Add fallback to an old attaching method

Syncing latest libbpf commits from kernel repository.
Baseline bpf-next commit:   69119673bd50b176ded34032fadd41530fb5af21
Checkpoint bpf-next commit: 4e15507fea70c0c312d79610efa46b6853ccf8e0
Baseline bpf commit:        6903cdae9f9f08d61e49c16cbef11c293e33a615
Checkpoint bpf commit:      4e15507fea70c0c312d79610efa46b6853ccf8e0

Andrii Nakryiko (1):
  libbpf: Forward-declare bpf_stats_type for systems with outdated UAPI
    headers

 src/bpf.h | 2 ++
 1 file changed, 2 insertions(+)

--
2.24.1

.travis.yml

@@ -35,72 +35,71 @@ stages:
 
 jobs:
     include:
-        - stage: Build
+        - stage: Build & Test
           name: Debian Build
           language: bash
           install:        $CI_ROOT/managers/debian.sh SETUP
-          script:         $CI_ROOT/managers/debian.sh RUN || travis_terminate
+          script:         $CI_ROOT/managers/debian.sh RUN || travis_terminate 1
           after_script:   $CI_ROOT/managers/debian.sh CLEANUP
 
         - name: Debian Build (ASan+UBSan)
           language: bash
           install:        $CI_ROOT/managers/debian.sh SETUP
-          script:         $CI_ROOT/managers/debian.sh RUN_ASAN || travis_terminate
+          script:         $CI_ROOT/managers/debian.sh RUN_ASAN || travis_terminate 1
           after_script:   $CI_ROOT/managers/debian.sh CLEANUP
 
         - name: Debian Build (clang)
           language: bash
           install:        $CI_ROOT/managers/debian.sh SETUP
-          script:         $CI_ROOT/managers/debian.sh RUN_CLANG || travis_terminate
+          script:         $CI_ROOT/managers/debian.sh RUN_CLANG || travis_terminate 1
           after_script:   $CI_ROOT/managers/debian.sh CLEANUP
 
         - name: Debian Build (clang ASan+UBSan)
           language: bash
           install:        $CI_ROOT/managers/debian.sh SETUP
-          script:         $CI_ROOT/managers/debian.sh RUN_CLANG_ASAN || travis_terminate
+          script:         $CI_ROOT/managers/debian.sh RUN_CLANG_ASAN || travis_terminate 1
           after_script:   $CI_ROOT/managers/debian.sh CLEANUP
 
         - name: Debian Build (gcc-8)
           language: bash
           install:        $CI_ROOT/managers/debian.sh SETUP
-          script:         $CI_ROOT/managers/debian.sh RUN_GCC8 || travis_terminate
+          script:         $CI_ROOT/managers/debian.sh RUN_GCC8 || travis_terminate 1
           after_script:   $CI_ROOT/managers/debian.sh CLEANUP
 
         - name: Debian Build (gcc-8 ASan+UBSan)
           language: bash
           install:        $CI_ROOT/managers/debian.sh SETUP
-          script:         $CI_ROOT/managers/debian.sh RUN_GCC8_ASAN || travis_terminate
+          script:         $CI_ROOT/managers/debian.sh RUN_GCC8_ASAN || travis_terminate 1
           after_script:   $CI_ROOT/managers/debian.sh CLEANUP
 
         - name: Ubuntu Bionic Build
           language: bash
-          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate 1
 
         - name: Ubuntu Bionic Build (arm)
           arch: arm64
           language: bash
-          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate 1
 
         - name: Ubuntu Bionic Build (s390x)
           arch: s390x
           language: bash
-          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate 1
 
         - name: Ubuntu Bionic Build (ppc64le)
           arch: ppc64le
           language: bash
-          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate 1
 
-        - stage: Build & Test
-          name: Kernel 5.5.0 + selftests
+        - name: Kernel 5.5.0 + selftests
           language: bash
           env: KERNEL=5.5.0
-          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate 1
 
         - name: Kernel LATEST + selftests
           language: bash
           env: KERNEL=LATEST
-          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate 1
 
         - stage: Coverity
           language: bash
@@ -121,4 +120,4 @@ jobs:
               - sudo apt-get -y build-dep libelf-dev
               - sudo apt-get install -y libelf-dev pkg-config
           script:
-              - scripts/coverity.sh || travis_terminate
+              - scripts/coverity.sh || travis_terminate 1

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-edadedf1c5b4e4404192a0a4c3c0c05e3b7672ab
+4e15507fea70c0c312d79610efa46b6853ccf8e0

CHECKPOINT-COMMIT

@@ -1 +1 @@
-2fcd80144b93ff90836a44f2054b4d82133d3a85
+69119673bd50b176ded34032fadd41530fb5af21

README.md

@@ -52,11 +52,12 @@ $ PKG_CONFIG_PATH=/build/root/lib64/pkgconfig DESTDIR=/build/root make install
 ```
 
 Distributions
-=====
+=============
 
 Distributions packaging libbpf from this mirror:
   - [Fedora](https://src.fedoraproject.org/rpms/libbpf)
   - [Gentoo](https://packages.gentoo.org/packages/dev-libs/libbpf)
+  - [Debian](https://packages.debian.org/sid/libbpf-dev)
 
 Benefits of packaging from the mirror over packaging from kernel sources:
   - Consistent versioning across distributions.
@@ -73,8 +74,54 @@ Package dependencies of libbpf, package names may vary across distros:
   - zlib
   - libelf
 
+BPF CO-RE (Compile Once – Run Everywhere)
+=========================================
+
+Libbpf supports building BPF CO-RE-enabled applications, which, in contrast to
+[BCC](https://github.com/iovisor/bcc/), do not require Clang/LLVM runtime
+being deployed to target servers and doesn't rely on kernel-devel headers
+being available.
+
+It does rely on kernel to be built with [BTF type
+information](https://www.kernel.org/doc/html/latest/bpf/btf.html), though.
+Some major Linux distributions come with kernel BTF already built in:
+  - Fedora 31+
+  - RHEL 8.2+
+  - OpenSUSE Tumbleweed (in the next release, as of 2020-06-04)
+  - Arch Linux (from kernel 5.7.1.arch1-1)
+
+If your kernel doesn't come with BTF built-in, you'll need to build custom
+kernel. You'll need:
+  - `pahole` 1.16+ tool (part of `dwarves` package), which performs DWARF to
+    BTF conversion;
+  - kernel built with `CONFIG_DEBUG_INFO_BTF=y` option;
+  - you can check if your kernel has BTF built-in by looking for
+    `/sys/kernel/btf/vmlinux` file:
+  
+```shell
+$ ls -la /sys/kernel/btf/vmlinux
+-r--r--r--. 1 root root 3541561 Jun  2 18:16 /sys/kernel/btf/vmlinux
+```
+  
+To develop and build BPF programs, you'll need Clang/LLVM 10+. The following
+distributions have Clang/LLVM 10+ packaged by default:
+  - Fedora 32+
+  - Ubuntu 20.04+
+  - Arch Linux
+
+Otherwise, please make sure to update it on your system.
+
+The following resources are useful to understand what BPF CO-RE is and how to
+use it:
+- [BPF Portability and CO-RE](https://facebookmicrosites.github.io/bpf/blog/2020/02/19/bpf-portability-and-co-re.html)
+- [HOWTO: BCC to libbpf conversion](https://facebookmicrosites.github.io/bpf/blog/2020/02/20/bcc-to-libbpf-howto-guide.html)
+- [libbpf-tools in BCC repo](https://github.com/iovisor/bcc/tree/master/libbpf-tools)
+  contain lots of real-world tools converted from BCC to BPF CO-RE. Consider
+  converting some more to both contribute to the BPF community and gain some
+  more experience with it.
+
 License
-=====
+=======
 
 This work is dual-licensed under BSD 2-clause license and GNU LGPL v2.1 license.
 You can choose between one of them if you use this work.

include/uapi/linux/bpf.h

@@ -73,7 +73,7 @@ struct bpf_insn {
 /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
 struct bpf_lpm_trie_key {
 	__u32	prefixlen;	/* up to 32 for AF_INET, 128 for AF_INET6 */
-	__u8	data[];	/* Arbitrary size */
+	__u8	data[0];	/* Arbitrary size */
 };
 
 struct bpf_cgroup_storage_key {
@@ -113,6 +113,10 @@ enum bpf_cmd {
 	BPF_MAP_DELETE_BATCH,
 	BPF_LINK_CREATE,
 	BPF_LINK_UPDATE,
+	BPF_LINK_GET_FD_BY_ID,
+	BPF_LINK_GET_NEXT_ID,
+	BPF_ENABLE_STATS,
+	BPF_ITER_CREATE,
 };
 
 enum bpf_map_type {
@@ -143,6 +147,7 @@ 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
@@ -215,11 +220,28 @@ enum bpf_attach_type {
 	BPF_TRACE_FEXIT,
 	BPF_MODIFY_RETURN,
 	BPF_LSM_MAC,
+	BPF_TRACE_ITER,
+	BPF_CGROUP_INET4_GETPEERNAME,
+	BPF_CGROUP_INET6_GETPEERNAME,
+	BPF_CGROUP_INET4_GETSOCKNAME,
+	BPF_CGROUP_INET6_GETSOCKNAME,
+	BPF_XDP_DEVMAP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+enum bpf_link_type {
+	BPF_LINK_TYPE_UNSPEC = 0,
+	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
+	BPF_LINK_TYPE_TRACING = 2,
+	BPF_LINK_TYPE_CGROUP = 3,
+	BPF_LINK_TYPE_ITER = 4,
+	BPF_LINK_TYPE_NETNS = 5,
+
+	MAX_BPF_LINK_TYPE,
+};
+
 /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
  *
  * NONE(default): No further bpf programs allowed in the subtree.
@@ -379,6 +401,12 @@ enum {
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
+/* type for BPF_ENABLE_STATS */
+enum bpf_stats_type {
+	/* enabled run_time_ns and run_cnt */
+	BPF_STATS_RUN_TIME = 0,
+};
+
 enum bpf_stack_build_id_status {
 	/* user space need an empty entry to identify end of a trace */
 	BPF_STACK_BUILD_ID_EMPTY = 0,
@@ -523,6 +551,7 @@ union bpf_attr {
 			__u32		prog_id;
 			__u32		map_id;
 			__u32		btf_id;
+			__u32		link_id;
 		};
 		__u32		next_id;
 		__u32		open_flags;
@@ -589,6 +618,15 @@ union bpf_attr {
 		__u32		old_prog_fd;
 	} link_update;
 
+	struct { /* struct used by BPF_ENABLE_STATS command */
+		__u32		type;
+	} enable_stats;
+
+	struct { /* struct used by BPF_ITER_CREATE command */
+		__u32		link_fd;
+		__u32		flags;
+	} iter_create;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
@@ -644,14 +682,16 @@ union bpf_attr {
  * 		For tracing programs, safely attempt to read *size* bytes from
  * 		kernel space address *unsafe_ptr* and store the data in *dst*.
  *
- * 		Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
- * 		instead.
+ * 		Generally, use **bpf_probe_read_user**\ () or
+ * 		**bpf_probe_read_kernel**\ () instead.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
  * u64 bpf_ktime_get_ns(void)
  * 	Description
  * 		Return the time elapsed since system boot, in nanoseconds.
+ * 		Does not include time the system was suspended.
+ * 		See: **clock_gettime**\ (**CLOCK_MONOTONIC**)
  * 	Return
  * 		Current *ktime*.
  *
@@ -1510,11 +1550,11 @@ union bpf_attr {
  * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
  * 	Description
  * 		Copy a NUL terminated string from an unsafe kernel address
- * 		*unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for
+ * 		*unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for
  * 		more details.
  *
- * 		Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str()
- * 		instead.
+ * 		Generally, use **bpf_probe_read_user_str**\ () or
+ * 		**bpf_probe_read_kernel_str**\ () instead.
  * 	Return
  * 		On success, the strictly positive length of the string,
  * 		including the trailing NUL character. On error, a negative
@@ -1542,7 +1582,7 @@ union bpf_attr {
  *
  * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
  * 	Description
- * 		Equivalent to bpf_get_socket_cookie() helper that accepts
+ * 		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.
@@ -1562,7 +1602,7 @@ union bpf_attr {
  * 	Return
  * 		0
  *
- * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
+ * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
  * 	Description
  * 		Emulate a call to **setsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1570,6 +1610,12 @@ union bpf_attr {
  * 		must be specified, see **setsockopt(2)** for more information.
  * 		The option value of length *optlen* is pointed by *optval*.
  *
+ * 		*bpf_socket* should be one of the following:
+ *
+ * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *
  * 		This helper actually implements a subset of **setsockopt()**.
  * 		It supports the following *level*\ s:
  *
@@ -1589,6 +1635,13 @@ 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
@@ -1634,15 +1687,15 @@ union bpf_attr {
  *
  * 		The lower two bits of *flags* are used as the return code if
  * 		the map lookup fails. This is so that the return value can be
- * 		one of the XDP program return codes up to XDP_TX, as chosen by
- * 		the caller. Any higher bits in the *flags* argument must be
+ * 		one of the XDP program return codes up to **XDP_TX**, as chosen
+ * 		by the caller. Any higher bits in the *flags* argument must be
  * 		unset.
  *
- * 		See also bpf_redirect(), which only supports redirecting to an
- * 		ifindex, but doesn't require a map to do so.
+ * 		See also **bpf_redirect**\ (), which only supports redirecting
+ * 		to an ifindex, but doesn't require a map to do so.
  * 	Return
  * 		**XDP_REDIRECT** on success, or the value of the two lower bits
- * 		of the **flags* argument on error.
+ * 		of the *flags* argument on error.
  *
  * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
  * 	Description
@@ -1747,7 +1800,7 @@ union bpf_attr {
  * 		the time running for event since last normalization. The
  * 		enabled and running times are accumulated since the perf event
  * 		open. To achieve scaling factor between two invocations of an
- * 		eBPF program, users can can use CPU id as the key (which is
+ * 		eBPF program, users can use CPU id as the key (which is
  * 		typical for perf array usage model) to remember the previous
  * 		value and do the calculation inside the eBPF program.
  * 	Return
@@ -1764,7 +1817,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
+ * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
  * 	Description
  * 		Emulate a call to **getsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1773,6 +1826,12 @@ union bpf_attr {
  * 		The retrieved value is stored in the structure pointed by
  * 		*opval* and of length *optlen*.
  *
+ * 		*bpf_socket* should be one of the following:
+ *
+ * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *
  * 		This helper actually implements a subset of **getsockopt()**.
  * 		It supports the following *level*\ s:
  *
@@ -1790,7 +1849,7 @@ union bpf_attr {
  * 		The first argument is the context *regs* on which the kprobe
  * 		works.
  *
- * 		This helper works by setting setting the PC (program counter)
+ * 		This helper works by setting the PC (program counter)
  * 		to an override function which is run in place of the original
  * 		probed function. This means the probed function is not run at
  * 		all. The replacement function just returns with the required
@@ -1959,18 +2018,19 @@ union bpf_attr {
  *
  * 		This helper works for IPv4 and IPv6, TCP and UDP sockets. The
  * 		domain (*addr*\ **->sa_family**) must be **AF_INET** (or
- * 		**AF_INET6**). Looking for a free port to bind to can be
- * 		expensive, therefore binding to port is not permitted by the
- * 		helper: *addr*\ **->sin_port** (or **sin6_port**, respectively)
- * 		must be set to zero.
+ * 		**AF_INET6**). It's advised to pass zero port (**sin_port**
+ * 		or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like
+ * 		behavior and lets the kernel efficiently pick up an unused
+ * 		port as long as 4-tuple is unique. Passing non-zero port might
+ * 		lead to degraded performance.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
  * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta)
  * 	Description
  * 		Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is
- * 		only possible to shrink the packet as of this writing,
- * 		therefore *delta* must be a negative integer.
+ * 		possible to both shrink and grow the packet tail.
+ * 		Shrink done via *delta* being a negative integer.
  *
  * 		A call to this helper is susceptible to change the underlying
  * 		packet buffer. Therefore, at load time, all checks on pointers
@@ -2256,7 +2316,7 @@ union bpf_attr {
  *		**bpf_rc_keydown**\ () again with the same values, or calling
  *		**bpf_rc_repeat**\ ().
  *
- *		Some protocols include a toggle bit, in case the button	was
+ *		Some protocols include a toggle bit, in case the button was
  *		released and pressed again between consecutive scancodes.
  *
  *		The *ctx* should point to the lirc sample as passed into
@@ -2602,7 +2662,6 @@ union bpf_attr {
  *
  * 		*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.
@@ -2785,7 +2844,6 @@ union bpf_attr {
  *
  *		*th* points to the start of the TCP header, while *th_len*
  *		contains the length of the TCP header.
- *
  *	Return
  *		On success, lower 32 bits hold the generated SYN cookie in
  *		followed by 16 bits which hold the MSS value for that cookie,
@@ -2868,7 +2926,7 @@ union bpf_attr {
  * 				// size, after checking its boundaries.
  * 			}
  *
- * 		In comparison, using **bpf_probe_read_user()** helper here
+ * 		In comparison, using **bpf_probe_read_user**\ () helper here
  * 		instead to read the string would require to estimate the length
  * 		at compile time, and would often result in copying more memory
  * 		than necessary.
@@ -2886,14 +2944,14 @@ union bpf_attr {
  * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
  * 	Description
  * 		Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
- * 		to *dst*. Same semantics as with bpf_probe_read_user_str() apply.
+ * 		to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply.
  * 	Return
- * 		On success, the strictly positive length of the string,	including
+ * 		On success, the strictly positive length of the string, including
  * 		the trailing NUL character. On error, a negative value.
  *
  * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
  *	Description
- *		Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock.
+ *		Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**.
  *		*rcv_nxt* is the ack_seq to be sent out.
  *	Return
  *		0 on success, or a negative error in case of failure.
@@ -2921,19 +2979,19 @@ union bpf_attr {
  * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags)
  *	Description
  *		For an eBPF program attached to a perf event, retrieve the
- *		branch records (struct perf_branch_entry) associated to *ctx*
- *		and store it in	the buffer pointed by *buf* up to size
+ *		branch records (**struct perf_branch_entry**) associated to *ctx*
+ *		and store it in the buffer pointed by *buf* up to size
  *		*size* bytes.
  *	Return
  *		On success, number of bytes written to *buf*. On error, a
  *		negative value.
  *
  *		The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to
- *		instead	return the number of bytes required to store all the
+ *		instead return the number of bytes required to store all the
  *		branch entries. If this flag is set, *buf* may be NULL.
  *
  *		**-EINVAL** if arguments invalid or **size** not a multiple
- *		of sizeof(struct perf_branch_entry).
+ *		of **sizeof**\ (**struct perf_branch_entry**\ ).
  *
  *		**-ENOENT** if architecture does not support branch records.
  *
@@ -2941,8 +2999,8 @@ union bpf_attr {
  *	Description
  *		Returns 0 on success, values for *pid* and *tgid* as seen from the current
  *		*namespace* will be returned in *nsdata*.
- *
- *		On failure, the returned value is one of the following:
+ *	Return
+ *		0 on success, or one of the following in case of failure:
  *
  *		**-EINVAL** if dev and inum supplied don't match dev_t and inode number
  *              with nsfs of current task, or if dev conversion to dev_t lost high bits.
@@ -2981,8 +3039,8 @@ union bpf_attr {
  * 		a global identifier that can be assumed unique. If *ctx* is
  * 		NULL, then the helper returns the cookie for the initial
  * 		network namespace. The cookie itself is very similar to that
- * 		of bpf_get_socket_cookie() helper, but for network namespaces
- * 		instead of sockets.
+ * 		of **bpf_get_socket_cookie**\ () helper, but for network
+ * 		namespaces instead of sockets.
  * 	Return
  * 		A 8-byte long opaque number.
  *
@@ -3017,14 +3075,183 @@ union bpf_attr {
  *
  *		The *flags* argument must be zero.
  *	Return
- *		0 on success, or a negative errno in case of failure.
+ *		0 on success, or a negative error in case of failure:
  *
- *		* **-EINVAL**		Unsupported flags specified.
- *		* **-ENOENT**		Socket is unavailable for assignment.
- *		* **-ENETUNREACH**	Socket is unreachable (wrong netns).
- *		* **-EOPNOTSUPP**	Unsupported operation, for example a
- *					call from outside of TC ingress.
- *		* **-ESOCKTNOSUPPORT**	Socket type not supported (reuseport).
+ *		**-EINVAL** if specified *flags* are not supported.
+ *
+ *		**-ENOENT** if the socket is unavailable for assignment.
+ *
+ *		**-ENETUNREACH** if the socket is unreachable (wrong netns).
+ *
+ *		**-EOPNOTSUPP** if the operation is not supported, for example
+ *		a call from outside of TC ingress.
+ *
+ *		**-ESOCKTNOSUPPORT** if the socket type is not supported
+ *		(reuseport).
+ *
+ * u64 bpf_ktime_get_boot_ns(void)
+ * 	Description
+ * 		Return the time elapsed since system boot, in nanoseconds.
+ * 		Does include the time the system was suspended.
+ * 		See: **clock_gettime**\ (**CLOCK_BOOTTIME**)
+ * 	Return
+ * 		Current *ktime*.
+ *
+ * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ * 	Description
+ * 		**bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print
+ * 		out the format string.
+ * 		The *m* represents the seq_file. The *fmt* and *fmt_size* are for
+ * 		the format string itself. The *data* and *data_len* are format string
+ * 		arguments. The *data* are a **u64** array and corresponding format string
+ * 		values are stored in the array. For strings and pointers where pointees
+ * 		are accessed, only the pointer values are stored in the *data* array.
+ * 		The *data_len* is the size of *data* in bytes.
+ *
+ *		Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
+ *		Reading kernel memory may fail due to either invalid address or
+ *		valid address but requiring a major memory fault. If reading kernel memory
+ *		fails, the string for **%s** will be an empty string, and the ip
+ *		address for **%p{i,I}{4,6}** will be 0. Not returning error to
+ *		bpf program is consistent with what **bpf_trace_printk**\ () does for now.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure:
+ *
+ *		**-EBUSY** if per-CPU memory copy buffer is busy, can try again
+ *		by returning 1 from bpf program.
+ *
+ *		**-EINVAL** if arguments are invalid, or if *fmt* is invalid/unsupported.
+ *
+ *		**-E2BIG** if *fmt* contains too many format specifiers.
+ *
+ *		**-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * int bpf_seq_write(struct seq_file *m, const void *data, u32 len)
+ * 	Description
+ * 		**bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data.
+ * 		The *m* represents the seq_file. The *data* and *len* represent the
+ * 		data to write in bytes.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure:
+ *
+ *		**-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * u64 bpf_sk_cgroup_id(struct bpf_sock *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
+ *		returned from **bpf_sk_lookup_xxx**\ (),
+ *		**bpf_sk_fullsock**\ (), etc. The format of returned id is
+ *		same as in **bpf_skb_cgroup_id**\ ().
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		the **CONFIG_SOCK_CGROUP_DATA** configuration option.
+ *	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)
+ *	Description
+ *		Return id of cgroup v2 that is ancestor of cgroup associated
+ *		with the *sk* at the *ancestor_level*.  The root cgroup is at
+ *		*ancestor_level* zero and each step down the hierarchy
+ *		increments the level. If *ancestor_level* == level of cgroup
+ *		associated with *sk*, then return value will be same as that
+ *		of **bpf_sk_cgroup_id**\ ().
+ *
+ *		The helper is useful to implement policies based on cgroups
+ *		that are upper in hierarchy than immediate cgroup associated
+ *		with *sk*.
+ *
+ *		The format of returned id and helper limitations are same as in
+ *		**bpf_sk_cgroup_id**\ ().
+ *	Return
+ *		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * int 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),			\
@@ -3151,7 +3378,18 @@ union bpf_attr {
 	FN(xdp_output),			\
 	FN(get_netns_cookie),		\
 	FN(get_current_ancestor_cgroup_id),	\
-	FN(sk_assign),
+	FN(sk_assign),			\
+	FN(ktime_get_boot_ns),		\
+	FN(seq_printf),			\
+	FN(seq_write),			\
+	FN(sk_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
@@ -3228,6 +3466,14 @@ 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),
@@ -3235,6 +3481,7 @@ enum {
 	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 {
@@ -3261,6 +3508,29 @@ 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,
@@ -3393,6 +3663,7 @@ struct bpf_sock {
 	__u32 dst_ip4;
 	__u32 dst_ip6[4];
 	__u32 state;
+	__s32 rx_queue_mapping;
 };
 
 struct bpf_tcp_sock {
@@ -3486,6 +3757,21 @@ 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 {
@@ -3508,6 +3794,8 @@ 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 {
@@ -3598,6 +3886,29 @@ struct bpf_btf_info {
 	__u32 id;
 } __attribute__((aligned(8)));
 
+struct bpf_link_info {
+	__u32 type;
+	__u32 id;
+	__u32 prog_id;
+	union {
+		struct {
+			__aligned_u64 tp_name; /* in/out: tp_name buffer ptr */
+			__u32 tp_name_len;     /* in/out: tp_name buffer len */
+		} raw_tracepoint;
+		struct {
+			__u32 attach_type;
+		} tracing;
+		struct {
+			__u64 cgroup_id;
+			__u32 attach_type;
+		} cgroup;
+		struct  {
+			__u32 netns_ino;
+			__u32 attach_type;
+		} netns;
+	};
+} __attribute__((aligned(8)));
+
 /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
  * by user and intended to be used by socket (e.g. to bind to, depends on
  * attach attach type).
@@ -3610,7 +3921,7 @@ struct bpf_sock_addr {
 	__u32 user_ip6[4];	/* Allows 1,2,4,8-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 user_port;	/* Allows 4-byte read and write.
+	__u32 user_port;	/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order
 				 */
 	__u32 family;		/* Allows 4-byte read, but no write */

include/uapi/linux/if_link.h

@@ -343,6 +343,7 @@ enum {
 	IFLA_BRPORT_NEIGH_SUPPRESS,
 	IFLA_BRPORT_ISOLATED,
 	IFLA_BRPORT_BACKUP_PORT,
+	IFLA_BRPORT_MRP_RING_OPEN,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)

scripts/sync-kernel.sh

@@ -85,36 +85,6 @@ commit_signature()
 	git show --pretty='("%s")|%aI|%b' --shortstat $1 -- ${2-.} | tr '\n' '|'
 }
 
-# Validate there are no non-empty merges (we can't handle them)
-# $1 - baseline tag
-# $2 - tip tag
-validate_merges()
-{
-	local baseline_tag=$1
-	local tip_tag=$2
-	local new_merges
-	local merge_change_cnt
-	local ignore_merge_resolutions
-	local desc
-
-	new_merges=$(git rev-list --merges --topo-order --reverse ${baseline_tag}..${tip_tag} ${LIBBPF_PATHS[@]})
-	for new_merge in ${new_merges}; do
-		desc=$(commit_desc ${new_merge})
-		echo "MERGE: ${desc}"
-		merge_change_cnt=$(git show --format='' ${new_merge} | wc -l)
-		if ((${merge_change_cnt} > 0)); then
-			read -p "Merge '${desc}' is non-empty, which will cause conflicts! Do you want to proceed? [y/N]: " ignore_merge_resolutions
-			case "${ignore_merge_resolutions}" in
-				"y" | "Y")
-					echo "Skipping '${desc}'..."
-					continue
-					;;
-			esac
-			exit 3
-		fi
-	done
-}
-
 # Cherry-pick commits touching libbpf-related files
 # $1 - baseline_tag
 # $2 - tip_tag
@@ -243,18 +213,14 @@ git branch ${BPF_TIP_TAG} ${BPF_TIP_COMMIT}
 git branch ${SQUASH_BASE_TAG} ${SQUASH_COMMIT}
 git checkout -b ${SQUASH_TIP_TAG} ${SQUASH_COMMIT}
 
-# Validate there are no non-empty merges in bpf-next and bpf trees
-validate_merges ${BASELINE_TAG} ${TIP_TAG}
-validate_merges ${BPF_BASELINE_TAG} ${BPF_TIP_TAG}
-
 # Cherry-pick new commits onto squashed baseline commit
 cherry_pick_commits ${BASELINE_TAG} ${TIP_TAG}
 cherry_pick_commits ${BPF_BASELINE_TAG} ${BPF_TIP_TAG}
 
 # Move all libbpf files into __libbpf directory.
-git filter-branch --prune-empty -f --tree-filter "${LIBBPF_TREE_FILTER}" ${SQUASH_TIP_TAG} ${SQUASH_BASE_TAG}
+FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch --prune-empty -f --tree-filter "${LIBBPF_TREE_FILTER}" ${SQUASH_TIP_TAG} ${SQUASH_BASE_TAG}
 # Make __libbpf a new root directory
-git filter-branch --prune-empty -f --subdirectory-filter __libbpf ${SQUASH_TIP_TAG} ${SQUASH_BASE_TAG}
+FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch --prune-empty -f --subdirectory-filter __libbpf ${SQUASH_TIP_TAG} ${SQUASH_BASE_TAG}
 
 # If there are no new commits with  libbpf-related changes, bail out
 COMMIT_CNT=$(git rev-list --count ${SQUASH_BASE_TAG}..${SQUASH_TIP_TAG})
@@ -318,8 +284,8 @@ echo "Verifying Linux's and Github's libbpf state"
 
 cd_to ${LINUX_REPO}
 git checkout -b ${VIEW_TAG} ${TIP_COMMIT}
-git filter-branch -f --tree-filter "${LIBBPF_TREE_FILTER}" ${VIEW_TAG}^..${VIEW_TAG}
-git filter-branch -f --subdirectory-filter __libbpf ${VIEW_TAG}^..${VIEW_TAG}
+FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --tree-filter "${LIBBPF_TREE_FILTER}" ${VIEW_TAG}^..${VIEW_TAG}
+FILTER_BRANCH_SQUELCH_WARNING=1 git filter-branch -f --subdirectory-filter __libbpf ${VIEW_TAG}^..${VIEW_TAG}
 git ls-files -- ${LIBBPF_VIEW_PATHS[@]} > ${TMP_DIR}/linux-view.ls
 
 cd_to ${LIBBPF_REPO}

src/Makefile

@@ -33,7 +33,7 @@ SHARED_OBJDIR := $(OBJDIR)/sharedobjs
 STATIC_OBJDIR := $(OBJDIR)/staticobjs
 OBJS := bpf.o btf.o libbpf.o libbpf_errno.o netlink.o \
 	nlattr.o str_error.o libbpf_probes.o bpf_prog_linfo.o xsk.o \
-	btf_dump.o hashmap.o
+	btf_dump.o hashmap.o ringbuf.o
 SHARED_OBJS := $(addprefix $(SHARED_OBJDIR)/,$(OBJS))
 STATIC_OBJS := $(addprefix $(STATIC_OBJDIR)/,$(OBJS))
 

src/bpf.c

@@ -619,6 +619,16 @@ int bpf_link_update(int link_fd, int new_prog_fd,
 	return sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr));
 }
 
+int bpf_iter_create(int link_fd)
+{
+	union bpf_attr attr;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.iter_create.link_fd = link_fd;
+
+	return sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr));
+}
+
 int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
 		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt)
 {
@@ -721,6 +731,11 @@ int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id)
 	return bpf_obj_get_next_id(start_id, next_id, BPF_BTF_GET_NEXT_ID);
 }
 
+int bpf_link_get_next_id(__u32 start_id, __u32 *next_id)
+{
+	return bpf_obj_get_next_id(start_id, next_id, BPF_LINK_GET_NEXT_ID);
+}
+
 int bpf_prog_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
@@ -751,13 +766,23 @@ int bpf_btf_get_fd_by_id(__u32 id)
 	return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
 }
 
-int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
+int bpf_link_get_fd_by_id(__u32 id)
+{
+	union bpf_attr attr;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.link_id = id;
+
+	return sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
+}
+
+int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
 {
 	union bpf_attr attr;
 	int err;
 
 	memset(&attr, 0, sizeof(attr));
-	attr.info.bpf_fd = prog_fd;
+	attr.info.bpf_fd = bpf_fd;
 	attr.info.info_len = *info_len;
 	attr.info.info = ptr_to_u64(info);
 
@@ -826,3 +851,13 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
 
 	return err;
 }
+
+int bpf_enable_stats(enum bpf_stats_type type)
+{
+	union bpf_attr attr;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.enable_stats.type = type;
+
+	return sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr));
+}

src/bpf.h

@@ -187,6 +187,8 @@ struct bpf_link_update_opts {
 LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd,
 			       const struct bpf_link_update_opts *opts);
 
+LIBBPF_API int bpf_iter_create(int link_fd);
+
 struct bpf_prog_test_run_attr {
 	int prog_fd;
 	int repeat;
@@ -216,10 +218,12 @@ LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data,
 LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id);
+LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
 LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
 LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);
-LIBBPF_API int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
+LIBBPF_API int bpf_link_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len);
 LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,
 			      __u32 *prog_ids, __u32 *prog_cnt);
@@ -230,6 +234,9 @@ LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
 				 __u64 *probe_offset, __u64 *probe_addr);
 
+enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */
+LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif

src/bpf_helper_defs.h

@@ -18,6 +18,7 @@ struct pt_regs;
 struct sk_reuseport_md;
 struct sockaddr;
 struct tcphdr;
+struct seq_file;
 struct __sk_buff;
 struct sk_msg_md;
 struct xdp_md;
@@ -71,8 +72,8 @@ static int (*bpf_map_delete_elem)(void *map, const void *key) = (void *) 3;
  * 	For tracing programs, safely attempt to read *size* bytes from
  * 	kernel space address *unsafe_ptr* and store the data in *dst*.
  *
- * 	Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
- * 	instead.
+ * 	Generally, use **bpf_probe_read_user**\ () or
+ * 	**bpf_probe_read_kernel**\ () instead.
  *
  * Returns
  * 	0 on success, or a negative error in case of failure.
@@ -83,6 +84,8 @@ static int (*bpf_probe_read)(void *dst, __u32 size, const void *unsafe_ptr) = (v
  * bpf_ktime_get_ns
  *
  * 	Return the time elapsed since system boot, in nanoseconds.
+ * 	Does not include time the system was suspended.
+ * 	See: **clock_gettime**\ (**CLOCK_MONOTONIC**)
  *
  * Returns
  * 	Current *ktime*.
@@ -1104,11 +1107,11 @@ static int (*bpf_xdp_adjust_head)(struct xdp_md *xdp_md, int delta) = (void *) 4
  * bpf_probe_read_str
  *
  * 	Copy a NUL terminated string from an unsafe kernel address
- * 	*unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for
+ * 	*unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for
  * 	more details.
  *
- * 	Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str()
- * 	instead.
+ * 	Generally, use **bpf_probe_read_user_str**\ () or
+ * 	**bpf_probe_read_kernel_str**\ () instead.
  *
  * Returns
  * 	On success, the strictly positive length of the string,
@@ -1167,6 +1170,12 @@ static __u32 (*bpf_set_hash)(struct __sk_buff *skb, __u32 hash) = (void *) 48;
  * 	must be specified, see **setsockopt(2)** for more information.
  * 	The option value of length *optlen* is pointed by *optval*.
  *
+ * 	*bpf_socket* should be one of the following:
+ *
+ * 	* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * 	* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 	  and **BPF_CGROUP_INET6_CONNECT**.
+ *
  * 	This helper actually implements a subset of **setsockopt()**.
  * 	It supports the following *level*\ s:
  *
@@ -1182,7 +1191,7 @@ static __u32 (*bpf_set_hash)(struct __sk_buff *skb, __u32 hash) = (void *) 48;
  * Returns
  * 	0 on success, or a negative error in case of failure.
  */
-static int (*bpf_setsockopt)(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) = (void *) 49;
+static int (*bpf_setsockopt)(void *bpf_socket, int level, int optname, void *optval, int optlen) = (void *) 49;
 
 /*
  * bpf_skb_adjust_room
@@ -1190,6 +1199,13 @@ static int (*bpf_setsockopt)(struct bpf_sock_ops *bpf_socket, int level, int opt
  * 	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
@@ -1239,16 +1255,16 @@ static int (*bpf_skb_adjust_room)(struct __sk_buff *skb, __s32 len_diff, __u32 m
  *
  * 	The lower two bits of *flags* are used as the return code if
  * 	the map lookup fails. This is so that the return value can be
- * 	one of the XDP program return codes up to XDP_TX, as chosen by
- * 	the caller. Any higher bits in the *flags* argument must be
+ * 	one of the XDP program return codes up to **XDP_TX**, as chosen
+ * 	by the caller. Any higher bits in the *flags* argument must be
  * 	unset.
  *
- * 	See also bpf_redirect(), which only supports redirecting to an
- * 	ifindex, but doesn't require a map to do so.
+ * 	See also **bpf_redirect**\ (), which only supports redirecting
+ * 	to an ifindex, but doesn't require a map to do so.
  *
  * Returns
  * 	**XDP_REDIRECT** on success, or the value of the two lower bits
- * 	of the **flags* argument on error.
+ * 	of the *flags* argument on error.
  */
 static int (*bpf_redirect_map)(void *map, __u32 key, __u64 flags) = (void *) 51;
 
@@ -1368,7 +1384,7 @@ static int (*bpf_xdp_adjust_meta)(struct xdp_md *xdp_md, int delta) = (void *) 5
  * 	the time running for event since last normalization. The
  * 	enabled and running times are accumulated since the perf event
  * 	open. To achieve scaling factor between two invocations of an
- * 	eBPF program, users can can use CPU id as the key (which is
+ * 	eBPF program, users can use CPU id as the key (which is
  * 	typical for perf array usage model) to remember the previous
  * 	value and do the calculation inside the eBPF program.
  *
@@ -1402,6 +1418,12 @@ static int (*bpf_perf_prog_read_value)(struct bpf_perf_event_data *ctx, struct b
  * 	The retrieved value is stored in the structure pointed by
  * 	*opval* and of length *optlen*.
  *
+ * 	*bpf_socket* should be one of the following:
+ *
+ * 	* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * 	* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 	  and **BPF_CGROUP_INET6_CONNECT**.
+ *
  * 	This helper actually implements a subset of **getsockopt()**.
  * 	It supports the following *level*\ s:
  *
@@ -1413,7 +1435,7 @@ static int (*bpf_perf_prog_read_value)(struct bpf_perf_event_data *ctx, struct b
  * Returns
  * 	0 on success, or a negative error in case of failure.
  */
-static int (*bpf_getsockopt)(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) = (void *) 57;
+static int (*bpf_getsockopt)(void *bpf_socket, int level, int optname, void *optval, int optlen) = (void *) 57;
 
 /*
  * bpf_override_return
@@ -1423,7 +1445,7 @@ static int (*bpf_getsockopt)(struct bpf_sock_ops *bpf_socket, int level, int opt
  * 	The first argument is the context *regs* on which the kprobe
  * 	works.
  *
- * 	This helper works by setting setting the PC (program counter)
+ * 	This helper works by setting the PC (program counter)
  * 	to an override function which is run in place of the original
  * 	probed function. This means the probed function is not run at
  * 	all. The replacement function just returns with the required
@@ -1616,10 +1638,11 @@ static int (*bpf_msg_pull_data)(struct sk_msg_md *msg, __u32 start, __u32 end, _
  *
  * 	This helper works for IPv4 and IPv6, TCP and UDP sockets. The
  * 	domain (*addr*\ **->sa_family**) must be **AF_INET** (or
- * 	**AF_INET6**). Looking for a free port to bind to can be
- * 	expensive, therefore binding to port is not permitted by the
- * 	helper: *addr*\ **->sin_port** (or **sin6_port**, respectively)
- * 	must be set to zero.
+ * 	**AF_INET6**). It's advised to pass zero port (**sin_port**
+ * 	or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like
+ * 	behavior and lets the kernel efficiently pick up an unused
+ * 	port as long as 4-tuple is unique. Passing non-zero port might
+ * 	lead to degraded performance.
  *
  * Returns
  * 	0 on success, or a negative error in case of failure.
@@ -1630,8 +1653,8 @@ static int (*bpf_bind)(struct bpf_sock_addr *ctx, struct sockaddr *addr, int add
  * bpf_xdp_adjust_tail
  *
  * 	Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is
- * 	only possible to shrink the packet as of this writing,
- * 	therefore *delta* must be a negative integer.
+ * 	possible to both shrink and grow the packet tail.
+ * 	Shrink done via *delta* being a negative integer.
  *
  * 	A call to this helper is susceptible to change the underlying
  * 	packet buffer. Therefore, at load time, all checks on pointers
@@ -1969,7 +1992,7 @@ static int (*bpf_rc_repeat)(void *ctx) = (void *) 77;
  * 	**bpf_rc_keydown**\ () again with the same values, or calling
  * 	**bpf_rc_repeat**\ ().
  *
- * 	Some protocols include a toggle bit, in case the button	was
+ * 	Some protocols include a toggle bit, in case the button was
  * 	released and pressed again between consecutive scancodes.
  *
  * 	The *ctx* should point to the lirc sample as passed into
@@ -2405,7 +2428,6 @@ static struct bpf_sock *(*bpf_skc_lookup_tcp)(void *ctx, struct bpf_sock_tuple *
  * 	*th* points to the start of the TCP header, while *th_len*
  * 	contains **sizeof**\ (**struct tcphdr**).
  *
- *
  * Returns
  * 	0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
  * 	error otherwise.
@@ -2628,7 +2650,6 @@ static int (*bpf_send_signal)(__u32 sig) = (void *) 109;
  * 	*th* points to the start of the TCP header, while *th_len*
  * 	contains the length of the TCP header.
  *
- *
  * Returns
  * 	On success, lower 32 bits hold the generated SYN cookie in
  * 	followed by 16 bits which hold the MSS value for that cookie,
@@ -2726,7 +2747,7 @@ static int (*bpf_probe_read_kernel)(void *dst, __u32 size, const void *unsafe_pt
  * 			// size, after checking its boundaries.
  * 		}
  *
- * 	In comparison, using **bpf_probe_read_user()** helper here
+ * 	In comparison, using **bpf_probe_read_user**\ () helper here
  * 	instead to read the string would require to estimate the length
  * 	at compile time, and would often result in copying more memory
  * 	than necessary.
@@ -2748,10 +2769,10 @@ static int (*bpf_probe_read_user_str)(void *dst, __u32 size, const void *unsafe_
  * bpf_probe_read_kernel_str
  *
  * 	Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
- * 	to *dst*. Same semantics as with bpf_probe_read_user_str() apply.
+ * 	to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply.
  *
  * Returns
- * 	On success, the strictly positive length of the string,	including
+ * 	On success, the strictly positive length of the string, including
  * 	the trailing NUL character. On error, a negative value.
  */
 static int (*bpf_probe_read_kernel_str)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 115;
@@ -2759,7 +2780,7 @@ static int (*bpf_probe_read_kernel_str)(void *dst, __u32 size, const void *unsaf
 /*
  * bpf_tcp_send_ack
  *
- * 	Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock.
+ * 	Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**.
  * 	*rcv_nxt* is the ack_seq to be sent out.
  *
  * Returns
@@ -2799,8 +2820,8 @@ static __u64 (*bpf_jiffies64)(void) = (void *) 118;
  * bpf_read_branch_records
  *
  * 	For an eBPF program attached to a perf event, retrieve the
- * 	branch records (struct perf_branch_entry) associated to *ctx*
- * 	and store it in	the buffer pointed by *buf* up to size
+ * 	branch records (**struct perf_branch_entry**) associated to *ctx*
+ * 	and store it in the buffer pointed by *buf* up to size
  * 	*size* bytes.
  *
  * Returns
@@ -2808,11 +2829,11 @@ static __u64 (*bpf_jiffies64)(void) = (void *) 118;
  * 	negative value.
  *
  * 	The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to
- * 	instead	return the number of bytes required to store all the
+ * 	instead return the number of bytes required to store all the
  * 	branch entries. If this flag is set, *buf* may be NULL.
  *
  * 	**-EINVAL** if arguments invalid or **size** not a multiple
- * 	of sizeof(struct perf_branch_entry).
+ * 	of **sizeof**\ (**struct perf_branch_entry**\ ).
  *
  * 	**-ENOENT** if architecture does not support branch records.
  */
@@ -2824,13 +2845,13 @@ static int (*bpf_read_branch_records)(struct bpf_perf_event_data *ctx, void *buf
  * 	Returns 0 on success, values for *pid* and *tgid* as seen from the current
  * 	*namespace* will be returned in *nsdata*.
  *
- * 	On failure, the returned value is one of the following:
+ * Returns
+ * 	0 on success, or one of the following in case of failure:
  *
  * 	**-EINVAL** if dev and inum supplied don't match dev_t and inode number
  * 	with nsfs of current task, or if dev conversion to dev_t lost high bits.
  *
  * 	**-ENOENT** if pidns does not exists for the current task.
- *
  */
 static int (*bpf_get_ns_current_pid_tgid)(__u64 dev, __u64 ino, struct bpf_pidns_info *nsdata, __u32 size) = (void *) 120;
 
@@ -2871,8 +2892,8 @@ static int (*bpf_xdp_output)(void *ctx, void *map, __u64 flags, void *data, __u6
  * 	a global identifier that can be assumed unique. If *ctx* is
  * 	NULL, then the helper returns the cookie for the initial
  * 	network namespace. The cookie itself is very similar to that
- * 	of bpf_get_socket_cookie() helper, but for network namespaces
- * 	instead of sockets.
+ * 	of **bpf_get_socket_cookie**\ () helper, but for network
+ * 	namespaces instead of sockets.
  *
  * Returns
  * 	A 8-byte long opaque number.
@@ -2916,15 +2937,228 @@ static __u64 (*bpf_get_current_ancestor_cgroup_id)(int ancestor_level) = (void *
  * 	The *flags* argument must be zero.
  *
  * Returns
- * 	0 on success, or a negative errno in case of failure.
+ * 	0 on success, or a negative error in case of failure:
  *
- * 	* **-EINVAL**		Unsupported flags specified.
- * 	* **-ENOENT**		Socket is unavailable for assignment.
- * 	* **-ENETUNREACH**	Socket is unreachable (wrong netns).
- * 	* **-EOPNOTSUPP**	Unsupported operation, for example a
- * 				call from outside of TC ingress.
- * 	* **-ESOCKTNOSUPPORT**	Socket type not supported (reuseport).
+ * 	**-EINVAL** if specified *flags* are not supported.
+ *
+ * 	**-ENOENT** if the socket is unavailable for assignment.
+ *
+ * 	**-ENETUNREACH** if the socket is unreachable (wrong netns).
+ *
+ * 	**-EOPNOTSUPP** if the operation is not supported, for example
+ * 	a call from outside of TC ingress.
+ *
+ * 	**-ESOCKTNOSUPPORT** if the socket type is not supported
+ * 	(reuseport).
  */
 static int (*bpf_sk_assign)(struct __sk_buff *skb, struct bpf_sock *sk, __u64 flags) = (void *) 124;
 
+/*
+ * bpf_ktime_get_boot_ns
+ *
+ * 	Return the time elapsed since system boot, in nanoseconds.
+ * 	Does include the time the system was suspended.
+ * 	See: **clock_gettime**\ (**CLOCK_BOOTTIME**)
+ *
+ * Returns
+ * 	Current *ktime*.
+ */
+static __u64 (*bpf_ktime_get_boot_ns)(void) = (void *) 125;
+
+/*
+ * bpf_seq_printf
+ *
+ * 	**bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print
+ * 	out the format string.
+ * 	The *m* represents the seq_file. The *fmt* and *fmt_size* are for
+ * 	the format string itself. The *data* and *data_len* are format string
+ * 	arguments. The *data* are a **u64** array and corresponding format string
+ * 	values are stored in the array. For strings and pointers where pointees
+ * 	are accessed, only the pointer values are stored in the *data* array.
+ * 	The *data_len* is the size of *data* in bytes.
+ *
+ * 	Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
+ * 	Reading kernel memory may fail due to either invalid address or
+ * 	valid address but requiring a major memory fault. If reading kernel memory
+ * 	fails, the string for **%s** will be an empty string, and the ip
+ * 	address for **%p{i,I}{4,6}** will be 0. Not returning error to
+ * 	bpf program is consistent with what **bpf_trace_printk**\ () does for now.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure:
+ *
+ * 	**-EBUSY** if per-CPU memory copy buffer is busy, can try again
+ * 	by returning 1 from bpf program.
+ *
+ * 	**-EINVAL** if arguments are invalid, or if *fmt* is invalid/unsupported.
+ *
+ * 	**-E2BIG** if *fmt* contains too many format specifiers.
+ *
+ * 	**-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ */
+static int (*bpf_seq_printf)(struct seq_file *m, const char *fmt, __u32 fmt_size, const void *data, __u32 data_len) = (void *) 126;
+
+/*
+ * bpf_seq_write
+ *
+ * 	**bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data.
+ * 	The *m* represents the seq_file. The *data* and *len* represent the
+ * 	data to write in bytes.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure:
+ *
+ * 	**-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ */
+static int (*bpf_seq_write)(struct seq_file *m, const void *data, __u32 len) = (void *) 127;
+
+/*
+ * bpf_sk_cgroup_id
+ *
+ * 	Return the cgroup v2 id of the socket *sk*.
+ *
+ * 	*sk* must be a non-**NULL** pointer to a full 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**\ ().
+ *
+ * 	This helper is available only if the kernel was compiled with
+ * 	the **CONFIG_SOCK_CGROUP_DATA** configuration option.
+ *
+ * Returns
+ * 	The id is returned or 0 in case the id could not be retrieved.
+ */
+static __u64 (*bpf_sk_cgroup_id)(struct bpf_sock *sk) = (void *) 128;
+
+/*
+ * bpf_sk_ancestor_cgroup_id
+ *
+ * 	Return id of cgroup v2 that is ancestor of cgroup associated
+ * 	with the *sk* at the *ancestor_level*.  The root cgroup is at
+ * 	*ancestor_level* zero and each step down the hierarchy
+ * 	increments the level. If *ancestor_level* == level of cgroup
+ * 	associated with *sk*, then return value will be same as that
+ * 	of **bpf_sk_cgroup_id**\ ().
+ *
+ * 	The helper is useful to implement policies based on cgroups
+ * 	that are upper in hierarchy than immediate cgroup associated
+ * 	with *sk*.
+ *
+ * 	The format of returned id and helper limitations are same as in
+ * 	**bpf_sk_cgroup_id**\ ().
+ *
+ * Returns
+ * 	The id is returned or 0 in case the id could not be retrieved.
+ */
+static __u64 (*bpf_sk_ancestor_cgroup_id)(struct bpf_sock *sk, int ancestor_level) = (void *) 129;
+
+/*
+ * bpf_ringbuf_output
+ *
+ * 	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.
+ *
+ * Returns
+ * 	0, on success;
+ * 	< 0, on error.
+ */
+static int (*bpf_ringbuf_output)(void *ringbuf, void *data, __u64 size, __u64 flags) = (void *) 130;
+
+/*
+ * bpf_ringbuf_reserve
+ *
+ * 	Reserve *size* bytes of payload in a ring buffer *ringbuf*.
+ *
+ * Returns
+ * 	Valid pointer with *size* bytes of memory available; NULL,
+ * 	otherwise.
+ */
+static void *(*bpf_ringbuf_reserve)(void *ringbuf, __u64 size, __u64 flags) = (void *) 131;
+
+/*
+ * bpf_ringbuf_submit
+ *
+ * 	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.
+ *
+ * Returns
+ * 	Nothing. Always succeeds.
+ */
+static void (*bpf_ringbuf_submit)(void *data, __u64 flags) = (void *) 132;
+
+/*
+ * bpf_ringbuf_discard
+ *
+ * 	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.
+ *
+ * Returns
+ * 	Nothing. Always succeeds.
+ */
+static void (*bpf_ringbuf_discard)(void *data, __u64 flags) = (void *) 133;
+
+/*
+ * bpf_ringbuf_query
+ *
+ * 	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.
+ *
+ * Returns
+ * 	Requested value, or 0, if flags are not recognized.
+ */
+static __u64 (*bpf_ringbuf_query)(void *ringbuf, __u64 flags) = (void *) 134;
+
+/*
+ * bpf_csum_level
+ *
+ * 	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.
+ *
+ * Returns
+ * 	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.
+ */
+static int (*bpf_csum_level)(struct __sk_buff *skb, __u64 level) = (void *) 135;
+
 

src/bpf_helpers.h

@@ -2,10 +2,17 @@
 #ifndef __BPF_HELPERS__
 #define __BPF_HELPERS__
 
+/*
+ * Note that bpf programs need to include either
+ * vmlinux.h (auto-generated from BTF) or linux/types.h
+ * in advance since bpf_helper_defs.h uses such types
+ * as __u64.
+ */
 #include "bpf_helper_defs.h"
 
 #define __uint(name, val) int (*name)[val]
 #define __type(name, val) typeof(val) *name
+#define __array(name, val) typeof(val) *name[]
 
 /* Helper macro to print out debug messages */
 #define bpf_printk(fmt, ...)				\
@@ -29,6 +36,20 @@
 #define __weak __attribute__((weak))
 #endif
 
+/*
+ * Helper macro to manipulate data structures
+ */
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER)  ((size_t)&((TYPE *)0)->MEMBER)
+#endif
+#ifndef container_of
+#define container_of(ptr, type, member)				\
+	({							\
+		void *__mptr = (void *)(ptr);			\
+		((type *)(__mptr - offsetof(type, member)));	\
+	})
+#endif
+
 /*
  * Helper structure used by eBPF C program
  * to describe BPF map attributes to libbpf loader

src/bpf_tracing.h

@@ -148,11 +148,11 @@ struct pt_regs;
 #define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4])
 #define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5])
 #define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), grps[14])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14])
 #define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11])
 #define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
 #define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), pdw.addr)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr)
 
 #elif defined(bpf_target_arm)
 
@@ -413,4 +413,20 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 }									    \
 static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 
+/*
+ * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values
+ * in a structure.
+ */
+#define BPF_SEQ_PRINTF(seq, fmt, args...)				    \
+	({								    \
+		_Pragma("GCC diagnostic push")				    \
+		_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	    \
+		static const char ___fmt[] = fmt;			    \
+		unsigned long long ___param[] = { args };		    \
+		_Pragma("GCC diagnostic pop")				    \
+		int ___ret = bpf_seq_printf(seq, ___fmt, sizeof(___fmt),    \
+					    ___param, sizeof(___param));    \
+		___ret;							    \
+	})
+
 #endif

src/btf_dump.c

@@ -658,7 +658,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 			if (!btf_dump_is_blacklisted(d, id)) {
 				btf_dump_emit_typedef_def(d, id, t, 0);
 				btf_dump_printf(d, ";\n\n");
-			};
+			}
 			tstate->fwd_emitted = 1;
 			break;
 		default:
@@ -1137,6 +1137,20 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack)
 	}
 }
 
+static void btf_dump_drop_mods(struct btf_dump *d, struct id_stack *decl_stack)
+{
+	const struct btf_type *t;
+	__u32 id;
+
+	while (decl_stack->cnt) {
+		id = decl_stack->ids[decl_stack->cnt - 1];
+		t = btf__type_by_id(d->btf, id);
+		if (!btf_is_mod(t))
+			return;
+		decl_stack->cnt--;
+	}
+}
+
 static void btf_dump_emit_name(const struct btf_dump *d,
 			       const char *name, bool last_was_ptr)
 {
@@ -1235,14 +1249,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			 * a const/volatile modifier for array, so we are
 			 * going to silently skip them here.
 			 */
-			while (decls->cnt) {
-				next_id = decls->ids[decls->cnt - 1];
-				next_t = btf__type_by_id(d->btf, next_id);
-				if (btf_is_mod(next_t))
-					decls->cnt--;
-				else
-					break;
-			}
+			btf_dump_drop_mods(d, decls);
 
 			if (decls->cnt == 0) {
 				btf_dump_emit_name(d, fname, last_was_ptr);
@@ -1270,7 +1277,15 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			__u16 vlen = btf_vlen(t);
 			int i;
 
-			btf_dump_emit_mods(d, decls);
+			/*
+			 * GCC emits extra volatile qualifier for
+			 * __attribute__((noreturn)) function pointers. Clang
+			 * doesn't do it. It's a GCC quirk for backwards
+			 * compatibility with code written for GCC <2.5. So,
+			 * similarly to extra qualifiers for array, just drop
+			 * them, instead of handling them.
+			 */
+			btf_dump_drop_mods(d, decls);
 			if (decls->cnt) {
 				btf_dump_printf(d, " (");
 				btf_dump_emit_type_chain(d, decls, fname, lvl);

src/hashmap.c

@@ -59,7 +59,14 @@ struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
 
 void hashmap__clear(struct hashmap *map)
 {
+	struct hashmap_entry *cur, *tmp;
+	size_t bkt;
+
+	hashmap__for_each_entry_safe(map, cur, tmp, bkt) {
+		free(cur);
+	}
 	free(map->buckets);
+	map->buckets = NULL;
 	map->cap = map->cap_bits = map->sz = 0;
 }
 
@@ -93,8 +100,7 @@ static int hashmap_grow(struct hashmap *map)
 	struct hashmap_entry **new_buckets;
 	struct hashmap_entry *cur, *tmp;
 	size_t new_cap_bits, new_cap;
-	size_t h;
-	int bkt;
+	size_t h, bkt;
 
 	new_cap_bits = map->cap_bits + 1;
 	if (new_cap_bits < HASHMAP_MIN_CAP_BITS)

src/hashmap.h

@@ -10,12 +10,10 @@
 
 #include <stdbool.h>
 #include <stddef.h>
-#ifdef __GLIBC__
-#include <bits/wordsize.h>
-#else
-#include <bits/reg.h>
+#include <limits.h>
+#ifndef __WORDSIZE
+#define __WORDSIZE (__SIZEOF_LONG__ * 8)
 #endif
-#include "libbpf_internal.h"
 
 static inline size_t hash_bits(size_t h, int bits)
 {

src/libbpf.h

@@ -253,11 +253,22 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_lsm(struct bpf_program *prog);
 LIBBPF_API struct bpf_link *
 bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_netns(struct bpf_program *prog, int netns_fd);
 
 struct bpf_map;
 
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
 
+struct bpf_iter_attach_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+};
+#define bpf_iter_attach_opts__last_field sz
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_iter(struct bpf_program *prog,
+			 const struct bpf_iter_attach_opts *opts);
+
 struct bpf_insn;
 
 /*
@@ -469,6 +480,27 @@ LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
 LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 				     size_t info_size, __u32 flags);
 
+/* Ring buffer APIs */
+struct ring_buffer;
+
+typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size);
+
+struct ring_buffer_opts {
+	size_t sz; /* size of this struct, for forward/backward compatiblity */
+};
+
+#define ring_buffer_opts__last_field sz
+
+LIBBPF_API struct ring_buffer *
+ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx,
+		 const struct ring_buffer_opts *opts);
+LIBBPF_API void ring_buffer__free(struct ring_buffer *rb);
+LIBBPF_API int ring_buffer__add(struct ring_buffer *rb, int map_fd,
+				ring_buffer_sample_fn sample_cb, void *ctx);
+LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms);
+LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb);
+
+/* Perf buffer APIs */
 struct perf_buffer;
 
 typedef void (*perf_buffer_sample_fn)(void *ctx, int cpu,
@@ -524,6 +556,7 @@ perf_buffer__new_raw(int map_fd, size_t page_cnt,
 
 LIBBPF_API void perf_buffer__free(struct perf_buffer *pb);
 LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms);
+LIBBPF_API int perf_buffer__consume(struct perf_buffer *pb);
 
 typedef enum bpf_perf_event_ret
 	(*bpf_perf_event_print_t)(struct perf_event_header *hdr,

src/libbpf.map

@@ -254,3 +254,19 @@ LIBBPF_0.0.8 {
 		bpf_program__set_lsm;
 		bpf_set_link_xdp_fd_opts;
 } LIBBPF_0.0.7;
+
+LIBBPF_0.0.9 {
+	global:
+		bpf_enable_stats;
+		bpf_iter_create;
+		bpf_link_get_fd_by_id;
+		bpf_link_get_next_id;
+		bpf_program__attach_iter;
+		bpf_program__attach_netns;
+		perf_buffer__consume;
+		ring_buffer__add;
+		ring_buffer__consume;
+		ring_buffer__free;
+		ring_buffer__new;
+		ring_buffer__poll;
+} LIBBPF_0.0.8;

src/libbpf_internal.h

@@ -153,7 +153,7 @@ struct btf_ext_info_sec {
 	__u32	sec_name_off;
 	__u32	num_info;
 	/* Followed by num_info * record_size number of bytes */
-	__u8	data[0];
+	__u8	data[];
 };
 
 /* The minimum bpf_func_info checked by the loader */

src/libbpf_probes.c

@@ -238,6 +238,11 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		if (btf_fd < 0)
 			return false;
 		break;
+	case BPF_MAP_TYPE_RINGBUF:
+		key_size = 0;
+		value_size = 0;
+		max_entries = 4096;
+		break;
 	case BPF_MAP_TYPE_UNSPEC:
 	case BPF_MAP_TYPE_HASH:
 	case BPF_MAP_TYPE_ARRAY:

src/netlink.c

@@ -321,6 +321,8 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 
 static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags)
 {
+	flags &= XDP_FLAGS_MODES;
+
 	if (info->attach_mode != XDP_ATTACHED_MULTI && !flags)
 		return info->prog_id;
 	if (flags & XDP_FLAGS_DRV_MODE)

src/ringbuf.c

@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/*
+ * Ring buffer operations.
+ *
+ * Copyright (C) 2020 Facebook, Inc.
+ */
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include <linux/err.h>
+#include <linux/bpf.h>
+#include <asm/barrier.h>
+#include <sys/mman.h>
+#include <sys/epoll.h>
+#include <tools/libc_compat.h>
+
+#include "libbpf.h"
+#include "libbpf_internal.h"
+#include "bpf.h"
+
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
+struct ring {
+	ring_buffer_sample_fn sample_cb;
+	void *ctx;
+	void *data;
+	unsigned long *consumer_pos;
+	unsigned long *producer_pos;
+	unsigned long mask;
+	int map_fd;
+};
+
+struct ring_buffer {
+	struct epoll_event *events;
+	struct ring *rings;
+	size_t page_size;
+	int epoll_fd;
+	int ring_cnt;
+};
+
+static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r)
+{
+	if (r->consumer_pos) {
+		munmap(r->consumer_pos, rb->page_size);
+		r->consumer_pos = NULL;
+	}
+	if (r->producer_pos) {
+		munmap(r->producer_pos, rb->page_size + 2 * (r->mask + 1));
+		r->producer_pos = NULL;
+	}
+}
+
+/* Add extra RINGBUF maps to this ring buffer manager */
+int ring_buffer__add(struct ring_buffer *rb, int map_fd,
+		     ring_buffer_sample_fn sample_cb, void *ctx)
+{
+	struct bpf_map_info info;
+	__u32 len = sizeof(info);
+	struct epoll_event *e;
+	struct ring *r;
+	void *tmp;
+	int err;
+
+	memset(&info, 0, sizeof(info));
+
+	err = bpf_obj_get_info_by_fd(map_fd, &info, &len);
+	if (err) {
+		err = -errno;
+		pr_warn("ringbuf: failed to get map info for fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+
+	if (info.type != BPF_MAP_TYPE_RINGBUF) {
+		pr_warn("ringbuf: map fd=%d is not BPF_MAP_TYPE_RINGBUF\n",
+			map_fd);
+		return -EINVAL;
+	}
+
+	tmp = reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings));
+	if (!tmp)
+		return -ENOMEM;
+	rb->rings = tmp;
+
+	tmp = reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events));
+	if (!tmp)
+		return -ENOMEM;
+	rb->events = tmp;
+
+	r = &rb->rings[rb->ring_cnt];
+	memset(r, 0, sizeof(*r));
+
+	r->map_fd = map_fd;
+	r->sample_cb = sample_cb;
+	r->ctx = ctx;
+	r->mask = info.max_entries - 1;
+
+	/* Map writable consumer page */
+	tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+		   map_fd, 0);
+	if (tmp == MAP_FAILED) {
+		err = -errno;
+		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+	r->consumer_pos = tmp;
+
+	/* Map read-only producer page and data pages. We map twice as big
+	 * data size to allow simple reading of samples that wrap around the
+	 * end of a ring buffer. See kernel implementation for details.
+	 * */
+	tmp = mmap(NULL, rb->page_size + 2 * info.max_entries, PROT_READ,
+		   MAP_SHARED, map_fd, rb->page_size);
+	if (tmp == MAP_FAILED) {
+		err = -errno;
+		ringbuf_unmap_ring(rb, r);
+		pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+	r->producer_pos = tmp;
+	r->data = tmp + rb->page_size;
+
+	e = &rb->events[rb->ring_cnt];
+	memset(e, 0, sizeof(*e));
+
+	e->events = EPOLLIN;
+	e->data.fd = rb->ring_cnt;
+	if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) {
+		err = -errno;
+		ringbuf_unmap_ring(rb, r);
+		pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+
+	rb->ring_cnt++;
+	return 0;
+}
+
+void ring_buffer__free(struct ring_buffer *rb)
+{
+	int i;
+
+	if (!rb)
+		return;
+
+	for (i = 0; i < rb->ring_cnt; ++i)
+		ringbuf_unmap_ring(rb, &rb->rings[i]);
+	if (rb->epoll_fd >= 0)
+		close(rb->epoll_fd);
+
+	free(rb->events);
+	free(rb->rings);
+	free(rb);
+}
+
+struct ring_buffer *
+ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx,
+		 const struct ring_buffer_opts *opts)
+{
+	struct ring_buffer *rb;
+	int err;
+
+	if (!OPTS_VALID(opts, ring_buffer_opts))
+		return NULL;
+
+	rb = calloc(1, sizeof(*rb));
+	if (!rb)
+		return NULL;
+
+	rb->page_size = getpagesize();
+
+	rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+	if (rb->epoll_fd < 0) {
+		err = -errno;
+		pr_warn("ringbuf: failed to create epoll instance: %d\n", err);
+		goto err_out;
+	}
+
+	err = ring_buffer__add(rb, map_fd, sample_cb, ctx);
+	if (err)
+		goto err_out;
+
+	return rb;
+
+err_out:
+	ring_buffer__free(rb);
+	return NULL;
+}
+
+static inline int roundup_len(__u32 len)
+{
+	/* clear out top 2 bits (discard and busy, if set) */
+	len <<= 2;
+	len >>= 2;
+	/* add length prefix */
+	len += BPF_RINGBUF_HDR_SZ;
+	/* round up to 8 byte alignment */
+	return (len + 7) / 8 * 8;
+}
+
+static int ringbuf_process_ring(struct ring* r)
+{
+	int *len_ptr, len, err, cnt = 0;
+	unsigned long cons_pos, prod_pos;
+	bool got_new_data;
+	void *sample;
+
+	cons_pos = smp_load_acquire(r->consumer_pos);
+	do {
+		got_new_data = false;
+		prod_pos = smp_load_acquire(r->producer_pos);
+		while (cons_pos < prod_pos) {
+			len_ptr = r->data + (cons_pos & r->mask);
+			len = smp_load_acquire(len_ptr);
+
+			/* sample not committed yet, bail out for now */
+			if (len & BPF_RINGBUF_BUSY_BIT)
+				goto done;
+
+			got_new_data = true;
+			cons_pos += roundup_len(len);
+
+			if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) {
+				sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ;
+				err = r->sample_cb(r->ctx, sample, len);
+				if (err) {
+					/* update consumer pos and bail out */
+					smp_store_release(r->consumer_pos,
+							  cons_pos);
+					return err;
+				}
+				cnt++;
+			}
+
+			smp_store_release(r->consumer_pos, cons_pos);
+		}
+	} while (got_new_data);
+done:
+	return cnt;
+}
+
+/* Consume available ring buffer(s) data without event polling.
+ * Returns number of records consumed across all registered ring buffers, or
+ * negative number if any of the callbacks return error.
+ */
+int ring_buffer__consume(struct ring_buffer *rb)
+{
+	int i, err, res = 0;
+
+	for (i = 0; i < rb->ring_cnt; i++) {
+		struct ring *ring = &rb->rings[i];
+
+		err = ringbuf_process_ring(ring);
+		if (err < 0)
+			return err;
+		res += err;
+	}
+	return res;
+}
+
+/* Poll for available data and consume records, if any are available.
+ * Returns number of records consumed, or negative number, if any of the
+ * registered callbacks returned error.
+ */
+int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
+{
+	int i, cnt, err, res = 0;
+
+	cnt = epoll_wait(rb->epoll_fd, rb->events, rb->ring_cnt, timeout_ms);
+	for (i = 0; i < cnt; i++) {
+		__u32 ring_id = rb->events[i].data.fd;
+		struct ring *ring = &rb->rings[ring_id];
+
+		err = ringbuf_process_ring(ring);
+		if (err < 0)
+			return err;
+		res += cnt;
+	}
+	return cnt < 0 ? -errno : res;
+}

travis-ci/vmtest/build_selftests.sh

@@ -1,11 +1,15 @@
 #!/bin/bash
 
+set -euxo pipefail
+
 LLVM_VER=11
 LIBBPF_PATH="${REPO_ROOT}"
 REPO_PATH="travis-ci/vmtest/bpf-next"
 
-# temporary work-around for failing tests
-rm "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c"
+PREPARE_SELFTESTS_SCRIPT=${VMTEST_ROOT}/prepare_selftests-${KERNEL}.sh
+if [ -f "${PREPARE_SELFTESTS_SCRIPT}" ]; then
+	(cd "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" && ${PREPARE_SELFTESTS_SCRIPT})
+fi
 
 make \
 	CLANG=clang-${LLVM_VER} \
@@ -21,5 +25,4 @@ cd ${LIBBPF_PATH}
 rm selftests/bpf/.gitignore
 git add selftests
 
-blacklist_path="${VMTEST_ROOT}/configs/blacklist"
-git add "${blacklist_path}"
+git add "${VMTEST_ROOT}/configs/blacklist"

travis-ci/vmtest/configs/blacklist/BLACKLIST-5.5.0

@@ -1,27 +1,53 @@
 # PERMANENTLY DISABLED
+align			# verifier output format changed
+bpf_iter		# bpf_iter support is missing
+bpf_obj_id		# bpf_link support missing for GET_OBJ_INFO, GET_FD_BY_ID, etc
 bpf_tcp_ca		# STRUCT_OPS is missing
+
+# latest Clang generates code that fails to verify
+bpf_verif_scale
+#bpf_verif_scale/strobemeta.o
+#bpf_verif_scale/strobemeta_nounroll1.o
+#bpf_verif_scale/strobemeta_nounroll2.o
+
 cgroup_attach_multi	# BPF_F_REPLACE_PROG missing
 cgroup_link		# LINK_CREATE is missing
+cgroup_skb_sk_lookup	# bpf_sk_lookup_tcp() helper is missing
+connect_force_port	# cgroup/get{peer,sock}name{4,6} support is missing
+enable_stats		# BPF_ENABLE_STATS support is missing
 fentry_fexit		# bpf_prog_test_tracing missing
 fentry_test		# bpf_prog_test_tracing missing
 fexit_bpf2bpf		# freplace is missing
 fexit_test		# bpf_prog_test_tracing missing
+flow_dissector		# bpf_link-based flow dissector is in 5.8+
+flow_dissector_reattach
 get_stack_raw_tp	# exercising BPF verifier bug causing infinite loop
 link_pinning		# bpf_link is missing
+load_bytes_relative	# new functionality in 5.8
 mmap			# 5.5 kernel is too permissive with re-mmaping
-modify_return		# fmod_ret is missing
+modify_return		# fmod_ret support is missing
 ns_current_pid_tgid	# bpf_get_ns_current_pid_tgid() helper is missing
 perf_branches		# bpf_read_branch_records() helper is missing
+ringbuf			# BPF_MAP_TYPE_RINGBUF is supported in 5.8+
+
+# bug in verifier w/ tracking references
+#reference_tracking/classifier/sk_lookup_success
+reference_tracking
+
 select_reuseport	# UDP support is missing
 sk_assign		# bpf_sk_assign helper missing
+skb_helpers		# helpers added in 5.8+
 sockmap_listen		# no listen socket supportin SOCKMAP
 skb_ctx			# ctx_{size, }_{in, out} in BPF_PROG_TEST_RUN is missing
 test_global_funcs	# kernel doesn't support BTF linkage=global on FUNCs
 test_lsm		# no BPF_LSM support
+test_overhead		# no fmod_ret support
 vmlinux			# hrtimer_nanosleep() signature changed incompatibly
+xdp_adjust_tail		# new XDP functionality added in 5.8
 xdp_attach		# IFLA_XDP_EXPECTED_FD support is missing
 xdp_bpf2bpf		# freplace is missing
 
 
 # TEMPORARILY DISABLED
 send_signal		# flaky
+cls_redirect		# latest Clang breaks BPF verification

travis-ci/vmtest/configs/blacklist/BLACKLIST-latest

@@ -2,3 +2,4 @@
 send_signal		# flaky
 test_lsm		# semi-working
 sk_assign		# needs better setup in Travis CI
+core_reloc		# temporary test breakage

travis-ci/vmtest/prepare_selftests-5.5.0.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+set -euxo pipefail
+
+# these tests expect vmlinux.h to have latest defiition of bpf_devmap_val xdp_md->egress_ifindex
+rm progs/test_xdp_with_devmap_helpers.c
+rm progs/test_xdp_devmap_helpers.c
+rm prog_tests/xdp_devmap_attach.c
+
+# no BPF_F_NO_PREALLOC in BTF and no sk_msg_md->sk field
+rm progs/test_skmsg_load_helpers.c
+rm prog_tests/sockmap_basic.c