summaryrefslogtreecommitdiff
path: root/tools/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-06-04 02:27:18 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-06-04 02:27:18 +0300
commitcb8e59cc87201af93dfbb6c3dccc8fcad72a09c2 (patch)
treea334db9022f89654b777bbce8c4c6632e65b9031 /tools/include
parent2e63f6ce7ed2c4ff83ba30ad9ccad422289a6c63 (diff)
parent065fcfd49763ec71ae345bb5c5a74f961031e70e (diff)
downloadlinux-cb8e59cc87201af93dfbb6c3dccc8fcad72a09c2.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller: 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz Augusto von Dentz. 2) Add GSO partial support to igc, from Sasha Neftin. 3) Several cleanups and improvements to r8169 from Heiner Kallweit. 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a device self-test. From Andrew Lunn. 5) Start moving away from custom driver versions, use the globally defined kernel version instead, from Leon Romanovsky. 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin. 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet. 8) Add sriov and vf support to hinic, from Luo bin. 9) Support Media Redundancy Protocol (MRP) in the bridging code, from Horatiu Vultur. 10) Support netmap in the nft_nat code, from Pablo Neira Ayuso. 11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina Dubroca. Also add ipv6 support for espintcp. 12) Lots of ReST conversions of the networking documentation, from Mauro Carvalho Chehab. 13) Support configuration of ethtool rxnfc flows in bcmgenet driver, from Doug Berger. 14) Allow to dump cgroup id and filter by it in inet_diag code, from Dmitry Yakunin. 15) Add infrastructure to export netlink attribute policies to userspace, from Johannes Berg. 16) Several optimizations to sch_fq scheduler, from Eric Dumazet. 17) Fallback to the default qdisc if qdisc init fails because otherwise a packet scheduler init failure will make a device inoperative. From Jesper Dangaard Brouer. 18) Several RISCV bpf jit optimizations, from Luke Nelson. 19) Correct the return type of the ->ndo_start_xmit() method in several drivers, it's netdev_tx_t but many drivers were using 'int'. From Yunjian Wang. 20) Add an ethtool interface for PHY master/slave config, from Oleksij Rempel. 21) Add BPF iterators, from Yonghang Song. 22) Add cable test infrastructure, including ethool interfaces, from Andrew Lunn. Marvell PHY driver is the first to support this facility. 23) Remove zero-length arrays all over, from Gustavo A. R. Silva. 24) Calculate and maintain an explicit frame size in XDP, from Jesper Dangaard Brouer. 25) Add CAP_BPF, from Alexei Starovoitov. 26) Support terse dumps in the packet scheduler, from Vlad Buslov. 27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei. 28) Add devm_register_netdev(), from Bartosz Golaszewski. 29) Minimize qdisc resets, from Cong Wang. 30) Get rid of kernel_getsockopt and kernel_setsockopt in order to eliminate set_fs/get_fs calls. From Christoph Hellwig. * git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits) selftests: net: ip_defrag: ignore EPERM net_failover: fixed rollback in net_failover_open() Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv" Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv" vmxnet3: allow rx flow hash ops only when rss is enabled hinic: add set_channels ethtool_ops support selftests/bpf: Add a default $(CXX) value tools/bpf: Don't use $(COMPILE.c) bpf, selftests: Use bpf_probe_read_kernel s390/bpf: Use bcr 0,%0 as tail call nop filler s390/bpf: Maintain 8-byte stack alignment selftests/bpf: Fix verifier test selftests/bpf: Fix sample_cnt shared between two threads bpf, selftests: Adapt cls_redirect to call csum_level helper bpf: Add csum_level helper for fixing up csum levels bpf: Fix up bpf_skb_adjust_room helper's skb csum setting sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf() crypto/chtls: IPv6 support for inline TLS Crypto/chcr: Fixes a coccinile check error Crypto/chcr: Fixes compilations warnings ...
Diffstat (limited to 'tools/include')
-rw-r--r--tools/include/uapi/linux/bpf.h390
-rw-r--r--tools/include/uapi/linux/if_link.h1
2 files changed, 345 insertions, 46 deletions
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7bbf1b65be10..c65b374a5090 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -73,7 +73,7 @@ struct bpf_insn {
/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
struct bpf_lpm_trie_key {
__u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */
- __u8 data[]; /* Arbitrary size */
+ __u8 data[0]; /* Arbitrary size */
};
struct bpf_cgroup_storage_key {
@@ -113,6 +113,10 @@ enum bpf_cmd {
BPF_MAP_DELETE_BATCH,
BPF_LINK_CREATE,
BPF_LINK_UPDATE,
+ BPF_LINK_GET_FD_BY_ID,
+ BPF_LINK_GET_NEXT_ID,
+ BPF_ENABLE_STATS,
+ BPF_ITER_CREATE,
};
enum bpf_map_type {
@@ -143,6 +147,7 @@ enum bpf_map_type {
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
@@ -215,11 +220,28 @@ enum bpf_attach_type {
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
};
#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+enum bpf_link_type {
+ BPF_LINK_TYPE_UNSPEC = 0,
+ 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,
+};
+
/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
*
* NONE(default): No further bpf programs allowed in the subtree.
@@ -379,6 +401,12 @@ enum {
*/
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
+/* type for BPF_ENABLE_STATS */
+enum bpf_stats_type {
+ /* enabled run_time_ns and run_cnt */
+ BPF_STATS_RUN_TIME = 0,
+};
+
enum bpf_stack_build_id_status {
/* user space need an empty entry to identify end of a trace */
BPF_STACK_BUILD_ID_EMPTY = 0,
@@ -523,6 +551,7 @@ union bpf_attr {
__u32 prog_id;
__u32 map_id;
__u32 btf_id;
+ __u32 link_id;
};
__u32 next_id;
__u32 open_flags;
@@ -589,6 +618,15 @@ union bpf_attr {
__u32 old_prog_fd;
} link_update;
+ struct { /* struct used by BPF_ENABLE_STATS command */
+ __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
@@ -644,14 +682,16 @@ union bpf_attr {
* 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.
*
* u64 bpf_ktime_get_ns(void)
* Description
* Return the time elapsed since system boot, in nanoseconds.
+ * Does not include time the system was suspended.
+ * See: **clock_gettime**\ (**CLOCK_MONOTONIC**)
* Return
* Current *ktime*.
*
@@ -1510,11 +1550,11 @@ union bpf_attr {
* 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
@@ -1542,7 +1582,7 @@ union bpf_attr {
*
* 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.
@@ -1562,7 +1602,7 @@ union bpf_attr {
* Return
* 0
*
- * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
+ * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
* Description
* Emulate a call to **setsockopt()** on the socket associated to
* *bpf_socket*, which must be a full socket. The *level* at
@@ -1570,6 +1610,12 @@ union bpf_attr {
* must be specified, see **setsockopt(2)** for more information.
* 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**.
+ *
* This helper actually implements a subset of **setsockopt()**.
* It supports the following *level*\ s:
*
@@ -1589,6 +1635,13 @@ union bpf_attr {
* 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
@@ -1634,12 +1687,12 @@ union bpf_attr {
*
* 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.
@@ -1747,7 +1800,7 @@ union bpf_attr {
* 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
@@ -1764,7 +1817,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
+ * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
* Description
* Emulate a call to **getsockopt()** on the socket associated to
* *bpf_socket*, which must be a full socket. The *level* at
@@ -1773,6 +1826,12 @@ union bpf_attr {
* The retrieved value is stored in the structure pointed by
* *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**.
+ *
* This helper actually implements a subset of **getsockopt()**.
* It supports the following *level*\ s:
*
@@ -1790,7 +1849,7 @@ union bpf_attr {
* 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
@@ -1959,18 +2018,19 @@ union bpf_attr {
*
* 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
@@ -2256,7 +2316,7 @@ union bpf_attr {
* **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
@@ -2602,7 +2662,6 @@ union bpf_attr {
*
* *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.
@@ -2785,7 +2844,6 @@ union bpf_attr {
*
* *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,
@@ -2868,7 +2926,7 @@ union bpf_attr {
* // 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.
@@ -2886,14 +2944,14 @@ union bpf_attr {
* 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.
@@ -2921,19 +2979,19 @@ union bpf_attr {
* 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.
*
@@ -2941,8 +2999,8 @@ union bpf_attr {
* 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.
@@ -2981,8 +3039,8 @@ union bpf_attr {
* 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.
*
@@ -3017,14 +3075,183 @@ union bpf_attr {
*
* The *flags* argument must be zero.
* Return
- * 0 on success, or a negative errno 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).
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-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**)
+ * 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), \
@@ -3151,7 +3378,18 @@ union bpf_attr {
FN(xdp_output), \
FN(get_netns_cookie), \
FN(get_current_ancestor_cgroup_id), \
- FN(sk_assign),
+ FN(sk_assign), \
+ 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
@@ -3228,6 +3466,14 @@ enum {
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),
@@ -3235,6 +3481,7 @@ enum {
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 {
@@ -3261,6 +3508,29 @@ enum {
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,
@@ -3393,6 +3663,7 @@ struct bpf_sock {
__u32 dst_ip4;
__u32 dst_ip6[4];
__u32 state;
+ __s32 rx_queue_mapping;
};
struct bpf_tcp_sock {
@@ -3486,6 +3757,8 @@ struct xdp_md {
/* 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 {
@@ -3508,6 +3781,8 @@ struct sk_msg_md {
__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 {
@@ -3598,6 +3873,29 @@ struct bpf_btf_info {
__u32 id;
} __attribute__((aligned(8)));
+struct bpf_link_info {
+ __u32 type;
+ __u32 id;
+ __u32 prog_id;
+ union {
+ struct {
+ __aligned_u64 tp_name; /* in/out: tp_name buffer ptr */
+ __u32 tp_name_len; /* in/out: tp_name buffer len */
+ } raw_tracepoint;
+ struct {
+ __u32 attach_type;
+ } tracing;
+ struct {
+ __u64 cgroup_id;
+ __u32 attach_type;
+ } cgroup;
+ struct {
+ __u32 netns_ino;
+ __u32 attach_type;
+ } netns;
+ };
+} __attribute__((aligned(8)));
+
/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
* by user and intended to be used by socket (e.g. to bind to, depends on
* attach attach type).
@@ -3610,7 +3908,7 @@ struct bpf_sock_addr {
__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/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index ca6665ea758a..cafedbbfefbe 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -343,6 +343,7 @@ enum {
IFLA_BRPORT_NEIGH_SUPPRESS,
IFLA_BRPORT_ISOLATED,
IFLA_BRPORT_BACKUP_PORT,
+ IFLA_BRPORT_MRP_RING_OPEN,
__IFLA_BRPORT_MAX
};
#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)