IB/core: Handle table with full and partial membership for the same P_Key

Extend the cached and non-cached P_Key table lookups to handle limited
and full membership of the same P_Key to co-exist in the P_Key table.

This is necessary for SR-IOV, to allow for some guests would to have
the full membership P_Key in their virtual P_Key table, while other
guests on the same physical HCA would have the limited one.
To support this, we need both the limited and full membership P_Keys
to be present in the master's (hypervisor physical port) P_Key table.

The algorithm for handling P_Key tables which contain both the limited
and the full membership versions of the same P_Key works as follows:

When scanning the P_Key table for a 15-bit P_Key:

A. If there is a full member version of that P_Key anywhere in the
    table, return its index (even if a limited-member version of the
    P_Key exists earlier in the table).

B. If the full member version is not in the table, but the
   limited-member version is in the table, return the index of the
   limited P_Key.

Signed-off-by: Liran Liss <liranl@mellanox.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

2 files changed, 25 insertions, 6 deletions

diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index 9353992f9eea..4da381b74f54 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -167,6 +167,7 @@ int ib_find_cached_pkey(struct ib_device *device,
         unsigned long flags;
         int i;
         int ret = -ENOENT;
+        int partial_ix = -1;
 
         if (port_num < start_port(device) || port_num > end_port(device))
                 return -EINVAL;
@@ -179,11 +180,19 @@ int ib_find_cached_pkey(struct ib_device *device,
 
         for (i = 0; i < cache->table_len; ++i)
                 if ((cache->table[i] & 0x7fff) == (pkey & 0x7fff)) {
-                        *index = i;
-                        ret = 0;
-                        break;
+                        if (cache->table[i] & 0x8000) {
+                                *index = i;
+                                ret = 0;
+                                break;
+                        } else
+                                partial_ix = i;
                 }
 
+        if (ret && partial_ix >= 0) {
+                *index = partial_ix;
+                ret = 0;
+        }
+
         read_unlock_irqrestore(&device->cache.lock, flags);
 
         return ret;
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index e711de400a01..18c1ece765f2 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -707,18 +707,28 @@ int ib_find_pkey(struct ib_device *device,
 {
         int ret, i;
         u16 tmp_pkey;
+        int partial_ix = -1;
 
         for (i = 0; i < device->pkey_tbl_len[port_num - start_port(device)]; ++i) {
                 ret = ib_query_pkey(device, port_num, i, &tmp_pkey);
                 if (ret)
                         return ret;
-
                 if ((pkey & 0x7fff) == (tmp_pkey & 0x7fff)) {
-                        *index = i;
-                        return 0;
+                        /* if there is full-member pkey take it.*/
+                        if (tmp_pkey & 0x8000) {
+                                *index = i;
+                                return 0;
+                        }
+                        if (partial_ix < 0)
+                                partial_ix = i;
                 }
         }
 
+        /*no full-member, if exists take the limited*/
+        if (partial_ix >= 0) {
+                *index = partial_ix;
+                return 0;
+        }
         return -ENOENT;
 }
 EXPORT_SYMBOL(ib_find_pkey);