sync: latest libbpf changes from kernel

Syncing latest libbpf commits from kernel repository.
Baseline commit:   8fc9f8bedf1bdaea48382ae2e3dd558e2b939cee
Checkpoint commit: 66b5f1c439843bcbab01cc7f3854ae2742f3d1e3

Andrii Nakryiko (2):
  libbpf: fix ptr to u64 conversion warning on 32-bit platforms
  libbpf: fix another GCC8 warning for strncpy

Baruch Siach (1):
  bpf: fix uapi bpf_prog_info fields alignment

Mauro Carvalho Chehab (2):
  docs: cgroup-v1: convert docs to ReST and rename to *.rst
  docs: cgroup-v1: add it to the admin-guide book

Stanislav Fomichev (1):
  bpf: sync bpf.h to tools/

 include/uapi/linux/bpf.h | 7 ++++---
 src/libbpf.c             | 4 ++--
 src/xsk.c                | 3 ++-
 3 files changed, 8 insertions(+), 6 deletions(-)

--
2.17.1

CHECKPOINT-COMMIT

@@ -1 +1 @@
-f49aa1de98363b6c5fba4637678d6b0ba3d18065
+66b5f1c439843bcbab01cc7f3854ae2742f3d1e3

include/linux/err.h

@@ -30,4 +30,9 @@ static inline bool IS_ERR_OR_NULL(const void *ptr)
 	return (!ptr) || IS_ERR_VALUE((unsigned long)ptr);
 }
 
+static inline long PTR_ERR_OR_ZERO(const void *ptr)
+{
+	return IS_ERR(ptr) ? PTR_ERR(ptr) : 0;
+}
+
 #endif

include/uapi/linux/bpf.h

@@ -170,6 +170,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_FLOW_DISSECTOR,
 	BPF_PROG_TYPE_CGROUP_SYSCTL,
 	BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+	BPF_PROG_TYPE_CGROUP_SOCKOPT,
 };
 
 enum bpf_attach_type {
@@ -192,6 +193,10 @@ enum bpf_attach_type {
 	BPF_LIRC_MODE2,
 	BPF_FLOW_DISSECTOR,
 	BPF_CGROUP_SYSCTL,
+	BPF_CGROUP_UDP4_RECVMSG,
+	BPF_CGROUP_UDP6_RECVMSG,
+	BPF_CGROUP_GETSOCKOPT,
+	BPF_CGROUP_SETSOCKOPT,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -260,6 +265,24 @@ enum bpf_attach_type {
  */
 #define BPF_F_ANY_ALIGNMENT	(1U << 1)
 
+/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose.
+ * Verifier does sub-register def/use analysis and identifies instructions whose
+ * def only matters for low 32-bit, high 32-bit is never referenced later
+ * through implicit zero extension. Therefore verifier notifies JIT back-ends
+ * that it is safe to ignore clearing high 32-bit for these instructions. This
+ * saves some back-ends a lot of code-gen. However such optimization is not
+ * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends
+ * hence hasn't used verifier's analysis result. But, we really want to have a
+ * way to be able to verify the correctness of the described optimization on
+ * x86_64 on which testsuites are frequently exercised.
+ *
+ * So, this flag is introduced. Once it is set, verifier will randomize high
+ * 32-bit for those instructions who has been identified as safe to ignore them.
+ * Then, if verifier is not doing correct analysis, such randomization will
+ * regress tests to expose bugs.
+ */
+#define BPF_F_TEST_RND_HI32	(1U << 2)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * two extensions:
  *
@@ -783,7 +806,7 @@ union bpf_attr {
  * 		based on a user-provided identifier for all traffic coming from
  * 		the tasks belonging to the related cgroup. See also the related
  * 		kernel documentation, available from the Linux sources in file
- * 		*Documentation/cgroup-v1/net_cls.txt*.
+ * 		*Documentation/admin-guide/cgroup-v1/net_cls.rst*.
  *
  * 		The Linux kernel has two versions for cgroups: there are
  * 		cgroups v1 and cgroups v2. Both are available to users, who can
@@ -1744,6 +1767,7 @@ union bpf_attr {
  * 		* **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out)
  * 		* **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission)
  * 		* **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change)
+ * 		* **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT)
  *
  * 		Therefore, this function can be used to clear a callback flag by
  * 		setting the appropriate bit to zero. e.g. to disable the RTO
@@ -2672,6 +2696,20 @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf-local-storage cannot be found.
+ *
+ * int bpf_send_signal(u32 sig)
+ *	Description
+ *		Send signal *sig* to the current task.
+ *	Return
+ *		0 on success or successfully queued.
+ *
+ *		**-EBUSY** if work queue under nmi is full.
+ *
+ *		**-EINVAL** if *sig* is invalid.
+ *
+ *		**-EPERM** if no permission to send the *sig*.
+ *
+ *		**-EAGAIN** if bpf program can try again.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2782,7 +2820,8 @@ union bpf_attr {
 	FN(strtol),			\
 	FN(strtoul),			\
 	FN(sk_storage_get),		\
-	FN(sk_storage_delete),
+	FN(sk_storage_delete),		\
+	FN(send_signal),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3031,6 +3070,12 @@ struct bpf_tcp_sock {
 				 * sum(delta(snd_una)), or how many bytes
 				 * were acked.
 				 */
+	__u32 dsack_dups;	/* RFC4898 tcpEStatsStackDSACKDups
+				 * total number of DSACK blocks received
+				 */
+	__u32 delivered;	/* Total data packets delivered incl. rexmits */
+	__u32 delivered_ce;	/* Like the above but only ECE marked packets */
+	__u32 icsk_retransmits;	/* Number of unrecovered [RTO] timeouts */
 };
 
 struct bpf_sock_tuple {
@@ -3050,6 +3095,10 @@ struct bpf_sock_tuple {
 	};
 };
 
+struct bpf_xdp_sock {
+	__u32 queue_id;
+};
+
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
@@ -3141,6 +3190,7 @@ struct bpf_prog_info {
 	char name[BPF_OBJ_NAME_LEN];
 	__u32 ifindex;
 	__u32 gpl_compatible:1;
+	__u32 :31; /* alignment pad */
 	__u64 netns_dev;
 	__u64 netns_ino;
 	__u32 nr_jited_ksyms;
@@ -3195,7 +3245,7 @@ struct bpf_sock_addr {
 	__u32 user_ip4;		/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 user_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 user_ip6[4];	/* Allows 1,2,4,8-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__u32 user_port;	/* Allows 4-byte read and write.
@@ -3204,12 +3254,13 @@ struct bpf_sock_addr {
 	__u32 family;		/* Allows 4-byte read, but no write */
 	__u32 type;		/* Allows 4-byte read, but no write */
 	__u32 protocol;		/* Allows 4-byte read, but no write */
-	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 msg_src_ip6[4];	/* Allows 1,2,4,8-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
@@ -3261,13 +3312,15 @@ struct bpf_sock_ops {
 	__u32 sk_txhash;
 	__u64 bytes_received;
 	__u64 bytes_acked;
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
 #define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
 #define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
 #define BPF_SOCK_OPS_STATE_CB_FLAG	(1<<2)
-#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x7		/* Mask of all currently
+#define BPF_SOCK_OPS_RTT_CB_FLAG	(1<<3)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS       0xF		/* Mask of all currently
 							 * supported cb flags
 							 */
 
@@ -3322,6 +3375,8 @@ enum {
 	BPF_SOCK_OPS_TCP_LISTEN_CB,	/* Called on listen(2), right after
 					 * socket transition to LISTEN state.
 					 */
+	BPF_SOCK_OPS_RTT_CB,		/* Called on every RTT.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
@@ -3376,8 +3431,8 @@ struct bpf_raw_tracepoint_args {
 /* DIRECT:  Skip the FIB rules and go to FIB table associated with device
  * OUTPUT:  Do lookup from egress perspective; default is ingress
  */
-#define BPF_FIB_LOOKUP_DIRECT  BIT(0)
-#define BPF_FIB_LOOKUP_OUTPUT  BIT(1)
+#define BPF_FIB_LOOKUP_DIRECT  (1U << 0)
+#define BPF_FIB_LOOKUP_OUTPUT  (1U << 1)
 
 enum {
 	BPF_FIB_LKUP_RET_SUCCESS,      /* lookup successful */
@@ -3500,4 +3555,15 @@ struct bpf_sysctl {
 				 */
 };
 
+struct bpf_sockopt {
+	__bpf_md_ptr(struct bpf_sock *, sk);
+	__bpf_md_ptr(void *, optval);
+	__bpf_md_ptr(void *, optval_end);
+
+	__s32	level;
+	__s32	optname;
+	__s32	optlen;
+	__s32	retval;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */

include/uapi/linux/if_link.h

@@ -636,6 +636,7 @@ enum {
 	IFLA_BOND_AD_USER_PORT_KEY,
 	IFLA_BOND_AD_ACTOR_SYSTEM,
 	IFLA_BOND_TLB_DYNAMIC_LB,
+	IFLA_BOND_PEER_NOTIF_DELAY,
 	__IFLA_BOND_MAX,
 };
 

include/uapi/linux/if_xdp.h

@@ -46,6 +46,7 @@ struct xdp_mmap_offsets {
 #define XDP_UMEM_FILL_RING		5
 #define XDP_UMEM_COMPLETION_RING	6
 #define XDP_STATISTICS			7
+#define XDP_OPTIONS			8
 
 struct xdp_umem_reg {
 	__u64 addr; /* Start of packet data area */
@@ -60,6 +61,13 @@ struct xdp_statistics {
 	__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
 };
 
+struct xdp_options {
+	__u32 flags;
+};
+
+/* Flags for the flags field of struct xdp_options */
+#define XDP_OPTIONS_ZEROCOPY (1 << 0)
+
 /* Pgoff for mmaping the rings */
 #define XDP_PGOFF_RX_RING			  0
 #define XDP_PGOFF_TX_RING		 0x80000000

scripts/sync-kernel.sh

@@ -65,7 +65,7 @@ git branch ${SQUASH_BASE_TAG} ${SQUASH_COMMIT}
 git checkout -b ${SQUASH_TIP_TAG} ${SQUASH_COMMIT}
 
 # Cherry-pick new commits onto squashed baseline commit
-LIBBPF_PATHS=(tools/lib/bpf tools/include/uapi/linux/{bpf_common.h,bpf.h,btf.h,if_link.h,netlink.h} tools/include/tools/libc_compat.h)
+LIBBPF_PATHS=(tools/lib/bpf tools/include/uapi/linux/{bpf_common.h,bpf.h,btf.h,if_link.h,if_xdp.h,netlink.h} tools/include/tools/libc_compat.h)
 
 LIBBPF_NEW_MERGES=$(git rev-list --merges --topo-order --reverse ${BASELINE_TAG}..${TIP_TAG} ${LIBBPF_PATHS[@]})
 for LIBBPF_NEW_MERGE in ${LIBBPF_NEW_MERGES}; do

src/.gitignore

@@ -1,2 +1,4 @@
 *.o
 *.a
+/libbpf.pc
+/libbpf.so*

src/Makefile

@@ -34,7 +34,8 @@ endif
 OBJDIR ?= .
 
 OBJS := $(addprefix $(OBJDIR)/,bpf.o btf.o libbpf.o libbpf_errno.o netlink.o \
-	nlattr.o str_error.o libbpf_probes.o bpf_prog_linfo.o xsk.o)
+	nlattr.o str_error.o libbpf_probes.o bpf_prog_linfo.o xsk.o \
+	btf_dump.o hashmap.o)
 
 LIBS := $(OBJDIR)/libbpf.a
 ifndef BUILD_STATIC_ONLY

src/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
 --------------------

src/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)

src/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 */

src/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;

src/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;
-
-	for (i = 0; i < max_size_log  && (1U << i) < size;  i++)
-		;
-	return 1U << i;
+	return (size_t)key;
 }
 
+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;
 }
 

src/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

src/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;
+}
+

src/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 */

src/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

src/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;

src/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)));
@@ -34,7 +43,7 @@ do {				\
 #define pr_info(fmt, ...)	__pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
 #define pr_debug(fmt, ...)	__pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
 
-int libbpf__probe_raw_btf(const char *raw_types, size_t types_len,
-			  const char *str_sec, size_t str_len);
+int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
+			 const char *str_sec, size_t str_len);
 
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */

src/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;
 	}
@@ -133,8 +134,8 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
 	return errno != EINVAL && errno != EOPNOTSUPP;
 }
 
-int libbpf__probe_raw_btf(const char *raw_types, size_t types_len,
-			  const char *str_sec, size_t str_len)
+int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
+			 const char *str_sec, size_t str_len)
 {
 	struct btf_header hdr = {
 		.magic = BTF_MAGIC,
@@ -157,14 +158,9 @@ int libbpf__probe_raw_btf(const char *raw_types, size_t types_len,
 	memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len);
 
 	btf_fd = bpf_load_btf(raw_btf, btf_len, NULL, 0, false);
-	if (btf_fd < 0) {
-		free(raw_btf);
-		return 0;
-	}
 
-	close(btf_fd);
 	free(raw_btf);
-	return 1;
+	return btf_fd;
 }
 
 static int load_sk_storage_btf(void)
@@ -190,7 +186,7 @@ static int load_sk_storage_btf(void)
 		BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */
 	};
 
-	return libbpf__probe_raw_btf((char *)types, sizeof(types),
+	return libbpf__load_raw_btf((char *)types, sizeof(types),
 				     strs, sizeof(strs));
 }
 

src/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;

src/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;
@@ -561,7 +517,8 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 		err = -errno;
 		goto out_socket;
 	}
-	strncpy(xsk->ifname, ifname, IFNAMSIZ);
+	strncpy(xsk->ifname, ifname, IFNAMSIZ - 1);
+	xsk->ifname[IFNAMSIZ - 1] = '\0';
 
 	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
 	if (err)
@@ -643,8 +600,16 @@ 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 +673,10 @@ 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);

src/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