sync: latest libbpf changes from kernel

Syncing latest libbpf commits from kernel repository.
Baseline bpf-next commit:   6f0b824a61f212e9707ff68abcabfdfa4724b811
Checkpoint bpf-next commit: 08a7491843224f8b96518fbe70d9e48163046054
Baseline bpf commit:        1d528e794f3db5d32279123a89957c44c4406a09
Checkpoint bpf commit:      22cc16c04b7893d8fc22810599f49a305d600b9e

Donglin Peng (4):
  libbpf: Add BTF permutation support for type reordering
  libbpf: Optimize type lookup with binary search for sorted BTF
  libbpf: Verify BTF sorting
  btf: Refactor the code by calling str_is_empty

Emil Tsalapatis (2):
  libbpf: Turn relo_core->sym_off unsigned
  libbpf: Move arena globals to the end of the arena

Ihor Solodrai (1):
  bpf: Migrate bpf_stream_vprintk() to KF_IMPLICIT_ARGS

Leon Hwang (2):
  bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags
  libbpf: Add BPF_F_CPU and BPF_F_ALL_CPUS flags support for percpu maps

Matt Bobrowski (1):
  bpf: add new BPF_CGROUP_ITER_CHILDREN control option

Menglong Dong (2):
  bpf: add fsession support
  libbpf: add fsession support

Thomas Gleixner (1):
  treewide: Update email address

Thomas Weißschuh (1):
  vfs: use UAPI types for new struct delegation definition

Varun R Mallya (1):
  libbpf: Fix OOB read in btf_dump_get_bitfield_value

 include/uapi/linux/bpf.h        |  11 ++
 include/uapi/linux/fcntl.h      |  10 +-
 include/uapi/linux/perf_event.h |   2 +-
 src/bpf.c                       |   1 +
 src/bpf.h                       |   8 +
 src/bpf_helpers.h               |   6 +-
 src/btf.c                       | 276 +++++++++++++++++++++++++++-----
 src/btf.h                       |  42 +++++
 src/btf_dump.c                  |   9 ++
 src/libbpf.c                    |  64 +++++---
 src/libbpf.h                    |  21 +--
 src/libbpf.map                  |   1 +
 12 files changed, 369 insertions(+), 82 deletions(-)

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

.github/workflows/test.yml

@@ -19,13 +19,8 @@ jobs:
           - kernel: 'LATEST'
             runs_on: 'ubuntu-24.04'
             arch: 'x86_64'
-            llvm-version: '18'
+            llvm-version: '21'
             pahole: 'master'
-          - kernel: 'LATEST'
-            runs_on: 'ubuntu-24.04'
-            arch: 'x86_64'
-            llvm-version: '18'
-            pahole: 'tmp.master'
     name: Linux ${{ matrix.kernel }} llvm-${{ matrix.llvm-version }}
     uses: ./.github/workflows/vmtest.yml
     with:

.mailmap

@@ -8,8 +8,10 @@ Dan Carpenter <error27@gmail.com> <dan.carpenter@oracle.com>
 Geliang Tang <geliang@kernel.org> <geliang.tang@suse.com>
 Herbert Xu <herbert@gondor.apana.org.au>
 Jakub Kicinski <kuba@kernel.org> <jakub.kicinski@netronome.com>
+Jean-Philippe Brucker <jpb@kernel.org> <jean-philippe@linaro.org>
 Jesper Dangaard Brouer <hawk@kernel.org> <brouer@redhat.com>
 Kees Cook <kees@kernel.org> <keescook@chromium.org>
+Kuniyuki Iwashima <kuniyu@google.com> <kuniyu@amazon.co.jp>
 Leo Yan <leo.yan@linux.dev> <leo.yan@linaro.org>
 Mark Starovoytov <mstarovo@pm.me> <mstarovoitov@marvell.com>
 Maxim Mikityanskiy <maxtram95@gmail.com> <maximmi@mellanox.com>

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-b4432656b36e5cc1d50a1f2dc15357543add530e
+22cc16c04b7893d8fc22810599f49a305d600b9e

CHECKPOINT-COMMIT

@@ -1 +1 @@
-9325d53fe9adff354b6a93fda5f38c165947da0f
+08a7491843224f8b96518fbe70d9e48163046054

ci/vmtest/configs/DENYLIST

@@ -1,5 +1,6 @@
 # TEMPORARY
 btf_dump/btf_dump: syntax
+bpf_cookie/perf_event
 kprobe_multi_bench_attach
 core_reloc/enum64val
 core_reloc/size___diff_sz
@@ -13,3 +14,4 @@ tc_redirect/tc_redirect_dtime # uapi breakage after net-next commit 885c36e59f46
 migrate_reuseport/IPv4 TCP_NEW_SYN_RECV reqsk_timer_handler # flaky, under investigation
 migrate_reuseport/IPv6 TCP_NEW_SYN_RECV reqsk_timer_handler # flaky, under investigation
 verify_pkcs7_sig # keeps failing
+verif_scale_pyperf600 # fails on newer Clangs

docs/program_types.rst

@@ -100,10 +100,26 @@ described in more detail in the footnotes.
 |                                           |                                        | ``uretprobe.s+`` [#uprobe]_      | Yes       |
 +                                           +                                        +----------------------------------+-----------+
 |                                           |                                        | ``usdt+`` [#usdt]_               |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``usdt.s+`` [#usdt]_             | Yes       |
 +                                           +----------------------------------------+----------------------------------+-----------+
 |                                           | ``BPF_TRACE_KPROBE_MULTI``             | ``kprobe.multi+`` [#kpmulti]_    |           |
 +                                           +                                        +----------------------------------+-----------+
 |                                           |                                        | ``kretprobe.multi+`` [#kpmulti]_ |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_KPROBE_SESSION``           | ``kprobe.session+`` [#kpmulti]_  |           |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_UPROBE_MULTI``             | ``uprobe.multi+`` [#upmul]_      |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uprobe.multi.s+`` [#upmul]_    | Yes       |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uretprobe.multi+`` [#upmul]_   |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uretprobe.multi.s+`` [#upmul]_ | Yes       |
++                                           +----------------------------------------+----------------------------------+-----------+
+|                                           | ``BPF_TRACE_UPROBE_SESSION``           | ``uprobe.session+`` [#upmul]_    |           |
++                                           +                                        +----------------------------------+-----------+
+|                                           |                                        | ``uprobe.session.s+`` [#upmul]_  | Yes       |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
 | ``BPF_PROG_TYPE_LIRC_MODE2``              | ``BPF_LIRC_MODE2``                     | ``lirc_mode2``                   |           |
 +-------------------------------------------+----------------------------------------+----------------------------------+-----------+
@@ -219,6 +235,8 @@ described in more detail in the footnotes.
              non-negative integer.
 .. [#ksyscall] The ``ksyscall`` attach format is ``ksyscall/<syscall>``.
 .. [#uprobe] The ``uprobe`` attach format is ``uprobe[.s]/<path>:<function>[+<offset>]``.
+.. [#upmul] The ``uprobe.multi`` attach format is ``uprobe.multi[.s]/<path>:<function-pattern>``
+            where ``function-pattern`` supports ``*`` and ``?`` wildcards.
 .. [#usdt] The ``usdt`` attach format is ``usdt/<path>:<provider>:<name>``.
 .. [#kpmulti] The ``kprobe.multi`` attach format is ``kprobe.multi/<pattern>`` where ``pattern``
               supports ``*`` and ``?`` wildcards. Valid characters for pattern are

fuzz/readme.md

@@ -0,0 +1,58 @@
+# About fuzzing
+
+Fuzzing is done by [OSS-Fuzz](https://google.github.io/oss-fuzz/).
+It works by creating a project-specific binary that combines fuzzer
+itself and a project provided entry point named
+`LLVMFuzzerTestOneInput()`. When invoked, this executable either
+searches for new test cases or runs an existing test case.
+
+File `fuzz/bpf-object-fuzzer.c` defines an entry point for the robot:
+- robot supplies bytes supposed to be an ELF file;
+- wrapper invokes `bpf_object__open_mem()` to process these bytes.
+
+File `scripts/build-fuzzers.sh` provides a recipe for fuzzer
+infrastructure on how to build the executable described above (see
+[here](https://github.com/google/oss-fuzz/tree/master/projects/libbpf)).
+
+# Reproducing fuzzing errors
+
+## Official way
+
+OSS-Fuzz project describes error reproduction steps in the official
+[documentation](https://google.github.io/oss-fuzz/advanced-topics/reproducing/).
+Suppose you received an email linking to the fuzzer generated test
+case, or got one as an artifact of the `CIFuzz` job (e.g. like
+[here](https://github.com/libbpf/libbpf/actions/runs/16375110681)).
+Actions to reproduce the error locally are:
+
+```sh
+git clone --depth=1 https://github.com/google/oss-fuzz.git
+cd oss-fuzz
+python infra/helper.py pull_images
+python infra/helper.py build_image libbpf
+python infra/helper.py build_fuzzers --sanitizer address libbpf <path-to-libbpf-checkout>
+python infra/helper.py reproduce libbpf bpf-object-fuzzer <path-to-test-case>
+```
+
+`<path-to-test-case>` is usually a `crash-<many-hex-digits>` file w/o
+extension, CI job wraps it into zip archive and attaches as an artifact.
+
+To recompile after some fixes, repeat the `build_fuzzers` and
+`reproduce` steps after modifying source code in
+`<path-to-libbpf-checkout>`.
+
+Note: the `build_fuzzers` step creates a binary
+`build/out/libbpf/bpf-object-fuzzer`, it can be executed directly if
+your environment is compatible.
+
+## Simple way
+
+From the project root:
+
+```sh
+SKIP_LIBELF_REBUILD=1 scripts/build-fuzzers.sh
+out/bpf-object-fuzzer <path-to-test-case>
+```
+
+`out/bpf-object-fuzzer` is the fuzzer executable described earlier,
+can be run with gdb etc.

include/linux/filter.h

@@ -123,6 +123,14 @@
 	BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_VALUE, 0, 0,	\
 			      MAP_FD, VALUE_OFF)
 
+#define BPF_JMP_REG(OP, DST, SRC, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_OP(OP) | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 #define BPF_JMP_IMM(OP, DST, IMM, OFF)				\
 	((struct bpf_insn) {					\
 		.code = BPF_JMP | BPF_OP(OP) | BPF_K,		\

include/linux/kernel.h

@@ -43,4 +43,18 @@
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
 #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
 
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#define be32_to_cpu(x)		__builtin_bswap32(x)
+#define cpu_to_be32(x)		__builtin_bswap32(x)
+#define be64_to_cpu(x)		__builtin_bswap64(x)
+#define cpu_to_be64(x)		__builtin_bswap64(x)
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+#define be32_to_cpu(x)		(x)
+#define cpu_to_be32(x)		(x)
+#define be64_to_cpu(x)		(x)
+#define cpu_to_be64(x)		(x)
+#else
+# error "__BYTE_ORDER__ undefined or invalid"
+#endif
+
 #endif

include/linux/types.h

@@ -30,4 +30,7 @@ struct list_head {
 	struct list_head *next, *prev;
 };
 
+/* needed on Android/Termux, where this linux/types.h is included by other include files */
+typedef unsigned __bitwise __poll_t;
+
 #endif

include/uapi/linux/bpf.h

@@ -5,8 +5,8 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
-#ifndef _UAPI__LINUX_BPF_H__
-#define _UAPI__LINUX_BPF_H__
+#ifndef __LINUX_BPF_H__
+#define __LINUX_BPF_H__
 
 #include <linux/types.h>
 #include <linux/bpf_common.h>
@@ -119,6 +119,14 @@ enum bpf_cgroup_iter_order {
 	BPF_CGROUP_ITER_DESCENDANTS_PRE,	/* walk descendants in pre-order. */
 	BPF_CGROUP_ITER_DESCENDANTS_POST,	/* walk descendants in post-order. */
 	BPF_CGROUP_ITER_ANCESTORS_UP,		/* walk ancestors upward. */
+	/*
+	 * Walks the immediate children of the specified parent
+	 * cgroup_subsys_state. Unlike BPF_CGROUP_ITER_DESCENDANTS_PRE,
+	 * BPF_CGROUP_ITER_DESCENDANTS_POST, and BPF_CGROUP_ITER_ANCESTORS_UP
+	 * the iterator does not include the specified parent as one of the
+	 * returned iterator elements.
+	 */
+	BPF_CGROUP_ITER_CHILDREN,
 };
 
 union bpf_iter_link_info {
@@ -450,6 +458,7 @@ union bpf_iter_link_info {
  *		* **struct bpf_map_info**
  *		* **struct bpf_btf_info**
  *		* **struct bpf_link_info**
+ *		* **struct bpf_token_info**
  *
  *	Return
  *		Returns zero on success. On error, -1 is returned and *errno*
@@ -906,6 +915,27 @@ union bpf_iter_link_info {
  *		A new file descriptor (a nonnegative integer), or -1 if an
  *		error occurred (in which case, *errno* is set appropriately).
  *
+ * BPF_PROG_STREAM_READ_BY_FD
+ *	Description
+ *		Read data of a program's BPF stream. The program is identified
+ *		by *prog_fd*, and the stream is identified by the *stream_id*.
+ *		The data is copied to a buffer pointed to by *stream_buf*, and
+ *		filled less than or equal to *stream_buf_len* bytes.
+ *
+ *	Return
+ *		Number of bytes read from the stream on success, or -1 if an
+ *		error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_PROG_ASSOC_STRUCT_OPS
+ * 	Description
+ * 		Associate a BPF program with a struct_ops map. The struct_ops
+ * 		map is identified by *map_fd* and the BPF program is
+ * 		identified by *prog_fd*.
+ *
+ * 	Return
+ * 		0 on success or -1 if an error occurred (in which case,
+ * 		*errno* is set appropriately).
+ *
  * NOTES
  *	eBPF objects (maps and programs) can be shared between processes.
  *
@@ -961,6 +991,8 @@ enum bpf_cmd {
 	BPF_LINK_DETACH,
 	BPF_PROG_BIND_MAP,
 	BPF_TOKEN_CREATE,
+	BPF_PROG_STREAM_READ_BY_FD,
+	BPF_PROG_ASSOC_STRUCT_OPS,
 	__MAX_BPF_CMD,
 };
 
@@ -1013,6 +1045,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_USER_RINGBUF,
 	BPF_MAP_TYPE_CGRP_STORAGE,
 	BPF_MAP_TYPE_ARENA,
+	BPF_MAP_TYPE_INSN_ARRAY,
 	__MAX_BPF_MAP_TYPE
 };
 
@@ -1120,6 +1153,7 @@ enum bpf_attach_type {
 	BPF_NETKIT_PEER,
 	BPF_TRACE_KPROBE_SESSION,
 	BPF_TRACE_UPROBE_SESSION,
+	BPF_TRACE_FSESSION,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1359,6 +1393,8 @@ enum {
 	BPF_NOEXIST	= 1, /* create new element if it didn't exist */
 	BPF_EXIST	= 2, /* update existing element */
 	BPF_F_LOCK	= 4, /* spin_lock-ed map_lookup/map_update */
+	BPF_F_CPU	= 8, /* cpu flag for percpu maps, upper 32-bit of flags is a cpu number */
+	BPF_F_ALL_CPUS	= 16, /* update value across all CPUs for percpu maps */
 };
 
 /* flags for BPF_MAP_CREATE command */
@@ -1417,6 +1453,9 @@ enum {
 
 /* Do not translate kernel bpf_arena pointers to user pointers */
 	BPF_F_NO_USER_CONV	= (1U << 18),
+
+/* Enable BPF ringbuf overwrite mode */
+	BPF_F_RB_OVERWRITE	= (1U << 19),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -1463,6 +1502,11 @@ struct bpf_stack_build_id {
 
 #define BPF_OBJ_NAME_LEN 16U
 
+enum {
+	BPF_STREAM_STDOUT = 1,
+	BPF_STREAM_STDERR = 2,
+};
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -1504,6 +1548,12 @@ union bpf_attr {
 		 * If provided, map_flags should have BPF_F_TOKEN_FD flag set.
 		 */
 		__s32	map_token_fd;
+
+		/* Hash of the program that has exclusive access to the map.
+		 */
+		__aligned_u64 excl_prog_hash;
+		/* Size of the passed excl_prog_hash. */
+		__u32 excl_prog_hash_size;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM and BPF_MAP_FREEZE commands */
@@ -1587,6 +1637,16 @@ union bpf_attr {
 		 * continuous.
 		 */
 		__u32		fd_array_cnt;
+		/* Pointer to a buffer containing the signature of the BPF
+		 * program.
+		 */
+		__aligned_u64   signature;
+		/* Size of the signature buffer in bytes. */
+		__u32 		signature_size;
+		/* ID of the kernel keyring to be used for signature
+		 * verification.
+		 */
+		__s32		keyring_id;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -1794,6 +1854,13 @@ union bpf_attr {
 				};
 				__u64		expected_revision;
 			} netkit;
+			struct {
+				union {
+					__u32	relative_fd;
+					__u32	relative_id;
+				};
+				__u64		expected_revision;
+			} cgroup;
 		};
 	} link_create;
 
@@ -1842,6 +1909,19 @@ union bpf_attr {
 		__u32		bpffs_fd;
 	} token_create;
 
+	struct {
+		__aligned_u64	stream_buf;
+		__u32		stream_buf_len;
+		__u32		stream_id;
+		__u32		prog_fd;
+	} prog_stream_read;
+
+	struct {
+		__u32		map_fd;
+		__u32		prog_fd;
+		__u32		flags;
+	} prog_assoc_struct_ops;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
@@ -2056,6 +2136,7 @@ union bpf_attr {
  * 		for updates resulting in a null checksum the value is set to
  * 		**CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates
  * 		that the modified header field is part of the pseudo-header.
+ * 		Flag **BPF_F_IPV6** should be set for IPv6 packets.
  *
  * 		This helper works in combination with **bpf_csum_diff**\ (),
  * 		which does not update the checksum in-place, but offers more
@@ -2402,7 +2483,7 @@ union bpf_attr {
  * 		into it. An example is available in file
  * 		*samples/bpf/trace_output_user.c* in the Linux kernel source
  * 		tree (the eBPF program counterpart is in
- * 		*samples/bpf/trace_output_kern.c*).
+ *		*samples/bpf/trace_output.bpf.c*).
  *
  * 		**bpf_perf_event_output**\ () achieves better performance
  * 		than **bpf_trace_printk**\ () for sharing data with user
@@ -4842,7 +4923,7 @@ union bpf_attr {
  *
  *		**-ENOENT** if the bpf_local_storage cannot be found.
  *
- * long bpf_d_path(struct path *path, char *buf, u32 sz)
+ * long bpf_d_path(const struct path *path, char *buf, u32 sz)
  *	Description
  *		Return full path for given **struct path** object, which
  *		needs to be the kernel BTF *path* object. The path is
@@ -4972,6 +5053,9 @@ union bpf_attr {
  * 		the netns switch takes place from ingress to ingress without
  * 		going through the CPU's backlog queue.
  *
+ * 		*skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during
+ * 		the netns switch.
+ *
  * 		The *flags* argument is reserved and must be 0. The helper is
  * 		currently only supported for tc BPF program types at the
  * 		ingress hook and for veth and netkit target device types. The
@@ -5566,7 +5650,7 @@ union bpf_attr {
  *	Return
  *		*sk* if casting is valid, or **NULL** otherwise.
  *
- * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ * long bpf_dynptr_from_mem(void *data, u64 size, u64 flags, struct bpf_dynptr *ptr)
  *	Description
  *		Get a dynptr to local memory *data*.
  *
@@ -5609,7 +5693,7 @@ union bpf_attr {
  *	Return
  *		Nothing. Always succeeds.
  *
- * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags)
+ * long bpf_dynptr_read(void *dst, u64 len, const struct bpf_dynptr *src, u64 offset, u64 flags)
  *	Description
  *		Read *len* bytes from *src* into *dst*, starting from *offset*
  *		into *src*.
@@ -5619,7 +5703,7 @@ union bpf_attr {
  *		of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
  *		*flags* is not 0.
  *
- * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags)
+ * long bpf_dynptr_write(const struct bpf_dynptr *dst, u64 offset, void *src, u64 len, u64 flags)
  *	Description
  *		Write *len* bytes from *src* into *dst*, starting from *offset*
  *		into *dst*.
@@ -5640,7 +5724,7 @@ union bpf_attr {
  *		is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs,
  *		other errors correspond to errors returned by **bpf_skb_store_bytes**\ ().
  *
- * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len)
+ * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u64 offset, u64 len)
  *	Description
  *		Get a pointer to the underlying dynptr data.
  *
@@ -6069,6 +6153,7 @@ enum {
 	BPF_F_PSEUDO_HDR		= (1ULL << 4),
 	BPF_F_MARK_MANGLED_0		= (1ULL << 5),
 	BPF_F_MARK_ENFORCE		= (1ULL << 6),
+	BPF_F_IPV6			= (1ULL << 7),
 };
 
 /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
@@ -6178,6 +6263,7 @@ enum {
 	BPF_RB_RING_SIZE = 1,
 	BPF_RB_CONS_POS = 2,
 	BPF_RB_PROD_POS = 3,
+	BPF_RB_OVERWRITE_POS = 4,
 };
 
 /* BPF ring buffer constants */
@@ -6629,6 +6715,8 @@ struct bpf_map_info {
 	__u32 btf_value_type_id;
 	__u32 btf_vmlinux_id;
 	__u64 map_extra;
+	__aligned_u64 hash;
+	__u32 hash_size;
 } __attribute__((aligned(8)));
 
 struct bpf_btf_info {
@@ -6648,11 +6736,15 @@ struct bpf_link_info {
 		struct {
 			__aligned_u64 tp_name; /* in/out: tp_name buffer ptr */
 			__u32 tp_name_len;     /* in/out: tp_name buffer len */
+			__u32 :32;
+			__u64 cookie;
 		} raw_tracepoint;
 		struct {
 			__u32 attach_type;
 			__u32 target_obj_id; /* prog_id for PROG_EXT, otherwise btf object id */
 			__u32 target_btf_id; /* BTF type id inside the object */
+			__u32 :32;
+			__u64 cookie;
 		} tracing;
 		struct {
 			__u64 cgroup_id;
@@ -6763,6 +6855,13 @@ struct bpf_link_info {
 	};
 } __attribute__((aligned(8)));
 
+struct bpf_token_info {
+	__u64 allowed_cmds;
+	__u64 allowed_maps;
+	__u64 allowed_progs;
+	__u64 allowed_attachs;
+} __attribute__((aligned(8)));
+
 /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
  * by user and intended to be used by socket (e.g. to bind to, depends on
  * attach type).
@@ -7134,6 +7233,8 @@ enum {
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
 	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
 	SK_BPF_CB_FLAGS		= 1009, /* Get or set sock ops flags in socket */
+	SK_BPF_BYPASS_PROT_MEM	= 1010, /* Get or Set sk->sk_bypass_prot_mem */
+
 };
 
 enum {
@@ -7370,6 +7471,10 @@ struct bpf_timer {
 	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
+struct bpf_task_work {
+	__u64 __opaque;
+} __attribute__((aligned(8)));
+
 struct bpf_wq {
 	__u64 __opaque[2];
 } __attribute__((aligned(8)));
@@ -7575,4 +7680,24 @@ enum bpf_kfunc_flags {
 	BPF_F_PAD_ZEROS = (1ULL << 0),
 };
 
-#endif /* _UAPI__LINUX_BPF_H__ */
+/*
+ * Values of a BPF_MAP_TYPE_INSN_ARRAY entry must be of this type.
+ *
+ * Before the map is used the orig_off field should point to an
+ * instruction inside the program being loaded. The other fields
+ * must be set to 0.
+ *
+ * After the program is loaded, the xlated_off will be adjusted
+ * by the verifier to point to the index of the original instruction
+ * in the xlated program. If the instruction is deleted, it will
+ * be set to (u32)-1. The jitted_off will be set to the corresponding
+ * offset in the jitted image of the program.
+ */
+struct bpf_insn_array_value {
+	__u32 orig_off;
+	__u32 xlated_off;
+	__u32 jitted_off;
+	__u32 :32;
+};
+
+#endif /* __LINUX_BPF_H__ */

include/uapi/linux/bpf_common.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI__LINUX_BPF_COMMON_H__
-#define _UAPI__LINUX_BPF_COMMON_H__
+#ifndef __LINUX_BPF_COMMON_H__
+#define __LINUX_BPF_COMMON_H__
 
 /* Instruction classes */
 #define BPF_CLASS(code) ((code) & 0x07)
@@ -54,4 +54,4 @@
 #define BPF_MAXINSNS 4096
 #endif
 
-#endif /* _UAPI__LINUX_BPF_COMMON_H__ */
+#endif /* __LINUX_BPF_COMMON_H__ */

include/uapi/linux/btf.h

@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /* Copyright (c) 2018 Facebook */
-#ifndef _UAPI__LINUX_BTF_H__
-#define _UAPI__LINUX_BTF_H__
+#ifndef __LINUX_BTF_H__
+#define __LINUX_BTF_H__
 
 #include <linux/types.h>
 
@@ -198,4 +198,4 @@ struct btf_enum64 {
 	__u32	val_hi32;
 };
 
-#endif /* _UAPI__LINUX_BTF_H__ */
+#endif /* __LINUX_BTF_H__ */

include/uapi/linux/fcntl.h

@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_FCNTL_H
+#define _LINUX_FCNTL_H
+
+#include <asm/fcntl.h>
+#include <linux/openat2.h>
+#include <linux/types.h>
+
+#define F_SETLEASE	(F_LINUX_SPECIFIC_BASE + 0)
+#define F_GETLEASE	(F_LINUX_SPECIFIC_BASE + 1)
+
+/*
+ * Request nofications on a directory.
+ * See below for events that may be notified.
+ */
+#define F_NOTIFY	(F_LINUX_SPECIFIC_BASE + 2)
+
+#define F_DUPFD_QUERY	(F_LINUX_SPECIFIC_BASE + 3)
+
+/* Was the file just created? */
+#define F_CREATED_QUERY	(F_LINUX_SPECIFIC_BASE + 4)
+
+/*
+ * Cancel a blocking posix lock; internal use only until we expose an
+ * asynchronous lock api to userspace:
+ */
+#define F_CANCELLK	(F_LINUX_SPECIFIC_BASE + 5)
+
+/* Create a file descriptor with FD_CLOEXEC set. */
+#define F_DUPFD_CLOEXEC	(F_LINUX_SPECIFIC_BASE + 6)
+
+/*
+ * Set and get of pipe page size array
+ */
+#define F_SETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 7)
+#define F_GETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 8)
+
+/*
+ * Set/Get seals
+ */
+#define F_ADD_SEALS	(F_LINUX_SPECIFIC_BASE + 9)
+#define F_GET_SEALS	(F_LINUX_SPECIFIC_BASE + 10)
+
+/*
+ * Types of seals
+ */
+#define F_SEAL_SEAL	0x0001	/* prevent further seals from being set */
+#define F_SEAL_SHRINK	0x0002	/* prevent file from shrinking */
+#define F_SEAL_GROW	0x0004	/* prevent file from growing */
+#define F_SEAL_WRITE	0x0008	/* prevent writes */
+#define F_SEAL_FUTURE_WRITE	0x0010  /* prevent future writes while mapped */
+#define F_SEAL_EXEC	0x0020  /* prevent chmod modifying exec bits */
+/* (1U << 31) is reserved for signed error codes */
+
+/*
+ * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
+ * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
+ * the specific file.
+ */
+#define F_GET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 11)
+#define F_SET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 12)
+#define F_GET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 13)
+#define F_SET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 14)
+
+/*
+ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
+ * used to clear any hints previously set.
+ */
+#define RWH_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NONE	1
+#define RWH_WRITE_LIFE_SHORT	2
+#define RWH_WRITE_LIFE_MEDIUM	3
+#define RWH_WRITE_LIFE_LONG	4
+#define RWH_WRITE_LIFE_EXTREME	5
+
+/*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
+
+/* Set/Get delegations */
+#define F_GETDELEG		(F_LINUX_SPECIFIC_BASE + 15)
+#define F_SETDELEG		(F_LINUX_SPECIFIC_BASE + 16)
+
+/* Argument structure for F_GETDELEG and F_SETDELEG */
+struct delegation {
+	__u32	d_flags;	/* Must be 0 */
+	__u16	d_type;		/* F_RDLCK, F_WRLCK, F_UNLCK */
+	__u16	__pad;		/* Must be 0 */
+};
+
+/*
+ * Types of directory notifications that may be requested.
+ */
+#define DN_ACCESS	0x00000001	/* File accessed */
+#define DN_MODIFY	0x00000002	/* File modified */
+#define DN_CREATE	0x00000004	/* File created */
+#define DN_DELETE	0x00000008	/* File removed */
+#define DN_RENAME	0x00000010	/* File renamed */
+#define DN_ATTRIB	0x00000020	/* File changed attibutes */
+#define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
+
+/* Reserved kernel ranges [-100], [-10000, -40000]. */
+#define AT_FDCWD		-100    /* Special value for dirfd used to
+					   indicate openat should use the
+					   current working directory. */
+
+/*
+ * The concept of process and threads in userland and the kernel is a confusing
+ * one - within the kernel every thread is a 'task' with its own individual PID,
+ * however from userland's point of view threads are grouped by a single PID,
+ * which is that of the 'thread group leader', typically the first thread
+ * spawned.
+ *
+ * To cut the Gideon knot, for internal kernel usage, we refer to
+ * PIDFD_SELF_THREAD to refer to the current thread (or task from a kernel
+ * perspective), and PIDFD_SELF_THREAD_GROUP to refer to the current thread
+ * group leader...
+ */
+#define PIDFD_SELF_THREAD		-10000 /* Current thread. */
+#define PIDFD_SELF_THREAD_GROUP		-10001 /* Current thread group leader. */
+
+#define FD_PIDFS_ROOT			-10002 /* Root of the pidfs filesystem */
+#define FD_NSFS_ROOT			-10003 /* Root of the nsfs filesystem */
+#define FD_INVALID			-10009 /* Invalid file descriptor: -10000 - EBADF = -10009 */
+
+/* Generic flags for the *at(2) family of syscalls. */
+
+/* Reserved for per-syscall flags	0xff. */
+#define AT_SYMLINK_NOFOLLOW		0x100   /* Do not follow symbolic
+						   links. */
+/* Reserved for per-syscall flags	0x200 */
+#define AT_SYMLINK_FOLLOW		0x400   /* Follow symbolic links. */
+#define AT_NO_AUTOMOUNT			0x800	/* Suppress terminal automount
+						   traversal. */
+#define AT_EMPTY_PATH			0x1000	/* Allow empty relative
+						   pathname to operate on dirfd
+						   directly. */
+/*
+ * These flags are currently statx(2)-specific, but they could be made generic
+ * in the future and so they should not be used for other per-syscall flags.
+ */
+#define AT_STATX_SYNC_TYPE		0x6000	/* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT		0x0000	/* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC		0x2000	/* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC		0x4000	/* - Don't sync attributes with the server */
+
+#define AT_RECURSIVE			0x8000	/* Apply to the entire subtree */
+
+/*
+ * Per-syscall flags for the *at(2) family of syscalls.
+ *
+ * These are flags that are so syscall-specific that a user passing these flags
+ * to the wrong syscall is so "clearly wrong" that we can safely call such
+ * usage "undefined behaviour".
+ *
+ * For example, the constants AT_REMOVEDIR and AT_EACCESS have the same value.
+ * AT_EACCESS is meaningful only to faccessat, while AT_REMOVEDIR is meaningful
+ * only to unlinkat. The two functions do completely different things and
+ * therefore, the flags can be allowed to overlap. For example, passing
+ * AT_REMOVEDIR to faccessat would be undefined behavior and thus treating it
+ * equivalent to AT_EACCESS is valid undefined behavior.
+ *
+ * Note for implementers: When picking a new per-syscall AT_* flag, try to
+ * reuse already existing flags first. This leaves us with as many unused bits
+ * as possible, so we can use them for generic bits in the future if necessary.
+ */
+
+/* Flags for renameat2(2) (must match legacy RENAME_* flags). */
+#define AT_RENAME_NOREPLACE	0x0001
+#define AT_RENAME_EXCHANGE	0x0002
+#define AT_RENAME_WHITEOUT	0x0004
+
+/* Flag for faccessat(2). */
+#define AT_EACCESS		0x200	/* Test access permitted for
+                                           effective IDs, not real IDs.  */
+/* Flag for unlinkat(2). */
+#define AT_REMOVEDIR		0x200   /* Remove directory instead of
+                                           unlinking file.  */
+/* Flags for name_to_handle_at(2). */
+#define AT_HANDLE_FID		0x200	/* File handle is needed to compare
+					   object identity and may not be
+					   usable with open_by_handle_at(2). */
+#define AT_HANDLE_MNT_ID_UNIQUE	0x001	/* Return the u64 unique mount ID. */
+#define AT_HANDLE_CONNECTABLE	0x002	/* Request a connectable file handle */
+
+/* Flags for execveat2(2). */
+#define AT_EXECVE_CHECK		0x10000	/* Only perform a check if execution
+					   would be allowed. */
+
+#endif /* _LINUX_FCNTL_H */

include/uapi/linux/if_link.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_IF_LINK_H
-#define _UAPI_LINUX_IF_LINK_H
+#ifndef _LINUX_IF_LINK_H
+#define _LINUX_IF_LINK_H
 
 #include <linux/types.h>
 #include <linux/netlink.h>
@@ -378,6 +378,9 @@ enum {
 	IFLA_GRO_IPV4_MAX_SIZE,
 	IFLA_DPLL_PIN,
 	IFLA_MAX_PACING_OFFLOAD_HORIZON,
+	IFLA_NETNS_IMMUTABLE,
+	IFLA_HEADROOM,
+	IFLA_TAILROOM,
 	__IFLA_MAX
 };
 
@@ -1396,6 +1399,8 @@ enum {
 	IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
 	IFLA_VXLAN_LOCALBYPASS,
 	IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */
+	IFLA_VXLAN_RESERVED_BITS,
+	IFLA_VXLAN_MC_ROUTE,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -1437,6 +1442,7 @@ enum {
 	IFLA_GENEVE_TTL_INHERIT,
 	IFLA_GENEVE_DF,
 	IFLA_GENEVE_INNER_PROTO_INHERIT,
+	IFLA_GENEVE_PORT_RANGE,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
@@ -1449,6 +1455,11 @@ enum ifla_geneve_df {
 	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
 };
 
+struct ifla_geneve_port_range {
+	__be16 low;
+	__be16 high;
+};
+
 /* Bareudp section  */
 enum {
 	IFLA_BAREUDP_UNSPEC,
@@ -1526,6 +1537,7 @@ enum {
 	IFLA_BOND_MISSED_MAX,
 	IFLA_BOND_NS_IP6_TARGET,
 	IFLA_BOND_COUPLED_CONTROL,
+	IFLA_BOND_BROADCAST_NEIGH,
 	__IFLA_BOND_MAX,
 };
 
@@ -1554,6 +1566,7 @@ enum {
 	IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
 	IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
 	IFLA_BOND_SLAVE_PRIO,
+	IFLA_BOND_SLAVE_ACTOR_PORT_PRIO,
 	__IFLA_BOND_SLAVE_MAX,
 };
 
@@ -1960,6 +1973,7 @@ struct ifla_rmnet_flags {
 enum {
 	IFLA_MCTP_UNSPEC,
 	IFLA_MCTP_NET,
+	IFLA_MCTP_PHYS_BINDING,
 	__IFLA_MCTP_MAX,
 };
 
@@ -1977,4 +1991,19 @@ enum {
 
 #define IFLA_DSA_MAX	(__IFLA_DSA_MAX - 1)
 
-#endif /* _UAPI_LINUX_IF_LINK_H */
+/* OVPN section */
+
+enum ovpn_mode {
+	OVPN_MODE_P2P,
+	OVPN_MODE_MP,
+};
+
+enum {
+	IFLA_OVPN_UNSPEC,
+	IFLA_OVPN_MODE,
+	__IFLA_OVPN_MAX,
+};
+
+#define IFLA_OVPN_MAX	(__IFLA_OVPN_MAX - 1)
+
+#endif /* _LINUX_IF_LINK_H */

include/uapi/linux/if_xdp.h

@@ -79,6 +79,7 @@ struct xdp_mmap_offsets {
 #define XDP_UMEM_COMPLETION_RING	6
 #define XDP_STATISTICS			7
 #define XDP_OPTIONS			8
+#define XDP_MAX_TX_SKB_BUDGET		9
 
 struct xdp_umem_reg {
 	__u64 addr; /* Start of packet data area */

include/uapi/linux/netdev.h

@@ -2,9 +2,10 @@
 /* Do not edit directly, auto-generated from: */
 /*	Documentation/netlink/specs/netdev.yaml */
 /* YNL-GEN uapi header */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
 
-#ifndef _UAPI_LINUX_NETDEV_H
-#define _UAPI_LINUX_NETDEV_H
+#ifndef _LINUX_NETDEV_H
+#define _LINUX_NETDEV_H
 
 #define NETDEV_FAMILY_NAME	"netdev"
 #define NETDEV_FAMILY_VERSION	1
@@ -77,6 +78,12 @@ enum netdev_qstats_scope {
 	NETDEV_QSTATS_SCOPE_QUEUE = 1,
 };
 
+enum netdev_napi_threaded {
+	NETDEV_NAPI_THREADED_DISABLED,
+	NETDEV_NAPI_THREADED_ENABLED,
+	NETDEV_NAPI_THREADED_BUSY_POLL,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
@@ -134,6 +141,7 @@ enum {
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
 	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
+	NETDEV_A_NAPI_THREADED,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
@@ -219,6 +227,7 @@ enum {
 	NETDEV_CMD_QSTATS_GET,
 	NETDEV_CMD_BIND_RX,
 	NETDEV_CMD_NAPI_SET,
+	NETDEV_CMD_BIND_TX,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
@@ -227,4 +236,4 @@ enum {
 #define NETDEV_MCGRP_MGMT	"mgmt"
 #define NETDEV_MCGRP_PAGE_POOL	"page-pool"
 
-#endif /* _UAPI_LINUX_NETDEV_H */
+#endif /* _LINUX_NETDEV_H */

include/uapi/linux/netlink.h

@@ -1,8 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI__LINUX_NETLINK_H
-#define _UAPI__LINUX_NETLINK_H
+#ifndef __LINUX_NETLINK_H
+#define __LINUX_NETLINK_H
 
-#include <linux/kernel.h>
+#include <linux/const.h>
 #include <linux/socket.h> /* for __kernel_sa_family_t */
 #include <linux/types.h>
 
@@ -20,7 +20,7 @@
 #define NETLINK_CONNECTOR	11
 #define NETLINK_NETFILTER	12	/* netfilter subsystem */
 #define NETLINK_IP6_FW		13
-#define NETLINK_DNRTMSG		14	/* DECnet routing messages */
+#define NETLINK_DNRTMSG		14	/* DECnet routing messages (obsolete) */
 #define NETLINK_KOBJECT_UEVENT	15	/* Kernel messages to userspace */
 #define NETLINK_GENERIC		16
 /* leave room for NETLINK_DM (DM Events) */
@@ -41,12 +41,20 @@ struct sockaddr_nl {
        	__u32		nl_groups;	/* multicast groups mask */
 };
 
+/**
+ * struct nlmsghdr - fixed format metadata header of Netlink messages
+ * @nlmsg_len:   Length of message including header
+ * @nlmsg_type:  Message content type
+ * @nlmsg_flags: Additional flags
+ * @nlmsg_seq:   Sequence number
+ * @nlmsg_pid:   Sending process port ID
+ */
 struct nlmsghdr {
-	__u32		nlmsg_len;	/* Length of message including header */
-	__u16		nlmsg_type;	/* Message content */
-	__u16		nlmsg_flags;	/* Additional flags */
-	__u32		nlmsg_seq;	/* Sequence number */
-	__u32		nlmsg_pid;	/* Sending process port ID */
+	__u32		nlmsg_len;
+	__u16		nlmsg_type;
+	__u16		nlmsg_flags;
+	__u32		nlmsg_seq;
+	__u32		nlmsg_pid;
 };
 
 /* Flags values */
@@ -54,7 +62,7 @@ struct nlmsghdr {
 #define NLM_F_REQUEST		0x01	/* It is request message. 	*/
 #define NLM_F_MULTI		0x02	/* Multipart message, terminated by NLMSG_DONE */
 #define NLM_F_ACK		0x04	/* Reply with ack, with zero or error code */
-#define NLM_F_ECHO		0x08	/* Echo this request 		*/
+#define NLM_F_ECHO		0x08	/* Receive resulting notifications */
 #define NLM_F_DUMP_INTR		0x10	/* Dump was inconsistent due to sequence change */
 #define NLM_F_DUMP_FILTERED	0x20	/* Dump was filtered as requested */
 
@@ -72,6 +80,7 @@ struct nlmsghdr {
 
 /* Modifiers to DELETE request */
 #define NLM_F_NONREC	0x100	/* Do not delete recursively	*/
+#define NLM_F_BULK	0x200	/* Delete multiple objects	*/
 
 /* Flags for ACK message */
 #define NLM_F_CAPPED	0x100	/* request was capped */
@@ -91,9 +100,10 @@ struct nlmsghdr {
 #define NLMSG_HDRLEN	 ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
 #define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN)
 #define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len))
-#define NLMSG_DATA(nlh)  ((void*)(((char*)nlh) + NLMSG_LENGTH(0)))
+#define NLMSG_DATA(nlh)  ((void *)(((char *)nlh) + NLMSG_HDRLEN))
 #define NLMSG_NEXT(nlh,len)	 ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
-				  (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len)))
+				  (struct nlmsghdr *)(((char *)(nlh)) + \
+				  NLMSG_ALIGN((nlh)->nlmsg_len)))
 #define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \
 			   (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \
 			   (nlh)->nlmsg_len <= (len))
@@ -129,6 +139,11 @@ struct nlmsgerr {
  * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to
  *	be used - in the success case - to identify a created
  *	object or operation or similar (binary)
+ * @NLMSGERR_ATTR_POLICY: policy for a rejected attribute
+ * @NLMSGERR_ATTR_MISS_TYPE: type of a missing required attribute,
+ *	%NLMSGERR_ATTR_MISS_NEST will not be present if the attribute was
+ *	missing at the message level
+ * @NLMSGERR_ATTR_MISS_NEST: offset of the nest where attribute was missing
  * @__NLMSGERR_ATTR_MAX: number of attributes
  * @NLMSGERR_ATTR_MAX: highest attribute number
  */
@@ -137,6 +152,9 @@ enum nlmsgerr_attrs {
 	NLMSGERR_ATTR_MSG,
 	NLMSGERR_ATTR_OFFS,
 	NLMSGERR_ATTR_COOKIE,
+	NLMSGERR_ATTR_POLICY,
+	NLMSGERR_ATTR_MISS_TYPE,
+	NLMSGERR_ATTR_MISS_NEST,
 
 	__NLMSGERR_ATTR_MAX,
 	NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1
@@ -249,4 +267,117 @@ struct nla_bitfield32 {
 	__u32 selector;
 };
 
-#endif /* _UAPI__LINUX_NETLINK_H */
+/*
+ * policy descriptions - it's specific to each family how this is used
+ * Normally, it should be retrieved via a dump inside another attribute
+ * specifying where it applies.
+ */
+
+/**
+ * enum netlink_attribute_type - type of an attribute
+ * @NL_ATTR_TYPE_INVALID: unused
+ * @NL_ATTR_TYPE_FLAG: flag attribute (present/not present)
+ * @NL_ATTR_TYPE_U8: 8-bit unsigned attribute
+ * @NL_ATTR_TYPE_U16: 16-bit unsigned attribute
+ * @NL_ATTR_TYPE_U32: 32-bit unsigned attribute
+ * @NL_ATTR_TYPE_U64: 64-bit unsigned attribute
+ * @NL_ATTR_TYPE_S8: 8-bit signed attribute
+ * @NL_ATTR_TYPE_S16: 16-bit signed attribute
+ * @NL_ATTR_TYPE_S32: 32-bit signed attribute
+ * @NL_ATTR_TYPE_S64: 64-bit signed attribute
+ * @NL_ATTR_TYPE_BINARY: binary data, min/max length may be specified
+ * @NL_ATTR_TYPE_STRING: string, min/max length may be specified
+ * @NL_ATTR_TYPE_NUL_STRING: NUL-terminated string,
+ *	min/max length may be specified
+ * @NL_ATTR_TYPE_NESTED: nested, i.e. the content of this attribute
+ *	consists of sub-attributes. The nested policy and maxtype
+ *	inside may be specified.
+ * @NL_ATTR_TYPE_NESTED_ARRAY: nested array, i.e. the content of this
+ *	attribute contains sub-attributes whose type is irrelevant
+ *	(just used to separate the array entries) and each such array
+ *	entry has attributes again, the policy for those inner ones
+ *	and the corresponding maxtype may be specified.
+ * @NL_ATTR_TYPE_BITFIELD32: &struct nla_bitfield32 attribute
+ * @NL_ATTR_TYPE_SINT: 32-bit or 64-bit signed attribute, aligned to 4B
+ * @NL_ATTR_TYPE_UINT: 32-bit or 64-bit unsigned attribute, aligned to 4B
+ */
+enum netlink_attribute_type {
+	NL_ATTR_TYPE_INVALID,
+
+	NL_ATTR_TYPE_FLAG,
+
+	NL_ATTR_TYPE_U8,
+	NL_ATTR_TYPE_U16,
+	NL_ATTR_TYPE_U32,
+	NL_ATTR_TYPE_U64,
+
+	NL_ATTR_TYPE_S8,
+	NL_ATTR_TYPE_S16,
+	NL_ATTR_TYPE_S32,
+	NL_ATTR_TYPE_S64,
+
+	NL_ATTR_TYPE_BINARY,
+	NL_ATTR_TYPE_STRING,
+	NL_ATTR_TYPE_NUL_STRING,
+
+	NL_ATTR_TYPE_NESTED,
+	NL_ATTR_TYPE_NESTED_ARRAY,
+
+	NL_ATTR_TYPE_BITFIELD32,
+
+	NL_ATTR_TYPE_SINT,
+	NL_ATTR_TYPE_UINT,
+};
+
+/**
+ * enum netlink_policy_type_attr - policy type attributes
+ * @NL_POLICY_TYPE_ATTR_UNSPEC: unused
+ * @NL_POLICY_TYPE_ATTR_TYPE: type of the attribute,
+ *	&enum netlink_attribute_type (U32)
+ * @NL_POLICY_TYPE_ATTR_MIN_VALUE_S: minimum value for signed
+ *	integers (S64)
+ * @NL_POLICY_TYPE_ATTR_MAX_VALUE_S: maximum value for signed
+ *	integers (S64)
+ * @NL_POLICY_TYPE_ATTR_MIN_VALUE_U: minimum value for unsigned
+ *	integers (U64)
+ * @NL_POLICY_TYPE_ATTR_MAX_VALUE_U: maximum value for unsigned
+ *	integers (U64)
+ * @NL_POLICY_TYPE_ATTR_MIN_LENGTH: minimum length for binary
+ *	attributes, no minimum if not given (U32)
+ * @NL_POLICY_TYPE_ATTR_MAX_LENGTH: maximum length for binary
+ *	attributes, no maximum if not given (U32)
+ * @NL_POLICY_TYPE_ATTR_POLICY_IDX: sub policy for nested and
+ *	nested array types (U32)
+ * @NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE: maximum sub policy
+ *	attribute for nested and nested array types, this can
+ *	in theory be < the size of the policy pointed to by
+ *	the index, if limited inside the nesting (U32)
+ * @NL_POLICY_TYPE_ATTR_BITFIELD32_MASK: valid mask for the
+ *	bitfield32 type (U32)
+ * @NL_POLICY_TYPE_ATTR_MASK: mask of valid bits for unsigned integers (U64)
+ * @NL_POLICY_TYPE_ATTR_PAD: pad attribute for 64-bit alignment
+ *
+ * @__NL_POLICY_TYPE_ATTR_MAX: number of attributes
+ * @NL_POLICY_TYPE_ATTR_MAX: highest attribute number
+ */
+enum netlink_policy_type_attr {
+	NL_POLICY_TYPE_ATTR_UNSPEC,
+	NL_POLICY_TYPE_ATTR_TYPE,
+	NL_POLICY_TYPE_ATTR_MIN_VALUE_S,
+	NL_POLICY_TYPE_ATTR_MAX_VALUE_S,
+	NL_POLICY_TYPE_ATTR_MIN_VALUE_U,
+	NL_POLICY_TYPE_ATTR_MAX_VALUE_U,
+	NL_POLICY_TYPE_ATTR_MIN_LENGTH,
+	NL_POLICY_TYPE_ATTR_MAX_LENGTH,
+	NL_POLICY_TYPE_ATTR_POLICY_IDX,
+	NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE,
+	NL_POLICY_TYPE_ATTR_BITFIELD32_MASK,
+	NL_POLICY_TYPE_ATTR_PAD,
+	NL_POLICY_TYPE_ATTR_MASK,
+
+	/* keep last */
+	__NL_POLICY_TYPE_ATTR_MAX,
+	NL_POLICY_TYPE_ATTR_MAX = __NL_POLICY_TYPE_ATTR_MAX - 1
+};
+
+#endif /* __LINUX_NETLINK_H */

include/uapi/linux/openat2.h

@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_OPENAT2_H
+#define _LINUX_OPENAT2_H
+
+#include <linux/types.h>
+
+/*
+ * Arguments for how openat2(2) should open the target path. If only @flags and
+ * @mode are non-zero, then openat2(2) operates very similarly to openat(2).
+ *
+ * However, unlike openat(2), unknown or invalid bits in @flags result in
+ * -EINVAL rather than being silently ignored. @mode must be zero unless one of
+ * {O_CREAT, O_TMPFILE} are set.
+ *
+ * @flags: O_* flags.
+ * @mode: O_CREAT/O_TMPFILE file mode.
+ * @resolve: RESOLVE_* flags.
+ */
+struct open_how {
+	__u64 flags;
+	__u64 mode;
+	__u64 resolve;
+};
+
+/* how->resolve flags for openat2(2). */
+#define RESOLVE_NO_XDEV		0x01 /* Block mount-point crossings
+					(includes bind-mounts). */
+#define RESOLVE_NO_MAGICLINKS	0x02 /* Block traversal through procfs-style
+					"magic-links". */
+#define RESOLVE_NO_SYMLINKS	0x04 /* Block traversal through all symlinks
+					(implies OEXT_NO_MAGICLINKS) */
+#define RESOLVE_BENEATH		0x08 /* Block "lexical" trickery like
+					"..", symlinks, and absolute
+					paths which escape the dirfd. */
+#define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
+					be scoped inside the dirfd
+					(similar to chroot(2)). */
+#define RESOLVE_CACHED		0x20 /* Only complete if resolution can be
+					completed through cached lookup. May
+					return -EAGAIN if that's not
+					possible. */
+
+#endif /* _LINUX_OPENAT2_H */

include/uapi/linux/pkt_cls.h

@@ -16,9 +16,40 @@ enum {
 	TCA_ACT_STATS,
 	TCA_ACT_PAD,
 	TCA_ACT_COOKIE,
+	TCA_ACT_FLAGS,
+	TCA_ACT_HW_STATS,
+	TCA_ACT_USED_HW_STATS,
+	TCA_ACT_IN_HW_COUNT,
 	__TCA_ACT_MAX
 };
 
+/* See other TCA_ACT_FLAGS_ * flags in include/net/act_api.h. */
+#define TCA_ACT_FLAGS_NO_PERCPU_STATS (1 << 0) /* Don't use percpu allocator for
+						* actions stats.
+						*/
+#define TCA_ACT_FLAGS_SKIP_HW	(1 << 1) /* don't offload action to HW */
+#define TCA_ACT_FLAGS_SKIP_SW	(1 << 2) /* don't use action in SW */
+
+/* tca HW stats type
+ * When user does not pass the attribute, he does not care.
+ * It is the same as if he would pass the attribute with
+ * all supported bits set.
+ * In case no bits are set, user is not interested in getting any HW statistics.
+ */
+#define TCA_ACT_HW_STATS_IMMEDIATE (1 << 0) /* Means that in dump, user
+					     * gets the current HW stats
+					     * state from the device
+					     * queried at the dump time.
+					     */
+#define TCA_ACT_HW_STATS_DELAYED (1 << 1) /* Means that in dump, user gets
+					   * HW stats that might be out of date
+					   * for some time, maybe couple of
+					   * seconds. This is the case when
+					   * driver polls stats updates
+					   * periodically or when it gets async
+					   * stats update from the device.
+					   */
+
 #define TCA_ACT_MAX __TCA_ACT_MAX
 #define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
 #define TCA_ACT_MAX_PRIO 32
@@ -63,12 +94,53 @@ enum {
 #define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
 #define TC_ACT_EXT_OPCODE_MAX	TC_ACT_GOTO_CHAIN
 
+/* These macros are put here for binary compatibility with userspace apps that
+ * make use of them. For kernel code and new userspace apps, use the TCA_ID_*
+ * versions.
+ */
+#define TCA_ACT_GACT 5
+#define TCA_ACT_IPT 6 /* obsoleted, can be reused */
+#define TCA_ACT_PEDIT 7
+#define TCA_ACT_MIRRED 8
+#define TCA_ACT_NAT 9
+#define TCA_ACT_XT 10
+#define TCA_ACT_SKBEDIT 11
+#define TCA_ACT_VLAN 12
+#define TCA_ACT_BPF 13
+#define TCA_ACT_CONNMARK 14
+#define TCA_ACT_SKBMOD 15
+#define TCA_ACT_CSUM 16
+#define TCA_ACT_TUNNEL_KEY 17
+#define TCA_ACT_SIMP 22
+#define TCA_ACT_IFE 25
+#define TCA_ACT_SAMPLE 26
+
 /* Action type identifiers*/
-enum {
-	TCA_ID_UNSPEC=0,
-	TCA_ID_POLICE=1,
+enum tca_id {
+	TCA_ID_UNSPEC = 0,
+	TCA_ID_POLICE = 1,
+	TCA_ID_GACT = TCA_ACT_GACT,
+	TCA_ID_IPT = TCA_ACT_IPT, /* Obsoleted, can be reused */
+	TCA_ID_PEDIT = TCA_ACT_PEDIT,
+	TCA_ID_MIRRED = TCA_ACT_MIRRED,
+	TCA_ID_NAT = TCA_ACT_NAT,
+	TCA_ID_XT = TCA_ACT_XT,
+	TCA_ID_SKBEDIT = TCA_ACT_SKBEDIT,
+	TCA_ID_VLAN = TCA_ACT_VLAN,
+	TCA_ID_BPF = TCA_ACT_BPF,
+	TCA_ID_CONNMARK = TCA_ACT_CONNMARK,
+	TCA_ID_SKBMOD = TCA_ACT_SKBMOD,
+	TCA_ID_CSUM = TCA_ACT_CSUM,
+	TCA_ID_TUNNEL_KEY = TCA_ACT_TUNNEL_KEY,
+	TCA_ID_SIMP = TCA_ACT_SIMP,
+	TCA_ID_IFE = TCA_ACT_IFE,
+	TCA_ID_SAMPLE = TCA_ACT_SAMPLE,
+	TCA_ID_CTINFO,
+	TCA_ID_MPLS,
+	TCA_ID_CT,
+	TCA_ID_GATE,
 	/* other actions go here */
-	__TCA_ID_MAX=255
+	__TCA_ID_MAX = 255
 };
 
 #define TCA_ID_MAX __TCA_ID_MAX
@@ -120,6 +192,10 @@ enum {
 	TCA_POLICE_RESULT,
 	TCA_POLICE_TM,
 	TCA_POLICE_PAD,
+	TCA_POLICE_RATE64,
+	TCA_POLICE_PEAKRATE64,
+	TCA_POLICE_PKTRATE64,
+	TCA_POLICE_PKTBURST64,
 	__TCA_POLICE_MAX
 #define TCA_POLICE_RESULT TCA_POLICE_RESULT
 };
@@ -170,16 +246,19 @@ struct tc_u32_key {
 };
 
 struct tc_u32_sel {
-	unsigned char		flags;
-	unsigned char		offshift;
-	unsigned char		nkeys;
+	/* New members MUST be added within the __struct_group() macro below. */
+	__struct_group(tc_u32_sel_hdr, hdr, /* no attrs */,
+		unsigned char		flags;
+		unsigned char		offshift;
+		unsigned char		nkeys;
 
-	__be16			offmask;
-	__u16			off;
-	short			offoff;
+		__be16			offmask;
+		__u16			off;
+		short			offoff;
 
-	short			hoff;
-	__be32			hmask;
+		short			hoff;
+		__be32			hmask;
+	);
 	struct tc_u32_key	keys[];
 };
 
@@ -286,12 +365,19 @@ enum {
 
 /* Basic filter */
 
+struct tc_basic_pcnt {
+	__u64 rcnt;
+	__u64 rhit;
+};
+
 enum {
 	TCA_BASIC_UNSPEC,
 	TCA_BASIC_CLASSID,
 	TCA_BASIC_EMATCHES,
 	TCA_BASIC_ACT,
 	TCA_BASIC_POLICE,
+	TCA_BASIC_PCNT,
+	TCA_BASIC_PAD,
 	__TCA_BASIC_MAX
 };
 
@@ -438,17 +524,79 @@ enum {
 
 	TCA_FLOWER_IN_HW_COUNT,
 
+	TCA_FLOWER_KEY_PORT_SRC_MIN,	/* be16 */
+	TCA_FLOWER_KEY_PORT_SRC_MAX,	/* be16 */
+	TCA_FLOWER_KEY_PORT_DST_MIN,	/* be16 */
+	TCA_FLOWER_KEY_PORT_DST_MAX,	/* be16 */
+
+	TCA_FLOWER_KEY_CT_STATE,	/* u16 */
+	TCA_FLOWER_KEY_CT_STATE_MASK,	/* u16 */
+	TCA_FLOWER_KEY_CT_ZONE,		/* u16 */
+	TCA_FLOWER_KEY_CT_ZONE_MASK,	/* u16 */
+	TCA_FLOWER_KEY_CT_MARK,		/* u32 */
+	TCA_FLOWER_KEY_CT_MARK_MASK,	/* u32 */
+	TCA_FLOWER_KEY_CT_LABELS,	/* u128 */
+	TCA_FLOWER_KEY_CT_LABELS_MASK,	/* u128 */
+
+	TCA_FLOWER_KEY_MPLS_OPTS,
+
+	TCA_FLOWER_KEY_HASH,		/* u32 */
+	TCA_FLOWER_KEY_HASH_MASK,	/* u32 */
+
+	TCA_FLOWER_KEY_NUM_OF_VLANS,    /* u8 */
+
+	TCA_FLOWER_KEY_PPPOE_SID,	/* be16 */
+	TCA_FLOWER_KEY_PPP_PROTO,	/* be16 */
+
+	TCA_FLOWER_KEY_L2TPV3_SID,	/* be32 */
+
+	TCA_FLOWER_L2_MISS,		/* u8 */
+
+	TCA_FLOWER_KEY_CFM,		/* nested */
+
+	TCA_FLOWER_KEY_SPI,		/* be32 */
+	TCA_FLOWER_KEY_SPI_MASK,	/* be32 */
+
+	TCA_FLOWER_KEY_ENC_FLAGS,	/* be32 */
+	TCA_FLOWER_KEY_ENC_FLAGS_MASK,	/* be32 */
+
 	__TCA_FLOWER_MAX,
 };
 
 #define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
 
+enum {
+	TCA_FLOWER_KEY_CT_FLAGS_NEW = 1 << 0, /* Beginning of a new connection. */
+	TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */
+	TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */
+	TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */
+	TCA_FLOWER_KEY_CT_FLAGS_INVALID = 1 << 4, /* Conntrack is invalid. */
+	TCA_FLOWER_KEY_CT_FLAGS_REPLY = 1 << 5, /* Packet is in the reply direction. */
+	__TCA_FLOWER_KEY_CT_FLAGS_MAX,
+};
+
 enum {
 	TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
 	TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
 					 * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
 					 * attributes
 					 */
+	TCA_FLOWER_KEY_ENC_OPTS_VXLAN,	/* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_VXLAN_
+					 * attributes
+					 */
+	TCA_FLOWER_KEY_ENC_OPTS_ERSPAN,	/* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_ERSPAN_
+					 * attributes
+					 */
+	TCA_FLOWER_KEY_ENC_OPTS_GTP,	/* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_GTP_
+					 * attributes
+					 */
+	TCA_FLOWER_KEY_ENC_OPTS_PFCP,	/* Nested
+					 * TCA_FLOWER_KEY_ENC_IPT_PFCP
+					 * attributes
+					 */
 	__TCA_FLOWER_KEY_ENC_OPTS_MAX,
 };
 
@@ -467,17 +615,105 @@ enum {
 		(__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
 
 enum {
-	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
-	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
+	TCA_FLOWER_KEY_ENC_OPT_VXLAN_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP,		/* u32 */
+	__TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX,
 };
 
+#define TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPT_ERSPAN_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER,              /* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX,            /* be32 */
+	TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR,              /* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID,             /* u8 */
+	__TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPT_GTP_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE,		/* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_GTP_QFI,			/* u8 */
+
+	__TCA_FLOWER_KEY_ENC_OPT_GTP_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GTP_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_GTP_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPT_PFCP_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE,		/* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID,		/* be64 */
+	__TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC,
+	TCA_FLOWER_KEY_MPLS_OPTS_LSE,
+	__TCA_FLOWER_KEY_MPLS_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_MPLS_OPTS_MAX (__TCA_FLOWER_KEY_MPLS_OPTS_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_UNSPEC,
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH,
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL,
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS,
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_TC,
+	TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL,
+	__TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX,
+};
+
+#define TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX \
+		(__TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
+	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
+	TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM = (1 << 2),
+	TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT = (1 << 3),
+	TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM = (1 << 4),
+	TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT = (1 << 5),
+	__TCA_FLOWER_KEY_FLAGS_MAX,
+};
+
+#define TCA_FLOWER_KEY_FLAGS_MAX (__TCA_FLOWER_KEY_FLAGS_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_CFM_OPT_UNSPEC,
+	TCA_FLOWER_KEY_CFM_MD_LEVEL,
+	TCA_FLOWER_KEY_CFM_OPCODE,
+	__TCA_FLOWER_KEY_CFM_OPT_MAX,
+};
+
+#define TCA_FLOWER_KEY_CFM_OPT_MAX (__TCA_FLOWER_KEY_CFM_OPT_MAX - 1)
+#define TCA_FLOWER_KEY_CFM_MAX	   (__TCA_FLOWER_KEY_CFM_OPT_MAX - 1)
+
+#define TCA_FLOWER_MASK_FLAGS_RANGE	(1 << 0) /* Range-based match */
+
 /* Match-all classifier */
 
+struct tc_matchall_pcnt {
+	__u64 rhit;
+};
+
 enum {
 	TCA_MATCHALL_UNSPEC,
 	TCA_MATCHALL_CLASSID,
 	TCA_MATCHALL_ACT,
 	TCA_MATCHALL_FLAGS,
+	TCA_MATCHALL_PCNT,
+	TCA_MATCHALL_PAD,
 	__TCA_MATCHALL_MAX,
 };
 

include/uapi/linux/pkt_sched.h

@@ -2,6 +2,7 @@
 #ifndef __LINUX_PKT_SCHED_H
 #define __LINUX_PKT_SCHED_H
 
+#include <linux/const.h>
 #include <linux/types.h>
 
 /* Logical priority bands not depending on specific packet scheduler.
@@ -255,6 +256,9 @@ enum {
 	TCA_RED_PARMS,
 	TCA_RED_STAB,
 	TCA_RED_MAX_P,
+	TCA_RED_FLAGS,		/* bitfield32 */
+	TCA_RED_EARLY_DROP_BLOCK, /* u32 */
+	TCA_RED_MARK_BLOCK,	/* u32 */
 	__TCA_RED_MAX,
 };
 
@@ -267,12 +271,28 @@ struct tc_red_qopt {
 	unsigned char   Wlog;		/* log(W)		*/
 	unsigned char   Plog;		/* log(P_max/(qth_max-qth_min))	*/
 	unsigned char   Scell_log;	/* cell size for idle damping */
+
+	/* This field can be used for flags that a RED-like qdisc has
+	 * historically supported. E.g. when configuring RED, it can be used for
+	 * ECN, HARDDROP and ADAPTATIVE. For SFQ it can be used for ECN,
+	 * HARDDROP. Etc. Because this field has not been validated, and is
+	 * copied back on dump, any bits besides those to which a given qdisc
+	 * has assigned a historical meaning need to be considered for free use
+	 * by userspace tools.
+	 *
+	 * Any further flags need to be passed differently, e.g. through an
+	 * attribute (such as TCA_RED_FLAGS above). Such attribute should allow
+	 * passing both recent and historic flags in one value.
+	 */
 	unsigned char	flags;
 #define TC_RED_ECN		1
 #define TC_RED_HARDDROP		2
 #define TC_RED_ADAPTATIVE	4
+#define TC_RED_NODROP		8
 };
 
+#define TC_RED_HISTORIC_FLAGS (TC_RED_ECN | TC_RED_HARDDROP | TC_RED_ADAPTATIVE)
+
 struct tc_red_xstats {
 	__u32           early;          /* Early drops */
 	__u32           pdrop;          /* Drops due to queue limits */
@@ -474,6 +494,7 @@ enum {
 	TCA_NETEM_JITTER64,
 	TCA_NETEM_SLOT,
 	TCA_NETEM_SLOT_DIST,
+	TCA_NETEM_PRNG_SEED,
 	__TCA_NETEM_MAX,
 };
 
@@ -590,6 +611,11 @@ enum {
 
 #define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1)
 
+enum {
+	TC_FP_EXPRESS = 1,
+	TC_FP_PREEMPTIBLE = 2,
+};
+
 struct tc_mqprio_qopt {
 	__u8	num_tc;
 	__u8	prio_tc_map[TC_QOPT_BITMASK + 1];
@@ -603,12 +629,23 @@ struct tc_mqprio_qopt {
 #define TC_MQPRIO_F_MIN_RATE		0x4
 #define TC_MQPRIO_F_MAX_RATE		0x8
 
+enum {
+	TCA_MQPRIO_TC_ENTRY_UNSPEC,
+	TCA_MQPRIO_TC_ENTRY_INDEX,		/* u32 */
+	TCA_MQPRIO_TC_ENTRY_FP,			/* u32 */
+
+	/* add new constants above here */
+	__TCA_MQPRIO_TC_ENTRY_CNT,
+	TCA_MQPRIO_TC_ENTRY_MAX = (__TCA_MQPRIO_TC_ENTRY_CNT - 1)
+};
+
 enum {
 	TCA_MQPRIO_UNSPEC,
 	TCA_MQPRIO_MODE,
 	TCA_MQPRIO_SHAPER,
 	TCA_MQPRIO_MIN_RATE64,
 	TCA_MQPRIO_MAX_RATE64,
+	TCA_MQPRIO_TC_ENTRY,
 	__TCA_MQPRIO_MAX,
 };
 
@@ -698,6 +735,8 @@ struct tc_codel_xstats {
 
 /* FQ_CODEL */
 
+#define FQ_CODEL_QUANTUM_MAX (1 << 20)
+
 enum {
 	TCA_FQ_CODEL_UNSPEC,
 	TCA_FQ_CODEL_TARGET,
@@ -709,6 +748,8 @@ enum {
 	TCA_FQ_CODEL_CE_THRESHOLD,
 	TCA_FQ_CODEL_DROP_BATCH_SIZE,
 	TCA_FQ_CODEL_MEMORY_LIMIT,
+	TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR,
+	TCA_FQ_CODEL_CE_THRESHOLD_MASK,
 	__TCA_FQ_CODEL_MAX
 };
 
@@ -785,15 +826,30 @@ enum {
 
 	TCA_FQ_CE_THRESHOLD,	/* DCTCP-like CE-marking threshold */
 
+	TCA_FQ_TIMER_SLACK,	/* timer slack */
+
+	TCA_FQ_HORIZON,		/* time horizon in us */
+
+	TCA_FQ_HORIZON_DROP,	/* drop packets beyond horizon, or cap their EDT */
+
+	TCA_FQ_PRIOMAP,		/* prio2band */
+
+	TCA_FQ_WEIGHTS,		/* Weights for each band */
+
+	TCA_FQ_OFFLOAD_HORIZON, /* dequeue paced packets within this horizon immediately (us units) */
+
 	__TCA_FQ_MAX
 };
 
 #define TCA_FQ_MAX	(__TCA_FQ_MAX - 1)
 
+#define FQ_BANDS 3
+#define FQ_MIN_WEIGHT 16384
+
 struct tc_fq_qd_stats {
 	__u64	gc_flows;
-	__u64	highprio_packets;
-	__u64	tcp_retrans;
+	__u64	highprio_packets;	/* obsolete */
+	__u64	tcp_retrans;		/* obsolete */
 	__u64	throttled;
 	__u64	flows_plimit;
 	__u64	pkts_too_long;
@@ -804,6 +860,12 @@ struct tc_fq_qd_stats {
 	__u32	throttled_flows;
 	__u32	unthrottle_latency_ns;
 	__u64	ce_mark;		/* packets above ce_threshold */
+	__u64	horizon_drops;
+	__u64	horizon_caps;
+	__u64	fastpath_packets;
+	__u64	band_drops[FQ_BANDS];
+	__u32	band_pkt_count[FQ_BANDS];
+	__u32	pad;
 };
 
 /* Heavy-Hitter Filter */
@@ -841,19 +903,56 @@ enum {
 	TCA_PIE_BETA,
 	TCA_PIE_ECN,
 	TCA_PIE_BYTEMODE,
+	TCA_PIE_DQ_RATE_ESTIMATOR,
 	__TCA_PIE_MAX
 };
 #define TCA_PIE_MAX   (__TCA_PIE_MAX - 1)
 
 struct tc_pie_xstats {
-	__u32 prob;             /* current probability */
-	__u32 delay;            /* current delay in ms */
-	__u32 avg_dq_rate;      /* current average dq_rate in bits/pie_time */
-	__u32 packets_in;       /* total number of packets enqueued */
-	__u32 dropped;          /* packets dropped due to pie_action */
-	__u32 overlimit;        /* dropped due to lack of space in queue */
-	__u32 maxq;             /* maximum queue size */
-	__u32 ecn_mark;         /* packets marked with ecn*/
+	__u64 prob;			/* current probability */
+	__u32 delay;			/* current delay in ms */
+	__u32 avg_dq_rate;		/* current average dq_rate in
+					 * bits/pie_time
+					 */
+	__u32 dq_rate_estimating;	/* is avg_dq_rate being calculated? */
+	__u32 packets_in;		/* total number of packets enqueued */
+	__u32 dropped;			/* packets dropped due to pie_action */
+	__u32 overlimit;		/* dropped due to lack of space
+					 * in queue
+					 */
+	__u32 maxq;			/* maximum queue size */
+	__u32 ecn_mark;			/* packets marked with ecn*/
+};
+
+/* FQ PIE */
+enum {
+	TCA_FQ_PIE_UNSPEC,
+	TCA_FQ_PIE_LIMIT,
+	TCA_FQ_PIE_FLOWS,
+	TCA_FQ_PIE_TARGET,
+	TCA_FQ_PIE_TUPDATE,
+	TCA_FQ_PIE_ALPHA,
+	TCA_FQ_PIE_BETA,
+	TCA_FQ_PIE_QUANTUM,
+	TCA_FQ_PIE_MEMORY_LIMIT,
+	TCA_FQ_PIE_ECN_PROB,
+	TCA_FQ_PIE_ECN,
+	TCA_FQ_PIE_BYTEMODE,
+	TCA_FQ_PIE_DQ_RATE_ESTIMATOR,
+	__TCA_FQ_PIE_MAX
+};
+#define TCA_FQ_PIE_MAX   (__TCA_FQ_PIE_MAX - 1)
+
+struct tc_fq_pie_xstats {
+	__u32 packets_in;	/* total number of packets enqueued */
+	__u32 dropped;		/* packets dropped due to fq_pie_action */
+	__u32 overlimit;	/* dropped due to lack of space in queue */
+	__u32 overmemory;	/* dropped due to lack of memory in queue */
+	__u32 ecn_mark;		/* packets marked with ecn */
+	__u32 new_flow_count;	/* count of new flows created by packets */
+	__u32 new_flows_len;	/* count of flows in new list */
+	__u32 old_flows_len;	/* count of flows in old list */
+	__u32 memory_usage;	/* total memory across all queues */
 };
 
 /* CBS */
@@ -880,8 +979,9 @@ struct tc_etf_qopt {
 	__s32 delta;
 	__s32 clockid;
 	__u32 flags;
-#define TC_ETF_DEADLINE_MODE_ON	BIT(0)
-#define TC_ETF_OFFLOAD_ON	BIT(1)
+#define TC_ETF_DEADLINE_MODE_ON	_BITUL(0)
+#define TC_ETF_OFFLOAD_ON	_BITUL(1)
+#define TC_ETF_SKIP_SOCK_CHECK	_BITUL(2)
 };
 
 enum {
@@ -913,6 +1013,7 @@ enum {
 	TCA_CAKE_INGRESS,
 	TCA_CAKE_ACK_FILTER,
 	TCA_CAKE_SPLIT_GSO,
+	TCA_CAKE_FWMARK,
 	__TCA_CAKE_MAX
 };
 #define TCA_CAKE_MAX	(__TCA_CAKE_MAX - 1)
@@ -1039,6 +1140,40 @@ enum {
 
 #define TCA_TAPRIO_SCHED_MAX (__TCA_TAPRIO_SCHED_MAX - 1)
 
+/* The format for the admin sched (dump only):
+ * [TCA_TAPRIO_SCHED_ADMIN_SCHED]
+ *   [TCA_TAPRIO_ATTR_SCHED_BASE_TIME]
+ *   [TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]
+ *     [TCA_TAPRIO_ATTR_SCHED_ENTRY]
+ *       [TCA_TAPRIO_ATTR_SCHED_ENTRY_CMD]
+ *       [TCA_TAPRIO_ATTR_SCHED_ENTRY_GATES]
+ *       [TCA_TAPRIO_ATTR_SCHED_ENTRY_INTERVAL]
+ */
+
+#define TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST	_BITUL(0)
+#define TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD	_BITUL(1)
+
+enum {
+	TCA_TAPRIO_TC_ENTRY_UNSPEC,
+	TCA_TAPRIO_TC_ENTRY_INDEX,		/* u32 */
+	TCA_TAPRIO_TC_ENTRY_MAX_SDU,		/* u32 */
+	TCA_TAPRIO_TC_ENTRY_FP,			/* u32 */
+
+	/* add new constants above here */
+	__TCA_TAPRIO_TC_ENTRY_CNT,
+	TCA_TAPRIO_TC_ENTRY_MAX = (__TCA_TAPRIO_TC_ENTRY_CNT - 1)
+};
+
+enum {
+	TCA_TAPRIO_OFFLOAD_STATS_PAD = 1,	/* u64 */
+	TCA_TAPRIO_OFFLOAD_STATS_WINDOW_DROPS,	/* u64 */
+	TCA_TAPRIO_OFFLOAD_STATS_TX_OVERRUNS,	/* u64 */
+
+	/* add new constants above here */
+	__TCA_TAPRIO_OFFLOAD_STATS_CNT,
+	TCA_TAPRIO_OFFLOAD_STATS_MAX = (__TCA_TAPRIO_OFFLOAD_STATS_CNT - 1)
+};
+
 enum {
 	TCA_TAPRIO_ATTR_UNSPEC,
 	TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */
@@ -1047,9 +1182,101 @@ enum {
 	TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */
 	TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */
 	TCA_TAPRIO_PAD,
+	TCA_TAPRIO_ATTR_PAD = TCA_TAPRIO_PAD,
+	TCA_TAPRIO_ATTR_ADMIN_SCHED, /* The admin sched, only used in dump */
+	TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, /* s64 */
+	TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, /* s64 */
+	TCA_TAPRIO_ATTR_FLAGS, /* u32 */
+	TCA_TAPRIO_ATTR_TXTIME_DELAY, /* u32 */
+	TCA_TAPRIO_ATTR_TC_ENTRY, /* nest */
 	__TCA_TAPRIO_ATTR_MAX,
 };
 
 #define TCA_TAPRIO_ATTR_MAX (__TCA_TAPRIO_ATTR_MAX - 1)
 
+/* ETS */
+
+#define TCQ_ETS_MAX_BANDS 16
+
+enum {
+	TCA_ETS_UNSPEC,
+	TCA_ETS_NBANDS,		/* u8 */
+	TCA_ETS_NSTRICT,	/* u8 */
+	TCA_ETS_QUANTA,		/* nested TCA_ETS_QUANTA_BAND */
+	TCA_ETS_QUANTA_BAND,	/* u32 */
+	TCA_ETS_PRIOMAP,	/* nested TCA_ETS_PRIOMAP_BAND */
+	TCA_ETS_PRIOMAP_BAND,	/* u8 */
+	__TCA_ETS_MAX,
+};
+
+#define TCA_ETS_MAX (__TCA_ETS_MAX - 1)
+
+/* DUALPI2 */
+enum tc_dualpi2_drop_overload {
+	TC_DUALPI2_DROP_OVERLOAD_OVERFLOW = 0,
+	TC_DUALPI2_DROP_OVERLOAD_DROP = 1,
+	__TCA_DUALPI2_DROP_OVERLOAD_MAX,
+};
+#define TCA_DUALPI2_DROP_OVERLOAD_MAX (__TCA_DUALPI2_DROP_OVERLOAD_MAX - 1)
+
+enum tc_dualpi2_drop_early {
+	TC_DUALPI2_DROP_EARLY_DROP_DEQUEUE = 0,
+	TC_DUALPI2_DROP_EARLY_DROP_ENQUEUE = 1,
+	__TCA_DUALPI2_DROP_EARLY_MAX,
+};
+#define TCA_DUALPI2_DROP_EARLY_MAX (__TCA_DUALPI2_DROP_EARLY_MAX - 1)
+
+enum tc_dualpi2_ecn_mask {
+	TC_DUALPI2_ECN_MASK_L4S_ECT = 1,
+	TC_DUALPI2_ECN_MASK_CLA_ECT = 2,
+	TC_DUALPI2_ECN_MASK_ANY_ECT = 3,
+	__TCA_DUALPI2_ECN_MASK_MAX,
+};
+#define TCA_DUALPI2_ECN_MASK_MAX (__TCA_DUALPI2_ECN_MASK_MAX - 1)
+
+enum tc_dualpi2_split_gso {
+	TC_DUALPI2_SPLIT_GSO_NO_SPLIT_GSO = 0,
+	TC_DUALPI2_SPLIT_GSO_SPLIT_GSO = 1,
+	__TCA_DUALPI2_SPLIT_GSO_MAX,
+};
+#define TCA_DUALPI2_SPLIT_GSO_MAX (__TCA_DUALPI2_SPLIT_GSO_MAX - 1)
+
+enum {
+	TCA_DUALPI2_UNSPEC,
+	TCA_DUALPI2_LIMIT,		/* Packets */
+	TCA_DUALPI2_MEMORY_LIMIT,	/* Bytes */
+	TCA_DUALPI2_TARGET,		/* us */
+	TCA_DUALPI2_TUPDATE,		/* us */
+	TCA_DUALPI2_ALPHA,		/* Hz scaled up by 256 */
+	TCA_DUALPI2_BETA,		/* Hz scaled up by 256 */
+	TCA_DUALPI2_STEP_THRESH_PKTS,	/* Step threshold in packets */
+	TCA_DUALPI2_STEP_THRESH_US,	/* Step threshold in microseconds */
+	TCA_DUALPI2_MIN_QLEN_STEP,	/* Minimum qlen to apply STEP_THRESH */
+	TCA_DUALPI2_COUPLING,		/* Coupling factor between queues */
+	TCA_DUALPI2_DROP_OVERLOAD,	/* Whether to drop on overload */
+	TCA_DUALPI2_DROP_EARLY,		/* Whether to drop on enqueue */
+	TCA_DUALPI2_C_PROTECTION,	/* Percentage */
+	TCA_DUALPI2_ECN_MASK,		/* L4S queue classification mask */
+	TCA_DUALPI2_SPLIT_GSO,		/* Split GSO packets at enqueue */
+	TCA_DUALPI2_PAD,
+	__TCA_DUALPI2_MAX
+};
+
+#define TCA_DUALPI2_MAX   (__TCA_DUALPI2_MAX - 1)
+
+struct tc_dualpi2_xstats {
+	__u32 prob;		/* current probability */
+	__u32 delay_c;		/* current delay in C queue */
+	__u32 delay_l;		/* current delay in L queue */
+	__u32 packets_in_c;	/* number of packets enqueued in C queue */
+	__u32 packets_in_l;	/* number of packets enqueued in L queue */
+	__u32 maxq;		/* maximum queue size */
+	__u32 ecn_mark;		/* packets marked with ecn*/
+	__u32 step_marks;	/* ECN marks due to the step AQM */
+	__s32 credit;		/* current c_protection credit */
+	__u32 memory_used;	/* Memory used by both queues */
+	__u32 max_memory_used;	/* Maximum used memory */
+	__u32 memory_limit;	/* Memory limit of both queues */
+};
+
 #endif

include/uapi/linux/stddef.h

@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_STDDEF_H
+#define _LINUX_STDDEF_H
+
+#ifdef __KERNEL__
+
+#endif
+
+#ifndef __always_inline
+#define __always_inline inline
+#endif
+
+/* Not all C++ standards support type declarations inside an anonymous union */
+#ifndef __cplusplus
+#define __struct_group_tag(TAG)		TAG
+#else
+#define __struct_group_tag(TAG)
+#endif
+
+/**
+ * __struct_group() - Create a mirrored named and anonyomous struct
+ *
+ * @TAG: The tag name for the named sub-struct (usually empty)
+ * @NAME: The identifier name of the mirrored sub-struct
+ * @ATTRS: Any struct attributes (usually empty)
+ * @MEMBERS: The member declarations for the mirrored structs
+ *
+ * Used to create an anonymous union of two structs with identical layout
+ * and size: one anonymous and one named. The former's members can be used
+ * normally without sub-struct naming, and the latter can be used to
+ * reason about the start, end, and size of the group of struct members.
+ * The named struct can also be explicitly tagged for layer reuse (C only),
+ * as well as both having struct attributes appended.
+ */
+#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \
+	union { \
+		struct { MEMBERS } ATTRS; \
+		struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \
+	} ATTRS
+
+#ifdef __cplusplus
+/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */
+#define __DECLARE_FLEX_ARRAY(T, member)	\
+	T member[0]
+#else
+/**
+ * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
+ *
+ * @TYPE: The type of each flexible array element
+ * @NAME: The name of the flexible array member
+ *
+ * In order to have a flexible array member in a union or alone in a
+ * struct, it needs to be wrapped in an anonymous struct with at least 1
+ * named member, but that member can be empty.
+ */
+#define __DECLARE_FLEX_ARRAY(TYPE, NAME)	\
+	struct { \
+		struct { } __empty_ ## NAME; \
+		TYPE NAME[]; \
+	}
+#endif
+
+#ifndef __counted_by
+#define __counted_by(m)
+#endif
+
+#ifndef __counted_by_le
+#define __counted_by_le(m)
+#endif
+
+#ifndef __counted_by_be
+#define __counted_by_be(m)
+#endif
+
+#ifdef __KERNEL__
+#define __kernel_nonstring	__nonstring
+#else
+#define __kernel_nonstring
+#endif
+
+#endif /* _LINUX_STDDEF_H */

scripts/build-fuzzers.sh

@@ -35,44 +35,48 @@ if [[ "$SANITIZER" == undefined ]]; then
     CXXFLAGS+=" $UBSAN_FLAGS"
 fi
 
+export SKIP_LIBELF_REBUILD=${SKIP_LIBELF_REBUILD:=''}
+
 # Ideally libbelf should be built using release tarballs available
 # at https://sourceware.org/elfutils/ftp/. Unfortunately sometimes they
 # fail to compile (for example, elfutils-0.185 fails to compile with LDFLAGS enabled
 # due to https://bugs.gentoo.org/794601) so let's just point the script to
 # commits referring to versions of libelf that actually can be built
-rm -rf elfutils
-git clone https://sourceware.org/git/elfutils.git
-(
-cd elfutils
-git checkout 67a187d4c1790058fc7fd218317851cb68bb087c
-git log --oneline -1
+if [[ ! -e elfutils || "$SKIP_LIBELF_REBUILD" == "" ]]; then
+    rm -rf elfutils
+    git clone https://sourceware.org/git/elfutils.git
+    (
+        cd elfutils
+        git checkout 67a187d4c1790058fc7fd218317851cb68bb087c
+        git log --oneline -1
 
-# ASan isn't compatible with -Wl,--no-undefined: https://github.com/google/sanitizers/issues/380
-sed -i 's/^\(NO_UNDEFINED=\).*/\1/' configure.ac
+        # ASan isn't compatible with -Wl,--no-undefined: https://github.com/google/sanitizers/issues/380
+        sed -i 's/^\(NO_UNDEFINED=\).*/\1/' configure.ac
 
-# ASan isn't compatible with -Wl,-z,defs either:
-# https://clang.llvm.org/docs/AddressSanitizer.html#usage
-sed -i 's/^\(ZDEFS_LDFLAGS=\).*/\1/' configure.ac
+        # ASan isn't compatible with -Wl,-z,defs either:
+        # https://clang.llvm.org/docs/AddressSanitizer.html#usage
+        sed -i 's/^\(ZDEFS_LDFLAGS=\).*/\1/' configure.ac
 
-if [[ "$SANITIZER" == undefined ]]; then
-    # That's basicaly what --enable-sanitize-undefined does to turn off unaligned access
-    # elfutils heavily relies on on i386/x86_64 but without changing compiler flags along the way
-    sed -i 's/\(check_undefined_val\)=[0-9]/\1=1/' configure.ac
+        if [[ "$SANITIZER" == undefined ]]; then
+            # That's basicaly what --enable-sanitize-undefined does to turn off unaligned access
+            # elfutils heavily relies on on i386/x86_64 but without changing compiler flags along the way
+            sed -i 's/\(check_undefined_val\)=[0-9]/\1=1/' configure.ac
+        fi
+
+        autoreconf -i -f
+        if ! ./configure --enable-maintainer-mode --disable-debuginfod --disable-libdebuginfod \
+             --disable-demangler --without-bzlib --without-lzma --without-zstd \
+	     CC="$CC" CFLAGS="-Wno-error $CFLAGS" CXX="$CXX" CXXFLAGS="-Wno-error $CXXFLAGS" LDFLAGS="$CFLAGS"; then
+            cat config.log
+            exit 1
+        fi
+
+        make -C config -j$(nproc) V=1
+        make -C lib -j$(nproc) V=1
+        make -C libelf -j$(nproc) V=1
+    )
 fi
 
-autoreconf -i -f
-if ! ./configure --enable-maintainer-mode --disable-debuginfod --disable-libdebuginfod \
-            --disable-demangler --without-bzlib --without-lzma --without-zstd \
-	    CC="$CC" CFLAGS="-Wno-error $CFLAGS" CXX="$CXX" CXXFLAGS="-Wno-error $CXXFLAGS" LDFLAGS="$CFLAGS"; then
-    cat config.log
-    exit 1
-fi
-
-make -C config -j$(nproc) V=1
-make -C lib -j$(nproc) V=1
-make -C libelf -j$(nproc) V=1
-)
-
 make -C src BUILD_STATIC_ONLY=y V=1 clean
 make -C src -j$(nproc) CFLAGS="-I$(pwd)/elfutils/libelf $CFLAGS" BUILD_STATIC_ONLY=y V=1
 

scripts/sync-kernel.sh

@@ -39,18 +39,19 @@ trap "cd ${WORKDIR}; exit" INT TERM EXIT
 declare -A PATH_MAP
 PATH_MAP=(									\
 	[tools/lib/bpf]=src							\
-	[tools/include/uapi/linux/bpf_common.h]=include/uapi/linux/bpf_common.h	\
-	[tools/include/uapi/linux/bpf.h]=include/uapi/linux/bpf.h		\
-	[tools/include/uapi/linux/btf.h]=include/uapi/linux/btf.h		\
-	[tools/include/uapi/linux/fcntl.h]=include/uapi/linux/fcntl.h		\
-	[tools/include/uapi/linux/openat2.h]=include/uapi/linux/openat2.h	\
-	[tools/include/uapi/linux/if_link.h]=include/uapi/linux/if_link.h	\
-	[tools/include/uapi/linux/if_xdp.h]=include/uapi/linux/if_xdp.h		\
-	[tools/include/uapi/linux/netdev.h]=include/uapi/linux/netdev.h		\
-	[tools/include/uapi/linux/netlink.h]=include/uapi/linux/netlink.h	\
-	[tools/include/uapi/linux/pkt_cls.h]=include/uapi/linux/pkt_cls.h	\
-	[tools/include/uapi/linux/pkt_sched.h]=include/uapi/linux/pkt_sched.h	\
+	[include/uapi/linux/bpf_common.h]=include/uapi/linux/bpf_common.h	\
+	[include/uapi/linux/bpf.h]=include/uapi/linux/bpf.h			\
+	[include/uapi/linux/btf.h]=include/uapi/linux/btf.h			\
+	[include/uapi/linux/fcntl.h]=include/uapi/linux/fcntl.h			\
+	[include/uapi/linux/openat2.h]=include/uapi/linux/openat2.h		\
+	[include/uapi/linux/if_link.h]=include/uapi/linux/if_link.h		\
+	[include/uapi/linux/if_xdp.h]=include/uapi/linux/if_xdp.h		\
+	[include/uapi/linux/netdev.h]=include/uapi/linux/netdev.h		\
+	[include/uapi/linux/netlink.h]=include/uapi/linux/netlink.h		\
+	[include/uapi/linux/pkt_cls.h]=include/uapi/linux/pkt_cls.h		\
+	[include/uapi/linux/pkt_sched.h]=include/uapi/linux/pkt_sched.h		\
 	[include/uapi/linux/perf_event.h]=include/uapi/linux/perf_event.h	\
+	[include/uapi/linux/stddef.h]=include/uapi/linux/stddef.h		\
 	[Documentation/bpf/libbpf]=docs						\
 )
 
@@ -63,6 +64,7 @@ LIBBPF_TREE_FILTER="mkdir -p __libbpf/include/uapi/linux __libbpf/include/tools
 for p in "${!PATH_MAP[@]}"; do
 	LIBBPF_TREE_FILTER+="git mv -kf ${p} __libbpf/${PATH_MAP[${p}]} && "$'\\\n'
 done
+LIBBPF_TREE_FILTER+="find __libbpf/include/uapi/linux -type f -exec sed -i -e 's/_UAPI\(__\?LINUX\)/\1/g' -e 's@^#include <linux/compiler_types.h>@@' {} + && "$'\\\n'
 LIBBPF_TREE_FILTER+="git rm --ignore-unmatch -f __libbpf/src/{Makefile,Build,test_libbpf.c,.gitignore} >/dev/null"
 
 cd_to()
@@ -347,7 +349,7 @@ diff -u ${TMP_DIR}/linux-view.ls ${TMP_DIR}/github-view.ls
 echo "Comparing file contents..."
 CONSISTENT=1
 for F in $(cat ${TMP_DIR}/linux-view.ls); do
-	if ! diff -u "${LINUX_ABS_DIR}/${F}" "${GITHUB_ABS_DIR}/${F}"; then
+	if ! diff -u <(sed 's/_UAPI\(__\?LINUX\)/\1/' "${LINUX_ABS_DIR}/${F}") "${GITHUB_ABS_DIR}/${F}"; then
 		echo "${LINUX_ABS_DIR}/${F} and ${GITHUB_ABS_DIR}/${F} are different!"
 		CONSISTENT=0
 	fi

src/Makefile

@@ -9,7 +9,7 @@ else
 endif
 
 LIBBPF_MAJOR_VERSION := 1
-LIBBPF_MINOR_VERSION := 6
+LIBBPF_MINOR_VERSION := 7
 LIBBPF_PATCH_VERSION := 0
 LIBBPF_VERSION := $(LIBBPF_MAJOR_VERSION).$(LIBBPF_MINOR_VERSION).$(LIBBPF_PATCH_VERSION)
 LIBBPF_MAJMIN_VERSION := $(LIBBPF_MAJOR_VERSION).$(LIBBPF_MINOR_VERSION).0
@@ -55,9 +55,9 @@ endif
 OBJDIR ?= .
 SHARED_OBJDIR := $(OBJDIR)/sharedobjs
 STATIC_OBJDIR := $(OBJDIR)/staticobjs
-OBJS := bpf.o btf.o libbpf.o libbpf_errno.o netlink.o \
-	nlattr.o str_error.o libbpf_probes.o bpf_prog_linfo.o \
-	btf_dump.o hashmap.o ringbuf.o strset.o linker.o gen_loader.o \
+OBJS := bpf.o btf.o libbpf.o libbpf_utils.o netlink.o 			\
+	nlattr.o libbpf_probes.o bpf_prog_linfo.o 			\
+	btf_dump.o hashmap.o ringbuf.o strset.o linker.o gen_loader.o 	\
 	relo_core.o usdt.o zip.o elf.o features.o btf_iter.o btf_relocate.o
 SHARED_OBJS := $(addprefix $(SHARED_OBJDIR)/,$(OBJS))
 STATIC_OBJS := $(addprefix $(STATIC_OBJDIR)/,$(OBJS))

src/bpf.c

@@ -154,7 +154,7 @@ int bump_rlimit_memlock(void)
 
 	memlock_bumped = true;
 
-	/* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */
+	/* zero memlock_rlim disables auto-bumping RLIMIT_MEMLOCK */
 	if (memlock_rlim == 0)
 		return 0;
 
@@ -172,7 +172,7 @@ int bpf_map_create(enum bpf_map_type map_type,
 		   __u32 max_entries,
 		   const struct bpf_map_create_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, excl_prog_hash_size);
 	union bpf_attr attr;
 	int fd;
 
@@ -203,6 +203,8 @@ int bpf_map_create(enum bpf_map_type map_type,
 	attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0);
 
 	attr.map_token_fd = OPTS_GET(opts, token_fd, 0);
+	attr.excl_prog_hash = ptr_to_u64(OPTS_GET(opts, excl_prog_hash, NULL));
+	attr.excl_prog_hash_size = OPTS_GET(opts, excl_prog_hash_size, 0);
 
 	fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz);
 	return libbpf_err_errno(fd);
@@ -238,7 +240,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		  const struct bpf_insn *insns, size_t insn_cnt,
 		  struct bpf_prog_load_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, fd_array_cnt);
+	const size_t attr_sz = offsetofend(union bpf_attr, keyring_id);
 	void *finfo = NULL, *linfo = NULL;
 	const char *func_info, *line_info;
 	__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@@ -792,6 +794,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
 	case BPF_MODIFY_RETURN:
+	case BPF_TRACE_FSESSION:
 	case BPF_LSM_MAC:
 		attr.link_create.tracing.cookie = OPTS_GET(opts, tracing.cookie, 0);
 		if (!OPTS_ZEROED(opts, tracing))
@@ -837,6 +840,50 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, netkit))
 			return libbpf_err(-EINVAL);
 		break;
+	case BPF_CGROUP_INET_INGRESS:
+	case BPF_CGROUP_INET_EGRESS:
+	case BPF_CGROUP_INET_SOCK_CREATE:
+	case BPF_CGROUP_INET_SOCK_RELEASE:
+	case BPF_CGROUP_INET4_BIND:
+	case BPF_CGROUP_INET6_BIND:
+	case BPF_CGROUP_INET4_POST_BIND:
+	case BPF_CGROUP_INET6_POST_BIND:
+	case BPF_CGROUP_INET4_CONNECT:
+	case BPF_CGROUP_INET6_CONNECT:
+	case BPF_CGROUP_UNIX_CONNECT:
+	case BPF_CGROUP_INET4_GETPEERNAME:
+	case BPF_CGROUP_INET6_GETPEERNAME:
+	case BPF_CGROUP_UNIX_GETPEERNAME:
+	case BPF_CGROUP_INET4_GETSOCKNAME:
+	case BPF_CGROUP_INET6_GETSOCKNAME:
+	case BPF_CGROUP_UNIX_GETSOCKNAME:
+	case BPF_CGROUP_UDP4_SENDMSG:
+	case BPF_CGROUP_UDP6_SENDMSG:
+	case BPF_CGROUP_UNIX_SENDMSG:
+	case BPF_CGROUP_UDP4_RECVMSG:
+	case BPF_CGROUP_UDP6_RECVMSG:
+	case BPF_CGROUP_UNIX_RECVMSG:
+	case BPF_CGROUP_SOCK_OPS:
+	case BPF_CGROUP_DEVICE:
+	case BPF_CGROUP_SYSCTL:
+	case BPF_CGROUP_GETSOCKOPT:
+	case BPF_CGROUP_SETSOCKOPT:
+	case BPF_LSM_CGROUP:
+		relative_fd = OPTS_GET(opts, cgroup.relative_fd, 0);
+		relative_id = OPTS_GET(opts, cgroup.relative_id, 0);
+		if (relative_fd && relative_id)
+			return libbpf_err(-EINVAL);
+		if (relative_id) {
+			attr.link_create.cgroup.relative_id = relative_id;
+			attr.link_create.flags |= BPF_F_ID;
+		} else {
+			attr.link_create.cgroup.relative_fd = relative_fd;
+		}
+		attr.link_create.cgroup.expected_revision =
+			OPTS_GET(opts, cgroup.expected_revision, 0);
+		if (!OPTS_ZEROED(opts, cgroup))
+			return libbpf_err(-EINVAL);
+		break;
 	default:
 		if (!OPTS_ZEROED(opts, flags))
 			return libbpf_err(-EINVAL);
@@ -1331,3 +1378,42 @@ int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts)
 	fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
+
+int bpf_prog_stream_read(int prog_fd, __u32 stream_id, void *buf, __u32 buf_len,
+			 struct bpf_prog_stream_read_opts *opts)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_stream_read);
+	union bpf_attr attr;
+	int err;
+
+	if (!OPTS_VALID(opts, bpf_prog_stream_read_opts))
+		return libbpf_err(-EINVAL);
+
+	memset(&attr, 0, attr_sz);
+	attr.prog_stream_read.stream_buf = ptr_to_u64(buf);
+	attr.prog_stream_read.stream_buf_len = buf_len;
+	attr.prog_stream_read.stream_id = stream_id;
+	attr.prog_stream_read.prog_fd = prog_fd;
+
+	err = sys_bpf(BPF_PROG_STREAM_READ_BY_FD, &attr, attr_sz);
+	return libbpf_err_errno(err);
+}
+
+int bpf_prog_assoc_struct_ops(int prog_fd, int map_fd,
+			      struct bpf_prog_assoc_struct_ops_opts *opts)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_assoc_struct_ops);
+	union bpf_attr attr;
+	int err;
+
+	if (!OPTS_VALID(opts, bpf_prog_assoc_struct_ops_opts))
+		return libbpf_err(-EINVAL);
+
+	memset(&attr, 0, attr_sz);
+	attr.prog_assoc_struct_ops.map_fd = map_fd;
+	attr.prog_assoc_struct_ops.prog_fd = prog_fd;
+	attr.prog_assoc_struct_ops.flags = OPTS_GET(opts, flags, 0);
+
+	err = sys_bpf(BPF_PROG_ASSOC_STRUCT_OPS, &attr, attr_sz);
+	return libbpf_err_errno(err);
+}

src/bpf.h

@@ -54,9 +54,12 @@ struct bpf_map_create_opts {
 	__s32 value_type_btf_obj_fd;
 
 	__u32 token_fd;
+
+	const void *excl_prog_hash;
+	__u32 excl_prog_hash_size;
 	size_t :0;
 };
-#define bpf_map_create_opts__last_field token_fd
+#define bpf_map_create_opts__last_field excl_prog_hash_size
 
 LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
 			      const char *map_name,
@@ -286,6 +289,14 @@ LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch,
  *    Update spin_lock-ed map elements. This must be
  *    specified if the map value contains a spinlock.
  *
+ * **BPF_F_CPU**
+ *    As for percpu maps, update value on the specified CPU. And the cpu
+ *    info is embedded into the high 32 bits of **opts->elem_flags**.
+ *
+ * **BPF_F_ALL_CPUS**
+ *    As for percpu maps, update value across all CPUs. This flag cannot
+ *    be used with BPF_F_CPU at the same time.
+ *
  * @param fd BPF map file descriptor
  * @param keys pointer to an array of *count* keys
  * @param values pointer to an array of *count* values
@@ -438,6 +449,11 @@ struct bpf_link_create_opts {
 			__u32 relative_id;
 			__u64 expected_revision;
 		} netkit;
+		struct {
+			__u32 relative_fd;
+			__u32 relative_id;
+			__u64 expected_revision;
+		} cgroup;
 	};
 	size_t :0;
 };
@@ -704,6 +720,48 @@ struct bpf_token_create_opts {
 LIBBPF_API int bpf_token_create(int bpffs_fd,
 				struct bpf_token_create_opts *opts);
 
+struct bpf_prog_stream_read_opts {
+	size_t sz;
+	size_t :0;
+};
+#define bpf_prog_stream_read_opts__last_field sz
+/**
+ * @brief **bpf_prog_stream_read** reads data from the BPF stream of a given BPF
+ * program.
+ *
+ * @param prog_fd FD for the BPF program whose BPF stream is to be read.
+ * @param stream_id ID of the BPF stream to be read.
+ * @param buf Buffer to read data into from the BPF stream.
+ * @param buf_len Maximum number of bytes to read from the BPF stream.
+ * @param opts optional options, can be NULL
+ *
+ * @return The number of bytes read, on success; negative error code, otherwise
+ * (errno is also set to the error code)
+ */
+LIBBPF_API int bpf_prog_stream_read(int prog_fd, __u32 stream_id, void *buf, __u32 buf_len,
+				    struct bpf_prog_stream_read_opts *opts);
+
+struct bpf_prog_assoc_struct_ops_opts {
+	size_t sz;
+	__u32 flags;
+	size_t :0;
+};
+#define bpf_prog_assoc_struct_ops_opts__last_field flags
+
+/**
+ * @brief **bpf_prog_assoc_struct_ops** associates a BPF program with a
+ * struct_ops map.
+ *
+ * @param prog_fd FD for the BPF program
+ * @param map_fd FD for the struct_ops map to be associated with the BPF program
+ * @param opts optional options, can be NULL
+ *
+ * @return 0 on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_prog_assoc_struct_ops(int prog_fd, int map_fd,
+					 struct bpf_prog_assoc_struct_ops_opts *opts);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif

src/bpf_gen_internal.h

@@ -4,6 +4,7 @@
 #define __BPF_GEN_INTERNAL_H
 
 #include "bpf.h"
+#include "libbpf_internal.h"
 
 struct ksym_relo_desc {
 	const char *name;
@@ -50,6 +51,7 @@ struct bpf_gen {
 	__u32 nr_ksyms;
 	int fd_array;
 	int nr_fd_array;
+	int hash_insn_offset[SHA256_DWORD_SIZE];
 };
 
 void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps);

src/bpf_helper_defs.h

@@ -286,6 +286,7 @@ static long (* const bpf_l3_csum_replace)(struct __sk_buff *skb, __u32 offset, _
  * 	for updates resulting in a null checksum the value is set to
  * 	**CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates
  * 	that the modified header field is part of the pseudo-header.
+ * 	Flag **BPF_F_IPV6** should be set for IPv6 packets.
  *
  * 	This helper works in combination with **bpf_csum_diff**\ (),
  * 	which does not update the checksum in-place, but offers more
@@ -688,7 +689,7 @@ static __u32 (* const bpf_get_route_realm)(struct __sk_buff *skb) = (void *) 24;
  * 	into it. An example is available in file
  * 	*samples/bpf/trace_output_user.c* in the Linux kernel source
  * 	tree (the eBPF program counterpart is in
- * 	*samples/bpf/trace_output_kern.c*).
+ * 	*samples/bpf/trace_output.bpf.c*).
  *
  * 	**bpf_perf_event_output**\ () achieves better performance
  * 	than **bpf_trace_printk**\ () for sharing data with user
@@ -3557,7 +3558,7 @@ static int (* const bpf_inode_storage_delete)(void *map, void *inode) = (void *)
  * 	including the trailing NUL character. On error, a negative
  * 	value.
  */
-static long (* const bpf_d_path)(struct path *path, char *buf, __u32 sz) = (void *) 147;
+static long (* const bpf_d_path)(const struct path *path, char *buf, __u32 sz) = (void *) 147;
 
 /*
  * bpf_copy_from_user
@@ -3706,6 +3707,9 @@ static void *(* const bpf_this_cpu_ptr)(const void *percpu_ptr) = (void *) 154;
  * 	the netns switch takes place from ingress to ingress without
  * 	going through the CPU's backlog queue.
  *
+ * 	*skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during
+ * 	the netns switch.
+ *
  * 	The *flags* argument is reserved and must be 0. The helper is
  * 	currently only supported for tc BPF program types at the
  * 	ingress hook and for veth and netkit target device types. The
@@ -4480,7 +4484,7 @@ static struct mptcp_sock *(* const bpf_skc_to_mptcp_sock)(void *sk) = (void *) 1
  * 	0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
  * 	-EINVAL if flags is not 0.
  */
-static long (* const bpf_dynptr_from_mem)(void *data, __u32 size, __u64 flags, struct bpf_dynptr *ptr) = (void *) 197;
+static long (* const bpf_dynptr_from_mem)(void *data, __u64 size, __u64 flags, struct bpf_dynptr *ptr) = (void *) 197;
 
 /*
  * bpf_ringbuf_reserve_dynptr
@@ -4538,7 +4542,7 @@ static void (* const bpf_ringbuf_discard_dynptr)(struct bpf_dynptr *ptr, __u64 f
  * 	of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
  * 	*flags* is not 0.
  */
-static long (* const bpf_dynptr_read)(void *dst, __u32 len, const struct bpf_dynptr *src, __u32 offset, __u64 flags) = (void *) 201;
+static long (* const bpf_dynptr_read)(void *dst, __u64 len, const struct bpf_dynptr *src, __u64 offset, __u64 flags) = (void *) 201;
 
 /*
  * bpf_dynptr_write
@@ -4563,7 +4567,7 @@ static long (* const bpf_dynptr_read)(void *dst, __u32 len, const struct bpf_dyn
  * 	is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs,
  * 	other errors correspond to errors returned by **bpf_skb_store_bytes**\ ().
  */
-static long (* const bpf_dynptr_write)(const struct bpf_dynptr *dst, __u32 offset, void *src, __u32 len, __u64 flags) = (void *) 202;
+static long (* const bpf_dynptr_write)(const struct bpf_dynptr *dst, __u64 offset, void *src, __u64 len, __u64 flags) = (void *) 202;
 
 /*
  * bpf_dynptr_data
@@ -4581,7 +4585,7 @@ static long (* const bpf_dynptr_write)(const struct bpf_dynptr *dst, __u32 offse
  * 	read-only, if the dynptr is invalid, or if the offset and length
  * 	is out of bounds.
  */
-static void *(* const bpf_dynptr_data)(const struct bpf_dynptr *ptr, __u32 offset, __u32 len) = (void *) 203;
+static void *(* const bpf_dynptr_data)(const struct bpf_dynptr *ptr, __u64 offset, __u64 len) = (void *) 203;
 
 /*
  * bpf_tcp_raw_gen_syncookie_ipv4

src/bpf_helpers.h

@@ -215,6 +215,7 @@ enum libbpf_tristate {
 #define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull")))
 #define __arg_nullable __attribute((btf_decl_tag("arg:nullable")))
 #define __arg_trusted __attribute((btf_decl_tag("arg:trusted")))
+#define __arg_untrusted __attribute((btf_decl_tag("arg:untrusted")))
 #define __arg_arena __attribute((btf_decl_tag("arg:arena")))
 
 #ifndef ___bpf_concat
@@ -314,6 +315,22 @@ enum libbpf_tristate {
 			  ___param, sizeof(___param));		\
 })
 
+extern int bpf_stream_vprintk(int stream_id, const char *fmt__str, const void *args,
+			      __u32 len__sz) __weak __ksym;
+
+#define bpf_stream_printk(stream_id, fmt, args...)					\
+({											\
+	static const char ___fmt[] = fmt;						\
+	unsigned long long ___param[___bpf_narg(args)];					\
+											\
+	_Pragma("GCC diagnostic push")							\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")				\
+	___bpf_fill(___param, args);							\
+	_Pragma("GCC diagnostic pop")							\
+											\
+	bpf_stream_vprintk(stream_id, ___fmt, ___param, sizeof(___param));		\
+})
+
 /* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args
  * Otherwise use __bpf_vprintk
  */

src/bpf_tracing.h

@@ -311,7 +311,7 @@ struct pt_regs___arm64 {
 #define __PT_RET_REG regs[31]
 #define __PT_FP_REG __unsupported__
 #define __PT_RC_REG gpr[3]
-#define __PT_SP_REG sp
+#define __PT_SP_REG gpr[1]
 #define __PT_IP_REG nip
 
 #elif defined(bpf_target_sparc)

src/btf.c

@@ -12,6 +12,7 @@
 #include <sys/utsname.h>
 #include <sys/param.h>
 #include <sys/stat.h>
+#include <sys/mman.h>
 #include <linux/kernel.h>
 #include <linux/err.h>
 #include <linux/btf.h>
@@ -22,7 +23,6 @@
 #include "libbpf_internal.h"
 #include "hashmap.h"
 #include "strset.h"
-#include "str_error.h"
 
 #define BTF_MAX_NR_TYPES 0x7fffffffU
 #define BTF_MAX_STR_OFFSET 0x7fffffffU
@@ -92,6 +92,8 @@ struct btf {
 	 *   - for split BTF counts number of types added on top of base BTF.
 	 */
 	__u32 nr_types;
+	/* the start IDs of named types in sorted BTF */
+	int named_start_id;
 	/* if not NULL, points to the base BTF on top of which the current
 	 * split BTF is based
 	 */
@@ -120,6 +122,9 @@ struct btf {
 	/* whether base_btf should be freed in btf_free for this instance */
 	bool owns_base;
 
+	/* whether raw_data is a (read-only) mmap */
+	bool raw_data_is_mmap;
+
 	/* BTF object FD, if loaded into kernel */
 	int fd;
 
@@ -894,44 +899,103 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id)
 	return type_id;
 }
 
-__s32 btf__find_by_name(const struct btf *btf, const char *type_name)
+static void btf_check_sorted(struct btf *btf)
 {
-	__u32 i, nr_types = btf__type_cnt(btf);
+	__u32 i, n, named_start_id = 0;
 
-	if (!strcmp(type_name, "void"))
+	n = btf__type_cnt(btf);
+	for (i = btf->start_id + 1; i < n; i++) {
+		struct btf_type *ta = btf_type_by_id(btf, i - 1);
+		struct btf_type *tb = btf_type_by_id(btf, i);
+		const char *na = btf__str_by_offset(btf, ta->name_off);
+		const char *nb = btf__str_by_offset(btf, tb->name_off);
+
+		if (strcmp(na, nb) > 0)
+			return;
+
+		if (named_start_id == 0 && na[0] != '\0')
+			named_start_id = i - 1;
+		if (named_start_id == 0 && nb[0] != '\0')
+			named_start_id = i;
+	}
+
+	if (named_start_id)
+		btf->named_start_id = named_start_id;
+}
+
+static __s32 btf_find_type_by_name_bsearch(const struct btf *btf, const char *name,
+					   __s32 start_id)
+{
+	const struct btf_type *t;
+	const char *tname;
+	__s32 l, r, m;
+
+	l = start_id;
+	r = btf__type_cnt(btf) - 1;
+	while (l <= r) {
+		m = l + (r - l) / 2;
+		t = btf_type_by_id(btf, m);
+		tname = btf__str_by_offset(btf, t->name_off);
+		if (strcmp(tname, name) >= 0) {
+			if (l == r)
+				return r;
+			r = m;
+		} else {
+			l = m + 1;
+		}
+	}
+
+	return btf__type_cnt(btf);
+}
+
+static __s32 btf_find_by_name_kind(const struct btf *btf, int start_id,
+				   const char *type_name, __s32 kind)
+{
+	__u32 nr_types = btf__type_cnt(btf);
+	const struct btf_type *t;
+	const char *tname;
+	__s32 id;
+
+	if (start_id < btf->start_id) {
+		id = btf_find_by_name_kind(btf->base_btf, start_id,
+					   type_name, kind);
+		if (id >= 0)
+			return id;
+		start_id = btf->start_id;
+	}
+
+	if (kind == BTF_KIND_UNKN || strcmp(type_name, "void") == 0)
 		return 0;
 
-	for (i = 1; i < nr_types; i++) {
-		const struct btf_type *t = btf__type_by_id(btf, i);
-		const char *name = btf__name_by_offset(btf, t->name_off);
-
-		if (name && !strcmp(type_name, name))
-			return i;
+	if (btf->named_start_id > 0 && type_name[0]) {
+		start_id = max(start_id, btf->named_start_id);
+		id = btf_find_type_by_name_bsearch(btf, type_name, start_id);
+		for (; id < nr_types; id++) {
+			t = btf__type_by_id(btf, id);
+			tname = btf__str_by_offset(btf, t->name_off);
+			if (strcmp(tname, type_name) != 0)
+				return libbpf_err(-ENOENT);
+			if (kind < 0 || btf_kind(t) == kind)
+				return id;
+		}
+	} else {
+		for (id = start_id; id < nr_types; id++) {
+			t = btf_type_by_id(btf, id);
+			if (kind > 0 && btf_kind(t) != kind)
+				continue;
+			tname = btf__str_by_offset(btf, t->name_off);
+			if (strcmp(tname, type_name) == 0)
+				return id;
+		}
 	}
 
 	return libbpf_err(-ENOENT);
 }
 
-static __s32 btf_find_by_name_kind(const struct btf *btf, int start_id,
-				   const char *type_name, __u32 kind)
+/* the kind value of -1 indicates that kind matching should be skipped */
+__s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 {
-	__u32 i, nr_types = btf__type_cnt(btf);
-
-	if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void"))
-		return 0;
-
-	for (i = start_id; i < nr_types; i++) {
-		const struct btf_type *t = btf__type_by_id(btf, i);
-		const char *name;
-
-		if (btf_kind(t) != kind)
-			continue;
-		name = btf__name_by_offset(btf, t->name_off);
-		if (name && !strcmp(type_name, name))
-			return i;
-	}
-
-	return libbpf_err(-ENOENT);
+	return btf_find_by_name_kind(btf, 1, type_name, -1);
 }
 
 __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
@@ -951,6 +1015,17 @@ static bool btf_is_modifiable(const struct btf *btf)
 	return (void *)btf->hdr != btf->raw_data;
 }
 
+static void btf_free_raw_data(struct btf *btf)
+{
+	if (btf->raw_data_is_mmap) {
+		munmap(btf->raw_data, btf->raw_size);
+		btf->raw_data_is_mmap = false;
+	} else {
+		free(btf->raw_data);
+	}
+	btf->raw_data = NULL;
+}
+
 void btf__free(struct btf *btf)
 {
 	if (IS_ERR_OR_NULL(btf))
@@ -970,7 +1045,7 @@ void btf__free(struct btf *btf)
 		free(btf->types_data);
 		strset__free(btf->strs_set);
 	}
-	free(btf->raw_data);
+	btf_free_raw_data(btf);
 	free(btf->raw_data_swapped);
 	free(btf->type_offs);
 	if (btf->owns_base)
@@ -992,11 +1067,12 @@ static struct btf *btf_new_empty(struct btf *base_btf)
 	btf->fd = -1;
 	btf->ptr_sz = sizeof(void *);
 	btf->swapped_endian = false;
+	btf->named_start_id = 0;
 
 	if (base_btf) {
 		btf->base_btf = base_btf;
 		btf->start_id = btf__type_cnt(base_btf);
-		btf->start_str_off = base_btf->hdr->str_len;
+		btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off;
 		btf->swapped_endian = base_btf->swapped_endian;
 	}
 
@@ -1030,7 +1106,7 @@ struct btf *btf__new_empty_split(struct btf *base_btf)
 	return libbpf_ptr(btf_new_empty(base_btf));
 }
 
-static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
+static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf, bool is_mmap)
 {
 	struct btf *btf;
 	int err;
@@ -1043,19 +1119,26 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
 	btf->start_id = 1;
 	btf->start_str_off = 0;
 	btf->fd = -1;
+	btf->named_start_id = 0;
 
 	if (base_btf) {
 		btf->base_btf = base_btf;
 		btf->start_id = btf__type_cnt(base_btf);
-		btf->start_str_off = base_btf->hdr->str_len;
+		btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off;
 	}
 
-	btf->raw_data = malloc(size);
-	if (!btf->raw_data) {
-		err = -ENOMEM;
-		goto done;
+	if (is_mmap) {
+		btf->raw_data = (void *)data;
+		btf->raw_data_is_mmap = true;
+	} else {
+		btf->raw_data = malloc(size);
+		if (!btf->raw_data) {
+			err = -ENOMEM;
+			goto done;
+		}
+		memcpy(btf->raw_data, data, size);
 	}
-	memcpy(btf->raw_data, data, size);
+
 	btf->raw_size = size;
 
 	btf->hdr = btf->raw_data;
@@ -1071,6 +1154,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
 	err = err ?: btf_sanity_check(btf);
 	if (err)
 		goto done;
+	btf_check_sorted(btf);
 
 done:
 	if (err) {
@@ -1083,12 +1167,12 @@ done:
 
 struct btf *btf__new(const void *data, __u32 size)
 {
-	return libbpf_ptr(btf_new(data, size, NULL));
+	return libbpf_ptr(btf_new(data, size, NULL, false));
 }
 
 struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf)
 {
-	return libbpf_ptr(btf_new(data, size, base_btf));
+	return libbpf_ptr(btf_new(data, size, base_btf, false));
 }
 
 struct btf_elf_secs {
@@ -1209,7 +1293,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 
 	if (secs.btf_base_data) {
 		dist_base_btf = btf_new(secs.btf_base_data->d_buf, secs.btf_base_data->d_size,
-					NULL);
+					NULL, false);
 		if (IS_ERR(dist_base_btf)) {
 			err = PTR_ERR(dist_base_btf);
 			dist_base_btf = NULL;
@@ -1218,7 +1302,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 	}
 
 	btf = btf_new(secs.btf_data->d_buf, secs.btf_data->d_size,
-		      dist_base_btf ?: base_btf);
+		      dist_base_btf ?: base_btf, false);
 	if (IS_ERR(btf)) {
 		err = PTR_ERR(btf);
 		goto done;
@@ -1335,7 +1419,7 @@ static struct btf *btf_parse_raw(const char *path, struct btf *base_btf)
 	}
 
 	/* finally parse BTF data */
-	btf = btf_new(data, sz, base_btf);
+	btf = btf_new(data, sz, base_btf, false);
 
 err_out:
 	free(data);
@@ -1354,6 +1438,37 @@ struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf)
 	return libbpf_ptr(btf_parse_raw(path, base_btf));
 }
 
+static struct btf *btf_parse_raw_mmap(const char *path, struct btf *base_btf)
+{
+	struct stat st;
+	void *data;
+	struct btf *btf;
+	int fd, err;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return ERR_PTR(-errno);
+
+	if (fstat(fd, &st) < 0) {
+		err = -errno;
+		close(fd);
+		return ERR_PTR(err);
+	}
+
+	data = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+	err = -errno;
+	close(fd);
+
+	if (data == MAP_FAILED)
+		return ERR_PTR(err);
+
+	btf = btf_new(data, st.st_size, base_btf, true);
+	if (IS_ERR(btf))
+		munmap(data, st.st_size);
+
+	return btf;
+}
+
 static struct btf *btf_parse(const char *path, struct btf *base_btf, struct btf_ext **btf_ext)
 {
 	struct btf *btf;
@@ -1618,7 +1733,7 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf)
 		goto exit_free;
 	}
 
-	btf = btf_new(ptr, btf_info.btf_size, base_btf);
+	btf = btf_new(ptr, btf_info.btf_size, base_btf, false);
 
 exit_free:
 	free(ptr);
@@ -1658,14 +1773,13 @@ struct btf *btf__load_from_kernel_by_id(__u32 id)
 
 static void btf_invalidate_raw_data(struct btf *btf)
 {
-	if (btf->raw_data) {
-		free(btf->raw_data);
-		btf->raw_data = NULL;
-	}
+	if (btf->raw_data)
+		btf_free_raw_data(btf);
 	if (btf->raw_data_swapped) {
 		free(btf->raw_data_swapped);
 		btf->raw_data_swapped = NULL;
 	}
+	btf->named_start_id = 0;
 }
 
 /* Ensure BTF is ready to be modified (by splitting into a three memory
@@ -2020,7 +2134,7 @@ int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding
 	int sz, name_off;
 
 	/* non-empty name */
-	if (!name || !name[0])
+	if (str_is_empty(name))
 		return libbpf_err(-EINVAL);
 	/* byte_sz must be power of 2 */
 	if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 16)
@@ -2068,7 +2182,7 @@ int btf__add_float(struct btf *btf, const char *name, size_t byte_sz)
 	int sz, name_off;
 
 	/* non-empty name */
-	if (!name || !name[0])
+	if (str_is_empty(name))
 		return libbpf_err(-EINVAL);
 
 	/* byte_sz must be one of the explicitly allowed values */
@@ -2123,7 +2237,7 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref
 	if (!t)
 		return libbpf_err(-ENOMEM);
 
-	if (name && name[0]) {
+	if (!str_is_empty(name)) {
 		name_off = btf__add_str(btf, name);
 		if (name_off < 0)
 			return name_off;
@@ -2200,7 +2314,7 @@ static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32
 	if (!t)
 		return libbpf_err(-ENOMEM);
 
-	if (name && name[0]) {
+	if (!str_is_empty(name)) {
 		name_off = btf__add_str(btf, name);
 		if (name_off < 0)
 			return name_off;
@@ -2301,7 +2415,7 @@ int btf__add_field(struct btf *btf, const char *name, int type_id,
 	if (!m)
 		return libbpf_err(-ENOMEM);
 
-	if (name && name[0]) {
+	if (!str_is_empty(name)) {
 		name_off = btf__add_str(btf, name);
 		if (name_off < 0)
 			return name_off;
@@ -2339,7 +2453,7 @@ static int btf_add_enum_common(struct btf *btf, const char *name, __u32 byte_sz,
 	if (!t)
 		return libbpf_err(-ENOMEM);
 
-	if (name && name[0]) {
+	if (!str_is_empty(name)) {
 		name_off = btf__add_str(btf, name);
 		if (name_off < 0)
 			return name_off;
@@ -2397,7 +2511,7 @@ int btf__add_enum_value(struct btf *btf, const char *name, __s64 value)
 		return libbpf_err(-EINVAL);
 
 	/* non-empty name */
-	if (!name || !name[0])
+	if (str_is_empty(name))
 		return libbpf_err(-EINVAL);
 	if (value < INT_MIN || value > UINT_MAX)
 		return libbpf_err(-E2BIG);
@@ -2474,7 +2588,7 @@ int btf__add_enum64_value(struct btf *btf, const char *name, __u64 value)
 		return libbpf_err(-EINVAL);
 
 	/* non-empty name */
-	if (!name || !name[0])
+	if (str_is_empty(name))
 		return libbpf_err(-EINVAL);
 
 	/* decompose and invalidate raw data */
@@ -2514,7 +2628,7 @@ int btf__add_enum64_value(struct btf *btf, const char *name, __u64 value)
  */
 int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind)
 {
-	if (!name || !name[0])
+	if (str_is_empty(name))
 		return libbpf_err(-EINVAL);
 
 	switch (fwd_kind) {
@@ -2550,7 +2664,7 @@ int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind)
  */
 int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id)
 {
-	if (!name || !name[0])
+	if (str_is_empty(name))
 		return libbpf_err(-EINVAL);
 
 	return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id, 0);
@@ -2602,7 +2716,7 @@ int btf__add_restrict(struct btf *btf, int ref_type_id)
  */
 int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id)
 {
-	if (!value || !value[0])
+	if (str_is_empty(value))
 		return libbpf_err(-EINVAL);
 
 	return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id, 0);
@@ -2619,7 +2733,7 @@ int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id)
  */
 int btf__add_type_attr(struct btf *btf, const char *value, int ref_type_id)
 {
-	if (!value || !value[0])
+	if (str_is_empty(value))
 		return libbpf_err(-EINVAL);
 
 	return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id, 1);
@@ -2638,7 +2752,7 @@ int btf__add_func(struct btf *btf, const char *name,
 {
 	int id;
 
-	if (!name || !name[0])
+	if (str_is_empty(name))
 		return libbpf_err(-EINVAL);
 	if (linkage != BTF_FUNC_STATIC && linkage != BTF_FUNC_GLOBAL &&
 	    linkage != BTF_FUNC_EXTERN)
@@ -2724,7 +2838,7 @@ int btf__add_func_param(struct btf *btf, const char *name, int type_id)
 	if (!p)
 		return libbpf_err(-ENOMEM);
 
-	if (name && name[0]) {
+	if (!str_is_empty(name)) {
 		name_off = btf__add_str(btf, name);
 		if (name_off < 0)
 			return name_off;
@@ -2759,7 +2873,7 @@ int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id)
 	int sz, name_off;
 
 	/* non-empty name */
-	if (!name || !name[0])
+	if (str_is_empty(name))
 		return libbpf_err(-EINVAL);
 	if (linkage != BTF_VAR_STATIC && linkage != BTF_VAR_GLOBAL_ALLOCATED &&
 	    linkage != BTF_VAR_GLOBAL_EXTERN)
@@ -2808,7 +2922,7 @@ int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz)
 	int sz, name_off;
 
 	/* non-empty name */
-	if (!name || !name[0])
+	if (str_is_empty(name))
 		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
@@ -2885,7 +2999,7 @@ static int btf_add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
 	struct btf_type *t;
 	int sz, value_off;
 
-	if (!value || !value[0] || component_idx < -1)
+	if (str_is_empty(value) || component_idx < -1)
 		return libbpf_err(-EINVAL);
 
 	if (validate_type_id(ref_type_id))
@@ -3852,6 +3966,20 @@ err_out:
 	return err;
 }
 
+/*
+ * Calculate type signature hash of TYPEDEF, ignoring referenced type IDs,
+ * as referenced type IDs equivalence is established separately during type
+ * graph equivalence check algorithm.
+ */
+static long btf_hash_typedef(struct btf_type *t)
+{
+	long h;
+
+	h = hash_combine(0, t->name_off);
+	h = hash_combine(h, t->info);
+	return h;
+}
+
 static long btf_hash_common(struct btf_type *t)
 {
 	long h;
@@ -3869,6 +3997,13 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2)
 	       t1->size == t2->size;
 }
 
+/* Check structural compatibility of two TYPEDEF. */
+static bool btf_equal_typedef(struct btf_type *t1, struct btf_type *t2)
+{
+	return t1->name_off == t2->name_off &&
+	       t1->info == t2->info;
+}
+
 /* Calculate type signature hash of INT or TAG. */
 static long btf_hash_int_decl_tag(struct btf_type *t)
 {
@@ -4361,11 +4496,14 @@ static bool btf_dedup_identical_types(struct btf_dedup *d, __u32 id1, __u32 id2,
 	struct btf_type *t1, *t2;
 	int k1, k2;
 recur:
-	if (depth <= 0)
-		return false;
-
 	t1 = btf_type_by_id(d->btf, id1);
 	t2 = btf_type_by_id(d->btf, id2);
+	if (depth <= 0) {
+		pr_debug("Reached depth limit for identical type comparison for '%s'/'%s'\n",
+			 btf__name_by_offset(d->btf, t1->name_off),
+			 btf__name_by_offset(d->btf, t2->name_off));
+		return false;
+	}
 
 	k1 = btf_kind(t1);
 	k2 = btf_kind(t2);
@@ -4427,8 +4565,16 @@ recur:
 		for (i = 0, n = btf_vlen(t1); i < n; i++, m1++, m2++) {
 			if (m1->type == m2->type)
 				continue;
-			if (!btf_dedup_identical_types(d, m1->type, m2->type, depth - 1))
+			if (!btf_dedup_identical_types(d, m1->type, m2->type, depth - 1)) {
+				if (t1->name_off) {
+					pr_debug("%s '%s' size=%d vlen=%d id1[%u] id2[%u] shallow-equal but not identical for field#%d '%s'\n",
+						 k1 == BTF_KIND_STRUCT ? "STRUCT" : "UNION",
+						 btf__name_by_offset(d->btf, t1->name_off),
+						 t1->size, btf_vlen(t1), id1, id2, i,
+						 btf__name_by_offset(d->btf, m1->name_off));
+				}
 				return false;
+			}
 		}
 		return true;
 	}
@@ -4669,8 +4815,16 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		canon_m = btf_members(canon_type);
 		for (i = 0; i < vlen; i++) {
 			eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type);
-			if (eq <= 0)
+			if (eq <= 0) {
+				if (cand_type->name_off) {
+					pr_debug("%s '%s' size=%d vlen=%d cand_id[%u] canon_id[%u] shallow-equal but not equiv for field#%d '%s': %d\n",
+						 cand_kind == BTF_KIND_STRUCT ? "STRUCT" : "UNION",
+						 btf__name_by_offset(d->btf, cand_type->name_off),
+						 cand_type->size, vlen, cand_id, canon_id, i,
+						 btf__name_by_offset(d->btf, cand_m->name_off), eq);
+				}
 				return eq;
+			}
 			cand_m++;
 			canon_m++;
 		}
@@ -4795,13 +4949,30 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
 	}
 }
 
+static inline long btf_hash_by_kind(struct btf_type *t, __u16 kind)
+{
+	if (kind == BTF_KIND_TYPEDEF)
+		return btf_hash_typedef(t);
+	else
+		return btf_hash_struct(t);
+}
+
+static inline bool btf_equal_by_kind(struct btf_type *t1, struct btf_type *t2, __u16 kind)
+{
+	if (kind == BTF_KIND_TYPEDEF)
+		return btf_equal_typedef(t1, t2);
+	else
+		return btf_shallow_equal_struct(t1, t2);
+}
+
 /*
- * Deduplicate struct/union types.
+ * Deduplicate struct/union and typedef types.
  *
  * For each struct/union type its type signature hash is calculated, taking
  * into account type's name, size, number, order and names of fields, but
  * ignoring type ID's referenced from fields, because they might not be deduped
- * completely until after reference types deduplication phase. This type hash
+ * completely until after reference types deduplication phase. For each typedef
+ * type, the hash is computed based on the type’s name and size. This type hash
  * is used to iterate over all potential canonical types, sharing same hash.
  * For each canonical candidate we check whether type graphs that they form
  * (through referenced types in fields and so on) are equivalent using algorithm
@@ -4833,18 +5004,20 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 	t = btf_type_by_id(d->btf, type_id);
 	kind = btf_kind(t);
 
-	if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION)
+	if (kind != BTF_KIND_STRUCT &&
+		kind != BTF_KIND_UNION &&
+		kind != BTF_KIND_TYPEDEF)
 		return 0;
 
-	h = btf_hash_struct(t);
+	h = btf_hash_by_kind(t, kind);
 	for_each_dedup_cand(d, hash_entry, h) {
 		__u32 cand_id = hash_entry->value;
 		int eq;
 
 		/*
 		 * Even though btf_dedup_is_equiv() checks for
-		 * btf_shallow_equal_struct() internally when checking two
-		 * structs (unions) for equivalence, we need to guard here
+		 * btf_equal_by_kind() internally when checking two
+		 * structs (unions) or typedefs for equivalence, we need to guard here
 		 * from picking matching FWD type as a dedup candidate.
 		 * This can happen due to hash collision. In such case just
 		 * relying on btf_dedup_is_equiv() would lead to potentially
@@ -4852,7 +5025,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 		 * FWD and compatible STRUCT/UNION are considered equivalent.
 		 */
 		cand_type = btf_type_by_id(d->btf, cand_id);
-		if (!btf_shallow_equal_struct(t, cand_type))
+		if (!btf_equal_by_kind(t, cand_type, kind))
 			continue;
 
 		btf_dedup_clear_hypot_map(d);
@@ -4890,18 +5063,18 @@ static int btf_dedup_struct_types(struct btf_dedup *d)
 /*
  * Deduplicate reference type.
  *
- * Once all primitive and struct/union types got deduplicated, we can easily
+ * Once all primitive, struct/union and typedef types got deduplicated, we can easily
  * deduplicate all other (reference) BTF types. This is done in two steps:
  *
  * 1. Resolve all referenced type IDs into their canonical type IDs. This
- * resolution can be done either immediately for primitive or struct/union types
- * (because they were deduped in previous two phases) or recursively for
+ * resolution can be done either immediately for primitive, struct/union, and typedef
+ * types (because they were deduped in previous two phases) or recursively for
  * reference types. Recursion will always terminate at either primitive or
- * struct/union type, at which point we can "unwind" chain of reference types
- * one by one. There is no danger of encountering cycles because in C type
- * system the only way to form type cycle is through struct/union, so any chain
- * of reference types, even those taking part in a type cycle, will inevitably
- * reach struct/union at some point.
+ * struct/union and typedef types, at which point we can "unwind" chain of reference
+ * types one by one. There is no danger of encountering cycles in C, as the only way to
+ * form a type cycle is through struct or union types. Go can form such cycles through
+ * typedef. Thus, any chain of reference types, even those taking part in a type cycle,
+ * will inevitably reach a struct/union or typedef type at some point.
  *
  * 2. Once all referenced type IDs are resolved into canonical ones, BTF type
  * becomes "stable", in the sense that no further deduplication will cause
@@ -4933,7 +5106,6 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_RESTRICT:
 	case BTF_KIND_PTR:
-	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_TYPE_TAG:
 		ref_type_id = btf_dedup_ref_type(d, t->type);
@@ -5331,7 +5503,10 @@ struct btf *btf__load_vmlinux_btf(void)
 		pr_warn("kernel BTF is missing at '%s', was CONFIG_DEBUG_INFO_BTF enabled?\n",
 			sysfs_btf_path);
 	} else {
-		btf = btf__parse(sysfs_btf_path, NULL);
+		btf = btf_parse_raw_mmap(sysfs_btf_path, NULL);
+		if (IS_ERR(btf))
+			btf = btf__parse(sysfs_btf_path, NULL);
+
 		if (!btf) {
 			err = -errno;
 			pr_warn("failed to read kernel BTF from '%s': %s\n",
@@ -5766,7 +5941,7 @@ void btf_set_base_btf(struct btf *btf, const struct btf *base_btf)
 {
 	btf->base_btf = (struct btf *)base_btf;
 	btf->start_id = btf__type_cnt(base_btf);
-	btf->start_str_off = base_btf->hdr->str_len;
+	btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off;
 }
 
 int btf__relocate(struct btf *btf, const struct btf *base_btf)
@@ -5777,3 +5952,136 @@ int btf__relocate(struct btf *btf, const struct btf *base_btf)
 		btf->owns_base = false;
 	return libbpf_err(err);
 }
+
+struct btf_permute {
+	struct btf *btf;
+	__u32 *id_map;
+	__u32 start_offs;
+};
+
+/* Callback function to remap individual type ID references */
+static int btf_permute_remap_type_id(__u32 *type_id, void *ctx)
+{
+	struct btf_permute *p = ctx;
+	__u32 new_id = *type_id;
+
+	/* refer to the base BTF or VOID type */
+	if (new_id < p->btf->start_id)
+		return 0;
+
+	if (new_id >= btf__type_cnt(p->btf))
+		return -EINVAL;
+
+	*type_id = p->id_map[new_id - p->btf->start_id + p->start_offs];
+	return 0;
+}
+
+int btf__permute(struct btf *btf, __u32 *id_map, __u32 id_map_cnt,
+		 const struct btf_permute_opts *opts)
+{
+	struct btf_permute p;
+	struct btf_ext *btf_ext;
+	void *nt, *new_types = NULL;
+	__u32 *order_map = NULL;
+	int err = 0, i;
+	__u32 n, id, start_offs = 0;
+
+	if (!OPTS_VALID(opts, btf_permute_opts))
+		return libbpf_err(-EINVAL);
+
+	if (btf__base_btf(btf)) {
+		n = btf->nr_types;
+	} else {
+		if (id_map[0] != 0)
+			return libbpf_err(-EINVAL);
+		n = btf__type_cnt(btf);
+		start_offs = 1;
+	}
+
+	if (id_map_cnt != n)
+		return libbpf_err(-EINVAL);
+
+	/* record the sequence of types */
+	order_map = calloc(id_map_cnt, sizeof(*id_map));
+	if (!order_map) {
+		err = -ENOMEM;
+		goto done;
+	}
+
+	new_types = calloc(btf->hdr->type_len, 1);
+	if (!new_types) {
+		err = -ENOMEM;
+		goto done;
+	}
+
+	if (btf_ensure_modifiable(btf)) {
+		err = -ENOMEM;
+		goto done;
+	}
+
+	for (i = start_offs; i < id_map_cnt; i++) {
+		id = id_map[i];
+		if (id < btf->start_id || id >= btf__type_cnt(btf)) {
+			err = -EINVAL;
+			goto done;
+		}
+		id -= btf->start_id - start_offs;
+		/* cannot be mapped to the same ID */
+		if (order_map[id]) {
+			err = -EINVAL;
+			goto done;
+		}
+		order_map[id] = i + btf->start_id - start_offs;
+	}
+
+	p.btf = btf;
+	p.id_map = id_map;
+	p.start_offs = start_offs;
+	nt = new_types;
+	for (i = start_offs; i < id_map_cnt; i++) {
+		struct btf_field_iter it;
+		const struct btf_type *t;
+		__u32 *type_id;
+		int type_size;
+
+		id = order_map[i];
+		t = btf__type_by_id(btf, id);
+		type_size = btf_type_size(t);
+		memcpy(nt, t, type_size);
+
+		/* fix up referenced IDs for BTF */
+		err = btf_field_iter_init(&it, nt, BTF_FIELD_ITER_IDS);
+		if (err)
+			goto done;
+		while ((type_id = btf_field_iter_next(&it))) {
+			err = btf_permute_remap_type_id(type_id, &p);
+			if (err)
+				goto done;
+		}
+
+		nt += type_size;
+	}
+
+	/* fix up referenced IDs for btf_ext */
+	btf_ext = OPTS_GET(opts, btf_ext, NULL);
+	if (btf_ext) {
+		err = btf_ext_visit_type_ids(btf_ext, btf_permute_remap_type_id, &p);
+		if (err)
+			goto done;
+	}
+
+	for (nt = new_types, i = 0; i < id_map_cnt - start_offs; i++) {
+		btf->type_offs[i] = nt - new_types;
+		nt += btf_type_size(nt);
+	}
+
+	free(order_map);
+	free(btf->types_data);
+	btf->types_data = new_types;
+	return 0;
+
+done:
+	free(order_map);
+	free(new_types);
+	return libbpf_err(err);
+}

src/btf.h

@@ -94,6 +94,7 @@ LIBBPF_API struct btf *btf__new_empty(void);
  * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an
  * ELF BTF section except with a base BTF on top of which split BTF should be
  * based
+ * @param base_btf base BTF object
  * @return new BTF object instance which has to be eventually freed with
  * **btf__free()**
  *
@@ -115,6 +116,10 @@ LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf);
  * When that split BTF is loaded against a (possibly changed) base, this
  * distilled base BTF will help update references to that (possibly changed)
  * base BTF.
+ * @param src_btf source split BTF object
+ * @param new_base_btf pointer to where the new base BTF object pointer will be stored
+ * @param new_split_btf pointer to where the new split BTF object pointer will be stored
+ * @return 0 on success; negative error code, otherwise
  *
  * Both the new split and its associated new base BTF must be freed by
  * the caller.
@@ -264,6 +269,9 @@ LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts);
  * to base BTF kinds, and verify those references are compatible with
  * *base_btf*; if they are, *btf* is adjusted such that is re-parented to
  * *base_btf* and type ids and strings are adjusted to accommodate this.
+ * @param btf split BTF object to relocate
+ * @param base_btf base BTF object
+ * @return 0 on success; negative error code, otherwise
  *
  * If successful, 0 is returned and **btf** now has **base_btf** as its
  * base.
@@ -273,6 +281,48 @@ LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts);
  */
 LIBBPF_API int btf__relocate(struct btf *btf, const struct btf *base_btf);
 
+struct btf_permute_opts {
+	size_t sz;
+	/* optional .BTF.ext info along the main BTF info */
+	struct btf_ext *btf_ext;
+	size_t :0;
+};
+#define btf_permute_opts__last_field btf_ext
+
+/**
+ * @brief **btf__permute()** rearranges BTF types in-place according to a specified ID mapping
+ * @param btf BTF object to permute
+ * @param id_map Array mapping original type IDs to new IDs
+ * @param id_map_cnt Number of elements in @id_map
+ * @param opts Optional parameters, including BTF extension data for reference updates
+ * @return 0 on success, negative error code on failure
+ *
+ * **btf__permute()** reorders BTF types based on the provided @id_map array,
+ * updating all internal type references to maintain consistency. The function
+ * operates in-place, modifying the BTF object directly.
+ *
+ * For **base BTF**:
+ * - @id_map must include all types from ID 0 to `btf__type_cnt(btf) - 1`
+ * - @id_map_cnt must be `btf__type_cnt(btf)`
+ * - Mapping is defined as `id_map[original_id] = new_id`
+ * - `id_map[0]` must be 0 (void type cannot be moved)
+ *
+ * For **split BTF**:
+ * - @id_map must include only split types (types added on top of the base BTF)
+ * - @id_map_cnt must be `btf__type_cnt(btf) - btf__type_cnt(btf__base_btf(btf))`
+ * - Mapping is defined as `id_map[original_id - start_id] = new_id`
+ * - `start_id` equals `btf__type_cnt(btf__base_btf(btf))`
+ *
+ * After permutation, all type references within the BTF data and optional
+ * BTF extension (if provided via @opts) are updated automatically.
+ *
+ * On error, returns a negative error code and sets errno:
+ *   - `-EINVAL`: Invalid parameters or invalid ID mapping
+ *   - `-ENOMEM`: Memory allocation failure
+ */
+LIBBPF_API int btf__permute(struct btf *btf, __u32 *id_map, __u32 id_map_cnt,
+			    const struct btf_permute_opts *opts);
+
 struct btf_dump;
 
 struct btf_dump_opts {
@@ -326,9 +376,10 @@ struct btf_dump_type_data_opts {
 	bool compact;		/* no newlines/indentation */
 	bool skip_names;	/* skip member/type names */
 	bool emit_zeroes;	/* show 0-valued fields */
+	bool emit_strings;	/* print char arrays as strings */
 	size_t :0;
 };
-#define btf_dump_type_data_opts__last_field emit_zeroes
+#define btf_dump_type_data_opts__last_field emit_strings
 
 LIBBPF_API int
 btf_dump__dump_type_data(struct btf_dump *d, __u32 id,

src/btf_dump.c

@@ -21,7 +21,6 @@
 #include "hashmap.h"
 #include "libbpf.h"
 #include "libbpf_internal.h"
-#include "str_error.h"
 
 static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t";
 static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1;
@@ -68,6 +67,7 @@ struct btf_dump_data {
 	bool compact;
 	bool skip_names;
 	bool emit_zeroes;
+	bool emit_strings;
 	__u8 indent_lvl;	/* base indent level */
 	char indent_str[BTF_DATA_INDENT_STR_LEN];
 	/* below are used during iteration */
@@ -226,6 +226,9 @@ static void btf_dump_free_names(struct hashmap *map)
 	size_t bkt;
 	struct hashmap_entry *cur;
 
+	if (!map)
+		return;
+
 	hashmap__for_each_entry(map, cur, bkt)
 		free((void *)cur->pkey);
 
@@ -1759,9 +1762,18 @@ static int btf_dump_get_bitfield_value(struct btf_dump *d,
 	__u16 left_shift_bits, right_shift_bits;
 	const __u8 *bytes = data;
 	__u8 nr_copy_bits;
+	__u8 start_bit, nr_bytes;
 	__u64 num = 0;
 	int i;
 
+	/* Calculate how many bytes cover the bitfield */
+	start_bit = bits_offset % 8;
+	nr_bytes = (start_bit + bit_sz + 7) / 8;
+
+	/* Bound check */
+	if (data + nr_bytes > d->typed_dump->data_end)
+		return -E2BIG;
+
 	/* Maximum supported bitfield size is 64 bits */
 	if (t->size > 8) {
 		pr_warn("unexpected bitfield size %d\n", t->size);
@@ -2028,6 +2040,52 @@ static int btf_dump_var_data(struct btf_dump *d,
 	return btf_dump_dump_type_data(d, NULL, t, type_id, data, 0, 0);
 }
 
+static int btf_dump_string_data(struct btf_dump *d,
+				const struct btf_type *t,
+				__u32 id,
+				const void *data)
+{
+	const struct btf_array *array = btf_array(t);
+	const char *chars = data;
+	__u32 i;
+
+	/* Make sure it is a NUL-terminated string. */
+	for (i = 0; i < array->nelems; i++) {
+		if ((void *)(chars + i) >= d->typed_dump->data_end)
+			return -E2BIG;
+		if (chars[i] == '\0')
+			break;
+	}
+	if (i == array->nelems) {
+		/* The caller will print this as a regular array. */
+		return -EINVAL;
+	}
+
+	btf_dump_data_pfx(d);
+	btf_dump_printf(d, "\"");
+
+	for (i = 0; i < array->nelems; i++) {
+		char c = chars[i];
+
+		if (c == '\0') {
+			/*
+			 * When printing character arrays as strings, NUL bytes
+			 * are always treated as string terminators; they are
+			 * never printed.
+			 */
+			break;
+		}
+		if (isprint(c))
+			btf_dump_printf(d, "%c", c);
+		else
+			btf_dump_printf(d, "\\x%02x", (__u8)c);
+	}
+
+	btf_dump_printf(d, "\"");
+
+	return 0;
+}
+
 static int btf_dump_array_data(struct btf_dump *d,
 			       const struct btf_type *t,
 			       __u32 id,
@@ -2055,8 +2113,13 @@ static int btf_dump_array_data(struct btf_dump *d,
 		 * char arrays, so if size is 1 and element is
 		 * printable as a char, we'll do that.
 		 */
-		if (elem_size == 1)
+		if (elem_size == 1) {
+			if (d->typed_dump->emit_strings &&
+			    btf_dump_string_data(d, t, id, data) == 0) {
+				return 0;
+			}
 			d->typed_dump->is_array_char = true;
+		}
 	}
 
 	/* note that we increment depth before calling btf_dump_print() below;
@@ -2544,6 +2607,7 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
 	d->typed_dump->compact = OPTS_GET(opts, compact, false);
 	d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false);
 	d->typed_dump->emit_zeroes = OPTS_GET(opts, emit_zeroes, false);
+	d->typed_dump->emit_strings = OPTS_GET(opts, emit_strings, false);
 
 	ret = btf_dump_dump_type_data(d, NULL, t, id, data, 0, 0);
 

src/elf.c

@@ -9,7 +9,6 @@
 #include <linux/kernel.h>
 
 #include "libbpf_internal.h"
-#include "str_error.h"
 
 /* A SHT_GNU_versym section holds 16-bit words. This bit is set if
  * the symbol is hidden and can only be seen when referenced using an

src/features.c

@@ -6,7 +6,6 @@
 #include "libbpf.h"
 #include "libbpf_common.h"
 #include "libbpf_internal.h"
-#include "str_error.h"
 
 static inline __u64 ptr_to_u64(const void *ptr)
 {

src/gen_loader.c

@@ -4,6 +4,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
+#include <asm/byteorder.h>
 #include <linux/filter.h>
 #include <sys/param.h>
 #include "btf.h"
@@ -13,8 +14,6 @@
 #include "hashmap.h"
 #include "bpf_gen_internal.h"
 #include "skel_internal.h"
-#include <asm/byteorder.h>
-#include "str_error.h"
 
 #define MAX_USED_MAPS	64
 #define MAX_USED_PROGS	32
@@ -110,6 +109,7 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in
 
 static int add_data(struct bpf_gen *gen, const void *data, __u32 size);
 static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off);
+static void emit_signature_match(struct bpf_gen *gen);
 
 void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps)
 {
@@ -152,6 +152,8 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps
 	/* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */
 	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
 	emit(gen, BPF_EXIT_INSN());
+	if (OPTS_GET(gen->opts, gen_hash, false))
+		emit_signature_match(gen);
 }
 
 static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
@@ -368,6 +370,8 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off)
 	__emit_sys_close(gen);
 }
 
+static void compute_sha_update_offsets(struct bpf_gen *gen);
+
 int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 {
 	int i;
@@ -394,6 +398,9 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 			      blob_fd_array_off(gen, i));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0));
 	emit(gen, BPF_EXIT_INSN());
+	if (OPTS_GET(gen->opts, gen_hash, false))
+		compute_sha_update_offsets(gen);
+
 	pr_debug("gen: finish %s\n", errstr(gen->error));
 	if (!gen->error) {
 		struct gen_loader_opts *opts = gen->opts;
@@ -446,6 +453,22 @@ void bpf_gen__free(struct bpf_gen *gen)
 	_val;							\
 })
 
+static void compute_sha_update_offsets(struct bpf_gen *gen)
+{
+	__u64 sha[SHA256_DWORD_SIZE];
+	__u64 sha_dw;
+	int i;
+
+	libbpf_sha256(gen->data_start, gen->data_cur - gen->data_start, (__u8 *)sha);
+	for (i = 0; i < SHA256_DWORD_SIZE; i++) {
+		struct bpf_insn *insn =
+			(struct bpf_insn *)(gen->insn_start + gen->hash_insn_offset[i]);
+		sha_dw = tgt_endian(sha[i]);
+		insn[0].imm = (__u32)sha_dw;
+		insn[1].imm = sha_dw >> 32;
+	}
+}
+
 void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
 		       __u32 btf_raw_size)
 {
@@ -557,6 +580,29 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 		emit_sys_close_stack(gen, stack_off(inner_map_fd));
 }
 
+static void emit_signature_match(struct bpf_gen *gen)
+{
+	__s64 off;
+	int i;
+
+	for (i = 0; i < SHA256_DWORD_SIZE; i++) {
+		emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX,
+						 0, 0, 0, 0));
+		emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, i * sizeof(__u64)));
+		gen->hash_insn_offset[i] = gen->insn_cur - gen->insn_start;
+		emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_3, 0, 0, 0, 0, 0));
+
+		off =  -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1;
+		if (is_simm16(off)) {
+			emit(gen, BPF_MOV64_IMM(BPF_REG_7, -EINVAL));
+			emit(gen, BPF_JMP_REG(BPF_JNE, BPF_REG_2, BPF_REG_3, off));
+		} else {
+			gen->error = -ERANGE;
+			emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, -1));
+		}
+	}
+}
+
 void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name,
 				   enum bpf_attach_type type)
 {

src/libbpf.c

@@ -50,7 +50,6 @@
 #include "libbpf.h"
 #include "bpf.h"
 #include "btf.h"
-#include "str_error.h"
 #include "libbpf_internal.h"
 #include "hashmap.h"
 #include "bpf_gen_internal.h"
@@ -116,6 +115,7 @@ static const char * const attach_type_name[] = {
 	[BPF_TRACE_FENTRY]		= "trace_fentry",
 	[BPF_TRACE_FEXIT]		= "trace_fexit",
 	[BPF_MODIFY_RETURN]		= "modify_return",
+	[BPF_TRACE_FSESSION]		= "trace_fsession",
 	[BPF_LSM_MAC]			= "lsm_mac",
 	[BPF_LSM_CGROUP]		= "lsm_cgroup",
 	[BPF_SK_LOOKUP]			= "sk_lookup",
@@ -191,6 +191,7 @@ static const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_USER_RINGBUF]             = "user_ringbuf",
 	[BPF_MAP_TYPE_CGRP_STORAGE]		= "cgrp_storage",
 	[BPF_MAP_TYPE_ARENA]			= "arena",
+	[BPF_MAP_TYPE_INSN_ARRAY]		= "insn_array",
 };
 
 static const char * const prog_type_name[] = {
@@ -318,8 +319,6 @@ static void pr_perm_msg(int err)
 		buf);
 }
 
-#define STRERR_BUFSIZE  128
-
 /* Copied from tools/perf/util/util.h */
 #ifndef zfree
 # define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
@@ -372,6 +371,7 @@ enum reloc_type {
 	RELO_EXTERN_CALL,
 	RELO_SUBPROG_ADDR,
 	RELO_CORE,
+	RELO_INSN_ARRAY,
 };
 
 struct reloc_desc {
@@ -381,8 +381,17 @@ struct reloc_desc {
 		const struct bpf_core_relo *core_relo; /* used when type == RELO_CORE */
 		struct {
 			int map_idx;
-			int sym_off;
-			int ext_idx;
+			unsigned int sym_off;
+			/*
+			 * The following two fields can be unionized, as the
+			 * ext_idx field is used for extern symbols, and the
+			 * sym_size is used for jump tables, which are never
+			 * extern
+			 */
+			union {
+				int ext_idx;
+				int sym_size;
+			};
 		};
 	};
 };
@@ -424,6 +433,11 @@ struct bpf_sec_def {
 	libbpf_prog_attach_fn_t prog_attach_fn;
 };
 
+struct bpf_light_subprog {
+	__u32 sec_insn_off;
+	__u32 sub_insn_off;
+};
+
 /*
  * bpf_prog should be a better name but it has been used in
  * linux/filter.h.
@@ -496,6 +510,10 @@ struct bpf_program {
 	__u32 line_info_rec_size;
 	__u32 line_info_cnt;
 	__u32 prog_flags;
+	__u8  hash[SHA256_DIGEST_LENGTH];
+
+	struct bpf_light_subprog *subprogs;
+	__u32 subprog_cnt;
 };
 
 struct bpf_struct_ops {
@@ -575,6 +593,7 @@ struct bpf_map {
 	bool autocreate;
 	bool autoattach;
 	__u64 map_extra;
+	struct bpf_program *excl_prog;
 };
 
 enum extern_type {
@@ -597,7 +616,7 @@ struct extern_desc {
 	int sym_idx;
 	int btf_id;
 	int sec_btf_id;
-	const char *name;
+	char *name;
 	char *essent_name;
 	bool is_set;
 	bool is_weak;
@@ -668,6 +687,7 @@ struct elf_state {
 	int symbols_shndx;
 	bool has_st_ops;
 	int arena_data_shndx;
+	int jumptables_data_shndx;
 };
 
 struct usdt_manager;
@@ -735,9 +755,20 @@ struct bpf_object {
 
 	struct usdt_manager *usdt_man;
 
-	struct bpf_map *arena_map;
+	int arena_map_idx;
 	void *arena_data;
 	size_t arena_data_sz;
+	size_t arena_data_off;
+
+	void *jumptables_data;
+	size_t jumptables_data_sz;
+
+	struct {
+		struct bpf_program *prog;
+		unsigned int sym_off;
+		int fd;
+	} *jumptable_maps;
+	size_t jumptable_map_cnt;
 
 	struct kern_feature_cache *feat_cache;
 	char *token_path;
@@ -765,6 +796,7 @@ void bpf_program__unload(struct bpf_program *prog)
 
 	zfree(&prog->func_info);
 	zfree(&prog->line_info);
+	zfree(&prog->subprogs);
 }
 
 static void bpf_program__exit(struct bpf_program *prog)
@@ -1013,35 +1045,33 @@ find_struct_ops_kern_types(struct bpf_object *obj, const char *tname_raw,
 	const struct btf_member *kern_data_member;
 	struct btf *btf = NULL;
 	__s32 kern_vtype_id, kern_type_id;
-	char tname[256];
+	char tname[192], stname[256];
 	__u32 i;
 
 	snprintf(tname, sizeof(tname), "%.*s",
 		 (int)bpf_core_essential_name_len(tname_raw), tname_raw);
 
-	kern_type_id = find_ksym_btf_id(obj, tname, BTF_KIND_STRUCT,
-					&btf, mod_btf);
-	if (kern_type_id < 0) {
-		pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n",
-			tname);
-		return kern_type_id;
-	}
-	kern_type = btf__type_by_id(btf, kern_type_id);
+	snprintf(stname, sizeof(stname), "%s%s", STRUCT_OPS_VALUE_PREFIX, tname);
 
-	/* Find the corresponding "map_value" type that will be used
-	 * in map_update(BPF_MAP_TYPE_STRUCT_OPS).  For example,
-	 * find "struct bpf_struct_ops_tcp_congestion_ops" from the
-	 * btf_vmlinux.
+	/* Look for the corresponding "map_value" type that will be used
+	 * in map_update(BPF_MAP_TYPE_STRUCT_OPS) first, figure out the btf
+	 * and the mod_btf.
+	 * For example, find "struct bpf_struct_ops_tcp_congestion_ops".
 	 */
-	kern_vtype_id = find_btf_by_prefix_kind(btf, STRUCT_OPS_VALUE_PREFIX,
-						tname, BTF_KIND_STRUCT);
+	kern_vtype_id = find_ksym_btf_id(obj, stname, BTF_KIND_STRUCT, &btf, mod_btf);
 	if (kern_vtype_id < 0) {
-		pr_warn("struct_ops init_kern: struct %s%s is not found in kernel BTF\n",
-			STRUCT_OPS_VALUE_PREFIX, tname);
+		pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", stname);
 		return kern_vtype_id;
 	}
 	kern_vtype = btf__type_by_id(btf, kern_vtype_id);
 
+	kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+	if (kern_type_id < 0) {
+		pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", tname);
+		return kern_type_id;
+	}
+	kern_type = btf__type_by_id(btf, kern_type_id);
+
 	/* Find "struct tcp_congestion_ops" from
 	 * struct bpf_struct_ops_tcp_congestion_ops {
 	 *	[ ... ]
@@ -1054,8 +1084,8 @@ find_struct_ops_kern_types(struct bpf_object *obj, const char *tname_raw,
 			break;
 	}
 	if (i == btf_vlen(kern_vtype)) {
-		pr_warn("struct_ops init_kern: struct %s data is not found in struct %s%s\n",
-			tname, STRUCT_OPS_VALUE_PREFIX, tname);
+		pr_warn("struct_ops init_kern: struct %s data is not found in struct %s\n",
+			tname, stname);
 		return -EINVAL;
 	}
 
@@ -1517,6 +1547,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj->efile.obj_buf_sz = obj_buf_sz;
 	obj->efile.btf_maps_shndx = -1;
 	obj->kconfig_map_idx = -1;
+	obj->arena_map_idx = -1;
 
 	obj->kern_version = get_kernel_version();
 	obj->state  = OBJ_OPEN;
@@ -2874,7 +2905,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 	var_extra = btf_var(var);
 	map_name = btf__name_by_offset(obj->btf, var->name_off);
 
-	if (map_name == NULL || map_name[0] == '\0') {
+	if (str_is_empty(map_name)) {
 		pr_warn("map #%d: empty name.\n", var_idx);
 		return -EINVAL;
 	}
@@ -2962,10 +2993,11 @@ static int init_arena_map_data(struct bpf_object *obj, struct bpf_map *map,
 			       void *data, size_t data_sz)
 {
 	const long page_sz = sysconf(_SC_PAGE_SIZE);
+	const size_t data_alloc_sz = roundup(data_sz, page_sz);
 	size_t mmap_sz;
 
-	mmap_sz = bpf_map_mmap_sz(obj->arena_map);
-	if (roundup(data_sz, page_sz) > mmap_sz) {
+	mmap_sz = bpf_map_mmap_sz(map);
+	if (data_alloc_sz > mmap_sz) {
 		pr_warn("elf: sec '%s': declared ARENA map size (%zu) is too small to hold global __arena variables of size %zu\n",
 			sec_name, mmap_sz, data_sz);
 		return -E2BIG;
@@ -2977,6 +3009,9 @@ static int init_arena_map_data(struct bpf_object *obj, struct bpf_map *map,
 	memcpy(obj->arena_data, data, data_sz);
 	obj->arena_data_sz = data_sz;
 
+	/* place globals at the end of the arena */
+	obj->arena_data_off = mmap_sz - data_alloc_sz;
+
 	/* make bpf_map__init_value() work for ARENA maps */
 	map->mmaped = obj->arena_data;
 
@@ -2998,7 +3033,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
 
 	scn = elf_sec_by_idx(obj, obj->efile.btf_maps_shndx);
 	data = elf_sec_data(obj, scn);
-	if (!scn || !data) {
+	if (!data) {
 		pr_warn("elf: failed to get %s map definitions for %s\n",
 			MAPS_ELF_SEC, obj->path);
 		return -EINVAL;
@@ -3038,12 +3073,12 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
 		if (map->def.type != BPF_MAP_TYPE_ARENA)
 			continue;
 
-		if (obj->arena_map) {
+		if (obj->arena_map_idx >= 0) {
 			pr_warn("map '%s': only single ARENA map is supported (map '%s' is also ARENA)\n",
-				map->name, obj->arena_map->name);
+				map->name, obj->maps[obj->arena_map_idx].name);
 			return -EINVAL;
 		}
-		obj->arena_map = map;
+		obj->arena_map_idx = i;
 
 		if (obj->efile.arena_data) {
 			err = init_arena_map_data(obj, map, ARENA_SEC, obj->efile.arena_data_shndx,
@@ -3053,7 +3088,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
 				return err;
 		}
 	}
-	if (obj->efile.arena_data && !obj->arena_map) {
+	if (obj->efile.arena_data && obj->arena_map_idx < 0) {
 		pr_warn("elf: sec '%s': to use global __arena variables the ARENA map should be explicitly declared in SEC(\".maps\")\n",
 			ARENA_SEC);
 		return -ENOENT;
@@ -3944,6 +3979,13 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			} else if (strcmp(name, ARENA_SEC) == 0) {
 				obj->efile.arena_data = data;
 				obj->efile.arena_data_shndx = idx;
+			} else if (strcmp(name, JUMPTABLES_SEC) == 0) {
+				obj->jumptables_data = malloc(data->d_size);
+				if (!obj->jumptables_data)
+					return -ENOMEM;
+				memcpy(obj->jumptables_data, data->d_buf, data->d_size);
+				obj->jumptables_data_sz = data->d_size;
+				obj->efile.jumptables_data_shndx = idx;
 			} else {
 				pr_info("elf: skipping unrecognized data section(%d) %s\n",
 					idx, name);
@@ -4240,7 +4282,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 		if (!sym_is_extern(sym))
 			continue;
 		ext_name = elf_sym_str(obj, sym->st_name);
-		if (!ext_name || !ext_name[0])
+		if (str_is_empty(ext_name))
 			continue;
 
 		ext = obj->externs;
@@ -4259,7 +4301,9 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 			return ext->btf_id;
 		}
 		t = btf__type_by_id(obj->btf, ext->btf_id);
-		ext->name = btf__name_by_offset(obj->btf, t->name_off);
+		ext->name = strdup(btf__name_by_offset(obj->btf, t->name_off));
+		if (!ext->name)
+			return -ENOMEM;
 		ext->sym_idx = i;
 		ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK;
 
@@ -4482,6 +4526,44 @@ bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx)
 	}
 }
 
+static int bpf_prog_compute_hash(struct bpf_program *prog)
+{
+	struct bpf_insn *purged;
+	int i, err = 0;
+
+	purged = calloc(prog->insns_cnt, BPF_INSN_SZ);
+	if (!purged)
+		return -ENOMEM;
+
+	/* If relocations have been done, the map_fd needs to be
+	 * discarded for the digest calculation.
+	 */
+	for (i = 0; i < prog->insns_cnt; i++) {
+		purged[i] = prog->insns[i];
+		if (purged[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
+		    (purged[i].src_reg == BPF_PSEUDO_MAP_FD ||
+		     purged[i].src_reg == BPF_PSEUDO_MAP_VALUE)) {
+			purged[i].imm = 0;
+			i++;
+			if (i >= prog->insns_cnt ||
+			    prog->insns[i].code != 0 ||
+			    prog->insns[i].dst_reg != 0 ||
+			    prog->insns[i].src_reg != 0 ||
+			    prog->insns[i].off != 0) {
+				err = -EINVAL;
+				goto out;
+			}
+			purged[i] = prog->insns[i];
+			purged[i].imm = 0;
+		}
+	}
+	libbpf_sha256(purged, prog->insns_cnt * sizeof(struct bpf_insn),
+		      prog->hash);
+out:
+	free(purged);
+	return err;
+}
+
 static int bpf_program__record_reloc(struct bpf_program *prog,
 				     struct reloc_desc *reloc_desc,
 				     __u32 insn_idx, const char *sym_name,
@@ -4579,10 +4661,30 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
 
 	/* arena data relocation */
 	if (shdr_idx == obj->efile.arena_data_shndx) {
+		if (obj->arena_map_idx < 0) {
+			pr_warn("prog '%s': bad arena data relocation at insn %u, no arena maps defined\n",
+				prog->name, insn_idx);
+			return -LIBBPF_ERRNO__RELOC;
+		}
 		reloc_desc->type = RELO_DATA;
 		reloc_desc->insn_idx = insn_idx;
-		reloc_desc->map_idx = obj->arena_map - obj->maps;
+		reloc_desc->map_idx = obj->arena_map_idx;
+		reloc_desc->sym_off = sym->st_value + obj->arena_data_off;
+
+		map = &obj->maps[obj->arena_map_idx];
+		pr_debug("prog '%s': found arena map %d (%s, sec %d, off %zu) for insn %u\n",
+			 prog->name, obj->arena_map_idx, map->name, map->sec_idx,
+			 map->sec_offset, insn_idx);
+		return 0;
+	}
+
+	/* jump table data relocation */
+	if (shdr_idx == obj->efile.jumptables_data_shndx) {
+		reloc_desc->type = RELO_INSN_ARRAY;
+		reloc_desc->insn_idx = insn_idx;
+		reloc_desc->map_idx = -1;
 		reloc_desc->sym_off = sym->st_value;
+		reloc_desc->sym_size = sym->st_size;
 		return 0;
 	}
 
@@ -5080,6 +5182,16 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
 		return false;
 	}
 
+	/*
+	 * bpf_get_map_info_by_fd() for DEVMAP will always return flags with
+	 * BPF_F_RDONLY_PROG set, but it generally is not set at map creation time.
+	 * Thus, ignore the BPF_F_RDONLY_PROG flag in the flags returned from
+	 * bpf_get_map_info_by_fd() when checking for compatibility with an
+	 * existing DEVMAP.
+	 */
+	if (map->def.type == BPF_MAP_TYPE_DEVMAP || map->def.type == BPF_MAP_TYPE_DEVMAP_HASH)
+		map_info.map_flags &= ~BPF_F_RDONLY_PROG;
+
 	return (map_info.type == map->def.type &&
 		map_info.key_size == map->def.key_size &&
 		map_info.value_size == map->def.value_size &&
@@ -5211,6 +5323,14 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 	create_attr.token_fd = obj->token_fd;
 	if (obj->token_fd)
 		create_attr.map_flags |= BPF_F_TOKEN_FD;
+	if (map->excl_prog) {
+		err = bpf_prog_compute_hash(map->excl_prog);
+		if (err)
+			return err;
+
+		create_attr.excl_prog_hash = map->excl_prog->hash;
+		create_attr.excl_prog_hash_size = SHA256_DIGEST_LENGTH;
+	}
 
 	if (bpf_map__is_struct_ops(map)) {
 		create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id;
@@ -5510,7 +5630,8 @@ retry:
 					return err;
 				}
 				if (obj->arena_data) {
-					memcpy(map->mmaped, obj->arena_data, obj->arena_data_sz);
+					memcpy(map->mmaped + obj->arena_data_off, obj->arena_data,
+						obj->arena_data_sz);
 					zfree(&obj->arena_data);
 				}
 			}
@@ -6078,6 +6199,157 @@ static void poison_kfunc_call(struct bpf_program *prog, int relo_idx,
 	insn->imm = POISON_CALL_KFUNC_BASE + ext_idx;
 }
 
+static int find_jt_map(struct bpf_object *obj, struct bpf_program *prog, unsigned int sym_off)
+{
+	size_t i;
+
+	for (i = 0; i < obj->jumptable_map_cnt; i++) {
+		/*
+		 * This might happen that same offset is used for two different
+		 * programs (as jump tables can be the same). However, for
+		 * different programs different maps should be created.
+		 */
+		if (obj->jumptable_maps[i].sym_off == sym_off &&
+		    obj->jumptable_maps[i].prog == prog)
+			return obj->jumptable_maps[i].fd;
+	}
+
+	return -ENOENT;
+}
+
+static int add_jt_map(struct bpf_object *obj, struct bpf_program *prog, unsigned int sym_off, int map_fd)
+{
+	size_t cnt = obj->jumptable_map_cnt;
+	size_t size = sizeof(obj->jumptable_maps[0]);
+	void *tmp;
+
+	tmp = libbpf_reallocarray(obj->jumptable_maps, cnt + 1, size);
+	if (!tmp)
+		return -ENOMEM;
+
+	obj->jumptable_maps = tmp;
+	obj->jumptable_maps[cnt].prog = prog;
+	obj->jumptable_maps[cnt].sym_off = sym_off;
+	obj->jumptable_maps[cnt].fd = map_fd;
+	obj->jumptable_map_cnt++;
+
+	return 0;
+}
+
+static int find_subprog_idx(struct bpf_program *prog, int insn_idx)
+{
+	int i;
+
+	for (i = prog->subprog_cnt - 1; i >= 0; i--) {
+		if (insn_idx >= prog->subprogs[i].sub_insn_off)
+			return i;
+	}
+
+	return -1;
+}
+
+static int create_jt_map(struct bpf_object *obj, struct bpf_program *prog, struct reloc_desc *relo)
+{
+	const __u32 jt_entry_size = 8;
+	unsigned int sym_off = relo->sym_off;
+	int jt_size = relo->sym_size;
+	__u32 max_entries = jt_size / jt_entry_size;
+	__u32 value_size = sizeof(struct bpf_insn_array_value);
+	struct bpf_insn_array_value val = {};
+	int subprog_idx;
+	int map_fd, err;
+	__u64 insn_off;
+	__u64 *jt;
+	__u32 i;
+
+	map_fd = find_jt_map(obj, prog, sym_off);
+	if (map_fd >= 0)
+		return map_fd;
+
+	if (sym_off % jt_entry_size) {
+		pr_warn("map '.jumptables': jumptable start %u should be multiple of %u\n",
+			sym_off, jt_entry_size);
+		return -EINVAL;
+	}
+
+	if (jt_size % jt_entry_size) {
+		pr_warn("map '.jumptables': jumptable size %d should be multiple of %u\n",
+			jt_size, jt_entry_size);
+		return -EINVAL;
+	}
+
+	map_fd = bpf_map_create(BPF_MAP_TYPE_INSN_ARRAY, ".jumptables",
+				4, value_size, max_entries, NULL);
+	if (map_fd < 0)
+		return map_fd;
+
+	if (!obj->jumptables_data) {
+		pr_warn("map '.jumptables': ELF file is missing jump table data\n");
+		err = -EINVAL;
+		goto err_close;
+	}
+	if (sym_off + jt_size > obj->jumptables_data_sz) {
+		pr_warn("map '.jumptables': jumptables_data size is %zd, trying to access %d\n",
+			obj->jumptables_data_sz, sym_off + jt_size);
+		err = -EINVAL;
+		goto err_close;
+	}
+
+	subprog_idx = -1; /* main program */
+	if (relo->insn_idx < 0 || relo->insn_idx >= prog->insns_cnt) {
+		pr_warn("map '.jumptables': invalid instruction index %d\n", relo->insn_idx);
+		err = -EINVAL;
+		goto err_close;
+	}
+	if (prog->subprogs)
+		subprog_idx = find_subprog_idx(prog, relo->insn_idx);
+
+	jt = (__u64 *)(obj->jumptables_data + sym_off);
+	for (i = 0; i < max_entries; i++) {
+		/*
+		 * The offset should be made to be relative to the beginning of
+		 * the main function, not the subfunction.
+		 */
+		insn_off = jt[i]/sizeof(struct bpf_insn);
+		if (subprog_idx >= 0) {
+			insn_off -= prog->subprogs[subprog_idx].sec_insn_off;
+			insn_off += prog->subprogs[subprog_idx].sub_insn_off;
+		} else {
+			insn_off -= prog->sec_insn_off;
+		}
+
+		/*
+		 * LLVM-generated jump tables contain u64 records, however
+		 * should contain values that fit in u32.
+		 */
+		if (insn_off > UINT32_MAX) {
+			pr_warn("map '.jumptables': invalid jump table value 0x%llx at offset %u\n",
+				(long long)jt[i], sym_off + i * jt_entry_size);
+			err = -EINVAL;
+			goto err_close;
+		}
+
+		val.orig_off = insn_off;
+		err = bpf_map_update_elem(map_fd, &i, &val, 0);
+		if (err)
+			goto err_close;
+	}
+
+	err = bpf_map_freeze(map_fd);
+	if (err)
+		goto err_close;
+
+	err = add_jt_map(obj, prog, sym_off, map_fd);
+	if (err)
+		goto err_close;
+
+	return map_fd;
+
+err_close:
+	close(map_fd);
+	return err;
+}
+
 /* Relocate data references within program code:
  *  - map references;
  *  - global variable references;
@@ -6169,6 +6441,20 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 		case RELO_CORE:
 			/* will be handled by bpf_program_record_relos() */
 			break;
+		case RELO_INSN_ARRAY: {
+			int map_fd;
+
+			map_fd = create_jt_map(obj, prog, relo);
+			if (map_fd < 0) {
+				pr_warn("prog '%s': relo #%d: can't create jump table: sym_off %u\n",
+					prog->name, i, relo->sym_off);
+				return map_fd;
+			}
+			insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
+			insn->imm = map_fd;
+			insn->off = 0;
+		}
+			break;
 		default:
 			pr_warn("prog '%s': relo #%d: bad relo type %d\n",
 				prog->name, i, relo->type);
@@ -6366,36 +6652,62 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra
 	return 0;
 }
 
+static int save_subprog_offsets(struct bpf_program *main_prog, struct bpf_program *subprog)
+{
+	size_t size = sizeof(main_prog->subprogs[0]);
+	int cnt = main_prog->subprog_cnt;
+	void *tmp;
+
+	tmp = libbpf_reallocarray(main_prog->subprogs, cnt + 1, size);
+	if (!tmp)
+		return -ENOMEM;
+
+	main_prog->subprogs = tmp;
+	main_prog->subprogs[cnt].sec_insn_off = subprog->sec_insn_off;
+	main_prog->subprogs[cnt].sub_insn_off = subprog->sub_insn_off;
+	main_prog->subprog_cnt++;
+
+	return 0;
+}
+
 static int
 bpf_object__append_subprog_code(struct bpf_object *obj, struct bpf_program *main_prog,
 				struct bpf_program *subprog)
 {
-       struct bpf_insn *insns;
-       size_t new_cnt;
-       int err;
+	struct bpf_insn *insns;
+	size_t new_cnt;
+	int err;
 
-       subprog->sub_insn_off = main_prog->insns_cnt;
+	subprog->sub_insn_off = main_prog->insns_cnt;
 
-       new_cnt = main_prog->insns_cnt + subprog->insns_cnt;
-       insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns));
-       if (!insns) {
-               pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name);
-               return -ENOMEM;
-       }
-       main_prog->insns = insns;
-       main_prog->insns_cnt = new_cnt;
+	new_cnt = main_prog->insns_cnt + subprog->insns_cnt;
+	insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns));
+	if (!insns) {
+		pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name);
+		return -ENOMEM;
+	}
+	main_prog->insns = insns;
+	main_prog->insns_cnt = new_cnt;
 
-       memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns,
-              subprog->insns_cnt * sizeof(*insns));
+	memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns,
+	       subprog->insns_cnt * sizeof(*insns));
 
-       pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n",
-                main_prog->name, subprog->insns_cnt, subprog->name);
+	pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n",
+		 main_prog->name, subprog->insns_cnt, subprog->name);
 
-       /* The subprog insns are now appended. Append its relos too. */
-       err = append_subprog_relos(main_prog, subprog);
-       if (err)
-               return err;
-       return 0;
+	/* The subprog insns are now appended. Append its relos too. */
+	err = append_subprog_relos(main_prog, subprog);
+	if (err)
+		return err;
+
+	err = save_subprog_offsets(main_prog, subprog);
+	if (err) {
+		pr_warn("prog '%s': failed to add subprog offsets: %s\n",
+			main_prog->name, errstr(err));
+		return err;
+	}
+
+	return 0;
 }
 
 static int
@@ -8179,7 +8491,7 @@ static int kallsyms_cb(unsigned long long sym_addr, char sym_type,
 	struct bpf_object *obj = ctx;
 	const struct btf_type *t;
 	struct extern_desc *ext;
-	char *res;
+	const char *res;
 
 	res = strstr(sym_name, ".llvm.");
 	if (sym_type == 'd' && res)
@@ -9138,8 +9450,10 @@ void bpf_object__close(struct bpf_object *obj)
 	zfree(&obj->btf_custom_path);
 	zfree(&obj->kconfig);
 
-	for (i = 0; i < obj->nr_extern; i++)
+	for (i = 0; i < obj->nr_extern; i++) {
+		zfree(&obj->externs[i].name);
 		zfree(&obj->externs[i].essent_name);
+	}
 
 	zfree(&obj->externs);
 	obj->nr_extern = 0;
@@ -9160,6 +9474,13 @@ void bpf_object__close(struct bpf_object *obj)
 
 	zfree(&obj->arena_data);
 
+	zfree(&obj->jumptables_data);
+	obj->jumptables_data_sz = 0;
+
+	for (i = 0; i < obj->jumptable_map_cnt; i++)
+		close(obj->jumptable_maps[i].fd);
+	zfree(&obj->jumptable_maps);
+
 	free(obj);
 }
 
@@ -9206,7 +9527,7 @@ int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts)
 		return libbpf_err(-EFAULT);
 	if (!OPTS_VALID(opts, gen_loader_opts))
 		return libbpf_err(-EINVAL);
-	gen = calloc(sizeof(*gen), 1);
+	gen = calloc(1, sizeof(*gen));
 	if (!gen)
 		return libbpf_err(-ENOMEM);
 	gen->opts = opts;
@@ -9539,6 +9860,8 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("fentry.s+",		TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace),
 	SEC_DEF("fmod_ret.s+",		TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace),
 	SEC_DEF("fexit.s+",		TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace),
+	SEC_DEF("fsession+",		TRACING, BPF_TRACE_FSESSION, SEC_ATTACH_BTF, attach_trace),
+	SEC_DEF("fsession.s+",		TRACING, BPF_TRACE_FSESSION, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace),
 	SEC_DEF("freplace+",		EXT, 0, SEC_ATTACH_BTF, attach_trace),
 	SEC_DEF("lsm+",			LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm),
 	SEC_DEF("lsm.s+",		LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm),
@@ -10081,7 +10404,7 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name,
 			      enum bpf_attach_type attach_type,
 			      int *btf_obj_fd, int *btf_type_id)
 {
-	int ret, i, mod_len;
+	int ret, i, mod_len = 0;
 	const char *fn_name, *mod_name = NULL;
 
 	fn_name = strchr(attach_name, ':');
@@ -10499,6 +10822,27 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd)
 	return 0;
 }
 
+int bpf_map__set_exclusive_program(struct bpf_map *map, struct bpf_program *prog)
+{
+	if (map_is_created(map)) {
+		pr_warn("exclusive programs must be set before map creation\n");
+		return libbpf_err(-EINVAL);
+	}
+
+	if (map->obj != prog->obj) {
+		pr_warn("excl_prog and map must be from the same bpf object\n");
+		return libbpf_err(-EINVAL);
+	}
+
+	map->excl_prog = prog;
+	return 0;
+}
+
+struct bpf_program *bpf_map__exclusive_program(struct bpf_map *map)
+{
+	return map->excl_prog;
+}
+
 static struct bpf_map *
 __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
 {
@@ -10578,7 +10922,7 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name)
 }
 
 static int validate_map_op(const struct bpf_map *map, size_t key_sz,
-			   size_t value_sz, bool check_value_sz)
+			   size_t value_sz, bool check_value_sz, __u64 flags)
 {
 	if (!map_is_created(map)) /* map is not yet created */
 		return -ENOENT;
@@ -10605,6 +10949,20 @@ static int validate_map_op(const struct bpf_map *map, size_t key_sz,
 		int num_cpu = libbpf_num_possible_cpus();
 		size_t elem_sz = roundup(map->def.value_size, 8);
 
+		if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) {
+			if ((flags & BPF_F_CPU) && (flags & BPF_F_ALL_CPUS)) {
+				pr_warn("map '%s': BPF_F_CPU and BPF_F_ALL_CPUS are mutually exclusive\n",
+					map->name);
+				return -EINVAL;
+			}
+			if (map->def.value_size != value_sz) {
+				pr_warn("map '%s': unexpected value size %zu provided for either BPF_F_CPU or BPF_F_ALL_CPUS, expected %u\n",
+					map->name, value_sz, map->def.value_size);
+				return -EINVAL;
+			}
+			break;
+		}
+
 		if (value_sz != num_cpu * elem_sz) {
 			pr_warn("map '%s': unexpected value size %zu provided for per-CPU map, expected %d * %zu = %zd\n",
 				map->name, value_sz, num_cpu, elem_sz, num_cpu * elem_sz);
@@ -10629,7 +10987,7 @@ int bpf_map__lookup_elem(const struct bpf_map *map,
 {
 	int err;
 
-	err = validate_map_op(map, key_sz, value_sz, true);
+	err = validate_map_op(map, key_sz, value_sz, true, flags);
 	if (err)
 		return libbpf_err(err);
 
@@ -10642,7 +11000,7 @@ int bpf_map__update_elem(const struct bpf_map *map,
 {
 	int err;
 
-	err = validate_map_op(map, key_sz, value_sz, true);
+	err = validate_map_op(map, key_sz, value_sz, true, flags);
 	if (err)
 		return libbpf_err(err);
 
@@ -10654,7 +11012,7 @@ int bpf_map__delete_elem(const struct bpf_map *map,
 {
 	int err;
 
-	err = validate_map_op(map, key_sz, 0, false /* check_value_sz */);
+	err = validate_map_op(map, key_sz, 0, false /* check_value_sz */, flags);
 	if (err)
 		return libbpf_err(err);
 
@@ -10667,7 +11025,7 @@ int bpf_map__lookup_and_delete_elem(const struct bpf_map *map,
 {
 	int err;
 
-	err = validate_map_op(map, key_sz, value_sz, true);
+	err = validate_map_op(map, key_sz, value_sz, true, flags);
 	if (err)
 		return libbpf_err(err);
 
@@ -10679,7 +11037,7 @@ int bpf_map__get_next_key(const struct bpf_map *map,
 {
 	int err;
 
-	err = validate_map_op(map, key_sz, 0, false /* check_value_sz */);
+	err = validate_map_op(map, key_sz, 0, false /* check_value_sz */, 0);
 	if (err)
 		return libbpf_err(err);
 
@@ -10950,11 +11308,14 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p
 		}
 		link->link.fd = pfd;
 	}
-	if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
-		err = -errno;
-		pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n",
-			prog->name, pfd, errstr(err));
-		goto err_out;
+
+	if (!OPTS_GET(opts, dont_enable, false)) {
+		if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
+			err = -errno;
+			pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n",
+				prog->name, pfd, errstr(err));
+			goto err_out;
+		}
 	}
 
 	return &link->link;
@@ -11233,8 +11594,6 @@ static const char *arch_specific_syscall_pfx(void)
 	return "ia32";
 #elif defined(__s390x__)
 	return "s390x";
-#elif defined(__s390__)
-	return "s390";
 #elif defined(__arm__)
 	return "arm";
 #elif defined(__aarch64__)
@@ -11482,7 +11841,8 @@ static int avail_kallsyms_cb(unsigned long long sym_addr, char sym_type,
 		 *
 		 *   [0] fb6a421fb615 ("kallsyms: Match symbols exactly with CONFIG_LTO_CLANG")
 		 */
-		char sym_trim[256], *psym_trim = sym_trim, *sym_sfx;
+		char sym_trim[256], *psym_trim = sym_trim;
+		const char *sym_sfx;
 
 		if (!(sym_sfx = strstr(sym_name, ".llvm.")))
 			return 0;
@@ -12021,8 +12381,6 @@ static const char *arch_specific_lib_paths(void)
 	return "/lib/i386-linux-gnu";
 #elif defined(__s390x__)
 	return "/lib/s390x-linux-gnu";
-#elif defined(__s390__)
-	return "/lib/s390-linux-gnu";
 #elif defined(__arm__) && defined(__SOFTFP__)
 	return "/lib/arm-linux-gnueabi";
 #elif defined(__arm__) && !defined(__SOFTFP__)
@@ -12067,7 +12425,7 @@ static int resolve_full_path(const char *file, char *result, size_t result_sz)
 		if (!search_paths[i])
 			continue;
 		for (s = search_paths[i]; s != NULL; s = strchr(s, ':')) {
-			char *next_path;
+			const char *next_path;
 			int seg_len;
 
 			if (s[0] == ':')
@@ -12837,6 +13195,34 @@ struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifi
 	return bpf_program_attach_fd(prog, ifindex, "xdp", NULL);
 }
 
+struct bpf_link *
+bpf_program__attach_cgroup_opts(const struct bpf_program *prog, int cgroup_fd,
+				const struct bpf_cgroup_opts *opts)
+{
+	LIBBPF_OPTS(bpf_link_create_opts, link_create_opts);
+	__u32 relative_id;
+	int relative_fd;
+
+	if (!OPTS_VALID(opts, bpf_cgroup_opts))
+		return libbpf_err_ptr(-EINVAL);
+
+	relative_id = OPTS_GET(opts, relative_id, 0);
+	relative_fd = OPTS_GET(opts, relative_fd, 0);
+
+	if (relative_fd && relative_id) {
+		pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n",
+			prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
+	link_create_opts.cgroup.expected_revision = OPTS_GET(opts, expected_revision, 0);
+	link_create_opts.cgroup.relative_fd = relative_fd;
+	link_create_opts.cgroup.relative_id = relative_id;
+	link_create_opts.flags = OPTS_GET(opts, flags, 0);
+
+	return bpf_program_attach_fd(prog, cgroup_fd, "cgroup", &link_create_opts);
+}
+
 struct bpf_link *
 bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
 			const struct bpf_tcx_opts *opts)
@@ -13738,8 +14124,8 @@ int bpf_program__set_attach_target(struct bpf_program *prog,
 		return libbpf_err(-EINVAL);
 
 	if (attach_prog_fd && !attach_func_name) {
-		/* remember attach_prog_fd and let bpf_program__load() find
-		 * BTF ID during the program load
+		/* Store attach_prog_fd. The BTF ID will be resolved later during
+		 * the normal object/program load phase.
 		 */
 		prog->attach_prog_fd = attach_prog_fd;
 		return 0;
@@ -13771,6 +14157,37 @@ int bpf_program__set_attach_target(struct bpf_program *prog,
 	return 0;
 }
 
+int bpf_program__assoc_struct_ops(struct bpf_program *prog, struct bpf_map *map,
+				  struct bpf_prog_assoc_struct_ops_opts *opts)
+{
+	int prog_fd, map_fd;
+
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		pr_warn("prog '%s': can't associate BPF program without FD (was it loaded?)\n",
+			prog->name);
+		return libbpf_err(-EINVAL);
+	}
+
+	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) {
+		pr_warn("prog '%s': can't associate struct_ops program\n", prog->name);
+		return libbpf_err(-EINVAL);
+	}
+
+	map_fd = bpf_map__fd(map);
+	if (map_fd < 0) {
+		pr_warn("map '%s': can't associate BPF map without FD (was it created?)\n", map->name);
+		return libbpf_err(-EINVAL);
+	}
+
+	if (!bpf_map__is_struct_ops(map)) {
+		pr_warn("map '%s': can't associate non-struct_ops map\n", map->name);
+		return libbpf_err(-EINVAL);
+	}
+
+	return bpf_prog_assoc_struct_ops(prog_fd, map_fd, opts);
+}
+
 int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz)
 {
 	int err = 0, n, len, start, end = -1;
@@ -14036,7 +14453,10 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
 		if (!map_skel->mmaped)
 			continue;
 
-		*map_skel->mmaped = map->mmaped;
+		if (map->def.type == BPF_MAP_TYPE_ARENA)
+			*map_skel->mmaped = map->mmaped + map->obj->arena_data_off;
+		else
+			*map_skel->mmaped = map->mmaped;
 	}
 
 	return 0;

src/libbpf.h

@@ -24,8 +24,25 @@
 extern "C" {
 #endif
 
+/**
+ * @brief **libbpf_major_version()** provides the major version of libbpf.
+ * @return An integer, the major version number
+ */
 LIBBPF_API __u32 libbpf_major_version(void);
+
+/**
+ * @brief **libbpf_minor_version()** provides the minor version of libbpf.
+ * @return An integer, the minor version number
+ */
 LIBBPF_API __u32 libbpf_minor_version(void);
+
+/**
+ * @brief **libbpf_version_string()** provides the version of libbpf in a
+ * human-readable form, e.g., "v1.7".
+ * @return Pointer to a static string containing the version
+ *
+ * The format is *not* a part of a stable API and may change in the future.
+ */
 LIBBPF_API const char *libbpf_version_string(void);
 
 enum libbpf_errno {
@@ -49,6 +66,14 @@ enum libbpf_errno {
 	__LIBBPF_ERRNO__END,
 };
 
+/**
+ * @brief **libbpf_strerror()** converts the provided error code into a
+ * human-readable string.
+ * @param err The error code to convert
+ * @param buf Pointer to a buffer where the error message will be stored
+ * @param size The number of bytes in the buffer
+ * @return 0, on success; negative error code, otherwise
+ */
 LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size);
 
 /**
@@ -252,7 +277,7 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
  * @return 0, on success; negative error code, otherwise, error code is
  * stored in errno
  */
-int bpf_object__prepare(struct bpf_object *obj);
+LIBBPF_API int bpf_object__prepare(struct bpf_object *obj);
 
 /**
  * @brief **bpf_object__load()** loads BPF object into kernel.
@@ -423,7 +448,7 @@ LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
 
 /**
  * @brief **bpf_program__unpin()** unpins the BPF program from a file
- * in the BPFFS specified by a path. This decrements the programs
+ * in the BPFFS specified by a path. This decrements program's in-kernel
  * reference count.
  *
  * The file pinning the BPF program can also be unlinked by a different
@@ -456,14 +481,12 @@ LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path);
 
 /**
  * @brief **bpf_link__unpin()** unpins the BPF link from a file
- * in the BPFFS specified by a path. This decrements the links
- * reference count.
+ * in the BPFFS. This decrements link's in-kernel reference count.
  *
  * The file pinning the BPF link can also be unlinked by a different
  * process in which case this function will return an error.
  *
- * @param prog BPF program to unpin
- * @param path file path to the pin in a BPF file system
+ * @param link BPF link to unpin
  * @return 0, on success; negative error code, otherwise
  */
 LIBBPF_API int bpf_link__unpin(struct bpf_link *link);
@@ -499,9 +522,11 @@ struct bpf_perf_event_opts {
 	__u64 bpf_cookie;
 	/* don't use BPF link when attach BPF program */
 	bool force_ioctl_attach;
+	/* don't automatically enable the event */
+	bool dont_enable;
 	size_t :0;
 };
-#define bpf_perf_event_opts__last_field force_ioctl_attach
+#define bpf_perf_event_opts__last_field dont_enable
 
 LIBBPF_API struct bpf_link *
 bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd);
@@ -877,6 +902,21 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex,
 			   const struct bpf_netkit_opts *opts);
 
+struct bpf_cgroup_opts {
+	/* size of this struct, for forward/backward compatibility */
+	size_t sz;
+	__u32 flags;
+	__u32 relative_fd;
+	__u32 relative_id;
+	__u64 expected_revision;
+	size_t :0;
+};
+#define bpf_cgroup_opts__last_field expected_revision
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_cgroup_opts(const struct bpf_program *prog, int cgroup_fd,
+				const struct bpf_cgroup_opts *opts);
+
 struct bpf_map;
 
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
@@ -953,14 +993,35 @@ LIBBPF_API __u32 bpf_program__line_info_cnt(const struct bpf_program *prog);
  *   - fentry/fexit/fmod_ret;
  *   - lsm;
  *   - freplace.
- * @param prog BPF program to set the attach type for
- * @param type attach type to set the BPF map to have
+ * @param prog BPF program to configure; must be not yet loaded.
+ * @param attach_prog_fd FD of target BPF program (for freplace/extension).
+ * If >0 and func name omitted, defers BTF ID resolution.
+ * @param attach_func_name Target function name. Used either with
+ * attach_prog_fd to find destination BTF type ID in that BPF program, or
+ * alone (no attach_prog_fd) to resolve kernel (vmlinux/module) BTF ID.
+ * Must be provided if attach_prog_fd is 0.
  * @return error code; or 0 if no error occurred.
  */
 LIBBPF_API int
 bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd,
 			       const char *attach_func_name);
 
+struct bpf_prog_assoc_struct_ops_opts; /* defined in bpf.h */
+
+/**
+ * @brief **bpf_program__assoc_struct_ops()** associates a BPF program with a
+ * struct_ops map.
+ *
+ * @param prog BPF program
+ * @param map struct_ops map to be associated with the BPF program
+ * @param opts optional options, can be NULL
+ *
+ * @return 0, on success; negative error code, otherwise
+ */
+LIBBPF_API int
+bpf_program__assoc_struct_ops(struct bpf_program *prog, struct bpf_map *map,
+			      struct bpf_prog_assoc_struct_ops_opts *opts);
+
 /**
  * @brief **bpf_object__find_map_by_name()** returns BPF map of
  * the given name, if it exists within the passed BPF object
@@ -1056,6 +1117,7 @@ LIBBPF_API __u32 bpf_map__value_size(const struct bpf_map *map);
 /**
  * @brief **bpf_map__set_value_size()** sets map value size.
  * @param map the BPF map instance
+ * @param size the new value size
  * @return 0, on success; negative error, otherwise
  *
  * There is a special case for maps with associated memory-mapped regions, like
@@ -1154,13 +1216,14 @@ LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map);
  * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size**
  * @param value pointer to memory in which looked up value will be stored
  * @param value_sz size in byte of value data memory; it has to match BPF map
- * definition's **value_size**. For per-CPU BPF maps value size has to be
- * a product of BPF map value size and number of possible CPUs in the system
- * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for
- * per-CPU values value size has to be aligned up to closest 8 bytes for
- * alignment reasons, so expected size is: `round_up(value_size, 8)
- * * libbpf_num_possible_cpus()`.
- * @flags extra flags passed to kernel for this operation
+ * definition's **value_size**. For per-CPU BPF maps, value size can be
+ * `value_size` if either **BPF_F_CPU** or **BPF_F_ALL_CPUS** is specified
+ * in **flags**, otherwise a product of BPF map value size and number of
+ * possible CPUs in the system (could be fetched with
+ * **libbpf_num_possible_cpus()**). Note also that for per-CPU values value
+ * size has to be aligned up to closest 8 bytes, so expected size is:
+ * `round_up(value_size, 8) * libbpf_num_possible_cpus()`.
+ * @param flags extra flags passed to kernel for this operation
  * @return 0, on success; negative error, otherwise
  *
  * **bpf_map__lookup_elem()** is high-level equivalent of
@@ -1177,14 +1240,8 @@ LIBBPF_API int bpf_map__lookup_elem(const struct bpf_map *map,
  * @param key pointer to memory containing bytes of the key
  * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size**
  * @param value pointer to memory containing bytes of the value
- * @param value_sz size in byte of value data memory; it has to match BPF map
- * definition's **value_size**. For per-CPU BPF maps value size has to be
- * a product of BPF map value size and number of possible CPUs in the system
- * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for
- * per-CPU values value size has to be aligned up to closest 8 bytes for
- * alignment reasons, so expected size is: `round_up(value_size, 8)
- * * libbpf_num_possible_cpus()`.
- * @flags extra flags passed to kernel for this operation
+ * @param value_sz refer to **bpf_map__lookup_elem**'s description.'
+ * @param flags extra flags passed to kernel for this operation
  * @return 0, on success; negative error, otherwise
  *
  * **bpf_map__update_elem()** is high-level equivalent of
@@ -1200,7 +1257,7 @@ LIBBPF_API int bpf_map__update_elem(const struct bpf_map *map,
  * @param map BPF map to delete element from
  * @param key pointer to memory containing bytes of the key
  * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size**
- * @flags extra flags passed to kernel for this operation
+ * @param flags extra flags passed to kernel for this operation
  * @return 0, on success; negative error, otherwise
  *
  * **bpf_map__delete_elem()** is high-level equivalent of
@@ -1223,7 +1280,7 @@ LIBBPF_API int bpf_map__delete_elem(const struct bpf_map *map,
  * per-CPU values value size has to be aligned up to closest 8 bytes for
  * alignment reasons, so expected size is: `round_up(value_size, 8)
  * * libbpf_num_possible_cpus()`.
- * @flags extra flags passed to kernel for this operation
+ * @param flags extra flags passed to kernel for this operation
  * @return 0, on success; negative error, otherwise
  *
  * **bpf_map__lookup_and_delete_elem()** is high-level equivalent of
@@ -1249,6 +1306,28 @@ LIBBPF_API int bpf_map__lookup_and_delete_elem(const struct bpf_map *map,
  */
 LIBBPF_API int bpf_map__get_next_key(const struct bpf_map *map,
 				     const void *cur_key, void *next_key, size_t key_sz);
+/**
+ * @brief **bpf_map__set_exclusive_program()** sets a map to be exclusive to the
+ * specified program. This must be called *before* the map is created.
+ *
+ * @param map BPF map to make exclusive.
+ * @param prog BPF program to be the exclusive user of the map. Must belong
+ * to the same bpf_object as the map.
+ * @return 0 on success; a negative error code otherwise.
+ *
+ * This function must be called after the BPF object is opened but before
+ * it is loaded. Once the object is loaded, only the specified program
+ * will be able to access the map's contents.
+ */
+LIBBPF_API int bpf_map__set_exclusive_program(struct bpf_map *map, struct bpf_program *prog);
+
+/**
+ * @brief **bpf_map__exclusive_program()** returns the exclusive program
+ * that is registered with the map (if any).
+ * @param map BPF map to which the exclusive program is registered.
+ * @return the registered exclusive program.
+ */
+LIBBPF_API struct bpf_program *bpf_map__exclusive_program(struct bpf_map *map);
 
 struct bpf_xdp_set_link_opts {
 	size_t sz;
@@ -1289,6 +1368,7 @@ enum bpf_tc_attach_point {
 	BPF_TC_INGRESS = 1 << 0,
 	BPF_TC_EGRESS  = 1 << 1,
 	BPF_TC_CUSTOM  = 1 << 2,
+	BPF_TC_QDISC   = 1 << 3,
 };
 
 #define BPF_TC_PARENT(a, b) 	\
@@ -1303,9 +1383,11 @@ struct bpf_tc_hook {
 	int ifindex;
 	enum bpf_tc_attach_point attach_point;
 	__u32 parent;
+	__u32 handle;
+	const char *qdisc;
 	size_t :0;
 };
-#define bpf_tc_hook__last_field parent
+#define bpf_tc_hook__last_field qdisc
 
 struct bpf_tc_opts {
 	size_t sz;
@@ -1570,6 +1652,7 @@ struct perf_buffer_opts {
  * @param sample_cb function called on each received data record
  * @param lost_cb function called when record loss has occurred
  * @param ctx user-provided extra context passed into *sample_cb* and *lost_cb*
+ * @param opts optional parameters for the perf buffer, can be null
  * @return a new instance of struct perf_buffer on success, NULL on error with
  * *errno* containing an error code
  */
@@ -1790,9 +1873,10 @@ struct gen_loader_opts {
 	const char *insns;
 	__u32 data_sz;
 	__u32 insns_sz;
+	bool gen_hash;
 };
 
-#define gen_loader_opts__last_field insns_sz
+#define gen_loader_opts__last_field gen_hash
 LIBBPF_API int bpf_object__gen_loader(struct bpf_object *obj,
 				      struct gen_loader_opts *opts);
 

src/libbpf.map

@@ -437,6 +437,8 @@ LIBBPF_1.6.0 {
 		bpf_linker__add_fd;
 		bpf_linker__new_fd;
 		bpf_object__prepare;
+		bpf_prog_stream_read;
+		bpf_program__attach_cgroup_opts;
 		bpf_program__func_info;
 		bpf_program__func_info_cnt;
 		bpf_program__line_info;
@@ -444,3 +446,12 @@ LIBBPF_1.6.0 {
 		btf__add_decl_attr;
 		btf__add_type_attr;
 } LIBBPF_1.5.0;
+
+LIBBPF_1.7.0 {
+	global:
+		bpf_map__set_exclusive_program;
+		bpf_map__exclusive_program;
+		bpf_prog_assoc_struct_ops;
+		bpf_program__assoc_struct_ops;
+		btf__permute;
+} LIBBPF_1.6.0;

src/libbpf_errno.c

@@ -1,75 +0,0 @@
-// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-
-/*
- * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
- * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015 Huawei Inc.
- * Copyright (C) 2017 Nicira, Inc.
- */
-
-#undef _GNU_SOURCE
-#include <stdio.h>
-#include <string.h>
-
-#include "libbpf.h"
-#include "libbpf_internal.h"
-
-/* make sure libbpf doesn't use kernel-only integer typedefs */
-#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
-
-#define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
-#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
-#define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
-
-static const char *libbpf_strerror_table[NR_ERRNO] = {
-	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
-	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
-	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
-	[ERRCODE_OFFSET(ENDIAN)]	= "Endian mismatch",
-	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
-	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
-	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
-	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
-	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
-	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
-	[ERRCODE_OFFSET(WRNGPID)]	= "Wrong pid in netlink message",
-	[ERRCODE_OFFSET(INVSEQ)]	= "Invalid netlink sequence",
-	[ERRCODE_OFFSET(NLPARSE)]	= "Incorrect netlink message parsing",
-};
-
-int libbpf_strerror(int err, char *buf, size_t size)
-{
-	int ret;
-
-	if (!buf || !size)
-		return libbpf_err(-EINVAL);
-
-	err = err > 0 ? err : -err;
-
-	if (err < __LIBBPF_ERRNO__START) {
-		ret = strerror_r(err, buf, size);
-		buf[size - 1] = '\0';
-		return libbpf_err_errno(ret);
-	}
-
-	if (err < __LIBBPF_ERRNO__END) {
-		const char *msg;
-
-		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
-		ret = snprintf(buf, size, "%s", msg);
-		buf[size - 1] = '\0';
-		/* The length of the buf and msg is positive.
-		 * A negative number may be returned only when the
-		 * size exceeds INT_MAX. Not likely to appear.
-		 */
-		if (ret >= size)
-			return libbpf_err(-ERANGE);
-		return 0;
-	}
-
-	ret = snprintf(buf, size, "Unknown libbpf error %d", err);
-	buf[size - 1] = '\0';
-	if (ret >= size)
-		return libbpf_err(-ERANGE);
-	return libbpf_err(-ENOENT);
-}

src/libbpf_internal.h

@@ -74,6 +74,8 @@
 #define ELF64_ST_VISIBILITY(o) ((o) & 0x03)
 #endif
 
+#define JUMPTABLES_SEC ".jumptables"
+
 #define BTF_INFO_ENC(kind, kind_flag, vlen) \
 	((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
 #define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type)
@@ -172,6 +174,16 @@ do {				\
 #define pr_info(fmt, ...)	__pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
 #define pr_debug(fmt, ...)	__pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
 
+/**
+ * @brief **libbpf_errstr()** returns string corresponding to numeric errno
+ * @param err negative numeric errno
+ * @return pointer to string representation of the errno, that is invalidated
+ * upon the next call.
+ */
+const char *libbpf_errstr(int err);
+
+#define errstr(err) libbpf_errstr(err)
+
 #ifndef __has_builtin
 #define __has_builtin(x) 0
 #endif
@@ -712,6 +724,11 @@ static inline bool is_pow_of_2(size_t x)
 	return x && (x & (x - 1)) == 0;
 }
 
+static inline __u32 ror32(__u32 v, int bits)
+{
+	return (v >> bits) | (v << (32 - bits));
+}
+
 #define PROG_LOAD_ATTEMPTS 5
 int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts);
 
@@ -736,4 +753,8 @@ int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern,
 
 int probe_fd(int fd);
 
+#define SHA256_DIGEST_LENGTH 32
+#define SHA256_DWORD_SIZE SHA256_DIGEST_LENGTH / sizeof(__u64)
+
+void libbpf_sha256(const void *data, size_t len, __u8 out[SHA256_DIGEST_LENGTH]);
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */

src/libbpf_probes.c

@@ -364,6 +364,10 @@ static int probe_map_create(enum bpf_map_type map_type)
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
 		break;
+	case BPF_MAP_TYPE_INSN_ARRAY:
+		key_size	= sizeof(__u32);
+		value_size	= sizeof(struct bpf_insn_array_value);
+		break;
 	case BPF_MAP_TYPE_UNSPEC:
 	default:
 		return -EOPNOTSUPP;

src/libbpf_utils.c

@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
+ */
+
+#undef _GNU_SOURCE
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <linux/kernel.h>
+
+#include "libbpf.h"
+#include "libbpf_internal.h"
+
+#ifndef ENOTSUPP
+#define ENOTSUPP	524
+#endif
+
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
+#define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
+#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
+#define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
+
+static const char *libbpf_strerror_table[NR_ERRNO] = {
+	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
+	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
+	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
+	[ERRCODE_OFFSET(ENDIAN)]	= "Endian mismatch",
+	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
+	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
+	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
+	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
+	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
+	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
+	[ERRCODE_OFFSET(WRNGPID)]	= "Wrong pid in netlink message",
+	[ERRCODE_OFFSET(INVSEQ)]	= "Invalid netlink sequence",
+	[ERRCODE_OFFSET(NLPARSE)]	= "Incorrect netlink message parsing",
+};
+
+int libbpf_strerror(int err, char *buf, size_t size)
+{
+	int ret;
+
+	if (!buf || !size)
+		return libbpf_err(-EINVAL);
+
+	err = err > 0 ? err : -err;
+
+	if (err < __LIBBPF_ERRNO__START) {
+		ret = strerror_r(err, buf, size);
+		buf[size - 1] = '\0';
+		return libbpf_err_errno(ret);
+	}
+
+	if (err < __LIBBPF_ERRNO__END) {
+		const char *msg;
+
+		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
+		ret = snprintf(buf, size, "%s", msg);
+		buf[size - 1] = '\0';
+		/* The length of the buf and msg is positive.
+		 * A negative number may be returned only when the
+		 * size exceeds INT_MAX. Not likely to appear.
+		 */
+		if (ret >= size)
+			return libbpf_err(-ERANGE);
+		return 0;
+	}
+
+	ret = snprintf(buf, size, "Unknown libbpf error %d", err);
+	buf[size - 1] = '\0';
+	if (ret >= size)
+		return libbpf_err(-ERANGE);
+	return libbpf_err(-ENOENT);
+}
+
+const char *libbpf_errstr(int err)
+{
+	static __thread char buf[12];
+
+	if (err > 0)
+		err = -err;
+
+	switch (err) {
+	case -E2BIG:		return "-E2BIG";
+	case -EACCES:		return "-EACCES";
+	case -EADDRINUSE:	return "-EADDRINUSE";
+	case -EADDRNOTAVAIL:	return "-EADDRNOTAVAIL";
+	case -EAGAIN:		return "-EAGAIN";
+	case -EALREADY:		return "-EALREADY";
+	case -EBADF:		return "-EBADF";
+	case -EBADFD:		return "-EBADFD";
+	case -EBUSY:		return "-EBUSY";
+	case -ECANCELED:	return "-ECANCELED";
+	case -ECHILD:		return "-ECHILD";
+	case -EDEADLK:		return "-EDEADLK";
+	case -EDOM:		return "-EDOM";
+	case -EEXIST:		return "-EEXIST";
+	case -EFAULT:		return "-EFAULT";
+	case -EFBIG:		return "-EFBIG";
+	case -EILSEQ:		return "-EILSEQ";
+	case -EINPROGRESS:	return "-EINPROGRESS";
+	case -EINTR:		return "-EINTR";
+	case -EINVAL:		return "-EINVAL";
+	case -EIO:		return "-EIO";
+	case -EISDIR:		return "-EISDIR";
+	case -ELOOP:		return "-ELOOP";
+	case -EMFILE:		return "-EMFILE";
+	case -EMLINK:		return "-EMLINK";
+	case -EMSGSIZE:		return "-EMSGSIZE";
+	case -ENAMETOOLONG:	return "-ENAMETOOLONG";
+	case -ENFILE:		return "-ENFILE";
+	case -ENODATA:		return "-ENODATA";
+	case -ENODEV:		return "-ENODEV";
+	case -ENOENT:		return "-ENOENT";
+	case -ENOEXEC:		return "-ENOEXEC";
+	case -ENOLINK:		return "-ENOLINK";
+	case -ENOMEM:		return "-ENOMEM";
+	case -ENOSPC:		return "-ENOSPC";
+	case -ENOTBLK:		return "-ENOTBLK";
+	case -ENOTDIR:		return "-ENOTDIR";
+	case -ENOTSUPP:		return "-ENOTSUPP";
+	case -ENOTTY:		return "-ENOTTY";
+	case -ENXIO:		return "-ENXIO";
+	case -EOPNOTSUPP:	return "-EOPNOTSUPP";
+	case -EOVERFLOW:	return "-EOVERFLOW";
+	case -EPERM:		return "-EPERM";
+	case -EPIPE:		return "-EPIPE";
+	case -EPROTO:		return "-EPROTO";
+	case -EPROTONOSUPPORT:	return "-EPROTONOSUPPORT";
+	case -ERANGE:		return "-ERANGE";
+	case -EROFS:		return "-EROFS";
+	case -ESPIPE:		return "-ESPIPE";
+	case -ESRCH:		return "-ESRCH";
+	case -ETXTBSY:		return "-ETXTBSY";
+	case -EUCLEAN:		return "-EUCLEAN";
+	case -EXDEV:		return "-EXDEV";
+	default:
+		snprintf(buf, sizeof(buf), "%d", err);
+		return buf;
+	}
+}
+
+static inline __u32 get_unaligned_be32(const void *p)
+{
+	__be32 val;
+
+	memcpy(&val, p, sizeof(val));
+	return be32_to_cpu(val);
+}
+
+static inline void put_unaligned_be32(__u32 val, void *p)
+{
+	__be32 be_val = cpu_to_be32(val);
+
+	memcpy(p, &be_val, sizeof(be_val));
+}
+
+#define SHA256_BLOCK_LENGTH 64
+#define Ch(x, y, z) (((x) & (y)) ^ (~(x) & (z)))
+#define Maj(x, y, z) (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z)))
+#define Sigma_0(x) (ror32((x), 2) ^ ror32((x), 13) ^ ror32((x), 22))
+#define Sigma_1(x) (ror32((x), 6) ^ ror32((x), 11) ^ ror32((x), 25))
+#define sigma_0(x) (ror32((x), 7) ^ ror32((x), 18) ^ ((x) >> 3))
+#define sigma_1(x) (ror32((x), 17) ^ ror32((x), 19) ^ ((x) >> 10))
+
+static const __u32 sha256_K[64] = {
+	0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1,
+	0x923f82a4, 0xab1c5ed5, 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3,
+	0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174, 0xe49b69c1, 0xefbe4786,
+	0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
+	0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147,
+	0x06ca6351, 0x14292967, 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13,
+	0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85, 0xa2bfe8a1, 0xa81a664b,
+	0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
+	0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a,
+	0x5b9cca4f, 0x682e6ff3, 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208,
+	0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2,
+};
+
+#define SHA256_ROUND(i, a, b, c, d, e, f, g, h)                                \
+	{                                                                      \
+		__u32 tmp = h + Sigma_1(e) + Ch(e, f, g) + sha256_K[i] + w[i]; \
+		d += tmp;                                                      \
+		h = tmp + Sigma_0(a) + Maj(a, b, c);                           \
+	}
+
+static void sha256_blocks(__u32 state[8], const __u8 *data, size_t nblocks)
+{
+	while (nblocks--) {
+		__u32 a = state[0];
+		__u32 b = state[1];
+		__u32 c = state[2];
+		__u32 d = state[3];
+		__u32 e = state[4];
+		__u32 f = state[5];
+		__u32 g = state[6];
+		__u32 h = state[7];
+		__u32 w[64];
+		int i;
+
+		for (i = 0; i < 16; i++)
+			w[i] = get_unaligned_be32(&data[4 * i]);
+		for (; i < ARRAY_SIZE(w); i++)
+			w[i] = sigma_1(w[i - 2]) + w[i - 7] +
+			       sigma_0(w[i - 15]) + w[i - 16];
+		for (i = 0; i < ARRAY_SIZE(w); i += 8) {
+			SHA256_ROUND(i + 0, a, b, c, d, e, f, g, h);
+			SHA256_ROUND(i + 1, h, a, b, c, d, e, f, g);
+			SHA256_ROUND(i + 2, g, h, a, b, c, d, e, f);
+			SHA256_ROUND(i + 3, f, g, h, a, b, c, d, e);
+			SHA256_ROUND(i + 4, e, f, g, h, a, b, c, d);
+			SHA256_ROUND(i + 5, d, e, f, g, h, a, b, c);
+			SHA256_ROUND(i + 6, c, d, e, f, g, h, a, b);
+			SHA256_ROUND(i + 7, b, c, d, e, f, g, h, a);
+		}
+		state[0] += a;
+		state[1] += b;
+		state[2] += c;
+		state[3] += d;
+		state[4] += e;
+		state[5] += f;
+		state[6] += g;
+		state[7] += h;
+		data += SHA256_BLOCK_LENGTH;
+	}
+}
+
+void libbpf_sha256(const void *data, size_t len, __u8 out[SHA256_DIGEST_LENGTH])
+{
+	__u32 state[8] = { 0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a,
+			   0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19 };
+	const __be64 bitcount = cpu_to_be64((__u64)len * 8);
+	__u8 final_data[2 * SHA256_BLOCK_LENGTH] = { 0 };
+	size_t final_len = len % SHA256_BLOCK_LENGTH;
+	int i;
+
+	sha256_blocks(state, data, len / SHA256_BLOCK_LENGTH);
+
+	memcpy(final_data, data + len - final_len, final_len);
+	final_data[final_len] = 0x80;
+	final_len = roundup(final_len + 9, SHA256_BLOCK_LENGTH);
+	memcpy(&final_data[final_len - 8], &bitcount, 8);
+
+	sha256_blocks(state, final_data, final_len / SHA256_BLOCK_LENGTH);
+
+	for (i = 0; i < ARRAY_SIZE(state); i++)
+		put_unaligned_be32(state[i], &out[4 * i]);
+}

src/libbpf_version.h

@@ -4,6 +4,6 @@
 #define __LIBBPF_VERSION_H
 
 #define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 6
+#define LIBBPF_MINOR_VERSION 7
 
 #endif /* __LIBBPF_VERSION_H */

src/linker.c

@@ -25,7 +25,6 @@
 #include "btf.h"
 #include "libbpf_internal.h"
 #include "strset.h"
-#include "str_error.h"
 
 #define BTF_EXTERN_SEC ".extern"
 
@@ -2026,6 +2025,9 @@ static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj,
 			obj->sym_map[src_sym_idx] = dst_sec->sec_sym_idx;
 			return 0;
 		}
+
+		if (strcmp(src_sec->sec_name, JUMPTABLES_SEC) == 0)
+			goto add_sym;
 	}
 
 	if (sym_bind == STB_LOCAL)

src/netlink.c

@@ -529,9 +529,9 @@ int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id)
 }
 
 
-typedef int (*qdisc_config_t)(struct libbpf_nla_req *req);
+typedef int (*qdisc_config_t)(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook);
 
-static int clsact_config(struct libbpf_nla_req *req)
+static int clsact_config(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook)
 {
 	req->tc.tcm_parent = TC_H_CLSACT;
 	req->tc.tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0);
@@ -539,6 +539,16 @@ static int clsact_config(struct libbpf_nla_req *req)
 	return nlattr_add(req, TCA_KIND, "clsact", sizeof("clsact"));
 }
 
+static int qdisc_config(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook)
+{
+	const char *qdisc = OPTS_GET(hook, qdisc, NULL);
+
+	req->tc.tcm_parent = OPTS_GET(hook, parent, TC_H_ROOT);
+	req->tc.tcm_handle = OPTS_GET(hook, handle, 0);
+
+	return nlattr_add(req, TCA_KIND, qdisc, strlen(qdisc) + 1);
+}
+
 static int attach_point_to_config(struct bpf_tc_hook *hook,
 				  qdisc_config_t *config)
 {
@@ -552,6 +562,9 @@ static int attach_point_to_config(struct bpf_tc_hook *hook,
 		return 0;
 	case BPF_TC_CUSTOM:
 		return -EOPNOTSUPP;
+	case BPF_TC_QDISC:
+		*config = &qdisc_config;
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -596,7 +609,7 @@ static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags)
 	req.tc.tcm_family  = AF_UNSPEC;
 	req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0);
 
-	ret = config(&req);
+	ret = config(&req, hook);
 	if (ret < 0)
 		return ret;
 
@@ -639,6 +652,7 @@ int bpf_tc_hook_destroy(struct bpf_tc_hook *hook)
 	case BPF_TC_INGRESS:
 	case BPF_TC_EGRESS:
 		return libbpf_err(__bpf_tc_detach(hook, NULL, true));
+	case BPF_TC_QDISC:
 	case BPF_TC_INGRESS | BPF_TC_EGRESS:
 		return libbpf_err(tc_qdisc_delete(hook));
 	case BPF_TC_CUSTOM:

src/relo_core.c

@@ -64,7 +64,6 @@ enum libbpf_print_level {
 #include "libbpf.h"
 #include "bpf.h"
 #include "btf.h"
-#include "str_error.h"
 #include "libbpf_internal.h"
 #endif
 

src/ringbuf.c

@@ -21,7 +21,6 @@
 #include "libbpf.h"
 #include "libbpf_internal.h"
 #include "bpf.h"
-#include "str_error.h"
 
 struct ring {
 	ring_buffer_sample_fn sample_cb;

src/skel_internal.h

@@ -13,10 +13,15 @@
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <sys/mman.h>
+#include <linux/keyctl.h>
 #include <stdlib.h>
 #include "bpf.h"
 #endif
 
+#ifndef SHA256_DIGEST_LENGTH
+#define SHA256_DIGEST_LENGTH 32
+#endif
+
 #ifndef __NR_bpf
 # if defined(__mips__) && defined(_ABIO32)
 #  define __NR_bpf 4355
@@ -64,6 +69,11 @@ struct bpf_load_and_run_opts {
 	__u32 data_sz;
 	__u32 insns_sz;
 	const char *errstr;
+	void *signature;
+	__u32 signature_sz;
+	__s32 keyring_id;
+	void *excl_prog_hash;
+	__u32 excl_prog_hash_sz;
 };
 
 long kern_sys_bpf(__u32 cmd, void *attr, __u32 attr_size);
@@ -220,14 +230,19 @@ static inline int skel_map_create(enum bpf_map_type map_type,
 				  const char *map_name,
 				  __u32 key_size,
 				  __u32 value_size,
-				  __u32 max_entries)
+				  __u32 max_entries,
+				  const void *excl_prog_hash,
+				  __u32 excl_prog_hash_sz)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
+	const size_t attr_sz = offsetofend(union bpf_attr, excl_prog_hash_size);
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_sz);
 
 	attr.map_type = map_type;
+	attr.excl_prog_hash = (unsigned long) excl_prog_hash;
+	attr.excl_prog_hash_size = excl_prog_hash_sz;
+
 	strncpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.key_size = key_size;
 	attr.value_size = value_size;
@@ -300,6 +315,35 @@ static inline int skel_link_create(int prog_fd, int target_fd,
 	return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz);
 }
 
+static inline int skel_obj_get_info_by_fd(int fd)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, info);
+	__u8 sha[SHA256_DIGEST_LENGTH];
+	struct bpf_map_info info;
+	__u32 info_len = sizeof(info);
+	union bpf_attr attr;
+
+	memset(&info, 0, sizeof(info));
+	info.hash = (long) &sha;
+	info.hash_size = SHA256_DIGEST_LENGTH;
+
+	memset(&attr, 0, attr_sz);
+	attr.info.bpf_fd = fd;
+	attr.info.info = (long) &info;
+	attr.info.info_len = info_len;
+	return skel_sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, attr_sz);
+}
+
+static inline int skel_map_freeze(int fd)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, map_fd);
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_sz);
+	attr.map_fd = fd;
+
+	return skel_sys_bpf(BPF_MAP_FREEZE, &attr, attr_sz);
+}
 #ifdef __KERNEL__
 #define set_err
 #else
@@ -308,12 +352,13 @@ static inline int skel_link_create(int prog_fd, int target_fd,
 
 static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 {
-	const size_t prog_load_attr_sz = offsetofend(union bpf_attr, fd_array);
+	const size_t prog_load_attr_sz = offsetofend(union bpf_attr, keyring_id);
 	const size_t test_run_attr_sz = offsetofend(union bpf_attr, test);
 	int map_fd = -1, prog_fd = -1, key = 0, err;
 	union bpf_attr attr;
 
-	err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1);
+	err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1,
+				       opts->excl_prog_hash, opts->excl_prog_hash_sz);
 	if (map_fd < 0) {
 		opts->errstr = "failed to create loader map";
 		set_err;
@@ -327,11 +372,34 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 		goto out;
 	}
 
+#ifndef __KERNEL__
+	err = skel_map_freeze(map_fd);
+	if (err < 0) {
+		opts->errstr = "failed to freeze map";
+		set_err;
+		goto out;
+	}
+	err = skel_obj_get_info_by_fd(map_fd);
+	if (err < 0) {
+		opts->errstr = "failed to fetch obj info";
+		set_err;
+		goto out;
+	}
+#endif
+
 	memset(&attr, 0, prog_load_attr_sz);
 	attr.prog_type = BPF_PROG_TYPE_SYSCALL;
 	attr.insns = (long) opts->insns;
 	attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn);
 	attr.license = (long) "Dual BSD/GPL";
+#ifndef __KERNEL__
+	attr.signature = (long) opts->signature;
+	attr.signature_size = opts->signature_sz;
+#else
+	if (opts->signature || opts->signature_sz)
+		pr_warn("signatures are not supported from bpf_preload\n");
+#endif
+	attr.keyring_id = opts->keyring_id;
 	memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog"));
 	attr.fd_array = (long) &map_fd;
 	attr.log_level = opts->ctx->log_level;

src/str_error.c

@@ -1,104 +0,0 @@
-// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-#undef _GNU_SOURCE
-#include <string.h>
-#include <stdio.h>
-#include <errno.h>
-#include "str_error.h"
-
-#ifndef ENOTSUPP
-#define ENOTSUPP	524
-#endif
-
-/* make sure libbpf doesn't use kernel-only integer typedefs */
-#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
-
-/*
- * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl
- * libc, while checking strerror_r() return to avoid having to check this in
- * all places calling it.
- */
-char *libbpf_strerror_r(int err, char *dst, int len)
-{
-	int ret = strerror_r(err < 0 ? -err : err, dst, len);
-	/* on glibc <2.13, ret == -1 and errno is set, if strerror_r() can't
-	 * handle the error, on glibc >=2.13 *positive* (errno-like) error
-	 * code is returned directly
-	 */
-	if (ret == -1)
-		ret = errno;
-	if (ret) {
-		if (ret == EINVAL)
-			/* strerror_r() doesn't recognize this specific error */
-			snprintf(dst, len, "unknown error (%d)", err < 0 ? err : -err);
-		else
-			snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret);
-	}
-	return dst;
-}
-
-const char *libbpf_errstr(int err)
-{
-	static __thread char buf[12];
-
-	if (err > 0)
-		err = -err;
-
-	switch (err) {
-	case -E2BIG:		return "-E2BIG";
-	case -EACCES:		return "-EACCES";
-	case -EADDRINUSE:	return "-EADDRINUSE";
-	case -EADDRNOTAVAIL:	return "-EADDRNOTAVAIL";
-	case -EAGAIN:		return "-EAGAIN";
-	case -EALREADY:		return "-EALREADY";
-	case -EBADF:		return "-EBADF";
-	case -EBADFD:		return "-EBADFD";
-	case -EBUSY:		return "-EBUSY";
-	case -ECANCELED:	return "-ECANCELED";
-	case -ECHILD:		return "-ECHILD";
-	case -EDEADLK:		return "-EDEADLK";
-	case -EDOM:		return "-EDOM";
-	case -EEXIST:		return "-EEXIST";
-	case -EFAULT:		return "-EFAULT";
-	case -EFBIG:		return "-EFBIG";
-	case -EILSEQ:		return "-EILSEQ";
-	case -EINPROGRESS:	return "-EINPROGRESS";
-	case -EINTR:		return "-EINTR";
-	case -EINVAL:		return "-EINVAL";
-	case -EIO:		return "-EIO";
-	case -EISDIR:		return "-EISDIR";
-	case -ELOOP:		return "-ELOOP";
-	case -EMFILE:		return "-EMFILE";
-	case -EMLINK:		return "-EMLINK";
-	case -EMSGSIZE:		return "-EMSGSIZE";
-	case -ENAMETOOLONG:	return "-ENAMETOOLONG";
-	case -ENFILE:		return "-ENFILE";
-	case -ENODATA:		return "-ENODATA";
-	case -ENODEV:		return "-ENODEV";
-	case -ENOENT:		return "-ENOENT";
-	case -ENOEXEC:		return "-ENOEXEC";
-	case -ENOLINK:		return "-ENOLINK";
-	case -ENOMEM:		return "-ENOMEM";
-	case -ENOSPC:		return "-ENOSPC";
-	case -ENOTBLK:		return "-ENOTBLK";
-	case -ENOTDIR:		return "-ENOTDIR";
-	case -ENOTSUPP:		return "-ENOTSUPP";
-	case -ENOTTY:		return "-ENOTTY";
-	case -ENXIO:		return "-ENXIO";
-	case -EOPNOTSUPP:	return "-EOPNOTSUPP";
-	case -EOVERFLOW:	return "-EOVERFLOW";
-	case -EPERM:		return "-EPERM";
-	case -EPIPE:		return "-EPIPE";
-	case -EPROTO:		return "-EPROTO";
-	case -EPROTONOSUPPORT:	return "-EPROTONOSUPPORT";
-	case -ERANGE:		return "-ERANGE";
-	case -EROFS:		return "-EROFS";
-	case -ESPIPE:		return "-ESPIPE";
-	case -ESRCH:		return "-ESRCH";
-	case -ETXTBSY:		return "-ETXTBSY";
-	case -EUCLEAN:		return "-EUCLEAN";
-	case -EXDEV:		return "-EXDEV";
-	default:
-		snprintf(buf, sizeof(buf), "%d", err);
-		return buf;
-	}
-}

src/str_error.h

@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-#ifndef __LIBBPF_STR_ERROR_H
-#define __LIBBPF_STR_ERROR_H
-
-#define STRERR_BUFSIZE  128
-
-char *libbpf_strerror_r(int err, char *dst, int len);
-
-/**
- * @brief **libbpf_errstr()** returns string corresponding to numeric errno
- * @param err negative numeric errno
- * @return pointer to string representation of the errno, that is invalidated
- * upon the next call.
- */
-const char *libbpf_errstr(int err);
-
-#define errstr(err) libbpf_errstr(err)
-
-#endif /* __LIBBPF_STR_ERROR_H */

src/usdt.bpf.h

@@ -34,13 +34,32 @@ enum __bpf_usdt_arg_type {
 	BPF_USDT_ARG_CONST,
 	BPF_USDT_ARG_REG,
 	BPF_USDT_ARG_REG_DEREF,
+	BPF_USDT_ARG_SIB,
 };
 
+/*
+ * This struct layout is designed specifically to be backwards/forward
+ * compatible between libbpf versions for ARG_CONST, ARG_REG, and
+ * ARG_REG_DEREF modes. ARG_SIB requires libbpf v1.7+.
+ */
 struct __bpf_usdt_arg_spec {
 	/* u64 scalar interpreted depending on arg_type, see below */
 	__u64 val_off;
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	/* arg location case, see bpf_usdt_arg() for details */
-	enum __bpf_usdt_arg_type arg_type;
+	enum __bpf_usdt_arg_type arg_type: 8;
+	/* index register offset within struct pt_regs */
+	__u16 idx_reg_off: 12;
+	/* scale factor for index register (1, 2, 4, or 8) */
+	__u16 scale_bitshift: 4;
+	/* reserved for future use, keeps reg_off offset stable */
+	__u8 __reserved: 8;
+#else
+	__u8 __reserved: 8;
+	__u16 idx_reg_off: 12;
+	__u16 scale_bitshift: 4;
+	enum __bpf_usdt_arg_type arg_type: 8;
+#endif
 	/* offset of referenced register within struct pt_regs */
 	short reg_off;
 	/* whether arg should be interpreted as signed value */
@@ -149,7 +168,7 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res)
 {
 	struct __bpf_usdt_spec *spec;
 	struct __bpf_usdt_arg_spec *arg_spec;
-	unsigned long val;
+	unsigned long val, idx;
 	int err, spec_id;
 
 	*res = 0;
@@ -202,6 +221,27 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res)
 			return err;
 #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 		val >>= arg_spec->arg_bitshift;
+#endif
+		break;
+	case BPF_USDT_ARG_SIB:
+		/* Arg is in memory addressed by SIB (Scale-Index-Base) mode
+		 * (e.g., "-1@-96(%rbp,%rax,8)" in USDT arg spec). We first
+		 * fetch the base register contents and the index register
+		 * contents from pt_regs. Then we calculate the final address
+		 * as base + (index * scale) + offset, and do a user-space
+		 * probe read to fetch the argument value.
+		 */
+		err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off);
+		if (err)
+			return err;
+		err = bpf_probe_read_kernel(&idx, sizeof(idx), (void *)ctx + arg_spec->idx_reg_off);
+		if (err)
+			return err;
+		err = bpf_probe_read_user(&val, sizeof(val), (void *)(val + (idx << arg_spec->scale_bitshift) + arg_spec->val_off));
+		if (err)
+			return err;
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+		val >>= arg_spec->arg_bitshift;
 #endif
 		break;
 	default:

src/usdt.c

@@ -20,7 +20,6 @@
 #include "libbpf_common.h"
 #include "libbpf_internal.h"
 #include "hashmap.h"
-#include "str_error.h"
 
 /* libbpf's USDT support consists of BPF-side state/code and user-space
  * state/code working together in concert. BPF-side parts are defined in
@@ -59,7 +58,7 @@
  *
  * STAP_PROBE3(my_usdt_provider, my_usdt_probe_name, 123, x, &y);
  *
- * USDT is identified by it's <provider-name>:<probe-name> pair of names. Each
+ * USDT is identified by its <provider-name>:<probe-name> pair of names. Each
  * individual USDT has a fixed number of arguments (3 in the above example)
  * and specifies values of each argument as if it was a function call.
  *
@@ -81,7 +80,7 @@
  * NOP instruction that kernel can replace with an interrupt instruction to
  * trigger instrumentation code (BPF program for all that we care about).
  *
- * Semaphore above is and optional feature. It records an address of a 2-byte
+ * Semaphore above is an optional feature. It records an address of a 2-byte
  * refcount variable (normally in '.probes' ELF section) used for signaling if
  * there is anything that is attached to USDT. This is useful for user
  * applications if, for example, they need to prepare some arguments that are
@@ -121,7 +120,7 @@
  * a uprobe BPF program (which for kernel, at least currently, is just a kprobe
  * program, so BPF_PROG_TYPE_KPROBE program type). With the only difference
  * that uprobe is usually attached at the function entry, while USDT will
- * normally will be somewhere inside the function. But it should always be
+ * normally be somewhere inside the function. But it should always be
  * pointing to NOP instruction, which makes such uprobes the fastest uprobe
  * kind.
  *
@@ -151,7 +150,7 @@
  * libbpf sets to spec ID during attach time, or, if kernel is too old to
  * support BPF cookie, through IP-to-spec-ID map that libbpf maintains in such
  * case. The latter means that some modes of operation can't be supported
- * without BPF cookie. Such mode is attaching to shared library "generically",
+ * without BPF cookie. Such a mode is attaching to shared library "generically",
  * without specifying target process. In such case, it's impossible to
  * calculate absolute IP addresses for IP-to-spec-ID map, and thus such mode
  * is not supported without BPF cookie support.
@@ -185,7 +184,7 @@
  * as even if USDT spec string is the same, USDT cookie value can be
  * different. It was deemed excessive to try to deduplicate across independent
  * USDT attachments by taking into account USDT spec string *and* USDT cookie
- * value, which would complicated spec ID accounting significantly for little
+ * value, which would complicate spec ID accounting significantly for little
  * gain.
  */
 
@@ -200,12 +199,23 @@ enum usdt_arg_type {
 	USDT_ARG_CONST,
 	USDT_ARG_REG,
 	USDT_ARG_REG_DEREF,
+	USDT_ARG_SIB,
 };
 
 /* should match exactly struct __bpf_usdt_arg_spec from usdt.bpf.h */
 struct usdt_arg_spec {
 	__u64 val_off;
-	enum usdt_arg_type arg_type;
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	enum usdt_arg_type arg_type: 8;
+	__u16	idx_reg_off: 12;
+	__u16	scale_bitshift: 4;
+	__u8 __reserved: 8;     /* keep reg_off offset stable */
+#else
+	__u8 __reserved: 8;     /* keep reg_off offset stable */
+	__u16	idx_reg_off: 12;
+	__u16	scale_bitshift: 4;
+	enum usdt_arg_type arg_type: 8;
+#endif
 	short reg_off;
 	bool arg_signed;
 	char arg_bitshift;
@@ -570,9 +580,8 @@ static struct elf_seg *find_vma_seg(struct elf_seg *segs, size_t seg_cnt, long o
 	return NULL;
 }
 
-static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr,
-			   const char *data, size_t name_off, size_t desc_off,
-			   struct usdt_note *usdt_note);
+static int parse_usdt_note(GElf_Nhdr *nhdr, const char *data, size_t name_off,
+			   size_t desc_off, struct usdt_note *usdt_note);
 
 static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie);
 
@@ -626,7 +635,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *
 		struct elf_seg *seg = NULL;
 		void *tmp;
 
-		err = parse_usdt_note(elf, path, &nhdr, data->d_buf, name_off, desc_off, &note);
+		err = parse_usdt_note(&nhdr, data->d_buf, name_off, desc_off, &note);
 		if (err)
 			goto err_out;
 
@@ -1132,8 +1141,7 @@ err_out:
 /* Parse out USDT ELF note from '.note.stapsdt' section.
  * Logic inspired by perf's code.
  */
-static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr,
-			   const char *data, size_t name_off, size_t desc_off,
+static int parse_usdt_note(GElf_Nhdr *nhdr, const char *data, size_t name_off, size_t desc_off,
 			   struct usdt_note *note)
 {
 	const char *provider, *name, *args;
@@ -1283,11 +1291,51 @@ static int calc_pt_regs_off(const char *reg_name)
 
 static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
 {
-	char reg_name[16];
-	int len, reg_off;
-	long off;
+	char reg_name[16] = {0}, idx_reg_name[16] = {0};
+	int len, reg_off, idx_reg_off, scale = 1;
+	long off = 0;
 
-	if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", arg_sz, &off, reg_name, &len) == 3) {
+	if (sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^,] , %d ) %n",
+		   arg_sz, &off, reg_name, idx_reg_name, &scale, &len) == 5 ||
+		sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^,] , %d ) %n",
+		       arg_sz, reg_name, idx_reg_name, &scale, &len) == 4 ||
+		sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^)] ) %n",
+		       arg_sz, &off, reg_name, idx_reg_name, &len) == 4 ||
+		sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^)] ) %n",
+		       arg_sz, reg_name, idx_reg_name, &len) == 3
+		) {
+		/*
+		 * Scale Index Base case:
+		 * 1@-96(%rbp,%rax,8)
+		 * 1@(%rbp,%rax,8)
+		 * 1@-96(%rbp,%rax)
+		 * 1@(%rbp,%rax)
+		 */
+		arg->arg_type = USDT_ARG_SIB;
+		arg->val_off = off;
+
+		reg_off = calc_pt_regs_off(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+
+		idx_reg_off = calc_pt_regs_off(idx_reg_name);
+		if (idx_reg_off < 0)
+			return idx_reg_off;
+		arg->idx_reg_off = idx_reg_off;
+
+		/* validate scale factor and set fields directly */
+		switch (scale) {
+		case 1: arg->scale_bitshift = 0; break;
+		case 2: arg->scale_bitshift = 1; break;
+		case 4: arg->scale_bitshift = 2; break;
+		case 8: arg->scale_bitshift = 3; break;
+		default:
+			pr_warn("usdt: invalid SIB scale %d, expected 1, 2, 4, 8\n", scale);
+			return -EINVAL;
+		}
+	} else if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n",
+				arg_sz, &off, reg_name, &len) == 3) {
 		/* Memory dereference case, e.g., -4@-20(%rbp) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
@@ -1306,6 +1354,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 	} else if (sscanf(arg_str, " %d @ %%%15s %n", arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -4@%eax */
 		arg->arg_type = USDT_ARG_REG;
+		/* register read has no memory offset */
 		arg->val_off = 0;
 
 		reg_off = calc_pt_regs_off(reg_name);
@@ -1327,8 +1376,6 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 
 #elif defined(__s390x__)
 
-/* Do not support __s390__ for now, since user_pt_regs is broken with -m31. */
-
 static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
 {
 	unsigned int reg;