sync with latest libbpf

sync with latest libbpf with top commit: 092a60685625 Makefile: fix install flags order Signed-off-by: Yonghong Song <[email protected]>
nanshuaibo · Mar 20, 2021 · 887e05a · 887e05a
1 parent 24eeae2
commit 887e05a
Show file tree

Hide file tree

Showing 5 changed files with 158 additions and 14 deletions.
diff --git a/docs/kernel-versions.md b/docs/kernel-versions.md
@@ -208,6 +208,7 @@ Helper | Kernel version | License | Commit |
 -------|----------------|---------|--------|
 `BPF_FUNC_bind()` | 4.17 | | [`d74bad4e74ee`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=d74bad4e74ee373787a9ae24197c17b7cdc428d5) |
 `BPF_FUNC_bprm_opts_set()` | 5.11 | | [`3f6719c7b62f`](https://github.com/torvalds/linux/commit/3f6719c7b62f0327c9091e26d0da10e65668229e)
+`BPF_FUNC_check_mtu()` | 5.12 | | [`34b2021cc616`](https://github.com/torvalds/linux/commit/34b2021cc61642d61c3cf943d9e71925b827941b)
 `BPF_FUNC_clone_redirect()` | 4.2 | | [`3896d655f4d4`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=3896d655f4d491c67d669a15f275a39f713410f8)
 `BPF_FUNC_copy_from_user()` | 5.10 | | [`07be4c4a3e7a`](https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit?id=07be4c4a3e7a0db148e44b16c5190e753d1c8569)
 `BPF_FUNC_csum_diff()` | 4.6 | | [`7d672345ed29`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=7d672345ed295b1356a5d9f7111da1d1d7d65867)
@@ -216,6 +217,7 @@ Helper | Kernel version | License | Commit |
 `BPF_FUNC_current_task_under_cgroup()` | 4.9 | | [`60d20f9195b2`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=60d20f9195b260bdf0ac10c275ae9f6016f9c069)
 `BPF_FUNC_d_path()` | 5.10 | | [`6e22ab9da793`](https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit?id=6e22ab9da79343532cd3cde39df25e5a5478c692)
 `BPF_FUNC_fib_lookup()` | 4.18 | GPL | [`87f5fc7e48dd`](https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/?id=87f5fc7e48dd3175b30dd03b41564e1a8e136323)
+`BPF_FUNC_for_each_map_elem()` | 5.13 | | [`69c087ba6225`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit?id=69c087ba6225b574afb6e505b72cb75242a3d844)
 `BPF_FUNC_get_current_ancestor_cgroup_id()` | 5.6 | | [`b4490c5c4e02`](https://github.com/torvalds/linux/commit/b4490c5c4e023f09b7d27c9a9d3e7ad7d09ea6bf)
 `BPF_FUNC_get_cgroup_classid()` | 4.3 | | [`8d20aabe1c76`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=8d20aabe1c76cccac544d9fcc3ad7823d9e98a2d)
 `BPF_FUNC_get_current_cgroup_id()` | 4.18 | | [`bf6fa2c893c5`](https://github.com/torvalds/linux/commit/bf6fa2c893c5237b48569a13fa3c673041430b6c)

diff --git a/src/cc/compat/linux/virtual_bpf.h b/src/cc/compat/linux/virtual_bpf.h
@@ -20,7 +20,8 @@ R"********(
 
 /* ld/ldx fields */
 #define BPF_DW 0x18 /* double word (64-bit) */
-#define BPF_XADD 0xc0 /* exclusive add */
+#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */
+#define BPF_XADD 0xc0 /* exclusive add - legacy name */
 
 /* alu/jmp fields */
 #define BPF_MOV 0xb0 /* mov reg to reg */
@@ -44,6 +45,11 @@ R"********(
 #define BPF_CALL 0x80 /* function call */
 #define BPF_EXIT 0x90 /* function return */
 
+/* atomic op type fields (stored in immediate) */
+#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */
+#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */
+#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */
+
 /* Register numbers */
 enum {
  BPF_REG_0 = 0,
@@ -388,6 +394,15 @@ enum bpf_link_type {
  * is struct/union.
  */
 #define BPF_PSEUDO_BTF_ID 3
+/* insn[0].src_reg: BPF_PSEUDO_FUNC
+ * insn[0].imm: insn offset to the func
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of the function
+ * verifier type: PTR_TO_FUNC.
+ */
+#define BPF_PSEUDO_FUNC 4
 
 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
  * offset to another bpf function
@@ -1651,22 +1666,30 @@ union bpf_attr {
  * networking traffic statistics as it provides a global socket
  * identifier that can be assumed unique.
  * Return
- * A 8-byte long non-decreasing number on success, or 0 if the
- * socket field is missing inside *skb*.
+ * A 8-byte long unique number on success, or 0 if the socket
+ * field is missing inside *skb*.
  *
  * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
  * Description
  * Equivalent to bpf_get_socket_cookie() helper that accepts
  * *skb*, but gets socket from **struct bpf_sock_addr** context.
  * Return
- * A 8-byte long non-decreasing number.
+ * A 8-byte long unique number.
  *
  * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
  * Description
  * 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.
+ * A 8-byte long unique number.
+ *
+ * u64 bpf_get_socket_cookie(struct sock *sk)
+ * Description
+ * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
+ * *sk*, but gets socket from a BTF **struct sock**. This helper
+ * also works for sleepable programs.
+ * Return
+ * A 8-byte long unique number or 0 if *sk* is NULL.
  *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
  * Return
@@ -2226,6 +2249,9 @@ union bpf_attr {
  * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  * packet is not forwarded or needs assist from full stack
  *
+ * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ * was exceeded and output params->mtu_result contains the MTU.
+ *
  * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  * Description
  * Add an entry to, or update a sockhash *map* referencing sockets.
@@ -2449,7 +2475,7 @@ union bpf_attr {
  * running simultaneously.
  *
  * A user should care about the synchronization by himself.
- * For example, by using the **BPF_STX_XADD** instruction to alter
+ * For example, by using the **BPF_ATOMIC** instructions to alter
  * the shared data.
  * Return
  * A pointer to the local storage area.
@@ -2994,10 +3020,10 @@ union bpf_attr {
  * string length is larger than *size*, just *size*-1 bytes are
  * copied and the last byte is set to NUL.
  *
- * On success, the length of the copied string is returned. This
- * makes this helper useful in tracing programs for reading
- * strings, and more importantly to get its length at runtime. See
- * the following snippet:
+ * On success, returns the number of bytes that were written,
+ * including the terminal NUL. This makes this helper useful in
+ * tracing programs for reading strings, and more importantly to
+ * get its length at runtime. See the following snippet:
  *
  * ::
  *
@@ -3025,7 +3051,7 @@ union bpf_attr {
  * **->mm->env_start**: using this helper and the return value,
  * one can quickly iterate at the right offset of the memory area.
  * Return
- * On success, the strictly positive length of the string,
+ * On success, the strictly positive length of the output string,
  * including the trailing NUL character. On error, a negative
  * value.
  *
@@ -3831,6 +3857,96 @@ union bpf_attr {
  * Return
  * A pointer to a struct socket on success or NULL if the file is
  * not a socket.
+ *
+ * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
+ * Description
+ * Check ctx packet size against exceeding MTU of net device (based
+ * on *ifindex*). This helper will likely be used in combination
+ * with helpers that adjust/change the packet size.
+ *
+ * The argument *len_diff* can be used for querying with a planned
+ * size change. This allows to check MTU prior to changing packet
+ * ctx. Providing an *len_diff* adjustment that is larger than the
+ * actual packet size (resulting in negative packet size) will in
+ * principle not exceed the MTU, why it is not considered a
+ * failure. Other BPF-helpers are needed for performing the
+ * planned size change, why the responsability for catch a negative
+ * packet size belong in those helpers.
+ *
+ * Specifying *ifindex* zero means the MTU check is performed
+ * against the current net device. This is practical if this isn't
+ * used prior to redirect.
+ *
+ * The Linux kernel route table can configure MTUs on a more
+ * specific per route level, which is not provided by this helper.
+ * For route level MTU checks use the **bpf_fib_lookup**\ ()
+ * helper.
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** for tc cls_act programs.
+ *
+ * The *flags* argument can be a combination of one or more of the
+ * following values:
+ *
+ * **BPF_MTU_CHK_SEGS**
+ * This flag will only works for *ctx* **struct sk_buff**.
+ * If packet context contains extra packet segment buffers
+ * (often knows as GSO skb), then MTU check is harder to
+ * check at this point, because in transmit path it is
+ * possible for the skb packet to get re-segmented
+ * (depending on net device features). This could still be
+ * a MTU violation, so this flag enables performing MTU
+ * check against segments, with a different violation
+ * return code to tell it apart. Check cannot use len_diff.
+ *
+ * On return *mtu_len* pointer contains the MTU value of the net
+ * device. Remember the net device configured MTU is the L3 size,
+ * which is returned here and XDP and TX length operate at L2.
+ * Helper take this into account for you, but remember when using
+ * MTU value in your BPF-code. On input *mtu_len* must be a valid
+ * pointer and be initialized (to zero), else verifier will reject
+ * BPF program.
+ *
+ * Return
+ * * 0 on success, and populate MTU value in *mtu_len* pointer.
+ *
+ * * < 0 if any input argument is invalid (*mtu_len* not updated)
+ *
+ * MTU violations return positive values, but also populate MTU
+ * value in *mtu_len* pointer, as this can be needed for
+ * implementing PMTU handing:
+ *
+ * * **BPF_MTU_CHK_RET_FRAG_NEEDED**
+ * * **BPF_MTU_CHK_RET_SEGS_TOOBIG**
+ *
+ * long bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * For each element in **map**, call **callback_fn** function with
+ * **map**, **callback_ctx** and other map-specific parameters.
+ * The **callback_fn** should be a static function and
+ * the **callback_ctx** should be a pointer to the stack.
+ * The **flags** is used to control certain aspects of the helper.
+ * Currently, the **flags** must be 0.
+ *
+ * The following are a list of supported map types and their
+ * respective expected callback signatures:
+ *
+ * BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_PERCPU_HASH,
+ * BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH,
+ * BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PERCPU_ARRAY
+ *
+ * long (\*callback_fn)(struct bpf_map \*map, const void \*key, void \*value, void \*ctx);
+ *
+ * For per_cpu maps, the map_value is the value on the cpu where the
+ * bpf_prog is running.
+ *
+ * If **callback_fn** return 0, the helper will continue to the next
+ * element. If return value is 1, the helper will skip the rest of
+ * elements and return. Other return values are not used now.
+ *
+ * Return
+ * The number of traversed map elements for success, **-EINVAL** for
+ * invalid **flags**.
  */
 #define __BPF_FUNC_MAPPER(FN) \
  FN(unspec), \
@@ -3996,6 +4112,8 @@ union bpf_attr {
  FN(ktime_get_coarse_ns), \
  FN(ima_inode_hash), \
  FN(sock_from_file), \
+ FN(check_mtu), \
+ FN(for_each_map_elem), \
  /* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4496,6 +4614,7 @@ struct bpf_prog_info {
  __aligned_u64 prog_tags;
  __u64 run_time_ns;
  __u64 run_cnt;
+ __u64 recursion_misses;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -4976,9 +5095,13 @@ struct bpf_fib_lookup {
  __be16 sport;
  __be16 dport;
 
- /* total length of packet from network header - used for MTU check */
- __u16 tot_len;
+ union { /* used for MTU check */
+ /* input to lookup */
+ __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */
 
+ /* output: MTU value */
+ __u16 mtu_result;
+ };
  /* input: L3 device index for lookup
  * output: device index from FIB lookup
  */
@@ -5024,6 +5147,17 @@ struct bpf_redir_neigh {
  };
 };
 
+/* bpf_check_mtu flags*/
+enum bpf_check_mtu_flags {
+ BPF_MTU_CHK_SEGS = (1U << 0),
+};
+
+enum bpf_check_mtu_ret {
+ BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */
+ BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+ BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */
+};
+
 enum bpf_task_fd_type {
  BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */
  BPF_FD_TYPE_TRACEPOINT, /* tp name */

diff --git a/src/cc/export/helpers.h b/src/cc/export/helpers.h
@@ -837,6 +837,12 @@ static long (*bpf_ima_inode_hash)(struct inode *inode, void *dst, __u32 size) =
 struct file;
 static struct socket *(*bpf_sock_from_file)(struct file *file) =
  (void *)BPF_FUNC_sock_from_file;
+static long (*bpf_check_mtu)(void *ctx, __u32 ifindex, __u32 *mtu_len,
+ __s32 len_diff, __u64 flags) =
+ (void *)BPF_FUNC_check_mtu;
+static long (*bpf_for_each_map_elem)(void *map, void *callback_fn,
+ void *callback_ctx, __u64 flags) =
+ (void *)BPF_FUNC_for_each_map_elem;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions

diff --git a/src/cc/libbpf b/src/cc/libbpf
diff --git a/src/cc/libbpf.c b/src/cc/libbpf.c
@@ -261,6 +261,8 @@ static struct bpf_helper helpers[] = {
  {"ktime_get_coarse_ns", "5.11"},
  {"ima_inode_hash", "5.11"},
  {"sock_from_file", "5.11"},
+ {"check_mtu", "5.12"},
+ {"for_each_map_elem", "5.13"},
 };
 
 static uint64_t ptr_to_u64(void *ptr)