RDMA/core: Extend RDMA device registration to be net namespace aware

Presently, RDMA devices are always registered within the init network
namespace, even if the associated devlink device's namespace was
changed via a devlink reload. This mismatch leads to discrepancies
between the network namespace of the devlink device and that of the
RDMA device.

Therefore, extend the RDMA device allocation API to optionally take
the net namespace. This isn't limited to devices that support devlink
but allows all users to provide the network namespace if they need to
do so.

If a network namespace is provided during device allocation, it's up
to the caller to make sure the namespace stays valid until
ib_register_device() is called.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 468ed6bd472207054eff714f8b8d9d8a3dd1408a..c0f8b8cba7c0eadc6321d89d1c268106c28dc169 100644 (file)
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -557,6 +557,8 @@ static void rdma_init_coredev(struct ib_core_device *coredev,
 /**
  * _ib_alloc_device - allocate an IB device struct
  * @size:size of structure to allocate
+ * @net: network namespace device should be located in, namespace
+ *       must stay valid until ib_register_device() is completed.
  *
  * Low-level drivers should use ib_alloc_device() to allocate &struct
  * ib_device.  @size is the size of the structure to be allocated,
@@ -564,7 +566,7 @@ static void rdma_init_coredev(struct ib_core_device *coredev,
  * ib_dealloc_device() must be used to free structures allocated with
  * ib_alloc_device().
  */
-struct ib_device *_ib_alloc_device(size_t size)
+struct ib_device *_ib_alloc_device(size_t size, struct net *net)
 {
        struct ib_device *device;
        unsigned int i;
@@ -581,7 +583,15 @@ struct ib_device *_ib_alloc_device(size_t size)
                return NULL;
        }
 
-       rdma_init_coredev(&device->coredev, device, &init_net);
+       /* ib_devices_shared_netns can't change while we have active namespaces
+        * in the system which means either init_net is passed or the user has
+        * no idea what they are doing.
+        *
+        * To avoid breaking backward compatibility, when in shared mode,
+        * force to init the device in the init_net.
+        */
+       net = ib_devices_shared_netns ? &init_net : net;
+       rdma_init_coredev(&device->coredev, device, net);
 
        INIT_LIST_HEAD(&device->event_handler_list);
        spin_lock_init(&device->qp_open_list_lock);

diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c
index 5499025e8a0add4b4e1d3bab5b64eabf38afc048..d22d610c26963f95fe55ce7adbe2b83194d312c4 100644 (file)
--- a/drivers/infiniband/sw/rdmavt/vt.c
+++ b/drivers/infiniband/sw/rdmavt/vt.c
@@ -49,7 +49,7 @@ struct rvt_dev_info *rvt_alloc_device(size_t size, int nports)
 {
        struct rvt_dev_info *rdi;
 
-       rdi = container_of(_ib_alloc_device(size), struct rvt_dev_info, ibdev);
+       rdi = container_of(_ib_alloc_device(size, &init_net), struct rvt_dev_info, ibdev);
        if (!rdi)
                return rdi;
 

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 38f68d245fa6e20a923bf6993570d9ab695c2c16..b91a812348320a7e220098323a6181ef137847ef 100644 (file)
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2914,11 +2914,18 @@ struct ib_block_iter {
        unsigned int __pg_bit;          /* alignment of current block */
 };
 
-struct ib_device *_ib_alloc_device(size_t size);
+struct ib_device *_ib_alloc_device(size_t size, struct net *net);
 #define ib_alloc_device(drv_struct, member)                                    \
        container_of(_ib_alloc_device(sizeof(struct drv_struct) +              \
                                      BUILD_BUG_ON_ZERO(offsetof(              \
-                                             struct drv_struct, member))),    \
+                                             struct drv_struct, member)),     \
+                                     &init_net),                              \
+                    struct drv_struct, member)
+
+#define ib_alloc_device_with_net(drv_struct, member, net)                     \
+       container_of(_ib_alloc_device(sizeof(struct drv_struct) +              \
+                                     BUILD_BUG_ON_ZERO(offsetof(              \
+                                       struct drv_struct, member)), net),     \
                     struct drv_struct, member)
 
 void ib_dealloc_device(struct ib_device *device);