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, 30 insertions, 75 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 701e5dc75bb0..600e92cb629a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -35,55 +35,12 @@
 #include <net/geneve.h>
 #include <net/dsfield.h>
 #include "en.h"
+#include "en/txrx.h"
 #include "ipoib/ipoib.h"
 #include "en_accel/en_accel.h"
+#include "en_accel/ktls.h"
 #include "lib/clock.h"
 
-#define MLX5E_SQ_NOPS_ROOM  MLX5_SEND_WQE_MAX_WQEBBS
-
-#ifndef CONFIG_MLX5_EN_TLS
-#define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
-			    MLX5E_SQ_NOPS_ROOM)
-#else
-/* TLS offload requires MLX5E_SQ_STOP_ROOM to have
- * enough room for a resync SKB, a normal SKB and a NOP
- */
-#define MLX5E_SQ_STOP_ROOM (2 * MLX5_SEND_WQE_MAX_WQEBBS +\
-			    MLX5E_SQ_NOPS_ROOM)
-#endif
-
-static inline void mlx5e_tx_dma_unmap(struct device *pdev,
-				      struct mlx5e_sq_dma *dma)
-{
-	switch (dma->type) {
-	case MLX5E_DMA_MAP_SINGLE:
-		dma_unmap_single(pdev, dma->addr, dma->size, DMA_TO_DEVICE);
-		break;
-	case MLX5E_DMA_MAP_PAGE:
-		dma_unmap_page(pdev, dma->addr, dma->size, DMA_TO_DEVICE);
-		break;
-	default:
-		WARN_ONCE(true, "mlx5e_tx_dma_unmap unknown DMA type!\n");
-	}
-}
-
-static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
-{
-	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
-}
-
-static inline void mlx5e_dma_push(struct mlx5e_txqsq *sq,
-				  dma_addr_t addr,
-				  u32 size,
-				  enum mlx5e_dma_map_type map_type)
-{
-	struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, sq->dma_fifo_pc++);
-
-	dma->addr = addr;
-	dma->size = size;
-	dma->type = map_type;
-}
-
 static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma)
 {
 	int i;
@@ -277,23 +234,6 @@ dma_unmap_wqe_err:
 	return -ENOMEM;
 }
 
-static inline void mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq,
-					   struct mlx5_wq_cyc *wq,
-					   u16 pi, u16 nnops)
-{
-	struct mlx5e_tx_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
-
-	edge_wi = wi + nnops;
-
-	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
-	for (; wi < edge_wi; wi++) {
-		wi->skb        = NULL;
-		wi->num_wqebbs = 1;
-		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
-	}
-	sq->stats->nop += nnops;
-}
-
 static inline void
 mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		     u8 opcode, u16 ds_cnt, u8 num_wqebbs, u32 num_bytes, u8 num_dma,
@@ -301,6 +241,7 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		     bool xmit_more)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
+	bool send_doorbell;
 
 	wi->num_bytes = num_bytes;
 	wi->num_dma = num_dma;
@@ -310,23 +251,21 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode);
 	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | ds_cnt);
 
-	netdev_tx_sent_queue(sq->txq, num_bytes);
-
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 
 	sq->pc += wi->num_wqebbs;
-	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, MLX5E_SQ_STOP_ROOM))) {
+	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, sq->stop_room))) {
 		netif_tx_stop_queue(sq->txq);
 		sq->stats->stopped++;
 	}
 
-	if (!xmit_more || netif_xmit_stopped(sq->txq))
+	send_doorbell = __netdev_tx_sent_queue(sq->txq, num_bytes,
+					       xmit_more);
+	if (send_doorbell)
 		mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg);
 }
 
-#define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start))
-
 netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			  struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more)
 {
@@ -353,9 +292,12 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 		stats->packets += skb_shinfo(skb)->gso_segs;
 	} else {
+		u8 mode = mlx5e_transport_inline_tx_wqe(wqe) ?
+			MLX5_INLINE_MODE_TCP_UDP : sq->min_inline_mode;
+
 		opcode    = MLX5_OPCODE_SEND;
 		mss       = 0;
-		ihs       = mlx5e_calc_min_inline(sq->min_inline_mode, skb);
+		ihs       = mlx5e_calc_min_inline(mode, skb);
 		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 		stats->packets++;
 	}
@@ -380,11 +322,17 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 #ifdef CONFIG_MLX5_EN_IPSEC
 		struct mlx5_wqe_eth_seg cur_eth = wqe->eth;
 #endif
+#ifdef CONFIG_MLX5_EN_TLS
+		struct mlx5_wqe_ctrl_seg cur_ctrl = wqe->ctrl;
+#endif
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
-		mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
+		wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi);
 #ifdef CONFIG_MLX5_EN_IPSEC
 		wqe->eth = cur_eth;
 #endif
+#ifdef CONFIG_MLX5_EN_TLS
+		wqe->ctrl = cur_ctrl;
+#endif
 	}
 
 	/* fill wqe */
@@ -443,7 +391,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	u16 pi;
 
 	sq = priv->txq2sq[skb_get_queue_mapping(skb)];
-	mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
+	wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi);
 
 	/* might send skbs and update wqe and pi */
 	skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi);
@@ -531,8 +479,16 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 			wi = &sq->db.wqe_info[ci];
 			skb = wi->skb;
 
-			if (unlikely(!skb)) { /* nop */
-				sqcc++;
+			if (unlikely(!skb)) {
+#ifdef CONFIG_MLX5_EN_TLS
+				if (wi->resync_dump_frag) {
+					struct mlx5e_sq_dma *dma =
+						mlx5e_dma_get(sq, dma_fifo_cc++);
+
+					mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, dma);
+				}
+#endif
+				sqcc += wi->num_wqebbs;
 				continue;
 			}
 
@@ -574,8 +530,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	netdev_tx_completed_queue(sq->txq, npkts, nbytes);
 
 	if (netif_tx_queue_stopped(sq->txq) &&
-	    mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
-				   MLX5E_SQ_STOP_ROOM) &&
+	    mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) &&
 	    !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) {
 		netif_tx_wake_queue(sq->txq);
 		stats->wake++;