* [RFC bpf-next 6/9] net/ipv6: Update fib6 tracepoint to take fib6_info
From: David Ahern @ 2018-04-25 18:34 UTC (permalink / raw)
To: netdev, borkmann, ast
Cc: shm, roopa, brouer, toke, john.fastabend, David Ahern
In-Reply-To: <20180425183449.25134-1-dsahern@gmail.com>
Similar to IPv4, IPv6 should use the FIB lookup result in the
tracepoint.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/trace/events/fib6.h | 14 +++++++-------
net/ipv6/route.c | 14 ++++++--------
2 files changed, 13 insertions(+), 15 deletions(-)
diff --git a/include/trace/events/fib6.h b/include/trace/events/fib6.h
index 7e8d48a81b91..1b8d951e3c12 100644
--- a/include/trace/events/fib6.h
+++ b/include/trace/events/fib6.h
@@ -12,10 +12,10 @@
TRACE_EVENT(fib6_table_lookup,
- TP_PROTO(const struct net *net, const struct rt6_info *rt,
+ TP_PROTO(const struct net *net, const struct fib6_info *f6i,
struct fib6_table *table, const struct flowi6 *flp),
- TP_ARGS(net, rt, table, flp),
+ TP_ARGS(net, f6i, table, flp),
TP_STRUCT__entry(
__field( u32, tb_id )
@@ -48,20 +48,20 @@ TRACE_EVENT(fib6_table_lookup,
in6 = (struct in6_addr *)__entry->dst;
*in6 = flp->daddr;
- if (rt->rt6i_idev) {
- __assign_str(name, rt->rt6i_idev->dev->name);
+ if (f6i->fib6_nh.nh_dev) {
+ __assign_str(name, f6i->fib6_nh.nh_dev);
} else {
__assign_str(name, "");
}
- if (rt == net->ipv6.ip6_null_entry) {
+ if (f6i == net->ipv6.fib6_null_entry) {
struct in6_addr in6_zero = {};
in6 = (struct in6_addr *)__entry->gw;
*in6 = in6_zero;
- } else if (rt) {
+ } else if (f6i) {
in6 = (struct in6_addr *)__entry->gw;
- *in6 = rt->rt6i_gateway;
+ *in6 = f6i->fib6_nh.nh_gw;
}
),
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 353645ed3d2c..e4163d19d905 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1078,6 +1078,8 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
goto restart;
}
+ trace_fib6_table_lookup(net, f6i, table, fl6);
+
/* Search through exception table */
rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
if (rt) {
@@ -1096,8 +1098,6 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
rcu_read_unlock();
- trace_fib6_table_lookup(net, rt, table, fl6);
-
return rt;
}
@@ -1826,6 +1826,8 @@ struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
}
}
+ trace_fib6_table_lookup(net, f6i, table, fl6);
+
return f6i;
}
@@ -1852,7 +1854,6 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
rt = net->ipv6.ip6_null_entry;
rcu_read_unlock();
dst_hold(&rt->dst);
- trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
}
@@ -1863,7 +1864,6 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
dst_use_noref(&rt->dst, jiffies);
rcu_read_unlock();
- trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
!(f6i->fib6_flags & RTF_GATEWAY))) {
@@ -1889,9 +1889,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
dst_hold(&uncached_rt->dst);
}
- trace_fib6_table_lookup(net, uncached_rt, table, fl6);
return uncached_rt;
-
} else {
/* Get a percpu copy */
@@ -1905,7 +1903,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
local_bh_enable();
rcu_read_unlock();
- trace_fib6_table_lookup(net, pcpu_rt, table, fl6);
+
return pcpu_rt;
}
}
@@ -2483,7 +2481,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
rcu_read_unlock();
- trace_fib6_table_lookup(net, ret, table, fl6);
+ trace_fib6_table_lookup(net, rt, table, fl6);
return ret;
};
--
2.11.0
^ permalink raw reply related
* [RFC bpf-next 7/9] net/ipv6: Add fib lookup stubs for use in bpf helper
From: David Ahern @ 2018-04-25 18:34 UTC (permalink / raw)
To: netdev, borkmann, ast
Cc: shm, roopa, brouer, toke, john.fastabend, David Ahern
In-Reply-To: <20180425183449.25134-1-dsahern@gmail.com>
Add stubs to retrieve a handle to an IPv6 FIB table, fib6_get_table,
a stub to do a lookup in a specific table, fib6_table_lookup, and
a stub for a full route lookup.
The stubs are needed for core bpf code to handle the case when the
IPv6 module is not builtin.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/addrconf.h | 14 ++++++++++++++
net/ipv6/addrconf_core.c | 33 ++++++++++++++++++++++++++++++++-
net/ipv6/af_inet6.c | 6 +++++-
3 files changed, 51 insertions(+), 2 deletions(-)
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 8312cc25a3af..ff766ab207e0 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -223,6 +223,20 @@ struct ipv6_stub {
const struct in6_addr *addr);
int (*ipv6_dst_lookup)(struct net *net, struct sock *sk,
struct dst_entry **dst, struct flowi6 *fl6);
+
+ struct fib6_table *(*fib6_get_table)(struct net *net, u32 id);
+ struct fib6_info *(*fib6_lookup)(struct net *net, int oif,
+ struct flowi6 *fl6, int flags);
+ struct fib6_info *(*fib6_table_lookup)(struct net *net,
+ struct fib6_table *table,
+ int oif, struct flowi6 *fl6,
+ int flags);
+ struct fib6_info *(*fib6_multipath_select)(const struct net *net,
+ struct fib6_info *f6i,
+ struct flowi6 *fl6, int oif,
+ const struct sk_buff *skb,
+ int strict);
+
void (*udpv6_encap_enable)(void);
void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr,
const struct in6_addr *solicited_addr,
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 32b564dfd02a..2fe754fd4f5e 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -134,8 +134,39 @@ static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1,
return -EAFNOSUPPORT;
}
+static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id)
+{
+ return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_table_lookup(struct net *net, struct fib6_table *table,
+ int oif, struct flowi6 *fl6, int flags)
+{
+ return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+ int flags)
+{
+ return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_multipath_select(const struct net *net, struct fib6_info *f6i,
+ struct flowi6 *fl6, int oif,
+ const struct sk_buff *skb, int strict)
+{
+ return f6i;
+}
+
const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
- .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup,
+ .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup,
+ .fib6_get_table = eafnosupport_fib6_get_table,
+ .fib6_table_lookup = eafnosupport_fib6_table_lookup,
+ .fib6_lookup = eafnosupport_fib6_lookup,
+ .fib6_multipath_select = eafnosupport_fib6_multipath_select,
};
EXPORT_SYMBOL_GPL(ipv6_stub);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 36d622c477b1..c0e8255d50bb 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -887,7 +887,11 @@ static struct pernet_operations inet6_net_ops = {
static const struct ipv6_stub ipv6_stub_impl = {
.ipv6_sock_mc_join = ipv6_sock_mc_join,
.ipv6_sock_mc_drop = ipv6_sock_mc_drop,
- .ipv6_dst_lookup = ip6_dst_lookup,
+ .ipv6_dst_lookup = ip6_dst_lookup,
+ .fib6_get_table = fib6_get_table,
+ .fib6_table_lookup = fib6_table_lookup,
+ .fib6_lookup = fib6_lookup,
+ .fib6_multipath_select = fib6_multipath_select,
.udpv6_encap_enable = udpv6_encap_enable,
.ndisc_send_na = ndisc_send_na,
.nd_tbl = &nd_tbl,
--
2.11.0
^ permalink raw reply related
* [RFC bpf-next 8/9] bpf: Provide helper to do lookups in kernel FIB table
From: David Ahern @ 2018-04-25 18:34 UTC (permalink / raw)
To: netdev, borkmann, ast
Cc: shm, roopa, brouer, toke, john.fastabend, David Ahern
In-Reply-To: <20180425183449.25134-1-dsahern@gmail.com>
Provide a helper for doing a FIB and neighbor lookup in the kernel
tables from an XDP program. The helper provides a fastpath for forwarding
packets. If the packet is a local delivery or for any reason is not a
simple lookup and forward, the packet continues up the stack.
If it is to be forwarded, the forwarding can be done directly if the
neighbor is already known. If the neighbor does not exist, the first
few packets go up the stack for neighbor resolution. Once resolved, the
xdp program provides the fast path.
On successful lookup the nexthop dmac, current device smac and egress
device index are returned.
The API supports IPv4, IPv6 and MPLS protocols, but only IPv4 and IPv6
are implemented in this patch. The API includes layer 4 parameters if
the XDP program chooses to do deep packet inspection to allow compare
against ACLs implemented as FIB rules.
Header rewrite is left to the XDP program.
The lookup takes 2 flags:
- BPF_FIB_LOOKUP_DIRECT to do a lookup that bypasses FIB rules and goes
straight to the table associated with the device (expert setting for
those looking to maximize throughput)
- BPF_FIB_LOOKUP_OUTPUT to do a lookup from the egress perspective.
Default is an ingress lookup.
Initial performance numbers collected by Jesper, forwarded packets/sec:
Full stack XDP FIB lookup XDP Direct lookup
IPv4 1,947,969 7,074,156 7,415,333
IPv6 1,728,000 6,165,504 7,262,720
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/uapi/linux/bpf.h | 68 +++++++++++++-
net/core/filter.c | 233 +++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 300 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e6679393b687..82601c132b9f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -10,6 +10,8 @@
#include <linux/types.h>
#include <linux/bpf_common.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
/* Extended instruction set based on top of classic BPF */
@@ -783,6 +785,17 @@ union bpf_attr {
* @size: size of 'struct bpf_xfrm_state'
* @flags: room for future extensions
* Return: 0 on success or negative error
+ *
+ * int bpf_fib_lookup(ctx, params, plen, flags)
+ * Do a FIB lookup based on given parameters
+ * @ctx: pointer to context of type xdp_md
+ * @params: pointer to bpf_fib_lookup
+ * @plen: size of params argument
+ * @flags: u32 bitmask of BPF_FIB_LOOKUP_* flags
+ * Return: egress device index if packet is to be forwarded,
+ * 0 for local delivery (anything that needs to be handled
+ * by the full stack), or negative on error.
+ * If index is > 0, output data in bpf_fib_lookup is set
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -851,7 +864,9 @@ union bpf_attr {
FN(msg_pull_data), \
FN(bind), \
FN(xdp_adjust_tail), \
- FN(skb_get_xfrm_state),
+ FN(skb_get_xfrm_state), \
+ FN(fib_lookup), \
+
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -1255,4 +1270,55 @@ struct bpf_raw_tracepoint_args {
__u64 args[0];
};
+/* DIRECT: Skip the FIB rules and go to FIB table associated with device
+ * OUTPUT: Do lookup from egress perspective; default is ingress
+ */
+#define BPF_FIB_LOOKUP_DIRECT BIT(0)
+#define BPF_FIB_LOOKUP_OUTPUT BIT(1)
+
+struct bpf_fib_lookup {
+ /* input */
+ __u8 family; /* network family, AF_INET, AF_INET6, AF_MPLS */
+
+ /* set if lookup is to consider L4 data - e.g., FIB rules */
+ __u8 l4_protocol;
+ __be16 sport;
+ __be16 dport;
+
+ /* total length of packet from network header - used for MTU check */
+ __u16 tot_len;
+ __u32 ifindex; /* L3 device index for lookup */
+
+ union {
+ /* inputs to lookup */
+ __u8 tos; /* AF_INET */
+ __be32 flowlabel; /* AF_INET6 */
+
+ /* output: metric of fib result */
+ __u32 rt_metric;
+ };
+
+ union {
+ __be32 mpls_in;
+ __be32 ipv4_src;
+ struct in6_addr ipv6_src;
+ };
+
+ /* input to bpf_fib_lookup, *dst is destination address.
+ * output: bpf_fib_lookup sets to gateway address
+ */
+ union {
+ /* return for MPLS lookups */
+ __be32 mpls_out[4]; /* support up to 4 labels */
+ __be32 ipv4_dst;
+ struct in6_addr ipv6_dst;
+ };
+
+ /* output */
+ __be16 h_vlan_proto;
+ __be16 h_vlan_TCI;
+ __u8 smac[ETH_ALEN];
+ __u8 dmac[ETH_ALEN];
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/net/core/filter.c b/net/core/filter.c
index 8e45c6c7ab08..37602b2fb94a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -59,6 +59,10 @@
#include <net/tcp.h>
#include <net/xfrm.h>
#include <linux/bpf_trace.h>
+#include <linux/inetdevice.h>
+#include <net/ip_fib.h>
+#include <net/flow.h>
+#include <net/arp.h>
/**
* sk_filter_trim_cap - run a packet through a socket filter
@@ -3787,6 +3791,231 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = {
};
#endif
+#if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6)
+static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
+ const struct neighbour *neigh,
+ const struct net_device *dev)
+{
+ memcpy(params->dmac, neigh->ha, ETH_ALEN);
+ memcpy(params->smac, dev->dev_addr, ETH_ALEN);
+ params->h_vlan_TCI = 0;
+ params->h_vlan_proto = 0;
+
+ return dev->ifindex;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_INET)
+static int bpf_ipv4_fib_lookup(struct xdp_buff *ctx,
+ struct bpf_fib_lookup *params, u32 flags)
+{
+ struct net *net = dev_net(ctx->rxq->dev);
+ struct in_device *in_dev;
+ struct neighbour *neigh;
+ struct net_device *dev;
+ struct fib_result res;
+ struct fib_nh *nh;
+ struct flowi4 fl4;
+ int err;
+
+ dev = dev_get_by_index_rcu(net, params->ifindex);
+ if (unlikely(!dev))
+ return -ENODEV;
+
+ /* verify forwarding is enabled on this interface */
+ in_dev = __in_dev_get_rcu(dev);
+ if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
+ return 0;
+
+ if (flags & BPF_FIB_LOOKUP_OUTPUT) {
+ fl4.flowi4_iif = 1;
+ fl4.flowi4_oif = params->ifindex;
+ } else {
+ fl4.flowi4_iif = params->ifindex;
+ fl4.flowi4_oif = 0;
+ }
+ fl4.flowi4_tos = params->tos & IPTOS_RT_MASK;
+ fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
+ fl4.flowi4_flags = 0;
+
+ fl4.flowi4_proto = params->l4_protocol;
+ fl4.daddr = params->ipv4_dst;
+ fl4.saddr = params->ipv4_src;
+ fl4.fl4_sport = params->sport;
+ fl4.fl4_dport = params->dport;
+
+ if (flags & BPF_FIB_LOOKUP_DIRECT) {
+ u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
+ struct fib_table *tb;
+
+ tb = fib_get_table(net, tbid);
+ if (unlikely(!tb))
+ return 0;
+
+ err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
+ } else {
+ fl4.flowi4_mark = 0;
+ fl4.flowi4_secid = 0;
+ fl4.flowi4_tun_key.tun_id = 0;
+ fl4.flowi4_uid = sock_net_uid(net, NULL);
+
+ err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
+ }
+
+ if (err || res.type != RTN_UNICAST)
+ return 0;
+
+ if (res.fi->fib_nhs > 1)
+ fib_select_path(net, &res, &fl4, NULL);
+
+ nh = &res.fi->fib_nh[res.nh_sel];
+
+ /* do not handle lwt encaps right now */
+ if (nh->nh_lwtstate)
+ return 0;
+
+ dev = nh->nh_dev;
+ if (unlikely(!dev))
+ return 0;
+
+ if (nh->nh_gw)
+ params->ipv4_dst = nh->nh_gw;
+
+ params->rt_metric = res.fi->fib_priority;
+
+ /* xdp and cls_bpf programs are run in RCU-bh so
+ * rcu_read_lock_bh is not needed here
+ */
+ neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
+ if (neigh)
+ return bpf_fib_set_fwd_params(params, neigh, dev);
+
+ return 0;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int bpf_ipv6_fib_lookup(struct xdp_buff *ctx,
+ struct bpf_fib_lookup *params, u32 flags)
+{
+ struct net *net = dev_net(ctx->rxq->dev);
+ struct neighbour *neigh;
+ struct net_device *dev;
+ struct fib6_info *f6i;
+ struct flowi6 fl6;
+ int strict = 0;
+ int oif;
+
+ /* link local addresses are never forwarded */
+ if (rt6_need_strict(¶ms->ipv6_dst) ||
+ rt6_need_strict(¶ms->ipv6_src))
+ return 0;
+
+ dev = dev_get_by_index_rcu(net, params->ifindex);
+ if (unlikely(!dev))
+ return -ENODEV;
+
+ if (flags & BPF_FIB_LOOKUP_OUTPUT) {
+ fl6.flowi6_iif = 1;
+ oif = fl6.flowi6_oif = params->ifindex;
+ } else {
+ oif = fl6.flowi6_iif = params->ifindex;
+ fl6.flowi6_oif = 0;
+ strict = RT6_LOOKUP_F_HAS_SADDR;
+ }
+ fl6.flowlabel = params->flowlabel;
+ fl6.flowi6_scope = 0;
+ fl6.flowi6_flags = 0;
+ fl6.mp_hash = 0;
+
+ fl6.flowi6_proto = params->l4_protocol;
+ fl6.daddr = params->ipv6_dst;
+ fl6.saddr = params->ipv6_src;
+ fl6.fl6_sport = params->sport;
+ fl6.fl6_dport = params->dport;
+
+ if (flags & BPF_FIB_LOOKUP_DIRECT) {
+ u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
+ struct fib6_table *tb;
+
+ tb = ipv6_stub->fib6_get_table(net, tbid);
+ if (unlikely(!tb))
+ return 0;
+
+ f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
+ } else {
+ fl6.flowi6_mark = 0;
+ fl6.flowi6_secid = 0;
+ fl6.flowi6_tun_key.tun_id = 0;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
+
+ f6i = ipv6_stub->fib6_lookup(net, oif, &fl6, strict);
+ }
+
+ if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
+ return 0;
+
+ if (unlikely(f6i->fib6_flags & RTF_REJECT ||
+ f6i->fib6_type != RTN_UNICAST))
+ return 0;
+
+ if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
+ f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
+ fl6.flowi6_oif, NULL,
+ strict);
+
+ if (f6i->fib6_nh.nh_lwtstate)
+ return 0;
+
+ if (f6i->fib6_flags & RTF_GATEWAY)
+ params->ipv6_dst = f6i->fib6_nh.nh_gw;
+
+ dev = f6i->fib6_nh.nh_dev;
+ params->rt_metric = f6i->fib6_metric;
+
+ /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
+ * not needed here. Can not use __ipv6_neigh_lookup_noref here
+ * because we need to get nd_tbl via the stub
+ */
+ neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
+ ndisc_hashfn, ¶ms->ipv6_dst, dev);
+ if (neigh)
+ return bpf_fib_set_fwd_params(params, neigh, dev);
+
+ return 0;
+}
+#endif
+
+BPF_CALL_4(bpf_fib_lookup, struct xdp_buff *, ctx,
+ struct bpf_fib_lookup *, params, int, plen, u32, flags)
+{
+ if (plen < sizeof(*params))
+ return -EINVAL;
+
+ switch (params->family) {
+#if IS_ENABLED(CONFIG_INET)
+ case AF_INET:
+ return bpf_ipv4_fib_lookup(ctx, params, flags);
+#endif
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ return bpf_ipv6_fib_lookup(ctx, params, flags);
+#endif
+ }
+ return -ENOTSUPP;
+}
+
+static const struct bpf_func_proto bpf_fib_lookup_proto = {
+ .func = bpf_fib_lookup,
+ .gpl_only = true,
+ .pkt_access = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+};
+
static const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
@@ -3861,6 +4090,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_socket_cookie_proto;
case BPF_FUNC_get_socket_uid:
return &bpf_get_socket_uid_proto;
+ case BPF_FUNC_fib_lookup:
+ return &bpf_fib_lookup_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -3957,6 +4188,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_xdp_redirect_map_proto;
case BPF_FUNC_xdp_adjust_tail:
return &bpf_xdp_adjust_tail_proto;
+ case BPF_FUNC_fib_lookup:
+ return &bpf_fib_lookup_proto;
default:
return bpf_base_func_proto(func_id);
}
--
2.11.0
^ permalink raw reply related
* [RFC bpf-next 9/9] samples/bpf: Add examples of ipv4 and ipv6 forwarding in XDP
From: David Ahern @ 2018-04-25 18:34 UTC (permalink / raw)
To: netdev, borkmann, ast
Cc: shm, roopa, brouer, toke, john.fastabend, David Ahern
In-Reply-To: <20180425183449.25134-1-dsahern@gmail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
---
samples/bpf/Makefile | 4 +
samples/bpf/xdp_fwd_kern.c | 110 ++++++++++++++++++++++++
samples/bpf/xdp_fwd_user.c | 136 ++++++++++++++++++++++++++++++
tools/testing/selftests/bpf/bpf_helpers.h | 3 +
4 files changed, 253 insertions(+)
create mode 100644 samples/bpf/xdp_fwd_kern.c
create mode 100644 samples/bpf/xdp_fwd_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index aa8c392e2e52..c90d2ff74873 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -45,6 +45,7 @@ hostprogs-y += xdp_rxq_info
hostprogs-y += syscall_tp
hostprogs-y += cpustat
hostprogs-y += xdp_adjust_tail
+hostprogs-y += xdp_fwd
# Libbpf dependencies
LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
@@ -97,6 +98,7 @@ xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o
syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
cpustat-objs := bpf_load.o $(LIBBPF) cpustat_user.o
xdp_adjust_tail-objs := bpf_load.o $(LIBBPF) xdp_adjust_tail_user.o
+xdp_fwd-objs := bpf_load.o $(LIBBPF) xdp_fwd_user.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
@@ -151,6 +153,7 @@ always += xdp2skb_meta_kern.o
always += syscall_tp_kern.o
always += cpustat_kern.o
always += xdp_adjust_tail_kern.o
+always += xdp_fwd_kern.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -197,6 +200,7 @@ HOSTLOADLIBES_xdp_rxq_info += -lelf
HOSTLOADLIBES_syscall_tp += -lelf
HOSTLOADLIBES_cpustat += -lelf
HOSTLOADLIBES_xdp_adjust_tail += -lelf
+HOSTLOADLIBES_xdp_fwd += -lelf
# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c
new file mode 100644
index 000000000000..4012c073fc45
--- /dev/null
+++ b/samples/bpf/xdp_fwd_kern.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2017-18 David Ahern <dsahern@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#define KBUILD_MODNAME "foo"
+#include <uapi/linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+
+#include "bpf_helpers.h"
+
+#define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF)
+
+struct bpf_map_def SEC("maps") tx_port = {
+ .type = BPF_MAP_TYPE_DEVMAP,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 64,
+};
+
+static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct bpf_fib_lookup fib_params;
+ struct ethhdr *eth = data;
+ int out_index;
+ u16 h_proto;
+ u64 nh_off;
+
+ nh_off = sizeof(*eth);
+ if (data + nh_off > data_end)
+ return XDP_DROP;
+
+ __builtin_memset(&fib_params, 0, sizeof(fib_params));
+
+ h_proto = eth->h_proto;
+ if (h_proto == htons(ETH_P_IP)) {
+ struct iphdr *iph = data + nh_off;
+
+ if (iph + 1 > data_end)
+ return XDP_DROP;
+
+ fib_params.family = AF_INET;
+ fib_params.tos = iph->tos;
+ fib_params.l4_protocol = iph->protocol;
+ fib_params.sport = 0;
+ fib_params.dport = 0;
+ fib_params.tot_len = ntohs(iph->tot_len);
+ fib_params.ipv4_src = iph->saddr;
+ fib_params.ipv4_dst = iph->daddr;
+ } else if (h_proto == htons(ETH_P_IPV6)) {
+ struct ipv6hdr *iph = data + nh_off;
+
+ if (iph + 1 > data_end)
+ return XDP_DROP;
+
+ fib_params.family = AF_INET6;
+ fib_params.flowlabel = *(__be32 *)iph & IPV6_FLOWINFO_MASK;
+ fib_params.l4_protocol = iph->nexthdr;
+ fib_params.sport = 0;
+ fib_params.dport = 0;
+ fib_params.tot_len = ntohs(iph->payload_len);
+ fib_params.ipv6_src = iph->saddr;
+ fib_params.ipv6_dst = iph->daddr;
+ } else {
+ return XDP_PASS;
+ }
+
+ fib_params.ifindex = ctx->ingress_ifindex;
+
+ out_index = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
+
+ /* verify egress index has xdp support */
+ // TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with
+ // cannot pass map_type 14 into func bpf_map_lookup_elem#1:
+ if (out_index > 0) {
+ memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
+ memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
+ return bpf_redirect_map(&tx_port, out_index, 0);
+ }
+
+ return XDP_PASS;
+}
+
+SEC("xdp_fwd")
+int xdp_fwd_prog(struct xdp_md *ctx)
+{
+ return xdp_fwd_flags(ctx, 0);
+}
+
+SEC("xdp_fwd_direct")
+int xdp_fwd_direct_prog(struct xdp_md *ctx)
+{
+ return xdp_fwd_flags(ctx, BPF_FIB_LOOKUP_DIRECT);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c
new file mode 100644
index 000000000000..9c6606f57126
--- /dev/null
+++ b/samples/bpf/xdp_fwd_user.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2017-18 David Ahern <dsahern@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <linux/limits.h>
+#include <net/if.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <libgen.h>
+
+#include "bpf_load.h"
+#include "bpf_util.h"
+#include "libbpf.h"
+
+
+static int do_attach(int idx, int fd, const char *name)
+{
+ int err;
+
+ err = bpf_set_link_xdp_fd(idx, fd, 0);
+ if (err < 0)
+ printf("ERROR: failed to attach program to %s\n", name);
+
+ return err;
+}
+
+static int do_detach(int idx, const char *name)
+{
+ int err;
+
+ err = bpf_set_link_xdp_fd(idx, -1, 0);
+ if (err < 0)
+ printf("ERROR: failed to detach program from %s\n", name);
+
+ return err;
+}
+
+static void usage(const char *prog)
+{
+ fprintf(stderr,
+ "usage: %s [OPTS] interface-list\n"
+ "\nOPTS:\n"
+ " -d detach program\n"
+ " -D direct table lookups (skip fib rules)\n",
+ prog);
+}
+
+int main(int argc, char **argv)
+{
+ char filename[PATH_MAX];
+ int opt, i, idx, err;
+ int prog_id = 0;
+ int attach = 1;
+ int ret = 0;
+
+ while ((opt = getopt(argc, argv, ":dD")) != -1) {
+ switch (opt) {
+ case 'd':
+ attach = 0;
+ break;
+ case 'D':
+ prog_id = 1;
+ break;
+ default:
+ usage(basename(argv[0]));
+ return 1;
+ }
+ }
+
+ if (optind == argc) {
+ usage(basename(argv[0]));
+ return 1;
+ }
+
+ if (attach) {
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (access(filename, O_RDONLY) < 0) {
+ printf("error accessing file %s: %s\n",
+ filename, strerror(errno));
+ return 1;
+ }
+
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+
+ if (!prog_fd[prog_id]) {
+ printf("load_bpf_file: %s\n", strerror(errno));
+ return 1;
+ }
+ }
+ if (attach) {
+ for (i = 1; i < 64; ++i)
+ bpf_map_update_elem(map_fd[0], &i, &i, 0);
+ }
+
+ for (i = optind; i < argc; ++i) {
+ idx = if_nametoindex(argv[i]);
+ if (!idx)
+ idx = strtoul(argv[i], NULL, 0);
+
+ if (!idx) {
+ fprintf(stderr, "Invalid arg\n");
+ return 1;
+ }
+ if (!attach) {
+ err = do_detach(idx, argv[i]);
+ if (err)
+ ret = err;
+ } else {
+ err = do_attach(idx, prog_fd[prog_id], argv[i]);
+ if (err)
+ ret = err;
+ }
+ }
+
+ return ret;
+}
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 69d7b918e66a..4407766a5950 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -101,6 +101,9 @@ static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state,
int size, int flags) =
(void *) BPF_FUNC_skb_get_xfrm_state;
+static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params,
+ int plen, __u32 flags) =
+ (void *) BPF_FUNC_fib_lookup;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions
--
2.11.0
^ permalink raw reply related
* Re: [PATCH net-next v3] Add Common Applications Kept Enhanced (cake) qdisc
From: Toke Høiland-Jørgensen @ 2018-04-25 18:35 UTC (permalink / raw)
To: Eric Dumazet, netdev; +Cc: cake, Dave Taht
In-Reply-To: <c3412b75-156d-3e2c-0f3f-781f2f8bb042@gmail.com>
Eric Dumazet <eric.dumazet@gmail.com> writes:
> On 04/25/2018 09:17 AM, Toke Høiland-Jørgensen wrote:
>
>> Or am I to interpret that as a hard NAK on having this feature in CAKE
>> (even if we fix the issues you pointed out)?
>
> No strong NACK, as long as the current code is fixed.
>
> Right now, a malicious packet will kill the box or something bad like
> that.
Yeah, that's not good, obviously. I may just pull it out for now and add
it back in a separate patch once we've had time to fix it :)
-Toke
^ permalink raw reply
* Re: [PATCH 02/17] y2038: Remove newstat family from default syscall set
From: Geert Uytterhoeven @ 2018-04-25 18:36 UTC (permalink / raw)
To: Arnd Bergmann
Cc: Linux-Arch, Eric W. Biederman, libc-alpha, y2038 Mailman List,
Linux API, Linux Kernel Mailing List, Dominik Brodowski,
Albert ARIBAUD (3ADEV), Peter Zijlstra, Deepa Dinamani, netdev,
Darren Hart, Thomas Gleixner, Al Viro
In-Reply-To: <20180425160311.2718314-3-arnd@arndb.de>
On Wed, Apr 25, 2018 at 6:02 PM, Arnd Bergmann <arnd@arndb.de> wrote:
> We have four generations of stat() syscalls:
> - the oldstat syscalls that are only used on the older architectures
> - the newstat family that is used on all 64-bit architectures but
> lacked support for large files on 32-bit architectures.
> - the stat64 family that is used mostly on 32-bit architectures to
> replace newstat
> - statx() to replace all of the above, adding 64-bit timestamps among
> other things.
>
> We already compile stat64 only on those architectures that need it,
> but newstat is always built, including on those that don't reference
> it. This adds a new __ARCH_WANT_NEW_STAT symbol along the lines of
> __ARCH_WANT_OLD_STAT and __ARCH_WANT_STAT64 to control compilation of
> newstat. All architectures that need it use an explict define, the
> others now get a little bit smaller, and future architecture (including
> 64-bit targets) won't ever see it.
>
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
For m68k:
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org
In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds
_______________________________________________
Y2038 mailing list
Y2038@lists.linaro.org
https://lists.linaro.org/mailman/listinfo/y2038
^ permalink raw reply
* Re: [PATCH 04/17] asm-generic: Remove unneeded __ARCH_WANT_SYS_LLSEEK macro
From: Geert Uytterhoeven @ 2018-04-25 18:36 UTC (permalink / raw)
To: Arnd Bergmann
Cc: Linux-Arch, Eric W. Biederman, libc-alpha, y2038 Mailman List,
Linux API, Linux Kernel Mailing List, Dominik Brodowski,
Albert ARIBAUD (3ADEV), Peter Zijlstra, Deepa Dinamani, netdev,
Darren Hart, Thomas Gleixner, Al Viro
In-Reply-To: <20180425160311.2718314-5-arnd@arndb.de>
On Wed, Apr 25, 2018 at 6:02 PM, Arnd Bergmann <arnd@arndb.de> wrote:
> The sys_llseek sytem call is needed on all 32-bit architectures and
> none of the 64-bit ones, so we can remove the __ARCH_WANT_SYS_LLSEEK guard
> and simplify the include/asm-generic/unistd.h header further.
>
> Since 32-bit tasks can run either natively or in compat mode on 64-bit
> architectures, we have to check for both !CONFIG_64BIT and CONFIG_COMPAT.
>
> There are a few 64-bit architectures that also reference sys_llseek
> in their 64-bit ABI (e.g. sparc), but I verified that those all
> select CONFIG_COMPAT, so the #if check is still correct here. It's
> a bit odd to include it in the syscall table though, as it's the
> same as sys_lseek() on 64-bit, but with strange calling conventions.
>
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
For m68k:
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org
In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds
_______________________________________________
Y2038 mailing list
Y2038@lists.linaro.org
https://lists.linaro.org/mailman/listinfo/y2038
^ permalink raw reply
* Re: [PATCH net 1/1] net/smc: keep clcsock reference in smc_tcp_listen_work()
From: David Miller @ 2018-04-25 18:38 UTC (permalink / raw)
To: ubraun; +Cc: netdev, linux-s390, schwidefsky, heiko.carstens, raspl, ubraun
In-Reply-To: <20180425104858.48953-1-ubraun@linux.ibm.com>
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Wed, 25 Apr 2018 12:48:58 +0200
> The internal CLC socket should exist till the SMC-socket is released.
> Function tcp_listen_worker() releases the internal CLC socket of a
> listen socket, if an smc_close_active() is called. This function
> is called for the final release(), but it is called for shutdown
> SHUT_RDWR as well. This opens a door for protection faults, if
> socket calls using the internal CLC socket are called for a
> shutdown listen socket.
>
> With the changes of
> commit 3d502067599f ("net/smc: simplify wait when closing listen socket")
> there is no need anymore to release the internal CLC socket in
> function tcp_listen_worker((). It is sufficient to release it in
> smc_release().
>
> Fixes: 127f49705823 ("net/smc: release clcsock from tcp_listen_worker")
> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
> Reported-by: syzbot+9045fc589fcd196ef522@syzkaller.appspotmail.com
> Reported-by: syzbot+28a2c86cf19c81d871fa@syzkaller.appspotmail.com
> Reported-by: syzbot+9605e6cace1b5efd4a0a@syzkaller.appspotmail.com
> Reported-by: syzbot+cf9012c597c8379d535c@syzkaller.appspotmail.com
Applied and queued up for -stable.
^ permalink raw reply
* Re: [PATCH net-next v3] Add Common Applications Kept Enhanced (cake) qdisc
From: David Miller @ 2018-04-25 18:39 UTC (permalink / raw)
To: toke; +Cc: netdev, cake, dave.taht
In-Reply-To: <20180425134249.21300-1-toke@toke.dk>
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Wed, 25 Apr 2018 15:42:48 +0200
> +static void *cake_zalloc(size_t sz)
> +{
> + void *ptr = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN);
> +
> + if (!ptr)
> + ptr = vzalloc(sz);
> + return ptr;
> +}
This is just kvzalloc(sz, GFP_KERNEL | __GFP_NOWARN)?
^ permalink raw reply
* Re: [PATCH 0/3] Introduce LSM-hook for socketpair(2)
From: James Morris @ 2018-04-25 18:44 UTC (permalink / raw)
To: David Herrmann
Cc: linux-kernel, Paul Moore, teg, Stephen Smalley, selinux,
linux-security-module, Eric Paris, Serge E. Hallyn,
David S. Miller, netdev
In-Reply-To: <20180423133015.5455-1-dh.herrmann@gmail.com>
On Mon, 23 Apr 2018, David Herrmann wrote:
> This patch series tries to close this gap and makes both behave the
> same. A new LSM-hook is added which allows LSMs to cache the correct
> peer information on newly created socket-pairs.
Looks okay to me.
Once it's respun with the Smack backend and maybe the hook name change,
I'll merge this unless DaveM wants it to go in via his networking tree.
--
James Morris
<jmorris@namei.org>
^ permalink raw reply
* Re: [PATCH net-next v3] Add Common Applications Kept Enhanced (cake) qdisc
From: Toke Høiland-Jørgensen @ 2018-04-25 18:46 UTC (permalink / raw)
To: David Miller; +Cc: netdev, cake, dave.taht
In-Reply-To: <20180425.143948.235979083753006.davem@davemloft.net>
David Miller <davem@davemloft.net> writes:
> From: Toke Høiland-Jørgensen <toke@toke.dk>
> Date: Wed, 25 Apr 2018 15:42:48 +0200
>
>> +static void *cake_zalloc(size_t sz)
>> +{
>> + void *ptr = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN);
>> +
>> + if (!ptr)
>> + ptr = vzalloc(sz);
>> + return ptr;
>> +}
>
> This is just kvzalloc(sz, GFP_KERNEL | __GFP_NOWARN)?
Ah yes; we actually fixed that before, but guess it got lost this time
around. Will fix :)
-Toke
^ permalink raw reply
* Re: [Cake] [PATCH net-next v3] Add Common Applications Kept Enhanced (cake) qdisc
From: David Miller @ 2018-04-25 18:48 UTC (permalink / raw)
To: toke; +Cc: eric.dumazet, chromatix99, netdev, cake
In-Reply-To: <87lgdb5e4w.fsf@toke.dk>
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Wed, 25 Apr 2018 20:34:23 +0200
> Is it possible to get the sizes of the individual segments
> of a GSO packet? That way we could do the calculation for the whole
> super-packet...
Yes it is.
Otherwise the software GSO fallback wouldn't even be possible.
^ permalink raw reply
* Re: [PATCH 0/3] Introduce LSM-hook for socketpair(2)
From: David Miller @ 2018-04-25 18:48 UTC (permalink / raw)
To: jmorris
Cc: dh.herrmann, linux-kernel, paul, teg, sds, selinux,
linux-security-module, eparis, serge, netdev
In-Reply-To: <alpine.LRH.2.21.1804260443110.11568@namei.org>
From: James Morris <jmorris@namei.org>
Date: Thu, 26 Apr 2018 04:44:38 +1000 (AEST)
> On Mon, 23 Apr 2018, David Herrmann wrote:
>
>> This patch series tries to close this gap and makes both behave the
>> same. A new LSM-hook is added which allows LSMs to cache the correct
>> peer information on newly created socket-pairs.
>
> Looks okay to me.
>
> Once it's respun with the Smack backend and maybe the hook name change,
> I'll merge this unless DaveM wants it to go in via his networking tree.
No, feel free to take it via your tree James.
^ permalink raw reply
* Re: [PATCH 0/3] Introduce LSM-hook for socketpair(2)
From: Paul Moore @ 2018-04-25 18:51 UTC (permalink / raw)
To: James Morris
Cc: David Herrmann, linux-kernel, teg, Stephen Smalley, selinux,
linux-security-module, Eric Paris, Serge E. Hallyn,
David S. Miller, netdev
In-Reply-To: <alpine.LRH.2.21.1804260443110.11568@namei.org>
On Wed, Apr 25, 2018 at 2:44 PM, James Morris <jmorris@namei.org> wrote:
> On Mon, 23 Apr 2018, David Herrmann wrote:
>> This patch series tries to close this gap and makes both behave the
>> same. A new LSM-hook is added which allows LSMs to cache the correct
>> peer information on newly created socket-pairs.
>
> Looks okay to me.
>
> Once it's respun with the Smack backend and maybe the hook name change,
> I'll merge this unless DaveM wants it to go in via his networking tree.
Note my objection to the hook placement in patch 2/3; I think we
should move the hook out of the AF_UNIX layer and up into the socket
layer.
--
paul moore
www.paul-moore.com
^ permalink raw reply
* [PATCH net-next 00/10] udp gso
From: Willem de Bruijn @ 2018-04-25 18:55 UTC (permalink / raw)
To: netdev; +Cc: davem, alexander.duyck, dmichail, Willem de Bruijn
From: Willem de Bruijn <willemb@google.com>
Segmentation offload reduces cycles/byte for large packets by
amortizing the cost of protocol stack traversal.
This patchset implements GSO for UDP. A process can concatenate and
submit multiple datagrams to the same destination in one send call
by setting socket option SOL_UDP/UDP_SEGMENT with the segment size,
or passing an analogous cmsg at send time.
The stack will send the entire large (up to network layer max size)
datagram through the protocol layer. At the GSO layer, it is broken
up in individual segments. All receive the same network layer header
and UDP src and dst port. All but the last segment have the same UDP
header, but the last may differ in length and checksum.
Initial results show a significant reduction in UDP cycles/byte.
See the main patch for more details and benchmark results.
udp
876 MB/s 14873 msg/s 624666 calls/s
11,205,777,429 cycles
udp gso
2139 MB/s 36282 msg/s 36282 calls/s
11,204,374,561 cycles
The patch set is broken down as follows:
- patch 1 is a prerequisite: code rearrangement, noop otherwise
- patch 2 is the core feature
- patch 3,4,6 are refinements
- patch 5 adds the cmsg interface
- patch 7..10 are tests
This idea was presented previously at netconf 2017-2
http://vger.kernel.org/netconf2017_files/rx_hardening_and_udp_gso.pdf
Changes RFC -> v1
- MSG_MORE:
fixed, by allowing checksum offload with corking if gso
- SKB_GSO_UDP_L4:
made independent from SKB_GSO_UDP
and removed skb_is_ufo() wrapper
- NETIF_F_GSO_UDP_L4:
add to netdev_features_string
and to netdev-features.txt
add BUILD_BUG_ON to match SKB_GSO_UDP_L4 value
- UDP_MAX_SEGMENTS:
introduce limit on number of segments per gso skb
to avoid extreme cases like IP_MAX_MTU/IPV4_MIN_MTU
- CHECKSUM_PARTIAL:
test against missing feature after ndo_features_check
if not supported return error, analogous to udp_send_check
- MSG_ZEROCOPY: removed, deferred for now
Willem de Bruijn (11):
udp: expose inet cork to udp
udp: add gso
udp: better wmem accounting on gso
udp: paged allocation with gso
udp: add gso segment cmsg
udp: add gso support to virtual devices
selftests: udp gso
selftests: udp gso with connected sockets
selftests: udp gso with corking
selftests: udp gso benchmark
Documentation/networking/netdev-features.txt | 7 +
include/linux/netdev_features.h | 5 +-
include/linux/netdevice.h | 1 +
include/linux/skbuff.h | 2 +
include/linux/udp.h | 3 +
include/net/inet_sock.h | 1 +
include/net/ip.h | 3 +-
include/net/ipv6.h | 2 +
include/net/udp.h | 5 +
include/uapi/linux/udp.h | 1 +
net/core/ethtool.c | 1 +
net/core/skbuff.c | 2 +
net/ipv4/ip_output.c | 41 +-
net/ipv4/udp.c | 80 ++-
net/ipv4/udp_offload.c | 68 +-
net/ipv6/ip6_offload.c | 6 +-
net/ipv6/ip6_output.c | 45 +-
net/ipv6/udp.c | 31 +-
net/ipv6/udp_offload.c | 19 +-
tools/testing/selftests/net/.gitignore | 3 +
tools/testing/selftests/net/Makefile | 4 +-
tools/testing/selftests/net/udpgso.c | 621 ++++++++++++++++++
tools/testing/selftests/net/udpgso.sh | 29 +
tools/testing/selftests/net/udpgso_bench.sh | 74 +++
tools/testing/selftests/net/udpgso_bench_rx.c | 265 ++++++++
tools/testing/selftests/net/udpgso_bench_tx.c | 420 ++++++++++++
26 files changed, 1688 insertions(+), 51 deletions(-)
create mode 100644 tools/testing/selftests/net/udpgso.c
create mode 100755 tools/testing/selftests/net/udpgso.sh
create mode 100755 tools/testing/selftests/net/udpgso_bench.sh
create mode 100644 tools/testing/selftests/net/udpgso_bench_rx.c
create mode 100644 tools/testing/selftests/net/udpgso_bench_tx.c
--
2.17.0.441.gb46fe60e1d-goog
^ permalink raw reply
* [PATCH net-next 01/10] udp: expose inet cork to udp
From: Willem de Bruijn @ 2018-04-25 18:55 UTC (permalink / raw)
To: netdev; +Cc: davem, alexander.duyck, dmichail, Willem de Bruijn
In-Reply-To: <20180425185601.55511-1-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
UDP segmentation offload needs access to inet_cork in the udp layer.
Pass the struct to ip(6)_make_skb instead of allocating it on the
stack in that function itself.
This patch is a noop otherwise.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
include/net/ip.h | 2 +-
include/net/ipv6.h | 1 +
net/ipv4/ip_output.c | 17 ++++++++---------
net/ipv4/udp.c | 4 +++-
net/ipv6/ip6_output.c | 20 ++++++++++----------
net/ipv6/udp.c | 3 ++-
6 files changed, 25 insertions(+), 22 deletions(-)
diff --git a/include/net/ip.h b/include/net/ip.h
index dc4a2d6e58a5..7ec543a64bbc 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -171,7 +171,7 @@ struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4,
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
struct ipcm_cookie *ipc, struct rtable **rtp,
- unsigned int flags);
+ struct inet_cork *cork, unsigned int flags);
static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
{
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 68b167d98879..0dd722cab037 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -950,6 +950,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
void *from, int length, int transhdrlen,
struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags,
+ struct inet_cork_full *cork,
const struct sockcm_cookie *sockc);
static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 83c73bab2c3d..2883ff1e909c 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1470,9 +1470,8 @@ struct sk_buff *ip_make_skb(struct sock *sk,
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
struct ipcm_cookie *ipc, struct rtable **rtp,
- unsigned int flags)
+ struct inet_cork *cork, unsigned int flags)
{
- struct inet_cork cork;
struct sk_buff_head queue;
int err;
@@ -1481,22 +1480,22 @@ struct sk_buff *ip_make_skb(struct sock *sk,
__skb_queue_head_init(&queue);
- cork.flags = 0;
- cork.addr = 0;
- cork.opt = NULL;
- err = ip_setup_cork(sk, &cork, ipc, rtp);
+ cork->flags = 0;
+ cork->addr = 0;
+ cork->opt = NULL;
+ err = ip_setup_cork(sk, cork, ipc, rtp);
if (err)
return ERR_PTR(err);
- err = __ip_append_data(sk, fl4, &queue, &cork,
+ err = __ip_append_data(sk, fl4, &queue, cork,
¤t->task_frag, getfrag,
from, length, transhdrlen, flags);
if (err) {
- __ip_flush_pending_frames(sk, &queue, &cork);
+ __ip_flush_pending_frames(sk, &queue, cork);
return ERR_PTR(err);
}
- return __ip_make_skb(sk, fl4, &queue, &cork);
+ return __ip_make_skb(sk, fl4, &queue, cork);
}
/*
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 24b5c59b1c53..6b9d8017b319 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1030,9 +1030,11 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
/* Lockless fast path for the non-corking case. */
if (!corkreq) {
+ struct inet_cork cork;
+
skb = ip_make_skb(sk, fl4, getfrag, msg, ulen,
sizeof(struct udphdr), &ipc, &rt,
- msg->msg_flags);
+ &cork, msg->msg_flags);
err = PTR_ERR(skb);
if (!IS_ERR_OR_NULL(skb))
err = udp_send_skb(skb, fl4);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6a477d54f8c7..7fa1db447405 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1755,9 +1755,9 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
void *from, int length, int transhdrlen,
struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags,
+ struct inet_cork_full *cork,
const struct sockcm_cookie *sockc)
{
- struct inet_cork_full cork;
struct inet6_cork v6_cork;
struct sk_buff_head queue;
int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0);
@@ -1768,27 +1768,27 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
__skb_queue_head_init(&queue);
- cork.base.flags = 0;
- cork.base.addr = 0;
- cork.base.opt = NULL;
- cork.base.dst = NULL;
+ cork->base.flags = 0;
+ cork->base.addr = 0;
+ cork->base.opt = NULL;
+ cork->base.dst = NULL;
v6_cork.opt = NULL;
- err = ip6_setup_cork(sk, &cork, &v6_cork, ipc6, rt, fl6);
+ err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6);
if (err) {
- ip6_cork_release(&cork, &v6_cork);
+ ip6_cork_release(cork, &v6_cork);
return ERR_PTR(err);
}
if (ipc6->dontfrag < 0)
ipc6->dontfrag = inet6_sk(sk)->dontfrag;
- err = __ip6_append_data(sk, fl6, &queue, &cork.base, &v6_cork,
+ err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork,
¤t->task_frag, getfrag, from,
length + exthdrlen, transhdrlen + exthdrlen,
flags, ipc6, sockc);
if (err) {
- __ip6_flush_pending_frames(sk, &queue, &cork, &v6_cork);
+ __ip6_flush_pending_frames(sk, &queue, cork, &v6_cork);
return ERR_PTR(err);
}
- return __ip6_make_skb(sk, &queue, &cork, &v6_cork);
+ return __ip6_make_skb(sk, &queue, cork, &v6_cork);
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4ec76a87aeb8..824797f8d1ab 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1324,12 +1324,13 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
/* Lockless fast path for the non-corking case */
if (!corkreq) {
+ struct inet_cork_full cork;
struct sk_buff *skb;
skb = ip6_make_skb(sk, getfrag, msg, ulen,
sizeof(struct udphdr), &ipc6,
&fl6, (struct rt6_info *)dst,
- msg->msg_flags, &sockc);
+ msg->msg_flags, &cork, &sockc);
err = PTR_ERR(skb);
if (!IS_ERR_OR_NULL(skb))
err = udp_v6_send_skb(skb, &fl6);
--
2.17.0.441.gb46fe60e1d-goog
^ permalink raw reply related
* [PATCH net-next 02/10] udp: add gso
From: Willem de Bruijn @ 2018-04-25 18:55 UTC (permalink / raw)
To: netdev; +Cc: davem, alexander.duyck, dmichail, Willem de Bruijn
In-Reply-To: <20180425185601.55511-1-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Implement generic segmentation offload for udp datagrams. Callers can
concatenate and send at once the payload of multiple datagrams with
the same destination.
To set segment size, the caller sets socket option UDP_SEGMENT to the
length of each discrete payload. This value must be smaller than or
equal to the relevant MTU.
A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a
per send call basis.
Total byte length may then exceed MTU. If not an exact multiple of
segment size, the last segment will be shorter.
UDP GSO is not UFO. UFO fragments a single large datagram. GSO splits
a large payload into a number of discrete UDP datagrams.
The implementation adds a GSO type SKB_UDP_GSO_L4 to differentiate it
from UFO (SKB_UDP_GSO). It adds a gso_size field to the udp socket,
ip(v6) cmsg cookie and inet_cork structure to be able to set the value
at setsockopt or cmsg time and to work with both lockless and corked
paths.
IPPROTO_UDPLITE is excluded, as that protocol has no gso handler
registered.
Initial benchmark numbers show UDP GSO about as expensive as TCP GSO.
tcp tso
3197 MB/s 54232 msg/s 54232 calls/s
6,457,754,262 cycles
tcp gso
1765 MB/s 29939 msg/s 29939 calls/s
11,203,021,806 cycles
tcp without tso/gso *
739 MB/s 12548 msg/s 12548 calls/s
11,205,483,630 cycles
udp
876 MB/s 14873 msg/s 624666 calls/s
11,205,777,429 cycles
udp gso
2139 MB/s 36282 msg/s 36282 calls/s
11,204,374,561 cycles
[*] after reverting commit 0a6b2a1dc2a2
("tcp: switch to GSO being always on")
Measured total system cycles ('-a') for one core while pinning both
the network receive path and benchmark process to that core:
perf stat -a -C 12 -e cycles \
./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4
Note the reduction in calls/s with GSO. Bytes per syscall drops
increases from 1470 to 61818.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
include/linux/skbuff.h | 2 ++
include/linux/udp.h | 3 +++
include/net/inet_sock.h | 1 +
include/net/ip.h | 1 +
include/net/ipv6.h | 1 +
include/net/udp.h | 4 ++++
include/uapi/linux/udp.h | 1 +
net/core/skbuff.c | 2 ++
net/ipv4/ip_output.c | 9 ++++---
net/ipv4/udp.c | 33 ++++++++++++++++++++++---
net/ipv4/udp_offload.c | 52 +++++++++++++++++++++++++++++++++++++++-
net/ipv6/ip6_offload.c | 6 +++--
net/ipv6/ip6_output.c | 6 +++--
net/ipv6/udp.c | 23 +++++++++++++++---
net/ipv6/udp_offload.c | 19 ++++++++++++++-
15 files changed, 148 insertions(+), 15 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d274059529eb..a4a5c0c5cba8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -573,6 +573,8 @@ enum {
SKB_GSO_ESP = 1 << 15,
SKB_GSO_UDP = 1 << 16,
+
+ SKB_GSO_UDP_L4 = 1 << 17,
};
#if BITS_PER_LONG > 32
diff --git a/include/linux/udp.h b/include/linux/udp.h
index eaea63bc79bb..ca840345571b 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -55,6 +55,7 @@ struct udp_sock {
* when the socket is uncorked.
*/
__u16 len; /* total length of pending frames */
+ __u16 gso_size;
/*
* Fields specific to UDP-Lite.
*/
@@ -87,6 +88,8 @@ struct udp_sock {
int forward_deficit;
};
+#define UDP_MAX_SEGMENTS (1 << 6UL)
+
static inline struct udp_sock *udp_sk(const struct sock *sk)
{
return (struct udp_sock *)sk;
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 0a671c32d6b9..83d5b3c2ac42 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -147,6 +147,7 @@ struct inet_cork {
__u8 ttl;
__s16 tos;
char priority;
+ __u16 gso_size;
};
struct inet_cork_full {
diff --git a/include/net/ip.h b/include/net/ip.h
index 7ec543a64bbc..bada1f1f871e 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -76,6 +76,7 @@ struct ipcm_cookie {
__u8 ttl;
__s16 tos;
char priority;
+ __u16 gso_size;
};
#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 0dd722cab037..0a872a7c33c8 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -298,6 +298,7 @@ struct ipcm6_cookie {
__s16 tclass;
__s8 dontfrag;
struct ipv6_txoptions *opt;
+ __u16 gso_size;
};
static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
diff --git a/include/net/udp.h b/include/net/udp.h
index 0676b272f6ac..741d888d0fdb 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -174,6 +174,10 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
struct udphdr *uh, udp_lookup_t lookup);
int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);
+struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
+ netdev_features_t features,
+ unsigned int mss, __sum16 check);
+
static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
{
struct udphdr *uh;
diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
index efb7b5991c2f..09d00f8c442b 100644
--- a/include/uapi/linux/udp.h
+++ b/include/uapi/linux/udp.h
@@ -32,6 +32,7 @@ struct udphdr {
#define UDP_ENCAP 100 /* Set the socket to accept encapsulated packets */
#define UDP_NO_CHECK6_TX 101 /* Disable sending checksum for UDP6X */
#define UDP_NO_CHECK6_RX 102 /* Disable accpeting checksum for UDP6 */
+#define UDP_SEGMENT 103 /* Set GSO segmentation size */
/* UDP encapsulation types */
#define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ff49e352deea..c647cfe114e0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4940,6 +4940,8 @@ static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb)
thlen = tcp_hdrlen(skb);
} else if (unlikely(skb_is_gso_sctp(skb))) {
thlen = sizeof(struct sctphdr);
+ } else if (shinfo->gso_type & SKB_GSO_UDP_L4) {
+ thlen = sizeof(struct udphdr);
}
/* UFO sets gso_size to the size of the fragmentation
* payload, i.e. the size of the L4 (UDP) header is already
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 2883ff1e909c..da4abbee10f7 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -882,7 +882,8 @@ static int __ip_append_data(struct sock *sk,
skb = skb_peek_tail(queue);
exthdrlen = !skb ? rt->dst.header_len : 0;
- mtu = cork->fragsize;
+ mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
+
if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
tskey = sk->sk_tskey++;
@@ -906,7 +907,7 @@ static int __ip_append_data(struct sock *sk,
if (transhdrlen &&
length + fragheaderlen <= mtu &&
rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) &&
- !(flags & MSG_MORE) &&
+ (!(flags & MSG_MORE) || cork->gso_size) &&
!exthdrlen)
csummode = CHECKSUM_PARTIAL;
@@ -1135,6 +1136,8 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
*rtp = NULL;
cork->fragsize = ip_sk_use_pmtu(sk) ?
dst_mtu(&rt->dst) : rt->dst.dev->mtu;
+
+ cork->gso_size = sk->sk_type == SOCK_DGRAM ? ipc->gso_size : 0;
cork->dst = &rt->dst;
cork->length = 0;
cork->ttl = ipc->ttl;
@@ -1214,7 +1217,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
return -EOPNOTSUPP;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
- mtu = cork->fragsize;
+ mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 6b9d8017b319..bda022c5480b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -757,7 +757,8 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb,
}
EXPORT_SYMBOL(udp_set_csum);
-static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
+static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
+ struct inet_cork *cork)
{
struct sock *sk = skb->sk;
struct inet_sock *inet = inet_sk(sk);
@@ -777,6 +778,21 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
uh->len = htons(len);
uh->check = 0;
+ if (cork->gso_size) {
+ const int hlen = skb_network_header_len(skb) +
+ sizeof(struct udphdr);
+
+ if (hlen + cork->gso_size > cork->fragsize)
+ return -EINVAL;
+ if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS)
+ return -EINVAL;
+ if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite)
+ return -EIO;
+
+ skb_shinfo(skb)->gso_size = cork->gso_size;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+ }
+
if (is_udplite) /* UDP-Lite */
csum = udplite_csum(skb);
@@ -828,7 +844,7 @@ int udp_push_pending_frames(struct sock *sk)
if (!skb)
goto out;
- err = udp_send_skb(skb, fl4);
+ err = udp_send_skb(skb, fl4, &inet->cork.base);
out:
up->len = 0;
@@ -922,6 +938,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipc.sockc.tsflags = sk->sk_tsflags;
ipc.addr = inet->inet_saddr;
ipc.oif = sk->sk_bound_dev_if;
+ ipc.gso_size = up->gso_size;
if (msg->msg_controllen) {
err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6);
@@ -1037,7 +1054,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
&cork, msg->msg_flags);
err = PTR_ERR(skb);
if (!IS_ERR_OR_NULL(skb))
- err = udp_send_skb(skb, fl4);
+ err = udp_send_skb(skb, fl4, &cork);
goto out;
}
@@ -2367,6 +2384,12 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
up->no_check6_rx = valbool;
break;
+ case UDP_SEGMENT:
+ if (val < 0 || val > USHRT_MAX)
+ return -EINVAL;
+ up->gso_size = val;
+ break;
+
/*
* UDP-Lite's partial checksum coverage (RFC 3828).
*/
@@ -2457,6 +2480,10 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
val = up->no_check6_rx;
break;
+ case UDP_SEGMENT:
+ val = up->gso_size;
+ break;
+
/* The following two cannot be changed on UDP sockets, the return is
* always 0 (which corresponds to the full checksum coverage of UDP). */
case UDPLITE_SEND_CSCOV:
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index ea6e6e7df0ee..a3244768e45f 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -187,6 +187,53 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
}
EXPORT_SYMBOL(skb_udp_tunnel_segment);
+struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
+ netdev_features_t features,
+ unsigned int mss, __sum16 check)
+{
+ struct udphdr *uh = udp_hdr(gso_skb);
+ struct sk_buff *segs;
+ unsigned int hdrlen;
+
+ if (gso_skb->len <= sizeof(*uh) + mss)
+ return ERR_PTR(-EINVAL);
+
+ uh->len = htons(sizeof(*uh) + mss);
+ uh->check = check;
+ skb_pull(gso_skb, sizeof(*uh));
+ hdrlen = gso_skb->data - skb_mac_header(gso_skb);
+
+ segs = skb_segment(gso_skb, features);
+ if (unlikely(IS_ERR_OR_NULL(segs)))
+ return segs;
+
+ /* If last packet is not full, fix up its header */
+ if (segs->prev->len != hdrlen + mss) {
+ unsigned int mss_last = segs->prev->len - hdrlen;
+
+ uh = udp_hdr(segs->prev);
+ uh->len = htons(sizeof(*uh) + mss_last);
+ csum_replace2(&uh->check, htons(mss), htons(mss_last));
+ }
+
+ return segs;
+}
+
+static struct sk_buff *__udp4_gso_segment(struct sk_buff *gso_skb,
+ netdev_features_t features)
+{
+ const struct iphdr *iph = ip_hdr(gso_skb);
+ unsigned int mss = skb_shinfo(gso_skb)->gso_size;
+
+ if (!can_checksum_protocol(features, htons(ETH_P_IP)))
+ return ERR_PTR(-EIO);
+
+ return __udp_gso_segment(gso_skb, features, mss,
+ udp_v4_check(sizeof(struct udphdr) + mss,
+ iph->saddr, iph->daddr, 0));
+}
+EXPORT_SYMBOL_GPL(__udp4_gso_segment);
+
static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
netdev_features_t features)
{
@@ -203,12 +250,15 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
goto out;
}
- if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP))
+ if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4)))
goto out;
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto out;
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+ return __udp4_gso_segment(skb, features);
+
mss = skb_shinfo(skb)->gso_size;
if (unlikely(skb->len <= mss))
goto out;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 4a87f9428ca5..5b3f2f89ef41 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -88,9 +88,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
if (skb->encapsulation &&
skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6))
- udpfrag = proto == IPPROTO_UDP && encap;
+ udpfrag = proto == IPPROTO_UDP && encap &&
+ (skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
else
- udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+ udpfrag = proto == IPPROTO_UDP && !skb->encapsulation &&
+ (skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
ops = rcu_dereference(inet6_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment)) {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7fa1db447405..a1c4a78132d2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1240,6 +1240,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
if (mtu < IPV6_MIN_MTU)
return -EINVAL;
cork->base.fragsize = mtu;
+ cork->base.gso_size = sk->sk_type == SOCK_DGRAM ? ipc6->gso_size : 0;
+
if (dst_allfrag(xfrm_dst_path(&rt->dst)))
cork->base.flags |= IPCORK_ALLFRAG;
cork->base.length = 0;
@@ -1281,7 +1283,7 @@ static int __ip6_append_data(struct sock *sk,
dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
}
- mtu = cork->fragsize;
+ mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
orig_mtu = mtu;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
@@ -1329,7 +1331,7 @@ static int __ip6_append_data(struct sock *sk,
if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
headersize == sizeof(struct ipv6hdr) &&
length <= mtu - headersize &&
- !(flags & MSG_MORE) &&
+ (!(flags & MSG_MORE) || cork->gso_size) &&
rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
csummode = CHECKSUM_PARTIAL;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 824797f8d1ab..86b7dd58d4b4 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1023,7 +1023,8 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
* Sending
*/
-static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6)
+static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
+ struct inet_cork *cork)
{
struct sock *sk = skb->sk;
struct udphdr *uh;
@@ -1042,6 +1043,21 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6)
uh->len = htons(len);
uh->check = 0;
+ if (cork->gso_size) {
+ const int hlen = skb_network_header_len(skb) +
+ sizeof(struct udphdr);
+
+ if (hlen + cork->gso_size > cork->fragsize)
+ return -EINVAL;
+ if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS)
+ return -EINVAL;
+ if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite)
+ return -EIO;
+
+ skb_shinfo(skb)->gso_size = cork->gso_size;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+ }
+
if (is_udplite)
csum = udplite_csum(skb);
else if (udp_sk(sk)->no_check6_tx) { /* UDP csum disabled */
@@ -1093,7 +1109,7 @@ static int udp_v6_push_pending_frames(struct sock *sk)
if (!skb)
goto out;
- err = udp_v6_send_skb(skb, &fl6);
+ err = udp_v6_send_skb(skb, &fl6, &inet_sk(sk)->cork.base);
out:
up->len = 0;
@@ -1127,6 +1143,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipc6.hlimit = -1;
ipc6.tclass = -1;
ipc6.dontfrag = -1;
+ ipc6.gso_size = up->gso_size;
sockc.tsflags = sk->sk_tsflags;
/* destination address check */
@@ -1333,7 +1350,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
msg->msg_flags, &cork, &sockc);
err = PTR_ERR(skb);
if (!IS_ERR_OR_NULL(skb))
- err = udp_v6_send_skb(skb, &fl6);
+ err = udp_v6_send_skb(skb, &fl6, &cork.base);
goto out;
}
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 2a04dc9c781b..f7b85b1e6b3e 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -17,6 +17,20 @@
#include <net/ip6_checksum.h>
#include "ip6_offload.h"
+static struct sk_buff *__udp6_gso_segment(struct sk_buff *gso_skb,
+ netdev_features_t features)
+{
+ const struct ipv6hdr *ip6h = ipv6_hdr(gso_skb);
+ unsigned int mss = skb_shinfo(gso_skb)->gso_size;
+
+ if (!can_checksum_protocol(features, htons(ETH_P_IPV6)))
+ return ERR_PTR(-EIO);
+
+ return __udp_gso_segment(gso_skb, features, mss,
+ udp_v6_check(sizeof(struct udphdr) + mss,
+ &ip6h->saddr, &ip6h->daddr, 0));
+}
+
static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
netdev_features_t features)
{
@@ -42,12 +56,15 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
const struct ipv6hdr *ipv6h;
struct udphdr *uh;
- if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP))
+ if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4)))
goto out;
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto out;
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+ return __udp6_gso_segment(skb, features);
+
/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
* do checksum of UDP packets sent as multiple IP fragments.
*/
--
2.17.0.441.gb46fe60e1d-goog
^ permalink raw reply related
* [PATCH net-next 03/10] udp: better wmem accounting on gso
From: Willem de Bruijn @ 2018-04-25 18:55 UTC (permalink / raw)
To: netdev; +Cc: davem, alexander.duyck, dmichail, Willem de Bruijn
In-Reply-To: <20180425185601.55511-1-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
skb_segment by default transfers allocated wmem from the gso skb
to the tail of the segment list. This underreports real truesize
of the list, especially if the tail might be dropped.
Similar to tcp_gso_segment, update wmem_alloc with the aggregate
list truesize and make each segment responsible for its own
share by setting skb->destructor.
Clear gso_skb->destructor prior to calling skb_segment to skip
the default assignment to tail.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
net/ipv4/udp_offload.c | 20 ++++++++++++++++++--
1 file changed, 18 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index a3244768e45f..acfef71459f8 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -192,7 +192,9 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
unsigned int mss, __sum16 check)
{
struct udphdr *uh = udp_hdr(gso_skb);
- struct sk_buff *segs;
+ struct sock *sk = gso_skb->sk;
+ struct sk_buff *segs, *seg;
+ unsigned int sum_truesize = 0;
unsigned int hdrlen;
if (gso_skb->len <= sizeof(*uh) + mss)
@@ -203,9 +205,23 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
skb_pull(gso_skb, sizeof(*uh));
hdrlen = gso_skb->data - skb_mac_header(gso_skb);
+ /* clear destructor to avoid skb_segment assigning it to tail */
+ WARN_ON_ONCE(gso_skb->destructor != sock_wfree);
+ gso_skb->destructor = NULL;
+
segs = skb_segment(gso_skb, features);
- if (unlikely(IS_ERR_OR_NULL(segs)))
+ if (unlikely(IS_ERR_OR_NULL(segs))) {
+ gso_skb->destructor = sock_wfree;
return segs;
+ }
+
+ for (seg = segs; seg; seg = seg->next) {
+ seg->destructor = sock_wfree;
+ seg->sk = sk;
+ sum_truesize += seg->truesize;
+ }
+
+ refcount_add(sum_truesize - gso_skb->truesize, &sk->sk_wmem_alloc);
/* If last packet is not full, fix up its header */
if (segs->prev->len != hdrlen + mss) {
--
2.17.0.441.gb46fe60e1d-goog
^ permalink raw reply related
* [PATCH net-next 04/10] udp: paged allocation with gso
From: Willem de Bruijn @ 2018-04-25 18:55 UTC (permalink / raw)
To: netdev; +Cc: davem, alexander.duyck, dmichail, Willem de Bruijn
In-Reply-To: <20180425185601.55511-1-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
When sending large datagrams that are later segmented, store data in
page frags to avoid copying from linear in skb_segment.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
net/ipv4/ip_output.c | 15 +++++++++++----
net/ipv6/ip6_output.c | 19 ++++++++++++++-----
2 files changed, 25 insertions(+), 9 deletions(-)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index da4abbee10f7..f2338e40c37d 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -878,11 +878,13 @@ static int __ip_append_data(struct sock *sk,
struct rtable *rt = (struct rtable *)cork->dst;
unsigned int wmem_alloc_delta = 0;
u32 tskey = 0;
+ bool paged;
skb = skb_peek_tail(queue);
exthdrlen = !skb ? rt->dst.header_len : 0;
mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
+ paged = !!cork->gso_size;
if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
@@ -934,6 +936,7 @@ static int __ip_append_data(struct sock *sk,
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
+ unsigned int pagedlen = 0;
struct sk_buff *skb_prev;
alloc_new_skb:
skb_prev = skb;
@@ -954,8 +957,12 @@ static int __ip_append_data(struct sock *sk,
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
- else
+ else if (!paged)
alloclen = fraglen;
+ else {
+ alloclen = min_t(int, fraglen, MAX_HEADER);
+ pagedlen = fraglen - alloclen;
+ }
alloclen += exthdrlen;
@@ -999,7 +1006,7 @@ static int __ip_append_data(struct sock *sk,
/*
* Find where to start putting bytes.
*/
- data = skb_put(skb, fraglen + exthdrlen);
+ data = skb_put(skb, fraglen + exthdrlen - pagedlen);
skb_set_network_header(skb, exthdrlen);
skb->transport_header = (skb->network_header +
fragheaderlen);
@@ -1015,7 +1022,7 @@ static int __ip_append_data(struct sock *sk,
pskb_trim_unique(skb_prev, maxfraglen);
}
- copy = datalen - transhdrlen - fraggap;
+ copy = datalen - transhdrlen - fraggap - pagedlen;
if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
@@ -1023,7 +1030,7 @@ static int __ip_append_data(struct sock *sk,
}
offset += copy;
- length -= datalen - fraggap;
+ length -= copy + transhdrlen;
transhdrlen = 0;
exthdrlen = 0;
csummode = CHECKSUM_NONE;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a1c4a78132d2..dfd8af41824e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1276,6 +1276,7 @@ static int __ip6_append_data(struct sock *sk,
int csummode = CHECKSUM_NONE;
unsigned int maxnonfragsize, headersize;
unsigned int wmem_alloc_delta = 0;
+ bool paged;
skb = skb_peek_tail(queue);
if (!skb) {
@@ -1283,6 +1284,7 @@ static int __ip6_append_data(struct sock *sk,
dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
}
+ paged = !!cork->gso_size;
mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
orig_mtu = mtu;
@@ -1374,6 +1376,7 @@ static int __ip6_append_data(struct sock *sk,
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
+ unsigned int pagedlen = 0;
alloc_new_skb:
/* There's no room in the current skb */
if (skb)
@@ -1396,11 +1399,17 @@ static int __ip6_append_data(struct sock *sk,
if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
+ fraglen = datalen + fragheaderlen;
+
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
- else
- alloclen = datalen + fragheaderlen;
+ else if (!paged)
+ alloclen = fraglen;
+ else {
+ alloclen = min_t(int, fraglen, MAX_HEADER);
+ pagedlen = fraglen - alloclen;
+ }
alloclen += dst_exthdrlen;
@@ -1422,7 +1431,7 @@ static int __ip6_append_data(struct sock *sk,
*/
alloclen += sizeof(struct frag_hdr);
- copy = datalen - transhdrlen - fraggap;
+ copy = datalen - transhdrlen - fraggap - pagedlen;
if (copy < 0) {
err = -EINVAL;
goto error;
@@ -1461,7 +1470,7 @@ static int __ip6_append_data(struct sock *sk,
/*
* Find where to start putting bytes
*/
- data = skb_put(skb, fraglen);
+ data = skb_put(skb, fraglen - pagedlen);
skb_set_network_header(skb, exthdrlen);
data += fragheaderlen;
skb->transport_header = (skb->network_header +
@@ -1484,7 +1493,7 @@ static int __ip6_append_data(struct sock *sk,
}
offset += copy;
- length -= datalen - fraggap;
+ length -= copy + transhdrlen;
transhdrlen = 0;
exthdrlen = 0;
dst_exthdrlen = 0;
--
2.17.0.441.gb46fe60e1d-goog
^ permalink raw reply related
* [PATCH net-next 05/10] udp: add gso segment cmsg
From: Willem de Bruijn @ 2018-04-25 18:55 UTC (permalink / raw)
To: netdev; +Cc: davem, alexander.duyck, dmichail, Willem de Bruijn
In-Reply-To: <20180425185601.55511-1-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Allow specifying segment size in the send call.
The new control message performs the same function as socket option
UDP_SEGMENT while avoiding the extra system call.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
include/net/udp.h | 1 +
net/ipv4/udp.c | 43 +++++++++++++++++++++++++++++++++++++++++--
net/ipv6/udp.c | 5 ++++-
3 files changed, 46 insertions(+), 3 deletions(-)
diff --git a/include/net/udp.h b/include/net/udp.h
index 741d888d0fdb..05990746810e 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -273,6 +273,7 @@ int udp_abort(struct sock *sk, int err);
int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
int udp_push_pending_frames(struct sock *sk);
void udp_flush_pending_frames(struct sock *sk);
+int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size);
void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
int udp_rcv(struct sk_buff *skb);
int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index bda022c5480b..350bdafc462b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -853,6 +853,42 @@ int udp_push_pending_frames(struct sock *sk)
}
EXPORT_SYMBOL(udp_push_pending_frames);
+static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size)
+{
+ switch (cmsg->cmsg_type) {
+ case UDP_SEGMENT:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u16)))
+ return -EINVAL;
+ *gso_size = *(__u16 *)CMSG_DATA(cmsg);
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
+int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size)
+{
+ struct cmsghdr *cmsg;
+ bool need_ip = false;
+ int err;
+
+ for_each_cmsghdr(cmsg, msg) {
+ if (!CMSG_OK(msg, cmsg))
+ return -EINVAL;
+
+ if (cmsg->cmsg_level != SOL_UDP) {
+ need_ip = true;
+ continue;
+ }
+
+ err = __udp_cmsg_send(cmsg, gso_size);
+ if (err)
+ return err;
+ }
+
+ return need_ip;
+}
+
int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct inet_sock *inet = inet_sk(sk);
@@ -941,8 +977,11 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipc.gso_size = up->gso_size;
if (msg->msg_controllen) {
- err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6);
- if (unlikely(err)) {
+ err = udp_cmsg_send(sk, msg, &ipc.gso_size);
+ if (err > 0)
+ err = ip_cmsg_send(sk, msg, &ipc,
+ sk->sk_family == AF_INET6);
+ if (unlikely(err < 0)) {
kfree(ipc.opt);
return err;
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 86b7dd58d4b4..6acfdd3e442b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1276,7 +1276,10 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
opt->tot_len = sizeof(*opt);
ipc6.opt = opt;
- err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6, &sockc);
+ err = udp_cmsg_send(sk, msg, &ipc6.gso_size);
+ if (err > 0)
+ err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6,
+ &ipc6, &sockc);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
--
2.17.0.441.gb46fe60e1d-goog
^ permalink raw reply related
* [PATCH net-next 06/10] udp: add gso support to virtual devices
From: Willem de Bruijn @ 2018-04-25 18:55 UTC (permalink / raw)
To: netdev; +Cc: davem, alexander.duyck, dmichail, Willem de Bruijn
In-Reply-To: <20180425185601.55511-1-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Virtual devices such as tunnels and bonding can handle large packets.
Only segment packets when reaching a physical or loopback device.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
Documentation/networking/netdev-features.txt | 7 +++++++
include/linux/netdev_features.h | 5 ++++-
include/linux/netdevice.h | 1 +
net/core/ethtool.c | 1 +
4 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/Documentation/networking/netdev-features.txt b/Documentation/networking/netdev-features.txt
index c77f9d57eb91..c4a54c162547 100644
--- a/Documentation/networking/netdev-features.txt
+++ b/Documentation/networking/netdev-features.txt
@@ -113,6 +113,13 @@ whatever headers there might be.
NETIF_F_TSO_ECN means that hardware can properly split packets with CWR bit
set, be it TCPv4 (when NETIF_F_TSO is enabled) or TCPv6 (NETIF_F_TSO6).
+ * Transmit UDP segmentation offload
+
+NETIF_F_GSO_UDP_GSO_L4 accepts a single UDP header with a payload that exceeds
+gso_size. On segmentation, it segments the payload on gso_size boundaries and
+replicates the network and UDP headers (fixing up the last one if less than
+gso_size).
+
* Transmit DMA from high memory
On platforms where this is relevant, NETIF_F_HIGHDMA signals that
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 35b79f47a13d..fe2f3b30960e 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -55,8 +55,9 @@ enum {
NETIF_F_GSO_SCTP_BIT, /* ... SCTP fragmentation */
NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */
NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */
+ NETIF_F_GSO_UDP_L4_BIT, /* ... UDP payload GSO (not UFO) */
/**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */
- NETIF_F_GSO_UDP_BIT,
+ NETIF_F_GSO_UDP_L4_BIT,
NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */
NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */
@@ -147,6 +148,7 @@ enum {
#define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM)
#define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT)
#define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD)
+#define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4)
#define for_each_netdev_feature(mask_addr, bit) \
for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT)
@@ -216,6 +218,7 @@ enum {
NETIF_F_GSO_GRE_CSUM | \
NETIF_F_GSO_IPXIP4 | \
NETIF_F_GSO_IPXIP6 | \
+ NETIF_F_GSO_UDP_L4 | \
NETIF_F_GSO_UDP_TUNNEL | \
NETIF_F_GSO_UDP_TUNNEL_CSUM)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 14e0777ffcfb..366c32891158 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4186,6 +4186,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
+ BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT));
return (features & feature) == feature;
}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 03416e6dd5d7..4650fd6d678c 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -92,6 +92,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial",
[NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation",
[NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation",
+ [NETIF_F_GSO_UDP_L4_BIT] = "tx-udp-segmentation",
[NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc",
[NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp",
--
2.17.0.441.gb46fe60e1d-goog
^ permalink raw reply related
* [PATCH net-next 07/10] selftests: udp gso
From: Willem de Bruijn @ 2018-04-25 18:55 UTC (permalink / raw)
To: netdev; +Cc: davem, alexander.duyck, dmichail, Willem de Bruijn
In-Reply-To: <20180425185601.55511-1-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Validate udp gso, including edge cases (such as min/max gso sizes).
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
tools/testing/selftests/net/.gitignore | 1 +
tools/testing/selftests/net/Makefile | 3 +-
tools/testing/selftests/net/udpgso.c | 486 +++++++++++++++++++++++++
tools/testing/selftests/net/udpgso.sh | 16 +
4 files changed, 505 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/net/udpgso.c
create mode 100755 tools/testing/selftests/net/udpgso.sh
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 5559f6add046..67a26240407c 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -8,3 +8,4 @@ reuseport_bpf_numa
reuseport_dualstack
reuseaddr_conflict
tcp_mmap
+udpgso
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index c3761c35f542..db3303348315 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,12 +5,13 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g
CFLAGS += -I../../../../usr/include/
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
-TEST_PROGS += fib_tests.sh fib-onlink-tests.sh in_netns.sh pmtu.sh
+TEST_PROGS += fib_tests.sh fib-onlink-tests.sh in_netns.sh pmtu.sh udpgso.sh
TEST_GEN_FILES = socket
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
TEST_GEN_FILES += tcp_mmap
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
+TEST_GEN_PROGS += udpgso
include ../lib.mk
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
new file mode 100644
index 000000000000..68a230dfee73
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso.c
@@ -0,0 +1,486 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <stddef.h>
+#include <arpa/inet.h>
+#include <error.h>
+#include <errno.h>
+#include <net/if.h>
+#include <linux/in.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <netinet/if_ether.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#ifndef ETH_MAX_MTU
+#define ETH_MAX_MTU 0xFFFFU
+#endif
+
+#ifndef UDP_SEGMENT
+#define UDP_SEGMENT 103
+#endif
+
+#define CONST_MTU_TEST 1500
+
+#define CONST_HDRLEN_V4 (sizeof(struct iphdr) + sizeof(struct udphdr))
+#define CONST_HDRLEN_V6 (sizeof(struct ip6_hdr) + sizeof(struct udphdr))
+
+#define CONST_MSS_V4 (CONST_MTU_TEST - CONST_HDRLEN_V4)
+#define CONST_MSS_V6 (CONST_MTU_TEST - CONST_HDRLEN_V6)
+
+#define CONST_MAX_SEGS_V4 (ETH_MAX_MTU / CONST_MSS_V4)
+#define CONST_MAX_SEGS_V6 (ETH_MAX_MTU / CONST_MSS_V6)
+
+static bool cfg_do_ipv4;
+static bool cfg_do_ipv6;
+static bool cfg_do_connectionless;
+static bool cfg_do_setsockopt;
+static int cfg_specific_test_id = -1;
+
+static const char cfg_ifname[] = "lo";
+static unsigned short cfg_port = 9000;
+
+static char buf[ETH_MAX_MTU];
+
+struct testcase {
+ int tlen; /* send() buffer size, may exceed mss */
+ bool tfail; /* send() call is expected to fail */
+ int gso_len; /* mss after applying gso */
+ int r_num_mss; /* recv(): number of calls of full mss */
+ int r_len_last; /* recv(): size of last non-mss dgram, if any */
+};
+
+const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT;
+const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) };
+
+struct testcase testcases_v4[] = {
+ {
+ /* no GSO: send a single byte */
+ .tlen = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* no GSO: send a single MSS */
+ .tlen = CONST_MSS_V4,
+ .r_num_mss = 1,
+ },
+ {
+ /* no GSO: send a single MSS + 1B: fail */
+ .tlen = CONST_MSS_V4 + 1,
+ .tfail = true,
+ },
+ {
+ /* send a single MSS: will fail with GSO, because the segment
+ * logic in udp4_ufo_fragment demands a gso skb to be > MTU
+ */
+ .tlen = CONST_MSS_V4,
+ .gso_len = CONST_MSS_V4,
+ .tfail = true,
+ .r_num_mss = 1,
+ },
+ {
+ /* send a single MSS + 1B */
+ .tlen = CONST_MSS_V4 + 1,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* send exactly 2 MSS */
+ .tlen = CONST_MSS_V4 * 2,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = 2,
+ },
+ {
+ /* send 2 MSS + 1B */
+ .tlen = (CONST_MSS_V4 * 2) + 1,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = 2,
+ .r_len_last = 1,
+ },
+ {
+ /* send MAX segs */
+ .tlen = (ETH_MAX_MTU / CONST_MSS_V4) * CONST_MSS_V4,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = (ETH_MAX_MTU / CONST_MSS_V4),
+ },
+
+ {
+ /* send MAX bytes */
+ .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = CONST_MAX_SEGS_V4,
+ .r_len_last = ETH_MAX_MTU - CONST_HDRLEN_V4 -
+ (CONST_MAX_SEGS_V4 * CONST_MSS_V4),
+ },
+ {
+ /* send MAX + 1: fail */
+ .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4 + 1,
+ .gso_len = CONST_MSS_V4,
+ .tfail = true,
+ },
+ {
+ /* EOL */
+ }
+};
+
+#ifndef IP6_MAX_MTU
+#define IP6_MAX_MTU (ETH_MAX_MTU + sizeof(struct ip6_hdr))
+#endif
+
+struct testcase testcases_v6[] = {
+ {
+ /* no GSO: send a single byte */
+ .tlen = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* no GSO: send a single MSS */
+ .tlen = CONST_MSS_V6,
+ .r_num_mss = 1,
+ },
+ {
+ /* no GSO: send a single MSS + 1B: fail */
+ .tlen = CONST_MSS_V6 + 1,
+ .tfail = true,
+ },
+ {
+ /* send a single MSS: will fail with GSO, because the segment
+ * logic in udp4_ufo_fragment demands a gso skb to be > MTU
+ */
+ .tlen = CONST_MSS_V6,
+ .gso_len = CONST_MSS_V6,
+ .tfail = true,
+ .r_num_mss = 1,
+ },
+ {
+ /* send a single MSS + 1B */
+ .tlen = CONST_MSS_V6 + 1,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* send exactly 2 MSS */
+ .tlen = CONST_MSS_V6 * 2,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = 2,
+ },
+ {
+ /* send 2 MSS + 1B */
+ .tlen = (CONST_MSS_V6 * 2) + 1,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = 2,
+ .r_len_last = 1,
+ },
+ {
+ /* send MAX segs */
+ .tlen = (IP6_MAX_MTU / CONST_MSS_V6) * CONST_MSS_V6,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = (IP6_MAX_MTU / CONST_MSS_V6),
+ },
+
+ {
+ /* send MAX bytes */
+ .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = CONST_MAX_SEGS_V6,
+ .r_len_last = IP6_MAX_MTU - CONST_HDRLEN_V6 -
+ (CONST_MAX_SEGS_V6 * CONST_MSS_V6),
+ },
+ {
+ /* send MAX + 1: fail */
+ .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6 + 1,
+ .gso_len = CONST_MSS_V6,
+ .tfail = true,
+ },
+ {
+ /* EOL */
+ }
+};
+
+static unsigned int get_device_mtu(int fd, const char *ifname)
+{
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+
+ strcpy(ifr.ifr_name, ifname);
+
+ if (ioctl(fd, SIOCGIFMTU, &ifr))
+ error(1, errno, "ioctl get mtu");
+
+ return ifr.ifr_mtu;
+}
+
+static void __set_device_mtu(int fd, const char *ifname, unsigned int mtu)
+{
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+
+ ifr.ifr_mtu = mtu;
+ strcpy(ifr.ifr_name, ifname);
+
+ if (ioctl(fd, SIOCSIFMTU, &ifr))
+ error(1, errno, "ioctl set mtu");
+}
+
+static void set_device_mtu(int fd, int mtu)
+{
+ int val;
+
+ val = get_device_mtu(fd, cfg_ifname);
+ fprintf(stderr, "device mtu (orig): %u\n", val);
+
+ __set_device_mtu(fd, cfg_ifname, mtu);
+ val = get_device_mtu(fd, cfg_ifname);
+ if (val != mtu)
+ error(1, 0, "unable to set device mtu to %u\n", val);
+
+ fprintf(stderr, "device mtu (test): %u\n", val);
+}
+
+static void set_pmtu_discover(int fd, bool is_ipv4)
+{
+ int level, name, val;
+
+ if (is_ipv4) {
+ level = SOL_IP;
+ name = IP_MTU_DISCOVER;
+ val = IP_PMTUDISC_DO;
+ } else {
+ level = SOL_IPV6;
+ name = IPV6_MTU_DISCOVER;
+ val = IPV6_PMTUDISC_DO;
+ }
+
+ if (setsockopt(fd, level, name, &val, sizeof(val)))
+ error(1, errno, "setsockopt path mtu");
+}
+
+static bool send_one(int fd, int len, int gso_len,
+ struct sockaddr *addr, socklen_t alen)
+{
+ char control[CMSG_SPACE(sizeof(uint16_t))] = {0};
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ struct cmsghdr *cm;
+ int ret;
+
+ iov.iov_base = buf;
+ iov.iov_len = len;
+
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+
+ msg.msg_name = addr;
+ msg.msg_namelen = alen;
+
+ if (gso_len && !cfg_do_setsockopt) {
+ msg.msg_control = control;
+ msg.msg_controllen = sizeof(control);
+
+ cm = CMSG_FIRSTHDR(&msg);
+ cm->cmsg_level = SOL_UDP;
+ cm->cmsg_type = UDP_SEGMENT;
+ cm->cmsg_len = CMSG_LEN(sizeof(uint16_t));
+ *((uint16_t *) CMSG_DATA(cm)) = gso_len;
+ }
+
+ ret = sendmsg(fd, &msg, 0);
+ if (ret == -1 && (errno == EMSGSIZE || errno == ENOMEM))
+ return false;
+ if (ret == -1)
+ error(1, errno, "sendmsg");
+ if (ret != len)
+ error(1, 0, "sendto: %d != %u", ret, len);
+
+ return true;
+}
+
+static int recv_one(int fd, int flags)
+{
+ int ret;
+
+ ret = recv(fd, buf, sizeof(buf), flags);
+ if (ret == -1 && errno == EAGAIN && (flags & MSG_DONTWAIT))
+ return 0;
+ if (ret == -1)
+ error(1, errno, "recv");
+
+ return ret;
+}
+
+static void run_one(struct testcase *test, int fdt, int fdr,
+ struct sockaddr *addr, socklen_t alen)
+{
+ int i, ret, val, mss;
+ bool sent;
+
+ fprintf(stderr, "ipv%d tx:%d gso:%d %s\n",
+ addr->sa_family == AF_INET ? 4 : 6,
+ test->tlen, test->gso_len,
+ test->tfail ? "(fail)" : "");
+
+ val = test->gso_len;
+ if (cfg_do_setsockopt) {
+ if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val)))
+ error(1, errno, "setsockopt udp segment");
+ }
+
+ sent = send_one(fdt, test->tlen, test->gso_len, addr, alen);
+ if (sent && test->tfail)
+ error(1, 0, "send succeeded while expecting failure");
+ if (!sent && !test->tfail)
+ error(1, 0, "send failed while expecting success");
+ if (!sent)
+ return;
+
+ mss = addr->sa_family == AF_INET ? CONST_MSS_V4 : CONST_MSS_V6;
+
+ /* Recv all full MSS datagrams */
+ for (i = 0; i < test->r_num_mss; i++) {
+ ret = recv_one(fdr, 0);
+ if (ret != mss)
+ error(1, 0, "recv.%d: %d != %d", i, ret, mss);
+ }
+
+ /* Recv the non-full last datagram, if tlen was not a multiple of mss */
+ if (test->r_len_last) {
+ ret = recv_one(fdr, 0);
+ if (ret != test->r_len_last)
+ error(1, 0, "recv.%d: %d != %d (last)",
+ i, ret, test->r_len_last);
+ }
+
+ /* Verify received all data */
+ ret = recv_one(fdr, MSG_DONTWAIT);
+ if (ret)
+ error(1, 0, "recv: unexpected datagram");
+}
+
+static void run_all(int fdt, int fdr, struct sockaddr *addr, socklen_t alen)
+{
+ struct testcase *tests, *test;
+
+ tests = addr->sa_family == AF_INET ? testcases_v4 : testcases_v6;
+
+ for (test = tests; test->tlen; test++) {
+ /* if a specific test is given, then skip all others */
+ if (cfg_specific_test_id == -1 ||
+ cfg_specific_test_id == test - tests)
+ run_one(test, fdt, fdr, addr, alen);
+ }
+}
+
+static void run_test(struct sockaddr *addr, socklen_t alen)
+{
+ struct timeval tv = { .tv_usec = 100 * 1000 };
+ int fdr, fdt;
+
+ fdr = socket(addr->sa_family, SOCK_DGRAM, 0);
+ if (fdr == -1)
+ error(1, errno, "socket r");
+
+ if (bind(fdr, addr, alen))
+ error(1, errno, "bind");
+
+ /* Have tests fail quickly instead of hang */
+ if (setsockopt(fdr, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+ error(1, errno, "setsockopt rcv timeout");
+
+ fdt = socket(addr->sa_family, SOCK_DGRAM, 0);
+ if (fdt == -1)
+ error(1, errno, "socket t");
+
+ /* Do not fragment these datagrams: only succeed if GSO works */
+ set_pmtu_discover(fdt, addr->sa_family == AF_INET);
+
+ if (cfg_do_connectionless) {
+ set_device_mtu(fdt, CONST_MTU_TEST);
+ run_all(fdt, fdr, addr, alen);
+ }
+
+ if (close(fdt))
+ error(1, errno, "close t");
+ if (close(fdr))
+ error(1, errno, "close r");
+}
+
+static void run_test_v4(void)
+{
+ struct sockaddr_in addr = {0};
+
+ addr.sin_family = AF_INET;
+ addr.sin_port = htons(cfg_port);
+ addr.sin_addr = addr4;
+
+ run_test((void *)&addr, sizeof(addr));
+}
+
+static void run_test_v6(void)
+{
+ struct sockaddr_in6 addr = {0};
+
+ addr.sin6_family = AF_INET6;
+ addr.sin6_port = htons(cfg_port);
+ addr.sin6_addr = addr6;
+
+ run_test((void *)&addr, sizeof(addr));
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "46Cst:")) != -1) {
+ switch (c) {
+ case '4':
+ cfg_do_ipv4 = true;
+ break;
+ case '6':
+ cfg_do_ipv6 = true;
+ break;
+ case 'C':
+ cfg_do_connectionless = true;
+ break;
+ case 's':
+ cfg_do_setsockopt = true;
+ break;
+ case 't':
+ cfg_specific_test_id = strtoul(optarg, NULL, 0);
+ break;
+ default:
+ error(1, 0, "%s: parse error", argv[0]);
+ }
+ }
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+
+ if (cfg_do_ipv4)
+ run_test_v4();
+ if (cfg_do_ipv6)
+ run_test_v6();
+
+ fprintf(stderr, "OK\n");
+ return 0;
+}
+
diff --git a/tools/testing/selftests/net/udpgso.sh b/tools/testing/selftests/net/udpgso.sh
new file mode 100755
index 000000000000..7977b97e060c
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso.sh
@@ -0,0 +1,16 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgso regression tests
+
+echo "ipv4 cmsg"
+./in_netns.sh ./udpgso -4 -C
+
+echo "ipv4 setsockopt"
+./in_netns.sh ./udpgso -4 -C -s
+
+echo "ipv6 cmsg"
+./in_netns.sh ./udpgso -6 -C
+
+echo "ipv6 setsockopt"
+./in_netns.sh ./udpgso -6 -C -s
--
2.17.0.441.gb46fe60e1d-goog
^ permalink raw reply related
* [PATCH net-next 08/10] selftests: udp gso with connected sockets
From: Willem de Bruijn @ 2018-04-25 18:55 UTC (permalink / raw)
To: netdev; +Cc: davem, alexander.duyck, dmichail, Willem de Bruijn
In-Reply-To: <20180425185601.55511-1-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Connected sockets use path mtu instead of device mtu.
Test this path by inserting a route mtu that is lower than the device
mtu. Verify that the path mtu for the connection matches this lower
number, then run the same test as in the connectionless case.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
tools/testing/selftests/net/udpgso.c | 117 +++++++++++++++++++++++++-
tools/testing/selftests/net/udpgso.sh | 7 ++
2 files changed, 122 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index 68a230dfee73..a47dca025346 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -47,6 +47,7 @@
static bool cfg_do_ipv4;
static bool cfg_do_ipv6;
+static bool cfg_do_connected;
static bool cfg_do_connectionless;
static bool cfg_do_setsockopt;
static int cfg_specific_test_id = -1;
@@ -273,6 +274,101 @@ static void set_pmtu_discover(int fd, bool is_ipv4)
error(1, errno, "setsockopt path mtu");
}
+static unsigned int get_path_mtu(int fd, bool is_ipv4)
+{
+ socklen_t vallen;
+ unsigned int mtu;
+ int ret;
+
+ vallen = sizeof(mtu);
+ if (is_ipv4)
+ ret = getsockopt(fd, SOL_IP, IP_MTU, &mtu, &vallen);
+ else
+ ret = getsockopt(fd, SOL_IPV6, IPV6_MTU, &mtu, &vallen);
+
+ if (ret)
+ error(1, errno, "getsockopt mtu");
+
+
+ fprintf(stderr, "path mtu (read): %u\n", mtu);
+ return mtu;
+}
+
+/* very wordy version of system("ip route add dev lo mtu 1500 127.0.0.3/32") */
+static void set_route_mtu(int mtu, bool is_ipv4)
+{
+ struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+ struct nlmsghdr *nh;
+ struct rtattr *rta;
+ struct rtmsg *rt;
+ char data[NLMSG_ALIGN(sizeof(*nh)) +
+ NLMSG_ALIGN(sizeof(*rt)) +
+ NLMSG_ALIGN(RTA_LENGTH(sizeof(addr6))) +
+ NLMSG_ALIGN(RTA_LENGTH(sizeof(int))) +
+ NLMSG_ALIGN(RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)))];
+ int fd, ret, alen, off = 0;
+
+ alen = is_ipv4 ? sizeof(addr4) : sizeof(addr6);
+
+ fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+ if (fd == -1)
+ error(1, errno, "socket netlink");
+
+ memset(data, 0, sizeof(data));
+
+ nh = (void *)data;
+ nh->nlmsg_type = RTM_NEWROUTE;
+ nh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE;
+ off += NLMSG_ALIGN(sizeof(*nh));
+
+ rt = (void *)(data + off);
+ rt->rtm_family = is_ipv4 ? AF_INET : AF_INET6;
+ rt->rtm_table = RT_TABLE_MAIN;
+ rt->rtm_dst_len = alen << 3;
+ rt->rtm_protocol = RTPROT_BOOT;
+ rt->rtm_scope = RT_SCOPE_UNIVERSE;
+ rt->rtm_type = RTN_UNICAST;
+ off += NLMSG_ALIGN(sizeof(*rt));
+
+ rta = (void *)(data + off);
+ rta->rta_type = RTA_DST;
+ rta->rta_len = RTA_LENGTH(alen);
+ if (is_ipv4)
+ memcpy(RTA_DATA(rta), &addr4, alen);
+ else
+ memcpy(RTA_DATA(rta), &addr6, alen);
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ rta = (void *)(data + off);
+ rta->rta_type = RTA_OIF;
+ rta->rta_len = RTA_LENGTH(sizeof(int));
+ *((int *)(RTA_DATA(rta))) = 1; //if_nametoindex("lo");
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ /* MTU is a subtype in a metrics type */
+ rta = (void *)(data + off);
+ rta->rta_type = RTA_METRICS;
+ rta->rta_len = RTA_LENGTH(0) + RTA_LENGTH(sizeof(int));
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ /* now fill MTU subtype. Note that it fits within above rta_len */
+ rta = (void *)(((char *) rta) + RTA_LENGTH(0));
+ rta->rta_type = RTAX_MTU;
+ rta->rta_len = RTA_LENGTH(sizeof(int));
+ *((int *)(RTA_DATA(rta))) = mtu;
+
+ nh->nlmsg_len = off;
+
+ ret = sendto(fd, data, off, 0, (void *)&nladdr, sizeof(nladdr));
+ if (ret != off)
+ error(1, errno, "send netlink: %uB != %uB\n", ret, off);
+
+ if (close(fd))
+ error(1, errno, "close netlink");
+
+ fprintf(stderr, "route mtu (test): %u\n", mtu);
+}
+
static bool send_one(int fd, int len, int gso_len,
struct sockaddr *addr, socklen_t alen)
{
@@ -391,7 +487,7 @@ static void run_all(int fdt, int fdr, struct sockaddr *addr, socklen_t alen)
static void run_test(struct sockaddr *addr, socklen_t alen)
{
struct timeval tv = { .tv_usec = 100 * 1000 };
- int fdr, fdt;
+ int fdr, fdt, val;
fdr = socket(addr->sa_family, SOCK_DGRAM, 0);
if (fdr == -1)
@@ -416,6 +512,20 @@ static void run_test(struct sockaddr *addr, socklen_t alen)
run_all(fdt, fdr, addr, alen);
}
+ if (cfg_do_connected) {
+ set_device_mtu(fdt, CONST_MTU_TEST + 100);
+ set_route_mtu(CONST_MTU_TEST, addr->sa_family == AF_INET);
+
+ if (connect(fdt, addr, alen))
+ error(1, errno, "connect");
+
+ val = get_path_mtu(fdt, addr->sa_family == AF_INET);
+ if (val != CONST_MTU_TEST)
+ error(1, 0, "bad path mtu %u\n", val);
+
+ run_all(fdt, fdr, addr, 0 /* use connected addr */);
+ }
+
if (close(fdt))
error(1, errno, "close t");
if (close(fdr))
@@ -448,7 +558,7 @@ static void parse_opts(int argc, char **argv)
{
int c;
- while ((c = getopt(argc, argv, "46Cst:")) != -1) {
+ while ((c = getopt(argc, argv, "46cCst:")) != -1) {
switch (c) {
case '4':
cfg_do_ipv4 = true;
@@ -456,6 +566,9 @@ static void parse_opts(int argc, char **argv)
case '6':
cfg_do_ipv6 = true;
break;
+ case 'c':
+ cfg_do_connected = true;
+ break;
case 'C':
cfg_do_connectionless = true;
break;
diff --git a/tools/testing/selftests/net/udpgso.sh b/tools/testing/selftests/net/udpgso.sh
index 7977b97e060c..7cdf0e7c1dde 100755
--- a/tools/testing/selftests/net/udpgso.sh
+++ b/tools/testing/selftests/net/udpgso.sh
@@ -14,3 +14,10 @@ echo "ipv6 cmsg"
echo "ipv6 setsockopt"
./in_netns.sh ./udpgso -6 -C -s
+
+echo "ipv4 connected"
+./in_netns.sh ./udpgso -4 -c
+
+# blocked on 2nd loopback address
+# echo "ipv6 connected"
+# ./in_netns.sh ./udpgso -6 -c
--
2.17.0.441.gb46fe60e1d-goog
^ permalink raw reply related
* [PATCH net-next 09/10] selftests: udp gso with corking
From: Willem de Bruijn @ 2018-04-25 18:56 UTC (permalink / raw)
To: netdev; +Cc: davem, alexander.duyck, dmichail, Willem de Bruijn
In-Reply-To: <20180425185601.55511-1-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Corked sockets take a different path to construct a udp datagram than
the lockless fast path. Test this alternate path.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
tools/testing/selftests/net/udpgso.c | 42 ++++++++++++++++++++-------
tools/testing/selftests/net/udpgso.sh | 6 ++++
2 files changed, 38 insertions(+), 10 deletions(-)
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index a47dca025346..6b1998b9f7df 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -49,6 +49,7 @@ static bool cfg_do_ipv4;
static bool cfg_do_ipv6;
static bool cfg_do_connected;
static bool cfg_do_connectionless;
+static bool cfg_do_msgmore;
static bool cfg_do_setsockopt;
static int cfg_specific_test_id = -1;
@@ -369,6 +370,23 @@ static void set_route_mtu(int mtu, bool is_ipv4)
fprintf(stderr, "route mtu (test): %u\n", mtu);
}
+static bool __send_one(int fd, struct msghdr *msg, int flags)
+{
+ int ret;
+
+ ret = sendmsg(fd, msg, flags);
+ if (ret == -1 && (errno == EMSGSIZE || errno == ENOMEM))
+ return false;
+ if (ret == -1)
+ error(1, errno, "sendmsg");
+ if (ret != msg->msg_iov->iov_len)
+ error(1, 0, "sendto: %d != %lu", ret, msg->msg_iov->iov_len);
+ if (msg->msg_flags)
+ error(1, 0, "sendmsg: return flags 0x%x\n", msg->msg_flags);
+
+ return true;
+}
+
static bool send_one(int fd, int len, int gso_len,
struct sockaddr *addr, socklen_t alen)
{
@@ -376,7 +394,6 @@ static bool send_one(int fd, int len, int gso_len,
struct msghdr msg = {0};
struct iovec iov = {0};
struct cmsghdr *cm;
- int ret;
iov.iov_base = buf;
iov.iov_len = len;
@@ -398,15 +415,17 @@ static bool send_one(int fd, int len, int gso_len,
*((uint16_t *) CMSG_DATA(cm)) = gso_len;
}
- ret = sendmsg(fd, &msg, 0);
- if (ret == -1 && (errno == EMSGSIZE || errno == ENOMEM))
- return false;
- if (ret == -1)
- error(1, errno, "sendmsg");
- if (ret != len)
- error(1, 0, "sendto: %d != %u", ret, len);
+ /* If MSG_MORE, send 1 byte followed by remainder */
+ if (cfg_do_msgmore && len > 1) {
+ iov.iov_len = 1;
+ if (!__send_one(fd, &msg, MSG_MORE))
+ error(1, 0, "send 1B failed");
- return true;
+ iov.iov_base++;
+ iov.iov_len = len - 1;
+ }
+
+ return __send_one(fd, &msg, 0);
}
static int recv_one(int fd, int flags)
@@ -558,7 +577,7 @@ static void parse_opts(int argc, char **argv)
{
int c;
- while ((c = getopt(argc, argv, "46cCst:")) != -1) {
+ while ((c = getopt(argc, argv, "46cCmst:")) != -1) {
switch (c) {
case '4':
cfg_do_ipv4 = true;
@@ -572,6 +591,9 @@ static void parse_opts(int argc, char **argv)
case 'C':
cfg_do_connectionless = true;
break;
+ case 'm':
+ cfg_do_msgmore = true;
+ break;
case 's':
cfg_do_setsockopt = true;
break;
diff --git a/tools/testing/selftests/net/udpgso.sh b/tools/testing/selftests/net/udpgso.sh
index 7cdf0e7c1dde..fec24f584fe9 100755
--- a/tools/testing/selftests/net/udpgso.sh
+++ b/tools/testing/selftests/net/udpgso.sh
@@ -21,3 +21,9 @@ echo "ipv4 connected"
# blocked on 2nd loopback address
# echo "ipv6 connected"
# ./in_netns.sh ./udpgso -6 -c
+
+echo "ipv4 msg_more"
+./in_netns.sh ./udpgso -4 -C -m
+
+echo "ipv6 msg_more"
+./in_netns.sh ./udpgso -6 -C -m
--
2.17.0.441.gb46fe60e1d-goog
^ permalink raw reply related
* [PATCH net-next 10/10] selftests: udp gso benchmark
From: Willem de Bruijn @ 2018-04-25 18:56 UTC (permalink / raw)
To: netdev; +Cc: davem, alexander.duyck, dmichail, Willem de Bruijn
In-Reply-To: <20180425185601.55511-1-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
Send udp data between a source and sink, optionally with udp gso.
The two processes are expected to be run on separate hosts.
A script is included that runs them together over loopback in a
single namespace for functionality testing.
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
tools/testing/selftests/net/.gitignore | 2 +
tools/testing/selftests/net/Makefile | 3 +-
tools/testing/selftests/net/udpgso_bench.sh | 74 +++
tools/testing/selftests/net/udpgso_bench_rx.c | 265 +++++++++++
tools/testing/selftests/net/udpgso_bench_tx.c | 420 ++++++++++++++++++
5 files changed, 763 insertions(+), 1 deletion(-)
create mode 100755 tools/testing/selftests/net/udpgso_bench.sh
create mode 100644 tools/testing/selftests/net/udpgso_bench_rx.c
create mode 100644 tools/testing/selftests/net/udpgso_bench_tx.c
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 67a26240407c..f0e6c35a93ae 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -9,3 +9,5 @@ reuseport_dualstack
reuseaddr_conflict
tcp_mmap
udpgso
+udpgso_bench_rx
+udpgso_bench_tx
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index db3303348315..df9102ec7b7a 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -6,12 +6,13 @@ CFLAGS += -I../../../../usr/include/
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
TEST_PROGS += fib_tests.sh fib-onlink-tests.sh in_netns.sh pmtu.sh udpgso.sh
+TEST_PROGS += udpgso_bench.sh
TEST_GEN_FILES = socket
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
TEST_GEN_FILES += tcp_mmap
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
-TEST_GEN_PROGS += udpgso
+TEST_GEN_PROGS += udpgso udpgso_bench_tx udpgso_bench_rx
include ../lib.mk
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
new file mode 100755
index 000000000000..792fa4d0285e
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -0,0 +1,74 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgso benchmarks
+
+wake_children() {
+ local -r jobs="$(jobs -p)"
+
+ if [[ "${jobs}" != "" ]]; then
+ kill -1 ${jobs} 2>/dev/null
+ fi
+}
+trap wake_children EXIT
+
+run_one() {
+ local -r args=$@
+
+ ./udpgso_bench_rx &
+ ./udpgso_bench_rx -t &
+
+ ./udpgso_bench_tx ${args}
+}
+
+run_in_netns() {
+ local -r args=$@
+
+ ./in_netns.sh $0 __subprocess ${args}
+}
+
+run_udp() {
+ local -r args=$@
+
+ echo "udp"
+ run_in_netns ${args}
+
+ echo "udp gso"
+ run_in_netns ${args} -S
+
+ echo "udp gso zerocopy"
+ run_in_netns ${args} -S -z
+}
+
+run_tcp() {
+ local -r args=$@
+
+ echo "tcp"
+ run_in_netns ${args} -t
+
+ echo "tcp zerocopy"
+ run_in_netns ${args} -t -z
+}
+
+run_all() {
+ local -r core_args="-l 4"
+ local -r ipv4_args="${core_args} -4 -D 127.0.0.1"
+ local -r ipv6_args="${core_args} -6 -D ::1"
+
+ echo "ipv4"
+ run_tcp "${ipv4_args}"
+ run_udp "${ipv4_args}"
+
+ echo "ipv6"
+ run_tcp "${ipv4_args}"
+ run_udp "${ipv6_args}"
+}
+
+if [[ $# -eq 0 ]]; then
+ run_all
+elif [[ $1 == "__subprocess" ]]; then
+ shift
+ run_one $@
+else
+ run_in_netns $@
+fi
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
new file mode 100644
index 000000000000..727cf67a3f75
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <error.h>
+#include <errno.h>
+#include <limits.h>
+#include <linux/errqueue.h>
+#include <linux/if_packet.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+static int cfg_port = 8000;
+static bool cfg_tcp;
+static bool cfg_verify;
+
+static bool interrupted;
+static unsigned long packets, bytes;
+
+static void sigint_handler(int signum)
+{
+ if (signum == SIGINT)
+ interrupted = true;
+}
+
+static unsigned long gettimeofday_ms(void)
+{
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+ return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static void do_poll(int fd)
+{
+ struct pollfd pfd;
+ int ret;
+
+ pfd.events = POLLIN;
+ pfd.revents = 0;
+ pfd.fd = fd;
+
+ do {
+ ret = poll(&pfd, 1, 10);
+ if (ret == -1)
+ error(1, errno, "poll");
+ if (ret == 0)
+ continue;
+ if (pfd.revents != POLLIN)
+ error(1, errno, "poll: 0x%x expected 0x%x\n",
+ pfd.revents, POLLIN);
+ } while (!ret && !interrupted);
+}
+
+static int do_socket(bool do_tcp)
+{
+ struct sockaddr_in6 addr = {0};
+ int fd, val;
+
+ fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket");
+
+ val = 1 << 21;
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val)))
+ error(1, errno, "setsockopt rcvbuf");
+ val = 1;
+ if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val)))
+ error(1, errno, "setsockopt reuseport");
+
+ addr.sin6_family = PF_INET6;
+ addr.sin6_port = htons(cfg_port);
+ addr.sin6_addr = in6addr_any;
+ if (bind(fd, (void *) &addr, sizeof(addr)))
+ error(1, errno, "bind");
+
+ if (do_tcp) {
+ int accept_fd = fd;
+
+ if (listen(accept_fd, 1))
+ error(1, errno, "listen");
+
+ do_poll(accept_fd);
+
+ fd = accept(accept_fd, NULL, NULL);
+ if (fd == -1)
+ error(1, errno, "accept");
+ if (close(accept_fd))
+ error(1, errno, "close accept fd");
+ }
+
+ return fd;
+}
+
+/* Flush all outstanding bytes for the tcp receive queue */
+static void do_flush_tcp(int fd)
+{
+ int ret;
+
+ while (true) {
+ /* MSG_TRUNC flushes up to len bytes */
+ ret = recv(fd, NULL, 1 << 21, MSG_TRUNC | MSG_DONTWAIT);
+ if (ret == -1 && errno == EAGAIN)
+ return;
+ if (ret == -1)
+ error(1, errno, "flush");
+ if (ret == 0) {
+ /* client detached */
+ exit(0);
+ }
+
+ packets++;
+ bytes += ret;
+ }
+
+}
+
+static char sanitized_char(char val)
+{
+ return (val >= 'a' && val <= 'z') ? val : '.';
+}
+
+static void do_verify_udp(const char *data, int len)
+{
+ char cur = data[0];
+ int i;
+
+ /* verify contents */
+ if (cur < 'a' || cur > 'z')
+ error(1, 0, "data initial byte out of range");
+
+ for (i = 1; i < len; i++) {
+ if (cur == 'z')
+ cur = 'a';
+ else
+ cur++;
+
+ if (data[i] != cur)
+ error(1, 0, "data[%d]: len %d, %c(%hhu) != %c(%hhu)\n",
+ i, len,
+ sanitized_char(data[i]), data[i],
+ sanitized_char(cur), cur);
+ }
+}
+
+/* Flush all outstanding datagrams. Verify first few bytes of each. */
+static void do_flush_udp(int fd)
+{
+ static char rbuf[ETH_DATA_LEN];
+ int ret, len, budget = 256;
+
+ len = cfg_verify ? sizeof(rbuf) : 0;
+ while (budget--) {
+ /* MSG_TRUNC will make return value full datagram length */
+ ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+ if (ret == -1 && errno == EAGAIN)
+ return;
+ if (ret == -1)
+ error(1, errno, "recv");
+ if (len) {
+ if (ret == 0)
+ error(1, errno, "recv: 0 byte datagram\n");
+
+ do_verify_udp(rbuf, ret);
+ }
+
+ packets++;
+ bytes += ret;
+ }
+}
+
+static void usage(const char *filepath)
+{
+ error(1, 0, "Usage: %s [-tv] [-p port]", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "ptv")) != -1) {
+ switch (c) {
+ case 'p':
+ cfg_port = htons(strtoul(optarg, NULL, 0));
+ break;
+ case 't':
+ cfg_tcp = true;
+ break;
+ case 'v':
+ cfg_verify = true;
+ break;
+ }
+ }
+
+ if (optind != argc)
+ usage(argv[0]);
+
+ if (cfg_tcp && cfg_verify)
+ error(1, 0, "TODO: implement verify mode for tcp");
+}
+
+static void do_recv(void)
+{
+ unsigned long tnow, treport;
+ int fd;
+
+ fd = do_socket(cfg_tcp);
+
+ treport = gettimeofday_ms() + 1000;
+ do {
+ do_poll(fd);
+
+ if (cfg_tcp)
+ do_flush_tcp(fd);
+ else
+ do_flush_udp(fd);
+
+ tnow = gettimeofday_ms();
+ if (tnow > treport) {
+ if (packets)
+ fprintf(stderr,
+ "%s rx: %6lu MB/s %8lu calls/s\n",
+ cfg_tcp ? "tcp" : "udp",
+ bytes >> 20, packets);
+ bytes = packets = 0;
+ treport = tnow + 1000;
+ }
+
+ } while (!interrupted);
+
+ if (close(fd))
+ error(1, errno, "close");
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+
+ signal(SIGINT, sigint_handler);
+
+ do_recv();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
new file mode 100644
index 000000000000..e821564053cf
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -0,0 +1,420 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <netinet/if_ether.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#ifndef ETH_MAX_MTU
+#define ETH_MAX_MTU 0xFFFFU
+#endif
+
+#ifndef UDP_SEGMENT
+#define UDP_SEGMENT 103
+#endif
+
+#ifndef SO_ZEROCOPY
+#define SO_ZEROCOPY 60
+#endif
+
+#ifndef MSG_ZEROCOPY
+#define MSG_ZEROCOPY 0x4000000
+#endif
+
+#define NUM_PKT 100
+
+static bool cfg_cache_trash;
+static int cfg_cpu = -1;
+static int cfg_connected = true;
+static int cfg_family = PF_UNSPEC;
+static uint16_t cfg_mss;
+static int cfg_payload_len = (1472 * 42);
+static int cfg_port = 8000;
+static int cfg_runtime_ms = -1;
+static bool cfg_segment;
+static bool cfg_sendmmsg;
+static bool cfg_tcp;
+static bool cfg_zerocopy;
+
+static socklen_t cfg_alen;
+static struct sockaddr_storage cfg_dst_addr;
+
+static bool interrupted;
+static char buf[NUM_PKT][ETH_MAX_MTU];
+
+static void sigint_handler(int signum)
+{
+ if (signum == SIGINT)
+ interrupted = true;
+}
+
+static unsigned long gettimeofday_ms(void)
+{
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+ return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static int set_cpu(int cpu)
+{
+ cpu_set_t mask;
+
+ CPU_ZERO(&mask);
+ CPU_SET(cpu, &mask);
+ if (sched_setaffinity(0, sizeof(mask), &mask))
+ error(1, 0, "setaffinity %d", cpu);
+
+ return 0;
+}
+
+static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr)
+{
+ struct sockaddr_in6 *addr6 = (void *) sockaddr;
+ struct sockaddr_in *addr4 = (void *) sockaddr;
+
+ switch (domain) {
+ case PF_INET:
+ addr4->sin_family = AF_INET;
+ addr4->sin_port = htons(cfg_port);
+ if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+ error(1, 0, "ipv4 parse error: %s", str_addr);
+ break;
+ case PF_INET6:
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = htons(cfg_port);
+ if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+ error(1, 0, "ipv6 parse error: %s", str_addr);
+ break;
+ default:
+ error(1, 0, "illegal domain");
+ }
+}
+
+static void flush_zerocopy(int fd)
+{
+ struct msghdr msg = {0}; /* flush */
+ int ret;
+
+ while (1) {
+ ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+ if (ret == -1 && errno == EAGAIN)
+ break;
+ if (ret == -1)
+ error(1, errno, "errqueue");
+ if (msg.msg_flags != (MSG_ERRQUEUE | MSG_CTRUNC))
+ error(1, 0, "errqueue: flags 0x%x\n", msg.msg_flags);
+ msg.msg_flags = 0;
+ }
+}
+
+static int send_tcp(int fd, char *data)
+{
+ int ret, done = 0, count = 0;
+
+ while (done < cfg_payload_len) {
+ ret = send(fd, data + done, cfg_payload_len - done,
+ cfg_zerocopy ? MSG_ZEROCOPY : 0);
+ if (ret == -1)
+ error(1, errno, "write");
+
+ done += ret;
+ count++;
+ }
+
+ return count;
+}
+
+static int send_udp(int fd, char *data)
+{
+ int ret, total_len, len, count = 0;
+
+ total_len = cfg_payload_len;
+
+ while (total_len) {
+ len = total_len < cfg_mss ? total_len : cfg_mss;
+
+ ret = sendto(fd, data, len, cfg_zerocopy ? MSG_ZEROCOPY : 0,
+ cfg_connected ? NULL : (void *)&cfg_dst_addr,
+ cfg_connected ? 0 : cfg_alen);
+ if (ret == -1)
+ error(1, errno, "write");
+ if (ret != len)
+ error(1, errno, "write: %uB != %uB\n", ret, len);
+
+ total_len -= len;
+ count++;
+ }
+
+ return count;
+}
+
+static int send_udp_sendmmsg(int fd, char *data)
+{
+ const int max_nr_msg = ETH_MAX_MTU / ETH_DATA_LEN;
+ struct mmsghdr mmsgs[max_nr_msg];
+ struct iovec iov[max_nr_msg];
+ unsigned int off = 0, left;
+ int i = 0, ret;
+
+ memset(mmsgs, 0, sizeof(mmsgs));
+
+ left = cfg_payload_len;
+ while (left) {
+ if (i == max_nr_msg)
+ error(1, 0, "sendmmsg: exceeds max_nr_msg");
+
+ iov[i].iov_base = data + off;
+ iov[i].iov_len = cfg_mss < left ? cfg_mss : left;
+
+ mmsgs[i].msg_hdr.msg_iov = iov + i;
+ mmsgs[i].msg_hdr.msg_iovlen = 1;
+
+ off += iov[i].iov_len;
+ left -= iov[i].iov_len;
+ i++;
+ }
+
+ ret = sendmmsg(fd, mmsgs, i, cfg_zerocopy ? MSG_ZEROCOPY : 0);
+ if (ret == -1)
+ error(1, errno, "sendmmsg");
+
+ return ret;
+}
+
+static void send_udp_segment_cmsg(struct cmsghdr *cm)
+{
+ uint16_t *valp;
+
+ cm->cmsg_level = SOL_UDP;
+ cm->cmsg_type = UDP_SEGMENT;
+ cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss));
+ valp = (void *)CMSG_DATA(cm);
+ *valp = cfg_mss;
+}
+
+static int send_udp_segment(int fd, char *data)
+{
+ char control[CMSG_SPACE(sizeof(cfg_mss))] = {0};
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ int ret;
+
+ iov.iov_base = data;
+ iov.iov_len = cfg_payload_len;
+
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+
+ msg.msg_control = control;
+ msg.msg_controllen = sizeof(control);
+ send_udp_segment_cmsg(CMSG_FIRSTHDR(&msg));
+
+ msg.msg_name = (void *)&cfg_dst_addr;
+ msg.msg_namelen = cfg_alen;
+
+ ret = sendmsg(fd, &msg, cfg_zerocopy ? MSG_ZEROCOPY : 0);
+ if (ret == -1)
+ error(1, errno, "sendmsg");
+ if (ret != iov.iov_len)
+ error(1, 0, "sendmsg: %u != %lu\n", ret, iov.iov_len);
+
+ return 1;
+}
+
+static void usage(const char *filepath)
+{
+ error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]",
+ filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int max_len, hdrlen;
+ int c;
+
+ while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) {
+ switch (c) {
+ case '4':
+ if (cfg_family != PF_UNSPEC)
+ error(1, 0, "Pass one of -4 or -6");
+ cfg_family = PF_INET;
+ cfg_alen = sizeof(struct sockaddr_in);
+ break;
+ case '6':
+ if (cfg_family != PF_UNSPEC)
+ error(1, 0, "Pass one of -4 or -6");
+ cfg_family = PF_INET6;
+ cfg_alen = sizeof(struct sockaddr_in6);
+ break;
+ case 'c':
+ cfg_cache_trash = true;
+ break;
+ case 'C':
+ cfg_cpu = strtol(optarg, NULL, 0);
+ break;
+ case 'D':
+ setup_sockaddr(cfg_family, optarg, &cfg_dst_addr);
+ break;
+ case 'l':
+ cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000;
+ break;
+ case 'm':
+ cfg_sendmmsg = true;
+ break;
+ case 'p':
+ cfg_port = strtoul(optarg, NULL, 0);
+ break;
+ case 's':
+ cfg_payload_len = strtoul(optarg, NULL, 0);
+ break;
+ case 'S':
+ cfg_segment = true;
+ break;
+ case 't':
+ cfg_tcp = true;
+ break;
+ case 'u':
+ cfg_connected = false;
+ break;
+ case 'z':
+ cfg_zerocopy = true;
+ break;
+ }
+ }
+
+ if (optind != argc)
+ usage(argv[0]);
+
+ if (cfg_family == PF_UNSPEC)
+ error(1, 0, "must pass one of -4 or -6");
+ if (cfg_tcp && !cfg_connected)
+ error(1, 0, "connectionless tcp makes no sense");
+ if (cfg_segment && cfg_sendmmsg)
+ error(1, 0, "cannot combine segment offload and sendmmsg");
+
+ if (cfg_family == PF_INET)
+ hdrlen = sizeof(struct iphdr) + sizeof(struct udphdr);
+ else
+ hdrlen = sizeof(struct ip6_hdr) + sizeof(struct udphdr);
+
+ cfg_mss = ETH_DATA_LEN - hdrlen;
+ max_len = ETH_MAX_MTU - hdrlen;
+
+ if (cfg_payload_len > max_len)
+ error(1, 0, "payload length %u exceeds max %u",
+ cfg_payload_len, max_len);
+}
+
+static void set_pmtu_discover(int fd, bool is_ipv4)
+{
+ int level, name, val;
+
+ if (is_ipv4) {
+ level = SOL_IP;
+ name = IP_MTU_DISCOVER;
+ val = IP_PMTUDISC_DO;
+ } else {
+ level = SOL_IPV6;
+ name = IPV6_MTU_DISCOVER;
+ val = IPV6_PMTUDISC_DO;
+ }
+
+ if (setsockopt(fd, level, name, &val, sizeof(val)))
+ error(1, errno, "setsockopt path mtu");
+}
+
+int main(int argc, char **argv)
+{
+ unsigned long num_msgs, num_sends;
+ unsigned long tnow, treport, tstop;
+ int fd, i, val;
+
+ parse_opts(argc, argv);
+
+ if (cfg_cpu > 0)
+ set_cpu(cfg_cpu);
+
+ for (i = 0; i < sizeof(buf[0]); i++)
+ buf[0][i] = 'a' + (i % 26);
+ for (i = 1; i < NUM_PKT; i++)
+ memcpy(buf[i], buf[0], sizeof(buf[0]));
+
+ signal(SIGINT, sigint_handler);
+
+ fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket");
+
+ if (cfg_zerocopy) {
+ val = 1;
+ if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val)))
+ error(1, errno, "setsockopt zerocopy");
+ }
+
+ if (cfg_connected &&
+ connect(fd, (void *)&cfg_dst_addr, cfg_alen))
+ error(1, errno, "connect");
+
+ if (cfg_segment)
+ set_pmtu_discover(fd, cfg_family == PF_INET);
+
+ num_msgs = num_sends = 0;
+ tnow = gettimeofday_ms();
+ tstop = tnow + cfg_runtime_ms;
+ treport = tnow + 1000;
+
+ i = 0;
+ do {
+ if (cfg_tcp)
+ num_sends += send_tcp(fd, buf[i]);
+ else if (cfg_segment)
+ num_sends += send_udp_segment(fd, buf[i]);
+ else if (cfg_sendmmsg)
+ num_sends += send_udp_sendmmsg(fd, buf[i]);
+ else
+ num_sends += send_udp(fd, buf[i]);
+ num_msgs++;
+
+ if (cfg_zerocopy && ((num_msgs & 0xF) == 0))
+ flush_zerocopy(fd);
+
+ tnow = gettimeofday_ms();
+ if (tnow > treport) {
+ fprintf(stderr,
+ "%s tx: %6lu MB/s %8lu calls/s %6lu msg/s\n",
+ cfg_tcp ? "tcp" : "udp",
+ (num_msgs * cfg_payload_len) >> 20,
+ num_sends, num_msgs);
+ num_msgs = num_sends = 0;
+ treport = tnow + 1000;
+ }
+
+ /* cold cache when writing buffer */
+ if (cfg_cache_trash)
+ i = ++i < NUM_PKT ? i : 0;
+
+ } while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop));
+
+ if (close(fd))
+ error(1, errno, "close");
+
+ return 0;
+}
--
2.17.0.441.gb46fe60e1d-goog
^ 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