diff --git a/Makefile b/Makefile
index c4322dea3ca2..af07bf5bb238 100644
--- a/Makefile
+++ b/Makefile
@@ -826,6 +826,15 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign)
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 
+# clang sets -fmerge-all-constants by default as optimization, but this
+# is non-conforming behavior for C and in fact breaks the kernel, so we
+# need to disable it here generally.
+KBUILD_CFLAGS	+= $(call cc-option,-fno-merge-all-constants)
+
+# for gcc -fno-merge-all-constants disables everything, but it is fine
+# to have actual conforming behavior enabled.
+KBUILD_CFLAGS	+= $(call cc-option,-fmerge-constants)
+
 # Make sure -fstack-check isn't enabled (like gentoo apparently did)
 KBUILD_CFLAGS  += $(call cc-option,-fno-stack-check,)
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e24aa3241387..43f95d190eea 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1845,7 +1845,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	union bpf_attr attr = {};
 	int err;
 
-	if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled)
+	if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
 	err = check_uarg_tail_zero(uattr, sizeof(attr), size);
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index 21b0122cb39c..1d5632d8bbcc 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -14,6 +14,15 @@
 
 static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs);
 
+static void fei_post_handler(struct kprobe *kp, struct pt_regs *regs,
+			     unsigned long flags)
+{
+	/*
+	 * A dummy post handler is required to prohibit optimizing, because
+	 * jump optimization does not support execution path overriding.
+	 */
+}
+
 struct fei_attr {
 	struct list_head list;
 	struct kprobe kp;
@@ -56,6 +65,7 @@ static struct fei_attr *fei_attr_new(const char *sym, unsigned long addr)
 			return NULL;
 		}
 		attr->kp.pre_handler = fei_kprobe_handler;
+		attr->kp.post_handler = fei_post_handler;
 		attr->retval = adjust_error_retval(addr, 0);
 		INIT_LIST_HEAD(&attr->list);
 	}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index c0a9e310d715..01e6b3a38871 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -661,32 +661,6 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx,
-	   struct bpf_perf_event_value *, buf, u32, size)
-{
-	int err = -EINVAL;
-
-	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
-		goto clear;
-	err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled,
-				    &buf->running);
-	if (unlikely(err))
-		goto clear;
-	return 0;
-clear:
-	memset(buf, 0, size);
-	return err;
-}
-
-static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = {
-         .func           = bpf_perf_prog_read_value_tp,
-         .gpl_only       = true,
-         .ret_type       = RET_INTEGER,
-         .arg1_type      = ARG_PTR_TO_CTX,
-         .arg2_type      = ARG_PTR_TO_UNINIT_MEM,
-         .arg3_type      = ARG_CONST_SIZE,
-};
-
 static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -694,8 +668,6 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 		return &bpf_perf_event_output_proto_tp;
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto_tp;
-	case BPF_FUNC_perf_prog_read_value:
-		return &bpf_perf_prog_read_value_proto_tp;
 	default:
 		return tracing_func_proto(func_id);
 	}
@@ -723,6 +695,46 @@ const struct bpf_verifier_ops tracepoint_verifier_ops = {
 const struct bpf_prog_ops tracepoint_prog_ops = {
 };
 
+BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx,
+	   struct bpf_perf_event_value *, buf, u32, size)
+{
+	int err = -EINVAL;
+
+	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
+		goto clear;
+	err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled,
+				    &buf->running);
+	if (unlikely(err))
+		goto clear;
+	return 0;
+clear:
+	memset(buf, 0, size);
+	return err;
+}
+
+static const struct bpf_func_proto bpf_perf_prog_read_value_proto = {
+         .func           = bpf_perf_prog_read_value,
+         .gpl_only       = true,
+         .ret_type       = RET_INTEGER,
+         .arg1_type      = ARG_PTR_TO_CTX,
+         .arg2_type      = ARG_PTR_TO_UNINIT_MEM,
+         .arg3_type      = ARG_CONST_SIZE,
+};
+
+static const struct bpf_func_proto *pe_prog_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_perf_event_output:
+		return &bpf_perf_event_output_proto_tp;
+	case BPF_FUNC_get_stackid:
+		return &bpf_get_stackid_proto_tp;
+	case BPF_FUNC_perf_prog_read_value:
+		return &bpf_perf_prog_read_value_proto;
+	default:
+		return tracing_func_proto(func_id);
+	}
+}
+
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    struct bpf_insn_access_aux *info)
 {
@@ -779,7 +791,7 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
 }
 
 const struct bpf_verifier_ops perf_event_verifier_ops = {
-	.get_func_proto		= tp_prog_func_proto,
+	.get_func_proto		= pe_prog_func_proto,
 	.is_valid_access	= pe_prog_is_valid_access,
 	.convert_ctx_access	= pe_prog_convert_ctx_access,
 };
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 2efb213716fa..3e9335493fe4 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -5467,7 +5467,7 @@ static struct bpf_test tests[] = {
 	{
 		"BPF_MAXINSNS: Jump, gap, jump, ...",
 		{ },
-#ifdef CONFIG_BPF_JIT_ALWAYS_ON
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_X86)
 		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
 #else
 		CLASSIC | FLAG_NO_DATA,