* [PATCH net-next 07/14] gtp: Support encapsulation of IPv6 packets
From: Tom Herbert @ 2017-09-19 0:38 UTC (permalink / raw)
To: davem; +Cc: netdev, pablo, laforge, rohit, Tom Herbert
In-Reply-To: <20170919003904.5124-1-tom@quantonium.net>
Allow IPv6 mobile subscriber packets. This entails adding an IPv6 mobile
subscriber address to pdp context and IPv6 specific variants to find pdp
contexts by address.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
drivers/net/gtp.c | 259 +++++++++++++++++++++++++++++++++++++----------
include/uapi/linux/gtp.h | 1 +
2 files changed, 209 insertions(+), 51 deletions(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index a928279c382c..62c0c968efa6 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -54,9 +54,13 @@ struct pdp_ctx {
} u;
u8 gtp_version;
__be16 gtp_port;
- u16 af;
- struct in_addr ms_addr_ip4;
+ u16 ms_af;
+ union {
+ struct in_addr ms_addr_ip4;
+ struct in6_addr ms_addr_ip6;
+ };
+
struct in_addr peer_addr_ip4;
struct sock *sk;
@@ -80,7 +84,9 @@ struct gtp_dev {
unsigned int role;
unsigned int hash_size;
struct hlist_head *tid_hash;
- struct hlist_head *addr_hash;
+
+ struct hlist_head *addr4_hash;
+ struct hlist_head *addr6_hash;
struct gro_cells gro_cells;
};
@@ -98,6 +104,7 @@ static void pdp_context_delete(struct pdp_ctx *pctx);
static inline u32 gtp0_hashfn(u64 tid)
{
u32 *tid32 = (u32 *) &tid;
+
return jhash_2words(tid32[0], tid32[1], gtp_h_initval);
}
@@ -111,6 +118,11 @@ static inline u32 ipv4_hashfn(__be32 ip)
return jhash_1word((__force u32)ip, gtp_h_initval);
}
+static inline u32 ipv6_hashfn(const struct in6_addr *a)
+{
+ return __ipv6_addr_jhash(a, gtp_h_initval);
+}
+
/* Resolve a PDP context structure based on the 64bit TID. */
static struct pdp_ctx *gtp0_pdp_find(struct gtp_dev *gtp, u64 tid)
{
@@ -149,10 +161,10 @@ static struct pdp_ctx *ipv4_pdp_find(struct gtp_dev *gtp, __be32 ms_addr)
struct hlist_head *head;
struct pdp_ctx *pdp;
- head = >p->addr_hash[ipv4_hashfn(ms_addr) % gtp->hash_size];
+ head = >p->addr4_hash[ipv4_hashfn(ms_addr) % gtp->hash_size];
hlist_for_each_entry_rcu(pdp, head, hlist_addr) {
- if (pdp->af == AF_INET &&
+ if (pdp->ms_af == AF_INET &&
pdp->ms_addr_ip4.s_addr == ms_addr)
return pdp;
}
@@ -176,32 +188,95 @@ static bool gtp_check_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
return iph->saddr == pctx->ms_addr_ip4.s_addr;
}
+/* Resolve a PDP context based on IPv6 address of MS. */
+static struct pdp_ctx *ipv6_pdp_find(struct gtp_dev *gtp,
+ const struct in6_addr *ms_addr)
+{
+ struct hlist_head *head;
+ struct pdp_ctx *pdp;
+
+ head = >p->addr6_hash[ipv6_hashfn(ms_addr) % gtp->hash_size];
+
+ hlist_for_each_entry_rcu(pdp, head, hlist_addr) {
+ if (pdp->ms_af == AF_INET6 &&
+ ipv6_addr_equal(&pdp->ms_addr_ip6, ms_addr))
+ return pdp;
+ }
+
+ return NULL;
+}
+
+static bool gtp_check_ms_ipv6(struct sk_buff *skb, struct pdp_ctx *pctx,
+ unsigned int hdrlen, unsigned int role)
+{
+ struct ipv6hdr *ipv6h;
+
+ if (!pskb_may_pull(skb, hdrlen + sizeof(struct ipv6hdr)))
+ return false;
+
+ ipv6h = (struct ipv6hdr *)(skb->data + hdrlen);
+
+ if (role == GTP_ROLE_SGSN)
+ return ipv6_addr_equal(&ipv6h->daddr, &pctx->ms_addr_ip6);
+ else
+ return ipv6_addr_equal(&ipv6h->saddr, &pctx->ms_addr_ip6);
+}
+
/* Check if the inner IP address in this packet is assigned to any
* existing mobile subscriber.
*/
static bool gtp_check_ms(struct sk_buff *skb, struct pdp_ctx *pctx,
unsigned int hdrlen, unsigned int role)
{
- switch (ntohs(skb->protocol)) {
- case ETH_P_IP:
+ struct iphdr *iph;
+
+ /* Minimally there needs to be an IPv4 header */
+ if (!pskb_may_pull(skb, hdrlen + sizeof(struct iphdr)))
+ return false;
+
+ iph = (struct iphdr *)(skb->data + hdrlen);
+
+ switch (iph->version) {
+ case 4:
return gtp_check_ms_ipv4(skb, pctx, hdrlen, role);
+ case 6:
+ return gtp_check_ms_ipv6(skb, pctx, hdrlen, role);
}
+
return false;
}
+static u16 ipver_to_eth(struct iphdr *iph)
+{
+ switch (iph->version) {
+ case 4:
+ return htons(ETH_P_IP);
+ case 6:
+ return htons(ETH_P_IPV6);
+ default:
+ return 0;
+ }
+}
+
static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb,
- unsigned int hdrlen, unsigned int role)
+ unsigned int hdrlen, unsigned int role)
{
struct pcpu_sw_netstats *stats;
+ u16 inner_protocol;
if (!gtp_check_ms(skb, pctx, hdrlen, role)) {
netdev_dbg(pctx->dev, "No PDP ctx for this MS\n");
return 1;
}
+ inner_protocol = ipver_to_eth((struct iphdr *)(skb->data + hdrlen));
+ if (!inner_protocol)
+ return -1;
+
/* Get rid of the GTP + UDP headers. */
- if (iptunnel_pull_header(skb, hdrlen, skb->protocol,
- !net_eq(sock_net(pctx->sk), dev_net(pctx->dev))))
+ if (iptunnel_pull_header(skb, hdrlen, inner_protocol,
+ !net_eq(sock_net(pctx->sk),
+ dev_net(pctx->dev))))
return -1;
netdev_dbg(pctx->dev, "forwarding packet from GGSN to uplink\n");
@@ -239,7 +314,8 @@ static int gtp0_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
if (!gtp)
goto pass;
- if (!pskb_may_pull(skb, hdrlen))
+ /* Pull through IP header since gtp_rx looks at IP version */
+ if (!pskb_may_pull(skb, hdrlen + sizeof(struct iphdr)))
goto drop;
gtp0 = (struct gtp0_header *)(skb->data + sizeof(struct udphdr));
@@ -285,7 +361,8 @@ static int gtp1u_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
if (!gtp)
goto pass;
- if (!pskb_may_pull(skb, hdrlen))
+ /* Pull through IP header since gtp_rx looks at IP version */
+ if (!pskb_may_pull(skb, hdrlen + sizeof(struct iphdr)))
goto drop;
gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr));
@@ -307,8 +384,10 @@ static int gtp1u_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
if (gtp1->flags & GTP1_F_MASK)
hdrlen += 4;
- /* Make sure the header is larger enough, including extensions. */
- if (!pskb_may_pull(skb, hdrlen))
+ /* Make sure the header is larger enough, including extensions and
+ * also an IP header since gtp_rx looks at IP version
+ */
+ if (!pskb_may_pull(skb, hdrlen + sizeof(struct iphdr)))
goto drop;
gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr));
@@ -389,7 +468,8 @@ static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
gtp0->flags = 0x1e; /* v0, GTP-non-prime. */
gtp0->type = GTP_TPDU;
gtp0->length = htons(payload_len);
- gtp0->seq = htons((atomic_inc_return(&pctx->tx_seq) - 1) % 0xffff);
+ gtp0->seq = htons((atomic_inc_return(&pctx->tx_seq) - 1) %
+ 0xffff);
gtp0->flow = htons(pctx->u.v0.flow);
gtp0->number = 0xff;
gtp0->spare[0] = gtp0->spare[1] = gtp0->spare[2] = 0xff;
@@ -507,6 +587,23 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev)
break;
}
+ case ETH_P_IPV6: {
+ struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+
+ if (gtp->role == GTP_ROLE_SGSN)
+ pctx = ipv6_pdp_find(gtp, &ipv6h->saddr);
+ else
+ pctx = ipv6_pdp_find(gtp, &ipv6h->daddr);
+
+ if (!pctx) {
+ netdev_dbg(dev, "no PDP ctx found for %pI6, skip\n",
+ &ipv6h->daddr);
+ err = -ENOENT;
+ goto tx_err;
+ }
+
+ break;
+ }
default:
err = -EOPNOTSUPP;
goto tx_err;
@@ -674,23 +771,32 @@ static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
{
int i;
- gtp->addr_hash = kmalloc(sizeof(struct hlist_head) * hsize, GFP_KERNEL);
- if (gtp->addr_hash == NULL)
- return -ENOMEM;
+ gtp->addr4_hash = kmalloc_array(hsize, sizeof(*gtp->addr4_hash),
+ GFP_KERNEL);
+ if (!gtp->addr4_hash)
+ goto err;
+
+ gtp->addr6_hash = kmalloc_array(hsize, sizeof(*gtp->addr6_hash),
+ GFP_KERNEL);
+ if (!gtp->addr6_hash)
+ goto err;
- gtp->tid_hash = kmalloc(sizeof(struct hlist_head) * hsize, GFP_KERNEL);
- if (gtp->tid_hash == NULL)
- goto err1;
+ gtp->tid_hash = kmalloc_array(hsize, sizeof(struct hlist_head),
+ GFP_KERNEL);
+ if (!gtp->tid_hash)
+ goto err;
gtp->hash_size = hsize;
for (i = 0; i < hsize; i++) {
- INIT_HLIST_HEAD(>p->addr_hash[i]);
+ INIT_HLIST_HEAD(>p->addr4_hash[i]);
+ INIT_HLIST_HEAD(>p->addr6_hash[i]);
INIT_HLIST_HEAD(>p->tid_hash[i]);
}
return 0;
-err1:
- kfree(gtp->addr_hash);
+err:
+ kfree(gtp->addr4_hash);
+ kfree(gtp->addr6_hash);
return -ENOMEM;
}
@@ -704,7 +810,8 @@ static void gtp_hashtable_free(struct gtp_dev *gtp)
pdp_context_delete(pctx);
synchronize_rcu();
- kfree(gtp->addr_hash);
+ kfree(gtp->addr4_hash);
+ kfree(gtp->addr6_hash);
kfree(gtp->tid_hash);
}
@@ -826,16 +933,13 @@ static struct gtp_dev *gtp_find_dev(struct net *src_net, struct nlattr *nla[])
return gtp;
}
-static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
+static void pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
{
__be16 default_port = 0;
pctx->gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
- pctx->af = AF_INET;
pctx->peer_addr_ip4.s_addr =
nla_get_be32(info->attrs[GTPA_PEER_ADDRESS]);
- pctx->ms_addr_ip4.s_addr =
- nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
switch (pctx->gtp_version) {
case GTP_V0:
@@ -862,33 +966,46 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
pctx->gtp_port = default_port;
}
-static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
- struct genl_info *info)
+static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk,
+ struct genl_info *info)
{
struct net_device *dev = gtp->dev;
+ struct hlist_head *addr_list;
+ struct pdp_ctx *pctx = NULL;
u32 hash_ms, hash_tid = 0;
- struct pdp_ctx *pctx;
- bool found = false;
- __be32 ms_addr;
+ struct in6_addr ms6_addr;
+ __be32 ms_addr = 0;
+ int ms_af;
int err;
- ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
- hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size;
+ /* Caller ensures we have either v4 or v6 mobile subscriber address */
+ if (info->attrs[GTPA_MS_ADDRESS]) {
+ /* IPv4 mobile subscriber */
- hlist_for_each_entry_rcu(pctx, >p->addr_hash[hash_ms], hlist_addr) {
- if (pctx->ms_addr_ip4.s_addr == ms_addr) {
- found = true;
- break;
- }
+ ms_addr = nla_get_in_addr(info->attrs[GTPA_MS_ADDRESS]);
+ hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size;
+ addr_list = >p->addr4_hash[hash_ms];
+ ms_af = AF_INET;
+
+ pctx = ipv4_pdp_find(gtp, ms_addr);
+ } else {
+ /* IPv6 mobile subscriber */
+
+ ms6_addr = nla_get_in6_addr(info->attrs[GTPA_MS6_ADDRESS]);
+ hash_ms = ipv6_hashfn(&ms6_addr) % gtp->hash_size;
+ addr_list = >p->addr6_hash[hash_ms];
+ ms_af = AF_INET6;
+
+ pctx = ipv6_pdp_find(gtp, &ms6_addr);
}
- if (found) {
+ if (pctx) {
if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)
return -EEXIST;
if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
- ipv4_pdp_fill(pctx, info);
+ pdp_fill(pctx, info);
if (pctx->gtp_version == GTP_V0)
netdev_dbg(dev, "GTPv0-U: update tunnel id = %llx (pdp %p)\n",
@@ -914,7 +1031,18 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
sock_hold(sk);
pctx->sk = sk;
pctx->dev = gtp->dev;
- ipv4_pdp_fill(pctx, info);
+ pctx->ms_af = ms_af;
+
+ switch (ms_af) {
+ case AF_INET:
+ pctx->ms_addr_ip4.s_addr = ms_addr;
+ break;
+ case AF_INET6:
+ pctx->ms_addr_ip6 = ms6_addr;
+ break;
+ }
+
+ pdp_fill(pctx, info);
atomic_set(&pctx->tx_seq, 0);
switch (pctx->gtp_version) {
@@ -931,7 +1059,7 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
break;
}
- hlist_add_head_rcu(&pctx->hlist_addr, >p->addr_hash[hash_ms]);
+ hlist_add_head_rcu(&pctx->hlist_addr, addr_list);
hlist_add_head_rcu(&pctx->hlist_tid, >p->tid_hash[hash_tid]);
switch (pctx->gtp_version) {
@@ -973,11 +1101,17 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
int err;
if (!info->attrs[GTPA_VERSION] ||
- !info->attrs[GTPA_LINK] ||
- !info->attrs[GTPA_PEER_ADDRESS] ||
- !info->attrs[GTPA_MS_ADDRESS])
+ !info->attrs[GTPA_LINK] ||
+ !info->attrs[GTPA_PEER_ADDRESS])
return -EINVAL;
+ if (!(!!info->attrs[GTPA_MS_ADDRESS] ^
+ !!info->attrs[GTPA_MS6_ADDRESS])) {
+ /* Either v4 or v6 mobile subscriber address must be set */
+
+ return -EINVAL;
+ }
+
version = nla_get_u32(info->attrs[GTPA_VERSION]);
switch (version) {
@@ -1016,7 +1150,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
goto out_unlock;
}
- err = ipv4_pdp_add(gtp, sk, info);
+ err = gtp_pdp_add(gtp, sk, info);
out_unlock:
rcu_read_unlock();
@@ -1036,6 +1170,11 @@ static struct pdp_ctx *gtp_find_pdp_by_link(struct net *net,
__be32 ip = nla_get_be32(nla[GTPA_MS_ADDRESS]);
return ipv4_pdp_find(gtp, ip);
+ } else if (nla[GTPA_MS6_ADDRESS]) {
+ struct in6_addr ip6 =
+ nla_get_in6_addr(nla[GTPA_MS6_ADDRESS]);
+
+ return ipv6_pdp_find(gtp, &ip6);
} else if (nla[GTPA_VERSION]) {
u32 gtp_version = nla_get_u32(nla[GTPA_VERSION]);
@@ -1106,10 +1245,26 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
goto nlmsg_failure;
if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) ||
- nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer_addr_ip4.s_addr) ||
- nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr))
+ nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer_addr_ip4.s_addr))
goto nla_put_failure;
+ switch (pctx->ms_af) {
+ case AF_INET:
+ if (nla_put_be32(skb, GTPA_MS_ADDRESS,
+ pctx->ms_addr_ip4.s_addr))
+ goto nla_put_failure;
+
+ break;
+ case AF_INET6:
+ if (nla_put_in6_addr(skb, GTPA_MS6_ADDRESS,
+ &pctx->ms_addr_ip6))
+ goto nla_put_failure;
+
+ break;
+ default:
+ goto nla_put_failure;
+ }
+
switch (pctx->gtp_version) {
case GTP_V0:
if (nla_put_u64_64bit(skb, GTPA_TID, pctx->u.v0.tid, GTPA_PAD) ||
@@ -1219,6 +1374,8 @@ static struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
[GTPA_TID] = { .type = NLA_U64, },
[GTPA_PEER_ADDRESS] = { .type = NLA_U32, },
[GTPA_MS_ADDRESS] = { .type = NLA_U32, },
+ [GTPA_MS6_ADDRESS] = { .len = FIELD_SIZEOF(struct ipv6hdr,
+ daddr) },
[GTPA_FLOW] = { .type = NLA_U16, },
[GTPA_NET_NS_FD] = { .type = NLA_U32, },
[GTPA_I_TEI] = { .type = NLA_U32, },
diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h
index b2283a5c6d7f..ae4e632c0360 100644
--- a/include/uapi/linux/gtp.h
+++ b/include/uapi/linux/gtp.h
@@ -28,6 +28,7 @@ enum gtp_attrs {
GTPA_O_TEI, /* for GTPv1 only */
GTPA_PAD,
GTPA_PORT,
+ GTPA_MS6_ADDRESS,
__GTPA_MAX,
};
#define GTPA_MAX (__GTPA_MAX + 1)
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 06/14] gtp: Eliminate pktinfo and add port configuration
From: Tom Herbert @ 2017-09-19 0:38 UTC (permalink / raw)
To: davem; +Cc: netdev, pablo, laforge, rohit, Tom Herbert
In-Reply-To: <20170919003904.5124-1-tom@quantonium.net>
The gtp pktinfo structure is unnecessary and needs a lot of code to
manage it. Remove it. Also, add per pdp port configuration for transmit.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
drivers/net/gtp.c | 167 ++++++++++++++++++++---------------------------
include/uapi/linux/gtp.h | 1 +
2 files changed, 71 insertions(+), 97 deletions(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index f2089fa4f004..a928279c382c 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -53,6 +53,7 @@ struct pdp_ctx {
} v1;
} u;
u8 gtp_version;
+ __be16 gtp_port;
u16 af;
struct in_addr ms_addr_ip4;
@@ -418,149 +419,112 @@ static inline void gtp1_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
*/
}
-struct gtp_pktinfo {
- struct sock *sk;
- struct iphdr *iph;
- struct flowi4 fl4;
- struct rtable *rt;
- struct pdp_ctx *pctx;
- struct net_device *dev;
- __be16 gtph_port;
-};
-
-static void gtp_push_header(struct sk_buff *skb, struct gtp_pktinfo *pktinfo)
+static void gtp_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
{
- switch (pktinfo->pctx->gtp_version) {
+ switch (pctx->gtp_version) {
case GTP_V0:
- pktinfo->gtph_port = htons(GTP0_PORT);
- gtp0_push_header(skb, pktinfo->pctx);
+ gtp0_push_header(skb, pctx);
break;
case GTP_V1:
- pktinfo->gtph_port = htons(GTP1U_PORT);
- gtp1_push_header(skb, pktinfo->pctx);
+ gtp1_push_header(skb, pctx);
break;
}
}
-static inline void gtp_set_pktinfo_ipv4(struct gtp_pktinfo *pktinfo,
- struct sock *sk, struct iphdr *iph,
- struct pdp_ctx *pctx, struct rtable *rt,
- struct flowi4 *fl4,
- struct net_device *dev)
-{
- pktinfo->sk = sk;
- pktinfo->iph = iph;
- pktinfo->pctx = pctx;
- pktinfo->rt = rt;
- pktinfo->fl4 = *fl4;
- pktinfo->dev = dev;
-}
-
-static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
- struct gtp_pktinfo *pktinfo)
+static int gtp_xmit(struct sk_buff *skb, struct net_device *dev,
+ struct pdp_ctx *pctx)
{
- struct gtp_dev *gtp = netdev_priv(dev);
- struct pdp_ctx *pctx;
+ struct sock *sk = pctx->sk;
+ __be32 saddr = inet_sk(sk)->inet_saddr;
struct rtable *rt;
- struct flowi4 fl4;
- struct iphdr *iph;
- struct sock *sk;
- __be32 saddr;
-
- /* Read the IP destination address and resolve the PDP context.
- * Prepend PDP header with TEI/TID from PDP ctx.
- */
- iph = ip_hdr(skb);
- if (gtp->role == GTP_ROLE_SGSN)
- pctx = ipv4_pdp_find(gtp, iph->saddr);
- else
- pctx = ipv4_pdp_find(gtp, iph->daddr);
+ int err = 0;
- if (!pctx) {
- netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n",
- &iph->daddr);
- return -ENOENT;
- }
- netdev_dbg(dev, "found PDP context %p\n", pctx);
+ /* Ensure there is sufficient headroom. */
+ err = skb_cow_head(skb, dev->needed_headroom);
+ if (unlikely(err))
+ goto out_err;
- sk = pctx->sk;
- saddr = inet_sk(sk)->inet_saddr;
+ skb_reset_inner_headers(skb);
rt = ip_tunnel_get_route(dev, skb, sk->sk_protocol,
sk->sk_bound_dev_if, RT_CONN_FLAGS(sk),
pctx->peer_addr_ip4.s_addr, &saddr,
- pktinfo->gtph_port, pktinfo->gtph_port,
+ pctx->gtp_port, pctx->gtp_port,
&pctx->dst_cache, NULL);
if (IS_ERR(rt)) {
- if (rt == ERR_PTR(-ELOOP)) {
- netdev_dbg(dev, "circular route to SSGN %pI4\n",
- &pctx->peer_addr_ip4.s_addr);
- dev->stats.collisions++;
- goto err_rt;
- } else {
- netdev_dbg(dev, "no route to SSGN %pI4\n",
- &pctx->peer_addr_ip4.s_addr);
- dev->stats.tx_carrier_errors++;
- goto err;
- }
+ err = PTR_ERR(rt);
+ goto out_err;
}
skb_dst_drop(skb);
- gtp_set_pktinfo_ipv4(pktinfo, sk, iph, pctx, rt, &fl4, dev);
- gtp_push_header(skb, pktinfo);
+ gtp_push_header(skb, pctx);
+ udp_tunnel_xmit_skb(rt, sk, skb, saddr,
+ pctx->peer_addr_ip4.s_addr,
+ 0, ip4_dst_hoplimit(&rt->dst), 0,
+ pctx->gtp_port, pctx->gtp_port,
+ false, false);
+
+ netdev_dbg(dev, "gtp -> IP src: %pI4 dst: %pI4\n",
+ &saddr, &pctx->peer_addr_ip4.s_addr);
return 0;
-err_rt:
- ip_rt_put(rt);
-err:
- return -EBADMSG;
+
+out_err:
+ if (err == -ELOOP)
+ dev->stats.collisions++;
+ else
+ dev->stats.tx_carrier_errors++;
+
+ return err;
}
static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev)
{
unsigned int proto = ntohs(skb->protocol);
- struct gtp_pktinfo pktinfo;
+ struct gtp_dev *gtp = netdev_priv(dev);
+ struct pdp_ctx *pctx;
int err;
- /* Ensure there is sufficient headroom. */
- if (skb_cow_head(skb, dev->needed_headroom))
- goto tx_err;
-
- skb_reset_inner_headers(skb);
-
/* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */
rcu_read_lock();
switch (proto) {
- case ETH_P_IP:
- err = gtp_build_skb_ip4(skb, dev, &pktinfo);
+ case ETH_P_IP: {
+ struct iphdr *iph = ip_hdr(skb);
+
+ if (gtp->role == GTP_ROLE_SGSN)
+ pctx = ipv4_pdp_find(gtp, iph->saddr);
+ else
+ pctx = ipv4_pdp_find(gtp, iph->daddr);
+
+ if (!pctx) {
+ netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n",
+ &iph->daddr);
+ err = -ENOENT;
+ goto tx_err;
+ }
+
break;
+ }
default:
err = -EOPNOTSUPP;
- break;
+ goto tx_err;
}
- rcu_read_unlock();
+
+ netdev_dbg(dev, "found PDP context %p\n", pctx);
+
+ err = gtp_xmit(skb, dev, pctx);
if (err < 0)
goto tx_err;
- switch (proto) {
- case ETH_P_IP:
- netdev_dbg(pktinfo.dev, "gtp -> IP src: %pI4 dst: %pI4\n",
- &pktinfo.iph->saddr, &pktinfo.iph->daddr);
- udp_tunnel_xmit_skb(pktinfo.rt, pktinfo.sk, skb,
- pktinfo.fl4.saddr, pktinfo.fl4.daddr,
- pktinfo.iph->tos,
- ip4_dst_hoplimit(&pktinfo.rt->dst),
- 0,
- pktinfo.gtph_port, pktinfo.gtph_port,
- true, false);
- break;
- }
+ rcu_read_unlock();
return NETDEV_TX_OK;
+
tx_err:
+ rcu_read_unlock();
dev->stats.tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
@@ -864,6 +828,8 @@ static struct gtp_dev *gtp_find_dev(struct net *src_net, struct nlattr *nla[])
static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
{
+ __be16 default_port = 0;
+
pctx->gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
pctx->af = AF_INET;
pctx->peer_addr_ip4.s_addr =
@@ -879,14 +845,21 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
*/
pctx->u.v0.tid = nla_get_u64(info->attrs[GTPA_TID]);
pctx->u.v0.flow = nla_get_u16(info->attrs[GTPA_FLOW]);
+ default_port = htons(GTP0_PORT);
break;
case GTP_V1:
pctx->u.v1.i_tei = nla_get_u32(info->attrs[GTPA_I_TEI]);
pctx->u.v1.o_tei = nla_get_u32(info->attrs[GTPA_O_TEI]);
+ default_port = htons(GTP1U_PORT);
break;
default:
break;
}
+
+ if (info->attrs[GTPA_PORT])
+ pctx->gtp_port = nla_get_u16(info->attrs[GTPA_PORT]);
+ else
+ pctx->gtp_port = default_port;
}
static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h
index 57d1edb8efd9..b2283a5c6d7f 100644
--- a/include/uapi/linux/gtp.h
+++ b/include/uapi/linux/gtp.h
@@ -27,6 +27,7 @@ enum gtp_attrs {
GTPA_I_TEI, /* for GTPv1 only */
GTPA_O_TEI, /* for GTPv1 only */
GTPA_PAD,
+ GTPA_PORT,
__GTPA_MAX,
};
#define GTPA_MAX (__GTPA_MAX + 1)
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 05/14] gtp: Remove special mtu handling
From: Tom Herbert @ 2017-09-19 0:38 UTC (permalink / raw)
To: davem; +Cc: netdev, pablo, laforge, rohit, Tom Herbert
In-Reply-To: <20170919003904.5124-1-tom@quantonium.net>
Removes MTU handling in gtp_build_skb_ip4. This is non standard relative
to how other tunneling protocols handle MTU. The model espoused is that
the inner interface should set it's MTU to be less than the expected
path MTU on the overlay network. Path MTU discovery is not typically
used for modifying tunnel MTUs.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
drivers/net/gtp.c | 30 ------------------------------
1 file changed, 30 deletions(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 1de2ea6217ea..f2089fa4f004 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -466,8 +466,6 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
struct iphdr *iph;
struct sock *sk;
__be32 saddr;
- __be16 df;
- int mtu;
/* Read the IP destination address and resolve the PDP context.
* Prepend PDP header with TEI/TID from PDP ctx.
@@ -510,34 +508,6 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
skb_dst_drop(skb);
- /* This is similar to tnl_update_pmtu(). */
- df = iph->frag_off;
- if (df) {
- mtu = dst_mtu(&rt->dst) - dev->hard_header_len -
- sizeof(struct iphdr) - sizeof(struct udphdr);
- switch (pctx->gtp_version) {
- case GTP_V0:
- mtu -= sizeof(struct gtp0_header);
- break;
- case GTP_V1:
- mtu -= sizeof(struct gtp1_header);
- break;
- }
- } else {
- mtu = dst_mtu(&rt->dst);
- }
-
- rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu);
-
- if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
- mtu < ntohs(iph->tot_len)) {
- netdev_dbg(dev, "packet too big, fragmentation needed\n");
- memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
- htonl(mtu));
- goto err_rt;
- }
-
gtp_set_pktinfo_ipv4(pktinfo, sk, iph, pctx, rt, &fl4, dev);
gtp_push_header(skb, pktinfo);
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 04/14] gtp: udp recv clean up
From: Tom Herbert @ 2017-09-19 0:38 UTC (permalink / raw)
To: davem; +Cc: netdev, pablo, laforge, rohit, Tom Herbert
In-Reply-To: <20170919003904.5124-1-tom@quantonium.net>
Create separate UDP receive functions for GTP version 0 and version 1.
Set encap_rcv appropriately when configuring a socket. Also, convert to
using gro_cells.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
drivers/net/gtp.c | 130 +++++++++++++++++++++++++++++-------------------------
1 file changed, 71 insertions(+), 59 deletions(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 95df3bcebbb2..1de2ea6217ea 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -80,6 +80,8 @@ struct gtp_dev {
unsigned int hash_size;
struct hlist_head *tid_hash;
struct hlist_head *addr_hash;
+
+ struct gro_cells gro_cells;
};
static unsigned int gtp_net_id __read_mostly;
@@ -217,55 +219,83 @@ static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb,
stats->rx_bytes += skb->len;
u64_stats_update_end(&stats->syncp);
- netif_rx(skb);
+ gro_cells_receive(>p->gro_cells, skb);
+
return 0;
}
-/* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */
-static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
+/* UDP encapsulation receive handler for GTPv0-U . See net/ipv4/udp.c.
+ * Return codes: 0: success, <0: error, >0: pass up to userspace UDP socket.
+ */
+static int gtp0_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
+ struct gtp_dev *gtp = rcu_dereference_sk_user_data(sk);
unsigned int hdrlen = sizeof(struct udphdr) +
sizeof(struct gtp0_header);
struct gtp0_header *gtp0;
struct pdp_ctx *pctx;
+ if (!gtp)
+ goto pass;
+
if (!pskb_may_pull(skb, hdrlen))
- return -1;
+ goto drop;
gtp0 = (struct gtp0_header *)(skb->data + sizeof(struct udphdr));
if ((gtp0->flags >> 5) != GTP_V0)
- return 1;
+ goto pass;
if (gtp0->type != GTP_TPDU)
- return 1;
+ goto pass;
+
+ netdev_dbg(gtp->dev, "received GTP0 packet\n");
pctx = gtp0_pdp_find(gtp, be64_to_cpu(gtp0->tid));
if (!pctx) {
netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb);
- return 1;
+ goto pass;
+ }
+
+ if (!gtp_rx(pctx, skb, hdrlen, gtp->role)) {
+ /* Successfully received */
+ return 0;
}
- return gtp_rx(pctx, skb, hdrlen, gtp->role);
+drop:
+ kfree_skb(skb);
+ return 0;
+
+pass:
+ return 1;
}
-static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
+/* UDP encapsulation receive handler for GTPv0-U . See net/ipv4/udp.c.
+ * Return codes: 0: success, <0: error, >0: pass up to userspace UDP socket.
+ */
+static int gtp1u_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
+ struct gtp_dev *gtp = rcu_dereference_sk_user_data(sk);
unsigned int hdrlen = sizeof(struct udphdr) +
sizeof(struct gtp1_header);
struct gtp1_header *gtp1;
struct pdp_ctx *pctx;
+ if (!gtp)
+ goto pass;
+
if (!pskb_may_pull(skb, hdrlen))
- return -1;
+ goto drop;
gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr));
if ((gtp1->flags >> 5) != GTP_V1)
- return 1;
+ goto pass;
if (gtp1->type != GTP_TPDU)
- return 1;
+ goto pass;
+
+ netdev_dbg(gtp->dev, "received GTP1 packet\n");
/* From 29.060: "This field shall be present if and only if any one or
* more of the S, PN and E flags are set.".
@@ -278,17 +308,27 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
/* Make sure the header is larger enough, including extensions. */
if (!pskb_may_pull(skb, hdrlen))
- return -1;
+ goto drop;
gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr));
pctx = gtp1_pdp_find(gtp, ntohl(gtp1->tid));
if (!pctx) {
netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb);
- return 1;
+ goto pass;
+ }
+
+ if (!gtp_rx(pctx, skb, hdrlen, gtp->role)) {
+ /* Successfully received */
+ return 0;
}
- return gtp_rx(pctx, skb, hdrlen, gtp->role);
+drop:
+ kfree_skb(skb);
+ return 0;
+
+pass:
+ return 1;
}
static void gtp_encap_destroy(struct sock *sk)
@@ -317,49 +357,6 @@ static void gtp_encap_disable(struct gtp_dev *gtp)
gtp_encap_disable_sock(gtp->sk1u);
}
-/* UDP encapsulation receive handler. See net/ipv4/udp.c.
- * Return codes: 0: success, <0: error, >0: pass up to userspace UDP socket.
- */
-static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
-{
- struct gtp_dev *gtp;
- int ret = 0;
-
- gtp = rcu_dereference_sk_user_data(sk);
- if (!gtp)
- return 1;
-
- netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk);
-
- switch (udp_sk(sk)->encap_type) {
- case UDP_ENCAP_GTP0:
- netdev_dbg(gtp->dev, "received GTP0 packet\n");
- ret = gtp0_udp_encap_recv(gtp, skb);
- break;
- case UDP_ENCAP_GTP1U:
- netdev_dbg(gtp->dev, "received GTP1U packet\n");
- ret = gtp1u_udp_encap_recv(gtp, skb);
- break;
- default:
- ret = -1; /* Shouldn't happen. */
- }
-
- switch (ret) {
- case 1:
- netdev_dbg(gtp->dev, "pass up to the process\n");
- break;
- case 0:
- break;
- case -1:
- netdev_dbg(gtp->dev, "GTP packet has been dropped\n");
- kfree_skb(skb);
- ret = 0;
- break;
- }
-
- return ret;
-}
-
static int gtp_dev_init(struct net_device *dev)
{
struct gtp_dev *gtp = netdev_priv(dev);
@@ -627,6 +624,8 @@ static void gtp_link_setup(struct net_device *dev)
sizeof(struct iphdr) +
sizeof(struct udphdr) +
sizeof(struct gtp0_header);
+
+ gro_cells_init(>p->gro_cells, dev);
}
static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
@@ -683,6 +682,7 @@ static void gtp_dellink(struct net_device *dev, struct list_head *head)
{
struct gtp_dev *gtp = netdev_priv(dev);
+ gro_cells_destroy(>p->gro_cells);
gtp_encap_disable(gtp);
gtp_hashtable_free(gtp);
list_del_rcu(>p->list);
@@ -804,9 +804,21 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
sk = sock->sk;
sock_hold(sk);
+ switch (type) {
+ case UDP_ENCAP_GTP0:
+ tuncfg.encap_rcv = gtp0_udp_encap_recv;
+ break;
+ case UDP_ENCAP_GTP1U:
+ tuncfg.encap_rcv = gtp1u_udp_encap_recv;
+ break;
+ default:
+ pr_debug("Unknown encap type %u\n", type);
+ sk = ERR_PTR(-EINVAL);
+ goto out_sock;
+ }
+
tuncfg.sk_user_data = gtp;
tuncfg.encap_type = type;
- tuncfg.encap_rcv = gtp_encap_recv;
tuncfg.encap_destroy = gtp_encap_destroy;
setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg);
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 03/14] gtp: Call common functions to get tunnel routes and add dst_cache
From: Tom Herbert @ 2017-09-19 0:38 UTC (permalink / raw)
To: davem; +Cc: netdev, pablo, laforge, rohit, Tom Herbert
In-Reply-To: <20170919003904.5124-1-tom@quantonium.net>
Call ip_tunnel_get_route and dst_cache to pdp context which should
improve performance by obviating the need to perform a route lookup
on every packet.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
drivers/net/gtp.c | 59 ++++++++++++++++++++++++++++++-------------------------
1 file changed, 32 insertions(+), 27 deletions(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index f38e32a7ec9c..95df3bcebbb2 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -63,6 +63,8 @@ struct pdp_ctx {
atomic_t tx_seq;
struct rcu_head rcu_head;
+
+ struct dst_cache dst_cache;
};
/* One instance of the GTP device. */
@@ -379,20 +381,6 @@ static void gtp_dev_uninit(struct net_device *dev)
free_percpu(dev->tstats);
}
-static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4,
- const struct sock *sk,
- __be32 daddr)
-{
- memset(fl4, 0, sizeof(*fl4));
- fl4->flowi4_oif = sk->sk_bound_dev_if;
- fl4->daddr = daddr;
- fl4->saddr = inet_sk(sk)->inet_saddr;
- fl4->flowi4_tos = RT_CONN_FLAGS(sk);
- fl4->flowi4_proto = sk->sk_protocol;
-
- return ip_route_output_key(sock_net(sk), fl4);
-}
-
static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
{
int payload_len = skb->len;
@@ -479,6 +467,8 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
struct rtable *rt;
struct flowi4 fl4;
struct iphdr *iph;
+ struct sock *sk;
+ __be32 saddr;
__be16 df;
int mtu;
@@ -498,19 +488,27 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
}
netdev_dbg(dev, "found PDP context %p\n", pctx);
- rt = ip4_route_output_gtp(&fl4, pctx->sk, pctx->peer_addr_ip4.s_addr);
- if (IS_ERR(rt)) {
- netdev_dbg(dev, "no route to SSGN %pI4\n",
- &pctx->peer_addr_ip4.s_addr);
- dev->stats.tx_carrier_errors++;
- goto err;
- }
+ sk = pctx->sk;
+ saddr = inet_sk(sk)->inet_saddr;
- if (rt->dst.dev == dev) {
- netdev_dbg(dev, "circular route to SSGN %pI4\n",
- &pctx->peer_addr_ip4.s_addr);
- dev->stats.collisions++;
- goto err_rt;
+ rt = ip_tunnel_get_route(dev, skb, sk->sk_protocol,
+ sk->sk_bound_dev_if, RT_CONN_FLAGS(sk),
+ pctx->peer_addr_ip4.s_addr, &saddr,
+ pktinfo->gtph_port, pktinfo->gtph_port,
+ &pctx->dst_cache, NULL);
+
+ if (IS_ERR(rt)) {
+ if (rt == ERR_PTR(-ELOOP)) {
+ netdev_dbg(dev, "circular route to SSGN %pI4\n",
+ &pctx->peer_addr_ip4.s_addr);
+ dev->stats.collisions++;
+ goto err_rt;
+ } else {
+ netdev_dbg(dev, "no route to SSGN %pI4\n",
+ &pctx->peer_addr_ip4.s_addr);
+ dev->stats.tx_carrier_errors++;
+ goto err;
+ }
}
skb_dst_drop(skb);
@@ -543,7 +541,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
goto err_rt;
}
- gtp_set_pktinfo_ipv4(pktinfo, pctx->sk, iph, pctx, rt, &fl4, dev);
+ gtp_set_pktinfo_ipv4(pktinfo, sk, iph, pctx, rt, &fl4, dev);
gtp_push_header(skb, pktinfo);
return 0;
@@ -917,6 +915,7 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
struct pdp_ctx *pctx;
bool found = false;
__be32 ms_addr;
+ int err;
ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size;
@@ -951,6 +950,12 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
if (pctx == NULL)
return -ENOMEM;
+ err = dst_cache_init(&pctx->dst_cache, GFP_KERNEL);
+ if (err) {
+ kfree(pctx);
+ return err;
+ }
+
sock_hold(sk);
pctx->sk = sk;
pctx->dev = gtp->dev;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 02/14] vxlan: Call common functions to get tunnel routes
From: Tom Herbert @ 2017-09-19 0:38 UTC (permalink / raw)
To: davem; +Cc: netdev, pablo, laforge, rohit, Tom Herbert
In-Reply-To: <20170919003904.5124-1-tom@quantonium.net>
Call ip_tunnel_get_route and ip6_tnl_get_route to handle getting a route
and dealing with the dst_cache.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
drivers/net/vxlan.c | 84 ++++-------------------------------------------------
1 file changed, 5 insertions(+), 79 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d7c49cf1d5e9..810caa9adf37 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1867,47 +1867,11 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct net_device
struct dst_cache *dst_cache,
const struct ip_tunnel_info *info)
{
- bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
- struct rtable *rt = NULL;
- struct flowi4 fl4;
-
if (!sock4)
return ERR_PTR(-EIO);
- if (tos && !info)
- use_cache = false;
- if (use_cache) {
- rt = dst_cache_get_ip4(dst_cache, saddr);
- if (rt)
- return rt;
- }
-
- memset(&fl4, 0, sizeof(fl4));
- fl4.flowi4_oif = oif;
- fl4.flowi4_tos = RT_TOS(tos);
- fl4.flowi4_mark = skb->mark;
- fl4.flowi4_proto = IPPROTO_UDP;
- fl4.daddr = daddr;
- fl4.saddr = *saddr;
- fl4.fl4_dport = dport;
- fl4.fl4_sport = sport;
-
- rt = ip_route_output_key(vxlan->net, &fl4);
- if (likely(!IS_ERR(rt))) {
- if (rt->dst.dev == dev) {
- netdev_dbg(dev, "circular route to %pI4\n", &daddr);
- ip_rt_put(rt);
- return ERR_PTR(-ELOOP);
- }
-
- *saddr = fl4.saddr;
- if (use_cache)
- dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr);
- } else {
- netdev_dbg(dev, "no route to %pI4\n", &daddr);
- return ERR_PTR(-ENETUNREACH);
- }
- return rt;
+ return ip_tunnel_get_route(dev, skb, IPPROTO_UDP, oif, tos, daddr,
+ saddr, dport, sport, dst_cache, info);
}
#if IS_ENABLED(CONFIG_IPV6)
@@ -1922,50 +1886,12 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
struct dst_cache *dst_cache,
const struct ip_tunnel_info *info)
{
- bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
- struct dst_entry *ndst;
- struct flowi6 fl6;
- int err;
-
if (!sock6)
return ERR_PTR(-EIO);
- if (tos && !info)
- use_cache = false;
- if (use_cache) {
- ndst = dst_cache_get_ip6(dst_cache, saddr);
- if (ndst)
- return ndst;
- }
-
- memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_oif = oif;
- fl6.daddr = *daddr;
- fl6.saddr = *saddr;
- fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tos), label);
- fl6.flowi6_mark = skb->mark;
- fl6.flowi6_proto = IPPROTO_UDP;
- fl6.fl6_dport = dport;
- fl6.fl6_sport = sport;
-
- err = ipv6_stub->ipv6_dst_lookup(vxlan->net,
- sock6->sock->sk,
- &ndst, &fl6);
- if (unlikely(err < 0)) {
- netdev_dbg(dev, "no route to %pI6\n", daddr);
- return ERR_PTR(-ENETUNREACH);
- }
-
- if (unlikely(ndst->dev == dev)) {
- netdev_dbg(dev, "circular route to %pI6\n", daddr);
- dst_release(ndst);
- return ERR_PTR(-ELOOP);
- }
-
- *saddr = fl6.saddr;
- if (use_cache)
- dst_cache_set_ip6(dst_cache, ndst, saddr);
- return ndst;
+ return ip6_tnl_get_route(dev, skb, sock6->sock->sk, IPPROTO_UDP, oif,
+ tos, label, daddr, saddr, dport, sport,
+ dst_cache, info);
}
#endif
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 01/14] iptunnel: Add common functions to get a tunnel route
From: Tom Herbert @ 2017-09-19 0:38 UTC (permalink / raw)
To: davem; +Cc: netdev, pablo, laforge, rohit, Tom Herbert
In-Reply-To: <20170919003904.5124-1-tom@quantonium.net>
ip_tunnel_get_route and ip6_tnl_get_route are create to return
routes for a tunnel. These functions are derived from the VXLAN
functions.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
include/net/ip6_tunnel.h | 33 +++++++++++++++++++++++++++++++++
include/net/ip_tunnels.h | 33 +++++++++++++++++++++++++++++++++
net/ipv4/ip_tunnel.c | 41 +++++++++++++++++++++++++++++++++++++++++
net/ipv6/ip6_tunnel.c | 43 +++++++++++++++++++++++++++++++++++++++++++
4 files changed, 150 insertions(+)
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 08fbc7f7d8d7..233097bf07a2 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -142,6 +142,39 @@ __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr,
struct net *ip6_tnl_get_link_net(const struct net_device *dev);
int ip6_tnl_get_iflink(const struct net_device *dev);
int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu);
+struct dst_entry *__ip6_tnl_get_route(struct net_device *dev,
+ struct sk_buff *skb, struct sock *sk,
+ u8 proto, int oif, u8 tos, __be32 label,
+ const struct in6_addr *daddr,
+ struct in6_addr *saddr,
+ __be16 dport, __be16 sport,
+ struct dst_cache *dst_cache,
+ const struct ip_tunnel_info *info,
+ bool use_cache);
+
+static inline struct dst_entry *ip6_tnl_get_route(struct net_device *dev,
+ struct sk_buff *skb, struct sock *sk, u8 proto,
+ int oif, u8 tos, __be32 label,
+ const struct in6_addr *daddr,
+ struct in6_addr *saddr,
+ __be16 dport, __be16 sport,
+ struct dst_cache *dst_cache,
+ const struct ip_tunnel_info *info)
+{
+ bool use_cache = (ip_tunnel_dst_cache_usable(skb, info) &&
+ (!tos || info));
+
+ if (use_cache) {
+ struct dst_entry *ndst = dst_cache_get_ip6(dst_cache, saddr);
+
+ if (ndst)
+ return ndst;
+ }
+
+ return __ip6_tnl_get_route(dev, skb, sk, proto, oif, tos, label,
+ daddr, saddr, dport, sport, dst_cache,
+ info, use_cache);
+}
static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
struct net_device *dev)
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 992652856fe8..91d5150a1044 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -284,6 +284,39 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p, __u32 fwmark);
void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);
+struct rtable *__ip_tunnel_get_route(struct net_device *dev,
+ struct sk_buff *skb, u8 proto,
+ int oif, u8 tos,
+ __be32 daddr, __be32 *saddr,
+ __be16 dport, __be16 sport,
+ struct dst_cache *dst_cache,
+ const struct ip_tunnel_info *info,
+ bool use_cache);
+
+static inline struct rtable *ip_tunnel_get_route(struct net_device *dev,
+ struct sk_buff *skb, u8 proto,
+ int oif, u8 tos,
+ __be32 daddr, __be32 *saddr,
+ __be16 dport, __be16 sport,
+ struct dst_cache *dst_cache,
+ const struct ip_tunnel_info *info)
+{
+ bool use_cache = (ip_tunnel_dst_cache_usable(skb, info) &&
+ (!tos || info));
+
+ if (use_cache) {
+ struct rtable *rt;
+
+ rt = dst_cache_get_ip4(dst_cache, saddr);
+ if (rt)
+ return rt;
+ }
+
+ return __ip_tunnel_get_route(dev, skb, proto, oif, tos,
+ daddr, saddr, dport, sport,
+ dst_cache, info, use_cache);
+}
+
struct ip_tunnel_encap_ops {
size_t (*encap_hlen)(struct ip_tunnel_encap *e);
int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index e9805ad664ac..f0f35333febd 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -935,6 +935,47 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
}
EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
+struct rtable *__ip_tunnel_get_route(struct net_device *dev,
+ struct sk_buff *skb, u8 proto,
+ int oif, u8 tos,
+ __be32 daddr, __be32 *saddr,
+ __be16 dport, __be16 sport,
+ struct dst_cache *dst_cache,
+ const struct ip_tunnel_info *info,
+ bool use_cache)
+{
+ struct rtable *rt = NULL;
+ struct flowi4 fl4;
+
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.flowi4_oif = oif;
+ fl4.flowi4_tos = RT_TOS(tos);
+ fl4.flowi4_mark = skb->mark;
+ fl4.flowi4_proto = proto;
+ fl4.daddr = daddr;
+ fl4.saddr = *saddr;
+ fl4.fl4_dport = dport;
+ fl4.fl4_sport = sport;
+
+ rt = ip_route_output_key(dev_net(dev), &fl4);
+ if (likely(!IS_ERR(rt))) {
+ if (rt->dst.dev == dev) {
+ netdev_dbg(dev, "circular route to %pI4\n", &daddr);
+ ip_rt_put(rt);
+ return ERR_PTR(-ELOOP);
+ }
+
+ *saddr = fl4.saddr;
+ if (use_cache)
+ dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr);
+ } else {
+ netdev_dbg(dev, "no route to %pI4\n", &daddr);
+ return ERR_PTR(-ENETUNREACH);
+ }
+ return rt;
+}
+EXPORT_SYMBOL_GPL(__ip_tunnel_get_route);
+
int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index ae73164559d5..9a02b62c808b 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1663,6 +1663,49 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
return err;
}
+struct dst_entry *__ip6_tnl_get_route(struct net_device *dev,
+ struct sk_buff *skb, struct sock *sk,
+ u8 proto, int oif, u8 tos, __be32 label,
+ const struct in6_addr *daddr,
+ struct in6_addr *saddr,
+ __be16 dport, __be16 sport,
+ struct dst_cache *dst_cache,
+ const struct ip_tunnel_info *info,
+ bool use_cache)
+{
+ struct dst_entry *ndst;
+ struct flowi6 fl6;
+ int err;
+
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_oif = oif;
+ fl6.daddr = *daddr;
+ fl6.saddr = *saddr;
+ fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tos), label);
+ fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_proto = proto;
+ fl6.fl6_dport = dport;
+ fl6.fl6_sport = sport;
+
+ err = ipv6_stub->ipv6_dst_lookup(dev_net(dev), sk, &ndst, &fl6);
+ if (unlikely(err < 0)) {
+ netdev_dbg(dev, "no route to %pI6\n", daddr);
+ return ERR_PTR(-ENETUNREACH);
+ }
+
+ if (unlikely(ndst->dev == dev)) {
+ netdev_dbg(dev, "circular route to %pI6\n", daddr);
+ dst_release(ndst);
+ return ERR_PTR(-ELOOP);
+ }
+
+ *saddr = fl6.saddr;
+ if (use_cache)
+ dst_cache_set_ip6(dst_cache, ndst, saddr);
+ return ndst;
+}
+EXPORT_SYMBOL_GPL(__ip6_tnl_get_route);
+
/**
* ip6_tnl_change_mtu - change mtu manually for tunnel device
* @dev: virtual device associated with tunnel
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 00/14] gtp: Additional feature support
From: Tom Herbert @ 2017-09-19 0:38 UTC (permalink / raw)
To: davem; +Cc: netdev, pablo, laforge, rohit, Tom Herbert
This patch set builds upon the initial GTP implementation to make
support closer to that enjoyed by other encapsulation protocols.
The major items are:
- IPv6 support
- Configurable networking interfaces so that GTP kernel can be
used and tested without needing GSN network emulation (i.e. no user
space daemon needed).
- GSO,GRO
- Control of zero UDP checksums
- Port numbers are configurable
- Addition of a dst_cache in the GTP structure and other cleanup
Additionally, this patch set also includes a couple of general support
capabilities:
- A facility that allows application specific GSO callbacks
- Common functions to get a route fo for an IP tunnel
For IPv6 support, the mobile subscriber needs to allow IPv6 addresses,
and the remote enpoint can be IPv6.
For configurable interfaces, configuration is added to allow an
alterate means to configure a GTP and device. This follows the
typical UDP encapsulation model of specifying a listener port for
receive, and a remote address and port for transmit.
GRO was straightfoward to implement following the model of other
UDP encapsulations.
Providing GSO support had one wrinkle-- the GTP header includes a
payload length field that needs to be set per GSO segment. In order
to address that in a general way, I create the concept of
application specific GSO.
To implement application layer GSO I reserved the top four bits of
shinfo(skb)->gso_type. The idea is that an application or encapsulation
protocol (like GTP in this case) can register a GSO segment callback.
The facility returns a gso_type with upper four bits set to a value
(index into a table). When the application sets up a packet it includes
the code in the gso_type for the skb. At some point (e.g. from UDP
segment) the gso_type is checked in the skb and if the application
specific GSO is indicated then the callback is called. The
registered callbacks include a set of other gso_types so that
an application callback can be matched to an appropriate instance.
FOr instance, the GTP callback checks for the UDP GSO flags.
Zero UDP checksum, port number configuration, and dst_cache are
straightforwad.
Configuration is performed by iproute2/ip. I will post that
in a subsequent patch set.
Tested:
Configured the matrix of IPv4/IPv6 mobile subscriber, IPv4/IPv6 remote
peer, and GTP version 0 and 1 (eight combinations). Observed
connectivity and proper GSO/GRO. Also, tested VXLAN for
regression.
Tom Herbert (14):
iptunnel: Add common functions to get a tunnel route
vxlan: Call common functions to get tunnel routes
gtp: Call common functions to get tunnel routes and add dst_cache
gtp: udp recv clean up
gtp: Remove special mtu handling
gtp: Eliminate pktinfo and add port configuration
gtp: Support encapsulation of IPv6 packets
gtp: Support encpasulating over IPv6
gtp: Allow configuring GTP interface as standalone
gtp: Add support for devnet
net: Add a facility to support application defined GSO
gtp: Configuration for zero UDP checksum
gtp: Support for GRO
gtp: GSO support
drivers/net/gtp.c | 1300 ++++++++++++++++++++++++++++++++----------
drivers/net/vxlan.c | 84 +--
include/linux/netdevice.h | 31 +
include/linux/skbuff.h | 25 +
include/net/ip6_tunnel.h | 33 ++
include/net/ip_tunnels.h | 33 ++
include/uapi/linux/gtp.h | 8 +
include/uapi/linux/if_link.h | 6 +
net/core/dev.c | 47 ++
net/ipv4/ip_tunnel.c | 41 ++
net/ipv4/ip_tunnel_core.c | 6 +
net/ipv4/udp_offload.c | 20 +-
net/ipv6/ip6_tunnel.c | 43 ++
13 files changed, 1306 insertions(+), 371 deletions(-)
--
2.11.0
^ permalink raw reply
* Re: [PATCH net] tcp: remove two unused functions
From: David Miller @ 2017-09-19 0:26 UTC (permalink / raw)
To: ycheng; +Cc: netdev, ncardwell, edumazet
In-Reply-To: <20170918180516.22390-1-ycheng@google.com>
From: Yuchung Cheng <ycheng@google.com>
Date: Mon, 18 Sep 2017 11:05:16 -0700
> remove tcp_may_send_now and tcp_snd_test that are no longer used
>
> Fixes: 840a3cbe8969 ("tcp: remove forward retransmit feature")
> Signed-off-by: Yuchung Cheng <ycheng@google.com>
> Signed-off-by: Neal Cardwell <ncardwell@google.com>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
Applied, thanks.
^ permalink raw reply
* Re: [PATCH net 1/3] net: mvpp2: fix the dma_mask and coherent_dma_mask settings for PPv2.2
From: David Miller @ 2017-09-19 0:18 UTC (permalink / raw)
To: antoine.tenart
Cc: andrew, gregory.clement, thomas.petazzoni, miquel.raynal, nadavh,
linux, linux-kernel, mw, stefanc, netdev
In-Reply-To: <20170918130408.23114-2-antoine.tenart@free-electrons.com>
From: Antoine Tenart <antoine.tenart@free-electrons.com>
Date: Mon, 18 Sep 2017 15:04:06 +0200
> The dev->dma_mask usually points to dev->coherent_dma_mask. This is an
> issue as setting both of them will override the other. This is
> problematic here as the PPv2 driver uses a 32-bit-mask for coherent
> accesses (txq, rxq, bm) and a 40-bit mask for all other accesses due to
> an hardware limitation.
>
> This can lead to a memory remap for all dma_map_single() calls when
> dealing with memory above 4GB.
>
> Fixes: 2067e0a13cfe ("net: mvpp2: set dma mask and coherent dma mask on PPv2.2")
> Reported-by: Stefan Chulski <stefanc@marvell.com>
> Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
Yikes.
I surrmise that if the platform has made dev->dma_mask point to
&dev->coherent_dma_mask, it is because it does not allow the two
settings to be set separately.
By rearranging the pointer, you are bypassing that, and probably
breaking things or creating a situation that the DMA mapping
layer is not expecting.
I want to know more about the situations where dma_mask is set to
point to &coherent_dma_mask and how that is supposed to work.
At a minimum this commit log message needs to go into more detail.
Thanks.
^ permalink raw reply
* RE: [Intel-wired-lan] [PATCH 2/5] e1000e: Fix wrong comment related to link detection
From: Brown, Aaron F @ 2017-09-19 0:13 UTC (permalink / raw)
To: Benjamin Poirier, Kirsher, Jeffrey T
Cc: netdev@vger.kernel.org, intel-wired-lan@lists.osuosl.org,
linux-kernel@vger.kernel.org, Lennart Sorensen
In-Reply-To: <20170721183627.13373-2-bpoirier@suse.com>
> From: Intel-wired-lan [mailto:intel-wired-lan-bounces@osuosl.org] On Behalf
> Of Benjamin Poirier
> Sent: Friday, July 21, 2017 11:36 AM
> To: Kirsher, Jeffrey T <jeffrey.t.kirsher@intel.com>
> Cc: netdev@vger.kernel.org; intel-wired-lan@lists.osuosl.org; linux-
> kernel@vger.kernel.org; Lennart Sorensen <lsorense@csclub.uwaterloo.ca>
> Subject: [Intel-wired-lan] [PATCH 2/5] e1000e: Fix wrong comment related to
> link detection
>
> Reading e1000e_check_for_copper_link() shows that get_link_status is set to
> false after link has been detected. Therefore, it stays TRUE until then.
>
> Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
> ---
> drivers/net/ethernet/intel/e1000e/netdev.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
^ permalink raw reply
* Re: [PATCH] bpf: devmap: pass on return value of bpf_map_precharge_memlock
From: David Miller @ 2017-09-18 23:53 UTC (permalink / raw)
To: tklauser; +Cc: ast, daniel, john.fastabend, netdev
In-Reply-To: <20170918130346.10833-1-tklauser@distanz.ch>
From: Tobias Klauser <tklauser@distanz.ch>
Date: Mon, 18 Sep 2017 15:03:46 +0200
> If bpf_map_precharge_memlock in dev_map_alloc, -ENOMEM is returned
> regardless of the actual error produced by bpf_map_precharge_memlock.
> Fix it by passing on the error returned by bpf_map_precharge_memlock.
>
> Also return -EINVAL instead of -ENOMEM if the page count overflow check
> fails.
>
> This makes dev_map_alloc match the behavior of other bpf maps' alloc
> functions wrt. return values.
>
> Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Applied, thank you.
^ permalink raw reply
* Re: [PATCH] net_sched: use explicit size of struct tcmsg, remove need to declare tcm
From: David Miller @ 2017-09-18 23:52 UTC (permalink / raw)
To: colin.king
Cc: jhs, xiyou.wangcong, jiri, netdev, kernel-janitors, linux-kernel
In-Reply-To: <20170918114038.29741-1-colin.king@canonical.com>
From: Colin King <colin.king@canonical.com>
Date: Mon, 18 Sep 2017 12:40:38 +0100
> From: Colin Ian King <colin.king@canonical.com>
>
> Pointer tcm is being initialized and is never read, it is only being used
> to determine the size of struct tcmsg. Clean this up by removing
> variable tcm and explicitly using the sizeof struct tcmsg rather than *tcm.
> Cleans up clang warning:
>
> warning: Value stored to 'tcm' during its initialization is never read
>
> Signed-off-by: Colin Ian King <colin.king@canonical.com>
Applied to net-next.
^ permalink raw reply
* Re: [net PATCH] bnxt_en: check for ingress qdisc in flower offload
From: David Miller @ 2017-09-18 23:52 UTC (permalink / raw)
To: sathya.perla; +Cc: netdev, michael.chan
In-Reply-To: <1505734537-6695-1-git-send-email-sathya.perla@broadcom.com>
From: Sathya Perla <sathya.perla@broadcom.com>
Date: Mon, 18 Sep 2017 17:05:37 +0530
> Check for ingress-only qdisc for flower offload, as other qdiscs
> are not supported for flower offload.
>
> Suggested-by: Jiri Pirko <jiri@resnulli.us>
> Signed-off-by: Sathya Perla <sathya.perla@broadcom.com>
Applied, thanks.
^ permalink raw reply
* Re: [PATCH net-next v2 0/7] korina: performance fixes and cleanup
From: David Miller @ 2017-09-18 23:50 UTC (permalink / raw)
To: leroi.lists; +Cc: netdev
In-Reply-To: <20170917172353.32225-1-roman@advem.lv>
From: Roman Yeryomin <leroi.lists@gmail.com>
Date: Sun, 17 Sep 2017 20:23:53 +0300
> Changes from v1:
> - use GRO instead of increasing ring size
> - use NAPI_POLL_WEIGHT instead of defining own NAPI_WEIGHT
> - optimize rx descriptor flags processing
Series applied, thank you.
^ permalink raw reply
* Re: [PATCH RFC 6/6] Modify tag_ksz.c to support other KSZ switch drivers
From: Florian Fainelli @ 2017-09-18 23:48 UTC (permalink / raw)
To: Tristram.Ha, andrew
Cc: muvarov, pavel, nathan.leigh.conrad, vivien.didelot, netdev,
linux-kernel, Woojung.Huh
In-Reply-To: <93AF473E2DA327428DE3D46B72B1E9FD41124E0C@CHN-SV-EXMX02.mchp-main.com>
On 09/18/2017 04:44 PM, Tristram.Ha@microchip.com wrote:
>>> In the old DSA implementation all the ports are partitioned into its own
>> device
>>> and the bridge joining them will do all the forwarding. This is useful for
>> quick
>>> testing with some protocols like RSTP but it is probably useless for real
>>> operation.
>>
>> It is a good minimal driver, to get something into the kernel. You can
>> then add features to it.
>>
>>> The new switchdev model tries to use the switch hardware as much as
>>> possible. This offload_fwd_mark bit means the frame is forwarded by the
>>> hardware switch, so the software bridge does not need to do it again.
>> Without
>>> this bit there will be duplicated multicast frames coming out the ports if
>> internal
>>> forwarding is enabled.
>>
>> Correct. Once you switch driver is clever enough, you can enable
>> offload_fwd_mark.
>>
>>> When RSTP is used the port can be put in blocked state and so the
>> forwarding
>>> will stop for that port. Currently the switch driver will check that
>> membership
>>> to decide whether to set that bit.
>>
>> This i don't get. RSTP or STP just break loops. How does RSTP vs STP
>> mean you need to set offload_fwd_mark differently?
>>
>
> The logic of the switch driver is if the membership of the port receiving
> the frame contains other ports--not counting cpu port--the bit
> offload_fwd_mark is set. In RSTP closing the blocked port is generally good
> enough, but there are exceptions, so the port is removed from the
> membership of other forwarding ports. A disabled port will have its
> membership completely reset so it cannot receive anything. It does not
> matter much in RSTP as the software bridge should know whether to forward
> the frame or not.
>
> We are back to square one. Is there any plan to add this offload_fwd_mark
> support to DSA driver so that it can be reported properly? It can be set all the
> time, except during port initialization or before bridge creation the forwarding
> state does not reflect reality.
>
> If not the port membership can be fixed and there is no internal switch
> forwarding, leaving everything handled by the software bridge.
I am not really sure why this is such a concern for you so soon when
your driver is not even included yet. You should really aim for baby
steps here: get the basic driver(s) included, with a limited set of
features, and gradually add more features to the driver. When
fwd_offload_mark and RSTP become a real problem, we can most
definitively find a way to fix those in DSA and depending drivers.
--
Florian
^ permalink raw reply
* RE: [PATCH RFC 6/6] Modify tag_ksz.c to support other KSZ switch drivers
From: Tristram.Ha @ 2017-09-18 23:44 UTC (permalink / raw)
To: andrew
Cc: muvarov, pavel, nathan.leigh.conrad, vivien.didelot, f.fainelli,
netdev, linux-kernel, Woojung.Huh
In-Reply-To: <20170918225142.GC29615@lunn.ch>
> > In the old DSA implementation all the ports are partitioned into its own
> device
> > and the bridge joining them will do all the forwarding. This is useful for
> quick
> > testing with some protocols like RSTP but it is probably useless for real
> > operation.
>
> It is a good minimal driver, to get something into the kernel. You can
> then add features to it.
>
> > The new switchdev model tries to use the switch hardware as much as
> > possible. This offload_fwd_mark bit means the frame is forwarded by the
> > hardware switch, so the software bridge does not need to do it again.
> Without
> > this bit there will be duplicated multicast frames coming out the ports if
> internal
> > forwarding is enabled.
>
> Correct. Once you switch driver is clever enough, you can enable
> offload_fwd_mark.
>
> > When RSTP is used the port can be put in blocked state and so the
> forwarding
> > will stop for that port. Currently the switch driver will check that
> membership
> > to decide whether to set that bit.
>
> This i don't get. RSTP or STP just break loops. How does RSTP vs STP
> mean you need to set offload_fwd_mark differently?
>
The logic of the switch driver is if the membership of the port receiving
the frame contains other ports--not counting cpu port--the bit
offload_fwd_mark is set. In RSTP closing the blocked port is generally good
enough, but there are exceptions, so the port is removed from the
membership of other forwarding ports. A disabled port will have its
membership completely reset so it cannot receive anything. It does not
matter much in RSTP as the software bridge should know whether to forward
the frame or not.
We are back to square one. Is there any plan to add this offload_fwd_mark
support to DSA driver so that it can be reported properly? It can be set all the
time, except during port initialization or before bridge creation the forwarding
state does not reflect reality.
If not the port membership can be fixed and there is no internal switch
forwarding, leaving everything handled by the software bridge.
^ permalink raw reply
* Re: [PATCH] hamradio: baycom: use new parport device model
From: David Miller @ 2017-09-18 23:40 UTC (permalink / raw)
To: sudipm.mukherjee; +Cc: t.sailer, linux-kernel, linux-hams, netdev
In-Reply-To: <1505648780-4385-1-git-send-email-sudipm.mukherjee@gmail.com>
From: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Date: Sun, 17 Sep 2017 12:46:20 +0100
> Modify baycom driver to use the new parallel port device model.
>
> Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Applied to net-next, thanks.
^ permalink raw reply
* Re: [PATCH] Documentation: networking: fix ASCII art in switchdev.txt
From: David Miller @ 2017-09-18 23:39 UTC (permalink / raw)
To: rdunlap; +Cc: netdev, pavel, andrew, schwab, jiri, sfeldma
In-Reply-To: <984d9d24-b558-6308-3252-1c8ddd5eb7c8@infradead.org>
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 16 Sep 2017 13:10:06 -0700
> From: Randy Dunlap <rdunlap@infradead.org>
>
> Fix ASCII art in Documentation/networking/switchdev.txt:
>
> Change non-ASCII "spaces" to ASCII spaces.
>
> Change 2 erroneous '+' characters in ASCII art to '-' (at the '*'
> characters below):
>
> line 32:
> +--+----+----+----+-*--+----+---+ +-----+-----+
> line 41:
> +--------------+---*------------+
>
> Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Applied, thanks Randy.
^ permalink raw reply
* [PATCH net] bpf: one perf event close won't free bpf program attached by another perf event
From: Yonghong Song @ 2017-09-18 23:38 UTC (permalink / raw)
To: peterz, rostedt, ast, daniel, netdev; +Cc: kernel-team
This patch fixes a bug exhibited by the following scenario:
1. fd1 = perf_event_open with attr.config = ID1
2. attach bpf program prog1 to fd1
3. fd2 = perf_event_open with attr.config = ID1
<this will be successful>
4. user program closes fd2 and prog1 is detached from the tracepoint.
5. user program with fd1 does not work properly as tracepoint
no output any more.
The issue happens at step 4. Multiple perf_event_open can be called
successfully, but only one bpf prog pointer in the tp_event. In the
current logic, any fd release for the same tp_event will free
the tp_event->prog.
The fix is to free tp_event->prog only when the closing fd
corresponds to the one which registered the program.
Signed-off-by: Yonghong Song <yhs@fb.com>
---
Additional context: discussed with Alexei internally but did not find
a solution which can avoid introducing the additional field in
trace_event_call structure.
Peter, could you take a look as well and maybe you could have better
alternative? Thanks!
include/linux/trace_events.h | 1 +
kernel/events/core.c | 3 ++-
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 7f11050..2e0f222 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -272,6 +272,7 @@ struct trace_event_call {
int perf_refcount;
struct hlist_head __percpu *perf_events;
struct bpf_prog *prog;
+ struct perf_event *bpf_prog_owner;
int (*perf_perm)(struct trace_event_call *,
struct perf_event *);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3e691b7..6bc21e2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8171,6 +8171,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
}
}
event->tp_event->prog = prog;
+ event->tp_event->bpf_prog_owner = event;
return 0;
}
@@ -8185,7 +8186,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
return;
prog = event->tp_event->prog;
- if (prog) {
+ if (prog && event->tp_event->bpf_prog_owner == event) {
event->tp_event->prog = NULL;
bpf_prog_put(prog);
}
--
2.9.5
^ permalink raw reply related
* Re: [PATCH net] net/sched: cls_matchall: fix crash when used with classful qdisc
From: David Miller @ 2017-09-18 23:38 UTC (permalink / raw)
To: dcaratti; +Cc: jiri, jhs, jbenc, netdev
In-Reply-To: <b930159de5531a4d216a1cd2c2ef03aa41f421f9.1505562794.git.dcaratti@redhat.com>
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 16 Sep 2017 14:02:21 +0200
> this script, edited from Linux Advanced Routing and Traffic Control guide
>
> tc q a dev en0 root handle 1: htb default a
> tc c a dev en0 parent 1: classid 1:1 htb rate 6mbit burst 15k
> tc c a dev en0 parent 1:1 classid 1:a htb rate 5mbit ceil 6mbit burst 15k
> tc c a dev en0 parent 1:1 classid 1:b htb rate 1mbit ceil 6mbit burst 15k
> tc f a dev en0 parent 1:0 prio 1 $clsname $clsargs classid 1:b
> ping $address -c1
> tc -s c s dev en0
>
> classifies traffic to 1:b or 1:a, depending on whether the packet matches
> or not the pattern $clsargs of filter $clsname. However, when $clsname is
> 'matchall', a systematic crash can be observed in htb_classify(). HTB and
> classful qdiscs don't assign initial value to struct tcf_result, but then
> they expect it to contain valid values after filters have been run. Thus,
> current 'matchall' ignores the TCA_MATCHALL_CLASSID attribute, configured
> by user, and makes HTB (and classful qdiscs) dereference random pointers.
>
> By assigning head->res to *res in mall_classify(), before the actions are
> invoked, we fix this crash and enable TCA_MATCHALL_CLASSID functionality,
> that had no effect on 'matchall' classifier since its first introduction.
>
> BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1460213
> Reported-by: Jiri Benc <jbenc@redhat.com>
> Fixes: b87f7936a932 ("net/sched: introduce Match-all classifier")
> Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Applied and queued up for -stable, thanks.
^ permalink raw reply
* Re: [PATCH net] ip6_tunnel: do not allow loading ip6_tunnel if ipv6 is disabled in cmdline
From: David Miller @ 2017-09-18 23:35 UTC (permalink / raw)
To: lucien.xin; +Cc: netdev, xeb, jbenc
In-Reply-To: <107ac334855fea1e6492b2e523b788209e54ec2f.1505462312.git.lucien.xin@gmail.com>
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 15 Sep 2017 15:58:33 +0800
> If ipv6 has been disabled from cmdline since kernel started, it makes
> no sense to allow users to create any ip6 tunnel. Otherwise, it could
> some potential problem.
>
> Jianlin found a kernel crash caused by this in ip6_gre when he set
> ipv6.disable=1 in grub:
>
> [ 209.588865] Unable to handle kernel paging request for data at address 0x00000080
> [ 209.588872] Faulting instruction address: 0xc000000000a3aa6c
> [ 209.588879] Oops: Kernel access of bad area, sig: 11 [#1]
> [ 209.589062] NIP [c000000000a3aa6c] fib_rules_lookup+0x4c/0x260
> [ 209.589071] LR [c000000000b9ad90] fib6_rule_lookup+0x50/0xb0
> [ 209.589076] Call Trace:
> [ 209.589097] fib6_rule_lookup+0x50/0xb0
> [ 209.589106] rt6_lookup+0xc4/0x110
> [ 209.589116] ip6gre_tnl_link_config+0x214/0x2f0 [ip6_gre]
> [ 209.589125] ip6gre_newlink+0x138/0x3a0 [ip6_gre]
> [ 209.589134] rtnl_newlink+0x798/0xb80
> [ 209.589142] rtnetlink_rcv_msg+0xec/0x390
> [ 209.589151] netlink_rcv_skb+0x138/0x150
> [ 209.589159] rtnetlink_rcv+0x48/0x70
> [ 209.589169] netlink_unicast+0x538/0x640
> [ 209.589175] netlink_sendmsg+0x40c/0x480
> [ 209.589184] ___sys_sendmsg+0x384/0x4e0
> [ 209.589194] SyS_sendmsg+0xd4/0x140
> [ 209.589201] SyS_socketcall+0x3e0/0x4f0
> [ 209.589209] system_call+0x38/0xe0
>
> This patch is to return -EOPNOTSUPP in ip6_tunnel_init if ipv6 has been
> disabled from cmdline.
>
> Reported-by: Jianlin Shi <jishi@redhat.com>
> Signed-off-by: Xin Long <lucien.xin@gmail.com>
Applied and queued up for -stable, thanks.
^ permalink raw reply
* Re: [PATCH net] net: phy: Fix mask value write on gmii2rgmii converter speed register
From: David Miller @ 2017-09-18 23:34 UTC (permalink / raw)
To: fahad.kunnathadi
Cc: f.fainelli, michal.simek, andrew, appanad, soren.brinkmann,
netdev, linux-kernel
In-Reply-To: <1505457118-3933-1-git-send-email-fahad.kunnathadi@dexceldesigns.com>
From: Fahad Kunnathadi <fahad.kunnathadi@dexceldesigns.com>
Date: Fri, 15 Sep 2017 12:01:58 +0530
> To clear Speed Selection in MDIO control register(0x10),
> ie, clear bits 6 and 13 to zero while keeping other bits same.
> Before AND operation,The Mask value has to be perform with bitwise NOT
> operation (ie, ~ operator)
>
> This patch clears current speed selection before writing the
> new speed settings to gmii2rgmii converter
>
> Fixes: f411a6160bd4 ("net: phy: Add gmiitorgmii converter support")
>
> Signed-off-by: Fahad Kunnathadi <fahad.kunnathadi@dexceldesigns.com>
> Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Applied and queued up for -stable, thanks.
^ permalink raw reply
* [PATCH net] net: systemport: Fix 64-bit statistics dependency
From: Florian Fainelli @ 2017-09-18 23:31 UTC (permalink / raw)
To: netdev; +Cc: edumazet, davem, jqiaoulk, kiki-good, Florian Fainelli
There are several problems with commit 10377ba7673d ("net: systemport:
Support 64bit statistics", first one got fixed in 7095c973453e ("net:
systemport: Fix 64-bit stats deadlock").
The second problem is that this specific code updates the
stats64.tx_{packets,bytes} from ndo_get_stats64() and that is what we
are returning to ethtool -S. If we are not running a tool that involves
calling ndo_get_stats64(), then we won't get updated ethtool stats.
The solution to this is to update the stats from both call sites,
factoring that into a specific function, While at it, don't just check
the sizeof() but also the type of the statistics in order to use the
64-bit stats seqlock.
Fixes: 10377ba7673d ("net: systemport: Support 64bit statistics"
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/ethernet/broadcom/bcmsysport.c | 52 ++++++++++++++++++------------
1 file changed, 32 insertions(+), 20 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index c3c53f6cd9e6..83eec9a8c275 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -432,6 +432,27 @@ static void bcm_sysport_update_mib_counters(struct bcm_sysport_priv *priv)
netif_dbg(priv, hw, priv->netdev, "updated MIB counters\n");
}
+static void bcm_sysport_update_tx_stats(struct bcm_sysport_priv *priv,
+ u64 *tx_bytes, u64 *tx_packets)
+{
+ struct bcm_sysport_tx_ring *ring;
+ u64 bytes = 0, packets = 0;
+ unsigned int start;
+ unsigned int q;
+
+ for (q = 0; q < priv->netdev->num_tx_queues; q++) {
+ ring = &priv->tx_rings[q];
+ do {
+ start = u64_stats_fetch_begin_irq(&priv->syncp);
+ bytes = ring->bytes;
+ packets = ring->packets;
+ } while (u64_stats_fetch_retry_irq(&priv->syncp, start));
+
+ *tx_bytes += bytes;
+ *tx_packets += packets;
+ }
+}
+
static void bcm_sysport_get_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
@@ -439,11 +460,16 @@ static void bcm_sysport_get_stats(struct net_device *dev,
struct bcm_sysport_stats64 *stats64 = &priv->stats64;
struct u64_stats_sync *syncp = &priv->syncp;
struct bcm_sysport_tx_ring *ring;
+ u64 tx_bytes = 0, tx_packets = 0;
unsigned int start;
int i, j;
- if (netif_running(dev))
+ if (netif_running(dev)) {
bcm_sysport_update_mib_counters(priv);
+ bcm_sysport_update_tx_stats(priv, &tx_bytes, &tx_packets);
+ stats64->tx_bytes = tx_bytes;
+ stats64->tx_packets = tx_packets;
+ }
for (i = 0, j = 0; i < BCM_SYSPORT_STATS_LEN; i++) {
const struct bcm_sysport_stats *s;
@@ -461,12 +487,13 @@ static void bcm_sysport_get_stats(struct net_device *dev,
continue;
p += s->stat_offset;
- if (s->stat_sizeof == sizeof(u64))
+ if (s->stat_sizeof == sizeof(u64) &&
+ s->type == BCM_SYSPORT_STAT_NETDEV64) {
do {
start = u64_stats_fetch_begin_irq(syncp);
data[i] = *(u64 *)p;
} while (u64_stats_fetch_retry_irq(syncp, start));
- else
+ } else
data[i] = *(u32 *)p;
j++;
}
@@ -1716,27 +1743,12 @@ static void bcm_sysport_get_stats64(struct net_device *dev,
{
struct bcm_sysport_priv *priv = netdev_priv(dev);
struct bcm_sysport_stats64 *stats64 = &priv->stats64;
- struct bcm_sysport_tx_ring *ring;
- u64 tx_packets = 0, tx_bytes = 0;
unsigned int start;
- unsigned int q;
netdev_stats_to_stats64(stats, &dev->stats);
- for (q = 0; q < dev->num_tx_queues; q++) {
- ring = &priv->tx_rings[q];
- do {
- start = u64_stats_fetch_begin_irq(&priv->syncp);
- tx_bytes = ring->bytes;
- tx_packets = ring->packets;
- } while (u64_stats_fetch_retry_irq(&priv->syncp, start));
-
- stats->tx_bytes += tx_bytes;
- stats->tx_packets += tx_packets;
- }
-
- stats64->tx_bytes = stats->tx_bytes;
- stats64->tx_packets = stats->tx_packets;
+ bcm_sysport_update_tx_stats(priv, &stats->tx_bytes,
+ &stats->tx_packets);
do {
start = u64_stats_fetch_begin_irq(&priv->syncp);
--
2.9.3
^ permalink raw reply related
* Re: [PATCH net-next 00/12] net: dsa: b53/bcm_sf2 cleanups
From: David Miller @ 2017-09-18 23:24 UTC (permalink / raw)
To: f.fainelli; +Cc: netdev, andrew, vivien.didelot
In-Reply-To: <24876029-5ebb-075e-3f02-50cf0856474f@gmail.com>
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 18 Sep 2017 14:46:48 -0700
> On 09/18/2017 02:41 PM, Florian Fainelli wrote:
>> Hi all,
>>
>> This patch series is a first pass set of clean-ups to reduce the number of LOCs
>> between b53 and bcm_sf2 and sharing as many functions as possible.
>>
>> There is a number of additional cleanups queued up locally that require more
>> thorough testing.
>
> David, I just spotted a missing EXPORT_SYMBOL() in patch 8 that was not
> flagged since I had temporarily disabled modular build, I will resubmit
> this shortly after checking the other patches too. Thanks!
Ok.
^ permalink raw reply
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