diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bb3847caeae11..654fb94bf60cc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -31,6 +31,7 @@
 #include <linux/static_call.h>
 #include <linux/memcontrol.h>
 #include <linux/cfi.h>
+#include <linux/unaligned.h>
 #include <asm/rqspinlock.h>
 
 struct bpf_verifier_env;
@@ -1746,6 +1747,8 @@ struct bpf_prog_aux {
 	struct bpf_map __rcu *st_ops_assoc;
 };
 
+#define BPF_NR_CONTEXTS        4       /* normal, softirq, hardirq, NMI */
+
 struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
 	u16			jited:1,	/* Is our filter JIT'ed? */
@@ -1772,7 +1775,7 @@ struct bpf_prog {
 		u8 tag[BPF_TAG_SIZE];
 	};
 	struct bpf_prog_stats __percpu *stats;
-	int __percpu		*active;
+	u8 __percpu		*active;	/* u8[BPF_NR_CONTEXTS] for rerecursion protection */
 	unsigned int		(*bpf_func)(const void *ctx,
 					    const struct bpf_insn *insn);
 	struct bpf_prog_aux	*aux;		/* Auxiliary fields */
@@ -2004,6 +2007,36 @@ struct bpf_struct_ops_common_value {
 	enum bpf_struct_ops_state state;
 };
 
+static inline bool bpf_prog_get_recursion_context(struct bpf_prog *prog)
+{
+#ifdef CONFIG_ARM64
+	u8 rctx = interrupt_context_level();
+	u8 *active = this_cpu_ptr(prog->active);
+
+	active[rctx]++;
+	barrier();
+	if (get_unaligned_le32(active) != BIT(rctx * 8))
+		return false;
+
+	return true;
+#else
+	return this_cpu_inc_return(*(prog->active)) == 1;
+#endif
+}
+
+static inline void bpf_prog_put_recursion_context(struct bpf_prog *prog)
+{
+#ifdef CONFIG_ARM64
+	u8 rctx = interrupt_context_level();
+	u8 *active = this_cpu_ptr(prog->active);
+
+	barrier();
+	active[rctx]--;
+#else
+	this_cpu_dec(*(prog->active));
+#endif
+}
+
 #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
 /* This macro helps developer to register a struct_ops type and generate
  * type information correctly. Developers should use this macro to register
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c66316e325630..b5063acfcf92a 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -112,7 +112,8 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 		vfree(fp);
 		return NULL;
 	}
-	fp->active = alloc_percpu_gfp(int, bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags));
+	fp->active = __alloc_percpu_gfp(sizeof(u8[BPF_NR_CONTEXTS]), 8,
+					bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags));
 	if (!fp->active) {
 		vfree(fp);
 		kfree(aux);
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 976d89011b157..2a125d063e62b 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -949,7 +949,7 @@ static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tram
 
 	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
 
-	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
+	if (unlikely(!bpf_prog_get_recursion_context(prog))) {
 		bpf_prog_inc_misses_counter(prog);
 		if (prog->aux->recursion_detected)
 			prog->aux->recursion_detected(prog);
@@ -993,7 +993,7 @@ static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start,
 	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
 
 	update_prog_stats(prog, start);
-	this_cpu_dec(*(prog->active));
+	bpf_prog_put_recursion_context(prog);
 	rcu_read_unlock_migrate();
 }
 
@@ -1029,7 +1029,7 @@ u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
 
 	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
 
-	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
+	if (unlikely(!bpf_prog_get_recursion_context(prog))) {
 		bpf_prog_inc_misses_counter(prog);
 		if (prog->aux->recursion_detected)
 			prog->aux->recursion_detected(prog);
@@ -1044,7 +1044,7 @@ void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start,
 	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
 
 	update_prog_stats(prog, start);
-	this_cpu_dec(*(prog->active));
+	bpf_prog_put_recursion_context(prog);
 	migrate_enable();
 	rcu_read_unlock_trace();
 }
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index fe28d86f7c357..6e076485bf709 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2063,7 +2063,7 @@ void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args)
 	struct bpf_trace_run_ctx run_ctx;
 
 	cant_sleep();
-	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
+	if (unlikely(!bpf_prog_get_recursion_context(prog))) {
 		bpf_prog_inc_misses_counter(prog);
 		goto out;
 	}
@@ -2077,7 +2077,7 @@ void __bpf_trace_run(struct bpf_raw_tp_link *link, u64 *args)
 
 	bpf_reset_run_ctx(old_run_ctx);
 out:
-	this_cpu_dec(*(prog->active));
+	bpf_prog_put_recursion_context(prog);
 }
 
 #define UNPACK(...)			__VA_ARGS__