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: 2d4238f55697 ("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>

1 files changed, 64 insertions, 39 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 3fbe4cfadfbf..ee084ad80a61 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -250,6 +250,8 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 	ice_qvec_toggle_napi(vsi, q_vector, true);
 	ice_qvec_ena_irq(vsi, q_vector);
 
+	/* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */
+	synchronize_net();
 	ice_get_link_status(vsi->port_info, &link_up);
 	if (link_up) {
 		netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
@@ -464,6 +466,7 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
 /**
  * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
  * @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
  * @count: The number of buffers to allocate
  *
  * Place the @count of descriptors onto Rx ring. Handle the ring wrap
@@ -472,7 +475,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
  *
  * Returns true if all allocations were successful, false if any fail.
  */
-static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+				   struct xsk_buff_pool *xsk_pool, u16 count)
 {
 	u32 nb_buffs_extra = 0, nb_buffs = 0;
 	union ice_32b_rx_flex_desc *rx_desc;
@@ -484,8 +488,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	xdp = ice_xdp_buf(rx_ring, ntu);
 
 	if (ntu + count >= rx_ring->count) {
-		nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp,
-						   rx_desc,
+		nb_buffs_extra = ice_fill_rx_descs(xsk_pool, xdp, rx_desc,
 						   rx_ring->count - ntu);
 		if (nb_buffs_extra != rx_ring->count - ntu) {
 			ntu += nb_buffs_extra;
@@ -498,7 +501,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 		ice_release_rx_desc(rx_ring, 0);
 	}
 
-	nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count);
+	nb_buffs = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, count);
 
 	ntu += nb_buffs;
 	if (ntu == rx_ring->count)
@@ -514,6 +517,7 @@ exit:
 /**
  * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
  * @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
  * @count: The number of buffers to allocate
  *
  * Wrapper for internal allocation routine; figure out how many tail
@@ -521,7 +525,8 @@ exit:
  *
  * Returns true if all calls to internal alloc routine succeeded
  */
-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)
 {
 	u16 rx_thresh = ICE_RING_QUARTER(rx_ring);
 	u16 leftover, i, tail_bumps;
@@ -530,9 +535,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	leftover = count - (tail_bumps * rx_thresh);
 
 	for (i = 0; i < tail_bumps; i++)
-		if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh))
+		if (!__ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, rx_thresh))
 			return false;
-	return __ice_alloc_rx_bufs_zc(rx_ring, leftover);
+	return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover);
 }
 
 /**
@@ -601,8 +606,10 @@ out:
 /**
  * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
  * @xdp_ring: XDP Tx ring
+ * @xsk_pool: AF_XDP buffer pool pointer
  */
-static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring,
+				struct xsk_buff_pool *xsk_pool)
 {
 	u16 ntc = xdp_ring->next_to_clean;
 	struct ice_tx_desc *tx_desc;
@@ -653,7 +660,7 @@ skip:
 	if (xdp_ring->next_to_clean >= cnt)
 		xdp_ring->next_to_clean -= cnt;
 	if (xsk_frames)
-		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+		xsk_tx_completed(xsk_pool, xsk_frames);
 
 	return completed_frames;
 }
@@ -662,6 +669,7 @@ skip:
  * ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX
  * @xdp: XDP buffer to xmit
  * @xdp_ring: XDP ring to produce descriptor onto
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * note that this function works directly on xdp_buff, no need to convert
  * it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning
@@ -671,7 +679,8 @@ skip:
  * was not enough space on XDP ring
  */
 static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
-			      struct ice_tx_ring *xdp_ring)
+			      struct ice_tx_ring *xdp_ring,
+			      struct xsk_buff_pool *xsk_pool)
 {
 	struct skb_shared_info *sinfo = NULL;
 	u32 size = xdp->data_end - xdp->data;
@@ -685,7 +694,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
 
 	free_space = ICE_DESC_UNUSED(xdp_ring);
 	if (free_space < ICE_RING_QUARTER(xdp_ring))
-		free_space += ice_clean_xdp_irq_zc(xdp_ring);
+		free_space += ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
 
 	if (unlikely(!free_space))
 		goto busy;
@@ -705,7 +714,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
 		dma_addr_t dma;
 
 		dma = xsk_buff_xdp_get_dma(xdp);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+		xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, size);
 
 		tx_buf->xdp = xdp;
 		tx_buf->type = ICE_TX_BUF_XSK_TX;
@@ -747,12 +756,14 @@ busy:
  * @xdp: xdp_buff used as input to the XDP program
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
 static int
 ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-	       struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring)
+	       struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
+	       struct xsk_buff_pool *xsk_pool)
 {
 	int err, result = ICE_XDP_PASS;
 	u32 act;
@@ -763,7 +774,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
 		if (!err)
 			return ICE_XDP_REDIR;
-		if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+		if (xsk_uses_need_wakeup(xsk_pool) && err == -ENOBUFS)
 			result = ICE_XDP_EXIT;
 		else
 			result = ICE_XDP_CONSUMED;
@@ -774,7 +785,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	case XDP_PASS:
 		break;
 	case XDP_TX:
-		result = ice_xmit_xdp_tx_zc(xdp, xdp_ring);
+		result = ice_xmit_xdp_tx_zc(xdp, xdp_ring, xsk_pool);
 		if (result == ICE_XDP_CONSUMED)
 			goto out_failure;
 		break;
@@ -826,14 +837,16 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
 /**
  * ice_clean_rx_irq_zc - consumes packets from the hardware ring
  * @rx_ring: AF_XDP Rx ring
+ * @xsk_pool: AF_XDP buffer pool pointer
  * @budget: NAPI budget
  *
  * Returns number of processed packets on success, remaining budget on failure.
  */
-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)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
-	struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool;
 	u32 ntc = rx_ring->next_to_clean;
 	u32 ntu = rx_ring->next_to_use;
 	struct xdp_buff *first = NULL;
@@ -896,7 +909,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring);
+		xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring,
+					 xsk_pool);
 		if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
 			xdp_xmit |= xdp_res;
 		} else if (xdp_res == ICE_XDP_EXIT) {
@@ -945,7 +959,8 @@ construct_skb:
 	rx_ring->next_to_clean = ntc;
 	entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring);
 	if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
-		failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc);
+		failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool,
+						 entries_to_alloc);
 
 	ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
@@ -968,17 +983,19 @@ construct_skb:
 /**
  * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor
  * @xdp_ring: XDP ring to produce the HW Tx descriptor on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @desc: AF_XDP descriptor to pull the DMA address and length from
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
+static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring,
+			 struct xsk_buff_pool *xsk_pool, struct xdp_desc *desc,
 			 unsigned int *total_bytes)
 {
 	struct ice_tx_desc *tx_desc;
 	dma_addr_t dma;
 
-	dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr);
-	xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len);
+	dma = xsk_buff_raw_get_dma(xsk_pool, desc->addr);
+	xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, desc->len);
 
 	tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
 	tx_desc->buf_addr = cpu_to_le64(dma);
@@ -991,10 +1008,13 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
 /**
  * ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
+static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring,
+			       struct xsk_buff_pool *xsk_pool,
+			       struct xdp_desc *descs,
 			       unsigned int *total_bytes)
 {
 	u16 ntu = xdp_ring->next_to_use;
@@ -1004,8 +1024,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
 	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
 		dma_addr_t dma;
 
-		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len);
+		dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
+		xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len);
 
 		tx_desc = ICE_TX_DESC(xdp_ring, ntu++);
 		tx_desc->buf_addr = cpu_to_le64(dma);
@@ -1021,37 +1041,41 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
 /**
  * ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
  * @nb_pkts: count of packets to be send
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
-				u32 nb_pkts, unsigned int *total_bytes)
+static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring,
+				struct xsk_buff_pool *xsk_pool,
+				struct xdp_desc *descs, u32 nb_pkts,
+				unsigned int *total_bytes)
 {
 	u32 batched, leftover, i;
 
 	batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH);
 	leftover = nb_pkts & (PKTS_PER_BATCH - 1);
 	for (i = 0; i < batched; i += PKTS_PER_BATCH)
-		ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
+		ice_xmit_pkt_batch(xdp_ring, xsk_pool, &descs[i], total_bytes);
 	for (; i < batched + leftover; i++)
-		ice_xmit_pkt(xdp_ring, &descs[i], total_bytes);
+		ice_xmit_pkt(xdp_ring, xsk_pool, &descs[i], total_bytes);
 }
 
 /**
  * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * Returns true if there is no more work that needs to be done, false otherwise
  */
-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)
 {
-	struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs;
+	struct xdp_desc *descs = xsk_pool->tx_descs;
 	u32 nb_pkts, nb_processed = 0;
 	unsigned int total_bytes = 0;
 	int budget;
 
-	ice_clean_xdp_irq_zc(xdp_ring);
+	ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
 
 	if (!netif_carrier_ok(xdp_ring->vsi->netdev) ||
 	    !netif_running(xdp_ring->vsi->netdev))
@@ -1060,25 +1084,26 @@ bool ice_xmit_zc(struct ice_tx_ring *xdp_ring)
 	budget = ICE_DESC_UNUSED(xdp_ring);
 	budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring));
 
-	nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget);
+	nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget);
 	if (!nb_pkts)
 		return true;
 
 	if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
 		nb_processed = xdp_ring->count - xdp_ring->next_to_use;
-		ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
+		ice_fill_tx_hw_ring(xdp_ring, xsk_pool, descs, nb_processed,
+				    &total_bytes);
 		xdp_ring->next_to_use = 0;
 	}
 
-	ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
-			    &total_bytes);
+	ice_fill_tx_hw_ring(xdp_ring, xsk_pool, &descs[nb_processed],
+			    nb_pkts - nb_processed, &total_bytes);
 
 	ice_set_rs_bit(xdp_ring);
 	ice_xdp_ring_update_tail(xdp_ring);
 	ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes);
 
-	if (xsk_uses_need_wakeup(xdp_ring->xsk_pool))
-		xsk_set_tx_need_wakeup(xdp_ring->xsk_pool);
+	if (xsk_uses_need_wakeup(xsk_pool))
+		xsk_set_tx_need_wakeup(xsk_pool);
 
 	return nb_pkts < budget;
 }
@@ -1111,7 +1136,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
 
 	ring = vsi->rx_rings[queue_id]->xdp_ring;
 
-	if (!ring->xsk_pool)
+	if (!READ_ONCE(ring->xsk_pool))
 		return -EINVAL;
 
 	/* The idea here is that if NAPI is running, mark a miss, so