diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 79e7a0ec1da5..6926d0ca6c71 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1349,6 +1349,7 @@ st:			if (is_imm8(insn->off))
 			    insn->imm == (BPF_XOR | BPF_FETCH)) {
 				u8 *branch_target;
 				bool is64 = BPF_SIZE(insn->code) == BPF_DW;
+				u32 real_src_reg = src_reg;
 
 				/*
 				 * Can't be implemented with a single x86 insn.
@@ -1357,6 +1358,9 @@ st:			if (is_imm8(insn->off))
 
 				/* Will need RAX as a CMPXCHG operand so save R0 */
 				emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0);
+				if (src_reg == BPF_REG_0)
+					real_src_reg = BPF_REG_AX;
+
 				branch_target = prog;
 				/* Load old value */
 				emit_ldx(&prog, BPF_SIZE(insn->code),
@@ -1366,9 +1370,9 @@ st:			if (is_imm8(insn->off))
 				 * put the result in the AUX_REG.
 				 */
 				emit_mov_reg(&prog, is64, AUX_REG, BPF_REG_0);
-				maybe_emit_mod(&prog, AUX_REG, src_reg, is64);
+				maybe_emit_mod(&prog, AUX_REG, real_src_reg, is64);
 				EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)],
-				      add_2reg(0xC0, AUX_REG, src_reg));
+				      add_2reg(0xC0, AUX_REG, real_src_reg));
 				/* Attempt to swap in new value */
 				err = emit_atomic(&prog, BPF_CMPXCHG,
 						  dst_reg, AUX_REG, insn->off,
@@ -1381,7 +1385,7 @@ st:			if (is_imm8(insn->off))
 				 */
 				EMIT2(X86_JNE, -(prog - branch_target) - 2);
 				/* Return the pre-modification value */
-				emit_mov_reg(&prog, is64, src_reg, BPF_REG_0);
+				emit_mov_reg(&prog, is64, real_src_reg, BPF_REG_0);
 				/* Restore R0 after clobbering RAX */
 				emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX);
 				break;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4c24daa43bac..79c893310492 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3850,7 +3850,6 @@ union bpf_attr {
  *
  * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
  *	Description
-
  *		Check ctx packet size against exceeding MTU of net device (based
  *		on *ifindex*).  This helper will likely be used in combination
  *		with helpers that adjust/change the packet size.
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2efeb5f4b343..b1a76fe046cb 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4321,8 +4321,6 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
 		 * is not supported yet.
 		 * BPF_PROG_TYPE_RAW_TRACEPOINT is fine.
 		 */
-		if (log->level & BPF_LOG_LEVEL)
-			bpf_log(log, "arg#%d type is not a struct\n", arg);
 		return NULL;
 	}
 	tname = btf_name_by_offset(btf, t->name_off);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 0ae015ad1e05..aa1e64196d8d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1118,6 +1118,8 @@ static void bpf_prog_clone_free(struct bpf_prog *fp)
 	 * clone is guaranteed to not be locked.
 	 */
 	fp->aux = NULL;
+	fp->stats = NULL;
+	fp->active = NULL;
 	__bpf_prog_free(fp);
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1dda9d81f12c..3d34ba492d46 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1120,7 +1120,7 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
 		reg->type = PTR_TO_RDWR_BUF;
 		break;
 	default:
-		WARN_ON("unknown nullable register type");
+		WARN_ONCE(1, "unknown nullable register type");
 	}
 }
 
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index 7409d7860aa6..80d966cfcaa1 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -260,6 +260,11 @@ static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size)
 	return btf_id__add(root, id, false);
 }
 
+/* Older libelf.h and glibc elf.h might not yet define the ELF compression types. */
+#ifndef SHF_COMPRESSED
+#define SHF_COMPRESSED (1 << 11) /* Section with compressed data. */
+#endif
+
 /*
  * The data of compressed section should be aligned to 4
  * (for 32bit) or 8 (for 64 bit) bytes. The binutils ld
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4c24daa43bac..79c893310492 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3850,7 +3850,6 @@ union bpf_attr {
  *
  * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
  *	Description
-
  *		Check ctx packet size against exceeding MTU of net device (based
  *		on *ifindex*).  This helper will likely be used in combination
  *		with helpers that adjust/change the packet size.
diff --git a/tools/testing/selftests/bpf/progs/test_global_func11.c b/tools/testing/selftests/bpf/progs/test_global_func11.c
index 28488047c849..ef5277d982d9 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func11.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func11.c
@@ -15,5 +15,5 @@ __noinline int foo(const struct S *s)
 SEC("cgroup_skb/ingress")
 int test_cls(struct __sk_buff *skb)
 {
-	return foo(skb);
+	return foo((const void *)skb);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index a621b58ab079..9afe947cfae9 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -446,10 +446,8 @@ int _geneve_get_tunnel(struct __sk_buff *skb)
 	}
 
 	ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
-	if (ret < 0) {
-		ERROR(ret);
-		return TC_ACT_SHOT;
-	}
+	if (ret < 0)
+		gopt.opt_class = 0;
 
 	bpf_trace_printk(fmt, sizeof(fmt),
 			key.tunnel_id, key.remote_ipv4, gopt.opt_class);
diff --git a/tools/testing/selftests/bpf/verifier/atomic_and.c b/tools/testing/selftests/bpf/verifier/atomic_and.c
index 1bdc8e6684f7..fe4bb70eb9c5 100644
--- a/tools/testing/selftests/bpf/verifier/atomic_and.c
+++ b/tools/testing/selftests/bpf/verifier/atomic_and.c
@@ -75,3 +75,26 @@
 	},
 	.result = ACCEPT,
 },
+{
+	"BPF_ATOMIC_AND with fetch - r0 as source reg",
+	.insns = {
+		/* val = 0x110; */
+		BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0x110),
+		/* old = atomic_fetch_and(&val, 0x011); */
+		BPF_MOV64_IMM(BPF_REG_0, 0x011),
+		BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_10, BPF_REG_0, -8),
+		/* if (old != 0x110) exit(3); */
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0x110, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 3),
+		BPF_EXIT_INSN(),
+		/* if (val != 0x010) exit(2); */
+		BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -8),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x010, 2),
+		BPF_MOV64_IMM(BPF_REG_1, 2),
+		BPF_EXIT_INSN(),
+		/* exit(0); */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+},