summaryrefslogtreecommitdiffstats
path: root/tools/lib
diff options
context:
space:
mode:
Diffstat (limited to 'tools/lib')
-rw-r--r--tools/lib/bpf/bpf_helpers.h31
-rw-r--r--tools/lib/bpf/bpf_tracing.h107
-rw-r--r--tools/lib/bpf/btf.c32
-rw-r--r--tools/lib/bpf/btf.h25
-rw-r--r--tools/lib/bpf/btf_dump.c2
-rw-r--r--tools/lib/bpf/libbpf.c106
-rw-r--r--tools/lib/bpf/libbpf.h111
-rw-r--r--tools/lib/bpf/libbpf.map10
-rw-r--r--tools/lib/bpf/libbpf_probes.c1
-rw-r--r--tools/lib/bpf/libbpf_version.h2
-rw-r--r--tools/lib/bpf/nlattr.c2
-rw-r--r--tools/lib/bpf/ringbuf.c271
-rw-r--r--tools/lib/bpf/usdt.c2
13 files changed, 596 insertions, 106 deletions
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 867b734839dd..d37c4fe2849d 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -131,7 +131,7 @@
/*
* Helper function to perform a tail call with a constant/immediate map slot.
*/
-#if (!defined(__clang__) || __clang_major__ >= 8) && defined(__bpf__)
+#if __clang_major__ >= 8 && defined(__bpf__)
static __always_inline void
bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
{
@@ -139,8 +139,8 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
__bpf_unreachable();
/*
- * Provide a hard guarantee that the compiler won't optimize setting r2
- * (map pointer) and r3 (constant map index) from _different paths_ ending
+ * Provide a hard guarantee that LLVM won't optimize setting r2 (map
+ * pointer) and r3 (constant map index) from _different paths_ ending
* up at the _same_ call insn as otherwise we won't be able to use the
* jmpq/nopl retpoline-free patching by the x86-64 JIT in the kernel
* given they mismatch. See also d2e4c1e6c294 ("bpf: Constant map key
@@ -148,37 +148,18 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
*
* Note on clobber list: we need to stay in-line with BPF calling
* convention, so even if we don't end up using r0, r4, r5, we need
- * to mark them as clobber so that the compiler doesn't end up using
- * them before / after the call.
+ * to mark them as clobber so that LLVM doesn't end up using them
+ * before / after the call.
*/
- asm volatile(
-#ifdef __clang__
- "r1 = %[ctx]\n\t"
+ asm volatile("r1 = %[ctx]\n\t"
"r2 = %[map]\n\t"
"r3 = %[slot]\n\t"
-#else
- "mov %%r1,%[ctx]\n\t"
- "mov %%r2,%[map]\n\t"
- "mov %%r3,%[slot]\n\t"
-#endif
"call 12"
:: [ctx]"r"(ctx), [map]"r"(map), [slot]"i"(slot)
: "r0", "r1", "r2", "r3", "r4", "r5");
}
#endif
-/*
- * Helper structure used by eBPF C program
- * to describe BPF map attributes to libbpf loader
- */
-struct bpf_map_def {
- unsigned int type;
- unsigned int key_size;
- unsigned int value_size;
- unsigned int max_entries;
- unsigned int map_flags;
-} __attribute__((deprecated("use BTF-defined maps in .maps section")));
-
enum libbpf_pin_type {
LIBBPF_PIN_NONE,
/* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index 5fdb93da423b..2972dc25ff72 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -438,6 +438,113 @@ typeof(name(0)) name(unsigned long long *ctx) \
static __always_inline typeof(name(0)) \
____##name(unsigned long long *ctx, ##args)
+#ifndef ___bpf_nth2
+#define ___bpf_nth2(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, \
+ _14, _15, _16, _17, _18, _19, _20, _21, _22, _23, _24, N, ...) N
+#endif
+#ifndef ___bpf_narg2
+#define ___bpf_narg2(...) \
+ ___bpf_nth2(_, ##__VA_ARGS__, 12, 12, 11, 11, 10, 10, 9, 9, 8, 8, 7, 7, \
+ 6, 6, 5, 5, 4, 4, 3, 3, 2, 2, 1, 1, 0)
+#endif
+
+#define ___bpf_treg_cnt(t) \
+ __builtin_choose_expr(sizeof(t) == 1, 1, \
+ __builtin_choose_expr(sizeof(t) == 2, 1, \
+ __builtin_choose_expr(sizeof(t) == 4, 1, \
+ __builtin_choose_expr(sizeof(t) == 8, 1, \
+ __builtin_choose_expr(sizeof(t) == 16, 2, \
+ (void)0)))))
+
+#define ___bpf_reg_cnt0() (0)
+#define ___bpf_reg_cnt1(t, x) (___bpf_reg_cnt0() + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt2(t, x, args...) (___bpf_reg_cnt1(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt3(t, x, args...) (___bpf_reg_cnt2(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt4(t, x, args...) (___bpf_reg_cnt3(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt5(t, x, args...) (___bpf_reg_cnt4(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt6(t, x, args...) (___bpf_reg_cnt5(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt7(t, x, args...) (___bpf_reg_cnt6(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt8(t, x, args...) (___bpf_reg_cnt7(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt9(t, x, args...) (___bpf_reg_cnt8(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt10(t, x, args...) (___bpf_reg_cnt9(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt11(t, x, args...) (___bpf_reg_cnt10(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt12(t, x, args...) (___bpf_reg_cnt11(args) + ___bpf_treg_cnt(t))
+#define ___bpf_reg_cnt(args...) ___bpf_apply(___bpf_reg_cnt, ___bpf_narg2(args))(args)
+
+#define ___bpf_union_arg(t, x, n) \
+ __builtin_choose_expr(sizeof(t) == 1, ({ union { __u8 z[1]; t x; } ___t = { .z = {ctx[n]}}; ___t.x; }), \
+ __builtin_choose_expr(sizeof(t) == 2, ({ union { __u16 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \
+ __builtin_choose_expr(sizeof(t) == 4, ({ union { __u32 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \
+ __builtin_choose_expr(sizeof(t) == 8, ({ union { __u64 z[1]; t x; } ___t = {.z = {ctx[n]} }; ___t.x; }), \
+ __builtin_choose_expr(sizeof(t) == 16, ({ union { __u64 z[2]; t x; } ___t = {.z = {ctx[n], ctx[n + 1]} }; ___t.x; }), \
+ (void)0)))))
+
+#define ___bpf_ctx_arg0(n, args...)
+#define ___bpf_ctx_arg1(n, t, x) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt1(t, x))
+#define ___bpf_ctx_arg2(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt2(t, x, args)) ___bpf_ctx_arg1(n, args)
+#define ___bpf_ctx_arg3(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt3(t, x, args)) ___bpf_ctx_arg2(n, args)
+#define ___bpf_ctx_arg4(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt4(t, x, args)) ___bpf_ctx_arg3(n, args)
+#define ___bpf_ctx_arg5(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt5(t, x, args)) ___bpf_ctx_arg4(n, args)
+#define ___bpf_ctx_arg6(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt6(t, x, args)) ___bpf_ctx_arg5(n, args)
+#define ___bpf_ctx_arg7(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt7(t, x, args)) ___bpf_ctx_arg6(n, args)
+#define ___bpf_ctx_arg8(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt8(t, x, args)) ___bpf_ctx_arg7(n, args)
+#define ___bpf_ctx_arg9(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt9(t, x, args)) ___bpf_ctx_arg8(n, args)
+#define ___bpf_ctx_arg10(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt10(t, x, args)) ___bpf_ctx_arg9(n, args)
+#define ___bpf_ctx_arg11(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt11(t, x, args)) ___bpf_ctx_arg10(n, args)
+#define ___bpf_ctx_arg12(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt12(t, x, args)) ___bpf_ctx_arg11(n, args)
+#define ___bpf_ctx_arg(args...) ___bpf_apply(___bpf_ctx_arg, ___bpf_narg2(args))(___bpf_reg_cnt(args), args)
+
+#define ___bpf_ctx_decl0()
+#define ___bpf_ctx_decl1(t, x) , t x
+#define ___bpf_ctx_decl2(t, x, args...) , t x ___bpf_ctx_decl1(args)
+#define ___bpf_ctx_decl3(t, x, args...) , t x ___bpf_ctx_decl2(args)
+#define ___bpf_ctx_decl4(t, x, args...) , t x ___bpf_ctx_decl3(args)
+#define ___bpf_ctx_decl5(t, x, args...) , t x ___bpf_ctx_decl4(args)
+#define ___bpf_ctx_decl6(t, x, args...) , t x ___bpf_ctx_decl5(args)
+#define ___bpf_ctx_decl7(t, x, args...) , t x ___bpf_ctx_decl6(args)
+#define ___bpf_ctx_decl8(t, x, args...) , t x ___bpf_ctx_decl7(args)
+#define ___bpf_ctx_decl9(t, x, args...) , t x ___bpf_ctx_decl8(args)
+#define ___bpf_ctx_decl10(t, x, args...) , t x ___bpf_ctx_decl9(args)
+#define ___bpf_ctx_decl11(t, x, args...) , t x ___bpf_ctx_decl10(args)
+#define ___bpf_ctx_decl12(t, x, args...) , t x ___bpf_ctx_decl11(args)
+#define ___bpf_ctx_decl(args...) ___bpf_apply(___bpf_ctx_decl, ___bpf_narg2(args))(args)
+
+/*
+ * BPF_PROG2 is an enhanced version of BPF_PROG in order to handle struct
+ * arguments. Since each struct argument might take one or two u64 values
+ * in the trampoline stack, argument type size is needed to place proper number
+ * of u64 values for each argument. Therefore, BPF_PROG2 has different
+ * syntax from BPF_PROG. For example, for the following BPF_PROG syntax:
+ *
+ * int BPF_PROG(test2, int a, int b) { ... }
+ *
+ * the corresponding BPF_PROG2 syntax is:
+ *
+ * int BPF_PROG2(test2, int, a, int, b) { ... }
+ *
+ * where type and the corresponding argument name are separated by comma.
+ *
+ * Use BPF_PROG2 macro if one of the arguments might be a struct/union larger
+ * than 8 bytes:
+ *
+ * int BPF_PROG2(test_struct_arg, struct bpf_testmod_struct_arg_1, a, int, b,
+ * int, c, int, d, struct bpf_testmod_struct_arg_2, e, int, ret)
+ * {
+ * // access a, b, c, d, e, and ret directly
+ * ...
+ * }
+ */
+#define BPF_PROG2(name, args...) \
+name(unsigned long long *ctx); \
+static __always_inline typeof(name(0)) \
+____##name(unsigned long long *ctx ___bpf_ctx_decl(args)); \
+typeof(name(0)) name(unsigned long long *ctx) \
+{ \
+ return ____##name(ctx ___bpf_ctx_arg(args)); \
+} \
+static __always_inline typeof(name(0)) \
+____##name(unsigned long long *ctx ___bpf_ctx_decl(args))
+
struct pt_regs;
#define ___bpf_kprobe_args0() ctx
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 361131518d63..d88647da2c7f 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -4642,20 +4642,17 @@ static int btf_dedup_remap_types(struct btf_dedup *d)
*/
struct btf *btf__load_vmlinux_btf(void)
{
- struct {
- const char *path_fmt;
- bool raw_btf;
- } locations[] = {
+ const char *locations[] = {
/* try canonical vmlinux BTF through sysfs first */
- { "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
- /* fall back to trying to find vmlinux ELF on disk otherwise */
- { "/boot/vmlinux-%1$s" },
- { "/lib/modules/%1$s/vmlinux-%1$s" },
- { "/lib/modules/%1$s/build/vmlinux" },
- { "/usr/lib/modules/%1$s/kernel/vmlinux" },
- { "/usr/lib/debug/boot/vmlinux-%1$s" },
- { "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
- { "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
+ "/sys/kernel/btf/vmlinux",
+ /* fall back to trying to find vmlinux on disk otherwise */
+ "/boot/vmlinux-%1$s",
+ "/lib/modules/%1$s/vmlinux-%1$s",
+ "/lib/modules/%1$s/build/vmlinux",
+ "/usr/lib/modules/%1$s/kernel/vmlinux",
+ "/usr/lib/debug/boot/vmlinux-%1$s",
+ "/usr/lib/debug/boot/vmlinux-%1$s.debug",
+ "/usr/lib/debug/lib/modules/%1$s/vmlinux",
};
char path[PATH_MAX + 1];
struct utsname buf;
@@ -4665,15 +4662,12 @@ struct btf *btf__load_vmlinux_btf(void)
uname(&buf);
for (i = 0; i < ARRAY_SIZE(locations); i++) {
- snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);
+ snprintf(path, PATH_MAX, locations[i], buf.release);
- if (access(path, R_OK))
+ if (faccessat(AT_FDCWD, path, R_OK, AT_EACCESS))
continue;
- if (locations[i].raw_btf)
- btf = btf__parse_raw(path);
- else
- btf = btf__parse_elf(path, NULL);
+ btf = btf__parse(path, NULL);
err = libbpf_get_error(btf);
pr_debug("loading kernel BTF '%s': %d\n", path, err);
if (err)
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index ae543144ee30..8e6880d91c84 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -486,6 +486,8 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t)
return (struct btf_enum *)(t + 1);
}
+struct btf_enum64;
+
static inline struct btf_enum64 *btf_enum64(const struct btf_type *t)
{
return (struct btf_enum64 *)(t + 1);
@@ -493,7 +495,28 @@ static inline struct btf_enum64 *btf_enum64(const struct btf_type *t)
static inline __u64 btf_enum64_value(const struct btf_enum64 *e)
{
- return ((__u64)e->val_hi32 << 32) | e->val_lo32;
+ /* struct btf_enum64 is introduced in Linux 6.0, which is very
+ * bleeding-edge. Here we are avoiding relying on struct btf_enum64
+ * definition coming from kernel UAPI headers to support wider range
+ * of system-wide kernel headers.
+ *
+ * Given this header can be also included from C++ applications, that
+ * further restricts C tricks we can use (like using compatible
+ * anonymous struct). So just treat struct btf_enum64 as
+ * a three-element array of u32 and access second (lo32) and third
+ * (hi32) elements directly.
+ *
+ * For reference, here is a struct btf_enum64 definition:
+ *
+ * const struct btf_enum64 {
+ * __u32 name_off;
+ * __u32 val_lo32;
+ * __u32 val_hi32;
+ * };
+ */
+ const __u32 *e64 = (const __u32 *)e;
+
+ return ((__u64)e64[2] << 32) | e64[1];
}
static inline struct btf_member *btf_members(const struct btf_type *t)
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 627edb5bb6de..4221f73a74d0 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -2385,7 +2385,7 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
d->typed_dump->indent_lvl = OPTS_GET(opts, indent_level, 0);
/* default indent string is a tab */
- if (!opts->indent_str)
+ if (!OPTS_GET(opts, indent_str, NULL))
d->typed_dump->indent_str[0] = '\t';
else
libbpf_strlcpy(d->typed_dump->indent_str, opts->indent_str,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 3ad139285fad..184ce1684dcd 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -163,6 +163,7 @@ static const char * const map_type_name[] = {
[BPF_MAP_TYPE_INODE_STORAGE] = "inode_storage",
[BPF_MAP_TYPE_TASK_STORAGE] = "task_storage",
[BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter",
+ [BPF_MAP_TYPE_USER_RINGBUF] = "user_ringbuf",
};
static const char * const prog_type_name[] = {
@@ -883,7 +884,7 @@ __u32 get_kernel_version(void)
__u32 major, minor, patch;
struct utsname info;
- if (access(ubuntu_kver_file, R_OK) == 0) {
+ if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) == 0) {
FILE *f;
f = fopen(ubuntu_kver_file, "r");
@@ -2096,19 +2097,30 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf,
return true;
}
+static int pathname_concat(char *buf, size_t buf_sz, const char *path, const char *name)
+{
+ int len;
+
+ len = snprintf(buf, buf_sz, "%s/%s", path, name);
+ if (len < 0)
+ return -EINVAL;
+ if (len >= buf_sz)
+ return -ENAMETOOLONG;
+
+ return 0;
+}
+
static int build_map_pin_path(struct bpf_map *map, const char *path)
{
char buf[PATH_MAX];
- int len;
+ int err;
if (!path)
path = "/sys/fs/bpf";
- len = snprintf(buf, PATH_MAX, "%s/%s", path, bpf_map__name(map));
- if (len < 0)
- return -EINVAL;
- else if (len >= PATH_MAX)
- return -ENAMETOOLONG;
+ err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map));
+ if (err)
+ return err;
return bpf_map__set_pin_path(map, buf);
}
@@ -2372,6 +2384,12 @@ static size_t adjust_ringbuf_sz(size_t sz)
return sz;
}
+static bool map_is_ringbuf(const struct bpf_map *map)
+{
+ return map->def.type == BPF_MAP_TYPE_RINGBUF ||
+ map->def.type == BPF_MAP_TYPE_USER_RINGBUF;
+}
+
static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def)
{
map->def.type = def->map_type;
@@ -2386,7 +2404,7 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def
map->btf_value_type_id = def->value_type_id;
/* auto-adjust BPF ringbuf map max_entries to be a multiple of page size */
- if (map->def.type == BPF_MAP_TYPE_RINGBUF)
+ if (map_is_ringbuf(map))
map->def.max_entries = adjust_ringbuf_sz(map->def.max_entries);
if (def->parts & MAP_DEF_MAP_TYPE)
@@ -4369,7 +4387,7 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
map->def.max_entries = max_entries;
/* auto-adjust BPF ringbuf map max_entries to be a multiple of page size */
- if (map->def.type == BPF_MAP_TYPE_RINGBUF)
+ if (map_is_ringbuf(map))
map->def.max_entries = adjust_ringbuf_sz(map->def.max_entries);
return 0;
@@ -7961,17 +7979,9 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
continue;
if (path) {
- int len;
-
- len = snprintf(buf, PATH_MAX, "%s/%s", path,
- bpf_map__name(map));
- if (len < 0) {
- err = -EINVAL;
- goto err_unpin_maps;
- } else if (len >= PATH_MAX) {
- err = -ENAMETOOLONG;
+ err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map));
+ if (err)
goto err_unpin_maps;
- }
sanitize_pin_path(buf);
pin_path = buf;
} else if (!map->pin_path) {
@@ -8009,14 +8019,9 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
char buf[PATH_MAX];
if (path) {
- int len;
-
- len = snprintf(buf, PATH_MAX, "%s/%s", path,
- bpf_map__name(map));
- if (len < 0)
- return libbpf_err(-EINVAL);
- else if (len >= PATH_MAX)
- return libbpf_err(-ENAMETOOLONG);
+ err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map));
+ if (err)
+ return libbpf_err(err);
sanitize_pin_path(buf);
pin_path = buf;
} else if (!map->pin_path) {
@@ -8034,6 +8039,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
{
struct bpf_program *prog;
+ char buf[PATH_MAX];
int err;
if (!obj)
@@ -8045,17 +8051,9 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
}
bpf_object__for_each_program(prog, obj) {
- char buf[PATH_MAX];
- int len;
-
- len = snprintf(buf, PATH_MAX, "%s/%s", path, prog->name);
- if (len < 0) {
- err = -EINVAL;
- goto err_unpin_programs;
- } else if (len >= PATH_MAX) {
- err = -ENAMETOOLONG;
+ err = pathname_concat(buf, sizeof(buf), path, prog->name);
+ if (err)
goto err_unpin_programs;
- }
err = bpf_program__pin(prog, buf);
if (err)
@@ -8066,13 +8064,7 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
err_unpin_programs:
while ((prog = bpf_object__prev_program(obj, prog))) {
- char buf[PATH_MAX];
- int len;
-
- len = snprintf(buf, PATH_MAX, "%s/%s", path, prog->name);
- if (len < 0)
- continue;
- else if (len >= PATH_MAX)
+ if (pathname_concat(buf, sizeof(buf), path, prog->name))
continue;
bpf_program__unpin(prog, buf);
@@ -8091,13 +8083,10 @@ int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
bpf_object__for_each_program(prog, obj) {
char buf[PATH_MAX];
- int len;
- len = snprintf(buf, PATH_MAX, "%s/%s", path, prog->name);
- if (len < 0)
- return libbpf_err(-EINVAL);
- else if (len >= PATH_MAX)
- return libbpf_err(-ENAMETOOLONG);
+ err = pathname_concat(buf, sizeof(buf), path, prog->name);
+ if (err)
+ return libbpf_err(err);
err = bpf_program__unpin(prog, buf);
if (err)
@@ -9084,11 +9073,15 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac
int err = 0;
/* BPF program's BTF ID */
- if (attach_prog_fd) {
+ if (prog->type == BPF_PROG_TYPE_EXT || attach_prog_fd) {
+ if (!attach_prog_fd) {
+ pr_warn("prog '%s': attach program FD is not set\n", prog->name);
+ return -EINVAL;
+ }
err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd);
if (err < 0) {
- pr_warn("failed to find BPF program (FD %d) BTF ID for '%s': %d\n",
- attach_prog_fd, attach_name, err);
+ pr_warn("prog '%s': failed to find BPF program (FD %d) BTF ID for '%s': %d\n",
+ prog->name, attach_prog_fd, attach_name, err);
return err;
}
*btf_obj_fd = 0;
@@ -9105,7 +9098,8 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac
err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id);
}
if (err) {
- pr_warn("failed to find kernel BTF type ID of '%s': %d\n", attach_name, err);
+ pr_warn("prog '%s': failed to find kernel BTF type ID of '%s': %d\n",
+ prog->name, attach_name, err);
return err;
}
return 0;
@@ -9910,7 +9904,7 @@ static bool use_debugfs(void)
static int has_debugfs = -1;
if (has_debugfs < 0)
- has_debugfs = access(DEBUGFS, F_OK) == 0;
+ has_debugfs = faccessat(AT_FDCWD, DEBUGFS, F_OK, AT_EACCESS) == 0;
return has_debugfs == 1;
}
@@ -10727,7 +10721,7 @@ static int resolve_full_path(const char *file, char *result, size_t result_sz)
continue;
snprintf(result, result_sz, "%.*s/%s", seg_len, s, file);
/* ensure it has required permissions */
- if (access(result, perm) < 0)
+ if (faccessat(AT_FDCWD, result, perm, AT_EACCESS) < 0)
continue;
pr_debug("resolved '%s' to '%s'\n", file, result);
return 0;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 88a1ac34b12a..eee883f007f9 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -118,7 +118,9 @@ struct bpf_object_open_opts {
* auto-pinned to that path on load; defaults to "/sys/fs/bpf".
*/
const char *pin_root_path;
- long :0;
+
+ __u32 :32; /* stub out now removed attach_prog_fd */
+
/* Additional kernel config content that augments and overrides
* system Kconfig for CONFIG_xxx externs.
*/
@@ -1011,6 +1013,7 @@ LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook,
/* Ring buffer APIs */
struct ring_buffer;
+struct user_ring_buffer;
typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size);
@@ -1030,6 +1033,112 @@ LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms);
LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb);
LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
+struct user_ring_buffer_opts {
+ size_t sz; /* size of this struct, for forward/backward compatibility */
+};
+
+#define user_ring_buffer_opts__last_field sz
+
+/* @brief **user_ring_buffer__new()** creates a new instance of a user ring
+ * buffer.
+ *
+ * @param map_fd A file descriptor to a BPF_MAP_TYPE_USER_RINGBUF map.
+ * @param opts Options for how the ring buffer should be created.
+ * @return A user ring buffer on success; NULL and errno being set on a
+ * failure.
+ */
+LIBBPF_API struct user_ring_buffer *
+user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts);
+
+/* @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the
+ * user ring buffer.
+ * @param rb A pointer to a user ring buffer.
+ * @param size The size of the sample, in bytes.
+ * @return A pointer to an 8-byte aligned reserved region of the user ring
+ * buffer; NULL, and errno being set if a sample could not be reserved.
+ *
+ * This function is *not* thread safe, and callers must synchronize accessing
+ * this function if there are multiple producers. If a size is requested that
+ * is larger than the size of the entire ring buffer, errno will be set to
+ * E2BIG and NULL is returned. If the ring buffer could accommodate the size,
+ * but currently does not have enough space, errno is set to ENOSPC and NULL is
+ * returned.
+ *
+ * After initializing the sample, callers must invoke
+ * **user_ring_buffer__submit()** to post the sample to the kernel. Otherwise,
+ * the sample must be freed with **user_ring_buffer__discard()**.
+ */
+LIBBPF_API void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size);
+
+/* @brief **user_ring_buffer__reserve_blocking()** reserves a record in the
+ * ring buffer, possibly blocking for up to @timeout_ms until a sample becomes
+ * available.
+ * @param rb The user ring buffer.
+ * @param size The size of the sample, in bytes.
+ * @param timeout_ms The amount of time, in milliseconds, for which the caller
+ * should block when waiting for a sample. -1 causes the caller to block
+ * indefinitely.
+ * @return A pointer to an 8-byte aligned reserved region of the user ring
+ * buffer; NULL, and errno being set if a sample could not be reserved.
+ *
+ * This function is *not* thread safe, and callers must synchronize
+ * accessing this function if there are multiple producers
+ *
+ * If **timeout_ms** is -1, the function will block indefinitely until a sample
+ * becomes available. Otherwise, **timeout_ms** must be non-negative, or errno
+ * is set to EINVAL, and NULL is returned. If **timeout_ms** is 0, no blocking
+ * will occur and the function will return immediately after attempting to
+ * reserve a sample.
+ *
+ * If **size** is larger than the size of the entire ring buffer, errno is set
+ * to E2BIG and NULL is returned. If the ring buffer could accommodate
+ * **size**, but currently does not have enough space, the caller will block
+ * until at most **timeout_ms** has elapsed. If insufficient space is available
+ * at that time, errno is set to ENOSPC, and NULL is returned.
+ *
+ * The kernel guarantees that it will wake up this thread to check if
+ * sufficient space is available in the ring buffer at least once per
+ * invocation of the **bpf_ringbuf_drain()** helper function, provided that at
+ * least one sample is consumed, and the BPF program did not invoke the
+ * function with BPF_RB_NO_WAKEUP. A wakeup may occur sooner than that, but the
+ * kernel does not guarantee this. If the helper function is invoked with
+ * BPF_RB_FORCE_WAKEUP, a wakeup event will be sent even if no sample is
+ * consumed.
+ *
+ * When a sample of size **size** is found within **timeout_ms**, a pointer to
+ * the sample is returned. After initializing the sample, callers must invoke
+ * **user_ring_buffer__submit()** to post the sample to the ring buffer.
+ * Otherwise, the sample must be freed with **user_ring_buffer__discard()**.
+ */
+LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb,
+ __u32 size,
+ int timeout_ms);
+
+/* @brief **user_ring_buffer__submit()** submits a previously reserved sample
+ * into the ring buffer.
+ * @param rb The user ring buffer.
+ * @param sample A reserved sample.
+ *
+ * It is not necessary to synchronize amongst multiple producers when invoking
+ * this function.
+ */
+LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample);
+
+/* @brief **user_ring_buffer__discard()** discards a previously reserved sample.
+ * @param rb The user ring buffer.
+ * @param sample A reserved sample.
+ *
+ * It is not necessary to synchronize amongst multiple producers when invoking
+ * this function.
+ */
+LIBBPF_API void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample);
+
+/* @brief **user_ring_buffer__free()** frees a ring buffer that was previously
+ * created with **user_ring_buffer__new()**.
+ * @param rb The user ring buffer being freed.
+ */
+LIBBPF_API void user_ring_buffer__free(struct user_ring_buffer *rb);
+
/* Perf buffer APIs */
struct perf_buffer;
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 2b928dc21af0..c1d6aa7c82b6 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -368,3 +368,13 @@ LIBBPF_1.0.0 {
libbpf_bpf_prog_type_str;
perf_buffer__buffer;
};
+
+LIBBPF_1.1.0 {
+ global:
+ user_ring_buffer__discard;
+ user_ring_buffer__free;
+ user_ring_buffer__new;
+ user_ring_buffer__reserve;
+ user_ring_buffer__reserve_blocking;
+ user_ring_buffer__submit;
+} LIBBPF_1.0.0;
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 6d495656f554..f3a8e8e74eb8 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -231,6 +231,7 @@ static int probe_map_create(enum bpf_map_type map_type)
return btf_fd;
break;
case BPF_MAP_TYPE_RINGBUF:
+ case BPF_MAP_TYPE_USER_RINGBUF:
key_size = 0;
value_size = 0;
max_entries = 4096;
diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h
index 2fb2f4290080..e944f5bce728 100644
--- a/tools/lib/bpf/libbpf_version.h
+++ b/tools/lib/bpf/libbpf_version.h
@@ -4,6 +4,6 @@
#define __LIBBPF_VERSION_H
#define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 0
+#define LIBBPF_MINOR_VERSION 1
#endif /* __LIBBPF_VERSION_H */
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index f57e77a6e40f..3900d052ed19 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -32,7 +32,7 @@ static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
static int nla_ok(const struct nlattr *nla, int remaining)
{
- return remaining >= sizeof(*nla) &&
+ return remaining >= (int)sizeof(*nla) &&
nla->nla_len >= sizeof(*nla) &&
nla->nla_len <= remaining;
}
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 8bc117bcc7bc..d285171d4b69 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -16,6 +16,7 @@
#include <asm/barrier.h>
#include <sys/mman.h>
#include <sys/epoll.h>
+#include <time.h>
#include "libbpf.h"
#include "libbpf_internal.h"
@@ -39,6 +40,23 @@ struct ring_buffer {
int ring_cnt;
};
+struct user_ring_buffer {
+ struct epoll_event event;
+ unsigned long *consumer_pos;
+ unsigned long *producer_pos;
+ void *data;
+ unsigned long mask;
+ size_t page_size;
+ int map_fd;
+ int epoll_fd;
+};
+
+/* 8-byte ring buffer header structure */
+struct ringbuf_hdr {
+ __u32 len;
+ __u32 pad;
+};
+
static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r)
{
if (r->consumer_pos) {
@@ -300,3 +318,256 @@ int ring_buffer__epoll_fd(const struct ring_buffer *rb)
{
return rb->epoll_fd;
}
+
+static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
+{
+ if (rb->consumer_pos) {
+ munmap(rb->consumer_pos, rb->page_size);
+ rb->consumer_pos = NULL;
+ }
+ if (rb->producer_pos) {
+ munmap(rb->producer_pos, rb->page_size + 2 * (rb->mask + 1));
+ rb->producer_pos = NULL;
+ }
+}
+
+void user_ring_buffer__free(struct user_ring_buffer *rb)
+{
+ if (!rb)
+ return;
+
+ user_ringbuf_unmap_ring(rb);
+
+ if (rb->epoll_fd >= 0)
+ close(rb->epoll_fd);
+
+ free(rb);
+}
+
+static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd)
+{
+ struct bpf_map_info info;
+ __u32 len = sizeof(info);
+ void *tmp;
+ struct epoll_event *rb_epoll;
+ int err;
+
+ memset(&info, 0, sizeof(info));
+
+ err = bpf_obj_get_info_by_fd(map_fd, &info, &len);
+ if (err) {
+ err = -errno;
+ pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err);
+ return err;
+ }
+
+ if (info.type != BPF_MAP_TYPE_USER_RINGBUF) {
+ pr_warn("user ringbuf: map fd=%d is not BPF_MAP_TYPE_USER_RINGBUF\n", map_fd);
+ return -EINVAL;
+ }
+
+ rb->map_fd = map_fd;
+ rb->mask = info.max_entries - 1;
+
+ /* Map read-only consumer page */
+ tmp = mmap(NULL, rb->page_size, PROT_READ, MAP_SHARED, map_fd, 0);
+ if (tmp == MAP_FAILED) {
+ err = -errno;
+ pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
+ map_fd, err);
+ return err;
+ }
+ rb->consumer_pos = tmp;
+
+ /* Map read-write the producer page and data pages. We map the data
+ * region as twice the total size of the ring buffer to allow the
+ * simple reading and writing of samples that wrap around the end of
+ * the buffer. See the kernel implementation for details.
+ */
+ tmp = mmap(NULL, rb->page_size + 2 * info.max_entries,
+ PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, rb->page_size);
+ if (tmp == MAP_FAILED) {
+ err = -errno;
+ pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n",
+ map_fd, err);
+ return err;
+ }
+
+ rb->producer_pos = tmp;
+ rb->data = tmp + rb->page_size;
+
+ rb_epoll = &rb->event;
+ rb_epoll->events = EPOLLOUT;
+ if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, rb_epoll) < 0) {
+ err = -errno;
+ pr_warn("user ringbuf: failed to epoll add map fd=%d: %d\n", map_fd, err);
+ return err;
+ }
+
+ return 0;
+}
+
+struct user_ring_buffer *
+user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts)
+{
+ struct user_ring_buffer *rb;
+ int err;
+
+ if (!OPTS_VALID(opts, user_ring_buffer_opts))
+ return errno = EINVAL, NULL;
+
+ rb = calloc(1, sizeof(*rb));
+ if (!rb)
+ return errno = ENOMEM, NULL;
+
+ rb->page_size = getpagesize();
+
+ rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+ if (rb->epoll_fd < 0) {
+ err = -errno;
+ pr_warn("user ringbuf: failed to create epoll instance: %d\n", err);
+ goto err_out;
+ }
+
+ err = user_ringbuf_map(rb, map_fd);
+ if (err)
+ goto err_out;
+
+ return rb;
+
+err_out:
+ user_ring_buffer__free(rb);
+ return errno = -err, NULL;
+}
+
+static void user_ringbuf_commit(struct user_ring_buffer *rb, void *sample, bool discard)
+{
+ __u32 new_len;
+ struct ringbuf_hdr *hdr;
+ uintptr_t hdr_offset;
+
+ hdr_offset = rb->mask + 1 + (sample - rb->data) - BPF_RINGBUF_HDR_SZ;
+ hdr = rb->data + (hdr_offset & rb->mask);
+
+ new_len = hdr->len & ~BPF_RINGBUF_BUSY_BIT;
+ if (discard)
+ new_len |= BPF_RINGBUF_DISCARD_BIT;
+
+ /* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in
+ * the kernel.
+ */
+ __atomic_exchange_n(&hdr->len, new_len, __ATOMIC_ACQ_REL);
+}
+
+void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample)
+{
+ user_ringbuf_commit(rb, sample, true);
+}
+
+void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample)
+{
+ user_ringbuf_commit(rb, sample, false);
+}
+
+void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size)
+{
+ __u32 avail_size, total_size, max_size;
+ /* 64-bit to avoid overflow in case of extreme application behavior */
+ __u64 cons_pos, prod_pos;
+ struct ringbuf_hdr *hdr;
+
+ /* Synchronizes with smp_store_release() in __bpf_user_ringbuf_peek() in
+ * the kernel.
+ */
+ cons_pos = smp_load_acquire(rb->consumer_pos);
+ /* Synchronizes with smp_store_release() in user_ringbuf_commit() */
+ prod_pos = smp_load_acquire(rb->producer_pos);
+
+ max_size = rb->mask + 1;
+ avail_size = max_size - (prod_pos - cons_pos);
+ /* Round up total size to a multiple of 8. */
+ total_size = (size + BPF_RINGBUF_HDR_SZ + 7) / 8 * 8;
+
+ if (total_size > max_size)
+ return errno = E2BIG, NULL;
+
+ if (avail_size < total_size)
+ return errno = ENOSPC, NULL;
+
+ hdr = rb->data + (prod_pos & rb->mask);
+ hdr->len = size | BPF_RINGBUF_BUSY_BIT;
+ hdr->pad = 0;
+
+ /* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in
+ * the kernel.
+ */
+ smp_store_release(rb->producer_pos, prod_pos + total_size);
+
+ return (void *)rb->data + ((prod_pos + BPF_RINGBUF_HDR_SZ) & rb->mask);
+}
+
+static __u64 ns_elapsed_timespec(const struct timespec *start, const struct timespec *end)
+{
+ __u64 start_ns, end_ns, ns_per_s = 1000000000;
+
+ start_ns = (__u64)start->tv_sec * ns_per_s + start->tv_nsec;
+ end_ns = (__u64)end->tv_sec * ns_per_s + end->tv_nsec;
+
+ return end_ns - start_ns;
+}
+
+void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, __u32 size, int timeout_ms)
+{
+ void *sample;
+ int err, ms_remaining = timeout_ms;
+ struct timespec start;
+
+ if (timeout_ms < 0 && timeout_ms != -1)
+ return errno = EINVAL, NULL;
+
+ if (timeout_ms != -1) {
+ err = clock_gettime(CLOCK_MONOTONIC, &start);
+ if (err)
+ return NULL;
+ }
+
+ do {
+ int cnt, ms_elapsed;
+ struct timespec curr;
+ __u64 ns_per_ms = 1000000;
+
+ sample = user_ring_buffer__reserve(rb, size);
+ if (sample)
+ return sample;
+ else if (errno != ENOSPC)
+ return NULL;
+
+ /* The kernel guarantees at least one event notification
+ * delivery whenever at least one sample is drained from the
+ * ring buffer in an invocation to bpf_ringbuf_drain(). Other
+ * additional events may be delivered at any time, but only one
+ * event is guaranteed per bpf_ringbuf_drain() invocation,
+ * provided that a sample is drained, and the BPF program did
+ * not pass BPF_RB_NO_WAKEUP to bpf_ringbuf_drain(). If
+ * BPF_RB_FORCE_WAKEUP is passed to bpf_ringbuf_drain(), a
+ * wakeup event will be delivered even if no samples are
+ * drained.
+ */
+ cnt = epoll_wait(rb->epoll_fd, &rb->event, 1, ms_remaining);
+ if (cnt < 0)
+ return NULL;
+
+ if (timeout_ms == -1)
+ continue;
+
+ err = clock_gettime(CLOCK_MONOTONIC, &curr);
+ if (err)
+ return NULL;
+
+ ms_elapsed = ns_elapsed_timespec(&start, &curr) / ns_per_ms;
+ ms_remaining = timeout_ms - ms_elapsed;
+ } while (ms_remaining > 0);
+
+ /* Try one more time to reserve a sample after the specified timeout has elapsed. */
+ return user_ring_buffer__reserve(rb, size);
+}
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index d18e37982344..e83b497c2245 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -282,7 +282,7 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
* If this is not supported, USDTs with semaphores will not be supported.
* Added in: a6ca88b241d5 ("trace_uprobe: support reference counter in fd-based uprobe")
*/
- man->has_sema_refcnt = access(ref_ctr_sysfs_path, F_OK) == 0;
+ man->has_sema_refcnt = faccessat(AT_FDCWD, ref_ctr_sysfs_path, F_OK, AT_EACCESS) == 0;
return man;
}
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-05 23:15:08 +0100