The libarena code currently defines the non-atomic bitmap set/get
operations as __weak functions, in accordance with the libarena
coding style. This, however, is significant overhead to call
functions that span single-digit instructions.

Make an exception and expose the getters/setters as static inline
functions in the header. Since the function body is now inlined
into the caller, mark reads/writes with READ_ONCE()/WRITE_ONCE()
to prevent compiler optimizations from breaking code that locklessly
polls the bitmap.

Signed-off-by: Emil Tsalapatis <emil@etsalapatis.com>
---
 .../bpf/libarena/include/libarena/bitmap.h    | 29 +++++++++++++++++--
 .../selftests/bpf/libarena/src/bitmap.bpf.c   | 18 ------------
 2 files changed, 26 insertions(+), 21 deletions(-)

diff --git a/tools/testing/selftests/bpf/libarena/include/libarena/bitmap.h b/tools/testing/selftests/bpf/libarena/include/libarena/bitmap.h
index 8c5936ae9958..163e2b83d943 100644
--- a/tools/testing/selftests/bpf/libarena/include/libarena/bitmap.h
+++ b/tools/testing/selftests/bpf/libarena/include/libarena/bitmap.h
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: LGPL-2.1 OR BSD-2-Clause
 #pragma once
 
+#include <bpf_atomic.h>
+
 #define BITS_PER_BYTE		8
 #define BYTES_TO_BITS(nb)	((nb) * BITS_PER_BYTE)
 
@@ -16,11 +18,8 @@ struct arena_bitmap {
 struct arena_bitmap __arena *bmp_alloc(size_t bits);
 void bmp_free(struct arena_bitmap __arena *bmp);
 
-void __bmp_set_bit(u32 bit, struct arena_bitmap __arena *bmp);
-void __bmp_clear_bit(u32 bit, struct arena_bitmap __arena *bmp);
 void bmp_set_bit(u32 bit, struct arena_bitmap __arena *bmp);
 void bmp_clear_bit(u32 bit, struct arena_bitmap __arena *bmp);
-bool bmp_test_bit(u32 bit, struct arena_bitmap __arena *bmp);
 bool bmp_test_and_clear_bit(u32 bit, struct arena_bitmap __arena *bmp);
 bool bmp_test_and_set_bit(u32 bit, struct arena_bitmap __arena *bmp);
 
@@ -33,3 +32,27 @@ void bmp_copy(size_t bits, struct arena_bitmap __arena *dst, struct arena_bitmap
 bool bmp_intersects(size_t bits, struct arena_bitmap __arena *arg1, struct arena_bitmap __arena *arg2);
 bool bmp_subset(size_t bits, struct arena_bitmap __arena *big, struct arena_bitmap __arena *small);
 void bmp_print(size_t bits, struct arena_bitmap __arena *bmp);
+
+static __always_inline
+void __bmp_set_bit(u32 bit, struct arena_bitmap __arena *bmp)
+{
+	volatile u64 __arena *word = &bmp->bits[BIT_WORD(bit)];
+
+	*word |= BIT_MASK(bit);
+}
+
+static __always_inline
+void __bmp_clear_bit(u32 bit, struct arena_bitmap __arena *bmp)
+{
+	volatile u64 __arena *word = &bmp->bits[BIT_WORD(bit)];
+
+	*word &= ~BIT_MASK(bit);
+}
+
+static __always_inline
+bool bmp_test_bit(u32 bit, struct arena_bitmap __arena *bmp)
+{
+	u64 word = READ_ONCE(bmp->bits[BIT_WORD(bit)]);
+
+	return word & BIT_MASK(bit);
+}
diff --git a/tools/testing/selftests/bpf/libarena/src/bitmap.bpf.c b/tools/testing/selftests/bpf/libarena/src/bitmap.bpf.c
index 5ff8e688ddc7..0390f20ce366 100644
--- a/tools/testing/selftests/bpf/libarena/src/bitmap.bpf.c
+++ b/tools/testing/selftests/bpf/libarena/src/bitmap.bpf.c
@@ -34,24 +34,6 @@ void bmp_free(struct arena_bitmap __arena *bmp)
 	arena_free(bmp);
 }
 
-__weak
-void __bmp_set_bit(u32 bit, struct arena_bitmap __arena *bmp)
-{
-	bmp->bits[BIT_WORD(bit)] |= BIT_MASK(bit);
-}
-
-__weak
-void __bmp_clear_bit(u32 bit, struct arena_bitmap __arena *bmp)
-{
-	bmp->bits[BIT_WORD(bit)] &= ~BIT_MASK(bit);
-}
-
-__weak
-bool bmp_test_bit(u32 bit, struct arena_bitmap __arena *bmp)
-{
-	return bmp->bits[BIT_WORD(bit)] & BIT_MASK(bit);
-}
-
 __weak
 bool bmp_test_and_clear_bit(u32 bit, struct arena_bitmap __arena *bmp)
 {
-- 
2.54.0