20 files changed, 1746 insertions, 910 deletions

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 9ae8f4ef0aac..f43249696d9f 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -1,6 +1,9 @@
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 # Most of this file is copied from tools/lib/traceevent/Makefile
 
+RM ?= rm
+srctree = $(abs_srctree)
+
 LIBBPF_VERSION := $(shell \
 	grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | \
 	sort -rV | head -n1 | cut -d'_' -f2)
@@ -56,7 +59,7 @@ ifndef VERBOSE
 endif
 
 FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-mmap zlib bpf reallocarray
+FEATURE_TESTS = libelf zlib bpf
 FEATURE_DISPLAY = libelf zlib bpf
 
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
@@ -98,16 +101,8 @@ else
   CFLAGS := -g -Wall
 endif
 
-ifeq ($(feature-libelf-mmap), 1)
-  override CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT
-endif
-
-ifeq ($(feature-reallocarray), 0)
-  override CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
-endif
-
 # Append required CFLAGS
-override CFLAGS += $(EXTRA_WARNINGS)
+override CFLAGS += $(EXTRA_WARNINGS) -Wno-switch-enum
 override CFLAGS += -Werror -Wall
 override CFLAGS += -fPIC
 override CFLAGS += $(INCLUDES)
@@ -197,7 +192,7 @@ $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED)
 	@ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION)
 
 $(OUTPUT)libbpf.a: $(BPF_IN_STATIC)
-	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
+	$(QUIET_LINK)$(RM) -f $@; $(AR) rcs $@ $^
 
 $(OUTPUT)libbpf.pc:
 	$(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \
@@ -271,10 +266,10 @@ install: install_lib install_pkgconfig install_headers
 ### Cleaning rules
 
 config-clean:
-	$(call QUIET_CLEAN, config)
+	$(call QUIET_CLEAN, feature-detect)
 	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
 
-clean:
+clean: config-clean
 	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS)		     \
 		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS)		     \
 		$(SHARED_OBJDIR) $(STATIC_OBJDIR)			     \
@@ -301,7 +296,7 @@ cscope:
 	cscope -b -q -I $(srctree)/include -f cscope.out
 
 tags:
-	rm -f TAGS tags
+	$(RM) -f TAGS tags
 	ls *.c *.h | xargs $(TAGS_PROG) -a
 
 # Declare the contents of the .PHONY variable as phony.  We keep that
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 0750681057c2..82b983ff6569 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -32,9 +32,6 @@
 #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
-
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
  * required to be defined explicitly.
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index eae5cccff761..bbcefb3ff5a5 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -19,32 +19,52 @@ enum bpf_field_info_kind {
 	BPF_FIELD_RSHIFT_U64 = 5,
 };
 
+/* second argument to __builtin_btf_type_id() built-in */
+enum bpf_type_id_kind {
+	BPF_TYPE_ID_LOCAL = 0,		/* BTF type ID in local program */
+	BPF_TYPE_ID_TARGET = 1,		/* BTF type ID in target kernel */
+};
+
+/* second argument to __builtin_preserve_type_info() built-in */
+enum bpf_type_info_kind {
+	BPF_TYPE_EXISTS = 0,		/* type existence in target kernel */
+	BPF_TYPE_SIZE = 1,		/* type size in target kernel */
+};
+
+/* second argument to __builtin_preserve_enum_value() built-in */
+enum bpf_enum_value_kind {
+	BPF_ENUMVAL_EXISTS = 0,		/* enum value existence in kernel */
+	BPF_ENUMVAL_VALUE = 1,		/* enum value value relocation */
+};
+
 #define __CORE_RELO(src, field, info)					      \
 	__builtin_preserve_field_info((src)->field, BPF_FIELD_##info)
 
 #if __BYTE_ORDER == __LITTLE_ENDIAN
 #define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
-	bpf_probe_read((void *)dst,					      \
-		       __CORE_RELO(src, fld, BYTE_SIZE),		      \
-		       (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
+	bpf_probe_read_kernel(						      \
+			(void *)dst,				      \
+			__CORE_RELO(src, fld, BYTE_SIZE),		      \
+			(const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
 #else
 /* semantics of LSHIFT_64 assumes loading values into low-ordered bytes, so
  * for big-endian we need to adjust destination pointer accordingly, based on
  * field byte size
  */
 #define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
-	bpf_probe_read((void *)dst + (8 - __CORE_RELO(src, fld, BYTE_SIZE)),  \
-		       __CORE_RELO(src, fld, BYTE_SIZE),		      \
-		       (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
+	bpf_probe_read_kernel(						      \
+			(void *)dst + (8 - __CORE_RELO(src, fld, BYTE_SIZE)), \
+			__CORE_RELO(src, fld, BYTE_SIZE),		      \
+			(const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
 #endif
 
 /*
  * Extract bitfield, identified by s->field, and return its value as u64.
  * All this is done in relocatable manner, so bitfield changes such as
  * signedness, bit size, offset changes, this will be handled automatically.
- * This version of macro is using bpf_probe_read() to read underlying integer
- * storage. Macro functions as an expression and its return type is
- * bpf_probe_read()'s return value: 0, on success, <0 on error.
+ * This version of macro is using bpf_probe_read_kernel() to read underlying
+ * integer storage. Macro functions as an expression and its return type is
+ * bpf_probe_read_kernel()'s return value: 0, on success, <0 on error.
  */
 #define BPF_CORE_READ_BITFIELD_PROBED(s, field) ({			      \
 	unsigned long long val = 0;					      \
@@ -92,15 +112,75 @@ enum bpf_field_info_kind {
 	__builtin_preserve_field_info(field, BPF_FIELD_EXISTS)
 
 /*
- * Convenience macro to get byte size of a field. Works for integers,
+ * Convenience macro to get the byte size of a field. Works for integers,
  * struct/unions, pointers, arrays, and enums.
  */
 #define bpf_core_field_size(field)					    \
 	__builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE)
 
 /*
- * bpf_core_read() abstracts away bpf_probe_read() call and captures offset
- * relocation for source address using __builtin_preserve_access_index()
+ * Convenience macro to get BTF type ID of a specified type, using a local BTF
+ * information. Return 32-bit unsigned integer with type ID from program's own
+ * BTF. Always succeeds.
+ */
+#define bpf_core_type_id_local(type)					    \
+	__builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_LOCAL)
+
+/*
+ * Convenience macro to get BTF type ID of a target kernel's type that matches
+ * specified local type.
+ * Returns:
+ *    - valid 32-bit unsigned type ID in kernel BTF;
+ *    - 0, if no matching type was found in a target kernel BTF.
+ */
+#define bpf_core_type_id_kernel(type)					    \
+	__builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_TARGET)
+
+/*
+ * Convenience macro to check that provided named type
+ * (struct/union/enum/typedef) exists in a target kernel.
+ * Returns:
+ *    1, if such type is present in target kernel's BTF;
+ *    0, if no matching type is found.
+ */
+#define bpf_core_type_exists(type)					    \
+	__builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_EXISTS)
+
+/*
+ * Convenience macro to get the byte size of a provided named type
+ * (struct/union/enum/typedef) in a target kernel.
+ * Returns:
+ *    >= 0 size (in bytes), if type is present in target kernel's BTF;
+ *    0, if no matching type is found.
+ */
+#define bpf_core_type_size(type)					    \
+	__builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_SIZE)
+
+/*
+ * Convenience macro to check that provided enumerator value is defined in
+ * a target kernel.
+ * Returns:
+ *    1, if specified enum type and its enumerator value are present in target
+ *    kernel's BTF;
+ *    0, if no matching enum and/or enum value within that enum is found.
+ */
+#define bpf_core_enum_value_exists(enum_type, enum_value)		    \
+	__builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_EXISTS)
+
+/*
+ * Convenience macro to get the integer value of an enumerator value in
+ * a target kernel.
+ * Returns:
+ *    64-bit value, if specified enum type and its enumerator value are
+ *    present in target kernel's BTF;
+ *    0, if no matching enum and/or enum value within that enum is found.
+ */
+#define bpf_core_enum_value(enum_type, enum_value)			    \
+	__builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_VALUE)
+
+/*
+ * bpf_core_read() abstracts away bpf_probe_read_kernel() call and captures
+ * offset relocation for source address using __builtin_preserve_access_index()
  * built-in, provided by Clang.
  *
  * __builtin_preserve_access_index() takes as an argument an expression of
@@ -115,8 +195,8 @@ enum bpf_field_info_kind {
  * (local) BTF, used to record relocation.
  */
 #define bpf_core_read(dst, sz, src)					    \
-	bpf_probe_read(dst, sz,						    \
-		       (const void *)__builtin_preserve_access_index(src))
+	bpf_probe_read_kernel(dst, sz,					    \
+			      (const void *)__builtin_preserve_access_index(src))
 
 /*
  * bpf_core_read_str() is a thin wrapper around bpf_probe_read_str()
@@ -124,8 +204,8 @@ enum bpf_field_info_kind {
  * argument.
  */
 #define bpf_core_read_str(dst, sz, src)					    \
-	bpf_probe_read_str(dst, sz,					    \
-			   (const void *)__builtin_preserve_access_index(src))
+	bpf_probe_read_kernel_str(dst, sz,				    \
+				  (const void *)__builtin_preserve_access_index(src))
 
 #define ___concat(a, b) a ## b
 #define ___apply(fn, n) ___concat(fn, n)
@@ -239,15 +319,17 @@ enum bpf_field_info_kind {
  *	int x = BPF_CORE_READ(s, a.b.c, d.e, f, g);
  *
  * BPF_CORE_READ will decompose above statement into 4 bpf_core_read (BPF
- * CO-RE relocatable bpf_probe_read() wrapper) calls, logically equivalent to:
+ * CO-RE relocatable bpf_probe_read_kernel() wrapper) calls, logically
+ * equivalent to:
  * 1. const void *__t = s->a.b.c;
  * 2. __t = __t->d.e;
  * 3. __t = __t->f;
  * 4. return __t->g;
  *
  * Equivalence is logical, because there is a heavy type casting/preservation
- * involved, as well as all the reads are happening through bpf_probe_read()
- * calls using __builtin_preserve_access_index() to emit CO-RE relocations.
+ * involved, as well as all the reads are happening through
+ * bpf_probe_read_kernel() calls using __builtin_preserve_access_index() to
+ * emit CO-RE relocations.
  *
  * N.B. Only up to 9 "field accessors" are supported, which should be more
  * than enough for any practical purpose.
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index e9a4ecddb7a5..1106777df00b 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -32,6 +32,9 @@
 #ifndef __always_inline
 #define __always_inline __attribute__((always_inline))
 #endif
+#ifndef __noinline
+#define __noinline __attribute__((noinline))
+#endif
 #ifndef __weak
 #define __weak __attribute__((weak))
 #endif
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index bafca49cb1e6..3ed1a27b5f7c 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -8,9 +8,6 @@
 #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
-
 struct bpf_prog_linfo {
 	void *raw_linfo;
 	void *raw_jited_linfo;
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index eebf020cbe3e..f9ef37707888 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -289,9 +289,9 @@ struct pt_regs;
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
 #else
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)					    \
-	({ bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
+	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
 #define BPF_KRETPROBE_READ_RET_IP(ip, ctx)				    \
-	({ bpf_probe_read(&(ip), sizeof(ip),				    \
+	({ bpf_probe_read_kernel(&(ip), sizeof(ip),			    \
 			  (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
 #endif
 
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 7dfca7016aaa..a3d259e614b0 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -21,9 +21,6 @@
 #include "libbpf_internal.h"
 #include "hashmap.h"
 
-/* make sure libbpf doesn't use kernel-only integer typedefs */
-#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
-
 #define BTF_MAX_NR_TYPES 0x7fffffffU
 #define BTF_MAX_STR_OFFSET 0x7fffffffU
 
@@ -61,7 +58,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t)
 		expand_by = max(btf->types_size >> 2, 16U);
 		new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by);
 
-		new_types = realloc(btf->types, sizeof(*new_types) * new_size);
+		new_types = libbpf_reallocarray(btf->types, new_size, sizeof(*new_types));
 		if (!new_types)
 			return -ENOMEM;
 
@@ -1131,14 +1128,14 @@ static int btf_ext_setup_line_info(struct btf_ext *btf_ext)
 	return btf_ext_setup_info(btf_ext, &param);
 }
 
-static int btf_ext_setup_field_reloc(struct btf_ext *btf_ext)
+static int btf_ext_setup_core_relos(struct btf_ext *btf_ext)
 {
 	struct btf_ext_sec_setup_param param = {
-		.off = btf_ext->hdr->field_reloc_off,
-		.len = btf_ext->hdr->field_reloc_len,
-		.min_rec_size = sizeof(struct bpf_field_reloc),
-		.ext_info = &btf_ext->field_reloc_info,
-		.desc = "field_reloc",
+		.off = btf_ext->hdr->core_relo_off,
+		.len = btf_ext->hdr->core_relo_len,
+		.min_rec_size = sizeof(struct bpf_core_relo),
+		.ext_info = &btf_ext->core_relo_info,
+		.desc = "core_relo",
 	};
 
 	return btf_ext_setup_info(btf_ext, &param);
@@ -1217,10 +1214,9 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 	if (err)
 		goto done;
 
-	if (btf_ext->hdr->hdr_len <
-	    offsetofend(struct btf_ext_header, field_reloc_len))
+	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len))
 		goto done;
-	err = btf_ext_setup_field_reloc(btf_ext);
+	err = btf_ext_setup_core_relos(btf_ext);
 	if (err)
 		goto done;
 
@@ -1575,7 +1571,7 @@ static int btf_dedup_hypot_map_add(struct btf_dedup *d,
 		__u32 *new_list;
 
 		d->hypot_cap += max((size_t)16, d->hypot_cap / 2);
-		new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap);
+		new_list = libbpf_reallocarray(d->hypot_list, d->hypot_cap, sizeof(__u32));
 		if (!new_list)
 			return -ENOMEM;
 		d->hypot_list = new_list;
@@ -1871,8 +1867,7 @@ static int btf_dedup_strings(struct btf_dedup *d)
 			struct btf_str_ptr *new_ptrs;
 
 			strs.cap += max(strs.cnt / 2, 16U);
-			new_ptrs = realloc(strs.ptrs,
-					   sizeof(strs.ptrs[0]) * strs.cap);
+			new_ptrs = libbpf_reallocarray(strs.ptrs, strs.cap, sizeof(strs.ptrs[0]));
 			if (!new_ptrs) {
 				err = -ENOMEM;
 				goto done;
@@ -2957,8 +2952,8 @@ static int btf_dedup_compact_types(struct btf_dedup *d)
 	d->btf->nr_types = next_type_id - 1;
 	d->btf->types_size = d->btf->nr_types;
 	d->btf->hdr->type_len = p - types_start;
-	new_types = realloc(d->btf->types,
-			    (1 + d->btf->nr_types) * sizeof(struct btf_type *));
+	new_types = libbpf_reallocarray(d->btf->types, (1 + d->btf->nr_types),
+					sizeof(struct btf_type *));
 	if (!new_types)
 		return -ENOMEM;
 	d->btf->types = new_types;
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 1ca14448df4c..91f0ad0e0325 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -24,44 +24,6 @@ struct btf_type;
 
 struct bpf_object;
 
-/*
- * The .BTF.ext ELF section layout defined as
- *   struct btf_ext_header
- *   func_info subsection
- *
- * The func_info subsection layout:
- *   record size for struct bpf_func_info in the func_info subsection
- *   struct btf_sec_func_info for section #1
- *   a list of bpf_func_info records for section #1
- *     where struct bpf_func_info mimics one in include/uapi/linux/bpf.h
- *     but may not be identical
- *   struct btf_sec_func_info for section #2
- *   a list of bpf_func_info records for section #2
- *   ......
- *
- * Note that the bpf_func_info record size in .BTF.ext may not
- * be the same as the one defined in include/uapi/linux/bpf.h.
- * The loader should ensure that record_size meets minimum
- * requirement and pass the record as is to the kernel. The
- * kernel will handle the func_info properly based on its contents.
- */
-struct btf_ext_header {
-	__u16	magic;
-	__u8	version;
-	__u8	flags;
-	__u32	hdr_len;
-
-	/* All offsets are in bytes relative to the end of this header */
-	__u32	func_info_off;
-	__u32	func_info_len;
-	__u32	line_info_off;
-	__u32	line_info_len;
-
-	/* optional part of .BTF.ext header */
-	__u32	field_reloc_off;
-	__u32	field_reloc_len;
-};
-
 LIBBPF_API void btf__free(struct btf *btf);
 LIBBPF_API struct btf *btf__new(const void *data, __u32 size);
 LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 57c00fa63932..6c079b3c8679 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -19,9 +19,6 @@
 #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
-
 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;
 
@@ -323,8 +320,7 @@ static int btf_dump_add_emit_queue_id(struct btf_dump *d, __u32 id)
 
 	if (d->emit_queue_cnt >= d->emit_queue_cap) {
 		new_cap = max(16, d->emit_queue_cap * 3 / 2);
-		new_queue = realloc(d->emit_queue,
-				    new_cap * sizeof(new_queue[0]));
+		new_queue = libbpf_reallocarray(d->emit_queue, new_cap, sizeof(new_queue[0]));
 		if (!new_queue)
 			return -ENOMEM;
 		d->emit_queue = new_queue;
@@ -1003,8 +999,7 @@ static int btf_dump_push_decl_stack_id(struct btf_dump *d, __u32 id)
 
 	if (d->decl_stack_cnt >= d->decl_stack_cap) {
 		new_cap = max(16, d->decl_stack_cap * 3 / 2);
-		new_stack = realloc(d->decl_stack,
-				    new_cap * sizeof(new_stack[0]));
+		new_stack = libbpf_reallocarray(d->decl_stack, new_cap, sizeof(new_stack[0]));
 		if (!new_stack)
 			return -ENOMEM;
 		d->decl_stack = new_stack;
diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c
index a405dad068f5..3c20b126d60d 100644
--- a/tools/lib/bpf/hashmap.c
+++ b/tools/lib/bpf/hashmap.c
@@ -15,6 +15,9 @@
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
+/* prevent accidental re-addition of reallocarray() */
+#pragma GCC poison reallocarray
+
 /* start with 4 buckets */
 #define HASHMAP_MIN_CAP_BITS 2
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7253b833576c..46d727b45c81 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -44,7 +44,6 @@
 #include <sys/vfs.h>
 #include <sys/utsname.h>
 #include <sys/resource.h>
-#include <tools/libc_compat.h>
 #include <libelf.h>
 #include <gelf.h>
 #include <zlib.h>
@@ -56,9 +55,6 @@
 #include "libbpf_internal.h"
 #include "hashmap.h"
 
-/* make sure libbpf doesn't use kernel-only integer typedefs */
-#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
-
 #ifndef EM_BPF
 #define EM_BPF 247
 #endif
@@ -67,6 +63,8 @@
 #define BPF_FS_MAGIC		0xcafe4a11
 #endif
 
+#define BPF_INSN_SZ (sizeof(struct bpf_insn))
+
 /* vsprintf() in __base_pr() uses nonliteral format string. It may break
  * compilation if user enables corresponding warning. Disable it explicitly.
  */
@@ -154,34 +152,35 @@ static void pr_perm_msg(int err)
 	___err; })
 #endif
 
-#ifdef HAVE_LIBELF_MMAP_SUPPORT
-# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ_MMAP
-#else
-# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
-#endif
-
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
 }
 
-struct bpf_capabilities {
+enum kern_feature_id {
 	/* v4.14: kernel support for program & map names. */
-	__u32 name:1;
+	FEAT_PROG_NAME,
 	/* v5.2: kernel support for global data sections. */
-	__u32 global_data:1;
+	FEAT_GLOBAL_DATA,
+	/* BTF support */
+	FEAT_BTF,
 	/* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
-	__u32 btf_func:1;
+	FEAT_BTF_FUNC,
 	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
-	__u32 btf_datasec:1;
-	/* BPF_F_MMAPABLE is supported for arrays */
-	__u32 array_mmap:1;
+	FEAT_BTF_DATASEC,
 	/* BTF_FUNC_GLOBAL is supported */
-	__u32 btf_func_global:1;
+	FEAT_BTF_GLOBAL_FUNC,
+	/* BPF_F_MMAPABLE is supported for arrays */
+	FEAT_ARRAY_MMAP,
 	/* kernel support for expected_attach_type in BPF_PROG_LOAD */
-	__u32 exp_attach_type:1;
+	FEAT_EXP_ATTACH_TYPE,
+	/* bpf_probe_read_{kernel,user}[_str] helpers */
+	FEAT_PROBE_READ_KERN,
+	__FEAT_CNT,
 };
 
+static bool kernel_supports(enum kern_feature_id feat_id);
+
 enum reloc_type {
 	RELO_LD64,
 	RELO_CALL,
@@ -209,6 +208,7 @@ struct bpf_sec_def {
 	bool is_exp_attach_type_optional;
 	bool is_attachable;
 	bool is_attach_btf;
+	bool is_sleepable;
 	attach_fn_t attach_fn;
 };
 
@@ -253,8 +253,6 @@ struct bpf_program {
 	__u32 func_info_rec_size;
 	__u32 func_info_cnt;
 
-	struct bpf_capabilities *caps;
-
 	void *line_info;
 	__u32 line_info_rec_size;
 	__u32 line_info_cnt;
@@ -403,6 +401,7 @@ struct bpf_object {
 		Elf_Data *rodata;
 		Elf_Data *bss;
 		Elf_Data *st_ops_data;
+		size_t shstrndx; /* section index for section name strings */
 		size_t strtabidx;
 		struct {
 			GElf_Shdr shdr;
@@ -436,12 +435,18 @@ struct bpf_object {
 	void *priv;
 	bpf_object_clear_priv_t clear_priv;
 
-	struct bpf_capabilities caps;
-
 	char path[];
 };
 #define obj_elf_valid(o)	((o)->efile.elf)
 
+static const char *elf_sym_str(const struct bpf_object *obj, size_t off);
+static const char *elf_sec_str(const struct bpf_object *obj, size_t off);
+static Elf_Scn *elf_sec_by_idx(const struct bpf_object *obj, size_t idx);
+static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name);
+static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr);
+static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn);
+static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn);
+
 void bpf_program__unload(struct bpf_program *prog)
 {
 	int i;
@@ -503,7 +508,7 @@ static char *__bpf_program__pin_name(struct bpf_program *prog)
 }
 
 static int
-bpf_program__init(void *data, size_t size, char *section_name, int idx,
+bpf_program__init(void *data, size_t size, const char *section_name, int idx,
 		  struct bpf_program *prog)
 {
 	const size_t bpf_insn_sz = sizeof(struct bpf_insn);
@@ -552,7 +557,7 @@ errout:
 
 static int
 bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
-			char *section_name, int idx)
+			const char *section_name, int idx)
 {
 	struct bpf_program prog, *progs;
 	int nr_progs, err;
@@ -561,11 +566,10 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
 	if (err)
 		return err;
 
-	prog.caps = &obj->caps;
 	progs = obj->programs;
 	nr_progs = obj->nr_programs;
 
-	progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
+	progs = libbpf_reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
 	if (!progs) {
 		/*
 		 * In this case the original obj->programs
@@ -578,7 +582,7 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
 		return -ENOMEM;
 	}
 
-	pr_debug("found program %s\n", prog.section_name);
+	pr_debug("elf: found program '%s'\n", prog.section_name);
 	obj->programs = progs;
 	obj->nr_programs = nr_progs + 1;
 	prog.obj = obj;
@@ -598,8 +602,7 @@ bpf_object__init_prog_names(struct bpf_object *obj)
 
 		prog = &obj->programs[pi];
 
-		for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
-		     si++) {
+		for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name; si++) {
 			GElf_Sym sym;
 
 			if (!gelf_getsym(symbols, si, &sym))
@@ -609,11 +612,9 @@ bpf_object__init_prog_names(struct bpf_object *obj)
 			if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
 				continue;
 
-			name = elf_strptr(obj->efile.elf,
-					  obj->efile.strtabidx,
-					  sym.st_name);
+			name = elf_sym_str(obj, sym.st_name);
 			if (!name) {
-				pr_warn("failed to get sym name string for prog %s\n",
+				pr_warn("prog '%s': failed to get symbol name\n",
 					prog->section_name);
 				return -LIBBPF_ERRNO__LIBELF;
 			}
@@ -623,17 +624,14 @@ bpf_object__init_prog_names(struct bpf_object *obj)
 			name = ".text";
 
 		if (!name) {
-			pr_warn("failed to find sym for prog %s\n",
+			pr_warn("prog '%s': failed to find program symbol\n",
 				prog->section_name);
 			return -EINVAL;
 		}
 
 		prog->name = strdup(name);
-		if (!prog->name) {
-			pr_warn("failed to allocate memory for prog sym %s\n",
-				name);
+		if (!prog->name)
 			return -ENOMEM;
-		}
 	}
 
 	return 0;
@@ -1066,13 +1064,18 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
 	obj->efile.obj_buf_sz = 0;
 }
 
+/* if libelf is old and doesn't support mmap(), fall back to read() */
+#ifndef ELF_C_READ_MMAP
+#define ELF_C_READ_MMAP ELF_C_READ
+#endif
+
 static int bpf_object__elf_init(struct bpf_object *obj)
 {
 	int err = 0;
 	GElf_Ehdr *ep;
 
 	if (obj_elf_valid(obj)) {
-		pr_warn("elf init: internal error\n");
+		pr_warn("elf: init internal error\n");
 		return -LIBBPF_ERRNO__LIBELF;
 	}
 
@@ -1090,31 +1093,44 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 
 			err = -errno;
 			cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
-			pr_warn("failed to open %s: %s\n", obj->path, cp);
+			pr_warn("elf: failed to open %s: %s\n", obj->path, cp);
 			return err;
 		}
 
-		obj->efile.elf = elf_begin(obj->efile.fd,
-					   LIBBPF_ELF_C_READ_MMAP, NULL);
+		obj->efile.elf = elf_begin(obj->efile.fd, ELF_C_READ_MMAP, NULL);
 	}
 
 	if (!obj->efile.elf) {
-		pr_warn("failed to open %s as ELF file\n", obj->path);
+		pr_warn("elf: failed to open %s as ELF file: %s\n", obj->path, elf_errmsg(-1));
 		err = -LIBBPF_ERRNO__LIBELF;
 		goto errout;
 	}
 
 	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
-		pr_warn("failed to get EHDR from %s\n", obj->path);
+		pr_warn("elf: failed to get ELF header from %s: %s\n", obj->path, elf_errmsg(-1));
 		err = -LIBBPF_ERRNO__FORMAT;
 		goto errout;
 	}
 	ep = &obj->efile.ehdr;
 
+	if (elf_getshdrstrndx(obj->efile.elf, &obj->efile.shstrndx)) {
+		pr_warn("elf: failed to get section names section index for %s: %s\n",
+			obj->path, elf_errmsg(-1));
+		err = -LIBBPF_ERRNO__FORMAT;
+		goto errout;
+	}
+
+	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
+	if (!elf_rawdata(elf_getscn(obj->efile.elf, obj->efile.shstrndx), NULL)) {
+		pr_warn("elf: failed to get section names strings from %s: %s\n",
+			obj->path, elf_errmsg(-1));
+		return -LIBBPF_ERRNO__FORMAT;
+	}
+
 	/* Old LLVM set e_machine to EM_NONE */
 	if (ep->e_type != ET_REL ||
 	    (ep->e_machine && ep->e_machine != EM_BPF)) {
-		pr_warn("%s is not an eBPF object file\n", obj->path);
+		pr_warn("elf: %s is not a valid eBPF object file\n", obj->path);
 		err = -LIBBPF_ERRNO__FORMAT;
 		goto errout;
 	}
@@ -1136,7 +1152,7 @@ static int bpf_object__check_endianness(struct bpf_object *obj)
 #else
 # error "Unrecognized __BYTE_ORDER__"
 #endif
-	pr_warn("endianness mismatch.\n");
+	pr_warn("elf: endianness mismatch in %s.\n", obj->path);
 	return -LIBBPF_ERRNO__ENDIAN;
 }
 
@@ -1171,55 +1187,10 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
 	return false;
 }
 
-static int bpf_object_search_section_size(const struct bpf_object *obj,
-					  const char *name, size_t *d_size)
-{
-	const GElf_Ehdr *ep = &obj->efile.ehdr;
-	Elf *elf = obj->efile.elf;
-	Elf_Scn *scn = NULL;
-	int idx = 0;
-
-	while ((scn = elf_nextscn(elf, scn)) != NULL) {
-		const char *sec_name;
-		Elf_Data *data;
-		GElf_Shdr sh;
-
-		idx++;
-		if (gelf_getshdr(scn, &sh) != &sh) {
-			pr_warn("failed to get section(%d) header from %s\n",
-				idx, obj->path);
-			return -EIO;
-		}
-
-		sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
-		if (!sec_name) {
-			pr_warn("failed to get section(%d) name from %s\n",
-				idx, obj->path);
-			return -EIO;
-		}
-
-		if (strcmp(name, sec_name))
-			continue;
-
-		data = elf_getdata(scn, 0);
-		if (!data) {
-			pr_warn("failed to get section(%d) data from %s(%s)\n",
-				idx, name, obj->path);
-			return -EIO;
-		}
-
-		*d_size = data->d_size;
-		return 0;
-	}
-
-	return -ENOENT;
-}
-
 int bpf_object__section_size(const struct bpf_object *obj, const char *name,
 			     __u32 *size)
 {
 	int ret = -ENOENT;
-	size_t d_size;
 
 	*size = 0;
 	if (!name) {
@@ -1237,9 +1208,13 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name,
 		if (obj->efile.st_ops_data)
 			*size = obj->efile.st_ops_data->d_size;
 	} else {
-		ret = bpf_object_search_section_size(obj, name, &d_size);
-		if (!ret)
-			*size = d_size;
+		Elf_Scn *scn = elf_sec_by_name(obj, name);
+		Elf_Data *data = elf_sec_data(obj, scn);
+
+		if (data) {
+			ret = 0; /* found it */
+			*size = data->d_size;
+		}
 	}
 
 	return *size ? 0 : ret;
@@ -1264,8 +1239,7 @@ int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
 		    GELF_ST_TYPE(sym.st_info) != STT_OBJECT)
 			continue;
 
-		sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
-				   sym.st_name);
+		sname = elf_sym_str(obj, sym.st_name);
 		if (!sname) {
 			pr_warn("failed to get sym name string for var %s\n",
 				name);
@@ -1290,7 +1264,7 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
 		return &obj->maps[obj->nr_maps++];
 
 	new_cap = max((size_t)4, obj->maps_cap * 3 / 2);
-	new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps));
+	new_maps = libbpf_reallocarray(obj->maps, new_cap, sizeof(*obj->maps));
 	if (!new_maps) {
 		pr_warn("alloc maps for object failed\n");
 		return ERR_PTR(-ENOMEM);
@@ -1742,12 +1716,12 @@ static int