diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-07 22:03:58 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-07 22:03:58 -0700 |
commit | 80f232121b69cc69a31ccb2b38c1665d770b0710 (patch) | |
tree | 106263eac4ff03b899df695e00dd11e593e74fe2 /tools/include | |
parent | 82efe439599439a5e1e225ce5740e6cfb777a7dd (diff) | |
parent | a9e41a529681b38087c91ebc0bb91e12f510ca2d (diff) | |
download | linux-next-80f232121b69cc69a31ccb2b38c1665d770b0710.tar.gz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.
2) Add fib_sync_mem to control the amount of dirty memory we allow to
queue up between synchronize RCU calls, from David Ahern.
3) Make flow classifier more lockless, from Vlad Buslov.
4) Add PHY downshift support to aquantia driver, from Heiner
Kallweit.
5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
contention on SLAB spinlocks in heavy RPC workloads.
6) Partial GSO offload support in XFRM, from Boris Pismenny.
7) Add fast link down support to ethtool, from Heiner Kallweit.
8) Use siphash for IP ID generator, from Eric Dumazet.
9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
entries, from David Ahern.
10) Move skb->xmit_more into a per-cpu variable, from Florian
Westphal.
11) Improve eBPF verifier speed and increase maximum program size,
from Alexei Starovoitov.
12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
spinlocks. From Neil Brown.
13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.
14) Improve link partner cap detection in generic PHY code, from
Heiner Kallweit.
15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
Maguire.
16) Remove SKB list implementation assumptions in SCTP, your's truly.
17) Various cleanups, optimizations, and simplifications in r8169
driver. From Heiner Kallweit.
18) Add memory accounting on TX and RX path of SCTP, from Xin Long.
19) Switch PHY drivers over to use dynamic featue detection, from
Heiner Kallweit.
20) Support flow steering without masking in dpaa2-eth, from Ioana
Ciocoi.
21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
Pirko.
22) Increase the strict parsing of current and future netlink
attributes, also export such policies to userspace. From Johannes
Berg.
23) Allow DSA tag drivers to be modular, from Andrew Lunn.
24) Remove legacy DSA probing support, also from Andrew Lunn.
25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
Haabendal.
26) Add a generic tracepoint for TX queue timeouts to ease debugging,
from Cong Wang.
27) More indirect call optimizations, from Paolo Abeni"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
cxgb4: Fix error path in cxgb4_init_module
net: phy: improve pause mode reporting in phy_print_status
dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
net: macb: Change interrupt and napi enable order in open
net: ll_temac: Improve error message on error IRQ
net/sched: remove block pointer from common offload structure
net: ethernet: support of_get_mac_address new ERR_PTR error
net: usb: smsc: fix warning reported by kbuild test robot
staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
net: dsa: support of_get_mac_address new ERR_PTR error
net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
vrf: sit mtu should not be updated when vrf netdev is the link
net: dsa: Fix error cleanup path in dsa_init_module
l2tp: Fix possible NULL pointer dereference
taprio: add null check on sched_nest to avoid potential null pointer dereference
net: mvpp2: cls: fix less than zero check on a u32 variable
net_sched: sch_fq: handle non connected flows
net_sched: sch_fq: do not assume EDT packets are ordered
net: hns3: use devm_kcalloc when allocating desc_cb
net: hns3: some cleanup for struct hns3_enet_ring
...
Diffstat (limited to 'tools/include')
-rw-r--r-- | tools/include/linux/filter.h | 21 | ||||
-rw-r--r-- | tools/include/uapi/linux/bpf.h | 291 | ||||
-rw-r--r-- | tools/include/uapi/linux/btf.h | 32 |
3 files changed, 332 insertions, 12 deletions
diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index cce0b02c0e28..ca28b6ab8db7 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -278,10 +278,29 @@ .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) +#define BPF_LD_IMM64_RAW_FULL(DST, SRC, OFF1, OFF2, IMM1, IMM2) \ + ((struct bpf_insn) { \ + .code = BPF_LD | BPF_DW | BPF_IMM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF1, \ + .imm = IMM1 }), \ + ((struct bpf_insn) { \ + .code = 0, /* zero is reserved opcode */ \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = OFF2, \ + .imm = IMM2 }) + /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ - BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) + BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_FD, 0, 0, \ + MAP_FD, 0) + +#define BPF_LD_MAP_VALUE(DST, MAP_FD, VALUE_OFF) \ + BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_VALUE, 0, 0, \ + MAP_FD, VALUE_OFF) /* Relative call */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 929c8e537a14..72336bac7573 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -105,6 +105,7 @@ enum bpf_cmd { BPF_BTF_GET_FD_BY_ID, BPF_TASK_FD_QUERY, BPF_MAP_LOOKUP_AND_DELETE_ELEM, + BPF_MAP_FREEZE, }; enum bpf_map_type { @@ -132,6 +133,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, + BPF_MAP_TYPE_SK_STORAGE, }; /* Note that tracing related programs such as @@ -166,6 +168,8 @@ enum bpf_prog_type { BPF_PROG_TYPE_LIRC_MODE2, BPF_PROG_TYPE_SK_REUSEPORT, BPF_PROG_TYPE_FLOW_DISSECTOR, + BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, }; enum bpf_attach_type { @@ -187,6 +191,7 @@ enum bpf_attach_type { BPF_CGROUP_UDP6_SENDMSG, BPF_LIRC_MODE2, BPF_FLOW_DISSECTOR, + BPF_CGROUP_SYSCTL, __MAX_BPF_ATTACH_TYPE }; @@ -255,8 +260,19 @@ enum bpf_attach_type { */ #define BPF_F_ANY_ALIGNMENT (1U << 1) -/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ +/* 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 + */ #define BPF_PSEUDO_MAP_FD 1 +#define BPF_PSEUDO_MAP_VALUE 2 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative * offset to another bpf function @@ -283,7 +299,7 @@ enum bpf_attach_type { #define BPF_OBJ_NAME_LEN 16U -/* Flags for accessing BPF object */ +/* Flags for accessing BPF object from syscall side. */ #define BPF_F_RDONLY (1U << 3) #define BPF_F_WRONLY (1U << 4) @@ -293,6 +309,10 @@ enum bpf_attach_type { /* Zero-initialize hash function seed. This should only be used for testing. */ #define BPF_F_ZERO_SEED (1U << 6) +/* Flags for accessing BPF object from program side. */ +#define BPF_F_RDONLY_PROG (1U << 7) +#define BPF_F_WRONLY_PROG (1U << 8) + /* flags for BPF_PROG_QUERY */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) @@ -396,6 +416,13 @@ union bpf_attr { __aligned_u64 data_out; __u32 repeat; __u32 duration; + __u32 ctx_size_in; /* input: len of ctx_in */ + __u32 ctx_size_out; /* input/output: len of ctx_out + * returns ENOSPC if ctx_out + * is too small. + */ + __aligned_u64 ctx_in; + __aligned_u64 ctx_out; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ @@ -1478,13 +1505,31 @@ 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*. * - * There is a single supported mode at this time: + * There are two supported modes at this time: + * + * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer + * (room space is added or removed below the layer 2 header). * * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer * (room space is added or removed below the layer 3 header). * - * All values for *flags* are reserved for future usage, and must - * be left at zero. + * The following flags are supported at this time: + * + * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size. + * Adjusting mss in this way is not allowed for datagrams. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 **: + * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 **: + * Any new space is reserved to hold a tunnel header. + * Configure skb offsets and other fields accordingly. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE **: + * * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **: + * Use with ENCAP_L3 flags to further specify the tunnel type. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L2(len) **: + * Use with ENCAP_L3/L4 flags to further specify the tunnel + * type; **len** is the length of the inner MAC header. * * A call to this helper is susceptible to change the underlaying * packet buffer. Therefore, at load time, all checks on pointers @@ -1694,12 +1739,19 @@ union bpf_attr { * error if an eBPF program tries to set a callback that is not * supported in the current kernel. * - * The supported callback values that *argval* can combine are: + * *argval* is a flag array which can combine these flags: * * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) * + * Therefore, this function can be used to clear a callback flag by + * setting the appropriate bit to zero. e.g. to disable the RTO + * callback: + * + * **bpf_sock_ops_cb_flags_set(bpf_sock,** + * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)** + * * Here are some examples of where one could call such eBPF * program: * @@ -2431,6 +2483,190 @@ union bpf_attr { * Return * A **struct bpf_sock** pointer on success, or **NULL** in * case of failure. + * + * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * This function is identical to bpf_sk_lookup_tcp, except that it + * also returns timewait or request sockets. Use bpf_sk_fullsock + * or bpf_tcp_socket to access the full structure. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from **reuse->socks**\ [] using the hash of the tuple. + * + * int bpf_tcp_check_syncookie(struct bpf_sock *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. + * + * iph points to the start of the IPv4 or IPv6 header, while + * iph_len contains sizeof(struct iphdr) or sizeof(struct ip6hdr). + * + * 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. + * + * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags) + * Description + * Get name of sysctl in /proc/sys/ and copy it into provided by + * program buffer *buf* of size *buf_len*. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is + * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name + * only (e.g. "tcp_mem"). + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get current value of sysctl as it is presented in /proc/sys + * (incl. newline, etc), and copy it as a string into provided + * by program buffer *buf* of size *buf_len*. + * + * The whole value is copied, no matter what file position user + * space issued e.g. sys_read at. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if current value was unavailable, e.g. because + * sysctl is uninitialized and read returns -EIO for it. + * + * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get new value being written by user space to sysctl (before + * the actual write happens) and copy it as a string into + * provided by program buffer *buf* of size *buf_len*. + * + * User space may write new value at file position > 0. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) + * Description + * Override new value being written by user space to sysctl with + * value provided by program in buffer *buf* of size *buf_len*. + * + * *buf* should contain a string in same form as provided by user + * space on sysctl write. + * + * User space may write new value at file position > 0. To override + * the whole sysctl value file position should be set to zero. + * Return + * 0 on success. + * + * **-E2BIG** if the *buf_len* is too big. + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to a long integer according to the given base + * and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by isspace(3)) followed by a single optional '-' + * sign. + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space strtol(3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than buf_len. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to an unsigned long integer according to the + * given base and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by isspace(3)). + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space strtoul(3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than buf_len. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-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) + * Description + * Get a bpf-local-storage from a sk. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem(map, &sk)** except this + * helper enforces the key must be a **bpf_fullsock()** + * and the map must be a BPF_MAP_TYPE_SK_STORAGE also. + * + * Underneath, the value is stored locally at *sk* 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-storages residing at sk. + * + * 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 + * together with BPF_SK_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_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * Description + * Delete a bpf-local-storage from a sk. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2531,7 +2767,17 @@ union bpf_attr { FN(sk_fullsock), \ FN(tcp_sock), \ FN(skb_ecn_set_ce), \ - FN(get_listener_sock), + FN(get_listener_sock), \ + FN(skc_lookup_tcp), \ + FN(tcp_check_syncookie), \ + FN(sysctl_get_name), \ + FN(sysctl_get_current_value), \ + FN(sysctl_get_new_value), \ + FN(sysctl_set_new_value), \ + FN(strtol), \ + FN(strtoul), \ + FN(sk_storage_get), \ + FN(sk_storage_delete), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2590,9 +2836,30 @@ enum bpf_func_id { /* Current network namespace */ #define BPF_F_CURRENT_NETNS (-1L) +/* BPF_FUNC_skb_adjust_room flags. */ +#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0) + +#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff +#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56 + +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1) +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2) +#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3) +#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4) +#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \ + BPF_ADJ_ROOM_ENCAP_L2_MASK) \ + << BPF_ADJ_ROOM_ENCAP_L2_SHIFT) + +/* BPF_FUNC_sysctl_get_name flags. */ +#define BPF_F_SYSCTL_BASE_NAME (1ULL << 0) + +/* BPF_FUNC_sk_storage_get flags */ +#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, + BPF_ADJ_ROOM_MAC, }; /* Mode for BPF_FUNC_skb_load_bytes_relative helper. */ @@ -3218,4 +3485,14 @@ struct bpf_line_info { struct bpf_spin_lock { __u32 val; }; + +struct bpf_sysctl { + __u32 write; /* Sysctl is being read (= 0) or written (= 1). + * Allows 1,2,4-byte read, but no write. + */ + __u32 file_pos; /* Sysctl file position to read from, write to. + * Allows 1,2,4-byte read an 4-byte write. + */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 7b7475ef2f17..9310652ca4f9 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -39,11 +39,11 @@ struct btf_type { * struct, union and fwd */ __u32 info; - /* "size" is used by INT, ENUM, STRUCT and UNION. + /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC. * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC and FUNC_PROTO. + * FUNC, FUNC_PROTO and VAR. * "type" is a type_id referring to another type. */ union { @@ -70,8 +70,10 @@ struct btf_type { #define BTF_KIND_RESTRICT 11 /* Restrict */ #define BTF_KIND_FUNC 12 /* Function */ #define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#define BTF_KIND_MAX 13 -#define NR_BTF_KINDS 14 +#define BTF_KIND_VAR 14 /* Variable */ +#define BTF_KIND_DATASEC 15 /* Section */ +#define BTF_KIND_MAX BTF_KIND_DATASEC +#define NR_BTF_KINDS (BTF_KIND_MAX + 1) /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. @@ -138,4 +140,26 @@ struct btf_param { __u32 type; }; +enum { + BTF_VAR_STATIC = 0, + BTF_VAR_GLOBAL_ALLOCATED, +}; + +/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe + * additional information related to the variable such as its linkage. + */ +struct btf_var { + __u32 linkage; +}; + +/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo" + * to describe all BTF_KIND_VAR types it contains along with it's + * in-section offset as well as size. + */ +struct btf_var_secinfo { + __u32 type; + __u32 offset; + __u32 size; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ |