xsk: remove AF_XDP socket from map when the socket is released

When an AF_XDP socket is released/closed the XSKMAP still holds a
reference to the socket in a "released" state. The socket will still
use the netdev queue resource, and block newly created sockets from
attaching to that queue, but no user application can access the
fill/complete/rx/tx queues. This results in that all applications need
to explicitly clear the map entry from the old "zombie state"
socket. This should be done automatically.

In this patch, the sockets tracks, and have a reference to, which maps
it resides in. When the socket is released, it will remove itself from
all maps.

Suggested-by: Bruce Richardson <bruce.richardson@intel.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 18 insertions, 0 deletions

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 6aebea2b18cb..f023b9940d64 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -55,6 +55,16 @@ struct xdp_umem {
 	struct list_head xsk_list;
 };
 
+/* Nodes are linked in the struct xdp_sock map_list field, and used to
+ * track which maps a certain socket reside in.
+ */
+struct xsk_map;
+struct xsk_map_node {
+	struct list_head node;
+	struct xsk_map *map;
+	struct xdp_sock **map_entry;
+};
+
 struct xdp_sock {
 	/* struct sock must be the first member of struct xdp_sock */
 	struct sock sk;
@@ -80,6 +90,9 @@ struct xdp_sock {
 	/* Protects generic receive. */
 	spinlock_t rx_lock;
 	u64 rx_dropped;
+	struct list_head map_list;
+	/* Protects map_list */
+	spinlock_t map_list_lock;
 };
 
 struct xdp_buff;
@@ -106,6 +119,11 @@ void xsk_clear_rx_need_wakeup(struct xdp_umem *umem);
 void xsk_clear_tx_need_wakeup(struct xdp_umem *umem);
 bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem);
 
+void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
+			     struct xdp_sock **map_entry);
+int xsk_map_inc(struct xsk_map *map);
+void xsk_map_put(struct xsk_map *map);
+
 static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
 {
 	return umem->pages[addr >> PAGE_SHIFT].addr + (addr & (PAGE_SIZE - 1));