flow_offload: update mangle action representation
Subsystems (8)
Pablo Neira Ayuso
maintainerv2 cover flow_offload: update mangle action representation
This patch updates the mangle action representation:
Patch 1) Undo bitwise NOT operation on the mangle mask (coming from tc
pedit userspace).
Patch 2) mangle value &= mask from the front-end side.
Patch 3) adjust offset, length and coalesce consecutive pedit keys into
one single action.
Patch 4) add support for payload mangling for netfilter.
After this patchset:
* Offset to payload does not need to be on the 32-bits boundaries anymore. This patchset adds front-end code to adjust the offset and length coming from the tc pedit representation, so drivers get an exact header field offset and length.
* This new front-end code coalesces consecutive pedit actions into one single action, so drivers can mangle IPv6 and ethernet address fields in one go, instead once for each 32-bit word.
On the driver side, diffstat -t shows that drivers code to deal with payload mangling gets simplified:
INSERTED,DELETED,MODIFIED,FILENAME
46,116,0,drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c (-70 LOC)
12,28,0,drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h (-16 LOC)
30,60,0,drivers/net/ethernet/mellanox/mlx5/core/en_tc.c (-30 LOC)
89,111,0,drivers/net/ethernet/netronome/nfp/flower/action.c (-17 LOC)While, on the front-end side the balance is the following:
123,22,0,net/sched/cls_api.c (+101 LOC)
Changes since v1:
* Fix missing flow_action->num_entries adjustment from tc_setup_flow_action() reported by Vlad Buslov.
* Action entry ID in netfilter payload mangling action was not properly set.
* Fix incorrect p_exact[] assignment logic in nfp_fl_set_helper().
Please, apply.
Pablo Neira Ayuso (4):
net: flow_offload: flip mangle action mask
net: flow_offload: bitwise AND on mangle action value field
net: flow_offload: mangle action at byte level
netfilter: nft_payload: packet mangling offload support
.../net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c | 163 +++++----------- .../net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h | 40 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 90 +++------ drivers/net/ethernet/netronome/nfp/flower/action.c | 204 ++++++++++----------- include/net/flow_offload.h | 7 +- net/netfilter/nft_payload.c | 73 ++++++++ net/sched/cls_api.c | 144 ++++++++++++--- 7 files changed, 382 insertions(+), 339 deletions(-)
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH v2 1/4 net: flow_offload: flip mangle action mask
Userspace tc pedit action performs a bitwise NOT operation on the mask. All of the existing drivers in the tree undo this operation. Prepare the mangle mask in the way the drivers expect from the tc_setup_flow_action() function.
--- drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c | 12 ++++++------ drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 6 +++--- drivers/net/ethernet/netronome/nfp/flower/action.c | 8 ++++---- net/sched/cls_api.c | 2 +- 4 files changed, 14 insertions(+), 14 deletions(-)
drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +6 -6
@@ -275,7 +275,7 @@ static int cxgb4_validate_flow_match(struct net_device *dev,static void offload_pedit (struct ch_filter_specification *fs,u32 val,u32 mask,u8 field) { -u32 set_val = val & ~mask; +u32 set_val = val & mask;u32 offset =0 ;u8 size =1 ;int i;
@@ -301,7 +301,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,offload_pedit (fs, val, mask,ETH_DMAC_31_0 );break ;case PEDIT_ETH_DMAC_47_32_SMAC_15_0 : -if (~mask &PEDIT_ETH_DMAC_MASK ) +if (mask &PEDIT_ETH_DMAC_MASK )offload_pedit (fs, val, mask,ETH_DMAC_47_32 );else offload_pedit(fs, val >> 16, mask >> 16,
@@ -353,7 +353,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,case FLOW_ACT_MANGLE_HDR_TYPE_TCP :switch (offset) {case PEDIT_TCP_SPORT_DPORT : -if (~mask &PEDIT_TCP_UDP_SPORT_MASK ) +if (mask &PEDIT_TCP_UDP_SPORT_MASK )offload_pedit (fs,cpu_to_be32 (val) >>16 ,cpu_to_be32 (mask) >>16 ,TCP_SPORT );
@@ -366,7 +366,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,case FLOW_ACT_MANGLE_HDR_TYPE_UDP :switch (offset) {case PEDIT_UDP_SPORT_DPORT : -if (~mask &PEDIT_TCP_UDP_SPORT_MASK ) +if (mask &PEDIT_TCP_UDP_SPORT_MASK )offload_pedit (fs,cpu_to_be32 (val) >>16 ,cpu_to_be32 (mask) >>16 ,UDP_SPORT );
@@ -510,7 +510,7 @@ static bool valid_pedit_action(struct net_device *dev,case FLOW_ACT_MANGLE_HDR_TYPE_TCP :switch (offset) {case PEDIT_TCP_SPORT_DPORT : -if (!valid_l4_mask (~mask)) { +if (!valid_l4_mask (mask)) {netdev_err (dev,"%s: Unsupported mask for TCP L4 ports\n" , __func__);return false;
@@ -525,7 +525,7 @@ static bool valid_pedit_action(struct net_device *dev,case FLOW_ACT_MANGLE_HDR_TYPE_UDP :switch (offset) {case PEDIT_UDP_SPORT_DPORT : -if (!valid_l4_mask (~mask)) { +if (!valid_l4_mask (mask)) {netdev_err (dev,"%s: Unsupported mask for UDP L4 ports\n" , __func__);return false;
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +3 -3
@@ -2508,7 +2508,7 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, val = act->mangle.val; offset = act->mangle.offset; - err =set_pedit_val (htype, ~mask, val, offset, &hdrs[cmd]); + err =set_pedit_val (htype, mask, val, offset, &hdrs[cmd]);if (err) goto out_err;
@@ -2608,7 +2608,7 @@ static bool is_action_keys_supported(const struct flow_action_entry *act) htype = act->mangle.htype; offset = act->mangle.offset; - mask = ~act->mangle.mask; + mask = act->mangle.mask;/* For IPv4 & IPv6 header check 4 byte word, * to determine that modified fields * are NOT ttl & hop_limit only.
@@ -2732,7 +2732,7 @@ static int add_vlan_rewrite_action(struct mlx5e_priv *priv, int namespace, .id = FLOW_ACTION_MANGLE, .mangle.htype = FLOW_ACT_MANGLE_HDR_TYPE_ETH, .mangle.offset = offsetof(struct vlan_ethhdr, h_vlan_TCI), - .mangle.mask = ~(u32)be16_to_cpu(*(__be16 *)&mask16), + .mangle.mask = (u32)be16_to_cpu(*(__be16 *)&mask16), .mangle.val = (u32)be16_to_cpu(*(__be16 *)&val16), };u8 match_prio_mask, match_prio_val;
drivers/net/ethernet/netronome/nfp/flower/action.c +4 -4
@@ -495,7 +495,7 @@ nfp_fl_set_eth(const struct flow_action_entry *act, u32 off,return -EOPNOTSUPP ; } - mask = ~act->mangle.mask; + mask = act->mangle.mask; exact = act->mangle.val;if (exact & ~mask) {
@@ -532,7 +532,7 @@ nfp_fl_set_ip4(const struct flow_action_entry *act, u32 off,__be32 exact, mask;/* We are expecting tcf_pedit to return a big endian value */ - mask = (__force __be32 )~act->mangle.mask; + mask = (__force __be32 )act->mangle.mask; exact = (__force __be32 )act->mangle.val;if (exact & ~mask) {
@@ -673,7 +673,7 @@ nfp_fl_set_ip6(const struct flow_action_entry *act, u32 off,u8 word;/* We are expecting tcf_pedit to return a big endian value */ - mask = (__force __be32 )~act->mangle.mask; + mask = (__force __be32 )act->mangle.mask; exact = (__force __be32 )act->mangle.val;if (exact & ~mask) {
@@ -713,7 +713,7 @@ nfp_fl_set_tport(const struct flow_action_entry *act, u32 off,return -EOPNOTSUPP ; } - mask = ~act->mangle.mask; + mask = act->mangle.mask; exact = act->mangle.val;if (exact & ~mask) {
net/sched/cls_api.c +1 -1
@@ -3379,7 +3379,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, goto err_out; } entry->mangle.htype =tcf_pedit_htype (act, k); - entry->mangle.mask =tcf_pedit_mask (act, k); + entry->mangle.mask = ~tcf_pedit_mask (act, k); entry->mangle.val =tcf_pedit_val (act, k); entry->mangle.offset =tcf_pedit_offset (act, k); entry = &flow_action->entries[++j];
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH v2 2/4 net: flow_offload: bitwise AND on mangle action value field
In reply to Pablo Neira AyusoDrivers perform a bitwise AND on the value and the mask. Update tc_setup_flow_action() to perform this operation so drivers do not need to do this.
--- drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c | 3 +-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- drivers/net/ethernet/netronome/nfp/flower/action.c | 9 ++++----- net/sched/cls_api.c | 3 ++- 4 files changed, 8 insertions(+), 9 deletions(-)
drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +1 -2
@@ -275,7 +275,6 @@ static int cxgb4_validate_flow_match(struct net_device *dev,static void offload_pedit (struct ch_filter_specification *fs,u32 val,u32 mask,u8 field) { -u32 set_val = val & mask;u32 offset =0 ;u8 size =1 ;int i;
@@ -287,7 +286,7 @@ static void offload_pedit(struct ch_filter_specification *fs, u32 val, u32 mask,break ; } } -memcpy ((u8 *)fs + offset, &set_val, size); +memcpy ((u8 *)fs + offset, &val, size); } static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +1 -1
@@ -2213,7 +2213,7 @@ static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset, goto out_err; *curr_pmask |= mask; - *curr_pval |= (val & mask); + *curr_pval |= val;return 0 ;
drivers/net/ethernet/netronome/nfp/flower/action.c +4 -5
@@ -477,7 +477,6 @@ static void nfp_fl_set_helper32(u32 value, u32 mask, u8 *p_exact, u8 *p_mask)u32 oldvalue =get_unaligned ((u32 *)p_exact);u32 oldmask =get_unaligned ((u32 *)p_mask); - value &= mask; value |= oldvalue & ~mask;put_unaligned (oldmask | mask, (u32 *)p_mask);
@@ -544,7 +543,7 @@ nfp_fl_set_ip4(const struct flow_action_entry *act, u32 off,case offsetof(struct iphdr , daddr): set_ip_addr->ipv4_dst_mask |= mask; set_ip_addr->ipv4_dst &= ~mask; - set_ip_addr->ipv4_dst |= exact & mask; + set_ip_addr->ipv4_dst |= exact; set_ip_addr->head.jump_id =NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS ; set_ip_addr->head.len_lw =sizeof (*set_ip_addr) >>NFP_FL_LW_SIZ ;
@@ -552,7 +551,7 @@ nfp_fl_set_ip4(const struct flow_action_entry *act, u32 off,case offsetof(struct iphdr , saddr): set_ip_addr->ipv4_src_mask |= mask; set_ip_addr->ipv4_src &= ~mask; - set_ip_addr->ipv4_src |= exact & mask; + set_ip_addr->ipv4_src |= exact; set_ip_addr->head.jump_id =NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS ; set_ip_addr->head.len_lw =sizeof (*set_ip_addr) >>NFP_FL_LW_SIZ ;
@@ -606,7 +605,7 @@ nfp_fl_set_ip6_helper(int opcode_tag, u8 word, __be32 exact, __be32 mask, { ip6->ipv6[word].mask |= mask; ip6->ipv6[word].exact &= ~mask; - ip6->ipv6[word].exact |= exact & mask; + ip6->ipv6[word].exact |= exact; ip6->reserved =cpu_to_be16 (0 ); ip6->head.jump_id = opcode_tag;
@@ -651,7 +650,7 @@ nfp_fl_set_ip6_hop_limit_flow_label(u32 off, __be32 exact, __be32 mask, ip_hl_fl->ipv6_label_mask |= mask; ip_hl_fl->ipv6_label &= ~mask; - ip_hl_fl->ipv6_label |= exact & mask; + ip_hl_fl->ipv6_label |= exact;break ; }
net/sched/cls_api.c +2 -1
@@ -3380,7 +3380,8 @@ int tc_setup_flow_action(struct flow_action *flow_action, } entry->mangle.htype =tcf_pedit_htype (act, k); entry->mangle.mask = ~tcf_pedit_mask (act, k); - entry->mangle.val =tcf_pedit_val (act, k); + entry->mangle.val =tcf_pedit_val (act, k) & + entry->mangle.mask; entry->mangle.offset =tcf_pedit_offset (act, k); entry = &flow_action->entries[++j]; }
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH v2 3/4 net: flow_offload: mangle action at byte level
In reply to Pablo Neira AyusoThe flow mangle action is originally modeled after the tc pedit action, this has a number of shortcomings:
1) The tc pedit offset must be set on the 32-bits boundaries. Many protocol header field offsets are not aligned to 32-bits, eg. port destination, port source and ethernet destination. This patch adjusts the offset accordingly and trim off length in these case, so drivers get an exact offset and length to the header fields.
2) The maximum mangle length is one word of 32-bits, hence you need to up to four actions to mangle an IPv6 address. This patch coalesces consecutive tc pedit actions into one single action so drivers can configure the IPv6 mangling in one go. Ethernet address fields now require one single action instead of two too.
The following drivers have been updated accordingly to use this new mangle action layout:
1) The cxgb4 driver does not need to split protocol field matching larger than one 32-bit words into multiple definitions. Instead one single definition per protocol field is enough. Checking for transport protocol ports is also simplified.
2) The mlx5 driver logic to disallow IPv4 ttl and IPv6 hoplimit fields becomes more simple too.
3) The nfp driver uses the nfp_fl_set_helper() function to configure the payload mangling. The memchr_inv() function is used to check for proper initialization of the value and mask. The driver has been updated to refer to the exact protocol header offsets too.
As a result, this patch reduces code complexity on the driver side at the cost of adding ~100 LOC at the core to perform offset and length adjustment; and to coalesce consecutive actions.
--- .../net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c | 162 +++++----------- .../net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h | 40 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 90 +++------ drivers/net/ethernet/netronome/nfp/flower/action.c | 203 ++++++++++----------- include/net/flow_offload.h | 7 +- net/sched/cls_api.c | 145 ++++++++++++--- 6 files changed, 309 insertions(+), 338 deletions(-)
drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +46 -116
@@ -44,20 +44,12 @@#define STATS_CHECK_PERIOD (HZ / 2)static struct ch_tc_pedit_fields pedits[] = { -PEDIT_FIELDS (ETH_ ,DMAC_31_0 ,4 , dmac,0 ), -PEDIT_FIELDS (ETH_ ,DMAC_47_32 ,2 , dmac,4 ), -PEDIT_FIELDS (ETH_ ,SMAC_15_0 ,2 , smac,0 ), -PEDIT_FIELDS (ETH_ ,SMAC_47_16 ,4 , smac,2 ), +PEDIT_FIELDS (ETH_ ,DMAC ,6 , dmac,0 ), +PEDIT_FIELDS (ETH_ ,SMAC ,6 , smac,0 ),PEDIT_FIELDS (IP4_ ,SRC ,4 , nat_fip,0 ),PEDIT_FIELDS (IP4_ ,DST ,4 , nat_lip,0 ), -PEDIT_FIELDS (IP6_ ,SRC_31_0 ,4 , nat_fip,0 ), -PEDIT_FIELDS (IP6_ ,SRC_63_32 ,4 , nat_fip,4 ), -PEDIT_FIELDS (IP6_ ,SRC_95_64 ,4 , nat_fip,8 ), -PEDIT_FIELDS (IP6_ ,SRC_127_96 ,4 , nat_fip,12 ), -PEDIT_FIELDS (IP6_ ,DST_31_0 ,4 , nat_lip,0 ), -PEDIT_FIELDS (IP6_ ,DST_63_32 ,4 , nat_lip,4 ), -PEDIT_FIELDS (IP6_ ,DST_95_64 ,4 , nat_lip,8 ), -PEDIT_FIELDS (IP6_ ,DST_127_96 ,4 , nat_lip,12 ), +PEDIT_FIELDS (IP6_ ,SRC ,16 , nat_fip,0 ), +PEDIT_FIELDS (IP6_ ,DST ,16 , nat_lip,0 ),PEDIT_FIELDS (TCP_ ,SPORT ,2 , nat_fport,0 ),PEDIT_FIELDS (TCP_ ,DPORT ,2 , nat_lport,0 ),PEDIT_FIELDS (UDP_ ,SPORT ,2 , nat_fport,0 ),
@@ -272,8 +264,8 @@ static int cxgb4_validate_flow_match(struct net_device *dev,return 0 ; } -static void offload_pedit (struct ch_filter_specification *fs,u32 val,u32 mask, -u8 field) +static void offload_pedit (struct ch_filter_specification *fs, +struct flow_action_entry *act,u8 field) {u32 offset =0 ;u8 size =1 ;
@@ -286,92 +278,68 @@ static void offload_pedit(struct ch_filter_specification *fs, u32 val, u32 mask,break ; } } -memcpy ((u8 *)fs + offset, &val, size); +memcpy ((u8 *)fs + offset, act->mangle.val, size); } -static void process_pedit_field (struct ch_filter_specification *fs,u32 val, -u32 mask,u32 offset,u8 htype) +static void process_pedit_field (struct ch_filter_specification *fs, +struct flow_action_entry *act) { +u32 offset = act->mangle.offset; +u8 htype = act->mangle.htype; +switch (htype) {case FLOW_ACT_MANGLE_HDR_TYPE_ETH :switch (offset) { -case PEDIT_ETH_DMAC_31_0 : +case PEDIT_ETH_DMAC : fs->newdmac =1 ; -offload_pedit (fs, val, mask,ETH_DMAC_31_0 ); -break ; -case PEDIT_ETH_DMAC_47_32_SMAC_15_0 : -if (mask &PEDIT_ETH_DMAC_MASK ) -offload_pedit (fs, val, mask,ETH_DMAC_47_32 ); -else -offload_pedit (fs, val >>16 , mask >>16 , -ETH_SMAC_15_0 ); +offload_pedit (fs, act,ETH_DMAC );break ; -case PEDIT_ETH_SMAC_47_16 : +case PEDIT_ETH_SMAC : fs->newsmac =1 ; -offload_pedit (fs, val, mask,ETH_SMAC_47_16 ); +offload_pedit (fs, act,ETH_SMAC ); +break ; }break ;case FLOW_ACT_MANGLE_HDR_TYPE_IP4 :switch (offset) {case PEDIT_IP4_SRC : -offload_pedit (fs, val, mask,IP4_SRC ); +offload_pedit (fs, act,IP4_SRC );break ;case PEDIT_IP4_DST : -offload_pedit (fs, val, mask,IP4_DST ); +offload_pedit (fs, act,IP4_DST ); } fs->nat_mode =NAT_MODE_ALL ;break ;case FLOW_ACT_MANGLE_HDR_TYPE_IP6 :switch (offset) { -case PEDIT_IP6_SRC_31_0 : -offload_pedit (fs, val, mask,IP6_SRC_31_0 ); -break ; -case PEDIT_IP6_SRC_63_32 : -offload_pedit (fs, val, mask,IP6_SRC_63_32 ); -break ; -case PEDIT_IP6_SRC_95_64 : -offload_pedit (fs, val, mask,IP6_SRC_95_64 ); -break ; -case PEDIT_IP6_SRC_127_96 : -offload_pedit (fs, val, mask,IP6_SRC_127_96 ); -break ; -case PEDIT_IP6_DST_31_0 : -offload_pedit (fs, val, mask,IP6_DST_31_0 ); +case PEDIT_IP6_SRC : +offload_pedit (fs, act,IP6_SRC );break ; -case PEDIT_IP6_DST_63_32 : -offload_pedit (fs, val, mask,IP6_DST_63_32 ); +case PEDIT_IP6_DST : +offload_pedit (fs, act,IP6_DST );break ; -case PEDIT_IP6_DST_95_64 : -offload_pedit (fs, val, mask,IP6_DST_95_64 ); -break ; -case PEDIT_IP6_DST_127_96 : -offload_pedit (fs, val, mask,IP6_DST_127_96 ); } fs->nat_mode =NAT_MODE_ALL ;break ;case FLOW_ACT_MANGLE_HDR_TYPE_TCP :switch (offset) { -case PEDIT_TCP_SPORT_DPORT : -if (mask &PEDIT_TCP_UDP_SPORT_MASK ) -offload_pedit (fs,cpu_to_be32 (val) >>16 , -cpu_to_be32 (mask) >>16 , -TCP_SPORT ); -else -offload_pedit (fs,cpu_to_be32 (val), -cpu_to_be32 (mask),TCP_DPORT ); +case PEDIT_TCP_SPORT : +offload_pedit (fs, act,TCP_SPORT ); +break ; +case PEDIT_TCP_DPORT : +offload_pedit (fs, act,TCP_DPORT ); +break ; } fs->nat_mode =NAT_MODE_ALL ;break ;case FLOW_ACT_MANGLE_HDR_TYPE_UDP :switch (offset) { -case PEDIT_UDP_SPORT_DPORT : -if (mask &PEDIT_TCP_UDP_SPORT_MASK ) -offload_pedit (fs,cpu_to_be32 (val) >>16 , -cpu_to_be32 (mask) >>16 , -UDP_SPORT ); -else -offload_pedit (fs,cpu_to_be32 (val), -cpu_to_be32 (mask),UDP_DPORT ); +case PEDIT_UDP_SPORT : +offload_pedit (fs, act,UDP_SPORT ); +break ; +case PEDIT_UDP_DPORT : +offload_pedit (fs, act,UDP_DPORT ); +break ; } fs->nat_mode =NAT_MODE_ALL ; }
@@ -424,17 +392,8 @@ static void cxgb4_process_flow_actions(struct net_device *in, } }break ; -case FLOW_ACTION_MANGLE : { -u32 mask, val, offset; -u8 htype; - - htype = act->mangle.htype; - mask = act->mangle.mask; - val = act->mangle.val; - offset = act->mangle.offset; - -process_pedit_field (fs, val, mask, offset, htype); - } +case FLOW_ACTION_MANGLE : +process_pedit_field (fs, act);break ;default :break ;
@@ -442,35 +401,20 @@ static void cxgb4_process_flow_actions(struct net_device *in, } } -static bool valid_l4_mask (u32 mask) -{ -u16 hi, lo; - -/* Either the upper 16-bits (SPORT) OR the lower -* 16-bits (DPORT) can be set, but NOT BOTH. -*/ - hi = (mask >>16 ) &0xFFFF ; - lo = mask &0xFFFF ; - -return hi && lo ? false : true; -} -static bool valid_pedit_action (struct net_device *dev,const struct flow_action_entry *act) { -u32 mask, offset; +u32 offset;u8 htype; htype = act->mangle.htype; - mask = act->mangle.mask; offset = act->mangle.offset;switch (htype) {case FLOW_ACT_MANGLE_HDR_TYPE_ETH :switch (offset) { -case PEDIT_ETH_DMAC_31_0 : -case PEDIT_ETH_DMAC_47_32_SMAC_15_0 : -case PEDIT_ETH_SMAC_47_16 : +case PEDIT_ETH_DMAC : +case PEDIT_ETH_SMAC :break ;default : netdev_err(dev, "%s: Unsupported pedit field\n",
@@ -491,14 +435,8 @@ static bool valid_pedit_action(struct net_device *dev,break ;case FLOW_ACT_MANGLE_HDR_TYPE_IP6 :switch (offset) { -case PEDIT_IP6_SRC_31_0 : -case PEDIT_IP6_SRC_63_32 : -case PEDIT_IP6_SRC_95_64 : -case PEDIT_IP6_SRC_127_96 : -case PEDIT_IP6_DST_31_0 : -case PEDIT_IP6_DST_63_32 : -case PEDIT_IP6_DST_95_64 : -case PEDIT_IP6_DST_127_96 : +case PEDIT_IP6_SRC : +case PEDIT_IP6_DST :break ;default : netdev_err(dev, "%s: Unsupported pedit field\n",
@@ -508,12 +446,8 @@ static bool valid_pedit_action(struct net_device *dev,break ;case FLOW_ACT_MANGLE_HDR_TYPE_TCP :switch (offset) { -case PEDIT_TCP_SPORT_DPORT : -if (!valid_l4_mask (mask)) { -netdev_err (dev,"%s: Unsupported mask for TCP L4 ports\n" , - __func__); -return false; - } +case PEDIT_TCP_SPORT : +case PEDIT_TCP_DPORT :break ;default : netdev_err(dev, "%s: Unsupported pedit field\n",
@@ -523,12 +457,8 @@ static bool valid_pedit_action(struct net_device *dev,break ;case FLOW_ACT_MANGLE_HDR_TYPE_UDP :switch (offset) { -case PEDIT_UDP_SPORT_DPORT : -if (!valid_l4_mask (mask)) { -netdev_err (dev,"%s: Unsupported mask for UDP L4 ports\n" , - __func__); -return false; - } +case PEDIT_UDP_SPORT : +case PEDIT_UDP_DPORT :break ;default : netdev_err(dev, "%s: Unsupported pedit field\n",
drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h +12 -28
@@ -55,23 +55,14 @@ struct ch_tc_flower_entry { };enum { -ETH_DMAC_31_0 ,/* dmac bits 0.. 31 */ -ETH_DMAC_47_32 ,/* dmac bits 32..47 */ -ETH_SMAC_15_0 ,/* smac bits 0.. 15 */ -ETH_SMAC_47_16 ,/* smac bits 16..47 */ +ETH_DMAC ,/* 48-bits dmac bits */ +ETH_SMAC ,/* 48-bits smac bits */ IP4_SRC ,/* 32-bit IPv4 src */ IP4_DST ,/* 32-bit IPv4 dst */ -IP6_SRC_31_0 ,/* src bits 0.. 31 */ -IP6_SRC_63_32 ,/* src bits 63.. 32 */ -IP6_SRC_95_64 ,/* src bits 95.. 64 */ -IP6_SRC_127_96 ,/* src bits 127..96 */ - -IP6_DST_31_0 ,/* dst bits 0.. 31 */ -IP6_DST_63_32 ,/* dst bits 63.. 32 */ -IP6_DST_95_64 ,/* dst bits 95.. 64 */ -IP6_DST_127_96 ,/* dst bits 127..96 */ +IP6_SRC ,/* 128-bit IPv6 src */ +IP6_DST ,/* 128-bit IPv6 dst */ TCP_SPORT ,/* 16-bit TCP sport */ TCP_DPORT ,/* 16-bit TCP dport */
@@ -90,23 +81,16 @@ struct ch_tc_pedit_fields { { type## field, size, \ offsetof(struct ch_filter_specification, fs_field) + (offset) } -#define PEDIT_ETH_DMAC_MASK 0xffff -#define PEDIT_TCP_UDP_SPORT_MASK 0xffff -#define PEDIT_ETH_DMAC_31_0 0x0 -#define PEDIT_ETH_DMAC_47_32_SMAC_15_0 0x4 -#define PEDIT_ETH_SMAC_47_16 0x8 +#define PEDIT_ETH_DMAC 0x0 +#define PEDIT_ETH_SMAC 0x6 +#define PEDIT_IP6_SRC 0x8 +#define PEDIT_IP6_DST 0x18#define PEDIT_IP4_SRC 0xC#define PEDIT_IP4_DST 0x10 -#define PEDIT_IP6_SRC_31_0 0x8 -#define PEDIT_IP6_SRC_63_32 0xC -#define PEDIT_IP6_SRC_95_64 0x10 -#define PEDIT_IP6_SRC_127_96 0x14 -#define PEDIT_IP6_DST_31_0 0x18 -#define PEDIT_IP6_DST_63_32 0x1C -#define PEDIT_IP6_DST_95_64 0x20 -#define PEDIT_IP6_DST_127_96 0x24 -#define PEDIT_TCP_SPORT_DPORT 0x0 -#define PEDIT_UDP_SPORT_DPORT 0x0 +#define PEDIT_TCP_SPORT 0x0 +#define PEDIT_TCP_DPORT 0x2 +#define PEDIT_UDP_SPORT 0x0 +#define PEDIT_UDP_DPORT 0x2int cxgb4_tc_flower_replace (struct net_device *dev,struct flow_cls_offload *cls);
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +30 -60
136 lines not on this page · raw message
drivers/net/ethernet/netronome/nfp/flower/action.c +93 -110
304 lines not on this page · raw message
include/net/flow_offload.h +5 -2
@@ -154,6 +154,8 @@ enum flow_action_mangle_base { FLOW_ACT_MANGLE_HDR_TYPE_UDP, }; +#define FLOW_ACTION_MANGLE_MAXLEN 16 +struct flow_action_entry {enum flow_action_id id;union {
@@ -167,8 +169,9 @@ struct flow_action_entry {struct {/* FLOW_ACTION_PACKET_EDIT */ enum flow_action_mangle_base htype;u32 offset; -u32 mask; -u32 val; +u8 mask[FLOW_ACTION_MANGLE_MAXLEN ]; +u8 val[FLOW_ACTION_MANGLE_MAXLEN ]; +u8 len; } mangle;const struct ip_tunnel_info *tunnel;/* FLOW_ACTION_TUNNEL_ENCAP */ u32 csum_flags;/* FLOW_ACTION_CSUM */
net/sched/cls_api.c +123 -22
168 lines not on this page · raw message
Signature · 1 line
2.11.0
Re: [PATCH net-next,v2 3/4] net: flow_offload: mangle action at byte level
Quoted 44 lines · Pablo Neira Ayuso
The flow mangle action is originally modeled after the tc pedit action, this has a number of shortcomings:
1) The tc pedit offset must be set on the 32-bits boundaries. Many protocol header field offsets are not aligned to 32-bits, eg. port destination, port source and ethernet destination. This patch adjusts the offset accordingly and trim off length in these case, so drivers get an exact offset and length to the header fields.
2) The maximum mangle length is one word of 32-bits, hence you need to up to four actions to mangle an IPv6 address. This patch coalesces consecutive tc pedit actions into one single action so drivers can configure the IPv6 mangling in one go. Ethernet address fields now require one single action instead of two too.
The following drivers have been updated accordingly to use this new mangle action layout:
1) The cxgb4 driver does not need to split protocol field matching larger than one 32-bit words into multiple definitions. Instead one single definition per protocol field is enough. Checking for transport protocol ports is also simplified.
2) The mlx5 driver logic to disallow IPv4 ttl and IPv6 hoplimit fields becomes more simple too.
3) The nfp driver uses the
nfp_fl_set_helper()function to configure the payload mangling. Thememchr_inv()function is used to check for proper initialization of the value and mask. The driver has been updated to refer to the exact protocol header offsets too.As a result, this patch reduces code complexity on the driver side at the cost of adding ~100 LOC at the core to perform offset and length adjustment; and to coalesce consecutive actions.
Signed-off-by Pablo Neira Ayuso <[email protected]>--- .../net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c | 162 +++++----------- .../net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h | 40 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 90 +++------ drivers/net/ethernet/netronome/nfp/flower/action.c | 203 ++++++++++----------- include/net/flow_offload.h | 7 +- net/sched/cls_api.c | 145 ++++++++++++--- 6 files changed, 309 insertions(+), 338 deletions(-)
[...]
Quoted 106 lines
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +16
-53@@ -2201,19 +2201,24 @@ static int pedit_header_offsets[] = {#define pedit_header (_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype]) -static int set_pedit_val (u8 hdr_type,u32 mask,u32 val,u32 offset, +static int set_pedit_val (u8 hdr_type,const struct flow_action_entry *act,struct pedit_headers_action *hdrs) { -u32 *curr_pmask, *curr_pval; +u32 offset = act->mangle.offset; +u8 *curr_pmask, *curr_pval; +int i; - curr_pmask = (u32 *)(pedit_header (&hdrs->masks, hdr_type) + offset); - curr_pval = (u32 *)(pedit_header (&hdrs->vals, hdr_type) + offset); + curr_pmask = (u8 *)(pedit_header (&hdrs->masks, hdr_type) + offset); + curr_pval = (u8 *)(pedit_header (&hdrs->vals, hdr_type) + offset); -if (*curr_pmask & mask)/* disallow acting twice on the same location */ - goto out_err; +for (i =0 ; i < act->mangle.len; i++) { +/* disallow acting twice on the same location */ +if (curr_pmask[i] & act->mangle.mask[i]) + goto out_err; - *curr_pmask |= mask; - *curr_pval |= val; + curr_pmask[i] |= act->mangle.mask[i]; + curr_pval[i] |= act->mangle.val[i]; + }return 0 ;@@ -2487,7 +2492,6 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, {u8 cmd = (act->id ==FLOW_ACTION_MANGLE ) ?0 :1 ;int err = -EOPNOTSUPP ; -u32 mask, val, offset;u8 htype; htype = act->mangle.htype;@@ -2504,11 +2508,7 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, goto out_err; } - mask = act->mangle.mask; - val = act->mangle.val; - offset = act->mangle.offset; - - err =set_pedit_val (htype, mask, val, offset, &hdrs[cmd]); + err =set_pedit_val (htype, act, &hdrs[cmd]);if (err) goto out_err;@@ -2589,50 +2589,18 @@ static bool csum_offload_supported(struct mlx5e_priv *priv,return true; } -struct ip_ttl_word { -__u8 ttl; -__u8 protocol; -__sum16 check; -}; - -struct ipv6_hoplimit_word { -__be16 payload_len; -__u8 nexthdr; -__u8 hop_limit; -}; -static bool is_action_keys_supported (const struct flow_action_entry *act) { -u32 mask, offset; -u8 htype; +u32 offset = act->mangle.offset; +u8 htype = act->mangle.htype; - htype = act->mangle.htype; - offset = act->mangle.offset; - mask = act->mangle.mask; -/* For IPv4 & IPv6 header check 4 byte word, -* to determine that modified fields -* are NOT ttl & hop_limit only. -*/ -if (htype ==FLOW_ACT_MANGLE_HDR_TYPE_IP4 ) { -struct ip_ttl_word *ttl_word = - (struct ip_ttl_word *)&mask; - -if (offset != offsetof(struct iphdr , ttl) || - ttl_word->protocol || - ttl_word->check) { -return true; - } - }else if (htype ==FLOW_ACT_MANGLE_HDR_TYPE_IP6 ) { -struct ipv6_hoplimit_word *hoplimit_word = - (struct ipv6_hoplimit_word *)&mask; - -if (offset != offsetof(struct ipv6hdr , payload_len) || - hoplimit_word->payload_len || - hoplimit_word->nexthdr) { -return true; - }
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c static bool csum_offload_supported(struct mlx5e_priv *priv, · line 2604
Quoted 10 lines
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +7
-2- } -return false; +if ((htype ==FLOW_ACT_MANGLE_HDR_TYPE_IP4 && + offset == offsetof(struct iphdr , ttl)) || + (htype ==FLOW_ACT_MANGLE_HDR_TYPE_IP6 && + offset == offsetof(struct ipv6hdr , hop_limit))) +return false; + +return true; }
With this change is_action_keys_supported() incorrectly returns true for non-IP{4|6} mangles. I guess naming of the functions doesn't help because it should be something like is_action_iphdr_keys_supported()...
Anyway, this results following rule to be incorrectly rejected by driver:
tc filter add dev ens1f0_0 protocol ip parent ffff: prio 3 flower dst_mac e4:1d:2d:fd:8b:02 skip_sw
action pedit ex munge eth src set 11:22:33:44:55:66 munge eth dst set
aa:bb:cc:dd:ee:ff pipe
action csum ip pipe
action tunnel_key set id 98 src_ip 2.2.2.2 dst_ip 2.2.2.3 dst_port 1234 action mirred egress redirect dev vxlan1
The pedit action is rejected by conditional that follows the loop in modify_header_match_supported() which calls is_action_keys_supported(). With this change modify_ip_header==true (even though the pedit only modifies eth header), which causes failure because ip proto is not supported:
Error: mlx5_core: can't offload re-write of non TCP/UDP.
ERROR: [ 3345.830338] can't offload re-write of ip proto 0
Pablo Neira Ayuso
maintainerPATCH v2 4/4 netfilter: nft_payload: packet mangling offload support
In reply to Pablo Neira AyusoThis patch allows for mangling packet fields using hardware offload infrastructure.
--- net/netfilter/nft_payload.c | 73 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+)
net/netfilter/nft_payload.c +73 -0
@@ -562,12 +562,85 @@ static int nft_payload_set_dump(struct sk_buff *skb, const struct nft_expr *exprreturn -1 ; } +static int nft_payload_offload_set_nh (struct nft_offload_ctx *ctx, +struct nft_flow_rule *flow, +const struct nft_payload_set *priv) +{ +int type =FLOW_ACT_MANGLE_UNSPEC ; + +switch (ctx->dep.l3num) { +case htons (ETH_P_IP ): + type =FLOW_ACT_MANGLE_HDR_TYPE_IP4 ; +break ; +case htons (ETH_P_IPV6 ): + type =FLOW_ACT_MANGLE_HDR_TYPE_IP6 ; +break ; + } + +return type; +} + +static int nft_payload_offload_set_th (struct nft_offload_ctx *ctx, +struct nft_flow_rule *flow, +const struct nft_payload_set *priv) +{ +int type =FLOW_ACT_MANGLE_UNSPEC ; + +switch (ctx->dep.protonum) { +case IPPROTO_TCP : + type =FLOW_ACT_MANGLE_HDR_TYPE_TCP ; +break ; +case IPPROTO_UDP : + type =FLOW_ACT_MANGLE_HDR_TYPE_UDP ; +break ; + } + +return type; +} + +static int nft_payload_set_offload (struct nft_offload_ctx *ctx, +struct nft_flow_rule *flow, +const struct nft_expr *expr) +{ +const struct nft_payload_set *priv =nft_expr_priv (expr); +struct nft_offload_reg *sreg = &ctx->regs[priv->sreg]; +int type =FLOW_ACT_MANGLE_UNSPEC ; +struct flow_action_entry *entry; + +switch (priv->base) { +case NFT_PAYLOAD_LL_HEADER : + type =FLOW_ACT_MANGLE_HDR_TYPE_ETH ; +break ; +case NFT_PAYLOAD_NETWORK_HEADER : + type =nft_payload_offload_set_nh (ctx, flow, priv); +break ; +case NFT_PAYLOAD_TRANSPORT_HEADER : + type =nft_payload_offload_set_th (ctx, flow, priv); +break ; +default : +WARN_ON_ONCE (1 ); +break ; + } + + entry = &flow->rule->action.entries[ctx->num_actions++]; + entry->id =FLOW_ACTION_MANGLE ; + entry->mangle.htype = type; + entry->mangle.offset = priv->offset; + entry->mangle.len = priv->len; + +memcpy (entry->mangle.val, sreg->data.data, priv->len); +memset (entry->mangle.mask,0xff , priv->len); + +return type !=FLOW_ACT_MANGLE_UNSPEC ?0 : -EOPNOTSUPP ; +} +static const struct nft_expr_ops nft_payload_set_ops = { .type = &nft_payload_type, .size =NFT_EXPR_SIZE (sizeof (struct nft_payload_set )), .eval = nft_payload_set_eval, .init = nft_payload_set_init, .dump = nft_payload_set_dump, + .offload = nft_payload_set_offload, }; static const struct nft_expr_ops *
Signature · 1 line
2.11.0