diff options
author | Jakub Kicinski <kuba@kernel.org> | 2022-06-17 19:35:17 -0700 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2022-06-17 19:35:19 -0700 |
commit | 9fb424c4c29df0d7f39b686d4037cbc7e06ed7b5 (patch) | |
tree | 0fe62515d647b35b3c6ac06590469fe33d37dc1c /tools/lib/bpf | |
parent | 4875d94c69d5a4836c4225b51429d277c297aae8 (diff) | |
parent | f5be22c64bd6ee6c1cb0b34f4ff748d43879cd4c (diff) |
Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
pull-request: bpf-next 2022-06-17
We've added 72 non-merge commits during the last 15 day(s) which contain
a total of 92 files changed, 4582 insertions(+), 834 deletions(-).
The main changes are:
1) Add 64 bit enum value support to BTF, from Yonghong Song.
2) Implement support for sleepable BPF uprobe programs, from Delyan Kratunov.
3) Add new BPF helpers to issue and check TCP SYN cookies without binding to a
socket especially useful in synproxy scenarios, from Maxim Mikityanskiy.
4) Fix libbpf's internal USDT address translation logic for shared libraries as
well as uprobe's symbol file offset calculation, from Andrii Nakryiko.
5) Extend libbpf to provide an API for textual representation of the various
map/prog/attach/link types and use it in bpftool, from Daniel Müller.
6) Provide BTF line info for RV64 and RV32 JITs, and fix a put_user bug in the
core seen in 32 bit when storing BPF function addresses, from Pu Lehui.
7) Fix libbpf's BTF pointer size guessing by adding a list of various aliases
for 'long' types, from Douglas Raillard.
8) Fix bpftool to readd setting rlimit since probing for memcg-based accounting
has been unreliable and caused a regression on COS, from Quentin Monnet.
9) Fix UAF in BPF cgroup's effective program computation triggered upon BPF link
detachment, from Tadeusz Struk.
10) Fix bpftool build bootstrapping during cross compilation which was pointing
to the wrong AR process, from Shahab Vahedi.
11) Fix logic bug in libbpf's is_pow_of_2 implementation, from Yuze Chi.
12) BPF hash map optimization to avoid grabbing spinlocks of all CPUs when there
is no free element. Also add a benchmark as reproducer, from Feng Zhou.
13) Fix bpftool's codegen to bail out when there's no BTF, from Michael Mullin.
14) Various minor cleanup and improvements all over the place.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (72 commits)
bpf: Fix bpf_skc_lookup comment wrt. return type
bpf: Fix non-static bpf_func_proto struct definitions
selftests/bpf: Don't force lld on non-x86 architectures
selftests/bpf: Add selftests for raw syncookie helpers in TC mode
bpf: Allow the new syncookie helpers to work with SKBs
selftests/bpf: Add selftests for raw syncookie helpers
bpf: Add helpers to issue and check SYN cookies in XDP
bpf: Allow helpers to accept pointers with a fixed size
bpf: Fix documentation of th_len in bpf_tcp_{gen,check}_syncookie
selftests/bpf: add tests for sleepable (uk)probes
libbpf: add support for sleepable uprobe programs
bpf: allow sleepable uprobe programs to attach
bpf: implement sleepable uprobes by chaining gps
bpf: move bpf_prog to bpf.h
libbpf: Fix internal USDT address translation logic for shared libraries
samples/bpf: Check detach prog exist or not in xdp_fwd
selftests/bpf: Avoid skipping certain subtests
selftests/bpf: Fix test_varlen verification failure with latest llvm
bpftool: Do not check return value from libbpf_set_strict_mode()
Revert "bpftool: Use libbpf 1.0 API mode instead of RLIMIT_MEMLOCK"
...
====================
Link: https://lore.kernel.org/r/20220617220836.7373-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'tools/lib/bpf')
-rw-r--r-- | tools/lib/bpf/btf.c | 229 | ||||
-rw-r--r-- | tools/lib/bpf/btf.h | 32 | ||||
-rw-r--r-- | tools/lib/bpf/btf_dump.c | 137 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.c | 296 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.h | 38 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.map | 8 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf_internal.h | 7 | ||||
-rw-r--r-- | tools/lib/bpf/linker.c | 7 | ||||
-rw-r--r-- | tools/lib/bpf/relo_core.c | 113 | ||||
-rw-r--r-- | tools/lib/bpf/relo_core.h | 4 | ||||
-rw-r--r-- | tools/lib/bpf/usdt.c | 123 |
11 files changed, 769 insertions, 225 deletions
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index bb1e06eb1eca..ae1520f7e1b0 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -130,7 +130,7 @@ static inline __u64 ptr_to_u64(const void *ptr) /* Ensure given dynamically allocated memory region pointed to by *data* with * capacity of *cap_cnt* elements each taking *elem_sz* bytes has enough - * memory to accomodate *add_cnt* new elements, assuming *cur_cnt* elements + * memory to accommodate *add_cnt* new elements, assuming *cur_cnt* elements * are already used. At most *max_cnt* elements can be ever allocated. * If necessary, memory is reallocated and all existing data is copied over, * new pointer to the memory region is stored at *data, new memory region @@ -305,6 +305,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(__u32); case BTF_KIND_ENUM: return base_size + vlen * sizeof(struct btf_enum); + case BTF_KIND_ENUM64: + return base_size + vlen * sizeof(struct btf_enum64); case BTF_KIND_ARRAY: return base_size + sizeof(struct btf_array); case BTF_KIND_STRUCT: @@ -334,6 +336,7 @@ static void btf_bswap_type_base(struct btf_type *t) static int btf_bswap_type_rest(struct btf_type *t) { struct btf_var_secinfo *v; + struct btf_enum64 *e64; struct btf_member *m; struct btf_array *a; struct btf_param *p; @@ -361,6 +364,13 @@ static int btf_bswap_type_rest(struct btf_type *t) e->val = bswap_32(e->val); } return 0; + case BTF_KIND_ENUM64: + for (i = 0, e64 = btf_enum64(t); i < vlen; i++, e64++) { + e64->name_off = bswap_32(e64->name_off); + e64->val_lo32 = bswap_32(e64->val_lo32); + e64->val_hi32 = bswap_32(e64->val_hi32); + } + return 0; case BTF_KIND_ARRAY: a = btf_array(t); a->type = bswap_32(a->type); @@ -472,9 +482,22 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) static int determine_ptr_size(const struct btf *btf) { + static const char * const long_aliases[] = { + "long", + "long int", + "int long", + "unsigned long", + "long unsigned", + "unsigned long int", + "unsigned int long", + "long unsigned int", + "long int unsigned", + "int unsigned long", + "int long unsigned", + }; const struct btf_type *t; const char *name; - int i, n; + int i, j, n; if (btf->base_btf && btf->base_btf->ptr_sz > 0) return btf->base_btf->ptr_sz; @@ -485,15 +508,16 @@ static int determine_ptr_size(const struct btf *btf) if (!btf_is_int(t)) continue; + if (t->size != 4 && t->size != 8) + continue; + name = btf__name_by_offset(btf, t->name_off); if (!name) continue; - if (strcmp(name, "long int") == 0 || - strcmp(name, "long unsigned int") == 0) { - if (t->size != 4 && t->size != 8) - continue; - return t->size; + for (j = 0; j < ARRAY_SIZE(long_aliases); j++) { + if (strcmp(name, long_aliases[j]) == 0) + return t->size; } } @@ -597,6 +621,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_DATASEC: case BTF_KIND_FLOAT: size = t->size; @@ -644,6 +669,7 @@ int btf__align_of(const struct btf *btf, __u32 id) switch (kind) { case BTF_KIND_INT: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_FLOAT: return min(btf_ptr_sz(btf), (size_t)t->size); case BTF_KIND_PTR: @@ -2115,20 +2141,8 @@ int btf__add_field(struct btf *btf, const char *name, int type_id, return 0; } -/* - * Append new BTF_KIND_ENUM type with: - * - *name* - name of the enum, can be NULL or empty for anonymous enums; - * - *byte_sz* - size of the enum, in bytes. - * - * Enum initially has no enum values in it (and corresponds to enum forward - * declaration). Enumerator values can be added by btf__add_enum_value() - * immediately after btf__add_enum() succeeds. - * - * Returns: - * - >0, type ID of newly added BTF type; - * - <0, on error. - */ -int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz) +static int btf_add_enum_common(struct btf *btf, const char *name, __u32 byte_sz, + bool is_signed, __u8 kind) { struct btf_type *t; int sz, name_off = 0; @@ -2153,13 +2167,35 @@ int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz) /* start out with vlen=0; it will be adjusted when adding enum values */ t->name_off = name_off; - t->info = btf_type_info(BTF_KIND_ENUM, 0, 0); + t->info = btf_type_info(kind, 0, is_signed); t->size = byte_sz; return btf_commit_type(btf, sz); } /* + * Append new BTF_KIND_ENUM type with: + * - *name* - name of the enum, can be NULL or empty for anonymous enums; + * - *byte_sz* - size of the enum, in bytes. + * + * Enum initially has no enum values in it (and corresponds to enum forward + * declaration). Enumerator values can be added by btf__add_enum_value() + * immediately after btf__add_enum() succeeds. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz) +{ + /* + * set the signedness to be unsigned, it will change to signed + * if any later enumerator is negative. + */ + return btf_add_enum_common(btf, name, byte_sz, false, BTF_KIND_ENUM); +} + +/* * Append new enum value for the current ENUM type with: * - *name* - name of the enumerator value, can't be NULL or empty; * - *value* - integer value corresponding to enum value *name*; @@ -2206,6 +2242,82 @@ int btf__add_enum_value(struct btf *btf, const char *name, __s64 value) t = btf_last_type(btf); btf_type_inc_vlen(t); + /* if negative value, set signedness to signed */ + if (value < 0) + t->info = btf_type_info(btf_kind(t), btf_vlen(t), true); + + btf->hdr->type_len += sz; + btf->hdr->str_off += sz; + return 0; +} + +/* + * Append new BTF_KIND_ENUM64 type with: + * - *name* - name of the enum, can be NULL or empty for anonymous enums; + * - *byte_sz* - size of the enum, in bytes. + * - *is_signed* - whether the enum values are signed or not; + * + * Enum initially has no enum values in it (and corresponds to enum forward + * declaration). Enumerator values can be added by btf__add_enum64_value() + * immediately after btf__add_enum64() succeeds. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_enum64(struct btf *btf, const char *name, __u32 byte_sz, + bool is_signed) +{ + return btf_add_enum_common(btf, name, byte_sz, is_signed, + BTF_KIND_ENUM64); +} + +/* + * Append new enum value for the current ENUM64 type with: + * - *name* - name of the enumerator value, can't be NULL or empty; + * - *value* - integer value corresponding to enum value *name*; + * Returns: + * - 0, on success; + * - <0, on error. + */ +int btf__add_enum64_value(struct btf *btf, const char *name, __u64 value) +{ + struct btf_enum64 *v; + struct btf_type *t; + int sz, name_off; + + /* last type should be BTF_KIND_ENUM64 */ + if (btf->nr_types == 0) + return libbpf_err(-EINVAL); + t = btf_last_type(btf); + if (!btf_is_enum64(t)) + return libbpf_err(-EINVAL); + + /* non-empty name */ + if (!name || !name[0]) + return libbpf_err(-EINVAL); + + /* decompose and invalidate raw data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_enum64); + v = btf_add_type_mem(btf, sz); + if (!v) + return libbpf_err(-ENOMEM); + + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + v->name_off = name_off; + v->val_lo32 = (__u32)value; + v->val_hi32 = value >> 32; + + /* update parent type's vlen */ + t = btf_last_type(btf); + btf_type_inc_vlen(t); + btf->hdr->type_len += sz; btf->hdr->str_off += sz; return 0; @@ -3470,7 +3582,7 @@ static bool btf_equal_int_tag(struct btf_type *t1, struct btf_type *t2) return info1 == info2; } -/* Calculate type signature hash of ENUM. */ +/* Calculate type signature hash of ENUM/ENUM64. */ static long btf_hash_enum(struct btf_type *t) { long h; @@ -3504,9 +3616,31 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) return true; } +static bool btf_equal_enum64(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_enum64 *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + vlen = btf_vlen(t1); + m1 = btf_enum64(t1); + m2 = btf_enum64(t2); + for (i = 0; i < vlen; i++) { + if (m1->name_off != m2->name_off || m1->val_lo32 != m2->val_lo32 || + m1->val_hi32 != m2->val_hi32) + return false; + m1++; + m2++; + } + return true; +} + static inline bool btf_is_enum_fwd(struct btf_type *t) { - return btf_is_enum(t) && btf_vlen(t) == 0; + return btf_is_any_enum(t) && btf_vlen(t) == 0; } static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) @@ -3519,6 +3653,17 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) t1->size == t2->size; } +static bool btf_compat_enum64(struct btf_type *t1, struct btf_type *t2) +{ + if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2)) + return btf_equal_enum64(t1, t2); + + /* ignore vlen when comparing */ + return t1->name_off == t2->name_off && + (t1->info & ~0xffff) == (t2->info & ~0xffff) && + t1->size == t2->size; +} + /* * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs, * as referenced type IDs equivalence is established separately during type @@ -3731,6 +3876,7 @@ static int btf_dedup_prep(struct btf_dedup *d) h = btf_hash_int_decl_tag(t); break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: h = btf_hash_enum(t); break; case BTF_KIND_STRUCT: @@ -3820,6 +3966,27 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) } break; + case BTF_KIND_ENUM64: + h = btf_hash_enum(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_enum64(t, cand)) { + new_id = cand_id; + break; + } + if (btf_compat_enum64(t, cand)) { + if (btf_is_enum_fwd(t)) { + /* resolve fwd to full enum */ + new_id = cand_id; + break; + } + /* resolve canonical enum fwd to full enum */ + d->map[cand_id] = type_id; + } + } + break; + case BTF_KIND_FWD: case BTF_KIND_FLOAT: h = btf_hash_common(t); @@ -4115,6 +4282,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, case BTF_KIND_ENUM: return btf_compat_enum(cand_type, canon_type); + case BTF_KIND_ENUM64: + return btf_compat_enum64(cand_type, canon_type); + case BTF_KIND_FWD: case BTF_KIND_FLOAT: return btf_equal_common(cand_type, canon_type); @@ -4717,6 +4887,7 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct case BTF_KIND_INT: case BTF_KIND_FLOAT: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: return 0; case BTF_KIND_FWD: @@ -4811,6 +4982,16 @@ int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ct } break; } + case BTF_KIND_ENUM64: { + struct btf_enum64 *m = btf_enum64(t); + + for (i = 0, n = btf_vlen(t); i < n; i++, m++) { + err = visit(&m->name_off, ctx); + if (err) + return err; + } + break; + } case BTF_KIND_FUNC_PROTO: { struct btf_param *m = btf_params(t); diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 951ac7475794..9fb416eb5644 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -215,6 +215,8 @@ LIBBPF_API int btf__add_field(struct btf *btf, const char *name, int field_type_ /* enum construction APIs */ LIBBPF_API int btf__add_enum(struct btf *btf, const char *name, __u32 bytes_sz); LIBBPF_API int btf__add_enum_value(struct btf *btf, const char *name, __s64 value); +LIBBPF_API int btf__add_enum64(struct btf *btf, const char *name, __u32 bytes_sz, bool is_signed); +LIBBPF_API int btf__add_enum64_value(struct btf *btf, const char *name, __u64 value); enum btf_fwd_kind { BTF_FWD_STRUCT = 0, @@ -393,9 +395,10 @@ btf_dump__dump_type_data(struct btf_dump *d, __u32 id, #ifndef BTF_KIND_FLOAT #define BTF_KIND_FLOAT 16 /* Floating point */ #endif -/* The kernel header switched to enums, so these two were never #defined */ +/* The kernel header switched to enums, so the following were never #defined */ #define BTF_KIND_DECL_TAG 17 /* Decl Tag */ #define BTF_KIND_TYPE_TAG 18 /* Type Tag */ +#define BTF_KIND_ENUM64 19 /* Enum for up-to 64bit values */ static inline __u16 btf_kind(const struct btf_type *t) { @@ -454,6 +457,11 @@ static inline bool btf_is_enum(const struct btf_type *t) return btf_kind(t) == BTF_KIND_ENUM; } +static inline bool btf_is_enum64(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM64; +} + static inline bool btf_is_fwd(const struct btf_type *t) { return btf_kind(t) == BTF_KIND_FWD; @@ -524,6 +532,18 @@ static inline bool btf_is_type_tag(const struct btf_type *t) return btf_kind(t) == BTF_KIND_TYPE_TAG; } +static inline bool btf_is_any_enum(const struct btf_type *t) +{ + return btf_is_enum(t) || btf_is_enum64(t); +} + +static inline bool btf_kind_core_compat(const struct btf_type *t1, + const struct btf_type *t2) +{ + return btf_kind(t1) == btf_kind(t2) || + (btf_is_any_enum(t1) && btf_is_any_enum(t2)); +} + static inline __u8 btf_int_encoding(const struct btf_type *t) { return BTF_INT_ENCODING(*(__u32 *)(t + 1)); @@ -549,6 +569,16 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t) return (struct btf_enum *)(t + 1); } +static inline struct btf_enum64 *btf_enum64(const struct btf_type *t) +{ + return (struct btf_enum64 *)(t + 1); +} + +static inline __u64 btf_enum64_value(const struct btf_enum64 *e) +{ + return ((__u64)e->val_hi32 << 32) | e->val_lo32; +} + static inline struct btf_member *btf_members(const struct btf_type *t) { return (struct btf_member *)(t + 1); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 6b1bc1f43728..f5275f819027 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -318,6 +318,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d) switch (btf_kind(t)) { case BTF_KIND_INT: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_FWD: case BTF_KIND_FLOAT: break; @@ -538,6 +539,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return 1; } case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_FWD: /* * non-anonymous or non-referenced enums are top-level @@ -739,6 +741,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) tstate->emit_state = EMITTED; break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: if (top_level_def) { btf_dump_emit_enum_def(d, id, t, 0); btf_dump_printf(d, ";\n\n"); @@ -989,38 +992,81 @@ static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id, btf_dump_printf(d, "enum %s", btf_dump_type_name(d, id)); } -static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, - const struct btf_type *t, - int lvl) +static void btf_dump_emit_enum32_val(struct btf_dump *d, + const struct btf_type *t, + int lvl, __u16 vlen) { const struct btf_enum *v = btf_enum(t); - __u16 vlen = btf_vlen(t); + bool is_signed = btf_kflag(t); + const char *fmt_str; const char *name; size_t dup_cnt; int i; + for (i = 0; i < vlen; i++, v++) { + name = btf_name_of(d, v->name_off); + /* enumerators share namespace with typedef idents */ + dup_cnt = btf_dump_name_dups(d, d->ident_names, name); + if (dup_cnt > 1) { + fmt_str = is_signed ? "\n%s%s___%zd = %d," : "\n%s%s___%zd = %u,"; + btf_dump_printf(d, fmt_str, pfx(lvl + 1), name, dup_cnt, v->val); + } else { + fmt_str = is_signed ? "\n%s%s = %d," : "\n%s%s = %u,"; + btf_dump_printf(d, fmt_str, pfx(lvl + 1), name, v->val); + } + } +} + +static void btf_dump_emit_enum64_val(struct btf_dump *d, + const struct btf_type *t, + int lvl, __u16 vlen) +{ + const struct btf_enum64 *v = btf_enum64(t); + bool is_signed = btf_kflag(t); + const char *fmt_str; + const char *name; + size_t dup_cnt; + __u64 val; + int i; + + for (i = 0; i < vlen; i++, v++) { + name = btf_name_of(d, v->name_off); + dup_cnt = btf_dump_name_dups(d, d->ident_names, name); + val = btf_enum64_value(v); + if (dup_cnt > 1) { + fmt_str = is_signed ? "\n%s%s___%zd = %lldLL," + : "\n%s%s___%zd = %lluULL,"; + btf_dump_printf(d, fmt_str, + pfx(lvl + 1), name, dup_cnt, + (unsigned long long)val); + } else { + fmt_str = is_signed ? "\n%s%s = %lldLL," + : "\n%s%s = %lluULL,"; + btf_dump_printf(d, fmt_str, + pfx(lvl + 1), name, + (unsigned long long)val); + } + } +} +static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, + int lvl) +{ + __u16 vlen = btf_vlen(t); + btf_dump_printf(d, "enum%s%s", t->name_off ? " " : "", btf_dump_type_name(d, id)); - if (vlen) { - btf_dump_printf(d, " {"); - for (i = 0; i < vlen; i++, v++) { - name = btf_name_of(d, v->name_off); - /* enumerators share namespace with typedef idents */ - dup_cnt = btf_dump_name_dups(d, d->ident_names, name); - if (dup_cnt > 1) { - btf_dump_printf(d, "\n%s%s___%zu = %u,", - pfx(lvl + 1), name, dup_cnt, - (__u32)v->val); - } else { - btf_dump_printf(d, "\n%s%s = %u,", - pfx(lvl + 1), name, - (__u32)v->val); - } - } - btf_dump_printf(d, "\n%s}", pfx(lvl)); - } + if (!vlen) + return; + + btf_dump_printf(d, " {"); + if (btf_is_enum(t)) + btf_dump_emit_enum32_val(d, t, lvl, vlen); + else + btf_dump_emit_enum64_val(d, t, lvl, vlen); + btf_dump_printf(d, "\n%s}", pfx(lvl)); } static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, @@ -1178,6 +1224,7 @@ skip_mod: break; case BTF_KIND_INT: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_FWD: case BTF_KIND_STRUCT: case BTF_KIND_UNION: @@ -1312,6 +1359,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, btf_dump_emit_struct_fwd(d, id, t); break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: btf_dump_emit_mods(d, decls); /* inline anonymous enum */ if (t->name_off == 0 && !d->skip_anon_defs) @@ -1988,7 +2036,8 @@ static int btf_dump_get_enum_value(struct btf_dump *d, __u32 id, __s64 *value) { - /* handle unaligned enum value */ + bool is_signed = btf_kflag(t); + if (!ptr_is_aligned(d->btf, id, data)) { __u64 val; int err; @@ -2005,13 +2054,13 @@ static int btf_dump_get_enum_value(struct btf_dump *d, *value = *(__s64 *)data; return 0; case 4: - *value = *(__s32 *)data; + *value = is_signed ? *(__s32 *)data : *(__u32 *)data; return 0; case 2: - *value = *(__s16 *)data; + *value = is_signed ? *(__s16 *)data : *(__u16 *)data; return 0; case 1: - *value = *(__s8 *)data; + *value = is_signed ? *(__s8 *)data : *(__u8 *)data; return 0; default: pr_warn("unexpected size %d for enum, id:[%u]\n", t->size, id); @@ -2024,7 +2073,7 @@ static int btf_dump_enum_data(struct btf_dump *d, __u32 id, const void *data) { - const struct btf_enum *e; + bool is_signed; __s64 value; int i, err; @@ -2032,14 +2081,31 @@ static int btf_dump_enum_data(struct btf_dump *d, if (err) return err; - for (i = 0, e = btf_enum(t); i < btf_vlen(t); i++, e++) { - if (value != e->val) - continue; - btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off)); - return 0; - } + is_signed = btf_kflag(t); + if (btf_is_enum(t)) { + const struct btf_enum *e; + + for (i = 0, e = btf_enum(t); i < btf_vlen(t); i++, e++) { + if (value != e->val) + continue; + btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off)); + return 0; + } - btf_dump_type_values(d, "%d", value); + btf_dump_type_values(d, is_signed ? "%d" : "%u", value); + } else { + const struct btf_enum64 *e; + + for (i = 0, e = btf_enum64(t); i < btf_vlen(t); i++, e++) { + if (value != btf_enum64_value(e)) + continue; + btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off)); + return 0; + } + + btf_dump_type_values(d, is_signed ? "%lldLL" : "%lluULL", + (unsigned long long)value); + } return 0; } @@ -2099,6 +2165,7 @@ static int btf_dump_type_data_check_overflow(struct btf_dump *d, case BTF_KIND_FLOAT: case BTF_KIND_PTR: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: if (data + bits_offset / 8 + size > d->typed_dump->data_end) return -E2BIG; break; @@ -2203,6 +2270,7 @@ static int btf_dump_type_data_check_zero(struct btf_dump *d, return -ENODATA; } case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: err = btf_dump_get_enum_value(d, t, data, id, &value); if (err) return err; @@ -2275,6 +2343,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, err = btf_dump_struct_data(d, t, id, data); break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: /* handle bitfield and int enum values */ if (bit_sz) { __u64 print_num; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e89cc9c885b3..49e359cd34df 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -72,6 +72,134 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog); +static const char * const attach_type_name[] = { + [BPF_CGROUP_INET_INGRESS] = "cgroup_inet_ingress", + [BPF_CGROUP_INET_EGRESS] = "cgroup_inet_egress", + [BPF_CGROUP_INET_SOCK_CREATE] = "cgroup_inet_sock_create", + [BPF_CGROUP_INET_SOCK_RELEASE] = "cgroup_inet_sock_release", + [BPF_CGROUP_SOCK_OPS] = "cgroup_sock_ops", + [BPF_CGROUP_DEVICE] = "cgroup_device", + [BPF_CGROUP_INET4_BIND] = "cgroup_inet4_bind", + [BPF_CGROUP_INET6_BIND] = "cgroup_inet6_bind", + [BPF_CGROUP_INET4_CONNECT] = "cgroup_inet4_connect", + [BPF_CGROUP_INET6_CONNECT] = "cgroup_inet6_connect", + [BPF_CGROUP_INET4_POST_BIND] = "cgroup_inet4_post_bind", + [BPF_CGROUP_INET6_POST_BIND] = "cgroup_inet6_post_bind", + [BPF_CGROUP_INET4_GETPEERNAME] = "cgroup_inet4_getpeername", + [BPF_CGROUP_INET6_GETPEERNAME] = "cgroup_inet6_getpeername", + [BPF_CGROUP_INET4_GETSOCKNAME] = "cgroup_inet4_getsockname", + [BPF_CGROUP_INET6_GETSOCKNAME] = "cgroup_inet6_getsockname", + [BPF_CGROUP_UDP4_SENDMSG] = "cgroup_udp4_sendmsg", + [BPF_CGROUP_UDP6_SENDMSG] = "cgroup_udp6_sendmsg", + [BPF_CGROUP_SYSCTL] = "cgroup_sysctl", + [BPF_CGROUP_UDP4_RECVMSG] = "cgroup_udp4_recvmsg", + [BPF_CGROUP_UDP6_RECVMSG] = "cgroup_udp6_recvmsg", + [BPF_CGROUP_GETSOCKOPT] = "cgroup_getsockopt", + [BPF_CGROUP_SETSOCKOPT] = "cgroup_setsockopt", + [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", + [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", + [BPF_SK_SKB_VERDICT] = "sk_skb_verdict", + [BPF_SK_MSG_VERDICT] = "sk_msg_verdict", + [BPF_LIRC_MODE2] = "lirc_mode2", + [BPF_FLOW_DISSECTOR] = "flow_dissector", + [BPF_TRACE_RAW_TP] = "trace_raw_tp", + [BPF_TRACE_FENTRY] = "trace_fentry", + [BPF_TRACE_FEXIT] = "trace_fexit", + [BPF_MODIFY_RETURN] = "modify_return", + [BPF_LSM_MAC] = "lsm_mac", + [BPF_SK_LOOKUP] = "sk_lookup", + [BPF_TRACE_ITER] = "trace_iter", + [BPF_XDP_DEVMAP] = "xdp_devmap", + [BPF_XDP_CPUMAP] = "xdp_cpumap", + [BPF_XDP] = "xdp", + [BPF_SK_REUSEPORT_SELECT] = "sk_reuseport_select", + [BPF_SK_REUSEPORT_SELECT_OR_MIGRATE] = "sk_reuseport_select_or_migrate", + [BPF_PERF_EVENT] = "perf_event", + [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", +}; + +static const char * const link_type_name[] = { + [BPF_LINK_TYPE_UNSPEC] = "unspec", + [BPF_LINK_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_LINK_TYPE_TRACING] = "tracing", + [BPF_LINK_TYPE_CGROUP] = "cgroup", + [BPF_LINK_TYPE_ITER] = "iter", + [BPF_LINK_TYPE_NETNS] = "netns", + [BPF_LINK_TYPE_XDP] = "xdp", + [BPF_LINK_TYPE_PERF_EVENT] = "perf_event", + [BPF_LINK_TYPE_KPROBE_MULTI] = "kprobe_multi", + [BPF_LINK_TYPE_STRUCT_OPS] = "struct_ops", +}; + +static const char * const map_type_name[] = { + [BPF_MAP_TYPE_UNSPEC] = "unspec", + [BPF_MAP_TYPE_HASH] = "hash", + [BPF_MAP_TYPE_ARRAY] = "array", + [BPF_MAP_TYPE_PROG_ARRAY] = "prog_array", + [BPF_MAP_TYPE_PERF_EVENT_ARRAY] = "perf_event_array", + [BPF_MAP_TYPE_PERCPU_HASH] = "percpu_hash", + [BPF_MAP_TYPE_PERCPU_ARRAY] = "percpu_array", + [BPF_MAP_TYPE_STACK_TRACE] = "stack_trace", + [BPF_MAP_TYPE_CGROUP_ARRAY] = "cgroup_array", + [BPF_MAP_TYPE_LRU_HASH] = "lru_hash", + [BPF_MAP_TYPE_LRU_PERCPU_HASH] = "lru_percpu_hash", + [BPF_MAP_TYPE_LPM_TRIE] = "lpm_trie", + [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", + [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", + [BPF_MAP_TYPE_DEVMAP] = "devmap", + [BPF_MAP_TYPE_DEVMAP_HASH] = "devmap_hash", + [BPF_MAP_TYPE_SOCKMAP] = "sockmap", + [BPF_MAP_TYPE_CPUMAP] = "cpumap", + [BPF_MAP_TYPE_XSKMAP] = "xskmap", + [BPF_MAP_TYPE_SOCKHASH] = "sockhash", + [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", + [BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray", + [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage", + [BPF_MAP_TYPE_QUEUE] = "queue", + [BPF_MAP_TYPE_STACK] = "stack", + [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", + [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", + [BPF_MAP_TYPE_RINGBUF] = "ringbuf", + [BPF_MAP_TYPE_INODE_STORAGE] = "inode_storage", + [BPF_MAP_TYPE_TASK_STORAGE] = "task_storage", + [BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter", +}; + +static const char * const prog_type_name[] = { + [BPF_PROG_TYPE_UNSPEC] = "unspec", + [BPF_PROG_TYPE_SOCKET_FILTER] = "socket_filter", + [BPF_PROG_TYPE_KPROBE] = "kprobe", + [BPF_PROG_TYPE_SCHED_CLS] = "sched_cls", + [BPF_PROG_TYPE_SCHED_ACT] = "sched_act", + [BPF_PROG_TYPE_TRACEPOINT] = "tracepoint", + [BPF_PROG_TYPE_XDP] = "xdp", + [BPF_PROG_TYPE_PERF_EVENT] = "perf_event", + [BPF_PROG_TYPE_CGROUP_SKB] = "cgroup_skb", + [BPF_PROG_TYPE_CGROUP_SOCK] = "cgroup_sock", + [BPF_PROG_TYPE_LWT_IN] = "lwt_in", + [BPF_PROG_TYPE_LWT_OUT] = "lwt_out", + [BPF_PROG_TYPE_LWT_XMIT] = "lwt_xmit", + [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", + [BPF_PROG_TYPE_SK_SKB] = "sk_skb", + [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", + [BPF_PROG_TYPE_SK_MSG] = "sk_msg", + [BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr", + [BPF_PROG_TYPE_LWT_SEG6LOCAL] = "lwt_seg6local", + [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", + [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", + [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", + [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", + [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable", + [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", + [BPF_PROG_TYPE_TRACING] = "tracing", + [BPF_PROG_TYPE_STRUCT_OPS] = "struct_ops", + [BPF_PROG_TYPE_EXT] = "ext", + [BPF_PROG_TYPE_LSM] = "lsm", + [BPF_PROG_TYPE_SK_LOOKUP] = "sk_lookup", + [BPF_PROG_TYPE_SYSCALL] = "syscall", +}; + static int __base_pr(enum libbpf_print_level level, const char *format, va_list args) { @@ -2114,6 +2242,7 @@ static const char *__btf_kind_str(__u16 kind) case BTF_KIND_FLOAT: return "float"; case BTF_KIND_DECL_TAG: return "decl_tag"; case BTF_KIND_TYPE_TAG: return "type_tag"; + case BTF_KIND_ENUM64: return "enum64"; default: return "unknown"; } } @@ -2642,12 +2771,13 @@ static bool btf_needs_sanitization(struct bpf_object *obj) bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); bool has_type_tag = kernel_supports(obj, FEAT_BTF_TYPE_TAG); + bool has_enum64 = kernel_supports(obj, FEAT_BTF_ENUM64); return !has_func || !has_datasec || !has_func_global || !has_float || - !has_decl_tag || !has_type_tag; + !has_decl_tag || !has_type_tag || !has_enum64; } -static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) +static int bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) { bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC); bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); @@ -2655,6 +2785,8 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); bool has_type_tag = kernel_supports(obj, FEAT_BTF_TYPE_TAG); + bool has_enum64 = kernel_supports(obj, FEAT_BTF_ENUM64); + int enum64_placeholder_id = 0; struct btf_type *t; int i, j, vlen; @@ -2717,8 +2849,32 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) /* replace TYPE_TAG with a CONST */ t->name_off = 0; t->info = BTF_INFO_ENC(BTF_KIND_CONST, 0, 0); - } + } else if (!has_enum64 && btf_is_enum(t)) { + /* clear the kflag */ + t->info = btf_type_info(btf_kind(t), btf_vlen(t), false); + } else if (!has_enum64 && btf_is_enum64(t)) { + /* replace ENUM64 with a union */ + struct btf_member *m; + + if (enum64_placeholder_id == 0) { + enum64_placeholder_id = btf__add_int(btf, "enum64_placeholder", 1, 0); + if (enum64_placeholder_id < 0) + return enum64_placeholder_id; + + t = (struct btf_type *)btf__type_by_id(btf, i); + } + + m = btf_members(t); + vlen = btf_vlen(t); + t->info = BTF_INFO_ENC(BTF_KIND_UNION, 0, vlen); + for (j = 0; j < vlen; j++, m++) { + m->type = enum64_placeholder_id; + m->offset = 0; + } + } } + + return 0; } static bool libbpf_needs_btf(const struct bpf_object *obj) @@ -3056,7 +3212,9 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) /* enforce 8-byte pointers for BPF-targeted BTFs */ btf__set_pointer_size(obj->btf, 8); - bpf_object__sanitize_btf(obj, kern_btf); + err = bpf_object__sanitize_btf(obj, kern_btf); + if (err) + return err; } if (obj->gen_loader) { @@ -3563,6 +3721,10 @@ static enum kcfg_type find_kcfg_type(const struct btf *btf, int id, if (strcmp(name, "libbpf_tristate")) return KCFG_UNKNOWN; return KCFG_TRISTATE; + case BTF_KIND_ENUM64: + if (strcmp(name, "libbpf_tristate")) + return KCFG_UNKNOWN; + return KCFG_TRISTATE; case BTF_KIND_ARRAY: if (btf_array(t)->nelems == 0) return KCFG_UNKNOWN; @@ -4746,6 +4908,17 @@ static int probe_kern_bpf_cookie(void) return probe_fd(ret); } +static int probe_kern_btf_enum64(void) +{ + 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))); +} + enum kern_feature_result { FEAT_UNKNOWN = 0, FEAT_SUPPORTED = 1, @@ -4811,6 +4984,9 @@ static struct kern_feature_desc { [FEAT_BPF_COOKIE] = { "BPF cookie support", probe_kern_bpf_cookie, }, + [FEAT_BTF_ENUM64] = { + "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, + }, }; bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) @@ -4943,11 +5119,6 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) static void bpf_map__destroy(struct bpf_map *map); -static bool is_pow_of_2(size_t x) -{ - return x && (x & (x - 1)); -} - static size_t adjust_ringbuf_sz(size_t sz) { __u32 page_sz = sysconf(_SC_PAGE_SIZE); @@ -5353,7 +5524,7 @@ int bpf_core_add_cands(struct bpf_core_cand *local_cand, n = btf__type_cnt(targ_btf); for (i = targ_start_id; i < n; i++) { t = btf__type_by_id(targ_btf, i); - if (btf_kind(t) != btf_kind(local_t)) + if (!btf_kind_core_compat(t, local_t)) continue; targ_name = btf__name_by_offset(targ_btf, t->name_off); @@ -5567,7 +5738,7 @@ int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, /* caller made sure that names match (ignoring flavor suffix) */ local_type = btf__type_by_id(local_btf, local_id); targ_type = btf__type_by_id(targ_btf, targ_id); - if (btf_kind(local_type) != btf_kind(targ_type)) + if (!btf_kind_core_compat(local_type, targ_type)) return 0; recur: @@ -5580,7 +5751,7 @@ recur: if (!local_type || !targ_type) return -EINVAL; - if (btf_kind(local_type) != btf_kind(targ_type)) + if (!btf_kind_core_compat(local_type, targ_type)) return 0; switch (btf_kind(local_type)) { @@ -5588,6 +5759,7 @@ recur: case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_FWD: return 1; case BTF_KIND_INT: @@ -9005,8 +9177,10 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), SEC_DEF("kprobe+", KPROBE, 0, SEC_NONE, attach_kprobe), SEC_DEF("uprobe+", KPROBE, 0, SEC_NONE, attach_uprobe), + SEC_DEF("uprobe.s+", KPROBE, 0, SEC_SLEEPABLE, attach_uprobe), SEC_DEF("kretprobe+", KPROBE, 0, SEC_NONE, attach_kprobe), SEC_DEF("uretprobe+", KPROBE, 0, SEC_NONE, attach_uprobe), + SEC_DEF("uretprobe.s+", KPROBE, 0, SEC_SLEEPABLE, attach_uprobe), SEC_DEF("kprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), SEC_DEF("kretprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), SEC_DEF("usdt+", KPROBE, 0, SEC_NONE, attach_usdt), @@ -9300,6 +9474,38 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, return libbpf_err(-ESRCH); } +const char *libbpf_bpf_attach_type_str(enum bpf_attach_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(attach_type_name)) + return NULL; + + return attach_type_name[t]; +} + +const char *libbpf_bpf_link_type_str(enum bpf_link_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(link_type_name)) + return NULL; + + return link_type_name[t]; +} + +const char *libbpf_bpf_map_type_str(enum bpf_map_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(map_type_name)) + return NULL; + + return map_type_name[t]; +} + +const char *libbpf_bpf_prog_type_str(enum bpf_prog_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(prog_type_name)) + return NULL; + + return prog_type_name[t]; +} + static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, size_t offset) { @@ -10988,43 +11194,6 @@ static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, return pfd; } -/* uprobes deal in relative offsets; subtract the base address associated with - * the mapped binary. See Documentation/trace/uprobetracer.rst for more - * details. - */ -static long elf_find_relative_offset(const char *filename, Elf *elf, long addr) -{ - size_t n; - int i; - - if (elf_getphdrnum(elf, &n)) { - pr_warn("elf: failed to find program headers for '%s': %s\n", filename, - elf_errmsg(-1)); - return -ENOENT; - } - - for (i = 0; i < n; i++) { - int seg_start, seg_end, seg_offset; - GElf_Phdr phdr; - - if (!gelf_getphdr(elf, i, &phdr)) { - pr_warn("elf: failed to get program header %d from '%s': %s\n", i, filename, - elf_errmsg(-1)); - return -ENOENT; - } - if (phdr.p_type != PT_LOAD || !(phdr.p_flags & PF_X)) - continue; - - seg_start = phdr.p_vaddr; - seg_end = seg_start + phdr.p_memsz; - seg_offset = phdr.p_offset; - if (addr >= seg_start && addr < seg_end) - return addr - seg_start + seg_offset; - } - pr_warn("elf: failed to find prog header containing 0x%lx in '%s'\n", addr, filename); - return -ENOENT; -} - /* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */ static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn) { @@ -11111,6 +11280,8 @@ static long elf_find_func_offset(const char *binary_path, const char *name) for (idx = 0; idx < nr_syms; idx++) { int curr_bind; GElf_Sym sym; + Elf_Scn *sym_scn; + GElf_Shdr sym_sh; if (!gelf_getsym(symbols, idx, &sym)) continue; @@ -11148,12 +11319,28 @@ static long elf_find_func_offset(const char *binary_path, const char *name) continue; } } - ret = sym.st_value; + + /* Transform symbol's virtual address (absolute for + * binaries and relative for shared libs) into file + * offset, which is what kernel is expecting for + * uprobe/uretprobe attachment. + * See Documentation/trace/uprobetracer.rst for more + * details. + * This is done by looking up symbol's containing + * section's header and using it's virtual address + * (sh_addr) and corresponding file offset (sh_offset) + * to transform sym.st_value (virtual address) into + * desired final file offset. + */ + sym_scn = elf_getscn(elf, sym.st_shndx); + if (!sym_scn) + continue; + if (!gelf_getshdr(sym_scn, &sym_sh)) + continue; + + ret = sym.st_value - sym_sh.sh_addr + sym_sh.sh_offset; last_bind = curr_bind; } - /* For binaries that are not shared libraries, we need relative offset */ - if (ret > 0 && !is_shared_lib) - ret = elf_find_relative_offset(binary_path, elf, ret); if (ret > 0) break; } @@ -11386,7 +11573,8 @@ static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf break; case 3: case 4: - opts.retprobe = strcmp(probe_type, "uretprobe") == 0; + opts.retprobe = strcmp(probe_type, "uretprobe") == 0 || + strcmp(probe_type, "uretprobe.s") == 0; if (opts.retprobe && offset != 0) { pr_warn("prog '%s': uretprobes do not support offset specification\n", prog->name); diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 9e9a3fd3edd8..fa27969da0da 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -51,6 +51,42 @@ enum libbpf_errno { LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size); +/** + * @brief **libbpf_bpf_attach_type_str()** converts the provided attach type + * value into a textual representation. + * @param t The attach type. + * @return Pointer to a static string identifying the attach type. NULL is + * returned for unknown **bpf_attach_type** values. + */ +LIBBPF_API const char *libbpf_bpf_attach_type_str(enum bpf_attach_type t); + +/** + * @brief **libbpf_bpf_link_type_str()** converts the provided link type value + * into a textual representation. + * @param t The link type. + * @return Pointer to a static string identifying the link type. NULL is + * returned for unknown **bpf_link_type** values. + */ +LIBBPF_API const char *libbpf_bpf_link_type_str(enum bpf_link_type t); + +/** + * @brief **libbpf_bpf_map_type_str()** converts the provided map type value + * into a textual representation. + * @param t The map type. + * @return Pointer to a static string identifying the map type. NULL is + * returned for unknown **bpf_map_type** values. + */ +LIBBPF_API const char *libbpf_bpf_map_type_str(enum bpf_map_type t); + +/** + * @brief **libbpf_bpf_prog_type_str()** converts the provided program type + * value into a textual representation. + * @param t The program type. + * @return Pointer to a static string identifying the program type. NULL is + * returned for unknown **bpf_prog_type** values. + */ +LIBBPF_API const char *libbpf_bpf_prog_type_str(enum bpf_prog_type t); + enum libbpf_print_level { LIBBPF_WARN, LIBBPF_INFO, @@ -71,7 +107,7 @@ struct bpf_object_open_attr { }; struct bpf_object_open_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; /* object name override, if provided: * - for object open from file, this will override setting object diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 52973cffc20c..116a2a8ee7c2 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -461,5 +461,13 @@ LIBBPF_0.8.0 { } LIBBPF_0.7.0; LIBBPF_1.0.0 { + global: + btf__add_enum64; + btf__add_enum64_value; + libbpf_bpf_attach_type_str; + libbpf_bpf_link_type_str; + libbpf_bpf_map_type_str; + libbpf_bpf_prog_type_str; + local: *; }; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 4abdbe2fea9d..a1ad145ffa74 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -351,6 +351,8 @@ enum kern_feature_id { FEAT_MEMCG_ACCOUNT, /* BPF cookie (bpf_get_attach_cookie() BPF helper) support */ FEAT_BPF_COOKIE, + /* BTF_KIND_ENUM64 support and BTF_KIND_ENUM kflag support */ + FEAT_BTF_ENUM64, __FEAT_CNT, }; @@ -580,4 +582,9 @@ struct bpf_link * usdt_manager_attach_usdt(struct usdt_manager *man, const char *usdt_provider, const char *usdt_name, __u64 usdt_cookie); +static inline bool is_pow_of_2(size_t x) +{ + return x && (x & (x - 1)) == 0; +} + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 9aa016fb55aa..4ac02c28e152 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -697,11 +697,6 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, return err; } -static bool is_pow_of_2(size_t x) -{ - return x && (x & (x - 1)) == 0; -} - static int linker_sanity_check_elf(struct src_obj *obj) { struct src_sec *sec; @@ -1340,6 +1335,7 @@ recur: case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_FWD: case BTF_KIND_FUNC: case BTF_KIND_VAR: @@ -1362,6 +1358,7 @@ recur: case BTF_KIND_INT: case BTF_KIND_FLOAT: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: /* ignore encoding for int and enum values for enum */ if (t1->size != t2->size) { pr_warn("global '%s': incompatible %s '%s' size %u and %u\n", diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index ba4453dfd1ed..6ad3c3891a9a 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -167,7 +167,7 @@ static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) * just a parsed access string representation): [0, 1, 2, 3]. * * High-level spec will capture only 3 points: - * - intial zero-index access by pointer (&s->... is the same as &s[0]...); + * - initial zero-index access by pointer (&s->... is the same as &s[0]...); * - field 'a' access (corresponds to '2' in low-level spec); * - array element #3 access (corresponds to '3' in low-level spec). * @@ -186,7 +186,7 @@ int bpf_core_parse_spec(const char *prog_name, const struct btf *btf, struct bpf_core_accessor *acc; const struct btf_type *t; const char *name, *spec_str; - __u32 id; + __u32 id, name_off; __s64 sz; spec_str = btf__name_by_offset(btf, relo->access_str_off); @@ -231,11 +231,13 @@ int bpf_core_parse_spec(const char *prog_name, const struct btf *btf, spec->len++; if (core_relo_is_enumval_based(relo->kind)) { - if (!btf_is_enum(t) || spec->raw_len > 1 || access_idx >= btf_vlen(t)) + if (!btf_is_any_enum(t) || spec->raw_len > 1 || access_idx >= btf_vlen(t)) return -EINVAL; /* record enumerator name in a first accessor */ - acc->name = btf__name_by_offset(btf, btf_enum(t)[access_idx].name_off); + name_off = btf_is_enum(t) ? btf_enum(t)[access_idx].name_off + : btf_enum64(t)[access_idx].name_off; + acc->name = btf__name_by_offset(btf, name_off); return 0; } @@ -340,7 +342,7 @@ recur: if (btf_is_composite(local_type) && btf_is_composite(targ_type)) return 1; - if (btf_kind(local_type) != btf_kind(targ_type)) + if (!btf_kind_core_compat(local_type, targ_type)) return 0; switch (btf_kind(local_type)) { @@ -348,6 +350,7 @@ recur: case BTF_KIND_FLOAT: return 1; case BTF_KIND_FWD: + case BTF_KIND_ENUM64: case BTF_KIND_ENUM: { const char *local_name, *targ_name; size_t local_len, targ_len; @@ -477,6 +480,7 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, const struct bpf_core_accessor *local_acc; struct bpf_core_accessor *targ_acc; int i, sz, matched; + __u32 name_off; memset(targ_spec, 0, sizeof(*targ_spec)); targ_spec->btf = targ_btf; @@ -494,18 +498,22 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, if (core_relo_is_enumval_based(local_spec->relo_kind)) { size_t local_essent_len, targ_essent_len; - const struct btf_enum *e; const char *targ_name; /* has to resolve to an enum */ targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, &targ_id); - if (!btf_is_enum(targ_type)) + if (!btf_is_any_enum(targ_type)) return 0; local_essent_len = bpf_core_essential_name_len(local_acc->name); - for (i = 0, e = btf_enum(targ_type); i < btf_vlen(targ_type); i++, e++) { - targ_name = btf__name_by_offset(targ_spec->btf, e->name_off); + for (i = 0; i < btf_vlen(targ_type); i++) { + if (btf_is_enum(targ_type)) + name_off = btf_enum(targ_type)[i].name_off; + else + name_off = btf_enum64(targ_type)[i].name_off; + + targ_name = btf__name_by_offset(targ_spec->btf, name_off); targ_essent_len = bpf_core_essential_name_len(targ_name); if (targ_essent_len != local_essent_len) continue; @@ -583,7 +591,7 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, static int bpf_core_calc_field_relo(const char *prog_name, const struct bpf_core_relo *relo, const struct bpf_core_spec *spec, - __u32 *val, __u32 *field_sz, __u32 *type_id, + __u64 *val, __u32 *field_sz, __u32 *type_id, bool *validate) { const struct bpf_core_accessor *acc; @@ -680,8 +688,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, *val = byte_sz; break; case BPF_CORE_FIELD_SIGNED: - /* enums will be assumed unsigned */ - *val = btf_is_enum(mt) || + *val = (btf_is_any_enum(mt) && BTF_INFO_KFLAG(mt->info)) || (btf_int_encoding(mt) & BTF_INT_SIGNED); if (validate) *validate = true; /* signedness is never ambiguous */ @@ -708,7 +715,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo, const struct bpf_core_spec *spec, - __u32 *val, bool *validate) + __u64 *val, bool *validate) { __s64 sz; @@ -751,10 +758,9 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo, static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo, const struct bpf_core_spec *spec, - __u32 *val) + __u64 *val) { const struct btf_type *t; - const struct btf_enum *e; switch (relo->kind) { case BPF_CORE_ENUMVAL_EXISTS: @@ -764,8 +770,10 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo, if (!spec) return -EUCLEAN; /* request instruction poisoning */ t = btf_type_by_id(spec->btf, spec->spec[0].type_id); - e = btf_enum(t) + spec->spec[0].idx; - *val = e->val; + if (btf_is_enum(t)) + *val = btf_enum(t)[spec->spec[0].idx].val; + else + *val = btf_enum64_value(btf_enum64(t) + spec->spec[0].idx); break; default: return -EOPNOTSUPP; @@ -929,7 +937,7 @@ int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn, int insn_idx, const struct bpf_core_relo *relo, int relo_idx, const struct bpf_core_relo_res *res) { - __u32 orig_val, new_val; + __u64 orig_val, new_val; __u8 class; class = BPF_CLASS(insn->code); @@ -954,28 +962,30 @@ poison: if (BPF_SRC(insn->code) != BPF_K) return -EINVAL; if (res->validate && insn->imm != orig_val) { - pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %u -> %u\n", + pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %llu -> %llu\n", prog_name, relo_idx, - insn_idx, insn->imm, orig_val, new_val); + insn_idx, insn->imm, (unsigned long long)orig_val, + (unsigned long long)new_val); return -EINVAL; } orig_val = insn->imm; insn->imm = new_val; - pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %u -> %u\n", + pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %llu -> %llu\n", prog_name, relo_idx, insn_idx, - orig_val, new_val); + (unsigned long long)orig_val, (unsigned long long)new_val); break; case BPF_LDX: case BPF_ST: case BPF_STX: if (res->validate && insn->off != orig_val) { - pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDX/ST/STX) value: got %u, exp %u -> %u\n", - prog_name, relo_idx, insn_idx, insn->off, orig_val, new_val); + pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDX/ST/STX) value: got %u, exp %llu -> %llu\n", + prog_name, relo_idx, insn_idx, insn->off, (unsigned long long)orig_val, + (unsigned long long)new_val); return -EINVAL; } if (new_val > SHRT_MAX) { - pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %u\n", - prog_name, relo_idx, insn_idx, new_val); + pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %llu\n", + prog_name, relo_idx, insn_idx, (unsigned long long)new_val); return -ERANGE; } if (res->fail_memsz_adjust) { @@ -987,8 +997,9 @@ poison: orig_val = insn->off; insn->off = new_val; - pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %u -> %u\n", - prog_name, relo_idx, insn_idx, orig_val, new_val); + pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %llu -> %llu\n", + prog_name, relo_idx, insn_idx, (unsigned long long)orig_val, + (unsigned long long)new_val); if (res->new_sz != res->orig_sz) { int insn_bytes_sz, insn_bpf_sz; @@ -1024,20 +1035,20 @@ poison: return -EINVAL; } - imm = insn[0].imm + ((__u64)insn[1].imm << 32); + imm = (__u32)insn[0].imm | ((__u64)insn[1].imm << 32); if (res->validate && imm != orig_val) { - pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %u -> %u\n", + pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %llu -> %llu\n", prog_name, relo_idx, insn_idx, (unsigned long long)imm, - orig_val, new_val); + (unsigned long long)orig_val, (unsigned long long)new_val); return -EINVAL; } insn[0].imm = new_val; - insn[1].imm = 0; /* currently only 32-bit values are supported */ - pr_debug("prog '%s': relo #%d: patched insn #%d (LDIMM64) imm64 %llu -> %u\n", + insn[1].imm = new_val >> 32; + pr_debug("prog '%s': relo #%d: patched insn #%d (LDIMM64) imm64 %llu -> %llu\n", prog_name, relo_idx, insn_idx, - (unsigned long long)imm, new_val); + (unsigned long long)imm, (unsigned long long)new_val); break; } default: @@ -1057,7 +1068,6 @@ poison: int bpf_core_format_spec(char *buf, size_t buf_sz, const struct bpf_core_spec *spec) { const struct btf_type *t; - const struct btf_enum *e; const char *s; __u32 type_id; int i, len = 0; @@ -1086,10 +1096,23 @@ int bpf_core_format_spec(char *buf, size_t buf_sz, const struct bpf_core_spec *s if (core_relo_is_enumval_based(spec->relo_kind)) { t = skip_mods_and_typedefs(spec->btf, type_id, NULL); - e = btf_enum(t) + spec->raw_spec[0]; - s = btf__name_by_offset(spec->btf, e->name_off); + if (btf_is_enum(t)) { + const struct btf_enum *e; + const char *fmt_str; + + e = btf_enum(t) + spec->raw_spec[0]; + s = btf__name_by_offset(spec->btf, e->name_off); + fmt_str = BTF_INFO_KFLAG(t->info) ? "::%s = %d" : "::%s = %u"; + append_buf(fmt_str, s, e->val); + } else { + const struct btf_enum64 *e; + const char *fmt_str; - append_buf("::%s = %u", s, e->val); + e = btf_enum64(t) + spec->raw_spec[0]; + s = btf__name_by_offset(spec->btf, e->name_off); + fmt_str = BTF_INFO_KFLAG(t->info) ? "::%s = %lld" : "::%s = %llu"; + append_buf(fmt_str, s, (unsigned long long)btf_enum64_value(e)); + } return len; } @@ -1148,11 +1171,11 @@ int bpf_core_format_spec(char *buf, size_t buf_sz, const struct bpf_core_spec *s * 3. It is supported and expected that there might be multiple flavors * matching the spec. As long as all the specs resolve to the same set of * offsets across all candidates, there is no error. If there is any - * ambiguity, CO-RE relocation will fail. This is necessary to accomodate - * imprefection of BTF deduplication, which can cause slight duplication of + * ambiguity, CO-RE relocation will fail. This is necessary to accommodate + * imperfection of BTF deduplication, which can cause slight duplication of * the same BTF type, if some directly or indirectly referenced (by * pointer) type gets resolved to different actual types in different - * object files. If such situation occurs, deduplicated BTF will end up + * object files. If such a situation occurs, deduplicated BTF will end up * with two (or more) structurally identical types, which differ only in * types they refer to through pointer. This should be OK in most cases and * is not an error. @@ -1261,10 +1284,12 @@ int bpf_core_calc_relo_insn(const char *prog_name, * decision and value, otherwise it's dangerous to * proceed due to ambiguity */ - pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %u != %s %u\n", + pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %llu != %s %llu\n", prog_name, relo_idx, - cand_res.poison ? "failure" : "success", cand_res.new_val, - targ_res->poison ? "failure" : "success", targ_res->new_val); + cand_res.poison ? "failure" : "success", + (unsigned long long)cand_res.new_val, + targ_res->poison ? "failure" : "success", + (unsigned long long)targ_res->new_val); return -EINVAL; } diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h index 073039d8ca4f..7df0da082f2c 100644 --- a/tools/lib/bpf/relo_core.h +++ b/tools/lib/bpf/relo_core.h @@ -46,9 +46,9 @@ struct bpf_core_spec { struct bpf_core_relo_res { /* expected value in the instruction, unless validate == false */ - __u32 orig_val; + __u64 orig_val; /* new value that needs to be patched up to */ - __u32 new_val; + __u64 new_val; /* relocation unsuccessful, poison instruction, but don't fail load */ bool poison; /* some relocations can't be validated against orig_val */ diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index f1c9339cfbbc..5159207cbfd9 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -441,7 +441,7 @@ static int parse_elf_segs(Elf *elf, const char *path, struct elf_seg **segs, siz return 0; } -static int parse_lib_segs(int pid, const char *lib_path, struct elf_seg **segs, size_t *seg_cnt) +static int parse_vma_segs(int pid, const char *lib_path, struct elf_seg **segs, size_t *seg_cnt) { char path[PATH_MAX], line[PATH_MAX], mode[16]; size_t seg_start, seg_end, seg_off; @@ -531,35 +531,40 @@ err_out: return err; } -static struct elf_seg *find_elf_seg(struct elf_seg *segs, size_t seg_cnt, long addr, bool relative) +static struct elf_seg *find_elf_seg(struct elf_seg *segs, size_t seg_cnt, long virtaddr) { struct elf_seg *seg; int i; - if (relative) { - /* for shared libraries, address is relative offset and thus - * should be fall within logical offset-based range of - * [offset_start, offset_end) - */ - for (i = 0, seg = segs; i < seg_cnt; i++, seg++) { - if (seg->offset <= addr && addr < seg->offset + (seg->end - seg->start)) - return seg; - } - } else { - /* for binaries, address is absolute and thus should be within - * absolute address range of [seg_start, seg_end) - */ - for (i = 0, seg = segs; i < seg_cnt; i++, seg++) { - if (seg->start <= addr && addr < seg->end) - return seg; - } + /* for ELF binaries (both executables and shared libraries), we are + * given virtual address (absolute for executables, relative for + * libraries) which should match address range of [seg_start, seg_end) + */ + for (i = 0, seg = segs; i < seg_cnt; i++, seg++) { + if (seg->start <= virtaddr && virtaddr < seg->end) + return seg; } + return NULL; +} +static struct elf_seg *find_vma_seg(struct elf_seg *segs, size_t seg_cnt, long offset) +{ + struct elf_seg *seg; + int i; + + /* for VMA segments from /proc/<pid>/maps file, provided "address" is + * actually a file offset, so should be fall within logical + * offset-based range of [offset_start, offset_end) + */ + for (i = 0, seg = segs; i < seg_cnt; i++, seg++) { + if (seg->offset <= offset && offset < seg->offset + (seg->end - seg->start)) + return seg; + } return NULL; } -static int parse_usdt_note(Elf *elf, const char *path, long base_addr, - GElf_Nhdr *nhdr, const char *data, size_t name_off, size_t desc_off, +static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, + const char *data, size_t name_off, size_t desc_off, struct usdt_note *usdt_note); static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie); @@ -568,8 +573,8 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * const char *usdt_provider, const char *usdt_name, __u64 usdt_cookie, struct usdt_target **out_targets, size_t *out_target_cnt) { - size_t off, name_off, desc_off, seg_cnt = 0, lib_seg_cnt = 0, target_cnt = 0; - struct elf_seg *segs = NULL, *lib_segs = NULL; + size_t off, name_off, desc_off, seg_cnt = 0, vma_seg_cnt = 0, target_cnt = 0; + struct elf_seg *segs = NULL, *vma_segs = NULL; struct usdt_target *targets = NULL, *target; long base_addr = 0; Elf_Scn *notes_scn, *base_scn; @@ -613,8 +618,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * struct elf_seg *seg = NULL; void *tmp; - err = parse_usdt_note(elf, path, base_addr, &nhdr, - data->d_buf, name_off, desc_off, ¬e); + err = parse_usdt_note(elf, path, &nhdr, data->d_buf, name_off, desc_off, ¬e); if (err) goto err_out; @@ -654,30 +658,29 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * usdt_rel_ip += base_addr - note.base_addr; } - if (ehdr.e_type == ET_EXEC) { - /* When attaching uprobes (which what USDTs basically - * are) kernel expects a relative IP to be specified, - * so if we are attaching to an executable ELF binary - * (i.e., not a shared library), we need to calculate - * proper relative IP based on ELF's load address - */ - seg = find_elf_seg(segs, seg_cnt, usdt_abs_ip, false /* relative */); - if (!seg) { - err = -ESRCH; - pr_warn("usdt: failed to find ELF program segment for '%s:%s' in '%s' at IP 0x%lx\n", - usdt_provider, usdt_name, path, usdt_abs_ip); - goto err_out; - } - if (!seg->is_exec) { - err = -ESRCH; - pr_warn("usdt: matched ELF binary '%s' segment [0x%lx, 0x%lx) for '%s:%s' at IP 0x%lx is not executable\n", - path, seg->start, seg->end, usdt_provider, usdt_name, - usdt_abs_ip); - goto err_out; - } + /* When attaching uprobes (which is what USDTs basically are) + * kernel expects file offset to be specified, not a relative + * virtual address, so we need to translate virtual address to + * file offset, for both ET_EXEC and ET_DYN binaries. + */ + seg = find_elf_seg(segs, seg_cnt, usdt_abs_ip); + if (!seg) { + err = -ESRCH; + pr_warn("usdt: failed to find ELF program segment for '%s:%s' in '%s' at IP 0x%lx\n", + usdt_provider, usdt_name, path, usdt_abs_ip); + goto err_out; + } + if (!seg->is_exec) { + err = -ESRCH; + pr_warn("usdt: matched ELF binary '%s' segment [0x%lx, 0x%lx) for '%s:%s' at IP 0x%lx is not executable\n", + path, seg->start, seg->end, usdt_provider, usdt_name, + usdt_abs_ip); + goto err_out; + } + /* translate from virtual address to file offset */ + usdt_rel_ip = usdt_abs_ip - seg->start + seg->offset; - usdt_rel_ip = usdt_abs_ip - (seg->start - seg->offset); - } else if (!man->has_bpf_cookie) { /* ehdr.e_type == ET_DYN */ + if (ehdr.e_type == ET_DYN && !man->has_bpf_cookie) { /* If we don't have BPF cookie support but need to * attach to a shared library, we'll need to know and * record absolute addresses of attach points due to @@ -697,9 +700,9 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * goto err_out; } - /* lib_segs are lazily initialized only if necessary */ - if (lib_seg_cnt == 0) { - err = parse_lib_segs(pid, path, &lib_segs, &lib_seg_cnt); + /* vma_segs are lazily initialized only if necessary */ + if (vma_seg_cnt == 0) { + err = parse_vma_segs(pid, path, &vma_segs, &vma_seg_cnt); if (err) { pr_warn("usdt: failed to get memory segments in PID %d for shared library '%s': %d\n", pid, path, err); @@ -707,7 +710,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * } } - seg = find_elf_seg(lib_segs, lib_seg_cnt, usdt_rel_ip, true /* relative */); + seg = find_vma_seg(vma_segs, vma_seg_cnt, usdt_rel_ip); if (!seg) { err = -ESRCH; pr_warn("usdt: failed to find shared lib memory segment for '%s:%s' in '%s' at relative IP 0x%lx\n", @@ -715,7 +718,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * goto err_out; } - usdt_abs_ip = seg->start + (usdt_rel_ip - seg->offset); + usdt_abs_ip = seg->start - seg->offset + usdt_rel_ip; } pr_debug("usdt: probe for '%s:%s' in %s '%s': addr 0x%lx base 0x%lx (resolved abs_ip 0x%lx rel_ip 0x%lx) args '%s' in segment [0x%lx, 0x%lx) at offset 0x%lx\n", @@ -723,7 +726,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * note.loc_addr, note.base_addr, usdt_abs_ip, usdt_rel_ip, note.args, seg ? seg->start : 0, seg ? seg->end : 0, seg ? seg->offset : 0); - /* Adjust semaphore address to be a relative offset */ + /* Adjust semaphore address to be a file offset */ if (note.sema_addr) { if (!man->has_sema_refcnt) { pr_warn("usdt: kernel doesn't support USDT semaphore refcounting for '%s:%s' in '%s'\n", @@ -732,7 +735,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * goto err_out; } - seg = find_elf_seg(segs, seg_cnt, note.sema_addr, false /* relative */); + seg = find_elf_seg(segs, seg_cnt, note.sema_addr); if (!seg) { err = -ESRCH; pr_warn("usdt: failed to find ELF loadable segment with semaphore of '%s:%s' in '%s' at 0x%lx\n", @@ -747,7 +750,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * goto err_out; } - usdt_sema_off = note.sema_addr - (seg->start - seg->offset); + usdt_sema_off = note.sema_addr - seg->start + seg->offset; pr_debug("usdt: sema for '%s:%s' in %s '%s': addr 0x%lx base 0x%lx (resolved 0x%lx) in segment [0x%lx, 0x%lx] at offset 0x%lx\n", usdt_provider, usdt_name, ehdr.e_type == ET_EXEC ? "exec" : "lib ", @@ -770,7 +773,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * target->rel_ip = usdt_rel_ip; target->sema_off = usdt_sema_off; - /* notes->args references strings from Elf itself, so they can + /* notes.args references strings from Elf itself, so they can * be referenced safely until elf_end() call */ target->spec_str = note.args; @@ -788,7 +791,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * err_out: free(segs); - free(lib_segs); + free(vma_segs); if (err < 0) free(targets); return err; @@ -1089,8 +1092,8 @@ err_out: /* Parse out USDT ELF note from '.note.stapsdt' section. * Logic inspired by perf's code. */ -static int parse_usdt_note(Elf *elf, const char *path, long base_addr, - GElf_Nhdr *nhdr, const char *data, size_t name_off, size_t desc_off, +static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, + const char *data, size_t name_off, size_t desc_off, struct usdt_note *note) { const char *provider, *name, *args; |