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

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

1 files changed, 71 insertions, 14 deletions

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 13242bf5b427..2d7ada0f0dbd 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -1,11 +1,12 @@
 /* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
 /* Copyright 2014-2016 Freescale Semiconductor Inc.
- * Copyright 2016 NXP
+ * Copyright 2016-2020 NXP
  */
 
 #ifndef __DPAA2_ETH_H
 #define __DPAA2_ETH_H
 
+#include <linux/dcbnl.h>
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
 #include <linux/fsl/mc.h>
@@ -36,27 +37,46 @@
 /* Convert L3 MTU to L2 MFL */
 #define DPAA2_ETH_L2_MAX_FRM(mtu)	((mtu) + VLAN_ETH_HLEN)
 
-/* Set the taildrop threshold (in bytes) to allow the enqueue of several jumbo
- * frames in the Rx queues (length of the current frame is not
- * taken into account when making the taildrop decision)
+/* Set the taildrop threshold (in bytes) to allow the enqueue of a large
+ * enough number of jumbo frames in the Rx queues (length of the current
+ * frame is not taken into account when making the taildrop decision)
  */
-#define DPAA2_ETH_TAILDROP_THRESH	(64 * 1024)
+#define DPAA2_ETH_FQ_TAILDROP_THRESH	(1024 * 1024)
 
 /* Maximum number of Tx confirmation frames to be processed
  * in a single NAPI call
  */
 #define DPAA2_ETH_TXCONF_PER_NAPI	256
 
-/* Buffer quota per queue. Must be large enough such that for minimum sized
- * frames taildrop kicks in before the bpool gets depleted, so we compute
- * how many 64B frames fit inside the taildrop threshold and add a margin
- * to accommodate the buffer refill delay.
+/* Buffer qouta per channel. We want to keep in check number of ingress frames
+ * in flight: for small sized frames, congestion group taildrop may kick in
+ * first; for large sizes, Rx FQ taildrop threshold will ensure only a
+ * reasonable number of frames will be pending at any given time.
+ * Ingress frame drop due to buffer pool depletion should be a corner case only
  */
-#define DPAA2_ETH_MAX_FRAMES_PER_QUEUE	(DPAA2_ETH_TAILDROP_THRESH / 64)
-#define DPAA2_ETH_NUM_BUFS		(DPAA2_ETH_MAX_FRAMES_PER_QUEUE + 256)
+#define DPAA2_ETH_NUM_BUFS		1280
 #define DPAA2_ETH_REFILL_THRESH \
 	(DPAA2_ETH_NUM_BUFS - DPAA2_ETH_BUFS_PER_CMD)
 
+/* Congestion group taildrop threshold: number of frames allowed to accumulate
+ * at any moment in a group of Rx queues belonging to the same traffic class.
+ * Choose value such that we don't risk depleting the buffer pool before the
+ * taildrop kicks in
+ */
+#define DPAA2_ETH_CG_TAILDROP_THRESH(priv)				\
+	(1024 * dpaa2_eth_queue_count(priv) / dpaa2_eth_tc_count(priv))
+
+/* Congestion group notification threshold: when this many frames accumulate
+ * on the Rx queues belonging to the same TC, the MAC is instructed to send
+ * PFC frames for that TC.
+ * When number of pending frames drops below exit threshold transmission of
+ * PFC frames is stopped.
+ */
+#define DPAA2_ETH_CN_THRESH_ENTRY(priv) \
+	(DPAA2_ETH_CG_TAILDROP_THRESH(priv) / 2)
+#define DPAA2_ETH_CN_THRESH_EXIT(priv) \
+	(DPAA2_ETH_CN_THRESH_ENTRY(priv) * 3 / 4)
+
 /* Maximum number of buffers that can be acquired/released through a single
  * QBMan command
  */
@@ -288,11 +308,15 @@ struct dpaa2_eth_ch_stats {
 	__u64 xdp_tx;
 	__u64 xdp_tx_err;
 	__u64 xdp_redirect;
+	/* Must be last, does not show up in ethtool stats */
+	__u64 frames;
 };
 
 /* Maximum number of queues associated with a DPNI */
 #define DPAA2_ETH_MAX_TCS		8
-#define DPAA2_ETH_MAX_RX_QUEUES		16
+#define DPAA2_ETH_MAX_RX_QUEUES_PER_TC	16
+#define DPAA2_ETH_MAX_RX_QUEUES		\
+	(DPAA2_ETH_MAX_RX_QUEUES_PER_TC * DPAA2_ETH_MAX_TCS)
 #define DPAA2_ETH_MAX_TX_QUEUES		16
 #define DPAA2_ETH_MAX_QUEUES		(DPAA2_ETH_MAX_RX_QUEUES + \
 					DPAA2_ETH_MAX_TX_QUEUES)
@@ -308,6 +332,11 @@ enum dpaa2_eth_fq_type {
 
 struct dpaa2_eth_priv;
 
+struct dpaa2_eth_xdp_fds {
+	struct dpaa2_fd fds[DEV_MAP_BULK_SIZE];
+	ssize_t num;
+};
+
 struct dpaa2_eth_fq {
 	u32 fqid;
 	u32 tx_qdbin;
@@ -325,6 +354,9 @@ struct dpaa2_eth_fq {
 			const struct dpaa2_fd *fd,
 			struct dpaa2_eth_fq *fq);
 	struct dpaa2_eth_fq_stats stats;
+
+	struct dpaa2_eth_xdp_fds xdp_redirect_fds;
+	struct dpaa2_eth_xdp_fds xdp_tx_fds;
 };
 
 struct dpaa2_eth_ch_xdp {
@@ -371,7 +403,9 @@ struct dpaa2_eth_priv {
 	struct dpaa2_eth_fq fq[DPAA2_ETH_MAX_QUEUES];
 	int (*enqueue)(struct dpaa2_eth_priv *priv,
 		       struct dpaa2_eth_fq *fq,
-		       struct dpaa2_fd *fd, u8 prio);
+		       struct dpaa2_fd *fd, u8 prio,
+		       u32 num_frames,
+		       int *frames_enqueued);
 
 	u8 num_channels;
 	struct dpaa2_eth_channel *channel[DPAA2_ETH_MAX_DPCONS];
@@ -402,7 +436,8 @@ struct dpaa2_eth_priv {
 	struct dpaa2_eth_drv_stats __percpu *percpu_extras;
 
 	u16 mc_token;
-	u8 rx_td_enabled;
+	u8 rx_fqtd_enabled;
+	u8 rx_cgtd_enabled;
 
 	struct dpni_link_state link_state;
 	bool do_link_poll;
@@ -413,6 +448,12 @@ struct dpaa2_eth_priv {
 	u64 rx_cls_fields;
 	struct dpaa2_eth_cls_rule *cls_rules;
 	u8 rx_cls_enabled;
+	u8 vlan_cls_enabled;
+	u8 pfc_enabled;
+#ifdef CONFIG_FSL_DPAA2_ETH_DCB
+	u8 dcbx_mode;
+	struct ieee_pfc pfc;
+#endif
 	struct bpf_prog *xdp_prog;
 #ifdef CONFIG_DEBUG_FS
 	struct dpaa2_debugfs dbg;
@@ -495,6 +536,17 @@ enum dpaa2_eth_rx_dist {
 	(dpaa2_eth_cmp_dpni_ver((priv), DPNI_PAUSE_VER_MAJOR,	\
 				DPNI_PAUSE_VER_MINOR) >= 0)
 
+static inline bool dpaa2_eth_tx_pause_enabled(u64 link_options)
+{
+	return !!(link_options & DPNI_LINK_OPT_PAUSE) ^
+	       !!(link_options & DPNI_LINK_OPT_ASYM_PAUSE);
+}
+
+static inline bool dpaa2_eth_rx_pause_enabled(u64 link_options)
+{
+	return !!(link_options & DPNI_LINK_OPT_PAUSE);
+}
+
 static inline
 unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv,
 				       struct sk_buff *skb)
@@ -534,4 +586,9 @@ int dpaa2_eth_cls_key_size(u64 key);
 int dpaa2_eth_cls_fld_off(int prot, int field);
 void dpaa2_eth_cls_trim_rule(void *key_mem, u64 fields);
 
+void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv,
+			       bool tx_pause, bool pfc);
+
+extern const struct dcbnl_rtnl_ops dpaa2_eth_dcbnl_ops;
+
 #endif	/* __DPAA2_H */