Merge pull request #5704 from hjelmn/v4.0.x_btl_vader

v4.0.x: btl/vader: ensure that the send tag is always written last

opal/mca/btl/vader/btl_vader_fbox.h

@@ -50,9 +50,10 @@ void mca_btl_vader_poll_handle_frag (mca_btl_vader_hdr_t *hdr, mca_btl_base_endp
 static inline void mca_btl_vader_fbox_set_header (mca_btl_vader_fbox_hdr_t *hdr, uint16_t tag,
                                                   uint16_t seq, uint32_t size)
 {
-    mca_btl_vader_fbox_hdr_t tmp = {.data = {.tag = tag, .seq = seq, .size = size}};
-    opal_atomic_wmb ();
+    mca_btl_vader_fbox_hdr_t tmp = {.data = {.tag = 0, .seq = seq, .size = size}};
     hdr->ival = tmp.ival;
+    opal_atomic_wmb ();
+    hdr->data.tag = tag;
 }
 
 /* attempt to reserve a contiguous segment from the remote ep */
@@ -138,9 +139,6 @@ static inline bool mca_btl_vader_fbox_sendi (mca_btl_base_endpoint_t *ep, unsign
         memcpy (data + header_size, payload, payload_size);
     }
 
-    /* write out part of the header now. the tag will be written when the data is available */
-    mca_btl_vader_fbox_set_header (MCA_BTL_VADER_FBOX_HDR(dst), tag, ep->fbox_out.seq++, data_size);
-
     end += size;
 
     if (OPAL_UNLIKELY(fbox_size == end)) {
@@ -152,6 +150,9 @@ static inline bool mca_btl_vader_fbox_sendi (mca_btl_base_endpoint_t *ep, unsign
         MCA_BTL_VADER_FBOX_HDR(ep->fbox_out.buffer + end)->ival = 0;
     }
 
+    /* write out part of the header now. the tag will be written when the data is available */
+    mca_btl_vader_fbox_set_header (MCA_BTL_VADER_FBOX_HDR(dst), tag, ep->fbox_out.seq++, data_size);
+
     /* align the buffer */
     ep->fbox_out.end = ((uint32_t) hbs << 31) | end;
     opal_atomic_wmb ();