ice: improve updating ice_{t,r}x_ring::xsk_pool

xsk_buff_pool pointers that ice ring structs hold are updated via
ndo_bpf that is executed in process context while it can be read by
remote CPU at the same time within NAPI poll. Use synchronize_net()
after pointer update and {READ,WRITE}_ONCE() when working with mentioned
pointer.

Fixes: 2d4238f5 ("ice: Add support for AF_XDP")
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

drivers/net/ethernet/intel/ice/ice.h

@@ -765,18 +765,17 @@ static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi,
 }
 
 /**
- * ice_xsk_pool - get XSK buffer pool bound to a ring
+ * ice_rx_xsk_pool - assign XSK buff pool to Rx ring
  * @ring: Rx ring to use
  *
- * Returns a pointer to xsk_buff_pool structure if there is a buffer pool
- * present, NULL otherwise.
+ * Sets XSK buff pool pointer on Rx ring.
  */
-static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
+static inline void ice_rx_xsk_pool(struct ice_rx_ring *ring)
 {
 	struct ice_vsi *vsi = ring->vsi;
 	u16 qid = ring->q_index;
 
-	return ice_get_xp_from_qid(vsi, qid);
+	WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
 }
 
 /**
@@ -801,7 +800,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
 	if (!ring)
 		return;
 
-	ring->xsk_pool = ice_get_xp_from_qid(vsi, qid);
+	WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
 }
 
 /**

drivers/net/ethernet/intel/ice/ice_base.c

@@ -536,7 +536,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 				return err;
 		}
 
-		ring->xsk_pool = ice_xsk_pool(ring);
+		ice_rx_xsk_pool(ring);
 		if (ring->xsk_pool) {
 			xdp_rxq_info_unreg(&ring->xdp_rxq);
 
@@ -597,7 +597,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			return 0;
 		}
 
-		ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
+		ok = ice_alloc_rx_bufs_zc(ring, ring->xsk_pool, num_bufs);
 		if (!ok) {
 			u16 pf_q = ring->vsi->rxq_map[ring->q_index];
 

drivers/net/ethernet/intel/ice/ice_main.c

@@ -2948,7 +2948,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi)
 	ice_for_each_rxq(vsi, i) {
 		struct ice_rx_ring *rx_ring = vsi->rx_rings[i];
 
-		if (rx_ring->xsk_pool)
+		if (READ_ONCE(rx_ring->xsk_pool))
 			napi_schedule(&rx_ring->q_vector->napi);
 	}
 }

drivers/net/ethernet/intel/ice/ice_txrx.c

@@ -1521,10 +1521,11 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	ice_for_each_tx_ring(tx_ring, q_vector->tx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(tx_ring->xsk_pool);
 		bool wd;
 
-		if (tx_ring->xsk_pool)
-			wd = ice_xmit_zc(tx_ring);
+		if (xsk_pool)
+			wd = ice_xmit_zc(tx_ring, xsk_pool);
 		else if (ice_ring_is_xdp(tx_ring))
 			wd = true;
 		else
@@ -1550,6 +1551,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		budget_per_ring = budget;
 
 	ice_for_each_rx_ring(rx_ring, q_vector->rx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool);
 		int cleaned;
 
 		/* A dedicated path for zero-copy allows making a single
@@ -1557,7 +1559,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		 * ice_clean_rx_irq function and makes the codebase cleaner.
 		 */
 		cleaned = rx_ring->xsk_pool ?
-			  ice_clean_rx_irq_zc(rx_ring, budget_per_ring) :
+			  ice_clean_rx_irq_zc(rx_ring, xsk_pool, budget_per_ring) :
 			  ice_clean_rx_irq(rx_ring, budget_per_ring);
 		work_done += cleaned;
 		/* if we clean as many as budgeted, we must not be done */

drivers/net/ethernet/intel/ice/ice_xsk.h

@@ -20,16 +20,20 @@ struct ice_vsi;
 #ifdef CONFIG_XDP_SOCKETS
 int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool,
 		       u16 qid);
-int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget);
+int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
+			struct xsk_buff_pool *xsk_pool,
+			int budget);
 int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags);
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count);
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+			  struct xsk_buff_pool *xsk_pool, u16 count);
 bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
 void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring);
 void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring);
-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring);
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool);
 int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc);
 #else
-static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring)
+static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring,
+			       struct xsk_buff_pool __always_unused *xsk_pool)
 {
 	return false;
 }
@@ -44,6 +48,7 @@ ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi,
 
 static inline int
 ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
+		    struct xsk_buff_pool __always_unused *xsk_pool,
 		    int __always_unused budget)
 {
 	return 0;
@@ -51,6 +56,7 @@ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
 
 static inline bool
 ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring,
+		     struct xsk_buff_pool __always_unused *xsk_pool,
 		     u16 __always_unused count)
 {
 	return false;