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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-06-19

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) new SO_REUSEPORT_DETACH_BPF setsocktopt, from Martin.

2) BTF based map definition, from Andrii.

3) support bpf_map_lookup_elem for xskmap, from Jonathan.

4) bounded loops and scalar precision logic in the verifier, from Alexei.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

arch/alpha/include/uapi/asm/socket.h

@@ -122,6 +122,8 @@
 #define SO_RCVTIMEO_NEW         66
 #define SO_SNDTIMEO_NEW         67
 
+#define SO_DETACH_REUSEPORT_BPF 68
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

arch/mips/include/uapi/asm/socket.h

@@ -133,6 +133,8 @@
 #define SO_RCVTIMEO_NEW         66
 #define SO_SNDTIMEO_NEW         67
 
+#define SO_DETACH_REUSEPORT_BPF 68
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

arch/parisc/include/uapi/asm/socket.h

@@ -114,6 +114,8 @@
 #define SO_RCVTIMEO_NEW         0x4040
 #define SO_SNDTIMEO_NEW         0x4041
 
+#define SO_DETACH_REUSEPORT_BPF 0x4042
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

arch/sparc/include/uapi/asm/socket.h

@@ -115,6 +115,8 @@
 #define SO_RCVTIMEO_NEW          0x0044
 #define SO_SNDTIMEO_NEW          0x0045
 
+#define SO_DETACH_REUSEPORT_BPF  0x0047
+
 #if !defined(__KERNEL__)
 
 

include/linux/bpf.h

@@ -277,6 +277,7 @@ enum bpf_reg_type {
 	PTR_TO_TCP_SOCK,	 /* reg points to struct tcp_sock */
 	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
 	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
+	PTR_TO_XDP_SOCK,	 /* reg points to struct xdp_sock */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -1098,6 +1099,15 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
 				    struct bpf_insn *insn_buf,
 				    struct bpf_prog *prog,
 				    u32 *target_size);
+
+bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
+				  struct bpf_insn_access_aux *info);
+
+u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
+				    const struct bpf_insn *si,
+				    struct bpf_insn *insn_buf,
+				    struct bpf_prog *prog,
+				    u32 *target_size);
 #else
 static inline bool bpf_tcp_sock_is_valid_access(int off, int size,
 						enum bpf_access_type type,
@@ -1114,6 +1124,21 @@ static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
 {
 	return 0;
 }
+static inline bool bpf_xdp_sock_is_valid_access(int off, int size,
+						enum bpf_access_type type,
+						struct bpf_insn_access_aux *info)
+{
+	return false;
+}
+
+static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
+						  const struct bpf_insn *si,
+						  struct bpf_insn *insn_buf,
+						  struct bpf_prog *prog,
+						  u32 *target_size)
+{
+	return 0;
+}
 #endif /* CONFIG_INET */
 
 #endif /* _LINUX_BPF_H */

include/linux/bpf_verifier.h

@@ -136,6 +136,8 @@ struct bpf_reg_state {
 	 */
 	s32 subreg_def;
 	enum bpf_reg_liveness live;
+	/* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */
+	bool precise;
 };
 
 enum bpf_stack_slot_type {
@@ -187,14 +189,77 @@ struct bpf_func_state {
 	struct bpf_stack_state *stack;
 };
 
+struct bpf_idx_pair {
+	u32 prev_idx;
+	u32 idx;
+};
+
 #define MAX_CALL_FRAMES 8
 struct bpf_verifier_state {
 	/* call stack tracking */
 	struct bpf_func_state *frame[MAX_CALL_FRAMES];
+	struct bpf_verifier_state *parent;
+	/*
+	 * 'branches' field is the number of branches left to explore:
+	 * 0 - all possible paths from this state reached bpf_exit or
+	 * were safely pruned
+	 * 1 - at least one path is being explored.
+	 * This state hasn't reached bpf_exit
+	 * 2 - at least two paths are being explored.
+	 * This state is an immediate parent of two children.
+	 * One is fallthrough branch with branches==1 and another
+	 * state is pushed into stack (to be explored later) also with
+	 * branches==1. The parent of this state has branches==1.
+	 * The verifier state tree connected via 'parent' pointer looks like:
+	 * 1
+	 * 1
+	 * 2 -> 1 (first 'if' pushed into stack)
+	 * 1
+	 * 2 -> 1 (second 'if' pushed into stack)
+	 * 1
+	 * 1
+	 * 1 bpf_exit.
+	 *
+	 * Once do_check() reaches bpf_exit, it calls update_branch_counts()
+	 * and the verifier state tree will look:
+	 * 1
+	 * 1
+	 * 2 -> 1 (first 'if' pushed into stack)
+	 * 1
+	 * 1 -> 1 (second 'if' pushed into stack)
+	 * 0
+	 * 0
+	 * 0 bpf_exit.
+	 * After pop_stack() the do_check() will resume at second 'if'.
+	 *
+	 * If is_state_visited() sees a state with branches > 0 it means
+	 * there is a loop. If such state is exactly equal to the current state
+	 * it's an infinite loop. Note states_equal() checks for states
+	 * equvalency, so two states being 'states_equal' does not mean
+	 * infinite loop. The exact comparison is provided by
+	 * states_maybe_looping() function. It's a stronger pre-check and
+	 * much faster than states_equal().
+	 *
+	 * This algorithm may not find all possible infinite loops or
+	 * loop iteration count may be too high.
+	 * In such cases BPF_COMPLEXITY_LIMIT_INSNS limit kicks in.
+	 */
+	u32 branches;
 	u32 insn_idx;
 	u32 curframe;
 	u32 active_spin_lock;
 	bool speculative;
+
+	/* first and last insn idx of this verifier state */
+	u32 first_insn_idx;
+	u32 last_insn_idx;
+	/* jmp history recorded from first to last.
+	 * backtracking is using it to go from last to first.
+	 * For most states jmp_history_cnt is [0-3].
+	 * For loops can go up to ~40.
+	 */
+	struct bpf_idx_pair *jmp_history;
+	u32 jmp_history_cnt;
 };
 
 #define bpf_get_spilled_reg(slot, frame)				\
@@ -309,7 +374,9 @@ struct bpf_verifier_env {
 	} cfg;
 	u32 subprog_cnt;
 	/* number of instructions analyzed by the verifier */
-	u32 insn_processed;
+	u32 prev_insn_processed, insn_processed;
+	/* number of jmps, calls, exits analyzed so far */
+	u32 prev_jmps_processed, jmps_processed;
 	/* total verification time */
 	u64 verification_time;
 	/* maximum number of verifier states kept in 'branching' instructions */

include/net/sock_reuseport.h

@@ -35,6 +35,8 @@ extern struct sock *reuseport_select_sock(struct sock *sk,
 					  struct sk_buff *skb,
 					  int hdr_len);
 extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog);
+extern int reuseport_detach_prog(struct sock *sk);
+
 int reuseport_get_id(struct sock_reuseport *reuse);
 
 #endif  /* _SOCK_REUSEPORT_H */

include/net/xdp_sock.h

@@ -58,11 +58,11 @@ struct xdp_sock {
 	struct xdp_umem *umem;
 	struct list_head flush_node;
 	u16 queue_id;
-	struct xsk_queue *tx ____cacheline_aligned_in_smp;
-	struct list_head list;
 	bool zc;
 	/* Protects multiple processes in the control path */
 	struct mutex mutex;
+	struct xsk_queue *tx ____cacheline_aligned_in_smp;
+	struct list_head list;
 	/* Mutual exclusion of NAPI TX thread and sendmsg error paths
 	 * in the SKB destructor callback.
 	 */

include/uapi/asm-generic/socket.h

@@ -117,6 +117,8 @@
 #define SO_RCVTIMEO_NEW         66
 #define SO_SNDTIMEO_NEW         67
 
+#define SO_DETACH_REUSEPORT_BPF 68
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))

include/uapi/linux/bpf.h

@@ -3085,6 +3085,10 @@ struct bpf_sock_tuple {
 	};
 };
 
+struct bpf_xdp_sock {
+	__u32 queue_id;
+};
+
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
@@ -3245,6 +3249,7 @@ struct bpf_sock_addr {
 	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
 				 * Stored in network byte order.
 				 */
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
@@ -3296,6 +3301,7 @@ struct bpf_sock_ops {
 	__u32 sk_txhash;
 	__u64 bytes_received;
 	__u64 bytes_acked;
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */

kernel/bpf/Makefile

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-y := core.o
+CFLAGS_core.o += $(call cc-disable-warning, override-init)
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o

kernel/bpf/devmap.c

@@ -80,8 +80,8 @@ static u64 dev_map_bitmap_size(const union bpf_attr *attr)
 static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_dtab *dtab;
-	int err = -EINVAL;
 	u64 cost;
+	int err;
 
 	if (!capable(CAP_NET_ADMIN))
 		return ERR_PTR(-EPERM);

kernel/bpf/xskmap.c

@@ -17,8 +17,8 @@ struct xsk_map {
 
 static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 {
-	int cpu, err = -EINVAL;
 	struct xsk_map *m;
+	int cpu, err;
 	u64 cost;
 
 	if (!capable(CAP_NET_ADMIN))
@@ -151,6 +151,12 @@ void __xsk_map_flush(struct bpf_map *map)
 }
 
 static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return __xsk_map_lookup_elem(map, *(u32 *)key);
+}
+
+static void *xsk_map_lookup_elem_sys_only(struct bpf_map *map, void *key)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
@@ -218,6 +224,7 @@ const struct bpf_map_ops xsk_map_ops = {
 	.map_free = xsk_map_free,
 	.map_get_next_key = xsk_map_get_next_key,
 	.map_lookup_elem = xsk_map_lookup_elem,
+	.map_lookup_elem_sys_only = xsk_map_lookup_elem_sys_only,
 	.map_update_elem = xsk_map_update_elem,
 	.map_delete_elem = xsk_map_delete_elem,
 	.map_check_btf = map_check_no_btf,

net/core/filter.c

@@ -5695,6 +5695,46 @@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
 	return INET_ECN_set_ce(skb);
 }
 
+bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
+				  struct bpf_insn_access_aux *info)
+{
+	if (off < 0 || off >= offsetofend(struct bpf_xdp_sock, queue_id))
+		return false;
+
+	if (off % size != 0)
+		return false;
+
+	switch (off) {
+	default:
+		return size == sizeof(__u32);
+	}
+}
+
+u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
+				    const struct bpf_insn *si,
+				    struct bpf_insn *insn_buf,
+				    struct bpf_prog *prog, u32 *target_size)
+{
+	struct bpf_insn *insn = insn_buf;
+
+#define BPF_XDP_SOCK_GET(FIELD)						\
+	do {								\
+		BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_sock, FIELD) >	\
+			     FIELD_SIZEOF(struct bpf_xdp_sock, FIELD));	\
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\
+				      si->dst_reg, si->src_reg,		\
+				      offsetof(struct xdp_sock, FIELD)); \
+	} while (0)
+
+	switch (si->off) {
+	case offsetof(struct bpf_xdp_sock, queue_id):
+		BPF_XDP_SOCK_GET(queue_id);
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
 static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = {
 	.func           = bpf_skb_ecn_set_ce,
 	.gpl_only       = false,
@@ -5897,6 +5937,10 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skc_lookup_tcp:
 		return &bpf_sock_addr_skc_lookup_tcp_proto;
 #endif /* CONFIG_INET */
+	case BPF_FUNC_sk_storage_get:
+		return &bpf_sk_storage_get_proto;
+	case BPF_FUNC_sk_storage_delete:
+		return &bpf_sk_storage_delete_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -5934,6 +5978,10 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
+#ifdef CONFIG_SOCK_CGROUP_DATA
+	case BPF_FUNC_skb_cgroup_id:
+		return &bpf_skb_cgroup_id_proto;
+#endif
 #ifdef CONFIG_INET
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
@@ -6114,6 +6162,14 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_perf_event_output:
 		return &bpf_sockopt_event_output_proto;
+	case BPF_FUNC_sk_storage_get:
+		return &bpf_sk_storage_get_proto;
+	case BPF_FUNC_sk_storage_delete:
+		return &bpf_sk_storage_delete_proto;
+#ifdef CONFIG_INET
+	case BPF_FUNC_tcp_sock:
+		return &bpf_tcp_sock_proto;
+#endif /* CONFIG_INET */
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -6801,6 +6857,13 @@ static bool sock_addr_is_valid_access(int off, int size,
 		if (size != size_default)
 			return false;
 		break;
+	case offsetof(struct bpf_sock_addr, sk):
+		if (type != BPF_READ)
+			return false;
+		if (size != sizeof(__u64))
+			return false;
+		info->reg_type = PTR_TO_SOCKET;
+		break;
 	default:
 		if (type == BPF_READ) {
 			if (size != size_default)
@@ -6844,6 +6907,11 @@ static bool sock_ops_is_valid_access(int off, int size,
 			if (size != sizeof(__u64))
 				return false;
 			break;
+		case offsetof(struct bpf_sock_ops, sk):
+			if (size != sizeof(__u64))
+				return false;
+			info->reg_type = PTR_TO_SOCKET_OR_NULL;
+			break;
 		default:
 			if (size != size_default)
 				return false;
@@ -7751,6 +7819,11 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type,
 			struct bpf_sock_addr_kern, struct in6_addr, t_ctx,
 			s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg);
 		break;
+	case offsetof(struct bpf_sock_addr, sk):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_addr_kern, sk),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_addr_kern, sk));
+		break;
 	}
 
 	return insn - insn_buf;
@@ -8010,6 +8083,19 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 		SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash,
 					  struct sock, type);
 		break;
+	case offsetof(struct bpf_sock_ops, sk):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
+						struct bpf_sock_ops_kern,
+						is_fullsock),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern,
+					       is_fullsock));
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
+						struct bpf_sock_ops_kern, sk),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern, sk));
+		break;
 	}
 	return insn - insn_buf;
 }

net/core/sock.c

@@ -1039,6 +1039,10 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		}
 		break;
 
+	case SO_DETACH_REUSEPORT_BPF:
+		ret = reuseport_detach_prog(sk);
+		break;
+
 	case SO_DETACH_FILTER:
 		ret = sk_detach_filter(sk);
 		break;

net/core/sock_reuseport.c

@@ -332,3 +332,27 @@ int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
 	return 0;
 }
 EXPORT_SYMBOL(reuseport_attach_prog);
+
+int reuseport_detach_prog(struct sock *sk)
+{
+	struct sock_reuseport *reuse;
+	struct bpf_prog *old_prog;
+
+	if (!rcu_access_pointer(sk->sk_reuseport_cb))
+		return sk->sk_reuseport ? -ENOENT : -EINVAL;
+
+	old_prog = NULL;
+	spin_lock_bh(&reuseport_lock);
+	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+	rcu_swap_protected(reuse->prog, old_prog,
+			   lockdep_is_held(&reuseport_lock));
+	spin_unlock_bh(&reuseport_lock);
+
+	if (!old_prog)
+		return -ENOENT;
+
+	sk_reuseport_prog_free(old_prog);
+	return 0;
+}
+EXPORT_SYMBOL(reuseport_detach_prog);

samples/bpf/Makefile

@@ -170,21 +170,12 @@ always += ibumad_kern.o
 always += hbm_out_kern.o
 
 KBUILD_HOSTCFLAGS += -I$(objtree)/usr/include
-KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/
+KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/bpf/
 KBUILD_HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
 KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
 KBUILD_HOSTCFLAGS += -I$(srctree)/tools/perf
 
 HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
-HOSTCFLAGS_trace_helpers.o += -I$(srctree)/tools/lib/bpf/
-
-HOSTCFLAGS_trace_output_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_offwaketime_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_spintest_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_trace_event_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_sampleip_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_task_fd_query_user.o += -I$(srctree)/tools/lib/bpf/
-HOSTCFLAGS_xdp_sample_pkts_user.o += -I$(srctree)/tools/lib/bpf/
 
 KBUILD_HOSTLDLIBS		+= $(LIBBPF) -lelf
 HOSTLDLIBS_tracex4		+= -lrt
@@ -206,6 +197,17 @@ HOSTCC = $(CROSS_COMPILE)gcc
 CLANG_ARCH_ARGS = -target $(ARCH)
 endif
 
+# Don't evaluate probes and warnings if we need to run make recursively
+ifneq ($(src),)
+HDR_PROBE := $(shell echo "\#include <linux/types.h>\n struct list_head { int a; }; int main() { return 0; }" | \
+	$(HOSTCC) $(KBUILD_HOSTCFLAGS) -x c - -o /dev/null 2>/dev/null && \
+	echo okay)
+
+ifeq ($(HDR_PROBE),)
+$(warning WARNING: Detected possible issues with include path.)
+$(warning WARNING: Please install kernel headers locally (make headers_install).)
+endif
+
 BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
 BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
@@ -223,6 +225,7 @@ ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),)
 	DWARF2BTF = y
 endif
 endif
+endif
 
 # Trick to allow make to be run from this directory
 all:

samples/bpf/fds_example.c

@@ -14,7 +14,7 @@
 
 #include <bpf/bpf.h>
 
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 #include "bpf_insn.h"
 #include "sock_example.h"
 

samples/bpf/hbm.c

@@ -50,8 +50,8 @@
 #include "cgroup_helpers.h"
 #include "hbm.h"
 #include "bpf_util.h"
-#include "bpf/bpf.h"
+#include "bpf.h"
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 
 bool outFlag = true;
 int minRate = 1000;		/* cgroup rate limit in Mbps */
@@ -411,7 +411,7 @@ static void Usage(void)
 	       "    -l         also limit flows using loopback\n"
 	       "    -n <#>     to create cgroup \"/hbm#\" and attach prog\n"
 	       "               Default is /hbm1\n"
-	       "    --no_cn    disable CN notifcations\n"
+	       "    --no_cn    disable CN notifications\n"
 	       "    -r <rate>  Rate in Mbps\n"
 	       "    -s         Update HBM stats\n"
 	       "    -t <time>  Exit after specified seconds (default is 0)\n"

samples/bpf/ibumad_user.c

@@ -25,7 +25,7 @@
 
 #include "bpf_load.h"
 #include "bpf_util.h"
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 
 static void dump_counts(int fd)
 {

samples/bpf/sockex1_user.c

@@ -3,7 +3,7 @@
 #include <assert.h>
 #include <linux/bpf.h>
 #include <bpf/bpf.h>
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 #include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>

samples/bpf/sockex2_user.c

@@ -3,7 +3,7 @@
 #include <assert.h>
 #include <linux/bpf.h>
 #include <bpf/bpf.h>
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 #include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>

samples/bpf/xdp1_user.c

@@ -15,8 +15,8 @@
 #include <net/if.h>
 
 #include "bpf_util.h"
-#include "bpf/bpf.h"
+#include "bpf.h"
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 
 static int ifindex;
 static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;

samples/bpf/xdp_adjust_tail_user.c

@@ -18,8 +18,8 @@
 #include <netinet/ether.h>
 #include <unistd.h>
 #include <time.h>
-#include "bpf/bpf.h"
+#include "bpf.h"
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 
 #define STATS_INTERVAL_S 2U
 

samples/bpf/xdp_fwd_user.c

@@ -24,7 +24,7 @@
 #include <fcntl.h>
 #include <libgen.h>
 
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 #include <bpf/bpf.h>
 
 

samples/bpf/xdp_redirect_cpu_user.c

@@ -25,7 +25,7 @@ static const char *__doc__ =
 #define MAX_PROG 6
 
 #include <bpf/bpf.h>
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 
 #include "bpf_util.h"
 

samples/bpf/xdp_redirect_map_user.c

@@ -16,7 +16,7 @@
 
 #include "bpf_util.h"
 #include <bpf/bpf.h>
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 
 static int ifindex_in;
 static int ifindex_out;

samples/bpf/xdp_redirect_user.c

@@ -16,7 +16,7 @@
 
 #include "bpf_util.h"
 #include <bpf/bpf.h>
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 
 static int ifindex_in;
 static int ifindex_out;

samples/bpf/xdp_router_ipv4_user.c

@@ -21,7 +21,7 @@
 #include <sys/ioctl.h>
 #include <sys/syscall.h>
 #include "bpf_util.h"
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 #include <sys/resource.h>
 #include <libgen.h>
 

samples/bpf/xdp_rxq_info_user.c

@@ -22,8 +22,8 @@ static const char *__doc__ = " XDP RX-queue info extract example\n\n"
 #include <arpa/inet.h>
 #include <linux/if_link.h>
 
-#include "bpf/bpf.h"
+#include "bpf.h"
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 #include "bpf_util.h"
 
 static int ifindex = -1;

samples/bpf/xdp_tx_iptunnel_user.c

@@ -14,7 +14,7 @@
 #include <netinet/ether.h>
 #include <unistd.h>
 #include <time.h>
-#include "bpf/libbpf.h"
+#include "libbpf.h"
 #include <bpf/bpf.h>
 #include "bpf_util.h"
 #include "xdp_tx_iptunnel_common.h"

samples/bpf/xdpsock_user.c

@@ -27,8 +27,8 @@
 #include <time.h>
 #include <unistd.h>
 
-#include "bpf/libbpf.h"
+#include "libbpf.h"
-#include "bpf/xsk.h"
+#include "xsk.h"
 #include <bpf/bpf.h>
 
 #ifndef SOL_XDP

tools/bpf/bpftool/common.c

@@ -21,6 +21,7 @@
 #include <sys/vfs.h>
 
 #include <bpf.h>
+#include <libbpf.h> /* libbpf_num_possible_cpus */
 
 #include "main.h"
 
@@ -439,57 +440,13 @@ unsigned int get_page_size(void)
 
 unsigned int get_possible_cpus(void)
 {
-	static unsigned int result;
+	int cpus = libbpf_num_possible_cpus();
-	char buf[128];
-	long int n;
-	char *ptr;
-	int fd;
 
-	if (result)
+	if (cpus < 0) {
-		return result;
+		p_err("Can't get # of possible cpus: %s", strerror(-cpus));
-
-	fd = open("/sys/devices/system/cpu/possible", O_RDONLY);
-	if (fd < 0) {
-		p_err("can't open sysfs possible cpus");
 		exit(-1);
 	}
-
+	return cpus;
-	n = read(fd, buf, sizeof(buf));
-	if (n < 2) {
-		p_err("can't read sysfs possible cpus");
-		exit(-1);
-	}
-	close(fd);
-
-	if (n == sizeof(buf)) {
-		p_err("read sysfs possible cpus overflow");
-		exit(-1);
-	}
-
-	ptr = buf;
-	n = 0;
-	while (*ptr && *ptr != '\n') {
-		unsigned int a, b;
-
-		if (sscanf(ptr, "%u-%u", &a, &b) == 2) {
-			n += b - a + 1;
-
-			ptr = strchr(ptr, '-') + 1;
-		} else if (sscanf(ptr, "%u", &a) == 1) {
-			n++;
-		} else {
-			assert(0);
-		}
-
-		while (isdigit(*ptr))
-			ptr++;
-		if (*ptr == ',')
-			ptr++;
-	}
-
-	result = n;
-
-	return result;
 }
 
 static char *

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

@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_SOCKET_H
+#define __ASM_GENERIC_SOCKET_H
+
+#include <linux/posix_types.h>
+#include <asm/sockios.h>
+
+/* For setsockopt(2) */
+#define SOL_SOCKET	1
+
+#define SO_DEBUG	1
+#define SO_REUSEADDR	2
+#define SO_TYPE		3
+#define SO_ERROR	4
+#define SO_DONTROUTE	5
+#define SO_BROADCAST	6
+#define SO_SNDBUF	7
+#define SO_RCVBUF	8
+#define SO_SNDBUFFORCE	32
+#define SO_RCVBUFFORCE	33
+#define SO_KEEPALIVE	9
+#define SO_OOBINLINE	10
+#define SO_NO_CHECK	11
+#define SO_PRIORITY	12
+#define SO_LINGER	13
+#define SO_BSDCOMPAT	14
+#define SO_REUSEPORT	15
+#ifndef SO_PASSCRED /* powerpc only differs in these */
+#define SO_PASSCRED	16
+#define SO_PEERCRED	17
+#define SO_RCVLOWAT	18
+#define SO_SNDLOWAT	19
+#define SO_RCVTIMEO_OLD	20
+#define SO_SNDTIMEO_OLD	21
+#endif
+
+/* Security levels - as per NRL IPv6 - don't actually do anything */
+#define SO_SECURITY_AUTHENTICATION		22
+#define SO_SECURITY_ENCRYPTION_TRANSPORT	23
+#define SO_SECURITY_ENCRYPTION_NETWORK		24
+
+#define SO_BINDTODEVICE	25
+
+/* Socket filtering */
+#define SO_ATTACH_FILTER	26
+#define SO_DETACH_FILTER	27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
+
+#define SO_PEERNAME		28
+
+#define SO_ACCEPTCONN		30
+
+#define SO_PEERSEC		31
+#define SO_PASSSEC		34
+
+#define SO_MARK			36
+
+#define SO_PROTOCOL		38
+#define SO_DOMAIN		39
+
+#define SO_RXQ_OVFL             40
+
+#define SO_WIFI_STATUS		41
+#define SCM_WIFI_STATUS	SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
+
+/* Instruct lower device to use last 4-bytes of skb data as FCS */
+#define SO_NOFCS		43
+
+#define SO_LOCK_FILTER		44
+
+#define SO_SELECT_ERR_QUEUE	45
+
+#define SO_BUSY_POLL		46
+
+#define SO_MAX_PACING_RATE	47
+
+#define SO_BPF_EXTENSIONS	48
+
+#define SO_INCOMING_CPU		49
+
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
+#define SO_ATTACH_REUSEPORT_CBPF	51
+#define SO_ATTACH_REUSEPORT_EBPF	52
+
+#define SO_CNX_ADVICE		53
+
+#define SCM_TIMESTAMPING_OPT_STATS	54
+
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
+#define SCM_TIMESTAMPING_PKTINFO	58
+
+#define SO_PEERGROUPS		59
+
+#define SO_ZEROCOPY		60
+
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
+#define SO_BINDTOIFINDEX	62
+
+#define SO_TIMESTAMP_OLD        29
+#define SO_TIMESTAMPNS_OLD      35
+#define SO_TIMESTAMPING_OLD     37
+
+#define SO_TIMESTAMP_NEW        63
+#define SO_TIMESTAMPNS_NEW      64
+#define SO_TIMESTAMPING_NEW     65
+
+#define SO_RCVTIMEO_NEW         66
+#define SO_SNDTIMEO_NEW         67
+
+#define SO_DETACH_REUSEPORT_BPF 68
+
+#if !defined(__KERNEL__)
+
+#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
+/* on 64-bit and x32, avoid the ?: operator */
+#define SO_TIMESTAMP		SO_TIMESTAMP_OLD
+#define SO_TIMESTAMPNS		SO_TIMESTAMPNS_OLD
+#define SO_TIMESTAMPING		SO_TIMESTAMPING_OLD
+
+#define SO_RCVTIMEO		SO_RCVTIMEO_OLD
+#define SO_SNDTIMEO		SO_SNDTIMEO_OLD
+#else
+#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW)
+#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW)
+#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW)
+
+#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW)
+#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW)
+#endif
+
+#define SCM_TIMESTAMP           SO_TIMESTAMP
+#define SCM_TIMESTAMPNS         SO_TIMESTAMPNS
+#define SCM_TIMESTAMPING        SO_TIMESTAMPING
+
+#endif
+
+#endif /* __ASM_GENERIC_SOCKET_H */

tools/include/uapi/linux/bpf.h

@@ -3085,6 +3085,10 @@ struct bpf_sock_tuple {
 	};
 };
 
+struct bpf_xdp_sock {
+	__u32 queue_id;
+};
+
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
@@ -3245,6 +3249,7 @@ struct bpf_sock_addr {
 	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
 				 * Stored in network byte order.
 				 */
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
@@ -3296,6 +3301,7 @@ struct bpf_sock_ops {
 	__u32 sk_txhash;
 	__u64 bytes_received;
 	__u64 bytes_acked;
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */

tools/lib/bpf/bpf.c

@@ -26,10 +26,11 @@
 #include <memory.h>
 #include <unistd.h>
 #include <asm/unistd.h>
+#include <errno.h>
 #include <linux/bpf.h>
 #include "bpf.h"
 #include "libbpf.h"
-#include <errno.h>
+#include "libbpf_internal.h"
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -53,10 +54,6 @@
 # endif
 #endif
 
-#ifndef min
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#endif
-
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;

tools/lib/bpf/bpf_prog_linfo.c

@@ -6,10 +6,7 @@
 #include <linux/err.h>
 #include <linux/bpf.h>
 #include "libbpf.h"
-
+#include "libbpf_internal.h"
-#ifndef min
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#endif
 
 struct bpf_prog_linfo {
 	void *raw_linfo;

tools/lib/bpf/btf.c

@@ -16,9 +16,6 @@
 #include "libbpf_internal.h"
 #include "hashmap.h"
 
-#define max(a, b) ((a) > (b) ? (a) : (b))
-#define min(a, b) ((a) < (b) ? (a) : (b))
-
 #define BTF_MAX_NR_TYPES 0x7fffffff
 #define BTF_MAX_STR_OFFSET 0x7fffffff
 

tools/lib/bpf/btf.h

@@ -17,6 +17,7 @@ extern "C" {
 
 #define BTF_ELF_SEC ".BTF"
 #define BTF_EXT_ELF_SEC ".BTF.ext"
+#define MAPS_ELF_SEC ".maps"
 
 struct btf;
 struct btf_ext;

tools/lib/bpf/btf_dump.c

@@ -18,9 +18,6 @@
 #include "libbpf.h"
 #include "libbpf_internal.h"
 
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#define max(x, y) ((x) < (y) ? (y) : (x))
-
 static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t";
 static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1;
 

tools/lib/bpf/libbpf.h

@@ -98,15 +98,16 @@ struct bpf_object_load_attr {
 LIBBPF_API int bpf_object__load(struct bpf_object *obj);
 LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr);
 LIBBPF_API int bpf_object__unload(struct bpf_object *obj);
-LIBBPF_API const char *bpf_object__name(struct bpf_object *obj);
+LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
-LIBBPF_API unsigned int bpf_object__kversion(struct bpf_object *obj);
+LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj);
 
 struct btf;
-LIBBPF_API struct btf *bpf_object__btf(struct bpf_object *obj);
+LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj);
 LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
 
 LIBBPF_API struct bpf_program *
-bpf_object__find_program_by_title(struct bpf_object *obj, const char *title);
+bpf_object__find_program_by_title(const struct bpf_object *obj,
+				  const char *title);
 
 LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\
@@ -118,7 +119,7 @@ LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev);
 typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *);
 LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv,
 				    bpf_object_clear_priv_t clear_priv);
-LIBBPF_API void *bpf_object__priv(struct bpf_object *prog);
+LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog);
 
 LIBBPF_API int
 libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
@@ -129,7 +130,7 @@ LIBBPF_API int libbpf_attach_type_by_name(const char *name,
 /* Accessors of bpf_program */
 struct bpf_program;
 LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
-						 struct bpf_object *obj);
+						 const struct bpf_object *obj);
 
 #define bpf_object__for_each_program(pos, obj)		\
 	for ((pos) = bpf_program__next(NULL, (obj));	\
@@ -137,24 +138,23 @@ LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
 	     (pos) = bpf_program__next((pos), (obj)))
 
 LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog,
-						 struct bpf_object *obj);
+						 const struct bpf_object *obj);
 
-typedef void (*bpf_program_clear_priv_t)(struct bpf_program *,
+typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *);
-					 void *);
 
 LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv,
 				     bpf_program_clear_priv_t clear_priv);
 
-LIBBPF_API void *bpf_program__priv(struct bpf_program *prog);
+LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog);
 LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog,
 					 __u32 ifindex);
 
-LIBBPF_API const char *bpf_program__title(struct bpf_program *prog,
+LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog,
 					  bool needs_copy);
 
 LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license,
 				 __u32 kern_version);
-LIBBPF_API int bpf_program__fd(struct bpf_program *prog);
+LIBBPF_API int bpf_program__fd(const struct bpf_program *prog);
 LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog,
 					 const char *path,
 					 int instance);
@@ -227,7 +227,7 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n,
 LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
 				     bpf_program_prep_t prep);
 
-LIBBPF_API int bpf_program__nth_fd(struct bpf_program *prog, int n);
+LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n);
 
 /*
  * Adjust type of BPF program. Default is kprobe.
@@ -246,14 +246,14 @@ LIBBPF_API void
 bpf_program__set_expected_attach_type(struct bpf_program *prog,
 				      enum bpf_attach_type type);
 
-LIBBPF_API bool bpf_program__is_socket_filter(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_tracepoint(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_raw_tracepoint(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_kprobe(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_sched_cls(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_sched_act(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_xdp(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
-LIBBPF_API bool bpf_program__is_perf_event(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog);
 
 /*
  * No need for __attribute__((packed)), all members of 'bpf_map_def'
@@ -275,10 +275,10 @@ struct bpf_map_def {
  */
 struct bpf_map;
 LIBBPF_API struct bpf_map *
-bpf_object__find_map_by_name(struct bpf_object *obj, const char *name);
+bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name);
 
 LIBBPF_API int
-bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name);
+bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name);
 
 /*
  * Get bpf_map through the offset of corresponding struct bpf_map_def
@@ -288,7 +288,7 @@ LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
 
 LIBBPF_API struct bpf_map *
-bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
+bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj);
 #define bpf_object__for_each_map(pos, obj)		\
 	for ((pos) = bpf_map__next(NULL, (obj));	\
 	     (pos) != NULL;				\
@@ -296,22 +296,22 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
 #define bpf_map__for_each bpf_object__for_each_map
 
 LIBBPF_API struct bpf_map *
-bpf_map__prev(struct bpf_map *map, struct bpf_object *obj);
+bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj);
 
-LIBBPF_API int bpf_map__fd(struct bpf_map *map);
+LIBBPF_API int bpf_map__fd(const struct bpf_map *map);
-LIBBPF_API const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
+LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map);
-LIBBPF_API const char *bpf_map__name(struct bpf_map *map);
+LIBBPF_API const char *bpf_map__name(const struct bpf_map *map);
 LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map);
 LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
 
 typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
 				 bpf_map_clear_priv_t clear_priv);
-LIBBPF_API void *bpf_map__priv(struct bpf_map *map);
+LIBBPF_API void *bpf_map__priv(const struct bpf_map *map);
 LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
 LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries);
-LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map);
+LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
-LIBBPF_API bool bpf_map__is_internal(struct bpf_map *map);
+LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
 LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
 LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
@@ -454,6 +454,22 @@ bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear);
 LIBBPF_API void
 bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
 
+/*
+ * A helper function to get the number of possible CPUs before looking up
+ * per-CPU maps. Negative errno is returned on failure.
+ *
+ * Example usage:
+ *
+ *     int ncpus = libbpf_num_possible_cpus();
+ *     if (ncpus < 0) {
+ *          // error handling
+ *     }
+ *     long values[ncpus];
+ *     bpf_map_lookup_elem(per_cpu_map_fd, key, values);
+ *
+ */
+LIBBPF_API int libbpf_num_possible_cpus(void);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif

tools/lib/bpf/libbpf.map

@@ -172,4 +172,5 @@ LIBBPF_0.0.4 {
 		btf_dump__new;
 		btf__parse_elf;
 		bpf_object__load_xattr;
+		libbpf_num_possible_cpus;
 } LIBBPF_0.0.3;

tools/lib/bpf/libbpf_internal.h

@@ -23,6 +23,13 @@
 #define BTF_PARAM_ENC(name, type) (name), (type)
 #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size)
 
+#ifndef min
+# define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
+#ifndef max
+# define max(x, y) ((x) < (y) ? (y) : (x))
+#endif
+
 extern void libbpf_print(enum libbpf_print_level level,
 			 const char *format, ...)
 	__attribute__((format(printf, 2, 3)));

tools/lib/bpf/xsk.c

@@ -60,10 +60,8 @@ struct xsk_socket {
 	struct xsk_umem *umem;
 	struct xsk_socket_config config;
 	int fd;
-	int xsks_map;
 	int ifindex;
 	int prog_fd;
-	int qidconf_map_fd;
 	int xsks_map_fd;
 	__u32 queue_id;
 	char ifname[IFNAMSIZ];
@@ -265,15 +263,11 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 	/* This is the C-program:
 	 * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
 	 * {
-	 *     int *qidconf, index = ctx->rx_queue_index;
+	 *     int index = ctx->rx_queue_index;
 	 *
 	 *     // A set entry here means that the correspnding queue_id
 	 *     // has an active AF_XDP socket bound to it.
-	 *     qidconf = bpf_map_lookup_elem(&qidconf_map, &index);
+	 *     if (bpf_map_lookup_elem(&xsks_map, &index))
-	 *     if (!qidconf)
-	 *         return XDP_ABORTED;
-	 *
-	 *     if (*qidconf)
 	 *         return bpf_redirect_map(&xsks_map, index, 0);
 	 *
 	 *     return XDP_PASS;
@@ -286,15 +280,10 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_1, -4),
 		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
 		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-		BPF_LD_MAP_FD(BPF_REG_1, xsk->qidconf_map_fd),
+		BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd),
 		BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 		BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-		BPF_MOV32_IMM(BPF_REG_0, 0),
-		/* if r1 == 0 goto +8 */
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 8),
 		BPF_MOV32_IMM(BPF_REG_0, 2),
-		/* r1 = *(u32 *)(r1 + 0) */
-		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 0),
 		/* if r1 == 0 goto +5 */
 		BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5),
 		/* r2 = *(u32 *)(r10 - 4) */
@@ -366,18 +355,11 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk)
 	if (max_queues < 0)
 		return max_queues;
 
-	fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "qidconf_map",
+	fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map",
 				 sizeof(int), sizeof(int), max_queues, 0);
 	if (fd < 0)
 		return fd;
-	xsk->qidconf_map_fd = fd;
 
-	fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map",
-				 sizeof(int), sizeof(int), max_queues, 0);
-	if (fd < 0) {
-		close(xsk->qidconf_map_fd);
-		return fd;
-	}
 	xsk->xsks_map_fd = fd;
 
 	return 0;
@@ -385,10 +367,8 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk)
 
 static void xsk_delete_bpf_maps(struct xsk_socket *xsk)
 {
-	close(xsk->qidconf_map_fd);
+	bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id);
 	close(xsk->xsks_map_fd);
-	xsk->qidconf_map_fd = -1;
-	xsk->xsks_map_fd = -1;
 }
 
 static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
@@ -417,10 +397,9 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
 	if (err)
 		goto out_map_ids;
 
-	for (i = 0; i < prog_info.nr_map_ids; i++) {
+	xsk->xsks_map_fd = -1;
-		if (xsk->qidconf_map_fd != -1 && xsk->xsks_map_fd != -1)
-			break;
 
+	for (i = 0; i < prog_info.nr_map_ids; i++) {
 		fd = bpf_map_get_fd_by_id(map_ids[i]);
 		if (fd < 0)
 			continue;
@@ -431,11 +410,6 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
 			continue;
 		}
 
-		if (!strcmp(map_info.name, "qidconf_map")) {
-			xsk->qidconf_map_fd = fd;
-			continue;
-		}
-
 		if (!strcmp(map_info.name, "xsks_map")) {
 			xsk->xsks_map_fd = fd;
 			continue;
@@ -445,40 +419,18 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
 	}
 
 	err = 0;
-	if (xsk->qidconf_map_fd < 0 || xsk->xsks_map_fd < 0) {
+	if (xsk->xsks_map_fd == -1)
 		err = -ENOENT;
-		xsk_delete_bpf_maps(xsk);
-	}
 
 out_map_ids:
 	free(map_ids);
 	return err;
 }
 
-static void xsk_clear_bpf_maps(struct xsk_socket *xsk)
-{
-	int qid = false;
-
-	bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0);
-	bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id);
-}
-
 static int xsk_set_bpf_maps(struct xsk_socket *xsk)
 {
-	int qid = true, fd = xsk->fd, err;
+	return bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id,
-
+				   &xsk->fd, 0);
-	err = bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0);
-	if (err)
-		goto out;
-
-	err = bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, &fd, 0);
-	if (err)
-		goto out;
-
-	return 0;
-out:
-	xsk_clear_bpf_maps(xsk);
-	return err;
 }
 
 static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
@@ -497,26 +449,27 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
 			return err;
 
 		err = xsk_load_xdp_prog(xsk);
-		if (err)
+		if (err) {
-			goto out_maps;
+			xsk_delete_bpf_maps(xsk);
+			return err;
+		}
 	} else {
 		xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id);
 		err = xsk_lookup_bpf_maps(xsk);
-		if (err)
+		if (err) {
-			goto out_load;
+			close(xsk->prog_fd);
+			return err;
+		}
 	}
 
 	err = xsk_set_bpf_maps(xsk);
-	if (err)
+	if (err) {
-		goto out_load;
+		xsk_delete_bpf_maps(xsk);
+		close(xsk->prog_fd);
+		return err;
+	}
 
 	return 0;
-
-out_load:
-	close(xsk->prog_fd);
-out_maps:
-	xsk_delete_bpf_maps(xsk);
-	return err;
 }
 
 int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
@@ -643,9 +596,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 		goto out_mmap_tx;
 	}
 
-	xsk->qidconf_map_fd = -1;
+	xsk->prog_fd = -1;
-	xsk->xsks_map_fd = -1;
-
 	if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
 		err = xsk_setup_xdp_prog(xsk);
 		if (err)
@@ -708,8 +659,10 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 	if (!xsk)
 		return;
 
-	xsk_clear_bpf_maps(xsk);
+	if (xsk->prog_fd != -1) {
 		xsk_delete_bpf_maps(xsk);
+		close(xsk->prog_fd);
+	}
 
 	optlen = sizeof(off);
 	err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);

tools/testing/selftests/bpf/Makefile

@@ -280,4 +280,5 @@ $(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES)
 		 ) > $(VERIFIER_TESTS_H))
 
 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(ALU32_BUILD_DIR) \
-	$(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H)
+	$(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H) \
+	feature

tools/testing/selftests/bpf/bpf_endian.h

@@ -2,6 +2,7 @@
 #ifndef __BPF_ENDIAN__
 #define __BPF_ENDIAN__
 
+#include <linux/stddef.h>
 #include <linux/swab.h>
 
 /* LLVM's BPF target selects the endianness of the CPU

tools/testing/selftests/bpf/bpf_helpers.h

@@ -31,7 +31,7 @@ static int (*bpf_map_pop_elem)(void *map, void *value) =
 	(void *) BPF_FUNC_map_pop_elem;
 static int (*bpf_map_peek_elem)(void *map, void *value) =
 	(void *) BPF_FUNC_map_peek_elem;
-static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) =
+static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
 	(void *) BPF_FUNC_probe_read;
 static unsigned long long (*bpf_ktime_get_ns)(void) =
 	(void *) BPF_FUNC_ktime_get_ns;
@@ -62,7 +62,7 @@ static int (*bpf_perf_event_output)(void *ctx, void *map,
 	(void *) BPF_FUNC_perf_event_output;
 static int (*bpf_get_stackid)(void *ctx, void *map, int flags) =
 	(void *) BPF_FUNC_get_stackid;
-static int (*bpf_probe_write_user)(void *dst, void *src, int size) =
+static int (*bpf_probe_write_user)(void *dst, const void *src, int size) =
 	(void *) BPF_FUNC_probe_write_user;
 static int (*bpf_current_task_under_cgroup)(void *map, int index) =
 	(void *) BPF_FUNC_current_task_under_cgroup;

tools/testing/selftests/bpf/bpf_util.h

@@ -6,44 +6,17 @@
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
+#include <libbpf.h> /* libbpf_num_possible_cpus */
 
 static inline unsigned int bpf_num_possible_cpus(void)
 {
-	static const char *fcpu = "/sys/devices/system/cpu/possible";
+	int possible_cpus = libbpf_num_possible_cpus();
-	unsigned int start, end, possible_cpus = 0;
-	char buff[128];
-	FILE *fp;
-	int len, n, i, j = 0;
 
-	fp = fopen(fcpu, "r");
+	if (possible_cpus < 0) {
-	if (!fp) {
+		printf("Failed to get # of possible cpus: '%s'!\n",
-		printf("Failed to open %s: '%s'!\n", fcpu, strerror(errno));
+		       strerror(-possible_cpus));
 		exit(1);
 	}
-
-	if (!fgets(buff, sizeof(buff), fp)) {
-		printf("Failed to read %s!\n", fcpu);
-		exit(1);
-	}
-
-	len = strlen(buff);
-	for (i = 0; i <= len; i++) {
-		if (buff[i] == ',' || buff[i] == '\0') {
-			buff[i] = '\0';
-			n = sscanf(&buff[j], "%u-%u", &start, &end);
-			if (n <= 0) {
-				printf("Failed to retrieve # possible CPUs!\n");
-				exit(1);
-			} else if (n == 1) {
-				end = start;
-			}
-			possible_cpus += end - start + 1;
-			j = i + 1;
-		}
-	}
-
-	fclose(fp);
-
 	return possible_cpus;
 }
 

tools/testing/selftests/bpf/cgroup_helpers.c

@@ -47,7 +47,7 @@ int enable_all_controllers(char *cgroup_path)
 	char buf[PATH_MAX];
 	char *c, *c2;
 	int fd, cfd;
-	size_t len;
+	ssize_t len;
 
 	snprintf(path, sizeof(path), "%s/cgroup.controllers", cgroup_path);
 	fd = open(path, O_RDONLY);

tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c

@@ -5,7 +5,7 @@ static int libbpf_debug_print(enum libbpf_print_level level,
 			      const char *format, va_list args)
 {
 	if (level != LIBBPF_DEBUG)
-		return 0;
+		return vfprintf(stderr, format, args);
 
 	if (!strstr(format, "verifier log"))
 		return 0;
@@ -32,24 +32,69 @@ static int check_load(const char *file, enum bpf_prog_type type)
 
 void test_bpf_verif_scale(void)
 {
-	const char *scale[] = {
+	const char *sched_cls[] = {
-		"./test_verif_scale1.o", "./test_verif_scale2.o", "./test_verif_scale3.o"
+		"./test_verif_scale1.o", "./test_verif_scale2.o", "./test_verif_scale3.o",
 	};
-	const char *pyperf[] = {
+	const char *raw_tp[] = {
-		"./pyperf50.o",	"./pyperf100.o", "./pyperf180.o"
+		/* full unroll by llvm */
+		"./pyperf50.o",	"./pyperf100.o", "./pyperf180.o",
+
+		/* partial unroll. llvm will unroll loop ~150 times.
+		 * C loop count -> 600.
+		 * Asm loop count -> 4.
+		 * 16k insns in loop body.
+		 * Total of 5 such loops. Total program size ~82k insns.
+		 */
+		"./pyperf600.o",
+
+		/* no unroll at all.
+		 * C loop count -> 600.
+		 * ASM loop count -> 600.
+		 * ~110 insns in loop body.
+		 * Total of 5 such loops. Total program size ~1500 insns.
+		 */
+		"./pyperf600_nounroll.o",
+
+		"./loop1.o", "./loop2.o",
+
+		/* partial unroll. 19k insn in a loop.
+		 * Total program size 20.8k insn.
+		 * ~350k processed_insns
+		 */
+		"./strobemeta.o",
+
+		/* no unroll, tiny loops */
+		"./strobemeta_nounroll1.o",
+		"./strobemeta_nounroll2.o",
+	};
+	const char *cg_sysctl[] = {
+		"./test_sysctl_loop1.o", "./test_sysctl_loop2.o",
 	};
 	int err, i;
 
 	if (verifier_stats)
 		libbpf_set_print(libbpf_debug_print);
 
-	for (i = 0; i < ARRAY_SIZE(scale); i++) {
+	err = check_load("./loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT);
-		err = check_load(scale[i], BPF_PROG_TYPE_SCHED_CLS);
+	printf("test_scale:loop3:%s\n", err ? (error_cnt--, "OK") : "FAIL");
-		printf("test_scale:%s:%s\n", scale[i], err ? "FAIL" : "OK");
+
+	for (i = 0; i < ARRAY_SIZE(sched_cls); i++) {
+		err = check_load(sched_cls[i], BPF_PROG_TYPE_SCHED_CLS);
+		printf("test_scale:%s:%s\n", sched_cls[i], err ? "FAIL" : "OK");
 	}
 
-	for (i = 0; i < ARRAY_SIZE(pyperf); i++) {
+	for (i = 0; i < ARRAY_SIZE(raw_tp); i++) {
-		err = check_load(pyperf[i], BPF_PROG_TYPE_RAW_TRACEPOINT);
+		err = check_load(raw_tp[i], BPF_PROG_TYPE_RAW_TRACEPOINT);
-		printf("test_scale:%s:%s\n", pyperf[i], err ? "FAIL" : "OK");
+		printf("test_scale:%s:%s\n", raw_tp[i], err ? "FAIL" : "OK");
 	}
+
+	for (i = 0; i < ARRAY_SIZE(cg_sysctl); i++) {
+		err = check_load(cg_sysctl[i], BPF_PROG_TYPE_CGROUP_SYSCTL);
+		printf("test_scale:%s:%s\n", cg_sysctl[i], err ? "FAIL" : "OK");
+	}
+	err = check_load("./test_xdp_loop.o", BPF_PROG_TYPE_XDP);
+	printf("test_scale:test_xdp_loop:%s\n", err ? "FAIL" : "OK");
+
+	err = check_load("./test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL);
+	printf("test_scale:test_seg6_loop:%s\n", err ? "FAIL" : "OK");
 }

tools/testing/selftests/bpf/progs/bpf_flow.c

@@ -57,17 +57,25 @@ struct frag_hdr {
 	__be32 identification;
 };
 
-struct bpf_map_def SEC("maps") jmp_table = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 key_size;
+	__u32 value_size;
+} jmp_table SEC(".maps") = {
 	.type = BPF_MAP_TYPE_PROG_ARRAY,
+	.max_entries = 8,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(__u32),
-	.max_entries = 8
 };
 
-struct bpf_map_def SEC("maps") last_dissection = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct bpf_flow_keys *value;
+} last_dissection SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct bpf_flow_keys),
 	.max_entries = 1,
 };
 

tools/testing/selftests/bpf/progs/loop1.c

@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <stdint.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("raw_tracepoint/kfree_skb")
+int nested_loops(volatile struct pt_regs* ctx)
+{
+	int i, j, sum = 0, m;
+
+	for (j = 0; j < 300; j++)
+		for (i = 0; i < j; i++) {
+			if (j & 1)
+				m = ctx->rax;
+			else
+				m = j;
+			sum += i * m;
+		}
+
+	return sum;
+}

tools/testing/selftests/bpf/progs/loop2.c

@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <stdint.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("raw_tracepoint/consume_skb")
+int while_true(volatile struct pt_regs* ctx)
+{
+	int i = 0;
+
+	while (true) {
+		if (ctx->rax & 1)
+			i += 3;
+		else
+			i += 7;
+		if (i > 40)
+			break;
+	}
+
+	return i;
+}

tools/testing/selftests/bpf/progs/loop3.c

@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <stdint.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("raw_tracepoint/consume_skb")
+int while_true(volatile struct pt_regs* ctx)
+{
+	__u64 i = 0, sum = 0;
+	do {
+		i++;
+		sum += ctx->rax;
+	} while (i < 0x100000000ULL);
+	return sum;
+}

tools/testing/selftests/bpf/progs/netcnt_prog.c

@@ -10,24 +10,22 @@
 #define REFRESH_TIME_NS	100000000
 #define NS_PER_SEC	1000000000
 
-struct bpf_map_def SEC("maps") percpu_netcnt = {
+struct {
+	__u32 type;
+	struct bpf_cgroup_storage_key *key;
+	struct percpu_net_cnt *value;
+} percpu_netcnt SEC(".maps") = {
 	.type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
-	.key_size = sizeof(struct bpf_cgroup_storage_key),
-	.value_size = sizeof(struct percpu_net_cnt),
 };
 
-BPF_ANNOTATE_KV_PAIR(percpu_netcnt, struct bpf_cgroup_storage_key,
+struct {
-		     struct percpu_net_cnt);
+	__u32 type;
-
+	struct bpf_cgroup_storage_key *key;
-struct bpf_map_def SEC("maps") netcnt = {
+	struct net_cnt *value;
+} netcnt SEC(".maps") = {
 	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
-	.key_size = sizeof(struct bpf_cgroup_storage_key),
-	.value_size = sizeof(struct net_cnt),
 };
 
-BPF_ANNOTATE_KV_PAIR(netcnt, struct bpf_cgroup_storage_key,
-		     struct net_cnt);
-
 SEC("cgroup/skb")
 int bpf_nextcnt(struct __sk_buff *skb)
 {

tools/testing/selftests/bpf/progs/pyperf.h

@@ -220,7 +220,11 @@ static inline __attribute__((__always_inline__)) int __on_event(struct pt_regs *
 		int32_t* symbol_counter = bpf_map_lookup_elem(&symbolmap, &sym);
 		if (symbol_counter == NULL)
 			return 0;
-#pragma unroll
+#ifdef NO_UNROLL
+#pragma clang loop unroll(disable)
+#else
+#pragma clang loop unroll(full)
+#endif
 		/* Unwind python stack */
 		for (int i = 0; i < STACK_MAX_LEN; ++i) {
 			if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) {

tools/testing/selftests/bpf/progs/pyperf600.c

@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#define STACK_MAX_LEN 600
+/* clang will not unroll the loop 600 times.
+ * Instead it will unroll it to the amount it deemed
+ * appropriate, but the loop will still execute 600 times.
+ * Total program size is around 90k insns
+ */
+#include "pyperf.h"

tools/testing/selftests/bpf/progs/pyperf600_nounroll.c

@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#define STACK_MAX_LEN 600
+#define NO_UNROLL
+/* clang will not unroll at all.
+ * Total program size is around 2k insns
+ */
+#include "pyperf.h"

tools/testing/selftests/bpf/progs/socket_cookie_prog.c

@@ -7,25 +7,36 @@
 #include "bpf_helpers.h"
 #include "bpf_endian.h"
 
-struct bpf_map_def SEC("maps") socket_cookies = {
+struct socket_cookie {
-	.type = BPF_MAP_TYPE_HASH,
+	__u64 cookie_key;
-	.key_size = sizeof(__u64),
+	__u32 cookie_value;
-	.value_size = sizeof(__u32),
+};
-	.max_entries = 1 << 8,
+
+struct {
+	__u32 type;
+	__u32 map_flags;
+	int *key;
+	struct socket_cookie *value;
+} socket_cookies SEC(".maps") = {
+	.type = BPF_MAP_TYPE_SK_STORAGE,
+	.map_flags = BPF_F_NO_PREALLOC,
 };
 
 SEC("cgroup/connect6")
 int set_cookie(struct bpf_sock_addr *ctx)
 {
-	__u32 cookie_value = 0xFF;
+	struct socket_cookie *p;
-	__u64 cookie_key;
 
 	if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6)
 		return 1;
 
-	cookie_key = bpf_get_socket_cookie(ctx);
+	p = bpf_sk_storage_get(&socket_cookies, ctx->sk, 0,
-	if (bpf_map_update_elem(&socket_cookies, &cookie_key, &cookie_value, 0))
+			       BPF_SK_STORAGE_GET_F_CREATE);
-		return 0;
+	if (!p)
+		return 1;
+
+	p->cookie_value = 0xFF;
+	p->cookie_key = bpf_get_socket_cookie(ctx);
 
 	return 1;
 }
@@ -33,9 +44,8 @@ int set_cookie(struct bpf_sock_addr *ctx)
 SEC("sockops")
 int update_cookie(struct bpf_sock_ops *ctx)
 {
-	__u32 new_cookie_value;
+	struct bpf_sock *sk;
-	__u32 *cookie_value;
+	struct socket_cookie *p;
-	__u64 cookie_key;
 
 	if (ctx->family != AF_INET6)
 		return 1;
@@ -43,14 +53,17 @@ int update_cookie(struct bpf_sock_ops *ctx)
 	if (ctx->op != BPF_SOCK_OPS_TCP_CONNECT_CB)
 		return 1;
 
-	cookie_key = bpf_get_socket_cookie(ctx);
+	if (!ctx->sk)
-
-	cookie_value = bpf_map_lookup_elem(&socket_cookies, &cookie_key);
-	if (!cookie_value)
 		return 1;
 
-	new_cookie_value = (ctx->local_port << 8) | *cookie_value;
+	p = bpf_sk_storage_get(&socket_cookies, ctx->sk, 0, 0);
-	bpf_map_update_elem(&socket_cookies, &cookie_key, &new_cookie_value, 0);
+	if (!p)
+		return 1;
+
+	if (p->cookie_key != bpf_get_socket_cookie(ctx))
+		return 1;
+
+	p->cookie_value = (ctx->local_port << 8) | p->cookie_value;
 
 	return 1;
 }

tools/testing/selftests/bpf/progs/sockmap_parse_prog.c

@@ -1,6 +1,5 @@
 #include <linux/bpf.h>
 #include "bpf_helpers.h"
-#include "bpf_util.h"
 #include "bpf_endian.h"
 
 int _version SEC("version") = 1;

tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c

@@ -1,6 +1,6 @@
 #include <linux/bpf.h>
+
 #include "bpf_helpers.h"
-#include "bpf_util.h"
 #include "bpf_endian.h"
 
 int _version SEC("version") = 1;

tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c

@@ -1,6 +1,5 @@
 #include <linux/bpf.h>
 #include "bpf_helpers.h"
-#include "bpf_util.h"
 #include "bpf_endian.h"
 
 int _version SEC("version") = 1;

tools/testing/selftests/bpf/progs/strobemeta.c

@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+// Copyright (c) 2019 Facebook
+
+#define STROBE_MAX_INTS 2
+#define STROBE_MAX_STRS 25
+#define STROBE_MAX_MAPS 100
+#define STROBE_MAX_MAP_ENTRIES 20
+/* full unroll by llvm #undef NO_UNROLL */
+#include "strobemeta.h"
+

tools/testing/selftests/bpf/progs/strobemeta.h

@@ -0,0 +1,528 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <stdint.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include "bpf_helpers.h"
+
+typedef uint32_t pid_t;
+struct task_struct {};
+
+#define TASK_COMM_LEN 16
+#define PERF_MAX_STACK_DEPTH 127
+
+#define STROBE_TYPE_INVALID 0
+#define STROBE_TYPE_INT 1
+#define STROBE_TYPE_STR 2
+#define STROBE_TYPE_MAP 3
+
+#define STACK_TABLE_EPOCH_SHIFT 20
+#define STROBE_MAX_STR_LEN 1
+#define STROBE_MAX_CFGS 32
+#define STROBE_MAX_PAYLOAD						\
+	(STROBE_MAX_STRS * STROBE_MAX_STR_LEN +				\
+	STROBE_MAX_MAPS * (1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN)
+
+struct strobe_value_header {
+	/*
+	 * meaning depends on type:
+	 * 1. int: 0, if value not set, 1 otherwise
+	 * 2. str: 1 always, whether value is set or not is determined by ptr
+	 * 3. map: 1 always, pointer points to additional struct with number
+	 *    of entries (up to STROBE_MAX_MAP_ENTRIES)
+	 */
+	uint16_t len;
+	/*
+	 * _reserved might be used for some future fields/flags, but we always
+	 * want to keep strobe_value_header to be 8 bytes, so BPF can read 16
+	 * bytes in one go and get both header and value
+	 */
+	uint8_t _reserved[6];
+};
+
+/*
+ * strobe_value_generic is used from BPF probe only, but needs to be a union
+ * of strobe_value_int/strobe_value_str/strobe_value_map
+ */
+struct strobe_value_generic {
+	struct strobe_value_header header;
+	union {
+		int64_t val;
+		void *ptr;
+	};
+};
+
+struct strobe_value_int {
+	struct strobe_value_header header;
+	int64_t value;
+};
+
+struct strobe_value_str {
+	struct strobe_value_header header;
+	const char* value;
+};
+
+struct strobe_value_map {
+	struct strobe_value_header header;
+	const struct strobe_map_raw* value;
+};
+
+struct strobe_map_entry {
+	const char* key;
+	const char* val;
+};
+
+/*
+ * Map of C-string key/value pairs with fixed maximum capacity. Each map has
+ * corresponding int64 ID, which application can use (or ignore) in whatever
+ * way appropriate. Map is "write-only", there is no way to get data out of
+ * map. Map is intended to be used to provide metadata for profilers and is
+ * not to be used for internal in-app communication. All methods are
+ * thread-safe.
+ */
+struct strobe_map_raw {
+	/*
+	 * general purpose unique ID that's up to application to decide
+	 * whether and how to use; for request metadata use case id is unique
+	 * request ID that's used to match metadata with stack traces on
+	 * Strobelight backend side
+	 */
+	int64_t id;
+	/* number of used entries in map */
+	int64_t cnt;
+	/*
+	 * having volatile doesn't change anything on BPF side, but clang
+	 * emits warnings for passing `volatile const char *` into
+	 * bpf_probe_read_str that expects just `const char *`
+	 */
+	const char* tag;
+	/*
+	 * key/value entries, each consisting of 2 pointers to key and value
+	 * C strings
+	 */
+	struct strobe_map_entry entries[STROBE_MAX_MAP_ENTRIES];
+};
+
+/* Following values define supported values of TLS mode */
+#define TLS_NOT_SET -1
+#define TLS_LOCAL_EXEC 0
+#define TLS_IMM_EXEC 1
+#define TLS_GENERAL_DYN 2
+
+/*
+ * structure that universally represents TLS location (both for static
+ * executables and shared libraries)
+ */
+struct strobe_value_loc {
+	/*
+	 * tls_mode defines what TLS mode was used for particular metavariable:
+	 * - -1 (TLS_NOT_SET) - no metavariable;
+	 * - 0 (TLS_LOCAL_EXEC) - Local Executable mode;
+	 * - 1 (TLS_IMM_EXEC) - Immediate Executable mode;
+	 * - 2 (TLS_GENERAL_DYN) - General Dynamic mode;
+	 * Local Dynamic mode is not yet supported, because never seen in
+	 * practice.  Mode defines how offset field is interpreted. See
+	 * calc_location() in below for details.
+	 */
+	int64_t tls_mode;
+	/*
+	 * TLS_LOCAL_EXEC: offset from thread pointer (fs:0 for x86-64,
+	 * tpidr_el0 for aarch64).
+	 * TLS_IMM_EXEC: absolute address of GOT entry containing offset
+	 * from thread pointer;
+	 * TLS_GENERAL_DYN: absolute addres of double GOT entry
+	 * containing tls_index_t struct;
+	 */
+	int64_t offset;
+};
+
+struct strobemeta_cfg {
+	int64_t req_meta_idx;
+	struct strobe_value_loc int_locs[STROBE_MAX_INTS];
+	struct strobe_value_loc str_locs[STROBE_MAX_STRS];
+	struct strobe_value_loc map_locs[STROBE_MAX_MAPS];
+};
+
+struct strobe_map_descr {
+	uint64_t id;
+	int16_t tag_len;
+	/*
+	 * cnt <0 - map value isn't set;
+	 * 0 - map has id set, but no key/value entries
+	 */
+	int16_t cnt;
+	/*
+	 * both key_lens[i] and val_lens[i] should be >0 for present key/value
+	 * entry
+	 */
+	uint16_t key_lens[STROBE_MAX_MAP_ENTRIES];
+	uint16_t val_lens[STROBE_MAX_MAP_ENTRIES];
+};
+
+struct strobemeta_payload {
+	/* req_id has valid request ID, if req_meta_valid == 1 */
+	int64_t req_id;
+	uint8_t req_meta_valid;
+	/*
+	 * mask has Nth bit set to 1, if Nth metavar was present and
+	 * successfully read
+	 */
+	uint64_t int_vals_set_mask;
+	int64_t int_vals[STROBE_MAX_INTS];
+	/* len is >0 for present values */
+	uint16_t str_lens[STROBE_MAX_STRS];
+	/* if map_descrs[i].cnt == -1, metavar is not present/set */
+	struct strobe_map_descr map_descrs[STROBE_MAX_MAPS];
+	/*
+	 * payload has compactly packed values of str and map variables in the
+	 * form: strval1\0strval2\0map1key1\0map1val1\0map2key1\0map2val1\0
+	 * (and so on); str_lens[i], key_lens[i] and val_lens[i] determines
+	 * value length
+	 */
+	char payload[STROBE_MAX_PAYLOAD];
+};
+
+struct strobelight_bpf_sample {
+	uint64_t ktime;
+	char comm[TASK_COMM_LEN];
+	pid_t pid;
+	int user_stack_id;
+	int kernel_stack_id;
+	int has_meta;
+	struct strobemeta_payload metadata;
+	/*
+	 * makes it possible to pass (<real payload size> + 1) as data size to
+	 * perf_submit() to avoid perf_submit's paranoia about passing zero as
+	 * size, as it deduces that <real payload size> might be
+	 * **theoretically** zero
+	 */
+	char dummy_safeguard;
+};
+
+struct bpf_map_def SEC("maps") samples = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 32,
+};
+
+struct bpf_map_def SEC("maps") stacks_0 = {
+	.type = BPF_MAP_TYPE_STACK_TRACE,
+	.key_size = sizeof(uint32_t),
+	.value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH,
+	.max_entries = 16,
+};
+
+struct bpf_map_def SEC("maps") stacks_1 = {
+	.type = BPF_MAP_TYPE_STACK_TRACE,
+	.key_size = sizeof(uint32_t),
+	.value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH,
+	.max_entries = 16,
+};
+
+struct bpf_map_def SEC("maps") sample_heap = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(uint32_t),
+	.value_size = sizeof(struct strobelight_bpf_sample),
+	.max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps") strobemeta_cfgs = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(pid_t),
+	.value_size = sizeof(struct strobemeta_cfg),
+	.max_entries = STROBE_MAX_CFGS,
+};
+
+/* Type for the dtv.  */
+/* https://github.com/lattera/glibc/blob/master/nptl/sysdeps/x86_64/tls.h#L34 */
+typedef union dtv {
+	size_t counter;
+	struct {
+		void* val;
+		bool is_static;
+	} pointer;
+} dtv_t;
+
+/* Partial definition for tcbhead_t */
+/* https://github.com/bminor/glibc/blob/master/sysdeps/x86_64/nptl/tls.h#L42 */
+struct tcbhead {
+	void* tcb;
+	dtv_t* dtv;
+};
+
+/*
+ * TLS module/offset information for shared library case.
+ * For x86-64, this is mapped onto two entries in GOT.
+ * For aarch64, this is pointed to by second GOT entry.
+ */
+struct tls_index {
+	uint64_t module;
+	uint64_t offset;
+};
+
+static inline __attribute__((always_inline))
+void *calc_location(struct strobe_value_loc *loc, void *tls_base)
+{
+	/*
+	 * tls_mode value is:
+	 * - -1 (TLS_NOT_SET), if no metavar is present;
+	 * - 0 (TLS_LOCAL_EXEC), if metavar uses Local Executable mode of TLS
+	 * (offset from fs:0 for x86-64 or tpidr_el0 for aarch64);
+	 * - 1 (TLS_IMM_EXEC), if metavar uses Immediate Executable mode of TLS;
+	 * - 2 (TLS_GENERAL_DYN), if metavar uses General Dynamic mode of TLS;
+	 * This schema allows to use something like:
+	 * (tls_mode + 1) * (tls_base + offset)
+	 * to get NULL for "no metavar" location, or correct pointer for local
+	 * executable mode without doing extra ifs.
+	 */
+	if (loc->tls_mode <= TLS_LOCAL_EXEC) {
+		/* static executable is simple, we just have offset from
+		 * tls_base */
+		void *addr = tls_base + loc->offset;
+		/* multiply by (tls_mode + 1) to get NULL, if we have no
+		 * metavar in this slot */
+		return (void *)((loc->tls_mode + 1) * (int64_t)addr);
+	}
+	/*
+	 * Other modes are more complicated, we need to jump through few hoops.
+	 *
+	 * For immediate executable mode (currently supported only for aarch64):
+	 *  - loc->offset is pointing to a GOT entry containing fixed offset
+	 *  relative to tls_base;
+	 *
+	 * For general dynamic mode:
+	 *  - loc->offset is pointing to a beginning of double GOT entries;
+	 *  - (for aarch64 only) second entry points to tls_index_t struct;
+	 *  - (for x86-64 only) two GOT entries are already tls_index_t;
+	 *  - tls_index_t->module is used to find start of TLS section in
+	 *  which variable resides;
+	 *  - tls_index_t->offset provides offset within that TLS section,
+	 *  pointing to value of variable.
+	 */
+	struct tls_index tls_index;
+	dtv_t *dtv;
+	void *tls_ptr;
+
+	bpf_probe_read(&tls_index, sizeof(struct tls_index),
+		       (void *)loc->offset);
+	/* valid module index is always positive */
+	if (tls_index.module > 0) {
+		/* dtv = ((struct tcbhead *)tls_base)->dtv[tls_index.module] */
+		bpf_probe_read(&dtv, sizeof(dtv),
+			       &((struct tcbhead *)tls_base)->dtv);
+		dtv += tls_index.module;
+	} else {
+		dtv = NULL;
+	}
+	bpf_probe_read(&tls_ptr, sizeof(void *), dtv);
+	/* if pointer has (void *)-1 value, then TLS wasn't initialized yet */
+	return tls_ptr && tls_ptr != (void *)-1
+		? tls_ptr + tls_index.offset
+		: NULL;
+}
+
+static inline __attribute__((always_inline))
+void read_int_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base,
+		  struct strobe_value_generic *value,
+		  struct strobemeta_payload *data)
+{
+	void *location = calc_location(&cfg->int_locs[idx], tls_base);
+	if (!location)
+		return;
+
+	bpf_probe_read(value, sizeof(struct strobe_value_generic), location);
+	data->int_vals[idx] = value->val;
+	if (value->header.len)
+		data->int_vals_set_mask |= (1 << idx);
+}
+
+static inline __attribute__((always_inline))
+uint64_t read_str_var(struct strobemeta_cfg* cfg, size_t idx, void *tls_base,
+		      struct strobe_value_generic *value,
+		      struct strobemeta_payload *data, void *payload)
+{
+	void *location;
+	uint32_t len;
+
+	data->str_lens[idx] = 0;
+	location = calc_location(&cfg->str_locs[idx], tls_base);
+	if (!location)
+		return 0;
+
+	bpf_probe_read(value, sizeof(struct strobe_value_generic), location);
+	len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, value->ptr);
+	/*
+	 * if bpf_probe_read_str returns error (<0), due to casting to
+	 * unsinged int, it will become big number, so next check is
+	 * sufficient to check for errors AND prove to BPF verifier, that
+	 * bpf_probe_read_str won't return anything bigger than
+	 * STROBE_MAX_STR_LEN
+	 */
+	if (len > STROBE_MAX_STR_LEN)
+		return 0;
+
+	data->str_lens[idx] = len;
+	return len;
+}
+
+static inline __attribute__((always_inline))
+void *read_map_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base,
+		   struct strobe_value_generic *value,
+		   struct strobemeta_payload* data, void *payload)
+{
+	struct strobe_map_descr* descr = &data->map_descrs[idx];
+	struct strobe_map_raw map;
+	void *location;
+	uint32_t len;
+	int i;
+
+	descr->tag_len = 0; /* presume no tag is set */
+	descr->cnt = -1; /* presume no value is set */
+
+	location = calc_location(&cfg->map_locs[idx], tls_base);
+	if (!location)
+		return payload;
+
+	bpf_probe_read(value, sizeof(struct strobe_value_generic), location);
+	if (bpf_probe_read(&map, sizeof(struct strobe_map_raw), value->ptr))
+		return payload;
+
+	descr->id = map.id;
+	descr->cnt = map.cnt;
+	if (cfg->req_meta_idx == idx) {
+		data->req_id = map.id;
+		data->req_meta_valid = 1;
+	}
+
+	len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, map.tag);
+	if (len <= STROBE_MAX_STR_LEN) {
+		descr->tag_len = len;
+		payload += len;
+	}
+
+#ifdef NO_UNROLL
+#pragma clang loop unroll(disable)
+#else
+#pragma unroll
+#endif
+	for (int i = 0; i < STROBE_MAX_MAP_ENTRIES && i < map.cnt; ++i) {
+		descr->key_lens[i] = 0;
+		len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN,
+					 map.entries[i].key);
+		if (len <= STROBE_MAX_STR_LEN) {
+			descr->key_lens[i] = len;
+			payload += len;
+		}
+		descr->val_lens[i] = 0;
+		len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN,
+					 map.entries[i].val);
+		if (len <= STROBE_MAX_STR_LEN) {
+			descr->val_lens[i] = len;
+			payload += len;
+		}
+	}
+
+	return payload;
+}
+
+/*
+ * read_strobe_meta returns NULL, if no metadata was read; otherwise returns
+ * pointer to *right after* payload ends
+ */
+static inline __attribute__((always_inline))
+void *read_strobe_meta(struct task_struct* task,
+		       struct strobemeta_payload* data) {
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+	struct strobe_value_generic value = {0};
+	struct strobemeta_cfg *cfg;
+	void *tls_base, *payload;
+
+	cfg = bpf_map_lookup_elem(&strobemeta_cfgs, &pid);
+	if (!cfg)
+		return NULL;
+
+	data->int_vals_set_mask = 0;
+	data->req_meta_valid = 0;
+	payload = data->payload;
+	/*
+	 * we don't have struct task_struct definition, it should be:
+	 * tls_base = (void *)task->thread.fsbase;
+	 */
+	tls_base = (void *)task;
+
+#ifdef NO_UNROLL
+#pragma clang loop unroll(disable)
+#else
+#pragma unroll
+#endif
+	for (int i = 0; i < STROBE_MAX_INTS; ++i) {
+		read_int_var(cfg, i, tls_base, &value, data);
+	}
+#ifdef NO_UNROLL
+#pragma clang loop unroll(disable)
+#else
+#pragma unroll
+#endif
+	for (int i = 0; i < STROBE_MAX_STRS; ++i) {
+		payload += read_str_var(cfg, i, tls_base, &value, data, payload);
+	}
+#ifdef NO_UNROLL
+#pragma clang loop unroll(disable)
+#else
+#pragma unroll
+#endif
+	for (int i = 0; i < STROBE_MAX_MAPS; ++i) {
+		payload = read_map_var(cfg, i, tls_base, &value, data, payload);
+	}
+	/*
+	 * return pointer right after end of payload, so it's possible to
+	 * calculate exact amount of useful data that needs to be sent
+	 */
+	return payload;
+}
+
+SEC("raw_tracepoint/kfree_skb")
+int on_event(struct pt_regs *ctx) {
+	pid_t pid =  bpf_get_current_pid_tgid() >> 32;
+	struct strobelight_bpf_sample* sample;
+	struct task_struct *task;
+	uint32_t zero = 0;
+	uint64_t ktime_ns;
+	void *sample_end;
+
+	sample = bpf_map_lookup_elem(&sample_heap, &zero);
+	if (!sample)
+		return 0; /* this will never happen */
+
+	sample->pid = pid;
+	bpf_get_current_comm(&sample->comm, TASK_COMM_LEN);
+	ktime_ns = bpf_ktime_get_ns();
+	sample->ktime = ktime_ns;
+
+	task = (struct task_struct *)bpf_get_current_task();
+	sample_end = read_strobe_meta(task, &sample->metadata);
+	sample->has_meta = sample_end != NULL;
+	sample_end = sample_end ? : &sample->metadata;
+
+	if ((ktime_ns >> STACK_TABLE_EPOCH_SHIFT) & 1) {
+		sample->kernel_stack_id = bpf_get_stackid(ctx, &stacks_1, 0);
+		sample->user_stack_id = bpf_get_stackid(ctx, &stacks_1, BPF_F_USER_STACK);
+	} else {
+		sample->kernel_stack_id = bpf_get_stackid(ctx, &stacks_0, 0);
+		sample->user_stack_id = bpf_get_stackid(ctx, &stacks_0, BPF_F_USER_STACK);
+	}
+
+	uint64_t sample_size = sample_end - (void *)sample;
+	/* should always be true */
+	if (sample_size < sizeof(struct strobelight_bpf_sample))
+		bpf_perf_event_output(ctx, &samples, 0, sample, 1 + sample_size);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c

@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+// Copyright (c) 2019 Facebook
+
+#define STROBE_MAX_INTS 2
+#define STROBE_MAX_STRS 25
+#define STROBE_MAX_MAPS 13
+#define STROBE_MAX_MAP_ENTRIES 20
+#define NO_UNROLL
+#include "strobemeta.h"

tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c

@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+// Copyright (c) 2019 Facebook
+
+#define STROBE_MAX_INTS 2
+#define STROBE_MAX_STRS 25
+#define STROBE_MAX_MAPS 30
+#define STROBE_MAX_MAP_ENTRIES 20
+#define NO_UNROLL
+#include "strobemeta.h"

tools/testing/selftests/bpf/progs/test_btf_newkv.c

@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+
+struct ipv_counts {
+	unsigned int v4;
+	unsigned int v6;
+};
+
+/* just to validate we can handle maps in multiple sections */
+struct bpf_map_def SEC("maps") btf_map_legacy = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(long long),
+	.max_entries = 4,
+};
+
+BPF_ANNOTATE_KV_PAIR(btf_map_legacy, int, struct ipv_counts);
+
+struct {
+	int *key;
+	struct ipv_counts *value;
+	unsigned int type;
+	unsigned int max_entries;
+} btf_map SEC(".maps") = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.max_entries = 4,
+};
+
+struct dummy_tracepoint_args {
+	unsigned long long pad;
+	struct sock *sock;
+};
+
+__attribute__((noinline))
+static int test_long_fname_2(struct dummy_tracepoint_args *arg)
+{
+	struct ipv_counts *counts;
+	int key = 0;
+
+	if (!arg->sock)
+		return 0;
+
+	counts = bpf_map_lookup_elem(&btf_map, &key);
+	if (!counts)
+		return 0;
+
+	counts->v6++;
+
+	/* just verify we can reference both maps */
+	counts = bpf_map_lookup_elem(&btf_map_legacy, &key);
+	if (!counts)
+		return 0;
+
+	return 0;
+}
+
+__attribute__((noinline))
+static int test_long_fname_1(struct dummy_tracepoint_args *arg)
+{
+	return test_long_fname_2(arg);
+}
+
+SEC("dummy_tracepoint")
+int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+{
+	return test_long_fname_1(arg);
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c

@@ -15,17 +15,25 @@ struct stack_trace_t {
 	struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP];
 };
 
-struct bpf_map_def SEC("maps") perfmap = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 key_size;
+	__u32 value_size;
+} perfmap SEC(".maps") = {
 	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.max_entries = 2,
 	.key_size = sizeof(int),
 	.value_size = sizeof(__u32),
-	.max_entries = 2,
 };
 
-struct bpf_map_def SEC("maps") stackdata_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct stack_trace_t *value;
+} stackdata_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct stack_trace_t),
 	.max_entries = 1,
 };
 
@@ -47,10 +55,13 @@ struct bpf_map_def SEC("maps") stackdata_map = {
  * issue and avoid complicated C programming massaging.
  * This is an acceptable workaround since there is one entry here.
  */
-struct bpf_map_def SEC("maps") rawdata_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u64 (*value)[2 * MAX_STACK_RAWTP];
+} rawdata_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2,
 	.max_entries = 1,
 };
 

tools/testing/selftests/bpf/progs/test_global_data.c

@@ -7,17 +7,23 @@
 
 #include "bpf_helpers.h"
 
-struct bpf_map_def SEC("maps") result_number = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u64 *value;
+} result_number SEC(".maps") = {
 	.type		= BPF_MAP_TYPE_ARRAY,
-	.key_size	= sizeof(__u32),
-	.value_size	= sizeof(__u64),
 	.max_entries	= 11,
 };
 
-struct bpf_map_def SEC("maps") result_string = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	const char (*value)[32];
+} result_string SEC(".maps") = {
 	.type		= BPF_MAP_TYPE_ARRAY,
-	.key_size	= sizeof(__u32),
-	.value_size	= 32,
 	.max_entries	= 5,
 };
 
@@ -27,10 +33,13 @@ struct foo {
 	__u64 c;
 };
 
-struct bpf_map_def SEC("maps") result_struct = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct foo *value;
+} result_struct SEC(".maps") = {
 	.type		= BPF_MAP_TYPE_ARRAY,
-	.key_size	= sizeof(__u32),
-	.value_size	= sizeof(struct foo),
 	.max_entries	= 5,
 };
 

tools/testing/selftests/bpf/progs/test_l4lb.c

@@ -169,38 +169,53 @@ struct eth_hdr {
 	unsigned short eth_proto;
 };
 
-struct bpf_map_def SEC("maps") vip_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	struct vip *key;
+	struct vip_meta *value;
+} vip_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(struct vip),
-	.value_size = sizeof(struct vip_meta),
 	.max_entries = MAX_VIPS,
 };
 
-struct bpf_map_def SEC("maps") ch_rings = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u32 *value;
+} ch_rings SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
 	.max_entries = CH_RINGS_SIZE,
 };
 
-struct bpf_map_def SEC("maps") reals = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct real_definition *value;
+} reals SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct real_definition),
 	.max_entries = MAX_REALS,
 };
 
-struct bpf_map_def SEC("maps") stats = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct vip_stats *value;
+} stats SEC(".maps") = {
 	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct vip_stats),
 	.max_entries = MAX_VIPS,
 };
 
-struct bpf_map_def SEC("maps") ctl_array = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct ctl_value *value;
+} ctl_array SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct ctl_value),
 	.max_entries = CTL_MAP_SIZE,
 };
 

tools/testing/selftests/bpf/progs/test_l4lb_noinline.c

@@ -165,38 +165,53 @@ struct eth_hdr {
 	unsigned short eth_proto;
 };
 
-struct bpf_map_def SEC("maps") vip_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	struct vip *key;
+	struct vip_meta *value;
+} vip_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(struct vip),
-	.value_size = sizeof(struct vip_meta),
 	.max_entries = MAX_VIPS,
 };
 
-struct bpf_map_def SEC("maps") ch_rings = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u32 *value;
+} ch_rings SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
 	.max_entries = CH_RINGS_SIZE,
 };
 
-struct bpf_map_def SEC("maps") reals = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct real_definition *value;
+} reals SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct real_definition),
 	.max_entries = MAX_REALS,
 };
 
-struct bpf_map_def SEC("maps") stats = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct vip_stats *value;
+} stats SEC(".maps") = {
 	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct vip_stats),
 	.max_entries = MAX_VIPS,
 };
 
-struct bpf_map_def SEC("maps") ctl_array = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct ctl_value *value;
+} ctl_array SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct ctl_value),
 	.max_entries = CTL_MAP_SIZE,
 };
 

tools/testing/selftests/bpf/progs/test_map_lock.c

@@ -11,29 +11,31 @@ struct hmap_elem {
 	int var[VAR_NUM];
 };
 
-struct bpf_map_def SEC("maps") hash_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct hmap_elem *value;
+} hash_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(int),
-	.value_size = sizeof(struct hmap_elem),
 	.max_entries = 1,
 };
 
-BPF_ANNOTATE_KV_PAIR(hash_map, int, struct hmap_elem);
-
 struct array_elem {
 	struct bpf_spin_lock lock;
 	int var[VAR_NUM];
 };
 
-struct bpf_map_def SEC("maps") array_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	int *key;
+	struct array_elem *value;
+} array_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(struct array_elem),
 	.max_entries = 1,
 };
 
-BPF_ANNOTATE_KV_PAIR(array_map, int, struct array_elem);
-
 SEC("map_lock_demo")
 int bpf_map_lock_test(struct __sk_buff *skb)
 {

tools/testing/selftests/bpf/progs/test_seg6_loop.c

@@ -0,0 +1,261 @@
+#include <stddef.h>
+#include <inttypes.h>
+#include <errno.h>
+#include <linux/seg6_local.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+/* Packet parsing state machine helpers. */
+#define cursor_advance(_cursor, _len) \
+	({ void *_tmp = _cursor; _cursor += _len; _tmp; })
+
+#define SR6_FLAG_ALERT (1 << 4)
+
+#define htonll(x) ((bpf_htonl(1)) == 1 ? (x) : ((uint64_t)bpf_htonl((x) & \
+				0xFFFFFFFF) << 32) | bpf_htonl((x) >> 32))
+#define ntohll(x) ((bpf_ntohl(1)) == 1 ? (x) : ((uint64_t)bpf_ntohl((x) & \
+				0xFFFFFFFF) << 32) | bpf_ntohl((x) >> 32))
+#define BPF_PACKET_HEADER __attribute__((packed))
+
+struct ip6_t {
+	unsigned int ver:4;
+	unsigned int priority:8;
+	unsigned int flow_label:20;
+	unsigned short payload_len;
+	unsigned char next_header;
+	unsigned char hop_limit;
+	unsigned long long src_hi;
+	unsigned long long src_lo;
+	unsigned long long dst_hi;
+	unsigned long long dst_lo;
+} BPF_PACKET_HEADER;
+
+struct ip6_addr_t {
+	unsigned long long hi;
+	unsigned long long lo;
+} BPF_PACKET_HEADER;
+
+struct ip6_srh_t {
+	unsigned char nexthdr;
+	unsigned char hdrlen;
+	unsigned char type;
+	unsigned char segments_left;
+	unsigned char first_segment;
+	unsigned char flags;
+	unsigned short tag;
+
+	struct ip6_addr_t segments[0];
+} BPF_PACKET_HEADER;
+
+struct sr6_tlv_t {
+	unsigned char type;
+	unsigned char len;
+	unsigned char value[0];
+} BPF_PACKET_HEADER;
+
+static __attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb)
+{
+	void *cursor, *data_end;
+	struct ip6_srh_t *srh;
+	struct ip6_t *ip;
+	uint8_t *ipver;
+
+	data_end = (void *)(long)skb->data_end;
+	cursor = (void *)(long)skb->data;
+	ipver = (uint8_t *)cursor;
+
+	if ((void *)ipver + sizeof(*ipver) > data_end)
+		return NULL;
+
+	if ((*ipver >> 4) != 6)
+		return NULL;
+
+	ip = cursor_advance(cursor, sizeof(*ip));
+	if ((void *)ip + sizeof(*ip) > data_end)
+		return NULL;
+
+	if (ip->next_header != 43)
+		return NULL;
+
+	srh = cursor_advance(cursor, sizeof(*srh));
+	if ((void *)srh + sizeof(*srh) > data_end)
+		return NULL;
+
+	if (srh->type != 4)
+		return NULL;
+
+	return srh;
+}
+
+static __attribute__((always_inline))
+int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad,
+		   uint32_t old_pad, uint32_t pad_off)
+{
+	int err;
+
+	if (new_pad != old_pad) {
+		err = bpf_lwt_seg6_adjust_srh(skb, pad_off,
+					  (int) new_pad - (int) old_pad);
+		if (err)
+			return err;
+	}
+
+	if (new_pad > 0) {
+		char pad_tlv_buf[16] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+					0, 0, 0};
+		struct sr6_tlv_t *pad_tlv = (struct sr6_tlv_t *) pad_tlv_buf;
+
+		pad_tlv->type = SR6_TLV_PADDING;
+		pad_tlv->len = new_pad - 2;
+
+		err = bpf_lwt_seg6_store_bytes(skb, pad_off,
+					       (void *)pad_tlv_buf, new_pad);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static __attribute__((always_inline))
+int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh,
+			  uint32_t *tlv_off, uint32_t *pad_size,
+			  uint32_t *pad_off)
+{
+	uint32_t srh_off, cur_off;
+	int offset_valid = 0;
+	int err;
+
+	srh_off = (char *)srh - (char *)(long)skb->data;
+	// cur_off = end of segments, start of possible TLVs
+	cur_off = srh_off + sizeof(*srh) +
+		sizeof(struct ip6_addr_t) * (srh->first_segment + 1);
+
+	*pad_off = 0;
+
+	// we can only go as far as ~10 TLVs due to the BPF max stack size
+	#pragma clang loop unroll(disable)
+	for (int i = 0; i < 100; i++) {
+		struct sr6_tlv_t tlv;
+
+		if (cur_off == *tlv_off)
+			offset_valid = 1;
+
+		if (cur_off >= srh_off + ((srh->hdrlen + 1) << 3))
+			break;
+
+		err = bpf_skb_load_bytes(skb, cur_off, &tlv, sizeof(tlv));
+		if (err)
+			return err;
+
+		if (tlv.type == SR6_TLV_PADDING) {
+			*pad_size = tlv.len + sizeof(tlv);
+			*pad_off = cur_off;
+
+			if (*tlv_off == srh_off) {
+				*tlv_off = cur_off;
+				offset_valid = 1;
+			}
+			break;
+
+		} else if (tlv.type == SR6_TLV_HMAC) {
+			break;
+		}
+
+		cur_off += sizeof(tlv) + tlv.len;
+	} // we reached the padding or HMAC TLVs, or the end of the SRH
+
+	if (*pad_off == 0)
+		*pad_off = cur_off;
+
+	if (*tlv_off == -1)
+		*tlv_off = cur_off;
+	else if (!offset_valid)
+		return -EINVAL;
+
+	return 0;
+}
+
+static __attribute__((always_inline))
+int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off,
+	    struct sr6_tlv_t *itlv, uint8_t tlv_size)
+{
+	uint32_t srh_off = (char *)srh - (char *)(long)skb->data;
+	uint8_t len_remaining, new_pad;
+	uint32_t pad_off = 0;
+	uint32_t pad_size = 0;
+	uint32_t partial_srh_len;
+	int err;
+
+	if (tlv_off != -1)
+		tlv_off += srh_off;
+
+	if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC)
+		return -EINVAL;
+
+	err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off);
+	if (err)
+		return err;
+
+	err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, sizeof(*itlv) + itlv->len);
+	if (err)
+		return err;
+
+	err = bpf_lwt_seg6_store_bytes(skb, tlv_off, (void *)itlv, tlv_size);
+	if (err)
+		return err;
+
+	// the following can't be moved inside update_tlv_pad because the
+	// bpf verifier has some issues with it
+	pad_off += sizeof(*itlv) + itlv->len;
+	partial_srh_len = pad_off - srh_off;
+	len_remaining = partial_srh_len % 8;
+	new_pad = 8 - len_remaining;
+
+	if (new_pad == 1) // cannot pad for 1 byte only
+		new_pad = 9;
+	else if (new_pad == 8)
+		new_pad = 0;
+
+	return update_tlv_pad(skb, new_pad, pad_size, pad_off);
+}
+
+// Add an Egress TLV fc00::4, add the flag A,
+// and apply End.X action to fc42::1
+SEC("lwt_seg6local")
+int __add_egr_x(struct __sk_buff *skb)
+{
+	unsigned long long hi = 0xfc42000000000000;
+	unsigned long long lo = 0x1;
+	struct ip6_srh_t *srh = get_srh(skb);
+	uint8_t new_flags = SR6_FLAG_ALERT;
+	struct ip6_addr_t addr;
+	int err, offset;
+
+	if (srh == NULL)
+		return BPF_DROP;
+
+	uint8_t tlv[20] = {2, 18, 0, 0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+			   0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4};
+
+	err = add_tlv(skb, srh, (srh->hdrlen+1) << 3,
+		      (struct sr6_tlv_t *)&tlv, 20);
+	if (err)
+		return BPF_DROP;
+
+	offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags);
+	err = bpf_lwt_seg6_store_bytes(skb, offset,
+				       (void *)&new_flags, sizeof(new_flags));
+	if (err)
+		return BPF_DROP;
+
+	addr.lo = htonll(lo);
+	addr.hi = htonll(hi);
+	err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X,
+				  (void *)&addr, sizeof(addr));
+	if (err)
+		return BPF_DROP;
+	return BPF_REDIRECT;
+}
+char __license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c

@@ -21,38 +21,55 @@ int _version SEC("version") = 1;
 #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
 #endif
 
-struct bpf_map_def SEC("maps") outer_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 key_size;
+	__u32 value_size;
+} outer_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	.max_entries = 1,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(__u32),
-	.max_entries = 1,
 };
 
-struct bpf_map_def SEC("maps") result_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u32 *value;
+} result_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
 	.max_entries = NR_RESULTS,
 };
 
-struct bpf_map_def SEC("maps") tmp_index_ovr_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	int *value;
+} tmp_index_ovr_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(int),
 	.max_entries = 1,
 };
 
-struct bpf_map_def SEC("maps") linum_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u32 *value;
+} linum_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
 	.max_entries = 1,
 };
 
-struct bpf_map_def SEC("maps") data_check_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct data_check *value;
+} data_check_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct data_check),
 	.max_entries = 1,
 };
 

tools/testing/selftests/bpf/progs/test_send_signal_kern.c

@@ -4,24 +4,26 @@
 #include <linux/version.h>
 #include "bpf_helpers.h"
 
-struct bpf_map_def SEC("maps") info_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u64 *value;
+} info_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64),
 	.max_entries = 1,
 };
 
-BPF_ANNOTATE_KV_PAIR(info_map, __u32, __u64);
+struct {
-
+	__u32 type;
-struct bpf_map_def SEC("maps") status_map = {
+	__u32 max_entries;
+	__u32 *key;
+	__u64 *value;
+} status_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64),
 	.max_entries = 1,
 };
 
-BPF_ANNOTATE_KV_PAIR(status_map, __u32, __u64);
-
 SEC("send_signal_demo")
 int bpf_send_signal_test(void *ctx)
 {

tools/testing/selftests/bpf/progs/test_sock_fields_kern.c

@@ -27,31 +27,43 @@ enum bpf_linum_array_idx {
 	__NR_BPF_LINUM_ARRAY_IDX,
 };
 
-struct bpf_map_def SEC("maps") addr_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct sockaddr_in6 *value;
+} addr_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct sockaddr_in6),
 	.max_entries = __NR_BPF_ADDR_ARRAY_IDX,
 };
 
-struct bpf_map_def SEC("maps") sock_result_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct bpf_sock *value;
+} sock_result_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct bpf_sock),
 	.max_entries = __NR_BPF_RESULT_ARRAY_IDX,
 };
 
-struct bpf_map_def SEC("maps") tcp_sock_result_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct bpf_tcp_sock *value;
+} tcp_sock_result_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct bpf_tcp_sock),
 	.max_entries = __NR_BPF_RESULT_ARRAY_IDX,
 };
 
-struct bpf_map_def SEC("maps") linum_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u32 *value;
+} linum_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
 	.max_entries = __NR_BPF_LINUM_ARRAY_IDX,
 };
 
@@ -60,26 +72,26 @@ struct bpf_spinlock_cnt {
 	__u32 cnt;
 };
 
-struct bpf_map_def SEC("maps") sk_pkt_out_cnt = {
+struct {
+	__u32 type;
+	__u32 map_flags;
+	int *key;
+	struct bpf_spinlock_cnt *value;
+} sk_pkt_out_cnt SEC(".maps") = {
 	.type = BPF_MAP_TYPE_SK_STORAGE,
-	.key_size = sizeof(int),
-	.value_size = sizeof(struct bpf_spinlock_cnt),
-	.max_entries = 0,
 	.map_flags = BPF_F_NO_PREALLOC,
 };
 
-BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt, int, struct bpf_spinlock_cnt);
+struct {
-
+	__u32 type;
-struct bpf_map_def SEC("maps") sk_pkt_out_cnt10 = {
+	__u32 map_flags;
+	int *key;
+	struct bpf_spinlock_cnt *value;
+} sk_pkt_out_cnt10 SEC(".maps") = {
 	.type = BPF_MAP_TYPE_SK_STORAGE,
-	.key_size = sizeof(int),
-	.value_size = sizeof(struct bpf_spinlock_cnt),
-	.max_entries = 0,
 	.map_flags = BPF_F_NO_PREALLOC,
 };
 
-BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt10, int, struct bpf_spinlock_cnt);
-
 static bool is_loopback6(__u32 *a6)
 {
 	return !a6[0] && !a6[1] && !a6[2] && a6[3] == bpf_htonl(1);

tools/testing/selftests/bpf/progs/test_spin_lock.c

@@ -10,30 +10,29 @@ struct hmap_elem {
 	int test_padding;
 };
 
-struct bpf_map_def SEC("maps") hmap = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	int *key;
+	struct hmap_elem *value;
+} hmap SEC(".maps") = {
 	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(int),
-	.value_size = sizeof(struct hmap_elem),
 	.max_entries = 1,
 };
 
-BPF_ANNOTATE_KV_PAIR(hmap, int, struct hmap_elem);
-
-
 struct cls_elem {
 	struct bpf_spin_lock lock;
 	volatile int cnt;
 };
 
-struct bpf_map_def SEC("maps") cls_map = {
+struct {
+	__u32 type;
+	struct bpf_cgroup_storage_key *key;
+	struct cls_elem *value;
+} cls_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
-	.key_size = sizeof(struct bpf_cgroup_storage_key),
-	.value_size = sizeof(struct cls_elem),
 };
 
-BPF_ANNOTATE_KV_PAIR(cls_map, struct bpf_cgroup_storage_key,
-		     struct cls_elem);
-
 struct bpf_vqueue {
 	struct bpf_spin_lock lock;
 	/* 4 byte hole */
@@ -42,14 +41,16 @@ struct bpf_vqueue {
 	unsigned int rate;
 };
 
-struct bpf_map_def SEC("maps") vqueue = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	int *key;
+	struct bpf_vqueue *value;
+} vqueue SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(struct bpf_vqueue),
 	.max_entries = 1,
 };
 
-BPF_ANNOTATE_KV_PAIR(vqueue, int, struct bpf_vqueue);
 #define CREDIT_PER_NS(delta, rate) (((delta) * rate) >> 20)
 
 SEC("spin_lock_demo")

tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c

@@ -8,34 +8,50 @@
 #define PERF_MAX_STACK_DEPTH         127
 #endif
 
-struct bpf_map_def SEC("maps") control_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u32 *value;
+} control_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
 	.max_entries = 1,
 };
 
-struct bpf_map_def SEC("maps") stackid_hmap = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u32 *value;
+} stackid_hmap SEC(".maps") = {
 	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
 	.max_entries = 16384,
 };
 
-struct bpf_map_def SEC("maps") stackmap = {
+typedef struct bpf_stack_build_id stack_trace_t[PERF_MAX_STACK_DEPTH];
+
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 map_flags;
+	__u32 key_size;
+	__u32 value_size;
+} stackmap SEC(".maps") = {
 	.type = BPF_MAP_TYPE_STACK_TRACE,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct bpf_stack_build_id)
-		* PERF_MAX_STACK_DEPTH,
 	.max_entries = 128,
 	.map_flags = BPF_F_STACK_BUILD_ID,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(stack_trace_t),
 };
 
-struct bpf_map_def SEC("maps") stack_amap = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	/* there seems to be a bug in kernel not handling typedef properly */
+	struct bpf_stack_build_id (*value)[PERF_MAX_STACK_DEPTH];
+} stack_amap SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct bpf_stack_build_id)
-		* PERF_MAX_STACK_DEPTH,
 	.max_entries = 128,
 };
 

tools/testing/selftests/bpf/progs/test_stacktrace_map.c

@@ -8,31 +8,47 @@
 #define PERF_MAX_STACK_DEPTH         127
 #endif
 
-struct bpf_map_def SEC("maps") control_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u32 *value;
+} control_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
 	.max_entries = 1,
 };
 
-struct bpf_map_def SEC("maps") stackid_hmap = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u32 *value;
+} stackid_hmap SEC(".maps") = {
 	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
 	.max_entries = 16384,
 };
 
-struct bpf_map_def SEC("maps") stackmap = {
+typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH];
+
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 key_size;
+	__u32 value_size;
+} stackmap SEC(".maps") = {
 	.type = BPF_MAP_TYPE_STACK_TRACE,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH,
 	.max_entries = 16384,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(stack_trace_t),
 };
 
-struct bpf_map_def SEC("maps") stack_amap = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u64 (*value)[PERF_MAX_STACK_DEPTH];
+} stack_amap SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH,
 	.max_entries = 16384,
 };
 

tools/testing/selftests/bpf/progs/test_sysctl_loop1.c

@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <stdint.h>
+#include <string.h>
+
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+
+#include "bpf_helpers.h"
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+/* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */
+#define TCP_MEM_LOOPS 28  /* because 30 doesn't fit into 512 bytes of stack */
+#define MAX_ULONG_STR_LEN 7
+#define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN)
+
+static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx)
+{
+	volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string";
+	unsigned char i;
+	char name[64];
+	int ret;
+
+	memset(name, 0, sizeof(name));
+	ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0);
+	if (ret < 0 || ret != sizeof(tcp_mem_name) - 1)
+		return 0;
+
+#pragma clang loop unroll(disable)
+	for (i = 0; i < sizeof(tcp_mem_name); ++i)
+		if (name[i] != tcp_mem_name[i])
+			return 0;
+
+	return 1;
+}
+
+SEC("cgroup/sysctl")
+int sysctl_tcp_mem(struct bpf_sysctl *ctx)
+{
+	unsigned long tcp_mem[TCP_MEM_LOOPS] = {};
+	char value[MAX_VALUE_STR_LEN];
+	unsigned char i, off = 0;
+	int ret;
+
+	if (ctx->write)
+		return 0;
+
+	if (!is_tcp_mem(ctx))
+		return 0;
+
+	ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN);
+	if (ret < 0 || ret >= MAX_VALUE_STR_LEN)
+		return 0;
+
+#pragma clang loop unroll(disable)
+	for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) {
+		ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0,
+				  tcp_mem + i);
+		if (ret <= 0 || ret > MAX_ULONG_STR_LEN)
+			return 0;
+		off += ret & MAX_ULONG_STR_LEN;
+	}
+
+	return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2];
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/test_sysctl_loop2.c

@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <stdint.h>
+#include <string.h>
+
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+
+#include "bpf_helpers.h"
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+/* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */
+#define TCP_MEM_LOOPS 20  /* because 30 doesn't fit into 512 bytes of stack */
+#define MAX_ULONG_STR_LEN 7
+#define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN)
+
+static __attribute__((noinline)) int is_tcp_mem(struct bpf_sysctl *ctx)
+{
+	volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string_to_stress_byte_loop";
+	unsigned char i;
+	char name[64];
+	int ret;
+
+	memset(name, 0, sizeof(name));
+	ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0);
+	if (ret < 0 || ret != sizeof(tcp_mem_name) - 1)
+		return 0;
+
+#pragma clang loop unroll(disable)
+	for (i = 0; i < sizeof(tcp_mem_name); ++i)
+		if (name[i] != tcp_mem_name[i])
+			return 0;
+
+	return 1;
+}
+
+
+SEC("cgroup/sysctl")
+int sysctl_tcp_mem(struct bpf_sysctl *ctx)
+{
+	unsigned long tcp_mem[TCP_MEM_LOOPS] = {};
+	char value[MAX_VALUE_STR_LEN];
+	unsigned char i, off = 0;
+	int ret;
+
+	if (ctx->write)
+		return 0;
+
+	if (!is_tcp_mem(ctx))
+		return 0;
+
+	ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN);
+	if (ret < 0 || ret >= MAX_VALUE_STR_LEN)
+		return 0;
+
+#pragma clang loop unroll(disable)
+	for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) {
+		ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0,
+				  tcp_mem + i);
+		if (ret <= 0 || ret > MAX_ULONG_STR_LEN)
+			return 0;
+		off += ret & MAX_ULONG_STR_LEN;
+	}
+
+	return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2];
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/test_sysctl_prog.c

@@ -8,7 +8,6 @@
 #include <linux/bpf.h>
 
 #include "bpf_helpers.h"
-#include "bpf_util.h"
 
 /* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */
 #define MAX_ULONG_STR_LEN 0xF
@@ -16,6 +15,10 @@
 /* Max supported length of sysctl value string (pow2). */
 #define MAX_VALUE_STR_LEN 0x40
 
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
 static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx)
 {
 	char tcp_mem_name[] = "net/ipv4/tcp_mem";

tools/testing/selftests/bpf/progs/test_tcp_estats.c

@@ -148,10 +148,13 @@ struct tcp_estats_basic_event {
 	struct tcp_estats_conn_id conn_id;
 };
 
-struct bpf_map_def SEC("maps") ev_record_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct tcp_estats_basic_event *value;
+} ev_record_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct tcp_estats_basic_event),
 	.max_entries = 1024,
 };
 

tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c

@@ -14,17 +14,23 @@
 #include "bpf_endian.h"
 #include "test_tcpbpf.h"
 
-struct bpf_map_def SEC("maps") global_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct tcpbpf_globals *value;
+} global_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct tcpbpf_globals),
 	.max_entries = 4,
 };
 
-struct bpf_map_def SEC("maps") sockopt_results = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	int *value;
+} sockopt_results SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(int),
 	.max_entries = 2,
 };
 

tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c

@@ -14,18 +14,26 @@
 #include "bpf_endian.h"
 #include "test_tcpnotify.h"
 
-struct bpf_map_def SEC("maps") global_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct tcpnotify_globals *value;
+} global_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct tcpnotify_globals),
 	.max_entries = 4,
 };
 
-struct bpf_map_def SEC("maps") perf_event_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 key_size;
+	__u32 value_size;
+} perf_event_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.max_entries = 2,
 	.key_size = sizeof(int),
 	.value_size = sizeof(__u32),
-	.max_entries = 2,
 };
 
 int _version SEC("version") = 1;

tools/testing/selftests/bpf/progs/test_xdp.c

@@ -22,17 +22,23 @@
 
 int _version SEC("version") = 1;
 
-struct bpf_map_def SEC("maps") rxcnt = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u64 *value;
+} rxcnt SEC(".maps") = {
 	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64),
 	.max_entries = 256,
 };
 
-struct bpf_map_def SEC("maps") vip2tnl = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	struct vip *key;
+	struct iptnl_info *value;
+} vip2tnl SEC(".maps") = {
 	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(struct vip),
-	.value_size = sizeof(struct iptnl_info),
 	.max_entries = MAX_IPTNL_ENTRIES,
 };
 

tools/testing/selftests/bpf/progs/test_xdp_loop.c

@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include <sys/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+#include "test_iptunnel_common.h"
+
+int _version SEC("version") = 1;
+
+struct bpf_map_def SEC("maps") rxcnt = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u64),
+	.max_entries = 256,
+};
+
+struct bpf_map_def SEC("maps") vip2tnl = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(struct vip),
+	.value_size = sizeof(struct iptnl_info),
+	.max_entries = MAX_IPTNL_ENTRIES,
+};
+
+static __always_inline void count_tx(__u32 protocol)
+{
+	__u64 *rxcnt_count;
+
+	rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol);
+	if (rxcnt_count)
+		*rxcnt_count += 1;
+}
+
+static __always_inline int get_dport(void *trans_data, void *data_end,
+				     __u8 protocol)
+{
+	struct tcphdr *th;
+	struct udphdr *uh;
+
+	switch (protocol) {
+	case IPPROTO_TCP:
+		th = (struct tcphdr *)trans_data;
+		if (th + 1 > data_end)
+			return -1;
+		return th->dest;
+	case IPPROTO_UDP:
+		uh = (struct udphdr *)trans_data;
+		if (uh + 1 > data_end)
+			return -1;
+		return uh->dest;
+	default:
+		return 0;
+	}
+}
+
+static __always_inline void set_ethhdr(struct ethhdr *new_eth,
+				       const struct ethhdr *old_eth,
+				       const struct iptnl_info *tnl,
+				       __be16 h_proto)
+{
+	memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source));
+	memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest));
+	new_eth->h_proto = h_proto;
+}
+
+static __always_inline int handle_ipv4(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	struct iphdr *iph = data + sizeof(struct ethhdr);
+	__u16 *next_iph;
+	__u16 payload_len;
+	struct vip vip = {};
+	int dport;
+	__u32 csum = 0;
+	int i;
+
+	if (iph + 1 > data_end)
+		return XDP_DROP;
+
+	dport = get_dport(iph + 1, data_end, iph->protocol);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = iph->protocol;
+	vip.family = AF_INET;
+	vip.daddr.v4 = iph->daddr;
+	vip.dport = dport;
+	payload_len = bpf_ntohs(iph->tot_len);
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v4-in-v4 */
+	if (!tnl || tnl->family != AF_INET)
+		return XDP_PASS;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr)))
+		return XDP_DROP;
+
+	data = (void *)(long)xdp->data;
+	data_end = (void *)(long)xdp->data_end;
+
+	new_eth = data;
+	iph = data + sizeof(*new_eth);
+	old_eth = data + sizeof(*iph);
+
+	if (new_eth + 1 > data_end ||
+	    old_eth + 1 > data_end ||
+	    iph + 1 > data_end)
+		return XDP_DROP;
+
+	set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP));
+
+	iph->version = 4;
+	iph->ihl = sizeof(*iph) >> 2;
+	iph->frag_off =	0;
+	iph->protocol = IPPROTO_IPIP;
+	iph->check = 0;
+	iph->tos = 0;
+	iph->tot_len = bpf_htons(payload_len + sizeof(*iph));
+	iph->daddr = tnl->daddr.v4;
+	iph->saddr = tnl->saddr.v4;
+	iph->ttl = 8;
+
+	next_iph = (__u16 *)iph;
+#pragma clang loop unroll(disable)
+	for (i = 0; i < sizeof(*iph) >> 1; i++)
+		csum += *next_iph++;
+
+	iph->check = ~((csum & 0xffff) + (csum >> 16));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+static __always_inline int handle_ipv6(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	struct ipv6hdr *ip6h = data + sizeof(struct ethhdr);
+	__u16 payload_len;
+	struct vip vip = {};
+	int dport;
+
+	if (ip6h + 1 > data_end)
+		return XDP_DROP;
+
+	dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = ip6h->nexthdr;
+	vip.family = AF_INET6;
+	memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr));
+	vip.dport = dport;
+	payload_len = ip6h->payload_len;
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v6-in-v6 */
+	if (!tnl || tnl->family != AF_INET6)
+		return XDP_PASS;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr)))
+		return XDP_DROP;
+
+	data = (void *)(long)xdp->data;
+	data_end = (void *)(long)xdp->data_end;
+
+	new_eth = data;
+	ip6h = data + sizeof(*new_eth);
+	old_eth = data + sizeof(*ip6h);
+
+	if (new_eth + 1 > data_end || old_eth + 1 > data_end ||
+	    ip6h + 1 > data_end)
+		return XDP_DROP;
+
+	set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6));
+
+	ip6h->version = 6;
+	ip6h->priority = 0;
+	memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
+	ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + sizeof(*ip6h));
+	ip6h->nexthdr = IPPROTO_IPV6;
+	ip6h->hop_limit = 8;
+	memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6));
+	memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+SEC("xdp_tx_iptunnel")
+int _xdp_tx_iptunnel(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eth = data;
+	__u16 h_proto;
+
+	if (eth + 1 > data_end)
+		return XDP_DROP;
+
+	h_proto = eth->h_proto;
+
+	if (h_proto == bpf_htons(ETH_P_IP))
+		return handle_ipv4(xdp);
+	else if (h_proto == bpf_htons(ETH_P_IPV6))
+
+		return handle_ipv6(xdp);
+	else
+		return XDP_DROP;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/test_xdp_noinline.c

@@ -163,52 +163,66 @@ struct lb_stats {
 	__u64 v1;
 };
 
-struct bpf_map_def __attribute__ ((section("maps"), used)) vip_map = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	struct vip_definition *key;
+	struct vip_meta *value;
+} vip_map SEC(".maps") = {
 	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(struct vip_definition),
-	.value_size = sizeof(struct vip_meta),
 	.max_entries = 512,
-	.map_flags = 0,
 };
 
-struct bpf_map_def __attribute__ ((section("maps"), used)) lru_cache = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 map_flags;
+	struct flow_key *key;
+	struct real_pos_lru *value;
+} lru_cache SEC(".maps") = {
 	.type = BPF_MAP_TYPE_LRU_HASH,
-	.key_size = sizeof(struct flow_key),
-	.value_size = sizeof(struct real_pos_lru),
 	.max_entries = 300,
 	.map_flags = 1U << 1,
 };
 
-struct bpf_map_def __attribute__ ((section("maps"), used)) ch_rings = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	__u32 *value;
+} ch_rings SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
 	.max_entries = 12 * 655,
-	.map_flags = 0,
 };
 
-struct bpf_map_def __attribute__ ((section("maps"), used)) reals = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct real_definition *value;
+} reals SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct real_definition),
 	.max_entries = 40,
-	.map_flags = 0,
 };
 
-struct bpf_map_def __attribute__ ((section("maps"), used)) stats = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct lb_stats *value;
+} stats SEC(".maps") = {
 	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct lb_stats),
 	.max_entries = 515,
-	.map_flags = 0,
 };
 
-struct bpf_map_def __attribute__ ((section("maps"), used)) ctl_array = {
+struct {
+	__u32 type;
+	__u32 max_entries;
+	__u32 *key;
+	struct ctl_value *value;
+} ctl_array SEC(".maps") = {
 	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(struct ctl_value),
 	.max_entries = 16,
-	.map_flags = 0,
 };
 
 struct eth_hdr {

tools/testing/selftests/bpf/test_btf.c

@@ -4016,13 +4016,9 @@ struct btf_file_test {
 };
 
 static struct btf_file_test file_tests[] = {
-{
+	{ .file = "test_btf_haskv.o", },
-	.file = "test_btf_haskv.o",
+	{ .file = "test_btf_newkv.o", },
-},
+	{ .file = "test_btf_nokv.o", .btf_kv_notfound = true, },
-{
-	.file = "test_btf_nokv.o",
-	.btf_kv_notfound = true,
-},
 };
 
 static int do_test_file(unsigned int test_num)

tools/testing/selftests/bpf/test_select_reuseport.c

@@ -523,6 +523,58 @@ static void test_pass_on_err(int type, sa_family_t family)
 	printf("OK\n");
 }
 
+static void test_detach_bpf(int type, sa_family_t family)
+{
+#ifdef SO_DETACH_REUSEPORT_BPF
+	__u32 nr_run_before = 0, nr_run_after = 0, tmp, i;
+	struct epoll_event ev;
+	int cli_fd, err, nev;
+	struct cmd cmd = {};
+	int optvalue = 0;
+
+	printf("%s: ", __func__);
+	err = setsockopt(sk_fds[0], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF,
+			 &optvalue, sizeof(optvalue));
+	CHECK(err == -1, "setsockopt(SO_DETACH_REUSEPORT_BPF)",
+	      "err:%d errno:%d\n", err, errno);
+
+	err = setsockopt(sk_fds[1], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF,
+			 &optvalue, sizeof(optvalue));
+	CHECK(err == 0 || errno != ENOENT, "setsockopt(SO_DETACH_REUSEPORT_BPF)",
+	      "err:%d errno:%d\n", err, errno);
+
+	for (i = 0; i < NR_RESULTS; i++) {
+		err = bpf_map_lookup_elem(result_map, &i, &tmp);
+		CHECK(err == -1, "lookup_elem(result_map)",
+		      "i:%u err:%d errno:%d\n", i, err, errno);
+		nr_run_before += tmp;
+	}
+
+	cli_fd = send_data(type, family, &cmd, sizeof(cmd), PASS);
+	nev = epoll_wait(epfd, &ev, 1, 5);
+	CHECK(nev <= 0, "nev <= 0",
+	      "nev:%d expected:1 type:%d family:%d data:(0, 0)\n",
+	      nev,  type, family);
+
+	for (i = 0; i < NR_RESULTS; i++) {
+		err = bpf_map_lookup_elem(result_map, &i, &tmp);
+		CHECK(err == -1, "lookup_elem(result_map)",
+		      "i:%u err:%d errno:%d\n", i, err, errno);
+		nr_run_after += tmp;
+	}
+
+	CHECK(nr_run_before != nr_run_after,
+	      "nr_run_before != nr_run_after",
+	      "nr_run_before:%u nr_run_after:%u\n",
+	      nr_run_before, nr_run_after);
+
+	printf("OK\n");
+	close(cli_fd);
+#else
+	printf("%s: SKIP\n", __func__);
+#endif
+}
+
 static void prepare_sk_fds(int type, sa_family_t family, bool inany)
 {
 	const int first = REUSEPORT_ARRAY_SIZE - 1;
@@ -664,6 +716,8 @@ static void test_all(void)
 			test_pass(type, family);
 			test_syncookie(type, family);
 			test_pass_on_err(type, family);
+			/* Must be the last test */
+			test_detach_bpf(type, family);
 
 			cleanup_per_test();
 			printf("\n");

tools/testing/selftests/bpf/test_socket_cookie.c

@@ -18,6 +18,11 @@
 #define CG_PATH			"/foo"
 #define SOCKET_COOKIE_PROG	"./socket_cookie_prog.o"
 
+struct socket_cookie {
+	__u64 cookie_key;
+	__u32 cookie_value;
+};
+
 static int start_server(void)
 {
 	struct sockaddr_in6 addr;
@@ -89,8 +94,7 @@ static int validate_map(struct bpf_map *map, int client_fd)
 	__u32 cookie_expected_value;
 	struct sockaddr_in6 addr;
 	socklen_t len = sizeof(addr);
-	__u32 cookie_value;
+	struct socket_cookie val;
-	__u64 cookie_key;
 	int err = 0;
 	int map_fd;
 
@@ -101,17 +105,7 @@ static int validate_map(struct bpf_map *map, int client_fd)
 
 	map_fd = bpf_map__fd(map);
 
-	err = bpf_map_get_next_key(map_fd, NULL, &cookie_key);
+	err = bpf_map_lookup_elem(map_fd, &client_fd, &val);
-	if (err) {
-		log_err("Can't get cookie key from map");
-		goto out;
-	}
-
-	err = bpf_map_lookup_elem(map_fd, &cookie_key, &cookie_value);
-	if (err) {
-		log_err("Can't get cookie value from map");
-		goto out;
-	}
 
 	err = getsockname(client_fd, (struct sockaddr *)&addr, &len);
 	if (err) {
@@ -120,8 +114,8 @@ static int validate_map(struct bpf_map *map, int client_fd)
 	}
 
 	cookie_expected_value = (ntohs(addr.sin6_port) << 8) | 0xFF;
-	if (cookie_value != cookie_expected_value) {
+	if (val.cookie_value != cookie_expected_value) {
-		log_err("Unexpected value in map: %x != %x", cookie_value,
+		log_err("Unexpected value in map: %x != %x", val.cookie_value,
 			cookie_expected_value);
 		goto err;
 	}

tools/testing/selftests/bpf/test_verifier.c

@@ -234,10 +234,10 @@ static void bpf_fill_scale1(struct bpf_test *self)
 		insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6,
 					-8 * (k % 64 + 1));
 	}
-	/* every jump adds 1 step to insn_processed, so to stay exactly
+	/* is_state_visited() doesn't allocate state for pruning for every jump.
-	 * within 1m limit add MAX_TEST_INSNS - MAX_JMP_SEQ - 1 MOVs and 1 EXIT
+	 * Hence multiply jmps by 4 to accommodate that heuristic
 	 */
-	while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1)
+	while (i < MAX_TEST_INSNS - MAX_JMP_SEQ * 4)
 		insn[i++] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 42);
 	insn[i] = BPF_EXIT_INSN();
 	self->prog_len = i + 1;
@@ -266,10 +266,7 @@ static void bpf_fill_scale2(struct bpf_test *self)
 		insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6,
 					-8 * (k % (64 - 4 * FUNC_NEST) + 1));
 	}
-	/* every jump adds 1 step to insn_processed, so to stay exactly
+	while (i < MAX_TEST_INSNS - MAX_JMP_SEQ * 4)
-	 * within 1m limit add MAX_TEST_INSNS - MAX_JMP_SEQ - 1 MOVs and 1 EXIT
-	 */
-	while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1)
 		insn[i++] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 42);
 	insn[i] = BPF_EXIT_INSN();
 	self->prog_len = i + 1;

tools/testing/selftests/bpf/verifier/calls.c

@@ -215,9 +215,11 @@
 	BPF_MOV64_IMM(BPF_REG_0, 3),
 	BPF_JMP_IMM(BPF_JA, 0, 0, -6),
 	},
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr = "back-edge from insn",
+	.errstr_unpriv = "back-edge from insn",
-	.result = REJECT,
+	.result_unpriv = REJECT,
+	.result = ACCEPT,
+	.retval = 1,
 },
 {
 	"calls: conditional call 4",
@@ -250,22 +252,24 @@
 	BPF_MOV64_IMM(BPF_REG_0, 3),
 	BPF_EXIT_INSN(),
 	},
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "back-edge from insn",
+	.result = ACCEPT,
-	.result = REJECT,
+	.retval = 1,
 },
 {
 	"calls: conditional call 6",
 	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -2),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -3),
 	BPF_EXIT_INSN(),
 	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct __sk_buff, mark)),
 	BPF_EXIT_INSN(),
 	},
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "back-edge from insn",
+	.errstr = "infinite loop detected",
 	.result = REJECT,
 },
 {

tools/testing/selftests/bpf/verifier/cfg.c

@@ -41,7 +41,8 @@
 	BPF_JMP_IMM(BPF_JA, 0, 0, -1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr = "back-edge",
+	.errstr = "unreachable insn 1",
+	.errstr_unpriv = "back-edge",
 	.result = REJECT,
 },
 {
@@ -53,18 +54,20 @@
 	BPF_JMP_IMM(BPF_JA, 0, 0, -4),
 	BPF_EXIT_INSN(),
 	},
-	.errstr = "back-edge",
+	.errstr = "unreachable insn 4",
+	.errstr_unpriv = "back-edge",
 	.result = REJECT,
 },
 {
 	"conditional loop",
 	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
 	BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -3),
 	BPF_EXIT_INSN(),
 	},
-	.errstr = "back-edge",
+	.errstr = "infinite loop detected",
+	.errstr_unpriv = "back-edge",
 	.result = REJECT,
 },

tools/testing/selftests/bpf/verifier/direct_packet_access.c

@@ -511,7 +511,8 @@
 		    offsetof(struct __sk_buff, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
 		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_IMM(BPF_REG_0, 0xffffffff),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, mark)),
 	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
 	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffff),

tools/testing/selftests/bpf/verifier/helper_access_var_len.c

@@ -29,9 +29,9 @@
 {
 	"helper access to variable memory: stack, bitwise AND, zero included",
 	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_2, 16),
 	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
 	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
@@ -46,9 +46,9 @@
 {
 	"helper access to variable memory: stack, bitwise AND + JMP, wrong max",
 	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_2, 16),
 	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
 	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 65),
@@ -122,9 +122,9 @@
 {
 	"helper access to variable memory: stack, JMP, bounds + offset",
 	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_2, 16),
 	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
 	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 5),
@@ -143,9 +143,9 @@
 {
 	"helper access to variable memory: stack, JMP, wrong max",
 	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_2, 16),
 	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
 	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 65, 4),
@@ -163,9 +163,9 @@
 {
 	"helper access to variable memory: stack, JMP, no max check",
 	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_2, 16),
 	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
 	BPF_MOV64_IMM(BPF_REG_4, 0),
@@ -183,9 +183,9 @@
 {
 	"helper access to variable memory: stack, JMP, no min check",
 	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_2, 16),
 	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
 	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 3),
@@ -201,9 +201,9 @@
 {
 	"helper access to variable memory: stack, JMP (signed), no min check",
 	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_2, 16),
 	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
 	BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, 64, 3),
@@ -244,6 +244,7 @@
 {
 	"helper access to variable memory: map, JMP, wrong max",
 	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8),
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
 	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
@@ -251,7 +252,7 @@
 	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
 	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
 	BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) + 1, 4),
@@ -262,7 +263,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.fixup_map_hash_48b = { 3 },
+	.fixup_map_hash_48b = { 4 },
 	.errstr = "invalid access to map value, value_size=48 off=0 size=49",
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -296,6 +297,7 @@
 {
 	"helper access to variable memory: map adjusted, JMP, wrong max",
 	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8),
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
 	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
@@ -304,7 +306,7 @@
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 20),
-	BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
 	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
 	BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) - 19, 4),
@@ -315,7 +317,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.fixup_map_hash_48b = { 3 },
+	.fixup_map_hash_48b = { 4 },
 	.errstr = "R1 min value is outside of the array range",
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -337,8 +339,8 @@
 {
 	"helper access to variable memory: size > 0 not allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)",
 	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
 	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 1),
 	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
 	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
@@ -562,6 +564,7 @@
 {
 	"helper access to variable memory: 8 bytes leak",
 	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
@@ -572,7 +575,6 @@
 	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
 	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
 	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_MOV64_IMM(BPF_REG_2, 1),
 	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
 	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63),

tools/testing/selftests/bpf/verifier/loops1.c

@@ -0,0 +1,161 @@
+{
+	"bounded loop, count to 4",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.retval = 4,
+},
+{
+	"bounded loop, count to 20",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
+	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 20, -2),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"bounded loop, count from positive unknown to 4",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_0, 0, 2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.retval = 4,
+},
+{
+	"bounded loop, count from totally unknown to 4",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"bounded loop, count to 4 with equality",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 4, -2),
+		BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"bounded loop, start in the middle",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_JMP_A(1),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+		BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2),
+		BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "back-edge",
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.retval = 4,
+},
+{
+	"bounded loop containing a forward jump",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+		BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_0, 0),
+		BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -3),
+		BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.retval = 4,
+},
+{
+	"bounded loop that jumps out rather than in",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_6, 0),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
+	BPF_JMP_IMM(BPF_JGT, BPF_REG_6, 10000, 2),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	BPF_JMP_A(-4),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"infinite loop after a conditional jump",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 5),
+	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, 2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+	BPF_JMP_A(-2),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "program is too large",
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"bounded recursion",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+	BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 4, 1),
+	BPF_EXIT_INSN(),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -5),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "back-edge",
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"infinite loop in two jumps",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_JMP_A(0),
+	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "loop detected",
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"infinite loop: three-jump trick",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, 1),
+	BPF_EXIT_INSN(),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, 1),
+	BPF_EXIT_INSN(),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, -11),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "loop detected",
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},

tools/testing/selftests/bpf/verifier/prevent_map_lookup.c

@@ -28,21 +28,6 @@
 	.errstr = "cannot pass map_type 18 into func bpf_map_lookup_elem",
 	.prog_type = BPF_PROG_TYPE_SOCK_OPS,
 },
-{
-	"prevent map lookup in xskmap",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_xskmap = { 3 },
-	.result = REJECT,
-	.errstr = "cannot pass map_type 17 into func bpf_map_lookup_elem",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
 {
 	"prevent map lookup in stack trace",
 	.insns = {