diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index f538c75db183..225f61f9bfca 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -7,7 +7,13 @@
 #ifndef __SCX_COMMON_BPF_H
 #define __SCX_COMMON_BPF_H
 
+#ifdef LSP
+#define __bpf__
+#include "../vmlinux/vmlinux.h"
+#else
 #include "vmlinux.h"
+#endif
+
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <asm-generic/errno.h>
@@ -309,6 +315,15 @@ void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym
 u32 bpf_cpumask_any_distribute(const struct cpumask *cpumask) __ksym;
 u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
 				   const struct cpumask *src2) __ksym;
+u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym;
+
+/*
+ * Access a cpumask in read-only mode (typically to check bits).
+ */
+const struct cpumask *cast_mask(struct bpf_cpumask *mask)
+{
+	return (const struct cpumask *)mask;
+}
 
 /* rcu */
 void bpf_rcu_read_lock(void) __ksym;
diff --git a/tools/sched_ext/include/scx/user_exit_info.h b/tools/sched_ext/include/scx/user_exit_info.h
index 891693ee604e..8ce2734402e1 100644
--- a/tools/sched_ext/include/scx/user_exit_info.h
+++ b/tools/sched_ext/include/scx/user_exit_info.h
@@ -25,7 +25,11 @@ struct user_exit_info {
 
 #ifdef __bpf__
 
+#ifdef LSP
+#include "../vmlinux/vmlinux.h"
+#else
 #include "vmlinux.h"
+#endif
 #include <bpf/bpf_core_read.h>
 
 #define UEI_DEFINE(__name)							\
diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c
index 936415b98ae7..e272bc39bbbd 100644
--- a/tools/sched_ext/scx_flatcg.bpf.c
+++ b/tools/sched_ext/scx_flatcg.bpf.c
@@ -225,7 +225,7 @@ static void cgrp_refresh_hweight(struct cgroup *cgrp, struct fcg_cgrp_ctx *cgc)
 				break;
 
 			/*
-			 * We can be oppotunistic here and not grab the
+			 * We can be opportunistic here and not grab the
 			 * cgv_tree_lock and deal with the occasional races.
 			 * However, hweight updates are already cached and
 			 * relatively low-frequency. Let's just do the
@@ -258,8 +258,7 @@ static void cgrp_cap_budget(struct cgv_node *cgv_node, struct fcg_cgrp_ctx *cgc)
 	 * and thus can't be updated and repositioned. Instead, we collect the
 	 * vtime deltas separately and apply it asynchronously here.
 	 */
-	delta = cgc->cvtime_delta;
-	__sync_fetch_and_sub(&cgc->cvtime_delta, delta);
+	delta = __sync_fetch_and_sub(&cgc->cvtime_delta, cgc->cvtime_delta);
 	cvtime = cgv_node->cvtime + delta;
 
 	/*