This bit indicates that the conntrack entry is offloaded to hardware flow table. nf_conntrack entry will be tagged with [HW_OFFLOAD] if it's offload to hardware. cat /proc/net/nf_conntrack ipv4 2 tcp 6 \ src=1.1.1.17 dst=1.1.1.16 sport=56394 dport=5001 \ src=1.1.1.16 dst=1.1.1.17 sport=5001 dport=56394 [HW_OFFLOAD] \ mark=0 zone=0 use=3 Note that HW_OFFLOAD/OFFLOAD/ASSURED are mutually exclusive. Signed-off-by: Bodong Wang <bodong@xxxxxxxxxxxx> Reviewed-by: Oz Shlomo <ozsh@xxxxxxxxxxxx> Reviewed-by: Paul Blakey <paulb@xxxxxxxxxxxx> --- include/uapi/linux/netfilter/nf_conntrack_common.h | 8 ++++++-- net/netfilter/nf_conntrack_standalone.c | 4 +++- net/netfilter/nf_flow_table_offload.c | 13 +++++++++++++ 3 files changed, 22 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index b6f0bb1dc799..4b3395082d15 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -114,15 +114,19 @@ enum ip_conntrack_status { IPS_OFFLOAD_BIT = 14, IPS_OFFLOAD = (1 << IPS_OFFLOAD_BIT), + /* Conntrack has been offloaded to hardware. */ + IPS_HW_OFFLOAD_BIT = 15, + IPS_HW_OFFLOAD = (1 << IPS_HW_OFFLOAD_BIT), + /* Be careful here, modifying these bits can make things messy, * so don't let users modify them directly. */ IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK | IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING | IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_UNTRACKED | - IPS_OFFLOAD), + IPS_OFFLOAD | IPS_HW_OFFLOAD), - __IPS_MAX_BIT = 15, + __IPS_MAX_BIT = 16, }; /* Connection tracking event types */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 9b57330c81f8..5a3e6c43ee68 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -348,7 +348,9 @@ static int ct_seq_show(struct seq_file *s, void *v) if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) goto release; - if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) + if (test_bit(IPS_HW_OFFLOAD_BIT, &ct->status)) + seq_puts(s, "[HW_OFFLOAD] "); + else if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) seq_puts(s, "[OFFLOAD] "); else if (test_bit(IPS_ASSURED_BIT, &ct->status)) seq_puts(s, "[ASSURED] "); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index e3b099c14eff..c9efd20ea65c 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -754,12 +754,15 @@ static void flow_offload_work_add(struct flow_offload_work *offload) err = flow_offload_rule_add(offload, flow_rule); if (err < 0) set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags); + else + set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); nf_flow_offload_destroy(flow_rule); } static void flow_offload_work_del(struct flow_offload_work *offload) { + clear_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL); flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY); set_bit(NF_FLOW_HW_DEAD, &offload->flow->flags); @@ -796,6 +799,16 @@ static void flow_offload_work_stats(struct flow_offload_work *offload) FLOW_OFFLOAD_DIR_REPLY, stats[1].pkts, stats[1].bytes); } + + /* Clear HW_OFFLOAD immediately when lastused stopped updating, this can + * happen in two scenarios: + * + * 1. TC rule on a higher level device (e.g. vxlan) was offloaded, but + * HW driver is unloaded. + * 2. One of the shared block driver is unloaded. + */ + if (!lastused) + clear_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); } static void flow_offload_work_handler(struct work_struct *work) -- 2.21.1