1 files changed, 37 insertions, 19 deletions

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 852dc17ab47a..72c453a8bf50 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2170,7 +2170,7 @@ union bpf_attr {
  *      Return
  *              0 on success, or a negative error in case of failure.
  *
- * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *      Description
  *              Look for TCP socket matching *tuple*, optionally in a child
  *              network namespace *netns*. The return value must be checked,
@@ -2187,12 +2187,14 @@ union bpf_attr {
  *              **sizeof**\ (*tuple*\ **->ipv6**)
  *                      Look for an IPv6 socket.
  *
- *              If the *netns* is zero, then the socket lookup table in the
- *              netns associated with the *ctx* will be used. For the TC hooks,
- *              this in the netns of the device in the skb. For socket hooks,
- *              this in the netns of the socket. If *netns* is non-zero, then
- *              it specifies the ID of the netns relative to the netns
- *              associated with the *ctx*.
+ *              If the *netns* is a negative signed 32-bit integer, then the
+ *              socket lookup table in the netns associated with the *ctx* will
+ *              will be used. For the TC hooks, this is the netns of the device
+ *              in the skb. For socket hooks, this is the netns of the socket.
+ *              If *netns* is any other signed 32-bit value greater than or
+ *              equal to zero then it specifies the ID of the netns relative to
+ *              the netns associated with the *ctx*. *netns* values beyond the
+ *              range of 32-bit integers are reserved for future use.
  *
  *              All values for *flags* are reserved for future usage, and must
  *              be left at zero.
@@ -2201,8 +2203,10 @@ union bpf_attr {
  *              **CONFIG_NET** configuration option.
  *      Return
  *              Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *              For sockets with reuseport option, the *struct bpf_sock*
+ *              result is from reuse->socks[] using the hash of the tuple.
  *
- * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *      Description
  *              Look for UDP socket matching *tuple*, optionally in a child
  *              network namespace *netns*. The return value must be checked,
@@ -2219,12 +2223,14 @@ union bpf_attr {
  *              **sizeof**\ (*tuple*\ **->ipv6**)
  *                      Look for an IPv6 socket.
  *
- *              If the *netns* is zero, then the socket lookup table in the
- *              netns associated with the *ctx* will be used. For the TC hooks,
- *              this in the netns of the device in the skb. For socket hooks,
- *              this in the netns of the socket. If *netns* is non-zero, then
- *              it specifies the ID of the netns relative to the netns
- *              associated with the *ctx*.
+ *              If the *netns* is a negative signed 32-bit integer, then the
+ *              socket lookup table in the netns associated with the *ctx* will
+ *              will be used. For the TC hooks, this is the netns of the device
+ *              in the skb. For socket hooks, this is the netns of the socket.
+ *              If *netns* is any other signed 32-bit value greater than or
+ *              equal to zero then it specifies the ID of the netns relative to
+ *              the netns associated with the *ctx*. *netns* values beyond the
+ *              range of 32-bit integers are reserved for future use.
  *
  *              All values for *flags* are reserved for future usage, and must
  *              be left at zero.
@@ -2233,6 +2239,8 @@ union bpf_attr {
  *              **CONFIG_NET** configuration option.
  *      Return
  *              Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *              For sockets with reuseport option, the *struct bpf_sock*
+ *              result is from reuse->socks[] using the hash of the tuple.
  *
  * int bpf_sk_release(struct bpf_sock *sk)
  *      Description
@@ -2405,6 +2413,9 @@ enum bpf_func_id {
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
 #define BPF_F_CTXLEN_MASK               (0xfffffULL << 32)
 
+/* Current network namespace */
+#define BPF_F_CURRENT_NETNS             (-1L)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
         BPF_ADJ_ROOM_NET,
@@ -2422,6 +2433,12 @@ enum bpf_lwt_encap_mode {
         BPF_LWT_ENCAP_SEG6_INLINE
 };
 
+#define __bpf_md_ptr(type, name)        \
+union {                                 \
+        type name;                      \
+        __u64 :64;                      \
+} __attribute__((aligned(8)))
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
@@ -2456,7 +2473,7 @@ struct __sk_buff {
         /* ... here. */
 
         __u32 data_meta;
-        struct bpf_flow_keys *flow_keys;
+        __bpf_md_ptr(struct bpf_flow_keys *, flow_keys);
 };
 
 struct bpf_tunnel_key {
@@ -2572,8 +2589,8 @@ enum sk_action {
  * be added to the end of this structure
  */
 struct sk_msg_md {
-        void *data;
-        void *data_end;
+        __bpf_md_ptr(void *, data);
+        __bpf_md_ptr(void *, data_end);
 
         __u32 family;
         __u32 remote_ip4;       /* Stored in network byte order */
@@ -2589,8 +2606,9 @@ 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 */
+        __bpf_md_ptr(void *, data);
+        /* End of directly accessible data */
+        __bpf_md_ptr(void *, data_end);
         /*
          * Total length of packet (starting from the tcp/udp header).
          * Note that the directly accessible bytes (data_end - data)