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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

2 files changed, 133 insertions, 5 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4c223ab30293..db6bdc375126 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -17,7 +17,7 @@
 #define BPF_ALU64       0x07    /* alu mode in double word width */
 
 /* ld/ldx fields */
-#define BPF_DW          0x18    /* double word */
+#define BPF_DW          0x18    /* double word (64-bit) */
 #define BPF_XADD        0xc0    /* exclusive add */
 
 /* alu/jmp fields */
@@ -197,8 +197,14 @@ enum bpf_attach_type {
  */
 #define BPF_F_STRICT_ALIGNMENT  (1U << 0)
 
+/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
 #define BPF_PSEUDO_MAP_FD       1
 
+/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
+ * offset to another bpf function
+ */
+#define BPF_PSEUDO_CALL         1
+
 /* flags for BPF_MAP_UPDATE_ELEM command */
 #define BPF_ANY         0 /* create new element or update existing */
 #define BPF_NOEXIST     1 /* create new element if it didn't exist */
@@ -239,6 +245,7 @@ union bpf_attr {
                                          * BPF_F_NUMA_NODE is set).
                                          */
                 char    map_name[BPF_OBJ_NAME_LEN];
+                __u32   map_ifindex;    /* ifindex of netdev to create on */
         };
 
         struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -635,6 +642,14 @@ union bpf_attr {
  *     @optlen: length of optval in bytes
  *     Return: 0 or negative error
  *
+ * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags)
+ *     Set callback flags for sock_ops
+ *     @bpf_sock_ops: pointer to bpf_sock_ops_kern struct
+ *     @flags: flags value
+ *     Return: 0 for no error
+ *             -EINVAL if there is no full tcp socket
+ *             bits in flags that are not supported by current kernel
+ *
  * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
  *     Grow or shrink room in sk_buff.
  *     @skb: pointer to skb
@@ -677,6 +692,10 @@ union bpf_attr {
  *     @buf: buf to fill
  *     @buf_size: size of the buf
  *     Return : 0 on success or negative error code
+ *
+ * int bpf_override_return(pt_regs, rc)
+ *      @pt_regs: pointer to struct pt_regs
+ *      @rc: the return value to set
  */
 #define __BPF_FUNC_MAPPER(FN)           \
         FN(unspec),                     \
@@ -736,7 +755,9 @@ union bpf_attr {
         FN(xdp_adjust_meta),            \
         FN(perf_event_read_value),      \
         FN(perf_prog_read_value),       \
-        FN(getsockopt),
+        FN(getsockopt),                 \
+        FN(override_return),            \
+        FN(sock_ops_cb_flags_set),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -888,6 +909,9 @@ struct xdp_md {
         __u32 data;
         __u32 data_end;
         __u32 data_meta;
+        /* Below access go through struct xdp_rxq_info */
+        __u32 ingress_ifindex; /* rxq->dev->ifindex */
+        __u32 rx_queue_index;  /* rxq->queue_index  */
 };
 
 enum sk_action {
@@ -910,6 +934,9 @@ struct bpf_prog_info {
         __u32 nr_map_ids;
         __aligned_u64 map_ids;
         char name[BPF_OBJ_NAME_LEN];
+        __u32 ifindex;
+        __u64 netns_dev;
+        __u64 netns_ino;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -920,6 +947,9 @@ struct bpf_map_info {
         __u32 max_entries;
         __u32 map_flags;
         char  name[BPF_OBJ_NAME_LEN];
+        __u32 ifindex;
+        __u64 netns_dev;
+        __u64 netns_ino;
 } __attribute__((aligned(8)));
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
@@ -931,8 +961,9 @@ struct bpf_map_info {
 struct bpf_sock_ops {
         __u32 op;
         union {
-                __u32 reply;
-                __u32 replylong[4];
+                __u32 args[4];          /* Optionally passed to bpf program */
+                __u32 reply;            /* Returned by bpf program          */
+                __u32 replylong[4];     /* Optionally returned by bpf prog  */
         };
         __u32 family;
         __u32 remote_ip4;       /* Stored in network byte order */
@@ -941,8 +972,45 @@ struct bpf_sock_ops {
         __u32 local_ip6[4];     /* Stored in network byte order */
         __u32 remote_port;      /* Stored in network byte order */
         __u32 local_port;       /* stored in host byte order */
+        __u32 is_fullsock;      /* Some TCP fields are only valid if
+                                 * there is a full socket. If not, the
+                                 * fields read as zero.
+                                 */
+        __u32 snd_cwnd;
+        __u32 srtt_us;          /* Averaged RTT << 3 in usecs */
+        __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */
+        __u32 state;
+        __u32 rtt_min;
+        __u32 snd_ssthresh;
+        __u32 rcv_nxt;
+        __u32 snd_nxt;
+        __u32 snd_una;
+        __u32 mss_cache;
+        __u32 ecn_flags;
+        __u32 rate_delivered;
+        __u32 rate_interval_us;
+        __u32 packets_out;
+        __u32 retrans_out;
+        __u32 total_retrans;
+        __u32 segs_in;
+        __u32 data_segs_in;
+        __u32 segs_out;
+        __u32 data_segs_out;
+        __u32 lost_out;
+        __u32 sacked_out;
+        __u32 sk_txhash;
+        __u64 bytes_received;
+        __u64 bytes_acked;
 };
 
+/* Definitions for bpf_sock_ops_cb_flags */
+#define BPF_SOCK_OPS_RTO_CB_FLAG        (1<<0)
+#define BPF_SOCK_OPS_RETRANS_CB_FLAG    (1<<1)
+#define BPF_SOCK_OPS_STATE_CB_FLAG      (1<<2)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x7             /* Mask of all currently
+                                                         * supported cb flags
+                                                         */
+
 /* List of known BPF sock_ops operators.
  * New entries can only be added at the end
  */
@@ -976,6 +1044,43 @@ enum {
                                          * a congestion threshold. RTTs above