Sync with latest libbpf repo

Sync up to the following commit: 8b0b41f812c2 Remove travis-ci symlink Some helpers sync'ed previously were marked as 5.20 since the official release number is not out then. Later on upstream didn't use 5.20 and instead used 6.0. So change those 5.20 version to 6.0 in this patch as well. Signed-off-by: Yonghong Song <[email protected]>
nanshuaibo · Oct 8, 2022 · 40306f1 · 40306f1
1 parent 8c6f846
commit 40306f1
Show file tree

Hide file tree

Showing 6 changed files with 166 additions and 33 deletions.
diff --git a/docs/kernel-versions.md b/docs/kernel-versions.md
@@ -269,6 +269,7 @@ Helper | Kernel version | License | Commit |
 `BPF_FUNC_ktime_get_boot_ns()` | 5.7 | GPL | [`71d19214776e`](https://kernel.googlesource.com/pub/scm/linux/kernel/git/bpf/bpf-next/+/71d19214776e61b33da48f7c1b46e522c7f78221)
 `BPF_FUNC_ktime_get_coarse_ns()` | 5.11 | GPL | [`d05512618056`](https://github.com/torvalds/linux/commit/d055126180564a57fe533728a4e93d0cb53d49b3)
 `BPF_FUNC_ktime_get_ns()` | 4.1 | GPL | [`d9847d310ab4`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=d9847d310ab4003725e6ed1822682e24bd406908)
+`BPF_FUNC_ktime_get_tai_ns()` | 6.1 | | [`c8996c98f703`](https://github.com/torvalds/linux/commit/c8996c98f703b09afe77a1d247dae691c9849dc1)
 `BPF_FUNC_l3_csum_replace()` | 4.1 | | [`91bc4822c3d6`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=91bc4822c3d61b9bb7ef66d3b77948a4f9177954)
 `BPF_FUNC_l4_csum_replace()` | 4.1 | | [`91bc4822c3d6`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=91bc4822c3d61b9bb7ef66d3b77948a4f9177954)
 `BPF_FUNC_load_hdr_opt()` | 5.10 | | [`0813a841566f`](https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit?id=0813a841566f0962a5551be7749b43c45f0022a0)
@@ -395,10 +396,10 @@ Helper | Kernel version | License | Commit |
 `BPF_FUNC_task_storage_get()` | 5.11 | | [`4cf1bc1f1045`](https://github.com/torvalds/linux/commit/4cf1bc1f10452065a29d576fc5693fc4fab5b919)
 `BPF_FUNC_tcp_check_syncookie()` | 5.2 | | [`399040847084`](https://kernel.googlesource.com/pub/scm/linux/kernel/git/davem/net-next/+/399040847084a69f345e0a52fd62f04654e0fce3)
 `BPF_FUNC_tcp_gen_syncookie()` | 5.3 | | [`70d66244317e`](https://github.com/torvalds/linux/commit/70d66244317e958092e9c971b08dd5b7fd29d9cb#diff-05da4bf36c7fbcd176254e1615d98b28)
-`BPF_FUNC_tcp_raw_check_syncookie_ipv4()` | 5.20 | | [`33bf9885040c`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit?id=33bf9885040c399cf6a95bd33216644126728e14)
-`BPF_FUNC_tcp_raw_check_syncookie_ipv6()` | 5.20 | | [`33bf9885040c`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit?id=33bf9885040c399cf6a95bd33216644126728e14)
-`BPF_FUNC_tcp_raw_gen_syncookie_ipv4()` | 5.20 | | [`33bf9885040c`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit?id=33bf9885040c399cf6a95bd33216644126728e14)
-`BPF_FUNC_tcp_raw_gen_syncookie_ipv6()` | 5.20 | | [`33bf9885040c`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit?id=33bf9885040c399cf6a95bd33216644126728e14)
+`BPF_FUNC_tcp_raw_check_syncookie_ipv4()` | 6.0 | | [`33bf9885040c`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit?id=33bf9885040c399cf6a95bd33216644126728e14)
+`BPF_FUNC_tcp_raw_check_syncookie_ipv6()` | 6.0 | | [`33bf9885040c`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit?id=33bf9885040c399cf6a95bd33216644126728e14)
+`BPF_FUNC_tcp_raw_gen_syncookie_ipv4()` | 6.0 | | [`33bf9885040c`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit?id=33bf9885040c399cf6a95bd33216644126728e14)
+`BPF_FUNC_tcp_raw_gen_syncookie_ipv6()` | 6.0 | | [`33bf9885040c`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit?id=33bf9885040c399cf6a95bd33216644126728e14)
 `BPF_FUNC_tcp_send_ack()` | 5.5 | | [`206057fe020a`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit/?id=206057fe020ac5c037d5e2dd6562a9bd216ec765)
 `BPF_FUNC_tcp_sock()` | 5.1 | | [`655a51e536c0`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit/?id=655a51e536c09d15ffa3603b1b6fce2b45b85a1f)
 `BPF_FUNC_this_cpu_ptr()` | 5.10 | | [`63d9b80dcf2c`](https://github.com/torvalds/linux/commit/63d9b80dcf2c67bc5ade61cbbaa09d7af21f43f1) |
@@ -408,6 +409,7 @@ Helper | Kernel version | License | Commit |
 `BPF_FUNC_timer_cancel()` | 5.15 | | [`b00628b1c7d5`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/commit/?id=b00628b1c7d595ae5b544e059c27b1f5828314b4)
 `BPF_FUNC_trace_printk()` | 4.1 | GPL | [`9c959c863f82`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=9c959c863f8217a2ff3d7c296e8223654d240569)
 `BPF_FUNC_trace_vprintk()` | 5.16 | GPL | [`10aceb629e19`](https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git?id=10aceb629e198429c849d5e995c3bb1ba7a9aaa3)
+`BPF_FUNC_user_ringbuf_drain()` | 6.1 | | [`205715673844`](https://github.com/torvalds/linux/commit/20571567384428dfc9fe5cf9f2e942e1df13c2dd)
 `BPF_FUNC_xdp_adjust_head()` | 4.10 | | [`17bedab27231`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=17bedab2723145d17b14084430743549e6943d03)
 `BPF_FUNC_xdp_adjust_meta()` | 4.15 | | [`de8f3a83b0a0`](https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=de8f3a83b0a0fddb2cf56e7a718127e9619ea3da)
 `BPF_FUNC_xdp_adjust_tail()` | 4.18 | | [`b32cc5b9a346`](https://git.kernel.org/cgit/linux/kernel/git/davem/net-next.git/commit/?id=b32cc5b9a346319c171e3ad905e0cddda032b5eb)

diff --git a/introspection/bps.c b/introspection/bps.c
@@ -81,6 +81,7 @@ static const char * const map_type_strings[] = {
  [BPF_MAP_TYPE_INODE_STORAGE] = "inode_storage",
  [BPF_MAP_TYPE_TASK_STORAGE] = "task_storage",
  [BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter",
+ [BPF_MAP_TYPE_USER_RINGBUF] = "user_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
@@ -88,10 +88,29 @@ struct bpf_cgroup_storage_key {
  __u32 attach_type; /* program attach type (enum bpf_attach_type) */
 };
 
+enum bpf_cgroup_iter_order {
+ BPF_CGROUP_ITER_ORDER_UNSPEC = 0,
+ BPF_CGROUP_ITER_SELF_ONLY, /* process only a single object. */
+ BPF_CGROUP_ITER_DESCENDANTS_PRE, /* walk descendants in pre-order. */
+ BPF_CGROUP_ITER_DESCENDANTS_POST, /* walk descendants in post-order. */
+ BPF_CGROUP_ITER_ANCESTORS_UP, /* walk ancestors upward. */
+};
+
 union bpf_iter_link_info {
  struct {
  __u32 map_fd;
  } map;
+ struct {
+ enum bpf_cgroup_iter_order order;
+
+ /* At most one of cgroup_fd and cgroup_id can be non-zero. If
+ * both are zero, the walk starts from the default cgroup v2
+ * root. For walking v1 hierarchy, one should always explicitly
+ * specify cgroup_fd.
+ */
+ __u32 cgroup_fd;
+ __u64 cgroup_id;
+ } cgroup;
 };
 
 /* BPF syscall commands, see bpf(2) man-page for more details. */
@@ -910,6 +929,7 @@ enum bpf_map_type {
  BPF_MAP_TYPE_INODE_STORAGE,
  BPF_MAP_TYPE_TASK_STORAGE,
  BPF_MAP_TYPE_BLOOM_FILTER,
+ BPF_MAP_TYPE_USER_RINGBUF,
 };
 
 /* Note that tracing related programs such as
@@ -1234,7 +1254,7 @@ enum {
 
 /* Query effective (directly attached + inherited from ancestor cgroups)
  * programs that will be executed for events within a cgroup.
- * attach_flags with this flag are returned only for directly attached programs.
+ * attach_flags with this flag are always returned 0.
  */
 #define BPF_F_QUERY_EFFECTIVE (1U << 0)
 
@@ -1433,7 +1453,10 @@ union bpf_attr {
  __u32 attach_flags;
  __aligned_u64 prog_ids;
  __u32 prog_cnt;
- __aligned_u64 prog_attach_flags; /* output: per-program attach_flags */
+ /* output: per-program attach_flags.
+ * not allowed to be set during effective query.
+ */
+ __aligned_u64 prog_attach_flags;
  } query;
 
  struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
@@ -2574,10 +2597,12 @@ union bpf_attr {
  * 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).
+ * (room space is added or removed between the layer 2 and
+ * layer 3 headers).
  *
  * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
- * (room space is added or removed below the layer 3 header).
+ * (room space is added or removed between the layer 3 and
+ * layer 4 headers).
  *
  * The following flags are supported at this time:
  *
@@ -3009,8 +3034,18 @@ union bpf_attr {
  * **BPF_F_USER_STACK**
  * Collect a user space stack instead of a kernel stack.
  * **BPF_F_USER_BUILD_ID**
- * Collect buildid+offset instead of ips for user stack,
- * only valid if **BPF_F_USER_STACK** is also specified.
+ * Collect (build_id, file_offset) instead of ips for user
+ * stack, only valid if **BPF_F_USER_STACK** is also
+ * specified.
+ *
+ * *file_offset* is an offset relative to the beginning
+ * of the executable or shared object file backing the vma
+ * which the *ip* falls in. It is *not* an offset relative
+ * to that object's base address. Accordingly, it must be
+ * adjusted by adding (sh_addr - sh_offset), where
+ * sh_{addr,offset} correspond to the executable section
+ * containing *file_offset* in the object, for comparisons
+ * to symbols' st_value to be valid.
  *
  * **bpf_get_stack**\ () can collect up to
  * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
@@ -4426,7 +4461,7 @@ union bpf_attr {
  *
  * **-EEXIST** if the option already exists.
  *
- * **-EFAULT** on failrue to parse the existing header options.
+ * **-EFAULT** on failure to parse the existing header options.
  *
  * **-EPERM** if the helper cannot be used under the current
  * *skops*\ **->op**.
@@ -4635,7 +4670,7 @@ union bpf_attr {
  * a *map* with *task* as the **key**. From this
  * perspective, the usage is not much different from
  * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
- * helper enforces the key must be an task_struct and the map must also
+ * helper enforces the key must be a task_struct and the map must also
  * be a **BPF_MAP_TYPE_TASK_STORAGE**.
  *
  * Underneath, the value is stored locally at *task* instead of
@@ -4693,7 +4728,7 @@ union bpf_attr {
  *
  * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size)
  * Description
- * Returns the stored IMA hash of the *inode* (if it's avaialable).
+ * Returns the stored IMA hash of the *inode* (if it's available).
  * If the hash is larger than *size*, then only *size*
  * bytes will be copied to *dst*
  * Return
@@ -4717,12 +4752,12 @@ union bpf_attr {
  *
  * 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
+ * ctx. Providing a *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.
+ * principle not exceed the MTU, which is why it is not considered
+ * a failure. Other BPF helpers are needed for performing the
+ * planned size change; therefore the responsibility for catching
+ * a negative packet size belongs in those helpers.
  *
  * Specifying *ifindex* zero means the MTU check is performed
  * against the current net device. This is practical if this isn't
@@ -4920,6 +4955,7 @@ union bpf_attr {
  * Get address of the traced function (for tracing and kprobe programs).
  * Return
  * Address of the traced function.
+ * 0 for kprobes placed within the function (not at the entry).
  *
  * u64 bpf_get_attach_cookie(void *ctx)
  * Description
@@ -5049,12 +5085,12 @@ union bpf_attr {
  *
  * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
  * Description
- * Get **n**-th argument (zero based) of the traced function (for tracing programs)
+ * Get **n**-th argument register (zero based) of the traced function (for tracing programs)
  * returned in **value**.
  *
  * Return
  * 0 on success.
- * **-EINVAL** if n >= arguments count of traced function.
+ * **-EINVAL** if n >= argument register count of traced function.
  *
  * long bpf_get_func_ret(void *ctx, u64 *value)
  * Description
@@ -5067,24 +5103,37 @@ union bpf_attr {
  *
  * long bpf_get_func_arg_cnt(void *ctx)
  * Description
- * Get number of arguments of the traced function (for tracing programs).
+ * Get number of registers of the traced function (for tracing programs) where
+ * function arguments are stored in these registers.
  *
  * Return
- * The number of arguments of the traced function.
+ * The number of argument registers of the traced function.
  *
  * int bpf_get_retval(void)
  * Description
- * Get the syscall's return value that will be returned to userspace.
+ * Get the BPF program's return value that will be returned to the upper layers.
  *
- * This helper is currently supported by cgroup programs only.
+ * This helper is currently supported by cgroup programs and only by the hooks
+ * where BPF program's return value is returned to the userspace via errno.
  * Return
- * The syscall's return value.
+ * The BPF program's return value.
  *
  * int bpf_set_retval(int retval)
  * Description
- * Set the syscall's return value that will be returned to userspace.
+ * Set the BPF program's return value that will be returned to the upper layers.
+ *
+ * This helper is currently supported by cgroup programs and only by the hooks
+ * where BPF program's return value is returned to the userspace via errno.
+ *
+ * Note that there is the following corner case where the program exports an error
+ * via bpf_set_retval but signals success via 'return 1':
+ *
+ * bpf_set_retval(-EPERM);
+ * return 1;
+ *
+ * In this case, the BPF program's return value will use helper's -EPERM. This
+ * still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case.
  *
- * This helper is currently supported by cgroup programs only.
  * Return
  * 0 on success, or a negative error in case of failure.
  *
@@ -5332,6 +5381,55 @@ union bpf_attr {
  * **-EACCES** if the SYN cookie is not valid.
  *
  * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * u64 bpf_ktime_get_tai_ns(void)
+ * Description
+ * A nonsettable system-wide clock derived from wall-clock time but
+ * ignoring leap seconds. This clock does not experience
+ * discontinuities and backwards jumps caused by NTP inserting leap
+ * seconds as CLOCK_REALTIME does.
+ *
+ * See: **clock_gettime**\ (**CLOCK_TAI**)
+ * Return
+ * Current *ktime*.
+ *
+ * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags)
+ * Description
+ * Drain samples from the specified user ring buffer, and invoke
+ * the provided callback for each such sample:
+ *
+ * long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx);
+ *
+ * If **callback_fn** returns 0, the helper will continue to try
+ * and drain the next sample, up to a maximum of
+ * BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ * the helper will skip the rest of the samples and return. Other
+ * return values are not used now, and will be rejected by the
+ * verifier.
+ * Return
+ * The number of drained samples if no error was encountered while
+ * draining samples, or 0 if no samples were present in the ring
+ * buffer. If a user-space producer was epoll-waiting on this map,
+ * and at least one sample was drained, they will receive an event
+ * notification notifying them of available space in the ring
+ * buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ * function, no wakeup notification will be sent. If the
+ * BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ * be sent even if no sample was drained.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EBUSY** if the ring buffer is contended, and another calling
+ * context was concurrently draining the ring buffer.
+ *
+ * **-EINVAL** if user-space is not properly tracking the ring
+ * buffer due to the producer position not being aligned to 8
+ * bytes, a sample not being aligned to 8 bytes, or the producer
+ * position not matching the advertised length of a sample.
+ *
+ * **-E2BIG** if user-space has tried to publish a sample which is
+ * larger than the size of the ring buffer, or which cannot fit
+ * within a struct bpf_dynptr.
  */
 #define __BPF_FUNC_MAPPER(FN) \
  FN(unspec), \
@@ -5542,6 +5640,8 @@ union bpf_attr {
  FN(tcp_raw_gen_syncookie_ipv6), \
  FN(tcp_raw_check_syncookie_ipv4), \
  FN(tcp_raw_check_syncookie_ipv6), \
+ FN(ktime_get_tai_ns), \
+ FN(user_ringbuf_drain), \
  /* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5604,6 +5704,11 @@ enum {
  BPF_F_SEQ_NUMBER = (1ULL << 3),
 };
 
+/* BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+ BPF_F_TUNINFO_FLAGS = (1ULL << 4),
+};
+
 /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
  * BPF_FUNC_perf_event_read_value flags.
  */
@@ -5793,7 +5898,10 @@ struct bpf_tunnel_key {
  };
  __u8 tunnel_tos;
  __u8 tunnel_ttl;
- __u16 tunnel_ext; /* Padding, future use. */
+ union {
+ __u16 tunnel_ext; /* compat */
+ __be16 tunnel_flags;
+ };
  __u32 tunnel_label;
  union {
  __u32 local_ipv4;
@@ -5837,6 +5945,11 @@ enum bpf_ret_code {
  * represented by BPF_REDIRECT above).
  */
  BPF_LWT_REROUTE = 128,
+ /* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+ * to indicate that no custom dissection was performed, and
+ * fallback to standard dissector is requested.
+ */
+ BPF_FLOW_DISSECTOR_CONTINUE = 129,
 };
 
 struct bpf_sock {
@@ -6135,11 +6248,22 @@ struct bpf_link_info {
  struct {
  __aligned_u64 target_name; /* in/out: target_name buffer ptr */
  __u32 target_name_len; /* in/out: target_name buffer len */
+
+ /* If the iter specific field is 32 bits, it can be put
+ * in the first or second union. Otherwise it should be
+ * put in the second union.
+ */
  union {
  struct {
  __u32 map_id;
  } map;
  };
+ union {
+ struct {
+ __u64 cgroup_id;
+ __u32 order;
+ } cgroup;
+ };
  } iter;
  struct {
  __u32 netns_ino;

diff --git a/src/cc/export/helpers.h b/src/cc/export/helpers.h
@@ -1025,6 +1025,10 @@ static long (*bpf_tcp_raw_check_syncookie_ipv4)(struct iphdr *iph, struct tcphdr
 static long (*bpf_tcp_raw_check_syncookie_ipv6)(struct ipv6hdr *iph, struct tcphdr *th) =
  (void *)BPF_FUNC_tcp_raw_check_syncookie_ipv6;
 
+static __u64 (*bpf_ktime_get_tai_ns)(void) = (void *)BPF_FUNC_ktime_get_tai_ns;
+static long (*bpf_user_ringbuf_drain)(void *map, void *callback_fn, void *ctx, __u64 flags) =
+ (void *)BPF_FUNC_user_ringbuf_drain;
+
 /* 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