uapi: update headers
Update kernel headers from 5.8.0 merge
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index dc5314d..6cad144 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -116,6 +116,7 @@
BPF_LINK_GET_FD_BY_ID,
BPF_LINK_GET_NEXT_ID,
BPF_ENABLE_STATS,
+ BPF_ITER_CREATE,
};
enum bpf_map_type {
@@ -146,6 +147,7 @@
BPF_MAP_TYPE_SK_STORAGE,
BPF_MAP_TYPE_DEVMAP_HASH,
BPF_MAP_TYPE_STRUCT_OPS,
+ BPF_MAP_TYPE_RINGBUF,
};
/* Note that tracing related programs such as
@@ -218,6 +220,12 @@
BPF_TRACE_FEXIT,
BPF_MODIFY_RETURN,
BPF_LSM_MAC,
+ BPF_TRACE_ITER,
+ BPF_CGROUP_INET4_GETPEERNAME,
+ BPF_CGROUP_INET6_GETPEERNAME,
+ BPF_CGROUP_INET4_GETSOCKNAME,
+ BPF_CGROUP_INET6_GETSOCKNAME,
+ BPF_XDP_DEVMAP,
__MAX_BPF_ATTACH_TYPE
};
@@ -228,6 +236,8 @@
BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
BPF_LINK_TYPE_TRACING = 2,
BPF_LINK_TYPE_CGROUP = 3,
+ BPF_LINK_TYPE_ITER = 4,
+ BPF_LINK_TYPE_NETNS = 5,
MAX_BPF_LINK_TYPE,
};
@@ -612,6 +622,11 @@
__u32 type;
} enable_stats;
+ struct { /* struct used by BPF_ITER_CREATE command */
+ __u32 link_fd;
+ __u32 flags;
+ } iter_create;
+
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF
@@ -667,8 +682,8 @@
* For tracing programs, safely attempt to read *size* bytes from
* kernel space address *unsafe_ptr* and store the data in *dst*.
*
- * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
- * instead.
+ * Generally, use **bpf_probe_read_user**\ () or
+ * **bpf_probe_read_kernel**\ () instead.
* Return
* 0 on success, or a negative error in case of failure.
*
@@ -676,7 +691,7 @@
* Description
* Return the time elapsed since system boot, in nanoseconds.
* Does not include time the system was suspended.
- * See: clock_gettime(CLOCK_MONOTONIC)
+ * See: **clock_gettime**\ (**CLOCK_MONOTONIC**)
* Return
* Current *ktime*.
*
@@ -1535,11 +1550,11 @@
* int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
* Copy a NUL terminated string from an unsafe kernel address
- * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for
+ * *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for
* more details.
*
- * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str()
- * instead.
+ * Generally, use **bpf_probe_read_user_str**\ () or
+ * **bpf_probe_read_kernel_str**\ () instead.
* Return
* On success, the strictly positive length of the string,
* including the trailing NUL character. On error, a negative
@@ -1567,7 +1582,7 @@
*
* u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
* Description
- * Equivalent to bpf_get_socket_cookie() helper that accepts
+ * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
* *skb*, but gets socket from **struct bpf_sock_ops** context.
* Return
* A 8-byte long non-decreasing number.
@@ -1596,6 +1611,7 @@
* The option value of length *optlen* is pointed by *optval*.
*
* *bpf_socket* should be one of the following:
+ *
* * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
* * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
* and **BPF_CGROUP_INET6_CONNECT**.
@@ -1619,6 +1635,13 @@
* Grow or shrink the room for data in the packet associated to
* *skb* by *len_diff*, and according to the selected *mode*.
*
+ * By default, the helper will reset any offloaded checksum
+ * indicator of the skb to CHECKSUM_NONE. This can be avoided
+ * by the following flag:
+ *
+ * * **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded
+ * checksum data of the skb to CHECKSUM_NONE.
+ *
* There are two supported modes at this time:
*
* * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
@@ -1664,12 +1687,12 @@
*
* The lower two bits of *flags* are used as the return code if
* the map lookup fails. This is so that the return value can be
- * one of the XDP program return codes up to XDP_TX, as chosen by
- * the caller. Any higher bits in the *flags* argument must be
+ * one of the XDP program return codes up to **XDP_TX**, as chosen
+ * by the caller. Any higher bits in the *flags* argument must be
* unset.
*
- * See also bpf_redirect(), which only supports redirecting to an
- * ifindex, but doesn't require a map to do so.
+ * See also **bpf_redirect**\ (), which only supports redirecting
+ * to an ifindex, but doesn't require a map to do so.
* Return
* **XDP_REDIRECT** on success, or the value of the two lower bits
* of the *flags* argument on error.
@@ -1777,7 +1800,7 @@
* the time running for event since last normalization. The
* enabled and running times are accumulated since the perf event
* open. To achieve scaling factor between two invocations of an
- * eBPF program, users can can use CPU id as the key (which is
+ * eBPF program, users can use CPU id as the key (which is
* typical for perf array usage model) to remember the previous
* value and do the calculation inside the eBPF program.
* Return
@@ -1804,6 +1827,7 @@
* *opval* and of length *optlen*.
*
* *bpf_socket* should be one of the following:
+ *
* * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
* * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
* and **BPF_CGROUP_INET6_CONNECT**.
@@ -1825,7 +1849,7 @@
* The first argument is the context *regs* on which the kprobe
* works.
*
- * This helper works by setting setting the PC (program counter)
+ * This helper works by setting the PC (program counter)
* to an override function which is run in place of the original
* probed function. This means the probed function is not run at
* all. The replacement function just returns with the required
@@ -1994,18 +2018,19 @@
*
* This helper works for IPv4 and IPv6, TCP and UDP sockets. The
* domain (*addr*\ **->sa_family**) must be **AF_INET** (or
- * **AF_INET6**). Looking for a free port to bind to can be
- * expensive, therefore binding to port is not permitted by the
- * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively)
- * must be set to zero.
+ * **AF_INET6**). It's advised to pass zero port (**sin_port**
+ * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like
+ * behavior and lets the kernel efficiently pick up an unused
+ * port as long as 4-tuple is unique. Passing non-zero port might
+ * lead to degraded performance.
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta)
* Description
* Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is
- * only possible to shrink the packet as of this writing,
- * therefore *delta* must be a negative integer.
+ * possible to both shrink and grow the packet tail.
+ * Shrink done via *delta* being a negative integer.
*
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
@@ -2291,7 +2316,7 @@
* **bpf_rc_keydown**\ () again with the same values, or calling
* **bpf_rc_repeat**\ ().
*
- * Some protocols include a toggle bit, in case the button was
+ * Some protocols include a toggle bit, in case the button was
* released and pressed again between consecutive scancodes.
*
* The *ctx* should point to the lirc sample as passed into
@@ -2637,7 +2662,6 @@
*
* *th* points to the start of the TCP header, while *th_len*
* contains **sizeof**\ (**struct tcphdr**).
- *
* Return
* 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
* error otherwise.
@@ -2820,7 +2844,6 @@
*
* *th* points to the start of the TCP header, while *th_len*
* contains the length of the TCP header.
- *
* Return
* On success, lower 32 bits hold the generated SYN cookie in
* followed by 16 bits which hold the MSS value for that cookie,
@@ -2903,7 +2926,7 @@
* // size, after checking its boundaries.
* }
*
- * In comparison, using **bpf_probe_read_user()** helper here
+ * In comparison, using **bpf_probe_read_user**\ () helper here
* instead to read the string would require to estimate the length
* at compile time, and would often result in copying more memory
* than necessary.
@@ -2921,14 +2944,14 @@
* int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
* Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
- * to *dst*. Same semantics as with bpf_probe_read_user_str() apply.
+ * to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply.
* Return
- * On success, the strictly positive length of the string, including
+ * On success, the strictly positive length of the string, including
* the trailing NUL character. On error, a negative value.
*
* int bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
* Description
- * Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock.
+ * Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**.
* *rcv_nxt* is the ack_seq to be sent out.
* Return
* 0 on success, or a negative error in case of failure.
@@ -2956,19 +2979,19 @@
* int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags)
* Description
* For an eBPF program attached to a perf event, retrieve the
- * branch records (struct perf_branch_entry) associated to *ctx*
- * and store it in the buffer pointed by *buf* up to size
+ * branch records (**struct perf_branch_entry**) associated to *ctx*
+ * and store it in the buffer pointed by *buf* up to size
* *size* bytes.
* Return
* On success, number of bytes written to *buf*. On error, a
* negative value.
*
* The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to
- * instead return the number of bytes required to store all the
+ * instead return the number of bytes required to store all the
* branch entries. If this flag is set, *buf* may be NULL.
*
* **-EINVAL** if arguments invalid or **size** not a multiple
- * of sizeof(struct perf_branch_entry).
+ * of **sizeof**\ (**struct perf_branch_entry**\ ).
*
* **-ENOENT** if architecture does not support branch records.
*
@@ -2976,8 +2999,8 @@
* Description
* Returns 0 on success, values for *pid* and *tgid* as seen from the current
* *namespace* will be returned in *nsdata*.
- *
- * On failure, the returned value is one of the following:
+ * Return
+ * 0 on success, or one of the following in case of failure:
*
* **-EINVAL** if dev and inum supplied don't match dev_t and inode number
* with nsfs of current task, or if dev conversion to dev_t lost high bits.
@@ -3016,8 +3039,8 @@
* a global identifier that can be assumed unique. If *ctx* is
* NULL, then the helper returns the cookie for the initial
* network namespace. The cookie itself is very similar to that
- * of bpf_get_socket_cookie() helper, but for network namespaces
- * instead of sockets.
+ * of **bpf_get_socket_cookie**\ () helper, but for network
+ * namespaces instead of sockets.
* Return
* A 8-byte long opaque number.
*
@@ -3052,22 +3075,183 @@
*
* The *flags* argument must be zero.
* Return
- * 0 on success, or a negative errno in case of failure.
+ * 0 on success, or a negative error in case of failure:
*
- * * **-EINVAL** Unsupported flags specified.
- * * **-ENOENT** Socket is unavailable for assignment.
- * * **-ENETUNREACH** Socket is unreachable (wrong netns).
- * * **-EOPNOTSUPP** Unsupported operation, for example a
- * call from outside of TC ingress.
- * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport).
+ * **-EINVAL** if specified *flags* are not supported.
+ *
+ * **-ENOENT** if the socket is unavailable for assignment.
+ *
+ * **-ENETUNREACH** if the socket is unreachable (wrong netns).
+ *
+ * **-EOPNOTSUPP** if the operation is not supported, for example
+ * a call from outside of TC ingress.
+ *
+ * **-ESOCKTNOSUPPORT** if the socket type is not supported
+ * (reuseport).
*
* u64 bpf_ktime_get_boot_ns(void)
* Description
* Return the time elapsed since system boot, in nanoseconds.
* Does include the time the system was suspended.
- * See: clock_gettime(CLOCK_BOOTTIME)
+ * See: **clock_gettime**\ (**CLOCK_BOOTTIME**)
* Return
* Current *ktime*.
+ *
+ * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ * Description
+ * **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print
+ * out the format string.
+ * The *m* represents the seq_file. The *fmt* and *fmt_size* are for
+ * the format string itself. The *data* and *data_len* are format string
+ * arguments. The *data* are a **u64** array and corresponding format string
+ * values are stored in the array. For strings and pointers where pointees
+ * are accessed, only the pointer values are stored in the *data* array.
+ * The *data_len* is the size of *data* in bytes.
+ *
+ * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
+ * Reading kernel memory may fail due to either invalid address or
+ * valid address but requiring a major memory fault. If reading kernel memory
+ * fails, the string for **%s** will be an empty string, and the ip
+ * address for **%p{i,I}{4,6}** will be 0. Not returning error to
+ * bpf program is consistent with what **bpf_trace_printk**\ () does for now.
+ * Return
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-EBUSY** if per-CPU memory copy buffer is busy, can try again
+ * by returning 1 from bpf program.
+ *
+ * **-EINVAL** if arguments are invalid, or if *fmt* is invalid/unsupported.
+ *
+ * **-E2BIG** if *fmt* contains too many format specifiers.
+ *
+ * **-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * int bpf_seq_write(struct seq_file *m, const void *data, u32 len)
+ * Description
+ * **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data.
+ * The *m* represents the seq_file. The *data* and *len* represent the
+ * data to write in bytes.
+ * Return
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * u64 bpf_sk_cgroup_id(struct bpf_sock *sk)
+ * Description
+ * Return the cgroup v2 id of the socket *sk*.
+ *
+ * *sk* must be a non-**NULL** pointer to a full socket, e.g. one
+ * returned from **bpf_sk_lookup_xxx**\ (),
+ * **bpf_sk_fullsock**\ (), etc. The format of returned id is
+ * same as in **bpf_skb_cgroup_id**\ ().
+ *
+ * This helper is available only if the kernel was compiled with
+ * the **CONFIG_SOCK_CGROUP_DATA** configuration option.
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of cgroup associated
+ * with the *sk* 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 *sk*, then return value will be same as that
+ * of **bpf_sk_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with *sk*.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_sk_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
+ * Description
+ * Copy *size* bytes from *data* into a ring buffer *ringbuf*.
+ * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
+ * new data availability is sent.
+ * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
+ * new data availability is sent unconditionally.
+ * Return
+ * 0, on success;
+ * < 0, on error.
+ *
+ * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags)
+ * Description
+ * Reserve *size* bytes of payload in a ring buffer *ringbuf*.
+ * Return
+ * Valid pointer with *size* bytes of memory available; NULL,
+ * otherwise.
+ *
+ * void bpf_ringbuf_submit(void *data, u64 flags)
+ * Description
+ * Submit reserved ring buffer sample, pointed to by *data*.
+ * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
+ * new data availability is sent.
+ * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
+ * new data availability is sent unconditionally.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard(void *data, u64 flags)
+ * Description
+ * Discard reserved ring buffer sample, pointed to by *data*.
+ * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
+ * new data availability is sent.
+ * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
+ * new data availability is sent unconditionally.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * u64 bpf_ringbuf_query(void *ringbuf, u64 flags)
+ * Description
+ * Query various characteristics of provided ring buffer. What
+ * exactly is queries is determined by *flags*:
+ * - BPF_RB_AVAIL_DATA - amount of data not yet consumed;
+ * - BPF_RB_RING_SIZE - the size of ring buffer;
+ * - BPF_RB_CONS_POS - consumer position (can wrap around);
+ * - BPF_RB_PROD_POS - producer(s) position (can wrap around);
+ * Data returned is just a momentary snapshots of actual values
+ * and could be inaccurate, so this facility should be used to
+ * power heuristics and for reporting, not to make 100% correct
+ * calculation.
+ * Return
+ * Requested value, or 0, if flags are not recognized.
+ *
+ * int bpf_csum_level(struct sk_buff *skb, u64 level)
+ * Description
+ * Change the skbs checksum level by one layer up or down, or
+ * reset it entirely to none in order to have the stack perform
+ * checksum validation. The level is applicable to the following
+ * protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of
+ * | ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP |
+ * through **bpf_skb_adjust_room**\ () helper with passing in
+ * **BPF_F_ADJ_ROOM_NO_CSUM_RESET** flag would require one call
+ * to **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_DEC** since
+ * the UDP header is removed. Similarly, an encap of the latter
+ * into the former could be accompanied by a helper call to
+ * **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_INC** if the
+ * skb is still intended to be processed in higher layers of the
+ * stack instead of just egressing at tc.
+ *
+ * There are three supported level settings at this time:
+ *
+ * * **BPF_CSUM_LEVEL_INC**: Increases skb->csum_level for skbs
+ * with CHECKSUM_UNNECESSARY.
+ * * **BPF_CSUM_LEVEL_DEC**: Decreases skb->csum_level for skbs
+ * with CHECKSUM_UNNECESSARY.
+ * * **BPF_CSUM_LEVEL_RESET**: Resets skb->csum_level to 0 and
+ * sets CHECKSUM_NONE to force checksum validation by the stack.
+ * * **BPF_CSUM_LEVEL_QUERY**: No-op, returns the current
+ * skb->csum_level.
+ * Return
+ * 0 on success, or a negative error in case of failure. In the
+ * case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
+ * is returned or the error code -EACCES in case the skb is not
+ * subject to CHECKSUM_UNNECESSARY.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -3195,7 +3379,17 @@
FN(get_netns_cookie), \
FN(get_current_ancestor_cgroup_id), \
FN(sk_assign), \
- FN(ktime_get_boot_ns),
+ FN(ktime_get_boot_ns), \
+ FN(seq_printf), \
+ FN(seq_write), \
+ FN(sk_cgroup_id), \
+ FN(sk_ancestor_cgroup_id), \
+ FN(ringbuf_output), \
+ FN(ringbuf_reserve), \
+ FN(ringbuf_submit), \
+ FN(ringbuf_discard), \
+ FN(ringbuf_query), \
+ FN(csum_level),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -3272,6 +3466,14 @@
BPF_F_CURRENT_NETNS = (-1L),
};
+/* BPF_FUNC_csum_level level values. */
+enum {
+ BPF_CSUM_LEVEL_QUERY,
+ BPF_CSUM_LEVEL_INC,
+ BPF_CSUM_LEVEL_DEC,
+ BPF_CSUM_LEVEL_RESET,
+};
+
/* BPF_FUNC_skb_adjust_room flags. */
enum {
BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0),
@@ -3279,6 +3481,7 @@
BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2),
BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3),
BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4),
+ BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5),
};
enum {
@@ -3305,6 +3508,29 @@
BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0),
};
+/* BPF_FUNC_bpf_ringbuf_commit, BPF_FUNC_bpf_ringbuf_discard, and
+ * BPF_FUNC_bpf_ringbuf_output flags.
+ */
+enum {
+ BPF_RB_NO_WAKEUP = (1ULL << 0),
+ BPF_RB_FORCE_WAKEUP = (1ULL << 1),
+};
+
+/* BPF_FUNC_bpf_ringbuf_query flags */
+enum {
+ BPF_RB_AVAIL_DATA = 0,
+ BPF_RB_RING_SIZE = 1,
+ BPF_RB_CONS_POS = 2,
+ BPF_RB_PROD_POS = 3,
+};
+
+/* BPF ring buffer constants */
+enum {
+ BPF_RINGBUF_BUSY_BIT = (1U << 31),
+ BPF_RINGBUF_DISCARD_BIT = (1U << 30),
+ BPF_RINGBUF_HDR_SZ = 8,
+};
+
/* Mode for BPF_FUNC_skb_adjust_room helper. */
enum bpf_adj_room_mode {
BPF_ADJ_ROOM_NET,
@@ -3437,6 +3663,7 @@
__u32 dst_ip4;
__u32 dst_ip6[4];
__u32 state;
+ __s32 rx_queue_mapping;
};
struct bpf_tcp_sock {
@@ -3530,6 +3757,8 @@
/* Below access go through struct xdp_rxq_info */
__u32 ingress_ifindex; /* rxq->dev->ifindex */
__u32 rx_queue_index; /* rxq->queue_index */
+
+ __u32 egress_ifindex; /* txq->dev->ifindex */
};
enum sk_action {
@@ -3552,6 +3781,8 @@
__u32 remote_port; /* Stored in network byte order */
__u32 local_port; /* stored in host byte order */
__u32 size; /* Total size of sk_msg */
+
+ __bpf_md_ptr(struct bpf_sock *, sk); /* current socket */
};
struct sk_reuseport_md {
@@ -3658,6 +3889,10 @@
__u64 cgroup_id;
__u32 attach_type;
} cgroup;
+ struct {
+ __u32 netns_ino;
+ __u32 attach_type;
+ } netns;
};
} __attribute__((aligned(8)));
@@ -3673,7 +3908,7 @@
__u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write.
* Stored in network byte order.
*/
- __u32 user_port; /* Allows 4-byte read and write.
+ __u32 user_port; /* Allows 1,2,4-byte read and 4-byte write.
* Stored in network byte order
*/
__u32 family; /* Allows 4-byte read, but no write */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 80e33d2..7b600bf 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -233,10 +233,13 @@
* @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not
* sent to the CPU.
* @DEVLINK_TRAP_ACTION_TRAP: The sole copy of the packet is sent to the CPU.
+ * @DEVLINK_TRAP_ACTION_MIRROR: Packet is forwarded by the device and a copy is
+ * sent to the CPU.
*/
enum devlink_trap_action {
DEVLINK_TRAP_ACTION_DROP,
DEVLINK_TRAP_ACTION_TRAP,
+ DEVLINK_TRAP_ACTION_MIRROR,
};
/**
@@ -250,10 +253,16 @@
* control plane for resolution. Trapped packets
* are processed by devlink and injected to
* the kernel's Rx path.
+ * @DEVLINK_TRAP_TYPE_CONTROL: Packet was trapped because it is required for
+ * the correct functioning of the control plane.
+ * For example, an ARP request packet. Trapped
+ * packets are injected to the kernel's Rx path,
+ * but not reported to drop monitor.
*/
enum devlink_trap_type {
DEVLINK_TRAP_TYPE_DROP,
DEVLINK_TRAP_TYPE_EXCEPTION,
+ DEVLINK_TRAP_TYPE_CONTROL,
};
enum {
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index a4ac9f5..73e2d86 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -169,15 +169,70 @@
__IFLA_BRIDGE_MRP_MAX,
};
+#define IFLA_BRIDGE_MRP_MAX (__IFLA_BRIDGE_MRP_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_INSTANCE_UNSPEC,
+ IFLA_BRIDGE_MRP_INSTANCE_RING_ID,
+ IFLA_BRIDGE_MRP_INSTANCE_P_IFINDEX,
+ IFLA_BRIDGE_MRP_INSTANCE_S_IFINDEX,
+ IFLA_BRIDGE_MRP_INSTANCE_PRIO,
+ __IFLA_BRIDGE_MRP_INSTANCE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_INSTANCE_MAX (__IFLA_BRIDGE_MRP_INSTANCE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_PORT_STATE_UNSPEC,
+ IFLA_BRIDGE_MRP_PORT_STATE_STATE,
+ __IFLA_BRIDGE_MRP_PORT_STATE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_PORT_STATE_MAX (__IFLA_BRIDGE_MRP_PORT_STATE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_PORT_ROLE_UNSPEC,
+ IFLA_BRIDGE_MRP_PORT_ROLE_ROLE,
+ __IFLA_BRIDGE_MRP_PORT_ROLE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_PORT_ROLE_MAX (__IFLA_BRIDGE_MRP_PORT_ROLE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_RING_STATE_UNSPEC,
+ IFLA_BRIDGE_MRP_RING_STATE_RING_ID,
+ IFLA_BRIDGE_MRP_RING_STATE_STATE,
+ __IFLA_BRIDGE_MRP_RING_STATE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_RING_STATE_MAX (__IFLA_BRIDGE_MRP_RING_STATE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_RING_ROLE_UNSPEC,
+ IFLA_BRIDGE_MRP_RING_ROLE_RING_ID,
+ IFLA_BRIDGE_MRP_RING_ROLE_ROLE,
+ __IFLA_BRIDGE_MRP_RING_ROLE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_RING_ROLE_MAX (__IFLA_BRIDGE_MRP_RING_ROLE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_START_TEST_UNSPEC,
+ IFLA_BRIDGE_MRP_START_TEST_RING_ID,
+ IFLA_BRIDGE_MRP_START_TEST_INTERVAL,
+ IFLA_BRIDGE_MRP_START_TEST_MAX_MISS,
+ IFLA_BRIDGE_MRP_START_TEST_PERIOD,
+ IFLA_BRIDGE_MRP_START_TEST_MONITOR,
+ __IFLA_BRIDGE_MRP_START_TEST_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_START_TEST_MAX (__IFLA_BRIDGE_MRP_START_TEST_MAX - 1)
+
struct br_mrp_instance {
__u32 ring_id;
__u32 p_ifindex;
__u32 s_ifindex;
-};
-
-struct br_mrp_port_role {
- __u32 ring_id;
- __u32 role;
+ __u16 prio;
};
struct br_mrp_ring_state {
@@ -195,10 +250,9 @@
__u32 interval;
__u32 max_miss;
__u32 period;
+ __u32 monitor;
};
-#define IFLA_BRIDGE_MRP_MAX (__IFLA_BRIDGE_MRP_MAX - 1)
-
struct bridge_stp_xstats {
__u64 transition_blk;
__u64 transition_fwd;
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index cd144e3..eefcda8 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -29,6 +29,7 @@
NDA_LINK_NETNSID,
NDA_SRC_VNI,
NDA_PROTOCOL, /* Originator of entry */
+ NDA_NH_ID,
__NDA_MAX
};
diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h
index b56c5b8..b0a5613 100644
--- a/include/uapi/linux/nexthop.h
+++ b/include/uapi/linux/nexthop.h
@@ -49,6 +49,9 @@
NHA_GROUPS, /* flag; only return nexthop groups in dump */
NHA_MASTER, /* u32; only return nexthops with given master dev */
+ NHA_FDB, /* flag; nexthop belongs to a bridge fdb */
+ /* if NHA_FDB is added, OIF, BLACKHOLE, ENCAP cannot be set */
+
__NHA_MAX,
};
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index fc672b2..7576209 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -576,6 +576,8 @@
TCA_FLOWER_KEY_CT_LABELS, /* u128 */
TCA_FLOWER_KEY_CT_LABELS_MASK, /* u128 */
+ TCA_FLOWER_KEY_MPLS_OPTS,
+
__TCA_FLOWER_MAX,
};
@@ -641,6 +643,27 @@
(__TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX - 1)
enum {
+ TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC,
+ TCA_FLOWER_KEY_MPLS_OPTS_LSE,
+ __TCA_FLOWER_KEY_MPLS_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_MPLS_OPTS_MAX (__TCA_FLOWER_KEY_MPLS_OPTS_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_UNSPEC,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_TC,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL,
+ __TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX,
+};
+
+#define TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX \
+ (__TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX - 1)
+
+enum {
TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
};
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 9d802cd..bcb1ba4 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -609,11 +609,17 @@
TCA_HW_OFFLOAD,
TCA_INGRESS_BLOCK,
TCA_EGRESS_BLOCK,
+ TCA_DUMP_FLAGS,
__TCA_MAX
};
#define TCA_MAX (__TCA_MAX - 1)
+#define TCA_DUMP_FLAGS_TERSE (1 << 0) /* Means that in dump user gets only basic
+ * data necessary to identify the objects
+ * (handle, cookie, etc.) and stats.
+ */
+
#define TCA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg))))
#define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg))
