summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/bpf/test_run.c13
-rw-r--r--net/core/filter.c139
-rw-r--r--net/core/flow_dissector.c19
-rw-r--r--net/core/lwt_bpf.c2
-rw-r--r--net/ipv6/ip6_tunnel.c4
-rw-r--r--net/ipv6/seg6_local.c50
-rw-r--r--net/rds/ib_frmr.c1
-rw-r--r--net/sched/cls_flower.c248
8 files changed, 419 insertions, 57 deletions
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 22a78eedf4b1..f4078830ea50 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -11,12 +11,14 @@
#include <linux/filter.h>
#include <linux/sched/signal.h>
-static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx)
+static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx,
+ struct bpf_cgroup_storage *storage)
{
u32 ret;
preempt_disable();
rcu_read_lock();
+ bpf_cgroup_storage_set(storage);
ret = BPF_PROG_RUN(prog, ctx);
rcu_read_unlock();
preempt_enable();
@@ -26,14 +28,19 @@ static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx)
static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time)
{
+ struct bpf_cgroup_storage *storage = NULL;
u64 time_start, time_spent = 0;
u32 ret = 0, i;
+ storage = bpf_cgroup_storage_alloc(prog);
+ if (IS_ERR(storage))
+ return PTR_ERR(storage);
+
if (!repeat)
repeat = 1;
time_start = ktime_get_ns();
for (i = 0; i < repeat; i++) {
- ret = bpf_test_run_one(prog, ctx);
+ ret = bpf_test_run_one(prog, ctx, storage);
if (need_resched()) {
if (signal_pending(current))
break;
@@ -46,6 +53,8 @@ static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time)
do_div(time_spent, repeat);
*time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
+ bpf_cgroup_storage_free(storage);
+
return ret;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 7509bb7f0694..587bbfbd7db3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3814,6 +3814,30 @@ static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
.arg1_type = ARG_PTR_TO_CTX,
};
+BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx)
+{
+ return sock_gen_cookie(ctx->sk);
+}
+
+static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = {
+ .func = bpf_get_socket_cookie_sock_addr,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx)
+{
+ return sock_gen_cookie(ctx->sk);
+}
+
+static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = {
+ .func = bpf_get_socket_cookie_sock_ops,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb)
{
struct sock *sk = sk_to_full_sk(skb->sk);
@@ -4544,26 +4568,28 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
{
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
+ struct ipv6_sr_hdr *srh = srh_state->srh;
void *srh_tlvs, *srh_end, *ptr;
- struct ipv6_sr_hdr *srh;
int srhoff = 0;
- if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+ if (srh == NULL)
return -EINVAL;
- srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
srh_tlvs = (void *)((char *)srh + ((srh->first_segment + 1) << 4));
srh_end = (void *)((char *)srh + sizeof(*srh) + srh_state->hdrlen);
ptr = skb->data + offset;
if (ptr >= srh_tlvs && ptr + len <= srh_end)
- srh_state->valid = 0;
+ srh_state->valid = false;
else if (ptr < (void *)&srh->flags ||
ptr + len > (void *)&srh->segments)
return -EFAULT;
if (unlikely(bpf_try_make_writable(skb, offset + len)))
return -EFAULT;
+ if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+ return -EINVAL;
+ srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
memcpy(skb->data + offset, from, len);
return 0;
@@ -4579,52 +4605,78 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
.arg4_type = ARG_CONST_SIZE
};
-BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
- u32, action, void *, param, u32, param_len)
+static void bpf_update_srh_state(struct sk_buff *skb)
{
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
- struct ipv6_sr_hdr *srh;
int srhoff = 0;
- int err;
-
- if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
- return -EINVAL;
- srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
- if (!srh_state->valid) {
- if (unlikely((srh_state->hdrlen & 7) != 0))
- return -EBADMSG;
-
- srh->hdrlen = (u8)(srh_state->hdrlen >> 3);
- if (unlikely(!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3)))
- return -EBADMSG;
-
- srh_state->valid = 1;
+ if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) {
+ srh_state->srh = NULL;
+ } else {
+ srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
+ srh_state->hdrlen = srh_state->srh->hdrlen << 3;
+ srh_state->valid = true;
}
+}
+
+BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
+ u32, action, void *, param, u32, param_len)
+{
+ struct seg6_bpf_srh_state *srh_state =
+ this_cpu_ptr(&seg6_bpf_srh_states);
+ int hdroff = 0;
+ int err;
switch (action) {
case SEG6_LOCAL_ACTION_END_X:
+ if (!seg6_bpf_has_valid_srh(skb))
+ return -EBADMSG;
if (param_len != sizeof(struct in6_addr))
return -EINVAL;
return seg6_lookup_nexthop(skb, (struct in6_addr *)param, 0);
case SEG6_LOCAL_ACTION_END_T:
+ if (!seg6_bpf_has_valid_srh(skb))
+ return -EBADMSG;
if (param_len != sizeof(int))
return -EINVAL;
return seg6_lookup_nexthop(skb, NULL, *(int *)param);
+ case SEG6_LOCAL_ACTION_END_DT6:
+ if (!seg6_bpf_has_valid_srh(skb))
+ return -EBADMSG;
+ if (param_len != sizeof(int))
+ return -EINVAL;
+
+ if (ipv6_find_hdr(skb, &hdroff, IPPROTO_IPV6, NULL, NULL) < 0)
+ return -EBADMSG;
+ if (!pskb_pull(skb, hdroff))
+ return -EBADMSG;
+
+ skb_postpull_rcsum(skb, skb_network_header(skb), hdroff);
+ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+ skb->encapsulation = 0;
+
+ bpf_compute_data_pointers(skb);
+ bpf_update_srh_state(skb);
+ return seg6_lookup_nexthop(skb, NULL, *(int *)param);
case SEG6_LOCAL_ACTION_END_B6:
+ if (srh_state->srh && !seg6_bpf_has_valid_srh(skb))
+ return -EBADMSG;
err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6_INLINE,
param, param_len);
if (!err)
- srh_state->hdrlen =
- ((struct ipv6_sr_hdr *)param)->hdrlen << 3;
+ bpf_update_srh_state(skb);
+
return err;
case SEG6_LOCAL_ACTION_END_B6_ENCAP:
+ if (srh_state->srh && !seg6_bpf_has_valid_srh(skb))
+ return -EBADMSG;
err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6,
param, param_len);
if (!err)
- srh_state->hdrlen =
- ((struct ipv6_sr_hdr *)param)->hdrlen << 3;
+ bpf_update_srh_state(skb);
+
return err;
default:
return -EINVAL;
@@ -4646,15 +4698,14 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
{
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
+ struct ipv6_sr_hdr *srh = srh_state->srh;
void *srh_end, *srh_tlvs, *ptr;
- struct ipv6_sr_hdr *srh;
struct ipv6hdr *hdr;
int srhoff = 0;
int ret;
- if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+ if (unlikely(srh == NULL))
return -EINVAL;
- srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
srh_tlvs = (void *)((unsigned char *)srh + sizeof(*srh) +
((srh->first_segment + 1) << 4));
@@ -4684,8 +4735,11 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
hdr = (struct ipv6hdr *)skb->data;
hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+ if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+ return -EINVAL;
+ srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
srh_state->hdrlen += len;
- srh_state->valid = 0;
+ srh_state->valid = false;
return 0;
}
@@ -4768,6 +4822,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
*/
case BPF_FUNC_get_current_uid_gid:
return &bpf_get_current_uid_gid_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -4790,6 +4846,10 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
default:
return NULL;
}
+ case BPF_FUNC_get_socket_cookie:
+ return &bpf_get_socket_cookie_sock_addr_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -4813,6 +4873,17 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
}
static const struct bpf_func_proto *
+cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ switch (func_id) {
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
+ default:
+ return sk_filter_func_proto(func_id, prog);
+ }
+}
+
+static const struct bpf_func_proto *
tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
@@ -4932,6 +5003,10 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sock_map_update_proto;
case BPF_FUNC_sock_hash_update:
return &bpf_sock_hash_update_proto;
+ case BPF_FUNC_get_socket_cookie:
+ return &bpf_get_socket_cookie_sock_ops_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -4951,6 +5026,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_msg_cork_bytes_proto;
case BPF_FUNC_msg_pull_data:
return &bpf_msg_pull_data_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -4978,6 +5055,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sk_redirect_map_proto;
case BPF_FUNC_sk_redirect_hash:
return &bpf_sk_redirect_hash_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -6782,7 +6861,7 @@ const struct bpf_prog_ops xdp_prog_ops = {
};
const struct bpf_verifier_ops cg_skb_verifier_ops = {
- .get_func_proto = sk_filter_func_proto,
+ .get_func_proto = cg_skb_func_proto,
.is_valid_access = sk_filter_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
};
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 08a5184f4b34..ce9eeeb7c024 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -154,7 +154,9 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
!dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ENC_PORTS) &&
!dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_ENC_IP))
+ FLOW_DISSECTOR_KEY_ENC_IP) &&
+ !dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_OPTS))
return;
info = skb_tunnel_info(skb);
@@ -224,6 +226,21 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
ip->tos = key->tos;
ip->ttl = key->ttl;
}
+
+ if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) {
+ struct flow_dissector_key_enc_opts *enc_opt;
+
+ enc_opt = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_ENC_OPTS,
+ target_container);
+
+ if (info->options_len) {
+ enc_opt->len = info->options_len;
+ ip_tunnel_info_opts_get(enc_opt->data, info);
+ enc_opt->dst_opt_type = info->key.tun_flags &
+ TUNNEL_OPTIONS_PRESENT;
+ }
+ }
}
EXPORT_SYMBOL(skb_flow_dissect_tunnel_info);
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index e45098593dc0..3e85437f7106 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -50,10 +50,8 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
* mixing with BH RCU lock doesn't work.
*/
preempt_disable();
- rcu_read_lock();
bpf_compute_data_pointers(skb);
ret = bpf_prog_run_save_cb(lwt->prog, skb);
- rcu_read_unlock();
switch (ret) {
case BPF_OK:
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 00e138a44cbb..820cebe0c687 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1113,7 +1113,7 @@ route_lookup:
dst = NULL;
goto tx_err_link_failure;
}
- if (t->parms.collect_md &&
+ if (t->parms.collect_md && ipv6_addr_any(&fl6->saddr) &&
ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
&fl6->daddr, 0, &fl6->saddr))
goto tx_err_link_failure;
@@ -1255,6 +1255,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
key = &tun_info->key;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_IPIP;
+ fl6.saddr = key->u.ipv6.src;
fl6.daddr = key->u.ipv6.dst;
fl6.flowlabel = key->label;
dsfield = key->tos;
@@ -1326,6 +1327,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
key = &tun_info->key;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_IPV6;
+ fl6.saddr = key->u.ipv6.src;
fl6.daddr = key->u.ipv6.dst;
fl6.flowlabel = key->label;
dsfield = key->tos;
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index e1025b493a18..60325dbfe88b 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -459,36 +459,57 @@ drop:
DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states);
+bool seg6_bpf_has_valid_srh(struct sk_buff *skb)
+{
+ struct seg6_bpf_srh_state *srh_state =
+ this_cpu_ptr(&seg6_bpf_srh_states);
+ struct ipv6_sr_hdr *srh = srh_state->srh;
+
+ if (unlikely(srh == NULL))
+ return false;
+
+ if (unlikely(!srh_state->valid)) {
+ if ((srh_state->hdrlen & 7) != 0)
+ return false;
+
+ srh->hdrlen = (u8)(srh_state->hdrlen >> 3);
+ if (!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3))
+ return false;
+
+ srh_state->valid = true;
+ }
+
+ return true;
+}
+
static int input_action_end_bpf(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
struct seg6_bpf_srh_state *srh_state =
this_cpu_ptr(&seg6_bpf_srh_states);
- struct seg6_bpf_srh_state local_srh_state;
struct ipv6_sr_hdr *srh;
- int srhoff = 0;
int ret;
srh = get_and_validate_srh(skb);
- if (!srh)
- goto drop;
+ if (!srh) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
/* preempt_disable is needed to protect the per-CPU buffer srh_state,
* which is also accessed by the bpf_lwt_seg6_* helpers
*/
preempt_disable();
+ srh_state->srh = srh;
srh_state->hdrlen = srh->hdrlen << 3;
- srh_state->valid = 1;
+ srh_state->valid = true;
rcu_read_lock();
bpf_compute_data_pointers(skb);
ret = bpf_prog_run_save_cb(slwt->bpf.prog, skb);
rcu_read_unlock();
- local_srh_state = *srh_state;
- preempt_enable();
-
switch (ret) {
case BPF_OK:
case BPF_REDIRECT:
@@ -500,24 +521,17 @@ static int input_action_end_bpf(struct sk_buff *skb,
goto drop;
}
- if (unlikely((local_srh_state.hdrlen & 7) != 0))
- goto drop;
-
- if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
- goto drop;
- srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
- srh->hdrlen = (u8)(local_srh_state.hdrlen >> 3);
-
- if (!local_srh_state.valid &&
- unlikely(!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3)))
+ if (srh_state->srh && !seg6_bpf_has_valid_srh(skb))
goto drop;
+ preempt_enable();
if (ret != BPF_REDIRECT)
seg6_lookup_nexthop(skb, NULL, 0);
return dst_input(skb);
drop:
+ preempt_enable();
kfree_skb(skb);
return -EINVAL;
}
diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c
index d152e48ea371..8596eed6d9a8 100644
--- a/net/rds/ib_frmr.c
+++ b/net/rds/ib_frmr.c
@@ -61,6 +61,7 @@ static struct rds_ib_mr *rds_ib_alloc_frmr(struct rds_ib_device *rds_ibdev,
pool->fmr_attr.max_pages);
if (IS_ERR(frmr->mr)) {
pr_warn("RDS/IB: %s failed to allocate MR", __func__);
+ err = PTR_ERR(frmr->mr);
goto out_no_cigar;
}
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index a3b69bb6f4b0..6fd9bdd93796 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -24,6 +24,7 @@
#include <net/pkt_cls.h>
#include <net/ip.h>
#include <net/flow_dissector.h>
+#include <net/geneve.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
@@ -53,6 +54,7 @@ struct fl_flow_key {
struct flow_dissector_key_tcp tcp;
struct flow_dissector_key_ip ip;
struct flow_dissector_key_ip enc_ip;
+ struct flow_dissector_key_enc_opts enc_opts;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
struct fl_flow_mask_range {
@@ -482,6 +484,21 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
[TCA_FLOWER_KEY_ENC_IP_TOS_MASK] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_ENC_IP_TTL] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ENC_OPTS] = { .type = NLA_NESTED },
+ [TCA_FLOWER_KEY_ENC_OPTS_MASK] = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy
+enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = {
+ [TCA_FLOWER_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy
+geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = {
+ [TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY,
+ .len = 128 },
};
static void fl_set_key_val(struct nlattr **tb,
@@ -603,6 +620,145 @@ static void fl_set_key_ip(struct nlattr **tb, bool encap,
fl_set_key_val(tb, &key->ttl, ttl_key, &mask->ttl, ttl_mask, sizeof(key->ttl));
}
+static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key,
+ int depth, int option_len,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1];
+ struct nlattr *class = NULL, *type = NULL, *data = NULL;
+ struct geneve_opt *opt;
+ int err, data_len = 0;
+
+ if (option_len > sizeof(struct geneve_opt))
+ data_len = option_len - sizeof(struct geneve_opt);
+
+ opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len];
+ memset(opt, 0xff, option_len);
+ opt->length = data_len / 4;
+ opt->r1 = 0;
+ opt->r2 = 0;
+ opt->r3 = 0;
+
+ /* If no mask has been prodived we assume an exact match. */
+ if (!depth)
+ return sizeof(struct geneve_opt) + data_len;
+
+ if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_GENEVE) {
+ NL_SET_ERR_MSG(extack, "Non-geneve option type for mask");
+ return -EINVAL;
+ }
+
+ err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+ nla, geneve_opt_policy, extack);
+ if (err < 0)
+ return err;
+
+ /* We are not allowed to omit any of CLASS, TYPE or DATA
+ * fields from the key.
+ */
+ if (!option_len &&
+ (!tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS] ||
+ !tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE] ||
+ !tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA])) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data");
+ return -EINVAL;
+ }
+
+ /* Omitting any of CLASS, TYPE or DATA fields is allowed
+ * for the mask.
+ */
+ if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA]) {
+ int new_len = key->enc_opts.len;
+
+ data = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA];
+ data_len = nla_len(data);
+ if (data_len < 4) {
+ NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long");
+ return -ERANGE;
+ }
+ if (data_len % 4) {
+ NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long");
+ return -ERANGE;
+ }
+
+ new_len += sizeof(struct geneve_opt) + data_len;
+ BUILD_BUG_ON(FLOW_DIS_TUN_OPTS_MAX != IP_TUNNEL_OPTS_MAX);
+ if (new_len > FLOW_DIS_TUN_OPTS_MAX) {
+ NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size");
+ return -ERANGE;
+ }
+ opt->length = data_len / 4;
+ memcpy(opt->opt_data, nla_data(data), data_len);
+ }
+
+ if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS]) {
+ class = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS];
+ opt->opt_class = nla_get_be16(class);
+ }
+
+ if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE]) {
+ type = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE];
+ opt->type = nla_get_u8(type);
+ }
+
+ return sizeof(struct geneve_opt) + data_len;
+}
+
+static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
+ struct fl_flow_key *mask,
+ struct netlink_ext_ack *extack)
+{
+ const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL;
+ int option_len, key_depth, msk_depth = 0;
+
+ nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]);
+
+ if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) {
+ nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
+ msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
+ }
+
+ nla_for_each_attr(nla_opt_key, nla_enc_key,
+ nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS]), key_depth) {
+ switch (nla_type(nla_opt_key)) {
+ case TCA_FLOWER_KEY_ENC_OPTS_GENEVE:
+ option_len = 0;
+ key->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT;
+ option_len = fl_set_geneve_opt(nla_opt_key, key,
+ key_depth, option_len,
+ extack);
+ if (option_len < 0)
+ return option_len;
+
+ key->enc_opts.len += option_len;
+ /* At the same time we need to parse through the mask
+ * in order to verify exact and mask attribute lengths.
+ */
+ mask->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT;
+ option_len = fl_set_geneve_opt(nla_opt_msk, mask,
+ msk_depth, option_len,
+ extack);
+ if (option_len < 0)
+ return option_len;
+
+ mask->enc_opts.len += option_len;
+ if (key->enc_opts.len != mask->enc_opts.len) {
+ NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
+ return -EINVAL;
+ }
+
+ if (msk_depth)
+ nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
+ break;
+ default:
+ NL_SET_ERR_MSG(extack, "Unknown tunnel option type");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int fl_set_key(struct net *net, struct nlattr **tb,
struct fl_flow_key *key, struct fl_flow_key *mask,
struct netlink_ext_ack *extack)
@@ -799,6 +955,12 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
fl_set_key_ip(tb, true, &key->enc_ip, &mask->enc_ip);
+ if (tb[TCA_FLOWER_KEY_ENC_OPTS]) {
+ ret = fl_set_enc_opt(tb, key, mask, extack);
+ if (ret)
+ return ret;
+ }
+
if (tb[TCA_FLOWER_KEY_FLAGS])
ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags);
@@ -894,6 +1056,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_IP, enc_ip);
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_ENC_OPTS, enc_opts);
skb_flow_dissector_init(dissector, keys, cnt);
}
@@ -1174,8 +1338,8 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY;
cls_flower.cookie = (unsigned long)f;
cls_flower.dissector = &mask->dissector;
- cls_flower.mask = &f->mkey;
- cls_flower.key = &f->key;
+ cls_flower.mask = &mask->key;
+ cls_flower.key = &f->mkey;
cls_flower.exts = &f->exts;
cls_flower.classid = f->res.classid;
@@ -1414,6 +1578,83 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask)
return nla_put(skb, TCA_FLOWER_KEY_FLAGS_MASK, 4, &_mask);
}
+static int fl_dump_key_geneve_opt(struct sk_buff *skb,
+ struct flow_dissector_key_enc_opts *enc_opts)
+{
+ struct geneve_opt *opt;
+ struct nlattr *nest;
+ int opt_off = 0;
+
+ nest = nla_nest_start(skb, TCA_FLOWER_KEY_ENC_OPTS_GENEVE);
+ if (!nest)
+ goto nla_put_failure;
+
+ while (enc_opts->len > opt_off) {
+ opt = (struct geneve_opt *)&enc_opts->data[opt_off];
+
+ if (nla_put_be16(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS,
+ opt->opt_class))
+ goto nla_put_failure;
+ if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE,
+ opt->type))
+ goto nla_put_failure;
+ if (nla_put(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA,
+ opt->length * 4, opt->opt_data))
+ goto nla_put_failure;
+
+ opt_off += sizeof(struct geneve_opt) + opt->length * 4;
+ }
+ nla_nest_end(skb, nest);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -EMSGSIZE;
+}
+
+static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
+ struct flow_dissector_key_enc_opts *enc_opts)
+{
+ struct nlattr *nest;
+ int err;
+
+ if (!enc_opts->len)
+ return 0;
+
+ nest = nla_nest_start(skb, enc_opt_type);
+ if (!nest)
+ goto nla_put_failure;
+
+ switch (enc_opts->dst_opt_type) {
+ case TUNNEL_GENEVE_OPT:
+ err = fl_dump_key_geneve_opt(skb, enc_opts);
+ if (err)
+ goto nla_put_failure;
+ break;
+ default:
+ goto nla_put_failure;
+ }
+ nla_nest_end(skb, nest);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -EMSGSIZE;
+}
+
+static int fl_dump_key_enc_opt(struct sk_buff *skb,
+ struct flow_dissector_key_enc_opts *key_opts,
+ struct flow_dissector_key_enc_opts *msk_opts)
+{
+ int err;
+
+ err = fl_dump_key_options(skb, TCA_FLOWER_KEY_ENC_OPTS, key_opts);
+ if (err)
+ return err;
+
+ return fl_dump_key_options(skb, TCA_FLOWER_KEY_ENC_OPTS_MASK, msk_opts);
+}
+
static int fl_dump_key(struct sk_buff *skb, struct net *net,
struct fl_flow_key *key, struct fl_flow_key *mask)
{
@@ -1594,7 +1835,8 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
&mask->enc_tp.dst,
TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
sizeof(key->enc_tp.dst)) ||
- fl_dump_key_ip(skb, true, &key->enc_ip, &mask->enc_ip))
+ fl_dump_key_ip(skb, true, &key->enc_ip, &mask->enc_ip) ||
+ fl_dump_key_enc_opt(skb, &key->enc_opts, &mask->enc_opts))
goto nla_put_failure;
if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
generated by cgit (git 2.34.1) at 2025-09-24 22:43:14 +0000