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

Pull networking updates from David Miller:
 "Here we go, another merge window full of networking and #ebpf changes:

   1) Snoop DHCPACKS in batman-adv to learn MAC/IP pairs in the DHCP
      range without dealing with floods of ARP traffic, from Linus
      Lüssing.

   2) Throttle buffered multicast packet transmission in mt76, from
      Felix Fietkau.

   3) Support adaptive interrupt moderation in ice, from Brett Creeley.

   4) A lot of struct_size conversions, from Gustavo A. R. Silva.

   5) Add peek/push/pop commands to bpftool, as well as bash completion,
      from Stanislav Fomichev.

   6) Optimize sk_msg_clone(), from Vakul Garg.

   7) Add SO_BINDTOIFINDEX, from David Herrmann.

   8) Be more conservative with local resends due to local congestion,
      from Yuchung Cheng.

   9) Allow vetoing of unsupported VXLAN FDBs, from Petr Machata.

  10) Add health buffer support to devlink, from Eran Ben Elisha.

  11) Add TXQ scheduling API to mac80211, from Toke Høiland-Jørgensen.

  12) Add statistics to basic packet scheduler filter, from Cong Wang.

  13) Add GRE tunnel support for mlxsw Spectrum-2, from Nir Dotan.

  14) Lots of new IP tunneling forwarding tests, also from Nir Dotan.

  15) Add 3ad stats to bonding, from Nikolay Aleksandrov.

  16) Lots of probing improvements for bpftool, from Quentin Monnet.

  17) Various nfp drive #ebpf JIT improvements from Jakub Kicinski.

  18) Allow #ebpf programs to access gso_segs from skb shared info, from
      Eric Dumazet.

  19) Add sock_diag support for AF_XDP sockets, from Björn Töpel.

  20) Support 22260 iwlwifi devices, from Luca Coelho.

  21) Use rbtree for ipv6 defragmentation, from Peter Oskolkov.

  22) Add JMP32 instruction class support to #ebpf, from Jiong Wang.

  23) Add spinlock support to #ebpf, from Alexei Starovoitov.

  24) Support 256-bit keys and TLS 1.3 in ktls, from Dave Watson.

  25) Add device infomation API to devlink, from Jakub Kicinski.

  26) Add new timestamping socket options which are y2038 safe, from
      Deepa Dinamani.

  27) Add RX checksum offloading for various sh_eth chips, from Sergei
      Shtylyov.

  28) Flow offload infrastructure, from Pablo Neira Ayuso.

  29) Numerous cleanups, improvements, and bug fixes to the PHY layer
      and many drivers from Heiner Kallweit.

  30) Lots of changes to try and make packet scheduler classifiers run
      lockless as much as possible, from Vlad Buslov.

  31) Support BCM957504 chip in bnxt_en driver, from Erik Burrows.

  32) Add concurrency tests to tc-tests infrastructure, from Vlad
      Buslov.

  33) Add hwmon support to aquantia, from Heiner Kallweit.

  34) Allow 64-bit values for SO_MAX_PACING_RATE, from Eric Dumazet.

  And I would be remiss if I didn't thank the various major networking
  subsystem maintainers for integrating much of this work before I even
  saw it. Alexei Starovoitov, Daniel Borkmann, Pablo Neira Ayuso,
  Johannes Berg, Kalle Valo, and many others. Thank you!"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2207 commits)
  net/sched: avoid unused-label warning
  net: ignore sysctl_devconf_inherit_init_net without SYSCTL
  phy: mdio-mux: fix Kconfig dependencies
  net: phy: use phy_modify_mmd_changed in genphy_c45_an_config_aneg
  net: dsa: mv88e6xxx: add call to mv88e6xxx_ports_cmode_init to probe for new DSA framework
  selftest/net: Remove duplicate header
  sky2: Disable MSI on Dell Inspiron 1545 and Gateway P-79
  net/mlx5e: Update tx reporter status in case channels were successfully opened
  devlink: Add support for direct reporter health state update
  devlink: Update reporter state to error even if recover aborted
  sctp: call iov_iter_revert() after sending ABORT
  team: Free BPF filter when unregistering netdev
  ip6mr: Do not call __IP6_INC_STATS() from preemptible context
  isdn: mISDN: Fix potential NULL pointer dereference of kzalloc
  net: dsa: mv88e6xxx: support in-band signalling on SGMII ports with external PHYs
  cxgb4/chtls: Prefix adapter flags with CXGB4
  net-sysfs: Switch to bitmap_zalloc()
  mellanox: Switch to bitmap_zalloc()
  bpf: add test cases for non-pointer sanitiation logic
  mlxsw: i2c: Extend initialization by querying resources data
  ...

3 files changed, 454 insertions, 0 deletions

diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h
index 44acfbca12661..6f60a78d9a7e5 100644
--- a/include/trace/events/devlink.h
+++ b/include/trace/events/devlink.h
@@ -46,6 +46,131 @@ TRACE_EVENT(devlink_hwmsg,
 		  (int) __entry->len, __get_dynamic_array(buf), __entry->len)
 );
 
+/*
+ * Tracepoint for devlink hardware error:
+ */
+TRACE_EVENT(devlink_hwerr,
+	TP_PROTO(const struct devlink *devlink, int err, const char *msg),
+
+	TP_ARGS(devlink, err, msg),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink->dev->bus->name)
+		__string(dev_name, dev_name(devlink->dev))
+		__string(driver_name, devlink->dev->driver->name)
+		__field(int, err)
+		__string(msg, msg)
+		),
+
+	TP_fast_assign(
+		__assign_str(bus_name, devlink->dev->bus->name);
+		__assign_str(dev_name, dev_name(devlink->dev));
+		__assign_str(driver_name, devlink->dev->driver->name);
+		__entry->err = err;
+		__assign_str(msg, msg);
+		),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s err=%d %s",
+			__get_str(bus_name), __get_str(dev_name),
+			__get_str(driver_name), __entry->err, __get_str(msg))
+);
+
+/*
+ * Tracepoint for devlink health message:
+ */
+TRACE_EVENT(devlink_health_report,
+	TP_PROTO(const struct devlink *devlink, const char *reporter_name,
+		 const char *msg),
+
+	TP_ARGS(devlink, reporter_name, msg),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink->dev->bus->name)
+		__string(dev_name, dev_name(devlink->dev))
+		__string(driver_name, devlink->dev->driver->name)
+		__string(reporter_name, msg)
+		__string(msg, msg)
+	),
+
+	TP_fast_assign(
+		__assign_str(bus_name, devlink->dev->bus->name);
+		__assign_str(dev_name, dev_name(devlink->dev));
+		__assign_str(driver_name, devlink->dev->driver->name);
+		__assign_str(reporter_name, reporter_name);
+		__assign_str(msg, msg);
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: %s",
+		  __get_str(bus_name), __get_str(dev_name),
+		  __get_str(driver_name), __get_str(reporter_name),
+		  __get_str(msg))
+);
+
+/*
+ * Tracepoint for devlink health recover aborted message:
+ */
+TRACE_EVENT(devlink_health_recover_aborted,
+	TP_PROTO(const struct devlink *devlink, const char *reporter_name,
+		 bool health_state, u64 time_since_last_recover),
+
+	TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink->dev->bus->name)
+		__string(dev_name, dev_name(devlink->dev))
+		__string(driver_name, devlink->dev->driver->name)
+		__string(reporter_name, reporter_name)
+		__field(bool, health_state)
+		__field(u64, time_since_last_recover)
+	),
+
+	TP_fast_assign(
+		__assign_str(bus_name, devlink->dev->bus->name);
+		__assign_str(dev_name, dev_name(devlink->dev));
+		__assign_str(driver_name, devlink->dev->driver->name);
+		__assign_str(reporter_name, reporter_name);
+		__entry->health_state = health_state;
+		__entry->time_since_last_recover = time_since_last_recover;
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: health_state=%d time_since_last_recover=%llu recover aborted",
+		  __get_str(bus_name), __get_str(dev_name),
+		  __get_str(driver_name), __get_str(reporter_name),
+		  __entry->health_state,
+		  __entry->time_since_last_recover)
+);
+
+/*
+ * Tracepoint for devlink health reporter state update:
+ */
+TRACE_EVENT(devlink_health_reporter_state_update,
+	TP_PROTO(const struct devlink *devlink, const char *reporter_name,
+		 bool new_state),
+
+	TP_ARGS(devlink, reporter_name, new_state),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink->dev->bus->name)
+		__string(dev_name, dev_name(devlink->dev))
+		__string(driver_name, devlink->dev->driver->name)
+		__string(reporter_name, reporter_name)
+		__field(u8, new_state)
+	),
+
+	TP_fast_assign(
+		__assign_str(bus_name, devlink->dev->bus->name);
+		__assign_str(dev_name, dev_name(devlink->dev));
+		__assign_str(driver_name, devlink->dev->driver->name);
+		__assign_str(reporter_name, reporter_name);
+		__entry->new_state = new_state;
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: new_state=%d",
+		  __get_str(bus_name), __get_str(dev_name),
+		  __get_str(driver_name), __get_str(reporter_name),
+		  __entry->new_state)
+);
+
 #endif /* _TRACE_DEVLINK_H */
 
 /* This part must be outside protection */
@@ -64,6 +189,10 @@ static inline void trace_devlink_hwmsg(const struct devlink *devlink,
 {
 }
 
+static inline void trace_devlink_hwerr(const struct devlink *devlink,
+				       int err, const char *msg)
+{
+}
 #endif /* _TRACE_DEVLINK_H */
 
 #endif
diff --git a/include/trace/events/mlxsw.h b/include/trace/events/mlxsw.h
new file mode 100644
index 0000000000000..6a4cfaef33a21
--- /dev/null
+++ b/include/trace/events/mlxsw.h
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlxsw
+
+#if !defined(_MLXSW_TRACEPOINT_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _MLXSW_TRACEPOINT_H
+
+#include <linux/tracepoint.h>
+
+struct mlxsw_sp;
+struct mlxsw_sp_acl_atcam_region;
+struct mlxsw_sp_acl_tcam_vregion;
+
+TRACE_EVENT(mlxsw_sp_acl_atcam_entry_add_ctcam_spill,
+	TP_PROTO(const struct mlxsw_sp *mlxsw_sp,
+		 const struct mlxsw_sp_acl_atcam_region *aregion),
+
+	TP_ARGS(mlxsw_sp, aregion),
+
+	TP_STRUCT__entry(
+		__field(const void *, mlxsw_sp)
+		__field(const void *, aregion)
+	),
+
+	TP_fast_assign(
+		__entry->mlxsw_sp = mlxsw_sp;
+		__entry->aregion = aregion;
+	),
+
+	TP_printk("mlxsw_sp %p, aregion %p",
+		  __entry->mlxsw_sp, __entry->aregion)
+);
+
+TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_rehash,
+	TP_PROTO(const struct mlxsw_sp *mlxsw_sp,
+		 const struct mlxsw_sp_acl_tcam_vregion *vregion),
+
+	TP_ARGS(mlxsw_sp, vregion),
+
+	TP_STRUCT__entry(
+		__field(const void *, mlxsw_sp)
+		__field(const void *, vregion)
+	),
+
+	TP_fast_assign(
+		__entry->mlxsw_sp = mlxsw_sp;
+		__entry->vregion = vregion;
+	),
+
+	TP_printk("mlxsw_sp %p, vregion %p",
+		  __entry->mlxsw_sp, __entry->vregion)
+);
+
+TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_migrate,
+	TP_PROTO(const struct mlxsw_sp *mlxsw_sp,
+		 const struct mlxsw_sp_acl_tcam_vregion *vregion),
+
+	TP_ARGS(mlxsw_sp, vregion),
+
+	TP_STRUCT__entry(
+		__field(const void *, mlxsw_sp)
+		__field(const void *, vregion)
+	),
+
+	TP_fast_assign(
+		__entry->mlxsw_sp = mlxsw_sp;
+		__entry->vregion = vregion;
+	),
+
+	TP_printk("mlxsw_sp %p, vregion %p",
+		  __entry->mlxsw_sp, __entry->vregion)
+);
+
+TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_migrate_end,
+	TP_PROTO(const struct mlxsw_sp *mlxsw_sp,
+		 const struct mlxsw_sp_acl_tcam_vregion *vregion),
+
+	TP_ARGS(mlxsw_sp, vregion),
+
+	TP_STRUCT__entry(
+		__field(const void *, mlxsw_sp)
+		__field(const void *, vregion)
+	),
+
+	TP_fast_assign(
+		__entry->mlxsw_sp = mlxsw_sp;
+		__entry->vregion = vregion;
+	),
+
+	TP_printk("mlxsw_sp %p, vregion %p",
+		  __entry->mlxsw_sp, __entry->vregion)
+);
+
+TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_rehash_dis,
+	TP_PROTO(const struct mlxsw_sp *mlxsw_sp,
+		 const struct mlxsw_sp_acl_tcam_vregion *vregion),
+
+	TP_ARGS(mlxsw_sp, vregion),
+
+	TP_STRUCT__entry(
+		__field(const void *, mlxsw_sp)
+		__field(const void *, vregion)
+	),
+
+	TP_fast_assign(
+		__entry->mlxsw_sp = mlxsw_sp;
+		__entry->vregion = vregion;
+	),
+
+	TP_printk("mlxsw_sp %p, vregion %p",
+		  __entry->mlxsw_sp, __entry->vregion)
+);
+
+#endif /* _MLXSW_TRACEPOINT_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/neigh.h b/include/trace/events/neigh.h
new file mode 100644
index 0000000000000..0bdb08557763e
--- /dev/null
+++ b/include/trace/events/neigh.h
@@ -0,0 +1,206 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM neigh
+
+#if !defined(_TRACE_NEIGH_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NEIGH_H
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/tracepoint.h>
+#include <net/neighbour.h>
+
+#define neigh_state_str(state)				\
+	__print_symbolic(state,				\
+		{ NUD_INCOMPLETE, "incomplete" },	\
+		{ NUD_REACHABLE, "reachable" },		\
+		{ NUD_STALE, "stale" },			\
+		{ NUD_DELAY, "delay" },			\
+		{ NUD_PROBE, "probe" },			\
+		{ NUD_FAILED, "failed" },		\
+		{ NUD_NOARP, "noarp" },			\
+		{ NUD_PERMANENT, "permanent"})
+
+TRACE_EVENT(neigh_update,
+
+	TP_PROTO(struct neighbour *n, const u8 *lladdr, u8 new,
+		 u32 flags, u32 nlmsg_pid),
+
+	TP_ARGS(n, lladdr, new, flags, nlmsg_pid),
+
+	TP_STRUCT__entry(
+		__field(u32, family)
+		__string(dev, (n->dev ? n->dev->name : "NULL"))
+		__array(u8, lladdr, MAX_ADDR_LEN)
+		__field(u8, lladdr_len)
+		__field(u8, flags)
+		__field(u8, nud_state)
+		__field(u8, type)
+		__field(u8, dead)
+		__field(int, refcnt)
+		__array(__u8, primary_key4, 4)
+		__array(__u8, primary_key6, 16)
+		__field(unsigned long, confirmed)
+		__field(unsigned long, updated)
+		__field(unsigned long, used)
+		__array(u8, new_lladdr, MAX_ADDR_LEN)
+		__field(u8, new_state)
+		__field(u32, update_flags)
+		__field(u32, pid)
+	),
+
+	TP_fast_assign(
+		int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN);
+		struct in6_addr *pin6;
+		__be32 *p32;
+
+		__entry->family = n->tbl->family;
+		__assign_str(dev, (n->dev ? n->dev->name : "NULL"));
+		__entry->lladdr_len = lladdr_len;
+		memcpy(__entry->lladdr, n->ha, lladdr_len);
+		__entry->flags = n->flags;
+		__entry->nud_state = n->nud_state;
+		__entry->type = n->type;
+		__entry->dead = n->dead;
+		__entry->refcnt = refcount_read(&n->refcnt);
+		pin6 = (struct in6_addr *)__entry->primary_key6;
+		p32 = (__be32 *)__entry->primary_key4;
+
+		if (n->tbl->family == AF_INET)
+			*p32 = *(__be32 *)n->primary_key;
+		else
+			*p32 = 0;
+
+#if IS_ENABLED(CONFIG_IPV6)
+		if (n->tbl->family == AF_INET6) {
+			pin6 = (struct in6_addr *)__entry->primary_key6;
+			*pin6 = *(struct in6_addr *)n->primary_key;
+		} else
+#endif
+		{
+			ipv6_addr_set_v4mapped(*p32, pin6);
+		}
+		__entry->confirmed = n->confirmed;
+		__entry->updated = n->updated;
+		__entry->used = n->used;
+		if (lladdr)
+			memcpy(__entry->new_lladdr, lladdr, lladdr_len);
+		__entry->new_state = new;
+		__entry->update_flags = flags;
+		__entry->pid = nlmsg_pid;
+	),
+
+	TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x "
+		  "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c "
+		  "confirmed %lu updated %lu used %lu new_lladdr %s "
+		  "new_state %s update_flags %02x pid %d",
+		  __entry->family, __get_str(dev),
+		  __print_hex_str(__entry->lladdr, __entry->lladdr_len),
+		  __entry->flags, neigh_state_str(__entry->nud_state),
+		  __entry->type, __entry->dead, __entry->refcnt,
+		  __entry->primary_key4, __entry->primary_key6,
+		  __entry->confirmed, __entry->updated, __entry->used,
+		  __print_hex_str(__entry->new_lladdr, __entry->lladdr_len),
+		  neigh_state_str(__entry->new_state),
+		  __entry->update_flags, __entry->pid)
+);
+
+DECLARE_EVENT_CLASS(neigh__update,
+	TP_PROTO(struct neighbour *n, int err),
+	TP_ARGS(n, err),
+	TP_STRUCT__entry(
+		__field(u32, family)
+		__string(dev, (n->dev ? n->dev->name : "NULL"))
+		__array(u8, lladdr, MAX_ADDR_LEN)
+		__field(u8, lladdr_len)
+		__field(u8, flags)
+		__field(u8, nud_state)
+		__field(u8, type)
+		__field(u8, dead)
+		__field(int, refcnt)
+		__array(__u8, primary_key4, 4)
+		__array(__u8, primary_key6, 16)
+		__field(unsigned long, confirmed)
+		__field(unsigned long, updated)
+		__field(unsigned long, used)
+		__field(u32, err)
+	),
+
+	TP_fast_assign(
+		int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN);
+		struct in6_addr *pin6;
+		__be32 *p32;
+
+		__entry->family = n->tbl->family;
+		__assign_str(dev, (n->dev ? n->dev->name : "NULL"));
+		__entry->lladdr_len = lladdr_len;
+		memcpy(__entry->lladdr, n->ha, lladdr_len);
+		__entry->flags = n->flags;
+		__entry->nud_state = n->nud_state;
+		__entry->type = n->type;
+		__entry->dead = n->dead;
+		__entry->refcnt = refcount_read(&n->refcnt);
+		pin6 = (struct in6_addr *)__entry->primary_key6;
+		p32 = (__be32 *)__entry->primary_key4;
+
+		if (n->tbl->family == AF_INET)
+			*p32 = *(__be32 *)n->primary_key;
+		else
+			*p32 = 0;
+
+#if IS_ENABLED(CONFIG_IPV6)
+		if (n->tbl->family == AF_INET6) {
+			pin6 = (struct in6_addr *)__entry->primary_key6;
+			*pin6 = *(struct in6_addr *)n->primary_key;
+		} else
+#endif
+		{
+			ipv6_addr_set_v4mapped(*p32, pin6);
+		}
+
+		__entry->confirmed = n->confirmed;
+		__entry->updated = n->updated;
+		__entry->used = n->used;
+		__entry->err = err;
+	),
+
+	TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x "
+		  "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c "
+		  "confirmed %lu updated %lu used %lu err %d",
+		  __entry->family, __get_str(dev),
+		  __print_hex_str(__entry->lladdr, __entry->lladdr_len),
+		  __entry->flags, neigh_state_str(__entry->nud_state),
+		  __entry->type, __entry->dead, __entry->refcnt,
+		  __entry->primary_key4, __entry->primary_key6,
+		  __entry->confirmed, __entry->updated, __entry->used,
+		  __entry->err)
+);
+
+DEFINE_EVENT(neigh__update, neigh_update_done,
+	TP_PROTO(struct neighbour *neigh, int err),
+	TP_ARGS(neigh, err)
+);
+
+DEFINE_EVENT(neigh__update, neigh_timer_handler,
+	TP_PROTO(struct neighbour *neigh, int err),
+	TP_ARGS(neigh, err)
+);
+
+DEFINE_EVENT(neigh__update, neigh_event_send_done,
+	TP_PROTO(struct neighbour *neigh, int err),
+	TP_ARGS(neigh, err)
+);
+
+DEFINE_EVENT(neigh__update, neigh_event_send_dead,
+	TP_PROTO(struct neighbour *neigh, int err),
+	TP_ARGS(neigh, err)
+);
+
+DEFINE_EVENT(neigh__update, neigh_cleanup_and_release,
+	TP_PROTO(struct neighbour *neigh, int rc),
+	TP_ARGS(neigh, rc)
+);
+
+#endif /* _TRACE_NEIGH_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>