Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says: ==================== pull-request: bpf-next 2019-07-09 The following pull-request contains BPF updates for your *net-next* tree. The main changes are: 1) Lots of libbpf improvements: i) addition of new APIs to attach BPF programs to tracing entities such as {k,u}probes or tracepoints, ii) improve specification of BTF-defined maps by eliminating the need for data initialization for some of the members, iii) addition of a high-level API for setting up and polling perf buffers for BPF event output helpers, all from Andrii. 2) Add "prog run" subcommand to bpftool in order to test-run programs through the kernel testing infrastructure of BPF, from Quentin. 3) Improve verifier for BPF sockaddr programs to support 8-byte stores for user_ip6 and msg_src_ip6 members given clang tends to generate such stores, from Stanislav. 4) Enable the new BPF JIT zero-extension optimization for further riscv64 ALU ops, from Luke. 5) Fix a bpftool json JIT dump crash on powerpc, from Jiri. 6) Fix an AF_XDP race in generic XDP's receive path, from Ilya. 7) Various smaller fixes from Ilya, Yue and Arnd. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-08 19:14:38 -07:00 · 2019-07-08 19:14:38 -07:00 · 17ccf9e31e
parent 7650b1a9bd bf0bdd1343
commit 17ccf9e31e
67 changed files with 2473 additions and 1045 deletions
--- a/arch/riscv/net/bpf_jit_comp.c
+++ b/arch/riscv/net/bpf_jit_comp.c
@ -757,31 +757,31 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_ADD | BPF_X:
 	case BPF_ALU64 | BPF_ADD | BPF_X:
 		emit(is64 ? rv_add(rd, rd, rs) : rv_addw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_SUB | BPF_X:
 	case BPF_ALU64 | BPF_SUB | BPF_X:
 		emit(is64 ? rv_sub(rd, rd, rs) : rv_subw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_AND | BPF_X:
 	case BPF_ALU64 | BPF_AND | BPF_X:
 		emit(rv_and(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_OR | BPF_X:
 	case BPF_ALU64 | BPF_OR | BPF_X:
 		emit(rv_or(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_XOR | BPF_X:
 	case BPF_ALU64 | BPF_XOR | BPF_X:
 		emit(rv_xor(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MUL | BPF_X:
@ -811,13 +811,13 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_RSH | BPF_X:
 	case BPF_ALU64 | BPF_RSH | BPF_X:
 		emit(is64 ? rv_srl(rd, rd, rs) : rv_srlw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_ARSH | BPF_X:
 	case BPF_ALU64 | BPF_ARSH | BPF_X:
 		emit(is64 ? rv_sra(rd, rd, rs) : rv_sraw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;

@ -826,7 +826,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU64 | BPF_NEG:
 		emit(is64 ? rv_sub(rd, RV_REG_ZERO, rd) :
 		     rv_subw(rd, RV_REG_ZERO, rd), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;

--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@ -747,6 +747,12 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 	return size <= size_default && (size & (size - 1)) == 0;
 }

+#define bpf_ctx_wide_store_ok(off, size, type, field)			\
+	(size == sizeof(__u64) &&					\
+	off >= offsetof(type, field) &&					\
+	off + sizeof(__u64) <= offsetofend(type, field) &&		\
+	off % sizeof(__u64) == 0)
+
 #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))

 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@ -2223,9 +2223,7 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)

 static inline void tcp_bpf_rtt(struct sock *sk)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTT_CB_FLAG))
+	if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG))
 		tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL);
 }

--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@ -67,6 +67,8 @@ struct xdp_sock {
 	 * in the SKB destructor callback.
 	 */
 	spinlock_t tx_completion_lock;
+	/* Protects generic receive. */
+	spinlock_t rx_lock;
 	u64 rx_dropped;
 };

--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@ -3247,7 +3247,7 @@ 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-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__u32 user_port;	/* Allows 4-byte read and write.
@ -3256,10 +3256,10 @@ 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-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__bpf_md_ptr(struct bpf_sock *, sk);
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@ -939,6 +939,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);

+#ifdef CONFIG_NET
 static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
 					     enum bpf_attach_type attach_type)
 {
@ -1120,6 +1121,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	return ret;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt);
+#endif

 static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
 			      size_t *lenp)
@ -1386,10 +1388,12 @@ static const struct bpf_func_proto *
 cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
+#ifdef CONFIG_NET
 	case BPF_FUNC_sk_storage_get:
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
+#endif
 #ifdef CONFIG_INET
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
--- a/net/core/filter.c
+++ b/net/core/filter.c
@ -6890,6 +6890,16 @@ static bool sock_addr_is_valid_access(int off, int size,
 			if (!bpf_ctx_narrow_access_ok(off, size, size_default))
 				return false;
 		} else {
+			if (bpf_ctx_wide_store_ok(off, size,
+						  struct bpf_sock_addr,
+						  user_ip6))
+				return true;
+
+			if (bpf_ctx_wide_store_ok(off, size,
+						  struct bpf_sock_addr,
+						  msg_src_ip6))
+				return true;
+
 			if (size != size_default)
 				return false;
 		}
@ -7730,9 +7740,6 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 /* SOCK_ADDR_STORE_NESTED_FIELD_OFF() has semantic similar to
 * SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF() but for store operation.
 *
- * It doesn't support SIZE argument though since narrow stores are not
- * supported for now.
- *
 * In addition it uses Temporary Field TF (member of struct S) as the 3rd
 * "register" since two registers available in convert_ctx_access are not
 * enough: we can't override neither SRC, since it contains value to store, nor
@ -7740,7 +7747,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 * instructions. But we need a temporary place to save pointer to nested
 * structure whose field we want to store to.
 */
-#define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, OFF, TF)		       \
+#define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, OFF, TF)	       \
 	do {								       \
 		int tmp_reg = BPF_REG_9;				       \
 		if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg)	       \
@ -7751,8 +7758,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 				      offsetof(S, TF));			       \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg,	       \
 				      si->dst_reg, offsetof(S, F));	       \
-		*insn++ = BPF_STX_MEM(					       \
-			BPF_FIELD_SIZEOF(NS, NF), tmp_reg, si->src_reg,	       \
+		*insn++ = BPF_STX_MEM(SIZE, tmp_reg, si->src_reg,	       \
 			bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF),	       \
 				       target_size)			       \
 				+ OFF);					       \
@ -7764,8 +7770,8 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 						      TF)		       \
 	do {								       \
 		if (type == BPF_WRITE) {				       \
-			SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, OFF,    \
-							 TF);		       \
+			SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE,   \
+							 OFF, TF);	       \
 		} else {						       \
 			SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(		       \
 				S, NS, F, NF, SIZE, OFF);  \
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@ -129,13 +129,17 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	u64 addr;
 	int err;

-	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
-		return -EINVAL;
+	spin_lock_bh(&xs->rx_lock);
+
+	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) {
+		err = -EINVAL;
+		goto out_unlock;
+	}

 	if (!xskq_peek_addr(xs->umem->fq, &addr) ||
 	    len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) {
-		xs->rx_dropped++;
-		return -ENOSPC;
+		err = -ENOSPC;
+		goto out_drop;
 	}

 	addr += xs->umem->headroom;
@ -144,13 +148,21 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	memcpy(buffer, xdp->data_meta, len + metalen);
 	addr += metalen;
 	err = xskq_produce_batch_desc(xs->rx, addr, len);
-	if (!err) {
-		xskq_discard_addr(xs->umem->fq);
-		xsk_flush(xs);
-		return 0;
-	}
+	if (err)
+		goto out_drop;

+	xskq_discard_addr(xs->umem->fq);
+	xskq_produce_flush_desc(xs->rx);
+
+	spin_unlock_bh(&xs->rx_lock);
+
+	xs->sk.sk_data_ready(&xs->sk);
+	return 0;
+
+out_drop:
 	xs->rx_dropped++;
+out_unlock:
+	spin_unlock_bh(&xs->rx_lock);
 	return err;
 }

@ -787,6 +799,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,

 	xs = xdp_sk(sk);
 	mutex_init(&xs->mutex);
+	spin_lock_init(&xs->rx_lock);
 	spin_lock_init(&xs->tx_completion_lock);

 	mutex_lock(&net->xdp.lock);
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@ -29,6 +29,7 @@ PROG COMMANDS
 |	**bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*]
 |	**bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*]
 |	**bpftool** **prog tracelog**
+|	**bpftool** **prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*]
 |	**bpftool** **prog help**
 |
 |	*MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
@ -146,6 +147,39 @@ DESCRIPTION
 		  streaming data from BPF programs to user space, one can use
 		  perf events (see also **bpftool-map**\ (8)).

+	**bpftool prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*]
+		  Run BPF program *PROG* in the kernel testing infrastructure
+		  for BPF, meaning that the program works on the data and
+		  context provided by the user, and not on actual packets or
+		  monitored functions etc. Return value and duration for the
+		  test run are printed out to the console.
+
+		  Input data is read from the *FILE* passed with **data_in**.
+		  If this *FILE* is "**-**", input data is read from standard
+		  input. Input context, if any, is read from *FILE* passed with
+		  **ctx_in**. Again, "**-**" can be used to read from standard
+		  input, but only if standard input is not already in use for
+		  input data. If a *FILE* is passed with **data_out**, output
+		  data is written to that file. Similarly, output context is
+		  written to the *FILE* passed with **ctx_out**. For both
+		  output flows, "**-**" can be used to print to the standard
+		  output (as plain text, or JSON if relevant option was
+		  passed). If output keywords are omitted, output data and
+		  context are discarded. Keywords **data_size_out** and
+		  **ctx_size_out** are used to pass the size (in bytes) for the
+		  output buffers to the kernel, although the default of 32 kB
+		  should be more than enough for most cases.
+
+		  Keyword **repeat** is used to indicate the number of
+		  consecutive runs to perform. Note that output data and
+		  context printed to files correspond to the last of those
+		  runs. The duration printed out at the end of the runs is an
+		  average over all runs performed by the command.
+
+		  Not all program types support test run. Among those which do,
+		  not all of them can take the **ctx_in**/**ctx_out**
+		  arguments. bpftool does not perform checks on program types.
+
 	**bpftool prog help**
 		  Print short help message.

--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@ -342,6 +342,13 @@ _bpftool()
                load|loadall)
                    local obj

+                    # Propose "load/loadall" to complete "bpftool prog load",
+                    # or bash tries to complete "load" as a filename below.
+                    if [[ ${#words[@]} -eq 3 ]]; then
+                        COMPREPLY=( $( compgen -W "load loadall" -- "$cur" ) )
+                        return 0
+                    fi
+
                    if [[ ${#words[@]} -lt 6 ]]; then
                        _filedir
                        return 0
@ -408,10 +415,34 @@ _bpftool()
                tracelog)
                    return 0
                    ;;
+                run)
+                    if [[ ${#words[@]} -lt 5 ]]; then
+                        _filedir
+                        return 0
+                    fi
+                    case $prev in
+                        id)
+                            _bpftool_get_prog_ids
+                            return 0
+                            ;;
+                        data_in|data_out|ctx_in|ctx_out)
+                            _filedir
+                            return 0
+                            ;;
+                        repeat|data_size_out|ctx_size_out)
+                            return 0
+                            ;;
+                        *)
+                            _bpftool_once_attr 'data_in data_out data_size_out \
+                                ctx_in ctx_out ctx_size_out repeat'
+                            return 0
+                            ;;
+                    esac
+                    ;;
                *)
                    [[ $prev == $object ]] && \
-                        COMPREPLY=( $( compgen -W 'dump help pin attach detach load \
-                            show list tracelog' -- "$cur" ) )
+                        COMPREPLY=( $( compgen -W 'dump help pin attach detach \
+                            load loadall show list tracelog run' -- "$cur" ) )
                    ;;
            esac
            ;;
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@ -11,6 +11,8 @@
 * Licensed under the GNU General Public License, version 2.0 (GPLv2)
 */

+#define _GNU_SOURCE
+#include <stdio.h>
 #include <stdarg.h>
 #include <stdint.h>
 #include <stdio.h>
@ -44,11 +46,13 @@ static int fprintf_json(void *out, const char *fmt, ...)
 	char *s;

 	va_start(ap, fmt);
+	if (vasprintf(&s, fmt, ap) < 0)
+		return -1;
+	va_end(ap);
+
 	if (!oper_count) {
 		int i;

-		s = va_arg(ap, char *);
-
 		/* Strip trailing spaces */
 		i = strlen(s) - 1;
 		while (s[i] == ' ')
@ -61,11 +65,10 @@ static int fprintf_json(void *out, const char *fmt, ...)
 	} else if (!strcmp(fmt, ",")) {
 		   /* Skip */
 	} else {
-		s = va_arg(ap, char *);
 		jsonw_string(json_wtr, s);
 		oper_count++;
 	}
-	va_end(ap);
+	free(s);
 	return 0;
 }

--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@ -117,6 +117,35 @@ bool is_prefix(const char *pfx, const char *str)
 	return !memcmp(str, pfx, strlen(pfx));
 }

+/* Last argument MUST be NULL pointer */
+int detect_common_prefix(const char *arg, ...)
+{
+	unsigned int count = 0;
+	const char *ref;
+	char msg[256];
+	va_list ap;
+
+	snprintf(msg, sizeof(msg), "ambiguous prefix: '%s' could be '", arg);
+	va_start(ap, arg);
+	while ((ref = va_arg(ap, const char *))) {
+		if (!is_prefix(arg, ref))
+			continue;
+		count++;
+		if (count > 1)
+			strncat(msg, "' or '", sizeof(msg) - strlen(msg) - 1);
+		strncat(msg, ref, sizeof(msg) - strlen(msg) - 1);
+	}
+	va_end(ap);
+	strncat(msg, "'", sizeof(msg) - strlen(msg) - 1);
+
+	if (count >= 2) {
+		p_err(msg);
+		return -1;
+	}
+
+	return 0;
+}
+
 void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep)
 {
 	unsigned char *data = arg;
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@ -101,6 +101,7 @@ void p_err(const char *fmt, ...);
 void p_info(const char *fmt, ...);

 bool is_prefix(const char *pfx, const char *str);
+int detect_common_prefix(const char *arg, ...);
 void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep);
 void usage(void) __noreturn;

--- a/tools/bpf/bpftool/map_perf_ring.c
+++ b/tools/bpf/bpftool/map_perf_ring.c
@ -28,7 +28,7 @@

 #define MMAP_PAGE_CNT	16

-static bool stop;
+static volatile bool stop;

 struct event_ring_info {
 	int fd;
@ -44,32 +44,44 @@ struct perf_event_sample {
 	unsigned char data[];
 };

+struct perf_event_lost {
+	struct perf_event_header header;
+	__u64 id;
+	__u64 lost;
+};
+
 static void int_exit(int signo)
 {
 	fprintf(stderr, "Stopping...\n");
 	stop = true;
 }

+struct event_pipe_ctx {
+	bool all_cpus;
+	int cpu;
+	int idx;
+};
+
 static enum bpf_perf_event_ret
-print_bpf_output(struct perf_event_header *event, void *private_data)
+print_bpf_output(void *private_data, int cpu, struct perf_event_header *event)
 {
-	struct perf_event_sample *e = container_of(event, struct perf_event_sample,
+	struct perf_event_sample *e = container_of(event,
+						   struct perf_event_sample,
 						   header);
-	struct event_ring_info *ring = private_data;
-	struct {
-		struct perf_event_header header;
-		__u64 id;
-		__u64 lost;
-	} *lost = (typeof(lost))event;
+	struct perf_event_lost *lost = container_of(event,
+						    struct perf_event_lost,
+						    header);
+	struct event_pipe_ctx *ctx = private_data;
+	int idx = ctx->all_cpus ? cpu : ctx->idx;

 	if (json_output) {
 		jsonw_start_object(json_wtr);
 		jsonw_name(json_wtr, "type");
 		jsonw_uint(json_wtr, e->header.type);
 		jsonw_name(json_wtr, "cpu");
-		jsonw_uint(json_wtr, ring->cpu);
+		jsonw_uint(json_wtr, cpu);
 		jsonw_name(json_wtr, "index");
-		jsonw_uint(json_wtr, ring->key);
+		jsonw_uint(json_wtr, idx);
 		if (e->header.type == PERF_RECORD_SAMPLE) {
 			jsonw_name(json_wtr, "timestamp");
 			jsonw_uint(json_wtr, e->time);
@ -89,7 +101,7 @@ print_bpf_output(struct perf_event_header *event, void *private_data)
 		if (e->header.type == PERF_RECORD_SAMPLE) {
 			printf("== @%lld.%09lld CPU: %d index: %d =====\n",
 			       e->time / 1000000000ULL, e->time % 1000000000ULL,
-			       ring->cpu, ring->key);
+			       cpu, idx);
 			fprint_hex(stdout, e->data, e->size, " ");
 			printf("\n");
 		} else if (e->header.type == PERF_RECORD_LOST) {
@ -103,87 +115,25 @@ print_bpf_output(struct perf_event_header *event, void *private_data)
 	return LIBBPF_PERF_EVENT_CONT;
 }

-static void
-perf_event_read(struct event_ring_info *ring, void **buf, size_t *buf_len)
+int do_event_pipe(int argc, char **argv)
 {
-	enum bpf_perf_event_ret ret;
-
-	ret = bpf_perf_event_read_simple(ring->mem,
-					 MMAP_PAGE_CNT * get_page_size(),
-					 get_page_size(), buf, buf_len,
-					 print_bpf_output, ring);
-	if (ret != LIBBPF_PERF_EVENT_CONT) {
-		fprintf(stderr, "perf read loop failed with %d\n", ret);
-		stop = true;
-	}
-}
-
-static int perf_mmap_size(void)
-{
-	return get_page_size() * (MMAP_PAGE_CNT + 1);
-}
-
-static void *perf_event_mmap(int fd)
-{
-	int mmap_size = perf_mmap_size();
-	void *base;
-
-	base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
-	if (base == MAP_FAILED) {
-		p_err("event mmap failed: %s\n", strerror(errno));
-		return NULL;
-	}
-
-	return base;
-}
-
-static void perf_event_unmap(void *mem)
-{
-	if (munmap(mem, perf_mmap_size()))
-		fprintf(stderr, "Can't unmap ring memory!\n");
-}
-
-static int bpf_perf_event_open(int map_fd, int key, int cpu)
-{
-	struct perf_event_attr attr = {
+	struct perf_event_attr perf_attr = {
 		.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME,
 		.type = PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_BPF_OUTPUT,
+		.sample_period = 1,
+		.wakeup_events = 1,
 	};
-	int pmu_fd;
-
-	pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
-	if (pmu_fd < 0) {
-		p_err("failed to open perf event %d for CPU %d", key, cpu);
-		return -1;
-	}
-
-	if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) {
-		p_err("failed to update map for event %d for CPU %d", key, cpu);
-		goto err_close;
-	}
-	if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) {
-		p_err("failed to enable event %d for CPU %d", key, cpu);
-		goto err_close;
-	}
-
-	return pmu_fd;
-
-err_close:
-	close(pmu_fd);
-	return -1;
-}
-
-int do_event_pipe(int argc, char **argv)
-{
-	int i, nfds, map_fd, index = -1, cpu = -1;
 	struct bpf_map_info map_info = {};
-	struct event_ring_info *rings;
-	size_t tmp_buf_sz = 0;
-	void *tmp_buf = NULL;
-	struct pollfd *pfds;
+	struct perf_buffer_raw_opts opts = {};
+	struct event_pipe_ctx ctx = {
+		.all_cpus = true,
+		.cpu = -1,
+		.idx = -1,
+	};
+	struct perf_buffer *pb;
 	__u32 map_info_len;
-	bool do_all = true;
+	int err, map_fd;

 	map_info_len = sizeof(map_info);
 	map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len);
@ -205,7 +155,7 @@ int do_event_pipe(int argc, char **argv)
 			char *endptr;

 			NEXT_ARG();
-			cpu = strtoul(*argv, &endptr, 0);
+			ctx.cpu = strtoul(*argv, &endptr, 0);
 			if (*endptr) {
 				p_err("can't parse %s as CPU ID", **argv);
 				goto err_close_map;
@ -216,7 +166,7 @@ int do_event_pipe(int argc, char **argv)
 			char *endptr;

 			NEXT_ARG();
-			index = strtoul(*argv, &endptr, 0);
+			ctx.idx = strtoul(*argv, &endptr, 0);
 			if (*endptr) {
 				p_err("can't parse %s as index", **argv);
 				goto err_close_map;
@ -228,45 +178,32 @@ int do_event_pipe(int argc, char **argv)
 			goto err_close_map;
 		}

-		do_all = false;
+		ctx.all_cpus = false;
 	}

-	if (!do_all) {
-		if (index == -1 || cpu == -1) {
+	if (!ctx.all_cpus) {
+		if (ctx.idx == -1 || ctx.cpu == -1) {
 			p_err("cpu and index must be specified together");
 			goto err_close_map;
 		}
-
-		nfds = 1;
 	} else {
-		nfds = min(get_possible_cpus(), map_info.max_entries);
-		cpu = 0;
-		index = 0;
+		ctx.cpu = 0;
+		ctx.idx = 0;
 	}

-	rings = calloc(nfds, sizeof(rings[0]));
-	if (!rings)
+	opts.attr = &perf_attr;
+	opts.event_cb = print_bpf_output;
+	opts.ctx = &ctx;
+	opts.cpu_cnt = ctx.all_cpus ? 0 : 1;
+	opts.cpus = &ctx.cpu;
+	opts.map_keys = &ctx.idx;
+
+	pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &opts);
+	err = libbpf_get_error(pb);
+	if (err) {
+		p_err("failed to create perf buffer: %s (%d)",
+		      strerror(err), err);
 		goto err_close_map;
-
-	pfds = calloc(nfds, sizeof(pfds[0]));
-	if (!pfds)
-		goto err_free_rings;
-
-	for (i = 0; i < nfds; i++) {
-		rings[i].cpu = cpu + i;
-		rings[i].key = index + i;
-
-		rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key,
-						  rings[i].cpu);
-		if (rings[i].fd < 0)
-			goto err_close_fds_prev;
-
-		rings[i].mem = perf_event_mmap(rings[i].fd);
-		if (!rings[i].mem)
-			goto err_close_fds_current;
-
-		pfds[i].fd = rings[i].fd;
-		pfds[i].events = POLLIN;
 	}

 	signal(SIGINT, int_exit);
@ -277,34 +214,24 @@ int do_event_pipe(int argc, char **argv)
 		jsonw_start_array(json_wtr);

 	while (!stop) {
-		poll(pfds, nfds, 200);
-		for (i = 0; i < nfds; i++)
-			perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz);
+		err = perf_buffer__poll(pb, 200);
+		if (err < 0 && err != -EINTR) {
+			p_err("perf buffer polling failed: %s (%d)",
+			      strerror(err), err);
+			goto err_close_pb;
+		}
 	}
-	free(tmp_buf);

 	if (json_output)
 		jsonw_end_array(json_wtr);

-	for (i = 0; i < nfds; i++) {
-		perf_event_unmap(rings[i].mem);
-		close(rings[i].fd);
-	}
-	free(pfds);
-	free(rings);
+	perf_buffer__free(pb);
 	close(map_fd);

 	return 0;

-err_close_fds_prev:
-	while (i--) {
-		perf_event_unmap(rings[i].mem);
-err_close_fds_current:
-		close(rings[i].fd);
-	}
-	free(pfds);
-err_free_rings:
-	free(rings);
+err_close_pb:
+	perf_buffer__free(pb);
 err_close_map:
 	close(map_fd);
 	return -1;
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@ -15,6 +15,7 @@
 #include <sys/stat.h>

 #include <linux/err.h>
+#include <linux/sizes.h>

 #include <bpf.h>
 #include <btf.h>
@ -748,6 +749,344 @@ static int do_detach(int argc, char **argv)
 	return 0;
 }

+static int check_single_stdin(char *file_data_in, char *file_ctx_in)
+{
+	if (file_data_in && file_ctx_in &&
+	    !strcmp(file_data_in, "-") && !strcmp(file_ctx_in, "-")) {
+		p_err("cannot use standard input for both data_in and ctx_in");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int get_run_data(const char *fname, void **data_ptr, unsigned int *size)
+{
+	size_t block_size = 256;
+	size_t buf_size = block_size;
+	size_t nb_read = 0;
+	void *tmp;
+	FILE *f;
+
+	if (!fname) {
+		*data_ptr = NULL;
+		*size = 0;
+		return 0;
+	}
+
+	if (!strcmp(fname, "-"))
+		f = stdin;
+	else
+		f = fopen(fname, "r");
+	if (!f) {
+		p_err("failed to open %s: %s", fname, strerror(errno));
+		return -1;
+	}
+
+	*data_ptr = malloc(block_size);
+	if (!*data_ptr) {
+		p_err("failed to allocate memory for data_in/ctx_in: %s",
+		      strerror(errno));
+		goto err_fclose;
+	}
+
+	while ((nb_read += fread(*data_ptr + nb_read, 1, block_size, f))) {
+		if (feof(f))
+			break;
+		if (ferror(f)) {
+			p_err("failed to read data_in/ctx_in from %s: %s",
+			      fname, strerror(errno));
+			goto err_free;
+		}
+		if (nb_read > buf_size - block_size) {
+			if (buf_size == UINT32_MAX) {
+				p_err("data_in/ctx_in is too long (max: %d)",
+				      UINT32_MAX);
+				goto err_free;
+			}
+			/* No space for fread()-ing next chunk; realloc() */
+			buf_size *= 2;
+			tmp = realloc(*data_ptr, buf_size);
+			if (!tmp) {
+				p_err("failed to reallocate data_in/ctx_in: %s",
+				      strerror(errno));
+				goto err_free;
+			}
+			*data_ptr = tmp;
+		}
+	}
+	if (f != stdin)
+		fclose(f);
+
+	*size = nb_read;
+	return 0;
+
+err_free:
+	free(*data_ptr);
+	*data_ptr = NULL;
+err_fclose:
+	if (f != stdin)
+		fclose(f);
+	return -1;
+}
+
+static void hex_print(void *data, unsigned int size, FILE *f)
+{
+	size_t i, j;
+	char c;
+
+	for (i = 0; i < size; i += 16) {
+		/* Row offset */
+		fprintf(f, "%07zx\t", i);
+
+		/* Hexadecimal values */
+		for (j = i; j < i + 16 && j < size; j++)
+			fprintf(f, "%02x%s", *(uint8_t *)(data + j),
+				j % 2 ? " " : "");
+		for (; j < i + 16; j++)
+			fprintf(f, "  %s", j % 2 ? " " : "");
+
+		/* ASCII values (if relevant), '.' otherwise */
+		fprintf(f, "| ");
+		for (j = i; j < i + 16 && j < size; j++) {
+			c = *(char *)(data + j);
+			if (c < ' ' || c > '~')
+				c = '.';
+			fprintf(f, "%c%s", c, j == i + 7 ? " " : "");
+		}
+
+		fprintf(f, "\n");
+	}
+}
+
+static int
+print_run_output(void *data, unsigned int size, const char *fname,
+		 const char *json_key)
+{
+	size_t nb_written;
+	FILE *f;
+
+	if (!fname)
+		return 0;
+
+	if (!strcmp(fname, "-")) {
+		f = stdout;
+		if (json_output) {
+			jsonw_name(json_wtr, json_key);
+			print_data_json(data, size);
+		} else {
+			hex_print(data, size, f);
+		}
+		return 0;
+	}
+
+	f = fopen(fname, "w");
+	if (!f) {
+		p_err("failed to open %s: %s", fname, strerror(errno));
+		return -1;
+	}
+
+	nb_written = fwrite(data, 1, size, f);
+	fclose(f);
+	if (nb_written != size) {
+		p_err("failed to write output data/ctx: %s", strerror(errno));
+		return -1;
+	}
+
+	return 0;
+}
+
+static int alloc_run_data(void **data_ptr, unsigned int size_out)
+{
+	*data_ptr = calloc(size_out, 1);
+	if (!*data_ptr) {
+		p_err("failed to allocate memory for output data/ctx: %s",
+		      strerror(errno));
+		return -1;
+	}
+
+	return 0;
+}
+
+static int do_run(int argc, char **argv)
+{
+	char *data_fname_in = NULL, *data_fname_out = NULL;
+	char *ctx_fname_in = NULL, *ctx_fname_out = NULL;
+	struct bpf_prog_test_run_attr test_attr = {0};
+	const unsigned int default_size = SZ_32K;
+	void *data_in = NULL, *data_out = NULL;
+	void *ctx_in = NULL, *ctx_out = NULL;
+	unsigned int repeat = 1;
+	int fd, err;
+
+	if (!REQ_ARGS(4))
+		return -1;
+
+	fd = prog_parse_fd(&argc, &argv);
+	if (fd < 0)
+		return -1;
+
+	while (argc) {
+		if (detect_common_prefix(*argv, "data_in", "data_out",
+					 "data_size_out", NULL))
+			return -1;
+		if (detect_common_prefix(*argv, "ctx_in", "ctx_out",
+					 "ctx_size_out", NULL))
+			return -1;
+
+		if (is_prefix(*argv, "data_in")) {
+			NEXT_ARG();
+			if (!REQ_ARGS(1))
+				return -1;
+
+			data_fname_in = GET_ARG();
+			if (check_single_stdin(data_fname_in, ctx_fname_in))
+				return -1;
+		} else if (is_prefix(*argv, "data_out")) {
+			NEXT_ARG();
+			if (!REQ_ARGS(1))
+				return -1;
+
+			data_fname_out = GET_ARG();
+		} else if (is_prefix(*argv, "data_size_out")) {
+			char *endptr;
+
+			NEXT_ARG();
+			if (!REQ_ARGS(1))
+				return -1;
+
+			test_attr.data_size_out = strtoul(*argv, &endptr, 0);
+			if (*endptr) {
+				p_err("can't parse %s as output data size",
+				      *argv);
+				return -1;
+			}
+			NEXT_ARG();
+		} else if (is_prefix(*argv, "ctx_in")) {
+			NEXT_ARG();
+			if (!REQ_ARGS(1))
+				return -1;
+
+			ctx_fname_in = GET_ARG();
+			if (check_single_stdin(data_fname_in, ctx_fname_in))
+				return -1;
+		} else if (is_prefix(*argv, "ctx_out")) {
+			NEXT_ARG();
+			if (!REQ_ARGS(1))
+				return -1;
+
+			ctx_fname_out = GET_ARG();
+		} else if (is_prefix(*argv, "ctx_size_out")) {
+			char *endptr;
+
+			NEXT_ARG();
+			if (!REQ_ARGS(1))
+				return -1;
+
+			test_attr.ctx_size_out = strtoul(*argv, &endptr, 0);
+			if (*endptr) {
+				p_err("can't parse %s as output context size",
+				      *argv);
+				return -1;
+			}
+			NEXT_ARG();
+		} else if (is_prefix(*argv, "repeat")) {
+			char *endptr;
+
+			NEXT_ARG();
+			if (!REQ_ARGS(1))
+				return -1;
+
+			repeat = strtoul(*argv, &endptr, 0);
+			if (*endptr) {
+				p_err("can't parse %s as repeat number",
+				      *argv);
+				return -1;
+			}
+			NEXT_ARG();
+		} else {
+			p_err("expected no more arguments, 'data_in', 'data_out', 'data_size_out', 'ctx_in', 'ctx_out', 'ctx_size_out' or 'repeat', got: '%s'?",
+			      *argv);
+			return -1;
+		}
+	}
+
+	err = get_run_data(data_fname_in, &data_in, &test_attr.data_size_in);
+	if (err)
+		return -1;
+
+	if (data_in) {
+		if (!test_attr.data_size_out)
+			test_attr.data_size_out = default_size;
+		err = alloc_run_data(&data_out, test_attr.data_size_out);
+		if (err)
+			goto free_data_in;
+	}
+
+	err = get_run_data(ctx_fname_in, &ctx_in, &test_attr.ctx_size_in);
+	if (err)
+		goto free_data_out;
+
+	if (ctx_in) {
+		if (!test_attr.ctx_size_out)
+			test_attr.ctx_size_out = default_size;
+		err = alloc_run_data(&ctx_out, test_attr.ctx_size_out);
+		if (err)
+			goto free_ctx_in;
+	}
+
+	test_attr.prog_fd	= fd;
+	test_attr.repeat	= repeat;
+	test_attr.data_in	= data_in;
+	test_attr.data_out	= data_out;
+	test_attr.ctx_in	= ctx_in;
+	test_attr.ctx_out	= ctx_out;
+
+	err = bpf_prog_test_run_xattr(&test_attr);
+	if (err) {
+		p_err("failed to run program: %s", strerror(errno));
+		goto free_ctx_out;
+	}
+
+	err = 0;
+
+	if (json_output)
+		jsonw_start_object(json_wtr);	/* root */
+
+	/* Do not exit on errors occurring when printing output data/context,
+	 * we still want to print return value and duration for program run.
+	 */
+	if (test_attr.data_size_out)
+		err += print_run_output(test_attr.data_out,
+					test_attr.data_size_out,
+					data_fname_out, "data_out");
+	if (test_attr.ctx_size_out)
+		err += print_run_output(test_attr.ctx_out,
+					test_attr.ctx_size_out,
+					ctx_fname_out, "ctx_out");
+
+	if (json_output) {
+		jsonw_uint_field(json_wtr, "retval", test_attr.retval);
+		jsonw_uint_field(json_wtr, "duration", test_attr.duration);
+		jsonw_end_object(json_wtr);	/* root */
+	} else {
+		fprintf(stdout, "Return value: %u, duration%s: %uns\n",
+			test_attr.retval,
+			repeat > 1 ? " (average)" : "", test_attr.duration);
+	}
+
+free_ctx_out:
+	free(ctx_out);
+free_ctx_in:
+	free(ctx_in);
+free_data_out:
+	free(data_out);
+free_data_in:
+	free(data_in);
+
+	return err;
+}
+
 static int load_with_options(int argc, char **argv, bool first_prog_only)
 {
 	struct bpf_object_load_attr load_attr = { 0 };
@ -1058,6 +1397,11 @@ static int do_help(int argc, char **argv)
 		"                         [pinmaps MAP_DIR]\n"
 		"       %s %s attach PROG ATTACH_TYPE [MAP]\n"
 		"       %s %s detach PROG ATTACH_TYPE [MAP]\n"
+		"       %s %s run PROG \\\n"
+		"                         data_in FILE \\\n"
+		"                         [data_out FILE [data_size_out L]] \\\n"
+		"                         [ctx_in FILE [ctx_out FILE [ctx_size_out M]]] \\\n"
+		"                         [repeat N]\n"
 		"       %s %s tracelog\n"
 		"       %s %s help\n"
 		"\n"
@ -1079,7 +1423,8 @@ static int do_help(int argc, char **argv)
 		"",
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
-		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]);
+		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+		bin_name, argv[-2]);

 	return 0;
 }
@ -1095,6 +1440,7 @@ static const struct cmd cmds[] = {
 	{ "attach",	do_attach },
 	{ "detach",	do_detach },
 	{ "tracelog",	do_tracelog },
+	{ "run",	do_run },
 	{ 0 }
 };

--- a/tools/include/linux/sizes.h
+++ b/tools/include/linux/sizes.h
@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * include/linux/sizes.h
+ */
+#ifndef __LINUX_SIZES_H__
+#define __LINUX_SIZES_H__
+
+#include <linux/const.h>
+
+#define SZ_1				0x00000001
+#define SZ_2				0x00000002
+#define SZ_4				0x00000004
+#define SZ_8				0x00000008
+#define SZ_16				0x00000010
+#define SZ_32				0x00000020
+#define SZ_64				0x00000040
+#define SZ_128				0x00000080
+#define SZ_256				0x00000100
+#define SZ_512				0x00000200
+
+#define SZ_1K				0x00000400
+#define SZ_2K				0x00000800
+#define SZ_4K				0x00001000
+#define SZ_8K				0x00002000
+#define SZ_16K				0x00004000
+#define SZ_32K				0x00008000
+#define SZ_64K				0x00010000
+#define SZ_128K				0x00020000
+#define SZ_256K				0x00040000
+#define SZ_512K				0x00080000
+
+#define SZ_1M				0x00100000
+#define SZ_2M				0x00200000
+#define SZ_4M				0x00400000
+#define SZ_8M				0x00800000
+#define SZ_16M				0x01000000
+#define SZ_32M				0x02000000
+#define SZ_64M				0x04000000
+#define SZ_128M				0x08000000
+#define SZ_256M				0x10000000
+#define SZ_512M				0x20000000
+
+#define SZ_1G				0x40000000
+#define SZ_2G				0x80000000
+
+#define SZ_4G				_AC(0x100000000, ULL)
+
+#endif /* __LINUX_SIZES_H__ */
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@ -3244,7 +3244,7 @@ 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-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__u32 user_port;	/* Allows 4-byte read and write.
@ -3253,10 +3253,10 @@ 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-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__bpf_md_ptr(struct bpf_sock *, sk);
--- 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
 --------------------
--- 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>
@ -1028,40 +1031,40 @@ static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf,
 	}
 }

-static bool get_map_field_int(const char *map_name,
-			      const struct btf *btf,
+/*
+ * 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,
-			      const void *data, __u32 *res) {
+			      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);
-	__u32 int_info = *(const __u32 *)(const void *)(t + 1);
+	const struct btf_array *arr_info;
+	const struct btf_type *arr_t;

-	if (BTF_INFO_KIND(t->info) != BTF_KIND_INT) {
-		pr_warning("map '%s': attr '%s': expected INT, got %u.\n",
+	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;
 	}
-	if (t->size != 4 || BTF_INT_BITS(int_info) != 32 ||
-	    BTF_INT_OFFSET(int_info)) {
-		pr_warning("map '%s': attr '%s': expected 32-bit non-bitfield integer, "
-			   "got %u-byte (%d-bit) one with bit offset %d.\n",
-			   map_name, name, t->size, BTF_INT_BITS(int_info),
-			   BTF_INT_OFFSET(int_info));
-		return false;
-	}
-	if (BTF_INFO_KFLAG(def->info) && BTF_MEMBER_BITFIELD_SIZE(m->offset)) {
-		pr_warning("map '%s': attr '%s': bitfield is not supported.\n",
-			   map_name, name);
-		return false;
-	}
-	if (m->offset % 32) {
-		pr_warning("map '%s': attr '%s': unaligned fields are not supported.\n",
-			   map_name, name);
-		return false;
-	}

-	*res = *(const __u32 *)(data + m->offset / 8);
+	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;
 }

@ -1074,7 +1077,6 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 	const struct btf_var_secinfo *vi;
 	const struct btf_var *var_extra;
 	const struct btf_member *m;
-	const void *def_data;
 	const char *map_name;
 	struct bpf_map *map;
 	int vlen, i;
@ -1131,7 +1133,6 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 	pr_debug("map '%s': at sec_idx %d, offset %zu.\n",
 		 map_name, map->sec_idx, map->sec_offset);

-	def_data = data->d_buf + vi->offset;
 	vlen = BTF_INFO_VLEN(def->info);
 	m = (const void *)(def + 1);
 	for (i = 0; i < vlen; i++, m++) {
@ -1144,19 +1145,19 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		}
 		if (strcmp(name, "type") == 0) {
 			if (!get_map_field_int(map_name, obj->btf, def, m,
-					       def_data, &map->def.type))
+					       &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,
-					       def_data, &map->def.max_entries))
+					       &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,
-					       def_data, &map->def.map_flags))
+					       &map->def.map_flags))
 				return -EINVAL;
 			pr_debug("map '%s': found map_flags = %u.\n",
 				 map_name, map->def.map_flags);
@ -1164,7 +1165,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 			__u32 sz;

 			if (!get_map_field_int(map_name, obj->btf, def, m,
-					       def_data, &sz))
+					       &sz))
 				return -EINVAL;
 			pr_debug("map '%s': found key_size = %u.\n",
 				 map_name, sz);
@ -1207,7 +1208,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 			__u32 sz;

 			if (!get_map_field_int(map_name, obj->btf, def, m,
-					       def_data, &sz))
+					       &sz))
 				return -EINVAL;
 			pr_debug("map '%s': found value_size = %u.\n",
 				 map_name, sz);
@ -2115,6 +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;

@ -2137,7 +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;
@ -2154,9 +2171,10 @@ bpf_object__create_maps(struct bpf_object *obj)
 		*pfd = bpf_create_map_xattr(&create_attr);
 		if (*pfd < 0 && (create_attr.btf_key_type_id ||
 				 create_attr.btf_value_type_id)) {
-			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+			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;
@ -2168,11 +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;
@ -3941,6 +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,
@ -3989,6 +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 */
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@ -165,6 +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;

 /*
@ -337,6 +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,
@ -344,6 +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);
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@ -167,10 +167,20 @@ LIBBPF_0.0.3 {

 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;
-		bpf_object__load_xattr;
 		libbpf_num_possible_cpus;
+		perf_buffer__free;
+		perf_buffer__new;
+		perf_buffer__new_raw;
+		perf_buffer__poll;
 } LIBBPF_0.0.3;
--- 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;
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@ -42,3 +42,4 @@ xdping
 test_sockopt
 test_sockopt_sk
 test_sockopt_multi
+test_tcp_rtt
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@ -8,6 +8,9 @@
 */
 #define SEC(NAME) __attribute__((section(NAME), used))

+#define __uint(name, val) int (*name)[val]
+#define __type(name, val) val *name
+
 /* helper macro to print out debug messages */
 #define bpf_printk(fmt, ...)				\
 ({							\
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+ssize_t get_base_addr() {
+	size_t start;
+	char buf[256];
+	FILE *f;
+
+	f = fopen("/proc/self/maps", "r");
+	if (!f)
+		return -errno;
+
+	while (fscanf(f, "%zx-%*x %s %*s\n", &start, buf) == 2) {
+		if (strcmp(buf, "r-xp") == 0) {
+			fclose(f);
+			return start;
+		}
+	}
+
+	fclose(f);
+	return -EINVAL;
+}
+
+#ifdef __x86_64__
+#define SYS_KPROBE_NAME "__x64_sys_nanosleep"
+#else
+#define SYS_KPROBE_NAME "sys_nanosleep"
+#endif
+
+void test_attach_probe(void)
+{
+	const char *kprobe_name = "kprobe/sys_nanosleep";
+	const char *kretprobe_name = "kretprobe/sys_nanosleep";
+	const char *uprobe_name = "uprobe/trigger_func";
+	const char *uretprobe_name = "uretprobe/trigger_func";
+	const int kprobe_idx = 0, kretprobe_idx = 1;
+	const int uprobe_idx = 2, uretprobe_idx = 3;
+	const char *file = "./test_attach_probe.o";
+	struct bpf_program *kprobe_prog, *kretprobe_prog;
+	struct bpf_program *uprobe_prog, *uretprobe_prog;
+	struct bpf_object *obj;
+	int err, prog_fd, duration = 0, res;
+	struct bpf_link *kprobe_link = NULL;
+	struct bpf_link *kretprobe_link = NULL;
+	struct bpf_link *uprobe_link = NULL;
+	struct bpf_link *uretprobe_link = NULL;
+	int results_map_fd;
+	size_t uprobe_offset;
+	ssize_t base_addr;
+
+	base_addr = get_base_addr();
+	if (CHECK(base_addr < 0, "get_base_addr",
+		  "failed to find base addr: %zd", base_addr))
+		return;
+	uprobe_offset = (size_t)&get_base_addr - base_addr;
+
+	/* load programs */
+	err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd);
+	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
+		return;
+
+	kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name);
+	if (CHECK(!kprobe_prog, "find_probe",
+		  "prog '%s' not found\n", kprobe_name))
+		goto cleanup;
+	kretprobe_prog = bpf_object__find_program_by_title(obj, kretprobe_name);
+	if (CHECK(!kretprobe_prog, "find_probe",
+		  "prog '%s' not found\n", kretprobe_name))
+		goto cleanup;
+	uprobe_prog = bpf_object__find_program_by_title(obj, uprobe_name);
+	if (CHECK(!uprobe_prog, "find_probe",
+		  "prog '%s' not found\n", uprobe_name))
+		goto cleanup;
+	uretprobe_prog = bpf_object__find_program_by_title(obj, uretprobe_name);
+	if (CHECK(!uretprobe_prog, "find_probe",
+		  "prog '%s' not found\n", uretprobe_name))
+		goto cleanup;
+
+	/* load maps */
+	results_map_fd = bpf_find_map(__func__, obj, "results_map");
+	if (CHECK(results_map_fd < 0, "find_results_map",
+		  "err %d\n", results_map_fd))
+		goto cleanup;
+
+	kprobe_link = bpf_program__attach_kprobe(kprobe_prog,
+						 false /* retprobe */,
+						 SYS_KPROBE_NAME);
+	if (CHECK(IS_ERR(kprobe_link), "attach_kprobe",
+		  "err %ld\n", PTR_ERR(kprobe_link))) {
+		kprobe_link = NULL;
+		goto cleanup;
+	}
+	kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog,
+						    true /* retprobe */,
+						    SYS_KPROBE_NAME);
+	if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe",
+		  "err %ld\n", PTR_ERR(kretprobe_link))) {
+		kretprobe_link = NULL;
+		goto cleanup;
+	}
+	uprobe_link = bpf_program__attach_uprobe(uprobe_prog,
+						 false /* retprobe */,
+						 0 /* self pid */,
+						 "/proc/self/exe",
+						 uprobe_offset);
+	if (CHECK(IS_ERR(uprobe_link), "attach_uprobe",
+		  "err %ld\n", PTR_ERR(uprobe_link))) {
+		uprobe_link = NULL;
+		goto cleanup;
+	}
+	uretprobe_link = bpf_program__attach_uprobe(uretprobe_prog,
+						    true /* retprobe */,
+						    -1 /* any pid */,
+						    "/proc/self/exe",
+						    uprobe_offset);
+	if (CHECK(IS_ERR(uretprobe_link), "attach_uretprobe",
+		  "err %ld\n", PTR_ERR(uretprobe_link))) {
+		uretprobe_link = NULL;
+		goto cleanup;
+	}
+
+	/* trigger & validate kprobe && kretprobe */
+	usleep(1);
+
+	err = bpf_map_lookup_elem(results_map_fd, &kprobe_idx, &res);
+	if (CHECK(err, "get_kprobe_res",
+		  "failed to get kprobe res: %d\n", err))
+		goto cleanup;
+	if (CHECK(res != kprobe_idx + 1, "check_kprobe_res",
+		  "wrong kprobe res: %d\n", res))
+		goto cleanup;
+
+	err = bpf_map_lookup_elem(results_map_fd, &kretprobe_idx, &res);
+	if (CHECK(err, "get_kretprobe_res",
+		  "failed to get kretprobe res: %d\n", err))
+		goto cleanup;
+	if (CHECK(res != kretprobe_idx + 1, "check_kretprobe_res",
+		  "wrong kretprobe res: %d\n", res))
+		goto cleanup;
+
+	/* trigger & validate uprobe & uretprobe */
+	get_base_addr();
+
+	err = bpf_map_lookup_elem(results_map_fd, &uprobe_idx, &res);
+	if (CHECK(err, "get_uprobe_res",
+		  "failed to get uprobe res: %d\n", err))
+		goto cleanup;
+	if (CHECK(res != uprobe_idx + 1, "check_uprobe_res",
+		  "wrong uprobe res: %d\n", res))
+		goto cleanup;
+
+	err = bpf_map_lookup_elem(results_map_fd, &uretprobe_idx, &res);
+	if (CHECK(err, "get_uretprobe_res",
+		  "failed to get uretprobe res: %d\n", err))
+		goto cleanup;
+	if (CHECK(res != uretprobe_idx + 1, "check_uretprobe_res",
+		  "wrong uretprobe res: %d\n", res))
+		goto cleanup;
+
+cleanup:
+	bpf_link__destroy(kprobe_link);
+	bpf_link__destroy(kretprobe_link);
+	bpf_link__destroy(uprobe_link);
+	bpf_link__destroy(uretprobe_link);
+	bpf_object__close(obj);
+}
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <sched.h>
+#include <sys/socket.h>
+#include <test_progs.h>
+
+#ifdef __x86_64__
+#define SYS_KPROBE_NAME "__x64_sys_nanosleep"
+#else
+#define SYS_KPROBE_NAME "sys_nanosleep"
+#endif
+
+static void on_sample(void *ctx, int cpu, void *data, __u32 size)
+{
+	int cpu_data = *(int *)data, duration = 0;
+	cpu_set_t *cpu_seen = ctx;
+
+	if (cpu_data != cpu)
+		CHECK(cpu_data != cpu, "check_cpu_data",
+		      "cpu_data %d != cpu %d\n", cpu_data, cpu);
+
+	CPU_SET(cpu, cpu_seen);
+}
+
+void test_perf_buffer(void)
+{
+	int err, prog_fd, nr_cpus, i, duration = 0;
+	const char *prog_name = "kprobe/sys_nanosleep";
+	const char *file = "./test_perf_buffer.o";
+	struct perf_buffer_opts pb_opts = {};
+	struct bpf_map *perf_buf_map;
+	cpu_set_t cpu_set, cpu_seen;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	struct perf_buffer *pb;
+	struct bpf_link *link;
+
+	nr_cpus = libbpf_num_possible_cpus();
+	if (CHECK(nr_cpus < 0, "nr_cpus", "err %d\n", nr_cpus))
+		return;
+
+	/* load program */
+	err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd);
+	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
+		return;
+
+	prog = bpf_object__find_program_by_title(obj, prog_name);
+	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name))
+		goto out_close;
+
+	/* load map */
+	perf_buf_map = bpf_object__find_map_by_name(obj, "perf_buf_map");
+	if (CHECK(!perf_buf_map, "find_perf_buf_map", "not found\n"))
+		goto out_close;
+
+	/* attach kprobe */
+	link = bpf_program__attach_kprobe(prog, false /* retprobe */,
+					  SYS_KPROBE_NAME);
+	if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link)))
+		goto out_close;
+
+	/* set up perf buffer */
+	pb_opts.sample_cb = on_sample;
+	pb_opts.ctx = &cpu_seen;
+	pb = perf_buffer__new(bpf_map__fd(perf_buf_map), 1, &pb_opts);
+	if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb)))
+		goto out_detach;
+
+	/* trigger kprobe on every CPU */
+	CPU_ZERO(&cpu_seen);
+	for (i = 0; i < nr_cpus; i++) {
+		CPU_ZERO(&cpu_set);
+		CPU_SET(i, &cpu_set);
+
+		err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set),
+					     &cpu_set);
+		if (err && CHECK(err, "set_affinity", "cpu #%d, err %d\n",
+				 i, err))
+			goto out_detach;
+
+		usleep(1);
+	}
+
+	/* read perf buffer */
+	err = perf_buffer__poll(pb, 100);
+	if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err))
+		goto out_free_pb;
+
+	if (CHECK(CPU_COUNT(&cpu_seen) != nr_cpus, "seen_cpu_cnt",
+		  "expect %d, seen %d\n", nr_cpus, CPU_COUNT(&cpu_seen)))
+		goto out_free_pb;
+
+out_free_pb:
+	perf_buffer__free(pb);
+out_detach:
+	bpf_link__destroy(link);
+out_close:
+	bpf_object__close(obj);
+}
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
@ -4,11 +4,13 @@
 void test_stacktrace_build_id(void)
 {
 	int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
+	const char *prog_name = "tracepoint/random/urandom_read";
 	const char *file = "./test_stacktrace_build_id.o";
-	int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len;
-	struct perf_event_attr attr = {};
+	int err, prog_fd, stack_trace_len;
 	__u32 key, previous_key, val, duration = 0;
+	struct bpf_program *prog;
 	struct bpf_object *obj;
+	struct bpf_link *link = NULL;
 	char buf[256];
 	int i, j;
 	struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
@ -18,44 +20,16 @@ void test_stacktrace_build_id(void)
 retry:
 	err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
 	if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
-		goto out;
+		return;

-	/* Get the ID for the sched/sched_switch tracepoint */
-	snprintf(buf, sizeof(buf),
-		 "/sys/kernel/debug/tracing/events/random/urandom_read/id");
-	efd = open(buf, O_RDONLY, 0);
-	if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
+	prog = bpf_object__find_program_by_title(obj, prog_name);
+	if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
 		goto close_prog;

-	bytes = read(efd, buf, sizeof(buf));
-	close(efd);
-	if (CHECK(bytes <= 0 || bytes >= sizeof(buf),
-		  "read", "bytes %d errno %d\n", bytes, errno))
+	link = bpf_program__attach_tracepoint(prog, "random", "urandom_read");
+	if (CHECK(IS_ERR(link), "attach_tp", "err %ld\n", PTR_ERR(link)))
 		goto close_prog;

-	/* Open the perf event and attach bpf progrram */
-	attr.config = strtol(buf, NULL, 0);
-	attr.type = PERF_TYPE_TRACEPOINT;
-	attr.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN;
-	attr.sample_period = 1;
-	attr.wakeup_events = 1;
-	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
-			 0 /* cpu 0 */, -1 /* group id */,
-			 0 /* flags */);
-	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
-		  pmu_fd, errno))
-		goto close_prog;
-
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
-	if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n",
-		  err, errno))
-		goto close_pmu;
-
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
-	if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n",
-		  err, errno))
-		goto disable_pmu;
-
 	/* find map fds */
 	control_map_fd = bpf_find_map(__func__, obj, "control_map");
 	if (CHECK(control_map_fd < 0, "bpf_find_map control_map",
@ -133,8 +107,7 @@ void test_stacktrace_build_id(void)
 	 * try it one more time.
 	 */
 	if (build_id_matches < 1 && retry--) {
-		ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
-		close(pmu_fd);
+		bpf_link__destroy(link);
 		bpf_object__close(obj);
 		printf("%s:WARN:Didn't find expected build ID from the map, retrying\n",
 		       __func__);
@ -152,14 +125,8 @@ void test_stacktrace_build_id(void)
 	      "err %d errno %d\n", err, errno);

 disable_pmu:
-	ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
-
-close_pmu:
-	close(pmu_fd);
+	bpf_link__destroy(link);

 close_prog:
 	bpf_object__close(obj);
-
-out:
-	return;
 }
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
@ -17,6 +17,7 @@ static __u64 read_perf_max_sample_freq(void)
 void test_stacktrace_build_id_nmi(void)
 {
 	int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
+	const char *prog_name = "tracepoint/random/urandom_read";
 	const char *file = "./test_stacktrace_build_id.o";
 	int err, pmu_fd, prog_fd;
 	struct perf_event_attr attr = {
@ -25,7 +26,9 @@ void test_stacktrace_build_id_nmi(void)
 		.config = PERF_COUNT_HW_CPU_CYCLES,
 	};
 	__u32 key, previous_key, val, duration = 0;
+	struct bpf_program *prog;
 	struct bpf_object *obj;
+	struct bpf_link *link;
 	char buf[256];
 	int i, j;
 	struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
@ -39,6 +42,10 @@ void test_stacktrace_build_id_nmi(void)
 	if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
 		return;

+	prog = bpf_object__find_program_by_title(obj, prog_name);
+	if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
+		goto close_prog;
+
 	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
 			 0 /* cpu 0 */, -1 /* group id */,
 			 0 /* flags */);
@ -47,15 +54,12 @@ void test_stacktrace_build_id_nmi(void)
 		  pmu_fd, errno))
 		goto close_prog;

-	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
-	if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n",
-		  err, errno))
-		goto close_pmu;
-
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
-	if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n",
-		  err, errno))
-		goto disable_pmu;
+	link = bpf_program__attach_perf_event(prog, pmu_fd);
+	if (CHECK(IS_ERR(link), "attach_perf_event",
+		  "err %ld\n", PTR_ERR(link))) {
+		close(pmu_fd);
+		goto close_prog;
+	}

 	/* find map fds */
 	control_map_fd = bpf_find_map(__func__, obj, "control_map");
@ -134,8 +138,7 @@ void test_stacktrace_build_id_nmi(void)
 	 * try it one more time.
 	 */
 	if (build_id_matches < 1 && retry--) {
-		ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
-		close(pmu_fd);
+		bpf_link__destroy(link);
 		bpf_object__close(obj);
 		printf("%s:WARN:Didn't find expected build ID from the map, retrying\n",
 		       __func__);
@ -154,11 +157,7 @@ void test_stacktrace_build_id_nmi(void)
 	 */

 disable_pmu:
-	ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
-
-close_pmu:
-	close(pmu_fd);
-
+	bpf_link__destroy(link);
 close_prog:
 	bpf_object__close(obj);
 }
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
@ -4,50 +4,26 @@
 void test_stacktrace_map(void)
 {
 	int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
+	const char *prog_name = "tracepoint/sched/sched_switch";
+	int err, prog_fd, stack_trace_len;
 	const char *file = "./test_stacktrace_map.o";
-	int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len;
-	struct perf_event_attr attr = {};
 	__u32 key, val, duration = 0;
+	struct bpf_program *prog;
 	struct bpf_object *obj;
-	char buf[256];
+	struct bpf_link *link;

 	err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
 	if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
 		return;

-	/* Get the ID for the sched/sched_switch tracepoint */
-	snprintf(buf, sizeof(buf),
-		 "/sys/kernel/debug/tracing/events/sched/sched_switch/id");
-	efd = open(buf, O_RDONLY, 0);
-	if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
+	prog = bpf_object__find_program_by_title(obj, prog_name);
+	if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
 		goto close_prog;

-	bytes = read(efd, buf, sizeof(buf));
-	close(efd);
-	if (bytes <= 0 || bytes >= sizeof(buf))
+	link = bpf_program__attach_tracepoint(prog, "sched", "sched_switch");
+	if (CHECK(IS_ERR(link), "attach_tp", "err %ld\n", PTR_ERR(link)))
 		goto close_prog;

-	/* Open the perf event and attach bpf progrram */
-	attr.config = strtol(buf, NULL, 0);
-	attr.type = PERF_TYPE_TRACEPOINT;
-	attr.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN;
-	attr.sample_period = 1;
-	attr.wakeup_events = 1;
-	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
-			 0 /* cpu 0 */, -1 /* group id */,
-			 0 /* flags */);
-	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
-		  pmu_fd, errno))
-		goto close_prog;
-
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
-	if (err)
-		goto disable_pmu;
-
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
-	if (err)
-		goto disable_pmu;
-
 	/* find map fds */
 	control_map_fd = bpf_find_map(__func__, obj, "control_map");
 	if (control_map_fd < 0)
@ -96,8 +72,7 @@ void test_stacktrace_map(void)
 disable_pmu:
 	error_cnt++;
 disable_pmu_noerr:
-	ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
-	close(pmu_fd);
+	bpf_link__destroy(link);
 close_prog:
 	bpf_object__close(obj);
 }
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
@ -3,18 +3,25 @@

 void test_stacktrace_map_raw_tp(void)
 {
+	const char *prog_name = "tracepoint/sched/sched_switch";
 	int control_map_fd, stackid_hmap_fd, stackmap_fd;
 	const char *file = "./test_stacktrace_map.o";
-	int efd, err, prog_fd;
 	__u32 key, val, duration = 0;
+	int err, prog_fd;
+	struct bpf_program *prog;
 	struct bpf_object *obj;
+	struct bpf_link *link = NULL;

 	err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
 	if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
 		return;

-	efd = bpf_raw_tracepoint_open("sched_switch", prog_fd);
-	if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno))
+	prog = bpf_object__find_program_by_title(obj, prog_name);
+	if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
+		goto close_prog;
+
+	link = bpf_program__attach_raw_tracepoint(prog, "sched_switch");
+	if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link)))
 		goto close_prog;

 	/* find map fds */
@ -55,5 +62,7 @@ void test_stacktrace_map_raw_tp(void)
 close_prog:
 	error_cnt++;
 close_prog_noerr:
+	if (!IS_ERR_OR_NULL(link))
+		bpf_link__destroy(link);
 	bpf_object__close(obj);
 }
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@ -58,26 +58,18 @@ struct frag_hdr {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 key_size;
-	__u32 value_size;
-} jmp_table SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PROG_ARRAY,
-	.max_entries = 8,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
-};
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 8);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct bpf_flow_keys *value;
-} last_dissection SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct bpf_flow_keys);
+} last_dissection SEC(".maps");

 static __always_inline int export_flow_keys(struct bpf_flow_keys *keys,
 					    int ret)
--- a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
@ -4,19 +4,19 @@
 #include <linux/bpf.h>
 #include "bpf_helpers.h"

-struct bpf_map_def SEC("maps") cg_ids = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} cg_ids SEC(".maps");

-struct bpf_map_def SEC("maps") pidmap = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+} pidmap SEC(".maps");

 SEC("tracepoint/syscalls/sys_enter_nanosleep")
 int trace(void *ctx)
--- a/tools/testing/selftests/bpf/progs/netcnt_prog.c
+++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c
@ -11,20 +11,16 @@
 #define NS_PER_SEC	1000000000

 struct {
-	__u32 type;
-	struct bpf_cgroup_storage_key *key;
-	struct percpu_net_cnt *value;
-} percpu_netcnt SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
-};
+	__uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, struct percpu_net_cnt);
+} percpu_netcnt SEC(".maps");

 struct {
-	__u32 type;
-	struct bpf_cgroup_storage_key *key;
-	struct net_cnt *value;
-} netcnt SEC(".maps") = {
-	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
-};
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, struct net_cnt);
+} netcnt SEC(".maps");

 SEC("cgroup/skb")
 int bpf_nextcnt(struct __sk_buff *skb)
--- a/tools/testing/selftests/bpf/progs/pyperf.h
+++ b/tools/testing/selftests/bpf/progs/pyperf.h
@ -58,14 +58,6 @@ typedef struct {
 } Event;


-struct bpf_elf_map {
-	__u32 type;
-	__u32 size_key;
-	__u32 size_value;
-	__u32 max_elem;
-	__u32 flags;
-};
-
 typedef int pid_t;

 typedef struct {
@ -118,47 +110,47 @@ static __always_inline bool get_frame_data(void *frame_ptr, PidData *pidData,
 	return true;
 }

-struct bpf_elf_map SEC("maps") pidmap = {
-	.type = BPF_MAP_TYPE_HASH,
-	.size_key = sizeof(int),
-	.size_value = sizeof(PidData),
-	.max_elem = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, PidData);
+} pidmap SEC(".maps");

-struct bpf_elf_map SEC("maps") eventmap = {
-	.type = BPF_MAP_TYPE_HASH,
-	.size_key = sizeof(int),
-	.size_value = sizeof(Event),
-	.max_elem = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, Event);
+} eventmap SEC(".maps");

-struct bpf_elf_map SEC("maps") symbolmap = {
-	.type = BPF_MAP_TYPE_HASH,
-	.size_key = sizeof(Symbol),
-	.size_value = sizeof(int),
-	.max_elem = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, Symbol);
+	__type(value, int);
+} symbolmap SEC(".maps");

-struct bpf_elf_map SEC("maps") statsmap = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.size_key = sizeof(Stats),
-	.size_value = sizeof(int),
-	.max_elem = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, Stats);
+} statsmap SEC(".maps");

-struct bpf_elf_map SEC("maps") perfmap = {
-	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
-	.size_key = sizeof(int),
-	.size_value = sizeof(int),
-	.max_elem = 32,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(max_entries, 32);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} perfmap SEC(".maps");

-struct bpf_elf_map SEC("maps") stackmap = {
-	.type = BPF_MAP_TYPE_STACK_TRACE,
-	.size_key = sizeof(int),
-	.size_value = sizeof(long long) * 127,
-	.max_elem = 1000,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(max_entries, 1000);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(long long) * 127);
+} stackmap SEC(".maps");

 static __always_inline int __on_event(struct pt_regs *ctx)
 {
--- a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
+++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
@ -13,14 +13,11 @@ struct socket_cookie {
 };

 struct {
-	__u32 type;
-	__u32 map_flags;
-	int *key;
-	struct socket_cookie *value;
-} socket_cookies SEC(".maps") = {
-	.type = BPF_MAP_TYPE_SK_STORAGE,
-	.map_flags = BPF_F_NO_PREALLOC,
-};
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct socket_cookie);
+} socket_cookies SEC(".maps");

 SEC("cgroup/connect6")
 int set_cookie(struct bpf_sock_addr *ctx)
--- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
@ -4,33 +4,33 @@

 int _version SEC("version") = 1;

-struct bpf_map_def SEC("maps") sock_map_rx = {
-	.type = BPF_MAP_TYPE_SOCKMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 20,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} sock_map_rx SEC(".maps");

-struct bpf_map_def SEC("maps") sock_map_tx = {
-	.type = BPF_MAP_TYPE_SOCKMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 20,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} sock_map_tx SEC(".maps");

-struct bpf_map_def SEC("maps") sock_map_msg = {
-	.type = BPF_MAP_TYPE_SOCKMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 20,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} sock_map_msg SEC(".maps");

-struct bpf_map_def SEC("maps") sock_map_break = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 20,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map_break SEC(".maps");

 SEC("sk_skb2")
 int bpf_prog2(struct __sk_buff *skb)
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@ -204,40 +204,40 @@ struct strobelight_bpf_sample {
 	char dummy_safeguard;
 };

-struct bpf_map_def SEC("maps") samples = {
-	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 32,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(max_entries, 32);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} samples SEC(".maps");

-struct bpf_map_def SEC("maps") stacks_0 = {
-	.type = BPF_MAP_TYPE_STACK_TRACE,
-	.key_size = sizeof(uint32_t),
-	.value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH,
-	.max_entries = 16,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(max_entries, 16);
+	__uint(key_size, sizeof(uint32_t));
+	__uint(value_size, sizeof(uint64_t) * PERF_MAX_STACK_DEPTH);
+} stacks_0 SEC(".maps");

-struct bpf_map_def SEC("maps") stacks_1 = {
-	.type = BPF_MAP_TYPE_STACK_TRACE,
-	.key_size = sizeof(uint32_t),
-	.value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH,
-	.max_entries = 16,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(max_entries, 16);
+	__uint(key_size, sizeof(uint32_t));
+	__uint(value_size, sizeof(uint64_t) * PERF_MAX_STACK_DEPTH);
+} stacks_1 SEC(".maps");

-struct bpf_map_def SEC("maps") sample_heap = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(uint32_t),
-	.value_size = sizeof(struct strobelight_bpf_sample),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, uint32_t);
+	__type(value, struct strobelight_bpf_sample);
+} sample_heap SEC(".maps");

-struct bpf_map_def SEC("maps") strobemeta_cfgs = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(pid_t),
-	.value_size = sizeof(struct strobemeta_cfg),
-	.max_entries = STROBE_MAX_CFGS,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, STROBE_MAX_CFGS);
+	__type(key, pid_t);
+	__type(value, struct strobemeta_cfg);
+} strobemeta_cfgs SEC(".maps");

 /* Type for the dtv.  */
 /* https://github.com/lattera/glibc/blob/master/nptl/sysdeps/x86_64/tls.h#L34 */
--- a/tools/testing/selftests/bpf/progs/test_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 4);
+	__type(key, int);
+	__type(value, int);
+} results_map SEC(".maps");
+
+SEC("kprobe/sys_nanosleep")
+int handle_sys_nanosleep_entry(struct pt_regs *ctx)
+{
+	const int key = 0, value = 1;
+
+	bpf_map_update_elem(&results_map, &key, &value, 0);
+	return 0;
+}
+
+SEC("kretprobe/sys_nanosleep")
+int handle_sys_getpid_return(struct pt_regs *ctx)
+{
+	const int key = 1, value = 2;
+
+	bpf_map_update_elem(&results_map, &key, &value, 0);
+	return 0;
+}
+
+SEC("uprobe/trigger_func")
+int handle_uprobe_entry(struct pt_regs *ctx)
+{
+	const int key = 2, value = 3;
+
+	bpf_map_update_elem(&results_map, &key, &value, 0);
+	return 0;
+}
+
+SEC("uretprobe/trigger_func")
+int handle_uprobe_return(struct pt_regs *ctx)
+{
+	const int key = 3, value = 4;
+
+	bpf_map_update_elem(&results_map, &key, &value, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1;
--- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
@ -21,14 +21,11 @@ struct bpf_map_def SEC("maps") btf_map_legacy = {
 BPF_ANNOTATE_KV_PAIR(btf_map_legacy, int, struct ipv_counts);

 struct {
-	int *key;
-	struct ipv_counts *value;
-	unsigned int type;
-	unsigned int max_entries;
-} btf_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 4,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 4);
+	__type(key, int);
+	__type(value, struct ipv_counts);
+} btf_map SEC(".maps");

 struct dummy_tracepoint_args {
 	unsigned long long pad;
--- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
@ -16,26 +16,18 @@ struct stack_trace_t {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 key_size;
-	__u32 value_size;
-} perfmap SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
-	.max_entries = 2,
-	.key_size = sizeof(int),
-	.value_size = sizeof(__u32),
-};
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(max_entries, 2);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(__u32));
+} perfmap SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct stack_trace_t *value;
-} stackdata_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct stack_trace_t);
+} stackdata_map SEC(".maps");

 /* Allocate per-cpu space twice the needed. For the code below
 *   usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
@ -56,14 +48,11 @@ struct {
 * This is an acceptable workaround since there is one entry here.
 */
 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
 	__u64 (*value)[2 * MAX_STACK_RAWTP];
-} rawdata_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.max_entries = 1,
-};
+} rawdata_map SEC(".maps");

 SEC("tracepoint/raw_syscalls/sys_enter")
 int bpf_prog1(void *ctx)
--- a/tools/testing/selftests/bpf/progs/test_global_data.c
+++ b/tools/testing/selftests/bpf/progs/test_global_data.c
@ -8,24 +8,18 @@
 #include "bpf_helpers.h"

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u64 *value;
-} result_number SEC(".maps") = {
-	.type		= BPF_MAP_TYPE_ARRAY,
-	.max_entries	= 11,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 11);
+	__type(key, __u32);
+	__type(value, __u64);
+} result_number SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 5);
+	__type(key, __u32);
 	const char (*value)[32];
-} result_string SEC(".maps") = {
-	.type		= BPF_MAP_TYPE_ARRAY,
-	.max_entries	= 5,
-};
+} result_string SEC(".maps");

 struct foo {
 	__u8  a;
@ -34,14 +28,11 @@ struct foo {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct foo *value;
-} result_struct SEC(".maps") = {
-	.type		= BPF_MAP_TYPE_ARRAY,
-	.max_entries	= 5,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 5);
+	__type(key, __u32);
+	__type(value, struct foo);
+} result_struct SEC(".maps");

 /* Relocation tests for __u64s. */
 static       __u64 num0;
--- a/tools/testing/selftests/bpf/progs/test_l4lb.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb.c
@ -170,54 +170,39 @@ struct eth_hdr {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	struct vip *key;
-	struct vip_meta *value;
-} vip_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_HASH,
-	.max_entries = MAX_VIPS,
-};
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, MAX_VIPS);
+	__type(key, struct vip);
+	__type(value, struct vip_meta);
+} vip_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u32 *value;
-} ch_rings SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = CH_RINGS_SIZE,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, CH_RINGS_SIZE);
+	__type(key, __u32);
+	__type(value, __u32);
+} ch_rings SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct real_definition *value;
-} reals SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = MAX_REALS,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, MAX_REALS);
+	__type(key, __u32);
+	__type(value, struct real_definition);
+} reals SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct vip_stats *value;
-} stats SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.max_entries = MAX_VIPS,
-};
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, MAX_VIPS);
+	__type(key, __u32);
+	__type(value, struct vip_stats);
+} stats SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct ctl_value *value;
-} ctl_array SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = CTL_MAP_SIZE,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, CTL_MAP_SIZE);
+	__type(key, __u32);
+	__type(value, struct ctl_value);
+} ctl_array SEC(".maps");

 static __always_inline __u32 get_packet_hash(struct packet_description *pckt,
 					     bool ipv6)
--- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
@ -166,54 +166,39 @@ struct eth_hdr {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	struct vip *key;
-	struct vip_meta *value;
-} vip_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_HASH,
-	.max_entries = MAX_VIPS,
-};
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, MAX_VIPS);
+	__type(key, struct vip);
+	__type(value, struct vip_meta);
+} vip_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u32 *value;
-} ch_rings SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = CH_RINGS_SIZE,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, CH_RINGS_SIZE);
+	__type(key, __u32);
+	__type(value, __u32);
+} ch_rings SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct real_definition *value;
-} reals SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = MAX_REALS,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, MAX_REALS);
+	__type(key, __u32);
+	__type(value, struct real_definition);
+} reals SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct vip_stats *value;
-} stats SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.max_entries = MAX_VIPS,
-};
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, MAX_VIPS);
+	__type(key, __u32);
+	__type(value, struct vip_stats);
+} stats SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct ctl_value *value;
-} ctl_array SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = CTL_MAP_SIZE,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, CTL_MAP_SIZE);
+	__type(key, __u32);
+	__type(value, struct ctl_value);
+} ctl_array SEC(".maps");

 static __u32 get_packet_hash(struct packet_description *pckt,
 			     bool ipv6)
--- a/tools/testing/selftests/bpf/progs/test_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c
@ -5,23 +5,23 @@
 #include <linux/types.h>
 #include "bpf_helpers.h"

-struct bpf_map_def SEC("maps") mim_array = {
-	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
-	.key_size = sizeof(int),
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, 1);
+	__uint(map_flags, 0);
+	__uint(key_size, sizeof(__u32));
 	/* must be sizeof(__u32) for map in map */
-	.value_size = sizeof(__u32),
-	.max_entries = 1,
-	.map_flags = 0,
-};
+	__uint(value_size, sizeof(__u32));
+} mim_array SEC(".maps");

-struct bpf_map_def SEC("maps") mim_hash = {
-	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
-	.key_size = sizeof(int),
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 1);
+	__uint(map_flags, 0);
+	__uint(key_size, sizeof(int));
 	/* must be sizeof(__u32) for map in map */
-	.value_size = sizeof(__u32),
-	.max_entries = 1,
-	.map_flags = 0,
-};
+	__uint(value_size, sizeof(__u32));
+} mim_hash SEC(".maps");

 SEC("xdp_mimtest")
 int xdp_mimtest0(struct xdp_md *ctx)
--- a/tools/testing/selftests/bpf/progs/test_map_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_map_lock.c
@ -12,14 +12,11 @@ struct hmap_elem {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct hmap_elem *value;
-} hash_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_HASH,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct hmap_elem);
+} hash_map SEC(".maps");

 struct array_elem {
 	struct bpf_spin_lock lock;
@ -27,14 +24,11 @@ struct array_elem {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	int *key;
-	struct array_elem *value;
-} array_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct array_elem);
+} array_map SEC(".maps");

 SEC("map_lock_demo")
 int bpf_map_lock_test(struct __sk_buff *skb)
--- a/tools/testing/selftests/bpf/progs/test_obj_id.c
+++ b/tools/testing/selftests/bpf/progs/test_obj_id.c
@ -13,12 +13,12 @@

 int _version SEC("version") = 1;

-struct bpf_map_def SEC("maps") test_map_id = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} test_map_id SEC(".maps");

 SEC("test_obj_id_dummy")
 int test_obj_id(struct __sk_buff *skb)
--- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} perf_buf_map SEC(".maps");
+
+SEC("kprobe/sys_nanosleep")
+int handle_sys_nanosleep_entry(struct pt_regs *ctx)
+{
+	int cpu = bpf_get_smp_processor_id();
+
+	bpf_perf_event_output(ctx, &perf_buf_map, BPF_F_CURRENT_CPU,
+			      &cpu, sizeof(cpu));
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1;
--- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
@ -22,56 +22,39 @@ int _version SEC("version") = 1;
 #endif

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 key_size;
-	__u32 value_size;
-} outer_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
-	.max_entries = 1,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} outer_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u32 *value;
-} result_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = NR_RESULTS,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, NR_RESULTS);
+	__type(key, __u32);
+	__type(value, __u32);
+} result_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	int *value;
-} tmp_index_ovr_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, int);
+} tmp_index_ovr_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u32 *value;
-} linum_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+} linum_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct data_check *value;
-} data_check_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct data_check);
+} data_check_map SEC(".maps");

 #define GOTO_DONE(_result) ({			\
 	result = (_result);			\
--- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
@ -5,24 +5,18 @@
 #include "bpf_helpers.h"

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u64 *value;
-} info_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} info_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u64 *value;
-} status_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} status_map SEC(".maps");

 SEC("send_signal_demo")
 int bpf_send_signal_test(void *ctx)
--- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
@ -28,44 +28,32 @@ enum bpf_linum_array_idx {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct sockaddr_in6 *value;
-} addr_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = __NR_BPF_ADDR_ARRAY_IDX,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, __NR_BPF_ADDR_ARRAY_IDX);
+	__type(key, __u32);
+	__type(value, struct sockaddr_in6);
+} addr_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct bpf_sock *value;
-} sock_result_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = __NR_BPF_RESULT_ARRAY_IDX,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, __NR_BPF_RESULT_ARRAY_IDX);
+	__type(key, __u32);
+	__type(value, struct bpf_sock);
+} sock_result_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct bpf_tcp_sock *value;
-} tcp_sock_result_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = __NR_BPF_RESULT_ARRAY_IDX,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, __NR_BPF_RESULT_ARRAY_IDX);
+	__type(key, __u32);
+	__type(value, struct bpf_tcp_sock);
+} tcp_sock_result_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u32 *value;
-} linum_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = __NR_BPF_LINUM_ARRAY_IDX,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, __NR_BPF_LINUM_ARRAY_IDX);
+	__type(key, __u32);
+	__type(value, __u32);
+} linum_map SEC(".maps");

 struct bpf_spinlock_cnt {
 	struct bpf_spin_lock lock;
@ -73,24 +61,18 @@ struct bpf_spinlock_cnt {
 };

 struct {
-	__u32 type;
-	__u32 map_flags;
-	int *key;
-	struct bpf_spinlock_cnt *value;
-} sk_pkt_out_cnt SEC(".maps") = {
-	.type = BPF_MAP_TYPE_SK_STORAGE,
-	.map_flags = BPF_F_NO_PREALLOC,
-};
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct bpf_spinlock_cnt);
+} sk_pkt_out_cnt SEC(".maps");

 struct {
-	__u32 type;
-	__u32 map_flags;
-	int *key;
-	struct bpf_spinlock_cnt *value;
-} sk_pkt_out_cnt10 SEC(".maps") = {
-	.type = BPF_MAP_TYPE_SK_STORAGE,
-	.map_flags = BPF_F_NO_PREALLOC,
-};
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct bpf_spinlock_cnt);
+} sk_pkt_out_cnt10 SEC(".maps");

 static bool is_loopback6(__u32 *a6)
 {
--- a/tools/testing/selftests/bpf/progs/test_spin_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c
@ -11,14 +11,11 @@ struct hmap_elem {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	int *key;
-	struct hmap_elem *value;
-} hmap SEC(".maps") = {
-	.type = BPF_MAP_TYPE_HASH,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct hmap_elem);
+} hmap SEC(".maps");

 struct cls_elem {
 	struct bpf_spin_lock lock;
@ -26,12 +23,10 @@ struct cls_elem {
 };

 struct {
-	__u32 type;
-	struct bpf_cgroup_storage_key *key;
-	struct cls_elem *value;
-} cls_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
-};
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, struct cls_elem);
+} cls_map SEC(".maps");

 struct bpf_vqueue {
 	struct bpf_spin_lock lock;
@ -42,14 +37,11 @@ struct bpf_vqueue {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	int *key;
-	struct bpf_vqueue *value;
-} vqueue SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct bpf_vqueue);
+} vqueue SEC(".maps");

 #define CREDIT_PER_NS(delta, rate) (((delta) * rate) >> 20)

--- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
@ -9,51 +9,36 @@
 #endif

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u32 *value;
-} control_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+} control_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u32 *value;
-} stackid_hmap SEC(".maps") = {
-	.type = BPF_MAP_TYPE_HASH,
-	.max_entries = 16384,
-};
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 16384);
+	__type(key, __u32);
+	__type(value, __u32);
+} stackid_hmap SEC(".maps");

 typedef struct bpf_stack_build_id stack_trace_t[PERF_MAX_STACK_DEPTH];

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 map_flags;
-	__u32 key_size;
-	__u32 value_size;
-} stackmap SEC(".maps") = {
-	.type = BPF_MAP_TYPE_STACK_TRACE,
-	.max_entries = 128,
-	.map_flags = BPF_F_STACK_BUILD_ID,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(stack_trace_t),
-};
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(max_entries, 128);
+	__uint(map_flags, BPF_F_STACK_BUILD_ID);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(stack_trace_t));
+} stackmap SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 128);
+	__type(key, __u32);
 	/* there seems to be a bug in kernel not handling typedef properly */
 	struct bpf_stack_build_id (*value)[PERF_MAX_STACK_DEPTH];
-} stack_amap SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 128,
-};
+} stack_amap SEC(".maps");

 /* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */
 struct random_urandom_args {
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@ -9,48 +9,34 @@
 #endif

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u32 *value;
-} control_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+} control_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u32 *value;
-} stackid_hmap SEC(".maps") = {
-	.type = BPF_MAP_TYPE_HASH,
-	.max_entries = 16384,
-};
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 16384);
+	__type(key, __u32);
+	__type(value, __u32);
+} stackid_hmap SEC(".maps");

 typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH];

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 key_size;
-	__u32 value_size;
-} stackmap SEC(".maps") = {
-	.type = BPF_MAP_TYPE_STACK_TRACE,
-	.max_entries = 16384,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(stack_trace_t),
-};
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(max_entries, 16384);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(stack_trace_t));
+} stackmap SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 16384);
+	__type(key, __u32);
 	__u64 (*value)[PERF_MAX_STACK_DEPTH];
-} stack_amap SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 16384,
-};
+} stack_amap SEC(".maps");

 /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
 struct sched_switch_args {
--- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
@ -149,14 +149,11 @@ struct tcp_estats_basic_event {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct tcp_estats_basic_event *value;
-} ev_record_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_HASH,
-	.max_entries = 1024,
-};
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1024);
+	__type(key, __u32);
+	__type(value, struct tcp_estats_basic_event);
+} ev_record_map SEC(".maps");

 struct dummy_tracepoint_args {
 	unsigned long long pad;
--- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
@ -15,24 +15,18 @@
 #include "test_tcpbpf.h"

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct tcpbpf_globals *value;
-} global_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 4,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 4);
+	__type(key, __u32);
+	__type(value, struct tcpbpf_globals);
+} global_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	int *value;
-} sockopt_results SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 2,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, int);
+} sockopt_results SEC(".maps");

 static inline void update_event_map(int event)
 {
--- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
@ -15,26 +15,18 @@
 #include "test_tcpnotify.h"

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct tcpnotify_globals *value;
-} global_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 4,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 4);
+	__type(key, __u32);
+	__type(value, struct tcpnotify_globals);
+} global_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 key_size;
-	__u32 value_size;
-} perf_event_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
-	.max_entries = 2,
-	.key_size = sizeof(int),
-	.value_size = sizeof(__u32),
-};
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(max_entries, 2);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(__u32));
+} perf_event_map SEC(".maps");

 int _version SEC("version") = 1;

--- a/tools/testing/selftests/bpf/progs/test_xdp.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp.c
@ -23,24 +23,18 @@
 int _version SEC("version") = 1;

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u64 *value;
-} rxcnt SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.max_entries = 256,
-};
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 256);
+	__type(key, __u32);
+	__type(value, __u64);
+} rxcnt SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	struct vip *key;
-	struct iptnl_info *value;
-} vip2tnl SEC(".maps") = {
-	.type = BPF_MAP_TYPE_HASH,
-	.max_entries = MAX_IPTNL_ENTRIES,
-};
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, MAX_IPTNL_ENTRIES);
+	__type(key, struct vip);
+	__type(value, struct iptnl_info);
+} vip2tnl SEC(".maps");

 static __always_inline void count_tx(__u32 protocol)
 {
--- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
@ -18,19 +18,19 @@

 int _version SEC("version") = 1;

-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64),
-	.max_entries = 256,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 256);
+	__type(key, __u32);
+	__type(value, __u64);
+} rxcnt SEC(".maps");

-struct bpf_map_def SEC("maps") vip2tnl = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(struct vip),
-	.value_size = sizeof(struct iptnl_info),
-	.max_entries = MAX_IPTNL_ENTRIES,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, MAX_IPTNL_ENTRIES);
+	__type(key, struct vip);
+	__type(value, struct iptnl_info);
+} vip2tnl SEC(".maps");

 static __always_inline void count_tx(__u32 protocol)
 {
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@ -164,66 +164,47 @@ struct lb_stats {
 };

 struct {
-	__u32 type;
-	__u32 max_entries;
-	struct vip_definition *key;
-	struct vip_meta *value;
-} vip_map SEC(".maps") = {
-	.type = BPF_MAP_TYPE_HASH,
-	.max_entries = 512,
-};
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 512);
+	__type(key, struct vip_definition);
+	__type(value, struct vip_meta);
+} vip_map SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 map_flags;
-	struct flow_key *key;
-	struct real_pos_lru *value;
-} lru_cache SEC(".maps") = {
-	.type = BPF_MAP_TYPE_LRU_HASH,
-	.max_entries = 300,
-	.map_flags = 1U << 1,
-};
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__uint(max_entries, 300);
+	__uint(map_flags, 1U << 1);
+	__type(key, struct flow_key);
+	__type(value, struct real_pos_lru);
+} lru_cache SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	__u32 *value;
-} ch_rings SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 12 * 655,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 12 * 655);
+	__type(key, __u32);
+	__type(value, __u32);
+} ch_rings SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct real_definition *value;
-} reals SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 40,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 40);
+	__type(key, __u32);
+	__type(value, struct real_definition);
+} reals SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct lb_stats *value;
-} stats SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.max_entries = 515,
-};
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 515);
+	__type(key, __u32);
+	__type(value, struct lb_stats);
+} stats SEC(".maps");

 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct ctl_value *value;
-} ctl_array SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 16,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 16);
+	__type(key, __u32);
+	__type(value, struct ctl_value);
+} ctl_array SEC(".maps");

 struct eth_hdr {
 	unsigned char eth_dest[6];
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
@ -3,12 +3,12 @@
 #include <linux/bpf.h>
 #include "bpf_helpers.h"

-struct bpf_map_def SEC("maps") tx_port = {
-	.type = BPF_MAP_TYPE_DEVMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 8,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(max_entries, 8);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} tx_port SEC(".maps");

 SEC("redirect_map_0")
 int xdp_redirect_map_0(struct xdp_md *xdp)
--- a/tools/testing/selftests/bpf/progs/xdping_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdping_kern.c
@ -17,12 +17,12 @@

 #include "xdping.h"

-struct bpf_map_def SEC("maps") ping_map = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct pinginfo),
-	.max_entries = 256,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 256);
+	__type(key, __u32);
+	__type(value, struct pinginfo);
+} ping_map SEC(".maps");

 static __always_inline void swap_src_dst_mac(void *data)
 {
--- a/tools/testing/selftests/bpf/test_align.c
+++ b/tools/testing/selftests/bpf/test_align.c
@ -180,7 +180,7 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{7, "R0=pkt(id=0,off=8,r=8,imm=0)"},
+			{7, "R0_w=pkt(id=0,off=8,r=8,imm=0)"},
 			{7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
 			{8, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
 			{9, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
@ -315,7 +315,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{8, "R2=pkt(id=0,off=0,r=8,imm=0)"},
+			{8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
 			{8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Offset is added to packet pointer R5, resulting in
 			 * known fixed offset, and variable offset from R6.
@ -405,7 +405,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{8, "R2=pkt(id=0,off=0,r=8,imm=0)"},
+			{8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
 			{8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Adding 14 makes R6 be (4n+2) */
 			{9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
@ -473,12 +473,12 @@ static struct bpf_align_test tests[] = {
 			/* (4n) + 14 == (4n+2).  We blow our bounds, because
 			 * the add could overflow.
 			 */
-			{7, "R5=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"},
+			{7, "R5_w=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"},
 			/* Checked s>=0 */
 			{9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
 			/* packet pointer + nonnegative (4n+2) */
 			{11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
-			{13, "R4=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+			{13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
 			/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
 			 * We checked the bounds, but it might have been able
 			 * to overflow if the packet pointer started in the
@ -486,7 +486,7 @@ static struct bpf_align_test tests[] = {
 			 * So we did not get a 'range' on R6, and the access
 			 * attempt will fail.
 			 */
-			{15, "R6=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+			{15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
 		}
 	},
 	{
@ -521,7 +521,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{7, "R2=pkt(id=0,off=0,r=8,imm=0)"},
+			{7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
 			{9, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Adding 14 makes R6 be (4n+2) */
 			{10, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
@ -574,7 +574,7 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{7, "R2=pkt(id=0,off=0,r=8,imm=0)"},
+			{7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
 			{10, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"},
 			/* Adding 14 makes R6 be (4n+2) */
 			{11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@ -1418,7 +1418,7 @@ static void test_map_wronly(void)
 	assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM);
 }

-static void prepare_reuseport_grp(int type, int map_fd,
+static void prepare_reuseport_grp(int type, int map_fd, size_t map_elem_size,
 				  __s64 *fds64, __u64 *sk_cookies,
 				  unsigned int n)
 {
@ -1428,6 +1428,8 @@ static void prepare_reuseport_grp(int type, int map_fd,
 	const int optval = 1;
 	unsigned int i;
 	u64 sk_cookie;
+	void *value;
+	__s32 fd32;
 	__s64 fd64;
 	int err;

@ -1449,8 +1451,14 @@ static void prepare_reuseport_grp(int type, int map_fd,
 		      "err:%d errno:%d\n", err, errno);

 		/* reuseport_array does not allow unbound sk */
-		err = bpf_map_update_elem(map_fd, &index0, &fd64,
-					  BPF_ANY);
+		if (map_elem_size == sizeof(__u64))
+			value = &fd64;
+		else {
+			assert(map_elem_size == sizeof(__u32));
+			fd32 = (__s32)fd64;
+			value = &fd32;
+		}
+		err = bpf_map_update_elem(map_fd, &index0, value, BPF_ANY);
 		CHECK(err != -1 || errno != EINVAL,
 		      "reuseport array update unbound sk",
 		      "sock_type:%d err:%d errno:%d\n",
@ -1478,7 +1486,7 @@ static void prepare_reuseport_grp(int type, int map_fd,
 			 * reuseport_array does not allow
 			 * non-listening tcp sk.
 			 */
-			err = bpf_map_update_elem(map_fd, &index0, &fd64,
+			err = bpf_map_update_elem(map_fd, &index0, value,
 						  BPF_ANY);
 			CHECK(err != -1 || errno != EINVAL,
 			      "reuseport array update non-listening sk",
@ -1541,7 +1549,7 @@ static void test_reuseport_array(void)
 	for (t = 0; t < ARRAY_SIZE(types); t++) {
 		type = types[t];

-		prepare_reuseport_grp(type, map_fd, grpa_fds64,
+		prepare_reuseport_grp(type, map_fd, sizeof(__u64), grpa_fds64,
 				      grpa_cookies, ARRAY_SIZE(grpa_fds64));

 		/* Test BPF_* update flags */
@ -1649,7 +1657,8 @@ static void test_reuseport_array(void)
 				sizeof(__u32), sizeof(__u32), array_size, 0);
 	CHECK(map_fd == -1, "reuseport array create",
 	      "map_fd:%d, errno:%d\n", map_fd, errno);
-	prepare_reuseport_grp(SOCK_STREAM, map_fd, &fd64, &sk_cookie, 1);
+	prepare_reuseport_grp(SOCK_STREAM, map_fd, sizeof(__u32), &fd64,
+			      &sk_cookie, 1);
 	fd = fd64;
 	err = bpf_map_update_elem(map_fd, &index3, &fd, BPF_NOEXIST);
 	CHECK(err == -1, "reuseport array update 32 bit fd",
--- a/tools/testing/selftests/bpf/test_queue_stack_map.h
+++ b/tools/testing/selftests/bpf/test_queue_stack_map.h
@ -10,21 +10,21 @@

 int _version SEC("version") = 1;

-struct bpf_map_def __attribute__ ((section("maps"), used)) map_in = {
-	.type = MAP_TYPE,
-	.key_size = 0,
-	.value_size = sizeof(__u32),
-	.max_entries = 32,
-	.map_flags = 0,
-};
+struct {
+	__uint(type, MAP_TYPE);
+	__uint(max_entries, 32);
+	__uint(map_flags, 0);
+	__uint(key_size, 0);
+	__uint(value_size, sizeof(__u32));
+} map_in SEC(".maps");

-struct bpf_map_def __attribute__ ((section("maps"), used)) map_out = {
-	.type = MAP_TYPE,
-	.key_size = 0,
-	.value_size = sizeof(__u32),
-	.max_entries = 32,
-	.map_flags = 0,
-};
+struct {
+	__uint(type, MAP_TYPE);
+	__uint(max_entries, 32);
+	__uint(map_flags, 0);
+	__uint(key_size, 0);
+	__uint(value_size, sizeof(__u32));
+} map_out SEC(".maps");

 SEC("test")
 int _test(struct __sk_buff *skb)
--- a/tools/testing/selftests/bpf/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/test_sockmap_kern.h
@ -28,61 +28,61 @@
 * are established and verdicts are decided.
 */

-struct bpf_map_def SEC("maps") sock_map = {
-	.type = TEST_MAP_TYPE,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 20,
-};
+struct {
+	__uint(type, TEST_MAP_TYPE);
+	__uint(max_entries, 20);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} sock_map SEC(".maps");

-struct bpf_map_def SEC("maps") sock_map_txmsg = {
-	.type = TEST_MAP_TYPE,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 20,
-};
+struct {
+	__uint(type, TEST_MAP_TYPE);
+	__uint(max_entries, 20);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} sock_map_txmsg SEC(".maps");

-struct bpf_map_def SEC("maps") sock_map_redir = {
-	.type = TEST_MAP_TYPE,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 20,
-};
+struct {
+	__uint(type, TEST_MAP_TYPE);
+	__uint(max_entries, 20);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} sock_map_redir SEC(".maps");

-struct bpf_map_def SEC("maps") sock_apply_bytes = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 1
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sock_apply_bytes SEC(".maps");

-struct bpf_map_def SEC("maps") sock_cork_bytes = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 1
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sock_cork_bytes SEC(".maps");

-struct bpf_map_def SEC("maps") sock_bytes = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 6
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 6);
+	__type(key, int);
+	__type(value, int);
+} sock_bytes SEC(".maps");

-struct bpf_map_def SEC("maps") sock_redir_flags = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 1
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sock_redir_flags SEC(".maps");

-struct bpf_map_def SEC("maps") sock_skb_opts = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 1
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sock_skb_opts SEC(".maps");

 SEC("sk_skb1")
 int bpf_prog1(struct __sk_buff *skb)
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@ -105,6 +105,7 @@ struct bpf_test {
 			__u64 data64[TEST_DATA_LEN / 8];
 		};
 	} retvals[MAX_TEST_RUNS];
+	enum bpf_attach_type expected_attach_type;
 };

 /* Note we want this to be 64 bit aligned so that the end of our array is
@ -850,6 +851,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	int fd_prog, expected_ret, alignment_prevented_execution;
 	int prog_len, prog_type = test->prog_type;
 	struct bpf_insn *prog = test->insns;
+	struct bpf_load_program_attr attr;
 	int run_errs, run_successes;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
@ -881,8 +883,17 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		pflags |= BPF_F_STRICT_ALIGNMENT;
 	if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
 		pflags |= BPF_F_ANY_ALIGNMENT;
-	fd_prog = bpf_verify_program(prog_type, prog, prog_len, pflags,
-				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 4);
+
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_type = prog_type;
+	attr.expected_attach_type = test->expected_attach_type;
+	attr.insns = prog;
+	attr.insns_cnt = prog_len;
+	attr.license = "GPL";
+	attr.log_level = 4;
+	attr.prog_flags = pflags;
+
+	fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog));
 	if (fd_prog < 0 && !bpf_probe_prog_type(prog_type, 0)) {
 		printf("SKIP (unsupported program type %d)\n", prog_type);
 		skips++;
@ -912,7 +923,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 			printf("FAIL\nUnexpected success to load!\n");
 			goto fail_log;
 		}
-		if (!strstr(bpf_vlog, expected_err)) {
+		if (!expected_err || !strstr(bpf_vlog, expected_err)) {
 			printf("FAIL\nUnexpected error message!\n\tEXP: %s\n\tRES: %s\n",
 			      expected_err, bpf_vlog);
 			goto fail_log;
--- a/tools/testing/selftests/bpf/verifier/wide_store.c
+++ b/tools/testing/selftests/bpf/verifier/wide_store.c
@ -0,0 +1,36 @@
+#define BPF_SOCK_ADDR(field, off, res, err) \
+{ \
+	"wide store to bpf_sock_addr." #field "[" #off "]", \
+	.insns = { \
+	BPF_MOV64_IMM(BPF_REG_0, 1), \
+	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, \
+		    offsetof(struct bpf_sock_addr, field[off])), \
+	BPF_EXIT_INSN(), \
+	}, \
+	.result = res, \
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
+	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
+	.errstr = err, \
+}
+
+/* user_ip6[0] is u64 aligned */
+BPF_SOCK_ADDR(user_ip6, 0, ACCEPT,
+	      NULL),
+BPF_SOCK_ADDR(user_ip6, 1, REJECT,
+	      "invalid bpf_context access off=12 size=8"),
+BPF_SOCK_ADDR(user_ip6, 2, ACCEPT,
+	      NULL),
+BPF_SOCK_ADDR(user_ip6, 3, REJECT,
+	      "invalid bpf_context access off=20 size=8"),
+
+/* msg_src_ip6[0] is _not_ u64 aligned */
+BPF_SOCK_ADDR(msg_src_ip6, 0, REJECT,
+	      "invalid bpf_context access off=44 size=8"),
+BPF_SOCK_ADDR(msg_src_ip6, 1, ACCEPT,
+	      NULL),
+BPF_SOCK_ADDR(msg_src_ip6, 2, REJECT,
+	      "invalid bpf_context access off=52 size=8"),
+BPF_SOCK_ADDR(msg_src_ip6, 3, REJECT,
+	      "invalid bpf_context access off=56 size=8"),
+
+#undef BPF_SOCK_ADDR