aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-10-15 18:42:13 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-10-15 18:42:13 -0700
commit9ff9b0d392ea08090cd1780fb196f36dbb586529 (patch)
tree276a3a5c4525b84dee64eda30b423fc31bf94850 /tools/include
parentMerge tag 'integrity-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity (diff)
parentMerge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next (diff)
downloadwireguard-linux-9ff9b0d392ea08090cd1780fb196f36dbb586529.tar.xz
wireguard-linux-9ff9b0d392ea08090cd1780fb196f36dbb586529.zip
Merge tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: - Add redirect_neigh() BPF packet redirect helper, allowing to limit stack traversal in common container configs and improving TCP back-pressure. Daniel reports ~10Gbps => ~15Gbps single stream TCP performance gain. - Expand netlink policy support and improve policy export to user space. (Ge)netlink core performs request validation according to declared policies. Expand the expressiveness of those policies (min/max length and bitmasks). Allow dumping policies for particular commands. This is used for feature discovery by user space (instead of kernel version parsing or trial and error). - Support IGMPv3/MLDv2 multicast listener discovery protocols in bridge. - Allow more than 255 IPv4 multicast interfaces. - Add support for Type of Service (ToS) reflection in SYN/SYN-ACK packets of TCPv6. - In Multi-patch TCP (MPTCP) support concurrent transmission of data on multiple subflows in a load balancing scenario. Enhance advertising addresses via the RM_ADDR/ADD_ADDR options. - Support SMC-Dv2 version of SMC, which enables multi-subnet deployments. - Allow more calls to same peer in RxRPC. - Support two new Controller Area Network (CAN) protocols - CAN-FD and ISO 15765-2:2016. - Add xfrm/IPsec compat layer, solving the 32bit user space on 64bit kernel problem. - Add TC actions for implementing MPLS L2 VPNs. - Improve nexthop code - e.g. handle various corner cases when nexthop objects are removed from groups better, skip unnecessary notifications and make it easier to offload nexthops into HW by converting to a blocking notifier. - Support adding and consuming TCP header options by BPF programs, opening the doors for easy experimental and deployment-specific TCP option use. - Reorganize TCP congestion control (CC) initialization to simplify life of TCP CC implemented in BPF. - Add support for shipping BPF programs with the kernel and loading them early on boot via the User Mode Driver mechanism, hence reusing all the user space infra we have. - Support sleepable BPF programs, initially targeting LSM and tracing. - Add bpf_d_path() helper for returning full path for given 'struct path'. - Make bpf_tail_call compatible with bpf-to-bpf calls. - Allow BPF programs to call map_update_elem on sockmaps. - Add BPF Type Format (BTF) support for type and enum discovery, as well as support for using BTF within the kernel itself (current use is for pretty printing structures). - Support listing and getting information about bpf_links via the bpf syscall. - Enhance kernel interfaces around NIC firmware update. Allow specifying overwrite mask to control if settings etc. are reset during update; report expected max time operation may take to users; support firmware activation without machine reboot incl. limits of how much impact reset may have (e.g. dropping link or not). - Extend ethtool configuration interface to report IEEE-standard counters, to limit the need for per-vendor logic in user space. - Adopt or extend devlink use for debug, monitoring, fw update in many drivers (dsa loop, ice, ionic, sja1105, qed, mlxsw, mv88e6xxx, dpaa2-eth). - In mlxsw expose critical and emergency SFP module temperature alarms. Refactor port buffer handling to make the defaults more suitable and support setting these values explicitly via the DCBNL interface. - Add XDP support for Intel's igb driver. - Support offloading TC flower classification and filtering rules to mscc_ocelot switches. - Add PTP support for Marvell Octeontx2 and PP2.2 hardware, as well as fixed interval period pulse generator and one-step timestamping in dpaa-eth. - Add support for various auth offloads in WiFi APs, e.g. SAE (WPA3) offload. - Add Lynx PHY/PCS MDIO module, and convert various drivers which have this HW to use it. Convert mvpp2 to split PCS. - Support Marvell Prestera 98DX3255 24-port switch ASICs, as well as 7-port Mediatek MT7531 IP. - Add initial support for QCA6390 and IPQ6018 in ath11k WiFi driver, and wcn3680 support in wcn36xx. - Improve performance for packets which don't require much offloads on recent Mellanox NICs by 20% by making multiple packets share a descriptor entry. - Move chelsio inline crypto drivers (for TLS and IPsec) from the crypto subtree to drivers/net. Move MDIO drivers out of the phy directory. - Clean up a lot of W=1 warnings, reportedly the actively developed subsections of networking drivers should now build W=1 warning free. - Make sure drivers don't use in_interrupt() to dynamically adapt their code. Convert tasklets to use new tasklet_setup API (sadly this conversion is not yet complete). * tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2583 commits) Revert "bpfilter: Fix build error with CONFIG_BPFILTER_UMH" net, sockmap: Don't call bpf_prog_put() on NULL pointer bpf, selftest: Fix flaky tcp_hdr_options test when adding addr to lo bpf, sockmap: Add locking annotations to iterator netfilter: nftables: allow re-computing sctp CRC-32C in 'payload' statements net: fix pos incrementment in ipv6_route_seq_next net/smc: fix invalid return code in smcd_new_buf_create() net/smc: fix valid DMBE buffer sizes net/smc: fix use-after-free of delayed events bpfilter: Fix build error with CONFIG_BPFILTER_UMH cxgb4/ch_ipsec: Replace the module name to ch_ipsec from chcr net: sched: Fix suspicious RCU usage while accessing tcf_tunnel_info bpf: Fix register equivalence tracking. rxrpc: Fix loss of final ack on shutdown rxrpc: Fix bundle counting for exclusive connections netfilter: restore NF_INET_NUMHOOKS ibmveth: Identify ingress large send packets. ibmveth: Switch order of ibmveth_helper calls. cxgb4: handle 4-tuple PEDIT to NAT mode translation selftests: Add VRF route leaking tests ...
Diffstat (limited to 'tools/include')
-rw-r--r--tools/include/linux/btf_ids.h59
-rw-r--r--tools/include/uapi/linux/bpf.h655
2 files changed, 679 insertions, 35 deletions
diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h
index 4867d549e3c1..57890b357f85 100644
--- a/tools/include/linux/btf_ids.h
+++ b/tools/include/linux/btf_ids.h
@@ -3,6 +3,11 @@
#ifndef _LINUX_BTF_IDS_H
#define _LINUX_BTF_IDS_H
+struct btf_id_set {
+ u32 cnt;
+ u32 ids[];
+};
+
#ifdef CONFIG_DEBUG_INFO_BTF
#include <linux/compiler.h> /* for __PASTE */
@@ -62,7 +67,7 @@ asm( \
".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
"." #scope " " #name "; \n" \
#name ":; \n" \
-".popsection; \n"); \
+".popsection; \n");
#define BTF_ID_LIST(name) \
__BTF_ID_LIST(name, local) \
@@ -71,6 +76,13 @@ extern u32 name[];
#define BTF_ID_LIST_GLOBAL(name) \
__BTF_ID_LIST(name, globl)
+/* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with
+ * a single entry.
+ */
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) \
+ BTF_ID_LIST(name) \
+ BTF_ID(prefix, typename)
+
/*
* The BTF_ID_UNUSED macro defines 4 zero bytes.
* It's used when we want to define 'unused' entry
@@ -88,12 +100,57 @@ asm( \
".zero 4 \n" \
".popsection; \n");
+/*
+ * The BTF_SET_START/END macros pair defines sorted list of
+ * BTF IDs plus its members count, with following layout:
+ *
+ * BTF_SET_START(list)
+ * BTF_ID(type1, name1)
+ * BTF_ID(type2, name2)
+ * BTF_SET_END(list)
+ *
+ * __BTF_ID__set__list:
+ * .zero 4
+ * list:
+ * __BTF_ID__type1__name1__3:
+ * .zero 4
+ * __BTF_ID__type2__name2__4:
+ * .zero 4
+ *
+ */
+#define __BTF_SET_START(name, scope) \
+asm( \
+".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
+"." #scope " __BTF_ID__set__" #name "; \n" \
+"__BTF_ID__set__" #name ":; \n" \
+".zero 4 \n" \
+".popsection; \n");
+
+#define BTF_SET_START(name) \
+__BTF_ID_LIST(name, local) \
+__BTF_SET_START(name, local)
+
+#define BTF_SET_START_GLOBAL(name) \
+__BTF_ID_LIST(name, globl) \
+__BTF_SET_START(name, globl)
+
+#define BTF_SET_END(name) \
+asm( \
+".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
+".size __BTF_ID__set__" #name ", .-" #name " \n" \
+".popsection; \n"); \
+extern struct btf_id_set name;
+
#else
#define BTF_ID_LIST(name) static u32 name[5];
#define BTF_ID(prefix, name)
#define BTF_ID_UNUSED
#define BTF_ID_LIST_GLOBAL(name) u32 name[1];
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1];
+#define BTF_SET_START(name) static struct btf_id_set name = { 0 };
+#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
+#define BTF_SET_END(name)
#endif /* CONFIG_DEBUG_INFO_BTF */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b6238b2209b7..bf5a99d803e4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -124,6 +124,7 @@ enum bpf_cmd {
BPF_ENABLE_STATS,
BPF_ITER_CREATE,
BPF_LINK_DETACH,
+ BPF_PROG_BIND_MAP,
};
enum bpf_map_type {
@@ -155,6 +156,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_DEVMAP_HASH,
BPF_MAP_TYPE_STRUCT_OPS,
BPF_MAP_TYPE_RINGBUF,
+ BPF_MAP_TYPE_INODE_STORAGE,
};
/* Note that tracing related programs such as
@@ -345,19 +347,45 @@ enum bpf_link_type {
/* The verifier internal test flag. Behavior is undefined */
#define BPF_F_TEST_STATE_FREQ (1U << 3)
+/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will
+ * restrict map and helper usage for such programs. Sleepable BPF programs can
+ * only be attached to hooks where kernel execution context allows sleeping.
+ * Such programs are allowed to use helpers that may sleep like
+ * bpf_copy_from_user().
+ */
+#define BPF_F_SLEEPABLE (1U << 4)
+
/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
- * two extensions:
- *
- * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE
- * insn[0].imm: map fd map fd
- * insn[1].imm: 0 offset into value
- * insn[0].off: 0 0
- * insn[1].off: 0 0
- * ldimm64 rewrite: address of map address of map[0]+offset
- * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE
+ * the following extensions:
+ *
+ * insn[0].src_reg: BPF_PSEUDO_MAP_FD
+ * insn[0].imm: map fd
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of map
+ * 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
+ * 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
+/* insn[0].src_reg: BPF_PSEUDO_BTF_ID
+ * insn[0].imm: kernel btd id of VAR
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of the kernel variable
+ * verifier type: PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var
+ * is struct/union.
+ */
+#define BPF_PSEUDO_BTF_ID 3
/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
* offset to another bpf function
@@ -404,6 +432,12 @@ enum {
/* Enable memory-mapping BPF map */
BPF_F_MMAPABLE = (1U << 10),
+
+/* Share perf_event among processes */
+ BPF_F_PRESERVE_ELEMS = (1U << 11),
+
+/* Create a map that is suitable to be an inner map with dynamic max entries */
+ BPF_F_INNER_MAP = (1U << 12),
};
/* Flags for BPF_PROG_QUERY. */
@@ -414,6 +448,11 @@ enum {
*/
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
+/* Flags for BPF_PROG_TEST_RUN */
+
+/* If set, run the test on the cpu specified by bpf_attr.test.cpu */
+#define BPF_F_TEST_RUN_ON_CPU (1U << 0)
+
/* type for BPF_ENABLE_STATS */
enum bpf_stats_type {
/* enabled run_time_ns and run_cnt */
@@ -556,6 +595,8 @@ union bpf_attr {
*/
__aligned_u64 ctx_in;
__aligned_u64 ctx_out;
+ __u32 flags;
+ __u32 cpu;
} test;
struct { /* anonymous struct used by BPF_*_GET_*_ID */
@@ -622,8 +663,13 @@ union bpf_attr {
};
__u32 attach_type; /* attach type */
__u32 flags; /* extra flags */
- __aligned_u64 iter_info; /* extra bpf_iter_link_info */
- __u32 iter_info_len; /* iter_info length */
+ union {
+ __u32 target_btf_id; /* btf_id of target to attach to */
+ struct {
+ __aligned_u64 iter_info; /* extra bpf_iter_link_info */
+ __u32 iter_info_len; /* iter_info length */
+ };
+ };
} link_create;
struct { /* struct used by BPF_LINK_UPDATE command */
@@ -649,6 +695,12 @@ union bpf_attr {
__u32 flags;
} iter_create;
+ struct { /* struct used by BPF_PROG_BIND_MAP command */
+ __u32 prog_fd;
+ __u32 map_fd;
+ __u32 flags; /* extra flags */
+ } prog_bind_map;
+
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF
@@ -1438,8 +1490,8 @@ union bpf_attr {
* Return
* The return value depends on the result of the test, and can be:
*
- * * 0, if the *skb* task belongs to the cgroup2.
- * * 1, if the *skb* task does not belong to the cgroup2.
+ * * 0, if current task belongs to the cgroup2.
+ * * 1, if current task does not belong to the cgroup2.
* * A negative error code, if an error occurred.
*
* long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
@@ -1649,7 +1701,7 @@ union bpf_attr {
* **TCP_CONGESTION**, **TCP_BPF_IW**,
* **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
* **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
- * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**.
+ * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**.
* * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
* * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
* Return
@@ -2204,7 +2256,7 @@ union bpf_attr {
* Description
* This helper is used in programs implementing policies at the
* skb socket level. If the sk_buff *skb* is allowed to pass (i.e.
- * if the verdeict eBPF program returns **SK_PASS**), redirect it
+ * if the verdict eBPF program returns **SK_PASS**), redirect it
* to the socket referenced by *map* (of type
* **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
* egress interfaces can be used for redirection. The
@@ -2496,7 +2548,7 @@ union bpf_attr {
* result is from *reuse*\ **->socks**\ [] using the hash of the
* tuple.
*
- * long bpf_sk_release(struct bpf_sock *sock)
+ * long bpf_sk_release(void *sock)
* Description
* Release the reference held by *sock*. *sock* must be a
* non-**NULL** pointer that was returned from
@@ -2676,7 +2728,7 @@ union bpf_attr {
* result is from *reuse*\ **->socks**\ [] using the hash of the
* tuple.
*
- * long bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
* Description
* Check whether *iph* and *th* contain a valid SYN cookie ACK for
* the listening socket in *sk*.
@@ -2807,7 +2859,7 @@ union bpf_attr {
*
* **-ERANGE** if resulting value was out of range.
*
- * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags)
+ * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags)
* Description
* Get a bpf-local-storage from a *sk*.
*
@@ -2823,6 +2875,9 @@ union bpf_attr {
* "type". The bpf-local-storage "type" (i.e. the *map*) is
* searched against all bpf-local-storages residing at *sk*.
*
+ * *sk* is a kernel **struct sock** pointer for LSM program.
+ * *sk* is a **struct bpf_sock** pointer for other program types.
+ *
* An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be
* used such that a new bpf-local-storage will be
* created if one does not exist. *value* can be used
@@ -2835,13 +2890,14 @@ union bpf_attr {
* **NULL** if not found or there was an error in adding
* a new bpf-local-storage.
*
- * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk)
+ * long bpf_sk_storage_delete(struct bpf_map *map, void *sk)
* Description
* Delete a bpf-local-storage from a *sk*.
* Return
* 0 on success.
*
* **-ENOENT** if the bpf-local-storage cannot be found.
+ * **-EINVAL** if sk is not a fullsock (e.g. a request_sock).
*
* long bpf_send_signal(u32 sig)
* Description
@@ -2858,7 +2914,7 @@ union bpf_attr {
*
* **-EAGAIN** if bpf program can try again.
*
- * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
* Description
* Try to issue a SYN cookie for the packet with corresponding
* IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
@@ -3087,7 +3143,7 @@ union bpf_attr {
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
- * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
+ * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags)
* Description
* Helper is overloaded depending on BPF program type. This
* description applies to **BPF_PROG_TYPE_SCHED_CLS** and
@@ -3215,11 +3271,11 @@ union bpf_attr {
*
* **-EOVERFLOW** if an overflow happened: The same object will be tried again.
*
- * u64 bpf_sk_cgroup_id(struct bpf_sock *sk)
+ * u64 bpf_sk_cgroup_id(void *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
+ * *sk* must be a non-**NULL** pointer to a 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**\ ().
@@ -3229,7 +3285,7 @@ union bpf_attr {
* 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)
+ * u64 bpf_sk_ancestor_cgroup_id(void *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
@@ -3337,38 +3393,38 @@ union bpf_attr {
* Description
* Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
* Return
- * *sk* if casting is valid, or NULL otherwise.
+ * *sk* if casting is valid, or **NULL** otherwise.
*
* struct tcp_sock *bpf_skc_to_tcp_sock(void *sk)
* Description
* Dynamically cast a *sk* pointer to a *tcp_sock* pointer.
* Return
- * *sk* if casting is valid, or NULL otherwise.
+ * *sk* if casting is valid, or **NULL** otherwise.
*
* struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk)
* Description
* Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer.
* Return
- * *sk* if casting is valid, or NULL otherwise.
+ * *sk* if casting is valid, or **NULL** otherwise.
*
* struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk)
* Description
* Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
* Return
- * *sk* if casting is valid, or NULL otherwise.
+ * *sk* if casting is valid, or **NULL** otherwise.
*
* struct udp6_sock *bpf_skc_to_udp6_sock(void *sk)
* Description
* Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
* Return
- * *sk* if casting is valid, or NULL otherwise.
+ * *sk* if casting is valid, or **NULL** otherwise.
*
* long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
* Description
* Return a user or a kernel stack in bpf program provided buffer.
* To achieve this, the helper needs *task*, which is a valid
- * pointer to struct task_struct. To store the stacktrace, the
- * bpf program provides *buf* with a nonnegative *size*.
+ * pointer to **struct task_struct**. To store the stacktrace, the
+ * bpf program provides *buf* with a nonnegative *size*.
*
* The last argument, *flags*, holds the number of stack frames to
* skip (from 0 to 255), masked with
@@ -3395,6 +3451,293 @@ union bpf_attr {
* A non-negative value equal to or less than *size* on success,
* or a negative error in case of failure.
*
+ * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
+ * Description
+ * Load header option. Support reading a particular TCP header
+ * option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**).
+ *
+ * If *flags* is 0, it will search the option from the
+ * *skops*\ **->skb_data**. The comment in **struct bpf_sock_ops**
+ * has details on what skb_data contains under different
+ * *skops*\ **->op**.
+ *
+ * The first byte of the *searchby_res* specifies the
+ * kind that it wants to search.
+ *
+ * If the searching kind is an experimental kind
+ * (i.e. 253 or 254 according to RFC6994). It also
+ * needs to specify the "magic" which is either
+ * 2 bytes or 4 bytes. It then also needs to
+ * specify the size of the magic by using
+ * the 2nd byte which is "kind-length" of a TCP
+ * header option and the "kind-length" also
+ * includes the first 2 bytes "kind" and "kind-length"
+ * itself as a normal TCP header option also does.
+ *
+ * For example, to search experimental kind 254 with
+ * 2 byte magic 0xeB9F, the searchby_res should be
+ * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ].
+ *
+ * To search for the standard window scale option (3),
+ * the *searchby_res* should be [ 3, 0, 0, .... 0 ].
+ * Note, kind-length must be 0 for regular option.
+ *
+ * Searching for No-Op (0) and End-of-Option-List (1) are
+ * not supported.
+ *
+ * *len* must be at least 2 bytes which is the minimal size
+ * of a header option.
+ *
+ * Supported flags:
+ *
+ * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the
+ * saved_syn packet or the just-received syn packet.
+ *
+ * Return
+ * > 0 when found, the header option is copied to *searchby_res*.
+ * The return value is the total length copied. On failure, a
+ * negative error code is returned:
+ *
+ * **-EINVAL** if a parameter is invalid.
+ *
+ * **-ENOMSG** if the option is not found.
+ *
+ * **-ENOENT** if no syn packet is available when
+ * **BPF_LOAD_HDR_OPT_TCP_SYN** is used.
+ *
+ * **-ENOSPC** if there is not enough space. Only *len* number of
+ * bytes are copied.
+ *
+ * **-EFAULT** on failure to parse the header options in the
+ * packet.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags)
+ * Description
+ * Store header option. The data will be copied
+ * from buffer *from* with length *len* to the TCP header.
+ *
+ * The buffer *from* should have the whole option that
+ * includes the kind, kind-length, and the actual
+ * option data. The *len* must be at least kind-length
+ * long. The kind-length does not have to be 4 byte
+ * aligned. The kernel will take care of the padding
+ * and setting the 4 bytes aligned value to th->doff.
+ *
+ * This helper will check for duplicated option
+ * by searching the same option in the outgoing skb.
+ *
+ * This helper can only be called during
+ * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
+ *
+ * Return
+ * 0 on success, or negative error in case of failure:
+ *
+ * **-EINVAL** If param is invalid.
+ *
+ * **-ENOSPC** if there is not enough space in the header.
+ * Nothing has been written
+ *
+ * **-EEXIST** if the option already exists.
+ *
+ * **-EFAULT** on failrue to parse the existing header options.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags)
+ * Description
+ * Reserve *len* bytes for the bpf header option. The
+ * space will be used by **bpf_store_hdr_opt**\ () later in
+ * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
+ *
+ * If **bpf_reserve_hdr_opt**\ () is called multiple times,
+ * the total number of bytes will be reserved.
+ *
+ * This helper can only be called during
+ * **BPF_SOCK_OPS_HDR_OPT_LEN_CB**.
+ *
+ * Return
+ * 0 on success, or negative error in case of failure:
+ *
+ * **-EINVAL** if a parameter is invalid.
+ *
+ * **-ENOSPC** if there is not enough space in the header.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from an *inode*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *inode* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this
+ * helper enforces the key must be an inode and the map must also
+ * be a **BPF_MAP_TYPE_INODE_STORAGE**.
+ *
+ * Underneath, the value is stored locally at *inode* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf_local_storage residing at *inode*.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * int bpf_inode_storage_delete(struct bpf_map *map, void *inode)
+ * Description
+ * Delete a bpf_local_storage from an *inode*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * long bpf_d_path(struct path *path, char *buf, u32 sz)
+ * Description
+ * Return full path for given **struct path** object, which
+ * needs to be the kernel BTF *path* object. The path is
+ * returned in the provided buffer *buf* of size *sz* and
+ * is zero terminated.
+ *
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
+ * Description
+ * Read *size* bytes from user space address *user_ptr* and store
+ * the data in *dst*. This is a wrapper of **copy_from_user**\ ().
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ * Description
+ * Use BTF to store a string representation of *ptr*->ptr in *str*,
+ * using *ptr*->type_id. This value should specify the type
+ * that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1)
+ * can be used to look up vmlinux BTF type ids. Traversing the
+ * data structure using BTF, the type information and values are
+ * stored in the first *str_size* - 1 bytes of *str*. Safe copy of
+ * the pointer data is carried out to avoid kernel crashes during
+ * operation. Smaller types can use string space on the stack;
+ * larger programs can use map data to store the string
+ * representation.
+ *
+ * The string can be subsequently shared with userspace via
+ * bpf_perf_event_output() or ring buffer interfaces.
+ * bpf_trace_printk() is to be avoided as it places too small
+ * a limit on string size to be useful.
+ *
+ * *flags* is a combination of
+ *
+ * **BTF_F_COMPACT**
+ * no formatting around type information
+ * **BTF_F_NONAME**
+ * no struct/union member names/types
+ * **BTF_F_PTR_RAW**
+ * show raw (unobfuscated) pointer values;
+ * equivalent to printk specifier %px.
+ * **BTF_F_ZERO**
+ * show zero-valued struct/union members; they
+ * are not displayed by default
+ *
+ * Return
+ * The number of bytes that were written (or would have been
+ * written if output had to be truncated due to string size),
+ * or a negative error in cases of failure.
+ *
+ * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags)
+ * Description
+ * Use BTF to write to seq_write a string representation of
+ * *ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf().
+ * *flags* are identical to those used for bpf_snprintf_btf.
+ * Return
+ * 0 on success or a negative error in case of failure.
+ *
+ * u64 bpf_skb_cgroup_classid(struct sk_buff *skb)
+ * Description
+ * See **bpf_get_cgroup_classid**\ () for the main description.
+ * This helper differs from **bpf_get_cgroup_classid**\ () in that
+ * the cgroup v1 net_cls class is retrieved only from the *skb*'s
+ * associated socket instead of the current process.
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_redirect_neigh(u32 ifindex, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*
+ * and fill in L2 addresses from neighboring subsystem. This helper
+ * is somewhat similar to **bpf_redirect**\ (), except that it
+ * populates L2 addresses as well, meaning, internally, the helper
+ * performs a FIB lookup based on the skb's networking header to
+ * get the address of the next hop and then relies on the neighbor
+ * lookup for the L2 address of the nexthop.
+ *
+ * The *flags* argument is reserved and must be 0. The helper is
+ * currently only supported for tc BPF program types, and enabled
+ * for IPv4 and IPv6 protocols.
+ * Return
+ * The helper returns **TC_ACT_REDIRECT** on success or
+ * **TC_ACT_SHOT** on error.
+ *
+ * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu)
+ * Description
+ * Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ * pointer to the percpu kernel variable on *cpu*. A ksym is an
+ * extern variable decorated with '__ksym'. For ksym, there is a
+ * global var (either static or global) defined of the same name
+ * in the kernel. The ksym is percpu if the global var is percpu.
+ * The returned pointer points to the global percpu var on *cpu*.
+ *
+ * bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the
+ * kernel, except that bpf_per_cpu_ptr() may return NULL. This
+ * happens if *cpu* is larger than nr_cpu_ids. The caller of
+ * bpf_per_cpu_ptr() must check the returned value.
+ * Return
+ * A pointer pointing to the kernel percpu variable on *cpu*, or
+ * NULL, if *cpu* is invalid.
+ *
+ * void *bpf_this_cpu_ptr(const void *percpu_ptr)
+ * Description
+ * Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ * pointer to the percpu kernel variable on this cpu. See the
+ * description of 'ksym' in **bpf_per_cpu_ptr**\ ().
+ *
+ * bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in
+ * the kernel. Different from **bpf_per_cpu_ptr**\ (), it would
+ * never return NULL.
+ * Return
+ * A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * long bpf_redirect_peer(u32 ifindex, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*.
+ * This helper is somewhat similar to **bpf_redirect**\ (), except
+ * that the redirection happens to the *ifindex*' peer device and
+ * the netns switch takes place from ingress to ingress without
+ * going through the CPU's backlog queue.
+ *
+ * The *flags* argument is reserved and must be 0. The helper is
+ * currently only supported for tc BPF program types at the ingress
+ * hook and for veth device types. The peer device must reside in a
+ * different network namespace.
+ * Return
+ * The helper returns **TC_ACT_REDIRECT** on success or
+ * **TC_ACT_SHOT** on error.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -3539,6 +3882,20 @@ union bpf_attr {
FN(skc_to_tcp_request_sock), \
FN(skc_to_udp6_sock), \
FN(get_task_stack), \
+ FN(load_hdr_opt), \
+ FN(store_hdr_opt), \
+ FN(reserve_hdr_opt), \
+ FN(inode_storage_get), \
+ FN(inode_storage_delete), \
+ FN(d_path), \
+ FN(copy_from_user), \
+ FN(snprintf_btf), \
+ FN(seq_printf_btf), \
+ FN(skb_cgroup_classid), \
+ FN(redirect_neigh), \
+ FN(bpf_per_cpu_ptr), \
+ FN(bpf_this_cpu_ptr), \
+ FN(redirect_peer), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -3648,9 +4005,13 @@ enum {
BPF_F_SYSCTL_BASE_NAME = (1ULL << 0),
};
-/* BPF_FUNC_sk_storage_get flags */
+/* BPF_FUNC_<kernel_obj>_storage_get flags */
enum {
- BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0),
+ BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0),
+ /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility
+ * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead.
+ */
+ BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE,
};
/* BPF_FUNC_read_branch_records flags. */
@@ -4071,6 +4432,15 @@ struct bpf_link_info {
__u64 cgroup_id;
__u32 attach_type;
} cgroup;
+ struct {
+ __aligned_u64 target_name; /* in/out: target_name buffer ptr */
+ __u32 target_name_len; /* in/out: target_name buffer len */
+ union {
+ struct {
+ __u32 map_id;
+ } map;
+ };
+ } iter;
struct {
__u32 netns_ino;
__u32 attach_type;
@@ -4158,6 +4528,36 @@ struct bpf_sock_ops {
__u64 bytes_received;
__u64 bytes_acked;
__bpf_md_ptr(struct bpf_sock *, sk);
+ /* [skb_data, skb_data_end) covers the whole TCP header.
+ *
+ * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received
+ * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the
+ * header has not been written.
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have
+ * been written so far.
+ * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes
+ * the 3WHS.
+ * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes
+ * the 3WHS.
+ *
+ * bpf_load_hdr_opt() can also be used to read a particular option.
+ */
+ __bpf_md_ptr(void *, skb_data);
+ __bpf_md_ptr(void *, skb_data_end);
+ __u32 skb_len; /* The total length of a packet.
+ * It includes the header, options,
+ * and payload.
+ */
+ __u32 skb_tcp_flags; /* tcp_flags of the header. It provides
+ * an easy way to check for tcp_flags
+ * without parsing skb_data.
+ *
+ * In particular, the skb_tcp_flags
+ * will still be available in
+ * BPF_SOCK_OPS_HDR_OPT_LEN even though
+ * the outgoing header has not
+ * been written yet.
+ */
};
/* Definitions for bpf_sock_ops_cb_flags */
@@ -4166,8 +4566,51 @@ enum {
BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1),
BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2),
BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3),
+ /* Call bpf for all received TCP headers. The bpf prog will be
+ * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ * for the header option related helpers that will be useful
+ * to the bpf programs.
+ *
+ * It could be used at the client/active side (i.e. connect() side)
+ * when the server told it that the server was in syncookie
+ * mode and required the active side to resend the bpf-written
+ * options. The active side can keep writing the bpf-options until
+ * it received a valid packet from the server side to confirm
+ * the earlier packet (and options) has been received. The later
+ * example patch is using it like this at the active side when the
+ * server is in syncookie mode.
+ *
+ * The bpf prog will usually turn this off in the common cases.
+ */
+ BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4),
+ /* Call bpf when kernel has received a header option that
+ * the kernel cannot handle. The bpf prog will be called under
+ * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB.
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ * for the header option related helpers that will be useful
+ * to the bpf programs.
+ */
+ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5),
+ /* Call bpf when the kernel is writing header options for the
+ * outgoing packet. The bpf prog will first be called
+ * to reserve space in a skb under
+ * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then
+ * the bpf prog will be called to write the header option(s)
+ * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB
+ * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option
+ * related helpers that will be useful to the bpf programs.
+ *
+ * The kernel gets its chance to reserve space and write
+ * options first before the BPF program does.
+ */
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6),
/* Mask of all currently supported cb flags */
- BPF_SOCK_OPS_ALL_CB_FLAGS = 0xF,
+ BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F,
};
/* List of known BPF sock_ops operators.
@@ -4223,6 +4666,63 @@ enum {
*/
BPF_SOCK_OPS_RTT_CB, /* Called on every RTT.
*/
+ BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option.
+ * It will be called to handle
+ * the packets received at
+ * an already established
+ * connection.
+ *
+ * sock_ops->skb_data:
+ * Referring to the received skb.
+ * It covers the TCP header only.
+ *
+ * bpf_load_hdr_opt() can also
+ * be used to search for a
+ * particular option.
+ */
+ BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the
+ * header option later in
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ * Arg1: bool want_cookie. (in
+ * writing SYNACK only)
+ *
+ * sock_ops->skb_data:
+ * Not available because no header has
+ * been written yet.
+ *
+ * sock_ops->skb_tcp_flags:
+ * The tcp_flags of the
+ * outgoing skb. (e.g. SYN, ACK, FIN).
+ *
+ * bpf_reserve_hdr_opt() should
+ * be used to reserve space.
+ */
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options
+ * Arg1: bool want_cookie. (in
+ * writing SYNACK only)
+ *
+ * sock_ops->skb_data:
+ * Referring to the outgoing skb.
+ * It covers the TCP header
+ * that has already been written
+ * by the kernel and the
+ * earlier bpf-progs.
+ *
+ * sock_ops->skb_tcp_flags:
+ * The tcp_flags of the outgoing
+ * skb. (e.g. SYN, ACK, FIN).
+ *
+ * bpf_store_hdr_opt() should
+ * be used to write the
+ * option.
+ *
+ * bpf_load_hdr_opt() can also
+ * be used to search for a
+ * particular option that
+ * has already been written
+ * by the kernel or the
+ * earlier bpf-progs.
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
@@ -4250,6 +4750,63 @@ enum {
enum {
TCP_BPF_IW = 1001, /* Set TCP initial congestion window */
TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */
+ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */
+ TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */
+ /* Copy the SYN pkt to optval
+ *
+ * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the
+ * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit
+ * to only getting from the saved_syn. It can either get the
+ * syn packet from:
+ *
+ * 1. the just-received SYN packet (only available when writing the
+ * SYNACK). It will be useful when it is not necessary to
+ * save the SYN packet for latter use. It is also the only way
+ * to get the SYN during syncookie mode because the syn
+ * packet cannot be saved during syncookie.
+ *
+ * OR
+ *
+ * 2. the earlier saved syn which was done by
+ * bpf_setsockopt(TCP_SAVE_SYN).
+ *
+ * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the
+ * SYN packet is obtained.
+ *
+ * If the bpf-prog does not need the IP[46] header, the
+ * bpf-prog can avoid parsing the IP header by using
+ * TCP_BPF_SYN. Otherwise, the bpf-prog can get both
+ * IP[46] and TCP header by using TCP_BPF_SYN_IP.
+ *
+ * >0: Total number of bytes copied
+ * -ENOSPC: Not enough space in optval. Only optlen number of
+ * bytes is copied.
+ * -ENOENT: The SYN skb is not available now and the earlier SYN pkt
+ * is not saved by setsockopt(TCP_SAVE_SYN).
+ */
+ TCP_BPF_SYN = 1005, /* Copy the TCP header */
+ TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */
+ TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */
+};
+
+enum {
+ BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0),
+};
+
+/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ */
+enum {
+ BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the
+ * total option spaces
+ * required for an established
+ * sk in order to calculate the
+ * MSS. No skb is actually
+ * sent.
+ */
+ BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode
+ * when sending a SYN.
+ */
};
struct bpf_perf_event_value {
@@ -4447,4 +5004,34 @@ struct bpf_sk_lookup {
__u32 local_port; /* Host byte order */
};
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * type id is used to render the pointer data as the appropriate type
+ * via the bpf_snprintf_btf() helper described above. A flags field -
+ * potentially to specify additional details about the BTF pointer
+ * (rather than its mode of display) - is included for future use.
+ * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+ void *ptr;
+ __u32 type_id;
+ __u32 flags; /* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ * - BTF_F_COMPACT: no formatting around type information
+ * - BTF_F_NONAME: no struct/union member names/types
+ * - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ * equivalent to %px.
+ * - BTF_F_ZERO: show zero-valued struct/union members; they
+ * are not displayed by default
+ */
+enum {
+ BTF_F_COMPACT = (1ULL << 0),
+ BTF_F_NONAME = (1ULL << 1),
+ BTF_F_PTR_RAW = (1ULL << 2),
+ BTF_F_ZERO = (1ULL << 3),
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */