net: page_pool: don't try to stash the napi id

Page ppol tried to cache the NAPI ID in page pool info to avoid
having a dependency on the life cycle of the NAPI instance.
Since commit under Fixes the NAPI ID is not populated until
napi_enable() and there's a good chance that page pool is
created before NAPI gets enabled.

Protect the NAPI pointer with the existing page pool mutex,
the reading path already holds it. napi_id itself we need
to READ_ONCE(), it's protected by netdev_lock() which are
not holding in page pool.

Before this patch napi IDs were missing for mlx5:

# ./cli.py --spec netlink/specs/netdev.yaml --dump page-pool-get

[{'id': 144, 'ifindex': 2, 'inflight': 3072, 'inflight-mem': 12582912},
{'id': 143, 'ifindex': 2, 'inflight': 5568, 'inflight-mem': 22806528},
{'id': 142, 'ifindex': 2, 'inflight': 5120, 'inflight-mem': 20971520},
{'id': 141, 'ifindex': 2, 'inflight': 4992, 'inflight-mem': 20447232},
...

After:

[{'id': 144, 'ifindex': 2, 'inflight': 3072, 'inflight-mem': 12582912,
'napi-id': 565},
{'id': 143, 'ifindex': 2, 'inflight': 4224, 'inflight-mem': 17301504,
'napi-id': 525},
{'id': 142, 'ifindex': 2, 'inflight': 4288, 'inflight-mem': 17563648,
'napi-id': 524},
...

Fixes: 86e25f40aa1e ("net: napi: Add napi_config")
Reviewed-by: Mina Almasry <[e-mail]>
Reviewed-by: Toke Høiland-Jørgensen <[e-mail]>
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

include/net/page_pool/types.h

···
 	struct {
 		struct hlist_node list;
 		u64 detach_time;
-		u32 napi_id;
 		u32 id;
 	} user;
 };

net/core/dev.c

···
 static void __napi_hash_add_with_id(struct napi_struct *napi,
 				    unsigned int napi_id)
 {
-	napi->napi_id = napi_id;
+	WRITE_ONCE(napi->napi_id, napi_id);
 	hlist_add_head_rcu(&napi->napi_hash_node,
 			   &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
 }

net/core/page_pool.c

···
 	WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state));
 	WARN_ON(READ_ONCE(pool->p.napi->list_owner) != -1);
 
+	mutex_lock(&page_pools_lock);
 	WRITE_ONCE(pool->p.napi, NULL);
+	mutex_unlock(&page_pools_lock);
 }
 EXPORT_SYMBOL(page_pool_disable_direct_recycling);
 

net/core/page_pool_priv.h

···
 
 #include "netmem_priv.h"
 
+extern struct mutex page_pools_lock;
+
 s32 page_pool_inflight(const struct page_pool *pool, bool strict);
 
 int page_pool_list(struct page_pool *pool);

net/core/page_pool_user.c

···
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/xarray.h>
+#include <net/busy_poll.h>
 #include <net/net_debug.h>
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
···
 #include "netdev-genl-gen.h"
 
 static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1);
-/* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user.
+/* Protects: page_pools, netdevice->page_pools, pool->p.napi, pool->slow.netdev,
+ *	pool->user.
  * Ordering: inside rtnl_lock
  */
-static DEFINE_MUTEX(page_pools_lock);
+DEFINE_MUTEX(page_pools_lock);
 
 /* Page pools are only reachable from user space (via netlink) if they are
  * linked to a netdev at creation time. Following page pool "visibility"
···
 {
 	struct net_devmem_dmabuf_binding *binding = pool->mp_priv;
 	size_t inflight, refsz;
+	unsigned int napi_id;
 	void *hdr;
 
 	hdr = genlmsg_iput(rsp, info);
···
 	    nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX,
 			pool->slow.netdev->ifindex))
 		goto err_cancel;
-	if (pool->user.napi_id &&
-	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id))
+
+	napi_id = pool->p.napi ? READ_ONCE(pool->p.napi->napi_id) : 0;
+	if (napi_id >= MIN_NAPI_ID &&
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, napi_id))
 		goto err_cancel;
 
 	inflight = page_pool_inflight(pool, false);
···
 	if (pool->slow.netdev) {
 		hlist_add_head(&pool->user.list,
 			       &pool->slow.netdev->page_pools);
-		pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0;
-
 		netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF);
 	}