Use wc_wmb() when posting BlueFlame send WQEs

Use wc_wmb() after copying WQE to BlueFlame register to avoid having
WQEs reach the device out of order if the BlueFlame page is mapped with
write combining.

Signed-off-by: Roland Dreier <rolandd@cisco.com>

2 files changed, 18 insertions, 1 deletions

diff --git a/src/mlx4.h b/src/mlx4.h
index c4d389f..1e92b88 100644
--- a/src/mlx4.h
+++ b/src/mlx4.h
@@ -65,6 +65,20 @@
 #  define wmb() mb()
 #endif
 
+#ifndef wc_wmb
+
+#if defined(__i386__)
+#define wc_wmb() asm volatile("lock; addl $0,0(%%esp) " ::: "memory")
+#elif defined(__x86_64__)
+#define wc_wmb() asm volatile("sfence" ::: "memory")
+#elif defined(__ia64__)
+#define wc_wmb() asm volatile("fwb" ::: "memory")
+#else
+#define wc_wmb() wmb()
+#endif
+
+#endif
+
 #define HIDDEN		__attribute__((visibility ("hidden")))
 
 #define PFX		"mlx4: "
diff --git a/src/qp.c b/src/qp.c
index a70e5f2..a4384f9 100644
--- a/src/qp.c
+++ b/src/qp.c
@@ -282,9 +282,12 @@ out:
 		++qp->sq.head;
 
 		pthread_spin_lock(&ctx->bf_lock);
+
 		memcpy(ctx->bf_page + ctx->bf_offset, ctrl, align(size * 16, 64));
-		/* FIXME flush wc buffers */
+		wc_wmb();
+
 		ctx->bf_offset ^= ctx->bf_buf_size;
+
 		pthread_spin_unlock(&ctx->bf_lock);
 	} else if (nreq) {
 		qp->sq.head += nreq;