IB/mthca: Optimize large messages on Sinai HCAs

Sinai (one-port PCI Express) HCAs get improved throughput for messages
bigger than 80 KB in DDR mode if memory keys are formatted in a
specific way.  The enhancement only works if the memory key table is
smaller than 2^24 entries.  For larger tables, the enhancement is off
and a warning is printed (to avoid silent performance loss).

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

1 files changed, 8 insertions, 4 deletions

diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index 948a2861cae3..343eca507870 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -1277,7 +1277,8 @@ int mthca_INIT_HCA(struct mthca_dev *dev,
         int err;
 
 #define INIT_HCA_IN_SIZE                 0x200
-#define INIT_HCA_FLAGS_OFFSET            0x014
+#define INIT_HCA_FLAGS1_OFFSET           0x00c
+#define INIT_HCA_FLAGS2_OFFSET           0x014
 #define INIT_HCA_QPC_OFFSET              0x020
 #define  INIT_HCA_QPC_BASE_OFFSET        (INIT_HCA_QPC_OFFSET + 0x10)
 #define  INIT_HCA_LOG_QP_OFFSET          (INIT_HCA_QPC_OFFSET + 0x17)
@@ -1320,15 +1321,18 @@ int mthca_INIT_HCA(struct mthca_dev *dev,
 
         memset(inbox, 0, INIT_HCA_IN_SIZE);
 
+        if (dev->mthca_flags & MTHCA_FLAG_SINAI_OPT)
+                MTHCA_PUT(inbox, 0x1, INIT_HCA_FLAGS1_OFFSET);
+
 #if defined(__LITTLE_ENDIAN)
-        *(inbox + INIT_HCA_FLAGS_OFFSET / 4) &= ~cpu_to_be32(1 << 1);
+        *(inbox + INIT_HCA_FLAGS2_OFFSET / 4) &= ~cpu_to_be32(1 << 1);
 #elif defined(__BIG_ENDIAN)
-        *(inbox + INIT_HCA_FLAGS_OFFSET / 4) |= cpu_to_be32(1 << 1);
+        *(inbox + INIT_HCA_FLAGS2_OFFSET / 4) |= cpu_to_be32(1 << 1);
 #else
 #error Host endianness not defined
 #endif
         /* Check port for UD address vector: */
-        *(inbox + INIT_HCA_FLAGS_OFFSET / 4) |= cpu_to_be32(1);
+        *(inbox + INIT_HCA_FLAGS2_OFFSET / 4) |= cpu_to_be32(1);
 
         /* We leave wqe_quota, responder_exu, etc as 0 (default) */