phase 2

tools/accounting/getdelays.c

@@ -205,6 +205,8 @@ static void print_delayacct(struct taskstats *t)
 	       "RECLAIM  %12s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n"
 	       "THRASHING%12s%15s%15s\n"
+	       "      %15llu%15llu%15llums\n"
+	       "COMPACT  %12s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n",
 	       "count", "real total", "virtual total",
 	       "delay total", "delay average",
@@ -228,7 +230,11 @@ static void print_delayacct(struct taskstats *t)
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->thrashing_count,
 	       (unsigned long long)t->thrashing_delay_total,
-	       average_ms(t->thrashing_delay_total, t->thrashing_count));
+	       average_ms(t->thrashing_delay_total, t->thrashing_count),
+	       "count", "delay total", "delay average",
+	       (unsigned long long)t->compact_count,
+	       (unsigned long long)t->compact_delay_total,
+	       average_ms(t->compact_delay_total, t->compact_count));
 }
 
 static void task_context_switch_counts(struct taskstats *t)

tools/bootconfig/Makefile

@@ -15,9 +15,9 @@ CFLAGS = -Wall -g -I$(CURDIR)/include
 ALL_TARGETS := bootconfig
 ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
 
-all: $(ALL_PROGRAMS)
+all: $(ALL_PROGRAMS) test
 
-$(OUTPUT)bootconfig: main.c $(LIBSRC)
+$(OUTPUT)bootconfig: main.c include/linux/bootconfig.h $(LIBSRC)
 	$(CC) $(filter %.c,$^) $(CFLAGS) -o $@
 
 test: $(ALL_PROGRAMS) test-bootconfig.sh

tools/bootconfig/include/linux/bootconfig.h

@@ -2,10 +2,53 @@
 #ifndef _BOOTCONFIG_LINUX_BOOTCONFIG_H
 #define _BOOTCONFIG_LINUX_BOOTCONFIG_H
 
-#include "../../../../include/linux/bootconfig.h"
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <stdbool.h>
+#include <ctype.h>
+#include <errno.h>
+#include <string.h>
+
 
 #ifndef fallthrough
 # define fallthrough
 #endif
 
+#define WARN_ON(cond)	\
+	((cond) ? printf("Internal warning(%s:%d, %s): %s\n",	\
+			__FILE__, __LINE__, __func__, #cond) : 0)
+
+#define unlikely(cond)	(cond)
+
+/* Copied from lib/string.c */
+static inline char *skip_spaces(const char *str)
+{
+	while (isspace(*str))
+		++str;
+	return (char *)str;
+}
+
+static inline char *strim(char *s)
+{
+	size_t size;
+	char *end;
+
+	size = strlen(s);
+	if (!size)
+		return s;
+
+	end = s + size - 1;
+	while (end >= s && isspace(*end))
+		end--;
+	*(end + 1) = '\0';
+
+	return skip_spaces(s);
+}
+
+#define __init
+#define __initdata
+
+#include "../../../../include/linux/bootconfig.h"
+
 #endif

tools/bootconfig/main.c

@@ -12,9 +12,10 @@
 #include <errno.h>
 #include <endian.h>
 
-#include <linux/kernel.h>
 #include <linux/bootconfig.h>
 
+#define pr_err(fmt, ...) fprintf(stderr, fmt, ##__VA_ARGS__)
+
 static int xbc_show_value(struct xbc_node *node, bool semicolon)
 {
 	const char *val, *eol;
@@ -176,7 +177,7 @@ static int load_xbc_from_initrd(int fd, char **buf)
 {
 	struct stat stat;
 	int ret;
-	u32 size = 0, csum = 0, rcsum;
+	uint32_t size = 0, csum = 0, rcsum;
 	char magic[BOOTCONFIG_MAGIC_LEN];
 	const char *msg;
 
@@ -200,11 +201,11 @@ static int load_xbc_from_initrd(int fd, char **buf)
 	if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0)
 		return pr_errno("Failed to lseek for size", -errno);
 
-	if (read(fd, &size, sizeof(u32)) < 0)
+	if (read(fd, &size, sizeof(uint32_t)) < 0)
 		return pr_errno("Failed to read size", -errno);
 	size = le32toh(size);
 
-	if (read(fd, &csum, sizeof(u32)) < 0)
+	if (read(fd, &csum, sizeof(uint32_t)) < 0)
 		return pr_errno("Failed to read checksum", -errno);
 	csum = le32toh(csum);
 
@@ -229,7 +230,7 @@ static int load_xbc_from_initrd(int fd, char **buf)
 		return -EINVAL;
 	}
 
-	ret = xbc_init(*buf, &msg, NULL);
+	ret = xbc_init(*buf, size, &msg, NULL);
 	/* Wrong data */
 	if (ret < 0) {
 		pr_err("parse error: %s.\n", msg);
@@ -269,7 +270,7 @@ static int init_xbc_with_error(char *buf, int len)
 	if (!copy)
 		return -ENOMEM;
 
-	ret = xbc_init(buf, &msg, &pos);
+	ret = xbc_init(buf, len, &msg, &pos);
 	if (ret < 0)
 		show_xbc_error(copy, msg, pos);
 	free(copy);
@@ -362,7 +363,7 @@ static int apply_xbc(const char *path, const char *xbc_path)
 	size_t total_size;
 	struct stat stat;
 	const char *msg;
-	u32 size, csum;
+	uint32_t size, csum;
 	int pos, pad;
 	int ret, fd;
 
@@ -376,13 +377,13 @@ static int apply_xbc(const char *path, const char *xbc_path)
 
 	/* Backup the bootconfig data */
 	data = calloc(size + BOOTCONFIG_ALIGN +
-		      sizeof(u32) + sizeof(u32) + BOOTCONFIG_MAGIC_LEN, 1);
+		      sizeof(uint32_t) + sizeof(uint32_t) + BOOTCONFIG_MAGIC_LEN, 1);
 	if (!data)
 		return -ENOMEM;
 	memcpy(data, buf, size);
 
 	/* Check the data format */
-	ret = xbc_init(buf, &msg, &pos);
+	ret = xbc_init(buf, size, &msg, &pos);
 	if (ret < 0) {
 		show_xbc_error(data, msg, pos);
 		free(data);
@@ -391,12 +392,13 @@ static int apply_xbc(const char *path, const char *xbc_path)
 		return ret;
 	}
 	printf("Apply %s to %s\n", xbc_path, path);
+	xbc_get_info(&ret, NULL);
 	printf("\tNumber of nodes: %d\n", ret);
 	printf("\tSize: %u bytes\n", (unsigned int)size);
 	printf("\tChecksum: %d\n", (unsigned int)csum);
 
 	/* TODO: Check the options by schema */
-	xbc_destroy_all();
+	xbc_exit();
 	free(buf);
 
 	/* Remove old boot config if exists */
@@ -423,17 +425,17 @@ static int apply_xbc(const char *path, const char *xbc_path)
 	}
 
 	/* To align up the total size to BOOTCONFIG_ALIGN, get padding size */
-	total_size = stat.st_size + size + sizeof(u32) * 2 + BOOTCONFIG_MAGIC_LEN;
+	total_size = stat.st_size + size + sizeof(uint32_t) * 2 + BOOTCONFIG_MAGIC_LEN;
 	pad = ((total_size + BOOTCONFIG_ALIGN - 1) & (~BOOTCONFIG_ALIGN_MASK)) - total_size;
 	size += pad;
 
 	/* Add a footer */
 	p = data + size;
-	*(u32 *)p = htole32(size);
-	p += sizeof(u32);
+	*(uint32_t *)p = htole32(size);
+	p += sizeof(uint32_t);
 
-	*(u32 *)p = htole32(csum);
-	p += sizeof(u32);
+	*(uint32_t *)p = htole32(csum);
+	p += sizeof(uint32_t);
 
 	memcpy(p, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
 	p += BOOTCONFIG_MAGIC_LEN;

tools/bpf/bpftool/.gitignore

@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 *.d
 /bootstrap/
 /bpftool

tools/bpf/bpftool/Documentation/Makefile

@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 include ../../../scripts/Makefile.include
 
 INSTALL ?= install
@@ -24,7 +24,7 @@ man: man8
 man8: $(DOC_MAN8)
 
 RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
-RST2MAN_OPTS += --verbose
+RST2MAN_OPTS += --verbose --strip-comments
 
 list_pages = $(sort $(basename $(filter-out $(1),$(MAN8_RST))))
 see_also = $(subst " ",, \

tools/bpf/bpftool/Documentation/bpftool-btf.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ================
 bpftool-btf
 ================
@@ -7,13 +9,14 @@ tool for inspection of BTF data
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
 	**bpftool** [*OPTIONS*] **btf** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | {**-d** | **--debug** } |
-	{ **-B** | **--base-btf** } }
+	*OPTIONS* := { |COMMON_OPTIONS| | { **-B** | **--base-btf** } }
 
 	*COMMANDS* := { **dump** | **help** }
 

tools/bpf/bpftool/Documentation/bpftool-cgroup.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ================
 bpftool-cgroup
 ================
@@ -7,13 +9,14 @@ tool for inspection and simple manipulation of eBPF progs
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
 	**bpftool** [*OPTIONS*] **cgroup** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } |
-	{ **-f** | **--bpffs** } }
+	*OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } }
 
 	*COMMANDS* :=
 	{ **show** | **list** | **tree** | **attach** | **detach** | **help** }
@@ -30,9 +33,9 @@ CGROUP COMMANDS
 |	*PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
 |	*ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** |
 |		**bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** |
-|               **getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** |
-|               **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** |
-|               **sock_release** }
+|		**getpeername4** | **getpeername6** | **getsockname4** | **getsockname6** | **sendmsg4** |
+|		**sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | **getsockopt** | **setsockopt** |
+|		**sock_release** }
 |	*ATTACH_FLAGS* := { **multi** | **override** }
 
 DESCRIPTION
@@ -98,9 +101,9 @@ DESCRIPTION
 		  **sendmsg6** call to sendto(2), sendmsg(2), sendmmsg(2) for an
 		  unconnected udp6 socket (since 4.18);
 		  **recvmsg4** call to recvfrom(2), recvmsg(2), recvmmsg(2) for
-                  an unconnected udp4 socket (since 5.2);
+		  an unconnected udp4 socket (since 5.2);
 		  **recvmsg6** call to recvfrom(2), recvmsg(2), recvmmsg(2) for
-                  an unconnected udp6 socket (since 5.2);
+		  an unconnected udp6 socket (since 5.2);
 		  **sysctl** sysctl access (since 5.2);
 		  **getsockopt** call to getsockopt (since 5.3);
 		  **setsockopt** call to setsockopt (since 5.3);

tools/bpf/bpftool/Documentation/bpftool-feature.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ===============
 bpftool-feature
 ===============
@@ -7,12 +9,14 @@ tool for inspection of eBPF-related parameters for Linux kernel or net device
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
 	**bpftool** [*OPTIONS*] **feature** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } }
+	*OPTIONS* := { |COMMON_OPTIONS| }
 
 	*COMMANDS* := { **probe** | **help** }
 

tools/bpf/bpftool/Documentation/bpftool-gen.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ================
 bpftool-gen
 ================
@@ -7,13 +9,14 @@ tool for BPF code-generation
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
 	**bpftool** [*OPTIONS*] **gen** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } |
-	{ **-L** | **--use-loader** } }
+	*OPTIONS* := { |COMMON_OPTIONS| | { **-L** | **--use-loader** } }
 
 	*COMMAND* := { **object** | **skeleton** | **help** }
 

tools/bpf/bpftool/Documentation/bpftool-iter.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ============
 bpftool-iter
 ============
@@ -7,12 +9,14 @@ tool to create BPF iterators
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
 	**bpftool** [*OPTIONS*] **iter** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } }
+	*OPTIONS* := { |COMMON_OPTIONS| }
 
 	*COMMANDS* := { **pin** | **help** }
 

tools/bpf/bpftool/Documentation/bpftool-link.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ================
 bpftool-link
 ================
@@ -7,13 +9,14 @@ tool for inspection and simple manipulation of eBPF links
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
 	**bpftool** [*OPTIONS*] **link** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } |
-	{ **-f** | **--bpffs** } | { **-n** | **--nomount** } }
+	*OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } }
 
 	*COMMANDS* := { **show** | **list** | **pin** | **help** }
 

tools/bpf/bpftool/Documentation/bpftool-map.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ================
 bpftool-map
 ================
@@ -7,13 +9,14 @@ tool for inspection and simple manipulation of eBPF maps
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
 	**bpftool** [*OPTIONS*] **map** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } |
-	{ **-f** | **--bpffs** } | { **-n** | **--nomount** } }
+	*OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } }
 
 	*COMMANDS* :=
 	{ **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** |
@@ -52,7 +55,7 @@ MAP COMMANDS
 |		| **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash**
 |		| **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage**
 |		| **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage**
-		| **task_storage** }
+|		| **task_storage** | **bloom_filter** }
 
 DESCRIPTION
 ===========

tools/bpf/bpftool/Documentation/bpftool-net.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ================
 bpftool-net
 ================
@@ -7,12 +9,14 @@ tool for inspection of netdev/tc related bpf prog attachments
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
 	**bpftool** [*OPTIONS*] **net** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } }
+	*OPTIONS* := { |COMMON_OPTIONS| }
 
 	*COMMANDS* :=
 	{ **show** | **list** | **attach** | **detach** | **help** }
@@ -31,44 +35,44 @@ NET COMMANDS
 DESCRIPTION
 ===========
 	**bpftool net { show | list }** [ **dev** *NAME* ]
-                  List bpf program attachments in the kernel networking subsystem.
+		  List bpf program attachments in the kernel networking subsystem.
 
-                  Currently, only device driver xdp attachments and tc filter
-                  classification/action attachments are implemented, i.e., for
-                  program types **BPF_PROG_TYPE_SCHED_CLS**,
-                  **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**.
-                  For programs attached to a particular cgroup, e.g.,
-                  **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**,
-                  **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
-                  users can use **bpftool cgroup** to dump cgroup attachments.
-                  For sk_{filter, skb, msg, reuseport} and lwt/seg6
-                  bpf programs, users should consult other tools, e.g., iproute2.
+		  Currently, only device driver xdp attachments and tc filter
+		  classification/action attachments are implemented, i.e., for
+		  program types **BPF_PROG_TYPE_SCHED_CLS**,
+		  **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**.
+		  For programs attached to a particular cgroup, e.g.,
+		  **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**,
+		  **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+		  users can use **bpftool cgroup** to dump cgroup attachments.
+		  For sk_{filter, skb, msg, reuseport} and lwt/seg6
+		  bpf programs, users should consult other tools, e.g., iproute2.
 
-                  The current output will start with all xdp program attachments, followed by
-                  all tc class/qdisc bpf program attachments. Both xdp programs and
-                  tc programs are ordered based on ifindex number. If multiple bpf
-                  programs attached to the same networking device through **tc filter**,
-                  the order will be first all bpf programs attached to tc classes, then
-                  all bpf programs attached to non clsact qdiscs, and finally all
-                  bpf programs attached to root and clsact qdisc.
+		  The current output will start with all xdp program attachments, followed by
+		  all tc class/qdisc bpf program attachments. Both xdp programs and
+		  tc programs are ordered based on ifindex number. If multiple bpf
+		  programs attached to the same networking device through **tc filter**,
+		  the order will be first all bpf programs attached to tc classes, then
+		  all bpf programs attached to non clsact qdiscs, and finally all
+		  bpf programs attached to root and clsact qdisc.
 
 	**bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ]
-                  Attach bpf program *PROG* to network interface *NAME* with
-                  type specified by *ATTACH_TYPE*. Previously attached bpf program
-                  can be replaced by the command used with **overwrite** option.
-                  Currently, only XDP-related modes are supported for *ATTACH_TYPE*.
+		  Attach bpf program *PROG* to network interface *NAME* with
+		  type specified by *ATTACH_TYPE*. Previously attached bpf program
+		  can be replaced by the command used with **overwrite** option.
+		  Currently, only XDP-related modes are supported for *ATTACH_TYPE*.
 
-                  *ATTACH_TYPE* can be of:
-                  **xdp** - try native XDP and fallback to generic XDP if NIC driver does not support it;
-                  **xdpgeneric** - Generic XDP. runs at generic XDP hook when packet already enters receive path as skb;
-                  **xdpdrv** - Native XDP. runs earliest point in driver's receive path;
-                  **xdpoffload** - Offload XDP. runs directly on NIC on each packet reception;
+		  *ATTACH_TYPE* can be of:
+		  **xdp** - try native XDP and fallback to generic XDP if NIC driver does not support it;
+		  **xdpgeneric** - Generic XDP. runs at generic XDP hook when packet already enters receive path as skb;
+		  **xdpdrv** - Native XDP. runs earliest point in driver's receive path;
+		  **xdpoffload** - Offload XDP. runs directly on NIC on each packet reception;
 
 	**bpftool** **net detach** *ATTACH_TYPE* **dev** *NAME*
-                  Detach bpf program attached to network interface *NAME* with
-                  type specified by *ATTACH_TYPE*. To detach bpf program, same
-                  *ATTACH_TYPE* previously used for attach must be specified.
-                  Currently, only XDP-related modes are supported for *ATTACH_TYPE*.
+		  Detach bpf program attached to network interface *NAME* with
+		  type specified by *ATTACH_TYPE*. To detach bpf program, same
+		  *ATTACH_TYPE* previously used for attach must be specified.
+		  Currently, only XDP-related modes are supported for *ATTACH_TYPE*.
 
 	**bpftool net help**
 		  Print short help message.

tools/bpf/bpftool/Documentation/bpftool-perf.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ================
 bpftool-perf
 ================
@@ -7,12 +9,14 @@ tool for inspection of perf related bpf prog attachments
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
 	**bpftool** [*OPTIONS*] **perf** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } }
+	*OPTIONS* := { |COMMON_OPTIONS| }
 
 	*COMMANDS* :=
 	{ **show** | **list** | **help** }

tools/bpf/bpftool/Documentation/bpftool-prog.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ================
 bpftool-prog
 ================
@@ -7,12 +9,14 @@ tool for inspection and simple manipulation of eBPF progs
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
 	**bpftool** [*OPTIONS*] **prog** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } |
+	*OPTIONS* := { |COMMON_OPTIONS| |
 	{ **-f** | **--bpffs** } | { **-m** | **--mapcompat** } | { **-n** | **--nomount** } |
 	{ **-L** | **--use-loader** } }
 

tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ==================
 bpftool-struct_ops
 ==================
@@ -7,12 +9,14 @@ tool to register/unregister/introspect BPF struct_ops
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
 	**bpftool** [*OPTIONS*] **struct_ops** *COMMAND*
 
-	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } }
+	*OPTIONS* := { |COMMON_OPTIONS| }
 
 	*COMMANDS* :=
 	{ **show** | **list** | **dump** | **register** | **unregister** | **help** }

tools/bpf/bpftool/Documentation/bpftool.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 ================
 BPFTOOL
 ================
@@ -7,6 +9,8 @@ tool for inspection and simple manipulation of eBPF programs and maps
 
 :Manual section: 8
 
+.. include:: substitutions.rst
+
 SYNOPSIS
 ========
 
@@ -18,8 +22,7 @@ SYNOPSIS
 
 	*OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** }
 
-	*OPTIONS* := { { **-V** | **--version** } |
-	{ **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } }
+	*OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| }
 
 	*MAP-COMMANDS* :=
 	{ **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** |

tools/bpf/bpftool/Documentation/common_options.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
 -h, --help
 	  Print short help message (similar to **bpftool help**).
 
@@ -20,3 +22,12 @@
 	  Print all logs available, even debug-level information. This includes
 	  logs from libbpf as well as from the verifier, when attempting to
 	  load programs.
+
+-l, --legacy
+	  Use legacy libbpf mode which has more relaxed BPF program
+	  requirements. By default, bpftool has more strict requirements
+	  about section names, changes pinning logic and doesn't support
+	  some of the older non-BTF map declarations.
+
+	  See https://github.com/libbpf/libbpf/wiki/Libbpf:-the-road-to-v1.0
+	  for details.

tools/bpf/bpftool/Makefile

@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 include ../../scripts/Makefile.include
 
 ifeq ($(srctree),)
@@ -13,35 +13,55 @@ else
   Q = @
 endif
 
-BPF_DIR = $(srctree)/tools/lib/bpf/
+BPF_DIR = $(srctree)/tools/lib/bpf
 
 ifneq ($(OUTPUT),)
-  LIBBPF_OUTPUT = $(OUTPUT)/libbpf/
-  LIBBPF_PATH = $(LIBBPF_OUTPUT)
-  BOOTSTRAP_OUTPUT = $(OUTPUT)/bootstrap/
+  _OUTPUT := $(OUTPUT)
 else
-  LIBBPF_OUTPUT =
-  LIBBPF_PATH = $(BPF_DIR)
-  BOOTSTRAP_OUTPUT = $(CURDIR)/bootstrap/
+  _OUTPUT := $(CURDIR)
 endif
+BOOTSTRAP_OUTPUT := $(_OUTPUT)/bootstrap/
 
-LIBBPF = $(LIBBPF_PATH)libbpf.a
-LIBBPF_BOOTSTRAP_OUTPUT = $(BOOTSTRAP_OUTPUT)libbpf/
-LIBBPF_BOOTSTRAP = $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a
+LIBBPF_OUTPUT := $(_OUTPUT)/libbpf/
+LIBBPF_DESTDIR := $(LIBBPF_OUTPUT)
+LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include
+LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf
+LIBBPF := $(LIBBPF_OUTPUT)libbpf.a
+
+LIBBPF_BOOTSTRAP_OUTPUT := $(BOOTSTRAP_OUTPUT)libbpf/
+LIBBPF_BOOTSTRAP_DESTDIR := $(LIBBPF_BOOTSTRAP_OUTPUT)
+LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)/include
+LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf
+LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a
+
+# We need to copy hashmap.h and nlattr.h which is not otherwise exported by
+# libbpf, but still required by bpftool.
+LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h)
+LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h)
 
 ifeq ($(BPFTOOL_VERSION),)
 BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
 endif
 
-$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT):
+$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR) $(LIBBPF_BOOTSTRAP_HDRS_DIR):
 	$(QUIET_MKDIR)mkdir -p $@
 
-$(LIBBPF): FORCE | $(LIBBPF_OUTPUT)
-	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) $(LIBBPF_OUTPUT)libbpf.a
+$(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT)
+	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \
+		DESTDIR=$(LIBBPF_DESTDIR) prefix= $(LIBBPF) install_headers
 
-$(LIBBPF_BOOTSTRAP): FORCE | $(LIBBPF_BOOTSTRAP_OUTPUT)
+$(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_DIR)
+	$(call QUIET_INSTALL, $@)
+	$(Q)install -m 644 -t $(LIBBPF_HDRS_DIR) $<
+
+$(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \
-		ARCH= CC=$(HOSTCC) LD=$(HOSTLD) $@
+		DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR) prefix= \
+		ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers
+
+$(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR)
+	$(call QUIET_INSTALL, $@)
+	$(Q)install -m 644 -t $(LIBBPF_BOOTSTRAP_HDRS_DIR) $<
 
 $(LIBBPF)-clean: FORCE | $(LIBBPF_OUTPUT)
 	$(call QUIET_CLEAN, libbpf)
@@ -59,11 +79,10 @@ CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers
 CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS))
 CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \
 	-I$(if $(OUTPUT),$(OUTPUT),.) \
+	-I$(LIBBPF_INCLUDE) \
 	-I$(srctree)/kernel/bpf/ \
 	-I$(srctree)/tools/include \
-	-I$(srctree)/tools/include/uapi \
-	-I$(srctree)/tools/lib \
-	-I$(srctree)/tools/perf
+	-I$(srctree)/tools/include/uapi
 CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
 ifneq ($(EXTRA_CFLAGS),)
 CFLAGS += $(EXTRA_CFLAGS)
@@ -133,10 +152,16 @@ CFLAGS += -DHAVE_LIBBFD_SUPPORT
 SRCS += $(BFD_SRCS)
 endif
 
+HOST_CFLAGS = $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\
+		$(subst $(CLANG_CROSS_FLAGS),,$(CFLAGS)))
+
 BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool
 
 BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o)
+$(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP)
+
 OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
+$(OBJS): $(LIBBPF) $(LIBBPF_INTERNAL_HDRS)
 
 VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
 		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
@@ -159,13 +184,13 @@ else
 	$(Q)cp "$(VMLINUX_H)" $@
 endif
 
-$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF)
+$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP)
 	$(QUIET_CLANG)$(CLANG) \
 		-I$(if $(OUTPUT),$(OUTPUT),.) \
 		-I$(srctree)/tools/include/uapi/ \
-		-I$(LIBBPF_PATH) \
-		-I$(srctree)/tools/lib \
-		-g -O2 -Wall -target bpf -c $< -o $@ && $(LLVM_STRIP) -g $@
+		-I$(LIBBPF_BOOTSTRAP_INCLUDE) \
+		-g -O2 -Wall -target bpf -c $< -o $@
+	$(Q)$(LLVM_STRIP) -g $@
 
 $(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP)
 	$(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) gen skeleton $< > $@
@@ -180,25 +205,27 @@ endif
 CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS)
 
 $(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
-	$(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD -o $@ $<
+	$(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@
 
 $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
-	$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $<
+	$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@
 
-$(OUTPUT)feature.o: | zdep
+$(OUTPUT)feature.o:
+ifneq ($(feature-zlib), 1)
+	$(error "No zlib found")
+endif
 
 $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP)
-	$(QUIET_LINK)$(HOSTCC) $(CFLAGS) $(LDFLAGS) -o $@ $(BOOTSTRAP_OBJS) \
-		$(LIBS_BOOTSTRAP)
+	$(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@
 
 $(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
-	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OBJS) $(LIBS) -o $@
 
-$(BOOTSTRAP_OUTPUT)%.o: %.c | $(BOOTSTRAP_OUTPUT)
-	$(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD -o $@ $<
+$(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT)
+	$(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@
 
 $(OUTPUT)%.o: %.c
-	$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $<
+	$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@
 
 feature-detect-clean:
 	$(call QUIET_CLEAN, feature-detect)
@@ -213,10 +240,12 @@ clean: $(LIBBPF)-clean $(LIBBPF_BOOTSTRAP)-clean feature-detect-clean
 	$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool
 	$(Q)$(RM) -r -- $(OUTPUT)feature/
 
-install: $(OUTPUT)bpftool
+install-bin: $(OUTPUT)bpftool
 	$(call QUIET_INSTALL, bpftool)
 	$(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/sbin
 	$(Q)$(INSTALL) $(OUTPUT)bpftool $(DESTDIR)$(prefix)/sbin/bpftool
+
+install: install-bin
 	$(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(bash_compdir)
 	$(Q)$(INSTALL) -m 0644 bash-completion/bpftool $(DESTDIR)$(bash_compdir)
 
@@ -239,10 +268,7 @@ doc-uninstall:
 
 FORCE:
 
-zdep:
-	@if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi
-
 .SECONDARY:
-.PHONY: all FORCE clean install uninstall zdep
+.PHONY: all FORCE bootstrap clean install-bin install uninstall
 .PHONY: doc doc-clean doc-install doc-uninstall
 .DEFAULT_GOAL := all

tools/bpf/bpftool/bash-completion/bpftool

@@ -261,7 +261,7 @@ _bpftool()
     # Deal with options
     if [[ ${words[cword]} == -* ]]; then
         local c='--version --json --pretty --bpffs --mapcompat --debug \
-	       --use-loader --base-btf'
+	       --use-loader --base-btf --legacy'
         COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
         return 0
     fi
@@ -710,7 +710,8 @@ _bpftool()
                                 hash_of_maps devmap devmap_hash sockmap cpumap \
                                 xskmap sockhash cgroup_storage reuseport_sockarray \
                                 percpu_cgroup_storage queue stack sk_storage \
-                                struct_ops inode_storage task_storage ringbuf'
+                                struct_ops ringbuf inode_storage task_storage \
+                                bloom_filter'
                             COMPREPLY=( $( compgen -W "$BPFTOOL_MAP_CREATE_TYPES" -- "$cur" ) )
                             return 0
                             ;;

tools/bpf/bpftool/btf.c

@@ -8,14 +8,15 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
-#include <bpf/bpf.h>
-#include <bpf/btf.h>
-#include <bpf/libbpf.h>
 #include <linux/btf.h>
-#include <linux/hashtable.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/hashmap.h>
+#include <bpf/libbpf.h>
+
 #include "json_writer.h"
 #include "main.h"
 
@@ -37,16 +38,13 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_VAR]		= "VAR",
 	[BTF_KIND_DATASEC]	= "DATASEC",
 	[BTF_KIND_FLOAT]	= "FLOAT",
-};
-
-struct btf_attach_table {
-	DECLARE_HASHTABLE(table, 16);
+	[BTF_KIND_DECL_TAG]	= "DECL_TAG",
+	[BTF_KIND_TYPE_TAG]	= "TYPE_TAG",
 };
 
 struct btf_attach_point {
 	__u32 obj_id;
 	__u32 btf_id;
-	struct hlist_node hash;
 };
 
 static const char *btf_int_enc_str(__u8 encoding)
@@ -145,6 +143,7 @@ static int dump_btf_type(const struct btf *btf, __u32 id,
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_RESTRICT:
 	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_TYPE_TAG:
 		if (json_output)
 			jsonw_uint_field(w, "type_id", t->type);
 		else
@@ -328,7 +327,7 @@ static int dump_btf_type(const struct btf *btf, __u32 id,
 				printf("\n\ttype_id=%u offset=%u size=%u",
 				       v->type, v->offset, v->size);
 
-				if (v->type <= btf__get_nr_types(btf)) {
+				if (v->type < btf__type_cnt(btf)) {
 					vt = btf__type_by_id(btf, v->type);
 					printf(" (%s '%s')",
 					       btf_kind_str[btf_kind_safe(btf_kind(vt))],
@@ -347,6 +346,17 @@ static int dump_btf_type(const struct btf *btf, __u32 id,
 			printf(" size=%u", t->size);
 		break;
 	}
+	case BTF_KIND_DECL_TAG: {
+		const struct btf_decl_tag *tag = (const void *)(t + 1);
+
+		if (json_output) {
+			jsonw_uint_field(w, "type_id", t->type);
+			jsonw_int_field(w, "component_idx", tag->component_idx);
+		} else {
+			printf(" type_id=%u component_idx=%d", t->type, tag->component_idx);
+		}
+		break;
+	}
 	default:
 		break;
 	}
@@ -378,14 +388,14 @@ static int dump_btf_raw(const struct btf *btf,
 		}
 	} else {
 		const struct btf *base;
-		int cnt = btf__get_nr_types(btf);
+		int cnt = btf__type_cnt(btf);
 		int start_id = 1;
 
 		base = btf__base_btf(btf);
 		if (base)
-			start_id = btf__get_nr_types(base) + 1;
+			start_id = btf__type_cnt(base);
 
-		for (i = start_id; i <= cnt; i++) {
+		for (i = start_id; i < cnt; i++) {
 			t = btf__type_by_id(btf, i);
 			dump_btf_type(btf, i, t);
 		}
@@ -410,9 +420,10 @@ static int dump_btf_c(const struct btf *btf,
 	struct btf_dump *d;
 	int err = 0, i;
 
-	d = btf_dump__new(btf, NULL, NULL, btf_dump_printf);
-	if (IS_ERR(d))
-		return PTR_ERR(d);
+	d = btf_dump__new(btf, btf_dump_printf, NULL, NULL);
+	err = libbpf_get_error(d);
+	if (err)
+		return err;
 
 	printf("#ifndef __VMLINUX_H__\n");
 	printf("#define __VMLINUX_H__\n");
@@ -428,9 +439,9 @@ static int dump_btf_c(const struct btf *btf,
 				goto done;
 		}
 	} else {
-		int cnt = btf__get_nr_types(btf);
+		int cnt = btf__type_cnt(btf);
 
-		for (i = 1; i <= cnt; i++) {
+		for (i = 1; i < cnt; i++) {
 			err = btf_dump__dump_type(d, i);
 			if (err)
 				goto done;
@@ -539,8 +550,8 @@ static int do_dump(int argc, char **argv)
 		}
 
 		btf = btf__parse_split(*argv, base ?: base_btf);
-		if (IS_ERR(btf)) {
-			err = -PTR_ERR(btf);
+		err = libbpf_get_error(btf);
+		if (err) {
 			btf = NULL;
 			p_err("failed to load BTF from %s: %s",
 			      *argv, strerror(err));
@@ -633,21 +644,8 @@ static int btf_parse_fd(int *argc, char ***argv)
 	return fd;
 }
 
-static void delete_btf_table(struct btf_attach_table *tab)
-{
-	struct btf_attach_point *obj;
-	struct hlist_node *tmp;
-
-	unsigned int bkt;
-
-	hash_for_each_safe(tab->table, bkt, tmp, obj, hash) {
-		hash_del(&obj->hash);
-		free(obj);
-	}
-}
-
 static int
-build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type,
+build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type,
 		     void *info, __u32 *len)
 {
 	static const char * const names[] = {
@@ -655,7 +653,6 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type,
 		[BPF_OBJ_PROG]		= "prog",
 		[BPF_OBJ_MAP]		= "map",
 	};
-	struct btf_attach_point *obj_node;
 	__u32 btf_id, id = 0;
 	int err;
 	int fd;
@@ -729,28 +726,25 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type,
 		if (!btf_id)
 			continue;
 
-		obj_node = calloc(1, sizeof(*obj_node));
-		if (!obj_node) {
-			p_err("failed to allocate memory: %s", strerror(errno));
-			err = -ENOMEM;
+		err = hashmap__append(tab, u32_as_hash_field(btf_id),
+				      u32_as_hash_field(id));
+		if (err) {
+			p_err("failed to append entry to hashmap for BTF ID %u, object ID %u: %s",
+			      btf_id, id, strerror(errno));
 			goto err_free;
 		}
-
-		obj_node->obj_id = id;
-		obj_node->btf_id = btf_id;
-		hash_add(tab->table, &obj_node->hash, obj_node->btf_id);
 	}
 
 	return 0;
 
 err_free:
-	delete_btf_table(tab);
+	hashmap__free(tab);
 	return err;
 }
 
 static int
-build_btf_tables(struct btf_attach_table *btf_prog_table,
-		 struct btf_attach_table *btf_map_table)
+build_btf_tables(struct hashmap *btf_prog_table,
+		 struct hashmap *btf_map_table)
 {
 	struct bpf_prog_info prog_info;
 	__u32 prog_len = sizeof(prog_info);
@@ -766,7 +760,7 @@ build_btf_tables(struct btf_attach_table *btf_prog_table,
 	err = build_btf_type_table(btf_map_table, BPF_OBJ_MAP, &map_info,
 				   &map_len);
 	if (err) {
-		delete_btf_table(btf_prog_table);
+		hashmap__free(btf_prog_table);
 		return err;
 	}
 
@@ -775,10 +769,10 @@ build_btf_tables(struct btf_attach_table *btf_prog_table,
 
 static void
 show_btf_plain(struct bpf_btf_info *info, int fd,
-	       struct btf_attach_table *btf_prog_table,
-	       struct btf_attach_table *btf_map_table)
+	       struct hashmap *btf_prog_table,
+	       struct hashmap *btf_map_table)
 {
-	struct btf_attach_point *obj;
+	struct hashmap_entry *entry;
 	const char *name = u64_to_ptr(info->name);
 	int n;
 
@@ -792,29 +786,30 @@ show_btf_plain(struct bpf_btf_info *info, int fd,
 	printf("size %uB", info->btf_size);
 
 	n = 0;
-	hash_for_each_possible(btf_prog_table->table, obj, hash, info->id) {
-		if (obj->btf_id == info->id)
-			printf("%s%u", n++ == 0 ? "  prog_ids " : ",",
-			       obj->obj_id);
+	hashmap__for_each_key_entry(btf_prog_table, entry,
+				    u32_as_hash_field(info->id)) {
+		printf("%s%u", n++ == 0 ? "  prog_ids " : ",",
+		       hash_field_as_u32(entry->value));
 	}
 
 	n = 0;
-	hash_for_each_possible(btf_map_table->table, obj, hash, info->id) {
-		if (obj->btf_id == info->id)
-			printf("%s%u", n++ == 0 ? "  map_ids " : ",",
-			       obj->obj_id);
+	hashmap__for_each_key_entry(btf_map_table, entry,
+				    u32_as_hash_field(info->id)) {
+		printf("%s%u", n++ == 0 ? "  map_ids " : ",",
+		       hash_field_as_u32(entry->value));
 	}
-	emit_obj_refs_plain(&refs_table, info->id, "\n\tpids ");
+
+	emit_obj_refs_plain(refs_table, info->id, "\n\tpids ");
 
 	printf("\n");
 }
 
 static void
 show_btf_json(struct bpf_btf_info *info, int fd,
-	      struct btf_attach_table *btf_prog_table,
-	      struct btf_attach_table *btf_map_table)
+	      struct hashmap *btf_prog_table,
+	      struct hashmap *btf_map_table)
 {
-	struct btf_attach_point *obj;
+	struct hashmap_entry *entry;
 	const char *name = u64_to_ptr(info->name);
 
 	jsonw_start_object(json_wtr);	/* btf object */
@@ -823,23 +818,21 @@ show_btf_json(struct bpf_btf_info *info, int fd,
 
 	jsonw_name(json_wtr, "prog_ids");
 	jsonw_start_array(json_wtr);	/* prog_ids */
-	hash_for_each_possible(btf_prog_table->table, obj, hash,
-			       info->id) {
-		if (obj->btf_id == info->id)
-			jsonw_uint(json_wtr, obj->obj_id);
+	hashmap__for_each_key_entry(btf_prog_table, entry,
+				    u32_as_hash_field(info->id)) {
+		jsonw_uint(json_wtr, hash_field_as_u32(entry->value));
 	}
 	jsonw_end_array(json_wtr);	/* prog_ids */
 
 	jsonw_name(json_wtr, "map_ids");
 	jsonw_start_array(json_wtr);	/* map_ids */
-	hash_for_each_possible(btf_map_table->table, obj, hash,
-			       info->id) {
-		if (obj->btf_id == info->id)
-			jsonw_uint(json_wtr, obj->obj_id);
+	hashmap__for_each_key_entry(btf_map_table, entry,
+				    u32_as_hash_field(info->id)) {
+		jsonw_uint(json_wtr, hash_field_as_u32(entry->value));
 	}
 	jsonw_end_array(json_wtr);	/* map_ids */
 
-	emit_obj_refs_json(&refs_table, info->id, json_wtr); /* pids */
+	emit_obj_refs_json(refs_table, info->id, json_wtr); /* pids */
 
 	jsonw_bool_field(json_wtr, "kernel", info->kernel_btf);
 
@@ -850,8 +843,8 @@ show_btf_json(struct bpf_btf_info *info, int fd,
 }
 
 static int
-show_btf(int fd, struct btf_attach_table *btf_prog_table,
-	 struct btf_attach_table *btf_map_table)
+show_btf(int fd, struct hashmap *btf_prog_table,
+	 struct hashmap *btf_map_table)
 {
 	struct bpf_btf_info info;
 	__u32 len = sizeof(info);
@@ -888,8 +881,8 @@ show_btf(int fd, struct btf_attach_table *btf_prog_table,
 
 static int do_show(int argc, char **argv)
 {
-	struct btf_attach_table btf_prog_table;
-	struct btf_attach_table btf_map_table;
+	struct hashmap *btf_prog_table;
+	struct hashmap *btf_map_table;
 	int err, fd = -1;
 	__u32 id = 0;
 
@@ -905,9 +898,19 @@ static int do_show(int argc, char **argv)
 		return BAD_ARG();
 	}
 
-	hash_init(btf_prog_table.table);
-	hash_init(btf_map_table.table);
-	err = build_btf_tables(&btf_prog_table, &btf_map_table);
+	btf_prog_table = hashmap__new(hash_fn_for_key_as_id,
+				      equal_fn_for_key_as_id, NULL);
+	btf_map_table = hashmap__new(hash_fn_for_key_as_id,
+				     equal_fn_for_key_as_id, NULL);
+	if (!btf_prog_table || !btf_map_table) {
+		hashmap__free(btf_prog_table);
+		hashmap__free(btf_map_table);
+		if (fd >= 0)
+			close(fd);
+		p_err("failed to create hashmap for object references");
+		return -1;
+	}
+	err = build_btf_tables(btf_prog_table, btf_map_table);
 	if (err) {
 		if (fd >= 0)
 			close(fd);
@@ -916,7 +919,7 @@ static int do_show(int argc, char **argv)
 	build_obj_refs_table(&refs_table, BPF_OBJ_BTF);
 
 	if (fd >= 0) {
-		err = show_btf(fd, &btf_prog_table, &btf_map_table);
+		err = show_btf(fd, btf_prog_table, btf_map_table);
 		close(fd);
 		goto exit_free;
 	}
@@ -948,7 +951,7 @@ static int do_show(int argc, char **argv)
 			break;
 		}
 
-		err = show_btf(fd, &btf_prog_table, &btf_map_table);
+		err = show_btf(fd, btf_prog_table, btf_map_table);
 		close(fd);
 		if (err)
 			break;
@@ -958,9 +961,9 @@ static int do_show(int argc, char **argv)
 		jsonw_end_array(json_wtr);	/* root array */
 
 exit_free:
-	delete_btf_table(&btf_prog_table);
-	delete_btf_table(&btf_map_table);
-	delete_obj_refs_table(&refs_table);
+	hashmap__free(btf_prog_table);
+	hashmap__free(btf_map_table);
+	delete_obj_refs_table(refs_table);
 
 	return err;
 }

tools/bpf/bpftool/btf_dumper.c

@@ -32,14 +32,16 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d,
 				    const struct btf_type *func_proto,
 				    __u32 prog_id)
 {
-	struct bpf_prog_info_linear *prog_info = NULL;
 	const struct btf_type *func_type;
+	int prog_fd = -1, func_sig_len;
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
 	const char *prog_name = NULL;
-	struct bpf_func_info *finfo;
 	struct btf *prog_btf = NULL;
-	struct bpf_prog_info *info;
-	int prog_fd, func_sig_len;
+	struct bpf_func_info finfo;
+	__u32 finfo_rec_size;
 	char prog_str[1024];
+	int err;
 
 	/* Get the ptr's func_proto */
 	func_sig_len = btf_dump_func(d->btf, prog_str, func_proto, NULL, 0,
@@ -52,25 +54,30 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d,
 
 	/* Get the bpf_prog's name.  Obtain from func_info. */
 	prog_fd = bpf_prog_get_fd_by_id(prog_id);
-	if (prog_fd == -1)
+	if (prog_fd < 0)
 		goto print;
 
-	prog_info = bpf_program__get_prog_info_linear(prog_fd,
-						1UL << BPF_PROG_INFO_FUNC_INFO);
-	close(prog_fd);
-	if (IS_ERR(prog_info)) {
-		prog_info = NULL;
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	if (err)
 		goto print;
-	}
-	info = &prog_info->info;
 
-	if (!info->btf_id || !info->nr_func_info)
+	if (!info.btf_id || !info.nr_func_info)
 		goto print;
-	prog_btf = btf__load_from_kernel_by_id(info->btf_id);
+
+	finfo_rec_size = info.func_info_rec_size;
+	memset(&info, 0, sizeof(info));
+	info.nr_func_info = 1;
+	info.func_info_rec_size = finfo_rec_size;
+	info.func_info = ptr_to_u64(&finfo);
+
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	if (err)
+		goto print;
+
+	prog_btf = btf__load_from_kernel_by_id(info.btf_id);
 	if (libbpf_get_error(prog_btf))
 		goto print;
-	finfo = u64_to_ptr(info->func_info);
-	func_type = btf__type_by_id(prog_btf, finfo->type_id);
+	func_type = btf__type_by_id(prog_btf, finfo.type_id);
 	if (!func_type || !btf_is_func(func_type))
 		goto print;
 
@@ -92,7 +99,8 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d,
 	prog_str[sizeof(prog_str) - 1] = '\0';
 	jsonw_string(d->jw, prog_str);
 	btf__free(prog_btf);
-	free(prog_info);
+	if (prog_fd >= 0)
+		close(prog_fd);
 	return 0;
 }
 

tools/bpf/bpftool/common.c

@@ -22,6 +22,7 @@
 #include <sys/vfs.h>
 
 #include <bpf/bpf.h>
+#include <bpf/hashmap.h>
 #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
 
 #include "main.h"
@@ -73,6 +74,7 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = {
 	[BPF_XDP]			= "xdp",
 	[BPF_SK_REUSEPORT_SELECT]	= "sk_skb_reuseport_select",
 	[BPF_SK_REUSEPORT_SELECT_OR_MIGRATE]	= "sk_skb_reuseport_select_or_migrate",
+	[BPF_PERF_EVENT]		= "perf_event",
 };
 
 void p_err(const char *fmt, ...)
@@ -393,7 +395,7 @@ void print_hex_data_json(uint8_t *data, size_t len)
 }
 
 /* extra params for nftw cb */
-static struct pinned_obj_table *build_fn_table;
+static struct hashmap *build_fn_table;
 static enum bpf_obj_type build_fn_type;
 
 static int do_build_table_cb(const char *fpath, const struct stat *sb,
@@ -401,9 +403,9 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb,
 {
 	struct bpf_prog_info pinned_info;
 	__u32 len = sizeof(pinned_info);
-	struct pinned_obj *obj_node;
 	enum bpf_obj_type objtype;
 	int fd, err = 0;
+	char *path;
 
 	if (typeflag != FTW_F)
 		goto out_ret;
@@ -420,28 +422,26 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb,
 	if (bpf_obj_get_info_by_fd(fd, &pinned_info, &len))
 		goto out_close;
 
-	obj_node = calloc(1, sizeof(*obj_node));
-	if (!obj_node) {
+	path = strdup(fpath);
+	if (!path) {
 		err = -1;
 		goto out_close;
 	}
 
-	obj_node->id = pinned_info.id;
-	obj_node->path = strdup(fpath);
-	if (!obj_node->path) {
-		err = -1;
-		free(obj_node);
+	err = hashmap__append(build_fn_table, u32_as_hash_field(pinned_info.id), path);
+	if (err) {
+		p_err("failed to append entry to hashmap for ID %u, path '%s': %s",
+		      pinned_info.id, path, strerror(errno));
 		goto out_close;
 	}
 
-	hash_add(build_fn_table->table, &obj_node->hash, obj_node->id);
 out_close:
 	close(fd);
 out_ret:
 	return err;
 }
 
-int build_pinned_obj_table(struct pinned_obj_table *tab,
+int build_pinned_obj_table(struct hashmap *tab,
 			   enum bpf_obj_type type)
 {
 	struct mntent *mntent = NULL;
@@ -470,17 +470,18 @@ int build_pinned_obj_table(struct pinned_obj_table *tab,
 	return err;
 }
 
-void delete_pinned_obj_table(struct pinned_obj_table *tab)
+void delete_pinned_obj_table(struct hashmap *map)
 {
-	struct pinned_obj *obj;
-	struct hlist_node *tmp;
-	unsigned int bkt;
+	struct hashmap_entry *entry;
+	size_t bkt;
 
-	hash_for_each_safe(tab->table, bkt, tmp, obj, hash) {
-		hash_del(&obj->hash);
-		free(obj->path);
-		free(obj);
-	}
+	if (!map)
+		return;
+
+	hashmap__for_each_entry(map, entry, bkt)
+		free(entry->value);
+
+	hashmap__free(map);
 }
 
 unsigned int get_page_size(void)
@@ -962,3 +963,13 @@ int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
 
 	return fd;
 }
+
+size_t hash_fn_for_key_as_id(const void *key, void *ctx)
+{
+	return (size_t)key;
+}
+
+bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx)
+{
+	return k1 == k2;
+}

tools/bpf/bpftool/feature.c

@@ -467,7 +467,7 @@ static bool probe_bpf_syscall(const char *define_prefix)
 {
 	bool res;
 
-	bpf_load_program(BPF_PROG_TYPE_UNSPEC, NULL, 0, NULL, 0, NULL, 0);
+	bpf_prog_load(BPF_PROG_TYPE_UNSPEC, NULL, NULL, NULL, 0, NULL);
 	res = (errno != ENOSYS);
 
 	print_bool_feature("have_bpf_syscall",
@@ -624,6 +624,7 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
 		 */
 		switch (id) {
 		case BPF_FUNC_trace_printk:
+		case BPF_FUNC_trace_vprintk:
 		case BPF_FUNC_probe_write_user:
 			if (!full_mode)
 				continue;
@@ -642,15 +643,111 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
 }
 
 static void
-probe_large_insn_limit(const char *define_prefix, __u32 ifindex)
+probe_misc_feature(struct bpf_insn *insns, size_t len,
+		   const char *define_prefix, __u32 ifindex,
+		   const char *feat_name, const char *plain_name,
+		   const char *define_name)
 {
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.prog_ifindex = ifindex,
+	);
 	bool res;
+	int fd;
 
-	res = bpf_probe_large_insn_limit(ifindex);
-	print_bool_feature("have_large_insn_limit",
+	errno = 0;
+	fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL",
+			   insns, len, &opts);
+	res = fd >= 0 || !errno;
+
+	if (fd >= 0)
+		close(fd);
+
+	print_bool_feature(feat_name, plain_name, define_name, res,
+			   define_prefix);
+}
+
+/*
+ * Probe for availability of kernel commit (5.3):
+ *
+ * c04c0d2b968a ("bpf: increase complexity limit and maximum program size")
+ */
+static void probe_large_insn_limit(const char *define_prefix, __u32 ifindex)
+{
+	struct bpf_insn insns[BPF_MAXINSNS + 1];
+	int i;
+
+	for (i = 0; i < BPF_MAXINSNS; i++)
+		insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1);
+	insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
+
+	probe_misc_feature(insns, ARRAY_SIZE(insns),
+			   define_prefix, ifindex,
+			   "have_large_insn_limit",
 			   "Large program size limit",
-			   "LARGE_INSN_LIMIT",
-			   res, define_prefix);
+			   "LARGE_INSN_LIMIT");
+}
+
+/*
+ * Probe for bounded loop support introduced in commit 2589726d12a1
+ * ("bpf: introduce bounded loops").
+ */
+static void
+probe_bounded_loops(const char *define_prefix, __u32 ifindex)
+{
+	struct bpf_insn insns[4] = {
+		BPF_MOV64_IMM(BPF_REG_0, 10),
+		BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 1),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, -2),
+		BPF_EXIT_INSN()
+	};
+
+	probe_misc_feature(insns, ARRAY_SIZE(insns),
+			   define_prefix, ifindex,
+			   "have_bounded_loops",
+			   "Bounded loop support",
+			   "BOUNDED_LOOPS");
+}
+
+/*
+ * Probe for the v2 instruction set extension introduced in commit 92b31a9af73b
+ * ("bpf: add BPF_J{LT,LE,SLT,SLE} instructions").
+ */
+static void
+probe_v2_isa_extension(const char *define_prefix, __u32 ifindex)
+{
+	struct bpf_insn insns[4] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 0, 1),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN()
+	};
+
+	probe_misc_feature(insns, ARRAY_SIZE(insns),
+			   define_prefix, ifindex,
+			   "have_v2_isa_extension",
+			   "ISA extension v2",
+			   "V2_ISA_EXTENSION");
+}
+
+/*
+ * Probe for the v3 instruction set extension introduced in commit 092ed0968bb6
+ * ("bpf: verifier support JMP32").
+ */
+static void
+probe_v3_isa_extension(const char *define_prefix, __u32 ifindex)
+{
+	struct bpf_insn insns[4] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_JMP32_IMM(BPF_JLT, BPF_REG_0, 0, 1),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN()
+	};
+
+	probe_misc_feature(insns, ARRAY_SIZE(insns),
+			   define_prefix, ifindex,
+			   "have_v3_isa_extension",
+			   "ISA extension v3",
+			   "V3_ISA_EXTENSION");
 }
 
 static void
@@ -767,6 +864,9 @@ static void section_misc(const char *define_prefix, __u32 ifindex)
 			    "/*** eBPF misc features ***/",
 			    define_prefix);
 	probe_large_insn_limit(define_prefix, ifindex);
+	probe_bounded_loops(define_prefix, ifindex);
+	probe_v2_isa_extension(define_prefix, ifindex);
+	probe_v3_isa_extension(define_prefix, ifindex);
 	print_end_section();
 }
 

tools/bpf/bpftool/gen.c

@@ -18,7 +18,6 @@
 #include <sys/stat.h>
 #include <sys/mman.h>
 #include <bpf/btf.h>
-#include <bpf/bpf_gen_internal.h>
 
 #include "json_writer.h"
 #include "main.h"
@@ -34,6 +33,11 @@ static void sanitize_identifier(char *name)
 			name[i] = '_';
 }
 
+static bool str_has_prefix(const char *str, const char *prefix)
+{
+	return strncmp(str, prefix, strlen(prefix)) == 0;
+}
+
 static bool str_has_suffix(const char *str, const char *suffix)
 {
 	size_t i, n1 = strlen(str), n2 = strlen(suffix);
@@ -68,23 +72,47 @@ static void get_header_guard(char *guard, const char *obj_name)
 		guard[i] = toupper(guard[i]);
 }
 
-static const char *get_map_ident(const struct bpf_map *map)
+static bool get_map_ident(const struct bpf_map *map, char *buf, size_t buf_sz)
 {
+	static const char *sfxs[] = { ".data", ".rodata", ".bss", ".kconfig" };
 	const char *name = bpf_map__name(map);
+	int i, n;
 
-	if (!bpf_map__is_internal(map))
-		return name;
+	if (!bpf_map__is_internal(map)) {
+		snprintf(buf, buf_sz, "%s", name);
+		return true;
+	}
 
-	if (str_has_suffix(name, ".data"))
-		return "data";
-	else if (str_has_suffix(name, ".rodata"))
-		return "rodata";
-	else if (str_has_suffix(name, ".bss"))
-		return "bss";
-	else if (str_has_suffix(name, ".kconfig"))
-		return "kconfig";
-	else
-		return NULL;
+	for  (i = 0, n = ARRAY_SIZE(sfxs); i < n; i++) {
+		const char *sfx = sfxs[i], *p;
+
+		p = strstr(name, sfx);
+		if (p) {
+			snprintf(buf, buf_sz, "%s", p + 1);
+			sanitize_identifier(buf);
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static bool get_datasec_ident(const char *sec_name, char *buf, size_t buf_sz)
+{
+	static const char *pfxs[] = { ".data", ".rodata", ".bss", ".kconfig" };
+	int i, n;
+
+	for  (i = 0, n = ARRAY_SIZE(pfxs); i < n; i++) {
+		const char *pfx = pfxs[i];
+
+		if (str_has_prefix(sec_name, pfx)) {
+			snprintf(buf, buf_sz, "%s", sec_name + 1);
+			sanitize_identifier(buf);
+			return true;
+		}
+	}
+
+	return false;
 }
 
 static void codegen_btf_dump_printf(void *ctx, const char *fmt, va_list args)
@@ -101,24 +129,14 @@ static int codegen_datasec_def(struct bpf_object *obj,
 	const char *sec_name = btf__name_by_offset(btf, sec->name_off);
 	const struct btf_var_secinfo *sec_var = btf_var_secinfos(sec);
 	int i, err, off = 0, pad_cnt = 0, vlen = btf_vlen(sec);
-	const char *sec_ident;
-	char var_ident[256];
+	char var_ident[256], sec_ident[256];
 	bool strip_mods = false;
 
-	if (strcmp(sec_name, ".data") == 0) {
-		sec_ident = "data";
-		strip_mods = true;
-	} else if (strcmp(sec_name, ".bss") == 0) {
-		sec_ident = "bss";
-		strip_mods = true;
-	} else if (strcmp(sec_name, ".rodata") == 0) {
-		sec_ident = "rodata";
-		strip_mods = true;
-	} else if (strcmp(sec_name, ".kconfig") == 0) {
-		sec_ident = "kconfig";
-	} else {
+	if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident)))
 		return 0;
-	}
+
+	if (strcmp(sec_name, ".kconfig") != 0)
+		strip_mods = true;
 
 	printf("	struct %s__%s {\n", obj_name, sec_ident);
 	for (i = 0; i < vlen; i++, sec_var++) {
@@ -193,24 +211,64 @@ static int codegen_datasec_def(struct bpf_object *obj,
 static int codegen_datasecs(struct bpf_object *obj, const char *obj_name)
 {
 	struct btf *btf = bpf_object__btf(obj);
-	int n = btf__get_nr_types(btf);
+	int n = btf__type_cnt(btf);
 	struct btf_dump *d;
+	struct bpf_map *map;
+	const struct btf_type *sec;
+	char sec_ident[256], map_ident[256];
 	int i, err = 0;
 
-	d = btf_dump__new(btf, NULL, NULL, codegen_btf_dump_printf);
-	if (IS_ERR(d))
-		return PTR_ERR(d);
+	d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL);
+	err = libbpf_get_error(d);
+	if (err)
+		return err;
 
-	for (i = 1; i <= n; i++) {
-		const struct btf_type *t = btf__type_by_id(btf, i);
-
-		if (!btf_is_datasec(t))
+	bpf_object__for_each_map(map, obj) {
+		/* only generate definitions for memory-mapped internal maps */
+		if (!bpf_map__is_internal(map))
+			continue;
+		if (!(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
 			continue;
 
-		err = codegen_datasec_def(obj, btf, d, t, obj_name);
-		if (err)
-			goto out;
+		if (!get_map_ident(map, map_ident, sizeof(map_ident)))
+			continue;
+
+		sec = NULL;
+		for (i = 1; i < n; i++) {
+			const struct btf_type *t = btf__type_by_id(btf, i);
+			const char *name;
+
+			if (!btf_is_datasec(t))
+				continue;
+
+			name = btf__str_by_offset(btf, t->name_off);
+			if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident)))
+				continue;
+
+			if (strcmp(sec_ident, map_ident) == 0) {
+				sec = t;
+				break;
+			}
+		}
+
+		/* In some cases (e.g., sections like .rodata.cst16 containing
+		 * compiler allocated string constants only) there will be
+		 * special internal maps with no corresponding DATASEC BTF
+		 * type. In such case, generate empty structs for each such
+		 * map. It will still be memory-mapped and its contents
+		 * accessible from user-space through BPF skeleton.
+		 */
+		if (!sec) {
+			printf("	struct %s__%s {\n", obj_name, map_ident);
+			printf("	} *%s;\n", map_ident);
+		} else {
+			err = codegen_datasec_def(obj, btf, d, sec, obj_name);
+			if (err)
+				goto out;
+		}
 	}
+
+
 out:
 	btf_dump__free(d);
 	return err;
@@ -238,8 +296,8 @@ static void codegen(const char *template, ...)
 		} else if (c == '\n') {
 			break;
 		} else {
-			p_err("unrecognized character at pos %td in template '%s'",
-			      src - template - 1, template);
+			p_err("unrecognized character at pos %td in template '%s': '%c'",
+			      src - template - 1, template, c);
 			free(s);
 			exit(-1);
 		}
@@ -386,6 +444,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name)
 {
 	struct bpf_program *prog;
 	struct bpf_map *map;
+	char ident[256];
 
 	codegen("\
 		\n\
@@ -406,10 +465,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name)
 	}
 
 	bpf_object__for_each_map(map, obj) {
-		const char * ident;
-
-		ident = get_map_ident(map);
-		if (!ident)
+		if (!get_map_ident(map, ident, sizeof(ident)))
 			continue;
 		if (bpf_map__is_internal(map) &&
 		    (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
@@ -430,21 +486,16 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name)
 
 static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *header_guard)
 {
-	struct bpf_object_load_attr load_attr = {};
 	DECLARE_LIBBPF_OPTS(gen_loader_opts, opts);
 	struct bpf_map *map;
+	char ident[256];
 	int err = 0;
 
 	err = bpf_object__gen_loader(obj, &opts);
 	if (err)
 		return err;
 
-	load_attr.obj = obj;
-	if (verifier_logs)
-		/* log_level1 + log_level2 + stats, but not stable UAPI */
-		load_attr.log_level = 1 + 2 + 4;
-
-	err = bpf_object__load_xattr(&load_attr);
+	err = bpf_object__load(obj);
 	if (err) {
 		p_err("failed to load object file");
 		goto out;
@@ -478,12 +529,10 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 		",
 		obj_name, opts.data_sz);
 	bpf_object__for_each_map(map, obj) {
-		const char *ident;
 		const void *mmap_data = NULL;
 		size_t mmap_size = 0;
 
-		ident = get_map_ident(map);
-		if (!ident)
+		if (!get_map_ident(map, ident, sizeof(ident)))
 			continue;
 
 		if (!bpf_map__is_internal(map) ||
@@ -545,15 +594,15 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 				return err;				    \n\
 		", obj_name);
 	bpf_object__for_each_map(map, obj) {
-		const char *ident, *mmap_flags;
+		const char *mmap_flags;
 
-		ident = get_map_ident(map);
-		if (!ident)
+		if (!get_map_ident(map, ident, sizeof(ident)))
 			continue;
 
 		if (!bpf_map__is_internal(map) ||
 		    !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
 			continue;
+
 		if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG)
 			mmap_flags = "PROT_READ";
 		else
@@ -603,7 +652,8 @@ static int do_skeleton(int argc, char **argv)
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
 	char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data;
 	struct bpf_object *obj = NULL;
-	const char *file, *ident;
+	const char *file;
+	char ident[256];
 	struct bpf_program *prog;
 	int fd, err = -1;
 	struct bpf_map *map;
@@ -663,19 +713,22 @@ static int do_skeleton(int argc, char **argv)
 	if (obj_name[0] == '\0')
 		get_obj_name(obj_name, file);
 	opts.object_name = obj_name;
+	if (verifier_logs)
+		/* log_level1 + log_level2 + stats, but not stable UAPI */
+		opts.kernel_log_level = 1 + 2 + 4;
 	obj = bpf_object__open_mem(obj_data, file_sz, &opts);
-	if (IS_ERR(obj)) {
+	err = libbpf_get_error(obj);
+	if (err) {
 		char err_buf[256];
 
-		libbpf_strerror(PTR_ERR(obj), err_buf, sizeof(err_buf));
+		libbpf_strerror(err, err_buf, sizeof(err_buf));
 		p_err("failed to open BPF object file: %s", err_buf);
 		obj = NULL;
 		goto out;
 	}
 
 	bpf_object__for_each_map(map, obj) {
-		ident = get_map_ident(map);
-		if (!ident) {
+		if (!get_map_ident(map, ident, sizeof(ident))) {
 			p_err("ignoring unrecognized internal map '%s'...",
 			      bpf_map__name(map));
 			continue;
@@ -728,8 +781,7 @@ static int do_skeleton(int argc, char **argv)
 	if (map_cnt) {
 		printf("\tstruct {\n");
 		bpf_object__for_each_map(map, obj) {
-			ident = get_map_ident(map);
-			if (!ident)
+			if (!get_map_ident(map, ident, sizeof(ident)))
 				continue;
 			if (use_loader)
 				printf("\t\tstruct bpf_map_desc %s;\n", ident);
@@ -803,7 +855,10 @@ static int do_skeleton(int argc, char **argv)
 			}						    \n\
 									    \n\
 			err = %1$s__create_skeleton(obj);		    \n\
-			err = err ?: bpf_object__open_skeleton(obj->skeleton, opts);\n\
+			if (err)					    \n\
+				goto err_out;				    \n\
+									    \n\
+			err = bpf_object__open_skeleton(obj->skeleton, opts);\n\
 			if (err)					    \n\
 				goto err_out;				    \n\
 									    \n\
@@ -862,6 +917,8 @@ static int do_skeleton(int argc, char **argv)
 	codegen("\
 		\n\
 									    \n\
+		static inline const void *%1$s__elf_bytes(size_t *sz);	    \n\
+									    \n\
 		static inline int					    \n\
 		%1$s__create_skeleton(struct %1$s *obj)			    \n\
 		{							    \n\
@@ -893,9 +950,7 @@ static int do_skeleton(int argc, char **argv)
 		);
 		i = 0;
 		bpf_object__for_each_map(map, obj) {
-			ident = get_map_ident(map);
-
-			if (!ident)
+			if (!get_map_ident(map, ident, sizeof(ident)))
 				continue;
 
 			codegen("\
@@ -943,10 +998,20 @@ static int do_skeleton(int argc, char **argv)
 	codegen("\
 		\n\
 									    \n\
-			s->data_sz = %d;				    \n\
-			s->data = (void *)\"\\				    \n\
-		",
-		file_sz);
+			s->data = (void *)%2$s__elf_bytes(&s->data_sz);	    \n\
+									    \n\
+			return 0;					    \n\
+		err:							    \n\
+			bpf_object__destroy_skeleton(s);		    \n\
+			return -ENOMEM;					    \n\
+		}							    \n\
+									    \n\
+		static inline const void *%2$s__elf_bytes(size_t *sz)	    \n\
+		{							    \n\
+			*sz = %1$d;					    \n\
+			return (const void *)\"\\			    \n\
+		"
+		, file_sz, obj_name);
 
 	/* embed contents of BPF object file */
 	print_hex(obj_data, file_sz);
@@ -954,11 +1019,6 @@ static int do_skeleton(int argc, char **argv)
 	codegen("\
 		\n\
 		\";							    \n\
-									    \n\
-			return 0;					    \n\
-		err:							    \n\
-			bpf_object__destroy_skeleton(s);		    \n\
-			return -ENOMEM;					    \n\
 		}							    \n\
 									    \n\
 		#endif /* %s */						    \n\

tools/bpf/bpftool/iter.c

@@ -46,7 +46,8 @@ static int do_pin(int argc, char **argv)
 	}
 
 	obj = bpf_object__open(objfile);
-	if (IS_ERR(obj)) {
+	err = libbpf_get_error(obj);
+	if (err) {
 		p_err("can't open objfile %s", objfile);
 		goto close_map_fd;
 	}
@@ -57,15 +58,15 @@ static int do_pin(int argc, char **argv)
 		goto close_obj;
 	}
 
-	prog = bpf_program__next(NULL, obj);
+	prog = bpf_object__next_program(obj, NULL);
 	if (!prog) {
 		p_err("can't find bpf program in objfile %s", objfile);
 		goto close_obj;
 	}
 
 	link = bpf_program__attach_iter(prog, &iter_opts);
-	if (IS_ERR(link)) {
-		err = PTR_ERR(link);
+	err = libbpf_get_error(link);
+	if (err) {
 		p_err("attach_iter failed for program %s",
 		      bpf_program__name(prog));
 		goto close_obj;

tools/bpf/bpftool/link.c

@@ -7,6 +7,7 @@
 #include <unistd.h>
 
 #include <bpf/bpf.h>
+#include <bpf/hashmap.h>
 
 #include "json_writer.h"
 #include "main.h"
@@ -20,6 +21,8 @@ static const char * const link_type_name[] = {
 	[BPF_LINK_TYPE_NETNS]			= "netns",
 };
 
+static struct hashmap *link_table;
+
 static int link_parse_fd(int *argc, char ***argv)
 {
 	int fd;
@@ -156,19 +159,18 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 		break;
 	}
 
-	if (!hash_empty(link_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(link_table)) {
+		struct hashmap_entry *entry;
 
 		jsonw_name(json_wtr, "pinned");
 		jsonw_start_array(json_wtr);
-		hash_for_each_possible(link_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				jsonw_string(json_wtr, obj->path);
-		}
+		hashmap__for_each_key_entry(link_table, entry,
+					    u32_as_hash_field(info->id))
+			jsonw_string(json_wtr, entry->value);
 		jsonw_end_array(json_wtr);
 	}
 
-	emit_obj_refs_json(&refs_table, info->id, json_wtr);
+	emit_obj_refs_json(refs_table, info->id, json_wtr);
 
 	jsonw_end_object(json_wtr);
 
@@ -244,15 +246,14 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 		break;
 	}
 
-	if (!hash_empty(link_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(link_table)) {
+		struct hashmap_entry *entry;
 
-		hash_for_each_possible(link_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				printf("\n\tpinned %s", obj->path);
-		}
+		hashmap__for_each_key_entry(link_table, entry,
+					    u32_as_hash_field(info->id))
+			printf("\n\tpinned %s", (char *)entry->value);
 	}
-	emit_obj_refs_plain(&refs_table, info->id, "\n\tpids ");
+	emit_obj_refs_plain(refs_table, info->id, "\n\tpids ");
 
 	printf("\n");
 
@@ -302,8 +303,15 @@ static int do_show(int argc, char **argv)
 	__u32 id = 0;
 	int err, fd;
 
-	if (show_pinned)
-		build_pinned_obj_table(&link_table, BPF_OBJ_LINK);
+	if (show_pinned) {
+		link_table = hashmap__new(hash_fn_for_key_as_id,
+					  equal_fn_for_key_as_id, NULL);
+		if (!link_table) {
+			p_err("failed to create hashmap for pinned paths");
+			return -1;
+		}
+		build_pinned_obj_table(link_table, BPF_OBJ_LINK);
+	}
 	build_obj_refs_table(&refs_table, BPF_OBJ_LINK);
 
 	if (argc == 2) {
@@ -344,7 +352,10 @@ static int do_show(int argc, char **argv)
 	if (json_output)
 		jsonw_end_array(json_wtr);
 
-	delete_obj_refs_table(&refs_table);
+	delete_obj_refs_table(refs_table);
+
+	if (show_pinned)
+		delete_pinned_obj_table(link_table);
 
 	return errno == ENOENT ? 0 : -1;
 }

tools/bpf/bpftool/main.c

@@ -10,8 +10,9 @@
 #include <string.h>
 
 #include <bpf/bpf.h>
-#include <bpf/libbpf.h>
 #include <bpf/btf.h>
+#include <bpf/hashmap.h>
+#include <bpf/libbpf.h>
 
 #include "main.h"
 
@@ -30,11 +31,9 @@ bool block_mount;
 bool verifier_logs;
 bool relaxed_maps;
 bool use_loader;
+bool legacy_libbpf;
 struct btf *base_btf;
-struct pinned_obj_table prog_table;
-struct pinned_obj_table map_table;
-struct pinned_obj_table link_table;
-struct obj_refs_table refs_table;
+struct hashmap *refs_table;
 
 static void __noreturn clean_and_exit(int i)
 {
@@ -94,6 +93,7 @@ static int do_version(int argc, char **argv)
 		jsonw_name(json_wtr, "features");
 		jsonw_start_object(json_wtr);	/* features */
 		jsonw_bool_field(json_wtr, "libbfd", has_libbfd);
+		jsonw_bool_field(json_wtr, "libbpf_strict", !legacy_libbpf);
 		jsonw_bool_field(json_wtr, "skeletons", has_skeletons);
 		jsonw_end_object(json_wtr);	/* features */
 
@@ -107,6 +107,10 @@ static int do_version(int argc, char **argv)
 			printf(" libbfd");
 			nb_features++;
 		}
+		if (!legacy_libbpf) {
+			printf("%s libbpf_strict", nb_features++ ? "," : "");
+			nb_features++;
+		}
 		if (has_skeletons)
 			printf("%s skeletons", nb_features++ ? "," : "");
 		printf("\n");
@@ -398,8 +402,10 @@ int main(int argc, char **argv)
 		{ "debug",	no_argument,	NULL,	'd' },
 		{ "use-loader",	no_argument,	NULL,	'L' },
 		{ "base-btf",	required_argument, NULL, 'B' },
+		{ "legacy",	no_argument,	NULL,	'l' },
 		{ 0 }
 	};
+	bool version_requested = false;
 	int opt, ret;
 
 	setlinebuf(stdout);
@@ -411,16 +417,13 @@ int main(int argc, char **argv)
 	block_mount = false;
 	bin_name = argv[0];
 
-	hash_init(prog_table.table);
-	hash_init(map_table.table);
-	hash_init(link_table.table);
-
 	opterr = 0;
-	while ((opt = getopt_long(argc, argv, "VhpjfLmndB:",
+	while ((opt = getopt_long(argc, argv, "VhpjfLmndB:l",
 				  options, NULL)) >= 0) {
 		switch (opt) {
 		case 'V':
-			return do_version(argc, argv);
+			version_requested = true;
+			break;
 		case 'h':
 			return do_help(argc, argv);
 		case 'p':
@@ -462,6 +465,9 @@ int main(int argc, char **argv)
 		case 'L':
 			use_loader = true;
 			break;
+		case 'l':
+			legacy_libbpf = true;
+			break;
 		default:
 			p_err("unrecognized option '%s'", argv[optind - 1]);
 			if (json_output)
@@ -471,21 +477,25 @@ int main(int argc, char **argv)
 		}
 	}
 
+	if (!legacy_libbpf) {
+		ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+		if (ret)
+			p_err("failed to enable libbpf strict mode: %d", ret);
+	}
+
 	argc -= optind;
 	argv += optind;
 	if (argc < 0)
 		usage();
 
+	if (version_requested)
+		return do_version(argc, argv);
+
 	ret = cmd_select(cmds, argc, argv, do_help);
 
 	if (json_output)
 		jsonw_destroy(&json_wtr);
 
-	if (show_pinned) {
-		delete_pinned_obj_table(&prog_table);
-		delete_pinned_obj_table(&map_table);
-		delete_pinned_obj_table(&link_table);
-	}
 	btf__free(base_btf);
 
 	return ret;

tools/bpf/bpftool/main.h

@@ -11,9 +11,9 @@
 #include <linux/bpf.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
-#include <linux/hashtable.h>
 #include <tools/libc_compat.h>
 
+#include <bpf/hashmap.h>
 #include <bpf/libbpf.h>
 
 #include "json_writer.h"
@@ -57,7 +57,7 @@ static inline void *u64_to_ptr(__u64 ptr)
 #define HELP_SPEC_PROGRAM						\
 	"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG | name PROG_NAME }"
 #define HELP_SPEC_OPTIONS						\
-	"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug}"
+	"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug} | {-l|--legacy}"
 #define HELP_SPEC_MAP							\
 	"MAP := { id MAP_ID | pinned FILE | name MAP_NAME }"
 #define HELP_SPEC_LINK							\
@@ -90,11 +90,9 @@ extern bool block_mount;
 extern bool verifier_logs;
 extern bool relaxed_maps;
 extern bool use_loader;
+extern bool legacy_libbpf;
 extern struct btf *base_btf;
-extern struct pinned_obj_table prog_table;
-extern struct pinned_obj_table map_table;
-extern struct pinned_obj_table link_table;
-extern struct obj_refs_table refs_table;
+extern struct hashmap *refs_table;
 
 void __printf(1, 2) p_err(const char *fmt, ...);
 void __printf(1, 2) p_info(const char *fmt, ...);
@@ -108,28 +106,12 @@ void set_max_rlimit(void);
 
 int mount_tracefs(const char *target);
 
-struct pinned_obj_table {
-	DECLARE_HASHTABLE(table, 16);
-};
-
-struct pinned_obj {
-	__u32 id;
-	char *path;
-	struct hlist_node hash;
-};
-
-struct obj_refs_table {
-	DECLARE_HASHTABLE(table, 16);
-};
-
 struct obj_ref {
 	int pid;
 	char comm[16];
 };
 
 struct obj_refs {
-	struct hlist_node node;
-	__u32 id;
 	int ref_cnt;
 	struct obj_ref *refs;
 };
@@ -137,15 +119,15 @@ struct obj_refs {
 struct btf;
 struct bpf_line_info;
 
-int build_pinned_obj_table(struct pinned_obj_table *table,
+int build_pinned_obj_table(struct hashmap *table,
 			   enum bpf_obj_type type);
-void delete_pinned_obj_table(struct pinned_obj_table *tab);
-__weak int build_obj_refs_table(struct obj_refs_table *table,
+void delete_pinned_obj_table(struct hashmap *table);
+__weak int build_obj_refs_table(struct hashmap **table,
 				enum bpf_obj_type type);
-__weak void delete_obj_refs_table(struct obj_refs_table *table);
-__weak void emit_obj_refs_json(struct obj_refs_table *table, __u32 id,
+__weak void delete_obj_refs_table(struct hashmap *table);
+__weak void emit_obj_refs_json(struct hashmap *table, __u32 id,
 			       json_writer_t *json_wtr);
-__weak void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id,
+__weak void emit_obj_refs_plain(struct hashmap *table, __u32 id,
 				const char *prefix);
 void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode);
 void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode);
@@ -259,4 +241,23 @@ int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind,
 
 int print_all_levels(__maybe_unused enum libbpf_print_level level,
 		     const char *format, va_list args);
+
+size_t hash_fn_for_key_as_id(const void *key, void *ctx);
+bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx);
+
+static inline void *u32_as_hash_field(__u32 x)
+{
+	return (void *)(uintptr_t)x;
+}
+
+static inline __u32 hash_field_as_u32(const void *x)
+{
+	return (__u32)(uintptr_t)x;
+}
+
+static inline bool hashmap__empty(struct hashmap *map)
+{
+	return map ? hashmap__size(map) == 0 : true;
+}
+
 #endif

tools/bpf/bpftool/map.c

@@ -17,6 +17,7 @@
 
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
+#include <bpf/hashmap.h>
 
 #include "json_writer.h"
 #include "main.h"
@@ -52,10 +53,13 @@ const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_RINGBUF]			= "ringbuf",
 	[BPF_MAP_TYPE_INODE_STORAGE]		= "inode_storage",
 	[BPF_MAP_TYPE_TASK_STORAGE]		= "task_storage",
+	[BPF_MAP_TYPE_BLOOM_FILTER]		= "bloom_filter",
 };
 
 const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
 
+static struct hashmap *map_table;
+
 static bool map_is_per_cpu(__u32 type)
 {
 	return type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -535,19 +539,18 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
 	if (info->btf_id)
 		jsonw_int_field(json_wtr, "btf_id", info->btf_id);
 
-	if (!hash_empty(map_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(map_table)) {
+		struct hashmap_entry *entry;
 
 		jsonw_name(json_wtr, "pinned");
 		jsonw_start_array(json_wtr);
-		hash_for_each_possible(map_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				jsonw_string(json_wtr, obj->path);
-		}
+		hashmap__for_each_key_entry(map_table, entry,
+					    u32_as_hash_field(info->id))
+			jsonw_string(json_wtr, entry->value);
 		jsonw_end_array(json_wtr);
 	}
 
-	emit_obj_refs_json(&refs_table, info->id, json_wtr);
+	emit_obj_refs_json(refs_table, info->id, json_wtr);
 
 	jsonw_end_object(json_wtr);
 
@@ -610,13 +613,12 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
 	}
 	close(fd);
 
-	if (!hash_empty(map_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(map_table)) {
+		struct hashmap_entry *entry;
 
-		hash_for_each_possible(map_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				printf("\n\tpinned %s", obj->path);
-		}
+		hashmap__for_each_key_entry(map_table, entry,
+					    u32_as_hash_field(info->id))
+			printf("\n\tpinned %s", (char *)entry->value);
 	}
 	printf("\n");
 
@@ -636,7 +638,7 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
 	if (frozen)
 		printf("%sfrozen", info->btf_id ? "  " : "");
 
-	emit_obj_refs_plain(&refs_table, info->id, "\n\tpids ");
+	emit_obj_refs_plain(refs_table, info->id, "\n\tpids ");
 
 	printf("\n");
 	return 0;
@@ -694,8 +696,15 @@ static int do_show(int argc, char **argv)
 	int err;
 	int fd;
 
-	if (show_pinned)
-		build_pinned_obj_table(&map_table, BPF_OBJ_MAP);
+	if (show_pinned) {
+		map_table = hashmap__new(hash_fn_for_key_as_id,
+					 equal_fn_for_key_as_id, NULL);
+		if (!map_table) {
+			p_err("failed to create hashmap for pinned paths");
+			return -1;
+		}
+		build_pinned_obj_table(map_table, BPF_OBJ_MAP);
+	}
 	build_obj_refs_table(&refs_table, BPF_OBJ_MAP);
 
 	if (argc == 2)
@@ -740,7 +749,10 @@ static int do_show(int argc, char **argv)
 	if (json_output)
 		jsonw_end_array(json_wtr);
 
-	delete_obj_refs_table(&refs_table);
+	delete_obj_refs_table(refs_table);
+
+	if (show_pinned)
+		delete_pinned_obj_table(map_table);
 
 	return errno == ENOENT ? 0 : -1;
 }
@@ -800,7 +812,7 @@ static struct btf *get_map_kv_btf(const struct bpf_map_info *info)
 	if (info->btf_vmlinux_value_type_id) {
 		if (!btf_vmlinux) {
 			btf_vmlinux = libbpf_find_kernel_btf();
-			if (IS_ERR(btf_vmlinux))
+			if (libbpf_get_error(btf_vmlinux))
 				p_err("failed to get kernel btf");
 		}
 		return btf_vmlinux;
@@ -820,13 +832,13 @@ static struct btf *get_map_kv_btf(const struct bpf_map_info *info)
 
 static void free_map_kv_btf(struct btf *btf)
 {
-	if (!IS_ERR(btf) && btf != btf_vmlinux)
+	if (!libbpf_get_error(btf) && btf != btf_vmlinux)
 		btf__free(btf);
 }
 
 static void free_btf_vmlinux(void)
 {
-	if (!IS_ERR(btf_vmlinux))
+	if (!libbpf_get_error(btf_vmlinux))
 		btf__free(btf_vmlinux);
 }
 
@@ -851,8 +863,8 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr,
 
 	if (wtr) {
 		btf = get_map_kv_btf(info);
-		if (IS_ERR(btf)) {
-			err = PTR_ERR(btf);
+		err = libbpf_get_error(btf);
+		if (err) {
 			goto exit_free;
 		}
 
@@ -1249,7 +1261,10 @@ static int do_pin(int argc, char **argv)
 
 static int do_create(int argc, char **argv)
 {
-	struct bpf_create_map_attr attr = { NULL, };
+	LIBBPF_OPTS(bpf_map_create_opts, attr);
+	enum bpf_map_type map_type = BPF_MAP_TYPE_UNSPEC;
+	__u32 key_size = 0, value_size = 0, max_entries = 0;
+	const char *map_name = NULL;
 	const char *pinfile;
 	int err = -1, fd;
 
@@ -1264,30 +1279,30 @@ static int do_create(int argc, char **argv)
 		if (is_prefix(*argv, "type")) {
 			NEXT_ARG();
 
-			if (attr.map_type) {
+			if (map_type) {
 				p_err("map type already specified");
 				goto exit;
 			}
 
-			attr.map_type = map_type_from_str(*argv);
-			if ((int)attr.map_type < 0) {
+			map_type = map_type_from_str(*argv);
+			if ((int)map_type < 0) {
 				p_err("unrecognized map type: %s", *argv);
 				goto exit;
 			}
 			NEXT_ARG();
 		} else if (is_prefix(*argv, "name")) {
 			NEXT_ARG();
-			attr.name = GET_ARG();
+			map_name = GET_ARG();
 		} else if (is_prefix(*argv, "key")) {
-			if (parse_u32_arg(&argc, &argv, &attr.key_size,
+			if (parse_u32_arg(&argc, &argv, &key_size,
 					  "key size"))
 				goto exit;
 		} else if (is_prefix(*argv, "value")) {
-			if (parse_u32_arg(&argc, &argv, &attr.value_size,
+			if (parse_u32_arg(&argc, &argv, &value_size,
 					  "value size"))
 				goto exit;
 		} else if (is_prefix(*argv, "entries")) {
-			if (parse_u32_arg(&argc, &argv, &attr.max_entries,
+			if (parse_u32_arg(&argc, &argv, &max_entries,
 					  "max entries"))
 				goto exit;
 		} else if (is_prefix(*argv, "flags")) {
@@ -1328,14 +1343,14 @@ static int do_create(int argc, char **argv)
 		}
 	}
 
-	if (!attr.name) {
+	if (!map_name) {
 		p_err("map name not specified");
 		goto exit;
 	}
 
 	set_max_rlimit();
 
-	fd = bpf_create_map_xattr(&attr);
+	fd = bpf_map_create(map_type, map_name, key_size, value_size, max_entries, &attr);
 	if (fd < 0) {
 		p_err("map create failed: %s", strerror(errno));
 		goto exit;
@@ -1466,7 +1481,7 @@ static int do_help(int argc, char **argv)
 		"                 devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n"
 		"                 cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n"
 		"                 queue | stack | sk_storage | struct_ops | ringbuf | inode_storage |\n"
-		"                 task_storage }\n"
+		"                 task_storage | bloom_filter }\n"
 		"       " HELP_SPEC_OPTIONS " |\n"
 		"                    {-f|--bpffs} | {-n|--nomount} }\n"
 		"",

tools/bpf/bpftool/map_perf_ring.c

@@ -22,7 +22,6 @@
 #include <sys/syscall.h>
 
 #include <bpf/bpf.h>
-#include <perf-sys.h>
 
 #include "main.h"
 
@@ -125,7 +124,7 @@ int do_event_pipe(int argc, char **argv)
 		.wakeup_events = 1,
 	};
 	struct bpf_map_info map_info = {};
-	struct perf_buffer_raw_opts opts = {};
+	LIBBPF_OPTS(perf_buffer_raw_opts, opts);
 	struct event_pipe_ctx ctx = {
 		.all_cpus = true,
 		.cpu = -1,
@@ -191,14 +190,11 @@ int do_event_pipe(int argc, char **argv)
 		ctx.idx = 0;
 	}
 
-	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);
+	pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &perf_attr,
+				  print_bpf_output, &ctx, &opts);
 	err = libbpf_get_error(pb);
 	if (err) {
 		p_err("failed to create perf buffer: %s (%d)",

tools/bpf/bpftool/pids.c

@@ -6,35 +6,37 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+
 #include <bpf/bpf.h>
+#include <bpf/hashmap.h>
 
 #include "main.h"
 #include "skeleton/pid_iter.h"
 
 #ifdef BPFTOOL_WITHOUT_SKELETONS
 
-int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type)
+int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type)
 {
 	return -ENOTSUP;
 }
-void delete_obj_refs_table(struct obj_refs_table *table) {}
-void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id, const char *prefix) {}
-void emit_obj_refs_json(struct obj_refs_table *table, __u32 id, json_writer_t *json_writer) {}
+void delete_obj_refs_table(struct hashmap *map) {}
+void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix) {}
+void emit_obj_refs_json(struct hashmap *map, __u32 id, json_writer_t *json_writer) {}
 
 #else /* BPFTOOL_WITHOUT_SKELETONS */
 
 #include "pid_iter.skel.h"
 
-static void add_ref(struct obj_refs_table *table, struct pid_iter_entry *e)
+static void add_ref(struct hashmap *map, struct pid_iter_entry *e)
 {
+	struct hashmap_entry *entry;
 	struct obj_refs *refs;
 	struct obj_ref *ref;
+	int err, i;
 	void *tmp;
-	int i;
 
-	hash_for_each_possible(table->table, refs, node, e->id) {
-		if (refs->id != e->id)
-			continue;
+	hashmap__for_each_key_entry(map, entry, u32_as_hash_field(e->id)) {
+		refs = entry->value;
 
 		for (i = 0; i < refs->ref_cnt; i++) {
 			if (refs->refs[i].pid == e->pid)
@@ -64,7 +66,6 @@ static void add_ref(struct obj_refs_table *table, struct pid_iter_entry *e)
 		return;
 	}
 
-	refs->id = e->id;
 	refs->refs = malloc(sizeof(*refs->refs));
 	if (!refs->refs) {
 		free(refs);
@@ -76,7 +77,11 @@ static void add_ref(struct obj_refs_table *table, struct pid_iter_entry *e)
 	ref->pid = e->pid;
 	memcpy(ref->comm, e->comm, sizeof(ref->comm));
 	refs->ref_cnt = 1;
-	hash_add(table->table, &refs->node, e->id);
+
+	err = hashmap__append(map, u32_as_hash_field(e->id), refs);
+	if (err)
+		p_err("failed to append entry to hashmap for ID %u: %s",
+		      e->id, strerror(errno));
 }
 
 static int __printf(2, 0)
@@ -87,7 +92,7 @@ libbpf_print_none(__maybe_unused enum libbpf_print_level level,
 	return 0;
 }
 
-int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type)
+int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type)
 {
 	struct pid_iter_entry *e;
 	char buf[4096 / sizeof(*e) * sizeof(*e)];
@@ -95,7 +100,11 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type)
 	int err, ret, fd = -1, i;
 	libbpf_print_fn_t default_print;
 
-	hash_init(table->table);
+	*map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL);
+	if (!*map) {
+		p_err("failed to create hashmap for PID references");
+		return -1;
+	}
 	set_max_rlimit();
 
 	skel = pid_iter_bpf__open();
@@ -151,7 +160,7 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type)
 
 		e = (void *)buf;
 		for (i = 0; i < ret; i++, e++) {
-			add_ref(table, e);
+			add_ref(*map, e);
 		}
 	}
 	err = 0;
@@ -162,39 +171,44 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type)
 	return err;
 }
 
-void delete_obj_refs_table(struct obj_refs_table *table)
+void delete_obj_refs_table(struct hashmap *map)
 {
-	struct obj_refs *refs;
-	struct hlist_node *tmp;
-	unsigned int bkt;
+	struct hashmap_entry *entry;
+	size_t bkt;
+
+	if (!map)
+		return;
+
+	hashmap__for_each_entry(map, entry, bkt) {
+		struct obj_refs *refs = entry->value;
 
-	hash_for_each_safe(table->table, bkt, tmp, refs, node) {
-		hash_del(&refs->node);
 		free(refs->refs);
 		free(refs);
 	}
+
+	hashmap__free(map);
 }
 
-void emit_obj_refs_json(struct obj_refs_table *table, __u32 id,
+void emit_obj_refs_json(struct hashmap *map, __u32 id,
 			json_writer_t *json_writer)
 {
-	struct obj_refs *refs;
-	struct obj_ref *ref;
-	int i;
+	struct hashmap_entry *entry;
 
-	if (hash_empty(table->table))
+	if (hashmap__empty(map))
 		return;
 
-	hash_for_each_possible(table->table, refs, node, id) {
-		if (refs->id != id)
-			continue;
+	hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) {
+		struct obj_refs *refs = entry->value;
+		int i;
+
 		if (refs->ref_cnt == 0)
 			break;
 
 		jsonw_name(json_writer, "pids");
 		jsonw_start_array(json_writer);
 		for (i = 0; i < refs->ref_cnt; i++) {
-			ref = &refs->refs[i];
+			struct obj_ref *ref = &refs->refs[i];
+
 			jsonw_start_object(json_writer);
 			jsonw_int_field(json_writer, "pid", ref->pid);
 			jsonw_string_field(json_writer, "comm", ref->comm);
@@ -205,24 +219,24 @@ void emit_obj_refs_json(struct obj_refs_table *table, __u32 id,
 	}
 }
 
-void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id, const char *prefix)
+void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix)
 {
-	struct obj_refs *refs;
-	struct obj_ref *ref;
-	int i;
+	struct hashmap_entry *entry;
 
-	if (hash_empty(table->table))
+	if (hashmap__empty(map))
 		return;
 
-	hash_for_each_possible(table->table, refs, node, id) {
-		if (refs->id != id)
-			continue;
+	hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) {
+		struct obj_refs *refs = entry->value;
+		int i;
+
 		if (refs->ref_cnt == 0)
 			break;
 
 		printf("%s", prefix);
 		for (i = 0; i < refs->ref_cnt; i++) {
-			ref = &refs->refs[i];
+			struct obj_ref *ref = &refs->refs[i];
+
 			printf("%s%s(%d)", i == 0 ? "" : ", ", ref->comm, ref->pid);
 		}
 		break;

tools/bpf/bpftool/prog.c

@@ -24,8 +24,8 @@
 
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
+#include <bpf/hashmap.h>
 #include <bpf/libbpf.h>
-#include <bpf/bpf_gen_internal.h>
 #include <bpf/skel_internal.h>
 
 #include "cfg.h"
@@ -85,6 +85,8 @@ static const char * const attach_type_strings[] = {
 	[__MAX_BPF_ATTACH_TYPE] = NULL,
 };
 
+static struct hashmap *prog_table;
+
 static enum bpf_attach_type parse_attach_type(const char *str)
 {
 	enum bpf_attach_type type;
@@ -98,6 +100,76 @@ static enum bpf_attach_type parse_attach_type(const char *str)
 	return __MAX_BPF_ATTACH_TYPE;
 }
 
+static int prep_prog_info(struct bpf_prog_info *const info, enum dump_mode mode,
+			  void **info_data, size_t *const info_data_sz)
+{
+	struct bpf_prog_info holder = {};
+	size_t needed = 0;
+	void *ptr;
+
+	if (mode == DUMP_JITED) {
+		holder.jited_prog_len = info->jited_prog_len;
+		needed += info->jited_prog_len;
+	} else {
+		holder.xlated_prog_len = info->xlated_prog_len;
+		needed += info->xlated_prog_len;
+	}
+
+	holder.nr_jited_ksyms = info->nr_jited_ksyms;
+	needed += info->nr_jited_ksyms * sizeof(__u64);
+
+	holder.nr_jited_func_lens = info->nr_jited_func_lens;
+	needed += info->nr_jited_func_lens * sizeof(__u32);
+
+	holder.nr_func_info = info->nr_func_info;
+	holder.func_info_rec_size = info->func_info_rec_size;
+	needed += info->nr_func_info * info->func_info_rec_size;
+
+	holder.nr_line_info = info->nr_line_info;
+	holder.line_info_rec_size = info->line_info_rec_size;
+	needed += info->nr_line_info * info->line_info_rec_size;
+
+	holder.nr_jited_line_info = info->nr_jited_line_info;
+	holder.jited_line_info_rec_size = info->jited_line_info_rec_size;
+	needed += info->nr_jited_line_info * info->jited_line_info_rec_size;
+
+	if (needed > *info_data_sz) {
+		ptr = realloc(*info_data, needed);
+		if (!ptr)
+			return -1;
+
+		*info_data = ptr;
+		*info_data_sz = needed;
+	}
+	ptr = *info_data;
+
+	if (mode == DUMP_JITED) {
+		holder.jited_prog_insns = ptr_to_u64(ptr);
+		ptr += holder.jited_prog_len;
+	} else {
+		holder.xlated_prog_insns = ptr_to_u64(ptr);
+		ptr += holder.xlated_prog_len;
+	}
+
+	holder.jited_ksyms = ptr_to_u64(ptr);
+	ptr += holder.nr_jited_ksyms * sizeof(__u64);
+
+	holder.jited_func_lens = ptr_to_u64(ptr);
+	ptr += holder.nr_jited_func_lens * sizeof(__u32);
+
+	holder.func_info = ptr_to_u64(ptr);
+	ptr += holder.nr_func_info * holder.func_info_rec_size;
+
+	holder.line_info = ptr_to_u64(ptr);
+	ptr += holder.nr_line_info * holder.line_info_rec_size;
+
+	holder.jited_line_info = ptr_to_u64(ptr);
+	ptr += holder.nr_jited_line_info * holder.jited_line_info_rec_size;
+
+	*info = holder;
+	return 0;
+}
+
 static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
 {
 	struct timespec real_time_ts, boot_time_ts;
@@ -417,19 +489,18 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 	if (info->btf_id)
 		jsonw_int_field(json_wtr, "btf_id", info->btf_id);
 
-	if (!hash_empty(prog_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(prog_table)) {
+		struct hashmap_entry *entry;
 
 		jsonw_name(json_wtr, "pinned");
 		jsonw_start_array(json_wtr);
-		hash_for_each_possible(prog_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				jsonw_string(json_wtr, obj->path);
-		}
+		hashmap__for_each_key_entry(prog_table, entry,
+					    u32_as_hash_field(info->id))
+			jsonw_string(json_wtr, entry->value);
 		jsonw_end_array(json_wtr);
 	}
 
-	emit_obj_refs_json(&refs_table, info->id, json_wtr);
+	emit_obj_refs_json(refs_table, info->id, json_wtr);
 
 	show_prog_metadata(fd, info->nr_map_ids);
 
@@ -489,19 +560,18 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 	if (info->nr_map_ids)
 		show_prog_maps(fd, info->nr_map_ids);
 
-	if (!hash_empty(prog_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(prog_table)) {
+		struct hashmap_entry *entry;
 
-		hash_for_each_possible(prog_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				printf("\n\tpinned %s", obj->path);
-		}
+		hashmap__for_each_key_entry(prog_table, entry,
+					    u32_as_hash_field(info->id))
+			printf("\n\tpinned %s", (char *)entry->value);
 	}
 
 	if (info->btf_id)
 		printf("\n\tbtf_id %d", info->btf_id);
 
-	emit_obj_refs_plain(&refs_table, info->id, "\n\tpids ");
+	emit_obj_refs_plain(refs_table, info->id, "\n\tpids ");
 
 	printf("\n");
 
@@ -568,8 +638,15 @@ static int do_show(int argc, char **argv)
 	int err;
 	int fd;
 
-	if (show_pinned)
-		build_pinned_obj_table(&prog_table, BPF_OBJ_PROG);
+	if (show_pinned) {
+		prog_table = hashmap__new(hash_fn_for_key_as_id,
+					  equal_fn_for_key_as_id, NULL);
+		if (!prog_table) {
+			p_err("failed to create hashmap for pinned paths");
+			return -1;
+		}
+		build_pinned_obj_table(prog_table, BPF_OBJ_PROG);
+	}
 	build_obj_refs_table(&refs_table, BPF_OBJ_PROG);
 
 	if (argc == 2)
@@ -612,7 +689,10 @@ static int do_show(int argc, char **argv)
 	if (json_output)
 		jsonw_end_array(json_wtr);
 
-	delete_obj_refs_table(&refs_table);
+	delete_obj_refs_table(refs_table);
+
+	if (show_pinned)
+		delete_pinned_obj_table(prog_table);
 
 	return err;
 }
@@ -796,16 +876,18 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 
 static int do_dump(int argc, char **argv)
 {
-	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_info info;
+	__u32 info_len = sizeof(info);
+	size_t info_data_sz = 0;
+	void *info_data = NULL;
 	char *filepath = NULL;
 	bool opcodes = false;
 	bool visual = false;
 	enum dump_mode mode;
 	bool linum = false;
-	int *fds = NULL;
 	int nb_fds, i = 0;
+	int *fds = NULL;
 	int err = -1;
-	__u64 arrays;
 
 	if (is_prefix(*argv, "jited")) {
 		if (disasm_init())
@@ -865,43 +947,44 @@ static int do_dump(int argc, char **argv)
 		goto exit_close;
 	}
 
-	if (mode == DUMP_JITED)
-		arrays = 1UL << BPF_PROG_INFO_JITED_INSNS;
-	else
-		arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS;
-
-	arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS;
-	arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS;
-	arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO;
-	arrays |= 1UL << BPF_PROG_INFO_LINE_INFO;
-	arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO;
-
 	if (json_output && nb_fds > 1)
 		jsonw_start_array(json_wtr);	/* root array */
 	for (i = 0; i < nb_fds; i++) {
-		info_linear = bpf_program__get_prog_info_linear(fds[i], arrays);
-		if (IS_ERR_OR_NULL(info_linear)) {
+		memset(&info, 0, sizeof(info));
+
+		err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len);
+		if (err) {
+			p_err("can't get prog info: %s", strerror(errno));
+			break;
+		}
+
+		err = prep_prog_info(&info, mode, &info_data, &info_data_sz);
+		if (err) {
+			p_err("can't grow prog info_data");
+			break;
+		}
+
+		err = bpf_obj_get_info_by_fd(fds[i], &info, &info_len);
+		if (err) {
 			p_err("can't get prog info: %s", strerror(errno));
 			break;
 		}
 
 		if (json_output && nb_fds > 1) {
 			jsonw_start_object(json_wtr);	/* prog object */
-			print_prog_header_json(&info_linear->info);
+			print_prog_header_json(&info);
 			jsonw_name(json_wtr, "insns");
 		} else if (nb_fds > 1) {
-			print_prog_header_plain(&info_linear->info);
+			print_prog_header_plain(&info);
 		}
 
-		err = prog_dump(&info_linear->info, mode, filepath, opcodes,
-				visual, linum);
+		err = prog_dump(&info, mode, filepath, opcodes, visual, linum);
 
 		if (json_output && nb_fds > 1)
 			jsonw_end_object(json_wtr);	/* prog object */
 		else if (i != nb_fds - 1 && nb_fds > 1)
 			printf("\n");
 
-		free(info_linear);
 		if (err)
 			break;
 		close(fds[i]);
@@ -913,6 +996,7 @@ static int do_dump(int argc, char **argv)
 	for (; i < nb_fds; i++)
 		close(fds[i]);
 exit_free:
+	free(info_data);
 	free(fds);
 	return err;
 }
@@ -1380,7 +1464,6 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts,
 		.relaxed_maps = relaxed_maps,
 	);
-	struct bpf_object_load_attr load_attr = { 0 };
 	enum bpf_attach_type expected_attach_type;
 	struct map_replace *map_replace = NULL;
 	struct bpf_program *prog = NULL, *pos;
@@ -1402,8 +1485,6 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 
 	while (argc) {
 		if (is_prefix(*argv, "type")) {
-			char *type;
-
 			NEXT_ARG();
 
 			if (common_prog_type != BPF_PROG_TYPE_UNSPEC) {
@@ -1413,21 +1494,26 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 			if (!REQ_ARGS(1))
 				goto err_free_reuse_maps;
 
-			/* Put a '/' at the end of type to appease libbpf */
-			type = malloc(strlen(*argv) + 2);
-			if (!type) {
-				p_err("mem alloc failed");
-				goto err_free_reuse_maps;
-			}
-			*type = 0;
-			strcat(type, *argv);
-			strcat(type, "/");
+			err = libbpf_prog_type_by_name(*argv, &common_prog_type,
+						       &expected_attach_type);
+			if (err < 0) {
+				/* Put a '/' at the end of type to appease libbpf */
+				char *type = malloc(strlen(*argv) + 2);
 
-			err = get_prog_type_by_name(type, &common_prog_type,
-						    &expected_attach_type);
-			free(type);
-			if (err < 0)
-				goto err_free_reuse_maps;
+				if (!type) {
+					p_err("mem alloc failed");
+					goto err_free_reuse_maps;
+				}
+				*type = 0;
+				strcat(type, *argv);
+				strcat(type, "/");
+
+				err = get_prog_type_by_name(type, &common_prog_type,
+							    &expected_attach_type);
+				free(type);
+				if (err < 0)
+					goto err_free_reuse_maps;
+			}
 
 			NEXT_ARG();
 		} else if (is_prefix(*argv, "map")) {
@@ -1511,6 +1597,10 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 
 	set_max_rlimit();
 
+	if (verifier_logs)
+		/* log_level1 + log_level2 + stats, but not stable UAPI */
+		open_opts.kernel_log_level = 1 + 2 + 4;
+
 	obj = bpf_object__open_file(file, &open_opts);
 	if (libbpf_get_error(obj)) {
 		p_err("failed to open object file");
@@ -1565,7 +1655,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 	j = 0;
 	idx = 0;
 	bpf_object__for_each_map(map, obj) {
-		if (!bpf_map__is_offload_neutral(map))
+		if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
 			bpf_map__set_ifindex(map, ifindex);
 
 		if (j < old_map_fds && idx == map_replace[j].idx) {
@@ -1590,12 +1680,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 		goto err_close_obj;
 	}
 
-	load_attr.obj = obj;
-	if (verifier_logs)
-		/* log_level1 + log_level2 + stats, but not stable UAPI */
-		load_attr.log_level = 1 + 2 + 4;
-
-	err = bpf_object__load_xattr(&load_attr);
+	err = bpf_object__load(obj);
 	if (err) {
 		p_err("failed to load object file");
 		goto err_close_obj;
@@ -1606,7 +1691,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 		goto err_close_obj;
 
 	if (first_prog_only) {
-		prog = bpf_program__next(NULL, obj);
+		prog = bpf_object__next_program(obj, NULL);
 		if (!prog) {
 			p_err("object file doesn't contain any bpf program");
 			goto err_close_obj;
@@ -1650,6 +1735,11 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 	else
 		bpf_object__unpin_programs(obj, pinfile);
 err_close_obj:
+	if (!legacy_libbpf) {
+		p_info("Warning: bpftool is now running in libbpf strict mode and has more stringent requirements about BPF programs.\n"
+		       "If it used to work for this object file but now doesn't, see --legacy option for more details.\n");
+	}
+
 	bpf_object__close(obj);
 err_free_reuse_maps:
 	for (i = 0; i < old_map_fds; i++)
@@ -1682,17 +1772,19 @@ static int try_loader(struct gen_loader_opts *gen)
 					     sizeof(struct bpf_prog_desc));
 	int log_buf_sz = (1u << 24) - 1;
 	int err, fds_before, fd_delta;
-	char *log_buf;
+	char *log_buf = NULL;
 
 	ctx = alloca(ctx_sz);
 	memset(ctx, 0, ctx_sz);
 	ctx->sz = ctx_sz;
-	ctx->log_level = 1;
-	ctx->log_size = log_buf_sz;
-	log_buf = malloc(log_buf_sz);
-	if (!log_buf)
-		return -ENOMEM;
-	ctx->log_buf = (long) log_buf;
+	if (verifier_logs) {
+		ctx->log_level = 1 + 2 + 4;
+		ctx->log_size = log_buf_sz;
+		log_buf = malloc(log_buf_sz);
+		if (!log_buf)
+			return -ENOMEM;
+		ctx->log_buf = (long) log_buf;
+	}
 	opts.ctx = ctx;
 	opts.data = gen->data;
 	opts.data_sz = gen->data_sz;
@@ -1701,9 +1793,9 @@ static int try_loader(struct gen_loader_opts *gen)
 	fds_before = count_open_fds();
 	err = bpf_load_and_run(&opts);
 	fd_delta = count_open_fds() - fds_before;
-	if (err < 0) {
+	if (err < 0 || verifier_logs) {
 		fprintf(stderr, "err %d\n%s\n%s", err, opts.errstr, log_buf);
-		if (fd_delta)
+		if (fd_delta && err < 0)
 			fprintf(stderr, "loader prog leaked %d FDs\n",
 				fd_delta);
 	}
@@ -1715,7 +1807,6 @@ static int do_loader(int argc, char **argv)
 {
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts);
 	DECLARE_LIBBPF_OPTS(gen_loader_opts, gen);
-	struct bpf_object_load_attr load_attr = {};
 	struct bpf_object *obj;
 	const char *file;
 	int err = 0;
@@ -1724,6 +1815,10 @@ static int do_loader(int argc, char **argv)
 		return -1;
 	file = GET_ARG();
 
+	if (verifier_logs)
+		/* log_level1 + log_level2 + stats, but not stable UAPI */
+		open_opts.kernel_log_level = 1 + 2 + 4;
+
 	obj = bpf_object__open_file(file, &open_opts);
 	if (libbpf_get_error(obj)) {
 		p_err("failed to open object file");
@@ -1734,12 +1829,7 @@ static int do_loader(int argc, char **argv)
 	if (err)
 		goto err_close_obj;
 
-	load_attr.obj = obj;
-	if (verifier_logs)
-		/* log_level1 + log_level2 + stats, but not stable UAPI */
-		load_attr.log_level = 1 + 2 + 4;
-
-	err = bpf_object__load_xattr(&load_attr);
+	err = bpf_object__load(obj);
 	if (err) {
 		p_err("failed to load object file");
 		goto err_close_obj;
@@ -2009,41 +2099,58 @@ static void profile_print_readings(void)
 
 static char *profile_target_name(int tgt_fd)
 {
-	struct bpf_prog_info_linear *info_linear;
-	struct bpf_func_info *func_info;
+	struct bpf_func_info func_info;
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
 	const struct btf_type *t;
+	__u32 func_info_rec_size;
 	struct btf *btf = NULL;
 	char *name = NULL;
+	int err;
 
-	info_linear = bpf_program__get_prog_info_linear(
-		tgt_fd, 1UL << BPF_PROG_INFO_FUNC_INFO);
-	if (IS_ERR_OR_NULL(info_linear)) {
-		p_err("failed to get info_linear for prog FD %d", tgt_fd);
-		return NULL;
+	err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len);
+	if (err) {
+		p_err("failed to bpf_obj_get_info_by_fd for prog FD %d", tgt_fd);
+		goto out;
 	}
 
-	if (info_linear->info.btf_id == 0) {
+	if (info.btf_id == 0) {
 		p_err("prog FD %d doesn't have valid btf", tgt_fd);
 		goto out;
 	}
 
-	btf = btf__load_from_kernel_by_id(info_linear->info.btf_id);
+	func_info_rec_size = info.func_info_rec_size;
+	if (info.nr_func_info == 0) {
+		p_err("bpf_obj_get_info_by_fd for prog FD %d found 0 func_info", tgt_fd);
+		goto out;
+	}
+
+	memset(&info, 0, sizeof(info));
+	info.nr_func_info = 1;
+	info.func_info_rec_size = func_info_rec_size;
+	info.func_info = ptr_to_u64(&func_info);
+
+	err = bpf_obj_get_info_by_fd(tgt_fd, &info, &info_len);
+	if (err) {
+		p_err("failed to get func_info for prog FD %d", tgt_fd);
+		goto out;
+	}
+
+	btf = btf__load_from_kernel_by_id(info.btf_id);
 	if (libbpf_get_error(btf)) {
 		p_err("failed to load btf for prog FD %d", tgt_fd);
 		goto out;
 	}
 
-	func_info = u64_to_ptr(info_linear->info.func_info);
-	t = btf__type_by_id(btf, func_info[0].type_id);
+	t = btf__type_by_id(btf, func_info.type_id);
 	if (!t) {
 		p_err("btf %d doesn't have type %d",
-		      info_linear->info.btf_id, func_info[0].type_id);
+		      info.btf_id, func_info.type_id);
 		goto out;
 	}
 	name = strdup(btf__name_by_offset(btf, t->name_off));
 out:
 	btf__free(btf);
-	free(info_linear);
 	return name;
 }
 

tools/bpf/bpftool/skeleton/pid_iter.bpf.c

@@ -71,8 +71,8 @@ int iter(struct bpf_iter__task_file *ctx)
 
 	e.pid = task->tgid;
 	e.id = get_obj_id(file->private_data, obj_type);
-	bpf_probe_read_kernel(&e.comm, sizeof(e.comm),
-			      task->group_leader->comm);
+	bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm),
+				  task->group_leader->comm);
 	bpf_seq_write(ctx->meta->seq, &e, sizeof(e));
 
 	return 0;

tools/bpf/bpftool/struct_ops.c

@@ -32,7 +32,7 @@ static const struct btf *get_btf_vmlinux(void)
 		return btf_vmlinux;
 
 	btf_vmlinux = libbpf_find_kernel_btf();
-	if (IS_ERR(btf_vmlinux))
+	if (libbpf_get_error(btf_vmlinux))
 		p_err("struct_ops requires kernel CONFIG_DEBUG_INFO_BTF=y");
 
 	return btf_vmlinux;
@@ -45,7 +45,7 @@ static const char *get_kern_struct_ops_name(const struct bpf_map_info *info)
 	const char *st_ops_name;
 
 	kern_btf = get_btf_vmlinux();
-	if (IS_ERR(kern_btf))
+	if (libbpf_get_error(kern_btf))
 		return "<btf_vmlinux_not_found>";
 
 	t = btf__type_by_id(kern_btf, info->btf_vmlinux_value_type_id);
@@ -63,7 +63,7 @@ static __s32 get_map_info_type_id(void)
 		return map_info_type_id;
 
 	kern_btf = get_btf_vmlinux();
-	if (IS_ERR(kern_btf)) {
+	if (libbpf_get_error(kern_btf)) {
 		map_info_type_id = PTR_ERR(kern_btf);
 		return map_info_type_id;
 	}
@@ -252,7 +252,7 @@ static struct res do_one_id(const char *id_str, work_func func, void *data,
 	}
 
 	fd = bpf_map_get_fd_by_id(id);
-	if (fd == -1) {
+	if (fd < 0) {
 		p_err("can't get map by id (%lu): %s", id, strerror(errno));
 		res.nr_errs++;
 		return res;
@@ -415,7 +415,7 @@ static int do_dump(int argc, char **argv)
 	}
 
 	kern_btf = get_btf_vmlinux();
-	if (IS_ERR(kern_btf))
+	if (libbpf_get_error(kern_btf))
 		return -1;
 
 	if (!json_output) {
@@ -479,7 +479,7 @@ static int do_unregister(int argc, char **argv)
 
 static int do_register(int argc, char **argv)
 {
-	struct bpf_object_load_attr load_attr = {};
+	LIBBPF_OPTS(bpf_object_open_opts, open_opts);
 	const struct bpf_map_def *def;
 	struct bpf_map_info info = {};
 	__u32 info_len = sizeof(info);
@@ -494,18 +494,17 @@ static int do_register(int argc, char **argv)
 
 	file = GET_ARG();
 
-	obj = bpf_object__open(file);
-	if (IS_ERR_OR_NULL(obj))
+	if (verifier_logs)
+		/* log_level1 + log_level2 + stats, but not stable UAPI */
+		open_opts.kernel_log_level = 1 + 2 + 4;
+
+	obj = bpf_object__open_file(file, &open_opts);
+	if (libbpf_get_error(obj))
 		return -1;
 
 	set_max_rlimit();
 
-	load_attr.obj = obj;
-	if (verifier_logs)
-		/* log_level1 + log_level2 + stats, but not stable UAPI */
-		load_attr.log_level = 1 + 2 + 4;
-
-	if (bpf_object__load_xattr(&load_attr)) {
+	if (bpf_object__load(obj)) {
 		bpf_object__close(obj);
 		return -1;
 	}
@@ -516,7 +515,7 @@ static int do_register(int argc, char **argv)
 			continue;
 
 		link = bpf_map__attach_struct_ops(map);
-		if (IS_ERR(link)) {
+		if (libbpf_get_error(link)) {
 			p_err("can't register struct_ops %s: %s",
 			      bpf_map__name(map),
 			      strerror(-PTR_ERR(link)));
@@ -596,7 +595,7 @@ int do_struct_ops(int argc, char **argv)
 
 	err = cmd_select(cmds, argc, argv, do_help);
 
-	if (!IS_ERR(btf_vmlinux))
+	if (!libbpf_get_error(btf_vmlinux))
 		btf__free(btf_vmlinux);
 
 	return err;

tools/bpf/resolve_btfids/Makefile

@@ -23,6 +23,7 @@ CC       = $(HOSTCC)
 LD       = $(HOSTLD)
 ARCH     = $(HOSTARCH)
 RM      ?= rm
+CROSS_COMPILE =
 
 OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/
 
@@ -30,27 +31,33 @@ LIBBPF_SRC := $(srctree)/tools/lib/bpf/
 SUBCMD_SRC := $(srctree)/tools/lib/subcmd/
 
 BPFOBJ     := $(OUTPUT)/libbpf/libbpf.a
+LIBBPF_OUT := $(abspath $(dir $(BPFOBJ)))/
 SUBCMDOBJ  := $(OUTPUT)/libsubcmd/libsubcmd.a
 
+LIBBPF_DESTDIR := $(LIBBPF_OUT)
+LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include
+
 BINARY     := $(OUTPUT)/resolve_btfids
 BINARY_IN  := $(BINARY)-in.o
 
 all: $(BINARY)
 
-$(OUTPUT) $(OUTPUT)/libbpf $(OUTPUT)/libsubcmd:
+$(OUTPUT) $(OUTPUT)/libsubcmd $(LIBBPF_OUT):
 	$(call msg,MKDIR,,$@)
 	$(Q)mkdir -p $(@)
 
 $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd
 	$(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
 
-$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT)/libbpf
-	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC)  OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
+$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT)
+	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT)    \
+		    DESTDIR=$(LIBBPF_DESTDIR) prefix=			       \
+		    $(abspath $@) install_headers
 
 CFLAGS := -g \
           -I$(srctree)/tools/include \
           -I$(srctree)/tools/include/uapi \
-          -I$(LIBBPF_SRC) \
+          -I$(LIBBPF_INCLUDE) \
           -I$(SUBCMD_SRC)
 
 LIBS = -lelf -lz
@@ -58,7 +65,7 @@ LIBS = -lelf -lz
 export srctree OUTPUT CFLAGS Q
 include $(srctree)/tools/build/Makefile.include
 
-$(BINARY_IN): fixdep FORCE | $(OUTPUT)
+$(BINARY_IN): $(BPFOBJ) fixdep FORCE | $(OUTPUT)
 	$(Q)$(MAKE) $(build)=resolve_btfids
 
 $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN)
@@ -68,7 +75,8 @@ $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN)
 clean_objects := $(wildcard $(OUTPUT)/*.o                \
                             $(OUTPUT)/.*.o.cmd           \
                             $(OUTPUT)/.*.o.d             \
-                            $(OUTPUT)/libbpf             \
+                            $(LIBBPF_OUT)                \
+                            $(LIBBPF_DESTDIR)            \
                             $(OUTPUT)/libsubcmd          \
                             $(OUTPUT)/resolve_btfids)
 

tools/bpf/resolve_btfids/main.c

@@ -60,8 +60,8 @@
 #include <linux/rbtree.h>
 #include <linux/zalloc.h>
 #include <linux/err.h>
-#include <btf.h>
-#include <libbpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
 #include <parse-options.h>
 
 #define BTF_IDS_SECTION	".BTF_ids"
@@ -83,12 +83,14 @@ struct btf_id {
 		int	 cnt;
 	};
 	int		 addr_cnt;
+	bool		 is_set;
 	Elf64_Addr	 addr[ADDR_CNT];
 };
 
 struct object {
 	const char *path;
 	const char *btf;
+	const char *base_btf_path;
 
 	struct {
 		int		 fd;
@@ -450,8 +452,10 @@ static int symbols_collect(struct object *obj)
 			 * in symbol's size, together with 'cnt' field hence
 			 * that - 1.
 			 */
-			if (id)
+			if (id) {
 				id->cnt = sym.st_size / sizeof(int) - 1;
+				id->is_set = true;
+			}
 		} else {
 			pr_err("FAILED unsupported prefix %s\n", prefix);
 			return -1;
@@ -477,25 +481,36 @@ static int symbols_resolve(struct object *obj)
 	int nr_structs  = obj->nr_structs;
 	int nr_unions   = obj->nr_unions;
 	int nr_funcs    = obj->nr_funcs;
+	struct btf *base_btf = NULL;
 	int err, type_id;
 	struct btf *btf;
 	__u32 nr_types;
 
-	btf = btf__parse(obj->btf ?: obj->path, NULL);
+	if (obj->base_btf_path) {
+		base_btf = btf__parse(obj->base_btf_path, NULL);
+		err = libbpf_get_error(base_btf);
+		if (err) {
+			pr_err("FAILED: load base BTF from %s: %s\n",
+			       obj->base_btf_path, strerror(-err));
+			return -1;
+		}
+	}
+
+	btf = btf__parse_split(obj->btf ?: obj->path, base_btf);
 	err = libbpf_get_error(btf);
 	if (err) {
 		pr_err("FAILED: load BTF from %s: %s\n",
 			obj->btf ?: obj->path, strerror(-err));
-		return -1;
+		goto out;
 	}
 
 	err = -1;
-	nr_types = btf__get_nr_types(btf);
+	nr_types = btf__type_cnt(btf);
 
 	/*
 	 * Iterate all the BTF types and search for collected symbol IDs.
 	 */
-	for (type_id = 1; type_id <= nr_types; type_id++) {
+	for (type_id = 1; type_id < nr_types; type_id++) {
 		const struct btf_type *type;
 		struct rb_root *root;
 		struct btf_id *id;
@@ -545,6 +560,7 @@ static int symbols_resolve(struct object *obj)
 
 	err = 0;
 out:
+	btf__free(base_btf);
 	btf__free(btf);
 	return err;
 }
@@ -555,9 +571,8 @@ static int id_patch(struct object *obj, struct btf_id *id)
 	int *ptr = data->d_buf;
 	int i;
 
-	if (!id->id) {
+	if (!id->id && !id->is_set)
 		pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name);
-	}
 
 	for (i = 0; i < id->addr_cnt; i++) {
 		unsigned long addr = id->addr[i];
@@ -678,7 +693,6 @@ static const char * const resolve_btfids_usage[] = {
 
 int main(int argc, const char **argv)
 {
-	bool no_fail = false;
 	struct object obj = {
 		.efile = {
 			.idlist_shndx  = -1,
@@ -695,8 +709,8 @@ int main(int argc, const char **argv)
 			 "be more verbose (show errors, etc)"),
 		OPT_STRING(0, "btf", &obj.btf, "BTF data",
 			   "BTF data"),
-		OPT_BOOLEAN(0, "no-fail", &no_fail,
-			   "do not fail if " BTF_IDS_SECTION " section is not found"),
+		OPT_STRING('b', "btf_base", &obj.base_btf_path, "file",
+			   "path of file providing base BTF"),
 		OPT_END()
 	};
 	int err = -1;
@@ -717,9 +731,7 @@ int main(int argc, const char **argv)
 	 */
 	if (obj.efile.idlist_shndx == -1 ||
 	    obj.efile.symbols_shndx == -1) {
-		if (no_fail)
-			return 0;
-		pr_err("FAILED to find needed sections\n");
+		pr_debug("Cannot find .BTF_ids or symbols sections, nothing to do\n");
 		err = 0;
 		goto out;
 	}

tools/bpf/runqslower/Makefile

@@ -9,10 +9,10 @@ BPFTOOL ?= $(DEFAULT_BPFTOOL)
 LIBBPF_SRC := $(abspath ../../lib/bpf)
 BPFOBJ_OUTPUT := $(OUTPUT)libbpf/
 BPFOBJ := $(BPFOBJ_OUTPUT)libbpf.a
-BPF_INCLUDE := $(BPFOBJ_OUTPUT)
-INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../lib)        \
-       -I$(abspath ../../include/uapi)
-CFLAGS := -g -Wall
+BPF_DESTDIR := $(BPFOBJ_OUTPUT)
+BPF_INCLUDE := $(BPF_DESTDIR)/include
+INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../include/uapi)
+CFLAGS := -g -Wall $(CLANG_CROSS_FLAGS)
 
 # Try to detect best kernel BTF source
 KERNEL_REL := $(shell uname -r)
@@ -33,7 +33,7 @@ endif
 
 .DELETE_ON_ERROR:
 
-.PHONY: all clean runqslower
+.PHONY: all clean runqslower libbpf_hdrs
 all: runqslower
 
 runqslower: $(OUTPUT)/runqslower
@@ -46,13 +46,15 @@ clean:
 	$(Q)$(RM) $(OUTPUT)runqslower
 	$(Q)$(RM) -r .output
 
+libbpf_hdrs: $(BPFOBJ)
+
 $(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $^ -lelf -lz -o $@
 
 $(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h	      \
-			$(OUTPUT)/runqslower.bpf.o
+			$(OUTPUT)/runqslower.bpf.o | libbpf_hdrs
 
-$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h
+$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h | libbpf_hdrs
 
 $(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL)
 	$(QUIET_GEN)$(BPFTOOL) gen skeleton $< > $@
@@ -81,8 +83,9 @@ else
 endif
 
 $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OUTPUT)
-	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(BPFOBJ_OUTPUT) $@
+	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(BPFOBJ_OUTPUT) \
+		    DESTDIR=$(BPFOBJ_OUTPUT) prefix= $(abspath $@) install_headers
 
-$(DEFAULT_BPFTOOL): | $(BPFTOOL_OUTPUT)
+$(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT)
 	$(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT)   \
-		    CC=$(HOSTCC) LD=$(HOSTLD)
+		    ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD)

tools/bpf/runqslower/runqslower.bpf.c

@@ -68,7 +68,7 @@ int handle__sched_switch(u64 *ctx)
 	 */
 	struct task_struct *prev = (struct task_struct *)ctx[1];
 	struct task_struct *next = (struct task_struct *)ctx[2];
-	struct event event = {};
+	struct runq_event event = {};
 	u64 *tsp, delta_us;
 	long state;
 	u32 pid;

tools/bpf/runqslower/runqslower.c

@@ -100,7 +100,7 @@ static int bump_memlock_rlimit(void)
 
 void handle_event(void *ctx, int cpu, void *data, __u32 data_sz)
 {
-	const struct event *e = data;
+	const struct runq_event *e = data;
 	struct tm *tm;
 	char ts[32];
 	time_t t;
@@ -123,7 +123,6 @@ int main(int argc, char **argv)
 		.parser = parse_arg,
 		.doc = argp_program_doc,
 	};
-	struct perf_buffer_opts pb_opts;
 	struct perf_buffer *pb = NULL;
 	struct runqslower_bpf *obj;
 	int err;
@@ -165,9 +164,8 @@ int main(int argc, char **argv)
 	printf("Tracing run queue latency higher than %llu us\n", env.min_us);
 	printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)");
 
-	pb_opts.sample_cb = handle_event;
-	pb_opts.lost_cb = handle_lost_events;
-	pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, &pb_opts);
+	pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64,
+			      handle_event, handle_lost_events, NULL, NULL);
 	err = libbpf_get_error(pb);
 	if (err) {
 		pb = NULL;

tools/bpf/runqslower/runqslower.h

@@ -4,7 +4,7 @@
 
 #define TASK_COMM_LEN 16
 
-struct event {
+struct runq_event {
 	char task[TASK_COMM_LEN];
 	__u64 delta_us;
 	pid_t pid;

tools/build/Build.include

@@ -99,7 +99,7 @@ cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXX
 ###
 ## HOSTCC C flags
 
-host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(KBUILD_HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
+host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
 
 # output directory for tests below
 TMPOUT = .tmp_$$$$

tools/build/Makefile.feature

@@ -51,6 +51,7 @@ FEATURE_TESTS_BASIC :=                  \
         libslang                        \
         libslang-include-subdir         \
         libtraceevent                   \
+        libtracefs                      \
         libcrypto                       \
         libunwind                       \
         pthread-attr-setaffinity-np     \

tools/build/feature/Makefile

@@ -35,6 +35,7 @@ FILES=                                          \
          test-libslang.bin                      \
          test-libslang-include-subdir.bin       \
          test-libtraceevent.bin                 \
+         test-libtracefs.bin                    \
          test-libcrypto.bin                     \
          test-libunwind.bin                     \
          test-libunwind-debug-frame.bin         \
@@ -89,7 +90,7 @@ __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(
 ###############################
 
 $(OUTPUT)test-all.bin:
-	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap
+	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap
 
 $(OUTPUT)test-hello.bin:
 	$(BUILD)
@@ -198,6 +199,9 @@ $(OUTPUT)test-libslang-include-subdir.bin:
 $(OUTPUT)test-libtraceevent.bin:
 	$(BUILD) -ltraceevent
 
+$(OUTPUT)test-libtracefs.bin:
+	$(BUILD) -ltracefs
+
 $(OUTPUT)test-libcrypto.bin:
 	$(BUILD) -lcrypto
 
@@ -292,7 +296,7 @@ $(OUTPUT)test-jvmti-cmlr.bin:
 	$(BUILD)
 
 $(OUTPUT)test-llvm.bin:
-	$(BUILDXX) -std=gnu++11 				\
+	$(BUILDXX) -std=gnu++14 				\
 		-I$(shell $(LLVM_CONFIG) --includedir) 		\
 		-L$(shell $(LLVM_CONFIG) --libdir)		\
 		$(shell $(LLVM_CONFIG) --libs Core BPF)		\
@@ -300,12 +304,12 @@ $(OUTPUT)test-llvm.bin:
 		> $(@:.bin=.make.output) 2>&1
 
 $(OUTPUT)test-llvm-version.bin:
-	$(BUILDXX) -std=gnu++11 				\
+	$(BUILDXX) -std=gnu++14					\
 		-I$(shell $(LLVM_CONFIG) --includedir)		\
 		> $(@:.bin=.make.output) 2>&1
 
 $(OUTPUT)test-clang.bin:
-	$(BUILDXX) -std=gnu++11 				\
+	$(BUILDXX) -std=gnu++14					\
 		-I$(shell $(LLVM_CONFIG) --includedir) 		\
 		-L$(shell $(LLVM_CONFIG) --libdir)		\
 		-Wl,--start-group -lclangBasic -lclangDriver	\

tools/build/feature/test-bpf.c

@@ -14,6 +14,12 @@
 #  define __NR_bpf 349
 # elif defined(__s390__)
 #  define __NR_bpf 351
+# elif defined(__mips__) && defined(_ABIO32)
+#  define __NR_bpf 4355
+# elif defined(__mips__) && defined(_ABIN32)
+#  define __NR_bpf 6319
+# elif defined(__mips__) && defined(_ABI64)
+#  define __NR_bpf 5315
 # else
 #  error __NR_bpf not defined. libbpf does not support your arch.
 # endif

tools/cgroup/memcg_slabinfo.py

@@ -11,7 +11,7 @@ from drgn.helpers.linux import list_for_each_entry, list_empty
 from drgn.helpers.linux import for_each_page
 from drgn.helpers.linux.cpumask import for_each_online_cpu
 from drgn.helpers.linux.percpu import per_cpu_ptr
-from drgn import container_of, FaultError, Object
+from drgn import container_of, FaultError, Object, cast
 
 
 DESC = """
@@ -69,15 +69,15 @@ def oo_objects(s):
 
 
 def count_partial(n, fn):
-    nr_pages = 0
-    for page in list_for_each_entry('struct page', n.partial.address_of_(),
-                                    'lru'):
-         nr_pages += fn(page)
-    return nr_pages
+    nr_objs = 0
+    for slab in list_for_each_entry('struct slab', n.partial.address_of_(),
+                                    'slab_list'):
+         nr_objs += fn(slab)
+    return nr_objs
 
 
-def count_free(page):
-    return page.objects - page.inuse
+def count_free(slab):
+    return slab.objects - slab.inuse
 
 
 def slub_get_slabinfo(s, cfg):
@@ -145,14 +145,14 @@ def detect_kernel_config():
     return cfg
 
 
-def for_each_slab_page(prog):
+def for_each_slab(prog):
     PGSlab = 1 << prog.constant('PG_slab')
     PGHead = 1 << prog.constant('PG_head')
 
     for page in for_each_page(prog):
         try:
             if page.flags.value_() & PGSlab:
-                yield page
+                yield cast('struct slab *', page)
         except FaultError:
             pass
 
@@ -190,13 +190,13 @@ def main():
                                        'list'):
             obj_cgroups.add(ptr.value_())
 
-        # look over all slab pages, belonging to non-root memcgs
-        # and look for objects belonging to the given memory cgroup
-        for page in for_each_slab_page(prog):
-            objcg_vec_raw = page.memcg_data.value_()
+        # look over all slab folios and look for objects belonging
+        # to the given memory cgroup
+        for slab in for_each_slab(prog):
+            objcg_vec_raw = slab.memcg_data.value_()
             if objcg_vec_raw == 0:
                 continue
-            cache = page.slab_cache
+            cache = slab.slab_cache
             if not cache:
                 continue
             addr = cache.value_()

tools/iio/iio_event_monitor.c

@@ -279,6 +279,7 @@ static void print_event(struct iio_event_data *event)
 		printf(", direction: %s", iio_ev_dir_text[dir]);
 
 	printf("\n");
+	fflush(stdout);
 }
 
 /* Enable or disable events in sysfs if the knob is available */

tools/include/asm-generic/bitops.h

@@ -18,7 +18,6 @@
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/find.h>
 
 #ifndef _TOOLS_LINUX_BITOPS_H_
 #error only <linux/bitops.h> can be included directly

tools/include/linux/bitmap.h

@@ -1,9 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _PERF_BITOPS_H
-#define _PERF_BITOPS_H
+#ifndef _TOOLS_LINUX_BITMAP_H
+#define _TOOLS_LINUX_BITMAP_H
 
 #include <string.h>
 #include <linux/bitops.h>
+#include <linux/find.h>
 #include <stdlib.h>
 #include <linux/kernel.h>
 
@@ -181,4 +182,4 @@ static inline int bitmap_intersects(const unsigned long *src1,
 		return __bitmap_intersects(src1, src2, nbits);
 }
 
-#endif /* _PERF_BITOPS_H */
+#endif /* _TOOLS_LINUX_BITMAP_H */

tools/include/linux/hash.h

@@ -62,10 +62,7 @@ static inline u32 __hash_32_generic(u32 val)
 	return val * GOLDEN_RATIO_32;
 }
 
-#ifndef HAVE_ARCH_HASH_32
-#define hash_32 hash_32_generic
-#endif
-static inline u32 hash_32_generic(u32 val, unsigned int bits)
+static inline u32 hash_32(u32 val, unsigned int bits)
 {
 	/* High bits are more random, so use them. */
 	return __hash_32(val) >> (32 - bits);

tools/include/linux/kernel.h

@@ -7,6 +7,7 @@
 #include <assert.h>
 #include <linux/build_bug.h>
 #include <linux/compiler.h>
+#include <linux/math.h>
 #include <endian.h>
 #include <byteswap.h>
 
@@ -14,8 +15,6 @@
 #define UINT_MAX	(~0U)
 #endif
 
-#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
-
 #define PERF_ALIGN(x, a)	__PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
 #define __PERF_ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
 
@@ -52,15 +51,6 @@
 	_min1 < _min2 ? _min1 : _min2; })
 #endif
 
-#ifndef roundup
-#define roundup(x, y) (                                \
-{                                                      \
-	const typeof(y) __y = y;		       \
-	(((x) + (__y - 1)) / __y) * __y;	       \
-}                                                      \
-)
-#endif
-
 #ifndef BUG_ON
 #ifdef NDEBUG
 #define BUG_ON(cond) do { if (cond) {} } while (0)
@@ -102,17 +92,9 @@ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
 int scnprintf(char * buf, size_t size, const char * fmt, ...);
 int scnprintf_pad(char * buf, size_t size, const char * fmt, ...);
 
+#ifndef ARRAY_SIZE
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
-
-/*
- * This looks more complex than it should be. But we need to
- * get the type for the ~ right in round_down (it needs to be
- * as wide as the result!), and we want to evaluate the macro
- * arguments just once each.
- */
-#define __round_mask(x, y) ((__typeof__(x))((y)-1))
-#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
-#define round_down(x, y) ((x) & ~__round_mask(x, y))
+#endif
 
 #define current_gfp_context(k) 0
 #define synchronize_rcu()

tools/include/linux/objtool.h

@@ -66,6 +66,17 @@ struct unwind_hint {
 	static void __used __section(".discard.func_stack_frame_non_standard") \
 		*__func_stack_frame_non_standard_##func = func
 
+/*
+ * STACK_FRAME_NON_STANDARD_FP() is a frame-pointer-specific function ignore
+ * for the case where a function is intentionally missing frame pointer setup,
+ * but otherwise needs objtool/ORC coverage when frame pointers are disabled.
+ */
+#ifdef CONFIG_FRAME_POINTER
+#define STACK_FRAME_NON_STANDARD_FP(func) STACK_FRAME_NON_STANDARD(func)
+#else
+#define STACK_FRAME_NON_STANDARD_FP(func)
+#endif
+
 #else /* __ASSEMBLY__ */
 
 /*
@@ -127,6 +138,7 @@ struct unwind_hint {
 #define UNWIND_HINT(sp_reg, sp_offset, type, end)	\
 	"\n\t"
 #define STACK_FRAME_NON_STANDARD(func)
+#define STACK_FRAME_NON_STANDARD_FP(func)
 #else
 #define ANNOTATE_INTRA_FUNCTION_CALL
 .macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0

tools/include/linux/spinlock.h

@@ -37,6 +37,4 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex)
 	return true;
 }
 
-#include <linux/lockdep.h>
-
 #endif

tools/include/nolibc/nolibc.h

@@ -265,12 +265,17 @@ struct stat {
  *   - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively
  *   - the system call is performed by calling the syscall instruction
  *   - syscall return comes in rax
- *   - rcx and r8..r11 may be clobbered, others are preserved.
+ *   - rcx and r11 are clobbered, others are preserved.
  *   - the arguments are cast to long and assigned into the target registers
  *     which are then simply passed as registers to the asm code, so that we
  *     don't have to experience issues with register constraints.
  *   - the syscall number is always specified last in order to allow to force
  *     some registers before (gcc refuses a %-register at the last position).
+ *   - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1
+ *     Calling Conventions.
+ *
+ * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/x86-64-psABI
+ *
  */
 
 #define my_syscall0(num)                                                      \
@@ -280,9 +285,9 @@ struct stat {
 									      \
 	asm volatile (                                                        \
 		"syscall\n"                                                   \
-		: "=a" (_ret)                                                 \
+		: "=a"(_ret)                                                  \
 		: "0"(_num)                                                   \
-		: "rcx", "r8", "r9", "r10", "r11", "memory", "cc"             \
+		: "rcx", "r11", "memory", "cc"                                \
 	);                                                                    \
 	_ret;                                                                 \
 })
@@ -295,10 +300,10 @@ struct stat {
 									      \
 	asm volatile (                                                        \
 		"syscall\n"                                                   \
-		: "=a" (_ret)                                                 \
+		: "=a"(_ret)                                                  \
 		: "r"(_arg1),                                                 \
 		  "0"(_num)                                                   \
-		: "rcx", "r8", "r9", "r10", "r11", "memory", "cc"             \
+		: "rcx", "r11", "memory", "cc"                                \
 	);                                                                    \
 	_ret;                                                                 \
 })
@@ -312,10 +317,10 @@ struct stat {
 									      \
 	asm volatile (                                                        \
 		"syscall\n"                                                   \
-		: "=a" (_ret)                                                 \
+		: "=a"(_ret)                                                  \
 		: "r"(_arg1), "r"(_arg2),                                     \
 		  "0"(_num)                                                   \
-		: "rcx", "r8", "r9", "r10", "r11", "memory", "cc"             \
+		: "rcx", "r11", "memory", "cc"                                \
 	);                                                                    \
 	_ret;                                                                 \
 })
@@ -330,10 +335,10 @@ struct stat {
 									      \
 	asm volatile (                                                        \
 		"syscall\n"                                                   \
-		: "=a" (_ret)                                                 \
+		: "=a"(_ret)                                                  \
 		: "r"(_arg1), "r"(_arg2), "r"(_arg3),                         \
 		  "0"(_num)                                                   \
-		: "rcx", "r8", "r9", "r10", "r11", "memory", "cc"             \
+		: "rcx", "r11", "memory", "cc"                                \
 	);                                                                    \
 	_ret;                                                                 \
 })
@@ -349,10 +354,10 @@ struct stat {
 									      \
 	asm volatile (                                                        \
 		"syscall\n"                                                   \
-		: "=a" (_ret), "=r"(_arg4)                                    \
+		: "=a"(_ret)                                                  \
 		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4),             \
 		  "0"(_num)                                                   \
-		: "rcx", "r8", "r9", "r11", "memory", "cc"                    \
+		: "rcx", "r11", "memory", "cc"                                \
 	);                                                                    \
 	_ret;                                                                 \
 })
@@ -369,10 +374,10 @@ struct stat {
 									      \
 	asm volatile (                                                        \
 		"syscall\n"                                                   \
-		: "=a" (_ret), "=r"(_arg4), "=r"(_arg5)                       \
+		: "=a"(_ret)                                                  \
 		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
 		  "0"(_num)                                                   \
-		: "rcx", "r9", "r11", "memory", "cc"                          \
+		: "rcx", "r11", "memory", "cc"                                \
 	);                                                                    \
 	_ret;                                                                 \
 })
@@ -390,7 +395,7 @@ struct stat {
 									      \
 	asm volatile (                                                        \
 		"syscall\n"                                                   \
-		: "=a" (_ret), "=r"(_arg4), "=r"(_arg5)                       \
+		: "=a"(_ret)                                                  \
 		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
 		  "r"(_arg6), "0"(_num)                                       \
 		: "rcx", "r11", "memory", "cc"                                \
@@ -415,7 +420,7 @@ asm(".section .text\n"
     "and $-16, %rsp\n"          // x86 ABI : esp must be 16-byte aligned before call
     "call main\n"               // main() returns the status code, we'll exit with it.
     "mov %eax, %edi\n"          // retrieve exit code (32 bit)
-    "mov $60, %rax\n"           // NR_exit == 60
+    "mov $60, %eax\n"           // NR_exit == 60
     "syscall\n"                 // really exit
     "hlt\n"                     // ensure it does not return
     "");
@@ -1566,6 +1571,12 @@ pid_t sys_getpid(void)
 	return my_syscall0(__NR_getpid);
 }
 
+static __attribute__((unused))
+pid_t sys_gettid(void)
+{
+	return my_syscall0(__NR_gettid);
+}
+
 static __attribute__((unused))
 int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
 {
@@ -2024,6 +2035,18 @@ pid_t getpid(void)
 	return ret;
 }
 
+static __attribute__((unused))
+pid_t gettid(void)
+{
+	pid_t ret = sys_gettid();
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
 static __attribute__((unused))
 int gettimeofday(struct timeval *tv, struct timezone *tz)
 {

tools/include/uapi/asm-generic/unistd.h

@@ -880,8 +880,14 @@ __SYSCALL(__NR_memfd_secret, sys_memfd_secret)
 #define __NR_process_mrelease 448
 __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 
+#define __NR_futex_waitv 449
+__SYSCALL(__NR_futex_waitv, sys_futex_waitv)
+
+#define __NR_set_mempolicy_home_node 450
+__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
+
 #undef __NR_syscalls
-#define __NR_syscalls 449
+#define __NR_syscalls 451
 
 /*
  * 32 bit systems traditionally used different

tools/include/uapi/drm/drm.h

@@ -1096,6 +1096,24 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_TRANSFER	DRM_IOWR(0xCC, struct drm_syncobj_transfer)
 #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL	DRM_IOWR(0xCD, struct drm_syncobj_timeline_array)
 
+/**
+ * DRM_IOCTL_MODE_GETFB2 - Get framebuffer metadata.
+ *
+ * This queries metadata about a framebuffer. User-space fills
+ * &drm_mode_fb_cmd2.fb_id as the input, and the kernels fills the rest of the
+ * struct as the output.
+ *
+ * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles
+ * will be filled with GEM buffer handles. Planes are valid until one has a
+ * zero handle -- this can be used to compute the number of planes.
+ *
+ * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid
+ * until one has a zero &drm_mode_fb_cmd2.pitches.
+ *
+ * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set
+ * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the
+ * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier.
+ */
 #define DRM_IOCTL_MODE_GETFB2		DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
 
 /*

tools/include/uapi/drm/i915_drm.h

@@ -1522,6 +1522,12 @@ struct drm_i915_gem_caching {
 #define I915_TILING_NONE	0
 #define I915_TILING_X		1
 #define I915_TILING_Y		2
+/*
+ * Do not add new tiling types here.  The I915_TILING_* values are for
+ * de-tiling fence registers that no longer exist on modern platforms.  Although
+ * the hardware may support new types of tiling in general (e.g., Tile4), we
+ * do not need to add them to the uapi that is specific to now-defunct ioctls.
+ */
 #define I915_TILING_LAST	I915_TILING_Y
 
 #define I915_BIT_6_SWIZZLE_NONE		0
@@ -1824,6 +1830,7 @@ struct drm_i915_gem_context_param {
  * Extensions:
  *   i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
  *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
+ *   i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT)
  */
 #define I915_CONTEXT_PARAM_ENGINES	0xa
 
@@ -1846,6 +1853,55 @@ struct drm_i915_gem_context_param {
  * attempted to use it, never re-use this context param number.
  */
 #define I915_CONTEXT_PARAM_RINGSIZE	0xc
+
+/*
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT:
+ *
+ * Mark that the context makes use of protected content, which will result
+ * in the context being invalidated when the protected content session is.
+ * Given that the protected content session is killed on suspend, the device
+ * is kept awake for the lifetime of a protected context, so the user should
+ * make sure to dispose of them once done.
+ * This flag can only be set at context creation time and, when set to true,
+ * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE
+ * to false. This flag can't be set to true in conjunction with setting the
+ * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example:
+ *
+ * .. code-block:: C
+ *
+ *	struct drm_i915_gem_context_create_ext_setparam p_protected = {
+ *		.base = {
+ *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ *		},
+ *		.param = {
+ *			.param = I915_CONTEXT_PARAM_PROTECTED_CONTENT,
+ *			.value = 1,
+ *		}
+ *	};
+ *	struct drm_i915_gem_context_create_ext_setparam p_norecover = {
+ *		.base = {
+ *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ *			.next_extension = to_user_pointer(&p_protected),
+ *		},
+ *		.param = {
+ *			.param = I915_CONTEXT_PARAM_RECOVERABLE,
+ *			.value = 0,
+ *		}
+ *	};
+ *	struct drm_i915_gem_context_create_ext create = {
+ *		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ *		.extensions = to_user_pointer(&p_norecover);
+ *	};
+ *
+ *	ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * In addition to the normal failure cases, setting this flag during context
+ * creation can result in the following errors:
+ *
+ * -ENODEV: feature not available
+ * -EPERM: trying to mark a recoverable or not bannable context as protected
+ */
+#define I915_CONTEXT_PARAM_PROTECTED_CONTENT    0xd
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;
@@ -2049,6 +2105,135 @@ struct i915_context_engines_bond {
 	struct i915_engine_class_instance engines[N__]; \
 } __attribute__((packed)) name__
 
+/**
+ * struct i915_context_engines_parallel_submit - Configure engine for
+ * parallel submission.
+ *
+ * Setup a slot in the context engine map to allow multiple BBs to be submitted
+ * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
+ * in parallel. Multiple hardware contexts are created internally in the i915 to
+ * run these BBs. Once a slot is configured for N BBs only N BBs can be
+ * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
+ * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
+ * many BBs there are based on the slot's configuration. The N BBs are the last
+ * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
+ *
+ * The default placement behavior is to create implicit bonds between each
+ * context if each context maps to more than 1 physical engine (e.g. context is
+ * a virtual engine). Also we only allow contexts of same engine class and these
+ * contexts must be in logically contiguous order. Examples of the placement
+ * behavior are described below. Lastly, the default is to not allow BBs to be
+ * preempted mid-batch. Rather insert coordinated preemption points on all
+ * hardware contexts between each set of BBs. Flags could be added in the future
+ * to change both of these default behaviors.
+ *
+ * Returns -EINVAL if hardware context placement configuration is invalid or if
+ * the placement configuration isn't supported on the platform / submission
+ * interface.
+ * Returns -ENODEV if extension isn't supported on the platform / submission
+ * interface.
+ *
+ * .. code-block:: none
+ *
+ *	Examples syntax:
+ *	CS[X] = generic engine of same class, logical instance X
+ *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
+ *
+ *	Example 1 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=1,
+ *		     engines=CS[0],CS[1])
+ *
+ *	Results in the following valid placement:
+ *	CS[0], CS[1]
+ *
+ *	Example 2 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[2],CS[1],CS[3])
+ *
+ *	Results in the following valid placements:
+ *	CS[0], CS[1]
+ *	CS[2], CS[3]
+ *
+ *	This can be thought of as two virtual engines, each containing two
+ *	engines thereby making a 2D array. However, there are bonds tying the
+ *	entries together and placing restrictions on how they can be scheduled.
+ *	Specifically, the scheduler can choose only vertical columns from the 2D
+ *	array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the
+ *	scheduler wants to submit to CS[0], it must also choose CS[1] and vice
+ *	versa. Same for CS[2] requires also using CS[3].
+ *	VE[0] = CS[0], CS[2]
+ *	VE[1] = CS[1], CS[3]
+ *
+ *	Example 3 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[1],CS[1],CS[3])
+ *
+ *	Results in the following valid and invalid placements:
+ *	CS[0], CS[1]
+ *	CS[1], CS[3] - Not logically contiguous, return -EINVAL
+ */
+struct i915_context_engines_parallel_submit {
+	/**
+	 * @base: base user extension.
+	 */
+	struct i915_user_extension base;
+
+	/**
+	 * @engine_index: slot for parallel engine
+	 */
+	__u16 engine_index;
+
+	/**
+	 * @width: number of contexts per parallel engine or in other words the
+	 * number of batches in each submission
+	 */
+	__u16 width;
+
+	/**
+	 * @num_siblings: number of siblings per context or in other words the
+	 * number of possible placements for each submission
+	 */
+	__u16 num_siblings;
+
+	/**
+	 * @mbz16: reserved for future use; must be zero
+	 */
+	__u16 mbz16;
+
+	/**
+	 * @flags: all undefined flags must be zero, currently not defined flags
+	 */
+	__u64 flags;
+
+	/**
+	 * @mbz64: reserved for future use; must be zero
+	 */
+	__u64 mbz64[3];
+
+	/**
+	 * @engines: 2-d array of engine instances to configure parallel engine
+	 *
+	 * length = width (i) * num_siblings (j)
+	 * index = j + i * num_siblings
+	 */
+	struct i915_engine_class_instance engines[0];
+
+} __packed;
+
+#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \
+	struct i915_user_extension base; \
+	__u16 engine_index; \
+	__u16 width; \
+	__u16 num_siblings; \
+	__u16 mbz16; \
+	__u64 flags; \
+	__u64 mbz64[3]; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
 /**
  * DOC: Context Engine Map uAPI
  *
@@ -2108,6 +2293,7 @@ struct i915_context_param_engines {
 	__u64 extensions; /* linked chain of extension blocks, 0 terminates */
 #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
 #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
+#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
 	struct i915_engine_class_instance engines[0];
 } __attribute__((packed));
 
@@ -2726,14 +2912,20 @@ struct drm_i915_engine_info {
 
 	/** @flags: Engine flags. */
 	__u64 flags;
+#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE		(1 << 0)
 
 	/** @capabilities: Capabilities of this engine. */
 	__u64 capabilities;
 #define I915_VIDEO_CLASS_CAPABILITY_HEVC		(1 << 0)
 #define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC	(1 << 1)
 
+	/** @logical_instance: Logical instance of engine */
+	__u16 logical_instance;
+
 	/** @rsvd1: Reserved fields. */
-	__u64 rsvd1[4];
+	__u16 rsvd1[3];
+	/** @rsvd2: Reserved fields. */
+	__u64 rsvd2[3];
 };
 
 /**
@@ -2979,8 +3171,12 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see
 	 * struct drm_i915_gem_create_ext_memory_regions.
+	 *
+	 * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see
+	 * struct drm_i915_gem_create_ext_protected_content.
 	 */
 #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
+#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1
 	__u64 extensions;
 };
 
@@ -3038,6 +3234,50 @@ struct drm_i915_gem_create_ext_memory_regions {
 	__u64 regions;
 };
 
+/**
+ * struct drm_i915_gem_create_ext_protected_content - The
+ * I915_OBJECT_PARAM_PROTECTED_CONTENT extension.
+ *
+ * If this extension is provided, buffer contents are expected to be protected
+ * by PXP encryption and require decryption for scan out and processing. This
+ * is only possible on platforms that have PXP enabled, on all other scenarios
+ * using this extension will cause the ioctl to fail and return -ENODEV. The
+ * flags parameter is reserved for future expansion and must currently be set
+ * to zero.
+ *
+ * The buffer contents are considered invalid after a PXP session teardown.
+ *
+ * The encryption is guaranteed to be processed correctly only if the object
+ * is submitted with a context created using the
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks
+ * at submission time on the validity of the objects involved.
+ *
+ * Below is an example on how to create a protected object:
+ *
+ * .. code-block:: C
+ *
+ *      struct drm_i915_gem_create_ext_protected_content protected_ext = {
+ *              .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT },
+ *              .flags = 0,
+ *      };
+ *      struct drm_i915_gem_create_ext create_ext = {
+ *              .size = PAGE_SIZE,
+ *              .extensions = (uintptr_t)&protected_ext,
+ *      };
+ *
+ *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ *      if (err) ...
+ */
+struct drm_i915_gem_create_ext_protected_content {
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+	/** @flags: reserved for future usage, currently MBZ */
+	__u32 flags;
+};
+
+/* ID of the protected content session managed by i915 when PXP is active */
+#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf
+
 #if defined(__cplusplus)
 }
 #endif

tools/include/uapi/linux/bpf.h

@@ -906,6 +906,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_RINGBUF,
 	BPF_MAP_TYPE_INODE_STORAGE,
 	BPF_MAP_TYPE_TASK_STORAGE,
+	BPF_MAP_TYPE_BLOOM_FILTER,
 };
 
 /* Note that tracing related programs such as
@@ -1274,6 +1275,13 @@ union bpf_attr {
 						   * struct stored as the
 						   * map value
 						   */
+		/* Any per-map-type extra fields
+		 *
+		 * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
+		 * number of hash functions (if 0, the bloom filter will default
+		 * to using 5 hash functions).
+		 */
+		__u64	map_extra;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -1334,8 +1342,10 @@ union bpf_attr {
 			/* or valid module BTF object fd or 0 to attach to vmlinux */
 			__u32		attach_btf_obj_fd;
 		};
-		__u32		:32;		/* pad */
+		__u32		core_relo_cnt;	/* number of bpf_core_relo */
 		__aligned_u64	fd_array;	/* array of FDs */
+		__aligned_u64	core_relos;
+		__u32		core_relo_rec_size; /* sizeof(struct bpf_core_relo) */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -1629,7 +1639,7 @@ union bpf_attr {
  * u32 bpf_get_smp_processor_id(void)
  * 	Description
  * 		Get the SMP (symmetric multiprocessing) processor id. Note that
- * 		all programs run with preemption disabled, which means that the
+ * 		all programs run with migration disabled, which means that the
  * 		SMP processor id is stable during all the execution of the
  * 		program.
  * 	Return
@@ -1736,7 +1746,7 @@ union bpf_attr {
  * 		if the maximum number of tail calls has been reached for this
  * 		chain of programs. This limit is defined in the kernel by the
  * 		macro **MAX_TAIL_CALL_CNT** (not accessible to user space),
- * 		which is currently set to 32.
+ *		which is currently set to 33.
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
@@ -4046,7 +4056,7 @@ union bpf_attr {
  * 		arguments. The *data* are a **u64** array and corresponding format string
  * 		values are stored in the array. For strings and pointers where pointees
  * 		are accessed, only the pointer values are stored in the *data* array.
- * 		The *data_len* is the size of *data* in bytes.
+ * 		The *data_len* is the size of *data* in bytes - must be a multiple of 8.
  *
  *		Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
  *		Reading kernel memory may fail due to either invalid address or
@@ -4751,7 +4761,8 @@ union bpf_attr {
  *		Each format specifier in **fmt** corresponds to one u64 element
  *		in the **data** array. For strings and pointers where pointees
  *		are accessed, only the pointer values are stored in the *data*
- *		array. The *data_len* is the size of *data* in bytes.
+ *		array. The *data_len* is the size of *data* in bytes - must be
+ *		a multiple of 8.
  *
  *		Formats **%s** and **%p{i,I}{4,6}** require to read kernel
  *		memory. Reading kernel memory may fail due to either invalid
@@ -4877,6 +4888,136 @@ union bpf_attr {
  *		Get the struct pt_regs associated with **task**.
  *	Return
  *		A pointer to struct pt_regs.
+ *
+ * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags)
+ *	Description
+ *		Get branch trace from hardware engines like Intel LBR. The
+ *		hardware engine is stopped shortly after the helper is
+ *		called. Therefore, the user need to filter branch entries
+ *		based on the actual use case. To capture branch trace
+ *		before the trigger point of the BPF program, the helper
+ *		should be called at the beginning of the BPF program.
+ *
+ *		The data is stored as struct perf_branch_entry into output
+ *		buffer *entries*. *size* is the size of *entries* in bytes.
+ *		*flags* is reserved for now and must be zero.
+ *
+ *	Return
+ *		On success, number of bytes written to *buf*. On error, a
+ *		negative value.
+ *
+ *		**-EINVAL** if *flags* is not zero.
+ *
+ *		**-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ *	Description
+ *		Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64
+ *		to format and can handle more format args as a result.
+ *
+ *		Arguments are to be used as in **bpf_seq_printf**\ () helper.
+ *	Return
+ *		The number of bytes written to the buffer, or a negative error
+ *		in case of failure.
+ *
+ * struct unix_sock *bpf_skc_to_unix_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *unix_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res)
+ *	Description
+ *		Get the address of a kernel symbol, returned in *res*. *res* is
+ *		set to 0 if the symbol is not found.
+ *	Return
+ *		On success, zero. On error, a negative value.
+ *
+ *		**-EINVAL** if *flags* is not zero.
+ *
+ *		**-EINVAL** if string *name* is not the same size as *name_sz*.
+ *
+ *		**-ENOENT** if symbol is not found.
+ *
+ *		**-EPERM** if caller does not have permission to obtain kernel address.
+ *
+ * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags)
+ *	Description
+ *		Find vma of *task* that contains *addr*, call *callback_fn*
+ *		function with *task*, *vma*, and *callback_ctx*.
+ *		The *callback_fn* should be a static function and
+ *		the *callback_ctx* should be a pointer to the stack.
+ *		The *flags* is used to control certain aspects of the helper.
+ *		Currently, the *flags* must be 0.
+ *
+ *		The expected callback signature is
+ *
+ *		long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx);
+ *
+ *	Return
+ *		0 on success.
+ *		**-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
+ *		**-EBUSY** if failed to try lock mmap_lock.
+ *		**-EINVAL** for invalid **flags**.
+ *
+ * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags)
+ *	Description
+ *		For **nr_loops**, call **callback_fn** function
+ *		with **callback_ctx** as the context parameter.
+ *		The **callback_fn** should be a static function and
+ *		the **callback_ctx** should be a pointer to the stack.
+ *		The **flags** is used to control certain aspects of the helper.
+ *		Currently, the **flags** must be 0. Currently, nr_loops is
+ *		limited to 1 << 23 (~8 million) loops.
+ *
+ *		long (\*callback_fn)(u32 index, void \*ctx);
+ *
+ *		where **index** is the current index in the loop. The index
+ *		is zero-indexed.
+ *
+ *		If **callback_fn** returns 0, the helper will continue to the next
+ *		loop. If return value is 1, the helper will skip the rest of
+ *		the loops and return. Other return values are not used now,
+ *		and will be rejected by the verifier.
+ *
+ *	Return
+ *		The number of loops performed, **-EINVAL** for invalid **flags**,
+ *		**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ *	Description
+ *		Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ *		to be null-terminated and **s1_sz** is the maximum storage
+ *		size of **s1**. **s2** must be a read-only string.
+ *	Return
+ *		An integer less than, equal to, or greater than zero
+ *		if the first **s1_sz** bytes of **s1** is found to be
+ *		less than, to match, or be greater than **s2**.
+ *
+ * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
+ *	Description
+ *		Get **n**-th argument (zero based) of the traced function (for tracing programs)
+ *		returned in **value**.
+ *
+ *	Return
+ *		0 on success.
+ *		**-EINVAL** if n >= arguments count of traced function.
+ *
+ * long bpf_get_func_ret(void *ctx, u64 *value)
+ *	Description
+ *		Get return value of the traced function (for tracing programs)
+ *		in **value**.
+ *
+ *	Return
+ *		0 on success.
+ *		**-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ *
+ * long bpf_get_func_arg_cnt(void *ctx)
+ *	Description
+ *		Get number of arguments of the traced function (for tracing programs).
+ *
+ *	Return
+ *		The number of arguments of the traced function.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5055,6 +5196,16 @@ union bpf_attr {
 	FN(get_func_ip),		\
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
+	FN(get_branch_snapshot),	\
+	FN(trace_vprintk),		\
+	FN(skc_to_unix_sock),		\
+	FN(kallsyms_lookup_name),	\
+	FN(find_vma),			\
+	FN(loop),			\
+	FN(strncmp),			\
+	FN(get_func_arg),		\
+	FN(get_func_ret),		\
+	FN(get_func_arg_cnt),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5284,6 +5435,8 @@ struct __sk_buff {
 	__u32 gso_segs;
 	__bpf_md_ptr(struct bpf_sock *, sk);
 	__u32 gso_size;
+	__u32 :32;		/* Padding, future use. */
+	__u64 hwtstamp;
 };
 
 struct bpf_tunnel_key {
@@ -5577,6 +5730,7 @@ struct bpf_prog_info {
 	__u64 run_time_ns;
 	__u64 run_cnt;
 	__u64 recursion_misses;
+	__u32 verified_insns;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -5594,6 +5748,8 @@ struct bpf_map_info {
 	__u32 btf_id;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
+	__u32 :32;	/* alignment pad */
+	__u64 map_extra;
 } __attribute__((aligned(8)));
 
 struct bpf_btf_info {
@@ -6226,6 +6382,7 @@ struct bpf_sk_lookup {
 	__u32 local_ip4;	/* Network byte order */
 	__u32 local_ip6[4];	/* Network byte order */
 	__u32 local_port;	/* Host byte order */
+	__u32 ingress_ifindex;		/* The arriving interface. Determined by inet_iif. */
 };
 
 /*
@@ -6258,4 +6415,78 @@ enum {
 	BTF_F_ZERO	=	(1ULL << 3),
 };
 
+/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
+ * has to be adjusted by relocations. It is emitted by llvm and passed to
+ * libbpf and later to the kernel.
+ */
+enum bpf_core_relo_kind {
+	BPF_CORE_FIELD_BYTE_OFFSET = 0,      /* field byte offset */
+	BPF_CORE_FIELD_BYTE_SIZE = 1,        /* field size in bytes */
+	BPF_CORE_FIELD_EXISTS = 2,           /* field existence in target kernel */
+	BPF_CORE_FIELD_SIGNED = 3,           /* field signedness (0 - unsigned, 1 - signed) */
+	BPF_CORE_FIELD_LSHIFT_U64 = 4,       /* bitfield-specific left bitshift */
+	BPF_CORE_FIELD_RSHIFT_U64 = 5,       /* bitfield-specific right bitshift */
+	BPF_CORE_TYPE_ID_LOCAL = 6,          /* type ID in local BPF object */
+	BPF_CORE_TYPE_ID_TARGET = 7,         /* type ID in target kernel */
+	BPF_CORE_TYPE_EXISTS = 8,            /* type existence in target kernel */
+	BPF_CORE_TYPE_SIZE = 9,              /* type size in bytes */
+	BPF_CORE_ENUMVAL_EXISTS = 10,        /* enum value existence in target kernel */
+	BPF_CORE_ENUMVAL_VALUE = 11,         /* enum value integer value */
+};
+
+/*
+ * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf
+ * and from libbpf to the kernel.
+ *
+ * CO-RE relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ *   its insn->imm field to be relocated with actual field info;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ *   type or field;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ *   interpretation depends on specific relocation kind:
+ *     - for field-based relocations, string encodes an accessed field using
+ *       a sequence of field and array indices, separated by colon (:). It's
+ *       conceptually very close to LLVM's getelementptr ([0]) instruction's
+ *       arguments for identifying offset to a field.
+ *     - for type-based relocations, strings is expected to be just "0";
+ *     - for enum value-based relocations, string contains an index of enum
+ *       value within its enum type;
+ * - kind - one of enum bpf_core_relo_kind;
+ *
+ * Example:
+ *   struct sample {
+ *       int a;
+ *       struct {
+ *           int b[10];
+ *       };
+ *   };
+ *
+ *   struct sample *s = ...;
+ *   int *x = &s->a;     // encoded as "0:0" (a is field #0)
+ *   int *y = &s->b[5];  // encoded as "0:1:0:5" (anon struct is field #1,
+ *                       // b is field #0 inside anon struct, accessing elem #5)
+ *   int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ *		  __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit field relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_core_relo {
+	__u32 insn_off;
+	__u32 type_id;
+	__u32 access_str_off;
+	enum bpf_core_relo_kind kind;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */

tools/include/uapi/linux/btf.h

@@ -43,7 +43,7 @@ struct btf_type {
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC, FUNC_PROTO and VAR.
+	 * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -56,25 +56,30 @@ struct btf_type {
 #define BTF_INFO_VLEN(info)	((info) & 0xffff)
 #define BTF_INFO_KFLAG(info)	((info) >> 31)
 
-#define BTF_KIND_UNKN		0	/* Unknown	*/
-#define BTF_KIND_INT		1	/* Integer	*/
-#define BTF_KIND_PTR		2	/* Pointer	*/
-#define BTF_KIND_ARRAY		3	/* Array	*/
-#define BTF_KIND_STRUCT		4	/* Struct	*/
-#define BTF_KIND_UNION		5	/* Union	*/
-#define BTF_KIND_ENUM		6	/* Enumeration	*/
-#define BTF_KIND_FWD		7	/* Forward	*/
-#define BTF_KIND_TYPEDEF	8	/* Typedef	*/
-#define BTF_KIND_VOLATILE	9	/* Volatile	*/
-#define BTF_KIND_CONST		10	/* Const	*/
-#define BTF_KIND_RESTRICT	11	/* Restrict	*/
-#define BTF_KIND_FUNC		12	/* Function	*/
-#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
-#define BTF_KIND_VAR		14	/* Variable	*/
-#define BTF_KIND_DATASEC	15	/* Section	*/
-#define BTF_KIND_FLOAT		16	/* Floating point	*/
-#define BTF_KIND_MAX		BTF_KIND_FLOAT
-#define NR_BTF_KINDS		(BTF_KIND_MAX + 1)
+enum {
+	BTF_KIND_UNKN		= 0,	/* Unknown	*/
+	BTF_KIND_INT		= 1,	/* Integer	*/
+	BTF_KIND_PTR		= 2,	/* Pointer	*/
+	BTF_KIND_ARRAY		= 3,	/* Array	*/
+	BTF_KIND_STRUCT		= 4,	/* Struct	*/
+	BTF_KIND_UNION		= 5,	/* Union	*/
+	BTF_KIND_ENUM		= 6,	/* Enumeration	*/
+	BTF_KIND_FWD		= 7,	/* Forward	*/
+	BTF_KIND_TYPEDEF	= 8,	/* Typedef	*/
+	BTF_KIND_VOLATILE	= 9,	/* Volatile	*/
+	BTF_KIND_CONST		= 10,	/* Const	*/
+	BTF_KIND_RESTRICT	= 11,	/* Restrict	*/
+	BTF_KIND_FUNC		= 12,	/* Function	*/
+	BTF_KIND_FUNC_PROTO	= 13,	/* Function Proto	*/
+	BTF_KIND_VAR		= 14,	/* Variable	*/
+	BTF_KIND_DATASEC	= 15,	/* Section	*/
+	BTF_KIND_FLOAT		= 16,	/* Floating point	*/
+	BTF_KIND_DECL_TAG	= 17,	/* Decl Tag */
+	BTF_KIND_TYPE_TAG	= 18,	/* Type Tag */
+
+	NR_BTF_KINDS,
+	BTF_KIND_MAX		= NR_BTF_KINDS - 1,
+};
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -170,4 +175,15 @@ struct btf_var_secinfo {
 	__u32	size;
 };
 
+/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe
+ * additional information related to the tag applied location.
+ * If component_idx == -1, the tag is applied to a struct, union,
+ * variable or function. Otherwise, it is applied to a struct/union
+ * member or a func argument, and component_idx indicates which member
+ * or argument (0 ... vlen-1).
+ */
+struct btf_decl_tag {
+       __s32   component_idx;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */

tools/include/uapi/linux/if_link.h

@@ -7,24 +7,23 @@
 
 /* This struct should be in sync with struct rtnl_link_stats64 */
 struct rtnl_link_stats {
-	__u32	rx_packets;		/* total packets received	*/
-	__u32	tx_packets;		/* total packets transmitted	*/
-	__u32	rx_bytes;		/* total bytes received 	*/
-	__u32	tx_bytes;		/* total bytes transmitted	*/
-	__u32	rx_errors;		/* bad packets received		*/
-	__u32	tx_errors;		/* packet transmit problems	*/
-	__u32	rx_dropped;		/* no space in linux buffers	*/
-	__u32	tx_dropped;		/* no space available in linux	*/
-	__u32	multicast;		/* multicast packets received	*/
+	__u32	rx_packets;
+	__u32	tx_packets;
+	__u32	rx_bytes;
+	__u32	tx_bytes;
+	__u32	rx_errors;
+	__u32	tx_errors;
+	__u32	rx_dropped;
+	__u32	tx_dropped;
+	__u32	multicast;
 	__u32	collisions;
-
 	/* detailed rx_errors: */
 	__u32	rx_length_errors;
-	__u32	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u32	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u32	rx_frame_errors;	/* recv'd frame alignment error */
-	__u32	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u32	rx_missed_errors;	/* receiver missed packet	*/
+	__u32	rx_over_errors;
+	__u32	rx_crc_errors;
+	__u32	rx_frame_errors;
+	__u32	rx_fifo_errors;
+	__u32	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u32	tx_aborted_errors;
@@ -37,29 +36,201 @@ struct rtnl_link_stats {
 	__u32	rx_compressed;
 	__u32	tx_compressed;
 
-	__u32	rx_nohandler;		/* dropped, no handler found	*/
+	__u32	rx_nohandler;
 };
 
-/* The main device statistics structure */
+/**
+ * struct rtnl_link_stats64 - The main device statistics structure.
+ *
+ * @rx_packets: Number of good packets received by the interface.
+ *   For hardware interfaces counts all good packets received from the device
+ *   by the host, including packets which host had to drop at various stages
+ *   of processing (even in the driver).
+ *
+ * @tx_packets: Number of packets successfully transmitted.
+ *   For hardware interfaces counts packets which host was able to successfully
+ *   hand over to the device, which does not necessarily mean that packets
+ *   had been successfully transmitted out of the device, only that device
+ *   acknowledged it copied them out of host memory.
+ *
+ * @rx_bytes: Number of good received bytes, corresponding to @rx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @rx_errors: Total number of bad packets received on this network device.
+ *   This counter must include events counted by @rx_length_errors,
+ *   @rx_crc_errors, @rx_frame_errors and other errors not otherwise
+ *   counted.
+ *
+ * @tx_errors: Total number of transmit problems.
+ *   This counter must include events counter by @tx_aborted_errors,
+ *   @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors,
+ *   @tx_window_errors and other errors not otherwise counted.
+ *
+ * @rx_dropped: Number of packets received but not processed,
+ *   e.g. due to lack of resources or unsupported protocol.
+ *   For hardware interfaces this counter may include packets discarded
+ *   due to L2 address filtering but should not include packets dropped
+ *   by the device due to buffer exhaustion which are counted separately in
+ *   @rx_missed_errors (since procfs folds those two counters together).
+ *
+ * @tx_dropped: Number of packets dropped on their way to transmission,
+ *   e.g. due to lack of resources.
+ *
+ * @multicast: Multicast packets received.
+ *   For hardware interfaces this statistic is commonly calculated
+ *   at the device level (unlike @rx_packets) and therefore may include
+ *   packets which did not reach the host.
+ *
+ *   For IEEE 802.3 devices this counter may be equivalent to:
+ *
+ *    - 30.3.1.1.21 aMulticastFramesReceivedOK
+ *
+ * @collisions: Number of collisions during packet transmissions.
+ *
+ * @rx_length_errors: Number of packets dropped due to invalid length.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to a sum
+ *   of the following attributes:
+ *
+ *    - 30.3.1.1.23 aInRangeLengthErrors
+ *    - 30.3.1.1.24 aOutOfRangeLengthField
+ *    - 30.3.1.1.25 aFrameTooLongErrors
+ *
+ * @rx_over_errors: Receiver FIFO overflow event counter.
+ *
+ *   Historically the count of overflow events. Such events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   The recommended interpretation for high speed interfaces is -
+ *   number of packets dropped because they did not fit into buffers
+ *   provided by the host, e.g. packets larger than MTU or next buffer
+ *   in the ring was not available for a scatter transfer.
+ *
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   This statistics was historically used interchangeably with
+ *   @rx_fifo_errors.
+ *
+ *   This statistic corresponds to hardware events and is not commonly used
+ *   on software devices.
+ *
+ * @rx_crc_errors: Number of packets received with a CRC error.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.6 aFrameCheckSequenceErrors
+ *
+ * @rx_frame_errors: Receiver frame alignment errors.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to:
+ *
+ *    - 30.3.1.1.7 aAlignmentErrors
+ *
+ * @rx_fifo_errors: Receiver FIFO error counter.
+ *
+ *   Historically the count of overflow events. Those events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   This statistics was used interchangeably with @rx_over_errors.
+ *   Not recommended for use in drivers for high speed interfaces.
+ *
+ *   This statistic is used on software devices, e.g. to count software
+ *   packet queue overflow (can) or sequencing errors (GRE).
+ *
+ * @rx_missed_errors: Count of packets missed by the host.
+ *   Folded into the "drop" counter in `/proc/net/dev`.
+ *
+ *   Counts number of packets dropped by the device due to lack
+ *   of buffer space. This usually indicates that the host interface
+ *   is slower than the network interface, or host is not keeping up
+ *   with the receive packet rate.
+ *
+ *   This statistic corresponds to hardware events and is not used
+ *   on software devices.
+ *
+ * @tx_aborted_errors:
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *   For IEEE 802.3 devices capable of half-duplex operation this counter
+ *   must be equivalent to:
+ *
+ *    - 30.3.1.1.11 aFramesAbortedDueToXSColls
+ *
+ *   High speed interfaces may use this counter as a general device
+ *   discard counter.
+ *
+ * @tx_carrier_errors: Number of frame transmission errors due to loss
+ *   of carrier during transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.13 aCarrierSenseErrors
+ *
+ * @tx_fifo_errors: Number of frame transmission errors due to device
+ *   FIFO underrun / underflow. This condition occurs when the device
+ *   begins transmission of a frame but is unable to deliver the
+ *   entire frame to the transmitter in time for transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for
+ *   old half-duplex Ethernet.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices possibly equivalent to:
+ *
+ *    - 30.3.2.1.4 aSQETestErrors
+ *
+ * @tx_window_errors: Number of frame transmission errors due
+ *   to late collisions (for Ethernet - after the first 64B of transmission).
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.10 aLateCollisions
+ *
+ * @rx_compressed: Number of correctly received compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @tx_compressed: Number of transmitted compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @rx_nohandler: Number of packets received on the interface
+ *   but dropped by the networking stack because the device is
+ *   not designated to receive packets (e.g. backup link in a bond).
+ */
 struct rtnl_link_stats64 {
-	__u64	rx_packets;		/* total packets received	*/
-	__u64	tx_packets;		/* total packets transmitted	*/
-	__u64	rx_bytes;		/* total bytes received 	*/
-	__u64	tx_bytes;		/* total bytes transmitted	*/
-	__u64	rx_errors;		/* bad packets received		*/
-	__u64	tx_errors;		/* packet transmit problems	*/
-	__u64	rx_dropped;		/* no space in linux buffers	*/
-	__u64	tx_dropped;		/* no space available in linux	*/
-	__u64	multicast;		/* multicast packets received	*/
+	__u64	rx_packets;
+	__u64	tx_packets;
+	__u64	rx_bytes;
+	__u64	tx_bytes;
+	__u64	rx_errors;
+	__u64	tx_errors;
+	__u64	rx_dropped;
+	__u64	tx_dropped;
+	__u64	multicast;
 	__u64	collisions;
 
 	/* detailed rx_errors: */
 	__u64	rx_length_errors;
-	__u64	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u64	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u64	rx_frame_errors;	/* recv'd frame alignment error */
-	__u64	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u64	rx_missed_errors;	/* receiver missed packet	*/
+	__u64	rx_over_errors;
+	__u64	rx_crc_errors;
+	__u64	rx_frame_errors;
+	__u64	rx_fifo_errors;
+	__u64	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u64	tx_aborted_errors;
@@ -71,8 +242,7 @@ struct rtnl_link_stats64 {
 	/* for cslip etc */
 	__u64	rx_compressed;
 	__u64	tx_compressed;
-
-	__u64	rx_nohandler;		/* dropped, no handler found	*/
+	__u64	rx_nohandler;
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -170,12 +340,30 @@ enum {
 	IFLA_PROP_LIST,
 	IFLA_ALT_IFNAME, /* Alternative ifname */
 	IFLA_PERM_ADDRESS,
+	IFLA_PROTO_DOWN_REASON,
+
+	/* device (sysfs) name as parent, used instead
+	 * of IFLA_LINK where there's no parent netdev
+	 */
+	IFLA_PARENT_DEV_NAME,
+	IFLA_PARENT_DEV_BUS_NAME,
+	IFLA_GRO_MAX_SIZE,
+
 	__IFLA_MAX
 };
 
 
 #define IFLA_MAX (__IFLA_MAX - 1)
 
+enum {
+	IFLA_PROTO_DOWN_REASON_UNSPEC,
+	IFLA_PROTO_DOWN_REASON_MASK,	/* u32, mask for reason bits */
+	IFLA_PROTO_DOWN_REASON_VALUE,   /* u32, reason bit value */
+
+	__IFLA_PROTO_DOWN_REASON_CNT,
+	IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1
+};
+
 /* backwards compatibility for userspace */
 #ifndef __KERNEL__
 #define IFLA_RTA(r)  ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
@@ -293,6 +481,7 @@ enum {
 	IFLA_BR_MCAST_MLD_VERSION,
 	IFLA_BR_VLAN_STATS_PER_PORT,
 	IFLA_BR_MULTI_BOOLOPT,
+	IFLA_BR_MCAST_QUERIER_STATE,
 	__IFLA_BR_MAX,
 };
 
@@ -346,6 +535,8 @@ enum {
 	IFLA_BRPORT_BACKUP_PORT,
 	IFLA_BRPORT_MRP_RING_OPEN,
 	IFLA_BRPORT_MRP_IN_OPEN,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -433,6 +624,7 @@ enum macvlan_macaddr_mode {
 };
 
 #define MACVLAN_FLAG_NOPROMISC	1
+#define MACVLAN_FLAG_NODST	2 /* skip dst macvlan if matching src macvlan */
 
 /* VRF section */
 enum {
@@ -597,6 +789,18 @@ enum ifla_geneve_df {
 	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
 };
 
+/* Bareudp section  */
+enum {
+	IFLA_BAREUDP_UNSPEC,
+	IFLA_BAREUDP_PORT,
+	IFLA_BAREUDP_ETHERTYPE,
+	IFLA_BAREUDP_SRCPORT_MIN,
+	IFLA_BAREUDP_MULTIPROTO_MODE,
+	__IFLA_BAREUDP_MAX
+};
+
+#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1)
+
 /* PPP section */
 enum {
 	IFLA_PPP_UNSPEC,
@@ -655,6 +859,7 @@ enum {
 	IFLA_BOND_TLB_DYNAMIC_LB,
 	IFLA_BOND_PEER_NOTIF_DELAY,
 	IFLA_BOND_AD_LACP_ACTIVE,
+	IFLA_BOND_MISSED_MAX,
 	__IFLA_BOND_MAX,
 };
 
@@ -899,7 +1104,14 @@ enum {
 #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
 
 
-/* HSR section */
+/* HSR/PRP section, both uses same interface */
+
+/* Different redundancy protocols for hsr device */
+enum {
+	HSR_PROTOCOL_HSR,
+	HSR_PROTOCOL_PRP,
+	HSR_PROTOCOL_MAX,
+};
 
 enum {
 	IFLA_HSR_UNSPEC,
@@ -909,6 +1121,9 @@ enum {
 	IFLA_HSR_SUPERVISION_ADDR,	/* Supervision frame multicast addr */
 	IFLA_HSR_SEQ_NR,
 	IFLA_HSR_VERSION,		/* HSR version */
+	IFLA_HSR_PROTOCOL,		/* Indicate different protocol than
+					 * HSR. For example PRP.
+					 */
 	__IFLA_HSR_MAX,
 };
 
@@ -1033,6 +1248,8 @@ enum {
 #define RMNET_FLAGS_INGRESS_MAP_COMMANDS          (1U << 1)
 #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4           (1U << 2)
 #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4            (1U << 3)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5           (1U << 4)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5            (1U << 5)
 
 enum {
 	IFLA_RMNET_UNSPEC,
@@ -1048,4 +1265,14 @@ struct ifla_rmnet_flags {
 	__u32	mask;
 };
 
+/* MCTP section */
+
+enum {
+	IFLA_MCTP_UNSPEC,
+	IFLA_MCTP_NET,
+	__IFLA_MCTP_MAX,
+};
+
+#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */

tools/include/uapi/linux/kvm.h

@@ -269,6 +269,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_AP_RESET_HOLD    32
 #define KVM_EXIT_X86_BUS_LOCK     33
 #define KVM_EXIT_XEN              34
+#define KVM_EXIT_RISCV_SBI        35
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -397,13 +398,23 @@ struct kvm_run {
 		 * "ndata" is correct, that new fields are enumerated in "flags",
 		 * and that each flag enumerates fields that are 64-bit aligned
 		 * and sized (so that ndata+internal.data[] is valid/accurate).
+		 *
+		 * Space beyond the defined fields may be used to store arbitrary
+		 * debug information relating to the emulation failure. It is
+		 * accounted for in "ndata" but the format is unspecified and is
+		 * not represented in "flags". Any such information is *not* ABI!
 		 */
 		struct {
 			__u32 suberror;
 			__u32 ndata;
 			__u64 flags;
-			__u8  insn_size;
-			__u8  insn_bytes[15];
+			union {
+				struct {
+					__u8  insn_size;
+					__u8  insn_bytes[15];
+				};
+			};
+			/* Arbitrary debug data may follow. */
 		} emulation_failure;
 		/* KVM_EXIT_OSI */
 		struct {
@@ -469,6 +480,13 @@ struct kvm_run {
 		} msr;
 		/* KVM_EXIT_XEN */
 		struct kvm_xen_exit xen;
+		/* KVM_EXIT_RISCV_SBI */
+		struct {
+			unsigned long extension_id;
+			unsigned long function_id;
+			unsigned long args[6];
+			unsigned long ret[2];
+		} riscv_sbi;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1112,6 +1130,11 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_BINARY_STATS_FD 203
 #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
 #define KVM_CAP_ARM_MTE 205
+#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
+#define KVM_CAP_VM_GPA_BITS 207
+#define KVM_CAP_XSAVE2 208
+#define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_PPC_AIL_MODE_3 210
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1143,11 +1166,20 @@ struct kvm_irq_routing_hv_sint {
 	__u32 sint;
 };
 
+struct kvm_irq_routing_xen_evtchn {
+	__u32 port;
+	__u32 vcpu;
+	__u32 priority;
+};
+
+#define KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL ((__u32)(-1))
+
 /* gsi routing entry types */
 #define KVM_IRQ_ROUTING_IRQCHIP 1
 #define KVM_IRQ_ROUTING_MSI 2
 #define KVM_IRQ_ROUTING_S390_ADAPTER 3
 #define KVM_IRQ_ROUTING_HV_SINT 4
+#define KVM_IRQ_ROUTING_XEN_EVTCHN 5
 
 struct kvm_irq_routing_entry {
 	__u32 gsi;
@@ -1159,6 +1191,7 @@ struct kvm_irq_routing_entry {
 		struct kvm_irq_routing_msi msi;
 		struct kvm_irq_routing_s390_adapter adapter;
 		struct kvm_irq_routing_hv_sint hv_sint;
+		struct kvm_irq_routing_xen_evtchn xen_evtchn;
 		__u32 pad[8];
 	} u;
 };
@@ -1189,6 +1222,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL	(1 << 1)
 #define KVM_XEN_HVM_CONFIG_SHARED_INFO		(1 << 2)
 #define KVM_XEN_HVM_CONFIG_RUNSTATE		(1 << 3)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1223,11 +1257,16 @@ struct kvm_irqfd {
 
 /* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags.  */
 #define KVM_CLOCK_TSC_STABLE		2
+#define KVM_CLOCK_REALTIME		(1 << 2)
+#define KVM_CLOCK_HOST_TSC		(1 << 3)
 
 struct kvm_clock_data {
 	__u64 clock;
 	__u32 flags;
-	__u32 pad[9];
+	__u32 pad0;
+	__u64 realtime;
+	__u64 host_tsc;
+	__u32 pad[4];
 };
 
 /* For KVM_CAP_SW_TLB */
@@ -2007,4 +2046,7 @@ struct kvm_stats_desc {
 
 #define KVM_GET_STATS_FD  _IO(KVMIO,  0xce)
 
+/* Available with KVM_CAP_XSAVE2 */
+#define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
+
 #endif /* __LINUX_KVM_H */

tools/include/uapi/linux/perf_event.h

@@ -465,6 +465,8 @@ struct perf_event_attr {
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
 	 * siginfo_t::si_perf_data, e.g. to permit user to identify the event.
+	 * Note, siginfo_t::si_perf_data is long-sized, and sig_data will be
+	 * truncated accordingly on 32 bit architectures.
 	 */
 	__u64	sig_data;
 };
@@ -1141,6 +1143,21 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_TEXT_POKE			= 20,
 
+	/*
+	 * Data written to the AUX area by hardware due to aux_output, may need
+	 * to be matched to the event by an architecture-specific hardware ID.
+	 * This records the hardware ID, but requires sample_id to provide the
+	 * event ID. e.g. Intel PT uses this record to disambiguate PEBS-via-PT
+	 * records from multiple events.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				hw_id;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_AUX_OUTPUT_HW_ID		= 21,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
@@ -1210,14 +1227,16 @@ union perf_mem_data_src {
 			mem_remote:1,   /* remote */
 			mem_snoopx:2,	/* snoop mode, ext */
 			mem_blk:3,	/* access blocked */
-			mem_rsvd:21;
+			mem_hops:3,	/* hop level */
+			mem_rsvd:18;
 	};
 };
 #elif defined(__BIG_ENDIAN_BITFIELD)
 union perf_mem_data_src {
 	__u64 val;
 	struct {
-		__u64	mem_rsvd:21,
+		__u64	mem_rsvd:18,
+			mem_hops:3,	/* hop level */
 			mem_blk:3,	/* access blocked */
 			mem_snoopx:2,	/* snoop mode, ext */
 			mem_remote:1,   /* remote */
@@ -1241,7 +1260,13 @@ union perf_mem_data_src {
 #define PERF_MEM_OP_EXEC	0x10 /* code (execution) */
 #define PERF_MEM_OP_SHIFT	0
 
-/* memory hierarchy (memory level, hit or miss) */
+/*
+ * PERF_MEM_LVL_* namespace being depricated to some extent in the
+ * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields.
+ * Supporting this namespace inorder to not break defined ABIs.
+ *
+ * memory hierarchy (memory level, hit or miss)
+ */
 #define PERF_MEM_LVL_NA		0x01  /* not available */
 #define PERF_MEM_LVL_HIT	0x02  /* hit level */
 #define PERF_MEM_LVL_MISS	0x04  /* miss level  */
@@ -1307,6 +1332,14 @@ union perf_mem_data_src {
 #define PERF_MEM_BLK_ADDR	0x04 /* address conflict */
 #define PERF_MEM_BLK_SHIFT	40
 
+/* hop level */
+#define PERF_MEM_HOPS_0		0x01 /* remote core, same node */
+#define PERF_MEM_HOPS_1		0x02 /* remote node, same socket */
+#define PERF_MEM_HOPS_2		0x03 /* remote socket, same board */
+#define PERF_MEM_HOPS_3		0x04 /* remote board */
+/* 5-7 available */
+#define PERF_MEM_HOPS_SHIFT	43
+
 #define PERF_MEM_S(a, s) \
 	(((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
 

tools/include/uapi/linux/prctl.h

@@ -235,7 +235,7 @@ struct prctl_mm_map {
 #define PR_GET_TAGGED_ADDR_CTRL		56
 # define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
 /* MTE tag check fault modes */
-# define PR_MTE_TCF_NONE		0
+# define PR_MTE_TCF_NONE		0UL
 # define PR_MTE_TCF_SYNC		(1UL << 1)
 # define PR_MTE_TCF_ASYNC		(1UL << 2)
 # define PR_MTE_TCF_MASK		(PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC)
@@ -268,5 +268,11 @@ struct prctl_mm_map {
 # define PR_SCHED_CORE_SHARE_TO		2 /* push core_sched cookie to pid */
 # define PR_SCHED_CORE_SHARE_FROM	3 /* pull core_sched cookie to pid */
 # define PR_SCHED_CORE_MAX		4
+# define PR_SCHED_CORE_SCOPE_THREAD		0
+# define PR_SCHED_CORE_SCOPE_THREAD_GROUP	1
+# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP	2
+
+#define PR_SET_VMA		0x53564d41
+# define PR_SET_VMA_ANON_NAME		0
 
 #endif /* _LINUX_PRCTL_H */

tools/include/uapi/sound/asound.h

@@ -204,6 +204,11 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_S24_BE	((__force snd_pcm_format_t) 7) /* low three bytes */
 #define	SNDRV_PCM_FORMAT_U24_LE	((__force snd_pcm_format_t) 8) /* low three bytes */
 #define	SNDRV_PCM_FORMAT_U24_BE	((__force snd_pcm_format_t) 9) /* low three bytes */
+/*
+ * For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the
+ * available bit count in most significant bit. It's for the case of so-called 'left-justified' or
+ * `right-padding` sample which has less width than 32 bit.
+ */
 #define	SNDRV_PCM_FORMAT_S32_LE	((__force snd_pcm_format_t) 10)
 #define	SNDRV_PCM_FORMAT_S32_BE	((__force snd_pcm_format_t) 11)
 #define	SNDRV_PCM_FORMAT_U32_LE	((__force snd_pcm_format_t) 12)
@@ -302,7 +307,7 @@ typedef int __bitwise snd_pcm_subformat_t;
 #define SNDRV_PCM_INFO_HAS_LINK_ESTIMATED_ATIME    0x04000000  /* report estimated link audio time */
 #define SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME 0x08000000  /* report synchronized audio/system time */
 #define SNDRV_PCM_INFO_EXPLICIT_SYNC	0x10000000	/* needs explicit sync of pointers and data */
-
+#define SNDRV_PCM_INFO_NO_REWINDS	0x20000000	/* hardware can only support monotonic changes of appl_ptr */
 #define SNDRV_PCM_INFO_DRAIN_TRIGGER	0x40000000		/* internal kernel flag - trigger in drain */
 #define SNDRV_PCM_INFO_FIFO_IN_FRAMES	0x80000000	/* internal kernel flag - FIFO size is in frames */
 
@@ -1004,7 +1009,7 @@ typedef int __bitwise snd_ctl_elem_iface_t;
 #define SNDRV_CTL_ELEM_ACCESS_WRITE		(1<<1)
 #define SNDRV_CTL_ELEM_ACCESS_READWRITE		(SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE)
 #define SNDRV_CTL_ELEM_ACCESS_VOLATILE		(1<<2)	/* control value may be changed without a notification */
-// (1 << 3) is unused.
+/* (1 << 3) is unused. */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READ		(1<<4)	/* TLV read is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE		(1<<5)	/* TLV write is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE	(SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE)

tools/lib/bpf/.gitignore

@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-libbpf_version.h
 libbpf.pc
 libbpf.so.*
 TAGS

tools/lib/bpf/Makefile

@@ -8,7 +8,8 @@ VERSION_SCRIPT := libbpf.map
 LIBBPF_VERSION := $(shell \
 	grep -oE '^LIBBPF_([0-9.]+)' $(VERSION_SCRIPT) | \
 	sort -rV | head -n1 | cut -d'_' -f2)
-LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION)))
+LIBBPF_MAJOR_VERSION := $(word 1,$(subst ., ,$(LIBBPF_VERSION)))
+LIBBPF_MINOR_VERSION := $(word 2,$(subst ., ,$(LIBBPF_VERSION)))
 
 MAKEFLAGS += --no-print-directory
 
@@ -59,7 +60,8 @@ ifndef VERBOSE
   VERBOSE = 0
 endif
 
-INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
+INCLUDES = -I$(if $(OUTPUT),$(OUTPUT),.)				\
+	   -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
 
 export prefix libdir src obj
 
@@ -82,11 +84,13 @@ else
 endif
 
 # Append required CFLAGS
+override CFLAGS += -std=gnu89
 override CFLAGS += $(EXTRA_WARNINGS) -Wno-switch-enum
 override CFLAGS += -Werror -Wall
 override CFLAGS += $(INCLUDES)
 override CFLAGS += -fvisibility=hidden
 override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+override CFLAGS += $(CLANG_CROSS_FLAGS)
 
 # flags specific for shared library
 SHLIB_FLAGS := -DSHARED -fPIC
@@ -112,6 +116,7 @@ STATIC_OBJDIR	:= $(OUTPUT)staticobjs/
 BPF_IN_SHARED	:= $(SHARED_OBJDIR)libbpf-in.o
 BPF_IN_STATIC	:= $(STATIC_OBJDIR)libbpf-in.o
 BPF_HELPER_DEFS	:= $(OUTPUT)bpf_helper_defs.h
+BPF_GENERATED	:= $(BPF_HELPER_DEFS)
 
 LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
 LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
@@ -136,25 +141,19 @@ all: fixdep
 
 all_cmd: $(CMD_TARGETS) check
 
-$(BPF_IN_SHARED): force $(BPF_HELPER_DEFS)
+$(BPF_IN_SHARED): force $(BPF_GENERATED)
 	@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
 	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
 	@(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \
 	(diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true
-	@(test -f ../../include/uapi/linux/netlink.h -a -f ../../../include/uapi/linux/netlink.h && ( \
-	(diff -B ../../include/uapi/linux/netlink.h ../../../include/uapi/linux/netlink.h >/dev/null) || \
-	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/netlink.h' differs from latest version at 'include/uapi/linux/netlink.h'" >&2 )) || true
-	@(test -f ../../include/uapi/linux/if_link.h -a -f ../../../include/uapi/linux/if_link.h && ( \
-	(diff -B ../../include/uapi/linux/if_link.h ../../../include/uapi/linux/if_link.h >/dev/null) || \
-	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'" >&2 )) || true
 	@(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \
 	(diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)"
 
-$(BPF_IN_STATIC): force $(BPF_HELPER_DEFS)
+$(BPF_IN_STATIC): force $(BPF_GENERATED)
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
 
 $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
@@ -164,7 +163,7 @@ $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
 $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
 
 $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(VERSION_SCRIPT)
-	$(QUIET_LINK)$(CC) $(LDFLAGS) \
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) \
 		--shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
 		-Wl,--version-script=$(VERSION_SCRIPT) $< -lelf -lz -o $@
 	@ln -sf $(@F) $(OUTPUT)libbpf.so
@@ -179,7 +178,7 @@ $(OUTPUT)libbpf.pc:
 		-e "s|@VERSION@|$(LIBBPF_VERSION)|" \
 		< libbpf.pc.template > $@
 
-check: check_abi
+check: check_abi check_version
 
 check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
 	@if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then	 \
@@ -205,6 +204,21 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
 		exit 1;							 \
 	fi
 
+HDR_MAJ_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MAJOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
+HDR_MIN_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MINOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
+
+check_version: $(VERSION_SCRIPT) libbpf_version.h
+	@if [ "$(HDR_MAJ_VERSION)" != "$(LIBBPF_MAJOR_VERSION)" ]; then        \
+		echo "Error: libbpf major version mismatch detected: "	       \
+		     "'$(HDR_MAJ_VERSION)' != '$(LIBBPF_MAJOR_VERSION)'" >&2;  \
+		exit 1;							       \
+	fi
+	@if [ "$(HDR_MIN_VERSION)" != "$(LIBBPF_MINOR_VERSION)" ]; then	       \
+		echo "Error: libbpf minor version mismatch detected: "	       \
+		     "'$(HDR_MIN_VERSION)' != '$(LIBBPF_MINOR_VERSION)'" >&2;  \
+		exit 1;							       \
+	fi
+
 define do_install_mkdir
 	if [ ! -d '$(DESTDIR_SQ)$1' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1';	\
@@ -223,14 +237,24 @@ install_lib: all_cmd
 		$(call do_install_mkdir,$(libdir_SQ)); \
 		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
-INSTALL_HEADERS = bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \
-		  bpf_helpers.h $(BPF_HELPER_DEFS) bpf_tracing.h	     \
-		  bpf_endian.h bpf_core_read.h skel_internal.h
+SRC_HDRS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h	     \
+	    bpf_helpers.h bpf_tracing.h bpf_endian.h bpf_core_read.h	     \
+	    skel_internal.h libbpf_version.h
+GEN_HDRS := $(BPF_GENERATED)
 
-install_headers: $(BPF_HELPER_DEFS)
-	$(call QUIET_INSTALL, headers)					     \
-		$(foreach hdr,$(INSTALL_HEADERS),			     \
-			$(call do_install,$(hdr),$(prefix)/include/bpf,644);)
+INSTALL_PFX := $(DESTDIR)$(prefix)/include/bpf
+INSTALL_SRC_HDRS := $(addprefix $(INSTALL_PFX)/, $(SRC_HDRS))
+INSTALL_GEN_HDRS := $(addprefix $(INSTALL_PFX)/, $(notdir $(GEN_HDRS)))
+
+$(INSTALL_SRC_HDRS): $(INSTALL_PFX)/%.h: %.h
+	$(call QUIET_INSTALL, $@) \
+		$(call do_install,$<,$(prefix)/include/bpf,644)
+
+$(INSTALL_GEN_HDRS): $(INSTALL_PFX)/%.h: $(OUTPUT)%.h
+	$(call QUIET_INSTALL, $@) \
+		$(call do_install,$<,$(prefix)/include/bpf,644)
+
+install_headers: $(BPF_GENERATED) $(INSTALL_SRC_HDRS) $(INSTALL_GEN_HDRS)
 
 install_pkgconfig: $(PC_FILE)
 	$(call QUIET_INSTALL, $(PC_FILE)) \
@@ -240,12 +264,12 @@ install: install_lib install_pkgconfig install_headers
 
 clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS)		     \
-		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS)		     \
+		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED)		     \
 		$(SHARED_OBJDIR) $(STATIC_OBJDIR)			     \
 		$(addprefix $(OUTPUT),					     \
 			    *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc)
 
-PHONY += force cscope tags
+PHONY += force cscope tags check check_abi check_version
 force:
 
 cscope:

tools/lib/bpf/bpf.c

@@ -28,6 +28,9 @@
 #include <asm/unistd.h>
 #include <errno.h>
 #include <linux/bpf.h>
+#include <linux/filter.h>
+#include <limits.h>
+#include <sys/resource.h>
 #include "bpf.h"
 #include "libbpf.h"
 #include "libbpf_internal.h"
@@ -49,6 +52,12 @@
 #  define __NR_bpf 351
 # elif defined(__arc__)
 #  define __NR_bpf 280
+# elif defined(__mips__) && defined(_ABIO32)
+#  define __NR_bpf 4355
+# elif defined(__mips__) && defined(_ABIN32)
+#  define __NR_bpf 6319
+# elif defined(__mips__) && defined(_ABI64)
+#  define __NR_bpf 5315
 # else
 #  error __NR_bpf not defined. libbpf does not support your arch.
 # endif
@@ -65,133 +74,217 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 	return syscall(__NR_bpf, cmd, attr, size);
 }
 
-static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size)
+static inline int sys_bpf_fd(enum bpf_cmd cmd, union bpf_attr *attr,
+			     unsigned int size)
+{
+	int fd;
+
+	fd = sys_bpf(cmd, attr, size);
+	return ensure_good_fd(fd);
+}
+
+#define PROG_LOAD_ATTEMPTS 5
+
+static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
 {
-	int retries = 5;
 	int fd;
 
 	do {
-		fd = sys_bpf(BPF_PROG_LOAD, attr, size);
-	} while (fd < 0 && errno == EAGAIN && retries-- > 0);
+		fd = sys_bpf_fd(BPF_PROG_LOAD, attr, size);
+	} while (fd < 0 && errno == EAGAIN && --attempts > 0);
 
 	return fd;
 }
 
-int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
+/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to
+ * memcg-based memory accounting for BPF maps and progs. This was done in [0].
+ * We use the support for bpf_ktime_get_coarse_ns() helper, which was added in
+ * the same 5.11 Linux release ([1]), to detect memcg-based accounting for BPF.
+ *
+ *   [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/
+ *   [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper")
+ */
+int probe_memcg_account(void)
 {
+	const size_t prog_load_attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
+	struct bpf_insn insns[] = {
+		BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns),
+		BPF_EXIT_INSN(),
+	};
+	size_t insn_cnt = sizeof(insns) / sizeof(insns[0]);
+	union bpf_attr attr;
+	int prog_fd;
+
+	/* attempt loading freplace trying to use custom BTF */
+	memset(&attr, 0, prog_load_attr_sz);
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.insns = ptr_to_u64(insns);
+	attr.insn_cnt = insn_cnt;
+	attr.license = ptr_to_u64("GPL");
+
+	prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, prog_load_attr_sz);
+	if (prog_fd >= 0) {
+		close(prog_fd);
+		return 1;
+	}
+	return 0;
+}
+
+static bool memlock_bumped;
+static rlim_t memlock_rlim = RLIM_INFINITY;
+
+int libbpf_set_memlock_rlim(size_t memlock_bytes)
+{
+	if (memlock_bumped)
+		return libbpf_err(-EBUSY);
+
+	memlock_rlim = memlock_bytes;
+	return 0;
+}
+
+int bump_rlimit_memlock(void)
+{
+	struct rlimit rlim;
+
+	/* this the default in libbpf 1.0, but for now user has to opt-in explicitly */
+	if (!(libbpf_mode & LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK))
+		return 0;
+
+	/* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */
+	if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT))
+		return 0;
+
+	memlock_bumped = true;
+
+	/* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */
+	if (memlock_rlim == 0)
+		return 0;
+
+	rlim.rlim_cur = rlim.rlim_max = memlock_rlim;
+	if (setrlimit(RLIMIT_MEMLOCK, &rlim))
+		return -errno;
+
+	return 0;
+}
+
+int bpf_map_create(enum bpf_map_type map_type,
+		   const char *map_name,
+		   __u32 key_size,
+		   __u32 value_size,
+		   __u32 max_entries,
+		   const struct bpf_map_create_opts *opts)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, '\0', sizeof(attr));
+	bump_rlimit_memlock();
 
-	attr.map_type = create_attr->map_type;
-	attr.key_size = create_attr->key_size;
-	attr.value_size = create_attr->value_size;
-	attr.max_entries = create_attr->max_entries;
-	attr.map_flags = create_attr->map_flags;
-	if (create_attr->name)
-		memcpy(attr.map_name, create_attr->name,
-		       min(strlen(create_attr->name), BPF_OBJ_NAME_LEN - 1));
-	attr.numa_node = create_attr->numa_node;
-	attr.btf_fd = create_attr->btf_fd;
-	attr.btf_key_type_id = create_attr->btf_key_type_id;
-	attr.btf_value_type_id = create_attr->btf_value_type_id;
-	attr.map_ifindex = create_attr->map_ifindex;
-	if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS)
-		attr.btf_vmlinux_value_type_id =
-			create_attr->btf_vmlinux_value_type_id;
-	else
-		attr.inner_map_fd = create_attr->inner_map_fd;
+	memset(&attr, 0, attr_sz);
 
-	fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	if (!OPTS_VALID(opts, bpf_map_create_opts))
+		return libbpf_err(-EINVAL);
+
+	attr.map_type = map_type;
+	if (map_name)
+		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
+	attr.key_size = key_size;
+	attr.value_size = value_size;
+	attr.max_entries = max_entries;
+
+	attr.btf_fd = OPTS_GET(opts, btf_fd, 0);
+	attr.btf_key_type_id = OPTS_GET(opts, btf_key_type_id, 0);
+	attr.btf_value_type_id = OPTS_GET(opts, btf_value_type_id, 0);
+	attr.btf_vmlinux_value_type_id = OPTS_GET(opts, btf_vmlinux_value_type_id, 0);
+
+	attr.inner_map_fd = OPTS_GET(opts, inner_map_fd, 0);
+	attr.map_flags = OPTS_GET(opts, map_flags, 0);
+	attr.map_extra = OPTS_GET(opts, map_extra, 0);
+	attr.numa_node = OPTS_GET(opts, numa_node, 0);
+	attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0);
+
+	fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
+int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, p);
+
+	p.map_flags = create_attr->map_flags;
+	p.numa_node = create_attr->numa_node;
+	p.btf_fd = create_attr->btf_fd;
+	p.btf_key_type_id = create_attr->btf_key_type_id;
+	p.btf_value_type_id = create_attr->btf_value_type_id;
+	p.map_ifindex = create_attr->map_ifindex;
+	if (create_attr->map_type == BPF_MAP_TYPE_STRUCT_OPS)
+		p.btf_vmlinux_value_type_id = create_attr->btf_vmlinux_value_type_id;
+	else
+		p.inner_map_fd = create_attr->inner_map_fd;
+
+	return bpf_map_create(create_attr->map_type, create_attr->name,
+			      create_attr->key_size, create_attr->value_size,
+			      create_attr->max_entries, &p);
+}
+
 int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
 			int key_size, int value_size, int max_entries,
 			__u32 map_flags, int node)
 {
-	struct bpf_create_map_attr map_attr = {};
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
 
-	map_attr.name = name;
-	map_attr.map_type = map_type;
-	map_attr.map_flags = map_flags;
-	map_attr.key_size = key_size;
-	map_attr.value_size = value_size;
-	map_attr.max_entries = max_entries;
+	opts.map_flags = map_flags;
 	if (node >= 0) {
-		map_attr.numa_node = node;
-		map_attr.map_flags |= BPF_F_NUMA_NODE;
+		opts.numa_node = node;
+		opts.map_flags |= BPF_F_NUMA_NODE;
 	}
 
-	return bpf_create_map_xattr(&map_attr);
+	return bpf_map_create(map_type, name, key_size, value_size, max_entries, &opts);
 }
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size,
 		   int value_size, int max_entries, __u32 map_flags)
 {
-	struct bpf_create_map_attr map_attr = {};
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags);
 
-	map_attr.map_type = map_type;
-	map_attr.map_flags = map_flags;
-	map_attr.key_size = key_size;
-	map_attr.value_size = value_size;
-	map_attr.max_entries = max_entries;
-
-	return bpf_create_map_xattr(&map_attr);
+	return bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts);
 }
 
 int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
 			int key_size, int value_size, int max_entries,
 			__u32 map_flags)
 {
-	struct bpf_create_map_attr map_attr = {};
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags);
 
-	map_attr.name = name;
-	map_attr.map_type = map_type;
-	map_attr.map_flags = map_flags;
-	map_attr.key_size = key_size;
-	map_attr.value_size = value_size;
-	map_attr.max_entries = max_entries;
-
-	return bpf_create_map_xattr(&map_attr);
+	return bpf_map_create(map_type, name, key_size, value_size, max_entries, &opts);
 }
 
 int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
 			       int key_size, int inner_map_fd, int max_entries,
 			       __u32 map_flags, int node)
 {
-	union bpf_attr attr;
-	int fd;
-
-	memset(&attr, '\0', sizeof(attr));
-
-	attr.map_type = map_type;
-	attr.key_size = key_size;
-	attr.value_size = 4;
-	attr.inner_map_fd = inner_map_fd;
-	attr.max_entries = max_entries;
-	attr.map_flags = map_flags;
-	if (name)
-		memcpy(attr.map_name, name,
-		       min(strlen(name), BPF_OBJ_NAME_LEN - 1));
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
 
+	opts.inner_map_fd = inner_map_fd;
+	opts.map_flags = map_flags;
 	if (node >= 0) {
-		attr.map_flags |= BPF_F_NUMA_NODE;
-		attr.numa_node = node;
+		opts.map_flags |= BPF_F_NUMA_NODE;
+		opts.numa_node = node;
 	}
 
-	fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
-	return libbpf_err_errno(fd);
+	return bpf_map_create(map_type, name, key_size, 4, max_entries, &opts);
 }
 
 int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
 			  int key_size, int inner_map_fd, int max_entries,
 			  __u32 map_flags)
 {
-	return bpf_create_map_in_map_node(map_type, name, key_size,
-					  inner_map_fd, max_entries, map_flags,
-					  -1);
+	LIBBPF_OPTS(bpf_map_create_opts, opts,
+		.inner_map_fd = inner_map_fd,
+		.map_flags = map_flags,
+	);
+
+	return bpf_map_create(map_type, name, key_size, 4, max_entries, &opts);
 }
 
 static void *
@@ -219,57 +312,95 @@ alloc_zero_tailing_info(const void *orecord, __u32 cnt,
 	return info;
 }
 
-int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
+DEFAULT_VERSION(bpf_prog_load_v0_6_0, bpf_prog_load, LIBBPF_0.6.0)
+int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
+		         const char *prog_name, const char *license,
+		         const struct bpf_insn *insns, size_t insn_cnt,
+		         const struct bpf_prog_load_opts *opts)
 {
 	void *finfo = NULL, *linfo = NULL;
+	const char *func_info, *line_info;
+	__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
+	__u32 func_info_rec_size, line_info_rec_size;
+	int fd, attempts;
 	union bpf_attr attr;
-	int fd;
+	char *log_buf;
 
-	if (!load_attr->log_buf != !load_attr->log_buf_sz)
+	bump_rlimit_memlock();
+
+	if (!OPTS_VALID(opts, bpf_prog_load_opts))
 		return libbpf_err(-EINVAL);
 
-	if (load_attr->log_level > (4 | 2 | 1) || (load_attr->log_level && !load_attr->log_buf))
+	attempts = OPTS_GET(opts, attempts, 0);
+	if (attempts < 0)
 		return libbpf_err(-EINVAL);
+	if (attempts == 0)
+		attempts = PROG_LOAD_ATTEMPTS;
 
 	memset(&attr, 0, sizeof(attr));
-	attr.prog_type = load_attr->prog_type;
-	attr.expected_attach_type = load_attr->expected_attach_type;
 
-	if (load_attr->attach_prog_fd)
-		attr.attach_prog_fd = load_attr->attach_prog_fd;
+	attr.prog_type = prog_type;
+	attr.expected_attach_type = OPTS_GET(opts, expected_attach_type, 0);
+
+	attr.prog_btf_fd = OPTS_GET(opts, prog_btf_fd, 0);
+	attr.prog_flags = OPTS_GET(opts, prog_flags, 0);
+	attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0);
+	attr.kern_version = OPTS_GET(opts, kern_version, 0);
+
+	if (prog_name)
+		libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
+	attr.license = ptr_to_u64(license);
+
+	if (insn_cnt > UINT_MAX)
+		return libbpf_err(-E2BIG);
+
+	attr.insns = ptr_to_u64(insns);
+	attr.insn_cnt = (__u32)insn_cnt;
+
+	attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
+	attach_btf_obj_fd = OPTS_GET(opts, attach_btf_obj_fd, 0);
+
+	if (attach_prog_fd && attach_btf_obj_fd)
+		return libbpf_err(-EINVAL);
+
+	attr.attach_btf_id = OPTS_GET(opts, attach_btf_id, 0);
+	if (attach_prog_fd)
+		attr.attach_prog_fd = attach_prog_fd;
 	else
-		attr.attach_btf_obj_fd = load_attr->attach_btf_obj_fd;
-	attr.attach_btf_id = load_attr->attach_btf_id;
+		attr.attach_btf_obj_fd = attach_btf_obj_fd;
 
-	attr.prog_ifindex = load_attr->prog_ifindex;
-	attr.kern_version = load_attr->kern_version;
+	log_buf = OPTS_GET(opts, log_buf, NULL);
+	log_size = OPTS_GET(opts, log_size, 0);
+	log_level = OPTS_GET(opts, log_level, 0);
 
-	attr.insn_cnt = (__u32)load_attr->insn_cnt;
-	attr.insns = ptr_to_u64(load_attr->insns);
-	attr.license = ptr_to_u64(load_attr->license);
+	if (!!log_buf != !!log_size)
+		return libbpf_err(-EINVAL);
+	if (log_level > (4 | 2 | 1))
+		return libbpf_err(-EINVAL);
+	if (log_level && !log_buf)
+		return libbpf_err(-EINVAL);
 
-	attr.log_level = load_attr->log_level;
-	if (attr.log_level) {
-		attr.log_buf = ptr_to_u64(load_attr->log_buf);
-		attr.log_size = load_attr->log_buf_sz;
+	func_info_rec_size = OPTS_GET(opts, func_info_rec_size, 0);
+	func_info = OPTS_GET(opts, func_info, NULL);
+	attr.func_info_rec_size = func_info_rec_size;
+	attr.func_info = ptr_to_u64(func_info);
+	attr.func_info_cnt = OPTS_GET(opts, func_info_cnt, 0);
+
+	line_info_rec_size = OPTS_GET(opts, line_info_rec_size, 0);
+	line_info = OPTS_GET(opts, line_info, NULL);
+	attr.line_info_rec_size = line_info_rec_size;
+	attr.line_info = ptr_to_u64(line_info);
+	attr.line_info_cnt = OPTS_GET(opts, line_info_cnt, 0);
+
+	attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL));
+
+	if (log_level) {
+		attr.log_buf = ptr_to_u64(log_buf);
+		attr.log_size = log_size;
+		attr.log_level = log_level;
 	}
 
-	attr.prog_btf_fd = load_attr->prog_btf_fd;
-	attr.prog_flags = load_attr->prog_flags;
-
-	attr.func_info_rec_size = load_attr->func_info_rec_size;
-	attr.func_info_cnt = load_attr->func_info_cnt;
-	attr.func_info = ptr_to_u64(load_attr->func_info);
-
-	attr.line_info_rec_size = load_attr->line_info_rec_size;
-	attr.line_info_cnt = load_attr->line_info_cnt;
-	attr.line_info = ptr_to_u64(load_attr->line_info);
-
-	if (load_attr->name)
-		memcpy(attr.prog_name, load_attr->name,
-		       min(strlen(load_attr->name), (size_t)BPF_OBJ_NAME_LEN - 1));
-
-	fd = sys_bpf_prog_load(&attr, sizeof(attr));
+	fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
 	if (fd >= 0)
 		return fd;
 
@@ -279,11 +410,11 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 	 */
 	while (errno == E2BIG && (!finfo || !linfo)) {
 		if (!finfo && attr.func_info_cnt &&
-		    attr.func_info_rec_size < load_attr->func_info_rec_size) {
+		    attr.func_info_rec_size < func_info_rec_size) {
 			/* try with corrected func info records */
-			finfo = alloc_zero_tailing_info(load_attr->func_info,
-							load_attr->func_info_cnt,
-							load_attr->func_info_rec_size,
+			finfo = alloc_zero_tailing_info(func_info,
+							attr.func_info_cnt,
+							func_info_rec_size,
 							attr.func_info_rec_size);
 			if (!finfo) {
 				errno = E2BIG;
@@ -291,13 +422,12 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 			}
 
 			attr.func_info = ptr_to_u64(finfo);
-			attr.func_info_rec_size = load_attr->func_info_rec_size;
+			attr.func_info_rec_size = func_info_rec_size;
 		} else if (!linfo && attr.line_info_cnt &&
-			   attr.line_info_rec_size <
-			   load_attr->line_info_rec_size) {
-			linfo = alloc_zero_tailing_info(load_attr->line_info,
-							load_attr->line_info_cnt,
-							load_attr->line_info_rec_size,
+			   attr.line_info_rec_size < line_info_rec_size) {
+			linfo = alloc_zero_tailing_info(line_info,
+							attr.line_info_cnt,
+							line_info_rec_size,
 							attr.line_info_rec_size);
 			if (!linfo) {
 				errno = E2BIG;
@@ -305,26 +435,27 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 			}
 
 			attr.line_info = ptr_to_u64(linfo);
-			attr.line_info_rec_size = load_attr->line_info_rec_size;
+			attr.line_info_rec_size = line_info_rec_size;
 		} else {
 			break;
 		}
 
-		fd = sys_bpf_prog_load(&attr, sizeof(attr));
+		fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
 		if (fd >= 0)
 			goto done;
 	}
 
-	if (load_attr->log_level || !load_attr->log_buf)
-		goto done;
+	if (log_level == 0 && log_buf) {
+		/* log_level == 0 with non-NULL log_buf requires retrying on error
+		 * with log_level == 1 and log_buf/log_buf_size set, to get details of
+		 * failure
+		 */
+		attr.log_buf = ptr_to_u64(log_buf);
+		attr.log_size = log_size;
+		attr.log_level = 1;
 
-	/* Try again with log */
-	attr.log_buf = ptr_to_u64(load_attr->log_buf);
-	attr.log_size = load_attr->log_buf_sz;
-	attr.log_level = 1;
-	load_attr->log_buf[0] = 0;
-
-	fd = sys_bpf_prog_load(&attr, sizeof(attr));
+		fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
+	}
 done:
 	/* free() doesn't affect errno, so we don't need to restore it */
 	free(finfo);
@@ -332,17 +463,20 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 	return libbpf_err_errno(fd);
 }
 
+__attribute__((alias("bpf_load_program_xattr2")))
 int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
-			   char *log_buf, size_t log_buf_sz)
+			   char *log_buf, size_t log_buf_sz);
+
+static int bpf_load_program_xattr2(const struct bpf_load_program_attr *load_attr,
+				   char *log_buf, size_t log_buf_sz)
 {
-	struct bpf_prog_load_params p = {};
+	LIBBPF_OPTS(bpf_prog_load_opts, p);
 
 	if (!load_attr || !log_buf != !log_buf_sz)
 		return libbpf_err(-EINVAL);
 
-	p.prog_type = load_attr->prog_type;
 	p.expected_attach_type = load_attr->expected_attach_type;
-	switch (p.prog_type) {
+	switch (load_attr->prog_type) {
 	case BPF_PROG_TYPE_STRUCT_OPS:
 	case BPF_PROG_TYPE_LSM:
 		p.attach_btf_id = load_attr->attach_btf_id;
@@ -356,12 +490,9 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 		p.prog_ifindex = load_attr->prog_ifindex;
 		p.kern_version = load_attr->kern_version;
 	}
-	p.insn_cnt = load_attr->insns_cnt;
-	p.insns = load_attr->insns;
-	p.license = load_attr->license;
 	p.log_level = load_attr->log_level;
 	p.log_buf = log_buf;
-	p.log_buf_sz = log_buf_sz;
+	p.log_size = log_buf_sz;
 	p.prog_btf_fd = load_attr->prog_btf_fd;
 	p.func_info_rec_size = load_attr->func_info_rec_size;
 	p.func_info_cnt = load_attr->func_info_cnt;
@@ -369,10 +500,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	p.line_info_rec_size = load_attr->line_info_rec_size;
 	p.line_info_cnt = load_attr->line_info_cnt;
 	p.line_info = load_attr->line_info;
-	p.name = load_attr->name;
 	p.prog_flags = load_attr->prog_flags;
 
-	return libbpf__bpf_prog_load(&p);
+	return bpf_prog_load(load_attr->prog_type, load_attr->name, load_attr->license,
+			     load_attr->insns, load_attr->insns_cnt, &p);
 }
 
 int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
@@ -391,7 +522,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	load_attr.license = license;
 	load_attr.kern_version = kern_version;
 
-	return bpf_load_program_xattr(&load_attr, log_buf, log_buf_sz);
+	return bpf_load_program_xattr2(&load_attr, log_buf, log_buf_sz);
 }
 
 int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
@@ -402,6 +533,8 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	union bpf_attr attr;
 	int fd;
 
+	bump_rlimit_memlock();
+
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = type;
 	attr.insn_cnt = (__u32)insns_cnt;
@@ -414,7 +547,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	attr.kern_version = kern_version;
 	attr.prog_flags = prog_flags;
 
-	fd = sys_bpf_prog_load(&attr, sizeof(attr));
+	fd = sys_bpf_prog_load(&attr, sizeof(attr), PROG_LOAD_ATTEMPTS);
 	return libbpf_err_errno(fd);
 }
 
@@ -558,11 +691,11 @@ static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
 	return libbpf_err_errno(ret);
 }
 
-int bpf_map_delete_batch(int fd, void *keys, __u32 *count,
+int bpf_map_delete_batch(int fd, const void *keys, __u32 *count,
 			 const struct bpf_map_batch_opts *opts)
 {
 	return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL,
-				    NULL, keys, NULL, count, opts);
+				    NULL, (void *)keys, NULL, count, opts);
 }
 
 int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys,
@@ -582,11 +715,11 @@ int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch,
 				    count, opts);
 }
 
-int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count,
+int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *count,
 			 const struct bpf_map_batch_opts *opts)
 {
 	return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL,
-				    keys, values, count, opts);
+				    (void *)keys, (void *)values, count, opts);
 }
 
 int bpf_obj_pin(int fd, const char *pathname)
@@ -610,7 +743,7 @@ int bpf_obj_get(const char *pathname)
 	memset(&attr, 0, sizeof(attr));
 	attr.pathname = ptr_to_u64((void *)pathname);
 
-	fd = sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_OBJ_GET, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -721,7 +854,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 		break;
 	}
 proceed:
-	fd = sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -764,7 +897,7 @@ int bpf_iter_create(int link_fd)
 	memset(&attr, 0, sizeof(attr));
 	attr.iter_create.link_fd = link_fd;
 
-	fd = sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -922,7 +1055,7 @@ int bpf_prog_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_id = id;
 
-	fd = sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -934,7 +1067,7 @@ int bpf_map_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.map_id = id;
 
-	fd = sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -946,7 +1079,7 @@ int bpf_btf_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.btf_id = id;
 
-	fd = sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -958,7 +1091,7 @@ int bpf_link_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.link_id = id;
 
-	fd = sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -989,28 +1122,71 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 	attr.raw_tracepoint.name = ptr_to_u64(name);
 	attr.raw_tracepoint.prog_fd = prog_fd;
 
-	fd = sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
-int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
-		 bool do_log)
+int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_load_opts *opts)
 {
-	union bpf_attr attr = {};
+	const size_t attr_sz = offsetofend(union bpf_attr, btf_log_level);
+	union bpf_attr attr;
+	char *log_buf;
+	size_t log_size;
+	__u32 log_level;
 	int fd;
 
-	attr.btf = ptr_to_u64(btf);
+	bump_rlimit_memlock();
+
+	memset(&attr, 0, attr_sz);
+
+	if (!OPTS_VALID(opts, bpf_btf_load_opts))
+		return libbpf_err(-EINVAL);
+
+	log_buf = OPTS_GET(opts, log_buf, NULL);
+	log_size = OPTS_GET(opts, log_size, 0);
+	log_level = OPTS_GET(opts, log_level, 0);
+
+	if (log_size > UINT_MAX)
+		return libbpf_err(-EINVAL);
+	if (log_size && !log_buf)
+		return libbpf_err(-EINVAL);
+
+	attr.btf = ptr_to_u64(btf_data);
 	attr.btf_size = btf_size;
+	/* log_level == 0 and log_buf != NULL means "try loading without
+	 * log_buf, but retry with log_buf and log_level=1 on error", which is
+	 * consistent across low-level and high-level BTF and program loading
+	 * APIs within libbpf and provides a sensible behavior in practice
+	 */
+	if (log_level) {
+		attr.btf_log_buf = ptr_to_u64(log_buf);
+		attr.btf_log_size = (__u32)log_size;
+		attr.btf_log_level = log_level;
+	}
+
+	fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz);
+	if (fd < 0 && log_buf && log_level == 0) {
+		attr.btf_log_buf = ptr_to_u64(log_buf);
+		attr.btf_log_size = (__u32)log_size;
+		attr.btf_log_level = 1;
+		fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz);
+	}
+	return libbpf_err_errno(fd);
+}
+
+int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, bool do_log)
+{
+	LIBBPF_OPTS(bpf_btf_load_opts, opts);
+	int fd;
 
 retry:
 	if (do_log && log_buf && log_buf_size) {
-		attr.btf_log_level = 1;
-		attr.btf_log_size = log_buf_size;
-		attr.btf_log_buf = ptr_to_u64(log_buf);
+		opts.log_buf = log_buf;
+		opts.log_size = log_buf_size;
+		opts.log_level = 1;
 	}
 
-	fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr));
-
+	fd = bpf_btf_load(btf, btf_size, &opts);
 	if (fd < 0 && !do_log && log_buf && log_buf_size) {
 		do_log = true;
 		goto retry;
@@ -1051,7 +1227,7 @@ int bpf_enable_stats(enum bpf_stats_type type)
 	memset(&attr, 0, sizeof(attr));
 	attr.enable_stats.type = type;
 
-	fd = sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 

tools/lib/bpf/bpf.h

@@ -29,11 +29,38 @@
 #include <stdint.h>
 
 #include "libbpf_common.h"
+#include "libbpf_legacy.h"
 
 #ifdef __cplusplus
 extern "C" {
 #endif
 
+int libbpf_set_memlock_rlim(size_t memlock_bytes);
+
+struct bpf_map_create_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+
+	__u32 btf_fd;
+	__u32 btf_key_type_id;
+	__u32 btf_value_type_id;
+	__u32 btf_vmlinux_value_type_id;
+
+	__u32 inner_map_fd;
+	__u32 map_flags;
+	__u64 map_extra;
+
+	__u32 numa_node;
+	__u32 map_ifindex;
+};
+#define bpf_map_create_opts__last_field map_ifindex
+
+LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
+			      const char *map_name,
+			      __u32 key_size,
+			      __u32 value_size,
+			      __u32 max_entries,
+			      const struct bpf_map_create_opts *opts);
+
 struct bpf_create_map_attr {
 	const char *name;
 	enum bpf_map_type map_type;
@@ -52,25 +79,95 @@ struct bpf_create_map_attr {
 	};
 };
 
-LIBBPF_API int
-bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
+LIBBPF_API int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
 LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
 				   int key_size, int value_size,
 				   int max_entries, __u32 map_flags, int node);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
 LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
 				   int key_size, int value_size,
 				   int max_entries, __u32 map_flags);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
 LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size,
 			      int value_size, int max_entries, __u32 map_flags);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
 LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type,
 					  const char *name, int key_size,
 					  int inner_map_fd, int max_entries,
 					  __u32 map_flags, int node);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead")
 LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type,
 				     const char *name, int key_size,
 				     int inner_map_fd, int max_entries,
 				     __u32 map_flags);
 
+struct bpf_prog_load_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+
+	/* libbpf can retry BPF_PROG_LOAD command if bpf() syscall returns
+	 * -EAGAIN. This field determines how many attempts libbpf has to
+	 *  make. If not specified, libbpf will use default value of 5.
+	 */
+	int attempts;
+
+	enum bpf_attach_type expected_attach_type;
+	__u32 prog_btf_fd;
+	__u32 prog_flags;
+	__u32 prog_ifindex;
+	__u32 kern_version;
+
+	__u32 attach_btf_id;
+	__u32 attach_prog_fd;
+	__u32 attach_btf_obj_fd;
+
+	const int *fd_array;
+
+	/* .BTF.ext func info data */
+	const void *func_info;
+	__u32 func_info_cnt;
+	__u32 func_info_rec_size;
+
+	/* .BTF.ext line info data */
+	const void *line_info;
+	__u32 line_info_cnt;
+	__u32 line_info_rec_size;
+
+	/* verifier log options */
+	__u32 log_level;
+	__u32 log_size;
+	char *log_buf;
+};
+#define bpf_prog_load_opts__last_field log_buf
+
+LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
+			     const char *prog_name, const char *license,
+			     const struct bpf_insn *insns, size_t insn_cnt,
+			     const struct bpf_prog_load_opts *opts);
+/* this "specialization" should go away in libbpf 1.0 */
+LIBBPF_API int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
+				    const char *prog_name, const char *license,
+				    const struct bpf_insn *insns, size_t insn_cnt,
+				    const struct bpf_prog_load_opts *opts);
+
+/* This is an elaborate way to not conflict with deprecated bpf_prog_load()
+ * API, defined in libbpf.h. Once we hit libbpf 1.0, all this will be gone.
+ * With this approach, if someone is calling bpf_prog_load() with
+ * 4 arguments, they will use the deprecated API, which keeps backwards
+ * compatibility (both source code and binary). If bpf_prog_load() is called
+ * with 6 arguments, though, it gets redirected to __bpf_prog_load.
+ * So looking forward to libbpf 1.0 when this hack will be gone and
+ * __bpf_prog_load() will be called just bpf_prog_load().
+ */
+#ifndef bpf_prog_load
+#define bpf_prog_load(...) ___libbpf_overload(___bpf_prog_load, __VA_ARGS__)
+#define ___bpf_prog_load4(file, type, pobj, prog_fd) \
+	bpf_prog_load_deprecated(file, type, pobj, prog_fd)
+#define ___bpf_prog_load6(prog_type, prog_name, license, insns, insn_cnt, opts) \
+	bpf_prog_load(prog_type, prog_name, license, insns, insn_cnt, opts)
+#endif /* bpf_prog_load */
+
 struct bpf_load_program_attr {
 	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
@@ -100,15 +197,18 @@ struct bpf_load_program_attr {
 /* Flags to direct loading requirements */
 #define MAPS_RELAX_COMPAT	0x01
 
-/* Recommend log buffer size */
+/* Recommended log buffer size */
 #define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */
-LIBBPF_API int
-bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
-		       char *log_buf, size_t log_buf_sz);
+
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead")
+LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
+				      char *log_buf, size_t log_buf_sz);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead")
 LIBBPF_API int bpf_load_program(enum bpf_prog_type type,
 				const struct bpf_insn *insns, size_t insns_cnt,
 				const char *license, __u32 kern_version,
 				char *log_buf, size_t log_buf_sz);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead")
 LIBBPF_API int bpf_verify_program(enum bpf_prog_type type,
 				  const struct bpf_insn *insns,
 				  size_t insns_cnt, __u32 prog_flags,
@@ -116,6 +216,23 @@ LIBBPF_API int bpf_verify_program(enum bpf_prog_type type,
 				  char *log_buf, size_t log_buf_sz,
 				  int log_level);
 
+struct bpf_btf_load_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+
+	/* kernel log options */
+	char *log_buf;
+	__u32 log_level;
+	__u32 log_size;
+};
+#define bpf_btf_load_opts__last_field log_size
+
+LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
+			    const struct bpf_btf_load_opts *opts);
+
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_btf_load() instead")
+LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf,
+			    __u32 log_buf_size, bool do_log);
+
 LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
 				   __u64 flags);
 
@@ -137,17 +254,128 @@ struct bpf_map_batch_opts {
 };
 #define bpf_map_batch_opts__last_field flags
 
-LIBBPF_API int bpf_map_delete_batch(int fd, void *keys,
+
+/**
+ * @brief **bpf_map_delete_batch()** allows for batch deletion of multiple
+ * elements in a BPF map.
+ *
+ * @param fd BPF map file descriptor
+ * @param keys pointer to an array of *count* keys
+ * @param count input and output parameter; on input **count** represents the
+ * number of  elements in the map to delete in batch;
+ * on output if a non-EFAULT error is returned, **count** represents the number of deleted
+ * elements if the output **count** value is not equal to the input **count** value
+ * If EFAULT is returned, **count** should not be trusted to be correct.
+ * @param opts options for configuring the way the batch deletion works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_map_delete_batch(int fd, const void *keys,
 				    __u32 *count,
 				    const struct bpf_map_batch_opts *opts);
+
+/**
+ * @brief **bpf_map_lookup_batch()** allows for batch lookup of BPF map elements.
+ *
+ * The parameter *in_batch* is the address of the first element in the batch to read.
+ * *out_batch* is an output parameter that should be passed as *in_batch* to subsequent
+ * calls to **bpf_map_lookup_batch()**. NULL can be passed for *in_batch* to indicate
+ * that the batched lookup starts from the beginning of the map.
+ *
+ * The *keys* and *values* are output parameters which must point to memory large enough to
+ * hold *count* items based on the key and value size of the map *map_fd*. The *keys*
+ * buffer must be of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * @param fd BPF map file descriptor
+ * @param in_batch address of the first element in batch to read, can pass NULL to
+ * indicate that the batched lookup starts from the beginning of the map.
+ * @param out_batch output parameter that should be passed to next call as *in_batch*
+ * @param keys pointer to an array large enough for *count* keys
+ * @param values pointer to an array large enough for *count* values
+ * @param count input and output parameter; on input it's the number of elements
+ * in the map to read in batch; on output it's the number of elements that were
+ * successfully read.
+ * If a non-EFAULT error is returned, count will be set as the number of elements
+ * that were read before the error occurred.
+ * If EFAULT is returned, **count** should not be trusted to be correct.
+ * @param opts options for configuring the way the batch lookup works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
 LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch,
 				    void *keys, void *values, __u32 *count,
 				    const struct bpf_map_batch_opts *opts);
+
+/**
+ * @brief **bpf_map_lookup_and_delete_batch()** allows for batch lookup and deletion
+ * of BPF map elements where each element is deleted after being retrieved.
+ *
+ * @param fd BPF map file descriptor
+ * @param in_batch address of the first element in batch to read, can pass NULL to
+ * get address of the first element in *out_batch*
+ * @param out_batch output parameter that should be passed to next call as *in_batch*
+ * @param keys pointer to an array of *count* keys
+ * @param values pointer to an array large enough for *count* values
+ * @param count input and output parameter; on input it's the number of elements
+ * in the map to read and delete in batch; on output it represents the number of
+ * elements that were successfully read and deleted
+ * If a non-**EFAULT** error code is returned and if the output **count** value
+ * is not equal to the input **count** value, up to **count** elements may
+ * have been deleted.
+ * if **EFAULT** is returned up to *count* elements may have been deleted without
+ * being returned via the *keys* and *values* output parameters.
+ * @param opts options for configuring the way the batch lookup and delete works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
 LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch,
 					void *out_batch, void *keys,
 					void *values, __u32 *count,
 					const struct bpf_map_batch_opts *opts);
-LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values,
+
+/**
+ * @brief **bpf_map_update_batch()** updates multiple elements in a map
+ * by specifying keys and their corresponding values.
+ *
+ * The *keys* and *values* parameters must point to memory large enough
+ * to hold *count* items based on the key and value size of the map.
+ *
+ * The *opts* parameter can be used to control how *bpf_map_update_batch()*
+ * should handle keys that either do or do not already exist in the map.
+ * In particular the *flags* parameter of *bpf_map_batch_opts* can be
+ * one of the following:
+ *
+ * Note that *count* is an input and output parameter, where on output it
+ * represents how many elements were successfully updated. Also note that if
+ * **EFAULT** then *count* should not be trusted to be correct.
+ *
+ * **BPF_ANY**
+ *    Create new elements or update existing.
+ *
+ * **BPF_NOEXIST**
+ *    Create new elements only if they do not exist.
+ *
+ * **BPF_EXIST**
+ *    Update existing elements.
+ *
+ * **BPF_F_LOCK**
+ *    Update spin_lock-ed map elements. This must be
+ *    specified if the map value contains a spinlock.
+ *
+ * @param fd BPF map file descriptor
+ * @param keys pointer to an array of *count* keys
+ * @param values pointer to an array of *count* values
+ * @param count input and output parameter; on input it's the number of elements
+ * in the map to update in batch; on output if a non-EFAULT error is returned,
+ * **count** represents the number of updated elements if the output **count**
+ * value is not equal to the input **count** value.
+ * If EFAULT is returned, **count** should not be trusted to be correct.
+ * @param opts options for configuring the way the batch update works
+ * @return 0, on success; negative error code, otherwise (errno is also set to
+ * the error code)
+ */
+LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values,
 				    __u32 *count,
 				    const struct bpf_map_batch_opts *opts);
 
@@ -243,8 +471,6 @@ LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,
 			      __u32 *prog_ids, __u32 *prog_cnt);
 LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
-LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf,
-			    __u32 log_buf_size, bool do_log);
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
 				 __u64 *probe_offset, __u64 *probe_addr);

tools/lib/bpf/bpf_gen_internal.h

@@ -3,10 +3,27 @@
 #ifndef __BPF_GEN_INTERNAL_H
 #define __BPF_GEN_INTERNAL_H
 
+#include "bpf.h"
+
 struct ksym_relo_desc {
 	const char *name;
 	int kind;
 	int insn_idx;
+	bool is_weak;
+	bool is_typeless;
+};
+
+struct ksym_desc {
+	const char *name;
+	int ref;
+	int kind;
+	union {
+		/* used for kfunc */
+		int off;
+		/* used for typeless ksym */
+		bool typeless;
+	};
+	int insn;
 };
 
 struct bpf_gen {
@@ -22,20 +39,34 @@ struct bpf_gen {
 	int error;
 	struct ksym_relo_desc *relos;
 	int relo_cnt;
+	struct bpf_core_relo *core_relos;
+	int core_relo_cnt;
 	char attach_target[128];
 	int attach_kind;
+	struct ksym_desc *ksyms;
+	__u32 nr_ksyms;
+	int fd_array;
+	int nr_fd_array;
 };
 
-void bpf_gen__init(struct bpf_gen *gen, int log_level);
-int bpf_gen__finish(struct bpf_gen *gen);
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps);
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps);
 void bpf_gen__free(struct bpf_gen *gen);
 void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size);
-void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_attr *map_attr, int map_idx);
-struct bpf_prog_load_params;
-void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_attr, int prog_idx);
+void bpf_gen__map_create(struct bpf_gen *gen,
+			 enum bpf_map_type map_type, const char *map_name,
+			 __u32 key_size, __u32 value_size, __u32 max_entries,
+			 struct bpf_map_create_opts *map_attr, int map_idx);
+void bpf_gen__prog_load(struct bpf_gen *gen,
+			enum bpf_prog_type prog_type, const char *prog_name,
+			const char *license, struct bpf_insn *insns, size_t insn_cnt,
+			struct bpf_prog_load_opts *load_attr, int prog_idx);
 void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size);
 void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx);
 void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type);
-void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, int insn_idx);
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
+			    bool is_typeless, int kind, int insn_idx);
+void bpf_gen__record_relo_core(struct bpf_gen *gen, const struct bpf_core_relo *core_relo);
+void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int key, int inner_map_idx);
 
 #endif

tools/lib/bpf/bpf_helpers.h

@@ -14,14 +14,6 @@
 #define __type(name, val) typeof(val) *name
 #define __array(name, val) typeof(val) *name[]
 
-/* Helper macro to print out debug messages */
-#define bpf_printk(fmt, ...)				\
-({							\
-	char ____fmt[] = fmt;				\
-	bpf_trace_printk(____fmt, sizeof(____fmt),	\
-			 ##__VA_ARGS__);		\
-})
-
 /*
  * Helper macro to place programs, maps, license in
  * different sections in elf_bpf file. Section names
@@ -224,4 +216,47 @@ enum libbpf_tristate {
 		     ___param, sizeof(___param));		\
 })
 
+#ifdef BPF_NO_GLOBAL_DATA
+#define BPF_PRINTK_FMT_MOD
+#else
+#define BPF_PRINTK_FMT_MOD static const
+#endif
+
+#define __bpf_printk(fmt, ...)				\
+({							\
+	BPF_PRINTK_FMT_MOD char ____fmt[] = fmt;	\
+	bpf_trace_printk(____fmt, sizeof(____fmt),	\
+			 ##__VA_ARGS__);		\
+})
+
+/*
+ * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments
+ * instead of an array of u64.
+ */
+#define __bpf_vprintk(fmt, args...)				\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_trace_vprintk(___fmt, sizeof(___fmt),		\
+			  ___param, sizeof(___param));		\
+})
+
+/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args
+ * Otherwise use __bpf_vprintk
+ */
+#define ___bpf_pick_printk(...) \
+	___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk,	\
+		   __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk,		\
+		   __bpf_vprintk, __bpf_vprintk, __bpf_printk /*3*/, __bpf_printk /*2*/,\
+		   __bpf_printk /*1*/, __bpf_printk /*0*/)
+
+/* Helper macro to print out debug messages */
+#define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args)
+
 #endif

tools/lib/bpf/bpf_tracing.h

@@ -24,6 +24,9 @@
 #elif defined(__TARGET_ARCH_sparc)
 	#define bpf_target_sparc
 	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_riscv)
+	#define bpf_target_riscv
+	#define bpf_target_defined
 #else
 
 /* Fall back to what the compiler says */
@@ -48,6 +51,9 @@
 #elif defined(__sparc__)
 	#define bpf_target_sparc
 	#define bpf_target_defined
+#elif defined(__riscv) && __riscv_xlen == 64
+	#define bpf_target_riscv
+	#define bpf_target_defined
 #endif /* no compiler target */
 
 #endif
@@ -60,251 +66,204 @@
 
 #if defined(__KERNEL__) || defined(__VMLINUX_H__)
 
-#define PT_REGS_PARM1(x) ((x)->di)
-#define PT_REGS_PARM2(x) ((x)->si)
-#define PT_REGS_PARM3(x) ((x)->dx)
-#define PT_REGS_PARM4(x) ((x)->cx)
-#define PT_REGS_PARM5(x) ((x)->r8)
-#define PT_REGS_RET(x) ((x)->sp)
-#define PT_REGS_FP(x) ((x)->bp)
-#define PT_REGS_RC(x) ((x)->ax)
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->ip)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), di)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), si)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), dx)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), cx)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), bp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), ax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), ip)
+#define __PT_PARM1_REG di
+#define __PT_PARM2_REG si
+#define __PT_PARM3_REG dx
+#define __PT_PARM4_REG cx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG sp
+#define __PT_FP_REG bp
+#define __PT_RC_REG ax
+#define __PT_SP_REG sp
+#define __PT_IP_REG ip
 
 #else
 
 #ifdef __i386__
+
+#define __PT_PARM1_REG eax
+#define __PT_PARM2_REG edx
+#define __PT_PARM3_REG ecx
 /* i386 kernel is built with -mregparm=3 */
-#define PT_REGS_PARM1(x) ((x)->eax)
-#define PT_REGS_PARM2(x) ((x)->edx)
-#define PT_REGS_PARM3(x) ((x)->ecx)
-#define PT_REGS_PARM4(x) 0
-#define PT_REGS_PARM5(x) 0
-#define PT_REGS_RET(x) ((x)->esp)
-#define PT_REGS_FP(x) ((x)->ebp)
-#define PT_REGS_RC(x) ((x)->eax)
-#define PT_REGS_SP(x) ((x)->esp)
-#define PT_REGS_IP(x) ((x)->eip)
+#define __PT_PARM4_REG __unsupported__
+#define __PT_PARM5_REG __unsupported__
+#define __PT_RET_REG esp
+#define __PT_FP_REG ebp
+#define __PT_RC_REG eax
+#define __PT_SP_REG esp
+#define __PT_IP_REG eip
 
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), eax)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), edx)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), ecx)
-#define PT_REGS_PARM4_CORE(x) 0
-#define PT_REGS_PARM5_CORE(x) 0
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), esp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), ebp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), eax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), esp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), eip)
+#else /* __i386__ */
 
-#else
+#define __PT_PARM1_REG rdi
+#define __PT_PARM2_REG rsi
+#define __PT_PARM3_REG rdx
+#define __PT_PARM4_REG rcx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG rsp
+#define __PT_FP_REG rbp
+#define __PT_RC_REG rax
+#define __PT_SP_REG rsp
+#define __PT_IP_REG rip
 
-#define PT_REGS_PARM1(x) ((x)->rdi)
-#define PT_REGS_PARM2(x) ((x)->rsi)
-#define PT_REGS_PARM3(x) ((x)->rdx)
-#define PT_REGS_PARM4(x) ((x)->rcx)
-#define PT_REGS_PARM5(x) ((x)->r8)
-#define PT_REGS_RET(x) ((x)->rsp)
-#define PT_REGS_FP(x) ((x)->rbp)
-#define PT_REGS_RC(x) ((x)->rax)
-#define PT_REGS_SP(x) ((x)->rsp)
-#define PT_REGS_IP(x) ((x)->rip)
+#endif /* __i386__ */
 
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), rdi)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), rsi)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), rdx)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), rcx)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), rsp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), rbp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), rax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), rsp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), rip)
-
-#endif
-#endif
+#endif /* __KERNEL__ || __VMLINUX_H__ */
 
 #elif defined(bpf_target_s390)
 
 /* s390 provides user_pt_regs instead of struct pt_regs to userspace */
-struct pt_regs;
-#define PT_REGS_S390 const volatile user_pt_regs
-#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2])
-#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3])
-#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4])
-#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5])
-#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6])
-#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14])
-/* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11])
-#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2])
-#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
-#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[3])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr)
+#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
+#define __PT_PARM1_REG gprs[2]
+#define __PT_PARM2_REG gprs[3]
+#define __PT_PARM3_REG gprs[4]
+#define __PT_PARM4_REG gprs[5]
+#define __PT_PARM5_REG gprs[6]
+#define __PT_RET_REG grps[14]
+#define __PT_FP_REG gprs[11]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG gprs[2]
+#define __PT_SP_REG gprs[15]
+#define __PT_IP_REG psw.addr
 
 #elif defined(bpf_target_arm)
 
-#define PT_REGS_PARM1(x) ((x)->uregs[0])
-#define PT_REGS_PARM2(x) ((x)->uregs[1])
-#define PT_REGS_PARM3(x) ((x)->uregs[2])
-#define PT_REGS_PARM4(x) ((x)->uregs[3])
-#define PT_REGS_PARM5(x) ((x)->uregs[4])
-#define PT_REGS_RET(x) ((x)->uregs[14])
-#define PT_REGS_FP(x) ((x)->uregs[11]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->uregs[0])
-#define PT_REGS_SP(x) ((x)->uregs[13])
-#define PT_REGS_IP(x) ((x)->uregs[12])
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), uregs[0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), uregs[1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), uregs[2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), uregs[3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), uregs[4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), uregs[14])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), uregs[11])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), uregs[0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), uregs[13])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), uregs[12])
+#define __PT_PARM1_REG uregs[0]
+#define __PT_PARM2_REG uregs[1]
+#define __PT_PARM3_REG uregs[2]
+#define __PT_PARM4_REG uregs[3]
+#define __PT_PARM5_REG uregs[4]
+#define __PT_RET_REG uregs[14]
+#define __PT_FP_REG uregs[11]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG uregs[0]
+#define __PT_SP_REG uregs[13]
+#define __PT_IP_REG uregs[12]
 
 #elif defined(bpf_target_arm64)
 
 /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
-struct pt_regs;
-#define PT_REGS_ARM64 const volatile struct user_pt_regs
-#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1])
-#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2])
-#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3])
-#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4])
-#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30])
-/* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29])
-#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
-#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[30])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[29])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), pc)
+#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
+#define __PT_PARM1_REG regs[0]
+#define __PT_PARM2_REG regs[1]
+#define __PT_PARM3_REG regs[2]
+#define __PT_PARM4_REG regs[3]
+#define __PT_PARM5_REG regs[4]
+#define __PT_RET_REG regs[30]
+#define __PT_FP_REG regs[29]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG regs[0]
+#define __PT_SP_REG sp
+#define __PT_IP_REG pc
 
 #elif defined(bpf_target_mips)
 
-#define PT_REGS_PARM1(x) ((x)->regs[4])
-#define PT_REGS_PARM2(x) ((x)->regs[5])
-#define PT_REGS_PARM3(x) ((x)->regs[6])
-#define PT_REGS_PARM4(x) ((x)->regs[7])
-#define PT_REGS_PARM5(x) ((x)->regs[8])
-#define PT_REGS_RET(x) ((x)->regs[31])
-#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->regs[2])
-#define PT_REGS_SP(x) ((x)->regs[29])
-#define PT_REGS_IP(x) ((x)->cp0_epc)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), regs[4])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), regs[5])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), regs[6])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), regs[7])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[2])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc)
+#define __PT_PARM1_REG regs[4]
+#define __PT_PARM2_REG regs[5]
+#define __PT_PARM3_REG regs[6]
+#define __PT_PARM4_REG regs[7]
+#define __PT_PARM5_REG regs[8]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG regs[30]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG regs[2]
+#define __PT_SP_REG regs[29]
+#define __PT_IP_REG cp0_epc
 
 #elif defined(bpf_target_powerpc)
 
-#define PT_REGS_PARM1(x) ((x)->gpr[3])
-#define PT_REGS_PARM2(x) ((x)->gpr[4])
-#define PT_REGS_PARM3(x) ((x)->gpr[5])
-#define PT_REGS_PARM4(x) ((x)->gpr[6])
-#define PT_REGS_PARM5(x) ((x)->gpr[7])
-#define PT_REGS_RC(x) ((x)->gpr[3])
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->nip)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), gpr[3])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), gpr[4])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), gpr[5])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), gpr[6])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), gpr[7])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), gpr[3])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), nip)
+#define __PT_PARM1_REG gpr[3]
+#define __PT_PARM2_REG gpr[4]
+#define __PT_PARM3_REG gpr[5]
+#define __PT_PARM4_REG gpr[6]
+#define __PT_PARM5_REG gpr[7]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG gpr[3]
+#define __PT_SP_REG sp
+#define __PT_IP_REG nip
 
 #elif defined(bpf_target_sparc)
 
-#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
-#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
-#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
-#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
-#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
-#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I7])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), u_regs[UREG_FP])
-
+#define __PT_PARM1_REG u_regs[UREG_I0]
+#define __PT_PARM2_REG u_regs[UREG_I1]
+#define __PT_PARM3_REG u_regs[UREG_I2]
+#define __PT_PARM4_REG u_regs[UREG_I3]
+#define __PT_PARM5_REG u_regs[UREG_I4]
+#define __PT_RET_REG u_regs[UREG_I7]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG u_regs[UREG_I0]
+#define __PT_SP_REG u_regs[UREG_FP]
 /* Should this also be a bpf_target check for the sparc case? */
 #if defined(__arch64__)
-#define PT_REGS_IP(x) ((x)->tpc)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), tpc)
+#define __PT_IP_REG tpc
 #else
-#define PT_REGS_IP(x) ((x)->pc)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc)
+#define __PT_IP_REG pc
 #endif
 
+#elif defined(bpf_target_riscv)
+
+#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
+#define __PT_PARM1_REG a0
+#define __PT_PARM2_REG a1
+#define __PT_PARM3_REG a2
+#define __PT_PARM4_REG a3
+#define __PT_PARM5_REG a4
+#define __PT_RET_REG ra
+#define __PT_FP_REG fp
+#define __PT_RC_REG a5
+#define __PT_SP_REG sp
+#define __PT_IP_REG epc
+
 #endif
 
+#if defined(bpf_target_defined)
+
+struct pt_regs;
+
+/* allow some architecutres to override `struct pt_regs` */
+#ifndef __PT_REGS_CAST
+#define __PT_REGS_CAST(x) (x)
+#endif
+
+#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG)
+#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG)
+#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG)
+#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG)
+#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG)
+#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG)
+#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG)
+#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG)
+#define PT_REGS_SP(x) (__PT_REGS_CAST(x)->__PT_SP_REG)
+#define PT_REGS_IP(x) (__PT_REGS_CAST(x)->__PT_IP_REG)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_REG)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_REG)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_SP_REG)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_IP_REG)
+
 #if defined(bpf_target_powerpc)
+
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+
 #elif defined(bpf_target_sparc)
+
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#elif defined(bpf_target_defined)
+
+#else
+
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)					    \
 	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
 #define BPF_KRETPROBE_READ_RET_IP(ip, ctx)				    \
-	({ bpf_probe_read_kernel(&(ip), sizeof(ip),			    \
-			  (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+
 #endif
 
-#if !defined(bpf_target_defined)
+#else /* defined(bpf_target_defined) */
 
 #define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
@@ -331,7 +290,7 @@ struct pt_regs;
 #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 
-#endif /* !defined(bpf_target_defined) */
+#endif /* defined(bpf_target_defined) */
 
 #ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b
@@ -343,25 +302,23 @@ struct pt_regs;
 #define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
 #endif
 #ifndef ___bpf_narg
-#define ___bpf_narg(...) \
-	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#define ___bpf_narg(...) ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
 #endif
 
-#define ___bpf_ctx_cast0() ctx
-#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
-#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1]
-#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2]
-#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3]
-#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4]
-#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5]
-#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6]
-#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7]
-#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8]
+#define ___bpf_ctx_cast0()            ctx
+#define ___bpf_ctx_cast1(x)           ___bpf_ctx_cast0(), (void *)ctx[0]
+#define ___bpf_ctx_cast2(x, args...)  ___bpf_ctx_cast1(args), (void *)ctx[1]
+#define ___bpf_ctx_cast3(x, args...)  ___bpf_ctx_cast2(args), (void *)ctx[2]
+#define ___bpf_ctx_cast4(x, args...)  ___bpf_ctx_cast3(args), (void *)ctx[3]
+#define ___bpf_ctx_cast5(x, args...)  ___bpf_ctx_cast4(args), (void *)ctx[4]
+#define ___bpf_ctx_cast6(x, args...)  ___bpf_ctx_cast5(args), (void *)ctx[5]
+#define ___bpf_ctx_cast7(x, args...)  ___bpf_ctx_cast6(args), (void *)ctx[6]
+#define ___bpf_ctx_cast8(x, args...)  ___bpf_ctx_cast7(args), (void *)ctx[7]
+#define ___bpf_ctx_cast9(x, args...)  ___bpf_ctx_cast8(args), (void *)ctx[8]
 #define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
 #define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
 #define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
-#define ___bpf_ctx_cast(args...) \
-	___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
+#define ___bpf_ctx_cast(args...)      ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
 
 /*
  * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
@@ -394,19 +351,13 @@ ____##name(unsigned long long *ctx, ##args)
 
 struct pt_regs;
 
-#define ___bpf_kprobe_args0() ctx
-#define ___bpf_kprobe_args1(x) \
-	___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
-#define ___bpf_kprobe_args2(x, args...) \
-	___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
-#define ___bpf_kprobe_args3(x, args...) \
-	___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
-#define ___bpf_kprobe_args4(x, args...) \
-	___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
-#define ___bpf_kprobe_args5(x, args...) \
-	___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
-#define ___bpf_kprobe_args(args...) \
-	___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
+#define ___bpf_kprobe_args0()           ctx
+#define ___bpf_kprobe_args1(x)          ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args(args...)     ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
 
 /*
  * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
@@ -432,11 +383,9 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 static __attribute__((always_inline)) typeof(name(0))			    \
 ____##name(struct pt_regs *ctx, ##args)
 
-#define ___bpf_kretprobe_args0() ctx
-#define ___bpf_kretprobe_args1(x) \
-	___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
-#define ___bpf_kretprobe_args(args...) \
-	___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
+#define ___bpf_kretprobe_args0()       ctx
+#define ___bpf_kretprobe_args1(x)      ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
+#define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
 
 /*
  * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional

tools/lib/bpf/btf.c

@@ -57,7 +57,7 @@ struct btf {
 	 * representation is broken up into three independently allocated
 	 * memory regions to be able to modify them independently.
 	 * raw_data is nulled out at that point, but can be later allocated
-	 * and cached again if user calls btf__get_raw_data(), at which point
+	 * and cached again if user calls btf__raw_data(), at which point
 	 * raw_data will contain a contiguous copy of header, types, and
 	 * strings:
 	 *
@@ -189,12 +189,17 @@ int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_
 	return 0;
 }
 
+static void *btf_add_type_offs_mem(struct btf *btf, size_t add_cnt)
+{
+	return libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
+			      btf->nr_types, BTF_MAX_NR_TYPES, add_cnt);
+}
+
 static int btf_add_type_idx_entry(struct btf *btf, __u32 type_off)
 {
 	__u32 *p;
 
-	p = libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
-			   btf->nr_types, BTF_MAX_NR_TYPES, 1);
+	p = btf_add_type_offs_mem(btf, 1);
 	if (!p)
 		return -ENOMEM;
 
@@ -294,6 +299,7 @@ static int btf_type_size(const struct btf_type *t)
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_FLOAT:
+	case BTF_KIND_TYPE_TAG:
 		return base_size;
 	case BTF_KIND_INT:
 		return base_size + sizeof(__u32);
@@ -310,6 +316,8 @@ static int btf_type_size(const struct btf_type *t)
 		return base_size + sizeof(struct btf_var);
 	case BTF_KIND_DATASEC:
 		return base_size + vlen * sizeof(struct btf_var_secinfo);
+	case BTF_KIND_DECL_TAG:
+		return base_size + sizeof(struct btf_decl_tag);
 	default:
 		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
 		return -EINVAL;
@@ -342,6 +350,7 @@ static int btf_bswap_type_rest(struct btf_type *t)
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_FLOAT:
+	case BTF_KIND_TYPE_TAG:
 		return 0;
 	case BTF_KIND_INT:
 		*(__u32 *)(t + 1) = bswap_32(*(__u32 *)(t + 1));
@@ -382,6 +391,9 @@ static int btf_bswap_type_rest(struct btf_type *t)
 			v->size = bswap_32(v->size);
 		}
 		return 0;
+	case BTF_KIND_DECL_TAG:
+		btf_decl_tag(t)->component_idx = bswap_32(btf_decl_tag(t)->component_idx);
+		return 0;
 	default:
 		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
 		return -EINVAL;
@@ -431,13 +443,18 @@ __u32 btf__get_nr_types(const struct btf *btf)
 	return btf->start_id + btf->nr_types - 1;
 }
 
+__u32 btf__type_cnt(const struct btf *btf)
+{
+	return btf->start_id + btf->nr_types;
+}
+
 const struct btf *btf__base_btf(const struct btf *btf)
 {
 	return btf->base_btf;
 }
 
 /* internal helper returning non-const pointer to a type */
-struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id)
+struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id)
 {
 	if (type_id == 0)
 		return &btf_void;
@@ -462,8 +479,8 @@ static int determine_ptr_size(const struct btf *btf)
 	if (btf->base_btf && btf->base_btf->ptr_sz > 0)
 		return btf->base_btf->ptr_sz;
 
-	n = btf__get_nr_types(btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(btf, i);
 		if (!btf_is_int(t))
 			continue;
@@ -523,9 +540,9 @@ int btf__set_pointer_size(struct btf *btf, size_t ptr_sz)
 
 static bool is_host_big_endian(void)
 {
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	return false;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	return true;
 #else
 # error "Unrecognized __BYTE_ORDER__"
@@ -592,6 +609,8 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		case BTF_KIND_CONST:
 		case BTF_KIND_RESTRICT:
 		case BTF_KIND_VAR:
+		case BTF_KIND_DECL_TAG:
+		case BTF_KIND_TYPE_TAG:
 			type_id = t->type;
 			break;
 		case BTF_KIND_ARRAY:
@@ -633,6 +652,7 @@ int btf__align_of(const struct btf *btf, __u32 id)
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPE_TAG:
 		return btf__align_of(btf, t->type);
 	case BTF_KIND_ARRAY:
 		return btf__align_of(btf, btf_array(t)->type);
@@ -679,12 +699,12 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id)
 
 __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 {
-	__u32 i, nr_types = btf__get_nr_types(btf);
+	__u32 i, nr_types = btf__type_cnt(btf);
 
 	if (!strcmp(type_name, "void"))
 		return 0;
 
-	for (i = 1; i <= nr_types; i++) {
+	for (i = 1; i < nr_types; i++) {
 		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name = btf__name_by_offset(btf, t->name_off);
 
@@ -695,15 +715,15 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 	return libbpf_err(-ENOENT);
 }
 
-__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
-			     __u32 kind)
+static __s32 btf_find_by_name_kind(const struct btf *btf, int start_id,
+				   const char *type_name, __u32 kind)
 {
-	__u32 i, nr_types = btf__get_nr_types(btf);
+	__u32 i, nr_types = btf__type_cnt(btf);
 
 	if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void"))
 		return 0;
 
-	for (i = 1; i <= nr_types; i++) {
+	for (i = start_id; i < nr_types; i++) {
 		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name;
 
@@ -717,6 +737,18 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
 	return libbpf_err(-ENOENT);
 }
 
+__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
+				 __u32 kind)
+{
+	return btf_find_by_name_kind(btf, btf->start_id, type_name, kind);
+}
+
+__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
+			     __u32 kind)
+{
+	return btf_find_by_name_kind(btf, 1, type_name, kind);
+}
+
 static bool btf_is_modifiable(const struct btf *btf)
 {
 	return (void *)btf->hdr != btf->raw_data;
@@ -764,7 +796,7 @@ static struct btf *btf_new_empty(struct btf *base_btf)
 
 	if (base_btf) {
 		btf->base_btf = base_btf;
-		btf->start_id = btf__get_nr_types(base_btf) + 1;
+		btf->start_id = btf__type_cnt(base_btf);
 		btf->start_str_off = base_btf->hdr->str_len;
 	}
 
@@ -814,7 +846,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
 
 	if (base_btf) {
 		btf->base_btf = base_btf;
-		btf->start_id = btf__get_nr_types(base_btf) + 1;
+		btf->start_id = btf__type_cnt(base_btf);
 		btf->start_str_off = base_btf->hdr->str_len;
 	}
 
@@ -869,7 +901,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
 	}
 
-	fd = open(path, O_RDONLY);
+	fd = open(path, O_RDONLY | O_CLOEXEC);
 	if (fd < 0) {
 		err = -errno;
 		pr_warn("failed to open %s: %s\n", path, strerror(errno));
@@ -1090,149 +1122,88 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf)
 	return libbpf_ptr(btf_parse(path, base_btf, NULL));
 }
 
-static int compare_vsi_off(const void *_a, const void *_b)
-{
-	const struct btf_var_secinfo *a = _a;
-	const struct btf_var_secinfo *b = _b;
-
-	return a->offset - b->offset;
-}
-
-static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
-			     struct btf_type *t)
-{
-	__u32 size = 0, off = 0, i, vars = btf_vlen(t);
-	const char *name = btf__name_by_offset(btf, t->name_off);
-	const struct btf_type *t_var;
-	struct btf_var_secinfo *vsi;
-	const struct btf_var *var;
-	int ret;
-
-	if (!name) {
-		pr_debug("No name found in string section for DATASEC kind.\n");
-		return -ENOENT;
-	}
-
-	/* .extern datasec size and var offsets were set correctly during
-	 * extern collection step, so just skip straight to sorting variables
-	 */
-	if (t->size)
-		goto sort_vars;
-
-	ret = bpf_object__section_size(obj, name, &size);
-	if (ret || !size || (t->size && t->size != size)) {
-		pr_debug("Invalid size for section %s: %u bytes\n", name, size);
-		return -ENOENT;
-	}
-
-	t->size = size;
-
-	for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
-		t_var = btf__type_by_id(btf, vsi->type);
-		var = btf_var(t_var);
-
-		if (!btf_is_var(t_var)) {
-			pr_debug("Non-VAR type seen in section %s\n", name);
-			return -EINVAL;
-		}
-
-		if (var->linkage == BTF_VAR_STATIC)
-			continue;
-
-		name = btf__name_by_offset(btf, t_var->name_off);
-		if (!name) {
-			pr_debug("No name found in string section for VAR kind\n");
-			return -ENOENT;
-		}
-
-		ret = bpf_object__variable_offset(obj, name, &off);
-		if (ret) {
-			pr_debug("No offset found in symbol table for VAR %s\n",
-				 name);
-			return -ENOENT;
-		}
-
-		vsi->offset = off;
-	}
-
-sort_vars:
-	qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off);
-	return 0;
-}
-
-int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
-{
-	int err = 0;
-	__u32 i;
-
-	for (i = 1; i <= btf->nr_types; i++) {
-		struct btf_type *t = btf_type_by_id(btf, i);
-
-		/* Loader needs to fix up some of the things compiler
-		 * couldn't get its hands on while emitting BTF. This
-		 * is section size and global variable offset. We use
-		 * the info from the ELF itself for this purpose.
-		 */
-		if (btf_is_datasec(t)) {
-			err = btf_fixup_datasec(obj, btf, t);
-			if (err)
-				break;
-		}
-	}
-
-	return libbpf_err(err);
-}
-
 static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
 
-int btf__load_into_kernel(struct btf *btf)
+int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level)
 {
-	__u32 log_buf_size = 0, raw_size;
-	char *log_buf = NULL;
+	LIBBPF_OPTS(bpf_btf_load_opts, opts);
+	__u32 buf_sz = 0, raw_size;
+	char *buf = NULL, *tmp;
 	void *raw_data;
 	int err = 0;
 
 	if (btf->fd >= 0)
 		return libbpf_err(-EEXIST);
+	if (log_sz && !log_buf)
+		return libbpf_err(-EINVAL);
 
-retry_load:
-	if (log_buf_size) {
-		log_buf = malloc(log_buf_size);
-		if (!log_buf)
-			return libbpf_err(-ENOMEM);
-
-		*log_buf = 0;
-	}
-
+	/* cache native raw data representation */
 	raw_data = btf_get_raw_data(btf, &raw_size, false);
 	if (!raw_data) {
 		err = -ENOMEM;
 		goto done;
 	}
-	/* cache native raw data representation */
 	btf->raw_size = raw_size;
 	btf->raw_data = raw_data;
 
-	btf->fd = bpf_load_btf(raw_data, raw_size, log_buf, log_buf_size, false);
-	if (btf->fd < 0) {
-		if (!log_buf || errno == ENOSPC) {
-			log_buf_size = max((__u32)BPF_LOG_BUF_SIZE,
-					   log_buf_size << 1);
-			free(log_buf);
-			goto retry_load;
+retry_load:
+	/* if log_level is 0, we won't provide log_buf/log_size to the kernel,
+	 * initially. Only if BTF loading fails, we bump log_level to 1 and
+	 * retry, using either auto-allocated or custom log_buf. This way
+	 * non-NULL custom log_buf provides a buffer just in case, but hopes
+	 * for successful load and no need for log_buf.
+	 */
+	if (log_level) {
+		/* if caller didn't provide custom log_buf, we'll keep
+		 * allocating our own progressively bigger buffers for BTF
+		 * verification log
+		 */
+		if (!log_buf) {
+			buf_sz = max((__u32)BPF_LOG_BUF_SIZE, buf_sz * 2);
+			tmp = realloc(buf, buf_sz);
+			if (!tmp) {
+				err = -ENOMEM;
+				goto done;
+			}
+			buf = tmp;
+			buf[0] = '\0';
 		}
 
+		opts.log_buf = log_buf ? log_buf : buf;
+		opts.log_size = log_buf ? log_sz : buf_sz;
+		opts.log_level = log_level;
+	}
+
+	btf->fd = bpf_btf_load(raw_data, raw_size, &opts);
+	if (btf->fd < 0) {
+		/* time to turn on verbose mode and try again */
+		if (log_level == 0) {
+			log_level = 1;
+			goto retry_load;
+		}
+		/* only retry if caller didn't provide custom log_buf, but
+		 * make sure we can never overflow buf_sz
+		 */
+		if (!log_buf && errno == ENOSPC && buf_sz <= UINT_MAX / 2)
+			goto retry_load;
+
 		err = -errno;
-		pr_warn("Error loading BTF: %s(%d)\n", strerror(errno), errno);
-		if (*log_buf)
-			pr_warn("%s\n", log_buf);
-		goto done;
+		pr_warn("BTF loading error: %d\n", err);
+		/* don't print out contents of custom log_buf */
+		if (!log_buf && buf[0])
+			pr_warn("-- BEGIN BTF LOAD LOG ---\n%s\n-- END BTF LOAD LOG --\n", buf);
 	}
 
 done:
-	free(log_buf);
+	free(buf);
 	return libbpf_err(err);
 }
+
+int btf__load_into_kernel(struct btf *btf)
+{
+	return btf_load_into_kernel(btf, NULL, 0, 0);
+}
+
 int btf__load(struct btf *) __attribute__((alias("btf__load_into_kernel")));
 
 int btf__fd(const struct btf *btf)
@@ -1300,7 +1271,7 @@ static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endi
 	return NULL;
 }
 
-const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
+const void *btf__raw_data(const struct btf *btf_ro, __u32 *size)
 {
 	struct btf *btf = (struct btf *)btf_ro;
 	__u32 data_sz;
@@ -1308,7 +1279,7 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 
 	data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian);
 	if (!data)
-		return errno = -ENOMEM, NULL;
+		return errno = ENOMEM, NULL;
 
 	btf->raw_size = data_sz;
 	if (btf->swapped_endian)
@@ -1319,6 +1290,9 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 	return data;
 }
 
+__attribute__((alias("btf__raw_data")))
+const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
+
 const char *btf__str_by_offset(const struct btf *btf, __u32 offset)
 {
 	if (offset < btf->start_str_off)
@@ -1691,6 +1665,111 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t
 	return btf_commit_type(btf, sz);
 }
 
+static int btf_rewrite_type_ids(__u32 *type_id, void *ctx)
+{
+	struct btf *btf = ctx;
+
+	if (!*type_id) /* nothing to do for VOID references */
+		return 0;
+
+	/* we haven't updated btf's type count yet, so
+	 * btf->start_id + btf->nr_types - 1 is the type ID offset we should
+	 * add to all newly added BTF types
+	 */
+	*type_id += btf->start_id + btf->nr_types - 1;
+	return 0;
+}
+
+int btf__add_btf(struct btf *btf, const struct btf *src_btf)
+{
+	struct btf_pipe p = { .src = src_btf, .dst = btf };
+	int data_sz, sz, cnt, i, err, old_strs_len;
+	__u32 *off;
+	void *t;
+
+	/* appending split BTF isn't supported yet */
+	if (src_btf->base_btf)
+		return libbpf_err(-ENOTSUP);
+
+	/* deconstruct BTF, if necessary, and invalidate raw_data */
+	if (btf_ensure_modifiable(btf))
+		return libbpf_err(-ENOMEM);
+
+	/* remember original strings section size if we have to roll back
+	 * partial strings section changes
+	 */
+	old_strs_len = btf->hdr->str_len;
+
+	data_sz = src_btf->hdr->type_len;
+	cnt = btf__type_cnt(src_btf) - 1;
+
+	/* pre-allocate enough memory for new types */
+	t = btf_add_type_mem(btf, data_sz);
+	if (!t)
+		return libbpf_err(-ENOMEM);
+
+	/* pre-allocate enough memory for type offset index for new types */
+	off = btf_add_type_offs_mem(btf, cnt);
+	if (!off)
+		return libbpf_err(-ENOMEM);
+
+	/* bulk copy types data for all types from src_btf */
+	memcpy(t, src_btf->types_data, data_sz);
+
+	for (i = 0; i < cnt; i++) {
+		sz = btf_type_size(t);
+		if (sz < 0) {
+			/* unlikely, has to be corrupted src_btf */
+			err = sz;
+			goto err_out;
+		}
+
+		/* fill out type ID to type offset mapping for lookups by type ID */
+		*off = t - btf->types_data;
+
+		/* add, dedup, and remap strings referenced by this BTF type */
+		err = btf_type_visit_str_offs(t, btf_rewrite_str, &p);
+		if (err)
+			goto err_out;
+
+		/* remap all type IDs referenced from this BTF type */
+		err = btf_type_visit_type_ids(t, btf_rewrite_type_ids, btf);
+		if (err)
+			goto err_out;
+
+		/* go to next type data and type offset index entry */
+		t += sz;
+		off++;
+	}
+
+	/* Up until now any of the copied type data was effectively invisible,
+	 * so if we exited early before this point due to error, BTF would be
+	 * effectively unmodified. There would be extra internal memory
+	 * pre-allocated, but it would not be available for querying.  But now
+	 * that we've copied and rewritten all the data successfully, we can
+	 * update type count and various internal offsets and sizes to
+	 * "commit" the changes and made them visible to the outside world.
+	 */
+	btf->hdr->type_len += data_sz;
+	btf->hdr->str_off += data_sz;
+	btf->nr_types += cnt;
+
+	/* return type ID of the first added BTF type */
+	return btf->start_id + btf->nr_types - cnt;
+err_out:
+	/* zero out preallocated memory as if it was just allocated with
+	 * libbpf_add_mem()
+	 */
+	memset(btf->types_data + btf->hdr->type_len, 0, data_sz);
+	memset(btf->strs_data + old_strs_len, 0, btf->hdr->str_len - old_strs_len);
+
+	/* and now restore original strings section size; types data size
+	 * wasn't modified, so doesn't need restoring, see big comment above */
+	btf->hdr->str_len = old_strs_len;
+
+	return libbpf_err(err);
+}
+
 /*
  * Append new BTF_KIND_INT type with:
  *   - *name* - non-empty, non-NULL type name;
@@ -1939,7 +2018,7 @@ int btf__add_union(struct btf *btf, const char *name, __u32 byte_sz)
 
 static struct btf_type *btf_last_type(struct btf *btf)
 {
-	return btf_type_by_id(btf, btf__get_nr_types(btf));
+	return btf_type_by_id(btf, btf__type_cnt(btf) - 1);
 }
 
 /*
@@ -2192,6 +2271,22 @@ int btf__add_restrict(struct btf *btf, int ref_type_id)
 	return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id);
 }
 
+/*
+ * Append new BTF_KIND_TYPE_TAG type with:
+ *   - *value*, non-empty/non-NULL tag value;
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id)
+{
+	if (!value|| !value[0])
+		return libbpf_err(-EINVAL);
+
+	return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id);
+}
+
 /*
  * Append new BTF_KIND_FUNC type with:
  *   - *name*, non-empty/non-NULL name;
@@ -2446,6 +2541,48 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __
 	return 0;
 }
 
+/*
+ * Append new BTF_KIND_DECL_TAG type with:
+ *   - *value* - non-empty/non-NULL string;
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ *   - *component_idx* - -1 for tagging reference type, otherwise struct/union
+ *     member or function argument index;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
+		 int component_idx)
+{
+	struct btf_type *t;
+	int sz, value_off;
+
+	if (!value || !value[0] || component_idx < -1)
+		return libbpf_err(-EINVAL);
+
+	if (validate_type_id(ref_type_id))
+		return libbpf_err(-EINVAL);
+
+	if (btf_ensure_modifiable(btf))
+		return libbpf_err(-ENOMEM);
+
+	sz = sizeof(struct btf_type) + sizeof(struct btf_decl_tag);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return libbpf_err(-ENOMEM);
+
+	value_off = btf__add_str(btf, value);
+	if (value_off < 0)
+		return value_off;
+
+	t->name_off = value_off;
+	t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false);
+	t->type = ref_type_id;
+	btf_decl_tag(t)->component_idx = component_idx;
+
+	return btf_commit_type(btf, sz);
+}
+
 struct btf_ext_sec_setup_param {
 	__u32 off;
 	__u32 len;
@@ -2761,8 +2898,7 @@ __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext)
 
 struct btf_dedup;
 
-static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
-				       const struct btf_dedup_opts *opts);
+static struct btf_dedup *btf_dedup_new(struct btf *btf, const struct btf_dedup_opts *opts);
 static void btf_dedup_free(struct btf_dedup *d);
 static int btf_dedup_prep(struct btf_dedup *d);
 static int btf_dedup_strings(struct btf_dedup *d);
@@ -2909,12 +3045,17 @@ static int btf_dedup_remap_types(struct btf_dedup *d);
  * deduplicating structs/unions is described in greater details in comments for
  * `btf_dedup_is_equiv` function.
  */
-int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
-	       const struct btf_dedup_opts *opts)
+
+DEFAULT_VERSION(btf__dedup_v0_6_0, btf__dedup, LIBBPF_0.6.0)
+int btf__dedup_v0_6_0(struct btf *btf, const struct btf_dedup_opts *opts)
 {
-	struct btf_dedup *d = btf_dedup_new(btf, btf_ext, opts);
+	struct btf_dedup *d;
 	int err;
 
+	if (!OPTS_VALID(opts, btf_dedup_opts))
+		return libbpf_err(-EINVAL);
+
+	d = btf_dedup_new(btf, opts);
 	if (IS_ERR(d)) {
 		pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d));
 		return libbpf_err(-EINVAL);
@@ -2966,6 +3107,19 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
 	return libbpf_err(err);
 }
 
+COMPAT_VERSION(btf__dedup_deprecated, btf__dedup, LIBBPF_0.0.2)
+int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *unused_opts)
+{
+	LIBBPF_OPTS(btf_dedup_opts, opts, .btf_ext = btf_ext);
+
+	if (unused_opts) {
+		pr_warn("please use new version of btf__dedup() that supports options\n");
+		return libbpf_err(-ENOTSUP);
+	}
+
+	return btf__dedup(btf, &opts);
+}
+
 #define BTF_UNPROCESSED_ID ((__u32)-1)
 #define BTF_IN_PROGRESS_ID ((__u32)-2)
 
@@ -3078,8 +3232,7 @@ static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx)
 	return k1 == k2;
 }
 
-static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
-				       const struct btf_dedup_opts *opts)
+static struct btf_dedup *btf_dedup_new(struct btf *btf, const struct btf_dedup_opts *opts)
 {
 	struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup));
 	hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn;
@@ -3088,13 +3241,11 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 	if (!d)
 		return ERR_PTR(-ENOMEM);
 
-	d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds;
-	/* dedup_table_size is now used only to force collisions in tests */
-	if (opts && opts->dedup_table_size == 1)
+	if (OPTS_GET(opts, force_collisions, false))
 		hash_fn = btf_dedup_collision_hash_fn;
 
 	d->btf = btf;
-	d->btf_ext = btf_ext;
+	d->btf_ext = OPTS_GET(opts, btf_ext, NULL);
 
 	d->dedup_table = hashmap__new(hash_fn, btf_dedup_equal_fn, NULL);
 	if (IS_ERR(d->dedup_table)) {
@@ -3103,7 +3254,7 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 		goto done;
 	}
 
-	type_cnt = btf__get_nr_types(btf) + 1;
+	type_cnt = btf__type_cnt(btf);
 	d->map = malloc(sizeof(__u32) * type_cnt);
 	if (!d->map) {
 		err = -ENOMEM;
@@ -3264,8 +3415,8 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2)
 	       t1->size == t2->size;
 }
 
-/* Calculate type signature hash of INT. */
-static long btf_hash_int(struct btf_type *t)
+/* Calculate type signature hash of INT or TAG. */
+static long btf_hash_int_decl_tag(struct btf_type *t)
 {
 	__u32 info = *(__u32 *)(t + 1);
 	long h;
@@ -3275,8 +3426,8 @@ static long btf_hash_int(struct btf_type *t)
 	return h;
 }
 
-/* Check structural equality of two INTs. */
-static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
+/* Check structural equality of two INTs or TAGs. */
+static bool btf_equal_int_tag(struct btf_type *t1, struct btf_type *t2)
 {
 	__u32 info1, info2;
 
@@ -3540,10 +3691,12 @@ static int btf_dedup_prep(struct btf_dedup *d)
 		case BTF_KIND_TYPEDEF:
 		case BTF_KIND_FUNC:
 		case BTF_KIND_FLOAT:
+		case BTF_KIND_TYPE_TAG:
 			h = btf_hash_common(t);
 			break;
 		case BTF_KIND_INT:
-			h = btf_hash_int(t);
+		case BTF_KIND_DECL_TAG:
+			h = btf_hash_int_decl_tag(t);
 			break;
 		case BTF_KIND_ENUM:
 			h = btf_hash_enum(t);
@@ -3598,14 +3751,16 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_FUNC_PROTO:
 	case BTF_KIND_VAR:
 	case BTF_KIND_DATASEC:
+	case BTF_KIND_DECL_TAG:
+	case BTF_KIND_TYPE_TAG:
 		return 0;
 
 	case BTF_KIND_INT:
-		h = btf_hash_int(t);
+		h = btf_hash_int_decl_tag(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
-			if (btf_equal_int(t, cand)) {
+			if (btf_equal_int_tag(t, cand)) {
 				new_id = cand_id;
 				break;
 			}
@@ -3621,8 +3776,6 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 				new_id = cand_id;
 				break;
 			}
-			if (d->opts.dont_resolve_fwds)
-				continue;
 			if (btf_compat_enum(t, cand)) {
 				if (btf_is_enum_fwd(t)) {
 					/* resolve fwd to full enum */
@@ -3902,8 +4055,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return 0;
 
 	/* FWD <--> STRUCT/UNION equivalence check, if enabled */
-	if (!d->opts.dont_resolve_fwds
-	    && (cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD)
+	if ((cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD)
 	    && cand_kind != canon_kind) {
 		__u16 real_kind;
 		__u16 fwd_kind;
@@ -3926,13 +4078,10 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 
 	switch (cand_kind) {
 	case BTF_KIND_INT:
-		return btf_equal_int(cand_type, canon_type);
+		return btf_equal_int_tag(cand_type, canon_type);
 
 	case BTF_KIND_ENUM:
-		if (d->opts.dont_resolve_fwds)
-			return btf_equal_enum(cand_type, canon_type);
-		else
-			return btf_compat_enum(cand_type, canon_type);
+		return btf_compat_enum(cand_type, canon_type);
 
 	case BTF_KIND_FWD:
 	case BTF_KIND_FLOAT:
@@ -3944,6 +4093,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 	case BTF_KIND_PTR:
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
+	case BTF_KIND_TYPE_TAG:
 		if (cand_type->info != canon_type->info)
 			return 0;
 		return btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
@@ -4239,6 +4389,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_PTR:
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
+	case BTF_KIND_TYPE_TAG:
 		ref_type_id = btf_dedup_ref_type(d, t->type);
 		if (ref_type_id < 0)
 			return ref_type_id;
@@ -4255,6 +4406,23 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		}
 		break;
 
+	case BTF_KIND_DECL_TAG:
+		ref_type_id = btf_dedup_ref_type(d, t->type);
+		if (ref_type_id < 0)
+			return ref_type_id;
+		t->type = ref_type_id;
+
+		h = btf_hash_int_decl_tag(t);
+		for_each_dedup_cand(d, hash_entry, h) {
+			cand_id = (__u32)(long)hash_entry->value;
+			cand = btf_type_by_id(d->btf, cand_id);
+			if (btf_equal_int_tag(t, cand)) {
+				new_id = cand_id;
+				break;
+			}
+		}
+		break;
+
 	case BTF_KIND_ARRAY: {
 		struct btf_array *info = btf_array(t);
 
@@ -4527,6 +4695,8 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_VAR:
+	case BTF_KIND_DECL_TAG:
+	case BTF_KIND_TYPE_TAG:
 		return visit(&t->type, ctx);
 
 	case BTF_KIND_ARRAY: {

tools/lib/bpf/btf.h

@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 /* Copyright (c) 2018 Facebook */
+/*! \file */
 
 #ifndef __LIBBPF_BTF_H
 #define __LIBBPF_BTF_H
@@ -30,11 +31,80 @@ enum btf_endianness {
 	BTF_BIG_ENDIAN = 1,
 };
 
+/**
+ * @brief **btf__free()** frees all data of a BTF object
+ * @param btf BTF object to free
+ */
 LIBBPF_API void btf__free(struct btf *btf);
 
+/**
+ * @brief **btf__new()** creates a new instance of a BTF object from the raw
+ * bytes of an ELF's BTF section
+ * @param data raw bytes
+ * @param size number of bytes passed in `data`
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new(const void *data, __u32 size);
+
+/**
+ * @brief **btf__new_split()** create a new instance of a BTF object from the
+ * provided raw data bytes. It takes another BTF instance, **base_btf**, which
+ * serves as a base BTF, which is extended by types in a newly created BTF
+ * instance
+ * @param data raw bytes
+ * @param size length of raw bytes
+ * @param base_btf the base BTF object
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * If *base_btf* is NULL, `btf__new_split()` is equivalent to `btf__new()` and
+ * creates non-split BTF.
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf);
+
+/**
+ * @brief **btf__new_empty()** creates an empty BTF object.  Use
+ * `btf__add_*()` to populate such BTF object.
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new_empty(void);
+
+/**
+ * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an
+ * ELF BTF section except with a base BTF on top of which split BTF should be
+ * based
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * If *base_btf* is NULL, `btf__new_empty_split()` is equivalent to
+ * `btf__new_empty()` and creates non-split BTF.
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf);
 
 LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
@@ -50,16 +120,21 @@ LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
 
 LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id);
 LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf);
+LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_from_kernel_by_id instead")
 LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
 
+LIBBPF_DEPRECATED_SINCE(0, 6, "intended for internal libbpf use only")
 LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
+LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_into_kernel instead")
 LIBBPF_API int btf__load(struct btf *btf);
 LIBBPF_API int btf__load_into_kernel(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
 				   const char *type_name);
 LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf,
 					const char *type_name, __u32 kind);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__type_cnt() instead; note that btf__get_nr_types() == btf__type_cnt() - 1")
 LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf);
+LIBBPF_API __u32 btf__type_cnt(const struct btf *btf);
 LIBBPF_API const struct btf *btf__base_btf(const struct btf *btf);
 LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
 						  __u32 id);
@@ -72,7 +147,9 @@ LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id);
 LIBBPF_API int btf__fd(const struct btf *btf);
 LIBBPF_API void btf__set_fd(struct btf *btf, int fd);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__raw_data() instead")
 LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
+LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
@@ -101,6 +178,28 @@ LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
 LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
 LIBBPF_API int btf__add_type(struct btf *btf, const struct btf *src_btf,
 			     const struct btf_type *src_type);
+/**
+ * @brief **btf__add_btf()** appends all the BTF types from *src_btf* into *btf*
+ * @param btf BTF object which all the BTF types and strings are added to
+ * @param src_btf BTF object which all BTF types and referenced strings are copied from
+ * @return BTF type ID of the first appended BTF type, or negative error code
+ *
+ * **btf__add_btf()** can be used to simply and efficiently append the entire
+ * contents of one BTF object to another one. All the BTF type data is copied
+ * over, all referenced type IDs are adjusted by adding a necessary ID offset.
+ * Only strings referenced from BTF types are copied over and deduplicated, so
+ * if there were some unused strings in *src_btf*, those won't be copied over,
+ * which is consistent with the general string deduplication semantics of BTF
+ * writing APIs.
+ *
+ * If any error is encountered during this process, the contents of *btf* is
+ * left intact, which means that **btf__add_btf()** follows the transactional
+ * semantics and the operation as a whole is all-or-nothing.
+ *
+ * *src_btf* has to be non-split BTF, as of now copying types from split BTF
+ * is not supported and will result in -ENOTSUP error code returned.
+ */
+LIBBPF_API int btf__add_btf(struct btf *btf, const struct btf *src_btf);
 
 LIBBPF_API int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding);
 LIBBPF_API int btf__add_float(struct btf *btf, const char *name, size_t byte_sz);
@@ -128,6 +227,7 @@ LIBBPF_API int btf__add_typedef(struct btf *btf, const char *name, int ref_type_
 LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id);
 LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id);
 LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id);
+LIBBPF_API int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id);
 
 /* func and func_proto construction APIs */
 LIBBPF_API int btf__add_func(struct btf *btf, const char *name,
@@ -141,26 +241,91 @@ LIBBPF_API int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz
 LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id,
 					 __u32 offset, __u32 byte_sz);
 
-struct btf_dedup_opts {
-	unsigned int dedup_table_size;
-	bool dont_resolve_fwds;
-};
+/* tag construction API */
+LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
+			    int component_idx);
 
-LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
-			  const struct btf_dedup_opts *opts);
+struct btf_dedup_opts {
+	size_t sz;
+	/* optional .BTF.ext info to dedup along the main BTF info */
+	struct btf_ext *btf_ext;
+	/* force hash collisions (used for testing) */
+	bool force_collisions;
+	size_t :0;
+};
+#define btf_dedup_opts__last_field force_collisions
+
+LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts);
+
+LIBBPF_API int btf__dedup_v0_6_0(struct btf *btf, const struct btf_dedup_opts *opts);
+
+LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__dedup() instead")
+LIBBPF_API int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *opts);
+#define btf__dedup(...) ___libbpf_overload(___btf_dedup, __VA_ARGS__)
+#define ___btf_dedup3(btf, btf_ext, opts) btf__dedup_deprecated(btf, btf_ext, opts)
+#define ___btf_dedup2(btf, opts) btf__dedup(btf, opts)
 
 struct btf_dump;
 
 struct btf_dump_opts {
-	void *ctx;
+	union {
+		size_t sz;
+		void *ctx; /* DEPRECATED: will be gone in v1.0 */
+	};
 };
 
 typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args);
 
 LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf,
-					  const struct btf_ext *btf_ext,
-					  const struct btf_dump_opts *opts,
-					  btf_dump_printf_fn_t printf_fn);
+					  btf_dump_printf_fn_t printf_fn,
+					  void *ctx,
+					  const struct btf_dump_opts *opts);
+
+LIBBPF_API struct btf_dump *btf_dump__new_v0_6_0(const struct btf *btf,
+						 btf_dump_printf_fn_t printf_fn,
+						 void *ctx,
+						 const struct btf_dump_opts *opts);
+
+LIBBPF_API struct btf_dump *btf_dump__new_deprecated(const struct btf *btf,
+						     const struct btf_ext *btf_ext,
+						     const struct btf_dump_opts *opts,
+						     btf_dump_printf_fn_t printf_fn);
+
+/* Choose either btf_dump__new() or btf_dump__new_deprecated() based on the
+ * type of 4th argument. If it's btf_dump's print callback, use deprecated
+ * API; otherwise, choose the new btf_dump__new(). ___libbpf_override()
+ * doesn't work here because both variants have 4 input arguments.
+ *
+ * (void *) casts are necessary to avoid compilation warnings about type
+ * mismatches, because even though __builtin_choose_expr() only ever evaluates
+ * one side the other side still has to satisfy type constraints (this is
+ * compiler implementation limitation which might be lifted eventually,
+ * according to the documentation). So passing struct btf_ext in place of
+ * btf_dump_printf_fn_t would be generating compilation warning.  Casting to
+ * void * avoids this issue.
+ *
+ * Also, two type compatibility checks for a function and function pointer are
+ * required because passing function reference into btf_dump__new() as
+ * btf_dump__new(..., my_callback, ...) and as btf_dump__new(...,
+ * &my_callback, ...) (not explicit ampersand in the latter case) actually
+ * differs as far as __builtin_types_compatible_p() is concerned. Thus two
+ * checks are combined to detect callback argument.
+ *
+ * The rest works just like in case of ___libbpf_override() usage with symbol
+ * versioning.
+ *
+ * C++ compilers don't support __builtin_types_compatible_p(), so at least
+ * don't screw up compilation for them and let C++ users pick btf_dump__new
+ * vs btf_dump__new_deprecated explicitly.
+ */
+#ifndef __cplusplus
+#define btf_dump__new(a1, a2, a3, a4) __builtin_choose_expr(				\
+	__builtin_types_compatible_p(typeof(a4), btf_dump_printf_fn_t) ||		\
+	__builtin_types_compatible_p(typeof(a4), void(void *, const char *, va_list)),	\
+	btf_dump__new_deprecated((void *)a1, (void *)a2, (void *)a3, (void *)a4),	\
+	btf_dump__new((void *)a1, (void *)a2, (void *)a3, (void *)a4))
+#endif
+
 LIBBPF_API void btf_dump__free(struct btf_dump *d);
 
 LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id);
@@ -300,7 +465,8 @@ static inline bool btf_is_mod(const struct btf_type *t)
 
 	return kind == BTF_KIND_VOLATILE ||
 	       kind == BTF_KIND_CONST ||
-	       kind == BTF_KIND_RESTRICT;
+	       kind == BTF_KIND_RESTRICT ||
+	       kind == BTF_KIND_TYPE_TAG;
 }
 
 static inline bool btf_is_func(const struct btf_type *t)
@@ -328,6 +494,16 @@ static inline bool btf_is_float(const struct btf_type *t)
 	return btf_kind(t) == BTF_KIND_FLOAT;
 }
 
+static inline bool btf_is_decl_tag(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_DECL_TAG;
+}
+
+static inline bool btf_is_type_tag(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_TYPE_TAG;
+}
+
 static inline __u8 btf_int_encoding(const struct btf_type *t)
 {
 	return BTF_INT_ENCODING(*(__u32 *)(t + 1));
@@ -396,6 +572,12 @@ btf_var_secinfos(const struct btf_type *t)
 	return (struct btf_var_secinfo *)(t + 1);
 }
 
+struct btf_decl_tag;
+static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t)
+{
+	return (struct btf_decl_tag *)(t + 1);
+}
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif

tools/lib/bpf/btf_dump.c

@@ -77,9 +77,8 @@ struct btf_dump_data {
 
 struct btf_dump {
 	const struct btf *btf;
-	const struct btf_ext *btf_ext;
 	btf_dump_printf_fn_t printf_fn;
-	struct btf_dump_opts opts;
+	void *cb_ctx;
 	int ptr_sz;
 	bool strip_mods;
 	bool skip_anon_defs;
@@ -138,29 +137,32 @@ static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...)
 	va_list args;
 
 	va_start(args, fmt);
-	d->printf_fn(d->opts.ctx, fmt, args);
+	d->printf_fn(d->cb_ctx, fmt, args);
 	va_end(args);
 }
 
 static int btf_dump_mark_referenced(struct btf_dump *d);
 static int btf_dump_resize(struct btf_dump *d);
 
-struct btf_dump *btf_dump__new(const struct btf *btf,
-			       const struct btf_ext *btf_ext,
-			       const struct btf_dump_opts *opts,
-			       btf_dump_printf_fn_t printf_fn)
+DEFAULT_VERSION(btf_dump__new_v0_6_0, btf_dump__new, LIBBPF_0.6.0)
+struct btf_dump *btf_dump__new_v0_6_0(const struct btf *btf,
+				      btf_dump_printf_fn_t printf_fn,
+				      void *ctx,
+				      const struct btf_dump_opts *opts)
 {
 	struct btf_dump *d;
 	int err;
 
+	if (!printf_fn)
+		return libbpf_err_ptr(-EINVAL);
+
 	d = calloc(1, sizeof(struct btf_dump));
 	if (!d)
 		return libbpf_err_ptr(-ENOMEM);
 
 	d->btf = btf;
-	d->btf_ext = btf_ext;
 	d->printf_fn = printf_fn;
-	d->opts.ctx = opts ? opts->ctx : NULL;
+	d->cb_ctx = ctx;
 	d->ptr_sz = btf__pointer_size(btf) ? : sizeof(void *);
 
 	d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL);
@@ -186,9 +188,20 @@ struct btf_dump *btf_dump__new(const struct btf *btf,
 	return libbpf_err_ptr(err);
 }
 
+COMPAT_VERSION(btf_dump__new_deprecated, btf_dump__new, LIBBPF_0.0.4)
+struct btf_dump *btf_dump__new_deprecated(const struct btf *btf,
+					  const struct btf_ext *btf_ext,
+					  const struct btf_dump_opts *opts,
+					  btf_dump_printf_fn_t printf_fn)
+{
+	if (!printf_fn)
+		return libbpf_err_ptr(-EINVAL);
+	return btf_dump__new_v0_6_0(btf, printf_fn, opts ? opts->ctx : NULL, opts);
+}
+
 static int btf_dump_resize(struct btf_dump *d)
 {
-	int err, last_id = btf__get_nr_types(d->btf);
+	int err, last_id = btf__type_cnt(d->btf) - 1;
 
 	if (last_id <= d->last_id)
 		return 0;
@@ -262,7 +275,7 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
 {
 	int err, i;
 
-	if (id > btf__get_nr_types(d->btf))
+	if (id >= btf__type_cnt(d->btf))
 		return libbpf_err(-EINVAL);
 
 	err = btf_dump_resize(d);
@@ -294,11 +307,11 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
  */
 static int btf_dump_mark_referenced(struct btf_dump *d)
 {
-	int i, j, n = btf__get_nr_types(d->btf);
+	int i, j, n = btf__type_cnt(d->btf);
 	const struct btf_type *t;
 	__u16 vlen;
 
-	for (i = d->last_id + 1; i <= n; i++) {
+	for (i = d->last_id + 1; i < n; i++) {
 		t = btf__type_by_id(d->btf, i);
 		vlen = btf_vlen(t);
 
@@ -316,6 +329,8 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
 		case BTF_KIND_TYPEDEF:
 		case BTF_KIND_FUNC:
 		case BTF_KIND_VAR:
+		case BTF_KIND_DECL_TAG:
+		case BTF_KIND_TYPE_TAG:
 			d->type_states[t->type].referenced = 1;
 			break;
 
@@ -559,6 +574,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPE_TAG:
 		return btf_dump_order_type(d, t->type, through_ptr);
 
 	case BTF_KIND_FUNC_PROTO: {
@@ -583,6 +599,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 	case BTF_KIND_FUNC:
 	case BTF_KIND_VAR:
 	case BTF_KIND_DATASEC:
+	case BTF_KIND_DECL_TAG:
 		d->type_states[id].order_state = ORDERED;
 		return 0;
 
@@ -732,6 +749,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPE_TAG:
 		btf_dump_emit_type(d, t->type, cont_id);
 		break;
 	case BTF_KIND_ARRAY:
@@ -1152,6 +1170,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id,
 		case BTF_KIND_CONST:
 		case BTF_KIND_RESTRICT:
 		case BTF_KIND_FUNC_PROTO:
+		case BTF_KIND_TYPE_TAG:
 			id = t->type;
 			break;
 		case BTF_KIND_ARRAY:
@@ -1320,6 +1339,11 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 		case BTF_KIND_RESTRICT:
 			btf_dump_printf(d, " restrict");
 			break;
+		case BTF_KIND_TYPE_TAG:
+			btf_dump_emit_mods(d, decls);
+			name = btf_name_of(d, t->name_off);
+			btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name);
+			break;
 		case BTF_KIND_ARRAY: {
 			const struct btf_array *a = btf_array(t);
 			const struct btf_type *next_t;
@@ -1560,29 +1584,28 @@ static int btf_dump_get_bitfield_value(struct btf_dump *d,
 				       __u64 *value)
 {
 	__u16 left_shift_bits, right_shift_bits;
-	__u8 nr_copy_bits, nr_copy_bytes;
 	const __u8 *bytes = data;
-	int sz = t->size;
+	__u8 nr_copy_bits;
 	__u64 num = 0;
 	int i;
 
 	/* Maximum supported bitfield size is 64 bits */
-	if (sz > 8) {
-		pr_warn("unexpected bitfield size %d\n", sz);
+	if (t->size > 8) {
+		pr_warn("unexpected bitfield size %d\n", t->size);
 		return -EINVAL;
 	}
 
 	/* Bitfield value retrieval is done in two steps; first relevant bytes are
 	 * stored in num, then we left/right shift num to eliminate irrelevant bits.
 	 */
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	for (i = t->size - 1; i >= 0; i--)
+		num = num * 256 + bytes[i];
 	nr_copy_bits = bit_sz + bits_offset;
-	nr_copy_bytes = t->size;
-#if __BYTE_ORDER == __LITTLE_ENDIAN
-	for (i = nr_copy_bytes - 1; i >= 0; i--)
-		num = num * 256 + bytes[i];
-#elif __BYTE_ORDER == __BIG_ENDIAN
-	for (i = 0; i < nr_copy_bytes; i++)
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	for (i = 0; i < t->size; i++)
 		num = num * 256 + bytes[i];
+	nr_copy_bits = t->size * 8 - bits_offset;
 #else
 # error "Unrecognized __BYTE_ORDER__"
 #endif
@@ -1656,9 +1679,15 @@ static int btf_dump_base_type_check_zero(struct btf_dump *d,
 	return 0;
 }
 
-static bool ptr_is_aligned(const void *data, int data_sz)
+static bool ptr_is_aligned(const struct btf *btf, __u32 type_id,
+			   const void *data)
 {
-	return ((uintptr_t)data) % data_sz == 0;
+	int alignment = btf__align_of(btf, type_id);
+
+	if (alignment == 0)
+		return false;
+
+	return ((uintptr_t)data) % alignment == 0;
 }
 
 static int btf_dump_int_data(struct btf_dump *d,
@@ -1669,9 +1698,10 @@ static int btf_dump_int_data(struct btf_dump *d,
 {
 	__u8 encoding = btf_int_encoding(t);
 	bool sign = encoding & BTF_INT_SIGNED;
+	char buf[16] __attribute__((aligned(16)));
 	int sz = t->size;
 
-	if (sz == 0) {
+	if (sz == 0 || sz > sizeof(buf)) {
 		pr_warn("unexpected size %d for id [%u]\n", sz, type_id);
 		return -EINVAL;
 	}
@@ -1679,8 +1709,10 @@ static int btf_dump_int_data(struct btf_dump *d,
 	/* handle packed int data - accesses of integers not aligned on
 	 * int boundaries can cause problems on some platforms.
 	 */
-	if (!ptr_is_aligned(data, sz))
-		return btf_dump_bitfield_data(d, t, data, 0, 0);
+	if (!ptr_is_aligned(d->btf, type_id, data)) {
+		memcpy(buf, data, sz);
+		data = buf;
+	}
 
 	switch (sz) {
 	case 16: {
@@ -1690,10 +1722,10 @@ static int btf_dump_int_data(struct btf_dump *d,
 		/* avoid use of __int128 as some 32-bit platforms do not
 		 * support it.
 		 */
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 		lsi = ints[0];
 		msi = ints[1];
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 		lsi = ints[1];
 		msi = ints[0];
 #else
@@ -1766,7 +1798,7 @@ static int btf_dump_float_data(struct btf_dump *d,
 	int sz = t->size;
 
 	/* handle unaligned data; copy to local union */
-	if (!ptr_is_aligned(data, sz)) {
+	if (!ptr_is_aligned(d->btf, type_id, data)) {
 		memcpy(&fl, data, sz);
 		flp = &fl;
 	}
@@ -1929,7 +1961,7 @@ static int btf_dump_ptr_data(struct btf_dump *d,
 			      __u32 id,
 			      const void *data)
 {
-	if (ptr_is_aligned(data, d->ptr_sz) && d->ptr_sz == sizeof(void *)) {
+	if (ptr_is_aligned(d->btf, id, data) && d->ptr_sz == sizeof(void *)) {
 		btf_dump_type_values(d, "%p", *(void **)data);
 	} else {
 		union ptr_data pt;
@@ -1949,10 +1981,8 @@ static int btf_dump_get_enum_value(struct btf_dump *d,
 				   __u32 id,
 				   __s64 *value)
 {
-	int sz = t->size;
-
 	/* handle unaligned enum value */
-	if (!ptr_is_aligned(data, sz)) {
+	if (!ptr_is_aligned(d->btf, id, data)) {
 		__u64 val;
 		int err;
 
@@ -2215,6 +2245,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d,
 	case BTF_KIND_FWD:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_FUNC_PROTO:
+	case BTF_KIND_DECL_TAG:
 		err = btf_dump_unsupported_data(d, t, id);
 		break;
 	case BTF_KIND_INT:
@@ -2290,8 +2321,8 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
 	if (!opts->indent_str)
 		d->typed_dump->indent_str[0] = '\t';
 	else
-		strncat(d->typed_dump->indent_str, opts->indent_str,
-			sizeof(d->typed_dump->indent_str) - 1);
+		libbpf_strlcpy(d->typed_dump->indent_str, opts->indent_str,
+			       sizeof(d->typed_dump->indent_str));
 
 	d->typed_dump->compact = OPTS_GET(opts, compact, false);
 	d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false);

tools/lib/bpf/gen_loader.c

@@ -5,6 +5,7 @@
 #include <string.h>
 #include <errno.h>
 #include <linux/filter.h>
+#include <sys/param.h>
 #include "btf.h"
 #include "bpf.h"
 #include "libbpf.h"
@@ -12,9 +13,12 @@
 #include "hashmap.h"
 #include "bpf_gen_internal.h"
 #include "skel_internal.h"
+#include <asm/byteorder.h>
 
-#define MAX_USED_MAPS 64
-#define MAX_USED_PROGS 32
+#define MAX_USED_MAPS	64
+#define MAX_USED_PROGS	32
+#define MAX_KFUNC_DESCS 256
+#define MAX_FD_ARRAY_SZ (MAX_USED_MAPS + MAX_KFUNC_DESCS)
 
 /* The following structure describes the stack layout of the loader program.
  * In addition R6 contains the pointer to context.
@@ -29,9 +33,8 @@
  */
 struct loader_stack {
 	__u32 btf_fd;
-	__u32 map_fd[MAX_USED_MAPS];
-	__u32 prog_fd[MAX_USED_PROGS];
 	__u32 inner_map_fd;
+	__u32 prog_fd[MAX_USED_PROGS];
 };
 
 #define stack_off(field) \
@@ -39,6 +42,11 @@ struct loader_stack {
 
 #define attr_field(attr, field) (attr + offsetof(union bpf_attr, field))
 
+static int blob_fd_array_off(struct bpf_gen *gen, int index)
+{
+	return gen->fd_array + index * sizeof(int);
+}
+
 static int realloc_insn_buf(struct bpf_gen *gen, __u32 size)
 {
 	size_t off = gen->insn_cur - gen->insn_start;
@@ -99,11 +107,15 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in
 	emit(gen, insn2);
 }
 
-void bpf_gen__init(struct bpf_gen *gen, int log_level)
+static int add_data(struct bpf_gen *gen, const void *data, __u32 size);
+static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off);
+
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps)
 {
-	size_t stack_sz = sizeof(struct loader_stack);
+	size_t stack_sz = sizeof(struct loader_stack), nr_progs_sz;
 	int i;
 
+	gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	gen->log_level = log_level;
 	/* save ctx pointer into R6 */
 	emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1));
@@ -115,19 +127,27 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level)
 	emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0));
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
 
+	/* amount of stack actually used, only used to calculate iterations, not stack offset */
+	nr_progs_sz = offsetof(struct loader_stack, prog_fd[nr_progs]);
 	/* jump over cleanup code */
 	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0,
-			      /* size of cleanup code below */
-			      (stack_sz / 4) * 3 + 2));
+			      /* size of cleanup code below (including map fd cleanup) */
+			      (nr_progs_sz / 4) * 3 + 2 +
+			      /* 6 insns for emit_sys_close_blob,
+			       * 6 insns for debug_regs in emit_sys_close_blob
+			       */
+			      nr_maps * (6 + (gen->log_level ? 6 : 0))));
 
 	/* remember the label where all error branches will jump to */
 	gen->cleanup_label = gen->insn_cur - gen->insn_start;
 	/* emit cleanup code: close all temp FDs */
-	for (i = 0; i < stack_sz; i += 4) {
+	for (i = 0; i < nr_progs_sz; i += 4) {
 		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i));
 		emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1));
 		emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close));
 	}
+	for (i = 0; i < nr_maps; i++)
+		emit_sys_close_blob(gen, blob_fd_array_off(gen, i));
 	/* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */
 	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
 	emit(gen, BPF_EXIT_INSN());
@@ -135,16 +155,47 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level)
 
 static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
 {
+	__u32 size8 = roundup(size, 8);
+	__u64 zero = 0;
 	void *prev;
 
-	if (realloc_data_buf(gen, size))
+	if (realloc_data_buf(gen, size8))
 		return 0;
 	prev = gen->data_cur;
-	memcpy(gen->data_cur, data, size);
-	gen->data_cur += size;
+	if (data) {
+		memcpy(gen->data_cur, data, size);
+		memcpy(gen->data_cur + size, &zero, size8 - size);
+	} else {
+		memset(gen->data_cur, 0, size8);
+	}
+	gen->data_cur += size8;
 	return prev - gen->data_start;
 }
 
+/* Get index for map_fd/btf_fd slot in reserved fd_array, or in data relative
+ * to start of fd_array. Caller can decide if it is usable or not.
+ */
+static int add_map_fd(struct bpf_gen *gen)
+{
+	if (gen->nr_maps == MAX_USED_MAPS) {
+		pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS);
+		gen->error = -E2BIG;
+		return 0;
+	}
+	return gen->nr_maps++;
+}
+
+static int add_kfunc_btf_fd(struct bpf_gen *gen)
+{
+	int cur;
+
+	if (gen->nr_fd_array == MAX_KFUNC_DESCS) {
+		cur = add_data(gen, NULL, sizeof(int));
+		return (cur - gen->fd_array) / sizeof(int);
+	}
+	return MAX_USED_MAPS + gen->nr_fd_array++;
+}
+
 static int insn_bytes_to_bpf_size(__u32 sz)
 {
 	switch (sz) {
@@ -166,14 +217,22 @@ static void emit_rel_store(struct bpf_gen *gen, int off, int data)
 	emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0));
 }
 
-/* *(u64 *)(blob + off) = (u64)(void *)(%sp + stack_off) */
-static void emit_rel_store_sp(struct bpf_gen *gen, int off, int stack_off)
+static void move_blob2blob(struct bpf_gen *gen, int off, int size, int blob_off)
 {
-	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_10));
-	emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, stack_off));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_2, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_off));
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_2, 0));
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
 					 0, 0, 0, off));
-	emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0));
+}
+
+static void move_blob2ctx(struct bpf_gen *gen, int ctx_off, int size, int blob_off)
+{
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_off));
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_1, 0));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_6, BPF_REG_0, ctx_off));
 }
 
 static void move_ctx2blob(struct bpf_gen *gen, int off, int size, int ctx_off,
@@ -308,10 +367,16 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off)
 	__emit_sys_close(gen);
 }
 
-int bpf_gen__finish(struct bpf_gen *gen)
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 {
 	int i;
 
+	if (nr_progs < gen->nr_progs || nr_maps != gen->nr_maps) {
+		pr_warn("nr_progs %d/%d nr_maps %d/%d mismatch\n",
+			nr_progs, gen->nr_progs, nr_maps, gen->nr_maps);
+		gen->error = -EFAULT;
+		return gen->error;
+	}
 	emit_sys_close_stack(gen, stack_off(btf_fd));
 	for (i = 0; i < gen->nr_progs; i++)
 		move_stack2ctx(gen,
@@ -321,11 +386,11 @@ int bpf_gen__finish(struct bpf_gen *gen)
 			       offsetof(struct bpf_prog_desc, prog_fd), 4,
 			       stack_off(prog_fd[i]));
 	for (i = 0; i < gen->nr_maps; i++)
-		move_stack2ctx(gen,
-			       sizeof(struct bpf_loader_ctx) +
-			       sizeof(struct bpf_map_desc) * i +
-			       offsetof(struct bpf_map_desc, map_fd), 4,
-			       stack_off(map_fd[i]));
+		move_blob2ctx(gen,
+			      sizeof(struct bpf_loader_ctx) +
+			      sizeof(struct bpf_map_desc) * i +
+			      offsetof(struct bpf_map_desc, map_fd), 4,
+			      blob_fd_array_off(gen, i));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0));
 	emit(gen, BPF_EXIT_INSN());
 	pr_debug("gen: finish %d\n", gen->error);
@@ -381,46 +446,32 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
 }
 
 void bpf_gen__map_create(struct bpf_gen *gen,
-			 struct bpf_create_map_attr *map_attr, int map_idx)
+			 enum bpf_map_type map_type,
+			 const char *map_name,
+			 __u32 key_size, __u32 value_size, __u32 max_entries,
+			 struct bpf_map_create_opts *map_attr, int map_idx)
 {
-	int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id);
+	int attr_size = offsetofend(union bpf_attr, map_extra);
 	bool close_inner_map_fd = false;
-	int map_create_attr;
+	int map_create_attr, idx;
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
-	attr.map_type = map_attr->map_type;
-	attr.key_size = map_attr->key_size;
-	attr.value_size = map_attr->value_size;
+	attr.map_type = map_type;
+	attr.key_size = key_size;
+	attr.value_size = value_size;
 	attr.map_flags = map_attr->map_flags;
-	memcpy(attr.map_name, map_attr->name,
-	       min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1));
+	attr.map_extra = map_attr->map_extra;
+	if (map_name)
+		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.numa_node = map_attr->numa_node;
 	attr.map_ifindex = map_attr->map_ifindex;
-	attr.max_entries = map_attr->max_entries;
-	switch (attr.map_type) {
-	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
-	case BPF_MAP_TYPE_CGROUP_ARRAY:
-	case BPF_MAP_TYPE_STACK_TRACE:
-	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
-	case BPF_MAP_TYPE_HASH_OF_MAPS:
-	case BPF_MAP_TYPE_DEVMAP:
-	case BPF_MAP_TYPE_DEVMAP_HASH:
-	case BPF_MAP_TYPE_CPUMAP:
-	case BPF_MAP_TYPE_XSKMAP:
-	case BPF_MAP_TYPE_SOCKMAP:
-	case BPF_MAP_TYPE_SOCKHASH:
-	case BPF_MAP_TYPE_QUEUE:
-	case BPF_MAP_TYPE_STACK:
-	case BPF_MAP_TYPE_RINGBUF:
-		break;
-	default:
-		attr.btf_key_type_id = map_attr->btf_key_type_id;
-		attr.btf_value_type_id = map_attr->btf_value_type_id;
-	}
+	attr.max_entries = max_entries;
+	attr.btf_key_type_id = map_attr->btf_key_type_id;
+	attr.btf_value_type_id = map_attr->btf_value_type_id;
 
 	pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n",
-		 attr.map_name, map_idx, map_attr->map_type, attr.btf_value_type_id);
+		 attr.map_name, map_idx, map_type, attr.btf_value_type_id);
 
 	map_create_attr = add_data(gen, &attr, attr_size);
 	if (attr.btf_value_type_id)
@@ -447,7 +498,7 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 	/* emit MAP_CREATE command */
 	emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size);
 	debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d",
-		  attr.map_name, map_idx, map_attr->map_type, attr.value_size,
+		  attr.map_name, map_idx, map_type, value_size,
 		  attr.btf_value_type_id);
 	emit_check_err(gen);
 	/* remember map_fd in the stack, if successful */
@@ -462,9 +513,11 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 		gen->error = -EDOM; /* internal bug */
 		return;
 	} else {
-		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7,
-				      stack_off(map_fd[map_idx])));
-		gen->nr_maps++;
+		/* add_map_fd does gen->nr_maps++ */
+		idx = add_map_fd(gen);
+		emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+						 0, 0, 0, blob_fd_array_off(gen, idx)));
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_7, 0));
 	}
 	if (close_inner_map_fd)
 		emit_sys_close_stack(gen, stack_off(inner_map_fd));
@@ -506,8 +559,8 @@ static void emit_find_attach_target(struct bpf_gen *gen)
 	 */
 }
 
-void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind,
-			    int insn_idx)
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
+			    bool is_typeless, int kind, int insn_idx)
 {
 	struct ksym_relo_desc *relo;
 
@@ -519,38 +572,313 @@ void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind,
 	gen->relos = relo;
 	relo += gen->relo_cnt;
 	relo->name = name;
+	relo->is_weak = is_weak;
+	relo->is_typeless = is_typeless;
 	relo->kind = kind;
 	relo->insn_idx = insn_idx;
 	gen->relo_cnt++;
 }
 
-static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns)
+/* returns existing ksym_desc with ref incremented, or inserts a new one */
+static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_desc *relo)
 {
-	int name, insn, len = strlen(relo->name) + 1;
+	struct ksym_desc *kdesc;
+	int i;
 
-	pr_debug("gen: emit_relo: %s at %d\n", relo->name, relo->insn_idx);
-	name = add_data(gen, relo->name, len);
+	for (i = 0; i < gen->nr_ksyms; i++) {
+		if (!strcmp(gen->ksyms[i].name, relo->name)) {
+			gen->ksyms[i].ref++;
+			return &gen->ksyms[i];
+		}
+	}
+	kdesc = libbpf_reallocarray(gen->ksyms, gen->nr_ksyms + 1, sizeof(*kdesc));
+	if (!kdesc) {
+		gen->error = -ENOMEM;
+		return NULL;
+	}
+	gen->ksyms = kdesc;
+	kdesc = &gen->ksyms[gen->nr_ksyms++];
+	kdesc->name = relo->name;
+	kdesc->kind = relo->kind;
+	kdesc->ref = 1;
+	kdesc->off = 0;
+	kdesc->insn = 0;
+	return kdesc;
+}
 
+/* Overwrites BPF_REG_{0, 1, 2, 3, 4, 7}
+ * Returns result in BPF_REG_7
+ */
+static void emit_bpf_find_by_name_kind(struct bpf_gen *gen, struct ksym_relo_desc *relo)
+{
+	int name_off, len = strlen(relo->name) + 1;
+
+	name_off = add_data(gen, relo->name, len);
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
-					 0, 0, 0, name));
+					 0, 0, 0, name_off));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_3, relo->kind));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0));
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind));
 	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
 	debug_ret(gen, "find_by_name_kind(%s,%d)", relo->name, relo->kind);
-	emit_check_err(gen);
+}
+
+/* Overwrites BPF_REG_{0, 1, 2, 3, 4, 7}
+ * Returns result in BPF_REG_7
+ * Returns u64 symbol addr in BPF_REG_9
+ */
+static void emit_bpf_kallsyms_lookup_name(struct bpf_gen *gen, struct ksym_relo_desc *relo)
+{
+	int name_off, len = strlen(relo->name) + 1, res_off;
+
+	name_off = add_data(gen, relo->name, len);
+	res_off = add_data(gen, NULL, 8); /* res is u64 */
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, name_off));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_4, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, res_off));
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_4));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_kallsyms_lookup_name));
+	emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0));
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+	debug_ret(gen, "kallsyms_lookup_name(%s,%d)", relo->name, relo->kind);
+}
+
+/* Expects:
+ * BPF_REG_8 - pointer to instruction
+ *
+ * We need to reuse BTF fd for same symbol otherwise each relocation takes a new
+ * index, while kernel limits total kfunc BTFs to 256. For duplicate symbols,
+ * this would mean a new BTF fd index for each entry. By pairing symbol name
+ * with index, we get the insn->imm, insn->off pairing that kernel uses for
+ * kfunc_tab, which becomes the effective limit even though all of them may
+ * share same index in fd_array (such that kfunc_btf_tab has 1 element).
+ */
+static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn)
+{
+	struct ksym_desc *kdesc;
+	int btf_fd_idx;
+
+	kdesc = get_ksym_desc(gen, relo);
+	if (!kdesc)
+		return;
+	/* try to copy from existing bpf_insn */
+	if (kdesc->ref > 1) {
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + offsetof(struct bpf_insn, imm));
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, off), 2,
+			       kdesc->insn + offsetof(struct bpf_insn, off));
+		goto log;
+	}
+	/* remember insn offset, so we can copy BTF ID and FD later */
+	kdesc->insn = insn;
+	emit_bpf_find_by_name_kind(gen, relo);
+	if (!relo->is_weak)
+		emit_check_err(gen);
+	/* get index in fd_array to store BTF FD at */
+	btf_fd_idx = add_kfunc_btf_fd(gen);
+	if (btf_fd_idx > INT16_MAX) {
+		pr_warn("BTF fd off %d for kfunc %s exceeds INT16_MAX, cannot process relocation\n",
+			btf_fd_idx, relo->name);
+		gen->error = -E2BIG;
+		return;
+	}
+	kdesc->off = btf_fd_idx;
+	/* jump to success case */
+	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
+	/* set value for imm, off as 0 */
+	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0));
+	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0));
+	/* skip success case for ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 10));
 	/* store btf_id into insn[insn_idx].imm */
-	insn = insns + sizeof(struct bpf_insn) * relo->insn_idx +
-		offsetof(struct bpf_insn, imm);
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
+	/* obtain fd in BPF_REG_9 */
+	emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7));
+	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32));
+	/* jump to fd_array store if fd denotes module BTF */
+	emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2));
+	/* set the default value for off */
+	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0));
+	/* skip BTF fd store for vmlinux BTF */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4));
+	/* load fd_array slot pointer */
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
-					 0, 0, 0, insn));
-	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, 0));
-	if (relo->kind == BTF_KIND_VAR) {
-		/* store btf_obj_fd into insn[insn_idx + 1].imm */
-		emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
-		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7,
-				      sizeof(struct bpf_insn)));
+					 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx)));
+	/* store BTF fd in slot */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0));
+	/* store index into insn[insn_idx].off */
+	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx));
+log:
+	if (!gen->log_level)
+		return;
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8,
+			      offsetof(struct bpf_insn, imm)));
+	emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8,
+			      offsetof(struct bpf_insn, off)));
+	debug_regs(gen, BPF_REG_7, BPF_REG_9, " func (%s:count=%d): imm: %%d, off: %%d",
+		   relo->name, kdesc->ref);
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_fd_array_off(gen, kdesc->off)));
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_0, 0));
+	debug_regs(gen, BPF_REG_9, -1, " func (%s:count=%d): btf_fd",
+		   relo->name, kdesc->ref);
+}
+
+static void emit_ksym_relo_log(struct bpf_gen *gen, struct ksym_relo_desc *relo,
+			       int ref)
+{
+	if (!gen->log_level)
+		return;
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8,
+			      offsetof(struct bpf_insn, imm)));
+	emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8, sizeof(struct bpf_insn) +
+			      offsetof(struct bpf_insn, imm)));
+	debug_regs(gen, BPF_REG_7, BPF_REG_9, " var t=%d w=%d (%s:count=%d): imm[0]: %%d, imm[1]: %%d",
+		   relo->is_typeless, relo->is_weak, relo->name, ref);
+	emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code)));
+	debug_regs(gen, BPF_REG_9, -1, " var t=%d w=%d (%s:count=%d): insn.reg",
+		   relo->is_typeless, relo->is_weak, relo->name, ref);
+}
+
+/* Expects:
+ * BPF_REG_8 - pointer to instruction
+ */
+static void emit_relo_ksym_typeless(struct bpf_gen *gen,
+				    struct ksym_relo_desc *relo, int insn)
+{
+	struct ksym_desc *kdesc;
+
+	kdesc = get_ksym_desc(gen, relo);
+	if (!kdesc)
+		return;
+	/* try to copy from existing ldimm64 insn */
+	if (kdesc->ref > 1) {
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + offsetof(struct bpf_insn, imm));
+		move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm));
+		goto log;
+	}
+	/* remember insn offset, so we can copy ksym addr later */
+	kdesc->insn = insn;
+	/* skip typeless ksym_desc in fd closing loop in cleanup_relos */
+	kdesc->typeless = true;
+	emit_bpf_kallsyms_lookup_name(gen, relo);
+	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_7, -ENOENT, 1));
+	emit_check_err(gen);
+	/* store lower half of addr into insn[insn_idx].imm */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_9, offsetof(struct bpf_insn, imm)));
+	/* store upper half of addr into insn[insn_idx + 1].imm */
+	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32));
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_9,
+		      sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)));
+log:
+	emit_ksym_relo_log(gen, relo, kdesc->ref);
+}
+
+static __u32 src_reg_mask(void)
+{
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	return 0x0f; /* src_reg,dst_reg,... */
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	return 0xf0; /* dst_reg,src_reg,... */
+#else
+#error "Unsupported bit endianness, cannot proceed"
+#endif
+}
+
+/* Expects:
+ * BPF_REG_8 - pointer to instruction
+ */
+static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn)
+{
+	struct ksym_desc *kdesc;
+	__u32 reg_mask;
+
+	kdesc = get_ksym_desc(gen, relo);
+	if (!kdesc)
+		return;
+	/* try to copy from existing ldimm64 insn */
+	if (kdesc->ref > 1) {
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + offsetof(struct bpf_insn, imm));
+		move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm));
+		/* jump over src_reg adjustment if imm is not 0, reuse BPF_REG_0 from move_blob2blob */
+		emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3));
+		goto clear_src_reg;
+	}
+	/* remember insn offset, so we can copy BTF ID and FD later */
+	kdesc->insn = insn;
+	emit_bpf_find_by_name_kind(gen, relo);
+	if (!relo->is_weak)
+		emit_check_err(gen);
+	/* jump to success case */
+	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
+	/* set values for insn[insn_idx].imm, insn[insn_idx + 1].imm as 0 */
+	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0));
+	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 0));
+	/* skip success case for ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4));
+	/* store btf_id into insn[insn_idx].imm */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
+	/* store btf_obj_fd into insn[insn_idx + 1].imm */
+	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7,
+			      sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)));
+	/* skip src_reg adjustment */
+	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
+clear_src_reg:
+	/* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */
+	reg_mask = src_reg_mask();
+	emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code)));
+	emit(gen, BPF_ALU32_IMM(BPF_AND, BPF_REG_9, reg_mask));
+	emit(gen, BPF_STX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, offsetofend(struct bpf_insn, code)));
+
+	emit_ksym_relo_log(gen, relo, kdesc->ref);
+}
+
+void bpf_gen__record_relo_core(struct bpf_gen *gen,
+			       const struct bpf_core_relo *core_relo)
+{
+	struct bpf_core_relo *relos;
+
+	relos = libbpf_reallocarray(gen->core_relos, gen->core_relo_cnt + 1, sizeof(*relos));
+	if (!relos) {
+		gen->error = -ENOMEM;
+		return;
+	}
+	gen->core_relos = relos;
+	relos += gen->core_relo_cnt;
+	memcpy(relos, core_relo, sizeof(*relos));
+	gen->core_relo_cnt++;
+}
+
+static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns)
+{
+	int insn;
+
+	pr_debug("gen: emit_relo (%d): %s at %d\n", relo->kind, relo->name, relo->insn_idx);
+	insn = insns + sizeof(struct bpf_insn) * relo->insn_idx;
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_8, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, insn));
+	switch (relo->kind) {
+	case BTF_KIND_VAR:
+		if (relo->is_typeless)
+			emit_relo_ksym_typeless(gen, relo, insn);
+		else
+			emit_relo_ksym_btf(gen, relo, insn);
+		break;
+	case BTF_KIND_FUNC:
+		emit_relo_kfunc_btf(gen, relo, insn);
+		break;
+	default:
+		pr_warn("Unknown relocation kind '%d'\n", relo->kind);
+		gen->error = -EDOM;
+		return;
 	}
 }
 
@@ -562,48 +890,68 @@ static void emit_relos(struct bpf_gen *gen, int insns)
 		emit_relo(gen, gen->relos + i, insns);
 }
 
+static void cleanup_core_relo(struct bpf_gen *gen)
+{
+	if (!gen->core_relo_cnt)
+		return;
+	free(gen->core_relos);
+	gen->core_relo_cnt = 0;
+	gen->core_relos = NULL;
+}
+
 static void cleanup_relos(struct bpf_gen *gen, int insns)
 {
 	int i, insn;
 
-	for (i = 0; i < gen->relo_cnt; i++) {
-		if (gen->relos[i].kind != BTF_KIND_VAR)
-			continue;
-		/* close fd recorded in insn[insn_idx + 1].imm */
-		insn = insns +
-			sizeof(struct bpf_insn) * (gen->relos[i].insn_idx + 1) +
-			offsetof(struct bpf_insn, imm);
-		emit_sys_close_blob(gen, insn);
+	for (i = 0; i < gen->nr_ksyms; i++) {
+		/* only close fds for typed ksyms and kfuncs */
+		if (gen->ksyms[i].kind == BTF_KIND_VAR && !gen->ksyms[i].typeless) {
+			/* close fd recorded in insn[insn_idx + 1].imm */
+			insn = gen->ksyms[i].insn;
+			insn += sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm);
+			emit_sys_close_blob(gen, insn);
+		} else if (gen->ksyms[i].kind == BTF_KIND_FUNC) {
+			emit_sys_close_blob(gen, blob_fd_array_off(gen, gen->ksyms[i].off));
+			if (gen->ksyms[i].off < MAX_FD_ARRAY_SZ)
+				gen->nr_fd_array--;
+		}
+	}
+	if (gen->nr_ksyms) {
+		free(gen->ksyms);
+		gen->nr_ksyms = 0;
+		gen->ksyms = NULL;
 	}
 	if (gen->relo_cnt) {
 		free(gen->relos);
 		gen->relo_cnt = 0;
 		gen->relos = NULL;
 	}
+	cleanup_core_relo(gen);
 }
 
 void bpf_gen__prog_load(struct bpf_gen *gen,
-			struct bpf_prog_load_params *load_attr, int prog_idx)
+			enum bpf_prog_type prog_type, const char *prog_name,
+			const char *license, struct bpf_insn *insns, size_t insn_cnt,
+			struct bpf_prog_load_opts *load_attr, int prog_idx)
 {
-	int attr_size = offsetofend(union bpf_attr, fd_array);
-	int prog_load_attr, license, insns, func_info, line_info;
+	int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos;
+	int attr_size = offsetofend(union bpf_attr, core_relo_rec_size);
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
-	pr_debug("gen: prog_load: type %d insns_cnt %zd\n",
-		 load_attr->prog_type, load_attr->insn_cnt);
+	pr_debug("gen: prog_load: type %d insns_cnt %zd progi_idx %d\n",
+		 prog_type, insn_cnt, prog_idx);
 	/* add license string to blob of bytes */
-	license = add_data(gen, load_attr->license, strlen(load_attr->license) + 1);
+	license_off = add_data(gen, license, strlen(license) + 1);
 	/* add insns to blob of bytes */
-	insns = add_data(gen, load_attr->insns,
-			 load_attr->insn_cnt * sizeof(struct bpf_insn));
+	insns_off = add_data(gen, insns, insn_cnt * sizeof(struct bpf_insn));
 
-	attr.prog_type = load_attr->prog_type;
+	attr.prog_type = prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
 	attr.attach_btf_id = load_attr->attach_btf_id;
 	attr.prog_ifindex = load_attr->prog_ifindex;
 	attr.kern_version = 0;
-	attr.insn_cnt = (__u32)load_attr->insn_cnt;
+	attr.insn_cnt = (__u32)insn_cnt;
 	attr.prog_flags = load_attr->prog_flags;
 
 	attr.func_info_rec_size = load_attr->func_info_rec_size;
@@ -616,15 +964,19 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 	line_info = add_data(gen, load_attr->line_info,
 			     attr.line_info_cnt * attr.line_info_rec_size);
 
-	memcpy(attr.prog_name, load_attr->name,
-	       min((unsigned)strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1));
+	attr.core_relo_rec_size = sizeof(struct bpf_core_relo);
+	attr.core_relo_cnt = gen->core_relo_cnt;
+	core_relos = add_data(gen, gen->core_relos,
+			     attr.core_relo_cnt * attr.core_relo_rec_size);
+
+	libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	prog_load_attr = add_data(gen, &attr, attr_size);
 
 	/* populate union bpf_attr with a pointer to license */
-	emit_rel_store(gen, attr_field(prog_load_attr, license), license);
+	emit_rel_store(gen, attr_field(prog_load_attr, license), license_off);
 
 	/* populate union bpf_attr with a pointer to instructions */
-	emit_rel_store(gen, attr_field(prog_load_attr, insns), insns);
+	emit_rel_store(gen, attr_field(prog_load_attr, insns), insns_off);
 
 	/* populate union bpf_attr with a pointer to func_info */
 	emit_rel_store(gen, attr_field(prog_load_attr, func_info), func_info);
@@ -632,9 +984,11 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 	/* populate union bpf_attr with a pointer to line_info */
 	emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info);
 
-	/* populate union bpf_attr fd_array with a pointer to stack where map_fds are saved */
-	emit_rel_store_sp(gen, attr_field(prog_load_attr, fd_array),
-			  stack_off(map_fd[0]));
+	/* populate union bpf_attr with a pointer to core_relos */
+	emit_rel_store(gen, attr_field(prog_load_attr, core_relos), core_relos);
+
+	/* populate union bpf_attr fd_array with a pointer to data where map_fds are saved */
+	emit_rel_store(gen, attr_field(prog_load_attr, fd_array), gen->fd_array);
 
 	/* populate union bpf_attr with user provided log details */
 	move_ctx2blob(gen, attr_field(prog_load_attr, log_level), 4,
@@ -657,12 +1011,12 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7,
 				      offsetof(union bpf_attr, attach_btf_obj_fd)));
 	}
-	emit_relos(gen, insns);
+	emit_relos(gen, insns_off);
 	/* emit PROG_LOAD command */
 	emit_sys_bpf(gen, BPF_PROG_LOAD, prog_load_attr, attr_size);
 	debug_ret(gen, "prog_load %s insn_cnt %d", attr.prog_name, attr.insn_cnt);
 	/* successful or not, close btf module FDs used in extern ksyms and attach_btf_obj_fd */
-	cleanup_relos(gen, insns);
+	cleanup_relos(gen, insns_off);
 	if (gen->attach_kind) {
 		emit_sys_close_blob(gen,
 				    attr_field(prog_load_attr, attach_btf_obj_fd));
@@ -703,8 +1057,8 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user));
 
 	map_update_attr = add_data(gen, &attr, attr_size);
-	move_stack2blob(gen, attr_field(map_update_attr, map_fd), 4,
-			stack_off(map_fd[map_idx]));
+	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,
+		       blob_fd_array_off(gen, map_idx));
 	emit_rel_store(gen, attr_field(map_update_attr, key), key);
 	emit_rel_store(gen, attr_field(map_update_attr, value), value);
 	/* emit MAP_UPDATE_ELEM command */
@@ -713,6 +1067,33 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	emit_check_err(gen);
 }
 
+void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slot,
+				 int inner_map_idx)
+{
+	int attr_size = offsetofend(union bpf_attr, flags);
+	int map_update_attr, key;
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_size);
+	pr_debug("gen: populate_outer_map: outer %d key %d inner %d\n",
+		 outer_map_idx, slot, inner_map_idx);
+
+	key = add_data(gen, &slot, sizeof(slot));
+
+	map_update_attr = add_data(gen, &attr, attr_size);
+	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,
+		       blob_fd_array_off(gen, outer_map_idx));
+	emit_rel_store(gen, attr_field(map_update_attr, key), key);
+	emit_rel_store(gen, attr_field(map_update_attr, value),
+		       blob_fd_array_off(gen, inner_map_idx));
+
+	/* emit MAP_UPDATE_ELEM command */
+	emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size);
+	debug_ret(gen, "populate_outer_map outer %d key %d inner %d",
+		  outer_map_idx, slot, inner_map_idx);
+	emit_check_err(gen);
+}
+
 void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx)
 {
 	int attr_size = offsetofend(union bpf_attr, map_fd);
@@ -722,8 +1103,8 @@ void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx)
 	memset(&attr, 0, attr_size);
 	pr_debug("gen: map_freeze: idx %d\n", map_idx);
 	map_freeze_attr = add_data(gen, &attr, attr_size);
-	move_stack2blob(gen, attr_field(map_freeze_attr, map_fd), 4,
-			stack_off(map_fd[map_idx]));
+	move_blob2blob(gen, attr_field(map_freeze_attr, map_fd), 4,
+		       blob_fd_array_off(gen, map_idx));
 	/* emit MAP_FREEZE command */
 	emit_sys_bpf(gen, BPF_MAP_FREEZE, map_freeze_attr, attr_size);
 	debug_ret(gen, "map_freeze");

tools/lib/bpf/libbpf.h

@@ -24,6 +24,10 @@
 extern "C" {
 #endif
 
+LIBBPF_API __u32 libbpf_major_version(void);
+LIBBPF_API __u32 libbpf_minor_version(void);
+LIBBPF_API const char *libbpf_version_string(void);
+
 enum libbpf_errno {
 	__LIBBPF_ERRNO__START = 4000,
 
@@ -83,12 +87,15 @@ struct bpf_object_open_opts {
 	 * Non-relocatable instructions are replaced with invalid ones to
 	 * prevent accidental errors.
 	 * */
+	LIBBPF_DEPRECATED_SINCE(0, 6, "field has no effect")
 	bool relaxed_core_relocs;
 	/* maps that set the 'pinning' attribute in their definition will have
 	 * their pin_path attribute set to a file in this directory, and be
 	 * auto-pinned to that path on load; defaults to "/sys/fs/bpf".
 	 */
 	const char *pin_root_path;
+
+	LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__set_attach_target() on each individual bpf_program")
 	__u32 attach_prog_fd;
 	/* Additional kernel config content that augments and overrides
 	 * system Kconfig for CONFIG_xxx externs.
@@ -101,12 +108,73 @@ struct bpf_object_open_opts {
 	 * struct_ops, etc) will need actual kernel BTF at /sys/kernel/btf/vmlinux.
 	 */
 	const char *btf_custom_path;
+	/* Pointer to a buffer for storing kernel logs for applicable BPF
+	 * commands. Valid kernel_log_size has to be specified as well and are
+	 * passed-through to bpf() syscall. Keep in mind that kernel might
+	 * fail operation with -ENOSPC error if provided buffer is too small
+	 * to contain entire log output.
+	 * See the comment below for kernel_log_level for interaction between
+	 * log_buf and log_level settings.
+	 *
+	 * If specified, this log buffer will be passed for:
+	 *   - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden
+	 *     with bpf_program__set_log() on per-program level, to get
+	 *     BPF verifier log output.
+	 *   - during BPF object's BTF load into kernel (BPF_BTF_LOAD) to get
+	 *     BTF sanity checking log.
+	 *
+	 * Each BPF command (BPF_BTF_LOAD or BPF_PROG_LOAD) will overwrite
+	 * previous contents, so if you need more fine-grained control, set
+	 * per-program buffer with bpf_program__set_log_buf() to preserve each
+	 * individual program's verification log. Keep using kernel_log_buf
+	 * for BTF verification log, if necessary.
+	 */
+	char *kernel_log_buf;
+	size_t kernel_log_size;
+	/*
+	 * Log level can be set independently from log buffer. Log_level=0
+	 * means that libbpf will attempt loading BTF or program without any
+	 * logging requested, but will retry with either its own or custom log
+	 * buffer, if provided, and log_level=1 on any error.
+	 * And vice versa, setting log_level>0 will request BTF or prog
+	 * loading with verbose log from the first attempt (and as such also
+	 * for successfully loaded BTF or program), and the actual log buffer
+	 * could be either libbpf's own auto-allocated log buffer, if
+	 * kernel_log_buffer is NULL, or user-provided custom kernel_log_buf.
+	 * If user didn't provide custom log buffer, libbpf will emit captured
+	 * logs through its print callback.
+	 */
+	__u32 kernel_log_level;
+
+	size_t :0;
 };
-#define bpf_object_open_opts__last_field btf_custom_path
+#define bpf_object_open_opts__last_field kernel_log_level
 
 LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
+
+/**
+ * @brief **bpf_object__open_file()** creates a bpf_object by opening
+ * the BPF ELF object file pointed to by the passed path and loading it
+ * into memory.
+ * @param path BPF object file path
+ * @param opts options for how to load the bpf object, this parameter is
+ * optional and can be set to NULL
+ * @return pointer to the new bpf_object; or NULL is returned on error,
+ * error code is stored in errno
+ */
 LIBBPF_API struct bpf_object *
 bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts);
+
+/**
+ * @brief **bpf_object__open_mem()** creates a bpf_object by reading
+ * the BPF objects raw bytes from a memory buffer containing a valid
+ * BPF ELF object file.
+ * @param obj_buf pointer to the buffer containing ELF file bytes
+ * @param obj_buf_sz number of bytes in the buffer
+ * @param opts options for how to load the bpf object
+ * @return pointer to the new bpf_object; or NULL is returned on error,
+ * error code is stored in errno
+ */
 LIBBPF_API struct bpf_object *
 bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
 		     const struct bpf_object_open_opts *opts);
@@ -146,7 +214,9 @@ struct bpf_object_load_attr {
 
 /* Load/unload object into/from kernel */
 LIBBPF_API int bpf_object__load(struct bpf_object *obj);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__load() instead")
 LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr);
+LIBBPF_DEPRECATED_SINCE(0, 6, "bpf_object__unload() is deprecated, use bpf_object__close() instead")
 LIBBPF_API int bpf_object__unload(struct bpf_object *obj);
 
 LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
@@ -157,6 +227,7 @@ struct btf;
 LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj);
 LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
 
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__find_program_by_name() instead")
 LIBBPF_API struct bpf_program *
 bpf_object__find_program_by_title(const struct bpf_object *obj,
 				  const char *title);
@@ -164,7 +235,8 @@ LIBBPF_API struct bpf_program *
 bpf_object__find_program_by_name(const struct bpf_object *obj,
 				 const char *name);
 
-LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "track bpf_objects in application code instead")
+struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\
 	for ((pos) = bpf_object__next(NULL),		\
 		(tmp) = bpf_object__next(pos);		\
@@ -186,16 +258,22 @@ LIBBPF_API int libbpf_find_vmlinux_btf_id(const char *name,
 
 /* Accessors of bpf_program */
 struct bpf_program;
-LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
-						 const struct bpf_object *obj);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_program() instead")
+struct bpf_program *bpf_program__next(struct bpf_program *prog,
+				      const struct bpf_object *obj);
+LIBBPF_API struct bpf_program *
+bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prog);
 
-#define bpf_object__for_each_program(pos, obj)		\
-	for ((pos) = bpf_program__next(NULL, (obj));	\
-	     (pos) != NULL;				\
-	     (pos) = bpf_program__next((pos), (obj)))
+#define bpf_object__for_each_program(pos, obj)			\
+	for ((pos) = bpf_object__next_program((obj), NULL);	\
+	     (pos) != NULL;					\
+	     (pos) = bpf_object__next_program((obj), (pos)))
 
-LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog,
-						 const struct bpf_object *obj);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_program() instead")
+struct bpf_program *bpf_program__prev(struct bpf_program *prog,
+				      const struct bpf_object *obj);
+LIBBPF_API struct bpf_program *
+bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *prog);
 
 typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *);
 
@@ -214,18 +292,79 @@ LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload);
 
 /* returns program size in bytes */
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insn_cnt() instead")
 LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog);
 
-LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license,
-				 __u32 kern_version);
+struct bpf_insn;
+
+/**
+ * @brief **bpf_program__insns()** gives read-only access to BPF program's
+ * underlying BPF instructions.
+ * @param prog BPF program for which to return instructions
+ * @return a pointer to an array of BPF instructions that belong to the
+ * specified BPF program
+ *
+ * Returned pointer is always valid and not NULL. Number of `struct bpf_insn`
+ * pointed to can be fetched using **bpf_program__insn_cnt()** API.
+ *
+ * Keep in mind, libbpf can modify and append/delete BPF program's
+ * instructions as it processes BPF object file and prepares everything for
+ * uploading into the kernel. So depending on the point in BPF object
+ * lifetime, **bpf_program__insns()** can return different sets of
+ * instructions. As an example, during BPF object load phase BPF program
+ * instructions will be CO-RE-relocated, BPF subprograms instructions will be
+ * appended, ldimm64 instructions will have FDs embedded, etc. So instructions
+ * returned before **bpf_object__load()** and after it might be quite
+ * different.
+ */
+LIBBPF_API const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog);
+/**
+ * @brief **bpf_program__insn_cnt()** returns number of `struct bpf_insn`'s
+ * that form specified BPF program.
+ * @param prog BPF program for which to return number of BPF instructions
+ *
+ * See **bpf_program__insns()** documentation for notes on how libbpf can
+ * change instructions and their count during different phases of
+ * **bpf_object** lifetime.
+ */
+LIBBPF_API size_t bpf_program__insn_cnt(const struct bpf_program *prog);
+
+LIBBPF_DEPRECATED_SINCE(0, 6, "use bpf_object__load() instead")
+LIBBPF_API int bpf_program__load(struct bpf_program *prog, const char *license, __u32 kern_version);
 LIBBPF_API int bpf_program__fd(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated")
 LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog,
 					 const char *path,
 					 int instance);
+LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated")
 LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog,
 					   const char *path,
 					   int instance);
+
+/**
+ * @brief **bpf_program__pin()** pins the BPF program to a file
+ * in the BPF FS specified by a path. This increments the programs
+ * reference count, allowing it to stay loaded after the process
+ * which loaded it has exited.
+ *
+ * @param prog BPF program to pin, must already be loaded
+ * @param path file path in a BPF file system
+ * @return 0, on success; negative error code, otherwise
+ */
 LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
+
+/**
+ * @brief **bpf_program__unpin()** unpins the BPF program from a file
+ * in the BPFFS specified by a path. This decrements the programs
+ * reference count.
+ *
+ * The file pinning the BPF program can also be unlinked by a different
+ * process in which case this function will return an error.
+ *
+ * @param prog BPF program to unpin
+ * @param path file path to the pin in a BPF file system
+ * @return 0, on success; negative error code, otherwise
+ */
 LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path);
 LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
 
@@ -243,7 +382,7 @@ LIBBPF_API int bpf_link__detach(struct bpf_link *link);
 LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach(struct bpf_program *prog);
+bpf_program__attach(const struct bpf_program *prog);
 
 struct bpf_perf_event_opts {
 	/* size of this struct, for forward/backward compatiblity */
@@ -254,10 +393,10 @@ struct bpf_perf_event_opts {
 #define bpf_perf_event_opts__last_field bpf_cookie
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_perf_event(struct bpf_program *prog, int pfd);
+bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd);
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd,
+bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd,
 				    const struct bpf_perf_event_opts *opts);
 
 struct bpf_kprobe_opts {
@@ -266,7 +405,7 @@ struct bpf_kprobe_opts {
 	/* custom user-provided value fetchable through bpf_get_attach_cookie() */
 	__u64 bpf_cookie;
 	/* function's offset to install kprobe to */
-	unsigned long offset;
+	size_t offset;
 	/* kprobe is return probe */
 	bool retprobe;
 	size_t :0;
@@ -274,10 +413,10 @@ struct bpf_kprobe_opts {
 #define bpf_kprobe_opts__last_field retprobe
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe,
+bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe,
 			   const char *func_name);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_kprobe_opts(struct bpf_program *prog,
+bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
                                 const char *func_name,
                                 const struct bpf_kprobe_opts *opts);
 
@@ -296,12 +435,43 @@ struct bpf_uprobe_opts {
 };
 #define bpf_uprobe_opts__last_field retprobe
 
+/**
+ * @brief **bpf_program__attach_uprobe()** attaches a BPF program
+ * to the userspace function which is found by binary path and
+ * offset. You can optionally specify a particular proccess to attach
+ * to. You can also optionally attach the program to the function
+ * exit instead of entry.
+ *
+ * @param prog BPF program to attach
+ * @param retprobe Attach to function exit
+ * @param pid Process ID to attach the uprobe to, 0 for self (own process),
+ * -1 for all processes
+ * @param binary_path Path to binary that contains the function symbol
+ * @param func_offset Offset within the binary of the function symbol
+ * @return Reference to the newly created BPF link; or NULL is returned on error,
+ * error code is stored in errno
+ */
 LIBBPF_API struct bpf_link *
-bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe,
+bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe,
 			   pid_t pid, const char *binary_path,
 			   size_t func_offset);
+
+/**
+ * @brief **bpf_program__attach_uprobe_opts()** is just like
+ * bpf_program__attach_uprobe() except with a options struct
+ * for various configurations.
+ *
+ * @param prog BPF program to attach
+ * @param pid Process ID to attach the uprobe to, 0 for self (own process),
+ * -1 for all processes
+ * @param binary_path Path to binary that contains the function symbol
+ * @param func_offset Offset within the binary of the function symbol
+ * @param opts Options for altering program attachment
+ * @return Reference to the newly created BPF link; or NULL is returned on error,
+ * error code is stored in errno
+ */
 LIBBPF_API struct bpf_link *
-bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid,
+bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid,
 				const char *binary_path, size_t func_offset,
 				const struct bpf_uprobe_opts *opts);
 
@@ -314,35 +484,35 @@ struct bpf_tracepoint_opts {
 #define bpf_tracepoint_opts__last_field bpf_cookie
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_tracepoint(struct bpf_program *prog,
+bpf_program__attach_tracepoint(const struct bpf_program *prog,
 			       const char *tp_category,
 			       const char *tp_name);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_tracepoint_opts(struct bpf_program *prog,
+bpf_program__attach_tracepoint_opts(const struct bpf_program *prog,
 				    const char *tp_category,
 				    const char *tp_name,
 				    const struct bpf_tracepoint_opts *opts);
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
+bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
 				   const char *tp_name);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_trace(struct bpf_program *prog);
+bpf_program__attach_trace(const struct bpf_program *prog);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_lsm(struct bpf_program *prog);
+bpf_program__attach_lsm(const struct bpf_program *prog);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd);
+bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_netns(struct bpf_program *prog, int netns_fd);
+bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_xdp(struct bpf_program *prog, int ifindex);
+bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_freplace(struct bpf_program *prog,
+bpf_program__attach_freplace(const struct bpf_program *prog,
 			     int target_fd, const char *attach_func_name);
 
 struct bpf_map;
 
-LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
+LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
 
 struct bpf_iter_attach_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
@@ -352,11 +522,9 @@ struct bpf_iter_attach_opts {
 #define bpf_iter_attach_opts__last_field link_info_len
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_iter(struct bpf_program *prog,
+bpf_program__attach_iter(const struct bpf_program *prog,
 			 const struct bpf_iter_attach_opts *opts);
 
-struct bpf_insn;
-
 /*
  * Libbpf allows callers to adjust BPF programs before being loaded
  * into kernel. One program in an object file can be transformed into
@@ -385,7 +553,6 @@ struct bpf_insn;
  * one instance. In this case bpf_program__fd(prog) is equal to
  * bpf_program__nth_fd(prog, 0).
  */
-
 struct bpf_prog_prep_result {
 	/*
 	 * If not NULL, load new instruction array.
@@ -414,9 +581,11 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n,
 				  struct bpf_insn *insns, int insns_cnt,
 				  struct bpf_prog_prep_result *res);
 
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insns() for getting bpf_program instructions")
 LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
 				     bpf_program_prep_t prep);
 
+LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated")
 LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n);
 
 /*
@@ -446,6 +615,18 @@ LIBBPF_API void
 bpf_program__set_expected_attach_type(struct bpf_program *prog,
 				      enum bpf_attach_type type);
 
+LIBBPF_API __u32 bpf_program__flags(const struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_flags(struct bpf_program *prog, __u32 flags);
+
+/* Per-program log level and log buffer getters/setters.
+ * See bpf_object_open_opts comments regarding log_level and log_buf
+ * interactions.
+ */
+LIBBPF_API __u32 bpf_program__log_level(const struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level);
+LIBBPF_API const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size);
+LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size);
+
 LIBBPF_API int
 bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd,
 			       const char *attach_func_name);
@@ -478,9 +659,13 @@ struct bpf_map_def {
 	unsigned int map_flags;
 };
 
-/*
- * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel,
- * so no need to worry about a name clash.
+/**
+ * @brief **bpf_object__find_map_by_name()** returns BPF map of
+ * the given name, if it exists within the passed BPF object
+ * @param obj BPF object
+ * @param name name of the BPF map
+ * @return BPF map instance, if such map exists within the BPF object;
+ * or NULL otherwise.
  */
 LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name);
@@ -492,21 +677,32 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name);
  * Get bpf_map through the offset of corresponding struct bpf_map_def
  * in the BPF object file.
  */
-LIBBPF_API struct bpf_map *
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__find_map_by_name() instead")
+struct bpf_map *
 bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
 
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_map() instead")
+struct bpf_map *bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj);
 LIBBPF_API struct bpf_map *
-bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj);
+bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *map);
+
 #define bpf_object__for_each_map(pos, obj)		\
-	for ((pos) = bpf_map__next(NULL, (obj));	\
+	for ((pos) = bpf_object__next_map((obj), NULL);	\
 	     (pos) != NULL;				\
-	     (pos) = bpf_map__next((pos), (obj)))
+	     (pos) = bpf_object__next_map((obj), (pos)))
 #define bpf_map__for_each bpf_object__for_each_map
 
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_map() instead")
+struct bpf_map *bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj);
 LIBBPF_API struct bpf_map *
-bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj);
+bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map);
 
-/* get/set map FD */
+/**
+ * @brief **bpf_map__fd()** gets the file descriptor of the passed
+ * BPF map
+ * @param map the BPF map instance
+ * @return the file descriptor; or -EINVAL in case of an error
+ */
 LIBBPF_API int bpf_map__fd(const struct bpf_map *map);
 LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
 /* get map definition */
@@ -538,6 +734,9 @@ LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
 /* get/set map if_index */
 LIBBPF_API __u32 bpf_map__ifindex(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
+/* get/set map map_extra flags */
+LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map);
+LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra);
 
 typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
@@ -546,7 +745,16 @@ LIBBPF_API void *bpf_map__priv(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map,
 					  const void *data, size_t size);
 LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_map__type() instead")
 LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
+
+/**
+ * @brief **bpf_map__is_internal()** tells the caller whether or not the
+ * passed map is a special map created by libbpf automatically for things like
+ * global variables, __ksym externs, Kconfig values, etc
+ * @param map the bpf_map
+ * @return true, if the map is an internal map; false, otherwise
+ */
 LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path);
 LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map);
@@ -558,6 +766,38 @@ LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
 LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd);
 LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map);
 
+/**
+ * @brief **libbpf_get_error()** extracts the error code from the passed
+ * pointer
+ * @param ptr pointer returned from libbpf API function
+ * @return error code; or 0 if no error occured
+ *
+ * Many libbpf API functions which return pointers have logic to encode error
+ * codes as pointers, and do not return NULL. Meaning **libbpf_get_error()**
+ * should be used on the return value from these functions immediately after
+ * calling the API function, with no intervening calls that could clobber the
+ * `errno` variable. Consult the individual functions documentation to verify
+ * if this logic applies should be used.
+ *
+ * For these API functions, if `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)`
+ * is enabled, NULL is returned on error instead.
+ *
+ * If ptr is NULL, then errno should be already set by the failing
+ * API, because libbpf never returns NULL on success and it now always
+ * sets errno on error.
+ *
+ * Example usage:
+ *
+ *   struct perf_buffer *pb;
+ *
+ *   pb = perf_buffer__new(bpf_map__fd(obj->maps.events), PERF_BUFFER_PAGES, &opts);
+ *   err = libbpf_get_error(pb);
+ *   if (err) {
+ *	  pb = NULL;
+ *	  fprintf(stderr, "failed to open perf buffer: %d\n", err);
+ *	  goto cleanup;
+ *   }
+ */
 LIBBPF_API long libbpf_get_error(const void *ptr);
 
 struct bpf_prog_load_attr {
@@ -569,10 +809,12 @@ struct bpf_prog_load_attr {
 	int prog_flags;
 };
 
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__open() and bpf_object__load() instead")
 LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 				   struct bpf_object **pobj, int *prog_fd);
-LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type,
-			     struct bpf_object **pobj, int *prog_fd);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__open() and bpf_object__load() instead")
+LIBBPF_API int bpf_prog_load_deprecated(const char *file, enum bpf_prog_type type,
+					struct bpf_object **pobj, int *prog_fd);
 
 /* XDP related API */
 struct xdp_link_info {
@@ -670,18 +912,52 @@ 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;
+	union {
+		size_t sz;
+		struct { /* DEPRECATED: will be removed in v1.0 */
+			/* 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;
+		};
+	};
 };
+#define perf_buffer_opts__last_field sz
 
+/**
+ * @brief **perf_buffer__new()** creates BPF perfbuf manager for a specified
+ * BPF_PERF_EVENT_ARRAY map
+ * @param map_fd FD of BPF_PERF_EVENT_ARRAY BPF map that will be used by BPF
+ * code to send data over to user-space
+ * @param page_cnt number of memory pages allocated for each per-CPU buffer
+ * @param sample_cb function called on each received data record
+ * @param lost_cb function called when record loss has occurred
+ * @param ctx user-provided extra context passed into *sample_cb* and *lost_cb*
+ * @return a new instance of struct perf_buffer on success, NULL on error with
+ * *errno* containing an error code
+ */
 LIBBPF_API struct perf_buffer *
 perf_buffer__new(int map_fd, size_t page_cnt,
+		 perf_buffer_sample_fn sample_cb, perf_buffer_lost_fn lost_cb, void *ctx,
 		 const struct perf_buffer_opts *opts);
 
+LIBBPF_API struct perf_buffer *
+perf_buffer__new_v0_6_0(int map_fd, size_t page_cnt,
+			perf_buffer_sample_fn sample_cb, perf_buffer_lost_fn lost_cb, void *ctx,
+			const struct perf_buffer_opts *opts);
+
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use new variant of perf_buffer__new() instead")
+struct perf_buffer *perf_buffer__new_deprecated(int map_fd, size_t page_cnt,
+						const struct perf_buffer_opts *opts);
+
+#define perf_buffer__new(...) ___libbpf_overload(___perf_buffer_new, __VA_ARGS__)
+#define ___perf_buffer_new6(map_fd, page_cnt, sample_cb, lost_cb, ctx, opts) \
+	perf_buffer__new(map_fd, page_cnt, sample_cb, lost_cb, ctx, opts)
+#define ___perf_buffer_new3(map_fd, page_cnt, opts) \
+	perf_buffer__new_deprecated(map_fd, page_cnt, opts)
+
 enum bpf_perf_event_ret {
 	LIBBPF_PERF_EVENT_DONE	= 0,
 	LIBBPF_PERF_EVENT_ERROR	= -1,
@@ -695,12 +971,21 @@ typedef enum bpf_perf_event_ret
 
 /* 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;
+	union {
+		struct {
+			size_t sz;
+			long :0;
+			long :0;
+		};
+		struct { /* DEPRECATED: will be removed in v1.0 */
+			/* 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)
 	 */
@@ -710,11 +995,28 @@ struct perf_buffer_raw_opts {
 	/* if cpu_cnt > 0, map_keys specify map keys to set per-CPU FDs for */
 	int *map_keys;
 };
+#define perf_buffer_raw_opts__last_field map_keys
 
 LIBBPF_API struct perf_buffer *
-perf_buffer__new_raw(int map_fd, size_t page_cnt,
+perf_buffer__new_raw(int map_fd, size_t page_cnt, struct perf_event_attr *attr,
+		     perf_buffer_event_fn event_cb, void *ctx,
 		     const struct perf_buffer_raw_opts *opts);
 
+LIBBPF_API struct perf_buffer *
+perf_buffer__new_raw_v0_6_0(int map_fd, size_t page_cnt, struct perf_event_attr *attr,
+			    perf_buffer_event_fn event_cb, void *ctx,
+			    const struct perf_buffer_raw_opts *opts);
+
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use new variant of perf_buffer__new_raw() instead")
+struct perf_buffer *perf_buffer__new_raw_deprecated(int map_fd, size_t page_cnt,
+						    const struct perf_buffer_raw_opts *opts);
+
+#define perf_buffer__new_raw(...) ___libbpf_overload(___perf_buffer_new_raw, __VA_ARGS__)
+#define ___perf_buffer_new_raw6(map_fd, page_cnt, attr, event_cb, ctx, opts) \
+	perf_buffer__new_raw(map_fd, page_cnt, attr, event_cb, ctx, opts)
+#define ___perf_buffer_new_raw3(map_fd, page_cnt, opts) \
+	perf_buffer__new_raw_deprecated(map_fd, page_cnt, opts)
+
 LIBBPF_API void perf_buffer__free(struct perf_buffer *pb);
 LIBBPF_API int perf_buffer__epoll_fd(const struct perf_buffer *pb);
 LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms);
@@ -726,6 +1028,7 @@ LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_i
 typedef enum bpf_perf_event_ret
 	(*bpf_perf_event_print_t)(struct perf_event_header *hdr,
 				  void *private_data);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use perf_buffer__poll() or  perf_buffer__consume() instead")
 LIBBPF_API 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,
@@ -752,13 +1055,57 @@ bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
  * user, causing subsequent probes to fail. In this case, the caller may want
  * to adjust that limit with setrlimit().
  */
-LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type,
-				    __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_prog_type() instead")
+LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_map_type() instead")
 LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex);
-LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id,
-				 enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_helper() instead")
+LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "implement your own or use bpftool for feature detection")
 LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex);
 
+/**
+ * @brief **libbpf_probe_bpf_prog_type()** detects if host kernel supports
+ * BPF programs of a given type.
+ * @param prog_type BPF program type to detect kernel support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given program type is supported; 0, if given program type is
+ * not supported; negative error code if feature detection failed or can't be
+ * performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts);
+/**
+ * @brief **libbpf_probe_bpf_map_type()** detects if host kernel supports
+ * BPF maps of a given type.
+ * @param map_type BPF map type to detect kernel support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given map type is supported; 0, if given map type is
+ * not supported; negative error code if feature detection failed or can't be
+ * performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts);
+/**
+ * @brief **libbpf_probe_bpf_helper()** detects if host kernel supports the
+ * use of a given BPF helper from specified BPF program type.
+ * @param prog_type BPF program type used to check the support of BPF helper
+ * @param helper_id BPF helper ID (enum bpf_func_id) to check support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given combination of program type and helper is supported; 0,
+ * if the combination is not supported; negative error code if feature
+ * detection for provided input arguments failed or can't be performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type,
+				       enum bpf_func_id helper_id, const void *opts);
+
 /*
  * Get bpf_prog_info in continuous memory
  *
@@ -813,18 +1160,22 @@ struct bpf_prog_info_linear {
 	__u8			data[];
 };
 
+LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper")
 LIBBPF_API struct bpf_prog_info_linear *
 bpf_program__get_prog_info_linear(int fd, __u64 arrays);
 
+LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper")
 LIBBPF_API void
 bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear);
 
+LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper")
 LIBBPF_API void
 bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
 
-/*
- * A helper function to get the number of possible CPUs before looking up
- * per-CPU maps. Negative errno is returned on failure.
+/**
+ * @brief **libbpf_num_possible_cpus()** is a helper function to get the
+ * number of possible CPUs that the host kernel supports and expects.
+ * @return number of possible CPUs; or error code on failure
  *
  * Example usage:
  *
@@ -834,7 +1185,6 @@ bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
  *     }
  *     long values[ncpus];
  *     bpf_map_lookup_elem(per_cpu_map_fd, key, values);
- *
  */
 LIBBPF_API int libbpf_num_possible_cpus(void);
 
@@ -854,17 +1204,17 @@ struct bpf_object_skeleton {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 
 	const char *name;
-	void *data;
+	const void *data;
 	size_t data_sz;
 
 	struct bpf_object **obj;
 
 	int map_cnt;
-	int map_skel_sz; /* sizeof(struct bpf_skeleton_map) */
+	int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */
 	struct bpf_map_skeleton *maps;
 
 	int prog_cnt;
-	int prog_skel_sz; /* sizeof(struct bpf_skeleton_prog) */
+	int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */
 	struct bpf_prog_skeleton *progs;
 };
 

tools/lib/bpf/libbpf.map

@@ -386,3 +386,49 @@ LIBBPF_0.5.0 {
 		btf_dump__dump_type_data;
 		libbpf_set_strict_mode;
 } LIBBPF_0.4.0;
+
+LIBBPF_0.6.0 {
+	global:
+		bpf_map__map_extra;
+		bpf_map__set_map_extra;
+		bpf_map_create;
+		bpf_object__next_map;
+		bpf_object__next_program;
+		bpf_object__prev_map;
+		bpf_object__prev_program;
+		bpf_prog_load_deprecated;
+		bpf_prog_load;
+		bpf_program__flags;
+		bpf_program__insn_cnt;
+		bpf_program__insns;
+		bpf_program__set_flags;
+		btf__add_btf;
+		btf__add_decl_tag;
+		btf__add_type_tag;
+		btf__dedup;
+		btf__dedup_deprecated;
+		btf__raw_data;
+		btf__type_cnt;
+		btf_dump__new;
+		btf_dump__new_deprecated;
+		libbpf_major_version;
+		libbpf_minor_version;
+		libbpf_version_string;
+		perf_buffer__new;
+		perf_buffer__new_deprecated;
+		perf_buffer__new_raw;
+		perf_buffer__new_raw_deprecated;
+} LIBBPF_0.5.0;
+
+LIBBPF_0.7.0 {
+	global:
+		bpf_btf_load;
+		bpf_program__log_buf;
+		bpf_program__log_level;
+		bpf_program__set_log_buf;
+		bpf_program__set_log_level;
+		libbpf_probe_bpf_helper;
+		libbpf_probe_bpf_map_type;
+		libbpf_probe_bpf_prog_type;
+		libbpf_set_memlock_rlim_max;
+};

tools/lib/bpf/libbpf_common.h

@@ -10,6 +10,7 @@
 #define __LIBBPF_LIBBPF_COMMON_H
 
 #include <string.h>
+#include "libbpf_version.h"
 
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
@@ -17,6 +18,46 @@
 
 #define LIBBPF_DEPRECATED(msg) __attribute__((deprecated(msg)))
 
+/* Mark a symbol as deprecated when libbpf version is >= {major}.{minor} */
+#define LIBBPF_DEPRECATED_SINCE(major, minor, msg)			    \
+	__LIBBPF_MARK_DEPRECATED_ ## major ## _ ## minor		    \
+		(LIBBPF_DEPRECATED("libbpf v" # major "." # minor "+: " msg))
+
+#define __LIBBPF_CURRENT_VERSION_GEQ(major, minor)			    \
+	(LIBBPF_MAJOR_VERSION > (major) ||				    \
+	 (LIBBPF_MAJOR_VERSION == (major) && LIBBPF_MINOR_VERSION >= (minor)))
+
+/* Add checks for other versions below when planning deprecation of API symbols
+ * with the LIBBPF_DEPRECATED_SINCE macro.
+ */
+#if __LIBBPF_CURRENT_VERSION_GEQ(0, 6)
+#define __LIBBPF_MARK_DEPRECATED_0_6(X) X
+#else
+#define __LIBBPF_MARK_DEPRECATED_0_6(X)
+#endif
+#if __LIBBPF_CURRENT_VERSION_GEQ(0, 7)
+#define __LIBBPF_MARK_DEPRECATED_0_7(X) X
+#else
+#define __LIBBPF_MARK_DEPRECATED_0_7(X)
+#endif
+#if __LIBBPF_CURRENT_VERSION_GEQ(0, 8)
+#define __LIBBPF_MARK_DEPRECATED_0_8(X) X
+#else
+#define __LIBBPF_MARK_DEPRECATED_0_8(X)
+#endif
+
+/* This set of internal macros allows to do "function overloading" based on
+ * number of arguments provided by used in backwards-compatible way during the
+ * transition to libbpf 1.0
+ * It's ugly but necessary evil that will be cleaned up when we get to 1.0.
+ * See bpf_prog_load() overload for example.
+ */
+#define ___libbpf_cat(A, B) A ## B
+#define ___libbpf_select(NAME, NUM) ___libbpf_cat(NAME, NUM)
+#define ___libbpf_nth(_1, _2, _3, _4, _5, _6, N, ...) N
+#define ___libbpf_cnt(...) ___libbpf_nth(__VA_ARGS__, 6, 5, 4, 3, 2, 1)
+#define ___libbpf_overload(NAME, ...) ___libbpf_select(NAME, ___libbpf_cnt(__VA_ARGS__))(__VA_ARGS__)
+
 /* Helper macro to declare and initialize libbpf options struct
  *
  * This dance with uninitialized declaration, followed by memset to zero,
@@ -30,7 +71,7 @@
  * including any extra padding, it with memset() and then assigns initial
  * values provided by users in struct initializer-syntax as varargs.
  */
-#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...)				    \
+#define LIBBPF_OPTS(TYPE, NAME, ...)					    \
 	struct TYPE NAME = ({ 						    \
 		memset(&NAME, 0, sizeof(struct TYPE));			    \
 		(struct TYPE) {						    \

tools/lib/bpf/libbpf_internal.h

@@ -13,6 +13,8 @@
 #include <limits.h>
 #include <errno.h>
 #include <linux/err.h>
+#include <fcntl.h>
+#include <unistd.h>
 #include "libbpf_legacy.h"
 #include "relo_core.h"
 
@@ -52,8 +54,8 @@
 #endif
 
 /* Older libelf all end up in this expression, for both 32 and 64 bit */
-#ifndef GELF_ST_VISIBILITY
-#define GELF_ST_VISIBILITY(o) ((o) & 0x03)
+#ifndef ELF64_ST_VISIBILITY
+#define ELF64_ST_VISIBILITY(o) ((o) & 0x03)
 #endif
 
 #define BTF_INFO_ENC(kind, kind_flag, vlen) \
@@ -69,6 +71,10 @@
 #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size)
 #define BTF_TYPE_FLOAT_ENC(name, sz) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
+#define BTF_TYPE_DECL_TAG_ENC(value, type, component_idx) \
+	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx)
+#define BTF_TYPE_TYPE_TAG_ENC(value, type) \
+	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 0, 0), type)
 
 #ifndef likely
 #define likely(x) __builtin_expect(!!(x), 1)
@@ -87,20 +93,40 @@
 	(offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD))
 #endif
 
+/* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is
+ * a string literal known at compilation time or char * pointer known only at
+ * runtime.
+ */
+#define str_has_pfx(str, pfx) \
+	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
+
 /* Symbol versioning is different between static and shared library.
  * Properly versioned symbols are needed for shared library, but
  * only the symbol of the new version is needed for static library.
+ * Starting with GNU C 10, use symver attribute instead of .symver assembler
+ * directive, which works better with GCC LTO builds.
  */
-#ifdef SHARED
-# define COMPAT_VERSION(internal_name, api_name, version) \
+#if defined(SHARED) && defined(__GNUC__) && __GNUC__ >= 10
+
+#define DEFAULT_VERSION(internal_name, api_name, version) \
+	__attribute__((symver(#api_name "@@" #version)))
+#define COMPAT_VERSION(internal_name, api_name, version) \
+	__attribute__((symver(#api_name "@" #version)))
+
+#elif defined(SHARED)
+
+#define COMPAT_VERSION(internal_name, api_name, version) \
 	asm(".symver " #internal_name "," #api_name "@" #version);
-# define DEFAULT_VERSION(internal_name, api_name, version) \
+#define DEFAULT_VERSION(internal_name, api_name, version) \
 	asm(".symver " #internal_name "," #api_name "@@" #version);
-#else
-# define COMPAT_VERSION(internal_name, api_name, version)
-# define DEFAULT_VERSION(internal_name, api_name, version) \
+
+#else /* !SHARED */
+
+#define COMPAT_VERSION(internal_name, api_name, version)
+#define DEFAULT_VERSION(internal_name, api_name, version) \
 	extern typeof(internal_name) api_name \
 	__attribute__((alias(#internal_name)));
+
 #endif
 
 extern void libbpf_print(enum libbpf_print_level level,
@@ -143,10 +169,31 @@ static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size)
 	return realloc(ptr, total);
 }
 
+/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst
+ * is zero-terminated string no matter what (unless sz == 0, in which case
+ * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs
+ * in what is returned. Given this is internal helper, it's trivial to extend
+ * this, when necessary. Use this instead of strncpy inside libbpf source code.
+ */
+static inline void libbpf_strlcpy(char *dst, const char *src, size_t sz)
+{
+	size_t i;
+
+	if (sz == 0)
+		return;
+
+	sz--;
+	for (i = 0; i < sz && src[i]; i++)
+		dst[i] = src[i];
+	dst[i] = '\0';
+}
+
+__u32 get_kernel_version(void);
+
 struct btf;
 struct btf_type;
 
-struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id);
+struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id);
 const char *btf_kind_str(const struct btf_type *t);
 const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
 
@@ -171,8 +218,9 @@ enum map_def_parts {
 	MAP_DEF_NUMA_NODE	= 0x080,
 	MAP_DEF_PINNING		= 0x100,
 	MAP_DEF_INNER_MAP	= 0x200,
+	MAP_DEF_MAP_EXTRA	= 0x400,
 
-	MAP_DEF_ALL		= 0x3ff, /* combination of all above */
+	MAP_DEF_ALL		= 0x7ff, /* combination of all above */
 };
 
 struct btf_map_def {
@@ -186,6 +234,7 @@ struct btf_map_def {
 	__u32 map_flags;
 	__u32 numa_node;
 	__u32 pinning;
+	__u64 map_extra;
 };
 
 int parse_btf_map_def(const char *map_name, struct btf *btf,
@@ -244,46 +293,52 @@ static inline bool libbpf_validate_opts(const char *opts,
 					(opts)->sz - __off);		      \
 })
 
+enum kern_feature_id {
+	/* v4.14: kernel support for program & map names. */
+	FEAT_PROG_NAME,
+	/* v5.2: kernel support for global data sections. */
+	FEAT_GLOBAL_DATA,
+	/* BTF support */
+	FEAT_BTF,
+	/* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
+	FEAT_BTF_FUNC,
+	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
+	FEAT_BTF_DATASEC,
+	/* BTF_FUNC_GLOBAL is supported */
+	FEAT_BTF_GLOBAL_FUNC,
+	/* BPF_F_MMAPABLE is supported for arrays */
+	FEAT_ARRAY_MMAP,
+	/* kernel support for expected_attach_type in BPF_PROG_LOAD */
+	FEAT_EXP_ATTACH_TYPE,
+	/* bpf_probe_read_{kernel,user}[_str] helpers */
+	FEAT_PROBE_READ_KERN,
+	/* BPF_PROG_BIND_MAP is supported */
+	FEAT_PROG_BIND_MAP,
+	/* Kernel support for module BTFs */
+	FEAT_MODULE_BTF,
+	/* BTF_KIND_FLOAT support */
+	FEAT_BTF_FLOAT,
+	/* BPF perf link support */
+	FEAT_PERF_LINK,
+	/* BTF_KIND_DECL_TAG support */
+	FEAT_BTF_DECL_TAG,
+	/* BTF_KIND_TYPE_TAG support */
+	FEAT_BTF_TYPE_TAG,
+	/* memcg-based accounting for BPF maps and progs */
+	FEAT_MEMCG_ACCOUNT,
+	__FEAT_CNT,
+};
+
+int probe_memcg_account(void);
+bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
+int bump_rlimit_memlock(void);
 
 int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
 int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 			 const char *str_sec, size_t str_len);
+int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level);
 
-struct bpf_prog_load_params {
-	enum bpf_prog_type prog_type;
-	enum bpf_attach_type expected_attach_type;
-	const char *name;
-	const struct bpf_insn *insns;
-	size_t insn_cnt;
-	const char *license;
-	__u32 kern_version;
-	__u32 attach_prog_fd;
-	__u32 attach_btf_obj_fd;
-	__u32 attach_btf_id;
-	__u32 prog_ifindex;
-	__u32 prog_btf_fd;
-	__u32 prog_flags;
-
-	__u32 func_info_rec_size;
-	const void *func_info;
-	__u32 func_info_cnt;
-
-	__u32 line_info_rec_size;
-	const void *line_info;
-	__u32 line_info_cnt;
-
-	__u32 log_level;
-	char *log_buf;
-	size_t log_buf_sz;
-};
-
-int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr);
-
-int bpf_object__section_size(const struct bpf_object *obj, const char *name,
-			     __u32 *size);
-int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
-				__u32 *off);
 struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
 void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
 				const char **prefix, int *kind);
@@ -386,6 +441,8 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct
 int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx);
 int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx);
 int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx);
+__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
+				 __u32 kind);
 
 extern enum libbpf_strict_mode libbpf_mode;
 
@@ -447,4 +504,26 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn)
 	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
 }
 
+/* if fd is stdin, stdout, or stderr, dup to a fd greater than 2
+ * Takes ownership of the fd passed in, and closes it if calling
+ * fcntl(fd, F_DUPFD_CLOEXEC, 3).
+ */
+static inline int ensure_good_fd(int fd)
+{
+	int old_fd = fd, saved_errno;
+
+	if (fd < 0)
+		return fd;
+	if (fd < 3) {
+		fd = fcntl(fd, F_DUPFD_CLOEXEC, 3);
+		saved_errno = errno;
+		close(old_fd);
+		if (fd < 0) {
+			pr_warn("failed to dup FD %d to FD > 2: %d\n", old_fd, -saved_errno);
+			errno = saved_errno;
+		}
+	}
+	return fd;
+}
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */

tools/lib/bpf/libbpf_legacy.h

@@ -45,12 +45,41 @@ enum libbpf_strict_mode {
 	 * (positive) error code.
 	 */
 	LIBBPF_STRICT_DIRECT_ERRS = 0x02,
+	/*
+	 * Enforce strict BPF program section (SEC()) names.
+	 * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were
+	 * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become
+	 * unrecognized by libbpf and would have to be just SEC("xdp") and
+	 * SEC("xdp") and SEC("perf_event").
+	 *
+	 * Note, in this mode the program pin path will be based on the
+	 * function name instead of section name.
+	 */
+	LIBBPF_STRICT_SEC_NAME = 0x04,
+	/*
+	 * Disable the global 'bpf_objects_list'. Maintaining this list adds
+	 * a race condition to bpf_object__open() and bpf_object__close().
+	 * Clients can maintain it on their own if it is valuable for them.
+	 */
+	LIBBPF_STRICT_NO_OBJECT_LIST = 0x08,
+	/*
+	 * Automatically bump RLIMIT_MEMLOCK using setrlimit() before the
+	 * first BPF program or map creation operation. This is done only if
+	 * kernel is too old to support memcg-based memory accounting for BPF
+	 * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY,
+	 * but it can be overriden with libbpf_set_memlock_rlim_max() API.
+	 * Note that libbpf_set_memlock_rlim_max() needs to be called before
+	 * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load()
+	 * operation.
+	 */
+	LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10,
 
 	__LIBBPF_STRICT_LAST,
 };
 
 LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode);
 
+#define DECLARE_LIBBPF_OPTS LIBBPF_OPTS
 
 #ifdef __cplusplus
 } /* extern "C" */

tools/lib/bpf/libbpf_probes.c

@@ -33,7 +33,7 @@ static int get_vendor_id(int ifindex)
 
 	snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname);
 
-	fd = open(path, O_RDONLY);
+	fd = open(path, O_RDONLY | O_CLOEXEC);
 	if (fd < 0)
 		return -1;
 
@@ -48,41 +48,65 @@ static int get_vendor_id(int ifindex)
 	return strtol(buf, NULL, 0);
 }
 
-static int get_kernel_version(void)
+static int probe_prog_load(enum bpf_prog_type prog_type,
+			   const struct bpf_insn *insns, size_t insns_cnt,
+			   char *log_buf, size_t log_buf_sz,
+			   __u32 ifindex)
 {
-	int version, subversion, patchlevel;
-	struct utsname utsn;
-
-	/* Return 0 on failure, and attempt to probe with empty kversion */
-	if (uname(&utsn))
-		return 0;
-
-	if (sscanf(utsn.release, "%d.%d.%d",
-		   &version, &subversion, &patchlevel) != 3)
-		return 0;
-
-	return (version << 16) + (subversion << 8) + patchlevel;
-}
-
-static void
-probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
-	   size_t insns_cnt, char *buf, size_t buf_len, __u32 ifindex)
-{
-	struct bpf_load_program_attr xattr = {};
-	int fd;
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.log_buf = log_buf,
+		.log_size = log_buf_sz,
+		.log_level = log_buf ? 1 : 0,
+		.prog_ifindex = ifindex,
+	);
+	int fd, err, exp_err = 0;
+	const char *exp_msg = NULL;
+	char buf[4096];
 
 	switch (prog_type) {
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
-		xattr.expected_attach_type = BPF_CGROUP_INET4_CONNECT;
+		opts.expected_attach_type = BPF_CGROUP_INET4_CONNECT;
 		break;
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
-		xattr.expected_attach_type = BPF_CGROUP_GETSOCKOPT;
+		opts.expected_attach_type = BPF_CGROUP_GETSOCKOPT;
 		break;
 	case BPF_PROG_TYPE_SK_LOOKUP:
-		xattr.expected_attach_type = BPF_SK_LOOKUP;
+		opts.expected_attach_type = BPF_SK_LOOKUP;
 		break;
 	case BPF_PROG_TYPE_KPROBE:
-		xattr.kern_version = get_kernel_version();
+		opts.kern_version = get_kernel_version();
+		break;
+	case BPF_PROG_TYPE_LIRC_MODE2:
+		opts.expected_attach_type = BPF_LIRC_MODE2;
+		break;
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_LSM:
+		opts.log_buf = buf;
+		opts.log_size = sizeof(buf);
+		opts.log_level = 1;
+		if (prog_type == BPF_PROG_TYPE_TRACING)
+			opts.expected_attach_type = BPF_TRACE_FENTRY;
+		else
+			opts.expected_attach_type = BPF_MODIFY_RETURN;
+		opts.attach_btf_id = 1;
+
+		exp_err = -EINVAL;
+		exp_msg = "attach_btf_id 1 is not a function";
+		break;
+	case BPF_PROG_TYPE_EXT:
+		opts.log_buf = buf;
+		opts.log_size = sizeof(buf);
+		opts.log_level = 1;
+		opts.attach_btf_id = 1;
+
+		exp_err = -EINVAL;
+		exp_msg = "Cannot replace kernel functions";
+		break;
+	case BPF_PROG_TYPE_SYSCALL:
+		opts.prog_flags = BPF_F_SLEEPABLE;
+		break;
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		exp_err = -524; /* -ENOTSUPP */
 		break;
 	case BPF_PROG_TYPE_UNSPEC:
 	case BPF_PROG_TYPE_SOCKET_FILTER:
@@ -103,27 +127,42 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
-	case BPF_PROG_TYPE_LIRC_MODE2:
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
-	case BPF_PROG_TYPE_TRACING:
-	case BPF_PROG_TYPE_STRUCT_OPS:
-	case BPF_PROG_TYPE_EXT:
-	case BPF_PROG_TYPE_LSM:
-	default:
 		break;
+	default:
+		return -EOPNOTSUPP;
 	}
 
-	xattr.prog_type = prog_type;
-	xattr.insns = insns;
-	xattr.insns_cnt = insns_cnt;
-	xattr.license = "GPL";
-	xattr.prog_ifindex = ifindex;
-
-	fd = bpf_load_program_xattr(&xattr, buf, buf_len);
+	fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts);
+	err = -errno;
 	if (fd >= 0)
 		close(fd);
+	if (exp_err) {
+		if (fd >= 0 || err != exp_err)
+			return 0;
+		if (exp_msg && !strstr(buf, exp_msg))
+			return 0;
+		return 1;
+	}
+	return fd >= 0 ? 1 : 0;
+}
+
+int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN()
+	};
+	const size_t insn_cnt = ARRAY_SIZE(insns);
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0, 0);
+	return libbpf_err(ret);
 }
 
 bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
@@ -133,12 +172,16 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
 		BPF_EXIT_INSN()
 	};
 
+	/* prefer libbpf_probe_bpf_prog_type() unless offload is requested */
+	if (ifindex == 0)
+		return libbpf_probe_bpf_prog_type(prog_type, NULL) == 1;
+
 	if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS)
 		/* nfp returns -EINVAL on exit(0) with TC offload */
 		insns[0].imm = 2;
 
 	errno = 0;
-	probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
+	probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
 
 	return errno != EINVAL && errno != EOPNOTSUPP;
 }
@@ -166,7 +209,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 	memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len);
 	memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len);
 
-	btf_fd = bpf_load_btf(raw_btf, btf_len, NULL, 0, false);
+	btf_fd = bpf_btf_load(raw_btf, btf_len, NULL);
 
 	free(raw_btf);
 	return btf_fd;
@@ -199,17 +242,18 @@ static int load_local_storage_btf(void)
 				     strs, sizeof(strs));
 }
 
-bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+static int probe_map_create(enum bpf_map_type map_type, __u32 ifindex)
 {
-	int key_size, value_size, max_entries, map_flags;
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
+	int key_size, value_size, max_entries;
 	__u32 btf_key_type_id = 0, btf_value_type_id = 0;
-	struct bpf_create_map_attr attr = {};
-	int fd = -1, btf_fd = -1, fd_inner;
+	int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err;
+
+	opts.map_ifindex = ifindex;
 
 	key_size	= sizeof(__u32);
 	value_size	= sizeof(__u32);
 	max_entries	= 1;
-	map_flags	= 0;
 
 	switch (map_type) {
 	case BPF_MAP_TYPE_STACK_TRACE:
@@ -218,7 +262,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_LPM_TRIE:
 		key_size	= sizeof(__u64);
 		value_size	= sizeof(__u64);
-		map_flags	= BPF_F_NO_PREALLOC;
+		opts.map_flags	= BPF_F_NO_PREALLOC;
 		break;
 	case BPF_MAP_TYPE_CGROUP_STORAGE:
 	case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
@@ -237,17 +281,25 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		btf_value_type_id = 3;
 		value_size = 8;
 		max_entries = 0;
-		map_flags = BPF_F_NO_PREALLOC;
+		opts.map_flags = BPF_F_NO_PREALLOC;
 		btf_fd = load_local_storage_btf();
 		if (btf_fd < 0)
-			return false;
+			return btf_fd;
 		break;
 	case BPF_MAP_TYPE_RINGBUF:
 		key_size = 0;
 		value_size = 0;
 		max_entries = 4096;
 		break;
-	case BPF_MAP_TYPE_UNSPEC:
+	case BPF_MAP_TYPE_STRUCT_OPS:
+		/* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */
+		opts.btf_vmlinux_value_type_id = 1;
+		exp_err = -524; /* -ENOTSUPP */
+		break;
+	case BPF_MAP_TYPE_BLOOM_FILTER:
+		key_size = 0;
+		max_entries = 1;
+		break;
 	case BPF_MAP_TYPE_HASH:
 	case BPF_MAP_TYPE_ARRAY:
 	case BPF_MAP_TYPE_PROG_ARRAY:
@@ -266,9 +318,10 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_XSKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
-	case BPF_MAP_TYPE_STRUCT_OPS:
-	default:
 		break;
+	case BPF_MAP_TYPE_UNSPEC:
+	default:
+		return -EOPNOTSUPP;
 	}
 
 	if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
@@ -277,37 +330,102 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		 * map-in-map for offload
 		 */
 		if (ifindex)
-			return false;
+			goto cleanup;
 
-		fd_inner = bpf_create_map(BPF_MAP_TYPE_HASH,
-					  sizeof(__u32), sizeof(__u32), 1, 0);
+		fd_inner = bpf_map_create(BPF_MAP_TYPE_HASH, NULL,
+					  sizeof(__u32), sizeof(__u32), 1, NULL);
 		if (fd_inner < 0)
-			return false;
-		fd = bpf_create_map_in_map(map_type, NULL, sizeof(__u32),
-					   fd_inner, 1, 0);
-		close(fd_inner);
-	} else {
-		/* Note: No other restriction on map type probes for offload */
-		attr.map_type = map_type;
-		attr.key_size = key_size;
-		attr.value_size = value_size;
-		attr.max_entries = max_entries;
-		attr.map_flags = map_flags;
-		attr.map_ifindex = ifindex;
-		if (btf_fd >= 0) {
-			attr.btf_fd = btf_fd;
-			attr.btf_key_type_id = btf_key_type_id;
-			attr.btf_value_type_id = btf_value_type_id;
-		}
+			goto cleanup;
 
-		fd = bpf_create_map_xattr(&attr);
+		opts.inner_map_fd = fd_inner;
 	}
+
+	if (btf_fd >= 0) {
+		opts.btf_fd = btf_fd;
+		opts.btf_key_type_id = btf_key_type_id;
+		opts.btf_value_type_id = btf_value_type_id;
+	}
+
+	fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts);
+	err = -errno;
+
+cleanup:
 	if (fd >= 0)
 		close(fd);
+	if (fd_inner >= 0)
+		close(fd_inner);
 	if (btf_fd >= 0)
 		close(btf_fd);
 
-	return fd >= 0;
+	if (exp_err)
+		return fd < 0 && err == exp_err ? 1 : 0;
+	else
+		return fd >= 0 ? 1 : 0;
+}
+
+int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts)
+{
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	ret = probe_map_create(map_type, 0);
+	return libbpf_err(ret);
+}
+
+bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+{
+	return probe_map_create(map_type, ifindex) == 1;
+}
+
+int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helper_id,
+			    const void *opts)
+{
+	struct bpf_insn insns[] = {
+		BPF_EMIT_CALL((__u32)helper_id),
+		BPF_EXIT_INSN(),
+	};
+	const size_t insn_cnt = ARRAY_SIZE(insns);
+	char buf[4096];
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	/* we can't successfully load all prog types to check for BPF helper
+	 * support, so bail out with -EOPNOTSUPP error
+	 */
+	switch (prog_type) {
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_EXT:
+	case BPF_PROG_TYPE_LSM:
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		return -EOPNOTSUPP;
+	default:
+		break;
+	}
+
+	buf[0] = '\0';
+	ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf), 0);
+	if (ret < 0)
+		return libbpf_err(ret);
+
+	/* If BPF verifier doesn't recognize BPF helper ID (enum bpf_func_id)
+	 * at all, it will emit something like "invalid func unknown#181".
+	 * If BPF verifier recognizes BPF helper but it's not supported for
+	 * given BPF program type, it will emit "unknown func bpf_sys_bpf#166".
+	 * In both cases, provided combination of BPF program type and BPF
+	 * helper is not supported by the kernel.
+	 * In all other cases, probe_prog_load() above will either succeed (e.g.,
+	 * because BPF helper happens to accept no input arguments or it
+	 * accepts one input argument and initial PTR_TO_CTX is fine for
+	 * that), or we'll get some more specific BPF verifier error about
+	 * some unsatisfied conditions.
+	 */
+	if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func ")))
+		return 0;
+	return 1; /* assume supported */
 }
 
 bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
@@ -320,8 +438,7 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
 	char buf[4096] = {};
 	bool res;
 
-	probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf),
-		   ifindex);
+	probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), ifindex);
 	res = !grep(buf, "invalid func ") && !grep(buf, "unknown func ");
 
 	if (ifindex) {
@@ -353,8 +470,8 @@ bool bpf_probe_large_insn_limit(__u32 ifindex)
 	insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
 
 	errno = 0;
-	probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
-		   ifindex);
+	probe_prog_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
+			ifindex);
 
 	return errno != E2BIG && errno != EINVAL;
 }

tools/lib/bpf/linker.c

@@ -15,7 +15,6 @@
 #include <linux/btf.h>
 #include <elf.h>
 #include <libelf.h>
-#include <gelf.h>
 #include <fcntl.h>
 #include "libbpf.h"
 #include "btf.h"
@@ -303,7 +302,7 @@ static int init_output_elf(struct bpf_linker *linker, const char *file)
 	if (!linker->filename)
 		return -ENOMEM;
 
-	linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC, 0644);
+	linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
 	if (linker->fd < 0) {
 		err = -errno;
 		pr_warn("failed to create '%s': %d\n", file, err);
@@ -325,12 +324,12 @@ static int init_output_elf(struct bpf_linker *linker, const char *file)
 
 	linker->elf_hdr->e_machine = EM_BPF;
 	linker->elf_hdr->e_type = ET_REL;
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2LSB;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2MSB;
 #else
-#error "Unknown __BYTE_ORDER"
+#error "Unknown __BYTE_ORDER__"
 #endif
 
 	/* STRTAB */
@@ -540,12 +539,12 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
 				const struct bpf_linker_file_opts *opts,
 				struct src_obj *obj)
 {
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	const int host_endianness = ELFDATA2LSB;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	const int host_endianness = ELFDATA2MSB;
 #else
-#error "Unknown __BYTE_ORDER"
+#error "Unknown __BYTE_ORDER__"
 #endif
 	int err = 0;
 	Elf_Scn *scn;
@@ -558,7 +557,7 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
 
 	obj->filename = filename;
 
-	obj->fd = open(filename, O_RDONLY);
+	obj->fd = open(filename, O_RDONLY | O_CLOEXEC);
 	if (obj->fd < 0) {
 		err = -errno;
 		pr_warn("failed to open file '%s': %d\n", filename, err);
@@ -922,7 +921,7 @@ static int check_btf_type_id(__u32 *type_id, void *ctx)
 {
 	struct btf *btf = ctx;
 
-	if (*type_id > btf__get_nr_types(btf))
+	if (*type_id >= btf__type_cnt(btf))
 		return -EINVAL;
 
 	return 0;
@@ -949,8 +948,8 @@ static int linker_sanity_check_btf(struct src_obj *obj)
 	if (!obj->btf)
 		return 0;
 
-	n = btf__get_nr_types(obj->btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
 		t = btf_type_by_id(obj->btf, i);
 
 		err = err ?: btf_type_visit_type_ids(t, check_btf_type_id, obj->btf);
@@ -1660,8 +1659,8 @@ static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sy
 		return -EINVAL;
 	}
 
-	n = btf__get_nr_types(obj->btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(obj->btf, i);
 
 		/* some global and extern FUNCs and VARs might not be associated with any
@@ -2135,8 +2134,8 @@ static int linker_fixup_btf(struct src_obj *obj)
 	if (!obj->btf)
 		return 0;
 
-	n = btf__get_nr_types(obj->btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
 		struct btf_var_secinfo *vi;
 		struct btf_type *t;
 
@@ -2239,14 +2238,14 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 	if (!obj->btf)
 		return 0;
 
-	start_id = btf__get_nr_types(linker->btf) + 1;
-	n = btf__get_nr_types(obj->btf);
+	start_id = btf__type_cnt(linker->btf);
+	n = btf__type_cnt(obj->btf);
 
 	obj->btf_type_map = calloc(n + 1, sizeof(int));
 	if (!obj->btf_type_map)
 		return -ENOMEM;
 
-	for (i = 1; i <= n; i++) {
+	for (i = 1; i < n; i++) {
 		struct glob_sym *glob_sym = NULL;
 
 		t = btf__type_by_id(obj->btf, i);
@@ -2301,8 +2300,8 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 	}
 
 	/* remap all the types except DATASECs */
-	n = btf__get_nr_types(linker->btf);
-	for (i = start_id; i <= n; i++) {
+	n = btf__type_cnt(linker->btf);
+	for (i = start_id; i < n; i++) {
 		struct btf_type *dst_t = btf_type_by_id(linker->btf, i);
 
 		if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map))
@@ -2655,13 +2654,14 @@ static int emit_elf_data_sec(struct bpf_linker *linker, const char *sec_name,
 
 static int finalize_btf(struct bpf_linker *linker)
 {
+	LIBBPF_OPTS(btf_dedup_opts, opts);
 	struct btf *btf = linker->btf;
 	const void *raw_data;
 	int i, j, id, err;
 	__u32 raw_sz;
 
 	/* bail out if no BTF data was produced */
-	if (btf__get_nr_types(linker->btf) == 0)
+	if (btf__type_cnt(linker->btf) == 1)
 		return 0;
 
 	for (i = 1; i < linker->sec_cnt; i++) {
@@ -2691,14 +2691,15 @@ static int finalize_btf(struct bpf_linker *linker)
 		return err;
 	}
 
-	err = btf__dedup(linker->btf, linker->btf_ext, NULL);
+	opts.btf_ext = linker->btf_ext;
+	err = btf__dedup(linker->btf, &opts);
 	if (err) {
 		pr_warn("BTF dedup failed: %d\n", err);
 		return err;
 	}
 
 	/* Emit .BTF section */
-	raw_data = btf__get_raw_data(linker->btf, &raw_sz);
+	raw_data = btf__raw_data(linker->btf, &raw_sz);
 	if (!raw_data)
 		return -ENOMEM;
 

tools/lib/bpf/relo_core.c

@@ -1,6 +1,60 @@
 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2019 Facebook */
 
+#ifdef __KERNEL__
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/string.h>
+#include <linux/bpf_verifier.h>
+#include "relo_core.h"
+
+static const char *btf_kind_str(const struct btf_type *t)
+{
+	return btf_type_str(t);
+}
+
+static bool is_ldimm64_insn(struct bpf_insn *insn)
+{
+	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+}
+
+static const struct btf_type *
+skip_mods_and_typedefs(const struct btf *btf, u32 id, u32 *res_id)
+{
+	return btf_type_skip_modifiers(btf, id, res_id);
+}
+
+static const char *btf__name_by_offset(const struct btf *btf, u32 offset)
+{
+	return btf_name_by_offset(btf, offset);
+}
+
+static s64 btf__resolve_size(const struct btf *btf, u32 type_id)
+{
+	const struct btf_type *t;
+	int size;
+
+	t = btf_type_by_id(btf, type_id);
+	t = btf_resolve_size(btf, t, &size);
+	if (IS_ERR(t))
+		return PTR_ERR(t);
+	return size;
+}
+
+enum libbpf_print_level {
+	LIBBPF_WARN,
+	LIBBPF_INFO,
+	LIBBPF_DEBUG,
+};
+
+#undef pr_warn
+#undef pr_info
+#undef pr_debug
+#define pr_warn(fmt, log, ...)	bpf_log((void *)log, fmt, "", ##__VA_ARGS__)
+#define pr_info(fmt, log, ...)	bpf_log((void *)log, fmt, "", ##__VA_ARGS__)
+#define pr_debug(fmt, log, ...)	bpf_log((void *)log, fmt, "", ##__VA_ARGS__)
+#define libbpf_print(level, fmt, ...)	bpf_log((void *)prog_name, fmt, ##__VA_ARGS__)
+#else
 #include <stdio.h>
 #include <string.h>
 #include <errno.h>
@@ -12,33 +66,7 @@
 #include "btf.h"
 #include "str_error.h"
 #include "libbpf_internal.h"
-
-#define BPF_CORE_SPEC_MAX_LEN 64
-
-/* represents BPF CO-RE field or array element accessor */
-struct bpf_core_accessor {
-	__u32 type_id;		/* struct/union type or array element type */
-	__u32 idx;		/* field index or array index */
-	const char *name;	/* field name or NULL for array accessor */
-};
-
-struct bpf_core_spec {
-	const struct btf *btf;
-	/* high-level spec: named fields and array indices only */
-	struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN];
-	/* original unresolved (no skip_mods_or_typedefs) root type ID */
-	__u32 root_type_id;
-	/* CO-RE relocation kind */
-	enum bpf_core_relo_kind relo_kind;
-	/* high-level spec length */
-	int len;
-	/* raw, low-level spec: 1-to-1 with accessor spec string */
-	int raw_spec[BPF_CORE_SPEC_MAX_LEN];
-	/* raw spec length */
-	int raw_len;
-	/* field bit offset represented by spec */
-	__u32 bit_offset;
-};
+#endif
 
 static bool is_flex_arr(const struct btf *btf,
 			const struct bpf_core_accessor *acc,
@@ -51,25 +79,25 @@ static bool is_flex_arr(const struct btf *btf,
 		return false;
 
 	/* has to be the last member of enclosing struct */
-	t = btf__type_by_id(btf, acc->type_id);
+	t = btf_type_by_id(btf, acc->type_id);
 	return acc->idx == btf_vlen(t) - 1;
 }
 
 static const char *core_relo_kind_str(enum bpf_core_relo_kind kind)
 {
 	switch (kind) {
-	case BPF_FIELD_BYTE_OFFSET: return "byte_off";
-	case BPF_FIELD_BYTE_SIZE: return "byte_sz";
-	case BPF_FIELD_EXISTS: return "field_exists";
-	case BPF_FIELD_SIGNED: return "signed";
-	case BPF_FIELD_LSHIFT_U64: return "lshift_u64";
-	case BPF_FIELD_RSHIFT_U64: return "rshift_u64";
-	case BPF_TYPE_ID_LOCAL: return "local_type_id";
-	case BPF_TYPE_ID_TARGET: return "target_type_id";
-	case BPF_TYPE_EXISTS: return "type_exists";
-	case BPF_TYPE_SIZE: return "type_size";
-	case BPF_ENUMVAL_EXISTS: return "enumval_exists";
-	case BPF_ENUMVAL_VALUE: return "enumval_value";
+	case BPF_CORE_FIELD_BYTE_OFFSET: return "byte_off";
+	case BPF_CORE_FIELD_BYTE_SIZE: return "byte_sz";
+	case BPF_CORE_FIELD_EXISTS: return "field_exists";
+	case BPF_CORE_FIELD_SIGNED: return "signed";
+	case BPF_CORE_FIELD_LSHIFT_U64: return "lshift_u64";
+	case BPF_CORE_FIELD_RSHIFT_U64: return "rshift_u64";
+	case BPF_CORE_TYPE_ID_LOCAL: return "local_type_id";
+	case BPF_CORE_TYPE_ID_TARGET: return "target_type_id";
+	case BPF_CORE_TYPE_EXISTS: return "type_exists";
+	case BPF_CORE_TYPE_SIZE: return "type_size";
+	case BPF_CORE_ENUMVAL_EXISTS: return "enumval_exists";
+	case BPF_CORE_ENUMVAL_VALUE: return "enumval_value";
 	default: return "unknown";
 	}
 }
@@ -77,12 +105,12 @@ static const char *core_relo_kind_str(enum bpf_core_relo_kind kind)
 static bool core_relo_is_field_based(enum bpf_core_relo_kind kind)
 {
 	switch (kind) {
-	case BPF_FIELD_BYTE_OFFSET:
-	case BPF_FIELD_BYTE_SIZE:
-	case BPF_FIELD_EXISTS:
-	case BPF_FIELD_SIGNED:
-	case BPF_FIELD_LSHIFT_U64:
-	case BPF_FIELD_RSHIFT_U64:
+	case BPF_CORE_FIELD_BYTE_OFFSET:
+	case BPF_CORE_FIELD_BYTE_SIZE:
+	case BPF_CORE_FIELD_EXISTS:
+	case BPF_CORE_FIELD_SIGNED:
+	case BPF_CORE_FIELD_LSHIFT_U64:
+	case BPF_CORE_FIELD_RSHIFT_U64:
 		return true;
 	default:
 		return false;
@@ -92,10 +120,10 @@ static bool core_relo_is_field_based(enum bpf_core_relo_kind kind)
 static bool core_relo_is_type_based(enum bpf_core_relo_kind kind)
 {
 	switch (kind) {
-	case BPF_TYPE_ID_LOCAL:
-	case BPF_TYPE_ID_TARGET:
-	case BPF_TYPE_EXISTS:
-	case BPF_TYPE_SIZE:
+	case BPF_CORE_TYPE_ID_LOCAL:
+	case BPF_CORE_TYPE_ID_TARGET:
+	case BPF_CORE_TYPE_EXISTS:
+	case BPF_CORE_TYPE_SIZE:
 		return true;
 	default:
 		return false;
@@ -105,8 +133,8 @@ static bool core_relo_is_type_based(enum bpf_core_relo_kind kind)
 static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind)
 {
 	switch (kind) {
-	case BPF_ENUMVAL_EXISTS:
-	case BPF_ENUMVAL_VALUE:
+	case BPF_CORE_ENUMVAL_EXISTS:
+	case BPF_CORE_ENUMVAL_VALUE:
 		return true;
 	default:
 		return false;
@@ -150,7 +178,7 @@ static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind)
  * Enum value-based relocations (ENUMVAL_EXISTS/ENUMVAL_VALUE) use access
  * string to specify enumerator's value index that need to be relocated.
  */
-static int bpf_core_parse_spec(const struct btf *btf,
+static int bpf_core_parse_spec(const char *prog_name, const struct btf *btf,
 			       __u32 type_id,
 			       const char *spec_str,
 			       enum bpf_core_relo_kind relo_kind,
@@ -272,8 +300,8 @@ static int bpf_core_parse_spec(const struct btf *btf,
 				return sz;
 			spec->bit_offset += access_idx * sz * 8;
 		} else {
-			pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n",
-				type_id, spec_str, i, id, btf_kind_str(t));
+			pr_warn("prog '%s': relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n",
+				prog_name, type_id, spec_str, i, id, btf_kind_str(t));
 			return -EINVAL;
 		}
 	}
@@ -346,8 +374,6 @@ static int bpf_core_fields_are_compat(const struct btf *local_btf,
 		targ_id = btf_array(targ_type)->type;
 		goto recur;
 	default:
-		pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n",
-			btf_kind(local_type), local_id, targ_id);
 		return 0;
 	}
 }
@@ -388,7 +414,7 @@ static int bpf_core_match_member(const struct btf *local_btf,
 		return 0;
 
 	local_id = local_acc->type_id;
-	local_type = btf__type_by_id(local_btf, local_id);
+	local_type = btf_type_by_id(local_btf, local_id);
 	local_member = btf_members(local_type) + local_acc->idx;
 	local_name = btf__name_by_offset(local_btf, local_member->name_off);
 
@@ -571,7 +597,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 
 	*field_sz = 0;
 
-	if (relo->kind == BPF_FIELD_EXISTS) {
+	if (relo->kind == BPF_CORE_FIELD_EXISTS) {
 		*val = spec ? 1 : 0;
 		return 0;
 	}
@@ -580,11 +606,11 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 		return -EUCLEAN; /* request instruction poisoning */
 
 	acc = &spec->spec[spec->len - 1];
-	t = btf__type_by_id(spec->btf, acc->type_id);
+	t = btf_type_by_id(spec->btf, acc->type_id);
 
 	/* a[n] accessor needs special handling */
 	if (!acc->name) {
-		if (relo->kind == BPF_FIELD_BYTE_OFFSET) {
+		if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) {
 			*val = spec->bit_offset / 8;
 			/* remember field size for load/store mem size */
 			sz = btf__resolve_size(spec->btf, acc->type_id);
@@ -592,7 +618,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 				return -EINVAL;
 			*field_sz = sz;
 			*type_id = acc->type_id;
-		} else if (relo->kind == BPF_FIELD_BYTE_SIZE) {
+		} else if (relo->kind == BPF_CORE_FIELD_BYTE_SIZE) {
 			sz = btf__resolve_size(spec->btf, acc->type_id);
 			if (sz < 0)
 				return -EINVAL;
@@ -644,36 +670,36 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 		*validate = !bitfield;
 
 	switch (relo->kind) {
-	case BPF_FIELD_BYTE_OFFSET:
+	case BPF_CORE_FIELD_BYTE_OFFSET:
 		*val = byte_off;
 		if (!bitfield) {
 			*field_sz = byte_sz;
 			*type_id = field_type_id;
 		}
 		break;
-	case BPF_FIELD_BYTE_SIZE:
+	case BPF_CORE_FIELD_BYTE_SIZE:
 		*val = byte_sz;
 		break;
-	case BPF_FIELD_SIGNED:
+	case BPF_CORE_FIELD_SIGNED:
 		/* enums will be assumed unsigned */
 		*val = btf_is_enum(mt) ||
 		       (btf_int_encoding(mt) & BTF_INT_SIGNED);
 		if (validate)
 			*validate = true; /* signedness is never ambiguous */
 		break;
-	case BPF_FIELD_LSHIFT_U64:
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+	case BPF_CORE_FIELD_LSHIFT_U64:
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 		*val = 64 - (bit_off + bit_sz - byte_off  * 8);
 #else
 		*val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8);
 #endif
 		break;
-	case BPF_FIELD_RSHIFT_U64:
+	case BPF_CORE_FIELD_RSHIFT_U64:
 		*val = 64 - bit_sz;
 		if (validate)
 			*validate = true; /* right shift is never ambiguous */
 		break;
-	case BPF_FIELD_EXISTS:
+	case BPF_CORE_FIELD_EXISTS:
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -683,10 +709,14 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 
 static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
 				   const struct bpf_core_spec *spec,
-				   __u32 *val)
+				   __u32 *val, bool *validate)
 {
 	__s64 sz;
 
+	/* by default, always check expected value in bpf_insn */
+	if (validate)
+		*validate = true;
+
 	/* type-based relos return zero when target type is not found */
 	if (!spec) {
 		*val = 0;
@@ -694,20 +724,25 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
 	}
 
 	switch (relo->kind) {
-	case BPF_TYPE_ID_TARGET:
+	case BPF_CORE_TYPE_ID_TARGET:
 		*val = spec->root_type_id;
+		/* type ID, embedded in bpf_insn, might change during linking,
+		 * so enforcing it is pointless
+		 */
+		if (validate)
+			*validate = false;
 		break;
-	case BPF_TYPE_EXISTS:
+	case BPF_CORE_TYPE_EXISTS:
 		*val = 1;
 		break;
-	case BPF_TYPE_SIZE:
+	case BPF_CORE_TYPE_SIZE:
 		sz = btf__resolve_size(spec->btf, spec->root_type_id);
 		if (sz < 0)
 			return -EINVAL;
 		*val = sz;
 		break;
-	case BPF_TYPE_ID_LOCAL:
-	/* BPF_TYPE_ID_LOCAL is handled specially and shouldn't get here */
+	case BPF_CORE_TYPE_ID_LOCAL:
+	/* BPF_CORE_TYPE_ID_LOCAL is handled specially and shouldn't get here */
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -723,13 +758,13 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo,
 	const struct btf_enum *e;
 
 	switch (relo->kind) {
-	case BPF_ENUMVAL_EXISTS:
+	case BPF_CORE_ENUMVAL_EXISTS:
 		*val = spec ? 1 : 0;
 		break;
-	case BPF_ENUMVAL_VALUE:
+	case BPF_CORE_ENUMVAL_VALUE:
 		if (!spec)
 			return -EUCLEAN; /* request instruction poisoning */
-		t = btf__type_by_id(spec->btf, spec->spec[0].type_id);
+		t = btf_type_by_id(spec->btf, spec->spec[0].type_id);
 		e = btf_enum(t) + spec->spec[0].idx;
 		*val = e->val;
 		break;
@@ -805,8 +840,8 @@ static int bpf_core_calc_relo(const char *prog_name,
 		if (res->orig_sz != res->new_sz) {
 			const struct btf_type *orig_t, *new_t;
 
-			orig_t = btf__type_by_id(local_spec->btf, res->orig_type_id);
-			new_t = btf__type_by_id(targ_spec->btf, res->new_type_id);
+			orig_t = btf_type_by_id(local_spec->btf, res->orig_type_id);
+			new_t = btf_type_by_id(targ_spec->btf, res->new_type_id);
 
 			/* There are two use cases in which it's safe to
 			 * adjust load/store's mem size:
@@ -835,8 +870,8 @@ static int bpf_core_calc_relo(const char *prog_name,
 			res->fail_memsz_adjust = true;
 		}
 	} else if (core_relo_is_type_based(relo->kind)) {
-		err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val);
-		err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val);
+		err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val, &res->validate);
+		err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val, NULL);
 	} else if (core_relo_is_enumval_based(relo->kind)) {
 		err = bpf_core_calc_enumval_relo(relo, local_spec, &res->orig_val);
 		err = err ?: bpf_core_calc_enumval_relo(relo, targ_spec, &res->new_val);
@@ -1045,7 +1080,7 @@ static int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
  * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>,
  * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b
  */
-static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
+static void bpf_core_dump_spec(const char *prog_name, int level, const struct bpf_core_spec *spec)
 {
 	const struct btf_type *t;
 	const struct btf_enum *e;
@@ -1054,7 +1089,7 @@ static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
 	int i;
 
 	type_id = spec->root_type_id;
-	t = btf__type_by_id(spec->btf, type_id);
+	t = btf_type_by_id(spec->btf, type_id);
 	s = btf__name_by_offset(spec->btf, t->name_off);
 
 	libbpf_print(level, "[%u] %s %s", type_id, btf_kind_str(t), str_is_empty(s) ? "<anon>" : s);
@@ -1147,9 +1182,12 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 			     const struct bpf_core_relo *relo,
 			     int relo_idx,
 			     const struct btf *local_btf,
-			     struct bpf_core_cand_list *cands)
+			     struct bpf_core_cand_list *cands,
+			     struct bpf_core_spec *specs_scratch)
 {
-	struct bpf_core_spec local_spec, cand_spec, targ_spec = {};
+	struct bpf_core_spec *local_spec = &specs_scratch[0];
+	struct bpf_core_spec *cand_spec = &specs_scratch[1];
+	struct bpf_core_spec *targ_spec = &specs_scratch[2];
 	struct bpf_core_relo_res cand_res, targ_res;
 	const struct btf_type *local_type;
 	const char *local_name;
@@ -1158,10 +1196,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 	int i, j, err;
 
 	local_id = relo->type_id;
-	local_type = btf__type_by_id(local_btf, local_id);
-	if (!local_type)
-		return -EINVAL;
-
+	local_type = btf_type_by_id(local_btf, local_id);
 	local_name = btf__name_by_offset(local_btf, local_type->name_off);
 	if (!local_name)
 		return -EINVAL;
@@ -1170,7 +1205,8 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 	if (str_is_empty(spec_str))
 		return -EINVAL;
 
-	err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec);
+	err = bpf_core_parse_spec(prog_name, local_btf, local_id, spec_str,
+				  relo->kind, local_spec);
 	if (err) {
 		pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n",
 			prog_name, relo_idx, local_id, btf_kind_str(local_type),
@@ -1181,15 +1217,17 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 
 	pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog_name,
 		 relo_idx, core_relo_kind_str(relo->kind), relo->kind);
-	bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec);
+	bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, local_spec);
 	libbpf_print(LIBBPF_DEBUG, "\n");
 
 	/* TYPE_ID_LOCAL relo is special and doesn't need candidate search */
-	if (relo->kind == BPF_TYPE_ID_LOCAL) {
-		targ_res.validate = true;
+	if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) {
+		/* bpf_insn's imm value could get out of sync during linking */
+		memset(&targ_res, 0, sizeof(targ_res));
+		targ_res.validate = false;
 		targ_res.poison = false;
-		targ_res.orig_val = local_spec.root_type_id;
-		targ_res.new_val = local_spec.root_type_id;
+		targ_res.orig_val = local_spec->root_type_id;
+		targ_res.new_val = local_spec->root_type_id;
 		goto patch_insn;
 	}
 
@@ -1200,40 +1238,39 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 		return -EOPNOTSUPP;
 	}
 
-
 	for (i = 0, j = 0; i < cands->len; i++) {
-		err = bpf_core_spec_match(&local_spec, cands->cands[i].btf,
-					  cands->cands[i].id, &cand_spec);
+		err = bpf_core_spec_match(local_spec, cands->cands[i].btf,
+					  cands->cands[i].id, cand_spec);
 		if (err < 0) {
 			pr_warn("prog '%s': relo #%d: error matching candidate #%d ",
 				prog_name, relo_idx, i);
-			bpf_core_dump_spec(LIBBPF_WARN, &cand_spec);
+			bpf_core_dump_spec(prog_name, LIBBPF_WARN, cand_spec);
 			libbpf_print(LIBBPF_WARN, ": %d\n", err);
 			return err;
 		}
 
 		pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog_name,
 			 relo_idx, err == 0 ? "non-matching" : "matching", i);
-		bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec);
+		bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, cand_spec);
 		libbpf_print(LIBBPF_DEBUG, "\n");
 
 		if (err == 0)
 			continue;
 
-		err = bpf_core_calc_relo(prog_name, relo, relo_idx, &local_spec, &cand_spec, &cand_res);
+		err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, cand_spec, &cand_res);
 		if (err)
 			return err;
 
 		if (j == 0) {
 			targ_res = cand_res;
-			targ_spec = cand_spec;
-		} else if (cand_spec.bit_offset != targ_spec.bit_offset) {
+			*targ_spec = *cand_spec;
+		} else if (cand_spec->bit_offset != targ_spec->bit_offset) {
 			/* if there are many field relo candidates, they
 			 * should all resolve to the same bit offset
 			 */
 			pr_warn("prog '%s': relo #%d: field offset ambiguity: %u != %u\n",
-				prog_name, relo_idx, cand_spec.bit_offset,
-				targ_spec.bit_offset);
+				prog_name, relo_idx, cand_spec->bit_offset,
+				targ_spec->bit_offset);
 			return -EINVAL;
 		} else if (cand_res.poison != targ_res.poison || cand_res.new_val != targ_res.new_val) {
 			/* all candidates should result in the same relocation
@@ -1251,7 +1288,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 	}
 
 	/*
-	 * For BPF_FIELD_EXISTS relo or when used BPF program has field
+	 * For BPF_CORE_FIELD_EXISTS relo or when used BPF program has field
 	 * existence checks or kernel version/config checks, it's expected
 	 * that we might not find any candidates. In this case, if field
 	 * wasn't found in any candidate, the list of candidates shouldn't
@@ -1277,7 +1314,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 			 prog_name, relo_idx);
 
 		/* calculate single target relo result explicitly */
-		err = bpf_core_calc_relo(prog_name, relo, relo_idx, &local_spec, NULL, &targ_res);
+		err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, &targ_res);
 		if (err)
 			return err;
 	}

tools/lib/bpf/relo_core.h

@@ -4,81 +4,10 @@
 #ifndef __RELO_CORE_H
 #define __RELO_CORE_H
 
-/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
- * has to be adjusted by relocations.
- */
-enum bpf_core_relo_kind {
-	BPF_FIELD_BYTE_OFFSET = 0,	/* field byte offset */
-	BPF_FIELD_BYTE_SIZE = 1,	/* field size in bytes */
-	BPF_FIELD_EXISTS = 2,		/* field existence in target kernel */
-	BPF_FIELD_SIGNED = 3,		/* field signedness (0 - unsigned, 1 - signed) */
-	BPF_FIELD_LSHIFT_U64 = 4,	/* bitfield-specific left bitshift */
-	BPF_FIELD_RSHIFT_U64 = 5,	/* bitfield-specific right bitshift */
-	BPF_TYPE_ID_LOCAL = 6,		/* type ID in local BPF object */
-	BPF_TYPE_ID_TARGET = 7,		/* type ID in target kernel */
-	BPF_TYPE_EXISTS = 8,		/* type existence in target kernel */
-	BPF_TYPE_SIZE = 9,		/* type size in bytes */
-	BPF_ENUMVAL_EXISTS = 10,	/* enum value existence in target kernel */
-	BPF_ENUMVAL_VALUE = 11,		/* enum value integer value */
-};
-
-/* The minimum bpf_core_relo checked by the loader
- *
- * CO-RE relocation captures the following data:
- * - insn_off - instruction offset (in bytes) within a BPF program that needs
- *   its insn->imm field to be relocated with actual field info;
- * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
- *   type or field;
- * - access_str_off - offset into corresponding .BTF string section. String
- *   interpretation depends on specific relocation kind:
- *     - for field-based relocations, string encodes an accessed field using
- *     a sequence of field and array indices, separated by colon (:). It's
- *     conceptually very close to LLVM's getelementptr ([0]) instruction's
- *     arguments for identifying offset to a field.
- *     - for type-based relocations, strings is expected to be just "0";
- *     - for enum value-based relocations, string contains an index of enum
- *     value within its enum type;
- *
- * Example to provide a better feel.
- *
- *   struct sample {
- *       int a;
- *       struct {
- *           int b[10];
- *       };
- *   };
- *
- *   struct sample *s = ...;
- *   int x = &s->a;     // encoded as "0:0" (a is field #0)
- *   int y = &s->b[5];  // encoded as "0:1:0:5" (anon struct is field #1,
- *                      // b is field #0 inside anon struct, accessing elem #5)
- *   int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
- *
- * type_id for all relocs in this example  will capture BTF type id of
- * `struct sample`.
- *
- * Such relocation is emitted when using __builtin_preserve_access_index()
- * Clang built-in, passing expression that captures field address, e.g.:
- *
- * bpf_probe_read(&dst, sizeof(dst),
- *		  __builtin_preserve_access_index(&src->a.b.c));
- *
- * In this case Clang will emit field relocation recording necessary data to
- * be able to find offset of embedded `a.b.c` field within `src` struct.
- *
- *   [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
- */
-struct bpf_core_relo {
-	__u32   insn_off;
-	__u32   type_id;
-	__u32   access_str_off;
-	enum bpf_core_relo_kind kind;
-};
+#include <linux/bpf.h>
 
 struct bpf_core_cand {
 	const struct btf *btf;
-	const struct btf_type *t;
-	const char *name;
 	__u32 id;
 };
 
@@ -88,11 +17,39 @@ struct bpf_core_cand_list {
 	int len;
 };
 
+#define BPF_CORE_SPEC_MAX_LEN 64
+
+/* represents BPF CO-RE field or array element accessor */
+struct bpf_core_accessor {
+	__u32 type_id;		/* struct/union type or array element type */
+	__u32 idx;		/* field index or array index */
+	const char *name;	/* field name or NULL for array accessor */
+};
+
+struct bpf_core_spec {
+	const struct btf *btf;
+	/* high-level spec: named fields and array indices only */
+	struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN];
+	/* original unresolved (no skip_mods_or_typedefs) root type ID */
+	__u32 root_type_id;
+	/* CO-RE relocation kind */
+	enum bpf_core_relo_kind relo_kind;
+	/* high-level spec length */
+	int len;
+	/* raw, low-level spec: 1-to-1 with accessor spec string */
+	int raw_spec[BPF_CORE_SPEC_MAX_LEN];
+	/* raw spec length */
+	int raw_len;
+	/* field bit offset represented by spec */
+	__u32 bit_offset;
+};
+
 int bpf_core_apply_relo_insn(const char *prog_name,
 			     struct bpf_insn *insn, int insn_idx,
 			     const struct bpf_core_relo *relo, int relo_idx,
 			     const struct btf *local_btf,
-			     struct bpf_core_cand_list *cands);
+			     struct bpf_core_cand_list *cands,
+			     struct bpf_core_spec *specs_scratch);
 int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
 			      const struct btf *targ_btf, __u32 targ_id);
 

tools/lib/bpf/skel_internal.h

@@ -7,6 +7,16 @@
 #include <sys/syscall.h>
 #include <sys/mman.h>
 
+#ifndef __NR_bpf
+# if defined(__mips__) && defined(_ABIO32)
+#  define __NR_bpf 4355
+# elif defined(__mips__) && defined(_ABIN32)
+#  define __NR_bpf 6319
+# elif defined(__mips__) && defined(_ABI64)
+#  define __NR_bpf 5315
+# endif
+#endif
+
 /* This file is a base header for auto-generated *.lskel.h files.
  * Its contents will change and may become part of auto-generation in the future.
  *
@@ -65,8 +75,7 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 	int map_fd = -1, prog_fd = -1, key = 0, err;
 	union bpf_attr attr;
 
-	map_fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "__loader.map", 4,
-				     opts->data_sz, 1, 0);
+	map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1, NULL);
 	if (map_fd < 0) {
 		opts->errstr = "failed to create loader map";
 		err = -errno;

tools/lib/bpf/xsk.c

@@ -35,6 +35,11 @@
 #include "libbpf_internal.h"
 #include "xsk.h"
 
+/* entire xsk.h and xsk.c is going away in libbpf 1.0, so ignore all internal
+ * uses of deprecated APIs
+ */
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+
 #ifndef SOL_XDP
  #define SOL_XDP 283
 #endif
@@ -281,6 +286,7 @@ static int xsk_create_umem_rings(struct xsk_umem *umem, int fd,
 	return err;
 }
 
+DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4)
 int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 			    __u64 size, struct xsk_ring_prod *fill,
 			    struct xsk_ring_cons *comp,
@@ -299,7 +305,7 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 	if (!umem)
 		return -ENOMEM;
 
-	umem->fd = socket(AF_XDP, SOCK_RAW, 0);
+	umem->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0);
 	if (umem->fd < 0) {
 		err = -errno;
 		goto out_umem_alloc;
@@ -345,6 +351,7 @@ struct xsk_umem_config_v1 {
 	__u32 frame_headroom;
 };
 
+COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2)
 int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area,
 			    __u64 size, struct xsk_ring_prod *fill,
 			    struct xsk_ring_cons *comp,
@@ -358,14 +365,10 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area,
 	return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp,
 					&config);
 }
-COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2)
-DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4)
 
 static enum xsk_prog get_xsk_prog(void)
 {
 	enum xsk_prog detected = XSK_PROG_FALLBACK;
-	struct bpf_load_program_attr prog_attr;
-	struct bpf_create_map_attr map_attr;
 	__u32 size_out, retval, duration;
 	char data_in = 0, data_out;
 	struct bpf_insn insns[] = {
@@ -375,27 +378,15 @@ static enum xsk_prog get_xsk_prog(void)
 		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
 		BPF_EXIT_INSN(),
 	};
-	int prog_fd, map_fd, ret;
+	int prog_fd, map_fd, ret, insn_cnt = ARRAY_SIZE(insns);
 
-	memset(&map_attr, 0, sizeof(map_attr));
-	map_attr.map_type = BPF_MAP_TYPE_XSKMAP;
-	map_attr.key_size = sizeof(int);
-	map_attr.value_size = sizeof(int);
-	map_attr.max_entries = 1;
-
-	map_fd = bpf_create_map_xattr(&map_attr);
+	map_fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, NULL, sizeof(int), sizeof(int), 1, NULL);
 	if (map_fd < 0)
 		return detected;
 
 	insns[0].imm = map_fd;
 
-	memset(&prog_attr, 0, sizeof(prog_attr));
-	prog_attr.prog_type = BPF_PROG_TYPE_XDP;
-	prog_attr.insns = insns;
-	prog_attr.insns_cnt = ARRAY_SIZE(insns);
-	prog_attr.license = "GPL";
-
-	prog_fd = bpf_load_program_xattr(&prog_attr, NULL, 0);
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL);
 	if (prog_fd < 0) {
 		close(map_fd);
 		return detected;
@@ -495,10 +486,13 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 	};
 	struct bpf_insn *progs[] = {prog, prog_redirect_flags};
 	enum xsk_prog option = get_xsk_prog();
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.log_buf = log_buf,
+		.log_size = log_buf_size,
+	);
 
-	prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, progs[option], insns_cnt[option],
-				   "LGPL-2.1 or BSD-2-Clause", 0, log_buf,
-				   log_buf_size);
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "LGPL-2.1 or BSD-2-Clause",
+				progs[option], insns_cnt[option], &opts);
 	if (prog_fd < 0) {
 		pr_warn("BPF log buffer:\n%s", log_buf);
 		return prog_fd;
@@ -549,13 +543,12 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 	struct ifreq ifr = {};
 	int fd, err, ret;
 
-	fd = socket(AF_LOCAL, SOCK_DGRAM, 0);
+	fd = socket(AF_LOCAL, SOCK_DGRAM | SOCK_CLOEXEC, 0);
 	if (fd < 0)
 		return -errno;
 
 	ifr.ifr_data = (void *)&channels;
-	memcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ - 1);
-	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
+	libbpf_strlcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ);
 	err = ioctl(fd, SIOCETHTOOL, &ifr);
 	if (err && errno != EOPNOTSUPP) {
 		ret = -errno;
@@ -590,8 +583,8 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk)
 	if (max_queues < 0)
 		return max_queues;
 
-	fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map",
-				 sizeof(int), sizeof(int), max_queues, 0);
+	fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, "xsks_map",
+			    sizeof(int), sizeof(int), max_queues, NULL);
 	if (fd < 0)
 		return fd;
 
@@ -725,14 +718,12 @@ static int xsk_link_lookup(int ifindex, __u32 *prog_id, int *link_fd)
 
 static bool xsk_probe_bpf_link(void)
 {
-	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts,
-			    .flags = XDP_FLAGS_SKB_MODE);
-	struct bpf_load_program_attr prog_attr;
+	LIBBPF_OPTS(bpf_link_create_opts, opts, .flags = XDP_FLAGS_SKB_MODE);
 	struct bpf_insn insns[2] = {
 		BPF_MOV64_IMM(BPF_REG_0, XDP_PASS),
 		BPF_EXIT_INSN()
 	};
-	int prog_fd, link_fd = -1;
+	int prog_fd, link_fd = -1, insn_cnt = ARRAY_SIZE(insns);
 	int ifindex_lo = 1;
 	bool ret = false;
 	int err;
@@ -744,13 +735,7 @@ static bool xsk_probe_bpf_link(void)
 	if (link_fd >= 0)
 		return true;
 
-	memset(&prog_attr, 0, sizeof(prog_attr));
-	prog_attr.prog_type = BPF_PROG_TYPE_XDP;
-	prog_attr.insns = insns;
-	prog_attr.insns_cnt = ARRAY_SIZE(insns);
-	prog_attr.license = "GPL";
-
-	prog_fd = bpf_load_program_xattr(&prog_attr, NULL, 0);
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL);
 	if (prog_fd < 0)
 		return ret;
 
@@ -782,8 +767,7 @@ static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
 	}
 
 	ctx->ifindex = ifindex;
-	memcpy(ctx->ifname, ifname, IFNAMSIZ -1);
-	ctx->ifname[IFNAMSIZ - 1] = 0;
+	libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
 
 	xsk->ctx = ctx;
 	xsk->ctx->has_bpf_link = xsk_probe_bpf_link();
@@ -965,8 +949,7 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
 	ctx->refcount = 1;
 	ctx->umem = umem;
 	ctx->queue_id = queue_id;
-	memcpy(ctx->ifname, ifname, IFNAMSIZ - 1);
-	ctx->ifname[IFNAMSIZ - 1] = '\0';
+	libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
 
 	ctx->fill = fill;
 	ctx->comp = comp;
@@ -1046,7 +1029,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	}
 
 	if (umem->refcount++ > 0) {
-		xsk->fd = socket(AF_XDP, SOCK_RAW, 0);
+		xsk->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0);
 		if (xsk->fd < 0) {
 			err = -errno;
 			goto out_xsk_alloc;

tools/lib/bpf/xsk.h

@@ -23,6 +23,12 @@
 extern "C" {
 #endif
 
+/* This whole API has been deprecated and moved to libxdp that can be found at
+ * https://github.com/xdp-project/xdp-tools. The APIs are exactly the same so
+ * it should just be linking with libxdp instead of libbpf for this set of
+ * functionality. If not, please submit a bug report on the aforementioned page.
+ */
+
 /* Load-Acquire Store-Release barriers used by the XDP socket
  * library. The following macros should *NOT* be considered part of
  * the xsk.h API, and is subject to change anytime.
@@ -245,8 +251,10 @@ static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr)
 	return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr);
 }
 
-LIBBPF_API int xsk_umem__fd(const struct xsk_umem *umem);
-LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__fd(const struct xsk_umem *umem);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__fd(const struct xsk_socket *xsk);
 
 #define XSK_RING_CONS__DEFAULT_NUM_DESCS      2048
 #define XSK_RING_PROD__DEFAULT_NUM_DESCS      2048
@@ -263,10 +271,10 @@ struct xsk_umem_config {
 	__u32 flags;
 };
 
-LIBBPF_API int xsk_setup_xdp_prog(int ifindex,
-				  int *xsks_map_fd);
-LIBBPF_API int xsk_socket__update_xskmap(struct xsk_socket *xsk,
-					 int xsks_map_fd);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd);
 
 /* Flags for the libbpf_flags field. */
 #define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0)
@@ -280,40 +288,46 @@ struct xsk_socket_config {
 };
 
 /* Set config to NULL to get the default configuration. */
-LIBBPF_API int xsk_umem__create(struct xsk_umem **umem,
-				void *umem_area, __u64 size,
-				struct xsk_ring_prod *fill,
-				struct xsk_ring_cons *comp,
-				const struct xsk_umem_config *config);
-LIBBPF_API int xsk_umem__create_v0_0_2(struct xsk_umem **umem,
-				       void *umem_area, __u64 size,
-				       struct xsk_ring_prod *fill,
-				       struct xsk_ring_cons *comp,
-				       const struct xsk_umem_config *config);
-LIBBPF_API int xsk_umem__create_v0_0_4(struct xsk_umem **umem,
-				       void *umem_area, __u64 size,
-				       struct xsk_ring_prod *fill,
-				       struct xsk_ring_cons *comp,
-				       const struct xsk_umem_config *config);
-LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk,
-				  const char *ifname, __u32 queue_id,
-				  struct xsk_umem *umem,
-				  struct xsk_ring_cons *rx,
-				  struct xsk_ring_prod *tx,
-				  const struct xsk_socket_config *config);
-LIBBPF_API int
-xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
-			  const char *ifname,
-			  __u32 queue_id, struct xsk_umem *umem,
-			  struct xsk_ring_cons *rx,
-			  struct xsk_ring_prod *tx,
-			  struct xsk_ring_prod *fill,
-			  struct xsk_ring_cons *comp,
-			  const struct xsk_socket_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create(struct xsk_umem **umem,
+		     void *umem_area, __u64 size,
+		     struct xsk_ring_prod *fill,
+		     struct xsk_ring_cons *comp,
+		     const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create_v0_0_2(struct xsk_umem **umem,
+			    void *umem_area, __u64 size,
+			    struct xsk_ring_prod *fill,
+			    struct xsk_ring_cons *comp,
+			    const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create_v0_0_4(struct xsk_umem **umem,
+			    void *umem_area, __u64 size,
+			    struct xsk_ring_prod *fill,
+			    struct xsk_ring_cons *comp,
+			    const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__create(struct xsk_socket **xsk,
+		       const char *ifname, __u32 queue_id,
+		       struct xsk_umem *umem,
+		       struct xsk_ring_cons *rx,
+		       struct xsk_ring_prod *tx,
+		       const struct xsk_socket_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
+			      const char *ifname,
+			      __u32 queue_id, struct xsk_umem *umem,
+			      struct xsk_ring_cons *rx,
+			      struct xsk_ring_prod *tx,
+			      struct xsk_ring_prod *fill,
+			      struct xsk_ring_cons *comp,
+			      const struct xsk_socket_config *config);
 
 /* Returns 0 for success and -EBUSY if the umem is still in use. */
-LIBBPF_API int xsk_umem__delete(struct xsk_umem *umem);
-LIBBPF_API void xsk_socket__delete(struct xsk_socket *xsk);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__delete(struct xsk_umem *umem);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+void xsk_socket__delete(struct xsk_socket *xsk);
 
 #ifdef __cplusplus
 } /* extern "C" */

tools/lib/find_bit.c

@@ -96,6 +96,26 @@ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size)
 }
 #endif
 
+#ifndef find_first_and_bit
+/*
+ * Find the first set bit in two memory regions.
+ */
+unsigned long _find_first_and_bit(const unsigned long *addr1,
+				  const unsigned long *addr2,
+				  unsigned long size)
+{
+	unsigned long idx, val;
+
+	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+		val = addr1[idx] & addr2[idx];
+		if (val)
+			return min(idx * BITS_PER_LONG + __ffs(val), size);
+	}
+
+	return size;
+}
+#endif
+
 #ifndef find_first_zero_bit
 /*
  * Find the first cleared bit in a memory region.

tools/lib/perf/Documentation/libperf.txt

@@ -48,6 +48,7 @@ SYNOPSIS
   int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
   bool perf_cpu_map__empty(const struct perf_cpu_map *map);
   int perf_cpu_map__max(struct perf_cpu_map *map);
+  bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu);
 
   #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)
 --
@@ -135,16 +136,16 @@ SYNOPSIS
   int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
                        struct perf_thread_map *threads);
   void perf_evsel__close(struct perf_evsel *evsel);
-  void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
+  void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx);
   int perf_evsel__mmap(struct perf_evsel *evsel, int pages);
   void perf_evsel__munmap(struct perf_evsel *evsel);
-  void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);
-  int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+  void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread);
+  int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
                        struct perf_counts_values *count);
   int perf_evsel__enable(struct perf_evsel *evsel);
-  int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
+  int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
   int perf_evsel__disable(struct perf_evsel *evsel);
-  int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
+  int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
   struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
   struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
   struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);

tools/lib/perf/cpumap.c

@@ -10,15 +10,24 @@
 #include <ctype.h>
 #include <limits.h>
 
-struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
 {
-	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int));
+	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
 
 	if (cpus != NULL) {
-		cpus->nr = 1;
-		cpus->map[0] = -1;
+		cpus->nr = nr_cpus;
 		refcount_set(&cpus->refcnt, 1);
+
 	}
+	return cpus;
+}
+
+struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+{
+	struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);
+
+	if (cpus)
+		cpus->map[0].cpu = -1;
 
 	return cpus;
 }
@@ -54,15 +63,12 @@ static struct perf_cpu_map *cpu_map__default_new(void)
 	if (nr_cpus < 0)
 		return NULL;
 
-	cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int));
+	cpus = perf_cpu_map__alloc(nr_cpus);
 	if (cpus != NULL) {
 		int i;
 
 		for (i = 0; i < nr_cpus; ++i)
-			cpus->map[i] = i;
-
-		cpus->nr = nr_cpus;
-		refcount_set(&cpus->refcnt, 1);
+			cpus->map[i].cpu = i;
 	}
 
 	return cpus;
@@ -73,31 +79,32 @@ struct perf_cpu_map *perf_cpu_map__default_new(void)
 	return cpu_map__default_new();
 }
 
-static int cmp_int(const void *a, const void *b)
+
+static int cmp_cpu(const void *a, const void *b)
 {
-	return *(const int *)a - *(const int*)b;
+	const struct perf_cpu *cpu_a = a, *cpu_b = b;
+
+	return cpu_a->cpu - cpu_b->cpu;
 }
 
-static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
+static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus)
 {
-	size_t payload_size = nr_cpus * sizeof(int);
-	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size);
+	size_t payload_size = nr_cpus * sizeof(struct perf_cpu);
+	struct perf_cpu_map *cpus = perf_cpu_map__alloc(nr_cpus);
 	int i, j;
 
 	if (cpus != NULL) {
 		memcpy(cpus->map, tmp_cpus, payload_size);
-		qsort(cpus->map, nr_cpus, sizeof(int), cmp_int);
+		qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu);
 		/* Remove dups */
 		j = 0;
 		for (i = 0; i < nr_cpus; i++) {
-			if (i == 0 || cpus->map[i] != cpus->map[i - 1])
-				cpus->map[j++] = cpus->map[i];
+			if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu)
+				cpus->map[j++].cpu = cpus->map[i].cpu;
 		}
 		cpus->nr = j;
 		assert(j <= nr_cpus);
-		refcount_set(&cpus->refcnt, 1);
 	}
-
 	return cpus;
 }
 
@@ -105,7 +112,7 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
 {
 	struct perf_cpu_map *cpus = NULL;
 	int nr_cpus = 0;
-	int *tmp_cpus = NULL, *tmp;
+	struct perf_cpu *tmp_cpus = NULL, *tmp;
 	int max_entries = 0;
 	int n, cpu, prev;
 	char sep;
@@ -124,24 +131,24 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
 
 			if (new_max >= max_entries) {
 				max_entries = new_max + MAX_NR_CPUS / 2;
-				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+				tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
 				if (tmp == NULL)
 					goto out_free_tmp;
 				tmp_cpus = tmp;
 			}
 
 			while (++prev < cpu)
-				tmp_cpus[nr_cpus++] = prev;
+				tmp_cpus[nr_cpus++].cpu = prev;
 		}
 		if (nr_cpus == max_entries) {
 			max_entries += MAX_NR_CPUS;
-			tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+			tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
 			if (tmp == NULL)
 				goto out_free_tmp;
 			tmp_cpus = tmp;
 		}
 
-		tmp_cpus[nr_cpus++] = cpu;
+		tmp_cpus[nr_cpus++].cpu = cpu;
 		if (n == 2 && sep == '-')
 			prev = cpu;
 		else
@@ -179,7 +186,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 	unsigned long start_cpu, end_cpu = 0;
 	char *p = NULL;
 	int i, nr_cpus = 0;
-	int *tmp_cpus = NULL, *tmp;
+	struct perf_cpu *tmp_cpus = NULL, *tmp;
 	int max_entries = 0;
 
 	if (!cpu_list)
@@ -220,17 +227,17 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 		for (; start_cpu <= end_cpu; start_cpu++) {
 			/* check for duplicates */
 			for (i = 0; i < nr_cpus; i++)
-				if (tmp_cpus[i] == (int)start_cpu)
+				if (tmp_cpus[i].cpu == (int)start_cpu)
 					goto invalid;
 
 			if (nr_cpus == max_entries) {
 				max_entries += MAX_NR_CPUS;
-				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+				tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
 				if (tmp == NULL)
 					goto invalid;
 				tmp_cpus = tmp;
 			}
-			tmp_cpus[nr_cpus++] = (int)start_cpu;
+			tmp_cpus[nr_cpus++].cpu = (int)start_cpu;
 		}
 		if (*p)
 			++p;
@@ -250,12 +257,16 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 	return cpus;
 }
 
-int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
+struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
 {
+	struct perf_cpu result = {
+		.cpu = -1
+	};
+
 	if (cpus && idx < cpus->nr)
 		return cpus->map[idx];
 
-	return -1;
+	return result;
 }
 
 int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
@@ -265,25 +276,47 @@ int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
 
 bool perf_cpu_map__empty(const struct perf_cpu_map *map)
 {
-	return map ? map->map[0] == -1 : true;
+	return map ? map->map[0].cpu == -1 : true;
 }
 
-int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu)
+int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 {
-	int i;
+	int low, high;
 
-	for (i = 0; i < cpus->nr; ++i) {
-		if (cpus->map[i] == cpu)
-			return i;
+	if (!cpus)
+		return -1;
+
+	low = 0;
+	high = cpus->nr;
+	while (low < high) {
+		int idx = (low + high) / 2;
+		struct perf_cpu cpu_at_idx = cpus->map[idx];
+
+		if (cpu_at_idx.cpu == cpu.cpu)
+			return idx;
+
+		if (cpu_at_idx.cpu > cpu.cpu)
+			high = idx;
+		else
+			low = idx + 1;
 	}
 
 	return -1;
 }
 
-int perf_cpu_map__max(struct perf_cpu_map *map)
+bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 {
+	return perf_cpu_map__idx(cpus, cpu) != -1;
+}
+
+struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
+{
+	struct perf_cpu result = {
+		.cpu = -1
+	};
+
 	// cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well.
-	return map->nr > 0 ? map->map[map->nr - 1] : -1;
+	return map->nr > 0 ? map->map[map->nr - 1] : result;
 }
 
 /*
@@ -297,7 +330,7 @@ int perf_cpu_map__max(struct perf_cpu_map *map)
 struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 					 struct perf_cpu_map *other)
 {
-	int *tmp_cpus;
+	struct perf_cpu *tmp_cpus;
 	int tmp_len;
 	int i, j, k;
 	struct perf_cpu_map *merged;
@@ -311,19 +344,19 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 	if (!other)
 		return orig;
 	if (orig->nr == other->nr &&
-	    !memcmp(orig->map, other->map, orig->nr * sizeof(int)))
+	    !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu)))
 		return orig;
 
 	tmp_len = orig->nr + other->nr;
-	tmp_cpus = malloc(tmp_len * sizeof(int));
+	tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
 	if (!tmp_cpus)
 		return NULL;
 
 	/* Standard merge algorithm from wikipedia */
 	i = j = k = 0;
 	while (i < orig->nr && j < other->nr) {
-		if (orig->map[i] <= other->map[j]) {
-			if (orig->map[i] == other->map[j])
+		if (orig->map[i].cpu <= other->map[j].cpu) {
+			if (orig->map[i].cpu == other->map[j].cpu)
 				j++;
 			tmp_cpus[k++] = orig->map[i++];
 		} else

tools/lib/perf/evlist.c

@@ -407,7 +407,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *evlist, bool overwrite, int idx)
 
 static int
 perf_evlist__mmap_cb_mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
-			  int output, int cpu)
+			  int output, struct perf_cpu cpu)
 {
 	return perf_mmap__mmap(map, mp, output, cpu);
 }
@@ -426,7 +426,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	       int idx, struct perf_mmap_param *mp, int cpu_idx,
 	       int thread, int *_output, int *_output_overwrite)
 {
-	int evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
+	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
 	struct perf_evsel *evsel;
 	int revent;
 
@@ -643,14 +643,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map,
 	return overwrite ? evlist->mmap_ovw_first : evlist->mmap_first;
 }
 
-void __perf_evlist__set_leader(struct list_head *list)
+void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader)
 {
-	struct perf_evsel *evsel, *leader;
+	struct perf_evsel *first, *last, *evsel;
 
-	leader = list_entry(list->next, struct perf_evsel, node);
-	evsel = list_entry(list->prev, struct perf_evsel, node);
+	first = list_first_entry(list, struct perf_evsel, node);
+	last = list_last_entry(list, struct perf_evsel, node);
 
-	leader->nr_members = evsel->idx - leader->idx + 1;
+	leader->nr_members = last->idx - first->idx + 1;
 
 	__perf_evlist__for_each_entry(list, evsel)
 		evsel->leader = leader;
@@ -659,7 +659,10 @@ void __perf_evlist__set_leader(struct list_head *list)
 void perf_evlist__set_leader(struct perf_evlist *evlist)
 {
 	if (evlist->nr_entries) {
+		struct perf_evsel *first = list_entry(evlist->entries.next,
+						struct perf_evsel, node);
+
 		evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
-		__perf_evlist__set_leader(&evlist->entries);
+		__perf_evlist__set_leader(&evlist->entries, first);
 	}
 }

tools/lib/perf/evsel.c

@@ -43,18 +43,22 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y))
-#define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL)
+#define FD(_evsel, _cpu_map_idx, _thread)				\
+	((int *)xyarray__entry(_evsel->fd, _cpu_map_idx, _thread))
+#define MMAP(_evsel, _cpu_map_idx, _thread)				\
+	(_evsel->mmap ? ((struct perf_mmap *) xyarray__entry(_evsel->mmap, _cpu_map_idx, _thread)) \
+		      : NULL)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
 
 	if (evsel->fd) {
-		int cpu, thread;
-		for (cpu = 0; cpu < ncpus; cpu++) {
+		int idx, thread;
+
+		for (idx = 0; idx < ncpus; idx++) {
 			for (thread = 0; thread < nthreads; thread++) {
-				int *fd = FD(evsel, cpu, thread);
+				int *fd = FD(evsel, idx, thread);
 
 				if (fd)
 					*fd = -1;
@@ -74,13 +78,13 @@ static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthre
 
 static int
 sys_perf_event_open(struct perf_event_attr *attr,
-		    pid_t pid, int cpu, int group_fd,
+		    pid_t pid, struct perf_cpu cpu, int group_fd,
 		    unsigned long flags)
 {
-	return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+	return syscall(__NR_perf_event_open, attr, pid, cpu.cpu, group_fd, flags);
 }
 
-static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd)
+static int get_group_fd(struct perf_evsel *evsel, int cpu_map_idx, int thread, int *group_fd)
 {
 	struct perf_evsel *leader = evsel->leader;
 	int *fd;
@@ -97,7 +101,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
 	if (!leader->fd)
 		return -ENOTCONN;
 
-	fd = FD(leader, cpu, thread);
+	fd = FD(leader, cpu_map_idx, thread);
 	if (fd == NULL || *fd == -1)
 		return -EBADF;
 
@@ -109,7 +113,8 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
 int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 		     struct perf_thread_map *threads)
 {
-	int cpu, thread, err = 0;
+	struct perf_cpu cpu;
+	int idx, thread, err = 0;
 
 	if (cpus == NULL) {
 		static struct perf_cpu_map *empty_cpu_map;
@@ -136,24 +141,24 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 	}
 
 	if (evsel->fd == NULL &&
-	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+	    perf_evsel__alloc_fd(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
 		return -ENOMEM;
 
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
 		for (thread = 0; thread < threads->nr; thread++) {
 			int fd, group_fd, *evsel_fd;
 
-			evsel_fd = FD(evsel, cpu, thread);
+			evsel_fd = FD(evsel, idx, thread);
 			if (evsel_fd == NULL)
 				return -EINVAL;
 
-			err = get_group_fd(evsel, cpu, thread, &group_fd);
+			err = get_group_fd(evsel, idx, thread, &group_fd);
 			if (err < 0)
 				return err;
 
 			fd = sys_perf_event_open(&evsel->attr,
 						 threads->map[thread].pid,
-						 cpus->map[cpu], group_fd, 0);
+						 cpu, group_fd, 0);
 
 			if (fd < 0)
 				return -errno;
@@ -165,12 +170,12 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 	return err;
 }
 
-static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
+static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
 	int thread;
 
 	for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
-		int *fd = FD(evsel, cpu, thread);
+		int *fd = FD(evsel, cpu_map_idx, thread);
 
 		if (fd && *fd >= 0) {
 			close(*fd);
@@ -181,10 +186,8 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
 
 void perf_evsel__close_fd(struct perf_evsel *evsel)
 {
-	int cpu;
-
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++)
-		perf_evsel__close_fd_cpu(evsel, cpu);
+	for (int idx = 0; idx < xyarray__max_x(evsel->fd); idx++)
+		perf_evsel__close_fd_cpu(evsel, idx);
 }
 
 void perf_evsel__free_fd(struct perf_evsel *evsel)
@@ -202,29 +205,29 @@ void perf_evsel__close(struct perf_evsel *evsel)
 	perf_evsel__free_fd(evsel);
 }
 
-void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu)
+void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
 	if (evsel->fd == NULL)
 		return;
 
-	perf_evsel__close_fd_cpu(evsel, cpu);
+	perf_evsel__close_fd_cpu(evsel, cpu_map_idx);
 }
 
 void perf_evsel__munmap(struct perf_evsel *evsel)
 {
-	int cpu, thread;
+	int idx, thread;
 
 	if (evsel->fd == NULL || evsel->mmap == NULL)
 		return;
 
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+	for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int *fd = FD(evsel, cpu, thread);
+			int *fd = FD(evsel, idx, thread);
 
 			if (fd == NULL || *fd < 0)
 				continue;
 
-			perf_mmap__munmap(MMAP(evsel, cpu, thread));
+			perf_mmap__munmap(MMAP(evsel, idx, thread));
 		}
 	}
 
@@ -234,7 +237,7 @@ void perf_evsel__munmap(struct perf_evsel *evsel)
 
 int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 {
-	int ret, cpu, thread;
+	int ret, idx, thread;
 	struct perf_mmap_param mp = {
 		.prot = PROT_READ | PROT_WRITE,
 		.mask = (pages * page_size) - 1,
@@ -246,15 +249,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 	if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0)
 		return -ENOMEM;
 
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+	for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int *fd = FD(evsel, cpu, thread);
+			int *fd = FD(evsel, idx, thread);
 			struct perf_mmap *map;
+			struct perf_cpu cpu = perf_cpu_map__cpu(evsel->cpus, idx);
 
 			if (fd == NULL || *fd < 0)
 				continue;
 
-			map = MMAP(evsel, cpu, thread);
+			map = MMAP(evsel, idx, thread);
 			perf_mmap__init(map, NULL, false, NULL);
 
 			ret = perf_mmap__mmap(map, &mp, *fd, cpu);
@@ -268,14 +272,14 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 	return 0;
 }
 
-void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread)
+void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread)
 {
-	int *fd = FD(evsel, cpu, thread);
+	int *fd = FD(evsel, cpu_map_idx, thread);
 
-	if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL)
+	if (fd == NULL || *fd < 0 || MMAP(evsel, cpu_map_idx, thread) == NULL)
 		return NULL;
 
-	return MMAP(evsel, cpu, thread)->base;
+	return MMAP(evsel, cpu_map_idx, thread)->base;
 }
 
 int perf_evsel__read_size(struct perf_evsel *evsel)
@@ -303,19 +307,19 @@ int perf_evsel__read_size(struct perf_evsel *evsel)
 	return size;
 }
 
-int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
 		     struct perf_counts_values *count)
 {
 	size_t size = perf_evsel__read_size(evsel);
-	int *fd = FD(evsel, cpu, thread);
+	int *fd = FD(evsel, cpu_map_idx, thread);
 
 	memset(count, 0, sizeof(*count));
 
 	if (fd == NULL || *fd < 0)
 		return -EINVAL;
 
-	if (MMAP(evsel, cpu, thread) &&
-	    !perf_mmap__read_self(MMAP(evsel, cpu, thread), count))
+	if (MMAP(evsel, cpu_map_idx, thread) &&
+	    !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count))
 		return 0;
 
 	if (readn(*fd, count->values, size) <= 0)
@@ -326,13 +330,13 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 
 static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
 				 int ioc,  void *arg,
-				 int cpu)
+				 int cpu_map_idx)
 {
 	int thread;
 
 	for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
 		int err;
-		int *fd = FD(evsel, cpu, thread);
+		int *fd = FD(evsel, cpu_map_idx, thread);
 
 		if (fd == NULL || *fd < 0)
 			return -1;
@@ -346,9 +350,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
 	return 0;
 }
 
-int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu)
+int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
-	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu);
+	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu_map_idx);
 }
 
 int perf_evsel__enable(struct perf_evsel *evsel)
@@ -361,9 +365,9 @@ int perf_evsel__enable(struct perf_evsel *evsel)
 	return err;
 }
 
-int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu)
+int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
-	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu);
+	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu_map_idx);
 }
 
 int perf_evsel__disable(struct perf_evsel *evsel)
@@ -380,7 +384,7 @@ int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter)
 {
 	int err = 0, i;
 
-	for (i = 0; i < evsel->cpus->nr && !err; i++)
+	for (i = 0; i < perf_cpu_map__nr(evsel->cpus) && !err; i++)
 		err = perf_evsel__run_ioctl(evsel,
 				     PERF_EVENT_IOC_SET_FILTER,
 				     (void *)filter, i);
@@ -431,3 +435,22 @@ void perf_evsel__free_id(struct perf_evsel *evsel)
 	zfree(&evsel->id);
 	evsel->ids = 0;
 }
+
+void perf_counts_values__scale(struct perf_counts_values *count,
+			       bool scale, __s8 *pscaled)
+{
+	s8 scaled = 0;
+
+	if (scale) {
+		if (count->run == 0) {
+			scaled = -1;
+			count->val = 0;
+		} else if (count->run < count->ena) {
+			scaled = 1;
+			count->val = (u64)((double)count->val * count->ena / count->run);
+		}
+	}
+
+	if (pscaled)
+		*pscaled = scaled;
+}

tools/lib/perf/include/internal/cpumap.h

@@ -3,17 +3,27 @@
 #define __LIBPERF_INTERNAL_CPUMAP_H
 
 #include <linux/refcount.h>
+#include <perf/cpumap.h>
 
+/**
+ * A sized, reference counted, sorted array of integers representing CPU
+ * numbers. This is commonly used to capture which CPUs a PMU is associated
+ * with. The indices into the cpumap are frequently used as they avoid having
+ * gaps if CPU numbers were used. For events associated with a pid, rather than
+ * a CPU, a single dummy map with an entry of -1 is used.
+ */
 struct perf_cpu_map {
 	refcount_t	refcnt;
+	/** Length of the map array. */
 	int		nr;
-	int		map[];
+	/** The CPU values. */
+	struct perf_cpu	map[];
 };
 
 #ifndef MAX_NR_CPUS
 #define MAX_NR_CPUS	2048
 #endif
 
-int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu);
+int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu);
 
 #endif /* __LIBPERF_INTERNAL_CPUMAP_H */

tools/lib/perf/include/internal/evlist.h

@@ -4,6 +4,7 @@
 
 #include <linux/list.h>
 #include <api/fd/array.h>
+#include <internal/cpumap.h>
 #include <internal/evsel.h>
 
 #define PERF_EVLIST__HLIST_BITS 8
@@ -36,7 +37,7 @@ typedef void
 typedef struct perf_mmap*
 (*perf_evlist_mmap__cb_get_t)(struct perf_evlist*, bool, int);
 typedef int
-(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, int);
+(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, struct perf_cpu);
 
 struct perf_evlist_mmap_ops {
 	perf_evlist_mmap__cb_idx_t	idx;
@@ -127,5 +128,5 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 
 void perf_evlist__reset_id_hash(struct perf_evlist *evlist);
 
-void __perf_evlist__set_leader(struct list_head *list);
+void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader);
 #endif /* __LIBPERF_INTERNAL_EVLIST_H */

tools/lib/perf/include/internal/evsel.h

@@ -6,8 +6,8 @@
 #include <linux/perf_event.h>
 #include <stdbool.h>
 #include <sys/types.h>
+#include <internal/cpumap.h>
 
-struct perf_cpu_map;
 struct perf_thread_map;
 struct xyarray;
 
@@ -27,7 +27,7 @@ struct perf_sample_id {
 	* queue number.
 	*/
 	int			 idx;
-	int			 cpu;
+	struct perf_cpu		 cpu;
 	pid_t			 tid;
 
 	/* Holds total ID period value for PERF_SAMPLE_READ processing. */

tools/lib/perf/include/internal/mmap.h

@@ -6,6 +6,7 @@
 #include <linux/refcount.h>
 #include <linux/types.h>
 #include <stdbool.h>
+#include <internal/cpumap.h>
 
 /* perf sample has 16 bits size limit */
 #define PERF_SAMPLE_MAX_SIZE (1 << 16)
@@ -24,7 +25,7 @@ struct perf_mmap {
 	void			*base;
 	int			 mask;
 	int			 fd;
-	int			 cpu;
+	struct perf_cpu		 cpu;
 	refcount_t		 refcnt;
 	u64			 prev;
 	u64			 start;
@@ -46,7 +47,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map);
 void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
 		     bool overwrite, libperf_unmap_cb_t unmap_cb);
 int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
-		    int fd, int cpu);
+		    int fd, struct perf_cpu cpu);
 void perf_mmap__munmap(struct perf_mmap *map);
 void perf_mmap__get(struct perf_mmap *map);
 void perf_mmap__put(struct perf_mmap *map);

tools/lib/perf/include/perf/cpumap.h

@@ -3,10 +3,14 @@
 #define __LIBPERF_CPUMAP_H
 
 #include <perf/core.h>
+#include <perf/cpumap.h>
 #include <stdio.h>
 #include <stdbool.h>
 
-struct perf_cpu_map;
+/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
+struct perf_cpu {
+	int cpu;
+};
 
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
@@ -16,10 +20,11 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 						     struct perf_cpu_map *other);
 LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
-LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
+LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
-LIBPERF_API int perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
 
 #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)		\
 	for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx);	\

tools/lib/perf/include/perf/event.h

@@ -289,6 +289,11 @@ struct perf_record_itrace_start {
 	__u32			 tid;
 };
 
+struct perf_record_aux_output_hw_id {
+	struct perf_event_header header;
+	__u64			hw_id;
+};
+
 struct perf_record_thread_map_entry {
 	__u64			 pid;
 	char			 comm[16];
@@ -414,6 +419,7 @@ union perf_event {
 	struct perf_record_auxtrace_error	auxtrace_error;
 	struct perf_record_aux			aux;
 	struct perf_record_itrace_start		itrace_start;
+	struct perf_record_aux_output_hw_id	aux_output_hw_id;
 	struct perf_record_switch		context_switch;
 	struct perf_record_thread_map		thread_map;
 	struct perf_record_cpu_map		cpu_map;