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

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 99 insertions, 5 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b7db3261c62d..66917a4eba27 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -75,6 +75,11 @@ struct bpf_lpm_trie_key {
         __u8    data[0];        /* Arbitrary size */
 };
 
+struct bpf_cgroup_storage_key {
+        __u64   cgroup_inode_id;        /* cgroup inode id */
+        __u32   attach_type;            /* program attach type */
+};
+
 /* BPF syscall commands, see bpf(2) man-page for details. */
 enum bpf_cmd {
         BPF_MAP_CREATE,
@@ -120,6 +125,8 @@ enum bpf_map_type {
         BPF_MAP_TYPE_CPUMAP,
         BPF_MAP_TYPE_XSKMAP,
         BPF_MAP_TYPE_SOCKHASH,
+        BPF_MAP_TYPE_CGROUP_STORAGE,
+        BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 };
 
 enum bpf_prog_type {
@@ -144,6 +151,7 @@ enum bpf_prog_type {
         BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
         BPF_PROG_TYPE_LWT_SEG6LOCAL,
         BPF_PROG_TYPE_LIRC_MODE2,
+        BPF_PROG_TYPE_SK_REUSEPORT,
 };
 
 enum bpf_attach_type {
@@ -1371,6 +1379,20 @@ union bpf_attr {
  *              A 8-byte long non-decreasing number on success, or 0 if the
  *              socket field is missing inside *skb*.
  *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
+ *      Description
+ *              Equivalent to bpf_get_socket_cookie() helper that accepts
+ *              *skb*, but gets socket from **struct bpf_sock_addr** contex.
+ *      Return
+ *              A 8-byte long non-decreasing number.
+ *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
+ *      Description
+ *              Equivalent to bpf_get_socket_cookie() helper that accepts
+ *              *skb*, but gets socket from **struct bpf_sock_ops** contex.
+ *      Return
+ *              A 8-byte long non-decreasing number.
+ *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
  *      Return
  *              The owner UID of the socket associated to *skb*. If the socket
@@ -1826,7 +1848,7 @@ union bpf_attr {
  *              A non-negative value equal to or less than *size* on success,
  *              or a negative error in case of failure.
  *
- * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
  *      Description
  *              This helper is similar to **bpf_skb_load_bytes**\ () in that
  *              it provides an easy way to load *len* bytes from *offset*
@@ -1877,7 +1899,7 @@ union bpf_attr {
  *              * < 0 if any input argument is invalid
  *              *   0 on success (packet is forwarded, nexthop neighbor exists)
  *              * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
- *              *     packet is not forwarded or needs assist from full stack
+ *                packet is not forwarded or needs assist from full stack
  *
  * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
  *      Description
@@ -2033,7 +2055,6 @@ union bpf_attr {
  *              This helper is only available is the kernel was compiled with
  *              the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *              "**y**".
- *
  *      Return
  *              0
  *
@@ -2053,7 +2074,6 @@ union bpf_attr {
  *              This helper is only available is the kernel was compiled with
  *              the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *              "**y**".
- *
  *      Return
  *              0
  *
@@ -2073,10 +2093,54 @@ union bpf_attr {
  *      Return
  *              The id is returned or 0 in case the id could not be retrieved.
  *
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ *      Description
+ *              Return id of cgroup v2 that is ancestor of cgroup associated
+ *              with the *skb* at the *ancestor_level*.  The root cgroup is at
+ *              *ancestor_level* zero and each step down the hierarchy
+ *              increments the level. If *ancestor_level* == level of cgroup
+ *              associated with *skb*, then return value will be same as that
+ *              of **bpf_skb_cgroup_id**\ ().
+ *
+ *              The helper is useful to implement policies based on cgroups
+ *              that are upper in hierarchy than immediate cgroup associated
+ *              with *skb*.
+ *
+ *              The format of returned id and helper limitations are same as in
+ *              **bpf_skb_cgroup_id**\ ().
+ *      Return
+ *              The id is returned or 0 in case the id could not be retrieved.
+ *
  * u64 bpf_get_current_cgroup_id(void)
  *      Return
  *              A 64-bit integer containing the current cgroup id based
  *              on the cgroup within which the current task is running.
+ *
+ * void* get_local_storage(void *map, u64 flags)
+ *      Description
+ *              Get the pointer to the local storage area.
+ *              The type and the size of the local storage is defined
+ *              by the *map* argument.
+ *              The *flags* meaning is specific for each map type,
+ *              and has to be 0 for cgroup local storage.
+ *
+ *              Depending on the bpf program type, a local storage area
+ *              can be shared between multiple instances of the bpf program,
+ *              running simultaneously.
+ *
+ *              A user should care about the synchronization by himself.
+ *              For example, by using the BPF_STX_XADD instruction to alter
+ *              the shared data.
+ *      Return
+ *              Pointer to the local storage area.
+ *
+ * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
+ *      Description
+ *              Select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY map
+ *              It checks the selected sk is matching the incoming
+ *              request in the skb.
+ *      Return
+ *              0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)           \
         FN(unspec),                     \
@@ -2159,7 +2223,10 @@ union bpf_attr {
         FN(rc_repeat),                  \
         FN(rc_keydown),                 \
         FN(skb_cgroup_id),              \
-        FN(get_current_cgroup_id),
+        FN(get_current_cgroup_id),      \
+        FN(get_local_storage),          \
+        FN(sk_select_reuseport),        \
+        FN(skb_ancestor_cgroup_id),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2376,6 +2443,30 @@ struct sk_msg_md {
         __u32 local_port;       /* stored in host byte order */
 };
 
+struct sk_reuseport_md {
+        /*
+         * Start of directly accessible data. It begins from
+         * the tcp/udp header.
+         */
+        void *data;
+        void *data_end;         /* End of directly accessible data */
+        /*
+         * Total length of packet (starting from the tcp/udp header).
+         * Note that the directly accessible bytes (data_end - data)
+         * could be less than this "len".  Those bytes could be
+         * indirectly read by a helper "bpf_skb_load_bytes()".
+         */
+        __u32 len;
+        /*
+         * Eth protocol in the mac header (network byte order). e.g.
+         * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD)
+         */
+        __u32 eth_protocol;
+        __u32 ip_protocol;      /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
+        __u32 bind_inany;       /* Is sock bound to an INANY address? */
+        __u32 hash;             /* A hash of the packet 4 tuples */
+};
+
 #define BPF_TAG_SIZE    8
 
 struct bpf_prog_info {
@@ -2557,6 +2648,9 @@ enum {
                                          * Arg1: old_state
                                          * Arg2: new_state
                                          */
+        BPF_SOCK_OPS_TCP_LISTEN_CB,     /* Called on listen(2), right after
+                                         * socket transition to LISTEN state.
+                                         */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect