* [RFC bpf-next v1 1/4] netfilter: nf_tables: add flowtable map for xdp offload
2024-05-10 14:01 [RFC bpf-next v1 0/4] netfilter: Add the capability to offload flowtable in XDP layer Lorenzo Bianconi
@ 2024-05-10 14:01 ` Lorenzo Bianconi
2024-05-10 14:01 ` [RFC bpf-next v1 2/4] netfilter: add bpf_xdp_flow_offload_lookup kfunc Lorenzo Bianconi
` (2 subsequent siblings)
3 siblings, 0 replies; 6+ messages in thread
From: Lorenzo Bianconi @ 2024-05-10 14:01 UTC (permalink / raw)
To: bpf
Cc: pablo, kadlec, davem, edumazet, kuba, pabeni, netfilter-devel,
netdev, ast, daniel, andrii, lorenzo.bianconi, toke, fw, hawk,
horms, donhunte
From: Florian Westphal <fw@strlen.de>
This adds a small internal mapping table so that a new bpf (xdp) kfunc
can perform lookups in a flowtable.
As-is, xdp program has access to the device pointer, but no way to do a
lookup in a flowtable -- there is no way to obtain the needed struct
without questionable stunts.
This allows to obtain an nf_flowtable pointer given a net_device
structure.
In order to keep backward compatibility, the infrastructure allows the
user to add a given device to multiple flowtables, but it will always
return the first added mapping performing the lookup since it assumes
the right configuration is 1:1 mapping between flowtables and net_devices.
Signed-off-by: Florian Westphal <fw@strlen.de>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
include/net/netfilter/nf_flow_table.h | 2 +
net/netfilter/nf_flow_table_offload.c | 161 +++++++++++++++++++++++++-
2 files changed, 161 insertions(+), 2 deletions(-)
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 9abb7ee40d72f..0bbe6ea8e0651 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -305,6 +305,8 @@ struct flow_ports {
__be16 source, dest;
};
+struct nf_flowtable *nf_flowtable_by_dev(const struct net_device *dev);
+
unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state);
unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index a010b25076ca0..1acfcdbee42e8 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -17,6 +17,129 @@ static struct workqueue_struct *nf_flow_offload_add_wq;
static struct workqueue_struct *nf_flow_offload_del_wq;
static struct workqueue_struct *nf_flow_offload_stats_wq;
+struct flow_offload_xdp_ft {
+ struct list_head head;
+ struct nf_flowtable *ft;
+ struct rcu_head rcuhead;
+};
+
+struct flow_offload_xdp {
+ struct hlist_node hnode;
+ unsigned long net_device_addr;
+ struct list_head head;
+};
+
+#define NF_XDP_HT_BITS 4
+static DEFINE_HASHTABLE(nf_xdp_hashtable, NF_XDP_HT_BITS);
+static DEFINE_MUTEX(nf_xdp_hashtable_lock);
+
+/* caller must hold rcu read lock */
+struct nf_flowtable *nf_flowtable_by_dev(const struct net_device *dev)
+{
+ unsigned long key = (unsigned long)dev;
+ struct flow_offload_xdp *iter;
+
+ hash_for_each_possible_rcu(nf_xdp_hashtable, iter, hnode, key) {
+ if (key == iter->net_device_addr) {
+ struct flow_offload_xdp_ft *ft_elem;
+
+ /* The user is supposed to insert a given net_device
+ * just into a single nf_flowtable so we always return
+ * the first element here.
+ */
+ ft_elem = list_first_or_null_rcu(&iter->head,
+ struct flow_offload_xdp_ft,
+ head);
+ return ft_elem ? ft_elem->ft : NULL;
+ }
+ }
+
+ return NULL;
+}
+
+static int nf_flowtable_by_dev_insert(struct nf_flowtable *ft,
+ const struct net_device *dev)
+{
+ struct flow_offload_xdp *iter, *elem = NULL;
+ unsigned long key = (unsigned long)dev;
+ struct flow_offload_xdp_ft *ft_elem;
+
+ ft_elem = kzalloc(sizeof(*ft_elem), GFP_KERNEL_ACCOUNT);
+ if (!ft_elem)
+ return -ENOMEM;
+
+ ft_elem->ft = ft;
+
+ mutex_lock(&nf_xdp_hashtable_lock);
+
+ hash_for_each_possible(nf_xdp_hashtable, iter, hnode, key) {
+ if (key == iter->net_device_addr) {
+ elem = iter;
+ break;
+ }
+ }
+
+ if (!elem) {
+ elem = kzalloc(sizeof(*elem), GFP_KERNEL_ACCOUNT);
+ if (!elem)
+ goto err_unlock;
+
+ elem->net_device_addr = key;
+ INIT_LIST_HEAD(&elem->head);
+ hash_add_rcu(nf_xdp_hashtable, &elem->hnode, key);
+ }
+ list_add_tail_rcu(&ft_elem->head, &elem->head);
+
+ mutex_unlock(&nf_xdp_hashtable_lock);
+
+ return 0;
+
+err_unlock:
+ mutex_unlock(&nf_xdp_hashtable_lock);
+ kfree(ft_elem);
+
+ return -ENOMEM;
+}
+
+static void nf_flowtable_by_dev_remove(struct nf_flowtable *ft,
+ const struct net_device *dev)
+{
+ struct flow_offload_xdp *iter, *elem = NULL;
+ unsigned long key = (unsigned long)dev;
+
+ mutex_lock(&nf_xdp_hashtable_lock);
+
+ hash_for_each_possible(nf_xdp_hashtable, iter, hnode, key) {
+ if (key == iter->net_device_addr) {
+ elem = iter;
+ break;
+ }
+ }
+
+ if (elem) {
+ struct flow_offload_xdp_ft *ft_elem, *ft_next;
+
+ list_for_each_entry_safe(ft_elem, ft_next, &elem->head, head) {
+ if (ft_elem->ft == ft) {
+ list_del_rcu(&ft_elem->head);
+ kfree_rcu(ft_elem, rcuhead);
+ }
+ }
+
+ if (list_empty(&elem->head))
+ hash_del_rcu(&elem->hnode);
+ else
+ elem = NULL;
+ }
+
+ mutex_unlock(&nf_xdp_hashtable_lock);
+
+ if (elem) {
+ synchronize_rcu();
+ kfree(elem);
+ }
+}
+
struct flow_offload_work {
struct list_head list;
enum flow_cls_command cmd;
@@ -1183,6 +1306,38 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo,
return 0;
}
+static int nf_flow_offload_xdp_setup(struct nf_flowtable *flowtable,
+ struct net_device *dev,
+ enum flow_block_command cmd)
+{
+ switch (cmd) {
+ case FLOW_BLOCK_BIND:
+ return nf_flowtable_by_dev_insert(flowtable, dev);
+ case FLOW_BLOCK_UNBIND:
+ nf_flowtable_by_dev_remove(flowtable, dev);
+ return 0;
+ }
+
+ WARN_ON_ONCE(1);
+ return 0;
+}
+
+static void nf_flow_offload_xdp_cancel(struct nf_flowtable *flowtable,
+ struct net_device *dev,
+ enum flow_block_command cmd)
+{
+ switch (cmd) {
+ case FLOW_BLOCK_BIND:
+ nf_flowtable_by_dev_remove(flowtable, dev);
+ return;
+ case FLOW_BLOCK_UNBIND:
+ /* We do not re-bind in case hw offload would report error
+ * on *unregister*.
+ */
+ break;
+ }
+}
+
int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
struct net_device *dev,
enum flow_block_command cmd)
@@ -1192,7 +1347,7 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
int err;
if (!nf_flowtable_hw_offload(flowtable))
- return 0;
+ return nf_flow_offload_xdp_setup(flowtable, dev, cmd);
if (dev->netdev_ops->ndo_setup_tc)
err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd,
@@ -1200,8 +1355,10 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
else
err = nf_flow_table_indr_offload_cmd(&bo, flowtable, dev, cmd,
&extack);
- if (err < 0)
+ if (err < 0) {
+ nf_flow_offload_xdp_cancel(flowtable, dev, cmd);
return err;
+ }
return nf_flow_table_block_setup(flowtable, &bo, cmd);
}
--
2.45.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [RFC bpf-next v1 3/4] samples/bpf: Add bpf sample to offload flowtable traffic to xdp
2024-05-10 14:01 [RFC bpf-next v1 0/4] netfilter: Add the capability to offload flowtable in XDP layer Lorenzo Bianconi
2024-05-10 14:01 ` [RFC bpf-next v1 1/4] netfilter: nf_tables: add flowtable map for xdp offload Lorenzo Bianconi
2024-05-10 14:01 ` [RFC bpf-next v1 2/4] netfilter: add bpf_xdp_flow_offload_lookup kfunc Lorenzo Bianconi
@ 2024-05-10 14:01 ` Lorenzo Bianconi
2024-05-10 14:01 ` [RFC bpf-next v1 4/4] selftests/bpf: Add selftest for bpf_xdp_flow_offload_lookup kfunc Lorenzo Bianconi
3 siblings, 0 replies; 6+ messages in thread
From: Lorenzo Bianconi @ 2024-05-10 14:01 UTC (permalink / raw)
To: bpf
Cc: pablo, kadlec, davem, edumazet, kuba, pabeni, netfilter-devel,
netdev, ast, daniel, andrii, lorenzo.bianconi, toke, fw, hawk,
horms, donhunte
Introduce xdp_flowtable_offload bpf sample to offload sw flowtable logic
in xdp layer if hw flowtable is not available or does not support a
specific kind of traffic.
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
samples/bpf/Makefile | 7 +-
samples/bpf/xdp_flowtable_offload.bpf.c | 592 +++++++++++++++++++++++
samples/bpf/xdp_flowtable_offload_user.c | 128 +++++
3 files changed, 726 insertions(+), 1 deletion(-)
create mode 100644 samples/bpf/xdp_flowtable_offload.bpf.c
create mode 100644 samples/bpf/xdp_flowtable_offload_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 9aa027b144df6..a3d089ca224d5 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -46,6 +46,7 @@ tprogs-y += xdp_fwd
tprogs-y += task_fd_query
tprogs-y += ibumad
tprogs-y += hbm
+tprogs-y += xdp_flowtable_offload
# Libbpf dependencies
LIBBPF_SRC = $(TOOLS_PATH)/lib/bpf
@@ -98,6 +99,7 @@ ibumad-objs := ibumad_user.o
hbm-objs := hbm.o $(CGROUP_HELPERS)
xdp_router_ipv4-objs := xdp_router_ipv4_user.o $(XDP_SAMPLE)
+xdp_flowtable_offload-objs := xdp_flowtable_offload_user.o $(XDP_SAMPLE)
# Tell kbuild to always build the programs
always-y := $(tprogs-y)
@@ -306,6 +308,7 @@ $(obj)/$(TRACE_HELPERS) $(obj)/$(CGROUP_HELPERS) $(obj)/$(XDP_SAMPLE): | libbpf_
.PHONY: libbpf_hdrs
$(obj)/xdp_router_ipv4_user.o: $(obj)/xdp_router_ipv4.skel.h
+$(obj)/xdp_flowtable_offload_user.o: $(obj)/xdp_flowtable_offload.skel.h
$(obj)/tracex5.bpf.o: $(obj)/syscall_nrs.h
$(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
@@ -361,6 +364,7 @@ endef
CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
$(obj)/xdp_router_ipv4.bpf.o: $(obj)/xdp_sample.bpf.o
+$(obj)/xdp_flowtable_offload.bpf.o: $(obj)/xdp_sample.bpf.o
$(obj)/%.bpf.o: $(src)/%.bpf.c $(obj)/vmlinux.h $(src)/xdp_sample.bpf.h $(src)/xdp_sample_shared.h
@echo " CLANG-BPF " $@
@@ -370,10 +374,11 @@ $(obj)/%.bpf.o: $(src)/%.bpf.c $(obj)/vmlinux.h $(src)/xdp_sample.bpf.h $(src)/x
-I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \
-c $(filter %.bpf.c,$^) -o $@
-LINKED_SKELS := xdp_router_ipv4.skel.h
+LINKED_SKELS := xdp_router_ipv4.skel.h xdp_flowtable_offload.skel.h
clean-files += $(LINKED_SKELS)
xdp_router_ipv4.skel.h-deps := xdp_router_ipv4.bpf.o xdp_sample.bpf.o
+xdp_flowtable_offload.skel.h-deps := xdp_flowtable_offload.bpf.o xdp_sample.bpf.o
LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.bpf.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
diff --git a/samples/bpf/xdp_flowtable_offload.bpf.c b/samples/bpf/xdp_flowtable_offload.bpf.c
new file mode 100644
index 0000000000000..728c859feefae
--- /dev/null
+++ b/samples/bpf/xdp_flowtable_offload.bpf.c
@@ -0,0 +1,592 @@
+/* Copyright (c) 2024 Lorenzo Bianconi <lorenzo@kernel.org>
+ *
+ * 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 "vmlinux.h"
+#include "xdp_sample.bpf.h"
+#include "xdp_sample_shared.h"
+
+#define MAX_ERRNO 4095
+#define IS_ERR_VALUE(x) (unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO
+#define BIT(x) (1 << (x))
+
+#define ETH_P_IP 0x0800
+#define IP_MF 0x2000 /* "More Fragments" */
+#define IP_OFFSET 0x1fff /* "Fragment Offset" */
+
+#define IPV6_FLOWINFO_MASK __cpu_to_be32(0x0fffffff)
+
+#define CSUM_MANGLED_0 ((__sum16)0xffff)
+
+struct flow_offload_tuple_rhash *
+bpf_xdp_flow_offload_lookup(struct xdp_md *,
+ struct bpf_fib_lookup *, u32) __ksym;
+
+/* IP checksum utility routines */
+
+static __always_inline __u32 csum_add(__u32 csum, __u32 addend)
+{
+ __u32 res = csum + addend;
+
+ return res + (res < addend);
+}
+
+static __always_inline __u16 csum_fold(__u32 csum)
+{
+ csum = (csum & 0xffff) + (csum >> 16);
+ csum = (csum & 0xffff) + (csum >> 16);
+ return ~csum;
+}
+
+static __always_inline __u16 csum_replace4(__u32 csum, __u32 from, __u32 to)
+{
+ __u32 tmp = csum_add(~csum, ~from);
+
+ return csum_fold(csum_add(tmp, to));
+}
+
+static __always_inline __u16 csum_replace16(__u32 csum, __u32 *from, __u32 *to)
+{
+ __u32 diff[] = {
+ ~from[0], ~from[1], ~from[2], ~from[3],
+ to[0], to[1], to[2], to[3],
+ };
+
+ csum = bpf_csum_diff(0, 0, diff, sizeof(diff), ~csum);
+ return csum_fold(csum);
+}
+
+/* IP-TCP header utility routines */
+
+static __always_inline void ip_decrease_ttl(struct iphdr *iph)
+{
+ __u32 check = (__u32)iph->check;
+
+ check += (__u32)bpf_htons(0x0100);
+ iph->check = (__sum16)(check + (check >= 0xffff));
+ iph->ttl--;
+}
+
+static __always_inline bool
+xdp_flowtable_offload_check_iphdr(struct iphdr *iph)
+{
+ /* ip fragmented traffic */
+ if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET))
+ return false;
+
+ /* ip options */
+ if (iph->ihl * 4 != sizeof(*iph))
+ return false;
+
+ if (iph->ttl <= 1)
+ return false;
+
+ return true;
+}
+
+static __always_inline bool
+xdp_flowtable_offload_check_tcp_state(void *ports, void *data_end, u8 proto)
+{
+ if (proto == IPPROTO_TCP) {
+ struct tcphdr *tcph = ports;
+
+ if (tcph + 1 > data_end)
+ return false;
+
+ if (tcph->fin || tcph->rst)
+ return false;
+ }
+
+ return true;
+}
+
+/* IP nat utility routines */
+
+static __always_inline void
+xdp_flowtable_offload_nat_port(struct flow_ports *ports, void *data_end,
+ u8 proto, __be16 port, __be16 nat_port)
+{
+ switch (proto) {
+ case IPPROTO_TCP: {
+ struct tcphdr *tcph = (struct tcphdr *)ports;
+
+ if (tcph + 1 > data_end)
+ break;
+
+ tcph->check = csum_replace4((__u32)tcph->check, (__u32)port,
+ (__u32)nat_port);
+ break;
+ }
+ case IPPROTO_UDP: {
+ struct udphdr *udph = (struct udphdr *)ports;
+
+ if (udph + 1 > data_end)
+ break;
+
+ if (!udph->check)
+ break;
+
+ udph->check = csum_replace4((__u32)udph->check, (__u32)port,
+ (__u32)nat_port);
+ if (!udph->check)
+ udph->check = CSUM_MANGLED_0;
+ break;
+ }
+ default:
+ break;
+ }
+}
+
+static __always_inline void
+xdp_flowtable_offload_snat_port(const struct flow_offload *flow,
+ struct flow_ports *ports, void *data_end,
+ u8 proto, enum flow_offload_tuple_dir dir)
+{
+ __be16 port, nat_port;
+
+ if (ports + 1 > data_end)
+ return;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ port = ports->source;
+ bpf_core_read(&nat_port, bpf_core_type_size(nat_port),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port);
+ ports->source = nat_port;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ port = ports->dest;
+ bpf_core_read(&nat_port, bpf_core_type_size(nat_port),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port);
+ ports->dest = nat_port;
+ break;
+ default:
+ return;
+ }
+
+ xdp_flowtable_offload_nat_port(ports, data_end, proto, port, nat_port);
+}
+
+static __always_inline void
+xdp_flowtable_offload_dnat_port(const struct flow_offload *flow,
+ struct flow_ports *ports, void *data_end,
+ u8 proto, enum flow_offload_tuple_dir dir)
+{
+ __be16 port, nat_port;
+
+ if (ports + 1 > data_end)
+ return;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ port = ports->dest;
+ bpf_core_read(&nat_port, bpf_core_type_size(nat_port),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port);
+ ports->dest = nat_port;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ port = ports->source;
+ bpf_core_read(&nat_port, bpf_core_type_size(nat_port),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port);
+ ports->source = nat_port;
+ break;
+ default:
+ return;
+ }
+
+ xdp_flowtable_offload_nat_port(ports, data_end, proto, port, nat_port);
+}
+
+static __always_inline void
+xdp_flowtable_offload_ip_l4(struct iphdr *iph, void *data_end,
+ __be32 addr, __be32 nat_addr)
+{
+ switch (iph->protocol) {
+ case IPPROTO_TCP: {
+ struct tcphdr *tcph = (struct tcphdr *)(iph + 1);
+
+ if (tcph + 1 > data_end)
+ break;
+
+ tcph->check = csum_replace4((__u32)tcph->check, addr,
+ nat_addr);
+ break;
+ }
+ case IPPROTO_UDP: {
+ struct udphdr *udph = (struct udphdr *)(iph + 1);
+
+ if (udph + 1 > data_end)
+ break;
+
+ if (!udph->check)
+ break;
+
+ udph->check = csum_replace4((__u32)udph->check, addr,
+ nat_addr);
+ if (!udph->check)
+ udph->check = CSUM_MANGLED_0;
+ break;
+ }
+ default:
+ break;
+ }
+}
+
+static __always_inline void
+xdp_flowtable_offload_snat_ip(const struct flow_offload *flow,
+ struct iphdr *iph, void *data_end,
+ enum flow_offload_tuple_dir dir)
+{
+ __be32 addr, nat_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = iph->saddr;
+ bpf_core_read(&nat_addr, bpf_core_type_size(nat_addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr);
+ iph->saddr = nat_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = iph->daddr;
+ bpf_core_read(&nat_addr, bpf_core_type_size(nat_addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr);
+ iph->daddr = nat_addr;
+ break;
+ default:
+ return;
+ }
+ iph->check = csum_replace4((__u32)iph->check, addr, nat_addr);
+
+ xdp_flowtable_offload_ip_l4(iph, data_end, addr, nat_addr);
+}
+
+static __always_inline void
+xdp_flowtable_offload_get_dnat_ip(const struct flow_offload *flow,
+ enum flow_offload_tuple_dir dir,
+ __be32 *addr)
+{
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ bpf_core_read(addr, sizeof(*addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr);
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ bpf_core_read(addr, sizeof(*addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr);
+ break;
+ }
+}
+
+static __always_inline void
+xdp_flowtable_offload_dnat_ip(const struct flow_offload *flow,
+ struct iphdr *iph, void *data_end,
+ enum flow_offload_tuple_dir dir)
+{
+ __be32 addr, nat_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = iph->daddr;
+ bpf_core_read(&nat_addr, bpf_core_type_size(nat_addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr);
+ iph->daddr = nat_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = iph->saddr;
+ bpf_core_read(&nat_addr, bpf_core_type_size(nat_addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr);
+ iph->saddr = nat_addr;
+ break;
+ default:
+ return;
+ }
+ iph->check = csum_replace4((__u32)iph->check, addr, nat_addr);
+
+ xdp_flowtable_offload_ip_l4(iph, data_end, addr, nat_addr);
+}
+
+static __always_inline void
+xdp_flowtable_offload_ipv6_l4(struct ipv6hdr *ip6h, void *data_end,
+ struct in6_addr *addr, struct in6_addr *nat_addr)
+{
+ switch (ip6h->nexthdr) {
+ case IPPROTO_TCP: {
+ struct tcphdr *tcph = (struct tcphdr *)(ip6h + 1);
+
+ if (tcph + 1 > data_end)
+ break;
+
+ tcph->check = csum_replace16((__u32)tcph->check,
+ addr->in6_u.u6_addr32,
+ nat_addr->in6_u.u6_addr32);
+ break;
+ }
+ case IPPROTO_UDP: {
+ struct udphdr *udph = (struct udphdr *)(ip6h + 1);
+
+ if (udph + 1 > data_end)
+ break;
+
+ if (!udph->check)
+ break;
+
+ udph->check = csum_replace16((__u32)udph->check,
+ addr->in6_u.u6_addr32,
+ nat_addr->in6_u.u6_addr32);
+ if (!udph->check)
+ udph->check = CSUM_MANGLED_0;
+ break;
+ }
+ default:
+ break;
+ }
+}
+
+static __always_inline void
+xdp_flowtable_offload_snat_ipv6(const struct flow_offload *flow,
+ struct ipv6hdr *ip6h, void *data_end,
+ enum flow_offload_tuple_dir dir)
+{
+ struct in6_addr addr, nat_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = ip6h->saddr;
+ bpf_core_read(&nat_addr, bpf_core_type_size(nat_addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6);
+ ip6h->saddr = nat_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = ip6h->daddr;
+ bpf_core_read(&nat_addr, bpf_core_type_size(nat_addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6);
+ ip6h->daddr = nat_addr;
+ break;
+ default:
+ return;
+ }
+
+ xdp_flowtable_offload_ipv6_l4(ip6h, data_end, &addr, &nat_addr);
+}
+
+static __always_inline void
+xdp_flowtable_offload_get_dnat_ipv6(const struct flow_offload *flow,
+ enum flow_offload_tuple_dir dir,
+ struct in6_addr *addr)
+{
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ bpf_core_read(addr, sizeof(*addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6);
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ bpf_core_read(addr, sizeof(*addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6);
+ break;
+ }
+}
+
+static __always_inline void
+xdp_flowtable_offload_dnat_ipv6(const struct flow_offload *flow,
+ struct ipv6hdr *ip6h, void *data_end,
+ enum flow_offload_tuple_dir dir)
+{
+ struct in6_addr addr, nat_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = ip6h->daddr;
+ bpf_core_read(&nat_addr, bpf_core_type_size(nat_addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6);
+ ip6h->daddr = nat_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = ip6h->saddr;
+ bpf_core_read(&nat_addr, bpf_core_type_size(nat_addr),
+ &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6);
+ ip6h->saddr = nat_addr;
+ break;
+ default:
+ return;
+ }
+
+ xdp_flowtable_offload_ipv6_l4(ip6h, data_end, &addr, &nat_addr);
+}
+
+static __always_inline void
+xdp_flowtable_offload_forward_ip(const struct flow_offload *flow,
+ void *data, void *data_end,
+ struct flow_ports *ports,
+ enum flow_offload_tuple_dir dir,
+ unsigned long flags)
+{
+ struct iphdr *iph = data + sizeof(struct ethhdr);
+
+ if (iph + 1 > data_end)
+ return;
+
+ if (flags & BIT(NF_FLOW_SNAT)) {
+ xdp_flowtable_offload_snat_port(flow, ports, data_end,
+ iph->protocol, dir);
+ xdp_flowtable_offload_snat_ip(flow, iph, data_end, dir);
+ }
+ if (flags & BIT(NF_FLOW_DNAT)) {
+ xdp_flowtable_offload_dnat_port(flow, ports, data_end,
+ iph->protocol, dir);
+ xdp_flowtable_offload_dnat_ip(flow, iph, data_end, dir);
+ }
+
+ ip_decrease_ttl(iph);
+}
+
+static __always_inline void
+xdp_flowtable_offload_forward_ipv6(const struct flow_offload *flow,
+ void *data, void *data_end,
+ struct flow_ports *ports,
+ enum flow_offload_tuple_dir dir,
+ unsigned long flags)
+{
+ struct ipv6hdr *ip6h = data + sizeof(struct ethhdr);
+
+ if (ip6h + 1 > data_end)
+ return;
+
+ if (flags & BIT(NF_FLOW_SNAT)) {
+ xdp_flowtable_offload_snat_port(flow, ports, data_end,
+ ip6h->nexthdr, dir);
+ xdp_flowtable_offload_snat_ipv6(flow, ip6h, data_end, dir);
+ }
+ if (flags & BIT(NF_FLOW_DNAT)) {
+ xdp_flowtable_offload_dnat_port(flow, ports, data_end,
+ ip6h->nexthdr, dir);
+ xdp_flowtable_offload_dnat_ipv6(flow, ip6h, data_end, dir);
+ }
+
+ ip6h->hop_limit--;
+}
+
+SEC("xdp")
+int xdp_flowtable_offload(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct bpf_fib_lookup tuple = {
+ .ifindex = ctx->ingress_ifindex,
+ };
+ void *data = (void *)(long)ctx->data;
+ enum flow_offload_tuple_dir dir;
+ struct ethhdr *eth = data;
+ struct flow_offload *flow;
+ struct flow_ports *ports;
+ unsigned long flags;
+ int iifindex;
+
+ if (eth + 1 > data_end)
+ return XDP_PASS;
+
+ switch (eth->h_proto) {
+ case bpf_htons(ETH_P_IP): {
+ struct iphdr *iph = data + sizeof(*eth);
+
+ ports = (struct flow_ports *)(iph + 1);
+ if (ports + 1 > data_end)
+ return XDP_PASS;
+
+ /* sanity check on ip header */
+ if (!xdp_flowtable_offload_check_iphdr(iph))
+ return XDP_PASS;
+
+ if (!xdp_flowtable_offload_check_tcp_state(ports, data_end,
+ iph->protocol))
+ return XDP_PASS;
+
+ tuple.family = AF_INET;
+ tuple.tos = iph->tos;
+ tuple.l4_protocol = iph->protocol;
+ tuple.tot_len = bpf_ntohs(iph->tot_len);
+ tuple.ipv4_src = iph->saddr;
+ tuple.ipv4_dst = iph->daddr;
+ tuple.sport = ports->source;
+ tuple.dport = ports->dest;
+ break;
+ }
+ case bpf_htons(ETH_P_IPV6): {
+ struct in6_addr *src = (struct in6_addr *)tuple.ipv6_src;
+ struct in6_addr *dst = (struct in6_addr *)tuple.ipv6_dst;
+ struct ipv6hdr *ip6h = data + sizeof(*eth);
+
+ ports = (struct flow_ports *)(ip6h + 1);
+ if (ports + 1 > data_end)
+ return XDP_PASS;
+
+ if (ip6h->hop_limit <= 1)
+ return XDP_PASS;
+
+ if (!xdp_flowtable_offload_check_tcp_state(ports, data_end,
+ ip6h->nexthdr))
+ return XDP_PASS;
+
+ tuple.family = AF_INET6;
+ tuple.l4_protocol = ip6h->nexthdr;
+ tuple.tot_len = bpf_ntohs(ip6h->payload_len);
+ *src = ip6h->saddr;
+ *dst = ip6h->daddr;
+ tuple.sport = ports->source;
+ tuple.dport = ports->dest;
+ break;
+ }
+ default:
+ return XDP_PASS;
+ }
+
+ tuplehash = bpf_xdp_flow_offload_lookup(ctx, &tuple, sizeof(tuple));
+ if (IS_ERR_VALUE(tuplehash))
+ return XDP_PASS;
+
+ dir = tuplehash->tuple.dir;
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+ if (bpf_core_read(&flags, sizeof(flags), &flow->flags))
+ return XDP_PASS;
+
+ switch (tuplehash->tuple.xmit_type) {
+ case FLOW_OFFLOAD_XMIT_NEIGH:
+ /* update the destination address in case of dnatting before
+ * performing the route lookup
+ */
+ if (tuple.family == AF_INET6)
+ xdp_flowtable_offload_get_dnat_ipv6(flow, dir,
+ (struct in6_addr *)&tuple.ipv6_dst);
+ else
+ xdp_flowtable_offload_get_dnat_ip(flow, dir, &tuple.ipv4_src);
+
+ if (bpf_fib_lookup(ctx, &tuple, sizeof(tuple), 0))
+ return XDP_PASS;
+
+ if (tuple.family == AF_INET6)
+ xdp_flowtable_offload_forward_ipv6(flow, data, data_end,
+ ports, dir, flags);
+ else
+ xdp_flowtable_offload_forward_ip(flow, data, data_end,
+ ports, dir, flags);
+
+ __builtin_memcpy(eth->h_dest, tuple.dmac, ETH_ALEN);
+ __builtin_memcpy(eth->h_source, tuple.smac, ETH_ALEN);
+ iifindex = tuple.ifindex;
+ break;
+ case FLOW_OFFLOAD_XMIT_DIRECT:
+ default:
+ return XDP_PASS;
+ }
+
+ return bpf_redirect(iifindex, 0);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_flowtable_offload_user.c b/samples/bpf/xdp_flowtable_offload_user.c
new file mode 100644
index 0000000000000..179b1f34b48fd
--- /dev/null
+++ b/samples/bpf/xdp_flowtable_offload_user.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2024 Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+static const char *__doc__ =
+"XDP flowtable integration example\n"
+"Usage: xdp_flowtable_offload <IFINDEX|IFNAME>\n";
+
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <net/if.h>
+#include <unistd.h>
+#include <libgen.h>
+#include <getopt.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "bpf_util.h"
+#include "xdp_sample_user.h"
+#include "xdp_flowtable_offload.skel.h"
+
+static int mask = SAMPLE_RX_CNT | SAMPLE_EXCEPTION_CNT;
+
+DEFINE_SAMPLE_INIT(xdp_flowtable_offload);
+
+static const struct option long_options[] = {
+ { "help", no_argument, NULL, 'h' },
+ { "generic", no_argument, NULL, 'g' },
+ {}
+};
+
+int main(int argc, char **argv)
+{
+ struct xdp_flowtable_offload *skel;
+ int ret = EXIT_FAIL_OPTION;
+ char ifname[IF_NAMESIZE];
+ bool generic = false;
+ int ifindex;
+ int opt;
+
+ while ((opt = getopt_long(argc, argv, "hg",
+ long_options, NULL)) != -1) {
+ switch (opt) {
+ case 'g':
+ generic = true;
+ break;
+ case 'h':
+ default:
+ sample_usage(argv, long_options, __doc__, mask, false);
+ return ret;
+ }
+ }
+
+ if (argc <= optind) {
+ sample_usage(argv, long_options, __doc__, mask, true);
+ goto end;
+ }
+
+ ifindex = if_nametoindex(argv[optind]);
+ if (!ifindex)
+ ifindex = strtoul(argv[optind], NULL, 0);
+
+ if (!ifindex) {
+ fprintf(stderr, "Bad interface index or name\n");
+ sample_usage(argv, long_options, __doc__, mask, true);
+ goto end;
+ }
+
+ skel = xdp_flowtable_offload__open();
+ if (!skel) {
+ fprintf(stderr, "Failed to xdp_flowtable_offload__open: %s\n",
+ strerror(errno));
+ ret = EXIT_FAIL_BPF;
+ goto end;
+ }
+
+ ret = sample_init_pre_load(skel);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to sample_init_pre_load: %s\n", strerror(-ret));
+ ret = EXIT_FAIL_BPF;
+ goto end_destroy;
+ }
+
+ ret = xdp_flowtable_offload__load(skel);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to xdp_flowtable_offload__load: %s\n",
+ strerror(errno));
+ ret = EXIT_FAIL_BPF;
+ goto end_destroy;
+ }
+
+ ret = sample_init(skel, mask);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
+ ret = EXIT_FAIL;
+ goto end_destroy;
+ }
+
+ if (sample_install_xdp(skel->progs.xdp_flowtable_offload,
+ ifindex, generic, false) < 0) {
+ ret = EXIT_FAIL_XDP;
+ goto end_destroy;
+ }
+
+ ret = EXIT_FAIL;
+ if (!if_indextoname(ifindex, ifname)) {
+ fprintf(stderr, "Failed to if_indextoname for %d: %s\n", ifindex,
+ strerror(errno));
+ goto end_destroy;
+ }
+
+ ret = sample_run(2, NULL, NULL);
+ if (ret < 0) {
+ fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
+ ret = EXIT_FAIL;
+ goto end_destroy;
+ }
+ ret = EXIT_OK;
+end_destroy:
+ xdp_flowtable_offload__destroy(skel);
+end:
+ sample_exit(ret);
+}
--
2.45.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [RFC bpf-next v1 4/4] selftests/bpf: Add selftest for bpf_xdp_flow_offload_lookup kfunc
2024-05-10 14:01 [RFC bpf-next v1 0/4] netfilter: Add the capability to offload flowtable in XDP layer Lorenzo Bianconi
` (2 preceding siblings ...)
2024-05-10 14:01 ` [RFC bpf-next v1 3/4] samples/bpf: Add bpf sample to offload flowtable traffic to xdp Lorenzo Bianconi
@ 2024-05-10 14:01 ` Lorenzo Bianconi
3 siblings, 0 replies; 6+ messages in thread
From: Lorenzo Bianconi @ 2024-05-10 14:01 UTC (permalink / raw)
To: bpf
Cc: pablo, kadlec, davem, edumazet, kuba, pabeni, netfilter-devel,
netdev, ast, daniel, andrii, lorenzo.bianconi, toke, fw, hawk,
horms, donhunte
Introduce e2e selftest for bpf_xdp_flow_offload_lookup kfunc through
xdp_flowtable utility.
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
tools/testing/selftests/bpf/Makefile | 10 +-
tools/testing/selftests/bpf/config | 4 +
.../selftests/bpf/progs/xdp_flowtable.c | 142 ++++++++++++++++++
.../selftests/bpf/test_xdp_flowtable.sh | 112 ++++++++++++++
tools/testing/selftests/bpf/xdp_flowtable.c | 142 ++++++++++++++++++
5 files changed, 408 insertions(+), 2 deletions(-)
create mode 100644 tools/testing/selftests/bpf/progs/xdp_flowtable.c
create mode 100755 tools/testing/selftests/bpf/test_xdp_flowtable.sh
create mode 100644 tools/testing/selftests/bpf/xdp_flowtable.c
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 135023a357b3b..a5d4cd7d92c0a 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -133,7 +133,8 @@ TEST_PROGS := test_kmod.sh \
test_bpftool_metadata.sh \
test_doc_build.sh \
test_xsk.sh \
- test_xdp_features.sh
+ test_xdp_features.sh \
+ test_xdp_flowtable.sh
TEST_PROGS_EXTENDED := with_addr.sh \
with_tunnels.sh ima_setup.sh verify_sig_setup.sh \
@@ -144,7 +145,7 @@ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \
- xdp_features bpf_test_no_cfi.ko
+ xdp_features bpf_test_no_cfi.ko xdp_flowtable
TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi
@@ -477,6 +478,7 @@ test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o
xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o
xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o
xdp_features.skel.h-deps := xdp_features.bpf.o
+xdp_flowtable.skel.h-deps := xdp_flowtable.bpf.o
LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
@@ -711,6 +713,10 @@ $(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp
$(call msg,BINARY,,$@)
$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+$(OUTPUT)/xdp_flowtable: xdp_flowtable.c $(OUTPUT)/xdp_flowtable.skel.h | $(OUTPUT)
+ $(call msg,BINARY,,$@)
+ $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+
# Make sure we are able to include and link libbpf against c++.
$(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
$(call msg,CXX,,$@)
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index eeabd798bc3ae..1a9aea01145f7 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -82,6 +82,10 @@ CONFIG_NF_CONNTRACK=y
CONFIG_NF_CONNTRACK_MARK=y
CONFIG_NF_DEFRAG_IPV4=y
CONFIG_NF_DEFRAG_IPV6=y
+CONFIG_NF_TABLES=y
+CONFIG_NETFILTER_INGRESS=y
+CONFIG_NF_FLOW_TABLE=y
+CONFIG_NF_FLOW_TABLE_INET=y
CONFIG_NF_NAT=y
CONFIG_RC_CORE=y
CONFIG_SECURITY=y
diff --git a/tools/testing/selftests/bpf/progs/xdp_flowtable.c b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
new file mode 100644
index 0000000000000..cf725699e21d4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define MAX_ERRNO 4095
+#define IS_ERR_VALUE(x) (unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO
+
+#define ETH_P_IP 0x0800
+#define ETH_P_IPV6 0x86dd
+#define IP_MF 0x2000 /* "More Fragments" */
+#define IP_OFFSET 0x1fff /* "Fragment Offset" */
+#define AF_INET 2
+#define AF_INET6 10
+
+struct flow_offload_tuple_rhash *
+bpf_xdp_flow_offload_lookup(struct xdp_md *,
+ struct bpf_fib_lookup *, __u32) __ksym;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(max_entries, 1);
+} stats SEC(".maps");
+
+static __always_inline bool
+xdp_flowtable_offload_check_iphdr(struct iphdr *iph)
+{
+ /* ip fragmented traffic */
+ if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET))
+ return false;
+
+ /* ip options */
+ if (iph->ihl * 4 != sizeof(*iph))
+ return false;
+
+ if (iph->ttl <= 1)
+ return false;
+
+ return true;
+}
+
+static __always_inline bool
+xdp_flowtable_offload_check_tcp_state(void *ports, void *data_end, u8 proto)
+{
+ if (proto == IPPROTO_TCP) {
+ struct tcphdr *tcph = ports;
+
+ if (tcph + 1 > data_end)
+ return false;
+
+ if (tcph->fin || tcph->rst)
+ return false;
+ }
+
+ return true;
+}
+
+SEC("xdp.frags")
+int xdp_flowtable_do_lookup(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct bpf_fib_lookup tuple = {
+ .ifindex = ctx->ingress_ifindex,
+ };
+ void *data = (void *)(long)ctx->data;
+ struct ethhdr *eth = data;
+ struct flow_ports *ports;
+ __u32 *val, key = 0;
+
+ if (eth + 1 > data_end)
+ return XDP_DROP;
+
+ switch (eth->h_proto) {
+ case bpf_htons(ETH_P_IP): {
+ struct iphdr *iph = data + sizeof(*eth);
+
+ ports = (struct flow_ports *)(iph + 1);
+ if (ports + 1 > data_end)
+ return XDP_PASS;
+
+ /* sanity check on ip header */
+ if (!xdp_flowtable_offload_check_iphdr(iph))
+ return XDP_PASS;
+
+ if (!xdp_flowtable_offload_check_tcp_state(ports, data_end,
+ iph->protocol))
+ return XDP_PASS;
+
+ tuple.family = AF_INET;
+ tuple.tos = iph->tos;
+ tuple.l4_protocol = iph->protocol;
+ tuple.tot_len = bpf_ntohs(iph->tot_len);
+ tuple.ipv4_src = iph->saddr;
+ tuple.ipv4_dst = iph->daddr;
+ tuple.sport = ports->source;
+ tuple.dport = ports->dest;
+ break;
+ }
+ case bpf_htons(ETH_P_IPV6): {
+ struct in6_addr *src = (struct in6_addr *)tuple.ipv6_src;
+ struct in6_addr *dst = (struct in6_addr *)tuple.ipv6_dst;
+ struct ipv6hdr *ip6h = data + sizeof(*eth);
+
+ ports = (struct flow_ports *)(ip6h + 1);
+ if (ports + 1 > data_end)
+ return XDP_PASS;
+
+ if (ip6h->hop_limit <= 1)
+ return XDP_PASS;
+
+ if (!xdp_flowtable_offload_check_tcp_state(ports, data_end,
+ ip6h->nexthdr))
+ return XDP_PASS;
+
+ tuple.family = AF_INET6;
+ tuple.l4_protocol = ip6h->nexthdr;
+ tuple.tot_len = bpf_ntohs(ip6h->payload_len);
+ *src = ip6h->saddr;
+ *dst = ip6h->daddr;
+ tuple.sport = ports->source;
+ tuple.dport = ports->dest;
+ break;
+ }
+ default:
+ return XDP_PASS;
+ }
+
+ tuplehash = bpf_xdp_flow_offload_lookup(ctx, &tuple, sizeof(tuple));
+ if (IS_ERR_VALUE(tuplehash))
+ return XDP_PASS;
+
+ val = bpf_map_lookup_elem(&stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_xdp_flowtable.sh b/tools/testing/selftests/bpf/test_xdp_flowtable.sh
new file mode 100755
index 0000000000000..1a8a40aebbdf1
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_flowtable.sh
@@ -0,0 +1,112 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+readonly NS0="ns0-$(mktemp -u XXXXXX)"
+readonly NS1="ns1-$(mktemp -u XXXXXX)"
+readonly infile="$(mktemp)"
+readonly outfile="$(mktemp)"
+
+xdp_flowtable_pid=""
+ret=1
+
+setup_flowtable() {
+nft -f /dev/stdin <<EOF
+table inet nat {
+ chain postrouting {
+ type nat hook postrouting priority filter; policy accept;
+ meta oif v10 masquerade
+ }
+}
+table inet filter {
+ flowtable ft {
+ hook ingress priority filter
+ devices = { v01, v10 }
+ }
+ chain forward {
+ type filter hook forward priority filter
+ meta l4proto { tcp, udp } flow add @ft
+ }
+}
+EOF
+}
+
+setup() {
+ sysctl -w net.ipv4.ip_forward=1
+ sysctl -w net.ipv6.conf.all.forwarding=1
+
+ ip netns add ${NS0}
+ ip netns add ${NS1}
+
+ ip link add v01 type veth peer name v00 netns ${NS0}
+ ip link add v10 type veth peer name v11 netns ${NS1}
+
+ ip -n ${NS0} addr add 192.168.0.1/24 dev v00
+ ip -6 -n ${NS0} addr add 2001:db8::1/64 dev v00
+ ip -n ${NS0} link set dev v00 up
+ ip -n ${NS0} route add default via 192.168.0.2
+ ip -6 -n ${NS0} route add default via 2001:db8::2
+
+ ip addr add 192.168.0.2/24 dev v01
+ ip -6 addr add 2001:db8::2/64 dev v01
+ ip link set dev v01 up
+ ip addr add 192.168.1.1/24 dev v10
+ ip -6 addr add 2001:db8:1::1/64 dev v10
+ ip link set dev v10 up
+
+ ip -n ${NS1} addr add 192.168.1.2/24 dev v11
+ ip -6 -n ${NS1} addr add 2001:db8:1::2/64 dev v11
+ ip -n ${NS1} link set dev v11 up
+ ip -n ${NS1} route add default via 192.168.1.1
+ ip -6 -n ${NS1} route add default via 2001:db8:1::1
+
+ # Load XDP program
+ ./xdp_flowtable v01 &
+ xdp_flowtable_pid=$!
+
+ setup_flowtable
+
+ dd if=/dev/urandom of="${infile}" bs=8192 count=16 status=none
+}
+
+wait_for_nc_server() {
+ while sleep 1; do
+ ip netns exec ${NS1} ss -nutlp | grep -q ":$1"
+ [ $? -eq 0 ] && break
+ done
+}
+
+cleanup() {
+ {
+ rm -f "${infile}" "${outfile}"
+
+ nft delete table inet filter
+ nft delete table inet nat
+
+ ip link del v01
+ ip link del v10
+
+ ip netns del ${NS0}
+ ip netns del ${NS1}
+ } >/dev/null 2>/dev/null
+}
+
+test_xdp_flowtable_lookup() {
+ ## Run IPv4 test
+ ip netns exec ${NS1} nc -4 --no-shutdown -l 8084 > ${outfile} &
+ wait_for_nc_server 8084
+ ip netns exec ${NS0} timeout 2 nc -4 192.168.1.2 8084 < ${infile}
+
+ ## Run IPv6 test
+ ip netns exec ${NS1} nc -6 --no-shutdown -l 8086 > ${outfile} &
+ wait_for_nc_server 8086
+ ip netns exec ${NS0} timeout 2 nc -6 2001:db8:1::2 8086 < ${infile}
+
+ wait $xdp_flowtable_pid && ret=0
+}
+
+trap cleanup 0 2 3 6 9
+setup
+
+test_xdp_flowtable_lookup
+
+exit $ret
diff --git a/tools/testing/selftests/bpf/xdp_flowtable.c b/tools/testing/selftests/bpf/xdp_flowtable.c
new file mode 100644
index 0000000000000..dea24deda7359
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_flowtable.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <uapi/linux/bpf.h>
+#include <linux/if_link.h>
+#include <net/if.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <signal.h>
+#include <argp.h>
+
+#include "xdp_flowtable.skel.h"
+
+#define MAX_ITERATION 10
+
+static volatile bool exiting, verbosity;
+static char ifname[IF_NAMESIZE];
+static int ifindex = -ENODEV;
+const char *argp_program_version = "xdp-flowtable 0.0";
+const char argp_program_doc[] =
+"XDP flowtable application.\n"
+"\n"
+"USAGE: ./xdp-flowtable [-v] <iface-name>\n";
+
+static const struct argp_option opts[] = {
+ { "verbose", 'v', NULL, 0, "Verbose debug output" },
+ {},
+};
+
+static void sig_handler(int sig)
+{
+ exiting = true;
+}
+
+static int libbpf_print_fn(enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ if (level == LIBBPF_DEBUG && !verbosity)
+ return 0;
+ return vfprintf(stderr, format, args);
+}
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+ switch (key) {
+ case 'v':
+ verbosity = true;
+ break;
+ case ARGP_KEY_ARG:
+ errno = 0;
+ if (strlen(arg) >= IF_NAMESIZE) {
+ fprintf(stderr, "Invalid device name: %s\n", arg);
+ argp_usage(state);
+ return ARGP_ERR_UNKNOWN;
+ }
+
+ ifindex = if_nametoindex(arg);
+ if (!ifindex)
+ ifindex = strtoul(arg, NULL, 0);
+ if (!ifindex || !if_indextoname(ifindex, ifname)) {
+ fprintf(stderr,
+ "Bad interface index or name (%d): %s\n",
+ errno, strerror(errno));
+ argp_usage(state);
+ return ARGP_ERR_UNKNOWN;
+ }
+ break;
+ default:
+ return ARGP_ERR_UNKNOWN;
+ }
+
+ return 0;
+}
+
+static const struct argp argp = {
+ .options = opts,
+ .parser = parse_arg,
+ .doc = argp_program_doc,
+};
+
+int main(int argc, char **argv)
+{
+ unsigned int count = 0, key = 0;
+ struct xdp_flowtable *skel;
+ int i, err;
+
+ libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+ libbpf_set_print(libbpf_print_fn);
+
+ signal(SIGINT, sig_handler);
+ signal(SIGTERM, sig_handler);
+
+ /* Parse command line arguments */
+ err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
+ if (err)
+ return err;
+
+ /* Load and verify BPF application */
+ skel = xdp_flowtable__open();
+ if (!skel) {
+ fprintf(stderr, "Failed to open and load BPF skeleton\n");
+ return -EINVAL;
+ }
+
+ /* Load & verify BPF programs */
+ err = xdp_flowtable__load(skel);
+ if (err) {
+ fprintf(stderr, "Failed to load and verify BPF skeleton\n");
+ goto cleanup;
+ }
+
+ /* Attach the XDP program */
+ err = xdp_flowtable__attach(skel);
+ if (err) {
+ fprintf(stderr, "Failed to attach BPF skeleton\n");
+ goto cleanup;
+ }
+
+ err = bpf_xdp_attach(ifindex,
+ bpf_program__fd(skel->progs.xdp_flowtable_do_lookup),
+ XDP_FLAGS_DRV_MODE, NULL);
+ if (err) {
+ fprintf(stderr, "Failed attaching XDP program to device %s\n",
+ ifname);
+ goto cleanup;
+ }
+
+ /* Collect stats */
+ for (i = 0; i < MAX_ITERATION && !exiting; i++)
+ sleep(1);
+
+ /* Check results */
+ err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key),
+ &count, sizeof(count), 0);
+ if (!err && !count)
+ err = -EINVAL;
+
+ bpf_xdp_detach(ifindex, XDP_FLAGS_DRV_MODE, NULL);
+cleanup:
+ xdp_flowtable__destroy(skel);
+
+ return err;
+}
--
2.45.0
^ permalink raw reply related [flat|nested] 6+ messages in thread