IB/mthca: Fix access to MTT and MPT tables on non-cache-coherent CPUs

We allocate the MTT table with alloc_pages() and then do pci_map_sg(),
so we must call pci_dma_sync_sg() after the CPU writes to the MTT
table.  This works since the device will never write MTTs on mem-free
HCAs, once we get rid of the use of the WRITE_MTT firmware command.
This change is needed to make that work, and is an improvement for
now, since it gives FMRs a chance at working.

For MPTs, both the device and CPU might write there, so we must
allocate DMA coherent memory for these.

Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

1 files changed, 6 insertions, 2 deletions

diff --git a/drivers/infiniband/hw/mthca/mthca_mr.c b/drivers/infiniband/hw/mthca/mthca_mr.c
index f71ffa88db3..7d08f2038af 100644
--- a/drivers/infiniband/hw/mthca/mthca_mr.c
+++ b/drivers/infiniband/hw/mthca/mthca_mr.c
@@ -524,7 +524,7 @@ int mthca_fmr_alloc(struct mthca_dev *dev, u32 pd,
                 if (err)
                         goto err_out_mpt_free;
 
-                mr->mem.arbel.mpt = mthca_table_find(dev->mr_table.mpt_table, key);
+                mr->mem.arbel.mpt = mthca_table_find(dev->mr_table.mpt_table, key, NULL);
                 BUG_ON(!mr->mem.arbel.mpt);
         } else
                 mr->mem.tavor.mpt = dev->mr_table.tavor_fmr.mpt_base +
@@ -538,7 +538,8 @@ int mthca_fmr_alloc(struct mthca_dev *dev, u32 pd,
 
         if (mthca_is_memfree(dev)) {
                 mr->mem.arbel.mtts = mthca_table_find(dev->mr_table.mtt_table,
-                                                      mr->mtt->first_seg);
+                                                      mr->mtt->first_seg,
+                                                      &mr->mem.arbel.dma_handle);
                 BUG_ON(!mr->mem.arbel.mtts);
         } else
                 mr->mem.tavor.mtts = dev->mr_table.tavor_fmr.mtt_base + mtt_seg;
@@ -712,6 +713,9 @@ int mthca_arbel_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
                 fmr->mem.arbel.mtts[i] = cpu_to_be64(page_list[i] |
                                                      MTHCA_MTT_FLAG_PRESENT);
 
+        dma_sync_single(&dev->pdev->dev, fmr->mem.arbel.dma_handle,
+                        list_len * sizeof(u64), DMA_TO_DEVICE);
+
         fmr->mem.arbel.mpt->key    = cpu_to_be32(key);
         fmr->mem.arbel.mpt->lkey   = cpu_to_be32(key);
         fmr->mem.arbel.mpt->length = cpu_to_be64(list_len * (1ull << fmr->attr.page_shift));