summaryrefslogtreecommitdiff
path: root/tools/lib
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-07-11 10:55:49 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-07-11 10:55:49 -0700
commit237f83dfbe668443b5e31c3c7576125871cca674 (patch)
tree11848a8d0aa414a1d3ce2024e181071b1d9dea08 /tools/lib
parent8f6ccf6159aed1f04c6d179f61f6fb2691261e84 (diff)
parent1ff2f0fa450ea4e4f87793d9ed513098ec6e12be (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Some highlights from this development cycle: 1) Big refactoring of ipv6 route and neigh handling to support nexthop objects configurable as units from userspace. From David Ahern. 2) Convert explored_states in BPF verifier into a hash table, significantly decreased state held for programs with bpf2bpf calls, from Alexei Starovoitov. 3) Implement bpf_send_signal() helper, from Yonghong Song. 4) Various classifier enhancements to mvpp2 driver, from Maxime Chevallier. 5) Add aRFS support to hns3 driver, from Jian Shen. 6) Fix use after free in inet frags by allocating fqdirs dynamically and reworking how rhashtable dismantle occurs, from Eric Dumazet. 7) Add act_ctinfo packet classifier action, from Kevin Darbyshire-Bryant. 8) Add TFO key backup infrastructure, from Jason Baron. 9) Remove several old and unused ISDN drivers, from Arnd Bergmann. 10) Add devlink notifications for flash update status to mlxsw driver, from Jiri Pirko. 11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski. 12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes. 13) Various enhancements to ipv6 flow label handling, from Eric Dumazet and Willem de Bruijn. 14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van der Merwe, and others. 15) Various improvements to axienet driver including converting it to phylink, from Robert Hancock. 16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean. 17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana Radulescu. 18) Add devlink health reporting to mlx5, from Moshe Shemesh. 19) Convert stmmac over to phylink, from Jose Abreu. 20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from Shalom Toledo. 21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera. 22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel. 23) Track spill/fill of constants in BPF verifier, from Alexei Starovoitov. 24) Support bounded loops in BPF, from Alexei Starovoitov. 25) Various page_pool API fixes and improvements, from Jesper Dangaard Brouer. 26) Just like ipv4, support ref-countless ipv6 route handling. From Wei Wang. 27) Support VLAN offloading in aquantia driver, from Igor Russkikh. 28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy. 29) Add flower GRE encap/decap support to nfp driver, from Pieter Jansen van Vuuren. 30) Protect against stack overflow when using act_mirred, from John Hurley. 31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen. 32) Use page_pool API in netsec driver, Ilias Apalodimas. 33) Add Google gve network driver, from Catherine Sullivan. 34) More indirect call avoidance, from Paolo Abeni. 35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan. 36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek. 37) Add MPLS manipulation actions to TC, from John Hurley. 38) Add sending a packet to connection tracking from TC actions, and then allow flower classifier matching on conntrack state. From Paul Blakey. 39) Netfilter hw offload support, from Pablo Neira Ayuso" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits) net/mlx5e: Return in default case statement in tx_post_resync_params mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync(). net: dsa: add support for BRIDGE_MROUTER attribute pkt_sched: Include const.h net: netsec: remove static declaration for netsec_set_tx_de() net: netsec: remove superfluous if statement netfilter: nf_tables: add hardware offload support net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload net: flow_offload: add flow_block_cb_is_busy() and use it net: sched: remove tcf block API drivers: net: use flow block API net: sched: use flow block API net: flow_offload: add flow_block_cb_{priv, incref, decref}() net: flow_offload: add list handling functions net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free() net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_* net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND net: flow_offload: add flow_block_cb_setup_simple() net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC ...
Diffstat (limited to 'tools/lib')
-rw-r--r--tools/lib/bpf/Build4
-rw-r--r--tools/lib/bpf/Makefile12
-rw-r--r--tools/lib/bpf/README.rst3
-rw-r--r--tools/lib/bpf/bpf.c8
-rw-r--r--tools/lib/bpf/bpf.h1
-rw-r--r--tools/lib/bpf/bpf_prog_linfo.c5
-rw-r--r--tools/lib/bpf/btf.c332
-rw-r--r--tools/lib/bpf/btf.h20
-rw-r--r--tools/lib/bpf/btf_dump.c1333
-rw-r--r--tools/lib/bpf/hashmap.c229
-rw-r--r--tools/lib/bpf/hashmap.h173
-rw-r--r--tools/lib/bpf/libbpf.c1855
-rw-r--r--tools/lib/bpf/libbpf.h155
-rw-r--r--tools/lib/bpf/libbpf.map20
-rw-r--r--tools/lib/bpf/libbpf_internal.h9
-rw-r--r--tools/lib/bpf/libbpf_probes.c1
-rw-r--r--tools/lib/bpf/str_error.c2
-rw-r--r--tools/lib/bpf/xsk.c116
-rw-r--r--tools/lib/bpf/xsk.h2
19 files changed, 3709 insertions, 571 deletions
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index ee9d5362f35b..e3962cfbc9a6 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1,3 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
+ netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \
+ btf_dump.o
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index f91639bf5650..9312066a1ae3 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -3,7 +3,7 @@
BPF_VERSION = 0
BPF_PATCHLEVEL = 0
-BPF_EXTRAVERSION = 3
+BPF_EXTRAVERSION = 4
MAKEFLAGS += --no-print-directory
@@ -204,6 +204,16 @@ check_abi: $(OUTPUT)libbpf.so
"versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \
"Please make sure all LIBBPF_API symbols are" \
"versioned in $(VERSION_SCRIPT)." >&2; \
+ readelf -s --wide $(OUTPUT)libbpf-in.o | \
+ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}'| \
+ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \
+ readelf -s --wide $(OUTPUT)libbpf.so | \
+ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \
+ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \
+ diff -u $(OUTPUT)libbpf_global_syms.tmp \
+ $(OUTPUT)libbpf_versioned_syms.tmp; \
+ rm $(OUTPUT)libbpf_global_syms.tmp \
+ $(OUTPUT)libbpf_versioned_syms.tmp; \
exit 1; \
fi
diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst
index cef7b77eab69..8928f7787f2d 100644
--- a/tools/lib/bpf/README.rst
+++ b/tools/lib/bpf/README.rst
@@ -9,7 +9,8 @@ described here. It's recommended to follow these conventions whenever a
new function or type is added to keep libbpf API clean and consistent.
All types and functions provided by libbpf API should have one of the
-following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``.
+following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``,
+``perf_buffer_``.
System call wrappers
--------------------
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index c4a48086dc9a..c7d7993c44bb 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -26,10 +26,11 @@
#include <memory.h>
#include <unistd.h>
#include <asm/unistd.h>
+#include <errno.h>
#include <linux/bpf.h>
#include "bpf.h"
#include "libbpf.h"
-#include <errno.h>
+#include "libbpf_internal.h"
/*
* When building perf, unistd.h is overridden. __NR_bpf is
@@ -53,10 +54,6 @@
# endif
#endif
-#ifndef min
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#endif
-
static inline __u64 ptr_to_u64(const void *ptr)
{
return (__u64) (unsigned long) ptr;
@@ -256,6 +253,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
if (load_attr->name)
memcpy(attr.prog_name, load_attr->name,
min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1));
+ attr.prog_flags = load_attr->prog_flags;
fd = sys_bpf_prog_load(&attr, sizeof(attr));
if (fd >= 0)
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9593fec75652..ff42ca043dc8 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -87,6 +87,7 @@ struct bpf_load_program_attr {
const void *line_info;
__u32 line_info_cnt;
__u32 log_level;
+ __u32 prog_flags;
};
/* Flags to direct loading requirements */
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index 6978314ea7f6..8c67561c93b0 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -6,10 +6,7 @@
#include <linux/err.h>
#include <linux/bpf.h>
#include "libbpf.h"
-
-#ifndef min
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#endif
+#include "libbpf_internal.h"
struct bpf_prog_linfo {
void *raw_linfo;
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 03348c4d6bd4..467224feb43b 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -4,17 +4,17 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <fcntl.h>
#include <unistd.h>
#include <errno.h>
#include <linux/err.h>
#include <linux/btf.h>
+#include <gelf.h>
#include "btf.h"
#include "bpf.h"
#include "libbpf.h"
#include "libbpf_internal.h"
-
-#define max(a, b) ((a) > (b) ? (a) : (b))
-#define min(a, b) ((a) < (b) ? (a) : (b))
+#include "hashmap.h"
#define BTF_MAX_NR_TYPES 0x7fffffff
#define BTF_MAX_STR_OFFSET 0x7fffffff
@@ -417,6 +417,132 @@ done:
return btf;
}
+static bool btf_check_endianness(const GElf_Ehdr *ehdr)
+{
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ return ehdr->e_ident[EI_DATA] == ELFDATA2LSB;
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+ return ehdr->e_ident[EI_DATA] == ELFDATA2MSB;
+#else
+# error "Unrecognized __BYTE_ORDER__"
+#endif
+}
+
+struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
+{
+ Elf_Data *btf_data = NULL, *btf_ext_data = NULL;
+ int err = 0, fd = -1, idx = 0;
+ struct btf *btf = NULL;
+ Elf_Scn *scn = NULL;
+ Elf *elf = NULL;
+ GElf_Ehdr ehdr;
+
+ if (elf_version(EV_CURRENT) == EV_NONE) {
+ pr_warning("failed to init libelf for %s\n", path);
+ return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
+ }
+
+ fd = open(path, O_RDONLY);
+ if (fd < 0) {
+ err = -errno;
+ pr_warning("failed to open %s: %s\n", path, strerror(errno));
+ return ERR_PTR(err);
+ }
+
+ err = -LIBBPF_ERRNO__FORMAT;
+
+ elf = elf_begin(fd, ELF_C_READ, NULL);
+ if (!elf) {
+ pr_warning("failed to open %s as ELF file\n", path);
+ goto done;
+ }
+ if (!gelf_getehdr(elf, &ehdr)) {
+ pr_warning("failed to get EHDR from %s\n", path);
+ goto done;
+ }
+ if (!btf_check_endianness(&ehdr)) {
+ pr_warning("non-native ELF endianness is not supported\n");
+ goto done;
+ }
+ if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) {
+ pr_warning("failed to get e_shstrndx from %s\n", path);
+ goto done;
+ }
+
+ while ((scn = elf_nextscn(elf, scn)) != NULL) {
+ GElf_Shdr sh;
+ char *name;
+
+ idx++;
+ if (gelf_getshdr(scn, &sh) != &sh) {
+ pr_warning("failed to get section(%d) header from %s\n",
+ idx, path);
+ goto done;
+ }
+ name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
+ if (!name) {
+ pr_warning("failed to get section(%d) name from %s\n",
+ idx, path);
+ goto done;
+ }
+ if (strcmp(name, BTF_ELF_SEC) == 0) {
+ btf_data = elf_getdata(scn, 0);
+ if (!btf_data) {
+ pr_warning("failed to get section(%d, %s) data from %s\n",
+ idx, name, path);
+ goto done;
+ }
+ continue;
+ } else if (btf_ext && strcmp(name, BTF_EXT_ELF_SEC) == 0) {
+ btf_ext_data = elf_getdata(scn, 0);
+ if (!btf_ext_data) {
+ pr_warning("failed to get section(%d, %s) data from %s\n",
+ idx, name, path);
+ goto done;
+ }
+ continue;
+ }
+ }
+
+ err = 0;
+
+ if (!btf_data) {
+ err = -ENOENT;
+ goto done;
+ }
+ btf = btf__new(btf_data->d_buf, btf_data->d_size);
+ if (IS_ERR(btf))
+ goto done;
+
+ if (btf_ext && btf_ext_data) {
+ *btf_ext = btf_ext__new(btf_ext_data->d_buf,
+ btf_ext_data->d_size);
+ if (IS_ERR(*btf_ext))
+ goto done;
+ } else if (btf_ext) {
+ *btf_ext = NULL;
+ }
+done:
+ if (elf)
+ elf_end(elf);
+ close(fd);
+
+ if (err)
+ return ERR_PTR(err);
+ /*
+ * btf is always parsed before btf_ext, so no need to clean up
+ * btf_ext, if btf loading failed
+ */
+ if (IS_ERR(btf))
+ return btf;
+ if (btf_ext && IS_ERR(*btf_ext)) {
+ btf__free(btf);
+ err = PTR_ERR(*btf_ext);
+ return ERR_PTR(err);
+ }
+ return btf;
+}
+
static int compare_vsi_off(const void *_a, const void *_b)
{
const struct btf_var_secinfo *a = _a;
@@ -1165,16 +1291,9 @@ done:
return err;
}
-#define BTF_DEDUP_TABLE_DEFAULT_SIZE (1 << 14)
-#define BTF_DEDUP_TABLE_MAX_SIZE_LOG 31
#define BTF_UNPROCESSED_ID ((__u32)-1)
#define BTF_IN_PROGRESS_ID ((__u32)-2)
-struct btf_dedup_node {
- struct btf_dedup_node *next;
- __u32 type_id;
-};
-
struct btf_dedup {
/* .BTF section to be deduped in-place */
struct btf *btf;
@@ -1190,7 +1309,7 @@ struct btf_dedup {
* candidates, which is fine because we rely on subsequent
* btf_xxx_equal() checks to authoritatively verify type equality.
*/
- struct btf_dedup_node **dedup_table;
+ struct hashmap *dedup_table;
/* Canonical types map */
__u32 *map;
/* Hypothetical mapping, used during type graph equivalence checks */
@@ -1215,30 +1334,18 @@ struct btf_str_ptrs {
__u32 cap;
};
-static inline __u32 hash_combine(__u32 h, __u32 value)
+static long hash_combine(long h, long value)
{
-/* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
-#define GOLDEN_RATIO_PRIME 0x9e370001UL
- return h * 37 + value * GOLDEN_RATIO_PRIME;
-#undef GOLDEN_RATIO_PRIME
+ return h * 31 + value;
}
-#define for_each_dedup_cand(d, hash, node) \
- for (node = d->dedup_table[hash & (d->opts.dedup_table_size - 1)]; \
- node; \
- node = node->next)
+#define for_each_dedup_cand(d, node, hash) \
+ hashmap__for_each_key_entry(d->dedup_table, node, (void *)hash)
-static int btf_dedup_table_add(struct btf_dedup *d, __u32 hash, __u32 type_id)
+static int btf_dedup_table_add(struct btf_dedup *d, long hash, __u32 type_id)
{
- struct btf_dedup_node *node = malloc(sizeof(struct btf_dedup_node));
- int bucket = hash & (d->opts.dedup_table_size - 1);
-
- if (!node)
- return -ENOMEM;
- node->type_id = type_id;
- node->next = d->dedup_table[bucket];
- d->dedup_table[bucket] = node;
- return 0;
+ return hashmap__append(d->dedup_table,
+ (void *)hash, (void *)(long)type_id);
}
static int btf_dedup_hypot_map_add(struct btf_dedup *d,
@@ -1267,36 +1374,10 @@ static void btf_dedup_clear_hypot_map(struct btf_dedup *d)
d->hypot_cnt = 0;
}
-static void btf_dedup_table_free(struct btf_dedup *d)
-{
- struct btf_dedup_node *head, *tmp;
- int i;
-
- if (!d->dedup_table)
- return;
-
- for (i = 0; i < d->opts.dedup_table_size; i++) {
- while (d->dedup_table[i]) {
- tmp = d->dedup_table[i];
- d->dedup_table[i] = tmp->next;
- free(tmp);
- }
-
- head = d->dedup_table[i];
- while (head) {
- tmp = head;
- head = head->next;
- free(tmp);
- }
- }
-
- free(d->dedup_table);
- d->dedup_table = NULL;
-}
-
static void btf_dedup_free(struct btf_dedup *d)
{
- btf_dedup_table_free(d);
+ hashmap__free(d->dedup_table);
+ d->dedup_table = NULL;
free(d->map);
d->map = NULL;
@@ -1310,40 +1391,43 @@ static void btf_dedup_free(struct btf_dedup *d)
free(d);
}
-/* Find closest power of two >= to size, capped at 2^max_size_log */
-static __u32 roundup_pow2_max(__u32 size, int max_size_log)
+static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx)
{
- int i;
+ return (size_t)key;
+}
- for (i = 0; i < max_size_log && (1U << i) < size; i++)
- ;
- return 1U << i;
+static size_t btf_dedup_collision_hash_fn(const void *key, void *ctx)
+{
+ return 0;
}
+static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx)
+{
+ return k1 == k2;
+}
static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
const struct btf_dedup_opts *opts)
{
struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup));
+ hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn;
int i, err = 0;
- __u32 sz;
if (!d)
return ERR_PTR(-ENOMEM);
d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds;
- sz = opts && opts->dedup_table_size ? opts->dedup_table_size
- : BTF_DEDUP_TABLE_DEFAULT_SIZE;
- sz = roundup_pow2_max(sz, BTF_DEDUP_TABLE_MAX_SIZE_LOG);
- d->opts.dedup_table_size = sz;
+ /* dedup_table_size is now used only to force collisions in tests */
+ if (opts && opts->dedup_table_size == 1)
+ hash_fn = btf_dedup_collision_hash_fn;
d->btf = btf;
d->btf_ext = btf_ext;
- d->dedup_table = calloc(d->opts.dedup_table_size,
- sizeof(struct btf_dedup_node *));
- if (!d->dedup_table) {
- err = -ENOMEM;
+ d->dedup_table = hashmap__new(hash_fn, btf_dedup_equal_fn, NULL);
+ if (IS_ERR(d->dedup_table)) {
+ err = PTR_ERR(d->dedup_table);
+ d->dedup_table = NULL;
goto done;
}
@@ -1662,9 +1746,9 @@ done:
return err;
}
-static __u32 btf_hash_common(struct btf_type *t)
+static long btf_hash_common(struct btf_type *t)
{
- __u32 h;
+ long h;
h = hash_combine(0, t->name_off);
h = hash_combine(h, t->info);
@@ -1680,10 +1764,10 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2)
}
/* Calculate type signature hash of INT. */
-static __u32 btf_hash_int(struct btf_type *t)
+static long btf_hash_int(struct btf_type *t)
{
__u32 info = *(__u32 *)(t + 1);
- __u32 h;
+ long h;
h = btf_hash_common(t);
h = hash_combine(h, info);
@@ -1703,9 +1787,9 @@ static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
}
/* Calculate type signature hash of ENUM. */
-static __u32 btf_hash_enum(struct btf_type *t)
+static long btf_hash_enum(struct btf_type *t)
{
- __u32 h;
+ long h;
/* don't hash vlen and enum members to support enum fwd resolving */
h = hash_combine(0, t->name_off);
@@ -1757,11 +1841,11 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
* as referenced type IDs equivalence is established separately during type
* graph equivalence check algorithm.
*/
-static __u32 btf_hash_struct(struct btf_type *t)
+static long btf_hash_struct(struct btf_type *t)
{
struct btf_member *member = (struct btf_member *)(t + 1);
__u32 vlen = BTF_INFO_VLEN(t->info);
- __u32 h = btf_hash_common(t);
+ long h = btf_hash_common(t);
int i;
for (i = 0; i < vlen; i++) {
@@ -1804,10 +1888,10 @@ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2)
* under assumption that they were already resolved to canonical type IDs and
* are not going to change.
*/
-static __u32 btf_hash_array(struct btf_type *t)
+static long btf_hash_array(struct btf_type *t)
{
struct btf_array *info = (struct btf_array *)(t + 1);
- __u32 h = btf_hash_common(t);
+ long h = btf_hash_common(t);
h = hash_combine(h, info->type);
h = hash_combine(h, info->index_type);
@@ -1858,11 +1942,11 @@ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2)
* under assumption that they were already resolved to canonical type IDs and
* are not going to change.
*/
-static inline __u32 btf_hash_fnproto(struct btf_type *t)
+static long btf_hash_fnproto(struct btf_type *t)
{
struct btf_param *member = (struct btf_param *)(t + 1);
__u16 vlen = BTF_INFO_VLEN(t->info);
- __u32 h = btf_hash_common(t);
+ long h = btf_hash_common(t);
int i;
for (i = 0; i < vlen; i++) {
@@ -1880,7 +1964,7 @@ static inline __u32 btf_hash_fnproto(struct btf_type *t)
* This function is called during reference types deduplication to compare
* FUNC_PROTO to potential canonical representative.
*/
-static inline bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
+static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
{
struct btf_param *m1, *m2;
__u16 vlen;
@@ -1906,7 +1990,7 @@ static inline bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
* IDs. This check is performed during type graph equivalence check and
* referenced types equivalence is checked separately.
*/
-static inline bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
+static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
{
struct btf_param *m1, *m2;
__u16 vlen;
@@ -1937,11 +2021,12 @@ static inline bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
{
struct btf_type *t = d->btf->types[type_id];
+ struct hashmap_entry *hash_entry;
struct btf_type *cand;
- struct btf_dedup_node *cand_node;
/* if we don't find equivalent type, then we are canonical */
__u32 new_id = type_id;
- __u32 h;
+ __u32 cand_id;
+ long h;
switch (BTF_INFO_KIND(t->info)) {
case BTF_KIND_CONST:
@@ -1960,10 +2045,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
case BTF_KIND_INT:
h = btf_hash_int(t);
- for_each_dedup_cand(d, h, cand_node) {
- cand = d->btf->types[cand_node->type_id];
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
if (btf_equal_int(t, cand)) {
- new_id = cand_node->type_id;
+ new_id = cand_id;
break;
}
}
@@ -1971,10 +2057,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
case BTF_KIND_ENUM:
h = btf_hash_enum(t);
- for_each_dedup_cand(d, h, cand_node) {
- cand = d->btf->types[cand_node->type_id];
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
if (btf_equal_enum(t, cand)) {
- new_id = cand_node->type_id;
+ new_id = cand_id;
break;
}
if (d->opts.dont_resolve_fwds)
@@ -1982,21 +2069,22 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
if (btf_compat_enum(t, cand)) {
if (btf_is_enum_fwd(t)) {
/* resolve fwd to full enum */
- new_id = cand_node->type_id;
+ new_id = cand_id;
break;
}
/* resolve canonical enum fwd to full enum */
- d->map[cand_node->type_id] = type_id;
+ d->map[cand_id] = type_id;
}
}
break;
case BTF_KIND_FWD:
h = btf_hash_common(t);
- for_each_dedup_cand(d, h, cand_node) {
- cand = d->btf->types[cand_node->type_id];
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
if (btf_equal_common(t, cand)) {
- new_id = cand_node->type_id;
+ new_id = cand_id;
break;
}
}
@@ -2397,12 +2485,12 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
*/
static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
{
- struct btf_dedup_node *cand_node;
struct btf_type *cand_type, *t;
+ struct hashmap_entry *hash_entry;
/* if we don't find equivalent type, then we are canonical */
__u32 new_id = type_id;
__u16 kind;
- __u32 h;
+ long h;
/* already deduped or is in process of deduping (loop detected) */
if (d->map[type_id] <= BTF_MAX_NR_TYPES)
@@ -2415,7 +2503,8 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
return 0;
h = btf_hash_struct(t);
- for_each_dedup_cand(d, h, cand_node) {
+ for_each_dedup_cand(d, hash_entry, h) {
+ __u32 cand_id = (__u32)(long)hash_entry->value;
int eq;
/*
@@ -2428,17 +2517,17 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
* creating a loop (FWD -> STRUCT and STRUCT -> FWD), because
* FWD and compatible STRUCT/UNION are considered equivalent.
*/
- cand_type = d->btf->types[cand_node->type_id];
+ cand_type = d->btf->types[cand_id];
if (!btf_shallow_equal_struct(t, cand_type))
continue;
btf_dedup_clear_hypot_map(d);
- eq = btf_dedup_is_equiv(d, type_id, cand_node->type_id);
+ eq = btf_dedup_is_equiv(d, type_id, cand_id);
if (eq < 0)
return eq;
if (!eq)
continue;
- new_id = cand_node->type_id;
+ new_id = cand_id;
btf_dedup_merge_hypot_map(d);
break;
}
@@ -2488,12 +2577,12 @@ static int btf_dedup_struct_types(struct btf_dedup *d)
*/
static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
{
- struct btf_dedup_node *cand_node;
+ struct hashmap_entry *hash_entry;
+ __u32 new_id = type_id, cand_id;
struct btf_type *t, *cand;
/* if we don't find equivalent type, then we are representative type */
- __u32 new_id = type_id;
int ref_type_id;
- __u32 h;
+ long h;
if (d->map[type_id] == BTF_IN_PROGRESS_ID)
return -ELOOP;
@@ -2516,10 +2605,11 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
t->type = ref_type_id;
h = btf_hash_common(t);
- for_each_dedup_cand(d, h, cand_node) {
- cand = d->btf->types[cand_node->type_id];
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
if (btf_equal_common(t, cand)) {
- new_id = cand_node->type_id;
+ new_id = cand_id;
break;
}
}
@@ -2539,10 +2629,11 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
info->index_type = ref_type_id;
h = btf_hash_array(t);
- for_each_dedup_cand(d, h, cand_node) {
- cand = d->btf->types[cand_node->type_id];
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
if (btf_equal_array(t, cand)) {
- new_id = cand_node->type_id;
+ new_id = cand_id;
break;
}
}
@@ -2570,10 +2661,11 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
}
h = btf_hash_fnproto(t);
- for_each_dedup_cand(d, h, cand_node) {
- cand = d->btf->types[cand_node->type_id];
+ for_each_dedup_cand(d, hash_entry, h) {
+ cand_id = (__u32)(long)hash_entry->value;
+ cand = d->btf->types[cand_id];
if (btf_equal_fnproto(t, cand)) {
- new_id = cand_node->type_id;
+ new_id = cand_id;
break;
}
}
@@ -2600,7 +2692,9 @@ static int btf_dedup_ref_types(struct btf_dedup *d)
if (err < 0)
return err;
}
- btf_dedup_table_free(d);
+ /* we won't need d->dedup_table anymore */
+ hashmap__free(d->dedup_table);
+ d->dedup_table = NULL;
return 0;
}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index c7b399e81fce..88a52ae56fc6 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -4,6 +4,7 @@
#ifndef __LIBBPF_BTF_H
#define __LIBBPF_BTF_H
+#include <stdarg.h>
#include <linux/types.h>
#ifdef __cplusplus
@@ -16,6 +17,7 @@ extern "C" {
#define BTF_ELF_SEC ".BTF"
#define BTF_EXT_ELF_SEC ".BTF.ext"
+#define MAPS_ELF_SEC ".maps"
struct btf;
struct btf_ext;
@@ -59,6 +61,8 @@ struct btf_ext_header {
LIBBPF_API void btf__free(struct btf *btf);
LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size);
+LIBBPF_API struct btf *btf__parse_elf(const char *path,
+ struct btf_ext **btf_ext);
LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
LIBBPF_API int btf__load(struct btf *btf);
LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
@@ -100,6 +104,22 @@ struct btf_dedup_opts {
LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
const struct btf_dedup_opts *opts);
+struct btf_dump;
+
+struct btf_dump_opts {
+ void *ctx;
+};
+
+typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args);
+
+LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf,
+ const struct btf_ext *btf_ext,
+ const struct btf_dump_opts *opts,
+ btf_dump_printf_fn_t printf_fn);
+LIBBPF_API void btf_dump__free(struct btf_dump *d);
+
+LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
+
#ifdef __cplusplus
} /* extern "C" */
#endif
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
new file mode 100644
index 000000000000..7065bb5b2752
--- /dev/null
+++ b/tools/lib/bpf/btf_dump.c
@@ -0,0 +1,1333 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * BTF-to-C type converter.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/err.h>
+#include <linux/btf.h>
+#include "btf.h"
+#include "hashmap.h"
+#include "libbpf.h"
+#include "libbpf_internal.h"
+
+static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t";
+static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1;
+
+static const char *pfx(int lvl)
+{
+ return lvl >= PREFIX_CNT ? PREFIXES : &PREFIXES[PREFIX_CNT - lvl];
+}
+
+enum btf_dump_type_order_state {
+ NOT_ORDERED,
+ ORDERING,
+ ORDERED,
+};
+
+enum btf_dump_type_emit_state {
+ NOT_EMITTED,
+ EMITTING,
+ EMITTED,
+};
+
+/* per-type auxiliary state */
+struct btf_dump_type_aux_state {
+ /* topological sorting state */
+ enum btf_dump_type_order_state order_state: 2;
+ /* emitting state used to determine the need for forward declaration */
+ enum btf_dump_type_emit_state emit_state: 2;
+ /* whether forward declaration was already emitted */
+ __u8 fwd_emitted: 1;
+ /* whether unique non-duplicate name was already assigned */
+ __u8 name_resolved: 1;
+};
+
+struct btf_dump {
+ const struct btf *btf;
+ const struct btf_ext *btf_ext;
+ btf_dump_printf_fn_t printf_fn;
+ struct btf_dump_opts opts;
+
+ /* per-type auxiliary state */
+ struct btf_dump_type_aux_state *type_states;
+ /* per-type optional cached unique name, must be freed, if present */
+ const char **cached_names;
+
+ /* topo-sorted list of dependent type definitions */
+ __u32 *emit_queue;
+ int emit_queue_cap;
+ int emit_queue_cnt;
+
+ /*
+ * stack of type declarations (e.g., chain of modifiers, arrays,
+ * funcs, etc)
+ */
+ __u32 *decl_stack;
+ int decl_stack_cap;
+ int decl_stack_cnt;
+
+ /* maps struct/union/enum name to a number of name occurrences */
+ struct hashmap *type_names;
+ /*
+ * maps typedef identifiers and enum value names to a number of such
+ * name occurrences
+ */
+ struct hashmap *ident_names;
+};
+
+static size_t str_hash_fn(const void *key, void *ctx)
+{
+ const char *s = key;
+ size_t h = 0;
+
+ while (*s) {
+ h = h * 31 + *s;
+ s++;
+ }
+ return h;
+}
+
+static bool str_equal_fn(const void *a, const void *b, void *ctx)
+{
+ return strcmp(a, b) == 0;
+}
+
+static __u16 btf_kind_of(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info);
+}
+
+static __u16 btf_vlen_of(const struct btf_type *t)
+{
+ return BTF_INFO_VLEN(t->info);
+}
+
+static bool btf_kflag_of(const struct btf_type *t)
+{
+ return BTF_INFO_KFLAG(t->info);
+}
+
+static const char *btf_name_of(const struct btf_dump *d, __u32 name_off)
+{
+ return btf__name_by_offset(d->btf, name_off);
+}
+
+static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ d->printf_fn(d->opts.ctx, fmt, args);
+ va_end(args);
+}
+
+struct btf_dump *btf_dump__new(const struct btf *btf,
+ const struct btf_ext *btf_ext,
+ const struct btf_dump_opts *opts,
+ btf_dump_printf_fn_t printf_fn)
+{
+ struct btf_dump *d;
+ int err;
+
+ d = calloc(1, sizeof(struct btf_dump));
+ if (!d)
+ return ERR_PTR(-ENOMEM);
+
+ d->btf = btf;
+ d->btf_ext = btf_ext;
+ d->printf_fn = printf_fn;
+ d->opts.ctx = opts ? opts->ctx : NULL;
+
+ d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL);
+ if (IS_ERR(d->type_names)) {
+ err = PTR_ERR(d->type_names);
+ d->type_names = NULL;
+ btf_dump__free(d);
+ return ERR_PTR(err);
+ }
+ d->ident_names = hashmap__new(str_hash_fn, str_equal_fn, NULL);
+ if (IS_ERR(d->ident_names)) {
+ err = PTR_ERR(d->ident_names);
+ d->ident_names = NULL;
+ btf_dump__free(d);
+ return ERR_PTR(err);
+ }
+
+ return d;
+}
+
+void btf_dump__free(struct btf_dump *d)
+{
+ int i, cnt;
+
+ if (!d)
+ return;
+
+ free(d->type_states);
+ if (d->cached_names) {
+ /* any set cached name is owned by us and should be freed */
+ for (i = 0, cnt = btf__get_nr_types(d->btf); i <= cnt; i++) {
+ if (d->cached_names[i])
+ free((void *)d->cached_names[i]);
+ }
+ }
+ free(d->cached_names);
+ free(d->emit_queue);
+ free(d->decl_stack);
+ hashmap__free(d->type_names);
+ hashmap__free(d->ident_names);
+
+ free(d);
+}
+
+static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr);
+static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id);
+
+/*
+ * Dump BTF type in a compilable C syntax, including all the necessary
+ * dependent types, necessary for compilation. If some of the dependent types
+ * were already emitted as part of previous btf_dump__dump_type() invocation
+ * for another type, they won't be emitted again. This API allows callers to
+ * filter out BTF types according to user-defined criterias and emitted only
+ * minimal subset of types, necessary to compile everything. Full struct/union
+ * definitions will still be emitted, even if the only usage is through
+ * pointer and could be satisfied with just a forward declaration.
+ *
+ * Dumping is done in two high-level passes:
+ * 1. Topologically sort type definitions to satisfy C rules of compilation.
+ * 2. Emit type definitions in C syntax.
+ *
+ * Returns 0 on success; <0, otherwise.
+ */
+int btf_dump__dump_type(struct btf_dump *d, __u32 id)
+{
+ int err, i;
+
+ if (id > btf__get_nr_types(d->btf))
+ return -EINVAL;
+
+ /* type states are lazily allocated, as they might not be needed */
+ if (!d->type_states) {
+ d->type_states = calloc(1 + btf__get_nr_types(d->btf),
+ sizeof(d->type_states[0]));
+ if (!d->type_states)
+ return -ENOMEM;
+ d->cached_names = calloc(1 + btf__get_nr_types(d->btf),
+ sizeof(d->cached_names[0]));
+ if (!d->cached_names)
+ return -ENOMEM;
+
+ /* VOID is special */
+ d->type_states[0].order_state = ORDERED;
+ d->type_states[0].emit_state = EMITTED;
+ }
+
+ d->emit_queue_cnt = 0;
+ err = btf_dump_order_type(d, id, false);
+ if (err < 0)
+ return err;
+
+ for (i = 0; i < d->emit_queue_cnt; i++)
+ btf_dump_emit_type(d, d->emit_queue[i], 0 /*top-level*/);
+
+ return 0;
+}
+
+static int btf_dump_add_emit_queue_id(struct btf_dump *d, __u32 id)
+{
+ __u32 *new_queue;
+ size_t new_cap;
+
+ if (d->emit_queue_cnt >= d->emit_queue_cap) {
+ new_cap = max(16, d->emit_queue_cap * 3 / 2);
+ new_queue = realloc(d->emit_queue,
+ new_cap * sizeof(new_queue[0]));
+ if (!new_queue)
+ return -ENOMEM;
+ d->emit_queue = new_queue;
+ d->emit_queue_cap = new_cap;
+ }
+
+ d->emit_queue[d->emit_queue_cnt++] = id;
+ return 0;
+}
+
+/*
+ * Determine order of emitting dependent types and specified type to satisfy
+ * C compilation rules. This is done through topological sorting with an
+ * additional complication which comes from C rules. The main idea for C is
+ * that if some type is "embedded" into a struct/union, it's size needs to be
+ * known at the time of definition of containing type. E.g., for:
+ *
+ * struct A {};
+ * struct B { struct A x; }
+ *
+ * struct A *HAS* to be defined before struct B, because it's "embedded",
+ * i.e., it is part of struct B layout. But in the following case:
+ *
+ * struct A;
+ * struct B { struct A *x; }
+ * struct A {};
+ *
+ * it's enough to just have a forward declaration of struct A at the time of
+ * struct B definition, as struct B has a pointer to struct A, so the size of
+ * field x is known without knowing struct A size: it's sizeof(void *).
+ *
+ * Unfortunately, there are some trickier cases we need to handle, e.g.:
+ *
+ * struct A {}; // if this was forward-declaration: compilation error
+ * struct B {
+ * struct { // anonymous struct
+ * struct A y;
+ * } *x;
+ * };
+ *
+ * In this case, struct B's field x is a pointer, so it's size is known
+ * regardless of the size of (anonymous) struct it points to. But because this
+ * struct is anonymous and thus defined inline inside struct B, *and* it
+ * embeds struct A, compiler requires full definition of struct A to be known
+ * before struct B can be defined. This creates a transitive dependency
+ * between struct A and struct B. If struct A was forward-declared before
+ * struct B definition and fully defined after struct B definition, that would
+ * trigger compilation error.
+ *
+ * All this means that while we are doing topological sorting on BTF type
+ * graph, we need to determine relationships between different types (graph
+ * nodes):
+ * - weak link (relationship) between X and Y, if Y *CAN* be
+ * forward-declared at the point of X definition;
+ * - strong link, if Y *HAS* to be fully-defined before X can be defined.
+ *
+ * The rule is as follows. Given a chain of BTF types from X to Y, if there is
+ * BTF_KIND_PTR type in the chain and at least one non-anonymous type
+ * Z (excluding X, including Y), then link is weak. Otherwise, it's strong.
+ * Weak/strong relationship is determined recursively during DFS traversal and
+ * is returned as a result from btf_dump_order_type().
+ *
+ * btf_dump_order_type() is trying to avoid unnecessary forward declarations,
+ * but it is not guaranteeing that no extraneous forward declarations will be
+ * emitted.
+ *
+ * To avoid extra work, algorithm marks some of BTF types as ORDERED, when
+ * it's done with them, but not for all (e.g., VOLATILE, CONST, RESTRICT,
+ * ARRAY, FUNC_PROTO), as weak/strong semantics for those depends on the
+ * entire graph path, so depending where from one came to that BTF type, it
+ * might cause weak or strong ordering. For types like STRUCT/UNION/INT/ENUM,
+ * once they are processed, there is no need to do it again, so they are
+ * marked as ORDERED. We can mark PTR as ORDERED as well, as it semi-forces
+ * weak link, unless subsequent referenced STRUCT/UNION/ENUM is anonymous. But
+ * in any case, once those are processed, no need to do it again, as the
+ * result won't change.
+ *
+ * Returns:
+ * - 1, if type is part of strong link (so there is strong topological
+ * ordering requirements);
+ * - 0, if type is part of weak link (so can be satisfied through forward
+ * declaration);
+ * - <0, on error (e.g., unsatisfiable type loop detected).
+ */
+static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
+{
+ /*
+ * Order state is used to detect strong link cycles, but only for BTF
+ * kinds that are or could be an independent definition (i.e.,
+ * stand-alone fwd decl, enum, typedef, struct, union). Ptrs, arrays,
+ * func_protos, modifiers are just means to get to these definitions.
+ * Int/void don't need definitions, they are assumed to be always
+ * properly defined. We also ignore datasec, var, and funcs for now.
+ * So for all non-defining kinds, we never even set ordering state,
+ * for defining kinds we set ORDERING and subsequently ORDERED if it
+ * forms a strong link.
+ */
+ struct btf_dump_type_aux_state *tstate = &d->type_states[id];
+ const struct btf_type *t;
+ __u16 kind, vlen;
+ int err, i;
+
+ /* return true, letting typedefs know that it's ok to be emitted */
+ if (tstate->order_state == ORDERED)
+ return 1;
+
+ t = btf__type_by_id(d->btf, id);
+ kind = btf_kind_of(t);
+
+ if (tstate->order_state == ORDERING) {
+ /* type loop, but resolvable through fwd declaration */
+ if ((kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION) &&
+ through_ptr && t->name_off != 0)
+ return 0;
+ pr_warning("unsatisfiable type cycle, id:[%u]\n", id);
+ return -ELOOP;
+ }
+
+ switch (kind) {
+ case BTF_KIND_INT:
+ tstate->order_state = ORDERED;
+ return 0;
+
+ case BTF_KIND_PTR:
+ err = btf_dump_order_type(d, t->type, true);
+ tstate->order_state = ORDERED;
+ return err;
+
+ case BTF_KIND_ARRAY: {
+ const struct btf_array *a = (void *)(t + 1);
+
+ return btf_dump_order_type(d, a->type, through_ptr);
+ }
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ const struct btf_member *m = (void *)(t + 1);
+ /*
+ * struct/union is part of strong link, only if it's embedded
+ * (so no ptr in a path) or it's anonymous (so has to be
+ * defined inline, even if declared through ptr)
+ */
+ if (through_ptr && t->name_off != 0)
+ return 0;
+
+ tstate->order_state = ORDERING;
+
+ vlen = btf_vlen_of(t);
+ for (i = 0; i < vlen; i++, m++) {
+ err = btf_dump_order_type(d, m->type, false);
+ if (err < 0)
+ return err;
+ }
+
+ if (t->name_off != 0) {
+ err = btf_dump_add_emit_queue_id(d, id);
+ if (err < 0)
+ return err;
+ }
+
+ tstate->order_state = ORDERED;
+ return 1;
+ }
+ case BTF_KIND_ENUM:
+ case BTF_KIND_FWD:
+ if (t->name_off != 0) {
+ err = btf_dump_add_emit_queue_id(d, id);
+ if (err)
+ return err;
+ }
+ tstate->order_state = ORDERED;
+ return 1;
+
+ case BTF_KIND_TYPEDEF: {
+ int is_strong;
+
+ is_strong = btf_dump_order_type(d, t->type, through_ptr);
+ if (is_strong < 0)
+ return is_strong;
+
+ /* typedef is similar to struct/union w.r.t. fwd-decls */
+ if (through_ptr && !is_strong)
+ return 0;
+
+ /* typedef is always a named definition */
+ err = btf_dump_add_emit_queue_id(d, id);
+ if (err)
+ return err;
+
+ d->type_states[id].order_state = ORDERED;
+ return 1;
+ }
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ return btf_dump_order_type(d, t->type, through_ptr);
+
+ case BTF_KIND_FUNC_PROTO: {
+ const struct btf_param *p = (void *)(t + 1);
+ bool is_strong;
+
+ err = btf_dump_order_type(d, t->type, through_ptr);
+ if (err < 0)
+ return err;
+ is_strong = err > 0;
+
+ vlen = btf_vlen_of(t);
+ for (i = 0; i < vlen; i++, p++) {
+ err = btf_dump_order_type(d, p->type, through_ptr);
+ if (err < 0)
+ return err;
+ if (err > 0)
+ is_strong = true;
+ }
+ return is_strong;
+ }
+ case BTF_KIND_FUNC:
+ case BTF_KIND_VAR:
+ case BTF_KIND_DATASEC:
+ d->type_states[id].order_state = ORDERED;
+ return 0;
+
+ default:
+ return -EINVAL;
+ }
+}
+
+static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id,
+ const struct btf_type *t);
+static void btf_dump_emit_struct_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t, int lvl);
+
+static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id,
+ const struct btf_type *t);
+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_fwd_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t);
+
+static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t, int lvl);
+
+/* a local view into a shared stack */
+struct id_stack {
+ const __u32 *ids;
+ int cnt;
+};
+
+static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
+ const char *fname, int lvl);
+static void btf_dump_emit_type_chain(struct btf_dump *d,
+ struct id_stack *decl_stack,
+ const char *fname, int lvl);
+
+static const char *btf_dump_type_name(struct btf_dump *d, __u32 id);
+static const char *btf_dump_ident_name(struct btf_dump *d, __u32 id);
+static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map,
+ const char *orig_name);
+
+static bool btf_dump_is_blacklisted(struct btf_dump *d, __u32 id)
+{
+ const struct btf_type *t = btf__type_by_id(d->btf, id);
+
+ /* __builtin_va_list is a compiler built-in, which causes compilation
+ * errors, when compiling w/ different compiler, then used to compile
+ * original code (e.g., GCC to compile kernel, Clang to use generated
+ * C header from BTF). As it is built-in, it should be already defined
+ * properly internally in compiler.
+ */
+ if (t->name_off == 0)
+ return false;
+ return strcmp(btf_name_of(d, t->name_off), "__builtin_va_list") == 0;
+}
+
+/*
+ * Emit C-syntax definitions of types from chains of BTF types.
+ *
+ * High-level handling of determining necessary forward declarations are handled
+ * by btf_dump_emit_type() itself, but all nitty-gritty details of emitting type
+ * declarations/definitions in C syntax are handled by a combo of
+ * btf_dump_emit_type_decl()/btf_dump_emit_type_chain() w/ delegation to
+ * corresponding btf_dump_emit_*_{def,fwd}() functions.
+ *
+ * We also keep track of "containing struct/union type ID" to determine when
+ * we reference it from inside and thus can avoid emitting unnecessary forward
+ * declaration.
+ *
+ * This algorithm is designed in such a way, that even if some error occurs
+ * (either technical, e.g., out of memory, or logical, i.e., malformed BTF
+ * that doesn't comply to C rules completely), algorithm will try to proceed
+ * and produce as much meaningful output as possible.
+ */
+static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
+{
+ struct btf_dump_type_aux_state *tstate = &d->type_states[id];
+ bool top_level_def = cont_id == 0;
+ const struct btf_type *t;
+ __u16 kind;
+
+ if (tstate->emit_state == EMITTED)
+ return;
+
+ t = btf__type_by_id(d->btf, id);
+ kind = btf_kind_of(t);
+
+ if (top_level_def && t->name_off == 0) {
+ pr_warning("unexpected nameless definition, id:[%u]\n", id);
+ return;
+ }
+
+ if (tstate->emit_state == EMITTING) {
+ if (tstate->fwd_emitted)
+ return;
+
+ switch (kind) {
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ /*
+ * if we are referencing a struct/union that we are
+ * part of - then no need for fwd declaration
+ */
+ if (id == cont_id)
+ return;
+ if (t->name_off == 0) {
+ pr_warning("anonymous struct/union loop, id:[%u]\n",
+ id);
+ return;
+ }
+ btf_dump_emit_struct_fwd(d, id, t);
+ btf_dump_printf(d, ";\n\n");
+ tstate->fwd_emitted = 1;
+ break;
+ case BTF_KIND_TYPEDEF:
+ /*
+ * for typedef fwd_emitted means typedef definition
+ * was emitted, but it can be used only for "weak"
+ * references through pointer only, not for embedding
+ */
+ if (!btf_dump_is_blacklisted(d, id)) {
+ btf_dump_emit_typedef_def(d, id, t, 0);
+ btf_dump_printf(d, ";\n\n");
+ };
+ tstate->fwd_emitted = 1;
+ break;
+ default:
+ break;
+ }
+
+ return;
+ }
+
+ switch (kind) {
+ case BTF_KIND_INT:
+ tstate->emit_state = EMITTED;
+ break;
+ case BTF_KIND_ENUM:
+ if (top_level_def) {
+ btf_dump_emit_enum_def(d, id, t, 0);
+ btf_dump_printf(d, ";\n\n");
+ }
+ tstate->emit_state = EMITTED;
+ break;
+ case BTF_KIND_PTR:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ btf_dump_emit_type(d, t->type, cont_id);
+ break;
+ case BTF_KIND_ARRAY: {
+ const struct btf_array *a = (void *)(t + 1);
+
+ btf_dump_emit_type(d, a->type, cont_id);
+ break;
+ }
+ case BTF_KIND_FWD:
+ btf_dump_emit_fwd_def(d, id, t);
+ btf_dump_printf(d, ";\n\n");
+ tstate->emit_state = EMITTED;
+ break;
+ case BTF_KIND_TYPEDEF:
+ tstate->emit_state = EMITTING;
+ btf_dump_emit_type(d, t->type, id);
+ /*
+ * typedef can server as both definition and forward
+ * declaration; at this stage someone depends on
+ * typedef as a forward declaration (refers to it
+ * through pointer), so unless we already did it,
+ * emit typedef as a forward declaration
+ */
+ if (!tstate->fwd_emitted && !btf_dump_is_blacklisted(d, id)) {
+ btf_dump_emit_typedef_def(d, id, t, 0);
+ btf_dump_printf(d, ";\n\n");
+ }
+ tstate->emit_state = EMITTED;
+ break;
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ tstate->emit_state = EMITTING;
+ /* if it's a top-level struct/union definition or struct/union
+ * is anonymous, then in C we'll be emitting all fields and
+ * their types (as opposed to just `struct X`), so we need to
+ * make sure that all types, referenced from struct/union
+ * members have necessary forward-declarations, where
+ * applicable
+ */
+ if (top_level_def || t->name_off == 0) {
+ const struct btf_member *m = (void *)(t + 1);
+ __u16 vlen = btf_vlen_of(t);
+ int i, new_cont_id;
+
+ new_cont_id = t->name_off == 0 ? cont_id : id;
+ for (i = 0; i < vlen; i++, m++)
+ btf_dump_emit_type(d, m->type, new_cont_id);
+ } else if (!tstate->fwd_emitted && id != cont_id) {
+ btf_dump_emit_struct_fwd(d, id, t);
+ btf_dump_printf(d, ";\n\n");
+ tstate->fwd_emitted = 1;
+ }
+
+ if (top_level_def) {
+ btf_dump_emit_struct_def(d, id, t, 0);
+ btf_dump_printf(d, ";\n\n");
+ tstate->emit_state = EMITTED;
+ } else {
+ tstate->emit_state = NOT_EMITTED;
+ }
+ break;
+ case BTF_KIND_FUNC_PROTO: {
+ const struct btf_param *p = (void *)(t + 1);
+ __u16 vlen = btf_vlen_of(t);
+ int i;
+
+ btf_dump_emit_type(d, t->type, cont_id);
+ for (i = 0; i < vlen; i++, p++)
+ btf_dump_emit_type(d, p->type, cont_id);
+
+ break;
+ }
+ default:
+ break;
+ }
+}
+
+static int btf_align_of(const struct btf *btf, __u32 id)
+{
+ const struct btf_type *t = btf__type_by_id(btf, id);
+ __u16 kind = btf_kind_of(t);
+
+ switch (kind) {
+ case BTF_KIND_INT:
+ case BTF_KIND_ENUM:
+ return min(sizeof(void *), t->size);
+ case BTF_KIND_PTR:
+ return sizeof(void *);
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ return btf_align_of(btf, t->type);
+ case BTF_KIND_ARRAY: {
+ const struct btf_array *a = (void *)(t + 1);
+
+ return btf_align_of(btf, a->type);
+ }
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ const struct btf_member *m = (void *)(t + 1);
+ __u16 vlen = btf_vlen_of(t);
+ int i, align = 1;
+
+ for (i = 0; i < vlen; i++, m++)
+ align = max(align, btf_align_of(btf, m->type));
+
+ return align;
+ }
+ default:
+ pr_warning("unsupported BTF_KIND:%u\n", btf_kind_of(t));
+ return 1;
+ }
+}
+
+static bool btf_is_struct_packed(const struct btf *btf, __u32 id,
+ const struct btf_type *t)
+{
+ const struct btf_member *m;
+ int align, i, bit_sz;
+ __u16 vlen;
+ bool kflag;
+
+ align = btf_align_of(btf, id);
+ /* size of a non-packed struct has to be a multiple of its alignment*/
+ if (t->size % align)
+ return true;
+
+ m = (void *)(t + 1);
+ kflag = btf_kflag_of(t);
+ vlen = btf_vlen_of(t);
+ /* all non-bitfield fields have to be naturally aligned */
+ for (i = 0; i < vlen; i++, m++) {
+ align = btf_align_of(btf, m->type);
+ bit_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
+ if (bit_sz == 0 && m->offset % (8 * align) != 0)
+ return true;
+ }
+
+ /*
+ * if original struct was marked as packed, but its layout is
+ * naturally aligned, we'll detect that it's not packed
+ */
+ return false;
+}
+
+static int chip_away_bits(int total, int at_most)
+{
+ return total % at_most ? : at_most;
+}
+
+static void btf_dump_emit_bit_padding(const struct btf_dump *d,
+ int cur_off, int m_off, int m_bit_sz,
+ int align, int lvl)
+{
+ int off_diff = m_off - cur_off;
+ int ptr_bits = sizeof(void *) * 8;
+
+ if (off_diff <= 0)
+ /* no gap */
+ return;
+ if (m_bit_sz == 0 && off_diff < align * 8)
+ /* natural padding will take care of a gap */
+ return;
+
+ while (off_diff > 0) {
+ const char *pad_type;
+ int pad_bits;
+
+ if (ptr_bits > 32 && off_diff > 32) {
+ pad_type = "long";
+ pad_bits = chip_away_bits(off_diff, ptr_bits);
+ } else if (off_diff > 16) {
+ pad_type = "int";
+ pad_bits = chip_away_bits(off_diff, 32);
+ } else if (off_diff > 8) {
+ pad_type = "short";
+ pad_bits = chip_away_bits(off_diff, 16);
+ } else {
+ pad_type = "char";
+ pad_bits = chip_away_bits(off_diff, 8);
+ }
+ btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits);
+ off_diff -= pad_bits;
+ }
+}
+
+static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id,
+ const struct btf_type *t)
+{
+ btf_dump_printf(d, "%s %s",
+ btf_kind_of(t) == BTF_KIND_STRUCT ? "struct" : "union",
+ btf_dump_type_name(d, id));
+}
+
+static void btf_dump_emit_struct_def(struct btf_dump *d,
+ __u32 id,
+ const struct btf_type *t,
+ int lvl)
+{
+ const struct btf_member *m = (void *)(t + 1);
+ bool kflag = btf_kflag_of(t), is_struct;
+ int align, i, packed, off = 0;
+ __u16 vlen = btf_vlen_of(t);
+
+ is_struct = btf_kind_of(t) == BTF_KIND_STRUCT;
+ packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0;
+ align = packed ? 1 : btf_align_of(d->btf, id);
+
+ btf_dump_printf(d, "%s%s%s {",
+ is_struct ? "struct" : "union",
+ t->name_off ? " " : "",
+ btf_dump_type_name(d, id));
+
+ for (i = 0; i < vlen; i++, m++) {
+ const char *fname;
+ int m_off, m_sz;
+
+ fname = btf_name_of(d, m->name_off);
+ m_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0;
+ m_off = kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset;
+ align = packed ? 1 : btf_align_of(d->btf, m->type);
+
+ btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1);
+ btf_dump_printf(d, "\n%s", pfx(lvl + 1));
+ btf_dump_emit_type_decl(d, m->type, fname, lvl + 1);
+
+ if (m_sz) {
+ btf_dump_printf(d, ": %d", m_sz);
+ off = m_off + m_sz;
+ } else {
+ m_sz = max(0, btf__resolve_size(d->btf, m->type));
+ off = m_off + m_sz * 8;
+ }
+ btf_dump_printf(d, ";");
+ }
+
+ if (vlen)
+ btf_dump_printf(d, "\n");
+ btf_dump_printf(d, "%s}", pfx(lvl));
+ if (packed)
+ btf_dump_printf(d, " __attribute__((packed))");
+}
+
+static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id,
+ const struct btf_type *t)
+{
+ 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)
+{
+ const struct btf_enum *v = (void *)(t+1);
+ __u16 vlen = btf_vlen_of(t);
+ const char *name;
+ size_t dup_cnt;
+ int i;
+
+ 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 = %d,",
+ pfx(lvl + 1), name, dup_cnt,
+ (__s32)v->val);
+ } else {
+ btf_dump_printf(d, "\n%s%s = %d,",
+ pfx(lvl + 1), name,
+ (__s32)v->val);
+ }
+ }
+ btf_dump_printf(d, "\n%s}", pfx(lvl));
+ }
+}
+
+static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t)
+{
+ const char *name = btf_dump_type_name(d, id);
+
+ if (btf_kflag_of(t))
+ btf_dump_printf(d, "union %s", name);
+ else
+ btf_dump_printf(d, "struct %s", name);
+}
+
+static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id,
+ const struct btf_type *t, int lvl)
+{
+ const char *name = btf_dump_ident_name(d, id);
+
+ btf_dump_printf(d, "typedef ");
+ btf_dump_emit_type_decl(d, t->type, name, lvl);
+}
+
+static int btf_dump_push_decl_stack_id(struct btf_dump *d, __u32 id)
+{
+ __u32 *new_stack;
+ size_t new_cap;
+
+ if (d->decl_stack_cnt >= d->decl_stack_cap) {
+ new_cap = max(16, d->decl_stack_cap * 3 / 2);
+ new_stack = realloc(d->decl_stack,
+ new_cap * sizeof(new_stack[0]));
+ if (!new_stack)
+ return -ENOMEM;
+ d->decl_stack = new_stack;
+ d->decl_stack_cap = new_cap;
+ }
+
+ d->decl_stack[d->decl_stack_cnt++] = id;
+
+ return 0;
+}
+
+/*
+ * Emit type declaration (e.g., field type declaration in a struct or argument
+ * declaration in function prototype) in correct C syntax.
+ *
+ * For most types it's trivial, but there are few quirky type declaration
+ * cases worth mentioning:
+ * - function prototypes (especially nesting of function prototypes);
+ * - arrays;
+ * - const/volatile/restrict for pointers vs other types.
+ *
+ * For a good discussion of *PARSING* C syntax (as a human), see
+ * Peter van der Linden's "Expert C Programming: Deep C Secrets",
+ * Ch.3 "Unscrambling Declarations in C".
+ *
+ * It won't help with BTF to C conversion much, though, as it's an opposite
+ * problem. So we came up with this algorithm in reverse to van der Linden's
+ * parsing algorithm. It goes from structured BTF representation of type
+ * declaration to a valid compilable C syntax.
+ *
+ * For instance, consider this C typedef:
+ * typedef const int * const * arr[10] arr_t;
+ * It will be represented in BTF with this chain of BTF types:
+ * [typedef] -> [array] -> [ptr] -> [const] -> [ptr] -> [const] -> [int]
+ *
+ * Notice how [const] modifier always goes before type it modifies in BTF type
+ * graph, but in C syntax, const/volatile/restrict modifiers are written to
+ * the right of pointers, but to the left of other types. There are also other
+ * quirks, like function pointers, arrays of them, functions returning other
+ * functions, etc.
+ *
+ * We handle that by pushing all the types to a stack, until we hit "terminal"
+ * type (int/enum/struct/union/fwd). Then depending on the kind of a type on
+ * top of a stack, modifiers are handled differently. Array/function pointers
+ * have also wildly different syntax and how nesting of them are done. See
+ * code for authoritative definition.
+ *
+ * To avoid allocating new stack for each independent chain of BTF types, we
+ * share one bigger stack, with each chain working only on its own local view
+ * of a stack frame. Some care is required to "pop" stack frames after
+ * processing type declaration chain.
+ */
+static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
+ const char *fname, int lvl)
+{
+ struct id_stack decl_stack;
+ const struct btf_type *t;
+ int err, stack_start;
+ __u16 kind;
+
+ stack_start = d->decl_stack_cnt;
+ for (;;) {
+ err = btf_dump_push_decl_stack_id(d, id);
+ if (err < 0) {
+ /*
+ * if we don't have enough memory for entire type decl
+ * chain, restore stack, emit warning, and try to
+ * proceed nevertheless
+ */
+ pr_warning("not enough memory for decl stack:%d", err);
+ d->decl_stack_cnt = stack_start;
+ return;
+ }
+
+ /* VOID */
+ if (id == 0)
+ break;
+
+ t = btf__type_by_id(d->btf, id);
+ kind = btf_kind_of(t);
+ switch (kind) {
+ case BTF_KIND_PTR:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_FUNC_PROTO:
+ id = t->type;
+ break;
+ case BTF_KIND_ARRAY: {
+ const struct btf_array *a = (void *)(t + 1);
+
+ id = a->type;
+ break;
+ }
+ case BTF_KIND_INT:
+ case BTF_KIND_ENUM:
+ case BTF_KIND_FWD:
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ case BTF_KIND_TYPEDEF:
+ goto done;
+ default:
+ pr_warning("unexpected type in decl chain, kind:%u, id:[%u]\n",
+ kind, id);
+ goto done;
+ }
+ }
+done:
+ /*
+ * We might be inside a chain of declarations (e.g., array of function
+ * pointers returning anonymous (so inlined) structs, having another
+ * array field). Each of those needs its own "stack frame" to handle
+ * emitting of declarations. Those stack frames are non-overlapping
+ * portions of shared btf_dump->decl_stack. To make it a bit nicer to
+ * handle this set of nested stacks, we create a view corresponding to
+ * our own "stack frame" and work with it as an independent stack.
+ * We'll need to clean up after emit_type_chain() returns, though.
+ */
+ decl_stack.ids = d->decl_stack + stack_start;
+ decl_stack.cnt = d->decl_stack_cnt - stack_start;
+ btf_dump_emit_type_chain(d, &decl_stack, fname, lvl);
+ /*
+ * emit_type_chain() guarantees that it will pop its entire decl_stack
+ * frame before returning. But it works with a read-only view into
+ * decl_stack, so it doesn't actually pop anything from the
+ * perspective of shared btf_dump->decl_stack, per se. We need to
+ * reset decl_stack state to how it was before us to avoid it growing
+ * all the time.
+ */
+ d->decl_stack_cnt = stack_start;
+}
+
+static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack)
+{
+ const struct btf_type *t;
+ __u32 id;
+
+ while (decl_stack->cnt) {
+ id = decl_stack->ids[decl_stack->cnt - 1];
+ t = btf__type_by_id(d->btf, id);
+
+ switch (btf_kind_of(t)) {
+ case BTF_KIND_VOLATILE:
+ btf_dump_printf(d, "volatile ");
+ break;
+ case BTF_KIND_CONST:
+ btf_dump_printf(d, "const ");
+ break;
+ case BTF_KIND_RESTRICT:
+ btf_dump_printf(d, "restrict ");
+ break;
+ default:
+ return;
+ }
+ decl_stack->cnt--;
+ }
+}
+
+static bool btf_is_mod_kind(const struct btf *btf, __u32 id)
+{
+ const struct btf_type *t = btf__type_by_id(btf, id);
+
+ switch (btf_kind_of(t)) {
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static void btf_dump_emit_name(const struct btf_dump *d,
+ const char *name, bool last_was_ptr)
+{
+ bool separate = name[0] && !last_was_ptr;
+
+ btf_dump_printf(d, "%s%s", separate ? " " : "", name);
+}
+
+static void btf_dump_emit_type_chain(struct btf_dump *d,
+ struct id_stack *decls,
+ const char *fname, int lvl)
+{
+ /*
+ * last_was_ptr is used to determine if we need to separate pointer
+ * asterisk (*) from previous part of type signature with space, so
+ * that we get `int ***`, instead of `int * * *`. We default to true
+ * for cases where we have single pointer in a chain. E.g., in ptr ->
+ * func_proto case. func_proto will start a new emit_type_chain call
+ * with just ptr, which should be emitted as (*) or (*<fname>), so we
+ * don't want to prepend space for that last pointer.
+ */
+ bool last_was_ptr = true;
+ const struct btf_type *t;
+ const char *name;
+ __u16 kind;
+ __u32 id;
+
+ while (decls->cnt) {
+ id = decls->ids[--decls->cnt];
+ if (id == 0) {
+ /* VOID is a special snowflake */
+ btf_dump_emit_mods(d, decls);
+ btf_dump_printf(d, "void");
+ last_was_ptr = false;
+ continue;
+ }
+
+ t = btf__type_by_id(d->btf, id);
+ kind = btf_kind_of(t);
+
+ switch (kind) {
+ case BTF_KIND_INT:
+ btf_dump_emit_mods(d, decls);
+ name = btf_name_of(d, t->name_off);
+ btf_dump_printf(d, "%s", name);
+ break;
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ btf_dump_emit_mods(d, decls);
+ /* inline anonymous struct/union */
+ if (t->name_off == 0)
+ btf_dump_emit_struct_def(d, id, t, lvl);
+ else
+ btf_dump_emit_struct_fwd(d, id, t);
+ break;
+ case BTF_KIND_ENUM:
+ btf_dump_emit_mods(d, decls);
+ /* inline anonymous enum */
+ if (t->name_off == 0)
+ btf_dump_emit_enum_def(d, id, t, lvl);
+ else
+ btf_dump_emit_enum_fwd(d, id, t);
+ break;
+ case BTF_KIND_FWD:
+ btf_dump_emit_mods(d, decls);
+ btf_dump_emit_fwd_def(d, id, t);
+ break;
+ case BTF_KIND_TYPEDEF:
+ btf_dump_emit_mods(d, decls);
+ btf_dump_printf(d, "%s", btf_dump_ident_name(d, id));
+ break;
+ case BTF_KIND_PTR:
+ btf_dump_printf(d, "%s", last_was_ptr ? "*" : " *");
+ break;
+ case BTF_KIND_VOLATILE:
+ btf_dump_printf(d, " volatile");
+ break;
+ case BTF_KIND_CONST:
+ btf_dump_printf(d, " const");
+ break;
+ case BTF_KIND_RESTRICT:
+ btf_dump_printf(d, " restrict");
+ break;
+ case BTF_KIND_ARRAY: {
+ const struct btf_array *a = (void *)(t + 1);
+ const struct btf_type *next_t;
+ __u32 next_id;
+ bool multidim;
+ /*
+ * GCC has a bug
+ * (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=8354)
+ * which causes it to emit extra const/volatile
+ * modifiers for an array, if array's element type has
+ * const/volatile modifiers. Clang doesn't do that.
+ * In general, it doesn't seem very meaningful to have
+ * a const/volatile modifier for array, so we are
+ * going to silently skip them here.
+ */
+ while (decls->cnt) {
+ next_id = decls->ids[decls->cnt - 1];
+ if (btf_is_mod_kind(d->btf, next_id))
+ decls->cnt--;
+ else
+ break;
+ }
+
+ if (decls->cnt == 0) {
+ btf_dump_emit_name(d, fname, last_was_ptr);
+ btf_dump_printf(d, "[%u]", a->nelems);
+ return;
+ }
+
+ next_t = btf__type_by_id(d->btf, next_id);
+ multidim = btf_kind_of(next_t) == BTF_KIND_ARRAY;
+ /* we need space if we have named non-pointer */
+ if (fname[0] && !last_was_ptr)
+ btf_dump_printf(d, " ");
+ /* no parentheses for multi-dimensional array */
+ if (!multidim)
+ btf_dump_printf(d, "(");
+ btf_dump_emit_type_chain(d, decls, fname, lvl);
+ if (!multidim)
+ btf_dump_printf(d, ")");
+ btf_dump_printf(d, "[%u]", a->nelems);
+ return;
+ }
+ case BTF_KIND_FUNC_PROTO: {
+ const struct btf_param *p = (void *)(t + 1);
+ __u16 vlen = btf_vlen_of(t);
+ int i;
+
+ btf_dump_emit_mods(d, decls);
+ if (decls->cnt) {
+ btf_dump_printf(d, " (");
+ btf_dump_emit_type_chain(d, decls, fname, lvl);
+ btf_dump_printf(d, ")");
+ } else {
+ btf_dump_emit_name(d, fname, last_was_ptr);
+ }
+ btf_dump_printf(d, "(");
+ /*
+ * Clang for BPF target generates func_proto with no
+ * args as a func_proto with a single void arg (e.g.,
+ * `int (*f)(void)` vs just `int (*f)()`). We are
+ * going to pretend there are no args for such case.
+ */
+ if (vlen == 1 && p->type == 0) {
+ btf_dump_printf(d, ")");
+ return;
+ }
+
+ for (i = 0; i < vlen; i++, p++) {
+ if (i > 0)
+ btf_dump_printf(d, ", ");
+
+ /* last arg of type void is vararg */
+ if (i == vlen - 1 && p->type == 0) {
+ btf_dump_printf(d, "...");
+ break;
+ }
+
+ name = btf_name_of(d, p->name_off);
+ btf_dump_emit_type_decl(d, p->type, name, lvl);
+ }
+
+ btf_dump_printf(d, ")");
+ return;
+ }
+ default:
+ pr_warning("unexpected type in decl chain, kind:%u, id:[%u]\n",
+ kind, id);
+ return;
+ }
+
+ last_was_ptr = kind == BTF_KIND_PTR;
+ }
+
+ btf_dump_emit_name(d, fname, last_was_ptr);
+}
+
+/* return number of duplicates (occurrences) of a given name */
+static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map,
+ const char *orig_name)
+{
+ size_t dup_cnt = 0;
+
+ hashmap__find(name_map, orig_name, (void **)&dup_cnt);
+ dup_cnt++;
+ hashmap__set(name_map, orig_name, (void *)dup_cnt, NULL, NULL);
+
+ return dup_cnt;
+}
+
+static const char *btf_dump_resolve_name(struct btf_dump *d, __u32 id,
+ struct hashmap *name_map)
+{
+ struct btf_dump_type_aux_state *s = &d->type_states[id];
+ const struct btf_type *t = btf__type_by_id(d->btf, id);
+ const char *orig_name = btf_name_of(d, t->name_off);
+ const char **cached_name = &d->cached_names[id];
+ size_t dup_cnt;
+
+ if (t->name_off == 0)
+ return "";
+
+ if (s->name_resolved)
+ return *cached_name ? *cached_name : orig_name;
+
+ dup_cnt = btf_dump_name_dups(d, name_map, orig_name);
+ if (dup_cnt > 1) {
+ const size_t max_len = 256;
+ char new_name[max_len];
+
+ snprintf(new_name, max_len, "%s___%zu", orig_name, dup_cnt);
+ *cached_name = strdup(new_name);
+ }
+
+ s->name_resolved = 1;
+ return *cached_name ? *cached_name : orig_name;
+}
+
+static const char *btf_dump_type_name(struct btf_dump *d, __u32 id)
+{
+ return btf_dump_resolve_name(d, id, d->type_names);
+}
+
+static const char *btf_dump_ident_name(struct btf_dump *d, __u32 id)
+{
+ return btf_dump_resolve_name(d, id, d->ident_names);
+}
diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c
new file mode 100644
index 000000000000..6122272943e6
--- /dev/null
+++ b/tools/lib/bpf/hashmap.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * Generic non-thread safe hash map implementation.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <linux/err.h>
+#include "hashmap.h"
+
+/* start with 4 buckets */
+#define HASHMAP_MIN_CAP_BITS 2
+
+static void hashmap_add_entry(struct hashmap_entry **pprev,
+ struct hashmap_entry *entry)
+{
+ entry->next = *pprev;
+ *pprev = entry;
+}
+
+static void hashmap_del_entry(struct hashmap_entry **pprev,
+ struct hashmap_entry *entry)
+{
+ *pprev = entry->next;
+ entry->next = NULL;
+}
+
+void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
+ hashmap_equal_fn equal_fn, void *ctx)
+{
+ map->hash_fn = hash_fn;
+ map->equal_fn = equal_fn;
+ map->ctx = ctx;
+
+ map->buckets = NULL;
+ map->cap = 0;
+ map->cap_bits = 0;
+ map->sz = 0;
+}
+
+struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
+ hashmap_equal_fn equal_fn,
+ void *ctx)
+{
+ struct hashmap *map = malloc(sizeof(struct hashmap));
+
+ if (!map)
+ return ERR_PTR(-ENOMEM);
+ hashmap__init(map, hash_fn, equal_fn, ctx);
+ return map;
+}
+
+void hashmap__clear(struct hashmap *map)
+{
+ free(map->buckets);
+ map->cap = map->cap_bits = map->sz = 0;
+}
+
+void hashmap__free(struct hashmap *map)
+{
+ if (!map)
+ return;
+
+ hashmap__clear(map);
+ free(map);
+}
+
+size_t hashmap__size(const struct hashmap *map)
+{
+ return map->sz;
+}
+
+size_t hashmap__capacity(const struct hashmap *map)
+{
+ return map->cap;
+}
+
+static bool hashmap_needs_to_grow(struct hashmap *map)
+{
+ /* grow if empty or more than 75% filled */
+ return (map->cap == 0) || ((map->sz + 1) * 4 / 3 > map->cap);
+}
+
+static int hashmap_grow(struct hashmap *map)
+{
+ struct hashmap_entry **new_buckets;
+ struct hashmap_entry *cur, *tmp;
+ size_t new_cap_bits, new_cap;
+ size_t h;
+ int bkt;
+
+ new_cap_bits = map->cap_bits + 1;
+ if (new_cap_bits < HASHMAP_MIN_CAP_BITS)
+ new_cap_bits = HASHMAP_MIN_CAP_BITS;
+
+ new_cap = 1UL << new_cap_bits;
+ new_buckets = calloc(new_cap, sizeof(new_buckets[0]));
+ if (!new_buckets)
+ return -ENOMEM;
+
+ hashmap__for_each_entry_safe(map, cur, tmp, bkt) {
+ h = hash_bits(map->hash_fn(cur->key, map->ctx), new_cap_bits);
+ hashmap_add_entry(&new_buckets[h], cur);
+ }
+
+ map->cap = new_cap;
+ map->cap_bits = new_cap_bits;
+ free(map->buckets);
+ map->buckets = new_buckets;
+
+ return 0;
+}
+
+static bool hashmap_find_entry(const struct hashmap *map,
+ const void *key, size_t hash,
+ struct hashmap_entry ***pprev,
+ struct hashmap_entry **entry)
+{
+ struct hashmap_entry *cur, **prev_ptr;
+
+ if (!map->buckets)
+ return false;
+
+ for (prev_ptr = &map->buckets[hash], cur = *prev_ptr;
+ cur;
+ prev_ptr = &cur->next, cur = cur->next) {
+ if (map->equal_fn(cur->key, key, map->ctx)) {
+ if (pprev)
+ *pprev = prev_ptr;
+ *entry = cur;
+ return true;
+ }
+ }
+
+ return false;
+}
+
+int hashmap__insert(struct hashmap *map, const void *key, void *value,
+ enum hashmap_insert_strategy strategy,
+ const void **old_key, void **old_value)
+{
+ struct hashmap_entry *entry;
+ size_t h;
+ int err;
+
+ if (old_key)
+ *old_key = NULL;
+ if (old_value)
+ *old_value = NULL;
+
+ h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+ if (strategy != HASHMAP_APPEND &&
+ hashmap_find_entry(map, key, h, NULL, &entry)) {
+ if (old_key)
+ *old_key = entry->key;
+ if (old_value)
+ *old_value = entry->value;
+
+ if (strategy == HASHMAP_SET || strategy == HASHMAP_UPDATE) {
+ entry->key = key;
+ entry->value = value;
+ return 0;
+ } else if (strategy == HASHMAP_ADD) {
+ return -EEXIST;
+ }
+ }
+
+ if (strategy == HASHMAP_UPDATE)
+ return -ENOENT;
+
+ if (hashmap_needs_to_grow(map)) {
+ err = hashmap_grow(map);
+ if (err)
+ return err;
+ h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+ }
+
+ entry = malloc(sizeof(struct hashmap_entry));
+ if (!entry)
+ return -ENOMEM;
+
+ entry->key = key;
+ entry->value = value;
+ hashmap_add_entry(&map->buckets[h], entry);
+ map->sz++;
+
+ return 0;
+}
+
+bool hashmap__find(const struct hashmap *map, const void *key, void **value)
+{
+ struct hashmap_entry *entry;
+ size_t h;
+
+ h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+ if (!hashmap_find_entry(map, key, h, NULL, &entry))
+ return false;
+
+ if (value)
+ *value = entry->value;
+ return true;
+}
+
+bool hashmap__delete(struct hashmap *map, const void *key,
+ const void **old_key, void **old_value)
+{
+ struct hashmap_entry **pprev, *entry;
+ size_t h;
+
+ h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
+ if (!hashmap_find_entry(map, key, h, &pprev, &entry))
+ return false;
+
+ if (old_key)
+ *old_key = entry->key;
+ if (old_value)
+ *old_value = entry->value;
+
+ hashmap_del_entry(pprev, entry);
+ free(entry);
+ map->sz--;
+
+ return true;
+}
+
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
new file mode 100644
index 000000000000..03748a742146
--- /dev/null
+++ b/tools/lib/bpf/hashmap.h
@@ -0,0 +1,173 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/*
+ * Generic non-thread safe hash map implementation.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+#ifndef __LIBBPF_HASHMAP_H
+#define __LIBBPF_HASHMAP_H
+
+#include <stdbool.h>
+#include <stddef.h>
+#include "libbpf_internal.h"
+
+static inline size_t hash_bits(size_t h, int bits)
+{
+ /* shuffle bits and return requested number of upper bits */
+ return (h * 11400714819323198485llu) >> (__WORDSIZE - bits);
+}
+
+typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
+typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
+
+struct hashmap_entry {
+ const void *key;
+ void *value;
+ struct hashmap_entry *next;
+};
+
+struct hashmap {
+ hashmap_hash_fn hash_fn;
+ hashmap_equal_fn equal_fn;
+ void *ctx;
+
+ struct hashmap_entry **buckets;
+ size_t cap;
+ size_t cap_bits;
+ size_t sz;
+};
+
+#define HASHMAP_INIT(hash_fn, equal_fn, ctx) { \
+ .hash_fn = (hash_fn), \
+ .equal_fn = (equal_fn), \
+ .ctx = (ctx), \
+ .buckets = NULL, \
+ .cap = 0, \
+ .cap_bits = 0, \
+ .sz = 0, \
+}
+
+void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
+ hashmap_equal_fn equal_fn, void *ctx);
+struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
+ hashmap_equal_fn equal_fn,
+ void *ctx);
+void hashmap__clear(struct hashmap *map);
+void hashmap__free(struct hashmap *map);
+
+size_t hashmap__size(const struct hashmap *map);
+size_t hashmap__capacity(const struct hashmap *map);
+
+/*
+ * Hashmap insertion strategy:
+ * - HASHMAP_ADD - only add key/value if key doesn't exist yet;
+ * - HASHMAP_SET - add key/value pair if key doesn't exist yet; otherwise,
+ * update value;
+ * - HASHMAP_UPDATE - update value, if key already exists; otherwise, do
+ * nothing and return -ENOENT;
+ * - HASHMAP_APPEND - always add key/value pair, even if key already exists.
+ * This turns hashmap into a multimap by allowing multiple values to be
+ * associated with the same key. Most useful read API for such hashmap is
+ * hashmap__for_each_key_entry() iteration. If hashmap__find() is still
+ * used, it will return last inserted key/value entry (first in a bucket
+ * chain).
+ */
+enum hashmap_insert_strategy {
+ HASHMAP_ADD,
+ HASHMAP_SET,
+ HASHMAP_UPDATE,
+ HASHMAP_APPEND,
+};
+
+/*
+ * hashmap__insert() adds key/value entry w/ various semantics, depending on
+ * provided strategy value. If a given key/value pair replaced already
+ * existing key/value pair, both old key and old value will be returned
+ * through old_key and old_value to allow calling code do proper memory
+ * management.
+ */
+int hashmap__insert(struct hashmap *map, const void *key, void *value,
+ enum hashmap_insert_strategy strategy,
+ const void **old_key, void **old_value);
+
+static inline int hashmap__add(struct hashmap *map,
+ const void *key, void *value)
+{
+ return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL);
+}
+
+static inline int hashmap__set(struct hashmap *map,
+ const void *key, void *value,
+ const void **old_key, void **old_value)
+{
+ return hashmap__insert(map, key, value, HASHMAP_SET,
+ old_key, old_value);
+}
+
+static inline int hashmap__update(struct hashmap *map,
+ const void *key, void *value,
+ const void **old_key, void **old_value)
+{
+ return hashmap__insert(map, key, value, HASHMAP_UPDATE,
+ old_key, old_value);
+}
+
+static inline int hashmap__append(struct hashmap *map,
+ const void *key, void *value)
+{
+ return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL);
+}
+
+bool hashmap__delete(struct hashmap *map, const void *key,
+ const void **old_key, void **old_value);
+
+bool hashmap__find(const struct hashmap *map, const void *key, void **value);
+
+/*
+ * hashmap__for_each_entry - iterate over all entries in hashmap
+ * @map: hashmap to iterate
+ * @cur: struct hashmap_entry * used as a loop cursor
+ * @bkt: integer used as a bucket loop cursor
+ */
+#define hashmap__for_each_entry(map, cur, bkt) \
+ for (bkt = 0; bkt < map->cap; bkt++) \
+ for (cur = map->buckets[bkt]; cur; cur = cur->next)
+
+/*
+ * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe
+ * against removals
+ * @map: hashmap to iterate
+ * @cur: struct hashmap_entry * used as a loop cursor
+ * @tmp: struct hashmap_entry * used as a temporary next cursor storage
+ * @bkt: integer used as a bucket loop cursor
+ */
+#define hashmap__for_each_entry_safe(map, cur, tmp, bkt) \
+ for (bkt = 0; bkt < map->cap; bkt++) \
+ for (cur = map->buckets[bkt]; \
+ cur && ({tmp = cur->next; true; }); \
+ cur = tmp)
+
+/*
+ * hashmap__for_each_key_entry - iterate over entries associated with given key
+ * @map: hashmap to iterate
+ * @cur: struct hashmap_entry * used as a loop cursor
+ * @key: key to iterate entries for
+ */
+#define hashmap__for_each_key_entry(map, cur, _key) \
+ for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
+ map->cap_bits); \
+ map->buckets ? map->buckets[bkt] : NULL; }); \
+ cur; \
+ cur = cur->next) \
+ if (map->equal_fn(cur->key, (_key), map->ctx))
+
+#define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \
+ for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
+ map->cap_bits); \
+ cur = map->buckets ? map->buckets[bkt] : NULL; }); \
+ cur && ({ tmp = cur->next; true; }); \
+ cur = tmp) \
+ if (map->equal_fn(cur->key, (_key), map->ctx))
+
+#endif /* __LIBBPF_HASHMAP_H */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 151f7ac1882e..ed07789b3e62 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -32,6 +32,9 @@
#include <linux/limits.h>
#include <linux/perf_event.h>
#include <linux/ring_buffer.h>
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
@@ -188,6 +191,7 @@ struct bpf_program {
void *line_info;
__u32 line_info_rec_size;
__u32 line_info_cnt;
+ __u32 prog_flags;
};
enum libbpf_map_type {
@@ -206,7 +210,8 @@ static const char * const libbpf_type_to_btf_name[] = {
struct bpf_map {
int fd;
char *name;
- size_t offset;
+ int sec_idx;
+ size_t sec_offset;
int map_ifindex;
int inner_map_fd;
struct bpf_map_def def;
@@ -233,6 +238,7 @@ struct bpf_object {
size_t nr_programs;
struct bpf_map *maps;
size_t nr_maps;
+ size_t maps_cap;
struct bpf_secdata sections;
bool loaded;
@@ -259,6 +265,7 @@ struct bpf_object {
} *reloc;
int nr_reloc;
int maps_shndx;
+ int btf_maps_shndx;
int text_shndx;
int data_shndx;
int rodata_shndx;
@@ -348,8 +355,11 @@ static int
bpf_program__init(void *data, size_t size, char *section_name, int idx,
struct bpf_program *prog)
{
- if (size < sizeof(struct bpf_insn)) {
- pr_warning("corrupted section '%s'\n", section_name);
+ const size_t bpf_insn_sz = sizeof(struct bpf_insn);
+
+ if (size == 0 || size % bpf_insn_sz) {
+ pr_warning("corrupted section '%s', size: %zu\n",
+ section_name, size);
return -EINVAL;
}
@@ -375,9 +385,8 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx,
section_name);
goto errout;
}
- prog->insns_cnt = size / sizeof(struct bpf_insn);
- memcpy(prog->insns, data,
- prog->insns_cnt * sizeof(struct bpf_insn));
+ prog->insns_cnt = size / bpf_insn_sz;
+ memcpy(prog->insns, data, size);
prog->idx = idx;
prog->instances.fds = NULL;
prog->instances.nr = -1;
@@ -494,15 +503,14 @@ static struct bpf_object *bpf_object__new(const char *path,
strcpy(obj->path, path);
/* Using basename() GNU version which doesn't modify arg. */
- strncpy(obj->name, basename((void *)path),
- sizeof(obj->name) - 1);
+ strncpy(obj->name, basename((void *)path), sizeof(obj->name) - 1);
end = strchr(obj->name, '.');
if (end)
*end = 0;
obj->efile.fd = -1;
/*
- * Caller of this function should also calls
+ * Caller of this function should also call
* bpf_object__elf_finish() after data collection to return
* obj_buf to user. If not, we should duplicate the buffer to
* avoid user freeing them before elf finish.
@@ -510,6 +518,7 @@ static struct bpf_object *bpf_object__new(const char *path,
obj->efile.obj_buf = obj_buf;
obj->efile.obj_buf_sz = obj_buf_sz;
obj->efile.maps_shndx = -1;
+ obj->efile.btf_maps_shndx = -1;
obj->efile.data_shndx = -1;
obj->efile.rodata_shndx = -1;
obj->efile.bss_shndx = -1;
@@ -562,38 +571,35 @@ static int bpf_object__elf_init(struct bpf_object *obj)
} else {
obj->efile.fd = open(obj->path, O_RDONLY);
if (obj->efile.fd < 0) {
- char errmsg[STRERR_BUFSIZE];
- char *cp = libbpf_strerror_r(errno, errmsg,
- sizeof(errmsg));
+ char errmsg[STRERR_BUFSIZE], *cp;
+ err = -errno;
+ cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
pr_warning("failed to open %s: %s\n", obj->path, cp);
- return -errno;
+ return err;
}
obj->efile.elf = elf_begin(obj->efile.fd,
- LIBBPF_ELF_C_READ_MMAP,
- NULL);
+ LIBBPF_ELF_C_READ_MMAP, NULL);
}
if (!obj->efile.elf) {
- pr_warning("failed to open %s as ELF file\n",
- obj->path);
+ pr_warning("failed to open %s as ELF file\n", obj->path);
err = -LIBBPF_ERRNO__LIBELF;
goto errout;
}
if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
- pr_warning("failed to get EHDR from %s\n",
- obj->path);
+ pr_warning("failed to get EHDR from %s\n", obj->path);
err = -LIBBPF_ERRNO__FORMAT;
goto errout;
}
ep = &obj->efile.ehdr;
/* Old LLVM set e_machine to EM_NONE */
- if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) {
- pr_warning("%s is not an eBPF object file\n",
- obj->path);
+ if (ep->e_type != ET_REL ||
+ (ep->e_machine && ep->e_machine != EM_BPF)) {
+ pr_warning("%s is not an eBPF object file\n", obj->path);
err = -LIBBPF_ERRNO__FORMAT;
goto errout;
}
@@ -604,47 +610,31 @@ errout:
return err;
}
-static int
-bpf_object__check_endianness(struct bpf_object *obj)
+static int bpf_object__check_endianness(struct bpf_object *obj)
{
- static unsigned int const endian = 1;
-
- switch (obj->efile.ehdr.e_ident[EI_DATA]) {
- case ELFDATA2LSB:
- /* We are big endian, BPF obj is little endian. */
- if (*(unsigned char const *)&endian != 1)
- goto mismatch;
- break;
-
- case ELFDATA2MSB:
- /* We are little endian, BPF obj is big endian. */
- if (*(unsigned char const *)&endian != 0)
- goto mismatch;
- break;
- default:
- return -LIBBPF_ERRNO__ENDIAN;
- }
-
- return 0;
-
-mismatch:
- pr_warning("Error: endianness mismatch.\n");
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+ if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB)
+ return 0;
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+ if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB)
+ return 0;
+#else
+# error "Unrecognized __BYTE_ORDER__"
+#endif
+ pr_warning("endianness mismatch.\n");
return -LIBBPF_ERRNO__ENDIAN;
}
static int
-bpf_object__init_license(struct bpf_object *obj,
- void *data, size_t size)
+bpf_object__init_license(struct bpf_object *obj, void *data, size_t size)
{
- memcpy(obj->license, data,
- min(size, sizeof(obj->license) - 1));
+ memcpy(obj->license, data, min(size, sizeof(obj->license) - 1));
pr_debug("license of %s is %s\n", obj->path, obj->license);
return 0;
}
static int
-bpf_object__init_kversion(struct bpf_object *obj,
- void *data, size_t size)
+bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size)
{
__u32 kver;
@@ -654,8 +644,7 @@ bpf_object__init_kversion(struct bpf_object *obj,
}
memcpy(&kver, data, sizeof(kver));
obj->kern_version = kver;
- pr_debug("kernel version of %s is %x\n", obj->path,
- obj->kern_version);
+ pr_debug("kernel version of %s is %x\n", obj->path, obj->kern_version);
return 0;
}
@@ -664,7 +653,9 @@ static int compare_bpf_map(const void *_a, const void *_b)
const struct bpf_map *a = _a;
const struct bpf_map *b = _b;
- return a->offset - b->offset;
+ if (a->sec_idx != b->sec_idx)
+ return a->sec_idx - b->sec_idx;
+ return a->sec_offset - b->sec_offset;
}
static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
@@ -781,24 +772,55 @@ int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
return -ENOENT;
}
-static bool bpf_object__has_maps(const struct bpf_object *obj)
+static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
{
- return obj->efile.maps_shndx >= 0 ||
- obj->efile.data_shndx >= 0 ||
- obj->efile.rodata_shndx >= 0 ||
- obj->efile.bss_shndx >= 0;
+ struct bpf_map *new_maps;
+ size_t new_cap;
+ int i;
+
+ if (obj->nr_maps < obj->maps_cap)
+ return &obj->maps[obj->nr_maps++];
+
+ new_cap = max((size_t)4, obj->maps_cap * 3 / 2);
+ new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps));
+ if (!new_maps) {
+ pr_warning("alloc maps for object failed\n");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ obj->maps_cap = new_cap;
+ obj->maps = new_maps;
+
+ /* zero out new maps */
+ memset(obj->maps + obj->nr_maps, 0,
+ (obj->maps_cap - obj->nr_maps) * sizeof(*obj->maps));
+ /*
+ * fill all fd with -1 so won't close incorrect fd (fd=0 is stdin)
+ * when failure (zclose won't close negative fd)).
+ */
+ for (i = obj->nr_maps; i < obj->maps_cap; i++) {
+ obj->maps[i].fd = -1;
+ obj->maps[i].inner_map_fd = -1;
+ }
+
+ return &obj->maps[obj->nr_maps++];
}
static int
-bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
- enum libbpf_map_type type, Elf_Data *data,
- void **data_buff)
+bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
+ int sec_idx, Elf_Data *data, void **data_buff)
{
- struct bpf_map_def *def = &map->def;
char map_name[BPF_OBJ_NAME_LEN];
+ struct bpf_map_def *def;
+ struct bpf_map *map;
+
+ map = bpf_object__add_map(obj);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
map->libbpf_type = type;
- map->offset = ~(typeof(map->offset))0;
+ map->sec_idx = sec_idx;
+ map->sec_offset = 0;
snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name,
libbpf_type_to_btf_name[type]);
map->name = strdup(map_name);
@@ -806,13 +828,15 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
pr_warning("failed to alloc map name\n");
return -ENOMEM;
}
+ pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n",
+ map_name, map->sec_idx, map->sec_offset);
+ def = &map->def;
def->type = BPF_MAP_TYPE_ARRAY;
def->key_size = sizeof(int);
def->value_size = data->d_size;
def->max_entries = 1;
- def->map_flags = type == LIBBPF_MAP_RODATA ?
- BPF_F_RDONLY_PROG : 0;
+ def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0;
if (data_buff) {
*data_buff = malloc(data->d_size);
if (!*data_buff) {
@@ -827,30 +851,61 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
return 0;
}
-static int
-bpf_object__init_maps(struct bpf_object *obj, int flags)
+static int bpf_object__init_global_data_maps(struct bpf_object *obj)
+{
+ int err;
+
+ if (!obj->caps.global_data)
+ return 0;
+ /*
+ * Populate obj->maps with libbpf internal maps.
+ */
+ if (obj->efile.data_shndx >= 0) {
+ err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
+ obj->efile.data_shndx,
+ obj->efile.data,
+ &obj->sections.data);
+ if (err)
+ return err;
+ }
+ if (obj->efile.rodata_shndx >= 0) {
+ err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
+ obj->efile.rodata_shndx,
+ obj->efile.rodata,
+ &obj->sections.rodata);
+ if (err)
+ return err;
+ }
+ if (obj->efile.bss_shndx >= 0) {
+ err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
+ obj->efile.bss_shndx,
+ obj->efile.bss, NULL);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
{
- int i, map_idx, map_def_sz = 0, nr_syms, nr_maps = 0, nr_maps_glob = 0;
- bool strict = !(flags & MAPS_RELAX_COMPAT);
Elf_Data *symbols = obj->efile.symbols;
+ int i, map_def_sz = 0, nr_maps = 0, nr_syms;
Elf_Data *data = NULL;
- int ret = 0;
+ Elf_Scn *scn;
+
+ if (obj->efile.maps_shndx < 0)
+ return 0;
if (!symbols)
return -EINVAL;
- nr_syms = symbols->d_size / sizeof(GElf_Sym);
- if (obj->efile.maps_shndx >= 0) {
- Elf_Scn *scn = elf_getscn(obj->efile.elf,
- obj->efile.maps_shndx);
-
- if (scn)
- data = elf_getdata(scn, NULL);
- if (!scn || !data) {
- pr_warning("failed to get Elf_Data from map section %d\n",
- obj->efile.maps_shndx);
- return -EINVAL;
- }
+ scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx);
+ if (scn)
+ data = elf_getdata(scn, NULL);
+ if (!scn || !data) {
+ pr_warning("failed to get Elf_Data from map section %d\n",
+ obj->efile.maps_shndx);
+ return -EINVAL;
}
/*
@@ -860,16 +915,8 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
*
* TODO: Detect array of map and report error.
*/
- if (obj->caps.global_data) {
- if (obj->efile.data_shndx >= 0)
- nr_maps_glob++;
- if (obj->efile.rodata_shndx >= 0)
- nr_maps_glob++;
- if (obj->efile.bss_shndx >= 0)
- nr_maps_glob++;
- }
-
- for (i = 0; data && i < nr_syms; i++) {
+ nr_syms = symbols->d_size / sizeof(GElf_Sym);
+ for (i = 0; i < nr_syms; i++) {
GElf_Sym sym;
if (!gelf_getsym(symbols, i, &sym))
@@ -878,74 +925,59 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
continue;
nr_maps++;
}
-
- if (!nr_maps && !nr_maps_glob)
- return 0;
-
/* Assume equally sized map definitions */
- if (data) {
- pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path,
- nr_maps, data->d_size);
-
- map_def_sz = data->d_size / nr_maps;
- if (!data->d_size || (data->d_size % nr_maps) != 0) {
- pr_warning("unable to determine map definition size "
- "section %s, %d maps in %zd bytes\n",
- obj->path, nr_maps, data->d_size);
- return -EINVAL;
- }
- }
-
- nr_maps += nr_maps_glob;
- obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
- if (!obj->maps) {
- pr_warning("alloc maps for object failed\n");
- return -ENOMEM;
- }
- obj->nr_maps = nr_maps;
-
- for (i = 0; i < nr_maps; i++) {
- /*
- * fill all fd with -1 so won't close incorrect
- * fd (fd=0 is stdin) when failure (zclose won't close
- * negative fd)).
- */
- obj->maps[i].fd = -1;
- obj->maps[i].inner_map_fd = -1;
+ pr_debug("maps in %s: %d maps in %zd bytes\n",
+ obj->path, nr_maps, data->d_size);
+
+ map_def_sz = data->d_size / nr_maps;
+ if (!data->d_size || (data->d_size % nr_maps) != 0) {
+ pr_warning("unable to determine map definition size "
+ "section %s, %d maps in %zd bytes\n",
+ obj->path, nr_maps, data->d_size);
+ return -EINVAL;
}
- /*
- * Fill obj->maps using data in "maps" section.
- */
- for (i = 0, map_idx = 0; data && i < nr_syms; i++) {
+ /* Fill obj->maps using data in "maps" section. */
+ for (i = 0; i < nr_syms; i++) {
GElf_Sym sym;
const char *map_name;
struct bpf_map_def *def;
+ struct bpf_map *map;
if (!gelf_getsym(symbols, i, &sym))
continue;
if (sym.st_shndx != obj->efile.maps_shndx)
continue;
- map_name = elf_strptr(obj->efile.elf,
- obj->efile.strtabidx,
+ map = bpf_object__add_map(obj);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
sym.st_name);
+ if (!map_name) {
+ pr_warning("failed to get map #%d name sym string for obj %s\n",
+ i, obj->path);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
- obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC;
- obj->maps[map_idx].offset = sym.st_value;
+ map->libbpf_type = LIBBPF_MAP_UNSPEC;
+ map->sec_idx = sym.st_shndx;
+ map->sec_offset = sym.st_value;
+ pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n",
+ map_name, map->sec_idx, map->sec_offset);
if (sym.st_value + map_def_sz > data->d_size) {
pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
obj->path, map_name);
return -EINVAL;
}
- obj->maps[map_idx].name = strdup(map_name);
- if (!obj->maps[map_idx].name) {
+ map->name = strdup(map_name);
+ if (!map->name) {
pr_warning("failed to alloc map name\n");
return -ENOMEM;
}
- pr_debug("map %d is \"%s\"\n", map_idx,
- obj->maps[map_idx].name);
+ pr_debug("map %d is \"%s\"\n", i, map->name);
def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
/*
* If the definition of the map in the object file fits in
@@ -954,7 +986,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
* calloc above.
*/
if (map_def_sz <= sizeof(struct bpf_map_def)) {
- memcpy(&obj->maps[map_idx].def, def, map_def_sz);
+ memcpy(&map->def, def, map_def_sz);
} else {
/*
* Here the map structure being read is bigger than what
@@ -974,37 +1006,338 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
return -EINVAL;
}
}
- memcpy(&obj->maps[map_idx].def, def,
- sizeof(struct bpf_map_def));
+ memcpy(&map->def, def, sizeof(struct bpf_map_def));
}
- map_idx++;
}
+ return 0;
+}
- if (!obj->caps.global_data)
- goto finalize;
+static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf,
+ __u32 id)
+{
+ const struct btf_type *t = btf__type_by_id(btf, id);
- /*
- * Populate rest of obj->maps with libbpf internal maps.
- */
- if (obj->efile.data_shndx >= 0)
- ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
- LIBBPF_MAP_DATA,
- obj->efile.data,
- &obj->sections.data);
- if (!ret && obj->efile.rodata_shndx >= 0)
- ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
- LIBBPF_MAP_RODATA,
- obj->efile.rodata,
- &obj->sections.rodata);
- if (!ret && obj->efile.bss_shndx >= 0)
- ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
- LIBBPF_MAP_BSS,
- obj->efile.bss, NULL);
-finalize:
- if (!ret)
+ while (true) {
+ switch (BTF_INFO_KIND(t->info)) {
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_TYPEDEF:
+ t = btf__type_by_id(btf, t->type);
+ break;
+ default:
+ return t;
+ }
+ }
+}
+
+/*
+ * Fetch integer attribute of BTF map definition. Such attributes are
+ * represented using a pointer to an array, in which dimensionality of array
+ * encodes specified integer value. E.g., int (*type)[BPF_MAP_TYPE_ARRAY];
+ * encodes `type => BPF_MAP_TYPE_ARRAY` key/value pair completely using BTF
+ * type definition, while using only sizeof(void *) space in ELF data section.
+ */
+static bool get_map_field_int(const char *map_name, const struct btf *btf,
+ const struct btf_type *def,
+ const struct btf_member *m, __u32 *res) {
+ const struct btf_type *t = skip_mods_and_typedefs(btf, m->type);
+ const char *name = btf__name_by_offset(btf, m->name_off);
+ const struct btf_array *arr_info;
+ const struct btf_type *arr_t;
+
+ if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) {
+ pr_warning("map '%s': attr '%s': expected PTR, got %u.\n",
+ map_name, name, BTF_INFO_KIND(t->info));
+ return false;
+ }
+
+ arr_t = btf__type_by_id(btf, t->type);
+ if (!arr_t) {
+ pr_warning("map '%s': attr '%s': type [%u] not found.\n",
+ map_name, name, t->type);
+ return false;
+ }
+ if (BTF_INFO_KIND(arr_t->info) != BTF_KIND_ARRAY) {
+ pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n",
+ map_name, name, BTF_INFO_KIND(arr_t->info));
+ return false;
+ }
+ arr_info = (const void *)(arr_t + 1);
+ *res = arr_info->nelems;
+ return true;
+}
+
+static int bpf_object__init_user_btf_map(struct bpf_object *obj,
+ const struct btf_type *sec,
+ int var_idx, int sec_idx,
+ const Elf_Data *data, bool strict)
+{
+ const struct btf_type *var, *def, *t;
+ const struct btf_var_secinfo *vi;
+ const struct btf_var *var_extra;
+ const struct btf_member *m;
+ const char *map_name;
+ struct bpf_map *map;
+ int vlen, i;
+
+ vi = (const struct btf_var_secinfo *)(const void *)(sec + 1) + var_idx;
+ var = btf__type_by_id(obj->btf, vi->type);
+ var_extra = (const void *)(var + 1);
+ map_name = btf__name_by_offset(obj->btf, var->name_off);
+ vlen = BTF_INFO_VLEN(var->info);
+
+ if (map_name == NULL || map_name[0] == '\0') {
+ pr_warning("map #%d: empty name.\n", var_idx);
+ return -EINVAL;
+ }
+ if ((__u64)vi->offset + vi->size > data->d_size) {
+ pr_warning("map '%s' BTF data is corrupted.\n", map_name);
+ return -EINVAL;
+ }
+ if (BTF_INFO_KIND(var->info) != BTF_KIND_VAR) {
+ pr_warning("map '%s': unexpected var kind %u.\n",
+ map_name, BTF_INFO_KIND(var->info));
+ return -EINVAL;
+ }
+ if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED &&
+ var_extra->linkage != BTF_VAR_STATIC) {
+ pr_warning("map '%s': unsupported var linkage %u.\n",
+ map_name, var_extra->linkage);
+ return -EOPNOTSUPP;
+ }
+
+ def = skip_mods_and_typedefs(obj->btf, var->type);
+ if (BTF_INFO_KIND(def->info) != BTF_KIND_STRUCT) {
+ pr_warning("map '%s': unexpected def kind %u.\n",
+ map_name, BTF_INFO_KIND(var->info));
+ return -EINVAL;
+ }
+ if (def->size > vi->size) {
+ pr_warning("map '%s': invalid def size.\n", map_name);
+ return -EINVAL;
+ }
+
+ map = bpf_object__add_map(obj);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+ map->name = strdup(map_name);
+ if (!map->name) {
+ pr_warning("map '%s': failed to alloc map name.\n", map_name);
+ return -ENOMEM;
+ }
+ map->libbpf_type = LIBBPF_MAP_UNSPEC;
+ map->def.type = BPF_MAP_TYPE_UNSPEC;
+ map->sec_idx = sec_idx;
+ map->sec_offset = vi->offset;
+ pr_debug("map '%s': at sec_idx %d, offset %zu.\n",
+ map_name, map->sec_idx, map->sec_offset);
+
+ vlen = BTF_INFO_VLEN(def->info);
+ m = (const void *)(def + 1);
+ for (i = 0; i < vlen; i++, m++) {
+ const char *name = btf__name_by_offset(obj->btf, m->name_off);
+
+ if (!name) {
+ pr_warning("map '%s': invalid field #%d.\n",
+ map_name, i);
+ return -EINVAL;
+ }
+ if (strcmp(name, "type") == 0) {
+ if (!get_map_field_int(map_name, obj->btf, def, m,
+ &map->def.type))
+ return -EINVAL;
+ pr_debug("map '%s': found type = %u.\n",
+ map_name, map->def.type);
+ } else if (strcmp(name, "max_entries") == 0) {
+ if (!get_map_field_int(map_name, obj->btf, def, m,
+ &map->def.max_entries))
+ return -EINVAL;
+ pr_debug("map '%s': found max_entries = %u.\n",
+ map_name, map->def.max_entries);
+ } else if (strcmp(name, "map_flags") == 0) {
+ if (!get_map_field_int(map_name, obj->btf, def, m,
+ &map->def.map_flags))
+ return -EINVAL;
+ pr_debug("map '%s': found map_flags = %u.\n",
+ map_name, map->def.map_flags);
+ } else if (strcmp(name, "key_size") == 0) {
+ __u32 sz;
+
+ if (!get_map_field_int(map_name, obj->btf, def, m,
+ &sz))
+ return -EINVAL;
+ pr_debug("map '%s': found key_size = %u.\n",
+ map_name, sz);
+ if (map->def.key_size && map->def.key_size != sz) {
+ pr_warning("map '%s': conflicting key size %u != %u.\n",
+ map_name, map->def.key_size, sz);
+ return -EINVAL;
+ }
+ map->def.key_size = sz;
+ } else if (strcmp(name, "key") == 0) {
+ __s64 sz;
+
+ t = btf__type_by_id(obj->btf, m->type);
+ if (!t) {
+ pr_warning("map '%s': key type [%d] not found.\n",
+ map_name, m->type);
+ return -EINVAL;
+ }
+ if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) {
+ pr_warning("map '%s': key spec is not PTR: %u.\n",
+ map_name, BTF_INFO_KIND(t->info));
+ return -EINVAL;
+ }
+ sz = btf__resolve_size(obj->btf, t->type);
+ if (sz < 0) {
+ pr_warning("map '%s': can't determine key size for type [%u]: %lld.\n",
+ map_name, t->type, sz);
+ return sz;
+ }
+ pr_debug("map '%s': found key [%u], sz = %lld.\n",
+ map_name, t->type, sz);
+ if (map->def.key_size && map->def.key_size != sz) {
+ pr_warning("map '%s': conflicting key size %u != %lld.\n",
+ map_name, map->def.key_size, sz);
+ return -EINVAL;
+ }
+ map->def.key_size = sz;
+ map->btf_key_type_id = t->type;
+ } else if (strcmp(name, "value_size") == 0) {
+ __u32 sz;
+
+ if (!get_map_field_int(map_name, obj->btf, def, m,
+ &sz))
+ return -EINVAL;
+ pr_debug("map '%s': found value_size = %u.\n",
+ map_name, sz);
+ if (map->def.value_size && map->def.value_size != sz) {
+ pr_warning("map '%s': conflicting value size %u != %u.\n",
+ map_name, map->def.value_size, sz);
+ return -EINVAL;
+ }
+ map->def.value_size = sz;
+ } else if (strcmp(name, "value") == 0) {
+ __s64 sz;
+
+ t = btf__type_by_id(obj->btf, m->type);
+ if (!t) {
+ pr_warning("map '%s': value type [%d] not found.\n",
+ map_name, m->type);
+ return -EINVAL;
+ }
+ if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) {
+ pr_warning("map '%s': value spec is not PTR: %u.\n",
+ map_name, BTF_INFO_KIND(t->info));
+ return -EINVAL;
+ }
+ sz = btf__resolve_size(obj->btf, t->type);
+ if (sz < 0) {
+ pr_warning("map '%s': can't determine value size for type [%u]: %lld.\n",
+ map_name, t->type, sz);
+ return sz;
+ }
+ pr_debug("map '%s': found value [%u], sz = %lld.\n",
+ map_name, t->type, sz);
+ if (map->def.value_size && map->def.value_size != sz) {
+ pr_warning("map '%s': conflicting value size %u != %lld.\n",
+ map_name, map->def.value_size, sz);
+ return -EINVAL;
+ }
+ map->def.value_size = sz;
+ map->btf_value_type_id = t->type;
+ } else {
+ if (strict) {
+ pr_warning("map '%s': unknown field '%s'.\n",
+ map_name, name);
+ return -ENOTSUP;
+ }
+ pr_debug("map '%s': ignoring unknown field '%s'.\n",
+ map_name, name);
+ }
+ }
+
+ if (map->def.type == BPF_MAP_TYPE_UNSPEC) {
+ pr_warning("map '%s': map type isn't specified.\n", map_name);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict)
+{
+ const struct btf_type *sec = NULL;
+ int nr_types, i, vlen, err;
+ const struct btf_type *t;
+ const char *name;
+ Elf_Data *data;
+ Elf_Scn *scn;
+
+ if (obj->efile.btf_maps_shndx < 0)
+ return 0;
+
+ scn = elf_getscn(obj->efile.elf, obj->efile.btf_maps_shndx);
+ if (scn)
+ data = elf_getdata(scn, NULL);
+ if (!scn || !data) {
+ pr_warning("failed to get Elf_Data from map section %d (%s)\n",
+ obj->efile.maps_shndx, MAPS_ELF_SEC);
+ return -EINVAL;
+ }
+
+ nr_types = btf__get_nr_types(obj->btf);
+ for (i = 1; i <= nr_types; i++) {
+ t = btf__type_by_id(obj->btf, i);
+ if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC)
+ continue;
+ name = btf__name_by_offset(obj->btf, t->name_off);
+ if (strcmp(name, MAPS_ELF_SEC) == 0) {
+ sec = t;
+ break;
+ }
+ }
+
+ if (!sec) {
+ pr_warning("DATASEC '%s' not found.\n", MAPS_ELF_SEC);
+ return -ENOENT;
+ }
+
+ vlen = BTF_INFO_VLEN(sec->info);
+ for (i = 0; i < vlen; i++) {
+ err = bpf_object__init_user_btf_map(obj, sec, i,
+ obj->efile.btf_maps_shndx,
+ data, strict);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int bpf_object__init_maps(struct bpf_object *obj, int flags)
+{
+ bool strict = !(flags & MAPS_RELAX_COMPAT);
+ int err;
+
+ err = bpf_object__init_user_maps(obj, strict);
+ if (err)
+ return err;
+
+ err = bpf_object__init_user_btf_maps(obj, strict);
+ if (err)
+ return err;
+
+ err = bpf_object__init_global_data_maps(obj);
+ if (err)
+ return err;
+
+ if (obj->nr_maps) {
qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
compare_bpf_map);
- return ret;
+ }
+ return 0;
}
static bool section_have_execinstr(struct bpf_object *obj, int idx)
@@ -1093,6 +1426,86 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj)
}
}
+static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
+{
+ return obj->efile.btf_maps_shndx >= 0;
+}
+
+static int bpf_object__init_btf(struct bpf_object *obj,
+ Elf_Data *btf_data,
+ Elf_Data *btf_ext_data)
+{
+ bool btf_required = bpf_object__is_btf_mandatory(obj);
+ int err = 0;
+
+ if (btf_data) {
+ obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
+ if (IS_ERR(obj->btf)) {
+ pr_warning("Error loading ELF section %s: %d.\n",
+ BTF_ELF_SEC, err);
+ goto out;
+ }
+ err = btf__finalize_data(obj, obj->btf);
+ if (err) {
+ pr_warning("Error finalizing %s: %d.\n",
+ BTF_ELF_SEC, err);
+ goto out;
+ }
+ }
+ if (btf_ext_data) {
+ if (!obj->btf) {
+ pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n",
+ BTF_EXT_ELF_SEC, BTF_ELF_SEC);
+ goto out;
+ }
+ obj->btf_ext = btf_ext__new(btf_ext_data->d_buf,
+ btf_ext_data->d_size);
+ if (IS_ERR(obj->btf_ext)) {
+ pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
+ BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext));
+ obj->btf_ext = NULL;
+ goto out;
+ }
+ }
+out:
+ if (err || IS_ERR(obj->btf)) {
+ if (btf_required)
+ err = err ? : PTR_ERR(obj->btf);
+ else
+ err = 0;
+ if (!IS_ERR_OR_NULL(obj->btf))
+ btf__free(obj->btf);
+ obj->btf = NULL;
+ }
+ if (btf_required && !obj->btf) {
+ pr_warning("BTF is required, but is missing or corrupted.\n");
+ return err == 0 ? -ENOENT : err;
+ }
+ return 0;
+}
+
+static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
+{
+ int err = 0;
+
+ if (!obj->btf)
+ return 0;
+
+ bpf_object__sanitize_btf(obj);
+ bpf_object__sanitize_btf_ext(obj);
+
+ err = btf__load(obj->btf);
+ if (err) {
+ pr_warning("Error loading %s into kernel: %d.\n",
+ BTF_ELF_SEC, err);
+ btf__free(obj->btf);
+ obj->btf = NULL;
+ if (bpf_object__is_btf_mandatory(obj))
+ return err;
+ }
+ return 0;
+}
+
static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
{
Elf *elf = obj->efile.elf;
@@ -1104,8 +1517,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
/* Elf is corrupted/truncated, avoid calling elf_strptr. */
if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
- pr_warning("failed to get e_shstrndx from %s\n",
- obj->path);
+ pr_warning("failed to get e_shstrndx from %s\n", obj->path);
return -LIBBPF_ERRNO__FORMAT;
}
@@ -1118,24 +1530,21 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
if (gelf_getshdr(scn, &sh) != &sh) {
pr_warning("failed to get section(%d) header from %s\n",
idx, obj->path);
- err = -LIBBPF_ERRNO__FORMAT;
- goto out;
+ return -LIBBPF_ERRNO__FORMAT;
}
name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
if (!name) {
pr_warning("failed to get section(%d) name from %s\n",
idx, obj->path);
- err = -LIBBPF_ERRNO__FORMAT;
- goto out;
+ return -LIBBPF_ERRNO__FORMAT;
}
data = elf_getdata(scn, 0);
if (!data) {
pr_warning("failed to get section(%d) data from %s(%s)\n",
idx, name, obj->path);
- err = -LIBBPF_ERRNO__FORMAT;
- goto out;
+ return -LIBBPF_ERRNO__FORMAT;
}
pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
idx, name, (unsigned long)data->d_size,
@@ -1146,12 +1555,18 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
err = bpf_object__init_license(obj,
data->d_buf,
data->d_size);
+ if (err)
+ return err;
} else if (strcmp(name, "version") == 0) {
err = bpf_object__init_kversion(obj,
data->d_buf,
data->d_size);
+ if (err)
+ return err;
} else if (strcmp(name, "maps") == 0) {
obj->efile.maps_shndx = idx;
+ } else if (strcmp(name, MAPS_ELF_SEC) == 0) {
+ obj->efile.btf_maps_shndx = idx;
} else if (strcmp(name, BTF_ELF_SEC) == 0) {
btf_data = data;
} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
@@ -1160,11 +1575,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
if (obj->efile.symbols) {
pr_warning("bpf: multiple SYMTAB in %s\n",
obj->path);
- err = -LIBBPF_ERRNO__FORMAT;
- } else {
- obj->efile.symbols = data;
- obj->efile.strtabidx = sh.sh_link;
+ return -LIBBPF_ERRNO__FORMAT;
}
+ obj->efile.symbols = data;
+ obj->efile.strtabidx = sh.sh_link;
} else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) {
if (sh.sh_flags & SHF_EXECINSTR) {
if (strcmp(name, ".text") == 0)
@@ -1178,6 +1592,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
pr_warning("failed to alloc program %s (%s): %s",
name, obj->path, cp);
+ return err;
}
} else if (strcmp(name, ".data") == 0) {
obj->efile.data = data;
@@ -1189,8 +1604,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
pr_debug("skip section(%d) %s\n", idx, name);
}
} else if (sh.sh_type == SHT_REL) {
+ int nr_reloc = obj->efile.nr_reloc;
void *reloc = obj->efile.reloc;
- int nr_reloc = obj->efile.nr_reloc + 1;
int sec = sh.sh_info; /* points to other section */
/* Only do relo for section with exec instructions */
@@ -1200,79 +1615,37 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
continue;
}
- reloc = reallocarray(reloc, nr_reloc,
+ reloc = reallocarray(reloc, nr_reloc + 1,
sizeof(*obj->efile.reloc));
if (!reloc) {
pr_warning("realloc failed\n");
- err = -ENOMEM;
- } else {
- int n = nr_reloc - 1;
+ return -ENOMEM;
+ }
- obj->efile.reloc = reloc;
- obj->efile.nr_reloc = nr_reloc;
+ obj->efile.reloc = reloc;
+ obj->efile.nr_reloc++;
- obj->efile.reloc[n].shdr = sh;
- obj->efile.reloc[n].data = data;
- }
+ obj->efile.reloc[nr_reloc].shdr = sh;
+ obj->efile.reloc[nr_reloc].data = data;
} else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) {
obj->efile.bss = data;
obj->efile.bss_shndx = idx;
} else {
pr_debug("skip section(%d) %s\n", idx, name);
}
- if (err)
- goto out;
}
if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
pr_warning("Corrupted ELF file: index of strtab invalid\n");
- return LIBBPF_ERRNO__FORMAT;
- }
- if (btf_data) {
- obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
- if (IS_ERR(obj->btf)) {
- pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
- BTF_ELF_SEC, PTR_ERR(obj->btf));
- obj->btf = NULL;
- } else {
- err = btf__finalize_data(obj, obj->btf);
- if (!err) {
- bpf_object__sanitize_btf(obj);
- err = btf__load(obj->btf);
- }
- if (err) {
- pr_warning("Error finalizing and loading %s into kernel: %d. Ignored and continue.\n",
- BTF_ELF_SEC, err);
- btf__free(obj->btf);
- obj->btf = NULL;
- err = 0;
- }
- }
- }
- if (btf_ext_data) {
- if (!obj->btf) {
- pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n",
- BTF_EXT_ELF_SEC, BTF_ELF_SEC);
- } else {
- obj->btf_ext = btf_ext__new(btf_ext_data->d_buf,
- btf_ext_data->d_size);
- if (IS_ERR(obj->btf_ext)) {
- pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
- BTF_EXT_ELF_SEC,
- PTR_ERR(obj->btf_ext));
- obj->btf_ext = NULL;
- } else {
- bpf_object__sanitize_btf_ext(obj);
- }
- }
+ return -LIBBPF_ERRNO__FORMAT;
}
- if (bpf_object__has_maps(obj)) {
+ err = bpf_object__init_btf(obj, btf_data, btf_ext_data);
+ if (!err)
err = bpf_object__init_maps(obj, flags);
- if (err)
- goto out;
- }
- err = bpf_object__init_prog_names(obj);
-out:
+ if (!err)
+ err = bpf_object__sanitize_and_load_btf(obj);
+ if (!err)
+ err = bpf_object__init_prog_names(obj);
return err;
}
@@ -1291,7 +1664,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
}
struct bpf_program *
-bpf_object__find_program_by_title(struct bpf_object *obj, const char *title)
+bpf_object__find_program_by_title(const struct bpf_object *obj,
+ const char *title)
{
struct bpf_program *pos;
@@ -1313,7 +1687,8 @@ static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
int shndx)
{
- return shndx == obj->efile.maps_shndx;
+ return shndx == obj->efile.maps_shndx ||
+ shndx == obj->efile.btf_maps_shndx;
}
static bool bpf_object__relo_in_known_section(const struct bpf_object *obj,
@@ -1346,8 +1721,7 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
size_t nr_maps = obj->nr_maps;
int i, nrels;
- pr_debug("collecting relocating info for: '%s'\n",
- prog->section_name);
+ pr_debug("collecting relocating info for: '%s'\n", prog->section_name);
nrels = shdr->sh_size / shdr->sh_entsize;
prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels);
@@ -1358,23 +1732,21 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
prog->nr_reloc = nrels;
for (i = 0; i < nrels; i++) {
- GElf_Sym sym;
- GElf_Rel rel;
- unsigned int insn_idx;
- unsigned int shdr_idx;
struct bpf_insn *insns = prog->insns;
enum libbpf_map_type type;
+ unsigned int insn_idx;
+ unsigned int shdr_idx;
const char *name;
size_t map_idx;
+ GElf_Sym sym;
+ GElf_Rel rel;
if (!gelf_getrel(data, i, &rel)) {
pr_warning("relocation: failed to get %d reloc\n", i);
return -LIBBPF_ERRNO__FORMAT;
}
- if (!gelf_getsym(symbols,
- GELF_R_SYM(rel.r_info),
- &sym)) {
+ if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
pr_warning("relocation: symbol %"PRIx64" not found\n",
GELF_R_SYM(rel.r_info));
return -LIBBPF_ERRNO__FORMAT;
@@ -1435,16 +1807,19 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
if (maps[map_idx].libbpf_type != type)
continue;
if (type != LIBBPF_MAP_UNSPEC ||
- (type == LIBBPF_MAP_UNSPEC &&
- maps[map_idx].offset == sym.st_value)) {
- pr_debug("relocation: find map %zd (%s) for insn %u\n",
- map_idx, maps[map_idx].name, insn_idx);
+ (maps[map_idx].sec_idx == sym.st_shndx &&
+ maps[map_idx].sec_offset == sym.st_value)) {
+ pr_debug("relocation: found map %zd (%s, sec_idx %d, offset %zu) for insn %u\n",
+ map_idx, maps[map_idx].name,
+ maps[map_idx].sec_idx,
+ maps[map_idx].sec_offset,
+ insn_idx);
break;
}
}
if (map_idx >= nr_maps) {
- pr_warning("bpf relocation: map_idx %d large than %d\n",
+ pr_warning("bpf relocation: map_idx %d larger than %d\n",
(int)map_idx, (int)nr_maps - 1);
return -LIBBPF_ERRNO__RELOC;
}
@@ -1458,14 +1833,18 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
return 0;
}
-static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
+static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
{
struct bpf_map_def *def = &map->def;
__u32 key_type_id = 0, value_type_id = 0;
int ret;
+ /* if it's BTF-defined map, we don't need to search for type IDs */
+ if (map->sec_idx == obj->efile.btf_maps_shndx)
+ return 0;
+
if (!bpf_map__is_internal(map)) {
- ret = btf__get_map_kv_tids(btf, map->name, def->key_size,
+ ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size,
def->value_size, &key_type_id,
&value_type_id);
} else {
@@ -1473,7 +1852,7 @@ static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
* LLVM annotates global data differently in BTF, that is,
* only as '.data', '.bss' or '.rodata'.
*/
- ret = btf__find_by_name(btf,
+ ret = btf__find_by_name(obj->btf,
libbpf_type_to_btf_name[map->libbpf_type]);
}
if (ret < 0)
@@ -1737,6 +2116,7 @@ static int
bpf_object__create_maps(struct bpf_object *obj)
{
struct bpf_create_map_attr create_attr = {};
+ int nr_cpus = 0;
unsigned int i;
int err;
@@ -1759,7 +2139,22 @@ bpf_object__create_maps(struct bpf_object *obj)
create_attr.map_flags = def->map_flags;
create_attr.key_size = def->key_size;
create_attr.value_size = def->value_size;
- create_attr.max_entries = def->max_entries;
+ if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY &&
+ !def->max_entries) {
+ if (!nr_cpus)
+ nr_cpus = libbpf_num_possible_cpus();
+ if (nr_cpus < 0) {
+ pr_warning("failed to determine number of system CPUs: %d\n",
+ nr_cpus);
+ err = nr_cpus;
+ goto err_out;
+ }
+ pr_debug("map '%s': setting size to %d\n",
+ map->name, nr_cpus);
+ create_attr.max_entries = nr_cpus;
+ } else {
+ create_attr.max_entries = def->max_entries;
+ }
create_attr.btf_fd = 0;
create_attr.btf_key_type_id = 0;
create_attr.btf_value_type_id = 0;
@@ -1767,17 +2162,19 @@ bpf_object__create_maps(struct bpf_object *obj)
map->inner_map_fd >= 0)
create_attr.inner_map_fd = map->inner_map_fd;
- if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
+ if (obj->btf && !bpf_map_find_btf_info(obj, map)) {
create_attr.btf_fd = btf__fd(obj->btf);
create_attr.btf_key_type_id = map->btf_key_type_id;
create_attr.btf_value_type_id = map->btf_value_type_id;
}
*pfd = bpf_create_map_xattr(&create_attr);
- if (*pfd < 0 && create_attr.btf_key_type_id) {
- cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+ if (*pfd < 0 && (create_attr.btf_key_type_id ||
+ create_attr.btf_value_type_id)) {
+ err = -errno;
+ cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
- map->name, cp, errno);
+ map->name, cp, err);
create_attr.btf_fd = 0;
create_attr.btf_key_type_id = 0;
create_attr.btf_value_type_id = 0;
@@ -1789,11 +2186,11 @@ bpf_object__create_maps(struct bpf_object *obj)
if (*pfd < 0) {
size_t j;
- err = *pfd;
+ err = -errno;
err_out:
- cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
- pr_warning("failed to create map (name: '%s'): %s\n",
- map->name, cp);
+ cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
+ pr_warning("failed to create map (name: '%s'): %s(%d)\n",
+ map->name, cp, err);
for (j = 0; j < i; j++)
zclose(obj->maps[j].fd);
return err;
@@ -1807,7 +2204,7 @@ err_out:
}
}
- pr_debug("create map %s: fd=%d\n", map->name, *pfd);
+ pr_debug("created map %s: fd=%d\n", map->name, *pfd);
}
return 0;
@@ -1828,18 +2225,14 @@ check_btf_ext_reloc_err(struct bpf_program *prog, int err,
if (btf_prog_info) {
/*
* Some info has already been found but has problem
- * in the last btf_ext reloc. Must have to error
- * out.
+ * in the last btf_ext reloc. Must have to error out.
*/
pr_warning("Error in relocating %s for sec %s.\n",
info_name, prog->section_name);
return err;
}
- /*
- * Have problem loading the very first info. Ignore
- * the rest.
- */
+ /* Have problem loading the very first info. Ignore the rest. */
pr_warning("Cannot find %s for main program sec %s. Ignore all %s.\n",
info_name, prog->section_name, info_name);
return 0;
@@ -2043,9 +2436,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
return -LIBBPF_ERRNO__RELOC;
}
- err = bpf_program__collect_reloc(prog,
- shdr, data,
- obj);
+ err = bpf_program__collect_reloc(prog, shdr, data, obj);
if (err)
return err;
}
@@ -2062,6 +2453,9 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
char *log_buf;
int ret;
+ if (!insns || !insns_cnt)
+ return -EINVAL;
+
memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
load_attr.prog_type = prog->type;
load_attr.expected_attach_type = prog->expected_attach_type;
@@ -2080,8 +2474,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
load_attr.line_info_rec_size = prog->line_info_rec_size;
load_attr.line_info_cnt = prog->line_info_cnt;
load_attr.log_level = prog->log_level;
- if (!load_attr.insns || !load_attr.insns_cnt)
- return -EINVAL;
+ load_attr.prog_flags = prog->prog_flags;
retry_load:
log_buf = malloc(log_buf_size);
@@ -2219,14 +2612,14 @@ out:
return err;
}
-static bool bpf_program__is_function_storage(struct bpf_program *prog,
- struct bpf_object *obj)
+static bool bpf_program__is_function_storage(const struct bpf_program *prog,
+ const struct bpf_object *obj)
{
return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls;
}
static int
-bpf_object__load_progs(struct bpf_object *obj)
+bpf_object__load_progs(struct bpf_object *obj, int log_level)
{
size_t i;
int err;
@@ -2234,6 +2627,7 @@ bpf_object__load_progs(struct bpf_object *obj)
for (i = 0; i < obj->nr_programs; i++) {
if (bpf_program__is_function_storage(&obj->programs[i], obj))
continue;
+ obj->programs[i].log_level |= log_level;
err = bpf_program__load(&obj->programs[i],
obj->license,
obj->kern_version);
@@ -2270,6 +2664,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
case BPF_PROG_TYPE_PERF_EVENT:
case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
return false;
case BPF_PROG_TYPE_KPROBE:
default:
@@ -2360,11 +2755,9 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf,
snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
(unsigned long)obj_buf,
(unsigned long)obj_buf_sz);
- tmp_name[sizeof(tmp_name) - 1] = '\0';
name = tmp_name;
}
- pr_debug("loading object '%s' from buffer\n",
- name);
+ pr_debug("loading object '%s' from buffer\n", name);
return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true);
}
@@ -2385,10 +2778,14 @@ int bpf_object__unload(struct bpf_object *obj)
return 0;
}
-int bpf_object__load(struct bpf_object *obj)
+int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
{
+ struct bpf_object *obj;
int err;
+ if (!attr)
+ return -EINVAL;
+ obj = attr->obj;
if (!obj)
return -EINVAL;
@@ -2401,7 +2798,7 @@ int bpf_object__load(struct bpf_object *obj)
CHECK_ERR(bpf_object__create_maps(obj), err, out);
CHECK_ERR(bpf_object__relocate(obj), err, out);
- CHECK_ERR(bpf_object__load_progs(obj), err, out);
+ CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out);
return 0;
out:
@@ -2410,6 +2807,15 @@ out:
return err;
}
+int bpf_object__load(struct bpf_object *obj)
+{
+ struct bpf_object_load_attr attr = {
+ .obj = obj,
+ };
+
+ return bpf_object__load_xattr(&attr);
+}
+
static int check_path(const char *path)
{
char *cp, errmsg[STRERR_BUFSIZE];
@@ -2914,17 +3320,17 @@ bpf_object__next(struct bpf_object *prev)
return next;
}
-const char *bpf_object__name(struct bpf_object *obj)
+const char *bpf_object__name(const struct bpf_object *obj)
{
return obj ? obj->path : ERR_PTR(-EINVAL);
}
-unsigned int bpf_object__kversion(struct bpf_object *obj)
+unsigned int bpf_object__kversion(const struct bpf_object *obj)
{
return obj ? obj->kern_version : 0;
}
-struct btf *bpf_object__btf(struct bpf_object *obj)
+struct btf *bpf_object__btf(const struct bpf_object *obj)
{
return obj ? obj->btf : NULL;
}
@@ -2945,13 +3351,14 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv,
return 0;
}
-void *bpf_object__priv(struct bpf_object *obj)
+void *bpf_object__priv(const struct bpf_object *obj)
{
return obj ? obj->priv : ERR_PTR(-EINVAL);
}
static struct bpf_program *
-__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward)
+__bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj,
+ bool forward)
{
size_t nr_programs = obj->nr_programs;
ssize_t idx;
@@ -2976,7 +3383,7 @@ __bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward)
}
struct bpf_program *
-bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj)
{
struct bpf_program *prog = prev;
@@ -2988,7 +3395,7 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
}
struct bpf_program *
-bpf_program__prev(struct bpf_program *next, struct bpf_object *obj)
+bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj)
{
struct bpf_program *prog = next;
@@ -3010,7 +3417,7 @@ int bpf_program__set_priv(struct bpf_program *prog, void *priv,
return 0;
}
-void *bpf_program__priv(struct bpf_program *prog)
+void *bpf_program__priv(const struct bpf_program *prog)
{
return prog ? prog->priv : ERR_PTR(-EINVAL);
}
@@ -3020,7 +3427,7 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
prog->prog_ifindex = ifindex;
}
-const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
+const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy)
{
const char *title;
@@ -3036,7 +3443,7 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
return title;
}
-int bpf_program__fd(struct bpf_program *prog)
+int bpf_program__fd(const struct bpf_program *prog)
{
return bpf_program__nth_fd(prog, 0);
}
@@ -3069,7 +3476,7 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
return 0;
}
-int bpf_program__nth_fd(struct bpf_program *prog, int n)
+int bpf_program__nth_fd(const struct bpf_program *prog, int n)
{
int fd;
@@ -3097,25 +3504,25 @@ void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
prog->type = type;
}
-static bool bpf_program__is_type(struct bpf_program *prog,
+static bool bpf_program__is_type(const struct bpf_program *prog,
enum bpf_prog_type type)
{
return prog ? (prog->type == type) : false;
}
-#define BPF_PROG_TYPE_FNS(NAME, TYPE) \
-int bpf_program__set_##NAME(struct bpf_program *prog) \
-{ \
- if (!prog) \
- return -EINVAL; \
- bpf_program__set_type(prog, TYPE); \
- return 0; \
-} \
- \
-bool bpf_program__is_##NAME(struct bpf_program *prog) \
-{ \
- return bpf_program__is_type(prog, TYPE); \
-} \
+#define BPF_PROG_TYPE_FNS(NAME, TYPE) \
+int bpf_program__set_##NAME(struct bpf_program *prog) \
+{ \
+ if (!prog) \
+ return -EINVAL; \
+ bpf_program__set_type(prog, TYPE); \
+ return 0; \
+} \
+ \
+bool bpf_program__is_##NAME(const struct bpf_program *prog) \
+{ \
+ return bpf_program__is_type(prog, TYPE); \
+} \
BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
@@ -3216,6 +3623,10 @@ static const struct {
BPF_CGROUP_UDP6_RECVMSG),
BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL,
BPF_CGROUP_SYSCTL),
+ BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ BPF_CGROUP_GETSOCKOPT),
+ BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ BPF_CGROUP_SETSOCKOPT),
};
#undef BPF_PROG_SEC_IMPL
@@ -3314,17 +3725,17 @@ bpf_program__identify_section(struct bpf_program *prog,
expected_attach_type);
}
-int bpf_map__fd(struct bpf_map *map)
+int bpf_map__fd(const struct bpf_map *map)
{
return map ? map->fd : -EINVAL;
}
-const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
+const struct bpf_map_def *bpf_map__def(const struct bpf_map *map)
{
return map ? &map->def : ERR_PTR(-EINVAL);
}
-const char *bpf_map__name(struct bpf_map *map)
+const char *bpf_map__name(const struct bpf_map *map)
{
return map ? map->name : NULL;
}
@@ -3355,17 +3766,17 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv,
return 0;
}
-void *bpf_map__priv(struct bpf_map *map)
+void *bpf_map__priv(const struct bpf_map *map)
{
return map ? map->priv : ERR_PTR(-EINVAL);
}
-bool bpf_map__is_offload_neutral(struct bpf_map *map)
+bool bpf_map__is_offload_neutral(const struct bpf_map *map)
{
return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}
-bool bpf_map__is_internal(struct bpf_map *map)
+bool bpf_map__is_internal(const struct bpf_map *map)
{
return map->libbpf_type != LIBBPF_MAP_UNSPEC;
}
@@ -3390,7 +3801,7 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd)
}
static struct bpf_map *
-__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
+__bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
{
ssize_t idx;
struct bpf_map *s, *e;
@@ -3414,7 +3825,7 @@ __bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
}
struct bpf_map *
-bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj)
{
if (prev == NULL)
return obj->maps;
@@ -3423,7 +3834,7 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
}
struct bpf_map *
-bpf_map__prev(struct bpf_map *next, struct bpf_object *obj)
+bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj)
{
if (next == NULL) {
if (!obj->nr_maps)
@@ -3435,7 +3846,7 @@ bpf_map__prev(struct bpf_map *next, struct bpf_object *obj)
}
struct bpf_map *
-bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
+bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name)
{
struct bpf_map *pos;
@@ -3447,7 +3858,7 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
}
int
-bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name)
+bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name)
{
return bpf_map__fd(bpf_object__find_map_by_name(obj, name));
}
@@ -3455,20 +3866,12 @@ bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name)
struct bpf_map *
bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
{
- int i;
-
- for (i = 0; i < obj->nr_maps; i++) {
- if (obj->maps[i].offset == offset)
- return &obj->maps[i];
- }
- return ERR_PTR(-ENOENT);
+ return ERR_PTR(-ENOTSUP);
}
long libbpf_get_error(const void *ptr)
{
- if (IS_ERR(ptr))
- return PTR_ERR(ptr);
- return 0;
+ return PTR_ERR_OR_ZERO(ptr);
}
int bpf_prog_load(const char *file, enum bpf_prog_type type,
@@ -3487,10 +3890,7 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type,
int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
struct bpf_object **pobj, int *prog_fd)
{
- struct bpf_object_open_attr open_attr = {
- .file = attr->file,
- .prog_type = attr->prog_type,
- };
+ struct bpf_object_open_attr open_attr = {};
struct bpf_program *prog, *first_prog = NULL;
enum bpf_attach_type expected_attach_type;
enum bpf_prog_type prog_type;
@@ -3503,6 +3903,9 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
if (!attr->file)
return -EINVAL;
+ open_attr.file = attr->file;
+ open_attr.prog_type = attr->prog_type;
+
obj = bpf_object__open_xattr(&open_attr);
if (IS_ERR_OR_NULL(obj))
return -ENOENT;
@@ -3529,6 +3932,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
expected_attach_type);
prog->log_level = attr->log_level;
+ prog->prog_flags = attr->prog_flags;
if (!first_prog)
first_prog = prog;
}
@@ -3555,6 +3959,372 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
return 0;
}
+struct bpf_link {
+ int (*destroy)(struct bpf_link *link);
+};
+
+int bpf_link__destroy(struct bpf_link *link)
+{
+ int err;
+
+ if (!link)
+ return 0;
+
+ err = link->destroy(link);
+ free(link);
+
+ return err;
+}
+
+struct bpf_link_fd {
+ struct bpf_link link; /* has to be at the top of struct */
+ int fd; /* hook FD */
+};
+
+static int bpf_link__destroy_perf_event(struct bpf_link *link)
+{
+ struct bpf_link_fd *l = (void *)link;
+ int err;
+
+ err = ioctl(l->fd, PERF_EVENT_IOC_DISABLE, 0);
+ if (err)
+ err = -errno;
+
+ close(l->fd);
+ return err;
+}
+
+struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
+ int pfd)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link_fd *link;
+ int prog_fd, err;
+
+ if (pfd < 0) {
+ pr_warning("program '%s': invalid perf event FD %d\n",
+ bpf_program__title(prog, false), pfd);
+ return ERR_PTR(-EINVAL);
+ }
+ prog_fd = bpf_program__fd(prog);
+ if (prog_fd < 0) {
+ pr_warning("program '%s': can't attach BPF program w/o FD (did you load it?)\n",
+ bpf_program__title(prog, false));
+ return ERR_PTR(-EINVAL);
+ }
+
+ link = malloc(sizeof(*link));
+ if (!link)
+ return ERR_PTR(-ENOMEM);
+ link->link.destroy = &bpf_link__destroy_perf_event;
+ link->fd = pfd;
+
+ if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
+ err = -errno;
+ free(link);
+ pr_warning("program '%s': failed to attach to pfd %d: %s\n",
+ bpf_program__title(prog, false), pfd,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return ERR_PTR(err);
+ }
+ if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
+ err = -errno;
+ free(link);
+ pr_warning("program '%s': failed to enable pfd %d: %s\n",
+ bpf_program__title(prog, false), pfd,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return ERR_PTR(err);
+ }
+ return (struct bpf_link *)link;
+}
+
+/*
+ * this function is expected to parse integer in the range of [0, 2^31-1] from
+ * given file using scanf format string fmt. If actual parsed value is
+ * negative, the result might be indistinguishable from error
+ */
+static int parse_uint_from_file(const char *file, const char *fmt)
+{
+ char buf[STRERR_BUFSIZE];
+ int err, ret;
+ FILE *f;
+
+ f = fopen(file, "r");
+ if (!f) {
+ err = -errno;
+ pr_debug("failed to open '%s': %s\n", file,
+ libbpf_strerror_r(err, buf, sizeof(buf)));
+ return err;
+ }
+ err = fscanf(f, fmt, &ret);
+ if (err != 1) {
+ err = err == EOF ? -EIO : -errno;
+ pr_debug("failed to parse '%s': %s\n", file,
+ libbpf_strerror_r(err, buf, sizeof(buf)));
+ fclose(f);
+ return err;
+ }
+ fclose(f);
+ return ret;
+}
+
+static int determine_kprobe_perf_type(void)
+{
+ const char *file = "/sys/bus/event_source/devices/kprobe/type";
+
+ return parse_uint_from_file(file, "%d\n");
+}
+
+static int determine_uprobe_perf_type(void)
+{
+ const char *file = "/sys/bus/event_source/devices/uprobe/type";
+
+ return parse_uint_from_file(file, "%d\n");
+}
+
+static int determine_kprobe_retprobe_bit(void)
+{
+ const char *file = "/sys/bus/event_source/devices/kprobe/format/retprobe";
+
+ return parse_uint_from_file(file, "config:%d\n");
+}
+
+static int determine_uprobe_retprobe_bit(void)
+{
+ const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe";
+
+ return parse_uint_from_file(file, "config:%d\n");
+}
+
+static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
+ uint64_t offset, int pid)
+{
+ struct perf_event_attr attr = {};
+ char errmsg[STRERR_BUFSIZE];
+ int type, pfd, err;
+
+ type = uprobe ? determine_uprobe_perf_type()
+ : determine_kprobe_perf_type();
+ if (type < 0) {
+ pr_warning("failed to determine %s perf type: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(type, errmsg, sizeof(errmsg)));
+ return type;
+ }
+ if (retprobe) {
+ int bit = uprobe ? determine_uprobe_retprobe_bit()
+ : determine_kprobe_retprobe_bit();
+
+ if (bit < 0) {
+ pr_warning("failed to determine %s retprobe bit: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(bit, errmsg,
+ sizeof(errmsg)));
+ return bit;
+ }
+ attr.config |= 1 << bit;
+ }
+ attr.size = sizeof(attr);
+ attr.type = type;
+ attr.config1 = (uint64_t)(void *)name; /* kprobe_func or uprobe_path */
+ attr.config2 = offset; /* kprobe_addr or probe_offset */
+
+ /* pid filter is meaningful only for uprobes */
+ pfd = syscall(__NR_perf_event_open, &attr,
+ pid < 0 ? -1 : pid /* pid */,
+ pid == -1 ? 0 : -1 /* cpu */,
+ -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC);
+ if (pfd < 0) {
+ err = -errno;
+ pr_warning("%s perf_event_open() failed: %s\n",
+ uprobe ? "uprobe" : "kprobe",
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return err;
+ }
+ return pfd;
+}
+
+struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
+ bool retprobe,
+ const char *func_name)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link *link;
+ int pfd, err;
+
+ pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name,
+ 0 /* offset */, -1 /* pid */);
+ if (pfd < 0) {
+ pr_warning("program '%s': failed to create %s '%s' perf event: %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "kretprobe" : "kprobe", func_name,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link = bpf_program__attach_perf_event(prog, pfd);
+ if (IS_ERR(link)) {
+ close(pfd);
+ err = PTR_ERR(link);
+ pr_warning("program '%s': failed to attach to %s '%s': %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "kretprobe" : "kprobe", func_name,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return link;
+ }
+ return link;
+}
+
+struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
+ bool retprobe, pid_t pid,
+ const char *binary_path,
+ size_t func_offset)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link *link;
+ int pfd, err;
+
+ pfd = perf_event_open_probe(true /* uprobe */, retprobe,
+ binary_path, func_offset, pid);
+ if (pfd < 0) {
+ pr_warning("program '%s': failed to create %s '%s:0x%zx' perf event: %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "uretprobe" : "uprobe",
+ binary_path, func_offset,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link = bpf_program__attach_perf_event(prog, pfd);
+ if (IS_ERR(link)) {
+ close(pfd);
+ err = PTR_ERR(link);
+ pr_warning("program '%s': failed to attach to %s '%s:0x%zx': %s\n",
+ bpf_program__title(prog, false),
+ retprobe ? "uretprobe" : "uprobe",
+ binary_path, func_offset,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return link;
+ }
+ return link;
+}
+
+static int determine_tracepoint_id(const char *tp_category,
+ const char *tp_name)
+{
+ char file[PATH_MAX];
+ int ret;
+
+ ret = snprintf(file, sizeof(file),
+ "/sys/kernel/debug/tracing/events/%s/%s/id",
+ tp_category, tp_name);
+ if (ret < 0)
+ return -errno;
+ if (ret >= sizeof(file)) {
+ pr_debug("tracepoint %s/%s path is too long\n",
+ tp_category, tp_name);
+ return -E2BIG;
+ }
+ return parse_uint_from_file(file, "%d\n");
+}
+
+static int perf_event_open_tracepoint(const char *tp_category,
+ const char *tp_name)
+{
+ struct perf_event_attr attr = {};
+ char errmsg[STRERR_BUFSIZE];
+ int tp_id, pfd, err;
+
+ tp_id = determine_tracepoint_id(tp_category, tp_name);
+ if (tp_id < 0) {
+ pr_warning("failed to determine tracepoint '%s/%s' perf event ID: %s\n",
+ tp_category, tp_name,
+ libbpf_strerror_r(tp_id, errmsg, sizeof(errmsg)));
+ return tp_id;
+ }
+
+ attr.type = PERF_TYPE_TRACEPOINT;
+ attr.size = sizeof(attr);
+ attr.config = tp_id;
+
+ pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu */,
+ -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC);
+ if (pfd < 0) {
+ err = -errno;
+ pr_warning("tracepoint '%s/%s' perf_event_open() failed: %s\n",
+ tp_category, tp_name,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return err;
+ }
+ return pfd;
+}
+
+struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
+ const char *tp_category,
+ const char *tp_name)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link *link;
+ int pfd, err;
+
+ pfd = perf_event_open_tracepoint(tp_category, tp_name);
+ if (pfd < 0) {
+ pr_warning("program '%s': failed to create tracepoint '%s/%s' perf event: %s\n",
+ bpf_program__title(prog, false),
+ tp_category, tp_name,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link = bpf_program__attach_perf_event(prog, pfd);
+ if (IS_ERR(link)) {
+ close(pfd);
+ err = PTR_ERR(link);
+ pr_warning("program '%s': failed to attach to tracepoint '%s/%s': %s\n",
+ bpf_program__title(prog, false),
+ tp_category, tp_name,
+ libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+ return link;
+ }
+ return link;
+}
+
+static int bpf_link__destroy_fd(struct bpf_link *link)
+{
+ struct bpf_link_fd *l = (void *)link;
+
+ return close(l->fd);
+}
+
+struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
+ const char *tp_name)
+{
+ char errmsg[STRERR_BUFSIZE];
+ struct bpf_link_fd *link;
+ int prog_fd, pfd;
+
+ prog_fd = bpf_program__fd(prog);
+ if (prog_fd < 0) {
+ pr_warning("program '%s': can't attach before loaded\n",
+ bpf_program__title(prog, false));
+ return ERR_PTR(-EINVAL);
+ }
+
+ link = malloc(sizeof(*link));
+ if (!link)
+ return ERR_PTR(-ENOMEM);
+ link->link.destroy = &bpf_link__destroy_fd;
+
+ pfd = bpf_raw_tracepoint_open(tp_name, prog_fd);
+ if (pfd < 0) {
+ pfd = -errno;
+ free(link);
+ pr_warning("program '%s': failed to attach to raw tracepoint '%s': %s\n",
+ bpf_program__title(prog, false), tp_name,
+ libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+ return ERR_PTR(pfd);
+ }
+ link->fd = pfd;
+ return (struct bpf_link *)link;
+}
+
enum bpf_perf_event_ret
bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
void **copy_mem, size_t *copy_size,
@@ -3603,6 +4373,370 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
return ret;
}
+struct perf_buffer;
+
+struct perf_buffer_params {
+ struct perf_event_attr *attr;
+ /* if event_cb is specified, it takes precendence */
+ perf_buffer_event_fn event_cb;
+ /* sample_cb and lost_cb are higher-level common-case callbacks */
+ perf_buffer_sample_fn sample_cb;
+ perf_buffer_lost_fn lost_cb;
+ void *ctx;
+ int cpu_cnt;
+ int *cpus;
+ int *map_keys;
+};
+
+struct perf_cpu_buf {
+ struct perf_buffer *pb;
+ void *base; /* mmap()'ed memory */
+ void *buf; /* for reconstructing segmented data */
+ size_t buf_size;
+ int fd;
+ int cpu;
+ int map_key;
+};
+
+struct perf_buffer {
+ perf_buffer_event_fn event_cb;
+ perf_buffer_sample_fn sample_cb;
+ perf_buffer_lost_fn lost_cb;
+ void *ctx; /* passed into callbacks */
+
+ size_t page_size;
+ size_t mmap_size;
+ struct perf_cpu_buf **cpu_bufs;
+ struct epoll_event *events;
+ int cpu_cnt;
+ int epoll_fd; /* perf event FD */
+ int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */
+};
+
+static void perf_buffer__free_cpu_buf(struct perf_buffer *pb,
+ struct perf_cpu_buf *cpu_buf)
+{
+ if (!cpu_buf)
+ return;
+ if (cpu_buf->base &&
+ munmap(cpu_buf->base, pb->mmap_size + pb->page_size))
+ pr_warning("failed to munmap cpu_buf #%d\n", cpu_buf->cpu);
+ if (cpu_buf->fd >= 0) {
+ ioctl(cpu_buf->fd, PERF_EVENT_IOC_DISABLE, 0);
+ close(cpu_buf->fd);
+ }
+ free(cpu_buf->buf);
+ free(cpu_buf);
+}
+
+void perf_buffer__free(struct perf_buffer *pb)
+{
+ int i;
+
+ if (!pb)
+ return;
+ if (pb->cpu_bufs) {
+ for (i = 0; i < pb->cpu_cnt && pb->cpu_bufs[i]; i++) {
+ struct perf_cpu_buf *cpu_buf = pb->cpu_bufs[i];
+
+ bpf_map_delete_elem(pb->map_fd, &cpu_buf->map_key);
+ perf_buffer__free_cpu_buf(pb, cpu_buf);
+ }
+ free(pb->cpu_bufs);
+ }
+ if (pb->epoll_fd >= 0)
+ close(pb->epoll_fd);
+ free(pb->events);
+ free(pb);
+}
+
+static struct perf_cpu_buf *
+perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr,
+ int cpu, int map_key)
+{
+ struct perf_cpu_buf *cpu_buf;
+ char msg[STRERR_BUFSIZE];
+ int err;
+
+ cpu_buf = calloc(1, sizeof(*cpu_buf));
+ if (!cpu_buf)
+ return ERR_PTR(-ENOMEM);
+
+ cpu_buf->pb = pb;
+ cpu_buf->cpu = cpu;
+ cpu_buf->map_key = map_key;
+
+ cpu_buf->fd = syscall(__NR_perf_event_open, attr, -1 /* pid */, cpu,
+ -1, PERF_FLAG_FD_CLOEXEC);
+ if (cpu_buf->fd < 0) {
+ err = -errno;
+ pr_warning("failed to open perf buffer event on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ cpu_buf->base = mmap(NULL, pb->mmap_size + pb->page_size,
+ PROT_READ | PROT_WRITE, MAP_SHARED,
+ cpu_buf->fd, 0);
+ if (cpu_buf->base == MAP_FAILED) {
+ cpu_buf->base = NULL;
+ err = -errno;
+ pr_warning("failed to mmap perf buffer on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ if (ioctl(cpu_buf->fd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
+ err = -errno;
+ pr_warning("failed to enable perf buffer event on cpu #%d: %s\n",
+ cpu, libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ return cpu_buf;
+
+error:
+ perf_buffer__free_cpu_buf(pb, cpu_buf);
+ return (struct perf_cpu_buf *)ERR_PTR(err);
+}
+
+static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt,
+ struct perf_buffer_params *p);
+
+struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt,
+ const struct perf_buffer_opts *opts)
+{
+ struct perf_buffer_params p = {};
+ struct perf_event_attr attr = {
+ .config = PERF_COUNT_SW_BPF_OUTPUT,
+ .type = PERF_TYPE_SOFTWARE,
+ .sample_type = PERF_SAMPLE_RAW,
+ .sample_period = 1,
+ .wakeup_events = 1,
+ };
+
+ p.attr = &attr;
+ p.sample_cb = opts ? opts->sample_cb : NULL;
+ p.lost_cb = opts ? opts->lost_cb : NULL;
+ p.ctx = opts ? opts->ctx : NULL;
+
+ return __perf_buffer__new(map_fd, page_cnt, &p);
+}
+
+struct perf_buffer *
+perf_buffer__new_raw(int map_fd, size_t page_cnt,
+ const struct perf_buffer_raw_opts *opts)
+{
+ struct perf_buffer_params p = {};
+
+ p.attr = opts->attr;
+ p.event_cb = opts->event_cb;
+ p.ctx = opts->ctx;
+ p.cpu_cnt = opts->cpu_cnt;
+ p.cpus = opts->cpus;
+ p.map_keys = opts->map_keys;
+
+ return __perf_buffer__new(map_fd, page_cnt, &p);
+}
+
+static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt,
+ struct perf_buffer_params *p)
+{
+ struct bpf_map_info map = {};
+ char msg[STRERR_BUFSIZE];
+ struct perf_buffer *pb;
+ __u32 map_info_len;
+ int err, i;
+
+ if (page_cnt & (page_cnt - 1)) {
+ pr_warning("page count should be power of two, but is %zu\n",
+ page_cnt);
+ return ERR_PTR(-EINVAL);
+ }
+
+ map_info_len = sizeof(map);
+ err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len);
+ if (err) {
+ err = -errno;
+ pr_warning("failed to get map info for map FD %d: %s\n",
+ map_fd, libbpf_strerror_r(err, msg, sizeof(msg)));
+ return ERR_PTR(err);
+ }
+
+ if (map.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+ pr_warning("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
+ map.name);
+ return ERR_PTR(-EINVAL);
+ }
+
+ pb = calloc(1, sizeof(*pb));
+ if (!pb)
+ return ERR_PTR(-ENOMEM);
+
+ pb->event_cb = p->event_cb;
+ pb->sample_cb = p->sample_cb;
+ pb->lost_cb = p->lost_cb;
+ pb->ctx = p->ctx;
+
+ pb->page_size = getpagesize();
+ pb->mmap_size = pb->page_size * page_cnt;
+ pb->map_fd = map_fd;
+
+ pb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+ if (pb->epoll_fd < 0) {
+ err = -errno;
+ pr_warning("failed to create epoll instance: %s\n",
+ libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ if (p->cpu_cnt > 0) {
+ pb->cpu_cnt = p->cpu_cnt;
+ } else {
+ pb->cpu_cnt = libbpf_num_possible_cpus();
+ if (pb->cpu_cnt < 0) {
+ err = pb->cpu_cnt;
+ goto error;
+ }
+ if (map.max_entries < pb->cpu_cnt)
+ pb->cpu_cnt = map.max_entries;
+ }
+
+ pb->events = calloc(pb->cpu_cnt, sizeof(*pb->events));
+ if (!pb->events) {
+ err = -ENOMEM;
+ pr_warning("failed to allocate events: out of memory\n");
+ goto error;
+ }
+ pb->cpu_bufs = calloc(pb->cpu_cnt, sizeof(*pb->cpu_bufs));
+ if (!pb->cpu_bufs) {
+ err = -ENOMEM;
+ pr_warning("failed to allocate buffers: out of memory\n");
+ goto error;
+ }
+
+ for (i = 0; i < pb->cpu_cnt; i++) {
+ struct perf_cpu_buf *cpu_buf;
+ int cpu, map_key;
+
+ cpu = p->cpu_cnt > 0 ? p->cpus[i] : i;
+ map_key = p->cpu_cnt > 0 ? p->map_keys[i] : i;
+
+ cpu_buf = perf_buffer__open_cpu_buf(pb, p->attr, cpu, map_key);
+ if (IS_ERR(cpu_buf)) {
+ err = PTR_ERR(cpu_buf);
+ goto error;
+ }
+
+ pb->cpu_bufs[i] = cpu_buf;
+
+ err = bpf_map_update_elem(pb->map_fd, &map_key,
+ &cpu_buf->fd, 0);
+ if (err) {
+ err = -errno;
+ pr_warning("failed to set cpu #%d, key %d -> perf FD %d: %s\n",
+ cpu, map_key, cpu_buf->fd,
+ libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+
+ pb->events[i].events = EPOLLIN;
+ pb->events[i].data.ptr = cpu_buf;
+ if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd,
+ &pb->events[i]) < 0) {
+ err = -errno;
+ pr_warning("failed to epoll_ctl cpu #%d perf FD %d: %s\n",
+ cpu, cpu_buf->fd,
+ libbpf_strerror_r(err, msg, sizeof(msg)));
+ goto error;
+ }
+ }
+
+ return pb;
+
+error:
+ if (pb)
+ perf_buffer__free(pb);
+ return ERR_PTR(err);
+}
+
+struct perf_sample_raw {
+ struct perf_event_header header;
+ uint32_t size;
+ char data[0];
+};
+
+struct perf_sample_lost {
+ struct perf_event_header header;
+ uint64_t id;
+ uint64_t lost;
+ uint64_t sample_id;
+};
+
+static enum bpf_perf_event_ret
+perf_buffer__process_record(struct perf_event_header *e, void *ctx)
+{
+ struct perf_cpu_buf *cpu_buf = ctx;
+ struct perf_buffer *pb = cpu_buf->pb;
+ void *data = e;
+
+ /* user wants full control over parsing perf event */
+ if (pb->event_cb)
+ return pb->event_cb(pb->ctx, cpu_buf->cpu, e);
+
+ switch (e->type) {
+ case PERF_RECORD_SAMPLE: {
+ struct perf_sample_raw *s = data;
+
+ if (pb->sample_cb)
+ pb->sample_cb(pb->ctx, cpu_buf->cpu, s->data, s->size);
+ break;
+ }
+ case PERF_RECORD_LOST: {
+ struct perf_sample_lost *s = data;
+
+ if (pb->lost_cb)
+ pb->lost_cb(pb->ctx, cpu_buf->cpu, s->lost);
+ break;
+ }
+ default:
+ pr_warning("unknown perf sample type %d\n", e->type);
+ return LIBBPF_PERF_EVENT_ERROR;
+ }
+ return LIBBPF_PERF_EVENT_CONT;
+}
+
+static int perf_buffer__process_records(struct perf_buffer *pb,
+ struct perf_cpu_buf *cpu_buf)
+{
+ enum bpf_perf_event_ret ret;
+
+ ret = bpf_perf_event_read_simple(cpu_buf->base, pb->mmap_size,
+ pb->page_size, &cpu_buf->buf,
+ &cpu_buf->buf_size,
+ perf_buffer__process_record, cpu_buf);
+ if (ret != LIBBPF_PERF_EVENT_CONT)
+ return ret;
+ return 0;
+}
+
+int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms)
+{
+ int i, cnt, err;
+
+ cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms);
+ for (i = 0; i < cnt; i++) {
+ struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr;
+
+ err = perf_buffer__process_records(pb, cpu_buf);
+ if (err) {
+ pr_warning("error while processing records: %d\n", err);
+ return err;
+ }
+ }
+ return cnt < 0 ? -errno : cnt;
+}
+
struct bpf_prog_info_array_desc {
int array_offset; /* e.g. offset of jited_prog_insns */
int count_offset; /* e.g. offset of jited_prog_len */
@@ -3848,3 +4982,60 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear)
desc->array_offset, addr);
}
}
+
+int libbpf_num_possible_cpus(void)
+{
+ static const char *fcpu = "/sys/devices/system/cpu/possible";
+ int len = 0, n = 0, il = 0, ir = 0;
+ unsigned int start = 0, end = 0;
+ static int cpus;
+ char buf[128];
+ int error = 0;
+ int fd = -1;
+
+ if (cpus > 0)
+ return cpus;
+
+ fd = open(fcpu, O_RDONLY);
+ if (fd < 0) {
+ error = errno;
+ pr_warning("Failed to open file %s: %s\n",
+ fcpu, strerror(error));
+ return -error;
+ }
+ len = read(fd, buf, sizeof(buf));
+ close(fd);
+ if (len <= 0) {
+ error = len ? errno : EINVAL;
+ pr_warning("Failed to read # of possible cpus from %s: %s\n",
+ fcpu, strerror(error));
+ return -error;
+ }
+ if (len == sizeof(buf)) {
+ pr_warning("File %s size overflow\n", fcpu);
+ return -EOVERFLOW;
+ }
+ buf[len] = '\0';
+
+ for (ir = 0, cpus = 0; ir <= len; ir++) {
+ /* Each sub string separated by ',' has format \d+-\d+ or \d+ */
+ if (buf[ir] == ',' || buf[ir] == '\0') {
+ buf[ir] = '\0';
+ n = sscanf(&buf[il], "%u-%u", &start, &end);
+ if (n <= 0) {
+ pr_warning("Failed to get # CPUs from %s\n",
+ &buf[il]);
+ return -EINVAL;
+ } else if (n == 1) {
+ end = start;
+ }
+ cpus += end - start + 1;
+ il = ir + 1;
+ }
+ }
+ if (cpus <= 0) {
+ pr_warning("Invalid #CPUs %d from %s\n", cpus, fcpu);
+ return -EINVAL;
+ }
+ return cpus;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index c5ff00515ce7..5cbf459ece0b 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -89,18 +89,25 @@ LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj,
LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path);
LIBBPF_API void bpf_object__close(struct bpf_object *object);
+struct bpf_object_load_attr {
+ struct bpf_object *obj;
+ int log_level;
+};
+
/* Load/unload object into/from kernel */
LIBBPF_API int bpf_object__load(struct bpf_object *obj);
+LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr);
LIBBPF_API int bpf_object__unload(struct bpf_object *obj);
-LIBBPF_API const char *bpf_object__name(struct bpf_object *obj);
-LIBBPF_API unsigned int bpf_object__kversion(struct bpf_object *obj);
+LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
+LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj);
struct btf;
-LIBBPF_API struct btf *bpf_object__btf(struct bpf_object *obj);
+LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj);
LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
LIBBPF_API struct bpf_program *
-bpf_object__find_program_by_title(struct bpf_object *obj, const char *title);
+bpf_object__find_program_by_title(const struct bpf_object *obj,
+ const char *title);
LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev);
#define bpf_object__for_each_safe(pos, tmp) \
@@ -112,7 +119,7 @@ LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev);
typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *);
LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv,
bpf_object_clear_priv_t clear_priv);
-LIBBPF_API void *bpf_object__priv(struct bpf_object *prog);
+LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog);
LIBBPF_API int
libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
@@ -123,7 +130,7 @@ LIBBPF_API int libbpf_attach_type_by_name(const char *name,
/* Accessors of bpf_program */
struct bpf_program;
LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
- struct bpf_object *obj);
+ const struct bpf_object *obj);
#define bpf_object__for_each_program(pos, obj) \
for ((pos) = bpf_program__next(NULL, (obj)); \
@@ -131,24 +138,23 @@ LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
(pos) = bpf_program__next((pos), (obj)))
LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog,
- struct bpf_object *obj);
+ const struct bpf_object *obj);
-typedef void (*bpf_program_clear_priv_t)(struct bpf_program *,
- void *);
+typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *);
LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv,
bpf_program_clear_priv_t clear_priv);
-LIBBPF_API void *bpf_program__priv(struct bpf_program *prog);
+LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog);
LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog,
__u32 ifindex);
-LIBBPF_API const char *bpf_program__title(struct bpf_program *prog,
+LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog,
bool needs_copy);
LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license,
__u32 kern_version);
-LIBBPF_API int bpf_program__fd(struct bpf_program *prog);
+LIBBPF_API int bpf_program__fd(const struct bpf_program *prog);
LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog,
const char *path,
int instance);
@@ -159,6 +165,27 @@ LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path);
LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
+struct bpf_link;
+
+LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_perf_event(struct bpf_program *prog, int pfd);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe,
+ const char *func_name);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe,
+ pid_t pid, const char *binary_path,
+ size_t func_offset);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_tracepoint(struct bpf_program *prog,
+ const char *tp_category,
+ const char *tp_name);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
+ const char *tp_name);
+
struct bpf_insn;
/*
@@ -221,7 +248,7 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n,
LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
bpf_program_prep_t prep);
-LIBBPF_API int bpf_program__nth_fd(struct bpf_program *prog, int n);
+LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n);
/*
* Adjust type of BPF program. Default is kprobe.
@@ -240,14 +267,14 @@ LIBBPF_API void
bpf_program__set_expected_attach_type(struct bpf_program *prog,
enum bpf_attach_type type);
-LIBBPF_API bool bpf_program__is_socket_filter(struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_tracepoint(struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_raw_tracepoint(struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_kprobe(struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_sched_cls(struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_sched_act(struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_xdp(struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_perf_event(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog);
/*
* No need for __attribute__((packed)), all members of 'bpf_map_def'
@@ -269,10 +296,10 @@ struct bpf_map_def {
*/
struct bpf_map;
LIBBPF_API struct bpf_map *
-bpf_object__find_map_by_name(struct bpf_object *obj, const char *name);
+bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name);
LIBBPF_API int
-bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name);
+bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name);
/*
* Get bpf_map through the offset of corresponding struct bpf_map_def
@@ -282,7 +309,7 @@ LIBBPF_API struct bpf_map *
bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
LIBBPF_API struct bpf_map *
-bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
+bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj);
#define bpf_object__for_each_map(pos, obj) \
for ((pos) = bpf_map__next(NULL, (obj)); \
(pos) != NULL; \
@@ -290,22 +317,22 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
#define bpf_map__for_each bpf_object__for_each_map
LIBBPF_API struct bpf_map *
-bpf_map__prev(struct bpf_map *map, struct bpf_object *obj);
+bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj);
-LIBBPF_API int bpf_map__fd(struct bpf_map *map);
-LIBBPF_API const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
-LIBBPF_API const char *bpf_map__name(struct bpf_map *map);
+LIBBPF_API int bpf_map__fd(const struct bpf_map *map);
+LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map);
+LIBBPF_API const char *bpf_map__name(const struct bpf_map *map);
LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map);
LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
bpf_map_clear_priv_t clear_priv);
-LIBBPF_API void *bpf_map__priv(struct bpf_map *map);
+LIBBPF_API void *bpf_map__priv(const struct bpf_map *map);
LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries);
-LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map);
-LIBBPF_API bool bpf_map__is_internal(struct bpf_map *map);
+LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
+LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
@@ -320,6 +347,7 @@ struct bpf_prog_load_attr {
enum bpf_attach_type expected_attach_type;
int ifindex;
int log_level;
+ int prog_flags;
};
LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
@@ -330,6 +358,26 @@ LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type,
LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
+struct perf_buffer;
+
+typedef void (*perf_buffer_sample_fn)(void *ctx, int cpu,
+ void *data, __u32 size);
+typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt);
+
+/* common use perf buffer options */
+struct perf_buffer_opts {
+ /* if specified, sample_cb is called for each sample */
+ perf_buffer_sample_fn sample_cb;
+ /* if specified, lost_cb is called for each batch of lost samples */
+ perf_buffer_lost_fn lost_cb;
+ /* ctx is provided to sample_cb and lost_cb */
+ void *ctx;
+};
+
+LIBBPF_API struct perf_buffer *
+perf_buffer__new(int map_fd, size_t page_cnt,
+ const struct perf_buffer_opts *opts);
+
enum bpf_perf_event_ret {
LIBBPF_PERF_EVENT_DONE = 0,
LIBBPF_PERF_EVENT_ERROR = -1,
@@ -337,6 +385,35 @@ enum bpf_perf_event_ret {
};
struct perf_event_header;
+
+typedef enum bpf_perf_event_ret
+(*perf_buffer_event_fn)(void *ctx, int cpu, struct perf_event_header *event);
+
+/* raw perf buffer options, giving most power and control */
+struct perf_buffer_raw_opts {
+ /* perf event attrs passed directly into perf_event_open() */
+ struct perf_event_attr *attr;
+ /* raw event callback */
+ perf_buffer_event_fn event_cb;
+ /* ctx is provided to event_cb */
+ void *ctx;
+ /* if cpu_cnt == 0, open all on all possible CPUs (up to the number of
+ * max_entries of given PERF_EVENT_ARRAY map)
+ */
+ int cpu_cnt;
+ /* if cpu_cnt > 0, cpus is an array of CPUs to open ring buffers on */
+ int *cpus;
+ /* if cpu_cnt > 0, map_keys specify map keys to set per-CPU FDs for */
+ int *map_keys;
+};
+
+LIBBPF_API struct perf_buffer *
+perf_buffer__new_raw(int map_fd, size_t page_cnt,
+ const struct perf_buffer_raw_opts *opts);
+
+LIBBPF_API void perf_buffer__free(struct perf_buffer *pb);
+LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms);
+
typedef enum bpf_perf_event_ret
(*bpf_perf_event_print_t)(struct perf_event_header *hdr,
void *private_data);
@@ -447,6 +524,22 @@ bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear);
LIBBPF_API void
bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
+/*
+ * A helper function to get the number of possible CPUs before looking up
+ * per-CPU maps. Negative errno is returned on failure.
+ *
+ * Example usage:
+ *
+ * int ncpus = libbpf_num_possible_cpus();
+ * if (ncpus < 0) {
+ * // error handling
+ * }
+ * long values[ncpus];
+ * bpf_map_lookup_elem(per_cpu_map_fd, key, values);
+ *
+ */
+LIBBPF_API int libbpf_num_possible_cpus(void);
+
#ifdef __cplusplus
} /* extern "C" */
#endif
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 673001787cba..f9d316e873d8 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -164,3 +164,23 @@ LIBBPF_0.0.3 {
bpf_map_freeze;
btf__finalize_data;
} LIBBPF_0.0.2;
+
+LIBBPF_0.0.4 {
+ global:
+ bpf_link__destroy;
+ bpf_object__load_xattr;
+ bpf_program__attach_kprobe;
+ bpf_program__attach_perf_event;
+ bpf_program__attach_raw_tracepoint;
+ bpf_program__attach_tracepoint;
+ bpf_program__attach_uprobe;
+ btf_dump__dump_type;
+ btf_dump__free;
+ btf_dump__new;
+ btf__parse_elf;
+ libbpf_num_possible_cpus;
+ perf_buffer__free;
+ perf_buffer__new;
+ perf_buffer__new_raw;
+ perf_buffer__poll;
+} LIBBPF_0.0.3;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index dfab8012185c..2ac29bd36226 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -9,6 +9,8 @@
#ifndef __LIBBPF_LIBBPF_INTERNAL_H
#define __LIBBPF_LIBBPF_INTERNAL_H
+#include "libbpf.h"
+
#define BTF_INFO_ENC(kind, kind_flag, vlen) \
((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
#define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type)
@@ -21,6 +23,13 @@
#define BTF_PARAM_ENC(name, type) (name), (type)
#define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size)
+#ifndef min
+# define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
+#ifndef max
+# define max(x, y) ((x) < (y) ? (y) : (x))
+#endif
+
extern void libbpf_print(enum libbpf_print_level level,
const char *format, ...)
__attribute__((format(printf, 2, 3)));
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 6635a31a7a16..ace1a0708d99 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -101,6 +101,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
case BPF_PROG_TYPE_SK_REUSEPORT:
case BPF_PROG_TYPE_FLOW_DISSECTOR:
case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
default:
break;
}
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
index 00e48ac5b806..b8064eedc177 100644
--- a/tools/lib/bpf/str_error.c
+++ b/tools/lib/bpf/str_error.c
@@ -11,7 +11,7 @@
*/
char *libbpf_strerror_r(int err, char *dst, int len)
{
- int ret = strerror_r(err, dst, len);
+ int ret = strerror_r(err < 0 ? -err : err, dst, len);
if (ret)
snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret);
return dst;
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 38667b62f1fe..b33740221b7e 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -60,13 +60,12 @@ struct xsk_socket {
struct xsk_umem *umem;
struct xsk_socket_config config;
int fd;
- int xsks_map;
int ifindex;
int prog_fd;
- int qidconf_map_fd;
int xsks_map_fd;
__u32 queue_id;
char ifname[IFNAMSIZ];
+ bool zc;
};
struct xsk_nl_info {
@@ -265,15 +264,11 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
/* This is the C-program:
* SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
* {
- * int *qidconf, index = ctx->rx_queue_index;
+ * int index = ctx->rx_queue_index;
*
* // A set entry here means that the correspnding queue_id
* // has an active AF_XDP socket bound to it.
- * qidconf = bpf_map_lookup_elem(&qidconf_map, &index);
- * if (!qidconf)
- * return XDP_ABORTED;
- *
- * if (*qidconf)
+ * if (bpf_map_lookup_elem(&xsks_map, &index))
* return bpf_redirect_map(&xsks_map, index, 0);
*
* return XDP_PASS;
@@ -286,15 +281,10 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_1, -4),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
- BPF_LD_MAP_FD(BPF_REG_1, xsk->qidconf_map_fd),
+ BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd),
BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
- BPF_MOV32_IMM(BPF_REG_0, 0),
- /* if r1 == 0 goto +8 */
- BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 8),
BPF_MOV32_IMM(BPF_REG_0, 2),
- /* r1 = *(u32 *)(r1 + 0) */
- BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 0),
/* if r1 == 0 goto +5 */
BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5),
/* r2 = *(u32 *)(r10 - 4) */
@@ -337,7 +327,8 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
channels.cmd = ETHTOOL_GCHANNELS;
ifr.ifr_data = (void *)&channels;
- strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ);
+ strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1);
+ ifr.ifr_name[IFNAMSIZ - 1] = '\0';
err = ioctl(fd, SIOCETHTOOL, &ifr);
if (err && errno != EOPNOTSUPP) {
ret = -errno;
@@ -366,18 +357,11 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk)
if (max_queues < 0)
return max_queues;
- fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "qidconf_map",
+ fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map",
sizeof(int), sizeof(int), max_queues, 0);
if (fd < 0)
return fd;
- xsk->qidconf_map_fd = fd;
- fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map",
- sizeof(int), sizeof(int), max_queues, 0);
- if (fd < 0) {
- close(xsk->qidconf_map_fd);
- return fd;
- }
xsk->xsks_map_fd = fd;
return 0;
@@ -385,10 +369,8 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk)
static void xsk_delete_bpf_maps(struct xsk_socket *xsk)
{
- close(xsk->qidconf_map_fd);
+ bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id);
close(xsk->xsks_map_fd);
- xsk->qidconf_map_fd = -1;
- xsk->xsks_map_fd = -1;
}
static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
@@ -417,10 +399,9 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
if (err)
goto out_map_ids;
- for (i = 0; i < prog_info.nr_map_ids; i++) {
- if (xsk->qidconf_map_fd != -1 && xsk->xsks_map_fd != -1)
- break;
+ xsk->xsks_map_fd = -1;
+ for (i = 0; i < prog_info.nr_map_ids; i++) {
fd = bpf_map_get_fd_by_id(map_ids[i]);
if (fd < 0)
continue;
@@ -431,11 +412,6 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
continue;
}
- if (!strcmp(map_info.name, "qidconf_map")) {
- xsk->qidconf_map_fd = fd;
- continue;
- }
-
if (!strcmp(map_info.name, "xsks_map")) {
xsk->xsks_map_fd = fd;
continue;
@@ -445,40 +421,18 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
}
err = 0;
- if (xsk->qidconf_map_fd < 0 || xsk->xsks_map_fd < 0) {
+ if (xsk->xsks_map_fd == -1)
err = -ENOENT;
- xsk_delete_bpf_maps(xsk);
- }
out_map_ids:
free(map_ids);
return err;
}
-static void xsk_clear_bpf_maps(struct xsk_socket *xsk)
-{
- int qid = false;
-
- bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0);
- bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id);
-}
-
static int xsk_set_bpf_maps(struct xsk_socket *xsk)
{
- int qid = true, fd = xsk->fd, err;
-
- err = bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0);
- if (err)
- goto out;
-
- err = bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, &fd, 0);
- if (err)
- goto out;
-
- return 0;
-out:
- xsk_clear_bpf_maps(xsk);
- return err;
+ return bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id,
+ &xsk->fd, 0);
}
static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
@@ -497,26 +451,27 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
return err;
err = xsk_load_xdp_prog(xsk);
- if (err)
- goto out_maps;
+ if (err) {
+ xsk_delete_bpf_maps(xsk);
+ return err;
+ }
} else {
xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id);
err = xsk_lookup_bpf_maps(xsk);
- if (err)
- goto out_load;
+ if (err) {
+ close(xsk->prog_fd);
+ return err;
+ }
}
err = xsk_set_bpf_maps(xsk);
- if (err)
- goto out_load;
+ if (err) {
+ xsk_delete_bpf_maps(xsk);
+ close(xsk->prog_fd);
+ return err;
+ }
return 0;
-
-out_load:
- close(xsk->prog_fd);
-out_maps:
- xsk_delete_bpf_maps(xsk);
- return err;
}
int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
@@ -527,6 +482,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
void *rx_map = NULL, *tx_map = NULL;
struct sockaddr_xdp sxdp = {};
struct xdp_mmap_offsets off;
+ struct xdp_options opts;
struct xsk_socket *xsk;
socklen_t optlen;
int err;
@@ -643,8 +599,16 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
goto out_mmap_tx;
}
- xsk->qidconf_map_fd = -1;
- xsk->xsks_map_fd = -1;
+ xsk->prog_fd = -1;
+
+ optlen = sizeof(opts);
+ err = getsockopt(xsk->fd, SOL_XDP, XDP_OPTIONS, &opts, &optlen);
+ if (err) {
+ err = -errno;
+ goto out_mmap_tx;
+ }
+
+ xsk->zc = opts.flags & XDP_OPTIONS_ZEROCOPY;
if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
err = xsk_setup_xdp_prog(xsk);
@@ -708,8 +672,10 @@ void xsk_socket__delete(struct xsk_socket *xsk)
if (!xsk)
return;
- xsk_clear_bpf_maps(xsk);
- xsk_delete_bpf_maps(xsk);
+ if (xsk->prog_fd != -1) {
+ xsk_delete_bpf_maps(xsk);
+ close(xsk->prog_fd);
+ }
optlen = sizeof(off);
err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
index 82ea71a0f3ec..833a6e60d065 100644
--- a/tools/lib/bpf/xsk.h
+++ b/tools/lib/bpf/xsk.h
@@ -167,7 +167,7 @@ LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
#define XSK_RING_CONS__DEFAULT_NUM_DESCS 2048
#define XSK_RING_PROD__DEFAULT_NUM_DESCS 2048
-#define XSK_UMEM__DEFAULT_FRAME_SHIFT 11 /* 2048 bytes */
+#define XSK_UMEM__DEFAULT_FRAME_SHIFT 12 /* 4096 bytes */
#define XSK_UMEM__DEFAULT_FRAME_SIZE (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT)
#define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0