diff --git a/src/basic/siphash24.c b/src/basic/siphash24.c
index b73ede34c8..fb40f3d6bd 100644
--- a/src/basic/siphash24.c
+++ b/src/basic/siphash24.c
@@ -26,13 +26,17 @@
 #include "string-util.h"
 #include "unaligned.h"
 
-static uint64_t rotate_left(uint64_t x, uint8_t b) {
+/* The round is small enough that it is worth inlining at every call site, but large enough that gcc's
+ * -O2 inlining budget declines to do so on its own, leaving a call/ret and a reload of the state around
+ * six rounds of ~14 ALU ops. clang inlines it either way, and the SipHash reference implementation this
+ * file is derived from inlines the round manually, by writing it as a macro. */
+static inline _always_inline_ uint64_t rotate_left(uint64_t x, uint8_t b) {
         assert(b < 64);
 
         return (x << b) | (x >> (64 - b));
 }
 
-static void sipround(struct siphash *state) {
+static inline _always_inline_ void sipround(struct siphash *state) {
         assert(state);
 
         state->v0 += state->v1;
diff --git a/src/fundamental/macro.h b/src/fundamental/macro.h
index 970bfbcf4c..ef12a0dfba 100644
--- a/src/fundamental/macro.h
+++ b/src/fundamental/macro.h
@@ -76,6 +76,7 @@
 #define _align_(x) __attribute__((__aligned__(x)))
 #define _alignas_(x) __attribute__((__aligned__(alignof(x))))
 #define _alignptr_ __attribute__((__aligned__(sizeof(void *))))
+#define _always_inline_ __attribute__((__always_inline__))
 #define _cleanup_(x) __attribute__((__cleanup__(x)))
 #define _const_ __attribute__((__const__))
 #define _deprecated_ __attribute__((__deprecated__))