diff options
Diffstat (limited to 'samples/bpf/hbm_kern.h')
-rw-r--r-- | samples/bpf/hbm_kern.h | 117 |
1 files changed, 100 insertions, 17 deletions
diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h index c5635d924193..aa207a2eebbd 100644 --- a/samples/bpf/hbm_kern.h +++ b/samples/bpf/hbm_kern.h @@ -29,16 +29,10 @@ #define DROP_PKT 0 #define ALLOW_PKT 1 #define TCP_ECN_OK 1 +#define CWR 2 -#define HBM_DEBUG 0 // Set to 1 to enable debugging -#if HBM_DEBUG -#define bpf_printk(fmt, ...) \ -({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) -#else +#ifndef HBM_DEBUG // Define HBM_DEBUG to enable debugging +#undef bpf_printk #define bpf_printk(fmt, ...) #endif @@ -52,8 +46,18 @@ #define MAX_CREDIT (100 * MAX_BYTES_PER_PACKET) #define INIT_CREDIT (INITIAL_CREDIT_PACKETS * MAX_BYTES_PER_PACKET) +// Time base accounting for fq's EDT +#define BURST_SIZE_NS 100000 // 100us +#define MARK_THRESH_NS 50000 // 50us +#define DROP_THRESH_NS 500000 // 500us +// Reserve 20us of queuing for small packets (less than 120 bytes) +#define LARGE_PKT_DROP_THRESH_NS (DROP_THRESH_NS - 20000) +#define MARK_REGION_SIZE_NS (LARGE_PKT_DROP_THRESH_NS - MARK_THRESH_NS) + // rate in bytes per ns << 20 #define CREDIT_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20) +#define BYTES_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20) +#define BYTES_TO_NS(bytes, rate) div64_u64(((u64)(bytes)) << 20, (u64)(rate)) struct bpf_map_def SEC("maps") queue_state = { .type = BPF_MAP_TYPE_CGROUP_STORAGE, @@ -72,17 +76,48 @@ struct bpf_map_def SEC("maps") queue_stats = { BPF_ANNOTATE_KV_PAIR(queue_stats, int, struct hbm_queue_stats); struct hbm_pkt_info { + int cwnd; + int rtt; + int packets_out; bool is_ip; bool is_tcp; short ecn; }; -static __always_inline void hbm_get_pkt_info(struct __sk_buff *skb, - struct hbm_pkt_info *pkti) +static int get_tcp_info(struct __sk_buff *skb, struct hbm_pkt_info *pkti) +{ + struct bpf_sock *sk; + struct bpf_tcp_sock *tp; + + sk = skb->sk; + if (sk) { + sk = bpf_sk_fullsock(sk); + if (sk) { + if (sk->protocol == IPPROTO_TCP) { + tp = bpf_tcp_sock(sk); + if (tp) { + pkti->cwnd = tp->snd_cwnd; + pkti->rtt = tp->srtt_us >> 3; + pkti->packets_out = tp->packets_out; + return 0; + } + } + } + } + pkti->cwnd = 0; + pkti->rtt = 0; + pkti->packets_out = 0; + return 1; +} + +static void hbm_get_pkt_info(struct __sk_buff *skb, + struct hbm_pkt_info *pkti) { struct iphdr iph; struct ipv6hdr *ip6h; + pkti->cwnd = 0; + pkti->rtt = 0; bpf_skb_load_bytes(skb, 0, &iph, 12); if (iph.version == 6) { ip6h = (struct ipv6hdr *)&iph; @@ -98,22 +133,42 @@ static __always_inline void hbm_get_pkt_info(struct __sk_buff *skb, pkti->is_tcp = false; pkti->ecn = 0; } + if (pkti->is_tcp) + get_tcp_info(skb, pkti); } static __always_inline void hbm_init_vqueue(struct hbm_vqueue *qdp, int rate) { - bpf_printk("Initializing queue_state, rate:%d\n", rate * 128); - qdp->lasttime = bpf_ktime_get_ns(); - qdp->credit = INIT_CREDIT; - qdp->rate = rate * 128; + bpf_printk("Initializing queue_state, rate:%d\n", rate * 128); + qdp->lasttime = bpf_ktime_get_ns(); + qdp->credit = INIT_CREDIT; + qdp->rate = rate * 128; +} + +static __always_inline void hbm_init_edt_vqueue(struct hbm_vqueue *qdp, + int rate) +{ + unsigned long long curtime; + + curtime = bpf_ktime_get_ns(); + bpf_printk("Initializing queue_state, rate:%d\n", rate * 128); + qdp->lasttime = curtime - BURST_SIZE_NS; // support initial burst + qdp->credit = 0; // not used + qdp->rate = rate * 128; } static __always_inline void hbm_update_stats(struct hbm_queue_stats *qsp, int len, unsigned long long curtime, bool congestion_flag, - bool drop_flag) + bool drop_flag, + bool cwr_flag, + bool ecn_ce_flag, + struct hbm_pkt_info *pkti, + int credit) { + int rv = ALLOW_PKT; + if (qsp != NULL) { // Following is needed for work conserving __sync_add_and_fetch(&(qsp->bytes_total), len); @@ -123,7 +178,7 @@ static __always_inline void hbm_update_stats(struct hbm_queue_stats *qsp, qsp->firstPacketTime = curtime; qsp->lastPacketTime = curtime; __sync_add_and_fetch(&(qsp->pkts_total), 1); - if (congestion_flag || drop_flag) { + if (congestion_flag) { __sync_add_and_fetch(&(qsp->pkts_marked), 1); __sync_add_and_fetch(&(qsp->bytes_marked), len); } @@ -132,6 +187,34 @@ static __always_inline void hbm_update_stats(struct hbm_queue_stats *qsp, __sync_add_and_fetch(&(qsp->bytes_dropped), len); } + if (ecn_ce_flag) + __sync_add_and_fetch(&(qsp->pkts_ecn_ce), 1); + if (pkti->cwnd) { + __sync_add_and_fetch(&(qsp->sum_cwnd), + pkti->cwnd); + __sync_add_and_fetch(&(qsp->sum_cwnd_cnt), 1); + } + if (pkti->rtt) + __sync_add_and_fetch(&(qsp->sum_rtt), + pkti->rtt); + __sync_add_and_fetch(&(qsp->sum_credit), credit); + + if (drop_flag) + rv = DROP_PKT; + if (cwr_flag) + rv |= 2; + if (rv == DROP_PKT) + __sync_add_and_fetch(&(qsp->returnValCount[0]), + 1); + else if (rv == ALLOW_PKT) + __sync_add_and_fetch(&(qsp->returnValCount[1]), + 1); + else if (rv == 2) + __sync_add_and_fetch(&(qsp->returnValCount[2]), + 1); + else if (rv == 3) + __sync_add_and_fetch(&(qsp->returnValCount[3]), + 1); } } } |