| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <152638643041.9477.5642795713014271240.stgit@firesoul>
Date: Tue, 15 May 2018 14:13:50 +0200
From: Jesper Dangaard Brouer <brouer@...hat.com>
To: netdev@...r.kernel.org, Daniel Borkmann <borkmann@...earbox.net>,
Alexei Starovoitov <alexei.starovoitov@...il.com>,
Jesper Dangaard Brouer <brouer@...hat.com>
Cc: Christoph Hellwig <hch@...radead.org>,
BjörnTöpel <bjorn.topel@...el.com>,
Magnus Karlsson <magnus.karlsson@...el.com>,
makita.toshiaki@....ntt.co.jp
Subject: [bpf-next V3 PATCH 4/4] xdp: change ndo_xdp_xmit API to support
bulking
This patch change the API for ndo_xdp_xmit to support bulking
xdp_frames.
When kernel is compiled with CONFIG_RETPOLINE, XDP sees a huge slowdown.
Most of the slowdown is caused by DMA API indirect function calls, but
also the net_device->ndo_xdp_xmit() call.
Benchmarked patch with CONFIG_RETPOLINE, using xdp_redirect_map with
single flow/core test (CPU E5-1650 v4 @ 3.60GHz), showed
performance improved:
for driver ixgbe: 6,042,682 pps -> 6,853,768 pps = +811,086 pps
for driver i40e : 6,187,169 pps -> 6,724,519 pps = +537,350 pps
With frames avail as a bulk inside the driver ndo_xdp_xmit call,
further optimizations are possible, like bulk DMA-mapping for TX.
Testing without CONFIG_RETPOLINE show the same performance for
physical NIC drivers.
The virtual NIC driver tun sees a huge performance boost, as it can
avoid doing per frame producer locking, but instead amortize the
locking cost over the bulk.
V2: Fix compile errors reported by kbuild test robot <lkp@...el.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@...hat.com>
---
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 26 +++++++---
drivers/net/ethernet/intel/i40e/i40e_txrx.h | 2 -
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 21 ++++++--
drivers/net/tun.c | 37 +++++++++-----
drivers/net/virtio_net.c | 66 +++++++++++++++++++------
include/linux/netdevice.h | 14 +++--
include/net/page_pool.h | 5 +-
include/net/xdp.h | 1
include/trace/events/xdp.h | 10 ++--
kernel/bpf/devmap.c | 33 ++++++++-----
net/core/filter.c | 4 +-
net/core/xdp.c | 20 ++++++--
samples/bpf/xdp_monitor_kern.c | 10 ++++
samples/bpf/xdp_monitor_user.c | 35 +++++++++++--
14 files changed, 206 insertions(+), 78 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 5efa68de935b..9b698c5acd05 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3664,14 +3664,19 @@ netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
* @dev: netdev
* @xdp: XDP buffer
*
- * Returns Zero if sent, else an error code
+ * Returns number of frames successfully sent. Frames that fail are
+ * free'ed via XDP return API.
+ *
+ * For error cases, a negative errno code is returned and no-frames
+ * are transmitted (caller must handle freeing frames).
**/
-int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
+int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames)
{
struct i40e_netdev_priv *np = netdev_priv(dev);
unsigned int queue_index = smp_processor_id();
struct i40e_vsi *vsi = np->vsi;
- int err;
+ int drops = 0;
+ int i;
if (test_bit(__I40E_VSI_DOWN, vsi->state))
return -ENETDOWN;
@@ -3679,11 +3684,18 @@ int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs)
return -ENXIO;
- err = i40e_xmit_xdp_ring(xdpf, vsi->xdp_rings[queue_index]);
- if (err != I40E_XDP_TX)
- return -ENOSPC;
+ for (i = 0; i < n; i++) {
+ struct xdp_frame *xdpf = frames[i];
+ int err;
- return 0;
+ err = i40e_xmit_xdp_ring(xdpf, vsi->xdp_rings[queue_index]);
+ if (err != I40E_XDP_TX) {
+ xdp_return_frame_rx_napi(xdpf);
+ drops++;
+ }
+ }
+
+ return n - drops;
}
/**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index fdd2c55f03a6..eb8804b3d7b6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -487,7 +487,7 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw);
void i40e_detect_recover_hung(struct i40e_vsi *vsi);
int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
bool __i40e_chk_linearize(struct sk_buff *skb);
-int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf);
+int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames);
void i40e_xdp_flush(struct net_device *dev);
/**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 6652b201df5b..9645619f7729 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10017,11 +10017,13 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
}
}
-static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
+static int ixgbe_xdp_xmit(struct net_device *dev, int n,
+ struct xdp_frame **frames)
{
struct ixgbe_adapter *adapter = netdev_priv(dev);
struct ixgbe_ring *ring;
- int err;
+ int drops = 0;
+ int i;
if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state)))
return -ENETDOWN;
@@ -10033,11 +10035,18 @@ static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
if (unlikely(!ring))
return -ENXIO;
- err = ixgbe_xmit_xdp_ring(adapter, xdpf);
- if (err != IXGBE_XDP_TX)
- return -ENOSPC;
+ for (i = 0; i < n; i++) {
+ struct xdp_frame *xdpf = frames[i];
+ int err;
- return 0;
+ err = ixgbe_xmit_xdp_ring(adapter, xdpf);
+ if (err != IXGBE_XDP_TX) {
+ xdp_return_frame_rx_napi(xdpf);
+ drops++;
+ }
+ }
+
+ return n - drops;
}
static void ixgbe_xdp_flush(struct net_device *dev)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index d3c04ab9752a..4fe0c75c5e0b 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -70,6 +70,7 @@
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/sock.h>
+#include <net/xdp.h>
#include <linux/seq_file.h>
#include <linux/uio.h>
#include <linux/skb_array.h>
@@ -1290,34 +1291,44 @@ static const struct net_device_ops tun_netdev_ops = {
.ndo_get_stats64 = tun_net_get_stats64,
};
-static int tun_xdp_xmit(struct net_device *dev, struct xdp_frame *frame)
+static int tun_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames)
{
struct tun_struct *tun = netdev_priv(dev);
struct tun_file *tfile;
u32 numqueues;
- int ret = 0;
+ int drops = 0;
+ int cnt = n;
+ int i;
rcu_read_lock();
numqueues = READ_ONCE(tun->numqueues);
if (!numqueues) {
- ret = -ENOSPC;
- goto out;
+ rcu_read_unlock();
+ return -ENXIO; /* Caller will free/return all frames */
}
tfile = rcu_dereference(tun->tfiles[smp_processor_id() %
numqueues]);
- /* Encode the XDP flag into lowest bit for consumer to differ
- * XDP buffer from sk_buff.
- */
- if (ptr_ring_produce(&tfile->tx_ring, tun_xdp_to_ptr(frame))) {
- this_cpu_inc(tun->pcpu_stats->tx_dropped);
- ret = -ENOSPC;
+
+ spin_lock(&tfile->tx_ring.producer_lock);
+ for (i = 0; i < n; i++) {
+ struct xdp_frame *xdp = frames[i];
+ /* Encode the XDP flag into lowest bit for consumer to differ
+ * XDP buffer from sk_buff.
+ */
+ void *frame = tun_xdp_to_ptr(xdp);
+
+ if (__ptr_ring_produce(&tfile->tx_ring, frame)) {
+ this_cpu_inc(tun->pcpu_stats->tx_dropped);
+ xdp_return_frame_rx_napi(xdp);
+ drops++;
+ }
}
+ spin_unlock(&tfile->tx_ring.producer_lock);
-out:
rcu_read_unlock();
- return ret;
+ return cnt - drops;
}
static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp)
@@ -1327,7 +1338,7 @@ static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp)
if (unlikely(!frame))
return -EOVERFLOW;
- return tun_xdp_xmit(dev, frame);
+ return tun_xdp_xmit(dev, 1, &frame);
}
static void tun_xdp_flush(struct net_device *dev)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index f34794a76c4d..39a0783d1cde 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -419,23 +419,13 @@ static void virtnet_xdp_flush(struct net_device *dev)
virtqueue_kick(sq->vq);
}
-static int __virtnet_xdp_xmit(struct virtnet_info *vi,
- struct xdp_frame *xdpf)
+static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
+ struct send_queue *sq,
+ struct xdp_frame *xdpf)
{
struct virtio_net_hdr_mrg_rxbuf *hdr;
- struct xdp_frame *xdpf_sent;
- struct send_queue *sq;
- unsigned int len;
- unsigned int qp;
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 ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
- xdp_return_frame(xdpf_sent);
-
/* virtqueue want to use data area in-front of packet */
if (unlikely(xdpf->metasize > 0))
return -EOPNOTSUPP;
@@ -459,11 +449,40 @@ static int __virtnet_xdp_xmit(struct virtnet_info *vi,
return 0;
}
-static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
+static int __virtnet_xdp_tx_xmit(struct virtnet_info *vi,
+ struct xdp_frame *xdpf)
+{
+ struct xdp_frame *xdpf_sent;
+ struct send_queue *sq;
+ unsigned int len;
+ unsigned int qp;
+
+ 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 ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
+ xdp_return_frame(xdpf_sent);
+
+ return __virtnet_xdp_xmit_one(vi, sq, xdpf);
+}
+
+static int virtnet_xdp_xmit(struct net_device *dev,
+ int n, struct xdp_frame **frames)
{
struct virtnet_info *vi = netdev_priv(dev);
struct receive_queue *rq = vi->rq;
+ struct xdp_frame *xdpf_sent;
struct bpf_prog *xdp_prog;
+ struct send_queue *sq;
+ unsigned int len;
+ unsigned int qp;
+ int drops = 0;
+ int err;
+ int i;
+
+ qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
+ sq = &vi->sq[qp];
/* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
* indicate XDP resources have been successfully allocated.
@@ -472,7 +491,20 @@ static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
if (!xdp_prog)
return -ENXIO;
- return __virtnet_xdp_xmit(vi, xdpf);
+ /* Free up any pending old buffers before queueing new ones. */
+ while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
+ xdp_return_frame(xdpf_sent);
+
+ for (i = 0; i < n; i++) {
+ struct xdp_frame *xdpf = frames[i];
+
+ err = __virtnet_xdp_xmit_one(vi, sq, xdpf);
+ if (err) {
+ xdp_return_frame_rx_napi(xdpf);
+ drops++;
+ }
+ }
+ return n - drops;
}
static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
@@ -616,7 +648,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
xdpf = convert_to_xdp_frame(&xdp);
if (unlikely(!xdpf))
goto err_xdp;
- err = __virtnet_xdp_xmit(vi, xdpf);
+ err = __virtnet_xdp_tx_xmit(vi, xdpf);
if (unlikely(err)) {
trace_xdp_exception(vi->dev, xdp_prog, act);
goto err_xdp;
@@ -779,7 +811,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
xdpf = convert_to_xdp_frame(&xdp);
if (unlikely(!xdpf))
goto err_xdp;
- err = __virtnet_xdp_xmit(vi, xdpf);
+ err = __virtnet_xdp_tx_xmit(vi, xdpf);
if (unlikely(err)) {
trace_xdp_exception(vi->dev, xdp_prog, act);
if (unlikely(xdp_page != page))
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 03ed492c4e14..debdb6286170 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1185,9 +1185,13 @@ struct dev_ifalias {
* This function is used to set or query state related to XDP on the
* netdevice and manage BPF offload. See definition of
* enum bpf_netdev_command for details.
- * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_frame *xdp);
- * This function is used to submit a XDP packet for transmit on a
- * netdevice.
+ * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp);
+ * This function is used to submit @n XDP packets for transmit on a
+ * netdevice. Returns number of frames successfully transmitted, frames
+ * that got dropped are freed/returned via xdp_return_frame().
+ * Returns negative number, means general error invoking ndo, meaning
+ * no frames were xmit'ed and core-caller will free all frames.
+ * TODO: Consider add flag to allow sending flush operation.
* void (*ndo_xdp_flush)(struct net_device *dev);
* This function is used to inform the driver to flush a particular
* xdp tx queue. Must be called on same CPU as xdp_xmit.
@@ -1375,8 +1379,8 @@ struct net_device_ops {
int needed_headroom);
int (*ndo_bpf)(struct net_device *dev,
struct netdev_bpf *bpf);
- int (*ndo_xdp_xmit)(struct net_device *dev,
- struct xdp_frame *xdp);
+ int (*ndo_xdp_xmit)(struct net_device *dev, int n,
+ struct xdp_frame **xdp);
void (*ndo_xdp_flush)(struct net_device *dev);
};
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index c79087153148..694d055e01ef 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -115,13 +115,14 @@ void page_pool_destroy(struct page_pool *pool);
void __page_pool_put_page(struct page_pool *pool,
struct page *page, bool allow_direct);
-static inline void page_pool_put_page(struct page_pool *pool, struct page *page)
+static inline void page_pool_put_page(struct page_pool *pool,
+ struct page *page, bool allow_direct)
{
/* When page_pool isn't compiled-in, net/core/xdp.c doesn't
* allow registering MEM_TYPE_PAGE_POOL, but shield linker.
*/
#ifdef CONFIG_PAGE_POOL
- __page_pool_put_page(pool, page, false);
+ __page_pool_put_page(pool, page, allow_direct);
#endif
}
/* Very limited use-cases allow recycle direct */
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 0b689cf561c7..7ad779237ae8 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -104,6 +104,7 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
}
void xdp_return_frame(struct xdp_frame *xdpf);
+void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
void xdp_return_buff(struct xdp_buff *xdp);
int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index 2e9ef0650144..1ecf4c67fcf7 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -234,9 +234,9 @@ TRACE_EVENT(xdp_devmap_xmit,
TP_PROTO(const struct bpf_map *map, u32 map_index,
int sent, int drops,
const struct net_device *from_dev,
- const struct net_device *to_dev),
+ const struct net_device *to_dev, int err),
- TP_ARGS(map, map_index, sent, drops, from_dev, to_dev),
+ TP_ARGS(map, map_index, sent, drops, from_dev, to_dev, err),
TP_STRUCT__entry(
__field(int, map_id)
@@ -246,6 +246,7 @@ TRACE_EVENT(xdp_devmap_xmit,
__field(int, sent)
__field(int, from_ifindex)
__field(int, to_ifindex)
+ __field(int, err)
),
TP_fast_assign(
@@ -256,16 +257,17 @@ TRACE_EVENT(xdp_devmap_xmit,
__entry->sent = sent;
__entry->from_ifindex = from_dev->ifindex;
__entry->to_ifindex = to_dev->ifindex;
+ __entry->err = err;
),
TP_printk("ndo_xdp_xmit"
" map_id=%d map_index=%d action=%s"
" sent=%d drops=%d"
- " from_ifindex=%d to_ifindex=%d",
+ " from_ifindex=%d to_ifindex=%d err=%d",
__entry->map_id, __entry->map_index,
__print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
__entry->sent, __entry->drops,
- __entry->from_ifindex, __entry->to_ifindex)
+ __entry->from_ifindex, __entry->to_ifindex, __entry->err)
);
#endif /* _TRACE_XDP_H */
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 6f84100723b0..4dd8f0e3a8d9 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -222,7 +222,7 @@ static int bq_xmit_all(struct bpf_dtab_netdev *obj,
struct xdp_bulk_queue *bq)
{
struct net_device *dev = obj->dev;
- int sent = 0, drops = 0;
+ int sent = 0, drops = 0, err = 0;
int i;
if (unlikely(!bq->count))
@@ -234,23 +234,32 @@ static int bq_xmit_all(struct bpf_dtab_netdev *obj,
prefetch(xdpf);
}
- for (i = 0; i < bq->count; i++) {
- struct xdp_frame *xdpf = bq->q[i];
- int err;
-
- err = dev->netdev_ops->ndo_xdp_xmit(dev, xdpf);
- if (err) {
- drops++;
- xdp_return_frame(xdpf);
- }
- sent++;
+ sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q);
+ if (sent < 0) {
+ err = sent;
+ sent = 0;
+ goto error;
}
+ drops = bq->count - sent;
+out:
bq->count = 0;
trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit,
- sent, drops, bq->dev_rx, dev);
+ sent, drops, bq->dev_rx, dev, err);
bq->dev_rx = NULL;
return 0;
+error:
+ /* If ndo_xdp_xmit fails with an errno, no frames have been
+ * xmit'ed and it's our responsibility to them free all.
+ */
+ for (i = 0; i < bq->count; i++) {
+ struct xdp_frame *xdpf = bq->q[i];
+
+ /* RX path under NAPI protection, can return frames faster */
+ xdp_return_frame_rx_napi(xdpf);
+ drops++;
+ }
+ goto out;
}
/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled
diff --git a/net/core/filter.c b/net/core/filter.c
index 68277358cca9..1f663404e36a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3008,8 +3008,8 @@ static int __bpf_tx_xdp(struct net_device *dev,
if (unlikely(!xdpf))
return -EOVERFLOW;
- err = dev->netdev_ops->ndo_xdp_xmit(dev, xdpf);
- if (err)
+ err = dev->netdev_ops->ndo_xdp_xmit(dev, 1, &xdpf);
+ if (err <= 0)
return err;
dev->netdev_ops->ndo_xdp_flush(dev);
return 0;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index bf6758f74339..cb8c4e061a5a 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -308,7 +308,13 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
}
EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
-static void xdp_return(void *data, struct xdp_mem_info *mem)
+/* XDP RX runs under NAPI protection, and in different delivery error
+ * scenarios (e.g. queue full), it is possible to return the xdp_frame
+ * while still leveraging this protection. The @napi_direct boolian
+ * is used for those calls sites. Thus, allowing for faster recycling
+ * of xdp_frames/pages in those cases.
+ */
+static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct)
{
struct xdp_mem_allocator *xa;
struct page *page;
@@ -320,7 +326,7 @@ static void xdp_return(void *data, struct xdp_mem_info *mem)
xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
page = virt_to_head_page(data);
if (xa)
- page_pool_put_page(xa->page_pool, page);
+ page_pool_put_page(xa->page_pool, page, napi_direct);
else
put_page(page);
rcu_read_unlock();
@@ -340,12 +346,18 @@ static void xdp_return(void *data, struct xdp_mem_info *mem)
void xdp_return_frame(struct xdp_frame *xdpf)
{
- xdp_return(xdpf->data, &xdpf->mem);
+ __xdp_return(xdpf->data, &xdpf->mem, false);
}
EXPORT_SYMBOL_GPL(xdp_return_frame);
+void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
+{
+ __xdp_return(xdpf->data, &xdpf->mem, true);
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
+
void xdp_return_buff(struct xdp_buff *xdp)
{
- xdp_return(xdp->data, &xdp->rxq->mem);
+ __xdp_return(xdp->data, &xdp->rxq->mem, true);
}
EXPORT_SYMBOL_GPL(xdp_return_buff);
diff --git a/samples/bpf/xdp_monitor_kern.c b/samples/bpf/xdp_monitor_kern.c
index 2854aa0665ea..ad10fe700d7d 100644
--- a/samples/bpf/xdp_monitor_kern.c
+++ b/samples/bpf/xdp_monitor_kern.c
@@ -125,6 +125,7 @@ struct datarec {
u64 processed;
u64 dropped;
u64 info;
+ u64 err;
};
#define MAX_CPUS 64
@@ -228,6 +229,7 @@ struct devmap_xmit_ctx {
int sent; // offset:24; size:4; signed:1;
int from_ifindex; // offset:28; size:4; signed:1;
int to_ifindex; // offset:32; size:4; signed:1;
+ int err; // offset:36; size:4; signed:1;
};
SEC("tracepoint/xdp/xdp_devmap_xmit")
@@ -245,5 +247,13 @@ int trace_xdp_devmap_xmit(struct devmap_xmit_ctx *ctx)
/* Record bulk events, then userspace can calc average bulk size */
rec->info += 1;
+ /* Record error cases, where no frame were sent */
+ if (ctx->err)
+ rec->err++;
+
+ /* Catch API error of drv ndo_xdp_xmit sent more than count */
+ if (ctx->drops < 0)
+ rec->err++;
+
return 1;
}
diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c
index 7e18a454924c..dd558cbb2309 100644
--- a/samples/bpf/xdp_monitor_user.c
+++ b/samples/bpf/xdp_monitor_user.c
@@ -117,6 +117,7 @@ struct datarec {
__u64 processed;
__u64 dropped;
__u64 info;
+ __u64 err;
};
#define MAX_CPUS 64
@@ -152,6 +153,7 @@ static bool map_collect_record(int fd, __u32 key, struct record *rec)
__u64 sum_processed = 0;
__u64 sum_dropped = 0;
__u64 sum_info = 0;
+ __u64 sum_err = 0;
int i;
if ((bpf_map_lookup_elem(fd, &key, values)) != 0) {
@@ -170,10 +172,13 @@ static bool map_collect_record(int fd, __u32 key, struct record *rec)
sum_dropped += values[i].dropped;
rec->cpu[i].info = values[i].info;
sum_info += values[i].info;
+ rec->cpu[i].err = values[i].err;
+ sum_err += values[i].err;
}
rec->total.processed = sum_processed;
rec->total.dropped = sum_dropped;
rec->total.info = sum_info;
+ rec->total.err = sum_err;
return true;
}
@@ -274,6 +279,18 @@ static double calc_info(struct datarec *r, struct datarec *p, double period)
return pps;
}
+static double calc_err(struct datarec *r, struct datarec *p, double period)
+{
+ __u64 packets = 0;
+ double pps = 0;
+
+ if (period > 0) {
+ packets = r->err - p->err;
+ pps = packets / period;
+ }
+ return pps;
+}
+
static void stats_print(struct stats_record *stats_rec,
struct stats_record *stats_prev,
bool err_only)
@@ -412,11 +429,12 @@ static void stats_print(struct stats_record *stats_rec,
/* devmap ndo_xdp_xmit stats */
{
- char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %'-10.2f %s\n";
- char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %'-10.2f %s\n";
+ char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %'-10.2f %s %s\n";
+ char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %'-10.2f %s %s\n";
struct record *rec, *prev;
- double drop, info;
+ double drop, info, err;
char *i_str = "";
+ char *err_str = "";
rec = &stats_rec->xdp_devmap_xmit;
prev = &stats_prev->xdp_devmap_xmit;
@@ -428,22 +446,29 @@ static void stats_print(struct stats_record *stats_rec,
pps = calc_pps(r, p, t);
drop = calc_drop(r, p, t);
info = calc_info(r, p, t);
+ err = calc_err(r, p, t);
if (info > 0) {
i_str = "bulk-average";
info = (pps+drop) / info; /* calc avg bulk */
}
+ if (err > 0)
+ err_str = "drv-err";
if (pps > 0 || drop > 0)
printf(fmt1, "devmap-xmit",
- i, pps, drop, info, i_str);
+ i, pps, drop, info, i_str, err_str);
}
pps = calc_pps(&rec->total, &prev->total, t);
drop = calc_drop(&rec->total, &prev->total, t);
info = calc_info(&rec->total, &prev->total, t);
+ err = calc_err(&rec->total, &prev->total, t);
if (info > 0) {
i_str = "bulk-average";
info = (pps+drop) / info; /* calc avg bulk */
}
- printf(fmt2, "devmap-xmit", "total", pps, drop, info, i_str);
+ if (err > 0)
+ err_str = "drv-err";
+ printf(fmt2, "devmap-xmit", "total", pps, drop,
+ info, i_str, err_str);
}
printf("\n");
Powered by blists - more mailing lists