Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2023-12-18

This PR is larger than usual and contains changes in various parts
of the kernel.

The main changes are:

1) Fix kCFI bugs in BPF, from Peter Zijlstra.

End result: all forms of indirect calls from BPF into kernel
and from kernel into BPF work with CFI enabled. This allows BPF
to work with CONFIG_FINEIBT=y.

2) Introduce BPF token object, from Andrii Nakryiko.

It adds an ability to delegate a subset of BPF features from privileged
daemon (e.g., systemd) through special mount options for userns-bound
BPF FS to a trusted unprivileged application. The design accommodates
suggestions from Christian Brauner and Paul Moore.

Example:
$ sudo mkdir -p /sys/fs/bpf/token
$ sudo mount -t bpf bpffs /sys/fs/bpf/token \
             -o delegate_cmds=prog_load:MAP_CREATE \
             -o delegate_progs=kprobe \
             -o delegate_attachs=xdp

3) Various verifier improvements and fixes, from Andrii Nakryiko, Andrei Matei.

 - Complete precision tracking support for register spills
 - Fix verification of possibly-zero-sized stack accesses
 - Fix access to uninit stack slots
 - Track aligned STACK_ZERO cases as imprecise spilled registers.
   It improves the verifier "instructions processed" metric from single
   digit to 50-60% for some programs.
 - Fix verifier retval logic

4) Support for VLAN tag in XDP hints, from Larysa Zaremba.

5) Allocate BPF trampoline via bpf_prog_pack mechanism, from Song Liu.

End result: better memory utilization and lower I$ miss for calls to BPF
via BPF trampoline.

6) Fix race between BPF prog accessing inner map and parallel delete,
from Hou Tao.

7) Add bpf_xdp_get_xfrm_state() kfunc, from Daniel Xu.

It allows BPF interact with IPSEC infra. The intent is to support
software RSS (via XDP) for the upcoming ipsec pcpu work.
Experiments on AWS demonstrate single tunnel pcpu ipsec reaching
line rate on 100G ENA nics.

8) Expand bpf_cgrp_storage to support cgroup1 non-attach, from Yafang Shao.

9) BPF file verification via fsverity, from Song Liu.

It allows BPF progs get fsverity digest.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (164 commits)
  bpf: Ensure precise is reset to false in __mark_reg_const_zero()
  selftests/bpf: Add more uprobe multi fail tests
  bpf: Fail uprobe multi link with negative offset
  selftests/bpf: Test the release of map btf
  s390/bpf: Fix indirect trampoline generation
  selftests/bpf: Temporarily disable dummy_struct_ops test on s390
  x86/cfi,bpf: Fix bpf_exception_cb() signature
  bpf: Fix dtor CFI
  cfi: Add CFI_NOSEAL()
  x86/cfi,bpf: Fix bpf_struct_ops CFI
  x86/cfi,bpf: Fix bpf_callback_t CFI
  x86/cfi,bpf: Fix BPF JIT call
  cfi: Flip headers
  selftests/bpf: Add test for abnormal cnt during multi-kprobe attachment
  selftests/bpf: Don't use libbpf_get_error() in kprobe_multi_test
  selftests/bpf: Add test for abnormal cnt during multi-uprobe attachment
  bpf: Limit the number of kprobes when attaching program to multiple kprobes
  bpf: Limit the number of uprobes when attaching program to multiple uprobes
  bpf: xdp: Register generic_kfunc_set with XDP programs
  selftests/bpf: utilize string values for delegate_xxx mount options
  ...
====================

Link: https://lore.kernel.org/r/20231219000520.34178-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

14 files changed, 804 insertions, 482 deletions

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 2d0c282c8588..b6619199a706 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1,4 +1,4 @@
 libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
 	    netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \
 	    btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \
-	    usdt.o zip.o elf.o
+	    usdt.o zip.o elf.o features.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9dc9625651dc..0ad8e532b3cf 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -103,7 +103,7 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
  *   [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/
  *   [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper")
  */
-int probe_memcg_account(void)
+int probe_memcg_account(int token_fd)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
 	struct bpf_insn insns[] = {
@@ -120,6 +120,7 @@ int probe_memcg_account(void)
 	attr.insns = ptr_to_u64(insns);
 	attr.insn_cnt = insn_cnt;
 	attr.license = ptr_to_u64("GPL");
+	attr.prog_token_fd = token_fd;
 
 	prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz);
 	if (prog_fd >= 0) {
@@ -146,7 +147,7 @@ int bump_rlimit_memlock(void)
 	struct rlimit rlim;
 
 	/* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */
-	if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT))
+	if (memlock_bumped || feat_supported(NULL, FEAT_MEMCG_ACCOUNT))
 		return 0;
 
 	memlock_bumped = true;
@@ -169,7 +170,7 @@ 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_extra);
+	const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd);
 	union bpf_attr attr;
 	int fd;
 
@@ -181,7 +182,7 @@ int bpf_map_create(enum bpf_map_type map_type,
 		return libbpf_err(-EINVAL);
 
 	attr.map_type = map_type;
-	if (map_name && kernel_supports(NULL, FEAT_PROG_NAME))
+	if (map_name && feat_supported(NULL, FEAT_PROG_NAME))
 		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.key_size = key_size;
 	attr.value_size = value_size;
@@ -198,6 +199,8 @@ int bpf_map_create(enum bpf_map_type map_type,
 	attr.numa_node = OPTS_GET(opts, numa_node, 0);
 	attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0);
 
+	attr.map_token_fd = OPTS_GET(opts, token_fd, 0);
+
 	fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
@@ -232,7 +235,7 @@ 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, log_true_size);
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd);
 	void *finfo = NULL, *linfo = NULL;
 	const char *func_info, *line_info;
 	__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@@ -261,8 +264,9 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 	attr.prog_flags = OPTS_GET(opts, prog_flags, 0);
 	attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0);
 	attr.kern_version = OPTS_GET(opts, kern_version, 0);
+	attr.prog_token_fd = OPTS_GET(opts, token_fd, 0);
 
-	if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME))
+	if (prog_name && feat_supported(NULL, FEAT_PROG_NAME))
 		libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	attr.license = ptr_to_u64(license);
 
@@ -1182,7 +1186,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 
 int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size);
+	const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd);
 	union bpf_attr attr;
 	char *log_buf;
 	size_t log_size;
@@ -1207,6 +1211,8 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts
 
 	attr.btf = ptr_to_u64(btf_data);
 	attr.btf_size = btf_size;
+	attr.btf_token_fd = OPTS_GET(opts, token_fd, 0);
+
 	/* log_level == 0 and log_buf != NULL means "try loading without
 	 * log_buf, but retry with log_buf and log_level=1 on error", which is
 	 * consistent across low-level and high-level BTF and program loading
@@ -1287,3 +1293,20 @@ int bpf_prog_bind_map(int prog_fd, int map_fd,
 	ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
+
+int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, token_create);
+	union bpf_attr attr;
+	int fd;
+
+	if (!OPTS_VALID(opts, bpf_token_create_opts))
+		return libbpf_err(-EINVAL);
+
+	memset(&attr, 0, attr_sz);
+	attr.token_create.bpffs_fd = bpffs_fd;
+	attr.token_create.flags = OPTS_GET(opts, flags, 0);
+
+	fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz);
+	return libbpf_err_errno(fd);
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index d0f53772bdc0..991b86bfe7e4 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -51,8 +51,11 @@ struct bpf_map_create_opts {
 
 	__u32 numa_node;
 	__u32 map_ifindex;
+
+	__u32 token_fd;
+	size_t :0;
 };
-#define bpf_map_create_opts__last_field map_ifindex
+#define bpf_map_create_opts__last_field token_fd
 
 LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
 			      const char *map_name,
@@ -102,9 +105,10 @@ struct bpf_prog_load_opts {
 	 * If kernel doesn't support this feature, log_size is left unchanged.
 	 */
 	__u32 log_true_size;
+	__u32 token_fd;
 	size_t :0;
 };
-#define bpf_prog_load_opts__last_field log_true_size
+#define bpf_prog_load_opts__last_field token_fd
 
 LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
 			     const char *prog_name, const char *license,
@@ -130,9 +134,10 @@ struct bpf_btf_load_opts {
 	 * If kernel doesn't support this feature, log_size is left unchanged.
 	 */
 	__u32 log_true_size;
+	__u32 token_fd;
 	size_t :0;
 };
-#define bpf_btf_load_opts__last_field log_true_size
+#define bpf_btf_load_opts__last_field token_fd
 
 LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
 			    struct bpf_btf_load_opts *opts);
@@ -640,6 +645,30 @@ struct bpf_test_run_opts {
 LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
 				      struct bpf_test_run_opts *opts);
 
+struct bpf_token_create_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;
+	size_t :0;
+};
+#define bpf_token_create_opts__last_field flags
+
+/**
+ * @brief **bpf_token_create()** creates a new instance of BPF token derived
+ * from specified BPF FS mount point.
+ *
+ * BPF token created with this API can be passed to bpf() syscall for
+ * commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc.
+ *
+ * @param bpffs_fd FD for BPF FS instance from which to derive a BPF token
+ * instance.
+ * @param opts optional BPF token creation options, can be NULL
+ *
+ * @return BPF token FD > 0, on success; negative error code, otherwise (errno
+ * is also set to the error code)
+ */
+LIBBPF_API int bpf_token_create(int bpffs_fd,
+				struct bpf_token_create_opts *opts);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index 1ac57bb7ac55..7325a12692a3 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -111,6 +111,38 @@ enum bpf_enum_value_kind {
 	val;								      \
 })
 
+/*
+ * Write to a bitfield, identified by s->field.
+ * This is the inverse of BPF_CORE_WRITE_BITFIELD().
+ */
+#define BPF_CORE_WRITE_BITFIELD(s, field, new_val) ({			\
+	void *p = (void *)s + __CORE_RELO(s, field, BYTE_OFFSET);	\
+	unsigned int byte_size = __CORE_RELO(s, field, BYTE_SIZE);	\
+	unsigned int lshift = __CORE_RELO(s, field, LSHIFT_U64);	\
+	unsigned int rshift = __CORE_RELO(s, field, RSHIFT_U64);	\
+	unsigned long long mask, val, nval = new_val;			\
+	unsigned int rpad = rshift - lshift;				\
+									\
+	asm volatile("" : "+r"(p));					\
+									\
+	switch (byte_size) {						\
+	case 1: val = *(unsigned char *)p; break;			\
+	case 2: val = *(unsigned short *)p; break;			\
+	case 4: val = *(unsigned int *)p; break;			\
+	case 8: val = *(unsigned long long *)p; break;			\
+	}								\
+									\
+	mask = (~0ULL << rshift) >> lshift;				\
+	val = (val & ~mask) | ((nval << rpad) & mask);			\
+									\
+	switch (byte_size) {						\
+	case 1: *(unsigned char *)p      = val; break;			\
+	case 2: *(unsigned short *)p     = val; break;			\
+	case 4: *(unsigned int *)p       = val; break;			\
+	case 8: *(unsigned long long *)p = val; break;			\
+	}								\
+})
+
 #define ___bpf_field_ref1(field)	(field)
 #define ___bpf_field_ref2(type, field)	(((typeof(type) *)0)->field)
 #define ___bpf_field_ref(args...)					    \
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index ee95fd379d4d..63033c334320 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1317,7 +1317,9 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf)
 
 static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
 
-int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level)
+int btf_load_into_kernel(struct btf *btf,
+			 char *log_buf, size_t log_sz, __u32 log_level,
+			 int token_fd)
 {
 	LIBBPF_OPTS(bpf_btf_load_opts, opts);
 	__u32 buf_sz = 0, raw_size;
@@ -1367,6 +1369,7 @@ retry_load:
 		opts.log_level = log_level;
 	}
 
+	opts.token_fd = token_fd;
 	btf->fd = bpf_btf_load(raw_data, raw_size, &opts);
 	if (btf->fd < 0) {
 		/* time to turn on verbose mode and try again */
@@ -1394,7 +1397,7 @@ done:
 
 int btf__load_into_kernel(struct btf *btf)
 {
-	return btf_load_into_kernel(btf, NULL, 0, 0);
+	return btf_load_into_kernel(btf, NULL, 0, 0, 0);
 }
 
 int btf__fd(const struct btf *btf)
diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index b02faec748a5..c92e02394159 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -11,8 +11,6 @@
 #include "libbpf_internal.h"
 #include "str_error.h"
 
-#define STRERR_BUFSIZE  128
-
 /* 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
  * explicit version number. This is a GNU extension.
diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
new file mode 100644
index 000000000000..ce98a334be21
--- /dev/null
+++ b/tools/lib/bpf/features.c
@@ -0,0 +1,478 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+#include <linux/kernel.h>
+#include <linux/filter.h>
+#include "bpf.h"
+#include "libbpf.h"
+#include "libbpf_common.h"
+#include "libbpf_internal.h"
+#include "str_error.h"
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64)(unsigned long)ptr;
+}
+
+static int probe_fd(int fd)
+{
+	if (fd >= 0)
+		close(fd);
+	return fd >= 0;
+}
+
+static int probe_kern_prog_name(int token_fd)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_name);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	union bpf_attr attr;
+	int ret;
+
+	memset(&attr, 0, attr_sz);
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.license = ptr_to_u64("GPL");
+	attr.insns = ptr_to_u64(insns);
+	attr.insn_cnt = (__u32)ARRAY_SIZE(insns);
+	attr.prog_token_fd = token_fd;
+	libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name));
+
+	/* make sure loading with name works */
+	ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS);
+	return probe_fd(ret);
+}
+
+static int probe_kern_global_data(int token_fd)
+{
+	char *cp, errmsg[STRERR_BUFSIZE];
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
+		BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd);
+	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd);
+	int ret, map, insn_cnt = ARRAY_SIZE(insns);
+
+	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts);
+	if (map < 0) {
+		ret = -errno;
+		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
+		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
+			__func__, cp, -ret);
+		return ret;
+	}
+
+	insns[0].imm = map;
+
+	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
+	close(map);
+	return probe_fd(ret);
+}
+
+static int probe_kern_btf(int token_fd)
+{
+	static const char strs[] = "\0int";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_func(int token_fd)
+{
+	static const char strs[] = "\0int\0x\0a";
+	/* void x(int a) {} */
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* FUNC_PROTO */                                /* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
+		BTF_PARAM_ENC(7, 1),
+		/* FUNC x */                                    /* [3] */
+		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_func_global(int token_fd)
+{
+	static const char strs[] = "\0int\0x\0a";
+	/* static void x(int a) {} */
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* FUNC_PROTO */                                /* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
+		BTF_PARAM_ENC(7, 1),
+		/* FUNC x BTF_FUNC_GLOBAL */                    /* [3] */
+		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_datasec(int token_fd)
+{
+	static const char strs[] = "\0x\0.data";
+	/* static int a; */
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* DATASEC val */                               /* [3] */
+		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_float(int token_fd)
+{
+	static const char strs[] = "\0float";
+	__u32 types[] = {
+		/* float */
+		BTF_TYPE_FLOAT_ENC(1, 4),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_decl_tag(int token_fd)
+{
+	static const char strs[] = "\0tag";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* attr */
+		BTF_TYPE_DECL_TAG_ENC(1, 2, -1),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_btf_type_tag(int token_fd)
+{
+	static const char strs[] = "\0tag";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		/* attr */
+		BTF_TYPE_TYPE_TAG_ENC(1, 1),				/* [2] */
+		/* ptr */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2),	/* [3] */
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+static int probe_kern_array_mmap(int token_fd)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, opts,
+		.map_flags = BPF_F_MMAPABLE,
+		.token_fd = token_fd,
+	);
+	int fd;
+
+	fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts);
+	return probe_fd(fd);
+}
+
+static int probe_kern_exp_attach_type(int token_fd)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+		.token_fd = token_fd,
+	);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int fd, insn_cnt = ARRAY_SIZE(insns);
+
+	/* use any valid combination of program type and (optional)
+	 * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
+	 * to see if kernel supports expected_attach_type field for
+	 * BPF_PROG_LOAD command
+	 */
+	fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts);
+	return probe_fd(fd);
+}
+
+static int probe_kern_probe_read_kernel(int token_fd)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),	/* r1 = r10 (fp) */
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),	/* r1 += -8 */
+		BPF_MOV64_IMM(BPF_REG_2, 8),		/* r2 = 8 */
+		BPF_MOV64_IMM(BPF_REG_3, 0),		/* r3 = 0 */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel),
+		BPF_EXIT_INSN(),
+	};
+	int fd, insn_cnt = ARRAY_SIZE(insns);
+
+	fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
+	return probe_fd(fd);
+}
+
+static int probe_prog_bind_map(int token_fd)
+{
+	char *cp, errmsg[STRERR_BUFSIZE];
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd);
+	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd);
+	int ret, map, prog, insn_cnt = ARRAY_SIZE(insns);
+
+	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, &map_opts);
+	if (map < 0) {
+		ret = -errno;
+		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
+		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
+			__func__, cp, -ret);
+		return ret;
+	}
+
+	prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
+	if (prog < 0) {
+		close(map);
+		return 0;
+	}
+
+	ret = bpf_prog_bind_map(prog, map, NULL);
+
+	close(map);
+	close(prog);
+
+	return ret >= 0;
+}
+
+static int probe_module_btf(int token_fd)
+{
+	static const char strs[] = "\0int";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
+	};
+	struct bpf_btf_info info;
+	__u32 len = sizeof(info);
+	char name[16];
+	int fd, err;
+
+	fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd);
+	if (fd < 0)
+		return 0; /* BTF not supported at all */
+
+	memset(&info, 0, sizeof(info));
+	info.name = ptr_to_u64(name);
+	info.name_len = sizeof(name);
+
+	/* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer;
+	 * kernel's module BTF support coincides with support for
+	 * name/name_len fields in struct bpf_btf_info.
+	 */
+	err = bpf_btf_get_info_by_fd(fd, &info, &len);
+	close(fd);
+	return !err;
+}
+
+static int probe_perf_link(int token_fd)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
+	int prog_fd, link_fd, err;
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL",
+				insns, ARRAY_SIZE(insns), &opts);
+	if (prog_fd < 0)
+		return -errno;
+
+	/* use invalid perf_event FD to get EBADF, if link is supported;
+	 * otherwise EINVAL should be returned
+	 */
+	link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL);
+	err = -errno; /* close() can clobber errno */
+
+	if (link_fd >= 0)
+		close(link_fd);
+	close(prog_fd);
+
+	return link_fd < 0 && err == -EBADF;
+}
+
+static int probe_uprobe_multi_link(int token_fd)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
+		.expected_attach_type = BPF_TRACE_UPROBE_MULTI,
+		.token_fd = token_fd,
+	);
+	LIBBPF_OPTS(bpf_link_create_opts, link_opts);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd, link_fd, err;
+	unsigned long offset = 0;
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL",
+				insns, ARRAY_SIZE(insns), &load_opts);
+	if (prog_fd < 0)
+		return -errno;
+
+	/* Creating uprobe in '/' binary should fail with -EBADF. */
+	link_opts.uprobe_multi.path = "/";
+	link_opts.uprobe_multi.offsets = &offset;
+	link_opts.uprobe_multi.cnt = 1;
+
+	link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
+	err = -errno; /* close() can clobber errno */
+
+	if (link_fd >= 0)
+		close(link_fd);
+	close(prog_fd);
+
+	return link_fd < 0 && err == -EBADF;
+}
+
+static int probe_kern_bpf_cookie(int token_fd)
+{
+	struct bpf_insn insns[] = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
+	int ret, insn_cnt = ARRAY_SIZE(insns);
+
+	ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
+	return probe_fd(ret);
+}
+
+static int probe_kern_btf_enum64(int token_fd)
+{
+	static const char strs[] = "\0enum64";
+	__u32 types[] = {
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs), token_fd));
+}
+
+typedef int (*feature_probe_fn)(int /* token_fd */);
+
+static struct kern_feature_cache feature_cache;
+
+static struct kern_feature_desc {
+	const char *desc;
+	feature_probe_fn probe;
+} feature_probes[__FEAT_CNT] = {
+	[FEAT_PROG_NAME] = {
+		"BPF program name", probe_kern_prog_name,
+	},
+	[FEAT_GLOBAL_DATA] = {
+		"global variables", probe_kern_global_data,
+	},
+	[FEAT_BTF] = {
+		"minimal BTF", probe_kern_btf,
+	},
+	[FEAT_BTF_FUNC] = {
+		"BTF functions", probe_kern_btf_func,
+	},
+	[FEAT_BTF_GLOBAL_FUNC] = {
+		"BTF global function", probe_kern_btf_func_global,
+	},
+	[FEAT_BTF_DATASEC] = {
+		"BTF data section and variable", probe_kern_btf_datasec,
+	},
+	[FEAT_ARRAY_MMAP] = {
+		"ARRAY map mmap()", probe_kern_array_mmap,
+	},
+	[FEAT_EXP_ATTACH_TYPE] = {
+		"BPF_PROG_LOAD expected_attach_type attribute",
+		probe_kern_exp_attach_type,
+	},
+	[FEAT_PROBE_READ_KERN] = {
+		"bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel,
+	},
+	[FEAT_PROG_BIND_MAP] = {
+		"BPF_PROG_BIND_MAP support", probe_prog_bind_map,
+	},
+	[FEAT_MODULE_BTF] = {
+		"module BTF support", probe_module_btf,
+	},
+	[FEAT_BTF_FLOAT] = {
+		"BTF_KIND_FLOAT support", probe_kern_btf_float,
+	},
+	[FEAT_PERF_LINK] = {
+		"BPF perf link support", probe_perf_link,
+	},
+	[FEAT_BTF_DECL_TAG] = {
+		"BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag,
+	},
+	[FEAT_BTF_TYPE_TAG] = {
+		"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
+	},
+	[FEAT_MEMCG_ACCOUNT] = {
+		"memcg-based memory accounting", probe_memcg_account,
+	},
+	[FEAT_BPF_COOKIE] = {
+		"BPF cookie support", probe_kern_bpf_cookie,
+	},
+	[FEAT_BTF_ENUM64] = {
+		"BTF_KIND_ENUM64 support", probe_kern_btf_enum64,
+	},
+	[FEAT_SYSCALL_WRAPPER] = {
+		"Kernel using syscall wrapper", probe_kern_syscall_wrapper,
+	},
+	[FEAT_UPROBE_MULTI_LINK] = {
+		"BPF multi-uprobe link support", probe_uprobe_multi_link,
+	},
+};
+
+bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id)
+{
+	struct kern_feature_desc *feat = &feature_probes[feat_id];
+	int ret;
+
+	/* assume global feature cache, unless custom one is provided */
+	if (!cache)
+		cache = &feature_cache;
+
+	if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) {
+		ret = feat->probe(cache->token_fd);
+		if (ret > 0) {
+			WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED);
+		} else if (ret == 0) {
+			WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
+		} else {
+			pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret);
+			WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
+		}
+	}
+
+	return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED;
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ea9b8158c20d..4b5ff9508e18 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -59,6 +59,8 @@
 #define BPF_FS_MAGIC		0xcafe4a11
 #endif
 
+#define BPF_FS_DEFAULT_PATH "/sys/fs/bpf"
+
 #define BPF_INSN_SZ (sizeof(struct bpf_insn))
 
 /* vsprintf() in __base_pr() uses nonliteral format string. It may break
@@ -693,6 +695,10 @@ struct bpf_object {
 
 	struct usdt_manager *usdt_man;
 
+	struct kern_feature_cache *feat_cache;
+	char *token_path;
+	int token_fd;
+
 	char path[];
 };
 
@@ -2192,7 +2198,7 @@ static int build_map_pin_path(struct bpf_map *map, const char *path)
 	int err;
 
 	if (!path)
-		path = "/sys/fs/bpf";
+		path = BPF_FS_DEFAULT_PATH;
 
 	err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map));
 	if (err)
@@ -3054,9 +3060,15 @@ static bool prog_needs_vmlinux_btf(struct bpf_program *prog)
 	return false;
 }
 
+static bool map_needs_vmlinux_btf(struct bpf_map *map)
+{
+	return bpf_map__is_struct_ops(map);
+}
+
 static bool obj_needs_vmlinux_btf(const struct bpf_object *obj)
 {
 	struct bpf_program *prog;
+	struct bpf_map *map;
 	int i;
 
 	/* CO-RE relocations need kernel BTF, only when btf_custom_path
@@ -3081,6 +3093,11 @@ static bool obj_needs_vmlinux_btf(const struct bpf_object *obj)
 			return true;
 	}
 
+	bpf_object__for_each_map(map, obj) {
+		if (map_needs_vmlinux_btf(map))
+			return true;
+	}
+
 	return false;
 }
 
@@ -3268,7 +3285,7 @@ skip_exception_cb:
 	} else {
 		/* currently BPF_BTF_LOAD only supports log_level 1 */
 		err = btf_load_into_kernel(kern_btf, obj->log_buf, obj->log_size,
-					   obj->log_level ? 1 : 0);
+					   obj->log_level ? 1 : 0, obj->token_fd);
 	}
 	if (sanitize) {
 		if (!err) {
@@ -4591,6 +4608,63 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
 	return 0;
 }
 
+static int bpf_object_prepare_token(struct bpf_object *obj)
+{
+	const char *bpffs_path;
+	int bpffs_fd = -1, token_fd, err;
+	bool mandatory;
+	enum libbpf_print_level level;
+
+	/* token is already set up */
+	if (obj->token_fd > 0)
+		return 0;
+	/* token is explicitly prevented */
+	if (obj->token_fd < 0) {
+		pr_debug("object '%s': token is prevented, skipping...\n", obj->name);
+		/* reset to zero to avoid extra checks during map_create and prog_load steps */
+		obj->token_fd = 0;
+		return 0;
+	}
+
+	mandatory = obj->token_path != NULL;
+	level = mandatory ? LIBBPF_WARN : LIBBPF_DEBUG;
+
+	bpffs_path = obj->token_path ?: BPF_FS_DEFAULT_PATH;
+	bpffs_fd = open(bpffs_path, O_DIRECTORY, O_RDWR);
+	if (bpffs_fd < 0) {
+		err = -err