summaryrefslogtreecommitdiff
path: root/tools/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-06-30 15:51:09 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-06-30 15:51:09 -0700
commitdbe69e43372212527abf48609aba7fc39a6daa27 (patch)
tree96cfafdf70f5325ceeac1054daf7deca339c9730 /tools/include
parenta6eaf3850cb171c328a8b0db6d3c79286a1eba9d (diff)
parentb6df00789e2831fff7a2c65aa7164b2a4dcbe599 (diff)
Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core: - BPF: - add syscall program type and libbpf support for generating instructions and bindings for in-kernel BPF loaders (BPF loaders for BPF), this is a stepping stone for signed BPF programs - infrastructure to migrate TCP child sockets from one listener to another in the same reuseport group/map to improve flexibility of service hand-off/restart - add broadcast support to XDP redirect - allow bypass of the lockless qdisc to improving performance (for pktgen: +23% with one thread, +44% with 2 threads) - add a simpler version of "DO_ONCE()" which does not require jump labels, intended for slow-path usage - virtio/vsock: introduce SOCK_SEQPACKET support - add getsocketopt to retrieve netns cookie - ip: treat lowest address of a IPv4 subnet as ordinary unicast address allowing reclaiming of precious IPv4 addresses - ipv6: use prandom_u32() for ID generation - ip: add support for more flexible field selection for hashing across multi-path routes (w/ offload to mlxsw) - icmp: add support for extended RFC 8335 PROBE (ping) - seg6: add support for SRv6 End.DT46 behavior - mptcp: - DSS checksum support (RFC 8684) to detect middlebox meddling - support Connection-time 'C' flag - time stamping support - sctp: packetization Layer Path MTU Discovery (RFC 8899) - xfrm: speed up state addition with seq set - WiFi: - hidden AP discovery on 6 GHz and other HE 6 GHz improvements - aggregation handling improvements for some drivers - minstrel improvements for no-ack frames - deferred rate control for TXQs to improve reaction times - switch from round robin to virtual time-based airtime scheduler - add trace points: - tcp checksum errors - openvswitch - action execution, upcalls - socket errors via sk_error_report Device APIs: - devlink: add rate API for hierarchical control of max egress rate of virtual devices (VFs, SFs etc.) - don't require RCU read lock to be held around BPF hooks in NAPI context - page_pool: generic buffer recycling New hardware/drivers: - mobile: - iosm: PCIe Driver for Intel M.2 Modem - support for Qualcomm MSM8998 (ipa) - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU) - NXP SJA1110 Automotive Ethernet 10-port switch - Qualcomm QCA8327 switch support (qca8k) - Mikrotik 10/25G NIC (atl1c) Driver changes: - ACPI support for some MDIO, MAC and PHY devices from Marvell and NXP (our first foray into MAC/PHY description via ACPI) - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx - Mellanox/Nvidia NIC (mlx5) - NIC VF offload of L2 bridging - support IRQ distribution to Sub-functions - Marvell (prestera): - add flower and match all - devlink trap - link aggregation - Netronome (nfp): connection tracking offload - Intel 1GE (igc): add AF_XDP support - Marvell DPU (octeontx2): ingress ratelimit offload - Google vNIC (gve): new ring/descriptor format support - Qualcomm mobile (rmnet & ipa): inline checksum offload support - MediaTek WiFi (mt76) - mt7915 MSI support - mt7915 Tx status reporting - mt7915 thermal sensors support - mt7921 decapsulation offload - mt7921 enable runtime pm and deep sleep - Realtek WiFi (rtw88) - beacon filter support - Tx antenna path diversity support - firmware crash information via devcoredump - Qualcomm WiFi (wcn36xx) - Wake-on-WLAN support with magic packets and GTK rekeying - Micrel PHY (ksz886x/ksz8081): add cable test support" * tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits) tcp: change ICSK_CA_PRIV_SIZE definition tcp_yeah: check struct yeah size at compile time gve: DQO: Fix off by one in gve_rx_dqo() stmmac: intel: set PCI_D3hot in suspend stmmac: intel: Enable PHY WOL option in EHL net: stmmac: option to enable PHY WOL with PMT enabled net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del} net: use netdev_info in ndo_dflt_fdb_{add,del} ptp: Set lookup cookie when creating a PTP PPS source. net: sock: add trace for socket errors net: sock: introduce sk_error_report net: dsa: replay the local bridge FDB entries pointing to the bridge dev too net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev net: dsa: include fdb entries pointing to bridge in the host fdb list net: dsa: include bridge addresses which are local in the host fdb list net: dsa: sync static FDB entries on foreign interfaces to hardware net: dsa: install the host MDB and FDB entries in the master's RX filter net: dsa: reference count the FDB addresses at the cross-chip notifier level net: dsa: introduce a separate cross-chip notifier type for host FDBs net: dsa: reference count the MDB entries at the cross-chip notifier level ...
Diffstat (limited to 'tools/include')
-rw-r--r--tools/include/uapi/linux/bpf.h82
1 files changed, 75 insertions, 7 deletions
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index ec6d85a81744..bf9252c7381e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -527,6 +527,15 @@ union bpf_iter_link_info {
* Look up an element with the given *key* in the map referred to
* by the file descriptor *fd*, and if found, delete the element.
*
+ * For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map
+ * types, the *flags* argument needs to be set to 0, but for other
+ * map types, it may be specified as:
+ *
+ * **BPF_F_LOCK**
+ * Look up and delete the value of a spin-locked map
+ * without returning the lock. This must be specified if
+ * the elements contain a spinlock.
+ *
* The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types
* implement this command as a "pop" operation, deleting the top
* element rather than one corresponding to *key*.
@@ -536,6 +545,10 @@ union bpf_iter_link_info {
* This command is only valid for the following map types:
* * **BPF_MAP_TYPE_QUEUE**
* * **BPF_MAP_TYPE_STACK**
+ * * **BPF_MAP_TYPE_HASH**
+ * * **BPF_MAP_TYPE_PERCPU_HASH**
+ * * **BPF_MAP_TYPE_LRU_HASH**
+ * * **BPF_MAP_TYPE_LRU_PERCPU_HASH**
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
@@ -837,6 +850,7 @@ enum bpf_cmd {
BPF_PROG_ATTACH,
BPF_PROG_DETACH,
BPF_PROG_TEST_RUN,
+ BPF_PROG_RUN = BPF_PROG_TEST_RUN,
BPF_PROG_GET_NEXT_ID,
BPF_MAP_GET_NEXT_ID,
BPF_PROG_GET_FD_BY_ID,
@@ -937,6 +951,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_EXT,
BPF_PROG_TYPE_LSM,
BPF_PROG_TYPE_SK_LOOKUP,
+ BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
};
enum bpf_attach_type {
@@ -979,6 +994,8 @@ enum bpf_attach_type {
BPF_SK_LOOKUP,
BPF_XDP,
BPF_SK_SKB_VERDICT,
+ BPF_SK_REUSEPORT_SELECT,
+ BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
__MAX_BPF_ATTACH_TYPE
};
@@ -1097,8 +1114,8 @@ enum bpf_link_type {
/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
* the following extensions:
*
- * insn[0].src_reg: BPF_PSEUDO_MAP_FD
- * insn[0].imm: map fd
+ * insn[0].src_reg: BPF_PSEUDO_MAP_[FD|IDX]
+ * insn[0].imm: map fd or fd_idx
* insn[1].imm: 0
* insn[0].off: 0
* insn[1].off: 0
@@ -1106,15 +1123,19 @@ enum bpf_link_type {
* verifier type: CONST_PTR_TO_MAP
*/
#define BPF_PSEUDO_MAP_FD 1
-/* insn[0].src_reg: BPF_PSEUDO_MAP_VALUE
- * insn[0].imm: map fd
+#define BPF_PSEUDO_MAP_IDX 5
+
+/* insn[0].src_reg: BPF_PSEUDO_MAP_[IDX_]VALUE
+ * insn[0].imm: map fd or fd_idx
* insn[1].imm: offset into value
* insn[0].off: 0
* insn[1].off: 0
* ldimm64 rewrite: address of map[0]+offset
* verifier type: PTR_TO_MAP_VALUE
*/
-#define BPF_PSEUDO_MAP_VALUE 2
+#define BPF_PSEUDO_MAP_VALUE 2
+#define BPF_PSEUDO_MAP_IDX_VALUE 6
+
/* insn[0].src_reg: BPF_PSEUDO_BTF_ID
* insn[0].imm: kernel btd id of VAR
* insn[1].imm: 0
@@ -1314,6 +1335,8 @@ union bpf_attr {
/* or valid module BTF object fd or 0 to attach to vmlinux */
__u32 attach_btf_obj_fd;
};
+ __u32 :32; /* pad */
+ __aligned_u64 fd_array; /* array of FDs */
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -2534,8 +2557,12 @@ 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
- * unset.
+ * by the caller. The higher bits of *flags* can be set to
+ * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
+ *
+ * With BPF_F_BROADCAST the packet will be broadcasted to all the
+ * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress
+ * interface will be excluded when do broadcasting.
*
* See also **bpf_redirect**\ (), which only supports redirecting
* to an ifindex, but doesn't require a map to do so.
@@ -4735,6 +4762,24 @@ union bpf_attr {
* be zero-terminated except when **str_size** is 0.
*
* Or **-EBUSY** if the per-CPU memory copy buffer is busy.
+ *
+ * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size)
+ * Description
+ * Execute bpf syscall with given arguments.
+ * Return
+ * A syscall result.
+ *
+ * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags)
+ * Description
+ * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs.
+ * Return
+ * Returns btf_id and btf_obj_fd in lower and upper 32 bits.
+ *
+ * long bpf_sys_close(u32 fd)
+ * Description
+ * Execute close syscall for given FD.
+ * Return
+ * A syscall result.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -4903,6 +4948,9 @@ union bpf_attr {
FN(check_mtu), \
FN(for_each_map_elem), \
FN(snprintf), \
+ FN(sys_bpf), \
+ FN(btf_find_by_name_kind), \
+ FN(sys_close), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5080,6 +5128,12 @@ enum {
BPF_F_BPRM_SECUREEXEC = (1ULL << 0),
};
+/* Flags for bpf_redirect_map helper */
+enum {
+ BPF_F_BROADCAST = (1ULL << 3),
+ BPF_F_EXCLUDE_INGRESS = (1ULL << 4),
+};
+
#define __bpf_md_ptr(type, name) \
union { \
type name; \
@@ -5364,6 +5418,20 @@ struct sk_reuseport_md {
__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 */
+ /* When reuse->migrating_sk is NULL, it is selecting a sk for the
+ * new incoming connection request (e.g. selecting a listen sk for
+ * the received SYN in the TCP case). reuse->sk is one of the sk
+ * in the reuseport group. The bpf prog can use reuse->sk to learn
+ * the local listening ip/port without looking into the skb.
+ *
+ * When reuse->migrating_sk is not NULL, reuse->sk is closed and
+ * reuse->migrating_sk is the socket that needs to be migrated
+ * to another listening socket. migrating_sk could be a fullsock
+ * sk that is fully established or a reqsk that is in-the-middle
+ * of 3-way handshake.
+ */
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ __bpf_md_ptr(struct bpf_sock *, migrating_sk);
};
#define BPF_TAG_SIZE 8