxlan_port,
.ndo_udp_tunnel_del = liquidio_del_vxlan_port,
- .ndo_select_queue = select_q,
};
static int lio_nic_info(struct octeon_recv_info *recv_info, void *buf)
^ 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