* [PATCH v7 bpf-next 04/10] xdp: Helper function to clear kernel pointers in xdp_frame
From: Toshiaki Makita @ 2018-08-02 10:55 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann
Cc: Toshiaki Makita, netdev, Jesper Dangaard Brouer, Jakub Kicinski,
John Fastabend
In-Reply-To: <1533207314-2572-1-git-send-email-makita.toshiaki@lab.ntt.co.jp>
xdp_frame has kernel pointers which should not be readable from bpf
programs. When we want to reuse xdp_frame region but it may be read by
bpf programs later, we can use this helper to clear kernel pointers.
This is more efficient than calling memset() for the entire struct.
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
---
include/net/xdp.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/include/net/xdp.h b/include/net/xdp.h
index fcb033f..76b9525 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -84,6 +84,13 @@ struct xdp_frame {
struct net_device *dev_rx; /* used by cpumap */
};
+/* Clear kernel pointers in xdp_frame */
+static inline void xdp_scrub_frame(struct xdp_frame *frame)
+{
+ frame->data = NULL;
+ frame->dev_rx = NULL;
+}
+
/* Convert xdp_buff to xdp_frame */
static inline
struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
--
1.8.3.1
^ permalink raw reply related
* [PATCH v7 bpf-next 03/10] veth: Avoid drops by oversized packets when XDP is enabled
From: Toshiaki Makita @ 2018-08-02 10:55 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann
Cc: Toshiaki Makita, netdev, Jesper Dangaard Brouer, Jakub Kicinski,
John Fastabend
In-Reply-To: <1533207314-2572-1-git-send-email-makita.toshiaki@lab.ntt.co.jp>
Oversized packets including GSO packets can be dropped if XDP is
enabled on receiver side, so don't send such packets from peer.
Drop TSO and SCTP fragmentation features so that veth devices themselves
segment packets with XDP enabled. Also cap MTU accordingly.
v4:
- Don't auto-adjust MTU but cap max MTU.
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
---
drivers/net/veth.c | 47 +++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 45 insertions(+), 2 deletions(-)
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index d3b9f10..9edf104 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -543,6 +543,23 @@ static int veth_get_iflink(const struct net_device *dev)
return iflink;
}
+static netdev_features_t veth_fix_features(struct net_device *dev,
+ netdev_features_t features)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+ struct net_device *peer;
+
+ peer = rtnl_dereference(priv->peer);
+ if (peer) {
+ struct veth_priv *peer_priv = netdev_priv(peer);
+
+ if (peer_priv->_xdp_prog)
+ features &= ~NETIF_F_GSO_SOFTWARE;
+ }
+
+ return features;
+}
+
static void veth_set_rx_headroom(struct net_device *dev, int new_hr)
{
struct veth_priv *peer_priv, *priv = netdev_priv(dev);
@@ -572,6 +589,7 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
struct veth_priv *priv = netdev_priv(dev);
struct bpf_prog *old_prog;
struct net_device *peer;
+ unsigned int max_mtu;
int err;
old_prog = priv->_xdp_prog;
@@ -585,6 +603,15 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
goto err;
}
+ max_mtu = PAGE_SIZE - VETH_XDP_HEADROOM -
+ peer->hard_header_len -
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ if (peer->mtu > max_mtu) {
+ NL_SET_ERR_MSG_MOD(extack, "Peer MTU is too large to set XDP");
+ err = -ERANGE;
+ goto err;
+ }
+
if (dev->flags & IFF_UP) {
err = veth_enable_xdp(dev);
if (err) {
@@ -592,14 +619,29 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
goto err;
}
}
+
+ if (!old_prog) {
+ peer->hw_features &= ~NETIF_F_GSO_SOFTWARE;
+ peer->max_mtu = max_mtu;
+ }
}
if (old_prog) {
- if (!prog && dev->flags & IFF_UP)
- veth_disable_xdp(dev);
+ if (!prog) {
+ if (dev->flags & IFF_UP)
+ veth_disable_xdp(dev);
+
+ if (peer) {
+ peer->hw_features |= NETIF_F_GSO_SOFTWARE;
+ peer->max_mtu = ETH_MAX_MTU;
+ }
+ }
bpf_prog_put(old_prog);
}
+ if ((!!old_prog ^ !!prog) && peer)
+ netdev_update_features(peer);
+
return 0;
err:
priv->_xdp_prog = old_prog;
@@ -644,6 +686,7 @@ static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
.ndo_poll_controller = veth_poll_controller,
#endif
.ndo_get_iflink = veth_get_iflink,
+ .ndo_fix_features = veth_fix_features,
.ndo_features_check = passthru_features_check,
.ndo_set_rx_headroom = veth_set_rx_headroom,
.ndo_bpf = veth_xdp,
--
1.8.3.1
^ permalink raw reply related
* [PATCH v7 bpf-next 02/10] veth: Add driver XDP
From: Toshiaki Makita @ 2018-08-02 10:55 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann
Cc: Toshiaki Makita, netdev, Jesper Dangaard Brouer, Jakub Kicinski,
John Fastabend
In-Reply-To: <1533207314-2572-1-git-send-email-makita.toshiaki@lab.ntt.co.jp>
This is the basic implementation of veth driver XDP.
Incoming packets are sent from the peer veth device in the form of skb,
so this is generally doing the same thing as generic XDP.
This itself is not so useful, but a starting point to implement other
useful veth XDP features like TX and REDIRECT.
This introduces NAPI when XDP is enabled, because XDP is now heavily
relies on NAPI context. Use ptr_ring to emulate NIC ring. Tx function
enqueues packets to the ring and peer NAPI handler drains the ring.
Currently only one ring is allocated for each veth device, so it does
not scale on multiqueue env. This can be resolved by allocating rings
on the per-queue basis later.
Note that NAPI is not used but netif_rx is used when XDP is not loaded,
so this does not change the default behaviour.
v6:
- Check skb->len only when allocation is needed.
- Add __GFP_NOWARN to alloc_page() as it can be triggered by external
events.
v3:
- Fix race on closing the device.
- Add extack messages in ndo_bpf.
v2:
- Squashed with the patch adding NAPI.
- Implement adjust_tail.
- Don't acquire consumer lock because it is guarded by NAPI.
- Make poll_controller noop since it is unnecessary.
- Register rxq_info on enabling XDP rather than on opening the device.
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
---
drivers/net/veth.c | 374 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 367 insertions(+), 7 deletions(-)
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index a69ad39..d3b9f10 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -19,10 +19,18 @@
#include <net/xfrm.h>
#include <linux/veth.h>
#include <linux/module.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/ptr_ring.h>
+#include <linux/skb_array.h>
+#include <linux/bpf_trace.h>
#define DRV_NAME "veth"
#define DRV_VERSION "1.0"
+#define VETH_RING_SIZE 256
+#define VETH_XDP_HEADROOM (XDP_PACKET_HEADROOM + NET_IP_ALIGN)
+
struct pcpu_vstats {
u64 packets;
u64 bytes;
@@ -30,9 +38,16 @@ struct pcpu_vstats {
};
struct veth_priv {
+ struct napi_struct xdp_napi;
+ struct net_device *dev;
+ struct bpf_prog __rcu *xdp_prog;
+ struct bpf_prog *_xdp_prog;
struct net_device __rcu *peer;
atomic64_t dropped;
unsigned requested_headroom;
+ bool rx_notify_masked;
+ struct ptr_ring xdp_ring;
+ struct xdp_rxq_info xdp_rxq;
};
/*
@@ -98,11 +113,43 @@ static void veth_get_ethtool_stats(struct net_device *dev,
.get_link_ksettings = veth_get_link_ksettings,
};
-static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
+/* general routines */
+
+static void __veth_xdp_flush(struct veth_priv *priv)
+{
+ /* Write ptr_ring before reading rx_notify_masked */
+ smp_mb();
+ if (!priv->rx_notify_masked) {
+ priv->rx_notify_masked = true;
+ napi_schedule(&priv->xdp_napi);
+ }
+}
+
+static int veth_xdp_rx(struct veth_priv *priv, struct sk_buff *skb)
+{
+ if (unlikely(ptr_ring_produce(&priv->xdp_ring, skb))) {
+ dev_kfree_skb_any(skb);
+ return NET_RX_DROP;
+ }
+
+ return NET_RX_SUCCESS;
+}
+
+static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb, bool xdp)
{
struct veth_priv *priv = netdev_priv(dev);
+
+ return __dev_forward_skb(dev, skb) ?: xdp ?
+ veth_xdp_rx(priv, skb) :
+ netif_rx(skb);
+}
+
+static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
struct net_device *rcv;
int length = skb->len;
+ bool rcv_xdp = false;
rcu_read_lock();
rcv = rcu_dereference(priv->peer);
@@ -111,7 +158,10 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
goto drop;
}
- if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) {
+ rcv_priv = netdev_priv(rcv);
+ rcv_xdp = rcu_access_pointer(rcv_priv->xdp_prog);
+
+ if (likely(veth_forward_skb(rcv, skb, rcv_xdp) == NET_RX_SUCCESS)) {
struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);
u64_stats_update_begin(&stats->syncp);
@@ -122,14 +172,15 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
drop:
atomic64_inc(&priv->dropped);
}
+
+ if (rcv_xdp)
+ __veth_xdp_flush(rcv_priv);
+
rcu_read_unlock();
+
return NETDEV_TX_OK;
}
-/*
- * general routines
- */
-
static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
@@ -179,18 +230,254 @@ static void veth_set_multicast_list(struct net_device *dev)
{
}
+static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
+ int buflen)
+{
+ struct sk_buff *skb;
+
+ if (!buflen) {
+ buflen = SKB_DATA_ALIGN(headroom + len) +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ }
+ skb = build_skb(head, buflen);
+ if (!skb)
+ return NULL;
+
+ skb_reserve(skb, headroom);
+ skb_put(skb, len);
+
+ return skb;
+}
+
+static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
+ struct sk_buff *skb)
+{
+ u32 pktlen, headroom, act, metalen;
+ void *orig_data, *orig_data_end;
+ struct bpf_prog *xdp_prog;
+ int mac_len, delta, off;
+ struct xdp_buff xdp;
+
+ rcu_read_lock();
+ xdp_prog = rcu_dereference(priv->xdp_prog);
+ if (unlikely(!xdp_prog)) {
+ rcu_read_unlock();
+ goto out;
+ }
+
+ mac_len = skb->data - skb_mac_header(skb);
+ pktlen = skb->len + mac_len;
+ headroom = skb_headroom(skb) - mac_len;
+
+ if (skb_shared(skb) || skb_head_is_locked(skb) ||
+ skb_is_nonlinear(skb) || headroom < XDP_PACKET_HEADROOM) {
+ struct sk_buff *nskb;
+ int size, head_off;
+ void *head, *start;
+ struct page *page;
+
+ size = SKB_DATA_ALIGN(VETH_XDP_HEADROOM + pktlen) +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ if (size > PAGE_SIZE)
+ goto drop;
+
+ page = alloc_page(GFP_ATOMIC | __GFP_NOWARN);
+ if (!page)
+ goto drop;
+
+ head = page_address(page);
+ start = head + VETH_XDP_HEADROOM;
+ if (skb_copy_bits(skb, -mac_len, start, pktlen)) {
+ page_frag_free(head);
+ goto drop;
+ }
+
+ nskb = veth_build_skb(head,
+ VETH_XDP_HEADROOM + mac_len, skb->len,
+ PAGE_SIZE);
+ if (!nskb) {
+ page_frag_free(head);
+ goto drop;
+ }
+
+ skb_copy_header(nskb, skb);
+ head_off = skb_headroom(nskb) - skb_headroom(skb);
+ skb_headers_offset_update(nskb, head_off);
+ if (skb->sk)
+ skb_set_owner_w(nskb, skb->sk);
+ consume_skb(skb);
+ skb = nskb;
+ }
+
+ xdp.data_hard_start = skb->head;
+ xdp.data = skb_mac_header(skb);
+ xdp.data_end = xdp.data + pktlen;
+ xdp.data_meta = xdp.data;
+ xdp.rxq = &priv->xdp_rxq;
+ orig_data = xdp.data;
+ orig_data_end = xdp.data_end;
+
+ act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+ switch (act) {
+ case XDP_PASS:
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ case XDP_ABORTED:
+ trace_xdp_exception(priv->dev, xdp_prog, act);
+ case XDP_DROP:
+ goto drop;
+ }
+ rcu_read_unlock();
+
+ delta = orig_data - xdp.data;
+ off = mac_len + delta;
+ if (off > 0)
+ __skb_push(skb, off);
+ else if (off < 0)
+ __skb_pull(skb, -off);
+ skb->mac_header -= delta;
+ off = xdp.data_end - orig_data_end;
+ if (off != 0)
+ __skb_put(skb, off);
+ skb->protocol = eth_type_trans(skb, priv->dev);
+
+ metalen = xdp.data - xdp.data_meta;
+ if (metalen)
+ skb_metadata_set(skb, metalen);
+out:
+ return skb;
+drop:
+ rcu_read_unlock();
+ kfree_skb(skb);
+ return NULL;
+}
+
+static int veth_xdp_rcv(struct veth_priv *priv, int budget)
+{
+ int i, done = 0;
+
+ for (i = 0; i < budget; i++) {
+ struct sk_buff *skb = __ptr_ring_consume(&priv->xdp_ring);
+
+ if (!skb)
+ break;
+
+ skb = veth_xdp_rcv_skb(priv, skb);
+
+ if (skb)
+ napi_gro_receive(&priv->xdp_napi, skb);
+
+ done++;
+ }
+
+ return done;
+}
+
+static int veth_poll(struct napi_struct *napi, int budget)
+{
+ struct veth_priv *priv =
+ container_of(napi, struct veth_priv, xdp_napi);
+ int done;
+
+ done = veth_xdp_rcv(priv, budget);
+
+ if (done < budget && napi_complete_done(napi, done)) {
+ /* Write rx_notify_masked before reading ptr_ring */
+ smp_store_mb(priv->rx_notify_masked, false);
+ if (unlikely(!__ptr_ring_empty(&priv->xdp_ring))) {
+ priv->rx_notify_masked = true;
+ napi_schedule(&priv->xdp_napi);
+ }
+ }
+
+ return done;
+}
+
+static int veth_napi_add(struct net_device *dev)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+ int err;
+
+ err = ptr_ring_init(&priv->xdp_ring, VETH_RING_SIZE, GFP_KERNEL);
+ if (err)
+ return err;
+
+ netif_napi_add(dev, &priv->xdp_napi, veth_poll, NAPI_POLL_WEIGHT);
+ napi_enable(&priv->xdp_napi);
+
+ return 0;
+}
+
+static void veth_napi_del(struct net_device *dev)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+
+ napi_disable(&priv->xdp_napi);
+ netif_napi_del(&priv->xdp_napi);
+ priv->rx_notify_masked = false;
+ ptr_ring_cleanup(&priv->xdp_ring, __skb_array_destroy_skb);
+}
+
+static int veth_enable_xdp(struct net_device *dev)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+ int err;
+
+ if (!xdp_rxq_info_is_reg(&priv->xdp_rxq)) {
+ err = xdp_rxq_info_reg(&priv->xdp_rxq, dev, 0);
+ if (err < 0)
+ return err;
+
+ err = xdp_rxq_info_reg_mem_model(&priv->xdp_rxq,
+ MEM_TYPE_PAGE_SHARED, NULL);
+ if (err < 0)
+ goto err;
+
+ err = veth_napi_add(dev);
+ if (err)
+ goto err;
+ }
+
+ rcu_assign_pointer(priv->xdp_prog, priv->_xdp_prog);
+
+ return 0;
+err:
+ xdp_rxq_info_unreg(&priv->xdp_rxq);
+
+ return err;
+}
+
+static void veth_disable_xdp(struct net_device *dev)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+
+ rcu_assign_pointer(priv->xdp_prog, NULL);
+ veth_napi_del(dev);
+ xdp_rxq_info_unreg(&priv->xdp_rxq);
+}
+
static int veth_open(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
struct net_device *peer = rtnl_dereference(priv->peer);
+ int err;
if (!peer)
return -ENOTCONN;
+ if (priv->_xdp_prog) {
+ err = veth_enable_xdp(dev);
+ if (err)
+ return err;
+ }
+
if (peer->flags & IFF_UP) {
netif_carrier_on(dev);
netif_carrier_on(peer);
}
+
return 0;
}
@@ -203,6 +490,9 @@ static int veth_close(struct net_device *dev)
if (peer)
netif_carrier_off(peer);
+ if (priv->_xdp_prog)
+ veth_disable_xdp(dev);
+
return 0;
}
@@ -228,7 +518,7 @@ static void veth_dev_free(struct net_device *dev)
static void veth_poll_controller(struct net_device *dev)
{
/* veth only receives frames when its peer sends one
- * Since it's a synchronous operation, we are guaranteed
+ * Since it has nothing to do with disabling irqs, we are guaranteed
* never to have pending data when we poll for it so
* there is nothing to do here.
*
@@ -276,6 +566,72 @@ static void veth_set_rx_headroom(struct net_device *dev, int new_hr)
rcu_read_unlock();
}
+static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+ struct netlink_ext_ack *extack)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+ struct bpf_prog *old_prog;
+ struct net_device *peer;
+ int err;
+
+ old_prog = priv->_xdp_prog;
+ priv->_xdp_prog = prog;
+ peer = rtnl_dereference(priv->peer);
+
+ if (prog) {
+ if (!peer) {
+ NL_SET_ERR_MSG_MOD(extack, "Cannot set XDP when peer is detached");
+ err = -ENOTCONN;
+ goto err;
+ }
+
+ if (dev->flags & IFF_UP) {
+ err = veth_enable_xdp(dev);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Setup for XDP failed");
+ goto err;
+ }
+ }
+ }
+
+ if (old_prog) {
+ if (!prog && dev->flags & IFF_UP)
+ veth_disable_xdp(dev);
+ bpf_prog_put(old_prog);
+ }
+
+ return 0;
+err:
+ priv->_xdp_prog = old_prog;
+
+ return err;
+}
+
+static u32 veth_xdp_query(struct net_device *dev)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+ const struct bpf_prog *xdp_prog;
+
+ xdp_prog = priv->_xdp_prog;
+ if (xdp_prog)
+ return xdp_prog->aux->id;
+
+ return 0;
+}
+
+static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+ switch (xdp->command) {
+ case XDP_SETUP_PROG:
+ return veth_xdp_set(dev, xdp->prog, xdp->extack);
+ case XDP_QUERY_PROG:
+ xdp->prog_id = veth_xdp_query(dev);
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
static const struct net_device_ops veth_netdev_ops = {
.ndo_init = veth_dev_init,
.ndo_open = veth_open,
@@ -290,6 +646,7 @@ static void veth_set_rx_headroom(struct net_device *dev, int new_hr)
.ndo_get_iflink = veth_get_iflink,
.ndo_features_check = passthru_features_check,
.ndo_set_rx_headroom = veth_set_rx_headroom,
+ .ndo_bpf = veth_xdp,
};
#define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
@@ -451,10 +808,13 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
*/
priv = netdev_priv(dev);
+ priv->dev = dev;
rcu_assign_pointer(priv->peer, peer);
priv = netdev_priv(peer);
+ priv->dev = peer;
rcu_assign_pointer(priv->peer, dev);
+
return 0;
err_register_dev:
--
1.8.3.1
^ permalink raw reply related
* [PATCH v7 bpf-next 01/10] net: Export skb_headers_offset_update
From: Toshiaki Makita @ 2018-08-02 10:55 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann
Cc: Toshiaki Makita, netdev, Jesper Dangaard Brouer, Jakub Kicinski,
John Fastabend
In-Reply-To: <1533207314-2572-1-git-send-email-makita.toshiaki@lab.ntt.co.jp>
This is needed for veth XDP which does skb_copy_expand()-like operation.
v2:
- Drop skb_copy_header part because it has already been exported now.
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
---
include/linux/skbuff.h | 1 +
net/core/skbuff.c | 3 ++-
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index fd3cb1b..f692968 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1035,6 +1035,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
}
struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
+void skb_headers_offset_update(struct sk_buff *skb, int off);
int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask);
struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority);
void skb_copy_header(struct sk_buff *new, const struct sk_buff *old);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 266b954..f5670e6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1291,7 +1291,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
}
EXPORT_SYMBOL(skb_clone);
-static void skb_headers_offset_update(struct sk_buff *skb, int off)
+void skb_headers_offset_update(struct sk_buff *skb, int off)
{
/* Only adjust this if it actually is csum_start rather than csum */
if (skb->ip_summed == CHECKSUM_PARTIAL)
@@ -1305,6 +1305,7 @@ static void skb_headers_offset_update(struct sk_buff *skb, int off)
skb->inner_network_header += off;
skb->inner_mac_header += off;
}
+EXPORT_SYMBOL(skb_headers_offset_update);
void skb_copy_header(struct sk_buff *new, const struct sk_buff *old)
{
--
1.8.3.1
^ permalink raw reply related
* [PATCH v7 bpf-next 00/10] veth: Driver XDP
From: Toshiaki Makita @ 2018-08-02 10:55 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann
Cc: Toshiaki Makita, netdev, Jesper Dangaard Brouer, Jakub Kicinski,
John Fastabend
This patch set introduces driver XDP for veth.
Basically this is used in conjunction with redirect action of another XDP
program.
NIC -----------> veth===veth
(XDP) (redirect) (XDP)
In this case xdp_frame can be forwarded to the peer veth without
modification, so we can expect far better performance than generic XDP.
Envisioned use-cases
--------------------
* Container managed XDP program
Container host redirects frames to containers by XDP redirect action, and
privileged containers can deploy their own XDP programs.
* XDP program cascading
Two or more XDP programs can be called for each packet by redirecting
xdp frames to veth.
* Internal interface for an XDP bridge
When using XDP redirection to create a virtual bridge, veth can be used
to create an internal interface for the bridge.
Implementation
--------------
This changeset is making use of NAPI to implement ndo_xdp_xmit and
XDP_TX/REDIRECT. This is mainly because XDP heavily relies on NAPI
context.
- patch 1: Export a function needed for veth XDP.
- patch 2-3: Basic implementation of veth XDP.
- patch 4-6: Add ndo_xdp_xmit.
- patch 7-9: Add XDP_TX and XDP_REDIRECT.
- patch 10: Performance optimization for multi-queue env.
Tests and performance numbers
-----------------------------
Tested with a simple XDP program which only redirects packets between
NIC and veth. I used i40e 25G NIC (XXV710) for the physical NIC. The
server has 20 of Xeon Silver 2.20 GHz cores.
pktgen --(wire)--> XXV710 (i40e) <--(XDP redirect)--> veth===veth (XDP)
The rightmost veth loads XDP progs and just does DROP or TX. The number
of packets is measured in the XDP progs. The leftmost pktgen sends
packets at 37.1 Mpps (almost 25G wire speed).
veth XDP action Flows Mpps
================================
DROP 1 10.6
DROP 2 21.2
DROP 100 36.0
TX 1 5.0
TX 2 10.0
TX 100 31.0
I also measured netperf TCP_STREAM but was not so great performance due
to lack of tx/rx checksum offload and TSO, etc.
netperf <--(wire)--> XXV710 (i40e) <--(XDP redirect)--> veth===veth (XDP PASS)
Direction Flows Gbps
==============================
external->veth 1 20.8
external->veth 2 23.5
external->veth 100 23.6
veth->external 1 9.0
veth->external 2 17.8
veth->external 100 22.9
Also tested doing ifup/down or load/unload a XDP program repeatedly
during processing XDP packets in order to check if enabling/disabling
NAPI is working as expected, and found no problems.
v7:
- Introduce xdp_scrub_frame() to clear kernel pointers in xdp_frame and
use it instead of memset().
v6:
- Check skb->len only if reallocation is needed.
- Add __GFP_NOWARN to alloc_page() since it can be triggered by external
events.
- Fix sparse warning around EXPORT_SYMBOL.
v5:
- Fix broken SOBs.
v4:
- Don't adjust MTU automatically.
- Skip peer IFF_UP check on .ndo_xdp_xmit() because it is unnecessary.
Add comments to explain that.
- Use redirect_info instead of xdp_mem_info for storing no_direct flag
to avoid per packet copy cost.
v3:
- Drop skb bulk xmit patch since it makes little performance
difference. The hotspot in TCP skb xmit at this point is checksum
computation in skb_segment and packet copy on XDP_REDIRECT due to
cloned/nonlinear skb.
- Fix race on closing device.
- Add extack messages in ndo_bpf.
v2:
- Squash NAPI patch with "Add driver XDP" patch.
- Remove conversion from xdp_frame to skb when NAPI is not enabled.
- Introduce per-queue XDP ring (patch 8).
- Introduce bulk skb xmit when XDP is enabled on the peer (patch 9).
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Toshiaki Makita (10):
net: Export skb_headers_offset_update
veth: Add driver XDP
veth: Avoid drops by oversized packets when XDP is enabled
xdp: Helper function to clear kernel pointers in xdp_frame
veth: Handle xdp_frames in xdp napi ring
veth: Add ndo_xdp_xmit
bpf: Make redirect_info accessible from modules
xdp: Helpers for disabling napi_direct of xdp_return_frame
veth: Add XDP TX and REDIRECT
veth: Support per queue XDP ring
drivers/net/veth.c | 748 ++++++++++++++++++++++++++++++++++++++++++++++++-
include/linux/filter.h | 35 +++
include/linux/skbuff.h | 1 +
include/net/xdp.h | 7 +
net/core/filter.c | 29 +-
net/core/skbuff.c | 3 +-
net/core/xdp.c | 6 +-
7 files changed, 799 insertions(+), 30 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH net-next] net: Fix coding style in skb_push()
From: Ganesh Goudar @ 2018-08-02 10:04 UTC (permalink / raw)
To: netdev, davem; +Cc: arjun, Ganesh Goudar
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
---
net/core/skbuff.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 266b954..51b0a912 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1715,7 +1715,7 @@ void *skb_push(struct sk_buff *skb, unsigned int len)
{
skb->data -= len;
skb->len += len;
- if (unlikely(skb->data<skb->head))
+ if (unlikely(skb->data < skb->head))
skb_under_panic(skb, len, __builtin_return_address(0));
return skb->data;
}
--
2.1.0
^ permalink raw reply related
* [PATCH net-next] net/tls: Mark the end in scatterlist table
From: Vakul Garg @ 2018-08-02 15:13 UTC (permalink / raw)
To: netdev; +Cc: borisp, aviadye, davejwatson, davem, Vakul Garg
Function zerocopy_from_iter() unmarks the 'end' in input sgtable while
adding new entries in it. The last entry in sgtable remained unmarked.
This results in KASAN error report on using apis like sg_nents(). Before
returning, the function needs to mark the 'end' in the last entry it
adds.
Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
---
net/tls/tls_sw.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index ff3a6904a722..83d67df33f0c 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -311,6 +311,9 @@ static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
}
}
+ /* Mark the end in the last sg entry if newly added */
+ if (num_elem > *pages_used)
+ sg_mark_end(&to[num_elem - 1]);
out:
if (rc)
iov_iter_revert(from, size - *size_used);
--
2.13.6
^ permalink raw reply related
* UDP packets arriving on wrong sockets
From: Andrew Cann @ 2018-08-02 9:05 UTC (permalink / raw)
To: netdev
[-- Attachment #1: Type: text/plain, Size: 1538 bytes --]
Hi,
I posted this on stackoverflow yesterday but I'm reposting it here since it got
no response. Original post: https://stackoverflow.com/questions/51630337/udp-packets-arriving-on-wrong-sockets-on-linux
I have two UDP sockets bound to the same address and connected to addresses A
and B. I have two more UDP sockets bound to A and B and not connected.
This is what my /proc/net/udp looks like (trimmed for readability):
sl local_address rem_address
3937: 0100007F:DD9C 0300007F:9910
3937: 0100007F:DD9C 0200007F:907D
16962: 0200007F:907D 00000000:0000
19157: 0300007F:9910 00000000:0000
According to connect(2): "If the socket sockfd is of type SOCK_DGRAM, then addr
is the address to which datagrams are sent by default, *and the only address
from which datagrams are received*."
For some reason, my connected sockets are receiving packets that were destined
for each other. eg: The UDP socket connected to A sends a message to A, A then
sends a reply back. The UDP socket connected to B sends a message to B, B then
sends a reply back. But the reply from A arrives at the socket connected to B
and the reply from B arrives at the socket connected to A.
Why on earth would this be happening? Note that it happens randomly - sometimes
the replies arrive at the correct sockets and sometimes they don't. Is there
any way to prevent this or any situation under which connect() is supposed to
not work?
Any help explaining this would be hugely appreciated :)
- Andrew
[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply
* Hello
From: Nelson Lizy @ 2018-08-02 9:28 UTC (permalink / raw)
Dear Friend,
Please i need your kind Assistance. I will be very glad if you can
assist me to receive this sum of ( $22. Million US dollars.) into your
bank account for the benefit of our both families, reply me if you are
ready to receive this fund.
^ permalink raw reply
* Hello
From: Nelson Lizy @ 2018-08-02 9:28 UTC (permalink / raw)
Dear Friend,
Please i need your kind Assistance. I will be very glad if you can
assist me to receive this sum of ( $22. Million US dollars.) into your
bank account for the benefit of our both families, reply me if you are
ready to receive this fund.
^ permalink raw reply
* Hello
From: Nelson Lizy @ 2018-08-02 9:28 UTC (permalink / raw)
Dear Friend,
Please i need your kind Assistance. I will be very glad if you can
assist me to receive this sum of ( $22. Million US dollars.) into your
bank account for the benefit of our both families, reply me if you are
ready to receive this fund.
^ permalink raw reply
* Re: [RFC bpf-next 3/3] docs: Split filter.txt into separate documents.
From: Tobin C. Harding @ 2018-08-02 11:03 UTC (permalink / raw)
To: Daniel Borkmann
Cc: Alexei Starovoitov, Jonathan Corbet, David S. Miller,
Jay Schulist, linux-doc, netdev, linux-kernel
In-Reply-To: <514b4a99-5ebd-9bb5-f6f3-99fe1b19c25d@iogearbox.net>
On Thu, Aug 02, 2018 at 10:02:50AM +0200, Daniel Borkmann wrote:
> On 08/02/2018 08:28 AM, Tobin C. Harding wrote:
> > In preparation for conversion of Documentation/networking/filter.txt it was
> > noticed that the document contains a lot of information. The document may be
> > more accessible if it was split up. Some parts pertain to everyone, let's put
> > these bits in core-api/. The more hard core bits about eBPF internals could be
> > put with the other BPF docs in Documentation/bpf/. There is a small bit of
> > information on testing and miscellaneous matters that are useful for everyone
> > (everyone does testing, right) so lets keep that info at the bottom of both new
> > documents. (This includes the original authors.)
> >
> > Split Documentation/networking/filter.txt into Documentation/bpf/eBPF.rst and
> > Documentation/core-api/bpf.rst
> >
> > Cc: Jay Schulist <jschlst@samba.org>
> > Cc: Daniel Borkmann <daniel@iogearbox.net>
> > Cc; Alexei Starovoitov <ast@kernel.org>
> > Signed-off-by: Tobin C. Harding <me@tobin.cc>
> > ---
> > Documentation/networking/filter.txt | 1480 ---------------------------
> > 1 file changed, 1480 deletions(-)
> > delete mode 100644 Documentation/networking/filter.txt
>
> Missing git add given the new files are not present here?
Fail! Not reading the whole patch before sending it - Bad Tobin,no
biscuit.
> Overall I agree it would be good if we move all the content over into
> Documentation/bpf/ eventually, but would be useful to see a full diff.
Thanks for your very patient and polite response. I'll send it in the
morning to save embarrassing myself with any other late night errors.
Tobin
^ permalink raw reply
* AW: AW: AW: PROBLEM: Kernel Oops in UDP stack
From: Marcel Hellwig @ 2018-08-02 11:02 UTC (permalink / raw)
To: 'Eric Dumazet', Paolo Abeni,
'davem@davemloft.net', 'kuznet@ms2.inr.ac.ru',
'yoshfuji@linux-ipv6.org', 'andrew@lunn.ch'
Cc: 'netdev@vger.kernel.org',
'linux-kernel@vger.kernel.org', Matthias Wystrik
In-Reply-To: <1ae1b19241734bfaacff082d241932f9@ZCOM03.mut-group.com>
Hi everyone,
I did three things that evening.
* I created a small dts file, so I could boot a 3.5.7 kernel.
* Ported the pskb_expand_head from 3.5.7 to 3.4.113
* Ported the whole skbuf.{c,h} file from 3.5.7 to 3.4.113
Sadly enough the second and third one panicked as well, but interestingly not the first one (3.5.7 with a simple dts file). Now the question is: Is something changed outside of the skbuf (maybe in udp.{c,h}?) or is it because the dts uses a different approach of talking to the MAC of the lpc3250?
I may try a more recent kernel with a dts file (maybe a 4.x.x one), but I think that will be impossible to backport a patch for our 2.6 kernel :(
If anybody has any more ideas about why the dts kernel does not panic, you're very welcome.
Mit freundlichen Grüßen / With kind regards
Marcel Hellwig
B. Sc. Informatik
Entwickler
m-u-t GmbH
Am Marienhof 2
22880 Wedel
Germany
Phone: +49 4103 9308 - 474
Fax: +49 4103 9308 - 99
mhellwig@mut-group.com
www.mut-group.com
Geschäftsführer (Managing Director): Fabian Peters
Amtsgericht Pinneberg (Commercial Register No.): HRB 10304 PI
USt-IdNr. (VAT-No.): DE228275390
WEEE-Reg-Nr.: DE 72271808
^ permalink raw reply
* Re: [PATCH v6 bpf-next 00/14] bpf: cgroup local storage
From: Daniel Borkmann @ 2018-08-02 8:53 UTC (permalink / raw)
To: Roman Gushchin, netdev
Cc: linux-kernel, kernel-team, Alexei Starovoitov, Martin KaFai Lau
In-Reply-To: <20180801223740.11252-1-guro@fb.com>
On 08/02/2018 12:37 AM, Roman Gushchin wrote:
> This patchset implements cgroup local storage for bpf programs.
> The main idea is to provide a fast accessible memory for storing
> various per-cgroup data, e.g. number of transmitted packets.
>
> Cgroup local storage looks as a special type of map for userspace,
> and is accessible using generic bpf maps API for reading and
> updating of the data. The (cgroup inode id, attachment type) pair
> is used as a map key.
>
> A user can't create new entries or destroy existing entries;
> it happens automatically when a user attaches/detaches a bpf program
> to a cgroup.
>
> From a bpf program's point of view, cgroup storage is accessible
> without lookup using the special get_local_storage() helper function.
> It takes a map fd as an argument. It always returns a valid pointer
> to the corresponding memory area.
> To implement such a lookup-free access a pointer to the cgroup
> storage is saved for an attachment of a bpf program to a cgroup,
> if required by the program. Before running the program, it's saved
> in a special global per-cpu variable, which is accessible from the
> get_local_storage() helper.
>
> This patchset implement only cgroup local storage, however the API
> is intentionally made extensible to support other local storage types
> further: e.g. thread local storage, socket local storage, etc.
>
> Patch (1) adds an ability to charge bpf maps for consuming memory
> dynamically.
> Patch (2) introduces cgroup storage maps.
> Patch (3) implements a mechanism to pass cgroup storage pointer
> to a bpf program.
> Patch (4) implements allocation/releasing of cgroup local storage
> on attaching/detaching of a bpf program to/from a cgroup.
> Patch (5) extends bpf_prog_array to store cgroup storage pointers.
> Patch (6) introduces BPF_PTR_TO_MAP_VALUE, required to skip
> non-necessary NULL-check in bpf programs.
> Patch (7) disables creation of maps of cgroup storage maps.
> Patch (8) introduces the get_local_storage() helper.
> Patch (9) syncs bpf.h to tools/.
> Patch (10) adds cgroup storage maps support to bpftool.
> Patch (11) adds support for testing programs which are using
> cgroup storage without actually attaching them to cgroups.
> Patches (12), (13) and (14) are adding necessary tests.
>
> Signed-off-by: Roman Gushchin <guro@fb.com>
> Cc: Alexei Starovoitov <ast@kernel.org>
> Cc: Daniel Borkmann <daniel@iogearbox.net>
> Cc: Martin KaFai Lau <kafai@fb.com>
>
> v6->v5:
> - fixed an error with returning -EINVAL instead of a pointer
>
> v5->v4:
> - fixed an issue in verifier (test that flags == 0 properly)
> - added a corresponding test
> - added a note about synchronization, sync docs to tools/uapi/...
> - switched the cgroup test to use XADD
> - added a check for attr->max_entries to be 0, and atter->max_flags
> to be sane
> - use bpf_uncharge_memlock() in bpf_uncharge_memlock()
> - rebased to bpf-next
>
> v4->v3:
> - fixed a leak in cgroup attachment code (discovered by Daniel)
> - cgroup storage map will be released if the corresponding
> bpf program failed to load by any reason
> - introduced bpf_uncharge_memlock() helper
>
> v3->v2:
> - fixed more build and sparse issues
> - rebased to bpf-next
>
> v2->v1:
> - fixed build issues
> - removed explicit rlimit calls in patch 14
> - rebased to bpf-next
>
> Roman Gushchin (14):
> bpf: add ability to charge bpf maps memory dynamically
> bpf: introduce cgroup storage maps
> bpf: pass a pointer to a cgroup storage using pcpu variable
> bpf: allocate cgroup storage entries on attaching bpf programs
> bpf: extend bpf_prog_array to store pointers to the cgroup storage
> bpf/verifier: introduce BPF_PTR_TO_MAP_VALUE
> bpf: don't allow create maps of cgroup local storages
> bpf: introduce the bpf_get_local_storage() helper function
> bpf: sync bpf.h to tools/
> bpftool: add support for CGROUP_STORAGE maps
> bpf/test_run: support cgroup local storage
> selftests/bpf: add verifier cgroup storage tests
> selftests/bpf: add a cgroup storage test
> samples/bpf: extend test_cgrp2_attach2 test to use cgroup storage
Applied to bpf-next, thanks Roman!
^ permalink raw reply
* [PATCH v2] net: fec: check DMA addressing limitations
From: Stefan Agner @ 2018-08-02 8:42 UTC (permalink / raw)
To: fugang.duan, davem; +Cc: krzk, robin.murphy, netdev, linux-kernel, Stefan Agner
Check DMA addressing limitations as suggested by the DMA API
how-to. This does not fix a particular issue seen but is
considered good style.
Signed-off-by: Stefan Agner <stefan@agner.ch>
---
drivers/net/ethernet/freescale/fec_main.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index c729665107f5..cdf2f5447910 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3136,6 +3136,7 @@ static int fec_enet_init(struct net_device *ndev)
unsigned dsize = fep->bufdesc_ex ? sizeof(struct bufdesc_ex) :
sizeof(struct bufdesc);
unsigned dsize_log2 = __fls(dsize);
+ int ret;
WARN_ON(dsize != (1 << dsize_log2));
#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
@@ -3146,6 +3147,13 @@ static int fec_enet_init(struct net_device *ndev)
fep->tx_align = 0x3;
#endif
+ /* Check mask of the streaming and coherent API */
+ ret = dma_set_mask_and_coherent(&fep->pdev->dev, DMA_BIT_MASK(32));
+ if (ret < 0) {
+ dev_warn(&fep->pdev->dev, "No suitable DMA available\n");
+ return ret;
+ }
+
fec_enet_alloc_queue(ndev);
bd_size = (fep->total_tx_ring_size + fep->total_rx_ring_size) * dsize;
--
2.18.0
^ permalink raw reply related
* [PATCH 1/1] selftest/net: fix FILE_SIZE for 32 bit architecture.
From: Maninder Singh @ 2018-08-02 10:31 UTC (permalink / raw)
To: davem, shuahkh
Cc: netdev, linux-api, linux-kernel, edumazet, pankaj.m, a.sahrawat,
Maninder Singh, Vaneet Narang
In-Reply-To: <CGME20180802103616epcas5p48ec1e2ea3568b11683aa7b55254dffb0@epcas5p4.samsung.com>
FILE_SZ is defined as (1UL << 35), it will overflow
for 32 bit system and logic will break.
Signed-off-by: Maninder Singh <maninder1.s@samsung.com>
Signed-off-by: Vaneet Narang <v.narang@samsung.com>
---
tools/testing/selftests/net/tcp_mmap.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index e8c5dff..1d6ca12 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -85,7 +85,7 @@
#define MSG_ZEROCOPY 0x4000000
#endif
-#define FILE_SZ (1UL << 35)
+#define FILE_SZ (1ULL << 35)
static int cfg_family = AF_INET6;
static socklen_t cfg_alen = sizeof(struct sockaddr_in6);
static int cfg_port = 8787;
@@ -134,7 +134,7 @@ void hash_zone(void *zone, unsigned int length)
void *child_thread(void *arg)
{
- unsigned long total_mmap = 0, total = 0;
+ unsigned long long total_mmap = 0, total = 0;
struct tcp_zerocopy_receive zc;
unsigned long delta_usec;
int flags = MAP_SHARED;
@@ -316,7 +316,7 @@ int main(int argc, char *argv[])
{
struct sockaddr_storage listenaddr, addr;
unsigned int max_pacing_rate = 0;
- unsigned long total = 0;
+ unsigned long long total = 0;
char *host = NULL;
int fd, c, on = 1;
char *buffer;
@@ -431,7 +431,7 @@ int main(int argc, char *argv[])
zflg = 0;
}
while (total < FILE_SZ) {
- long wr = FILE_SZ - total;
+ unsigned long long wr = FILE_SZ - total;
if (wr > chunk_size)
wr = chunk_size;
--
1.9.1
^ permalink raw reply related
* Re: [PATCH net-next 5/9] net: stmmac: Add MDIO related functions for XGMAC2
From: Jose Abreu @ 2018-08-02 8:36 UTC (permalink / raw)
To: Andrew Lunn, Jose Abreu
Cc: netdev, David S. Miller, Joao Pinto, Giuseppe Cavallaro,
Alexandre Torgue
In-Reply-To: <20180801150812.GD32125@lunn.ch>
Hi Andrew,
On 01-08-2018 16:08, Andrew Lunn wrote:
> Hi Jose
>
>> +static int stmmac_xgmac2_mdio_read(struct stmmac_priv *priv, int phyaddr,
>> + int phyreg)
>> +{
>> + unsigned int mii_address = priv->hw->mii.addr;
>> + unsigned int mii_data = priv->hw->mii.data;
>> + u32 tmp, addr, value = MII_XGMAC_BUSY;
>> + int data;
>> +
>> + if (phyreg & MII_ADDR_C45) {
>> + addr = ((phyreg >> 16) & 0x1f) << 21;
>> + addr |= (phyaddr << 16) | (phyreg & 0xffff);
> Do you need to tell the hardware this is a C45 transfer? Normally an
> extra bit needs setting somewhere.
The organization of addr reg is the following:
DA [25:21] | PA [20:16] | RA [15:0]
DA is Device Address, PA is Port Address and RA is Register Address.
>
>> + } else {
>> + if (phyaddr >= 4)
>> + return -ENODEV;
> Can the MDIO bus be external? If so, is there a reason why there
> cannot be a PHY at addresses > 4. So maybe there is an Ethernet
> switch, which needs lots of addresses? And C45 can have devices > 4
> but C22 cannot?
Only ports 0 to 3 can be configured as C22 ports, according to
databook. This for MDIO bus trough controller.
>
>> + writel(~0x0, priv->ioaddr + 0x220);
>> + addr = (phyaddr << 16) | (phyreg & 0x1f);
>> + }
>> +
>> + value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift)
>> + & priv->hw->mii.clk_csr_mask;
>> + value |= BIT(18);
> Please add a #define for this bit.
Ok.
>
>> + value |= MII_XGMAC_READ;
>> +
>> + if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
>> + !(tmp & MII_XGMAC_BUSY), 100, 10000))
>> + return -EBUSY;
>> +
>> + writel(addr, priv->ioaddr + mii_address);
>> + writel(value, priv->ioaddr + mii_data);
>> +
>> + if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
>> + !(tmp & MII_XGMAC_BUSY), 100, 10000))
>> + return -EBUSY;
>> +
>> + /* Read the data from the MII data register */
>> + data = (int)readl(priv->ioaddr + mii_data) & GENMASK(15, 0);
> Is the cast needed? And why use GENMASK here, but not in all the other
> places you have masks in this code?
The GENMASK is needed, notice how we set more values into
mii_data (clk_csr, bit(18), cmd), this is not cleared by XGMAC2
upon the completion of the operation ...
>
>> /**
>> * stmmac_mdio_read
>> * @bus: points to the mii_bus structure
>> @@ -59,6 +141,9 @@ static int stmmac_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg)
>> int data;
>> u32 value = MII_BUSY;
>>
>> + if (priv->plat->has_xgmac)
>> + return stmmac_xgmac2_mdio_read(priv, phyaddr, phyreg);
> It would be cleaner to instead do this in stmmac_mdio_register() when
> setting new_bus->read.
Makes sense! Thanks!
Thanks and Best Regards,
Jose Miguel Abreu
>
> Andrew
^ permalink raw reply
* Re: [pull request][net-next 00/10] Mellanox, mlx5 and devlink updates 2018-07-31
From: Petr Machata @ 2018-08-02 8:29 UTC (permalink / raw)
To: David Miller
Cc: jakub.kicinski, saeedm, netdev, jiri, alexander.duyck, helgaas
In-Reply-To: <20180801.184035.163038060223453766.davem@davemloft.net>
David Miller <davem@davemloft.net> writes:
> From: Jakub Kicinski <jakub.kicinski@netronome.com>
> Date: Wed, 1 Aug 2018 17:00:47 -0700
>
>> On Wed, 1 Aug 2018 14:52:45 -0700, Saeed Mahameed wrote:
>>> - According to the discussion outcome, we are keeping the congestion control
>>> setting as mlx5 device specific for the current HW generation.
>>
>> I still see queuing and marking based on queue level. You want to add
>> a Qdisc that will mirror your HW's behaviour to offload, if you really
>> believe this is not a subset of RED, why not... But devlink params?
>
> I totally agree, devlink seems like absolutely to wrong level and set
> of interfaces to be doing this stuff.
>
> I will not pull these changes in and I probably should have not
> accepted the DCB changes from the other day and they were sneakily
> leading up to this crap.
Are you talking about the recent additions of DCB helpers
dcb_ieee_getapp_prio_dscp_mask_map() etc.?
If yes, I can assure there were no sneaky intentions at all. I'm at a
loss to understand the relation to mlx5 team's decision to use devlink
for congestion control configuration.
Could you please clarify your remark?
Thanks,
Petr
^ permalink raw reply
* Re: [PATCH net-next 7/9] net: stmmac: Integrate XGMAC into main driver flow
From: Jose Abreu @ 2018-08-02 8:26 UTC (permalink / raw)
To: Andrew Lunn, Jose Abreu
Cc: netdev, David S. Miller, Joao Pinto, Giuseppe Cavallaro,
Alexandre Torgue
In-Reply-To: <20180801152330.GE32125@lunn.ch>
Hi Andrew,
Thanks for the review!
On 01-08-2018 16:23, Andrew Lunn wrote:
>> @@ -842,6 +863,12 @@ static void stmmac_adjust_link(struct net_device *dev)
>> new_state = true;
>> ctrl &= ~priv->hw->link.speed_mask;
>> switch (phydev->speed) {
>> + case SPEED_10000:
>> + ctrl |= priv->hw->link.speed10000;
>> + break;
>> + case SPEED_2500:
>> + ctrl |= priv->hw->link.speed2500;
>> + break;
>> case SPEED_1000:
>> ctrl |= priv->hw->link.speed1000;
>> break;
> Hi Jose
>
> What PHY did you test this with?
We had some shipping issues with the 10G phy so right now I'm
using a 1G phy ... I would expect that as MDIO is used in both
phys then phylib would take care of everything as long as I
specify in the DT the right interface (SGMII) ... Am I making a
wrong assumption?
>
> 10G phys change the interface mode when the speed change. In general,
> 10/100/1000G copper uses SGMII. A 1G SFP optical module generally
> wants 1000Base-X. 2.5G wants 2500Base-X, 10G copper wants 10GKR, etc.
>
> So your adjust link callback needs to look at phydev->interface and
> reconfigure the MAC as requested.
Sorry, I'm not a phy expert but as long as I use MDIO shouldn't
this be transparent to MAC? I mean, there are no registers about
the interface to use in XGMAC2, there is only this speed
selection register that its implemented already in the
stmmac_adjust_link.
>
> You might also want to consider moving from phylib to phylink. It has
> a better interface for things like this, and makes support for SFP
> interfaces much easier. A MAC which supports 10G is likely to be used
> with SFPs...
Ok, I will take a look into it.
Thanks and Best Regards,
Jose Miguel Abreu
>
> Andrew
^ permalink raw reply
* Re: [PATCH net-next v7 3/4] net: vhost: factor out busy polling logic to vhost_net_busy_poll()
From: Jason Wang @ 2018-08-02 8:18 UTC (permalink / raw)
To: Tonghao Zhang
Cc: mst, makita.toshiaki, virtualization,
Linux Kernel Network Developers
In-Reply-To: <CAMDZJNWX7L4P0yO+-PeDFu_tmtLSntihO7rcLPB2GK4eN9zbwQ@mail.gmail.com>
On 2018年08月01日 17:52, Tonghao Zhang wrote:
>>> +
>>> + cpu_relax();
>>> + }
>>> +
>>> + preempt_enable();
>>> +
>>> + if (!rx)
>>> + vhost_net_enable_vq(net, vq);
>> No need to enable rx virtqueue, if we are sure handle_rx() will be
>> called soon.
> If we disable rx virtqueue in handle_tx and don't send packets from
> guest anymore(handle_tx is not called), so we can wake up for sock rx.
> so the network is broken.
Not sure I understand here. I mean is we schedule work for handle_rx(),
there's no need to enable it since handle_rx() will do this for us.
Thanks
^ permalink raw reply
* [PATCH net-next v2 3/3] qed: Add Multi-TC RoCE support
From: Denis Bolotin @ 2018-08-02 8:12 UTC (permalink / raw)
To: davem, netdev; +Cc: Denis Bolotin, Ariel Elior
In-Reply-To: <20180802081251.10003-1-denis.bolotin@cavium.com>
RoCE qps use a pair of physical queues (pq) received from the Queue Manager
(QM) - an offload queue (OFLD) and a low latency queue (LLT). The QM block
creates a pq for each TC, and allows RoCE qps to ask for a pq with a
specific TC. As a result, qps with different VLAN priorities can be mapped
to different TCs, and employ features such as PFC and ETS.
Signed-off-by: Denis Bolotin <denis.bolotin@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
---
drivers/net/ethernet/qlogic/qed/qed.h | 10 ++-
drivers/net/ethernet/qlogic/qed/qed_dev.c | 104 +++++++++++++++++++++++++----
drivers/net/ethernet/qlogic/qed/qed_roce.c | 61 ++++++++++++-----
3 files changed, 143 insertions(+), 32 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index f916f13..a60e1c8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -338,6 +338,9 @@ struct qed_hw_info {
u8 offload_tc;
bool offload_tc_set;
+ bool multi_tc_roce_en;
+#define IS_QED_MULTI_TC_ROCE(p_hwfn) (((p_hwfn)->hw_info.multi_tc_roce_en))
+
u32 concrete_fid;
u16 opaque_fid;
u16 ovlan;
@@ -400,8 +403,8 @@ struct qed_qm_info {
u16 start_pq;
u8 start_vport;
u16 pure_lb_pq;
- u16 offload_pq;
- u16 low_latency_pq;
+ u16 first_ofld_pq;
+ u16 first_llt_pq;
u16 pure_ack_pq;
u16 ooo_pq;
u16 first_vf_pq;
@@ -882,11 +885,14 @@ void qed_set_fw_mac_addr(__le16 *fw_msb,
#define PQ_FLAGS_OFLD (BIT(5))
#define PQ_FLAGS_VFS (BIT(6))
#define PQ_FLAGS_LLT (BIT(7))
+#define PQ_FLAGS_MTC (BIT(8))
/* physical queue index for cm context intialization */
u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags);
u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc);
u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf);
+u16 qed_get_cm_pq_idx_ofld_mtc(struct qed_hwfn *p_hwfn, u8 tc);
+u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc);
#define QED_LEADING_HWFN(dev) (&dev->hwfns[0])
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index a8e7683..04f18bc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -215,6 +215,8 @@ static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn)
break;
case QED_PCI_ETH_ROCE:
flags |= PQ_FLAGS_MCOS | PQ_FLAGS_OFLD | PQ_FLAGS_LLT;
+ if (IS_QED_MULTI_TC_ROCE(p_hwfn))
+ flags |= PQ_FLAGS_MTC;
break;
case QED_PCI_ETH_IWARP:
flags |= PQ_FLAGS_MCOS | PQ_FLAGS_ACK | PQ_FLAGS_OOO |
@@ -241,6 +243,16 @@ static u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn)
p_hwfn->cdev->p_iov_info->total_vfs : 0;
}
+static u8 qed_init_qm_get_num_mtc_tcs(struct qed_hwfn *p_hwfn)
+{
+ u32 pq_flags = qed_get_pq_flags(p_hwfn);
+
+ if (!(PQ_FLAGS_MTC & pq_flags))
+ return 1;
+
+ return qed_init_qm_get_num_tcs(p_hwfn);
+}
+
#define NUM_DEFAULT_RLS 1
static u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
@@ -282,8 +294,11 @@ static u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn)
(!!(PQ_FLAGS_MCOS & pq_flags)) *
qed_init_qm_get_num_tcs(p_hwfn) +
(!!(PQ_FLAGS_LB & pq_flags)) + (!!(PQ_FLAGS_OOO & pq_flags)) +
- (!!(PQ_FLAGS_ACK & pq_flags)) + (!!(PQ_FLAGS_OFLD & pq_flags)) +
- (!!(PQ_FLAGS_LLT & pq_flags)) +
+ (!!(PQ_FLAGS_ACK & pq_flags)) +
+ (!!(PQ_FLAGS_OFLD & pq_flags)) *
+ qed_init_qm_get_num_mtc_tcs(p_hwfn) +
+ (!!(PQ_FLAGS_LLT & pq_flags)) *
+ qed_init_qm_get_num_mtc_tcs(p_hwfn) +
(!!(PQ_FLAGS_VFS & pq_flags)) * qed_init_qm_get_num_vfs(p_hwfn);
}
@@ -474,9 +489,9 @@ static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn,
case PQ_FLAGS_ACK:
return &qm_info->pure_ack_pq;
case PQ_FLAGS_OFLD:
- return &qm_info->offload_pq;
+ return &qm_info->first_ofld_pq;
case PQ_FLAGS_LLT:
- return &qm_info->low_latency_pq;
+ return &qm_info->first_llt_pq;
case PQ_FLAGS_VFS:
return &qm_info->first_vf_pq;
default:
@@ -525,6 +540,43 @@ u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf)
return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_VFS) + vf;
}
+static u16 qed_get_cm_pq_offset_mtc(struct qed_hwfn *p_hwfn, u8 tc)
+{
+ u16 pq_offset = tc;
+ u8 num_tcs;
+
+ /* Verify that the pq returned is within pqs range */
+ num_tcs = qed_init_qm_get_num_mtc_tcs(p_hwfn);
+ if (pq_offset >= num_tcs) {
+ DP_ERR(p_hwfn,
+ "pq_offset %d must be smaller than %d (tc %d)\n",
+ pq_offset, num_tcs, tc);
+ return 0;
+ }
+
+ return pq_offset;
+}
+
+u16 qed_get_cm_pq_idx_ofld_mtc(struct qed_hwfn *p_hwfn, u8 tc)
+{
+ u16 first_ofld_pq, pq_offset;
+
+ first_ofld_pq = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+ pq_offset = qed_get_cm_pq_offset_mtc(p_hwfn, tc);
+
+ return first_ofld_pq + pq_offset;
+}
+
+u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc)
+{
+ u16 first_llt_pq, pq_offset;
+
+ first_llt_pq = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LLT);
+ pq_offset = qed_get_cm_pq_offset_mtc(p_hwfn, tc);
+
+ return first_llt_pq + pq_offset;
+}
+
/* Functions for creating specific types of pqs */
static void qed_init_qm_lb_pq(struct qed_hwfn *p_hwfn)
{
@@ -560,6 +612,20 @@ static void qed_init_qm_pure_ack_pq(struct qed_hwfn *p_hwfn)
PQ_INIT_SHARE_VPORT);
}
+static void qed_init_qm_mtc_pqs(struct qed_hwfn *p_hwfn)
+{
+ u8 num_tcs = qed_init_qm_get_num_mtc_tcs(p_hwfn);
+ struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+ u8 tc;
+
+ /* override pq's TC if offload TC is set */
+ for (tc = 0; tc < num_tcs; tc++)
+ qed_init_qm_pq(p_hwfn, qm_info,
+ qed_is_offload_tc_set(p_hwfn) ?
+ qed_get_offload_tc(p_hwfn) : tc,
+ PQ_INIT_SHARE_VPORT);
+}
+
static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
{
struct qed_qm_info *qm_info = &p_hwfn->qm_info;
@@ -568,8 +634,7 @@ static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
return;
qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OFLD, qm_info->num_pqs);
- qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
- PQ_INIT_SHARE_VPORT);
+ qed_init_qm_mtc_pqs(p_hwfn);
}
static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
@@ -580,8 +645,7 @@ static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
return;
qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LLT, qm_info->num_pqs);
- qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
- PQ_INIT_SHARE_VPORT);
+ qed_init_qm_mtc_pqs(p_hwfn);
}
static void qed_init_qm_mcos_pqs(struct qed_hwfn *p_hwfn)
@@ -664,12 +728,19 @@ static int qed_init_qm_sanity(struct qed_hwfn *p_hwfn)
return -EINVAL;
}
- if (qed_init_qm_get_num_pqs(p_hwfn) > RESC_NUM(p_hwfn, QED_PQ)) {
- DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n");
- return -EINVAL;
+ if (qed_init_qm_get_num_pqs(p_hwfn) <= RESC_NUM(p_hwfn, QED_PQ))
+ return 0;
+
+ if (QED_IS_ROCE_PERSONALITY(p_hwfn)) {
+ p_hwfn->hw_info.multi_tc_roce_en = 0;
+ DP_NOTICE(p_hwfn,
+ "multi-tc roce was disabled to reduce requested amount of pqs\n");
+ if (qed_init_qm_get_num_pqs(p_hwfn) <= RESC_NUM(p_hwfn, QED_PQ))
+ return 0;
}
- return 0;
+ DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n");
+ return -EINVAL;
}
static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn)
@@ -683,11 +754,13 @@ static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn)
/* top level params */
DP_VERBOSE(p_hwfn,
NETIF_MSG_HW,
- "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, pure_ack_pq %d\n",
+ "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, llt_pq %d, pure_ack_pq %d\n",
qm_info->start_pq,
qm_info->start_vport,
qm_info->pure_lb_pq,
- qm_info->offload_pq, qm_info->pure_ack_pq);
+ qm_info->first_ofld_pq,
+ qm_info->first_llt_pq,
+ qm_info->pure_ack_pq);
DP_VERBOSE(p_hwfn,
NETIF_MSG_HW,
"ooo_pq %d, first_vf_pq %d, num_pqs %d, num_vf_pqs %d, num_vports %d, max_phys_tcs_per_port %d\n",
@@ -2920,6 +2993,9 @@ static void qed_get_eee_caps(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
p_hwfn->hw_info.personality = protocol;
}
+ if (QED_IS_ROCE_PERSONALITY(p_hwfn))
+ p_hwfn->hw_info.multi_tc_roce_en = 1;
+
p_hwfn->hw_info.num_hw_tc = NUM_PHYS_TCS_4PORT_K2;
p_hwfn->hw_info.num_active_tc = 1;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index ada4c18..c60f6e9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -44,8 +44,10 @@
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/string.h>
+#include <linux/if_vlan.h>
#include "qed.h"
#include "qed_cxt.h"
+#include "qed_dcbx.h"
#include "qed_hsi.h"
#include "qed_hw.h"
#include "qed_init_ops.h"
@@ -231,16 +233,40 @@ static void qed_roce_set_real_cid(struct qed_hwfn *p_hwfn, u32 cid)
spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
}
+static u8 qed_roce_get_qp_tc(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
+{
+ u8 pri = 0, tc = 0;
+ int rc;
+
+ if (qp->vlan_id) {
+ pri = (qp->vlan_id & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+
+ /* Get the TC mapped to the VLAN priority */
+ rc = qed_dcbx_get_priority_tc(p_hwfn, pri, &tc);
+ if (rc)
+ DP_NOTICE(p_hwfn,
+ "qp icid %u: qed_dcbx_get_priority_tc failed\n",
+ qp->icid);
+ }
+
+ DP_VERBOSE(p_hwfn, QED_MSG_SP,
+ "qp icid %u tc: %u (vlan priority %s)\n",
+ qp->icid, tc, qp->vlan_id ? "enabled" : "disabled");
+
+ return tc;
+}
+
static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
struct qed_rdma_qp *qp)
{
struct roce_create_qp_resp_ramrod_data *p_ramrod;
+ u16 regular_latency_queue, low_latency_queue;
struct qed_sp_init_data init_data;
enum roce_flavor roce_flavor;
struct qed_spq_entry *p_ent;
- u16 regular_latency_queue;
enum protocol_type proto;
int rc;
+ u8 tc;
DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
@@ -324,12 +350,17 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
qp->rq_cq_id);
- regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
-
+ tc = qed_roce_get_qp_tc(p_hwfn, qp);
+ regular_latency_queue = qed_get_cm_pq_idx_ofld_mtc(p_hwfn, tc);
+ low_latency_queue = qed_get_cm_pq_idx_llt_mtc(p_hwfn, tc);
+ DP_VERBOSE(p_hwfn, QED_MSG_SP,
+ "qp icid %u pqs: regular_latency %u low_latency %u\n",
+ qp->icid, regular_latency_queue - CM_TX_PQ_BASE,
+ low_latency_queue - CM_TX_PQ_BASE);
p_ramrod->regular_latency_phy_queue =
cpu_to_le16(regular_latency_queue);
p_ramrod->low_latency_phy_queue =
- cpu_to_le16(regular_latency_queue);
+ cpu_to_le16(low_latency_queue);
p_ramrod->dpi = cpu_to_le16(qp->dpi);
@@ -345,11 +376,6 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
qp->stats_queue;
rc = qed_spq_post(p_hwfn, p_ent, NULL);
-
- DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
- "rc = %d regular physical queue = 0x%x\n", rc,
- regular_latency_queue);
-
if (rc)
goto err;
@@ -375,12 +401,13 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
struct qed_rdma_qp *qp)
{
struct roce_create_qp_req_ramrod_data *p_ramrod;
+ u16 regular_latency_queue, low_latency_queue;
struct qed_sp_init_data init_data;
enum roce_flavor roce_flavor;
struct qed_spq_entry *p_ent;
- u16 regular_latency_queue;
enum protocol_type proto;
int rc;
+ u8 tc;
DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
@@ -453,12 +480,17 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
p_ramrod->cq_cid =
cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id);
- regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
-
+ tc = qed_roce_get_qp_tc(p_hwfn, qp);
+ regular_latency_queue = qed_get_cm_pq_idx_ofld_mtc(p_hwfn, tc);
+ low_latency_queue = qed_get_cm_pq_idx_llt_mtc(p_hwfn, tc);
+ DP_VERBOSE(p_hwfn, QED_MSG_SP,
+ "qp icid %u pqs: regular_latency %u low_latency %u\n",
+ qp->icid, regular_latency_queue - CM_TX_PQ_BASE,
+ low_latency_queue - CM_TX_PQ_BASE);
p_ramrod->regular_latency_phy_queue =
cpu_to_le16(regular_latency_queue);
p_ramrod->low_latency_phy_queue =
- cpu_to_le16(regular_latency_queue);
+ cpu_to_le16(low_latency_queue);
p_ramrod->dpi = cpu_to_le16(qp->dpi);
@@ -471,9 +503,6 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
qp->stats_queue;
rc = qed_spq_post(p_hwfn, p_ent, NULL);
-
- DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d\n", rc);
-
if (rc)
goto err;
--
1.8.3.1
^ permalink raw reply related
* kernel panic: corrupted stack end detected inside scheduler (3)
From: syzbot @ 2018-08-02 8:14 UTC (permalink / raw)
To: aviadye, borisp, davejwatson, davem, linux-kernel, netdev,
syzkaller-bugs
Hello,
syzbot found the following crash on:
HEAD commit: fea49f60c9b7 net: ethernet: ti: cpsw: replace unnecessaril..
git tree: net-next
console output: https://syzkaller.appspot.com/x/log.txt?x=16d5fae8400000
kernel config: https://syzkaller.appspot.com/x/.config?x=d6a9eba95cc5dd8e
dashboard link: https://syzkaller.appspot.com/bug?extid=05b2210c521c829a20f5
compiler: gcc (GCC) 8.0.1 20180413 (experimental)
syzkaller repro:https://syzkaller.appspot.com/x/repro.syz?x=108ef064400000
C reproducer: https://syzkaller.appspot.com/x/repro.c?x=1022672c400000
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by: syzbot+05b2210c521c829a20f5@syzkaller.appspotmail.com
RBP: 00007ffdbb414a40 R08: 0000000020000000 R09: 000000000000001c
R10: 0000000000000040 R11: 0000000000000216 R12: 0000000000000004
R13: ffffffffffffffff R14: 0000000000000000 R15: 0000000000000000
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
Kernel panic - not syncing: corrupted stack end detected inside scheduler
general protection fault: 0000 [#1] SMP KASAN
CPU: 0 PID: 6188 Comm: syz-executor748 Not tainted 4.18.0-rc6+ #165
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline]
RIP: 0010:compound_head include/linux/page-flags.h:142 [inline]
RIP: 0010:put_page include/linux/mm.h:913 [inline]
RIP: 0010:tls_push_sg+0x2a3/0x880 net/tls/tls_main.c:133
Code: fb 4d 39 e5 75 a2 e8 4c 5f d6 fb 48 8b 85 08 ff ff ff 49 8d 7f 08 48
b9 00 00 00 00 00 fc ff df c6 00 00 48 89 f8 48 c1 e8 03 <80> 3c 08 00 0f
85 50 05 00 00 48 8b 85 08 ff ff ff 49 8b 5f 08 80
RSP: 0018:ffff8801c9f1f7b8 EFLAGS: 00010202
RAX: 0000000000000001 RBX: 0000000000000000 RCX: dffffc0000000000
RDX: 0000000000000000 RSI: ffffffff85a5b634 RDI: 0000000000000008
RBP: ffff8801c9f1f8d8 R08: ffff8801c7d88340 R09: 0000000000000000
R10: fffff94000e38bc6 R11: ffffea00071c5e37 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
FS: 000000000119b880(0000) GS:ffff8801db000000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f8c0bf4a000 CR3: 00000001c777e000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
tls_push_record+0xaf3/0x1400 net/tls/tls_sw.c:247
tls_sw_push_pending_record+0x22/0x30 net/tls/tls_sw.c:259
tls_handle_open_record net/tls/tls_main.c:155 [inline]
tls_sk_proto_close+0x759/0xb90 net/tls/tls_main.c:255
inet_release+0x104/0x1f0 net/ipv4/af_inet.c:428
inet6_release+0x50/0x70 net/ipv6/af_inet6.c:459
__sock_release+0xd7/0x250 net/socket.c:597
sock_close+0x19/0x20 net/socket.c:1157
__fput+0x355/0x8b0 fs/file_table.c:209
____fput+0x15/0x20 fs/file_table.c:243
task_work_run+0x1ec/0x2a0 kernel/task_work.c:113
tracehook_notify_resume include/linux/tracehook.h:192 [inline]
exit_to_usermode_loop+0x313/0x370 arch/x86/entry/common.c:166
prepare_exit_to_usermode arch/x86/entry/common.c:197 [inline]
syscall_return_slowpath arch/x86/entry/common.c:268 [inline]
do_syscall_64+0x6be/0x820 arch/x86/entry/common.c:293
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x4017f0
Code: 01 f0 ff ff 0f 83 d0 0a 00 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f
44 00 00 83 3d 3d 30 2d 00 00 75 14 b8 03 00 00 00 0f 05 <48> 3d 01 f0 ff
ff 0f 83 a4 0a 00 00 c3 48 83 ec 08 e8 5a 01 00 00
RSP: 002b:00007ffdbb414a28 EFLAGS: 00000246 ORIG_RAX: 0000000000000003
RAX: 0000000000000000 RBX: 0000000000000003 RCX: 00000000004017f0
RDX: 00000000fffffdef RSI: 00000000200005c0 RDI: 0000000000000003
RBP: 00007ffdbb414a40 R08: 0000000020000000 R09: 000000000000001c
R10: 0000000000000040 R11: 0000000000000246 R12: 0000000000000004
R13: ffffffffffffffff R14: 0000000000000000 R15: 0000000000000000
Modules linked in:
Dumping ftrace buffer:
(ftrace buffer empty)
Dumping ftrace buffer:
(ftrace buffer empty)
Kernel Offset: disabled
Rebooting in 86400 seconds..
---
This bug is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.
syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#bug-status-tracking for how to communicate with
syzbot.
syzbot can test patches for this bug, for details see:
https://goo.gl/tpsmEJ#testing-patches
^ permalink raw reply
* Re: [Query]: DSA Understanding
From: Lad, Prabhakar @ 2018-08-02 8:13 UTC (permalink / raw)
To: Andrew Lunn; +Cc: netdev
In-Reply-To: <20180726153906.GA10686@lunn.ch>
Hi Andrew,
Thank for your reply.
On Thu, Jul 26, 2018 at 4:39 PM, Andrew Lunn <andrew@lunn.ch> wrote:
>> I am bit confused on how dsa needs to be actually working,
>> Q's
>> 1] should I be running a dhcp server on eth1 (where switch is connected)
>> so that devices connected on lan* devices get an ip ?
>
> Nope. You need eth1 up, but otherwise you do not use it. Use the lanX
> interfaces like normal Linux interfaces. Run your dhclient on lanX, etc.
>>
>> 2] From the device where switch is connected if the cpu port wants to send
>> any data to any other user ports lan* how do i do it (just open
>> socket on eth1 or lan*) ?
>
> Just treat the lanX interfaces as normal Linux interfaces.
>
I have some more query’s on DSA.
I have manged to get the TI's cpsw slave1 connected to ksz9897
Ethernet switch chip partially working,
I have PC connected to lan4(ip = 169.254..126.126) and the PC ip is
169.254.78.251,
but when I ping from PC to lan4 I get Destination Host Unreachable,
but where as I can see
that in the tcpdump log for lan4 it does reply back, but it doesn’t
reach the PC, Is there I am missing
something here ?
Log from the device on which switch is present:
===================================
~$ ifconfig
eth0 Link encap:Ethernet HWaddr C4:F3:12:08:FE:7E
UP BROADCAST MULTICAST MTU:1500 Metric:1
RX packets:0 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:0 (0.0 B) TX bytes:0 (0.0 B)
Interrupt:102
eth1 Link encap:Ethernet HWaddr C4:F3:12:08:FE:7F
inet6 addr: fe80::c6f3:12ff:fe08:fe7f%lo/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:436 errors:0 dropped:0 overruns:0 frame:0
TX packets:516 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:37254 (36.3 KiB) TX bytes:51585 (50.3 KiB)
lan4 Link encap:Ethernet HWaddr C4:F3:12:08:FE:7F
inet addr:169.254.126.126 Bcast:169.254.255.255 Mask:255.255.0.0
inet6 addr: fe80::c6f3:12ff:fe08:fe7f%lo/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:436 errors:0 dropped:0 overruns:0 frame:0
TX packets:444 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:28970 (28.2 KiB) TX bytes:35214 (34.3 KiB)
lo Link encap:Local Loopback
inet addr:127.0.0.1 Mask:255.0.0.0
inet6 addr: ::1%1/128 Scope:Host
UP LOOPBACK RUNNING MTU:65536 Metric:1
RX packets:67 errors:0 dropped:0 overruns:0 frame:0
TX packets:67 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:6618 (6.4 KiB) TX bytes:6618 (6.4 KiB)
~$ tcpdump -i lan4 -v
[ 661.057166] device lan4 entered promiscuous mode
[ 661.061814] device eth1 entered promiscuous mode
tcpdump: listening on lan4, link-type EN10MB (Ethernet), capture size
262144 bytes
07:40:20.255355 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000 tell tango-charlie.local, length 46
07:40:20.255393 ARP, Ethernet (len 6), IPv4 (len 4), Reply
VB4-SN00000000 is-at c4:f3:12:08:fe:7f (oui Unknown), length 28
07:40:20.360936 IP6 (flowlabel 0x970aa, hlim 255, next-header UDP (17)
payload length: 53) VB4-SN00000000.mdns > ff02::fb.mdns: [udp sum o)
07:40:20.361085 IP (tos 0x0, ttl 255, id 17259, offset 0, flags [DF],
proto UDP (17), length 73)
VB4-SN00000000.mdns > 224.0.0.251.mdns: 0 PTR (QM)?
251.78.254.169.in-addr.arpa. (45)
07:40:20.361848 IP (tos 0x0, ttl 255, id 1808, offset 0, flags [DF],
proto UDP (17), length 100)
tango-charlie.local.mdns > 224.0.0.251.mdns: 0*- [0q] 1/0/0
251.78.254.169.in-addr.arpa. (Cache flush) PTR tango-charlie.local.
(72)
07:40:20.465933 IP6 (flowlabel 0x970aa, hlim 255, next-header UDP (17)
payload length: 98) VB4-SN00000000.mdns > ff02::fb.mdns: [udp sum o)
07:40:20.466124 IP (tos 0x0, ttl 255, id 17288, offset 0, flags [DF],
proto UDP (17), length 118)
VB4-SN00000000.mdns > 224.0.0.251.mdns: 0 PTR (QM)?
b.f.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.2.0.f.f.ip6.arpa.
(90)
07:40:21.254161 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000 tell tango-charlie.local, length 46
07:40:21.254181 ARP, Ethernet (len 6), IPv4 (len 4), Reply
VB4-SN00000000 is-at c4:f3:12:08:fe:7f (oui Unknown), length 28
07:40:25.470288 IP6 (flowlabel 0x970aa, hlim 255, next-header UDP (17)
payload length: 50) VB4-SN00000000.mdns > ff02::fb.mdns: [udp sum o)
07:40:31.301929 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000 tell tango-charlie.local, length 46
07:40:31.301957 ARP, Ethernet (len 6), IPv4 (len 4), Reply
VB4-SN00000000 is-at c4:f3:12:08:fe:7f (oui Unknown), length 28
07:40:32.319104 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000 tell tango-charlie.local, length 46
07:40:32.319131 ARP, Ethernet (len 6), IPv4 (len 4), Reply
VB4-SN00000000 is-at c4:f3:12:08:fe:7f (oui Unknown), length 28
07:40:33.317874 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000 tell tango-charlie.local, length 46
07:40:33.317900 ARP, Ethernet (len 6), IPv4 (len 4), Reply
VB4-SN00000000 is-at c4:f3:12:08:fe:7f (oui Unknown), length 28
07:40:34.317840 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000 tell tango-charlie.local, length 46
07:40:34.317866 ARP, Ethernet (len 6), IPv4 (len 4), Reply
VB4-SN00000000 is-at c4:f3:12:08:fe:7f (oui Unknown), length 28
~$ ethtool -S eth1
NIC statistics:
Good Rx Frames: 715
Broadcast Rx Frames: 553
Multicast Rx Frames: 162
Pause Rx Frames: 0
Rx CRC Errors: 0
Rx Align/Code Errors: 0
Oversize Rx Frames: 0
Rx Jabbers: 0
Undersize (Short) Rx Frames: 0
Rx Fragments: 0
Rx Octets: 63055
Good Tx Frames: 812
Broadcast Tx Frames: 34
Multicast Tx Frames: 283
Pause Tx Frames: 0
Deferred Tx Frames: 0
Collisions: 0
Single Collision Tx Frames: 0
Multiple Collision Tx Frames: 0
Excessive Collisions: 0
Late Collisions: 0
Tx Underrun: 0
Carrier Sense Errors: 0
Tx Octets: 85250
Rx + Tx 64 Octet Frames: 0
Rx + Tx 65-127 Octet Frames: 1287
Rx + Tx 128-255 Octet Frames: 168
Rx + Tx 256-511 Octet Frames: 72
Rx + Tx 512-1023 Octet Frames: 0
Rx + Tx 1024-Up Octet Frames: 0
Net Octets: 148305
Rx Start of Frame Overruns: 0
Rx Middle of Frame Overruns: 0
Rx DMA Overruns: 0
Rx DMA chan 0: head_enqueue: 1
Rx DMA chan 0: tail_enqueue: 813
Rx DMA chan 0: pad_enqueue: 0
Rx DMA chan 0: misqueued: 0
Rx DMA chan 0: desc_alloc_fail: 0
Rx DMA chan 0: pad_alloc_fail: 0
Rx DMA chan 0: runt_receive_buf: 0
Rx DMA chan 0: runt_transmit_bu: 0
Rx DMA chan 0: empty_dequeue: 0
Rx DMA chan 0: busy_dequeue: 668
Rx DMA chan 0: good_dequeue: 686
Rx DMA chan 0: requeue: 0
Rx DMA chan 0: teardown_dequeue: 0
Tx DMA chan 0: head_enqueue: 812
Tx DMA chan 0: tail_enqueue: 0
Tx DMA chan 0: pad_enqueue: 0
Tx DMA chan 0: misqueued: 0
Tx DMA chan 0: desc_alloc_fail: 0
Tx DMA chan 0: pad_alloc_fail: 0
Tx DMA chan 0: runt_receive_buf: 0
Tx DMA chan 0: runt_transmit_bu: 502
Tx DMA chan 0: empty_dequeue: 812
Tx DMA chan 0: busy_dequeue: 0
Tx DMA chan 0: good_dequeue: 812
Tx DMA chan 0: requeue: 0
Tx DMA chan 0: teardown_dequeue: 0
p05_rx_hi: 0
p05_rx_undersize: 0
p05_rx_fragments: 0
p05_rx_oversize: 0
p05_rx_jabbers: 0
p05_rx_symbol_err: 0
p05_rx_crc_err: 0
p05_rx_align_err: 0
p05_rx_mac_ctrl: 0
p05_rx_pause: 0
p05_rx_bcast: 34
p05_rx_mcast: 283
p05_rx_ucast: 495
p05_rx_64_or_less: 0
p05_rx_65_127: 675
p05_rx_128_255: 87
p05_rx_256_511: 50
p05_rx_512_1023: 0
p05_rx_1024_1522: 0
p05_rx_1523_2000: 0
p05_rx_2001: 0
p05_tx_hi: 0
p05_tx_late_col: 0
p05_tx_pause: 0
p05_tx_bcast: 553
p05_tx_mcast: 165
p05_tx_ucast: 0
p05_tx_deferred: 0
p05_tx_total_col: 0
p05_tx_exc_col: 0
p05_tx_single_col: 0
p05_tx_mult_col: 0
p05_rx_total: 85250
p05_tx_total: 63473
p05_rx_discards: 505
p05_tx_discards: 0
~$
~$ ethtool -S lan4
NIC statistics:
tx_packets: 736
tx_bytes: 59572
rx_packets: 701
rx_bytes: 45521
rx_hi: 0
rx_undersize: 0
rx_fragments: 0
rx_oversize: 0
rx_jabbers: 0
rx_symbol_err: 0
rx_crc_err: 0
rx_align_err: 0
rx_mac_ctrl: 0
rx_pause: 0
rx_bcast: 602
rx_mcast: 448
rx_ucast: 495
rx_64_or_less: 562
rx_65_127: 742
rx_128_255: 169
rx_256_511: 72
rx_512_1023: 0
rx_1024_1522: 0
rx_1523_2000: 0
rx_2001: 0
tx_hi: 0
tx_late_col: 0
tx_pause: 0
tx_bcast: 582
tx_mcast: 376
tx_ucast: 0
tx_deferred: 0
tx_total_col: 0
tx_exc_col: 0
tx_single_col: 0
tx_mult_col: 0
rx_total: 148965
tx_total: 104929
rx_discards: 505
tx_discards: 0
~$
Logs from the PC:
===================================
prabhakar@tango-charlie:~/Desktop/test$ ifconfig enx00e04c68c229
enx00e04c68c229 Link encap:Ethernet HWaddr 00:e0:4c:68:c2:29
inet addr:169.254.78.251 Bcast:169.254.255.255 Mask:255.255.0.0
inet6 addr: fe80::7cd0:12d6:d4bb:fc8b/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:209 errors:0 dropped:0 overruns:0 frame:0
TX packets:842 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:38308 (38.3 KB) TX bytes:60751 (60.7 KB)
prabhakar@tango-charlie:~/Desktop/test$ ping -I enx00e04c68c229 169.254.126.126
PING 169.254.126.126 (169.254.126.126) from 169.254.78.251
enx00e04c68c229: 56(84) bytes of data.
>From 169.254.78.251 icmp_seq=1 Destination Host Unreachable
>From 169.254.78.251 icmp_seq=2 Destination Host Unreachable
>From 169.254.78.251 icmp_seq=3 Destination Host Unreachable
>From 169.254.78.251 icmp_seq=4 Destination Host Unreachable
>From 169.254.78.251 icmp_seq=5 Destination Host Unreachable
>From 169.254.78.251 icmp_seq=6 Destination Host Unreachable
^C
--- 169.254.126.126 ping statistics ---
8 packets transmitted, 0 received, +6 errors, 100% packet loss, time 6999ms
pipe 4
prabhakar@tango-charlie:~/Desktop/test$ sudo tcpdump -i enx00e04c68c229 -v
[sudo] password for prabhakar:
tcpdump: listening on enx00e04c68c229, link-type EN10MB (Ethernet),
capture size 262144 bytes
09:09:39.692909 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000.local tell tango-charlie, length 28
09:09:39.794135 IP6 (flowlabel 0xaf44f, hlim 255, next-header UDP (17)
payload length: 54) tango-charlie.mdns > ff02::fb.mdns: [bad udp cksum
0x5fb4 -> 0x8657!] 0 PTR (QM)? 126.126.254.169.in-addr.arpa. (46)
09:09:39.794196 IP (tos 0x0, ttl 255, id 32415, offset 0, flags [DF],
proto UDP (17), length 74)
tango-charlie.mdns > 224.0.0.251.mdns: 0 PTR (QM)?
126.126.254.169.in-addr.arpa. (46)
09:09:39.795280 IP (tos 0x0, ttl 255, id 37104, offset 0, flags [DF],
proto UDP (17), length 102)
VB4-SN00000000.local.mdns > 224.0.0.251.mdns: 0*- [0q] 1/0/0
126.126.254.169.in-addr.arpa. (Cache flush) PTR VB4-SN00000000.local.
(74)
09:09:40.692890 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000.local tell tango-charlie, length 28
09:09:41.710153 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000.local tell tango-charlie, length 28
09:09:42.708884 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000.local tell tango-charlie, length 28
09:09:43.708884 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000.local tell tango-charlie, length 28
09:09:44.726124 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000.local tell tango-charlie, length 28
09:09:45.724892 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000.local tell tango-charlie, length 28
09:09:46.724887 ARP, Ethernet (len 6), IPv4 (len 4), Request who-has
VB4-SN00000000.local tell tango-charlie, length 28
^C
11 packets captured
11 packets received by filter
0 packets dropped by kernel
Cheers,
--Prabhakar
^ permalink raw reply
* [PATCH net-next] rxrpc: Remove set but not used variable 'nowj'
From: David Howells @ 2018-08-02 8:13 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel, weiyongjun1
From: Wei Yongjun <weiyongjun1@huawei.com>
Fixes gcc '-Wunused-but-set-variable' warning:
net/rxrpc/proc.c: In function 'rxrpc_call_seq_show':
net/rxrpc/proc.c:66:29: warning:
variable 'nowj' set but not used [-Wunused-but-set-variable]
unsigned long timeout = 0, nowj;
^
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/proc.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 163d05df339d..9805e3b85c36 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -63,7 +63,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
struct rxrpc_peer *peer;
struct rxrpc_call *call;
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
- unsigned long timeout = 0, nowj;
+ unsigned long timeout = 0;
rxrpc_seq_t tx_hard_ack, rx_hard_ack;
char lbuff[50], rbuff[50];
@@ -97,7 +97,6 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
if (call->state != RXRPC_CALL_SERVER_PREALLOC) {
timeout = READ_ONCE(call->expect_rx_by);
- nowj = jiffies;
timeout -= jiffies;
}
^ permalink raw reply related
* [PATCH net-next v2 2/3] qed: Add a flag which indicates if offload TC is set
From: Denis Bolotin @ 2018-08-02 8:12 UTC (permalink / raw)
To: davem, netdev; +Cc: Denis Bolotin, Ariel Elior
In-Reply-To: <20180802081251.10003-1-denis.bolotin@cavium.com>
Distinguish not set offload_tc from offload_tc 0 and add getters and
setters.
Signed-off-by: Denis Bolotin <denis.bolotin@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
---
drivers/net/ethernet/qlogic/qed/qed.h | 3 +++
drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 2 +-
drivers/net/ethernet/qlogic/qed/qed_dev.c | 32 +++++++++++++++++++++++++-----
drivers/net/ethernet/qlogic/qed/qed_mcp.c | 3 ++-
4 files changed, 33 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 1dfaccd..f916f13 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -336,6 +336,7 @@ struct qed_hw_info {
*/
u8 num_active_tc;
u8 offload_tc;
+ bool offload_tc_set;
u32 concrete_fid;
u16 opaque_fid;
@@ -921,4 +922,6 @@ void qed_get_protocol_stats(struct qed_dev *cdev,
int qed_mfw_fill_tlv_data(struct qed_hwfn *hwfn,
enum qed_mfw_tlv_type type,
union qed_mfw_tlv_data *tlv_data);
+
+void qed_hw_info_set_offload_tc(struct qed_hw_info *p_info, u8 tc);
#endif /* _QED_H */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 53c7be8..2c1c3c1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -208,7 +208,7 @@ static bool qed_dcbx_roce_v2_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee)
/* QM reconf data */
if (p_info->personality == personality)
- p_info->offload_tc = tc;
+ qed_hw_info_set_offload_tc(p_info, tc);
}
/* Update app protocol data and hw_info fields with the TLV info */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 6a0b46f..a8e7683 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -394,7 +394,25 @@ static void qed_init_qm_advance_vport(struct qed_hwfn *p_hwfn)
/* defines for pq init */
#define PQ_INIT_DEFAULT_WRR_GROUP 1
#define PQ_INIT_DEFAULT_TC 0
-#define PQ_INIT_OFLD_TC (p_hwfn->hw_info.offload_tc)
+
+void qed_hw_info_set_offload_tc(struct qed_hw_info *p_info, u8 tc)
+{
+ p_info->offload_tc = tc;
+ p_info->offload_tc_set = true;
+}
+
+static bool qed_is_offload_tc_set(struct qed_hwfn *p_hwfn)
+{
+ return p_hwfn->hw_info.offload_tc_set;
+}
+
+static u32 qed_get_offload_tc(struct qed_hwfn *p_hwfn)
+{
+ if (qed_is_offload_tc_set(p_hwfn))
+ return p_hwfn->hw_info.offload_tc;
+
+ return PQ_INIT_DEFAULT_TC;
+}
static void qed_init_qm_pq(struct qed_hwfn *p_hwfn,
struct qed_qm_info *qm_info,
@@ -538,7 +556,8 @@ static void qed_init_qm_pure_ack_pq(struct qed_hwfn *p_hwfn)
return;
qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_ACK, qm_info->num_pqs);
- qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+ qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
+ PQ_INIT_SHARE_VPORT);
}
static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
@@ -549,7 +568,8 @@ static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
return;
qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OFLD, qm_info->num_pqs);
- qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+ qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
+ PQ_INIT_SHARE_VPORT);
}
static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
@@ -560,7 +580,8 @@ static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
return;
qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LLT, qm_info->num_pqs);
- qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+ qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
+ PQ_INIT_SHARE_VPORT);
}
static void qed_init_qm_mcos_pqs(struct qed_hwfn *p_hwfn)
@@ -601,7 +622,8 @@ static void qed_init_qm_rl_pqs(struct qed_hwfn *p_hwfn)
qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_RLS, qm_info->num_pqs);
for (pf_rls_idx = 0; pf_rls_idx < num_pf_rls; pf_rls_idx++)
- qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_PF_RL);
+ qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
+ PQ_INIT_PF_RL);
}
static void qed_init_qm_pq_params(struct qed_hwfn *p_hwfn)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 8e4f60e..d89a0e2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1552,7 +1552,8 @@ void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
if (p_hwfn->ufp_info.mode == QED_UFP_MODE_VNIC_BW) {
p_hwfn->qm_info.ooo_tc = p_hwfn->ufp_info.tc;
- p_hwfn->hw_info.offload_tc = p_hwfn->ufp_info.tc;
+ qed_hw_info_set_offload_tc(&p_hwfn->hw_info,
+ p_hwfn->ufp_info.tc);
qed_qm_reconf(p_hwfn, p_ptt);
} else if (p_hwfn->ufp_info.mode == QED_UFP_MODE_ETS) {
--
1.8.3.1
^ 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