netfilter: nftables_offload: set address type in control dissector
Subsystems (2)
Pablo Neira Ayuso
maintainerPATCH v2 1/2 netfilter: nftables_offload: set address type in control dissector
This patch adds nft_flow_rule_set_addr_type() to set the address type from the nft_payload expression accordingly.
If the address type is not set in the control dissector then a rule that matches either source or destination IP address does not work.
After this patch, nft hardware offload generates the flow dissector configuration as tc-flower to match on an IP address.
This patch has been also tested functionally to make sure packets are filtered out by the NIC.
This is also getting the code aligned with the existing netfilter flow offload infrastructure which is also setting the control dissector.
---
v2: add a nice patch description and remove unnecessary EXPORT_SYMBOL()
per Jakub Kicinski.
include/net/netfilter/nf_tables_offload.h | 4 ++++ net/netfilter/nf_tables_offload.c | 17 +++++++++++++++++ net/netfilter/nft_payload.c | 4 ++++ 3 files changed, 25 insertions(+)
include/net/netfilter/nf_tables_offload.h +4 -0
@@ -37,6 +37,7 @@ void nft_offload_update_dependency(struct nft_offload_ctx *ctx,struct nft_flow_key {struct flow_dissector_key_basic basic; +struct flow_dissector_key_control control;union {struct flow_dissector_key_ipv4_addrs ipv4;struct flow_dissector_key_ipv6_addrs ipv6;
@@ -62,6 +63,9 @@ struct nft_flow_rule {#define NFT_OFFLOAD_F_ACTION (1 << 0) +void nft_flow_rule_set_addr_type (struct nft_flow_rule *flow, +enum flow_dissector_key_id addr_type); +struct nft_rule ;struct nft_flow_rule *nft_flow_rule_create (struct net *net,const struct nft_rule *rule);void nft_flow_rule_destroy (struct nft_flow_rule *flow);
net/netfilter/nf_tables_offload.c +17 -0
@@ -28,6 +28,23 @@ static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions)return flow; } +void nft_flow_rule_set_addr_type (struct nft_flow_rule *flow, +enum flow_dissector_key_id addr_type) +{ +struct nft_flow_match *match = &flow->match; +struct nft_flow_key *mask = &match->mask; +struct nft_flow_key *key = &match->key; + +if (match->dissector.used_keys &BIT (FLOW_DISSECTOR_KEY_CONTROL )) +return ; + + key->control.addr_type = addr_type; + mask->control.addr_type =0xffff ; + match->dissector.used_keys |=BIT (FLOW_DISSECTOR_KEY_CONTROL ); + match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL ] = + offsetof(struct nft_flow_key , control); +} +struct nft_flow_rule *nft_flow_rule_create (struct net *net,const struct nft_rule *rule) {
net/netfilter/nft_payload.c +4 -0
@@ -244,6 +244,7 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV4_ADDRS , ipv4, src,sizeof (struct in_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV4_ADDRS );break ;case offsetof(struct iphdr , daddr):if (priv->len !=sizeof (struct in_addr ))
@@ -251,6 +252,7 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV4_ADDRS , ipv4, dst,sizeof (struct in_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV4_ADDRS );break ;case offsetof(struct iphdr , protocol):if (priv->len !=sizeof (__u8))
@@ -280,6 +282,7 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV6_ADDRS , ipv6, src,sizeof (struct in6_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV6_ADDRS );break ;case offsetof(struct ipv6hdr , daddr):if (priv->len !=sizeof (struct in6_addr ))
@@ -287,6 +290,7 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV6_ADDRS , ipv6, dst,sizeof (struct in6_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV6_ADDRS );break ;case offsetof(struct ipv6hdr , nexthdr):if (priv->len !=sizeof (__u8))
Signature · 1 line
2.20.1
Pablo Neira Ayuso
maintainerPATCH v2 2/2 netfilter: nftables_offload: build mask based from the matching bytes
Userspace might match on prefix bytes of header fields if they are on the byte boundary, this requires that the mask is adjusted accordingly. Use NFT_OFFLOAD_MATCH_EXACT() for meta since prefix byte matching is not allowed for this type of selector.
The bitwise expression might be optimized out by userspace, hence the kernel need to infer the prefix from the number of payload bytes to match on. This patch adds nft_payload_offload_mask() to calculate the bitmask to match on the prefix.
---
v2: make a nice commit description as well for this.
include/net/netfilter/nf_tables_offload.h | 3 ++ net/netfilter/nft_cmp.c | 8 +-- net/netfilter/nft_meta.c | 16 +++--- net/netfilter/nft_payload.c | 66 +++++++++++++++++------ 4 files changed, 64 insertions(+), 29 deletions(-)
include/net/netfilter/nf_tables_offload.h +3 -0
@@ -78,6 +78,9 @@ int nft_flow_rule_offload_commit(struct net *net); offsetof(struct nft_flow_key, __base.__field); \ (__reg)->len = __len; \ (__reg)->key = __key; \ + +#define NFT_OFFLOAD_MATCH_EXACT (__key, __base, __field, __len, __reg) \ + NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \ memset(&(__reg)->mask, 0xff, (__reg)->len);int nft_chain_offload_priority (struct nft_base_chain *basechain);
net/netfilter/nft_cmp.c +4 -4
@@ -123,11 +123,11 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx,u8 *mask = (u8 *)&flow->match.mask;u8 *key = (u8 *)&flow->match.key; -if (priv->op !=NFT_CMP_EQ || reg->len != priv->len) +if (priv->op !=NFT_CMP_EQ || priv->len > reg->len)return -EOPNOTSUPP ; -memcpy (key + reg->offset, &priv->data, priv->len); -memcpy (mask + reg->offset, ®->mask, priv->len); +memcpy (key + reg->offset, &priv->data, reg->len); +memcpy (mask + reg->offset, ®->mask, reg->len); flow->match.dissector.used_keys |=BIT (reg->key); flow->match.dissector.offset[reg->key] = reg->base_offset;
@@ -137,7 +137,7 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx, nft_reg_load16(priv->data.data) != ARPHRD_ETHER) return -EOPNOTSUPP; -nft_offload_update_dependency (ctx, &priv->data, priv->len); +nft_offload_update_dependency (ctx, &priv->data, reg->len);return 0 ; }
net/netfilter/nft_meta.c +8 -8
@@ -724,22 +724,22 @@ static int nft_meta_get_offload(struct nft_offload_ctx *ctx,switch (priv->key) {case NFT_META_PROTOCOL : -NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_BASIC , basic, n_proto, -sizeof (__u16), reg); +NFT_OFFLOAD_MATCH_EXACT (FLOW_DISSECTOR_KEY_BASIC , basic, n_proto, +sizeof (__u16), reg);nft_offload_set_dependency (ctx,NFT_OFFLOAD_DEP_NETWORK );break ;case NFT_META_L4PROTO : -NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_BASIC , basic, ip_proto, -sizeof (__u8), reg); +NFT_OFFLOAD_MATCH_EXACT (FLOW_DISSECTOR_KEY_BASIC , basic, ip_proto, +sizeof (__u8), reg);nft_offload_set_dependency (ctx,NFT_OFFLOAD_DEP_TRANSPORT );break ;case NFT_META_IIF : -NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_META , meta, - ingress_ifindex,sizeof (__u32), reg); +NFT_OFFLOAD_MATCH_EXACT (FLOW_DISSECTOR_KEY_META , meta, + ingress_ifindex,sizeof (__u32), reg);break ;case NFT_META_IIFTYPE : -NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_META , meta, - ingress_iftype,sizeof (__u16), reg); +NFT_OFFLOAD_MATCH_EXACT (FLOW_DISSECTOR_KEY_META , meta, + ingress_iftype,sizeof (__u16), reg);break ;default :return -EOPNOTSUPP ;
net/netfilter/nft_payload.c +49 -17
174 lines not on this page · raw message
Signature · 1 line
2.20.1
Jakub Kicinski
maintainerQuoted 105 lines · On Thu, 26 Nov 2020 00:04:45 +0100 Pablo Neira Ayuso wrote:
This patch adds
nft_flow_rule_set_addr_type()to set the address type from thenft_payloadexpression accordingly.If the address type is not set in the control dissector then a rule that matches either source or destination IP address does not work.
After this patch, nft hardware offload generates the flow dissector configuration as tc-flower to match on an IP address.
This patch has been also tested functionally to make sure packets are filtered out by the NIC.
This is also getting the code aligned with the existing netfilter flow offload infrastructure which is also setting the control dissector.
Fixes c9626a2cbdb2 ("netfilter: nf_tables: add hardware offload support")Signed-off-by Pablo Neira Ayuso <[email protected]>---
v2: add a nice patch description and remove unnecessaryEXPORT_SYMBOL()
per Jakub Kicinski.include/net/netfilter/nf_tables_offload.h | 4 ++++ net/netfilter/nf_tables_offload.c | 17 +++++++++++++++++ net/netfilter/nft_payload.c | 4 ++++ 3 files changed, 25 insertions(+)include/net/netfilter/nf_tables_offload.h +4
-0@@ -37,6 +37,7 @@ void nft_offload_update_dependency(struct nft_offload_ctx *ctx,struct nft_flow_key {struct flow_dissector_key_basic basic; +struct flow_dissector_key_control control;union {struct flow_dissector_key_ipv4_addrs ipv4;struct flow_dissector_key_ipv6_addrs ipv6;@@ -62,6 +63,9 @@ struct nft_flow_rule {#define NFT_OFFLOAD_F_ACTION (1 << 0) +void nft_flow_rule_set_addr_type (struct nft_flow_rule *flow, +enum flow_dissector_key_id addr_type); +struct nft_rule ;struct nft_flow_rule *nft_flow_rule_create (struct net *net,const struct nft_rule *rule);void nft_flow_rule_destroy (struct nft_flow_rule *flow);net/netfilter/nf_tables_offload.c +17
-0@@ -28,6 +28,23 @@ static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions)return flow; } +void nft_flow_rule_set_addr_type (struct nft_flow_rule *flow, +enum flow_dissector_key_id addr_type) +{ +struct nft_flow_match *match = &flow->match; +struct nft_flow_key *mask = &match->mask; +struct nft_flow_key *key = &match->key; + +if (match->dissector.used_keys &BIT (FLOW_DISSECTOR_KEY_CONTROL )) +return ; + + key->control.addr_type = addr_type; + mask->control.addr_type =0xffff ; + match->dissector.used_keys |=BIT (FLOW_DISSECTOR_KEY_CONTROL ); + match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL ] = + offsetof(struct nft_flow_key , control); +} +struct nft_flow_rule *nft_flow_rule_create (struct net *net,const struct nft_rule *rule) {net/netfilter/nft_payload.c +3
-0@@ -244,6 +244,7 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV4_ADDRS , ipv4, src,sizeof (struct in_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV4_ADDRS );break ;case offsetof(struct iphdr , daddr):if (priv->len !=sizeof (struct in_addr ))@@ -251,6 +252,7 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV4_ADDRS , ipv4, dst,sizeof (struct in_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV4_ADDRS );break ;case offsetof(struct iphdr , protocol):if (priv->len !=sizeof (__u8))@@ -280,6 +282,7 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV6_ADDRS , ipv6, src,sizeof (struct in6_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV6_ADDRS );break ;case offsetof(struct ipv6hdr , daddr):if (priv->len !=sizeof (struct in6_addr ))
net/netfilter/nft_payload.c static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx, · line 296
Quoted 7 lines
net/netfilter/nft_payload.c +1
-0@@ -287,6 +290,7 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV6_ADDRS , ipv6, dst,sizeof (struct in6_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV6_ADDRS );break ;case offsetof(struct ipv6hdr , nexthdr):if (priv->len !=sizeof (__u8))
Still worries me this is done in a response to a match.
skb_flow_dissector_init() has a straight up BUG_ON() if the dissector did not set the CONTROL or BASIC. It says in the comment that both must be initialized. But nft does not call skb_flow_dissector_init()?
Are you 100% sure all cases will set CONTROL and BASIC now?
Pablo Neira Ayuso
maintainerHi Jakub,
Quoted 116 lines · Jakub Kicinski
Quoted 105 lines · On Thu, 26 Nov 2020 00:04:45 +0100 Pablo Neira Ayuso wrote:
This patch adds
nft_flow_rule_set_addr_type()to set the address type from thenft_payloadexpression accordingly.If the address type is not set in the control dissector then a rule that matches either source or destination IP address does not work.
After this patch, nft hardware offload generates the flow dissector configuration as tc-flower to match on an IP address.
This patch has been also tested functionally to make sure packets are filtered out by the NIC.
This is also getting the code aligned with the existing netfilter flow offload infrastructure which is also setting the control dissector.
Fixes c9626a2cbdb2 ("netfilter: nf_tables: add hardware offload support")Signed-off-by Pablo Neira Ayuso <[email protected]>---
v2: add a nice patch description and remove unnecessaryEXPORT_SYMBOL()
per Jakub Kicinski.include/net/netfilter/nf_tables_offload.h | 4 ++++ net/netfilter/nf_tables_offload.c | 17 +++++++++++++++++ net/netfilter/nft_payload.c | 4 ++++ 3 files changed, 25 insertions(+)include/net/netfilter/nf_tables_offload.h +4
-0@@ -37,6 +37,7 @@ void nft_offload_update_dependency(struct nft_offload_ctx *ctx,struct nft_flow_key {struct flow_dissector_key_basic basic; +struct flow_dissector_key_control control;union {struct flow_dissector_key_ipv4_addrs ipv4;struct flow_dissector_key_ipv6_addrs ipv6;@@ -62,6 +63,9 @@ struct nft_flow_rule {#define NFT_OFFLOAD_F_ACTION (1 << 0) +void nft_flow_rule_set_addr_type (struct nft_flow_rule *flow, +enum flow_dissector_key_id addr_type); +struct nft_rule ;struct nft_flow_rule *nft_flow_rule_create (struct net *net,const struct nft_rule *rule);void nft_flow_rule_destroy (struct nft_flow_rule *flow);net/netfilter/nf_tables_offload.c +17
-0@@ -28,6 +28,23 @@ static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions)return flow; } +void nft_flow_rule_set_addr_type (struct nft_flow_rule *flow, +enum flow_dissector_key_id addr_type) +{ +struct nft_flow_match *match = &flow->match; +struct nft_flow_key *mask = &match->mask; +struct nft_flow_key *key = &match->key; + +if (match->dissector.used_keys &BIT (FLOW_DISSECTOR_KEY_CONTROL )) +return ; + + key->control.addr_type = addr_type; + mask->control.addr_type =0xffff ; + match->dissector.used_keys |=BIT (FLOW_DISSECTOR_KEY_CONTROL ); + match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL ] = + offsetof(struct nft_flow_key , control); +} +struct nft_flow_rule *nft_flow_rule_create (struct net *net,const struct nft_rule *rule) {net/netfilter/nft_payload.c +3
-0@@ -244,6 +244,7 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV4_ADDRS , ipv4, src,sizeof (struct in_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV4_ADDRS );break ;case offsetof(struct iphdr , daddr):if (priv->len !=sizeof (struct in_addr ))@@ -251,6 +252,7 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV4_ADDRS , ipv4, dst,sizeof (struct in_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV4_ADDRS );break ;case offsetof(struct iphdr , protocol):if (priv->len !=sizeof (__u8))@@ -280,6 +282,7 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV6_ADDRS , ipv6, src,sizeof (struct in6_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV6_ADDRS );break ;case offsetof(struct ipv6hdr , daddr):if (priv->len !=sizeof (struct in6_addr ))net/netfilter/nft_payload.c static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx, · line 296
Quoted 7 lines
net/netfilter/nft_payload.c +1
-0@@ -287,6 +290,7 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx,NFT_OFFLOAD_MATCH (FLOW_DISSECTOR_KEY_IPV6_ADDRS , ipv6, dst,sizeof (struct in6_addr ), reg); +nft_flow_rule_set_addr_type (flow,FLOW_DISSECTOR_KEY_IPV6_ADDRS );break ;case offsetof(struct ipv6hdr , nexthdr):if (priv->len !=sizeof (__u8))Still worries me this is done in a response to a match.
Quoted 5 lines
skb_flow_dissector_init()has a straight upBUG_ON()if the dissector did not set the CONTROL or BASIC. It says in the comment that both must be initialized. But nft does not callskb_flow_dissector_init()?Are you 100% sure all cases will set CONTROL and BASIC now?
Enforcing skb_flow_dissector_init() for software make sense, but in Netfilter this is used for hardware offload only.
All drivers in the tree check for:
if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL))
before accessing struct flow_match_control.
I can set it on inconditionally, but the driver will get a value 0x0 and mask 0x0, which is the same as leaving it unset.
Jakub Kicinski
maintainerQuoted 11 lines · On Thu, 26 Nov 2020 01:44:37 +0100 Pablo Neira Ayuso wrote:
Quoted 7 lines
Still worries me this is done in a response to a match.
skb_flow_dissector_init()has a straight upBUG_ON()if the dissector did not set the CONTROL or BASIC. It says in the comment that both must be initialized. But nft does not callskb_flow_dissector_init()?Are you 100% sure all cases will set CONTROL and BASIC now?
Enforcing
skb_flow_dissector_init()for software make sense, but in Netfilter this is used for hardware offload only.
Quoted 8 lines
All drivers in the tree check for:
if (
flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL))before accessing struct
flow_match_control.I can set it on inconditionally, but the driver will get a value
0x0and mask0x0, which is the same as leaving it unset.
Ack, I didn't realize you don't actually ever use the dissector other than for offload.