libbpf: remove dependency on barrier.h in xsk.h

The use of smp_rmb() and smp_wmb() creates a Linux header dependency
on barrier.h that is unnecessary in most parts. This patch implements
the two small defines that are needed from barrier.h. As a bonus, the
new implementations are faster than the default ones as they default
to sfence and lfence for x86, while we only need a compiler barrier in
our case. Just as it is when the same ring access code is compiled in
the kernel.

Fixes: 1cad07884239 ("libbpf: add support for using AF_XDP sockets")
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 29 insertions, 3 deletions

diff --git a/tools/lib/bpf/libbpf_util.h b/tools/lib/bpf/libbpf_util.h
index 81ecda0cb9c9..71fbb2898b87 100644
--- a/tools/lib/bpf/libbpf_util.h
+++ b/tools/lib/bpf/libbpf_util.h
@@ -23,6 +23,31 @@ do {				\
 #define pr_info(fmt, ...)	__pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
 #define pr_debug(fmt, ...)	__pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
 
+/* Use these barrier functions instead of smp_[rw]mb() when they are
+ * used in a libbpf header file. That way they can be built into the
+ * application that uses libbpf.
+ */
+#if defined(__i386__) || defined(__x86_64__)
+# define libbpf_smp_rmb() asm volatile("" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("" : : : "memory")
+# define libbpf_smp_mb() \
+	asm volatile("lock; addl $0,-4(%%rsp)" : : : "memory", "cc")
+#elif defined(__aarch64__)
+# define libbpf_smp_rmb() asm volatile("dmb ishld" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
+# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
+#elif defined(__arm__)
+/* These are only valid for armv7 and above */
+# define libbpf_smp_rmb() asm volatile("dmb ish" : : : "memory")
+# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
+# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory")
+#else
+# warning Architecture missing native barrier functions in libbpf_util.h.
+# define libbpf_smp_rmb() __sync_synchronize()
+# define libbpf_smp_wmb() __sync_synchronize()
+# define libbpf_smp_mb() __sync_synchronize()
+#endif
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
index f264f24f06ac..2377c7a7f1b1 100644
--- a/tools/lib/bpf/xsk.h
+++ b/tools/lib/bpf/xsk.h
@@ -16,6 +16,7 @@
 #include <linux/if_xdp.h>
 
 #include "libbpf.h"
+#include "libbpf_util.h"
 
 #ifdef __cplusplus
 extern "C" {
@@ -123,7 +124,7 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb)
 	/* Make sure everything has been written to the ring before indicating
 	 * this to the kernel by writing the producer pointer.
 	 */
-	smp_wmb();
+	libbpf_smp_wmb();
 
 	*prod->producer += nb;
 }
@@ -137,7 +138,7 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
 		/* Make sure we do not speculatively read the data before
 		 * we have received the packet buffers from the ring.
 		 */
-		smp_rmb();
+		libbpf_smp_rmb();
 
 		*idx = cons->cached_cons;
 		cons->cached_cons += entries;
@@ -151,7 +152,7 @@ static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb)
 	/* Make sure data has been read before indicating we are done
 	 * with the entries by updating the consumer pointer.
 	 */
-	smp_mb();
+	libbpf_smp_mb();
 
 	*cons->consumer += nb;
 }