Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

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);
 		}
 	}
 }