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

Pull networking changes from David S Miller:

 1) Remove the ipv4 routing cache.  Now lookups go directly into the FIB
    trie and use prebuilt routes cached there.

    No more garbage collection, no more rDOS attacks on the routing
    cache.  Instead we now get predictable and consistent performance,
    no matter what the pattern of traffic we service.

    This has been almost 2 years in the making.  Special thanks to
    Julian Anastasov, Eric Dumazet, Steffen Klassert, and others who
    have helped along the way.

    I'm sure that with a change of this magnitude there will be some
    kind of fallout, but such things ought the be simple to fix at this
    point.  Luckily I'm not European so I'll be around all of August to
    fix things :-)

    The major stages of this work here are each fronted by a forced
    merge commit whose commit message contains a top-level description
    of the motivations and implementation issues.

 2) Pre-demux of established ipv4 TCP sockets, saves a route demux on
    input.

 3) TCP SYN/ACK performance tweaks from Eric Dumazet.

 4) Add namespace support for netfilter L4 conntrack helpers, from Gao
    Feng.

 5) Add config mechanism for Energy Efficient Ethernet to ethtool, from
    Yuval Mintz.

 6) Remove quadratic behavior from /proc/net/unix, from Eric Dumazet.

 7) Support for connection tracker helpers in userspace, from Pablo
    Neira Ayuso.

 8) Allow userspace driven TX load balancing functions in TEAM driver,
    from Jiri Pirko.

 9) Kill off NLMSG_PUT and RTA_PUT macros, more gross stuff with
    embedded gotos.

10) TCP Small Queues, essentially minimize the amount of TCP data queued
    up in the packet scheduler layer.  Whereas the existing BQL (Byte
    Queue Limits) limits the pkt_sched --> netdevice queuing levels,
    this controls the TCP --> pkt_sched queueing levels.

    From Eric Dumazet.

11) Reduce the number of get_page/put_page ops done on SKB fragments,
    from Alexander Duyck.

12) Implement protection against blind resets in TCP (RFC 5961), from
    Eric Dumazet.

13) Support the client side of TCP Fast Open, basically the ability to
    send data in the SYN exchange, from Yuchung Cheng.

    Basically, the sender queues up data with a sendmsg() call using
    MSG_FASTOPEN, then they do the connect() which emits the queued up
    fastopen data.

14) Avoid all the problems we get into in TCP when timers or PMTU events
    hit a locked socket.  The TCP Small Queues changes added a
    tcp_release_cb() that allows us to queue work up to the
    release_sock() caller, and that's what we use here too.  From Eric
    Dumazet.

15) Zero copy on TX support for TUN driver, from Michael S. Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1870 commits)
  genetlink: define lockdep_genl_is_held() when CONFIG_LOCKDEP
  r8169: revert "add byte queue limit support".
  ipv4: Change rt->rt_iif encoding.
  net: Make skb->skb_iif always track skb->dev
  ipv4: Prepare for change of rt->rt_iif encoding.
  ipv4: Remove all RTCF_DIRECTSRC handliing.
  ipv4: Really ignore ICMP address requests/replies.
  decnet: Don't set RTCF_DIRECTSRC.
  net/ipv4/ip_vti.c: Fix __rcu warnings detected by sparse.
  ipv4: Remove redundant assignment
  rds: set correct msg_namelen
  openvswitch: potential NULL deref in sample()
  tcp: dont drop MTU reduction indications
  bnx2x: Add new 57840 device IDs
  tcp: avoid oops in tcp_metrics and reset tcpm_stamp
  niu: Change niu_rbr_fill() to use unlikely() to check niu_rbr_add_page() return value
  niu: Fix to check for dma mapping errors.
  net: Fix references to out-of-scope variables in put_cmsg_compat()
  net: ethernet: davinci_emac: add pm_runtime support
  net: ethernet: davinci_emac: Remove unnecessary #include
  ...

1 files changed, 135 insertions, 4 deletions

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 6a8f002b8ed..4d7761f8c3f 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -36,6 +36,7 @@
 #include <linux/pci.h>
 #include <linux/completion.h>
 #include <linux/radix-tree.h>
+#include <linux/cpu_rmap.h>
 
 #include <linux/atomic.h>
 
@@ -70,6 +71,36 @@ enum {
 	MLX4_MFUNC_EQE_MASK     = (MLX4_MFUNC_MAX_EQES - 1)
 };
 
+/* Driver supports 3 diffrent device methods to manage traffic steering:
+ *	-device managed - High level API for ib and eth flow steering. FW is
+ *			  managing flow steering tables.
+ *	- B0 steering mode - Common low level API for ib and (if supported) eth.
+ *	- A0 steering mode - Limited low level API for eth. In case of IB,
+ *			     B0 mode is in use.
+ */
+enum {
+	MLX4_STEERING_MODE_A0,
+	MLX4_STEERING_MODE_B0,
+	MLX4_STEERING_MODE_DEVICE_MANAGED
+};
+
+static inline const char *mlx4_steering_mode_str(int steering_mode)
+{
+	switch (steering_mode) {
+	case MLX4_STEERING_MODE_A0:
+		return "A0 steering";
+
+	case MLX4_STEERING_MODE_B0:
+		return "B0 steering";
+
+	case MLX4_STEERING_MODE_DEVICE_MANAGED:
+		return "Device managed flow steering";
+
+	default:
+		return "Unrecognize steering mode";
+	}
+}
+
 enum {
 	MLX4_DEV_CAP_FLAG_RC		= 1LL <<  0,
 	MLX4_DEV_CAP_FLAG_UC		= 1LL <<  1,
@@ -102,7 +133,8 @@ enum {
 enum {
 	MLX4_DEV_CAP_FLAG2_RSS			= 1LL <<  0,
 	MLX4_DEV_CAP_FLAG2_RSS_TOP		= 1LL <<  1,
-	MLX4_DEV_CAP_FLAG2_RSS_XOR		= 1LL <<  2
+	MLX4_DEV_CAP_FLAG2_RSS_XOR		= 1LL <<  2,
+	MLX4_DEV_CAP_FLAG2_FS_EN		= 1LL <<  3
 };
 
 #define MLX4_ATTR_EXTENDED_PORT_INFO	cpu_to_be16(0xff90)
@@ -295,6 +327,8 @@ struct mlx4_caps {
 	int			num_amgms;
 	int			reserved_mcgs;
 	int			num_qp_per_mgm;
+	int			steering_mode;
+	int			fs_log_max_ucast_qp_range_size;
 	int			num_pds;
 	int			reserved_pds;
 	int			max_xrcds;
@@ -509,6 +543,8 @@ struct mlx4_dev {
 	u8			rev_id;
 	char			board_id[MLX4_BOARD_ID_LEN];
 	int			num_vfs;
+	u64			regid_promisc_array[MLX4_MAX_PORTS + 1];
+	u64			regid_allmulti_array[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_init_port_param {
@@ -623,9 +659,99 @@ int mlx4_unicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 int mlx4_unicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			enum mlx4_protocol prot);
 int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
-			  int block_mcast_loopback, enum mlx4_protocol protocol);
+			  u8 port, int block_mcast_loopback,
+			  enum mlx4_protocol protocol, u64 *reg_id);
 int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
-			  enum mlx4_protocol protocol);
+			  enum mlx4_protocol protocol, u64 reg_id);
+
+enum {
+	MLX4_DOMAIN_UVERBS	= 0x1000,
+	MLX4_DOMAIN_ETHTOOL     = 0x2000,
+	MLX4_DOMAIN_RFS         = 0x3000,
+	MLX4_DOMAIN_NIC    = 0x5000,
+};
+
+enum mlx4_net_trans_rule_id {
+	MLX4_NET_TRANS_RULE_ID_ETH = 0,
+	MLX4_NET_TRANS_RULE_ID_IB,
+	MLX4_NET_TRANS_RULE_ID_IPV6,
+	MLX4_NET_TRANS_RULE_ID_IPV4,
+	MLX4_NET_TRANS_RULE_ID_TCP,
+	MLX4_NET_TRANS_RULE_ID_UDP,
+	MLX4_NET_TRANS_RULE_NUM, /* should be last */
+};
+
+enum mlx4_net_trans_promisc_mode {
+	MLX4_FS_PROMISC_NONE = 0,
+	MLX4_FS_PROMISC_UPLINK,
+	/* For future use. Not implemented yet */
+	MLX4_FS_PROMISC_FUNCTION_PORT,
+	MLX4_FS_PROMISC_ALL_MULTI,
+};
+
+struct mlx4_spec_eth {
+	u8	dst_mac[6];
+	u8	dst_mac_msk[6];
+	u8	src_mac[6];
+	u8	src_mac_msk[6];
+	u8	ether_type_enable;
+	__be16	ether_type;
+	__be16	vlan_id_msk;
+	__be16	vlan_id;
+};
+
+struct mlx4_spec_tcp_udp {
+	__be16 dst_port;
+	__be16 dst_port_msk;
+	__be16 src_port;
+	__be16 src_port_msk;
+};
+
+struct mlx4_spec_ipv4 {
+	__be32 dst_ip;
+	__be32 dst_ip_msk;
+	__be32 src_ip;
+	__be32 src_ip_msk;
+};
+
+struct mlx4_spec_ib {
+	__be32	r_qpn;
+	__be32	qpn_msk;
+	u8	dst_gid[16];
+	u8	dst_gid_msk[16];
+};
+
+struct mlx4_spec_list {
+	struct	list_head list;
+	enum	mlx4_net_trans_rule_id id;
+	union {
+		struct mlx4_spec_eth eth;
+		struct mlx4_spec_ib ib;
+		struct mlx4_spec_ipv4 ipv4;
+		struct mlx4_spec_tcp_udp tcp_udp;
+	};
+};
+
+enum mlx4_net_trans_hw_rule_queue {
+	MLX4_NET_TRANS_Q_FIFO,
+	MLX4_NET_TRANS_Q_LIFO,
+};
+
+struct mlx4_net_trans_rule {
+	struct	list_head list;
+	enum	mlx4_net_trans_hw_rule_queue queue_mode;
+	bool	exclusive;
+	bool	allow_loopback;
+	enum	mlx4_net_trans_promisc_mode promisc_mode;
+	u8	port;
+	u16	priority;
+	u32	qpn;
+};
+
+int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn,
+				enum mlx4_net_trans_promisc_mode mode);
+int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port,
+				   enum mlx4_net_trans_promisc_mode mode);
 int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port);
 int mlx4_multicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port);
 int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port);
@@ -659,7 +785,8 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
 int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
 int mlx4_SYNC_TPT(struct mlx4_dev *dev);
 int mlx4_test_interrupts(struct mlx4_dev *dev);
-int mlx4_assign_eq(struct mlx4_dev *dev, char* name , int* vector);
+int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
+		   int *vector);
 void mlx4_release_eq(struct mlx4_dev *dev, int vec);
 
 int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port);
@@ -668,4 +795,8 @@ int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);
 int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx);
 void mlx4_counter_free(struct mlx4_dev *dev, u32 idx);
 
+int mlx4_flow_attach(struct mlx4_dev *dev,
+		     struct mlx4_net_trans_rule *rule, u64 *reg_id);
+int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id);
+
 #endif /* MLX4_DEVICE_H */