[IB] Fix MAD layer DMA mappings to avoid touching data buffer once mapped

The MAD layer was violating the DMA API by touching data buffers used
for sends after the DMA mapping was done.  This causes problems on
non-cache-coherent architectures, because the device doing DMA won't
see updates to the payload buffers that exist only in the CPU cache.

Fix this by having all MAD consumers use ib_create_send_mad() to
allocate their send buffers, and moving the DMA mapping into the MAD
layer so it can be done just before calling send (and after any
modifications of the send buffer by the MAD layer).

Tested on a non-cache-coherent PowerPC 440SPe system.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

1 files changed, 2 insertions, 0 deletions

diff --git a/drivers/infiniband/core/smi.h b/drivers/infiniband/core/smi.h
index db25503a0736..2b3c40198f81 100644
--- a/drivers/infiniband/core/smi.h
+++ b/drivers/infiniband/core/smi.h
@@ -39,6 +39,8 @@
 #ifndef __SMI_H_
 #define __SMI_H_
 
+#include <rdma/ib_smi.h>
+
 int smi_handle_dr_smp_recv(struct ib_smp *smp,
                            u8 node_type,
                            int port_num,