Commit f35faa4b authored by Parav Pandit's avatar Parav Pandit Committed by Jason Gunthorpe

IB/core: Simplify ib_query_gid to always refer to cache

Currently following inconsistencies exist.
1. ib_query_gid() returns GID from the software cache for a RoCE port
and returns GID from the HCA for an IB port.
This is incorrect because software GID cache is maintained regardless
of HCA port type.

2. GID is queries from the HCA via ib_query_gid and updated in the
software cache for IB link layer. Both of them might not be in sync.

ULPs such as SRP initiator, SRP target, IPoIB driver have historically
used ib_query_gid() API to query the GID. However CM used cached version
during CM processing, When software cache was introduced, this
inconsitency remained.

In order to simplify, improve readability and avoid link layer
specific above inconsistencies, this patch brings following changes.

1. ib_query_gid() always refers to the cache layer regardless of link
layer.

2. cache module who reads the GID entry from HCA and builds the cache,
directly invokes the HCA provider verb's query_gid() callback function.

3. ib_query_port() is being called in early stage where GID cache is not
yet build while reading port immutable property. Therefore it needs to
read the default GID from the HCA for IB link layer to publish the
subnet prefix.
Signed-off-by: default avatarParav Pandit <parav@mellanox.com>
Signed-off-by: default avatarLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
parent 0e1f9b92
...@@ -1116,8 +1116,8 @@ static void ib_cache_update(struct ib_device *device, ...@@ -1116,8 +1116,8 @@ static void ib_cache_update(struct ib_device *device,
if (!use_roce_gid_table) { if (!use_roce_gid_table) {
for (i = 0; i < gid_cache->table_len; ++i) { for (i = 0; i < gid_cache->table_len; ++i) {
ret = ib_query_gid(device, port, i, ret = device->query_gid(device, port, i,
gid_cache->table + i, NULL); gid_cache->table + i);
if (ret) { if (ret) {
pr_warn("ib_query_gid failed (%d) for %s (index %d)\n", pr_warn("ib_query_gid failed (%d) for %s (index %d)\n",
ret, device->name, i); ret, device->name, i);
......
...@@ -853,7 +853,7 @@ int ib_query_port(struct ib_device *device, ...@@ -853,7 +853,7 @@ int ib_query_port(struct ib_device *device,
if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND) if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND)
return 0; return 0;
err = ib_query_gid(device, port_num, 0, &gid, NULL); err = device->query_gid(device, port_num, 0, &gid);
if (err) if (err)
return err; return err;
...@@ -871,22 +871,13 @@ EXPORT_SYMBOL(ib_query_port); ...@@ -871,22 +871,13 @@ EXPORT_SYMBOL(ib_query_port);
* @attr: Returned GID attributes related to this GID index (only in RoCE). * @attr: Returned GID attributes related to this GID index (only in RoCE).
* NULL means ignore. * NULL means ignore.
* *
* ib_query_gid() fetches the specified GID table entry. * ib_query_gid() fetches the specified GID table entry from the cache.
*/ */
int ib_query_gid(struct ib_device *device, int ib_query_gid(struct ib_device *device,
u8 port_num, int index, union ib_gid *gid, u8 port_num, int index, union ib_gid *gid,
struct ib_gid_attr *attr) struct ib_gid_attr *attr)
{ {
if (rdma_protocol_roce(device, port_num))
return ib_get_cached_gid(device, port_num, index, gid, attr); return ib_get_cached_gid(device, port_num, index, gid, attr);
if (attr)
return -EINVAL;
if (!device->query_gid)
return -EOPNOTSUPP;
return device->query_gid(device, port_num, index, gid);
} }
EXPORT_SYMBOL(ib_query_gid); EXPORT_SYMBOL(ib_query_gid);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment