diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 3a12e6b400a296..02242614dcc78e 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -36,6 +36,7 @@ obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o
 endif
 ifeq ($(CONFIG_BPF_JIT),y)
 obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
+obj-$(CONFIG_BPF_SYSCALL) += cpumask.o
 obj-${CONFIG_BPF_LSM} += bpf_lsm.o
 endif
 obj-$(CONFIG_BPF_PRELOAD) += preload/
diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
new file mode 100644
index 00000000000000..e1fa15a7e07984
--- /dev/null
+++ b/kernel/bpf/cpumask.c
@@ -0,0 +1,263 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2023 Meta, Inc
+ */
+#include <linux/bpf.h>
+#include <linux/bpf_mem_alloc.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+#include <linux/cpumask.h>
+
+/**
+ * struct bpf_cpumask - refcounted BPF cpumask wrapper structure
+ * @cpumask:	The actual cpumask embedded in the struct.
+ * @usage:	Object reference counter. When the refcount goes to 0, the
+ *		memory is released back to the BPF allocator, which provides
+ *		RCU safety.
+ *
+ * Note that we explicitly embed a cpumask_t rather than a cpumask_var_t.  This
+ * is done to avoid confusing the verifier due to the typedef of cpumask_var_t
+ * changing depending on whether CONFIG_CPUMASK_OFFSTACK is defined or not. See
+ * the details in <linux/cpumask.h>. The consequence is that this structure is
+ * likely a bit larger than it needs to be when CONFIG_CPUMASK_OFFSTACK is
+ * defined due to embedding the whole NR_CPUS-size bitmap, but the extra memory
+ * overhead it's minimal. For the more typical case of CONFIG_CPUMASK_OFFSTACK
+ * not being defined, the structure is the same size regardless.
+ */
+struct bpf_cpumask {
+	cpumask_t cpumask;
+	refcount_t usage;
+};
+
+static struct bpf_mem_alloc bpf_cpumask_ma;
+
+static bool cpu_valid(u32 cpu)
+{
+	return cpu < nr_cpu_ids;
+}
+
+struct bpf_cpumask *bpf_cpumask_create(void)
+{
+	struct bpf_cpumask *cpumask;
+
+	cpumask = bpf_mem_alloc(&bpf_cpumask_ma, sizeof(*cpumask));
+	if (!cpumask)
+		return NULL;
+
+	memset(cpumask, 0, sizeof(*cpumask));
+	refcount_set(&cpumask->usage, 1);
+
+	return cpumask;
+}
+
+struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask)
+{
+	refcount_inc(&cpumask->usage);
+	return cpumask;
+}
+
+struct bpf_cpumask *bpf_cpumask_kptr_get(struct bpf_cpumask **cpumaskp)
+{
+	struct bpf_cpumask *cpumask;
+
+	/* The BPF memory allocator frees memory backing its caches in an RCU
+	 * callback. Thus, we can safely use RCU to ensure that the cpumask is
+	 * safe to read.
+	 */
+	rcu_read_lock();
+
+	cpumask = READ_ONCE(*cpumaskp);
+	if (cpumask && !refcount_inc_not_zero(&cpumask->usage))
+		cpumask = NULL;
+
+	rcu_read_unlock();
+	return cpumask;
+}
+
+void bpf_cpumask_release(struct bpf_cpumask *cpumask)
+{
+	if (!cpumask)
+		return;
+
+	if (refcount_dec_and_test(&cpumask->usage)) {
+		migrate_disable();
+		bpf_mem_free(&bpf_cpumask_ma, cpumask);
+		migrate_enable();
+	}
+}
+
+u32 bpf_cpumask_first(const struct cpumask *cpumask)
+{
+	return cpumask_first(cpumask);
+}
+
+u32 bpf_cpumask_first_zero(const struct cpumask *cpumask)
+{
+	return cpumask_first_zero(cpumask);
+}
+
+void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask)
+{
+	if (!cpu_valid(cpu))
+		return;
+
+	cpumask_set_cpu(cpu, (struct cpumask *)cpumask);
+}
+
+void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask)
+{
+	if (!cpu_valid(cpu))
+		return;
+
+	cpumask_clear_cpu(cpu, (struct cpumask *)cpumask);
+}
+
+bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask)
+{
+	if (!cpu_valid(cpu))
+		return false;
+
+	return cpumask_test_cpu(cpu, (struct cpumask *)cpumask);
+}
+
+bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask)
+{
+	if (!cpu_valid(cpu))
+		return false;
+
+	return cpumask_test_and_set_cpu(cpu, (struct cpumask *)cpumask);
+}
+
+bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask)
+{
+	if (!cpu_valid(cpu))
+		return false;
+
+	return cpumask_test_and_clear_cpu(cpu, (struct cpumask *)cpumask);
+}
+
+void bpf_cpumask_setall(struct bpf_cpumask *cpumask)
+{
+	cpumask_setall((struct cpumask *)cpumask);
+}
+
+void bpf_cpumask_clear(struct bpf_cpumask *cpumask)
+{
+	cpumask_clear((struct cpumask *)cpumask);
+}
+
+bool bpf_cpumask_and(struct bpf_cpumask *dst,
+		     const struct cpumask *src1,
+		     const struct cpumask *src2)
+{
+	return cpumask_and((struct cpumask *)dst, src1, src2);
+}
+
+void bpf_cpumask_or(struct bpf_cpumask *dst,
+		    const struct cpumask *src1,
+		    const struct cpumask *src2)
+{
+	cpumask_or((struct cpumask *)dst, src1, src2);
+}
+
+void bpf_cpumask_xor(struct bpf_cpumask *dst,
+		     const struct cpumask *src1,
+		     const struct cpumask *src2)
+{
+	cpumask_xor((struct cpumask *)dst, src1, src2);
+}
+
+bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2)
+{
+	return cpumask_equal(src1, src2);
+}
+
+bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2)
+{
+	return cpumask_intersects(src1, src2);
+}
+
+bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2)
+{
+	return cpumask_subset(src1, src2);
+}
+
+bool bpf_cpumask_empty(const struct cpumask *cpumask)
+{
+	return cpumask_empty(cpumask);
+}
+
+bool bpf_cpumask_full(const struct cpumask *cpumask)
+{
+	return cpumask_full(cpumask);
+}
+
+void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src)
+{
+	cpumask_copy((struct cpumask *)dst, src);
+}
+
+u32 bpf_cpumask_any(const struct cpumask *cpumask)
+{
+	return cpumask_any(cpumask);
+}
+
+u32 bpf_cpumask_any_and(const struct cpumask *src1, const struct cpumask *src2)
+{
+	return cpumask_any_and(src1, src2);
+}
+
+BTF_SET8_START(cpumask_kfunc_btf_ids)
+BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_cpumask_release, KF_RELEASE | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_cpumask_first, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_first_zero, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_set_cpu, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_clear_cpu, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_test_cpu, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_test_and_set_cpu, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_test_and_clear_cpu, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_setall, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_clear, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_and, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_or, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_xor, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_equal, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_intersects, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_subset, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_empty, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_full, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_any, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_cpumask_any_and, KF_TRUSTED_ARGS)
+BTF_SET8_END(cpumask_kfunc_btf_ids)
+
+static const struct btf_kfunc_id_set cpumask_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &cpumask_kfunc_btf_ids,
+};
+
+BTF_ID_LIST(cpumask_dtor_ids)
+BTF_ID(struct, bpf_cpumask)
+BTF_ID(func, bpf_cpumask_release)
+
+static int __init cpumask_kfunc_init(void)
+{
+	int ret;
+	const struct btf_id_dtor_kfunc cpumask_dtors[] = {
+		{
+			.btf_id	      = cpumask_dtor_ids[0],
+			.kfunc_btf_id = cpumask_dtor_ids[1]
+		},
+	};
+
+	ret = bpf_mem_alloc_init(&bpf_cpumask_ma, 0, false);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &cpumask_kfunc_set);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &cpumask_kfunc_set);
+	return  ret ?: register_btf_id_dtor_kfuncs(cpumask_dtors,
+						   ARRAY_SIZE(cpumask_dtors),
+						   THIS_MODULE);
+}
+
+late_initcall(cpumask_kfunc_init);