Several fiels in an incoming MAD extended info header were passed at incorrect
offsets (mostly off by 4 bytes). As the result, the HCA will fail to generate
traps in which this info is needed (e.g. traps which include the GRH of the
incoming packet), in violation of the IB spec.
Signed-off-by: Michael S. Tsirkin <[EMAIL PROTECTED]>
---
Roland, the offsets look wrong. Am I missing something?
Please review vs the spec, and if correct consider for 2.6.19.
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c
b/drivers/infiniband/hw/mthca/mthca_cmd.c
index 99a94d7..768df72 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -1820,11 +1820,11 @@ int mthca_MAD_IFC(struct mthca_dev *dev,
#define MAD_IFC_BOX_SIZE 0x400
#define MAD_IFC_MY_QPN_OFFSET 0x100
-#define MAD_IFC_RQPN_OFFSET 0x104
-#define MAD_IFC_SL_OFFSET 0x108
-#define MAD_IFC_G_PATH_OFFSET 0x109
-#define MAD_IFC_RLID_OFFSET 0x10a
-#define MAD_IFC_PKEY_OFFSET 0x10e
+#define MAD_IFC_RQPN_OFFSET 0x108
+#define MAD_IFC_SL_OFFSET 0x10c
+#define MAD_IFC_G_PATH_OFFSET 0x10d
+#define MAD_IFC_RLID_OFFSET 0x10e
+#define MAD_IFC_PKEY_OFFSET 0x112
#define MAD_IFC_GRH_OFFSET 0x140
inmailbox = mthca_alloc_mailbox(dev, GFP_KERNEL);
@@ -1862,7 +1862,7 @@ #define MAD_IFC_GRH_OFFSET 0x140
val = in_wc->dlid_path_bits |
(in_wc->wc_flags & IB_WC_GRH ? 0x80 : 0);
- MTHCA_PUT(inbox, val, MAD_IFC_GRH_OFFSET);
+ MTHCA_PUT(inbox, val, MAD_IFC_G_PATH_OFFSET);
MTHCA_PUT(inbox, in_wc->slid, MAD_IFC_RLID_OFFSET);
MTHCA_PUT(inbox, in_wc->pkey_index, MAD_IFC_PKEY_OFFSET);
@@ -1870,7 +1870,7 @@ #define MAD_IFC_GRH_OFFSET 0x140
if (in_grh)
memcpy(inbox + MAD_IFC_GRH_OFFSET, in_grh, 40);
- op_modifier |= 0x10;
+ op_modifier |= 0x4;
in_modifier |= in_wc->slid << 16;
}
--
MST
_______________________________________________
openib-general mailing list
openib-general@openib.org
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
