diff --git a/MAINTAINERS b/MAINTAINERS
index 64f659d8346c..2854d42288e9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3108,9 +3108,9 @@ S:	Maintained
 F:	arch/riscv/net/
 
 BPF JIT for S390
+M:	Ilya Leoshkevich <iii@linux.ibm.com>
 M:	Heiko Carstens <heiko.carstens@de.ibm.com>
 M:	Vasily Gorbik <gor@linux.ibm.com>
-M:	Christian Borntraeger <borntraeger@de.ibm.com>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
 S:	Maintained
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 6d944369ca87..ff65d22cf336 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -747,7 +747,7 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 	return size <= size_default && (size & (size - 1)) == 0;
 }
 
-#define bpf_ctx_wide_store_ok(off, size, type, field)			\
+#define bpf_ctx_wide_access_ok(off, size, type, field)			\
 	(size == sizeof(__u64) &&					\
 	off >= offsetof(type, field) &&					\
 	off + sizeof(__u64) <= offsetofend(type, field) &&		\
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6f68438aa4ed..81be929b89fc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3248,7 +3248,7 @@ struct bpf_sock_addr {
 	__u32 user_ip4;		/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 user_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
+	__u32 user_ip6[4];	/* Allows 1,2,4,8-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__u32 user_port;	/* Allows 4-byte read and write.
@@ -3260,7 +3260,7 @@ struct bpf_sock_addr {
 	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
+	__u32 msg_src_ip6[4];	/* Allows 1,2,4,8-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__bpf_md_ptr(struct bpf_sock *, sk);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 546ebee39e2a..5fcc7a17eb5a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1073,11 +1073,18 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
 				 !btf_type_is_var(size_type)))
 			return NULL;
 
-		size = btf->resolved_sizes[size_type_id];
 		size_type_id = btf->resolved_ids[size_type_id];
 		size_type = btf_type_by_id(btf, size_type_id);
 		if (btf_type_nosize_or_null(size_type))
 			return NULL;
+		else if (btf_type_has_size(size_type))
+			size = size_type->size;
+		else if (btf_type_is_array(size_type))
+			size = btf->resolved_sizes[size_type_id];
+		else if (btf_type_is_ptr(size_type))
+			size = sizeof(void *);
+		else
+			return NULL;
 	}
 
 	*type_id = size_type_id;
@@ -1602,7 +1609,6 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 	const struct btf_type *next_type;
 	u32 next_type_id = t->type;
 	struct btf *btf = env->btf;
-	u32 next_type_size = 0;
 
 	next_type = btf_type_by_id(btf, next_type_id);
 	if (!next_type || btf_type_is_resolve_source_only(next_type)) {
@@ -1620,7 +1626,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 	 * save us a few type-following when we use it later (e.g. in
 	 * pretty print).
 	 */
-	if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) {
+	if (!btf_type_id_size(btf, &next_type_id, NULL)) {
 		if (env_type_is_resolved(env, next_type_id))
 			next_type = btf_type_id_resolve(btf, &next_type_id);
 
@@ -1633,7 +1639,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 		}
 	}
 
-	env_stack_pop_resolved(env, next_type_id, next_type_size);
+	env_stack_pop_resolved(env, next_type_id, 0);
 
 	return 0;
 }
@@ -1645,7 +1651,6 @@ static int btf_var_resolve(struct btf_verifier_env *env,
 	const struct btf_type *t = v->t;
 	u32 next_type_id = t->type;
 	struct btf *btf = env->btf;
-	u32 next_type_size;
 
 	next_type = btf_type_by_id(btf, next_type_id);
 	if (!next_type || btf_type_is_resolve_source_only(next_type)) {
@@ -1675,12 +1680,12 @@ static int btf_var_resolve(struct btf_verifier_env *env,
 	 * forward types or similar that would resolve to size of
 	 * zero is allowed.
 	 */
-	if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) {
+	if (!btf_type_id_size(btf, &next_type_id, NULL)) {
 		btf_verifier_log_type(env, v->t, "Invalid type_id");
 		return -EINVAL;
 	}
 
-	env_stack_pop_resolved(env, next_type_id, next_type_size);
+	env_stack_pop_resolved(env, next_type_id, 0);
 
 	return 0;
 }
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a2e763703c30..5900cbb966b1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1519,9 +1519,9 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 			return -EFAULT;
 		}
 		*stack_mask |= 1ull << spi;
-	} else if (class == BPF_STX) {
+	} else if (class == BPF_STX || class == BPF_ST) {
 		if (*reg_mask & dreg)
-			/* stx shouldn't be using _scalar_ dst_reg
+			/* stx & st shouldn't be using _scalar_ dst_reg
 			 * to access memory. It means backtracking
 			 * encountered a case of pointer subtraction.
 			 */
@@ -1540,7 +1540,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 		if (!(*stack_mask & (1ull << spi)))
 			return 0;
 		*stack_mask &= ~(1ull << spi);
-		*reg_mask |= sreg;
+		if (class == BPF_STX)
+			*reg_mask |= sreg;
 	} else if (class == BPF_JMP || class == BPF_JMP32) {
 		if (opcode == BPF_CALL) {
 			if (insn->src_reg == BPF_PSEUDO_CALL)
@@ -1569,10 +1570,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 		if (mode == BPF_IND || mode == BPF_ABS)
 			/* to be analyzed */
 			return -ENOTSUPP;
-	} else if (class == BPF_ST) {
-		if (*reg_mask & dreg)
-			/* likely pointer subtraction */
-			return -ENOTSUPP;
 	}
 	return 0;
 }
@@ -6106,11 +6103,13 @@ static int check_return_code(struct bpf_verifier_env *env)
 		if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
 		    env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG)
 			range = tnum_range(1, 1);
+		break;
 	case BPF_PROG_TYPE_CGROUP_SKB:
 		if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) {
 			range = tnum_range(0, 3);
 			enforce_attach_type_range = tnum_range(2, 3);
 		}
+		break;
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 	case BPF_PROG_TYPE_SOCK_OPS:
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
diff --git a/net/core/filter.c b/net/core/filter.c
index 47f6386fb17a..0f6854ccf894 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6884,20 +6884,30 @@ static bool sock_addr_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4):
 	case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0],
 				msg_src_ip6[3]):
-		/* Only narrow read access allowed for now. */
 		if (type == BPF_READ) {
 			bpf_ctx_record_field_size(info, size_default);
+
+			if (bpf_ctx_wide_access_ok(off, size,
+						   struct bpf_sock_addr,
+						   user_ip6))
+				return true;
+
+			if (bpf_ctx_wide_access_ok(off, size,
+						   struct bpf_sock_addr,
+						   msg_src_ip6))
+				return true;
+
 			if (!bpf_ctx_narrow_access_ok(off, size, size_default))
 				return false;
 		} else {
-			if (bpf_ctx_wide_store_ok(off, size,
-						  struct bpf_sock_addr,
-						  user_ip6))
+			if (bpf_ctx_wide_access_ok(off, size,
+						   struct bpf_sock_addr,
+						   user_ip6))
 				return true;
 
-			if (bpf_ctx_wide_store_ok(off, size,
-						  struct bpf_sock_addr,
-						  msg_src_ip6))
+			if (bpf_ctx_wide_access_ok(off, size,
+						   struct bpf_sock_addr,
+						   msg_src_ip6))
 				return true;
 
 			if (size != size_default)
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 20c91f02d3d8..83de74ca729a 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -87,21 +87,20 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 	struct netdev_bpf bpf;
 	int err = 0;
 
+	ASSERT_RTNL();
+
 	force_zc = flags & XDP_ZEROCOPY;
 	force_copy = flags & XDP_COPY;
 
 	if (force_zc && force_copy)
 		return -EINVAL;
 
-	rtnl_lock();
-	if (xdp_get_umem_from_qid(dev, queue_id)) {
-		err = -EBUSY;
-		goto out_rtnl_unlock;
-	}
+	if (xdp_get_umem_from_qid(dev, queue_id))
+		return -EBUSY;
 
 	err = xdp_reg_umem_at_qid(dev, umem, queue_id);
 	if (err)
-		goto out_rtnl_unlock;
+		return err;
 
 	umem->dev = dev;
 	umem->queue_id = queue_id;
@@ -110,7 +109,7 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 
 	if (force_copy)
 		/* For copy-mode, we are done. */
-		goto out_rtnl_unlock;
+		return 0;
 
 	if (!dev->netdev_ops->ndo_bpf ||
 	    !dev->netdev_ops->ndo_xsk_async_xmit) {
@@ -125,7 +124,6 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
 	if (err)
 		goto err_unreg_umem;
-	rtnl_unlock();
 
 	umem->zc = true;
 	return 0;
@@ -135,8 +133,6 @@ err_unreg_umem:
 		err = 0; /* fallback to copy mode */
 	if (err)
 		xdp_clear_umem_at_qid(dev, queue_id);
-out_rtnl_unlock:
-	rtnl_unlock();
 	return err;
 }
 
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index d4d6f10aa936..59b57d708697 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -240,6 +240,9 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 
 	mutex_lock(&xs->mutex);
 
+	if (xs->queue_id >= xs->dev->real_num_tx_queues)
+		goto out;
+
 	while (xskq_peek_desc(xs->tx, &desc)) {
 		char *buffer;
 		u64 addr;
@@ -250,12 +253,6 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 			goto out;
 		}
 
-		if (xskq_reserve_addr(xs->umem->cq))
-			goto out;
-
-		if (xs->queue_id >= xs->dev->real_num_tx_queues)
-			goto out;
-
 		len = desc.len;
 		skb = sock_alloc_send_skb(sk, len, 1, &err);
 		if (unlikely(!skb)) {
@@ -267,7 +264,7 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 		addr = desc.addr;
 		buffer = xdp_umem_get_data(xs->umem, addr);
 		err = skb_store_bits(skb, 0, buffer, len);
-		if (unlikely(err)) {
+		if (unlikely(err) || xskq_reserve_addr(xs->umem->cq)) {
 			kfree_skb(skb);
 			goto out;
 		}
@@ -433,6 +430,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY))
 		return -EINVAL;
 
+	rtnl_lock();
 	mutex_lock(&xs->mutex);
 	if (xs->state != XSK_READY) {
 		err = -EBUSY;
@@ -518,6 +516,7 @@ out_unlock:
 		xs->state = XSK_BOUND;
 out_release:
 	mutex_unlock(&xs->mutex);
+	rtnl_unlock();
 	return err;
 }
 
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index f90daadfbc89..1d9be26b4edd 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -284,7 +284,7 @@ $(obj)/%.o: $(src)/%.c
 	$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
 		-I$(srctree)/tools/testing/selftests/bpf/ \
 		-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
-		-D__TARGET_ARCH_$(ARCH) -Wno-compare-distinct-pointer-types \
+		-D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \
 		-Wno-address-of-packed-member -Wno-tautological-compare \
 		-Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 3ef0d9051e10..7031a4bf87a0 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -74,6 +74,7 @@ static const char * const prog_type_name[] = {
 	[BPF_PROG_TYPE_SK_REUSEPORT]		= "sk_reuseport",
 	[BPF_PROG_TYPE_FLOW_DISSECTOR]		= "flow_dissector",
 	[BPF_PROG_TYPE_CGROUP_SYSCTL]		= "cgroup_sysctl",
+	[BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE]	= "raw_tracepoint_writable",
 	[BPF_PROG_TYPE_CGROUP_SOCKOPT]		= "cgroup_sockopt",
 };
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f506c68b2612..1f61374fcf81 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3245,7 +3245,7 @@ struct bpf_sock_addr {
 	__u32 user_ip4;		/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 user_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
+	__u32 user_ip6[4];	/* Allows 1,2,4,8-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__u32 user_port;	/* Allows 4-byte read and write.
@@ -3257,7 +3257,7 @@ struct bpf_sock_addr {
 	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
+	__u32 msg_src_ip6[4];	/* Allows 1,2,4,8-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__bpf_md_ptr(struct bpf_sock *, sk);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ed07789b3e62..794dd5064ae8 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4126,8 +4126,8 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
 	}
 	attr.size = sizeof(attr);
 	attr.type = type;
-	attr.config1 = (uint64_t)(void *)name; /* kprobe_func or uprobe_path */
-	attr.config2 = offset;		       /* kprobe_addr or probe_offset */
+	attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */
+	attr.config2 = offset;		 /* kprobe_addr or probe_offset */
 
 	/* pid filter is meaningful only for uprobes */
 	pfd = syscall(__NR_perf_event_open, &attr,
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index b33740221b7e..5007b5d4fd2c 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -517,7 +517,8 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 		err = -errno;
 		goto out_socket;
 	}
-	strncpy(xsk->ifname, ifname, IFNAMSIZ);
+	strncpy(xsk->ifname, ifname, IFNAMSIZ - 1);
+	xsk->ifname[IFNAMSIZ - 1] = '\0';
 
 	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
 	if (err)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 2620406a53ec..11c9c62c3362 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
+include ../../../../scripts/Kbuild.include
+include ../../../scripts/Makefile.arch
 
 LIBDIR := ../../../lib
 BPFDIR := $(LIBDIR)/bpf
@@ -81,13 +83,14 @@ all: $(TEST_CUSTOM_PROGS)
 $(OUTPUT)/urandom_read: $(OUTPUT)/%: %.c
 	$(CC) -o $@ $< -Wl,--build-id
 
-$(OUTPUT)/test_maps: map_tests/*.c
+$(OUTPUT)/test_stub.o: test_stub.c
+	$(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) -c -o $@ $<
 
 BPFOBJ := $(OUTPUT)/libbpf.a
 
-$(TEST_GEN_PROGS): test_stub.o $(BPFOBJ)
+$(TEST_GEN_PROGS): $(OUTPUT)/test_stub.o $(BPFOBJ)
 
-$(TEST_GEN_PROGS_EXTENDED): test_stub.o $(OUTPUT)/libbpf.a
+$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(OUTPUT)/libbpf.a
 
 $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
 $(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c
@@ -138,7 +141,8 @@ CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \
 
 CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
 	      $(CLANG_SYS_INCLUDES) \
-	      -Wno-compare-distinct-pointer-types
+	      -Wno-compare-distinct-pointer-types \
+	      -D__TARGET_ARCH_$(SRCARCH)
 
 $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
 $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
@@ -172,6 +176,7 @@ endif
 endif
 
 TEST_PROGS_CFLAGS := -I. -I$(OUTPUT)
+TEST_MAPS_CFLAGS := -I. -I$(OUTPUT)
 TEST_VERIFIER_CFLAGS := -I. -I$(OUTPUT) -Iverifier
 
 ifneq ($(SUBREG_CODEGEN),)
@@ -180,12 +185,12 @@ TEST_CUSTOM_PROGS += $(ALU32_BUILD_DIR)/test_progs_32
 $(ALU32_BUILD_DIR):
 	mkdir -p $@
 
-$(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read
+$(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read | $(ALU32_BUILD_DIR)
 	cp $< $@
 
 $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\
-						$(ALU32_BUILD_DIR) \
-						$(ALU32_BUILD_DIR)/urandom_read
+						$(ALU32_BUILD_DIR)/urandom_read \
+						| $(ALU32_BUILD_DIR)
 	$(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) \
 		-o $(ALU32_BUILD_DIR)/test_progs_32 \
 		test_progs.c test_stub.c trace_helpers.c prog_tests/*.c \
@@ -194,10 +199,10 @@ $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\
 $(ALU32_BUILD_DIR)/test_progs_32: $(PROG_TESTS_H)
 $(ALU32_BUILD_DIR)/test_progs_32: prog_tests/*.c
 
-$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR) \
-					$(ALU32_BUILD_DIR)/test_progs_32
-	$(CLANG) $(CLANG_FLAGS) \
-		 -O2 -target bpf -emit-llvm -c $< -o - |      \
+$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR)/test_progs_32 \
+					| $(ALU32_BUILD_DIR)
+	($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \
+		echo "clang failed") | \
 	$(LLC) -march=bpf -mattr=+alu32 -mcpu=$(CPU) $(LLC_FLAGS) \
 		-filetype=obj -o $@
 ifeq ($(DWARF2BTF),y)
@@ -208,32 +213,30 @@ endif
 # Have one program compiled without "-target bpf" to test whether libbpf loads
 # it successfully
 $(OUTPUT)/test_xdp.o: progs/test_xdp.c
-	$(CLANG) $(CLANG_FLAGS) \
-		-O2 -emit-llvm -c $< -o - | \
+	($(CLANG) $(CLANG_FLAGS) -O2 -emit-llvm -c $< -o - || \
+		echo "clang failed") | \
 	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
 ifeq ($(DWARF2BTF),y)
 	$(BTF_PAHOLE) -J $@
 endif
 
 $(OUTPUT)/%.o: progs/%.c
-	$(CLANG) $(CLANG_FLAGS) \
-		 -O2 -target bpf -emit-llvm -c $< -o - |      \
+	($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \
+		echo "clang failed") | \
 	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
 ifeq ($(DWARF2BTF),y)
 	$(BTF_PAHOLE) -J $@
 endif
 
-PROG_TESTS_H := $(OUTPUT)/prog_tests/tests.h
-test_progs.c: $(PROG_TESTS_H)
-$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS)
-$(OUTPUT)/test_progs: prog_tests/*.c
-
 PROG_TESTS_DIR = $(OUTPUT)/prog_tests
 $(PROG_TESTS_DIR):
 	mkdir -p $@
-
+PROG_TESTS_H := $(PROG_TESTS_DIR)/tests.h
 PROG_TESTS_FILES := $(wildcard prog_tests/*.c)
-$(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES)
+test_progs.c: $(PROG_TESTS_H)
+$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS)
+$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_H) $(PROG_TESTS_FILES)
+$(PROG_TESTS_H): $(PROG_TESTS_FILES) | $(PROG_TESTS_DIR)
 	$(shell ( cd prog_tests/; \
 		  echo '/* Generated header, do not edit */'; \
 		  echo '#ifdef DECLARE'; \
@@ -246,15 +249,15 @@ $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES)
 		  echo '#endif' \
 		 ) > $(PROG_TESTS_H))
 
-TEST_MAPS_CFLAGS := -I. -I$(OUTPUT)
 MAP_TESTS_DIR = $(OUTPUT)/map_tests
 $(MAP_TESTS_DIR):
 	mkdir -p $@
 MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h
+MAP_TESTS_FILES := $(wildcard map_tests/*.c)
 test_maps.c: $(MAP_TESTS_H)
 $(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS)
-MAP_TESTS_FILES := $(wildcard map_tests/*.c)
-$(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES)
+$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_H) $(MAP_TESTS_FILES)
+$(MAP_TESTS_H): $(MAP_TESTS_FILES) | $(MAP_TESTS_DIR)
 	$(shell ( cd map_tests/; \
 		  echo '/* Generated header, do not edit */'; \
 		  echo '#ifdef DECLARE'; \
@@ -267,16 +270,15 @@ $(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES)
 		  echo '#endif' \
 		 ) > $(MAP_TESTS_H))
 
-VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h
-test_verifier.c: $(VERIFIER_TESTS_H)
-$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS)
-
 VERIFIER_TESTS_DIR = $(OUTPUT)/verifier
 $(VERIFIER_TESTS_DIR):
 	mkdir -p $@
-
+VERIFIER_TESTS_H := $(VERIFIER_TESTS_DIR)/tests.h
 VERIFIER_TEST_FILES := $(wildcard verifier/*.c)
-$(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES)
+test_verifier.c: $(VERIFIER_TESTS_H)
+$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS)
+$(OUTPUT)/test_verifier: test_verifier.c $(VERIFIER_TESTS_H)
+$(VERIFIER_TESTS_H): $(VERIFIER_TEST_FILES) | $(VERIFIER_TESTS_DIR)
 	$(shell ( cd verifier/; \
 		  echo '/* Generated header, do not edit */'; \
 		  echo '#ifdef FILL_ARRAY'; \
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 5a3d92c8bec8..f804f210244e 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -315,8 +315,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 #if defined(__TARGET_ARCH_x86)
 	#define bpf_target_x86
 	#define bpf_target_defined
-#elif defined(__TARGET_ARCH_s930x)
-	#define bpf_target_s930x
+#elif defined(__TARGET_ARCH_s390)
+	#define bpf_target_s390
 	#define bpf_target_defined
 #elif defined(__TARGET_ARCH_arm)
 	#define bpf_target_arm
@@ -341,8 +341,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 #ifndef bpf_target_defined
 #if defined(__x86_64__)
 	#define bpf_target_x86
-#elif defined(__s390x__)
-	#define bpf_target_s930x
+#elif defined(__s390__)
+	#define bpf_target_s390
 #elif defined(__arm__)
 	#define bpf_target_arm
 #elif defined(__aarch64__)
@@ -358,6 +358,7 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 
 #if defined(bpf_target_x86)
 
+#ifdef __KERNEL__
 #define PT_REGS_PARM1(x) ((x)->di)
 #define PT_REGS_PARM2(x) ((x)->si)
 #define PT_REGS_PARM3(x) ((x)->dx)
@@ -368,19 +369,49 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 #define PT_REGS_RC(x) ((x)->ax)
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->ip)
+#else
+#ifdef __i386__
+/* i386 kernel is built with -mregparm=3 */
+#define PT_REGS_PARM1(x) ((x)->eax)
+#define PT_REGS_PARM2(x) ((x)->edx)
+#define PT_REGS_PARM3(x) ((x)->ecx)
+#define PT_REGS_PARM4(x) 0
+#define PT_REGS_PARM5(x) 0
+#define PT_REGS_RET(x) ((x)->esp)
+#define PT_REGS_FP(x) ((x)->ebp)
+#define PT_REGS_RC(x) ((x)->eax)
+#define PT_REGS_SP(x) ((x)->esp)
+#define PT_REGS_IP(x) ((x)->eip)
+#else
+#define PT_REGS_PARM1(x) ((x)->rdi)
+#define PT_REGS_PARM2(x) ((x)->rsi)
+#define PT_REGS_PARM3(x) ((x)->rdx)
+#define PT_REGS_PARM4(x) ((x)->rcx)
+#define PT_REGS_PARM5(x) ((x)->r8)
+#define PT_REGS_RET(x) ((x)->rsp)
+#define PT_REGS_FP(x) ((x)->rbp)
+#define PT_REGS_RC(x) ((x)->rax)
+#define PT_REGS_SP(x) ((x)->rsp)
+#define PT_REGS_IP(x) ((x)->rip)
+#endif
+#endif
 
-#elif defined(bpf_target_s390x)
+#elif defined(bpf_target_s390)
 
-#define PT_REGS_PARM1(x) ((x)->gprs[2])
-#define PT_REGS_PARM2(x) ((x)->gprs[3])
-#define PT_REGS_PARM3(x) ((x)->gprs[4])
-#define PT_REGS_PARM4(x) ((x)->gprs[5])
-#define PT_REGS_PARM5(x) ((x)->gprs[6])
-#define PT_REGS_RET(x) ((x)->gprs[14])
-#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->gprs[2])
-#define PT_REGS_SP(x) ((x)->gprs[15])
-#define PT_REGS_IP(x) ((x)->psw.addr)
+/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
+struct pt_regs;
+#define PT_REGS_S390 const volatile user_pt_regs
+#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2])
+#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3])
+#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4])
+#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5])
+#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6])
+#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14])
+/* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11])
+#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2])
+#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
+#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
 
 #elif defined(bpf_target_arm)
 
@@ -397,16 +428,20 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 
 #elif defined(bpf_target_arm64)
 
-#define PT_REGS_PARM1(x) ((x)->regs[0])
-#define PT_REGS_PARM2(x) ((x)->regs[1])
-#define PT_REGS_PARM3(x) ((x)->regs[2])
-#define PT_REGS_PARM4(x) ((x)->regs[3])
-#define PT_REGS_PARM5(x) ((x)->regs[4])
-#define PT_REGS_RET(x) ((x)->regs[30])
-#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->regs[0])
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->pc)
+/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
+struct pt_regs;
+#define PT_REGS_ARM64 const volatile struct user_pt_regs
+#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0])
+#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1])
+#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2])
+#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3])
+#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4])
+#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30])
+/* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29])
+#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0])
+#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
+#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
 
 #elif defined(bpf_target_mips)
 
@@ -452,10 +487,10 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 
 #endif
 
-#ifdef bpf_target_powerpc
+#if defined(bpf_target_powerpc)
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#elif bpf_target_sparc
+#elif defined(bpf_target_sparc)
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
 #else
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index a4686395522c..5ecc267d98b0 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -21,12 +21,6 @@ ssize_t get_base_addr() {
 	return -EINVAL;
 }
 
-#ifdef __x86_64__
-#define SYS_KPROBE_NAME "__x64_sys_nanosleep"
-#else
-#define SYS_KPROBE_NAME "sys_nanosleep"
-#endif
-
 void test_attach_probe(void)
 {
 	const char *kprobe_name = "kprobe/sys_nanosleep";
@@ -84,7 +78,7 @@ void test_attach_probe(void)
 
 	kprobe_link = bpf_program__attach_kprobe(kprobe_prog,
 						 false /* retprobe */,
-						 SYS_KPROBE_NAME);
+						 SYS_NANOSLEEP_KPROBE_NAME);
 	if (CHECK(IS_ERR(kprobe_link), "attach_kprobe",
 		  "err %ld\n", PTR_ERR(kprobe_link))) {
 		kprobe_link = NULL;
@@ -92,7 +86,7 @@ void test_attach_probe(void)
 	}
 	kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog,
 						    true /* retprobe */,
-						    SYS_KPROBE_NAME);
+						    SYS_NANOSLEEP_KPROBE_NAME);
 	if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe",
 		  "err %ld\n", PTR_ERR(kretprobe_link))) {
 		kretprobe_link = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index 3f1ef95865ff..3003fddc0613 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -5,12 +5,6 @@
 #include <sys/socket.h>
 #include <test_progs.h>
 
-#ifdef __x86_64__
-#define SYS_KPROBE_NAME "__x64_sys_nanosleep"
-#else
-#define SYS_KPROBE_NAME "sys_nanosleep"
-#endif
-
 static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 {
 	int cpu_data = *(int *)data, duration = 0;
@@ -56,7 +50,7 @@ void test_perf_buffer(void)
 
 	/* attach kprobe */
 	link = bpf_program__attach_kprobe(prog, false /* retprobe */,
-					  SYS_KPROBE_NAME);
+					  SYS_NANOSLEEP_KPROBE_NAME);
 	if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link)))
 		goto out_close;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index 67cea1686305..54218ee3c004 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -173,6 +173,18 @@ static int test_send_signal_tracepoint(void)
 	return test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint");
 }
 
+static int test_send_signal_perf(void)
+{
+	struct perf_event_attr attr = {
+		.sample_period = 1,
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_CPU_CLOCK,
+	};
+
+	return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
+				       "perf_sw_event");
+}
+
 static int test_send_signal_nmi(void)
 {
 	struct perf_event_attr attr = {
@@ -181,8 +193,26 @@ static int test_send_signal_nmi(void)
 		.type = PERF_TYPE_HARDWARE,
 		.config = PERF_COUNT_HW_CPU_CYCLES,
 	};
+	int pmu_fd;
 
-	return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, "perf_event");
+	/* Some setups (e.g. virtual machines) might run with hardware
+	 * perf events disabled. If this is the case, skip this test.
+	 */
+	pmu_fd = syscall(__NR_perf_event_open, &attr, 0 /* pid */,
+			 -1 /* cpu */, -1 /* group_fd */, 0 /* flags */);
+	if (pmu_fd == -1) {
+		if (errno == ENOENT) {
+			printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n",
+				__func__);
+			return 0;
+		}
+		/* Let the test fail with a more informative message */
+	} else {
+		close(pmu_fd);
+	}
+
+	return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
+				       "perf_hw_event");
 }
 
 void test_send_signal(void)
@@ -190,6 +220,7 @@ void test_send_signal(void)
 	int ret = 0;
 
 	ret |= test_send_signal_tracepoint();
+	ret |= test_send_signal_perf();
 	ret |= test_send_signal_nmi();
 	if (!ret)
 		printf("test_send_signal:OK\n");
diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c
index dea395af9ea9..7cdb7f878310 100644
--- a/tools/testing/selftests/bpf/progs/loop1.c
+++ b/tools/testing/selftests/bpf/progs/loop1.c
@@ -18,7 +18,7 @@ int nested_loops(volatile struct pt_regs* ctx)
 	for (j = 0; j < 300; j++)
 		for (i = 0; i < j; i++) {
 			if (j & 1)
-				m = ctx->rax;
+				m = PT_REGS_RC(ctx);
 			else
 				m = j;
 			sum += i * m;
diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c
index 0637bd8e8bcf..9b2f808a2863 100644
--- a/tools/testing/selftests/bpf/progs/loop2.c
+++ b/tools/testing/selftests/bpf/progs/loop2.c
@@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx)
 	int i = 0;
 
 	while (true) {
-		if (ctx->rax & 1)
+		if (PT_REGS_RC(ctx) & 1)
 			i += 3;
 		else
 			i += 7;
diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c
index 30a0f6cba080..d727657d51e2 100644
--- a/tools/testing/selftests/bpf/progs/loop3.c
+++ b/tools/testing/selftests/bpf/progs/loop3.c
@@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx)
 	__u64 i = 0, sum = 0;
 	do {
 		i++;
-		sum += ctx->rax;
+		sum += PT_REGS_RC(ctx);
 	} while (i < 0x100000000ULL);
 	return sum;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
index d06b47a09097..33254b771384 100644
--- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
@@ -47,11 +47,12 @@ struct {
  * issue and avoid complicated C programming massaging.
  * This is an acceptable workaround since there is one entry here.
  */
+typedef __u64 raw_stack_trace_t[2 * MAX_STACK_RAWTP];
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(max_entries, 1);
 	__type(key, __u32);
-	__u64 (*value)[2 * MAX_STACK_RAWTP];
+	__type(value, raw_stack_trace_t);
 } rawdata_map SEC(".maps");
 
 SEC("tracepoint/raw_syscalls/sys_enter")
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
index bbfc8337b6f0..f5638e26865d 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
@@ -36,8 +36,7 @@ struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 128);
 	__type(key, __u32);
-	/* there seems to be a bug in kernel not handling typedef properly */
-	struct bpf_stack_build_id (*value)[PERF_MAX_STACK_DEPTH];
+	__type(value, stack_trace_t);
 } stack_amap SEC(".maps");
 
 /* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index 803c15dc109d..fa0be3e10a10 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@@ -35,7 +35,7 @@ struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 16384);
 	__type(key, __u32);
-	__u64 (*value)[PERF_MAX_STACK_DEPTH];
+	__type(value, stack_trace_t);
 } stack_amap SEC(".maps");
 
 /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index dad8a7e33eaa..e88d7b9d65ab 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@@ -14,6 +14,7 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include "bpf_helpers.h"
+#include "bpf_endian.h"
 
 static __u32 rol32(__u32 word, unsigned int shift)
 {
@@ -305,7 +306,7 @@ bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval,
 	ip6h->nexthdr = IPPROTO_IPV6;
 	ip_suffix = pckt->flow.srcv6[3] ^ pckt->flow.port16[0];
 	ip6h->payload_len =
-	    __builtin_bswap16(pkt_bytes + sizeof(struct ipv6hdr));
+	    bpf_htons(pkt_bytes + sizeof(struct ipv6hdr));
 	ip6h->hop_limit = 4;
 
 	ip6h->saddr.in6_u.u6_addr32[0] = 1;
@@ -322,7 +323,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
 	      struct real_definition *dst, __u32 pkt_bytes)
 {
 
-	__u32 ip_suffix = __builtin_bswap16(pckt->flow.port16[0]);
+	__u32 ip_suffix = bpf_ntohs(pckt->flow.port16[0]);
 	struct eth_hdr *new_eth;
 	struct eth_hdr *old_eth;
 	__u16 *next_iph_u16;
@@ -352,7 +353,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
 	iph->protocol = IPPROTO_IPIP;
 	iph->check = 0;
 	iph->tos = 1;
-	iph->tot_len = __builtin_bswap16(pkt_bytes + sizeof(struct iphdr));
+	iph->tot_len = bpf_htons(pkt_bytes + sizeof(struct iphdr));
 	/* don't update iph->daddr, since it will overwrite old eth_proto
 	 * and multiple iterations of bpf_prog_run() will fail
 	 */
@@ -639,7 +640,7 @@ static int process_l3_headers_v6(struct packet_description *pckt,
 	iph_len = sizeof(struct ipv6hdr);
 	*protocol = ip6h->nexthdr;
 	pckt->flow.proto = *protocol;
-	*pkt_bytes = __builtin_bswap16(ip6h->payload_len);
+	*pkt_bytes = bpf_ntohs(ip6h->payload_len);
 	off += iph_len;
 	if (*protocol == 45) {
 		return XDP_DROP;
@@ -671,7 +672,7 @@ static int process_l3_headers_v4(struct packet_description *pckt,
 		return XDP_DROP;
 	*protocol = iph->protocol;
 	pckt->flow.proto = *protocol;
-	*pkt_bytes = __builtin_bswap16(iph->tot_len);
+	*pkt_bytes = bpf_ntohs(iph->tot_len);
 	off += 20;
 	if (iph->frag_off & 65343)
 		return XDP_DROP;
@@ -808,10 +809,10 @@ int balancer_ingress(struct xdp_md *ctx)
 	nh_off = sizeof(struct eth_hdr);
 	if (data + nh_off > data_end)
 		return XDP_DROP;
-	eth_proto = eth->eth_proto;
-	if (eth_proto == 8)
+	eth_proto = bpf_ntohs(eth->eth_proto);
+	if (eth_proto == ETH_P_IP)
 		return process_packet(data, nh_off, data_end, 0, ctx);
-	else if (eth_proto == 56710)
+	else if (eth_proto == ETH_P_IPV6)
 		return process_packet(data, nh_off, data_end, 1, ctx);
 	else
 		return XDP_DROP;
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 8351cb5f4a20..3d617e806054 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -3417,6 +3417,94 @@ static struct btf_raw_test raw_tests[] = {
 	.value_type_id = 1,
 	.max_entries = 4,
 },
+/*
+ * typedef int arr_t[16];
+ * struct s {
+ *	arr_t *a;
+ * };
+ */
+{
+	.descr = "struct->ptr->typedef->array->int size resolution",
+	.raw_types = {
+		BTF_STRUCT_ENC(NAME_TBD, 1, 8),			/* [1] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),
+		BTF_PTR_ENC(3),					/* [2] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 4),			/* [3] */
+		BTF_TYPE_ARRAY_ENC(5, 5, 16),			/* [4] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [5] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0s\0a\0arr_t"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "ptr_mod_chain_size_resolve_map",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int) * 16,
+	.key_type_id = 5 /* int */,
+	.value_type_id = 3 /* arr_t */,
+	.max_entries = 4,
+},
+/*
+ * typedef int arr_t[16][8][4];
+ * struct s {
+ *	arr_t *a;
+ * };
+ */
+{
+	.descr = "struct->ptr->typedef->multi-array->int size resolution",
+	.raw_types = {
+		BTF_STRUCT_ENC(NAME_TBD, 1, 8),			/* [1] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),
+		BTF_PTR_ENC(3),					/* [2] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 4),			/* [3] */
+		BTF_TYPE_ARRAY_ENC(5, 7, 16),			/* [4] */
+		BTF_TYPE_ARRAY_ENC(6, 7, 8),			/* [5] */
+		BTF_TYPE_ARRAY_ENC(7, 7, 4),			/* [6] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [7] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0s\0a\0arr_t"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "multi_arr_size_resolve_map",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int) * 16 * 8 * 4,
+	.key_type_id = 7 /* int */,
+	.value_type_id = 3 /* arr_t */,
+	.max_entries = 4,
+},
+/*
+ * typedef int int_t;
+ * typedef int_t arr3_t[4];
+ * typedef arr3_t arr2_t[8];
+ * typedef arr2_t arr1_t[16];
+ * struct s {
+ *	arr1_t *a;
+ * };
+ */
+{
+	.descr = "typedef/multi-arr mix size resolution",
+	.raw_types = {
+		BTF_STRUCT_ENC(NAME_TBD, 1, 8),			/* [1] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),
+		BTF_PTR_ENC(3),					/* [2] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 4),			/* [3] */
+		BTF_TYPE_ARRAY_ENC(5, 10, 16),			/* [4] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 6),			/* [5] */
+		BTF_TYPE_ARRAY_ENC(7, 10, 8),			/* [6] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 8),			/* [7] */
+		BTF_TYPE_ARRAY_ENC(9, 10, 4),			/* [8] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 10),			/* [9] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [10] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0s\0a\0arr1_t\0arr2_t\0arr3_t\0int_t"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "typedef_arra_mix_size_resolve_map",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int) * 16 * 8 * 4,
+	.key_type_id = 10 /* int */,
+	.value_type_id = 3 /* arr_t */,
+	.max_entries = 4,
+},
 
 }; /* struct btf_raw_test raw_tests[] */
 
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index f095e1d4c657..49e0f7d85643 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -92,3 +92,11 @@ int compare_map_keys(int map1_fd, int map2_fd);
 int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len);
 int extract_build_id(char *build_id, size_t size);
 void *spin_lock_thread(void *arg);
+
+#ifdef __x86_64__
+#define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep"
+#elif defined(__s390x__)
+#define SYS_NANOSLEEP_KPROBE_NAME "__s390x_sys_nanosleep"
+#else
+#define SYS_NANOSLEEP_KPROBE_NAME "sys_nanosleep"
+#endif
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index b0773291012a..84135d5f4b35 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -86,7 +86,7 @@ struct bpf_test {
 	int fixup_sk_storage_map[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
-	uint32_t retval, retval_unpriv, insn_processed;
+	uint32_t insn_processed;
 	int prog_len;
 	enum {
 		UNDEF,
@@ -95,16 +95,20 @@ struct bpf_test {
 	} result, result_unpriv;
 	enum bpf_prog_type prog_type;
 	uint8_t flags;
-	__u8 data[TEST_DATA_LEN];
 	void (*fill_helper)(struct bpf_test *self);
 	uint8_t runs;
-	struct {
-		uint32_t retval, retval_unpriv;
-		union {
-			__u8 data[TEST_DATA_LEN];
-			__u64 data64[TEST_DATA_LEN / 8];
-		};
-	} retvals[MAX_TEST_RUNS];
+#define bpf_testdata_struct_t					\
+	struct {						\
+		uint32_t retval, retval_unpriv;			\
+		union {						\
+			__u8 data[TEST_DATA_LEN];		\
+			__u64 data64[TEST_DATA_LEN / 8];	\
+		};						\
+	}
+	union {
+		bpf_testdata_struct_t;
+		bpf_testdata_struct_t retvals[MAX_TEST_RUNS];
+	};
 	enum bpf_attach_type expected_attach_type;
 };
 
@@ -949,17 +953,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		uint32_t expected_val;
 		int i;
 
-		if (!test->runs) {
-			expected_val = unpriv && test->retval_unpriv ?
-				test->retval_unpriv : test->retval;
-
-			err = do_prog_test_run(fd_prog, unpriv, expected_val,
-					       test->data, sizeof(test->data));
-			if (err)
-				run_errs++;
-			else
-				run_successes++;
-		}
+		if (!test->runs)
+			test->runs = 1;
 
 		for (i = 0; i < test->runs; i++) {
 			if (unpriv && test->retvals[i].retval_unpriv)
diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c
index bcb83196e459..f3c33e128709 100644
--- a/tools/testing/selftests/bpf/verifier/array_access.c
+++ b/tools/testing/selftests/bpf/verifier/array_access.c
@@ -226,7 +226,7 @@
 	BPF_LD_MAP_FD(BPF_REG_1, 0),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_array_ro = { 3 },
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index c3de1a2c9dc5..a53d99cebd9f 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -183,7 +183,7 @@
 	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
 	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
 	BPF_MOV64_IMM(BPF_REG_2, 0),
 	BPF_MOV64_IMM(BPF_REG_3, 0x100000),
diff --git a/tools/testing/selftests/bpf/verifier/wide_access.c b/tools/testing/selftests/bpf/verifier/wide_access.c
new file mode 100644
index 000000000000..ccade9312d21
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/wide_access.c
@@ -0,0 +1,73 @@
+#define BPF_SOCK_ADDR_STORE(field, off, res, err) \
+{ \
+	"wide store to bpf_sock_addr." #field "[" #off "]", \
+	.insns = { \
+	BPF_MOV64_IMM(BPF_REG_0, 1), \
+	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, \
+		    offsetof(struct bpf_sock_addr, field[off])), \
+	BPF_EXIT_INSN(), \
+	}, \
+	.result = res, \
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
+	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
+	.errstr = err, \
+}
+
+/* user_ip6[0] is u64 aligned */
+BPF_SOCK_ADDR_STORE(user_ip6, 0, ACCEPT,
+		    NULL),
+BPF_SOCK_ADDR_STORE(user_ip6, 1, REJECT,
+		    "invalid bpf_context access off=12 size=8"),
+BPF_SOCK_ADDR_STORE(user_ip6, 2, ACCEPT,
+		    NULL),
+BPF_SOCK_ADDR_STORE(user_ip6, 3, REJECT,
+		    "invalid bpf_context access off=20 size=8"),
+
+/* msg_src_ip6[0] is _not_ u64 aligned */
+BPF_SOCK_ADDR_STORE(msg_src_ip6, 0, REJECT,
+		    "invalid bpf_context access off=44 size=8"),
+BPF_SOCK_ADDR_STORE(msg_src_ip6, 1, ACCEPT,
+		    NULL),
+BPF_SOCK_ADDR_STORE(msg_src_ip6, 2, REJECT,
+		    "invalid bpf_context access off=52 size=8"),
+BPF_SOCK_ADDR_STORE(msg_src_ip6, 3, REJECT,
+		    "invalid bpf_context access off=56 size=8"),
+
+#undef BPF_SOCK_ADDR_STORE
+
+#define BPF_SOCK_ADDR_LOAD(field, off, res, err) \
+{ \
+	"wide load from bpf_sock_addr." #field "[" #off "]", \
+	.insns = { \
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, \
+		    offsetof(struct bpf_sock_addr, field[off])), \
+	BPF_MOV64_IMM(BPF_REG_0, 1), \
+	BPF_EXIT_INSN(), \
+	}, \
+	.result = res, \
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
+	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
+	.errstr = err, \
+}
+
+/* user_ip6[0] is u64 aligned */
+BPF_SOCK_ADDR_LOAD(user_ip6, 0, ACCEPT,
+		   NULL),
+BPF_SOCK_ADDR_LOAD(user_ip6, 1, REJECT,
+		   "invalid bpf_context access off=12 size=8"),
+BPF_SOCK_ADDR_LOAD(user_ip6, 2, ACCEPT,
+		   NULL),
+BPF_SOCK_ADDR_LOAD(user_ip6, 3, REJECT,
+		   "invalid bpf_context access off=20 size=8"),
+
+/* msg_src_ip6[0] is _not_ u64 aligned */
+BPF_SOCK_ADDR_LOAD(msg_src_ip6, 0, REJECT,
+		   "invalid bpf_context access off=44 size=8"),
+BPF_SOCK_ADDR_LOAD(msg_src_ip6, 1, ACCEPT,
+		   NULL),
+BPF_SOCK_ADDR_LOAD(msg_src_ip6, 2, REJECT,
+		   "invalid bpf_context access off=52 size=8"),
+BPF_SOCK_ADDR_LOAD(msg_src_ip6, 3, REJECT,
+		   "invalid bpf_context access off=56 size=8"),
+
+#undef BPF_SOCK_ADDR_LOAD
diff --git a/tools/testing/selftests/bpf/verifier/wide_store.c b/tools/testing/selftests/bpf/verifier/wide_store.c
deleted file mode 100644
index 8fe99602ded4..000000000000
--- a/tools/testing/selftests/bpf/verifier/wide_store.c
+++ /dev/null
@@ -1,36 +0,0 @@
-#define BPF_SOCK_ADDR(field, off, res, err) \
-{ \
-	"wide store to bpf_sock_addr." #field "[" #off "]", \
-	.insns = { \
-	BPF_MOV64_IMM(BPF_REG_0, 1), \
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, \
-		    offsetof(struct bpf_sock_addr, field[off])), \
-	BPF_EXIT_INSN(), \
-	}, \
-	.result = res, \
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
-	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
-	.errstr = err, \
-}
-
-/* user_ip6[0] is u64 aligned */
-BPF_SOCK_ADDR(user_ip6, 0, ACCEPT,
-	      NULL),
-BPF_SOCK_ADDR(user_ip6, 1, REJECT,
-	      "invalid bpf_context access off=12 size=8"),
-BPF_SOCK_ADDR(user_ip6, 2, ACCEPT,
-	      NULL),
-BPF_SOCK_ADDR(user_ip6, 3, REJECT,
-	      "invalid bpf_context access off=20 size=8"),
-
-/* msg_src_ip6[0] is _not_ u64 aligned */
-BPF_SOCK_ADDR(msg_src_ip6, 0, REJECT,
-	      "invalid bpf_context access off=44 size=8"),
-BPF_SOCK_ADDR(msg_src_ip6, 1, ACCEPT,
-	      NULL),
-BPF_SOCK_ADDR(msg_src_ip6, 2, REJECT,
-	      "invalid bpf_context access off=52 size=8"),
-BPF_SOCK_ADDR(msg_src_ip6, 3, REJECT,
-	      "invalid bpf_context access off=56 size=8"),
-
-#undef BPF_SOCK_ADDR