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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 150 insertions, 8 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 30f2ce76b517..e880ae6434ee 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -93,6 +93,7 @@ enum bpf_cmd {
         BPF_PROG_GET_FD_BY_ID,
         BPF_MAP_GET_FD_BY_ID,
         BPF_OBJ_GET_INFO_BY_FD,
+        BPF_PROG_QUERY,
 };
 
 enum bpf_map_type {
@@ -112,6 +113,7 @@ enum bpf_map_type {
         BPF_MAP_TYPE_HASH_OF_MAPS,
         BPF_MAP_TYPE_DEVMAP,
         BPF_MAP_TYPE_SOCKMAP,
+        BPF_MAP_TYPE_CPUMAP,
 };
 
 enum bpf_prog_type {
@@ -130,6 +132,7 @@ enum bpf_prog_type {
         BPF_PROG_TYPE_LWT_XMIT,
         BPF_PROG_TYPE_SOCK_OPS,
         BPF_PROG_TYPE_SK_SKB,
+        BPF_PROG_TYPE_CGROUP_DEVICE,
 };
 
 enum bpf_attach_type {
@@ -139,16 +142,53 @@ enum bpf_attach_type {
         BPF_CGROUP_SOCK_OPS,
         BPF_SK_SKB_STREAM_PARSER,
         BPF_SK_SKB_STREAM_VERDICT,
+        BPF_CGROUP_DEVICE,
         __MAX_BPF_ATTACH_TYPE
 };
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
-/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
- * to the given target_fd cgroup the descendent cgroup will be able to
- * override effective bpf program that was inherited from this cgroup
+/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
+ *
+ * NONE(default): No further bpf programs allowed in the subtree.
+ *
+ * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
+ * the program in this cgroup yields to sub-cgroup program.
+ *
+ * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
+ * that cgroup program gets run in addition to the program in this cgroup.
+ *
+ * Only one program is allowed to be attached to a cgroup with
+ * NONE or BPF_F_ALLOW_OVERRIDE flag.
+ * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
+ * release old program and attach the new one. Attach flags has to match.
+ *
+ * Multiple programs are allowed to be attached to a cgroup with
+ * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
+ * (those that were attached first, run first)
+ * The programs of sub-cgroup are executed first, then programs of
+ * this cgroup and then programs of parent cgroup.
+ * When children program makes decision (like picking TCP CA or sock bind)
+ * parent program has a chance to override it.
+ *
+ * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
+ * A cgroup with NONE doesn't allow any programs in sub-cgroups.
+ * Ex1:
+ * cgrp1 (MULTI progs A, B) ->
+ *    cgrp2 (OVERRIDE prog C) ->
+ *      cgrp3 (MULTI prog D) ->
+ *        cgrp4 (OVERRIDE prog E) ->
+ *          cgrp5 (NONE prog F)
+ * the event in cgrp5 triggers execution of F,D,A,B in that order.
+ * if prog F is detached, the execution is E,D,A,B
+ * if prog F and D are detached, the execution is E,A,B
+ * if prog F, E and D are detached, the execution is C,A,B
+ *
+ * All eligible programs are executed regardless of return code from
+ * earlier programs.
  */
 #define BPF_F_ALLOW_OVERRIDE    (1U << 0)
+#define BPF_F_ALLOW_MULTI       (1U << 1)
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -176,6 +216,15 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE         (1U << 2)
 
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE   (1U << 0)
+
+#define BPF_OBJ_NAME_LEN 16U
+
+/* Flags for accessing BPF object */
+#define BPF_F_RDONLY            (1U << 3)
+#define BPF_F_WRONLY            (1U << 4)
+
 union bpf_attr {
         struct { /* anonymous struct used by BPF_MAP_CREATE command */
                 __u32   map_type;       /* one of enum bpf_map_type */
@@ -189,6 +238,7 @@ union bpf_attr {
                 __u32   numa_node;      /* numa node (effective only if
                                          * BPF_F_NUMA_NODE is set).
                                          */
+                char    map_name[BPF_OBJ_NAME_LEN];
         };
 
         struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -211,11 +261,14 @@ union bpf_attr {
                 __aligned_u64   log_buf;        /* user supplied buffer */
                 __u32           kern_version;   /* checked when prog_type=kprobe */
                 __u32           prog_flags;
+                char            prog_name[BPF_OBJ_NAME_LEN];
+                __u32           prog_target_ifindex;    /* ifindex of netdev to prep for */
         };
 
         struct { /* anonymous struct used by BPF_OBJ_* commands */
                 __aligned_u64   pathname;
                 __u32           bpf_fd;
+                __u32           file_flags;
         };
 
         struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
@@ -243,6 +296,7 @@ union bpf_attr {
                         __u32           map_id;
                 };
                 __u32           next_id;
+                __u32           open_flags;
         };
 
         struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
@@ -250,6 +304,15 @@ union bpf_attr {
                 __u32           info_len;
                 __aligned_u64   info;
         } info;
+
+        struct { /* anonymous struct used by BPF_PROG_QUERY command */
+                __u32           target_fd;      /* container object to query */
+                __u32           attach_type;
+                __u32           query_flags;
+                __u32           attach_flags;
+                __aligned_u64   prog_ids;
+                __u32           prog_cnt;
+        } query;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -554,12 +617,22 @@ union bpf_attr {
  * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
  *     Calls setsockopt. Not all opts are available, only those with
  *     integer optvals plus TCP_CONGESTION.
- *     Supported levels: SOL_SOCKET and IPROTO_TCP
+ *     Supported levels: SOL_SOCKET and IPPROTO_TCP
+ *     @bpf_socket: pointer to bpf_socket
+ *     @level: SOL_SOCKET or IPPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @optlen: length of optval in bytes
+ *     Return: 0 or negative error
+ *
+ * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen)
+ *     Calls getsockopt. Not all opts are available.
+ *     Supported levels: IPPROTO_TCP
  *     @bpf_socket: pointer to bpf_socket
- *     @level: SOL_SOCKET or IPROTO_TCP
+ *     @level: IPPROTO_TCP
  *     @optname: option name
  *     @optval: pointer to option value
- *     @optlen: length of optval in byes
+ *     @optlen: length of optval in bytes
  *     Return: 0 or negative error
  *
  * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
@@ -583,6 +656,27 @@ union bpf_attr {
  *      @map: pointer to sockmap to update
  *      @key: key to insert/update sock in map
  *      @flags: same flags as map update elem
+ *
+ * int bpf_xdp_adjust_meta(xdp_md, delta)
+ *     Adjust the xdp_md.data_meta by delta
+ *     @xdp_md: pointer to xdp_md
+ *     @delta: An positive/negative integer to be added to xdp_md.data_meta
+ *     Return: 0 on success or negative on error
+ *
+ * int bpf_perf_event_read_value(map, flags, buf, buf_size)
+ *     read perf event counter value and perf event enabled/running time
+ *     @map: pointer to perf_event_array map
+ *     @flags: index of event in the map or bitmask flags
+ *     @buf: buf to fill
+ *     @buf_size: size of the buf
+ *     Return: 0 on success or negative error code
+ *
+ * int bpf_perf_prog_read_value(ctx, buf, buf_size)
+ *     read perf prog attached perf event counter and enabled/running time
+ *     @ctx: pointer to ctx
+ *     @buf: buf to fill
+ *     @buf_size: size of the buf
+ *     Return : 0 on success or negative error code
  */
 #define __BPF_FUNC_MAPPER(FN)           \
         FN(unspec),                     \
@@ -639,6 +733,10 @@ union bpf_attr {
         FN(redirect_map),               \
         FN(sk_redirect_map),            \
         FN(sock_map_update),            \
+        FN(xdp_adjust_meta),            \
+        FN(perf_event_read_value),      \
+        FN(perf_prog_read_value),       \
+        FN(getsockopt),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -682,7 +780,9 @@ enum bpf_func_id {
 #define BPF_F_ZERO_CSUM_TX              (1ULL << 1)
 #define BPF_F_DONT_FRAGMENT             (1ULL << 2)
 
-/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
+/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
+ * BPF_FUNC_perf_event_read_value flags.
+ */
 #define BPF_F_INDEX_MASK                0xffffffffULL
 #define BPF_F_CURRENT_CPU               BPF_F_INDEX_MASK
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
@@ -716,7 +816,7 @@ struct __sk_buff {
         __u32 data_end;
         __u32 napi_id;
 
-        /* accessed by BPF_PROG_TYPE_sk_skb types */
+        /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
         __u32 family;
         __u32 remote_ip4;       /* Stored in network byte order */
         __u32 local_ip4;        /* Stored in network byte order */
@@ -724,6 +824,9 @@ struct __sk_buff {
         __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 */
+        /* ... here. */
+
+        __u32 data_meta;
 };
 
 struct bpf_tunnel_key {
@@ -784,6 +887,7 @@ enum xdp_action {
 struct xdp_md {
         __u32 data;
         __u32 data_end;
+        __u32 data_meta;
 };
 
 enum sk_action {
@@ -793,6 +897,10 @@ enum sk_action {
 
 #define BPF_TAG_SIZE    8
 
+enum bpf_prog_status {
+        BPF_PROG_STATUS_DEV_BOUND       = (1 << 0),
+};
+
 struct bpf_prog_info {
         __u32 type;
         __u32 id;
@@ -801,6 +909,13 @@ struct bpf_prog_info {
         __u32 xlated_prog_len;
         __aligned_u64 jited_prog_insns;
         __aligned_u64 xlated_prog_insns;
+        __u64 load_time;        /* ns since boottime */
+        __u32 created_by_uid;
+        __u32 nr_map_ids;
+        __aligned_u64 map_ids;
+        char name[BPF_OBJ_NAME_LEN];
+        __u32 ifindex;
+        __u32 status;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -810,6 +925,7 @@ struct bpf_map_info {
         __u32 value_size;
         __u32 max_entries;
         __u32 map_flags;
+        char  name[BPF_OBJ_NAME_LEN];
 } __attribute__((aligned(8)));
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
@@ -859,9 +975,35 @@ enum {
         BPF_SOCK_OPS_NEEDS_ECN,         /* If connection's congestion control
                                          * needs ECN
                                          */
+        BPF_SOCK_OPS_BASE_RTT,          /* Get base RTT. The correct value is
+                                         * based on the path and may be
+                                         * dependent on the congestion control
+                                         * algorithm. In general it indicates
+                                         * a congestion threshold. RTTs above
+                                         * this indicate congestion
+                                         */
 };
 
 #define TCP_BPF_IW              1001    /* Set TCP initial congestion window */
 #define TCP_BPF_SNDCWND_CLAMP   1002    /* Set sndcwnd_clamp */
 
+struct bpf_perf_event_value {
+        __u64 counter;
+        __u64 enabled;
+        __u64 running;
+};
+
+#define BPF_DEVCG_ACC_MKNOD     (1ULL << 0)
+#define BPF_DEVCG_ACC_READ      (1ULL << 1)
+#define BPF_DEVCG_ACC_WRITE     (1ULL << 2)
+
+#define BPF_DEVCG_DEV_BLOCK     (1ULL << 0)
+#define BPF_DEVCG_DEV_CHAR      (1ULL << 1)
+
+struct bpf_cgroup_dev_ctx {
+        __u32 access_type; /* (access << 16) | type */
+        __u32 major;
+        __u32 minor;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */