sync with latest libbpf repo

sync with latest libbpf repo, added newer ringbuf_* helper functions and new csum_level() helper. Signed-off-by: Yonghong Song <[email protected]>
heatseekr · Jun 16, 2020 · 99fa312 · 99fa312
1 parent 2c93955
commit 99fa312
Show file tree

Hide file tree

Showing 6 changed files with 184 additions and 2 deletions.
diff --git a/docs/kernel-versions.md b/docs/kernel-versions.md
@@ -162,6 +162,7 @@ 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_clone_redirect()` | 4.2 | | [`3896d655f4d4`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=3896d655f4d491c67d669a15f275a39f713410f8)
 `BPF_FUNC_csum_diff()` | 4.6 | | [`7d672345ed29`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=7d672345ed295b1356a5d9f7111da1d1d7d65867)
+`BPF_FUNC_csum_level()` | 5.7 | | [`7cdec54f9713`](https://github.com/torvalds/linux/commit/7cdec54f9713256bb170873a1fc5c75c9127c9d2)
 `BPF_FUNC_csum_update()` | 4.9 | | [`36bbef52c7eb`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=36bbef52c7eb646ed6247055a2acd3851e317857)
 `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_fib_lookup()` | 4.18 | GPL | [`87f5fc7e48dd`](https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/?id=87f5fc7e48dd3175b30dd03b41564e1a8e136323)
@@ -225,6 +226,11 @@ Helper | Kernel version | License | Commit |
 `BPF_FUNC_read_branch_records()` | 5.6 | GPL | [`fff7b64355ea`](https://github.com/torvalds/linux/commit/fff7b64355eac6e29b50229ad1512315bc04b44e)
 `BPF_FUNC_redirect()` | 4.4 | | [`27b29f63058d`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=27b29f63058d26c6c1742f1993338280d5a41dc6)
 `BPF_FUNC_redirect_map()` | 4.14 | | [`97f91a7cf04f`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=97f91a7cf04ff605845c20948b8a80e54cbd3376)
+`BPF_FUNC_ringbuf_discard()` | 5.7 | | [`457f44363a88`](https://github.com/torvalds/linux/commit/457f44363a8894135c85b7a9afd2bd8196db24ab)
+`BPF_FUNC_ringbuf_output()` | 5.7 | | [`457f44363a88`](https://github.com/torvalds/linux/commit/457f44363a8894135c85b7a9afd2bd8196db24ab)
+`BPF_FUNC_ringbuf_query()` | 5.7 | | [`457f44363a88`](https://github.com/torvalds/linux/commit/457f44363a8894135c85b7a9afd2bd8196db24ab)
+`BPF_FUNC_ringbuf_reserve()` | 5.7 | | [`457f44363a88`](https://github.com/torvalds/linux/commit/457f44363a8894135c85b7a9afd2bd8196db24ab)
+`BPF_FUNC_ringbuf_submit()` | 5.7 | | [`457f44363a88`](https://github.com/torvalds/linux/commit/457f44363a8894135c85b7a9afd2bd8196db24ab)
 `BPF_FUNC_send_signal()` | 5.3 | | [`8b401f9ed244`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit/?id=8b401f9ed2441ad9e219953927a842d24ed051fc)
 `BPF_FUNC_send_signal_thread()` | 5.5 | | [`8482941f0906`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit/?id=8482941f09067da42f9c3362e15bfb3f3c19d610)
 `BPF_FUNC_seq_printf()` | 5.7 | GPL | [`492e639f0c22`](https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next/+/492e639f0c222784e2e0f121966375f641c61b15)

diff --git a/introspection/bps.c b/introspection/bps.c
@@ -75,6 +75,7 @@ static const char * const map_type_strings[] = {
  [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage",
  [BPF_MAP_TYPE_DEVMAP_HASH] = "devmap_hash",
  [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops",
+ [BPF_MAP_TYPE_RINGBUF] = "ringbuf",
 };
 
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))

diff --git a/src/cc/compat/linux/virtual_bpf.h b/src/cc/compat/linux/virtual_bpf.h
@@ -148,6 +148,7 @@ 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
@@ -225,6 +226,7 @@ enum bpf_attach_type {
  BPF_CGROUP_INET6_GETPEERNAME,
  BPF_CGROUP_INET4_GETSOCKNAME,
  BPF_CGROUP_INET6_GETSOCKNAME,
+ BPF_XDP_DEVMAP,
  __MAX_BPF_ATTACH_TYPE
 };
 
@@ -236,6 +238,7 @@ enum bpf_link_type {
  BPF_LINK_TYPE_TRACING = 2,
  BPF_LINK_TYPE_CGROUP = 3,
  BPF_LINK_TYPE_ITER = 4,
+ BPF_LINK_TYPE_NETNS = 5,
 
  MAX_BPF_LINK_TYPE,
 };
@@ -1633,6 +1636,13 @@ 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
@@ -3158,6 +3168,91 @@ union bpf_attr {
  * **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), \
@@ -3289,7 +3384,13 @@ union bpf_attr {
  FN(seq_printf), \
  FN(seq_write), \
  FN(sk_cgroup_id), \
- FN(sk_ancestor_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
@@ -3366,13 +3467,22 @@ 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),
  BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 = (1ULL << 1),
  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 {
@@ -3399,6 +3509,29 @@ 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,
@@ -3531,6 +3664,7 @@ struct bpf_sock {
  __u32 dst_ip4;
  __u32 dst_ip6[4];
  __u32 state;
+ __s32 rx_queue_mapping;
 };
 
 struct bpf_tcp_sock {
@@ -3624,6 +3758,21 @@ 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 */
+};
+
+/* DEVMAP map-value layout
+ *
+ * The struct data-layout of map-value is a configuration interface.
+ * New members can only be added to the end of this structure.
+ */
+struct bpf_devmap_val {
+ __u32 ifindex; /* device index */
+ union {
+ int fd; /* prog fd on map write */
+ __u32 id; /* prog id on map read */
+ } bpf_prog;
 };
 
 enum sk_action {
@@ -3646,6 +3795,8 @@ 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 {
@@ -3752,6 +3903,10 @@ struct bpf_link_info {
  __u64 cgroup_id;
  __u32 attach_type;
  } cgroup;
+ struct {
+ __u32 netns_ino;
+ __u32 attach_type;
+ } netns;
  };
 } __attribute__((aligned(8)));
 

diff --git a/src/cc/export/helpers.h b/src/cc/export/helpers.h
@@ -655,6 +655,20 @@ static __u64 (*bpf_sk_cgroup_id)(struct bpf_sock *sk) = (void *)BPF_FUNC_sk_cgro
 static __u64 (*bpf_sk_ancestor_cgroup_id)(struct bpf_sock *sk, int ancestor_level) =
  (void *)BPF_FUNC_sk_ancestor_cgroup_id;
 
+static int (*bpf_ringbuf_output)(void *ringbuf, void *data, __u64 size, __u64 flags) =
+ (void *)BPF_FUNC_ringbuf_output;
+static void *(*bpf_ringbuf_reserve)(void *ringbuf, __u64 size, __u64 flags) =
+ (void *)BPF_FUNC_ringbuf_reserve;
+static void (*bpf_ringbuf_submit)(void *data, __u64 flags) =
+ (void *)BPF_FUNC_ringbuf_submit;
+static void (*bpf_ringbuf_discard)(void *data, __u64 flags) =
+ (void *)BPF_FUNC_ringbuf_discard;
+static __u64 (*bpf_ringbuf_query)(void *ringbuf, __u64 flags) =
+ (void *)BPF_FUNC_ringbuf_query;
+
+static int (*bpf_csum_level)(struct __sk_buff *skb, __u64 level) =
+ (void *)BPF_FUNC_csum_level;
+
 /* 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
@@ -226,6 +226,12 @@ static struct bpf_helper helpers[] = {
  {"seq_write", "5.7"},
  {"sk_cgroup_id", "5.7"},
  {"sk_ancestor_cgroup_id", "5.7"},
+ {"ringbuf_output", "5.7"},
+ {"ringbuf_reserve", "5.7"},
+ {"ringbuf_submit", "5.7"},
+ {"ringbuf_discard", "5.7"},
+ {"ringbuf_query", "5.7"},
+ {"csum_level", "5.7"},
 };
 
 static uint64_t ptr_to_u64(void *ptr)