vmtests: blacklist mmap test on 5.5

5.5 kernel has a bug in kernel allowing to violate read-only access to
mmap()-ed map. Disable selftest that now is failing.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>

.travis.yml

@@ -8,17 +8,9 @@ env:
     global:
         - PROJECT_NAME='libbpf'
         - AUTHOR_EMAIL="$(git log -1 --pretty=\"%aE\")"
-        - CI_MANAGERS="$TRAVIS_BUILD_DIR/travis-ci/managers"
-        - VMTEST_ROOT="$TRAVIS_BUILD_DIR/travis-ci/vmtest"
         - REPO_ROOT="$TRAVIS_BUILD_DIR"
-        - GIT_FETCH_DEPTH=64
+        - CI_ROOT="$REPO_ROOT/travis-ci"
-        - VMTEST_SETUPCMD="PROJECT_NAME=${PROJECT_NAME} ./${PROJECT_NAME}/travis-ci/vmtest/run_selftests.sh"
+        - VMTEST_ROOT="$CI_ROOT/vmtest"
-    jobs:
-        # Setup command override.
-        # 5.5.0-rc6 is built from bpf-next; TODO(hex@): remove when pahole v1.16 is available
-        - KERNEL=5.5.0-rc6
-        - KERNEL=5.5.0
-        - KERNEL=LATEST
 
 addons:
     apt:
@@ -29,26 +21,7 @@ addons:
             - elfutils
             - libcap-dev
             - libelf-dev
-install: sudo adduser "${USER}" kvm
+            - libdw-dev
-before_script:
-    - wget -O - https://apt.llvm.org/llvm-snapshot.gpg.key | sudo apt-key add -
-    - echo "deb http://apt.llvm.org/bionic/ llvm-toolchain-bionic-10 main" | sudo tee -a /etc/apt/sources.list
-    - echo "deb http://archive.ubuntu.com/ubuntu eoan main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list
-    - sudo apt-get -qq update
-    - sudo apt-get -y install dwarves=1.15-1
-    - sudo apt-get -qq -y install clang-10 lld-10 llvm-10
-    - if [[ "${KERNEL}" = 'LATEST' ]]; then ${VMTEST_ROOT}/build_latest_kernel.sh travis-ci/vmtest/bpf-next; fi
-    - ${VMTEST_ROOT}/prepare_selftests.sh travis-ci/vmtest/bpf-next
-    # Escape whitespace characters.
-    - setup_cmd=$(sed 's/\([[:space:]]\)/\\\1/g' <<< "${VMTEST_SETUPCMD}")
-    - if [[ "${KERNEL}" = 'LATEST' ]]; then
-        sudo -E sudo -E -u "${USER}" "${VMTEST_ROOT}/run.sh" -b travis-ci/vmtest/bpf-next -o -d ~ -s "${setup_cmd}" ~/root.img;
-      else
-        sudo -E sudo -E -u "${USER}" "${VMTEST_ROOT}/run.sh" -k "${KERNEL}*" -o -d ~ -s "${setup_cmd}" ~/root.img;
-      fi; exitstatus=$?
-    - test $exitstatus -le 1
-script:
-    - test $exitstatus -eq 0
 
 stages:
     # Run Coverity periodically instead of for each PR for following reasons:
@@ -62,130 +35,72 @@ stages:
 
 jobs:
     include:
-        - stage: Build & test
+        - stage: Build
-          name: Debian Testing
+          name: Debian Build
           language: bash
-          env:
+          install:        $CI_ROOT/managers/debian.sh SETUP
-              - DEBIAN_RELEASE="testing"
+          script:         $CI_ROOT/managers/debian.sh RUN || travis_terminate
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
-          install:
-              - $CI_MANAGERS/debian.sh SETUP
-          # Override before_script: so VMTEST before_install commands are not executed.
-          before_script: true
-          script:
-              - $CI_MANAGERS/debian.sh RUN || travis_terminate
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
 
-        - name: Debian Testing (ASan+UBSan)
+        - name: Debian Build (ASan+UBSan)
           language: bash
-          env:
+          install:        $CI_ROOT/managers/debian.sh SETUP
-              - DEBIAN_RELEASE="testing"
+          script:         $CI_ROOT/managers/debian.sh RUN_ASAN || travis_terminate
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
-          install:
-              - $CI_MANAGERS/debian.sh SETUP
-          before_script: true
-          script:
-              - $CI_MANAGERS/debian.sh RUN_ASAN || travis_terminate
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
 
-        - name: Debian Testing (clang)
+        - name: Debian Build (clang)
           language: bash
-          env:
+          install:        $CI_ROOT/managers/debian.sh SETUP
-              - DEBIAN_RELEASE="testing"
+          script:         $CI_ROOT/managers/debian.sh RUN_CLANG || travis_terminate
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
-          install:
-              - $CI_MANAGERS/debian.sh SETUP
-          before_script: true
-          script:
-              - $CI_MANAGERS/debian.sh RUN_CLANG || travis_terminate
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
 
-        - name: Debian Testing (clang ASan+UBSan)
+        - name: Debian Build (clang ASan+UBSan)
           language: bash
-          env:
+          install:        $CI_ROOT/managers/debian.sh SETUP
-              - DEBIAN_RELEASE="testing"
+          script:         $CI_ROOT/managers/debian.sh RUN_CLANG_ASAN || travis_terminate
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
-          install:
-              - $CI_MANAGERS/debian.sh SETUP
-          before_script: true
-          script:
-              - $CI_MANAGERS/debian.sh RUN_CLANG_ASAN || travis_terminate
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
 
-        - name: Debian Testing (gcc-8)
+        - name: Debian Build (gcc-8)
           language: bash
-          env:
+          install:        $CI_ROOT/managers/debian.sh SETUP
-              - DEBIAN_RELEASE="testing"
+          script:         $CI_ROOT/managers/debian.sh RUN_GCC8 || travis_terminate
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
-          install:
-              - $CI_MANAGERS/debian.sh SETUP
-          before_script: true
-          script:
-              - $CI_MANAGERS/debian.sh RUN_GCC8 || travis_terminate
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
 
-        - name: Debian Testing (gcc-8 ASan+UBSan)
+        - name: Debian Build (gcc-8 ASan+UBSan)
           language: bash
-          env:
+          install:        $CI_ROOT/managers/debian.sh SETUP
-              - DEBIAN_RELEASE="testing"
+          script:         $CI_ROOT/managers/debian.sh RUN_GCC8_ASAN || travis_terminate
-              - CONT_NAME="libbpf-debian-$DEBIAN_RELEASE"
+          after_script:   $CI_ROOT/managers/debian.sh CLEANUP
-          before_install:
-              - sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
-              - docker --version
-          install:
-              - $CI_MANAGERS/debian.sh SETUP
-          before_script: true
-          script:
-              - $CI_MANAGERS/debian.sh RUN_GCC8_ASAN || travis_terminate
-          after_script:
-              - $CI_MANAGERS/debian.sh CLEANUP
 
-        - name: Ubuntu Bionic
+        - name: Ubuntu Bionic Build
           language: bash
-          before_script: true
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate
-          script:
-              - sudo $CI_MANAGERS/ubuntu.sh || travis_terminate
 
-        - name: Ubuntu Bionic (arm)
+        - name: Ubuntu Bionic Build (arm)
           arch: arm64
           language: bash
-          before_script: true
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate
-          script:
-              - sudo $CI_MANAGERS/ubuntu.sh || travis_terminate
 
-        - name: Ubuntu Bionic (s390x)
+        - name: Ubuntu Bionic Build (s390x)
           arch: s390x
           language: bash
-          before_script: true
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate
-          script:
-              - sudo $CI_MANAGERS/ubuntu.sh || travis_terminate
 
-        - name: Ubuntu Bionic (ppc64le)
+        - name: Ubuntu Bionic Build (ppc64le)
           arch: ppc64le
           language: bash
-          before_script: true
+          script: sudo $CI_ROOT/managers/ubuntu.sh || travis_terminate
-          script:
+
-              - sudo $CI_MANAGERS/ubuntu.sh || travis_terminate
+        - stage: Build & Test
+          name: Kernel 5.5.0 + selftests
+          language: bash
+          env: KERNEL=5.5.0
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate
+
+        - name: Kernel LATEST + selftests
+          language: bash
+          env: KERNEL=LATEST
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate
 
         - stage: Coverity
           language: bash
@@ -205,7 +120,5 @@ jobs:
               - sudo apt-get update
               - sudo apt-get -y build-dep libelf-dev
               - sudo apt-get install -y libelf-dev pkg-config
-          # Override before_script: so VMTEST before_script commands are not executed.
-          before_script: true
           script:
               - scripts/coverity.sh || travis_terminate

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-08dc225d8868d5094ada62f471ebdfcce9dbc298
+edadedf1c5b4e4404192a0a4c3c0c05e3b7672ab

CHECKPOINT-COMMIT

@@ -1 +1 @@
-35b9211c0a2427e8f39e534f442f43804fc8d5ca
+2fcd80144b93ff90836a44f2054b4d82133d3a85

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[0];	/* Arbitrary size */
+	__u8	data[];	/* Arbitrary size */
 };
 
 struct bpf_cgroup_storage_key {
@@ -111,6 +111,8 @@ enum bpf_cmd {
 	BPF_MAP_LOOKUP_AND_DELETE_BATCH,
 	BPF_MAP_UPDATE_BATCH,
 	BPF_MAP_DELETE_BATCH,
+	BPF_LINK_CREATE,
+	BPF_LINK_UPDATE,
 };
 
 enum bpf_map_type {
@@ -181,6 +183,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_TRACING,
 	BPF_PROG_TYPE_STRUCT_OPS,
 	BPF_PROG_TYPE_EXT,
+	BPF_PROG_TYPE_LSM,
 };
 
 enum bpf_attach_type {
@@ -210,6 +213,8 @@ enum bpf_attach_type {
 	BPF_TRACE_RAW_TP,
 	BPF_TRACE_FENTRY,
 	BPF_TRACE_FEXIT,
+	BPF_MODIFY_RETURN,
+	BPF_LSM_MAC,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -325,44 +330,46 @@ enum bpf_attach_type {
 #define BPF_PSEUDO_CALL		1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
-#define BPF_ANY		0 /* create new element or update existing */
+enum {
-#define BPF_NOEXIST	1 /* create new element if it didn't exist */
+	BPF_ANY		= 0, /* create new element or update existing */
-#define BPF_EXIST	2 /* update existing element */
+	BPF_NOEXIST	= 1, /* create new element if it didn't exist */
-#define BPF_F_LOCK	4 /* spin_lock-ed map_lookup/map_update */
+	BPF_EXIST	= 2, /* update existing element */
+	BPF_F_LOCK	= 4, /* spin_lock-ed map_lookup/map_update */
+};
 
 /* flags for BPF_MAP_CREATE command */
-#define BPF_F_NO_PREALLOC	(1U << 0)
+enum {
+	BPF_F_NO_PREALLOC	= (1U << 0),
 /* Instead of having one common LRU list in the
  * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
  * which can scale and perform better.
  * Note, the LRU nodes (including free nodes) cannot be moved
  * across different LRU lists.
  */
-#define BPF_F_NO_COMMON_LRU	(1U << 1)
+	BPF_F_NO_COMMON_LRU	= (1U << 1),
 /* Specify numa node during map creation */
-#define BPF_F_NUMA_NODE		(1U << 2)
+	BPF_F_NUMA_NODE		= (1U << 2),
-
-#define BPF_OBJ_NAME_LEN 16U
 
 /* Flags for accessing BPF object from syscall side. */
-#define BPF_F_RDONLY		(1U << 3)
+	BPF_F_RDONLY		= (1U << 3),
-#define BPF_F_WRONLY		(1U << 4)
+	BPF_F_WRONLY		= (1U << 4),
 
 /* Flag for stack_map, store build_id+offset instead of pointer */
-#define BPF_F_STACK_BUILD_ID	(1U << 5)
+	BPF_F_STACK_BUILD_ID	= (1U << 5),
 
 /* Zero-initialize hash function seed. This should only be used for testing. */
-#define BPF_F_ZERO_SEED		(1U << 6)
+	BPF_F_ZERO_SEED		= (1U << 6),
 
 /* Flags for accessing BPF object from program side. */
-#define BPF_F_RDONLY_PROG	(1U << 7)
+	BPF_F_RDONLY_PROG	= (1U << 7),
-#define BPF_F_WRONLY_PROG	(1U << 8)
+	BPF_F_WRONLY_PROG	= (1U << 8),
 
 /* Clone map from listener for newly accepted socket */
-#define BPF_F_CLONE		(1U << 9)
+	BPF_F_CLONE		= (1U << 9),
 
 /* Enable memory-mapping BPF map */
-#define BPF_F_MMAPABLE		(1U << 10)
+	BPF_F_MMAPABLE		= (1U << 10),
+};
 
 /* Flags for BPF_PROG_QUERY. */
 
@@ -391,6 +398,8 @@ struct bpf_stack_build_id {
 	};
 };
 
+#define BPF_OBJ_NAME_LEN 16U
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -534,7 +543,7 @@ union bpf_attr {
 		__u32		prog_cnt;
 	} query;
 
-	struct {
+	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
 		__u64 name;
 		__u32 prog_fd;
 	} raw_tracepoint;
@@ -562,6 +571,24 @@ union bpf_attr {
 		__u64		probe_offset;	/* output: probe_offset */
 		__u64		probe_addr;	/* output: probe_addr */
 	} task_fd_query;
+
+	struct { /* struct used by BPF_LINK_CREATE command */
+		__u32		prog_fd;	/* eBPF program to attach */
+		__u32		target_fd;	/* object to attach to */
+		__u32		attach_type;	/* attach type */
+		__u32		flags;		/* extra flags */
+	} link_create;
+
+	struct { /* struct used by BPF_LINK_UPDATE command */
+		__u32		link_fd;	/* link fd */
+		/* new program fd to update link with */
+		__u32		new_prog_fd;
+		__u32		flags;		/* extra flags */
+		/* expected link's program fd; is specified only if
+		 * BPF_F_REPLACE flag is set in flags */
+		__u32		old_prog_fd;
+	} link_update;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
@@ -1045,9 +1072,9 @@ union bpf_attr {
  * 		supports redirection to the egress interface, and accepts no
  * 		flag at all.
  *
- * 		The same effect can be attained with the more generic
+ * 		The same effect can also be attained with the more generic
- * 		**bpf_redirect_map**\ (), which requires specific maps to be
+ * 		**bpf_redirect_map**\ (), which uses a BPF map to store the
- * 		used but offers better performance.
+ * 		redirect target instead of providing it directly to the helper.
  * 	Return
  * 		For XDP, the helper returns **XDP_REDIRECT** on success or
  * 		**XDP_ABORTED** on error. For other program types, the values
@@ -1611,13 +1638,11 @@ union bpf_attr {
  * 		the caller. Any higher bits in the *flags* argument must be
  * 		unset.
  *
- * 		When used to redirect packets to net devices, this helper
+ * 		See also bpf_redirect(), which only supports redirecting to an
- * 		provides a high performance increase over **bpf_redirect**\ ().
+ * 		ifindex, but doesn't require a map to do so.
- * 		This is due to various implementation details of the underlying
- * 		mechanisms, one of which is the fact that **bpf_redirect_map**\
- * 		() tries to send packet as a "bulk" to the device.
  * 	Return
- * 		**XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ * 		**XDP_REDIRECT** on success, or the value of the two lower bits
+ * 		of the **flags* argument on error.
  *
  * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
  * 	Description
@@ -2892,6 +2917,114 @@ union bpf_attr {
  *		Obtain the 64bit jiffies
  *	Return
  *		The 64 bit jiffies
+ *
+ * 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
+ *		*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
+ *		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).
+ *
+ *		**-ENOENT** if architecture does not support branch records.
+ *
+ * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
+ *	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:
+ *
+ *		**-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.
+ *
+ * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ *	Description
+ *		Write raw *data* blob into a special BPF perf event held by
+ *		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ *		event must have the following attributes: **PERF_SAMPLE_RAW**
+ *		as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ *		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ *		The *flags* are used to indicate the index in *map* for which
+ *		the value must be put, masked with **BPF_F_INDEX_MASK**.
+ *		Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ *		to indicate that the index of the current CPU core should be
+ *		used.
+ *
+ *		The value to write, of *size*, is passed through eBPF stack and
+ *		pointed by *data*.
+ *
+ *		*ctx* is a pointer to in-kernel struct xdp_buff.
+ *
+ *		This helper is similar to **bpf_perf_eventoutput**\ () but
+ *		restricted to raw_tracepoint bpf programs.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_get_netns_cookie(void *ctx)
+ * 	Description
+ * 		Retrieve the cookie (generated by the kernel) of the network
+ * 		namespace the input *ctx* is associated with. The network
+ * 		namespace cookie remains stable for its lifetime and provides
+ * 		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.
+ * 	Return
+ * 		A 8-byte long opaque number.
+ *
+ * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level)
+ * 	Description
+ * 		Return id of cgroup v2 that is ancestor of the cgroup associated
+ * 		with the current task 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 the current task, then return value will be the
+ * 		same as that of **bpf_get_current_cgroup_id**\ ().
+ *
+ * 		The helper is useful to implement policies based on cgroups
+ * 		that are upper in hierarchy than immediate cgroup associated
+ * 		with the current task.
+ *
+ * 		The format of returned id and helper limitations are same as in
+ * 		**bpf_get_current_cgroup_id**\ ().
+ * 	Return
+ * 		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
+ *	Description
+ *		Assign the *sk* to the *skb*. When combined with appropriate
+ *		routing configuration to receive the packet towards the socket,
+ *		will cause *skb* to be delivered to the specified socket.
+ *		Subsequent redirection of *skb* via  **bpf_redirect**\ (),
+ *		**bpf_clone_redirect**\ () or other methods outside of BPF may
+ *		interfere with successful delivery to the socket.
+ *
+ *		This operation is only valid from TC ingress path.
+ *
+ *		The *flags* argument must be zero.
+ *	Return
+ *		0 on success, or a negative errno 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).
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3012,7 +3145,13 @@ union bpf_attr {
 	FN(probe_read_kernel_str),	\
 	FN(tcp_send_ack),		\
 	FN(send_signal_thread),		\
-	FN(jiffies64),
+	FN(jiffies64),			\
+	FN(read_branch_records),	\
+	FN(get_ns_current_pid_tgid),	\
+	FN(xdp_output),			\
+	FN(get_netns_cookie),		\
+	FN(get_current_ancestor_cgroup_id),	\
+	FN(sk_assign),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3027,69 +3166,100 @@ enum bpf_func_id {
 /* All flags used by eBPF helper functions, placed here. */
 
 /* BPF_FUNC_skb_store_bytes flags. */
-#define BPF_F_RECOMPUTE_CSUM		(1ULL << 0)
+enum {
-#define BPF_F_INVALIDATE_HASH		(1ULL << 1)
+	BPF_F_RECOMPUTE_CSUM		= (1ULL << 0),
+	BPF_F_INVALIDATE_HASH		= (1ULL << 1),
+};
 
 /* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags.
  * First 4 bits are for passing the header field size.
  */
-#define BPF_F_HDR_FIELD_MASK		0xfULL
+enum {
+	BPF_F_HDR_FIELD_MASK		= 0xfULL,
+};
 
 /* BPF_FUNC_l4_csum_replace flags. */
-#define BPF_F_PSEUDO_HDR		(1ULL << 4)
+enum {
-#define BPF_F_MARK_MANGLED_0		(1ULL << 5)
+	BPF_F_PSEUDO_HDR		= (1ULL << 4),
-#define BPF_F_MARK_ENFORCE		(1ULL << 6)
+	BPF_F_MARK_MANGLED_0		= (1ULL << 5),
+	BPF_F_MARK_ENFORCE		= (1ULL << 6),
+};
 
 /* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
-#define BPF_F_INGRESS			(1ULL << 0)
+enum {
+	BPF_F_INGRESS			= (1ULL << 0),
+};
 
 /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
-#define BPF_F_TUNINFO_IPV6		(1ULL << 0)
+enum {
+	BPF_F_TUNINFO_IPV6		= (1ULL << 0),
+};
 
 /* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */
-#define BPF_F_SKIP_FIELD_MASK		0xffULL
+enum {
-#define BPF_F_USER_STACK		(1ULL << 8)
+	BPF_F_SKIP_FIELD_MASK		= 0xffULL,
+	BPF_F_USER_STACK		= (1ULL << 8),
 /* flags used by BPF_FUNC_get_stackid only. */
-#define BPF_F_FAST_STACK_CMP		(1ULL << 9)
+	BPF_F_FAST_STACK_CMP		= (1ULL << 9),
-#define BPF_F_REUSE_STACKID		(1ULL << 10)
+	BPF_F_REUSE_STACKID		= (1ULL << 10),
 /* flags used by BPF_FUNC_get_stack only. */
-#define BPF_F_USER_BUILD_ID		(1ULL << 11)
+	BPF_F_USER_BUILD_ID		= (1ULL << 11),
+};
 
 /* BPF_FUNC_skb_set_tunnel_key flags. */
-#define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
+enum {
-#define BPF_F_DONT_FRAGMENT		(1ULL << 2)
+	BPF_F_ZERO_CSUM_TX		= (1ULL << 1),
-#define BPF_F_SEQ_NUMBER		(1ULL << 3)
+	BPF_F_DONT_FRAGMENT		= (1ULL << 2),
+	BPF_F_SEQ_NUMBER		= (1ULL << 3),
+};
 
 /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
  * BPF_FUNC_perf_event_read_value flags.
  */
-#define BPF_F_INDEX_MASK		0xffffffffULL
+enum {
-#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+	BPF_F_INDEX_MASK		= 0xffffffffULL,
+	BPF_F_CURRENT_CPU		= BPF_F_INDEX_MASK,
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
-#define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)
+	BPF_F_CTXLEN_MASK		= (0xfffffULL << 32),
+};
 
 /* Current network namespace */
-#define BPF_F_CURRENT_NETNS		(-1L)
+enum {
+	BPF_F_CURRENT_NETNS		= (-1L),
+};
 
 /* BPF_FUNC_skb_adjust_room flags. */
-#define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
+enum {
+	BPF_F_ADJ_ROOM_FIXED_GSO	= (1ULL << 0),
+	BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	= (1ULL << 1),
+	BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	= (1ULL << 2),
+	BPF_F_ADJ_ROOM_ENCAP_L4_GRE	= (1ULL << 3),
+	BPF_F_ADJ_ROOM_ENCAP_L4_UDP	= (1ULL << 4),
+};
 
-#define BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
+enum {
-#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
+	BPF_ADJ_ROOM_ENCAP_L2_MASK	= 0xff,
+	BPF_ADJ_ROOM_ENCAP_L2_SHIFT	= 56,
+};
 
-#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
-#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
-#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
-#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
 #define BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
 					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
 					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
 /* BPF_FUNC_sysctl_get_name flags. */
-#define BPF_F_SYSCTL_BASE_NAME		(1ULL << 0)
+enum {
+	BPF_F_SYSCTL_BASE_NAME		= (1ULL << 0),
+};
 
 /* BPF_FUNC_sk_storage_get flags */
-#define BPF_SK_STORAGE_GET_F_CREATE	(1ULL << 0)
+enum {
+	BPF_SK_STORAGE_GET_F_CREATE	= (1ULL << 0),
+};
+
+/* BPF_FUNC_read_branch_records flags. */
+enum {
+	BPF_F_GET_BRANCH_RECORDS_SIZE	= (1ULL << 0),
+};
 
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
@@ -3155,6 +3325,7 @@ struct __sk_buff {
 	__u32 wire_len;
 	__u32 gso_segs;
 	__bpf_md_ptr(struct bpf_sock *, sk);
+	__u32 gso_size;
 };
 
 struct bpf_tunnel_key {
@@ -3507,13 +3678,14 @@ struct bpf_sock_ops {
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
-#define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
+enum {
-#define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
+	BPF_SOCK_OPS_RTO_CB_FLAG	= (1<<0),
-#define BPF_SOCK_OPS_STATE_CB_FLAG	(1<<2)
+	BPF_SOCK_OPS_RETRANS_CB_FLAG	= (1<<1),
-#define BPF_SOCK_OPS_RTT_CB_FLAG	(1<<3)
+	BPF_SOCK_OPS_STATE_CB_FLAG	= (1<<2),
-#define BPF_SOCK_OPS_ALL_CB_FLAGS       0xF		/* Mask of all currently
+	BPF_SOCK_OPS_RTT_CB_FLAG	= (1<<3),
-							 * supported cb flags
+/* Mask of all currently supported cb flags */
-							 */
+	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0xF,
+};
 
 /* List of known BPF sock_ops operators.
  * New entries can only be added at the end
@@ -3592,8 +3764,10 @@ enum {
 	BPF_TCP_MAX_STATES	/* Leave at the end! */
 };
 
-#define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
+enum {
-#define TCP_BPF_SNDCWND_CLAMP	1002	/* Set sndcwnd_clamp */
+	TCP_BPF_IW		= 1001,	/* Set TCP initial congestion window */
+	TCP_BPF_SNDCWND_CLAMP	= 1002,	/* Set sndcwnd_clamp */
+};
 
 struct bpf_perf_event_value {
 	__u64 counter;
@@ -3601,12 +3775,16 @@ struct bpf_perf_event_value {
 	__u64 running;
 };
 
-#define BPF_DEVCG_ACC_MKNOD	(1ULL << 0)
+enum {
-#define BPF_DEVCG_ACC_READ	(1ULL << 1)
+	BPF_DEVCG_ACC_MKNOD	= (1ULL << 0),
-#define BPF_DEVCG_ACC_WRITE	(1ULL << 2)
+	BPF_DEVCG_ACC_READ	= (1ULL << 1),
+	BPF_DEVCG_ACC_WRITE	= (1ULL << 2),
+};
 
-#define BPF_DEVCG_DEV_BLOCK	(1ULL << 0)
+enum {
-#define BPF_DEVCG_DEV_CHAR	(1ULL << 1)
+	BPF_DEVCG_DEV_BLOCK	= (1ULL << 0),
+	BPF_DEVCG_DEV_CHAR	= (1ULL << 1),
+};
 
 struct bpf_cgroup_dev_ctx {
 	/* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
@@ -3622,8 +3800,10 @@ struct bpf_raw_tracepoint_args {
 /* DIRECT:  Skip the FIB rules and go to FIB table associated with device
  * OUTPUT:  Do lookup from egress perspective; default is ingress
  */
-#define BPF_FIB_LOOKUP_DIRECT  (1U << 0)
+enum {
-#define BPF_FIB_LOOKUP_OUTPUT  (1U << 1)
+	BPF_FIB_LOOKUP_DIRECT  = (1U << 0),
+	BPF_FIB_LOOKUP_OUTPUT  = (1U << 1),
+};
 
 enum {
 	BPF_FIB_LKUP_RET_SUCCESS,      /* lookup successful */
@@ -3695,9 +3875,11 @@ enum bpf_task_fd_type {
 	BPF_FD_TYPE_URETPROBE,		/* filename + offset */
 };
 
-#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG		(1U << 0)
+enum {
-#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL		(1U << 1)
+	BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG		= (1U << 0),
-#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP		(1U << 2)
+	BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL		= (1U << 1),
+	BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP		= (1U << 2),
+};
 
 struct bpf_flow_keys {
 	__u16	nhoff;
@@ -3763,4 +3945,8 @@ struct bpf_sockopt {
 	__s32	retval;
 };
 
+struct bpf_pidns_info {
+	__u32 pid;
+	__u32 tgid;
+};
 #endif /* _UAPI__LINUX_BPF_H__ */

include/uapi/linux/if_link.h

@@ -463,6 +463,7 @@ enum {
 	IFLA_MACSEC_REPLAY_PROTECT,
 	IFLA_MACSEC_VALIDATION,
 	IFLA_MACSEC_PAD,
+	IFLA_MACSEC_OFFLOAD,
 	__IFLA_MACSEC_MAX,
 };
 
@@ -489,6 +490,7 @@ enum macsec_validation_type {
 enum macsec_offload {
 	MACSEC_OFFLOAD_OFF = 0,
 	MACSEC_OFFLOAD_PHY = 1,
+	MACSEC_OFFLOAD_MAC = 2,
 	__MACSEC_OFFLOAD_END,
 	MACSEC_OFFLOAD_MAX = __MACSEC_OFFLOAD_END - 1,
 };
@@ -960,11 +962,12 @@ enum {
 #define XDP_FLAGS_SKB_MODE		(1U << 1)
 #define XDP_FLAGS_DRV_MODE		(1U << 2)
 #define XDP_FLAGS_HW_MODE		(1U << 3)
+#define XDP_FLAGS_REPLACE		(1U << 4)
 #define XDP_FLAGS_MODES			(XDP_FLAGS_SKB_MODE | \
 					 XDP_FLAGS_DRV_MODE | \
 					 XDP_FLAGS_HW_MODE)
 #define XDP_FLAGS_MASK			(XDP_FLAGS_UPDATE_IF_NOEXIST | \
-					 XDP_FLAGS_MODES)
+					 XDP_FLAGS_MODES | XDP_FLAGS_REPLACE)
 
 /* These are stored into IFLA_XDP_ATTACHED on dump. */
 enum {
@@ -984,6 +987,7 @@ enum {
 	IFLA_XDP_DRV_PROG_ID,
 	IFLA_XDP_SKB_PROG_ID,
 	IFLA_XDP_HW_PROG_ID,
+	IFLA_XDP_EXPECTED_FD,
 	__IFLA_XDP_MAX,
 };
 

scripts/sync-kernel.sh

@@ -49,7 +49,7 @@ PATH_MAP=(									\
 	[tools/include/tools/libc_compat.h]=include/tools/libc_compat.h		\
 )
 
-LIBBPF_PATHS="${!PATH_MAP[@]}"
+LIBBPF_PATHS="${!PATH_MAP[@]} :^tools/lib/bpf/Makefile :^tools/lib/bpf/Build :^tools/lib/bpf/.gitignore"
 LIBBPF_VIEW_PATHS="${PATH_MAP[@]}"
 LIBBPF_VIEW_EXCLUDE_REGEX='^src/(Makefile|Build|test_libbpf\.c|bpf_helper_defs\.h|\.gitignore)$'
 
@@ -79,9 +79,10 @@ commit_desc()
 # The idea is that this single-line signature is good enough to make final
 # decision about whether two commits are the same, across different repos.
 # $1 - commit ref
+# $2 - paths filter
 commit_signature()
 {
-	git log -n1 --pretty='("%s")|%aI|%b' --shortstat $1 | tr '\n' '|'
+	git show --pretty='("%s")|%aI|%b' --shortstat $1 -- ${2-.} | tr '\n' '|'
 }
 
 # Validate there are no non-empty merges (we can't handle them)
@@ -133,7 +134,7 @@ cherry_pick_commits()
 	new_commits=$(git rev-list --no-merges --topo-order --reverse ${baseline_tag}..${tip_tag} ${LIBBPF_PATHS[@]})
 	for new_commit in ${new_commits}; do
 		desc="$(commit_desc ${new_commit})"
-		signature="$(commit_signature ${new_commit})"
+		signature="$(commit_signature ${new_commit} "${LIBBPF_PATHS[@]}")"
 		synced_cnt=$(grep -F "${signature}" ${TMP_DIR}/libbpf_commits.txt | wc -l)
 		manual_check=0
 		if ((${synced_cnt} > 0)); then

src/bpf.c

@@ -235,7 +235,8 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
-	if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS) {
+	if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
+	    attr.prog_type == BPF_PROG_TYPE_LSM) {
 		attr.attach_btf_id = load_attr->attach_btf_id;
 	} else if (attr.prog_type == BPF_PROG_TYPE_TRACING ||
 		   attr.prog_type == BPF_PROG_TYPE_EXT) {
@@ -584,6 +585,40 @@ int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
 	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
 }
 
+int bpf_link_create(int prog_fd, int target_fd,
+		    enum bpf_attach_type attach_type,
+		    const struct bpf_link_create_opts *opts)
+{
+	union bpf_attr attr;
+
+	if (!OPTS_VALID(opts, bpf_link_create_opts))
+		return -EINVAL;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.link_create.prog_fd = prog_fd;
+	attr.link_create.target_fd = target_fd;
+	attr.link_create.attach_type = attach_type;
+
+	return sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
+}
+
+int bpf_link_update(int link_fd, int new_prog_fd,
+		    const struct bpf_link_update_opts *opts)
+{
+	union bpf_attr attr;
+
+	if (!OPTS_VALID(opts, bpf_link_update_opts))
+		return -EINVAL;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.link_update.link_fd = link_fd;
+	attr.link_update.new_prog_fd = new_prog_fd;
+	attr.link_update.flags = OPTS_GET(opts, flags, 0);
+	attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0);
+
+	return sys_bpf(BPF_LINK_UPDATE, &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)
 {

src/bpf.h

@@ -168,6 +168,25 @@ LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
 				enum bpf_attach_type type);
 
+struct bpf_link_create_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+};
+#define bpf_link_create_opts__last_field sz
+
+LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
+			       enum bpf_attach_type attach_type,
+			       const struct bpf_link_create_opts *opts);
+
+struct bpf_link_update_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;	   /* extra flags */
+	__u32 old_prog_fd; /* expected old program FD */
+};
+#define bpf_link_update_opts__last_field old_prog_fd
+
+LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd,
+			       const struct bpf_link_update_opts *opts);
+
 struct bpf_prog_test_run_attr {
 	int prog_fd;
 	int repeat;

src/bpf_helper_defs.h

@@ -4,6 +4,7 @@
 struct bpf_fib_lookup;
 struct bpf_perf_event_data;
 struct bpf_perf_event_value;
+struct bpf_pidns_info;
 struct bpf_sock;
 struct bpf_sock_addr;
 struct bpf_sock_ops;
@@ -576,9 +577,9 @@ static __u64 (*bpf_perf_event_read)(void *map, __u64 flags) = (void *) 22;
  * 	supports redirection to the egress interface, and accepts no
  * 	flag at all.
  *
- * 	The same effect can be attained with the more generic
+ * 	The same effect can also be attained with the more generic
- * 	**bpf_redirect_map**\ (), which requires specific maps to be
+ * 	**bpf_redirect_map**\ (), which uses a BPF map to store the
- * 	used but offers better performance.
+ * 	redirect target instead of providing it directly to the helper.
  *
  * Returns
  * 	For XDP, the helper returns **XDP_REDIRECT** on success or
@@ -1242,14 +1243,12 @@ static int (*bpf_skb_adjust_room)(struct __sk_buff *skb, __s32 len_diff, __u32 m
  * 	the caller. Any higher bits in the *flags* argument must be
  * 	unset.
  *
- * 	When used to redirect packets to net devices, this helper
+ * 	See also bpf_redirect(), which only supports redirecting to an
- * 	provides a high performance increase over **bpf_redirect**\ ().
+ * 	ifindex, but doesn't require a map to do so.
- * 	This is due to various implementation details of the underlying
- * 	mechanisms, one of which is the fact that **bpf_redirect_map**\
- * 	() tries to send packet as a "bulk" to the device.
  *
  * Returns
- * 	**XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
+ * 	**XDP_REDIRECT** on success, or the value of the two lower bits
+ * 	of the **flags* argument on error.
  */
 static int (*bpf_redirect_map)(void *map, __u32 key, __u64 flags) = (void *) 51;
 
@@ -2796,4 +2795,136 @@ static int (*bpf_send_signal_thread)(__u32 sig) = (void *) 117;
  */
 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
+ * 	*size* bytes.
+ *
+ * Returns
+ * 	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
+ * 	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).
+ *
+ * 	**-ENOENT** if architecture does not support branch records.
+ */
+static int (*bpf_read_branch_records)(struct bpf_perf_event_data *ctx, void *buf, __u32 size, __u64 flags) = (void *) 119;
+
+/*
+ * bpf_get_ns_current_pid_tgid
+ *
+ * 	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:
+ *
+ * 	**-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;
+
+/*
+ * bpf_xdp_output
+ *
+ * 	Write raw *data* blob into a special BPF perf event held by
+ * 	*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ * 	event must have the following attributes: **PERF_SAMPLE_RAW**
+ * 	as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ * 	**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ * 	The *flags* are used to indicate the index in *map* for which
+ * 	the value must be put, masked with **BPF_F_INDEX_MASK**.
+ * 	Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ * 	to indicate that the index of the current CPU core should be
+ * 	used.
+ *
+ * 	The value to write, of *size*, is passed through eBPF stack and
+ * 	pointed by *data*.
+ *
+ * 	*ctx* is a pointer to in-kernel struct xdp_buff.
+ *
+ * 	This helper is similar to **bpf_perf_eventoutput**\ () but
+ * 	restricted to raw_tracepoint bpf programs.
+ *
+ * Returns
+ * 	0 on success, or a negative error in case of failure.
+ */
+static int (*bpf_xdp_output)(void *ctx, void *map, __u64 flags, void *data, __u64 size) = (void *) 121;
+
+/*
+ * bpf_get_netns_cookie
+ *
+ * 	Retrieve the cookie (generated by the kernel) of the network
+ * 	namespace the input *ctx* is associated with. The network
+ * 	namespace cookie remains stable for its lifetime and provides
+ * 	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.
+ *
+ * Returns
+ * 	A 8-byte long opaque number.
+ */
+static __u64 (*bpf_get_netns_cookie)(void *ctx) = (void *) 122;
+
+/*
+ * bpf_get_current_ancestor_cgroup_id
+ *
+ * 	Return id of cgroup v2 that is ancestor of the cgroup associated
+ * 	with the current task 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 the current task, then return value will be the
+ * 	same as that of **bpf_get_current_cgroup_id**\ ().
+ *
+ * 	The helper is useful to implement policies based on cgroups
+ * 	that are upper in hierarchy than immediate cgroup associated
+ * 	with the current task.
+ *
+ * 	The format of returned id and helper limitations are same as in
+ * 	**bpf_get_current_cgroup_id**\ ().
+ *
+ * Returns
+ * 	The id is returned or 0 in case the id could not be retrieved.
+ */
+static __u64 (*bpf_get_current_ancestor_cgroup_id)(int ancestor_level) = (void *) 123;
+
+/*
+ * bpf_sk_assign
+ *
+ * 	Assign the *sk* to the *skb*. When combined with appropriate
+ * 	routing configuration to receive the packet towards the socket,
+ * 	will cause *skb* to be delivered to the specified socket.
+ * 	Subsequent redirection of *skb* via  **bpf_redirect**\ (),
+ * 	**bpf_clone_redirect**\ () or other methods outside of BPF may
+ * 	interfere with successful delivery to the socket.
+ *
+ * 	This operation is only valid from TC ingress path.
+ *
+ * 	The *flags* argument must be zero.
+ *
+ * Returns
+ * 	0 on success, or a negative errno 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).
+ */
+static int (*bpf_sk_assign)(struct __sk_buff *skb, struct bpf_sock *sk, __u64 flags) = (void *) 124;
+
 

src/bpf_tracing.h

@@ -49,7 +49,8 @@
 
 #if defined(bpf_target_x86)
 
-#ifdef __KERNEL__
+#if defined(__KERNEL__) || defined(__VMLINUX_H__)
+
 #define PT_REGS_PARM1(x) ((x)->di)
 #define PT_REGS_PARM2(x) ((x)->si)
 #define PT_REGS_PARM3(x) ((x)->dx)
@@ -60,7 +61,20 @@
 #define PT_REGS_RC(x) ((x)->ax)
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->ip)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), di)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), si)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), dx)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), cx)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), sp)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), bp)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), ax)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), ip)
+
 #else
+
 #ifdef __i386__
 /* i386 kernel is built with -mregparm=3 */
 #define PT_REGS_PARM1(x) ((x)->eax)
@@ -73,7 +87,20 @@
 #define PT_REGS_RC(x) ((x)->eax)
 #define PT_REGS_SP(x) ((x)->esp)
 #define PT_REGS_IP(x) ((x)->eip)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), eax)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), edx)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), ecx)
+#define PT_REGS_PARM4_CORE(x) 0
+#define PT_REGS_PARM5_CORE(x) 0
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), esp)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), ebp)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), eax)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), esp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), eip)
+
 #else
+
 #define PT_REGS_PARM1(x) ((x)->rdi)
 #define PT_REGS_PARM2(x) ((x)->rsi)
 #define PT_REGS_PARM3(x) ((x)->rdx)
@@ -84,6 +111,18 @@
 #define PT_REGS_RC(x) ((x)->rax)
 #define PT_REGS_SP(x) ((x)->rsp)
 #define PT_REGS_IP(x) ((x)->rip)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), rdi)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), rsi)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), rdx)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), rcx)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), rsp)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), rbp)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), rax)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), rsp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), rip)
+
 #endif
 #endif
 
@@ -104,6 +143,17 @@ struct pt_regs;
 #define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
 #define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[3])
+#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_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)
+
 #elif defined(bpf_target_arm)
 
 #define PT_REGS_PARM1(x) ((x)->uregs[0])
@@ -117,6 +167,17 @@ struct pt_regs;
 #define PT_REGS_SP(x) ((x)->uregs[13])
 #define PT_REGS_IP(x) ((x)->uregs[12])
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), uregs[0])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), uregs[1])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), uregs[2])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), uregs[3])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), uregs[4])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), uregs[14])
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), uregs[11])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), uregs[0])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), uregs[13])
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), uregs[12])
+
 #elif defined(bpf_target_arm64)
 
 /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
@@ -134,6 +195,17 @@ struct pt_regs;
 #define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
 #define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[1])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[2])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[3])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[4])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[30])
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[29])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), sp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), pc)
+
 #elif defined(bpf_target_mips)
 
 #define PT_REGS_PARM1(x) ((x)->regs[4])
@@ -147,6 +219,17 @@ struct pt_regs;
 #define PT_REGS_SP(x) ((x)->regs[29])
 #define PT_REGS_IP(x) ((x)->cp0_epc)
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), regs[4])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), regs[5])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), regs[6])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), regs[7])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31])
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[1])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29])
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc)
+
 #elif defined(bpf_target_powerpc)
 
 #define PT_REGS_PARM1(x) ((x)->gpr[3])
@@ -158,6 +241,15 @@ struct pt_regs;
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->nip)
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), gpr[3])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), gpr[4])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), gpr[5])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), gpr[6])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), gpr[7])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), gpr[3])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), nip)
+
 #elif defined(bpf_target_sparc)
 
 #define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
@@ -169,11 +261,22 @@ struct pt_regs;
 #define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
 #define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
 
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I1])
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I2])
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I3])
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I4])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I7])
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), u_regs[UREG_FP])
+
 /* Should this also be a bpf_target check for the sparc case? */
 #if defined(__arch64__)
 #define PT_REGS_IP(x) ((x)->tpc)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), tpc)
 #else
 #define PT_REGS_IP(x) ((x)->pc)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc)
 #endif
 
 #endif
@@ -192,4 +295,122 @@ struct pt_regs;
 			  (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
 #endif
 
+#define ___bpf_concat(a, b) a ## b
+#define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
+#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
+#define ___bpf_narg(...) \
+	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#define ___bpf_empty(...) \
+	___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
+
+#define ___bpf_ctx_cast0() ctx
+#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
+#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1]
+#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2]
+#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3]
+#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4]
+#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5]
+#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6]
+#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7]
+#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8]
+#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
+#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
+#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
+#define ___bpf_ctx_cast(args...) \
+	___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
+
+/*
+ * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
+ * similar kinds of BPF programs, that accept input arguments as a single
+ * pointer to untyped u64 array, where each u64 can actually be a typed
+ * pointer or integer of different size. Instead of requring user to write
+ * manual casts and work with array elements by index, BPF_PROG macro
+ * allows user to declare a list of named and typed input arguments in the
+ * same syntax as for normal C function. All the casting is hidden and
+ * performed transparently, while user code can just assume working with
+ * function arguments of specified type and name.
+ *
+ * Original raw context argument is preserved as well as 'ctx' argument.
+ * This is useful when using BPF helpers that expect original context
+ * as one of the parameters (e.g., for bpf_perf_event_output()).
+ */
+#define BPF_PROG(name, args...)						    \
+name(unsigned long long *ctx);						    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(unsigned long long *ctx, ##args);				    \
+typeof(name(0)) name(unsigned long long *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_ctx_cast(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(unsigned long long *ctx, ##args)
+
+struct pt_regs;
+
+#define ___bpf_kprobe_args0() ctx
+#define ___bpf_kprobe_args1(x) \
+	___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) \
+	___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) \
+	___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) \
+	___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) \
+	___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args(args...) \
+	___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
+
+/*
+ * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
+ * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific
+ * low-level way of getting kprobe input arguments from struct pt_regs, and
+ * provides a familiar typed and named function arguments syntax and
+ * semantics of accessing kprobe input paremeters.
+ *
+ * Original struct pt_regs* context is preserved as 'ctx' argument. This might
+ * be necessary when using BPF helpers like bpf_perf_event_output().
+ */
+#define BPF_KPROBE(name, args...)					    \
+name(struct pt_regs *ctx);						    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args);				    \
+typeof(name(0)) name(struct pt_regs *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_kprobe_args(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args)
+
+#define ___bpf_kretprobe_args0() ctx
+#define ___bpf_kretprobe_args1(x) \
+	___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
+#define ___bpf_kretprobe_args(args...) \
+	___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
+
+/*
+ * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional
+ * return value (in addition to `struct pt_regs *ctx`), but no input
+ * arguments, because they will be clobbered by the time probed function
+ * returns.
+ */
+#define BPF_KRETPROBE(name, args...)					    \
+name(struct pt_regs *ctx);						    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args);				    \
+typeof(name(0)) name(struct pt_regs *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_kretprobe_args(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
+
 #endif

src/btf.c

@@ -657,22 +657,32 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
 
 int btf__load(struct btf *btf)
 {
-	__u32 log_buf_size = BPF_LOG_BUF_SIZE;
+	__u32 log_buf_size = 0;
 	char *log_buf = NULL;
 	int err = 0;
 
 	if (btf->fd >= 0)
 		return -EEXIST;
 
-	log_buf = malloc(log_buf_size);
+retry_load:
-	if (!log_buf)
+	if (log_buf_size) {
-		return -ENOMEM;
+		log_buf = malloc(log_buf_size);
+		if (!log_buf)
+			return -ENOMEM;
 
-	*log_buf = 0;
+		*log_buf = 0;
+	}
 
 	btf->fd = bpf_load_btf(btf->data, btf->data_size,
 			       log_buf, log_buf_size, false);
 	if (btf->fd < 0) {
+		if (!log_buf || errno == ENOSPC) {
+			log_buf_size = max((__u32)BPF_LOG_BUF_SIZE,
+					   log_buf_size << 1);
+			free(log_buf);
+			goto retry_load;
+		}
+
 		err = -errno;
 		pr_warn("Error loading BTF: %s(%d)\n", strerror(errno), errno);
 		if (*log_buf)

src/btf_dump.c

@@ -916,13 +916,13 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id,
 			/* enumerators share namespace with typedef idents */
 			dup_cnt = btf_dump_name_dups(d, d->ident_names, name);
 			if (dup_cnt > 1) {
-				btf_dump_printf(d, "\n%s%s___%zu = %d,",
+				btf_dump_printf(d, "\n%s%s___%zu = %u,",
 						pfx(lvl + 1), name, dup_cnt,
-						(__s32)v->val);
+						(__u32)v->val);
 			} else {
-				btf_dump_printf(d, "\n%s%s = %d,",
+				btf_dump_printf(d, "\n%s%s = %u,",
 						pfx(lvl + 1), name,
-						(__s32)v->val);
+						(__u32)v->val);
 			}
 		}
 		btf_dump_printf(d, "\n%s}", pfx(lvl));
@@ -1030,7 +1030,7 @@ int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id,
 	if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts))
 		return -EINVAL;
 
-	fname = OPTS_GET(opts, field_name, NULL);
+	fname = OPTS_GET(opts, field_name, "");
 	lvl = OPTS_GET(opts, indent_level, 0);
 	btf_dump_emit_type_decl(d, id, fname, lvl);
 	return 0;

src/libbpf.c

@@ -24,6 +24,7 @@
 #include <endian.h>
 #include <fcntl.h>
 #include <errno.h>
+#include <ctype.h>
 #include <asm/unistd.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
@@ -177,6 +178,8 @@ struct bpf_capabilities {
 	__u32 array_mmap:1;
 	/* BTF_FUNC_GLOBAL is supported */
 	__u32 btf_func_global:1;
+	/* kernel support for expected_attach_type in BPF_PROG_LOAD */
+	__u32 exp_attach_type:1;
 };
 
 enum reloc_type {
@@ -193,6 +196,22 @@ struct reloc_desc {
 	int sym_off;
 };
 
+struct bpf_sec_def;
+
+typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec,
+					struct bpf_program *prog);
+
+struct bpf_sec_def {
+	const char *sec;
+	size_t len;
+	enum bpf_prog_type prog_type;
+	enum bpf_attach_type expected_attach_type;
+	bool is_exp_attach_type_optional;
+	bool is_attachable;
+	bool is_attach_btf;
+	attach_fn_t attach_fn;
+};
+
 /*
  * bpf_prog should be a better name but it has been used in
  * linux/filter.h.
@@ -203,6 +222,7 @@ struct bpf_program {
 	char *name;
 	int prog_ifindex;
 	char *section_name;
+	const struct bpf_sec_def *sec_def;
 	/* section_name with / replaced by _; makes recursive pinning
 	 * in bpf_object__pin_programs easier
 	 */
@@ -1283,7 +1303,7 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map)
 static char *internal_map_name(struct bpf_object *obj,
 			       enum libbpf_map_type type)
 {
-	char map_name[BPF_OBJ_NAME_LEN];
+	char map_name[BPF_OBJ_NAME_LEN], *p;
 	const char *sfx = libbpf_type_to_btf_name[type];
 	int sfx_len = max((size_t)7, strlen(sfx));
 	int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1,
@@ -1292,6 +1312,11 @@ static char *internal_map_name(struct bpf_object *obj,
 	snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name,
 		 sfx_len, libbpf_type_to_btf_name[type]);
 
+	/* sanitise map name to characters allowed by kernel */
+	for (p = map_name; *p && p < map_name + sizeof(map_name); p++)
+		if (!isalnum(*p) && *p != '_' && *p != '.')
+			*p = '_';
+
 	return strdup(map_name);
 }
 
@@ -1839,7 +1864,6 @@ resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id)
  * type definition, while using only sizeof(void *) space in ELF data section.
  */
 static bool get_map_field_int(const char *map_name, const struct btf *btf,
-			      const struct btf_type *def,
 			      const struct btf_member *m, __u32 *res)
 {
 	const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL);
@@ -1966,19 +1990,19 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 			return -EINVAL;
 		}
 		if (strcmp(name, "type") == 0) {
-			if (!get_map_field_int(map_name, obj->btf, def, m,
+			if (!get_map_field_int(map_name, obj->btf, m,
 					       &map->def.type))
 				return -EINVAL;
 			pr_debug("map '%s': found type = %u.\n",
 				 map_name, map->def.type);
 		} else if (strcmp(name, "max_entries") == 0) {
-			if (!get_map_field_int(map_name, obj->btf, def, m,
+			if (!get_map_field_int(map_name, obj->btf, m,
 					       &map->def.max_entries))
 				return -EINVAL;
 			pr_debug("map '%s': found max_entries = %u.\n",
 				 map_name, map->def.max_entries);
 		} else if (strcmp(name, "map_flags") == 0) {
-			if (!get_map_field_int(map_name, obj->btf, def, m,
+			if (!get_map_field_int(map_name, obj->btf, m,
 					       &map->def.map_flags))
 				return -EINVAL;
 			pr_debug("map '%s': found map_flags = %u.\n",
@@ -1986,8 +2010,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		} else if (strcmp(name, "key_size") == 0) {
 			__u32 sz;
 
-			if (!get_map_field_int(map_name, obj->btf, def, m,
+			if (!get_map_field_int(map_name, obj->btf, m, &sz))
-					       &sz))
 				return -EINVAL;
 			pr_debug("map '%s': found key_size = %u.\n",
 				 map_name, sz);
@@ -2029,8 +2052,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		} else if (strcmp(name, "value_size") == 0) {
 			__u32 sz;
 
-			if (!get_map_field_int(map_name, obj->btf, def, m,
+			if (!get_map_field_int(map_name, obj->btf, m, &sz))
-					       &sz))
 				return -EINVAL;
 			pr_debug("map '%s': found value_size = %u.\n",
 				 map_name, sz);
@@ -2073,8 +2095,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 			__u32 val;
 			int err;
 
-			if (!get_map_field_int(map_name, obj->btf, def, m,
+			if (!get_map_field_int(map_name, obj->btf, m, &val))
-					       &val))
 				return -EINVAL;
 			pr_debug("map '%s': found pinning = %u.\n",
 				 map_name, val);
@@ -2278,11 +2299,16 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj)
 	}
 }
 
-static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
+static bool libbpf_needs_btf(const struct bpf_object *obj)
 {
 	return obj->efile.btf_maps_shndx >= 0 ||
-		obj->efile.st_ops_shndx >= 0 ||
+	       obj->efile.st_ops_shndx >= 0 ||
-		obj->nr_extern > 0;
+	       obj->nr_extern > 0;
+}
+
+static bool kernel_needs_btf(const struct bpf_object *obj)
+{
+	return obj->efile.st_ops_shndx >= 0;
 }
 
 static int bpf_object__init_btf(struct bpf_object *obj,
@@ -2318,7 +2344,7 @@ static int bpf_object__init_btf(struct bpf_object *obj,
 		}
 	}
 out:
-	if (err && bpf_object__is_btf_mandatory(obj)) {
+	if (err && libbpf_needs_btf(obj)) {
 		pr_warn("BTF is required, but is missing or corrupted.\n");
 		return err;
 	}
@@ -2342,7 +2368,7 @@ static int bpf_object__finalize_btf(struct bpf_object *obj)
 	btf_ext__free(obj->btf_ext);
 	obj->btf_ext = NULL;
 
-	if (bpf_object__is_btf_mandatory(obj)) {
+	if (libbpf_needs_btf(obj)) {
 		pr_warn("BTF is required, but is missing or corrupted.\n");
 		return -ENOENT;
 	}
@@ -2351,7 +2377,8 @@ static int bpf_object__finalize_btf(struct bpf_object *obj)
 
 static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog)
 {
-	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
+	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS ||
+	    prog->type == BPF_PROG_TYPE_LSM)
 		return true;
 
 	/* BPF_PROG_TYPE_TRACING programs which do not attach to other programs
@@ -2406,7 +2433,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 			obj->btf_ext = NULL;
 		}
 
-		if (bpf_object__is_btf_mandatory(obj))
+		if (kernel_needs_btf(obj))
 			return err;
 	}
 	return 0;
@@ -3307,6 +3334,37 @@ static int bpf_object__probe_array_mmap(struct bpf_object *obj)
 	return 0;
 }
 
+static int
+bpf_object__probe_exp_attach_type(struct bpf_object *obj)
+{
+	struct bpf_load_program_attr attr;
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int fd;
+
+	memset(&attr, 0, sizeof(attr));
+	/* use any valid combination of program type and (optional)
+	 * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
+	 * to see if kernel supports expected_attach_type field for
+	 * BPF_PROG_LOAD command
+	 */
+	attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK;
+	attr.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE;
+	attr.insns = insns;
+	attr.insns_cnt = ARRAY_SIZE(insns);
+	attr.license = "GPL";
+
+	fd = bpf_load_program_xattr(&attr, NULL, 0);
+	if (fd >= 0) {
+		obj->caps.exp_attach_type = 1;
+		close(fd);
+		return 1;
+	}
+	return 0;
+}
+
 static int
 bpf_object__probe_caps(struct bpf_object *obj)
 {
@@ -3317,6 +3375,7 @@ bpf_object__probe_caps(struct bpf_object *obj)
 		bpf_object__probe_btf_func_global,
 		bpf_object__probe_btf_datasec,
 		bpf_object__probe_array_mmap,
+		bpf_object__probe_exp_attach_type,
 	};
 	int i, ret;
 
@@ -3862,6 +3921,10 @@ static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf,
 		if (str_is_empty(targ_name))
 			continue;
 
+		t = skip_mods_and_typedefs(targ_btf, i, NULL);
+		if (!btf_is_composite(t) && !btf_is_array(t))
+			continue;
+
 		targ_essent_len = bpf_core_essential_name_len(targ_name);
 		if (targ_essent_len != local_essent_len)
 			continue;
@@ -4840,8 +4903,8 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 {
 	struct bpf_load_program_attr load_attr;
 	char *cp, errmsg[STRERR_BUFSIZE];
-	int log_buf_size = BPF_LOG_BUF_SIZE;
+	size_t log_buf_size = 0;
-	char *log_buf;
+	char *log_buf = NULL;
 	int btf_fd, ret;
 
 	if (!insns || !insns_cnt)
@@ -4849,13 +4912,19 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 
 	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
 	load_attr.prog_type = prog->type;
-	load_attr.expected_attach_type = prog->expected_attach_type;
+	/* old kernels might not support specifying expected_attach_type */
+	if (!prog->caps->exp_attach_type && prog->sec_def &&
+	    prog->sec_def->is_exp_attach_type_optional)
+		load_attr.expected_attach_type = 0;
+	else
+		load_attr.expected_attach_type = prog->expected_attach_type;
 	if (prog->caps->name)
 		load_attr.name = prog->name;
 	load_attr.insns = insns;
 	load_attr.insns_cnt = insns_cnt;
 	load_attr.license = license;
-	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) {
+	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS ||
+	    prog->type == BPF_PROG_TYPE_LSM) {
 		load_attr.attach_btf_id = prog->attach_btf_id;
 	} else if (prog->type == BPF_PROG_TYPE_TRACING ||
 		   prog->type == BPF_PROG_TYPE_EXT) {
@@ -4881,22 +4950,28 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.prog_flags = prog->prog_flags;
 
 retry_load:
-	log_buf = malloc(log_buf_size);
+	if (log_buf_size) {
-	if (!log_buf)
+		log_buf = malloc(log_buf_size);
-		pr_warn("Alloc log buffer for bpf loader error, continue without log\n");
+		if (!log_buf)
+			return -ENOMEM;
+
+		*log_buf = 0;
+	}
 
 	ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size);
 
 	if (ret >= 0) {
-		if (load_attr.log_level)
+		if (log_buf && load_attr.log_level)
 			pr_debug("verifier log:\n%s", log_buf);
 		*pfd = ret;
 		ret = 0;
 		goto out;
 	}
 
-	if (errno == ENOSPC) {
+	if (!log_buf || errno == ENOSPC) {
-		log_buf_size <<= 1;
+		log_buf_size = max((size_t)BPF_LOG_BUF_SIZE,
+				   log_buf_size << 1);
+
 		free(log_buf);
 		goto retry_load;
 	}
@@ -4939,8 +5014,9 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 {
 	int err = 0, fd, i, btf_id;
 
-	if (prog->type == BPF_PROG_TYPE_TRACING ||
+	if ((prog->type == BPF_PROG_TYPE_TRACING ||
-	    prog->type == BPF_PROG_TYPE_EXT) {
+	     prog->type == BPF_PROG_TYPE_LSM ||
+	     prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {
 		btf_id = libbpf_find_attach_btf_id(prog);
 		if (btf_id <= 0)
 			return btf_id;
@@ -5042,6 +5118,8 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 	return 0;
 }
 
+static const struct bpf_sec_def *find_sec_def(const char *sec_name);
+
 static struct bpf_object *
 __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 		   const struct bpf_object_open_opts *opts)
@@ -5097,24 +5175,17 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 	bpf_object__elf_finish(obj);
 
 	bpf_object__for_each_program(prog, obj) {
-		enum bpf_prog_type prog_type;
+		prog->sec_def = find_sec_def(prog->section_name);
-		enum bpf_attach_type attach_type;
+		if (!prog->sec_def)
-
-		if (prog->type != BPF_PROG_TYPE_UNSPEC)
-			continue;
-
-		err = libbpf_prog_type_by_name(prog->section_name, &prog_type,
-					       &attach_type);
-		if (err == -ESRCH)
 			/* couldn't guess, but user might manually specify */
 			continue;
-		if (err)
-			goto out;
 
-		bpf_program__set_type(prog, prog_type);
+		bpf_program__set_type(prog, prog->sec_def->prog_type);
-		bpf_program__set_expected_attach_type(prog, attach_type);
+		bpf_program__set_expected_attach_type(prog,
-		if (prog_type == BPF_PROG_TYPE_TRACING ||
+				prog->sec_def->expected_attach_type);
-		    prog_type == BPF_PROG_TYPE_EXT)
+
+		if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING ||
+		    prog->sec_def->prog_type == BPF_PROG_TYPE_EXT)
 			prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
 	}
 
@@ -6179,6 +6250,7 @@ bool bpf_program__is_##NAME(const struct bpf_program *prog)	\
 }								\
 
 BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
+BPF_PROG_TYPE_FNS(lsm, BPF_PROG_TYPE_LSM);
 BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
 BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
 BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
@@ -6202,23 +6274,32 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	prog->expected_attach_type = type;
 }
 
-#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, btf, atype) \
+#define BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype_optional,	    \
-	{ string, sizeof(string) - 1, ptype, eatype, is_attachable, btf, atype }
+			  attachable, attach_btf)			    \
+	{								    \
+		.sec = string,						    \
+		.len = sizeof(string) - 1,				    \
+		.prog_type = ptype,					    \
+		.expected_attach_type = eatype,				    \
+		.is_exp_attach_type_optional = eatype_optional,		    \
+		.is_attachable = attachable,				    \
+		.is_attach_btf = attach_btf,				    \
+	}
 
 /* Programs that can NOT be attached. */
 #define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0)
 
 /* Programs that can be attached. */
 #define BPF_APROG_SEC(string, ptype, atype) \
-	BPF_PROG_SEC_IMPL(string, ptype, 0, 1, 0, atype)
+	BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0)
 
 /* Programs that must specify expected attach type at load time. */
 #define BPF_EAPROG_SEC(string, ptype, eatype) \
-	BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, 0, eatype)
+	BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 1, 0)
 
 /* Programs that use BTF to identify attach point */
 #define BPF_PROG_BTF(string, ptype, eatype) \
-	BPF_PROG_SEC_IMPL(string, ptype, eatype, 0, 1, 0)
+	BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1)
 
 /* Programs that can be attached but attach type can't be identified by section
  * name. Kept for backward compatibility.
@@ -6232,11 +6313,6 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	__VA_ARGS__							    \
 }
 
-struct bpf_sec_def;
-
-typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec,
-					struct bpf_program *prog);
-
 static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
 				      struct bpf_program *prog);
 static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
@@ -6245,17 +6321,8 @@ static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
 				      struct bpf_program *prog);
 static struct bpf_link *attach_trace(const struct bpf_sec_def *sec,
 				     struct bpf_program *prog);
-
+static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
-struct bpf_sec_def {
+				   struct bpf_program *prog);
-	const char *sec;
-	size_t len;
-	enum bpf_prog_type prog_type;
-	enum bpf_attach_type expected_attach_type;
-	bool is_attachable;
-	bool is_attach_btf;
-	enum bpf_attach_type attach_type;
-	attach_fn_t attach_fn;
-};
 
 static const struct bpf_sec_def section_defs[] = {
 	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
@@ -6284,6 +6351,10 @@ static const struct bpf_sec_def section_defs[] = {
 		.expected_attach_type = BPF_TRACE_FENTRY,
 		.is_attach_btf = true,
 		.attach_fn = attach_trace),
+	SEC_DEF("fmod_ret/", TRACING,
+		.expected_attach_type = BPF_MODIFY_RETURN,
+		.is_attach_btf = true,
+		.attach_fn = attach_trace),
 	SEC_DEF("fexit/", TRACING,
 		.expected_attach_type = BPF_TRACE_FEXIT,
 		.is_attach_btf = true,
@@ -6291,6 +6362,10 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("freplace/", EXT,
 		.is_attach_btf = true,
 		.attach_fn = attach_trace),
+	SEC_DEF("lsm/", LSM,
+		.is_attach_btf = true,
+		.expected_attach_type = BPF_LSM_MAC,
+		.attach_fn = attach_lsm),
 	BPF_PROG_SEC("xdp",			BPF_PROG_TYPE_XDP),
 	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
 	BPF_PROG_SEC("lwt_in",			BPF_PROG_TYPE_LWT_IN),
@@ -6553,6 +6628,7 @@ invalid_prog:
 }
 
 #define BTF_TRACE_PREFIX "btf_trace_"
+#define BTF_LSM_PREFIX "bpf_lsm_"
 #define BTF_MAX_NAME_SIZE 128
 
 static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
@@ -6580,9 +6656,15 @@ static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name,
 	if (attach_type == BPF_TRACE_RAW_TP)
 		err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name,
 					      BTF_KIND_TYPEDEF);
+	else if (attach_type == BPF_LSM_MAC)
+		err = find_btf_by_prefix_kind(btf, BTF_LSM_PREFIX, name,
+					      BTF_KIND_FUNC);
 	else
 		err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
 
+	if (err <= 0)
+		pr_warn("%s is not found in vmlinux BTF\n", name);
+
 	return err;
 }
 
@@ -6655,8 +6737,6 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog)
 			err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux,
 						    name + section_defs[i].len,
 						    attach_type);
-		if (err <= 0)
-			pr_warn("%s is not found in vmlinux BTF\n", name);
 		return err;
 	}
 	pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name);
@@ -6677,7 +6757,7 @@ int libbpf_attach_type_by_name(const char *name,
 			continue;
 		if (!section_defs[i].is_attachable)
 			return -EINVAL;
-		*attach_type = section_defs[i].attach_type;
+		*attach_type = section_defs[i].expected_attach_type;
 		return 0;
 	}
 	pr_debug("failed to guess attach type based on ELF section name '%s'\n", name);
@@ -6736,6 +6816,17 @@ void *bpf_map__priv(const struct bpf_map *map)
 	return map ? map->priv : ERR_PTR(-EINVAL);
 }
 
+int bpf_map__set_initial_value(struct bpf_map *map,
+			       const void *data, size_t size)
+{
+	if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG ||
+	    size != map->def.value_size || map->fd >= 0)
+		return -EINVAL;
+
+	memcpy(map->mmaped, data, size);
+	return 0;
+}
+
 bool bpf_map__is_offload_neutral(const struct bpf_map *map)
 {
 	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
@@ -6926,9 +7017,17 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 struct bpf_link {
 	int (*detach)(struct bpf_link *link);
 	int (*destroy)(struct bpf_link *link);
+	char *pin_path;		/* NULL, if not pinned */
+	int fd;			/* hook FD, -1 if not applicable */
 	bool disconnected;
 };
 
+/* Replace link's underlying BPF program with the new one */
+int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog)
+{
+	return bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL);
+}
+
 /* Release "ownership" of underlying BPF resource (typically, BPF program
  * attached to some BPF hook, e.g., tracepoint, kprobe, etc). Disconnected
  * link, when destructed through bpf_link__destroy() call won't attempt to
@@ -6955,26 +7054,109 @@ int bpf_link__destroy(struct bpf_link *link)
 		err = link->detach(link);
 	if (link->destroy)
 		link->destroy(link);
+	if (link->pin_path)
+		free(link->pin_path);
 	free(link);
 
 	return err;
 }
 
-struct bpf_link_fd {
+int bpf_link__fd(const struct bpf_link *link)
-	struct bpf_link link; /* has to be at the top of struct */
+{
-	int fd; /* hook FD */
+	return link->fd;
-};
+}
+
+const char *bpf_link__pin_path(const struct bpf_link *link)
+{
+	return link->pin_path;
+}
+
+static int bpf_link__detach_fd(struct bpf_link *link)
+{
+	return close(link->fd);
+}
+
+struct bpf_link *bpf_link__open(const char *path)
+{
+	struct bpf_link *link;
+	int fd;
+
+	fd = bpf_obj_get(path);
+	if (fd < 0) {
+		fd = -errno;
+		pr_warn("failed to open link at %s: %d\n", path, fd);
+		return ERR_PTR(fd);
+	}
+
+	link = calloc(1, sizeof(*link));
+	if (!link) {
+		close(fd);
+		return ERR_PTR(-ENOMEM);
+	}
+	link->detach = &bpf_link__detach_fd;
+	link->fd = fd;
+
+	link->pin_path = strdup(path);
+	if (!link->pin_path) {
+		bpf_link__destroy(link);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return link;
+}
+
+int bpf_link__pin(struct bpf_link *link, const char *path)
+{
+	int err;
+
+	if (link->pin_path)
+		return -EBUSY;
+	err = make_parent_dir(path);
+	if (err)
+		return err;
+	err = check_path(path);
+	if (err)
+		return err;
+
+	link->pin_path = strdup(path);
+	if (!link->pin_path)
+		return -ENOMEM;
+
+	if (bpf_obj_pin(link->fd, link->pin_path)) {
+		err = -errno;
+		zfree(&link->pin_path);
+		return err;
+	}
+
+	pr_debug("link fd=%d: pinned at %s\n", link->fd, link->pin_path);
+	return 0;
+}
+
+int bpf_link__unpin(struct bpf_link *link)
+{
+	int err;
+
+	if (!link->pin_path)
+		return -EINVAL;
+
+	err = unlink(link->pin_path);
+	if (err != 0)
+		return -errno;
+
+	pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path);
+	zfree(&link->pin_path);
+	return 0;
+}
 
 static int bpf_link__detach_perf_event(struct bpf_link *link)
 {
-	struct bpf_link_fd *l = (void *)link;
 	int err;
 
-	err = ioctl(l->fd, PERF_EVENT_IOC_DISABLE, 0);
+	err = ioctl(link->fd, PERF_EVENT_IOC_DISABLE, 0);
 	if (err)
 		err = -errno;
 
-	close(l->fd);
+	close(link->fd);
 	return err;
 }
 
@@ -6982,7 +7164,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 						int pfd)
 {
 	char errmsg[STRERR_BUFSIZE];
-	struct bpf_link_fd *link;
+	struct bpf_link *link;
 	int prog_fd, err;
 
 	if (pfd < 0) {
@@ -7000,7 +7182,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 	link = calloc(1, sizeof(*link));
 	if (!link)
 		return ERR_PTR(-ENOMEM);
-	link->link.detach = &bpf_link__detach_perf_event;
+	link->detach = &bpf_link__detach_perf_event;
 	link->fd = pfd;
 
 	if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
@@ -7019,7 +7201,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 			   libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		return ERR_PTR(err);
 	}
-	return (struct bpf_link *)link;
+	return link;
 }
 
 /*
@@ -7307,18 +7489,11 @@ out:
 	return link;
 }
 
-static int bpf_link__detach_fd(struct bpf_link *link)
-{
-	struct bpf_link_fd *l = (void *)link;
-
-	return close(l->fd);
-}
-
 struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 						    const char *tp_name)
 {
 	char errmsg[STRERR_BUFSIZE];
-	struct bpf_link_fd *link;
+	struct bpf_link *link;
 	int prog_fd, pfd;
 
 	prog_fd = bpf_program__fd(prog);
@@ -7331,7 +7506,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 	link = calloc(1, sizeof(*link));
 	if (!link)
 		return ERR_PTR(-ENOMEM);
-	link->link.detach = &bpf_link__detach_fd;
+	link->detach = &bpf_link__detach_fd;
 
 	pfd = bpf_raw_tracepoint_open(tp_name, prog_fd);
 	if (pfd < 0) {
@@ -7343,7 +7518,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 		return ERR_PTR(pfd);
 	}
 	link->fd = pfd;
-	return (struct bpf_link *)link;
+	return link;
 }
 
 static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
@@ -7354,10 +7529,11 @@ static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
 	return bpf_program__attach_raw_tracepoint(prog, tp_name);
 }
 
-struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
+/* Common logic for all BPF program types that attach to a btf_id */
+static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
 {
 	char errmsg[STRERR_BUFSIZE];
-	struct bpf_link_fd *link;
+	struct bpf_link *link;
 	int prog_fd, pfd;
 
 	prog_fd = bpf_program__fd(prog);
@@ -7370,13 +7546,13 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
 	link = calloc(1, sizeof(*link));
 	if (!link)
 		return ERR_PTR(-ENOMEM);
-	link->link.detach = &bpf_link__detach_fd;
+	link->detach = &bpf_link__detach_fd;
 
 	pfd = bpf_raw_tracepoint_open(NULL, prog_fd);
 	if (pfd < 0) {
 		pfd = -errno;
 		free(link);
-		pr_warn("program '%s': failed to attach to trace: %s\n",
+		pr_warn("program '%s': failed to attach: %s\n",
 			bpf_program__title(prog, false),
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
 		return ERR_PTR(pfd);
@@ -7385,12 +7561,62 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
 	return (struct bpf_link *)link;
 }
 
+struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
+{
+	return bpf_program__attach_btf_id(prog);
+}
+
+struct bpf_link *bpf_program__attach_lsm(struct bpf_program *prog)
+{
+	return bpf_program__attach_btf_id(prog);
+}
+
 static struct bpf_link *attach_trace(const struct bpf_sec_def *sec,
 				     struct bpf_program *prog)
 {
 	return bpf_program__attach_trace(prog);
 }
 
+static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
+				   struct bpf_program *prog)
+{
+	return bpf_program__attach_lsm(prog);
+}
+
+struct bpf_link *
+bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
+{
+	enum bpf_attach_type attach_type;
+	char errmsg[STRERR_BUFSIZE];
+	struct bpf_link *link;
+	int prog_fd, link_fd;
+
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		pr_warn("program '%s': can't attach before loaded\n",
+			bpf_program__title(prog, false));
+		return ERR_PTR(-EINVAL);
+	}
+
+	link = calloc(1, sizeof(*link));
+	if (!link)
+		return ERR_PTR(-ENOMEM);
+	link->detach = &bpf_link__detach_fd;
+
+	attach_type = bpf_program__get_expected_attach_type(prog);
+	link_fd = bpf_link_create(prog_fd, cgroup_fd, attach_type, NULL);
+	if (link_fd < 0) {
+		link_fd = -errno;
+		free(link);
+		pr_warn("program '%s': failed to attach to cgroup: %s\n",
+			bpf_program__title(prog, false),
+			libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
+		return ERR_PTR(link_fd);
+	}
+	link->fd = link_fd;
+	return link;
+}
+
 struct bpf_link *bpf_program__attach(struct bpf_program *prog)
 {
 	const struct bpf_sec_def *sec_def;
@@ -7404,10 +7630,9 @@ struct bpf_link *bpf_program__attach(struct bpf_program *prog)
 
 static int bpf_link__detach_struct_ops(struct bpf_link *link)
 {
-	struct bpf_link_fd *l = (void *)link;
 	__u32 zero = 0;
 
-	if (bpf_map_delete_elem(l->fd, &zero))
+	if (bpf_map_delete_elem(link->fd, &zero))
 		return -errno;
 
 	return 0;
@@ -7416,7 +7641,7 @@ static int bpf_link__detach_struct_ops(struct bpf_link *link)
 struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
 {
 	struct bpf_struct_ops *st_ops;
-	struct bpf_link_fd *link;
+	struct bpf_link *link;
 	__u32 i, zero = 0;
 	int err;
 
@@ -7448,10 +7673,10 @@ struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
 		return ERR_PTR(err);
 	}
 
-	link->link.detach = bpf_link__detach_struct_ops;
+	link->detach = bpf_link__detach_struct_ops;
 	link->fd = map->fd;
 
-	return (struct bpf_link *)link;
+	return link;
 }
 
 enum bpf_perf_event_ret
@@ -8132,6 +8357,31 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear)
 	}
 }
 
+int bpf_program__set_attach_target(struct bpf_program *prog,
+				   int attach_prog_fd,
+				   const char *attach_func_name)
+{
+	int btf_id;
+
+	if (!prog || attach_prog_fd < 0 || !attach_func_name)
+		return -EINVAL;
+
+	if (attach_prog_fd)
+		btf_id = libbpf_find_prog_btf_id(attach_func_name,
+						 attach_prog_fd);
+	else
+		btf_id = __find_vmlinux_btf_id(prog->obj->btf_vmlinux,
+					       attach_func_name,
+					       prog->expected_attach_type);
+
+	if (btf_id < 0)
+		return btf_id;
+
+	prog->attach_btf_id = btf_id;
+	prog->attach_prog_fd = attach_prog_fd;
+	return 0;
+}
+
 int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz)
 {
 	int err = 0, n, len, start, end = -1;

src/libbpf.h

@@ -219,6 +219,13 @@ LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
 
 struct bpf_link;
 
+LIBBPF_API struct bpf_link *bpf_link__open(const char *path);
+LIBBPF_API int bpf_link__fd(const struct bpf_link *link);
+LIBBPF_API const char *bpf_link__pin_path(const struct bpf_link *link);
+LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path);
+LIBBPF_API int bpf_link__unpin(struct bpf_link *link);
+LIBBPF_API int bpf_link__update_program(struct bpf_link *link,
+					struct bpf_program *prog);
 LIBBPF_API void bpf_link__disconnect(struct bpf_link *link);
 LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
 
@@ -240,11 +247,17 @@ bpf_program__attach_tracepoint(struct bpf_program *prog,
 LIBBPF_API struct bpf_link *
 bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 				   const char *tp_name);
-
 LIBBPF_API struct bpf_link *
 bpf_program__attach_trace(struct bpf_program *prog);
+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);
+
 struct bpf_map;
+
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
+
 struct bpf_insn;
 
 /*
@@ -316,6 +329,7 @@ LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_lsm(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
@@ -334,10 +348,15 @@ LIBBPF_API void
 bpf_program__set_expected_attach_type(struct bpf_program *prog,
 				      enum bpf_attach_type type);
 
+LIBBPF_API int
+bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd,
+			       const char *attach_func_name);
+
 LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_lsm(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
@@ -398,6 +417,8 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
 				 bpf_map_clear_priv_t clear_priv);
 LIBBPF_API void *bpf_map__priv(const struct bpf_map *map);
+LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map,
+					  const void *data, size_t size);
 LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
 LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries);
 LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
@@ -435,7 +456,15 @@ struct xdp_link_info {
 	__u8 attach_mode;
 };
 
+struct bpf_xdp_set_link_opts {
+	size_t sz;
+	int old_fd;
+};
+#define bpf_xdp_set_link_opts__last_field old_fd
+
 LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
+					const struct bpf_xdp_set_link_opts *opts);
 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);

src/libbpf.map

@@ -235,3 +235,22 @@ LIBBPF_0.0.7 {
 		btf__align_of;
 		libbpf_find_kernel_btf;
 } LIBBPF_0.0.6;
+
+LIBBPF_0.0.8 {
+	global:
+		bpf_link__fd;
+		bpf_link__open;
+		bpf_link__pin;
+		bpf_link__pin_path;
+		bpf_link__unpin;
+		bpf_link__update_program;
+		bpf_link_create;
+		bpf_link_update;
+		bpf_map__set_initial_value;
+		bpf_program__attach_cgroup;
+		bpf_program__attach_lsm;
+		bpf_program__is_lsm;
+		bpf_program__set_attach_target;
+		bpf_program__set_lsm;
+		bpf_set_link_xdp_fd_opts;
+} LIBBPF_0.0.7;

src/libbpf_probes.c

@@ -108,6 +108,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_TRACING:
 	case BPF_PROG_TYPE_STRUCT_OPS:
 	case BPF_PROG_TYPE_EXT:
+	case BPF_PROG_TYPE_LSM:
 	default:
 		break;
 	}

src/netlink.c

@@ -132,7 +132,8 @@ done:
 	return ret;
 }
 
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
+					 __u32 flags)
 {
 	int sock, seq = 0, ret;
 	struct nlattr *nla, *nla_xdp;
@@ -141,7 +142,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		struct ifinfomsg ifinfo;
 		char             attrbuf[64];
 	} req;
-	__u32 nl_pid;
+	__u32 nl_pid = 0;
 
 	sock = libbpf_netlink_open(&nl_pid);
 	if (sock < 0)
@@ -178,6 +179,14 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		nla->nla_len += nla_xdp->nla_len;
 	}
 
+	if (flags & XDP_FLAGS_REPLACE) {
+		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+		nla_xdp->nla_type = IFLA_XDP_EXPECTED_FD;
+		nla_xdp->nla_len = NLA_HDRLEN + sizeof(old_fd);
+		memcpy((char *)nla_xdp + NLA_HDRLEN, &old_fd, sizeof(old_fd));
+		nla->nla_len += nla_xdp->nla_len;
+	}
+
 	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
 
 	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
@@ -191,6 +200,29 @@ cleanup:
 	return ret;
 }
 
+int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
+			     const struct bpf_xdp_set_link_opts *opts)
+{
+	int old_fd = -1;
+
+	if (!OPTS_VALID(opts, bpf_xdp_set_link_opts))
+		return -EINVAL;
+
+	if (OPTS_HAS(opts, old_fd)) {
+		old_fd = OPTS_GET(opts, old_fd, -1);
+		flags |= XDP_FLAGS_REPLACE;
+	}
+
+	return __bpf_set_link_xdp_fd_replace(ifindex, fd,
+					     old_fd,
+					     flags);
+}
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+	return __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags);
+}
+
 static int __dump_link_nlmsg(struct nlmsghdr *nlh,
 			     libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {
@@ -256,7 +288,7 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 {
 	struct xdp_id_md xdp_id = {};
 	int sock, ret;
-	__u32 nl_pid;
+	__u32 nl_pid = 0;
 	__u32 mask;
 
 	if (flags & ~XDP_FLAGS_MASK || !info_size)
@@ -289,7 +321,7 @@ 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)
 {
-	if (info->attach_mode != XDP_ATTACHED_MULTI)
+	if (info->attach_mode != XDP_ATTACHED_MULTI && !flags)
 		return info->prog_id;
 	if (flags & XDP_FLAGS_DRV_MODE)
 		return info->drv_prog_id;

src/xsk.c

@@ -280,7 +280,11 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 	fill->consumer = map + off.fr.consumer;
 	fill->flags = map + off.fr.flags;
 	fill->ring = map + off.fr.desc;
-	fill->cached_cons = umem->config.fill_size;
+	fill->cached_prod = *fill->producer;
+	/* cached_cons is "size" bigger than the real consumer pointer
+	 * See xsk_prod_nb_free
+	 */
+	fill->cached_cons = *fill->consumer + umem->config.fill_size;
 
 	map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64),
 		   PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd,
@@ -297,6 +301,8 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 	comp->consumer = map + off.cr.consumer;
 	comp->flags = map + off.cr.flags;
 	comp->ring = map + off.cr.desc;
+	comp->cached_prod = *comp->producer;
+	comp->cached_cons = *comp->consumer;
 
 	*umem_ptr = umem;
 	return 0;
@@ -672,6 +678,8 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 		rx->consumer = rx_map + off.rx.consumer;
 		rx->flags = rx_map + off.rx.flags;
 		rx->ring = rx_map + off.rx.desc;
+		rx->cached_prod = *rx->producer;
+		rx->cached_cons = *rx->consumer;
 	}
 	xsk->rx = rx;
 
@@ -691,7 +699,11 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 		tx->consumer = tx_map + off.tx.consumer;
 		tx->flags = tx_map + off.tx.flags;
 		tx->ring = tx_map + off.tx.desc;
-		tx->cached_cons = xsk->config.tx_size;
+		tx->cached_prod = *tx->producer;
+		/* cached_cons is r->size bigger than the real consumer pointer
+		 * See xsk_prod_nb_free
+		 */
+		tx->cached_cons = *tx->consumer + xsk->config.tx_size;
 	}
 	xsk->tx = tx;
 

travis-ci/managers/debian.sh

@@ -2,7 +2,7 @@
 
 PHASES=(${@:-SETUP RUN RUN_ASAN CLEANUP})
 DEBIAN_RELEASE="${DEBIAN_RELEASE:-testing}"
-CONT_NAME="${CONT_NAME:-debian-$DEBIAN_RELEASE-$RANDOM}"
+CONT_NAME="${CONT_NAME:-libbpf-debian-$DEBIAN_RELEASE}"
 ENV_VARS="${ENV_VARS:-}"
 DOCKER_RUN="${DOCKER_RUN:-docker run}"
 REPO_ROOT="${REPO_ROOT:-$PWD}"
@@ -30,6 +30,10 @@ for phase in "${PHASES[@]}"; do
         SETUP)
             info "Setup phase"
             info "Using Debian $DEBIAN_RELEASE"
+
+            sudo apt-get -y -o Dpkg::Options::="--force-confnew" install docker-ce
+            docker --version
+
             docker pull debian:$DEBIAN_RELEASE
             info "Starting container $CONT_NAME"
             $DOCKER_RUN -v $REPO_ROOT:/build:rw \
@@ -57,7 +61,7 @@ for phase in "${PHASES[@]}"; do
             docker_exec mkdir build install
             docker_exec ${CC:-cc} --version
             info "build"
-            docker_exec make CFLAGS="${CFLAGS}" -C ./src -B OBJDIR=../build
+	    docker_exec make -j$((4*$(nproc))) CFLAGS="${CFLAGS}" -C ./src -B OBJDIR=../build
             info "ldd build/libbpf.so:"
             docker_exec ldd build/libbpf.so
             if ! docker_exec ldd build/libbpf.so | grep -q libelf; then
@@ -65,7 +69,7 @@ for phase in "${PHASES[@]}"; do
                 exit 1
             fi
             info "install"
-            docker_exec make -C src OBJDIR=../build DESTDIR=../install install
+            docker_exec make -j$((4*$(nproc))) -C src OBJDIR=../build DESTDIR=../install install
             docker_exec rm -rf build install
             ;;
         CLEANUP)

travis-ci/managers/ubuntu.sh

@@ -17,11 +17,11 @@ cd $REPO_ROOT
 CFLAGS="-g -O2 -Werror -Wall -fsanitize=address,undefined"
 mkdir build install
 cc --version
-make CFLAGS="${CFLAGS}" -C ./src -B OBJDIR=../build
+make -j$((4*$(nproc))) CFLAGS="${CFLAGS}" -C ./src -B OBJDIR=../build
 ldd build/libbpf.so
 if ! ldd build/libbpf.so | grep -q libelf; then
     echo "FAIL: No reference to libelf.so in libbpf.so!"
     exit 1
 fi
-make -C src OBJDIR=../build DESTDIR=../install install
+make -j$((4*$(nproc))) -C src OBJDIR=../build DESTDIR=../install install
 rm -rf build install

travis-ci/vmtest/build_latest_kernel.sh

@@ -1,8 +0,0 @@
-#!/bin/bash
-
-set -eux
-
-GIT_FETCH_DEPTH="${GIT_FETCH_DEPTH}" ${VMTEST_ROOT}/checkout_latest_kernel.sh $1
-cd $1
-cp ${VMTEST_ROOT}/configs/latest.config .config
-make -j $((4*$(nproc))) olddefconfig all

travis-ci/vmtest/build_pahole.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+set -eux
+
+CWD=$(pwd)
+REPO_PATH=$1
+PAHOLE_ORIGIN=https://git.kernel.org/pub/scm/devel/pahole/pahole.git
+
+mkdir -p ${REPO_PATH}
+cd ${REPO_PATH}
+git init
+git remote add origin ${PAHOLE_ORIGIN}
+git fetch origin
+git checkout master
+
+mkdir -p build
+cd build
+cmake -DCMAKE_BUILD_TYPE=RelWithDebInfo -D__LIB=lib ..
+make -j$((4*$(nproc))) all
+sudo make install
+
+export LD_LIBRARY_PATH=${LD_LIBRARY_PATH:-}:/usr/local/lib
+ldd $(which pahole)
+pahole --version
+

travis-ci/vmtest/build_selftests.sh

@@ -1,11 +1,16 @@
 #!/bin/bash
 
+LLVM_VER=11
 LIBBPF_PATH="${REPO_ROOT}"
 REPO_PATH="travis-ci/vmtest/bpf-next"
+
+# temporary work-around for failing tests
+rm "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c"
+
 make \
-	CLANG=clang-10 \
+	CLANG=clang-${LLVM_VER} \
-	LLC=llc-10 \
+	LLC=llc-${LLVM_VER} \
-	LLVM_STRIP=llvm-strip-10 \
+	LLVM_STRIP=llvm-strip-${LLVM_VER} \
 	VMLINUX_BTF="${VMLINUX_BTF}" \
 	-C "${REPO_ROOT}/${REPO_PATH}/tools/testing/selftests/bpf" \
 	-j $((4*$(nproc)))

travis-ci/vmtest/checkout_latest_kernel.sh

@@ -17,8 +17,8 @@ if [ ! -d "${REPO_PATH}" ]; then
 	cd ${REPO_PATH}
 	git init
 	git remote add bpf-next ${BPF_NEXT_ORIGIN}
-	git fetch --depth ${GIT_FETCH_DEPTH} bpf-next
+	for depth in 32 64 128; do
-	git reset --hard ${LINUX_SHA}
+		git fetch --depth ${depth} bpf-next
-else
+		git reset --hard ${LINUX_SHA} && break
-	cd ${REPO_PATH}
+	done
 fi

travis-ci/vmtest/configs/INDEX

@@ -1,5 +1,5 @@
 INDEX	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/INDEX
-libbpf-vmtest-rootfs-2020.01.10.tar.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/libbpf-vmtest-rootfs-2020.01.10.tar.zst
+libbpf-vmtest-rootfs-2020.03.11.tar.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/libbpf-vmtest-rootfs-2020.03.11.tar.zst
 vmlinux-5.5.0-rc6.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinux-5.5.0-rc6.zst
 vmlinux-5.5.0.zst	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinux-5.5.0.zst
 vmlinuz-5.5.0-rc6	https://libbpf-vmtest.s3-us-west-1.amazonaws.com/x86_64/vmlinuz-5.5.0-rc6

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

@@ -1,21 +1,27 @@
-mmap
+# PERMANENTLY DISABLED
-dctcp
+bpf_tcp_ca		# STRUCT_OPS is missing
-cubic
+cgroup_attach_multi	# BPF_F_REPLACE_PROG missing
-bpf_tcp_ca
+cgroup_link		# LINK_CREATE is missing
-bpf_verif_scale
+fentry_fexit		# bpf_prog_test_tracing missing
-cgroup_attach
+fentry_test		# bpf_prog_test_tracing missing
-pinning
+fexit_bpf2bpf		# freplace is missing
-send_signal_tracepoint_thread
+fexit_test		# bpf_prog_test_tracing missing
-test_syncookie
+get_stack_raw_tp	# exercising BPF verifier bug causing infinite loop
-select_reuseport
+link_pinning		# bpf_link is missing
-send_signal
+mmap			# 5.5 kernel is too permissive with re-mmaping
-sockopt_inherit
+modify_return		# fmod_ret is missing
-strobemeta_nounroll2
+ns_current_pid_tgid	# bpf_get_ns_current_pid_tgid() helper is missing
-stacktrace_build_id
+perf_branches		# bpf_read_branch_records() helper is missing
-tp_attach_query
+select_reuseport	# UDP support is missing
-tcp_rtt
+sk_assign		# bpf_sk_assign helper missing
-task_fd_query_tp
+sockmap_listen		# no listen socket supportin SOCKMAP
-stacktrace_map
+skb_ctx			# ctx_{size, }_{in, out} in BPF_PROG_TEST_RUN is missing
-test_global_funcs
+test_global_funcs	# kernel doesn't support BTF linkage=global on FUNCs
-skb_ctx
+test_lsm		# no BPF_LSM support
-fexit_bpf2bpf
+vmlinux			# hrtimer_nanosleep() signature changed incompatibly
+xdp_attach		# IFLA_XDP_EXPECTED_FD support is missing
+xdp_bpf2bpf		# freplace is missing
+
+
+# TEMPORARILY DISABLED
+send_signal		# flaky

travis-ci/vmtest/configs/blacklist/BLACKLIST-5.5.0-rc6

@@ -1,18 +0,0 @@
-mmap
-dctcp
-cubic
-bpf_tcp_ca
-bpf_verif_scale
-cgroup_attach
-pinning
-send_signal_tracepoint_thread
-test_syncookie
-select_reuseport
-send_signal
-sockopt_inherit
-strobemeta_nounroll2
-stacktrace_build_id
-tp_attach_query
-tcp_rtt
-task_fd_query_tp
-stacktrace_map

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

@@ -1,23 +1,4 @@
-mmap
+# TEMPORARILY DISABLED
-dctcp
+send_signal		# flaky
-cubic
+test_lsm		# semi-working
-bpf_tcp_ca
+sk_assign		# needs better setup in Travis CI
-bpf_verif_scale
-cgroup_attach
-pinning
-send_signal_tracepoint_thread
-test_syncookie
-select_reuseport
-send_signal
-sockopt_inherit
-strobemeta_nounroll2
-stacktrace_build_id
-tp_attach_query
-tcp_rtt
-task_fd_query_tp
-stacktrace_map
-fentry
-test_overhead
-kfree_skb
-fexit_stress
-fexit_test

travis-ci/vmtest/mkrootfs.sh

@@ -0,0 +1,148 @@
+#!/bin/bash
+
+# This script is based on drgn script for generating Arch Linux bootstrap
+# images.
+# https://github.com/osandov/drgn/blob/master/scripts/vmtest/mkrootfs.sh
+
+set -euo pipefail
+
+usage () {
+	USAGE_STRING="usage: $0 [NAME]
+       $0 -h
+
+Build an Arch Linux root filesystem image for testing libbpf in a virtual
+machine.
+
+The image is generated as a zstd-compressed tarball.
+
+This must be run as root, as most of the installation is done in a chroot.
+
+Arguments:
+  NAME   name of generated image file (default:
+         libbpf-vmtest-rootfs-\$DATE.tar.zst)
+
+Options:
+  -h     display this help message and exit"
+
+	case "$1" in
+		out)
+			echo "$USAGE_STRING"
+			exit 0
+			;;
+		err)
+			echo "$USAGE_STRING" >&2
+			exit 1
+			;;
+	esac
+}
+
+while getopts "h" OPT; do
+	case "$OPT" in
+		h)
+			usage out
+			;;
+		*)
+			usage err
+			;;
+	esac
+done
+if [[ $OPTIND -eq $# ]]; then
+	NAME="${!OPTIND}"
+elif [[ $OPTIND -gt $# ]]; then
+	NAME="libbpf-vmtest-rootfs-$(date +%Y.%m.%d).tar.zst"
+else
+	usage err
+fi
+
+pacman_conf=
+root=
+trap 'rm -rf "$pacman_conf" "$root"' EXIT
+pacman_conf="$(mktemp -p "$PWD")"
+cat > "$pacman_conf" << "EOF"
+[options]
+Architecture = x86_64
+CheckSpace
+SigLevel = Required DatabaseOptional
+[core]
+Include = /etc/pacman.d/mirrorlist
+[extra]
+Include = /etc/pacman.d/mirrorlist
+[community]
+Include = /etc/pacman.d/mirrorlist
+EOF
+root="$(mktemp -d -p "$PWD")"
+
+packages=(
+	busybox
+	# libbpf dependencies.
+	libelf
+	zlib
+	# selftests test_progs dependencies.
+	binutils
+	elfutils
+	glibc
+	# selftests test_verifier dependencies.
+	libcap
+)
+
+pacstrap -C "$pacman_conf" -cGM "$root" "${packages[@]}"
+
+# Remove unnecessary files from the chroot.
+
+# We don't need the pacman databases anymore.
+rm -rf "$root/var/lib/pacman/sync/"
+# We don't need D, Fortran, or Go.
+ rm -f "$root/usr/lib/libgdruntime."* \
+	"$root/usr/lib/libgphobos."* \
+	"$root/usr/lib/libgfortran."* \
+	"$root/usr/lib/libgo."*
+# We don't need any documentation.
+rm -rf "$root/usr/share/{doc,help,man,texinfo}"
+
+chroot "${root}" /bin/busybox --install
+
+cat > "$root/etc/fstab" << "EOF"
+dev /dev devtmpfs rw,nosuid 0 0
+proc /proc proc rw,nosuid,nodev,noexec 0 0
+sys /sys sysfs rw,nosuid,nodev,noexec 0 0
+debugfs /sys/kernel/debug debugfs mode=755,realtime 0 0
+bpffs /sys/fs/bpf bpf realtime 0 0
+EOF
+chmod 644 "$root/etc/fstab"
+
+cat > "$root/etc/inittab" << "EOF"
+::sysinit:/etc/init.d/rcS
+::ctrlaltdel:/sbin/reboot
+::shutdown:/sbin/swapoff -a
+::shutdown:/bin/umount -a -r
+::restart:/sbin/init
+EOF
+chmod 644 "$root/etc/inittab"
+
+mkdir -m 755 "$root/etc/init.d" "$root/etc/rcS.d"
+cat > "$root/etc/rcS.d/S10-mount" << "EOF"
+#!/bin/sh
+
+/bin/mount -a
+EOF
+chmod 755 "$root/etc/rcS.d/S10-mount"
+
+cat > "$root/etc/rcS.d/S40-network" << "EOF"
+#!/bin/sh
+
+ip link set lo up
+EOF
+chmod 755 "$root/etc/rcS.d/S40-network"
+
+cat > "$root/etc/init.d/rcS" << "EOF"
+#!/bin/sh
+
+for path in /etc/rcS.d/S*; do
+	[ -x "$path" ] && "$path"
+done
+EOF
+chmod 755 "$root/etc/init.d/rcS"
+
+chmod 755 "$root"
+tar -C "$root" -c . | zstd -T0 -19 -o "$NAME"
+chmod 644 "$NAME"

travis-ci/vmtest/prepare_selftests.sh

@@ -1,11 +1,14 @@
 #!/bin/bash
 
 set -eux
-GIT_FETCH_DEPTH="${GIT_FETCH_DEPTH}" ${VMTEST_ROOT}/checkout_latest_kernel.sh $1
 
-# Fix runqslower build
+REPO_PATH=$1
-# TODO(hex@): remove after the patch is merged from bpf to bpf-next tree
+
-cd $1
+${VMTEST_ROOT}/checkout_latest_kernel.sh ${REPO_PATH}
-wget https://lore.kernel.org/bpf/908498f794661c44dca54da9e09dc0c382df6fcb.1580425879.git.hex@fb.com/t.mbox.gz
+cd ${REPO_PATH}
-gunzip t.mbox.gz
+
-git apply t.mbox
+if [[ "${KERNEL}" = 'LATEST' ]]; then
+	cp ${VMTEST_ROOT}/configs/latest.config .config
+	make -j $((4*$(nproc))) olddefconfig all
+fi
+

travis-ci/vmtest/run_selftests.sh

@@ -1,19 +1,39 @@
 #!/bin/bash
 
-set -eux
+set -euxo pipefail
+
+test_progs() {
+	echo TEST_PROGS
+	./test_progs ${BLACKLIST:+-b$BLACKLIST} ${WHITELIST:+-t$WHITELIST}
+}
+
+test_maps() {
+	echo TEST_MAPS
+	# Allow failing on older kernels.
+	./test_maps
+}
+
+test_verifier() {
+	echo TEST_VERIFIER
+	./test_verifier
+}
 
 configs_path='libbpf/travis-ci/vmtest/configs'
 blacklist_path="$configs_path/blacklist/BLACKLIST-${KERNEL}"
 if [[ -s "${blacklist_path}" ]]; then
-	BLACKLIST=$(cat "${blacklist_path}" | tr '\n' ',')
+	BLACKLIST=$(cat "${blacklist_path}" | cut -d'#' -f1 | tr -s '[:space:]' ',')
 fi
 
 whitelist_path="$configs_path/whitelist/WHITELIST-${KERNEL}"
 if [[ -s "${whitelist_path}" ]]; then
-	WHITELIST=$(cat "${whitelist_path}" | tr '\n' ',')
+	WHITELIST=$(cat "${whitelist_path}" | cut -d'#' -f1 | tr -s '[:space:]' ',')
 fi
 
 cd libbpf/selftests/bpf
 
-echo TEST_PROGS
+test_progs
-./test_progs ${BLACKLIST:+-b$BLACKLIST} ${WHITELIST:+-t$WHITELIST}
+
+if [[ "${KERNEL}" == 'latest' ]]; then
+	test_maps
+	test_verifier
+fi

travis-ci/vmtest/run_vmtest.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+set -eux
+
+VMTEST_SETUPCMD="PROJECT_NAME=${PROJECT_NAME} ./${PROJECT_NAME}/travis-ci/vmtest/run_selftests.sh"
+
+echo "KERNEL: $KERNEL"
+
+# Build latest pahole
+${VMTEST_ROOT}/build_pahole.sh travis-ci/vmtest/pahole
+
+# Install required packages
+wget -O - https://apt.llvm.org/llvm-snapshot.gpg.key | sudo apt-key add -
+echo "deb http://apt.llvm.org/bionic/ llvm-toolchain-bionic main" | sudo tee -a /etc/apt/sources.list
+sudo apt-get -qq update
+sudo apt-get -qq -y install clang lld llvm
+
+# Build selftests (and latest kernel, if necessary)
+KERNEL="${KERNEL}" ${VMTEST_ROOT}/prepare_selftests.sh travis-ci/vmtest/bpf-next
+
+# Escape whitespace characters.
+setup_cmd=$(sed 's/\([[:space:]]\)/\\\1/g' <<< "${VMTEST_SETUPCMD}")
+
+sudo adduser "${USER}" kvm
+
+if [[ "${KERNEL}" = 'LATEST' ]]; then
+  sudo -E sudo -E -u "${USER}" "${VMTEST_ROOT}/run.sh" -b travis-ci/vmtest/bpf-next -o -d ~ -s "${setup_cmd}" ~/root.img;
+else
+  sudo -E sudo -E -u "${USER}" "${VMTEST_ROOT}/run.sh" -k "${KERNEL}*" -o -d ~ -s "${setup_cmd}" ~/root.img;
+fi

travis-ci/vmtest/setup_example.sh

@@ -1,11 +0,0 @@
-#!/bin/sh
-
-# An example of a script run on VM boot.
-# To execute it in TravisCI set VMTEST_SETUPCMD env var of .travis.yml in
-# libbpf root folder, e.g.
-# VMTEST_SETUPCMD="./${PROJECT_NAME}/travis-ci/vmtest/setup_example.sh"
-
-if [ ! -z "${PROJECT_NAME}" ]; then
-	echo "Running ${PROJECT_NAME} setup scripts..."
-fi
-echo "Hello, ${USER}!"