1 files changed, 352 insertions, 491 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 0b7d29192b2c..cd7b52fb6b46 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -2,83 +2,91 @@
 /* Copyright(c) 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
-#include <net/xdp_sock.h>
+#include <linux/stringify.h>
+#include <net/xdp_sock_drv.h>
 #include <net/xdp.h>
 
 #include "i40e.h"
 #include "i40e_txrx_common.h"
 #include "i40e_xsk.h"
 
+void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring)
+{
+	memset(rx_ring->rx_bi_zc, 0,
+	       sizeof(*rx_ring->rx_bi_zc) * rx_ring->count);
+}
+
+static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
+{
+	return &rx_ring->rx_bi_zc[idx];
+}
+
 /**
- * i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev
- * @vsi: Current VSI
- * @umem: UMEM to DMA map
+ * i40e_realloc_rx_xdp_bi - reallocate SW ring for either XSK or normal buffer
+ * @rx_ring: Current rx ring
+ * @pool_present: is pool for XSK present
  *
- * Returns 0 on success, <0 on failure
- **/
-static int i40e_xsk_umem_dma_map(struct i40e_vsi *vsi, struct xdp_umem *umem)
+ * Try allocating memory and return ENOMEM, if failed to allocate.
+ * If allocation was successful, substitute buffer with allocated one.
+ * Returns 0 on success, negative on failure
+ */
+static int i40e_realloc_rx_xdp_bi(struct i40e_ring *rx_ring, bool pool_present)
 {
-	struct i40e_pf *pf = vsi->back;
-	struct device *dev;
-	unsigned int i, j;
-	dma_addr_t dma;
+	size_t elem_size = pool_present ? sizeof(*rx_ring->rx_bi_zc) :
+					  sizeof(*rx_ring->rx_bi);
+	void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL);
 
-	dev = &pf->pdev->dev;
-	for (i = 0; i < umem->npgs; i++) {
-		dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE,
-					 DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
-		if (dma_mapping_error(dev, dma))
-			goto out_unmap;
+	if (!sw_ring)
+		return -ENOMEM;
 
-		umem->pages[i].dma = dma;
+	if (pool_present) {
+		kfree(rx_ring->rx_bi);
+		rx_ring->rx_bi = NULL;
+		rx_ring->rx_bi_zc = sw_ring;
+	} else {
+		kfree(rx_ring->rx_bi_zc);
+		rx_ring->rx_bi_zc = NULL;
+		rx_ring->rx_bi = sw_ring;
 	}
-
 	return 0;
-
-out_unmap:
-	for (j = 0; j < i; j++) {
-		dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
-				     DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
-		umem->pages[i].dma = 0;
-	}
-
-	return -1;
 }
 
 /**
- * i40e_xsk_umem_dma_unmap - DMA unmaps all UMEM memory for the netdev
+ * i40e_realloc_rx_bi_zc - reallocate rx SW rings
  * @vsi: Current VSI
- * @umem: UMEM to DMA map
- **/
-static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem)
+ * @zc: is zero copy set
+ *
+ * Reallocate buffer for rx_rings that might be used by XSK.
+ * XDP requires more memory, than rx_buf provides.
+ * Returns 0 on success, negative on failure
+ */
+int i40e_realloc_rx_bi_zc(struct i40e_vsi *vsi, bool zc)
 {
-	struct i40e_pf *pf = vsi->back;
-	struct device *dev;
-	unsigned int i;
-
-	dev = &pf->pdev->dev;
-
-	for (i = 0; i < umem->npgs; i++) {
-		dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE,
-				     DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR);
+	struct i40e_ring *rx_ring;
+	unsigned long q;
 
-		umem->pages[i].dma = 0;
+	for_each_set_bit(q, vsi->af_xdp_zc_qps, vsi->alloc_queue_pairs) {
+		rx_ring = vsi->rx_rings[q];
+		if (i40e_realloc_rx_xdp_bi(rx_ring, zc))
+			return -ENOMEM;
 	}
+	return 0;
 }
 
 /**
- * i40e_xsk_umem_enable - Enable/associate a UMEM to a certain ring/qid
+ * i40e_xsk_pool_enable - Enable/associate an AF_XDP buffer pool to a
+ * certain ring/qid
  * @vsi: Current VSI
- * @umem: UMEM
- * @qid: Rx ring to associate UMEM to
+ * @pool: buffer pool
+ * @qid: Rx ring to associate buffer pool with
  *
  * Returns 0 on success, <0 on failure
  **/
-static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
+static int i40e_xsk_pool_enable(struct i40e_vsi *vsi,
+				struct xsk_buff_pool *pool,
 				u16 qid)
 {
 	struct net_device *netdev = vsi->netdev;
-	struct xdp_umem_fq_reuse *reuseq;
 	bool if_running;
 	int err;
 
@@ -92,13 +100,7 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 	    qid >= netdev->real_num_tx_queues)
 		return -EINVAL;
 
-	reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count);
-	if (!reuseq)
-		return -ENOMEM;
-
-	xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
-
-	err = i40e_xsk_umem_dma_map(vsi, umem);
+	err = xsk_pool_dma_map(pool, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR);
 	if (err)
 		return err;
 
@@ -111,6 +113,10 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 		if (err)
 			return err;
 
+		err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], true);
+		if (err)
+			return err;
+
 		err = i40e_queue_pair_enable(vsi, qid);
 		if (err)
 			return err;
@@ -125,21 +131,22 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 }
 
 /**
- * i40e_xsk_umem_disable - Disassociate a UMEM from a certain ring/qid
+ * i40e_xsk_pool_disable - Disassociate an AF_XDP buffer pool from a
+ * certain ring/qid
  * @vsi: Current VSI
- * @qid: Rx ring to associate UMEM to
+ * @qid: Rx ring to associate buffer pool with
  *
  * Returns 0 on success, <0 on failure
  **/
-static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
+static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid)
 {
 	struct net_device *netdev = vsi->netdev;
-	struct xdp_umem *umem;
+	struct xsk_buff_pool *pool;
 	bool if_running;
 	int err;
 
-	umem = xdp_get_umem_from_qid(netdev, qid);
-	if (!umem)
+	pool = xsk_get_pool_from_qid(netdev, qid);
+	if (!pool)
 		return -EINVAL;
 
 	if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
@@ -151,9 +158,12 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 	}
 
 	clear_bit(qid, vsi->af_xdp_zc_qps);
-	i40e_xsk_umem_dma_unmap(vsi, umem);
+	xsk_pool_dma_unmap(pool, I40E_RX_DMA_ATTR);
 
 	if (if_running) {
+		err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], false);
+		if (err)
+			return err;
 		err = i40e_queue_pair_enable(vsi, qid);
 		if (err)
 			return err;
@@ -163,49 +173,50 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 }
 
 /**
- * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid
+ * i40e_xsk_pool_setup - Enable/disassociate an AF_XDP buffer pool to/from
+ * a ring/qid
  * @vsi: Current VSI
- * @umem: UMEM to enable/associate to a ring, or NULL to disable
- * @qid: Rx ring to (dis)associate UMEM (from)to
+ * @pool: Buffer pool to enable/associate to a ring, or NULL to disable
+ * @qid: Rx ring to (dis)associate buffer pool (from)to
  *
- * This function enables or disables a UMEM to a certain ring.
+ * This function enables or disables a buffer pool to a certain ring.
  *
  * Returns 0 on success, <0 on failure
  **/
-int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
+int i40e_xsk_pool_setup(struct i40e_vsi *vsi, struct xsk_buff_pool *pool,
 			u16 qid)
 {
-	return umem ? i40e_xsk_umem_enable(vsi, umem, qid) :
-		i40e_xsk_umem_disable(vsi, qid);
+	return pool ? i40e_xsk_pool_enable(vsi, pool, qid) :
+		i40e_xsk_pool_disable(vsi, qid);
 }
 
 /**
  * i40e_run_xdp_zc - Executes an XDP program on an xdp_buff
  * @rx_ring: Rx ring
  * @xdp: xdp_buff used as input to the XDP program
- *
- * This function enables or disables a UMEM to a certain ring.
+ * @xdp_prog: XDP program to run
  *
  * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR}
  **/
-static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
+static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp,
+			   struct bpf_prog *xdp_prog)
 {
-	struct xdp_umem *umem = rx_ring->xsk_umem;
 	int err, result = I40E_XDP_PASS;
 	struct i40e_ring *xdp_ring;
-	struct bpf_prog *xdp_prog;
-	u64 offset;
 	u32 act;
 
-	rcu_read_lock();
-	/* NB! xdp_prog will always be !NULL, due to the fact that
-	 * this path is enabled by setting an XDP program.
-	 */
-	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
-	offset = xdp->data - xdp->data_hard_start;
 
-	xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset);
+	if (likely(act == XDP_REDIRECT)) {
+		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
+		if (!err)
+			return I40E_XDP_REDIR;
+		if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+			result = I40E_XDP_EXIT;
+		else
+			result = I40E_XDP_CONSUMED;
+		goto out_failure;
+	}
 
 	switch (act) {
 	case XDP_PASS:
@@ -213,270 +224,65 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	case XDP_TX:
 		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
 		result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
+		if (result == I40E_XDP_CONSUMED)
+			goto out_failure;
 		break;
-	case XDP_REDIRECT:
-		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
+	case XDP_DROP:
+		result = I40E_XDP_CONSUMED;
 		break;
 	default:
-		bpf_warn_invalid_xdp_action(act);
-		/* fall through */
+		bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
+		fallthrough;
 	case XDP_ABORTED:
-		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
-		/* fallthrough -- handle aborts by dropping packet */
-	case XDP_DROP:
 		result = I40E_XDP_CONSUMED;
-		break;
+out_failure:
+		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 	}
-	rcu_read_unlock();
 	return result;
 }
 
-/**
- * i40e_alloc_buffer_zc - Allocates an i40e_rx_buffer
- * @rx_ring: Rx ring
- * @bi: Rx buffer to populate
- *
- * This function allocates an Rx buffer. The buffer can come from fill
- * queue, or via the recycle queue (next_to_alloc).
- *
- * Returns true for a successful allocation, false otherwise
- **/
-static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
-				 struct i40e_rx_buffer *bi)
-{
-	struct xdp_umem *umem = rx_ring->xsk_umem;
-	void *addr = bi->addr;
-	u64 handle, hr;
-
-	if (addr) {
-		rx_ring->rx_stats.page_reuse_count++;
-		return true;
-	}
-
-	if (!xsk_umem_peek_addr(umem, &handle)) {
-		rx_ring->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	hr = umem->headroom + XDP_PACKET_HEADROOM;
-
-	bi->dma = xdp_umem_get_dma(umem, handle);
-	bi->dma += hr;
-
-	bi->addr = xdp_umem_get_data(umem, handle);
-	bi->addr += hr;
-
-	bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
-
-	xsk_umem_release_addr(umem);
-	return true;
-}
-
-/**
- * i40e_alloc_buffer_slow_zc - Allocates an i40e_rx_buffer
- * @rx_ring: Rx ring
- * @bi: Rx buffer to populate
- *
- * This function allocates an Rx buffer. The buffer can come from fill
- * queue, or via the reuse queue.
- *
- * Returns true for a successful allocation, false otherwise
- **/
-static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring,
-				      struct i40e_rx_buffer *bi)
-{
-	struct xdp_umem *umem = rx_ring->xsk_umem;
-	u64 handle, hr;
-
-	if (!xsk_umem_peek_addr_rq(umem, &handle)) {
-		rx_ring->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	handle &= rx_ring->xsk_umem->chunk_mask;
-
-	hr = umem->headroom + XDP_PACKET_HEADROOM;
-
-	bi->dma = xdp_umem_get_dma(umem, handle);
-	bi->dma += hr;
-
-	bi->addr = xdp_umem_get_data(umem, handle);
-	bi->addr += hr;
-
-	bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
-
-	xsk_umem_release_addr_rq(umem);
-	return true;
-}
-
-static __always_inline bool
-__i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count,
-			   bool alloc(struct i40e_ring *rx_ring,
-				      struct i40e_rx_buffer *bi))
+bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
 {
 	u16 ntu = rx_ring->next_to_use;
 	union i40e_rx_desc *rx_desc;
-	struct i40e_rx_buffer *bi;
-	bool ok = true;
+	struct xdp_buff **xdp;
+	u32 nb_buffs, i;
+	dma_addr_t dma;
 
 	rx_desc = I40E_RX_DESC(rx_ring, ntu);
-	bi = &rx_ring->rx_bi[ntu];
-	do {
-		if (!alloc(rx_ring, bi)) {
-			ok = false;
-			goto no_buffers;
-		}
+	xdp = i40e_rx_bi(rx_ring, ntu);
 
-		dma_sync_single_range_for_device(rx_ring->dev, bi->dma, 0,
-						 rx_ring->rx_buf_len,
-						 DMA_BIDIRECTIONAL);
+	nb_buffs = min_t(u16, count, rx_ring->count - ntu);
+	nb_buffs = xsk_buff_alloc_batch(rx_ring->xsk_pool, xdp, nb_buffs);
+	if (!nb_buffs)
+		return false;
 
-		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
+	i = nb_buffs;
+	while (i--) {
+		dma = xsk_buff_xdp_get_dma(*xdp);
+		rx_desc->read.pkt_addr = cpu_to_le64(dma);
+		rx_desc->read.hdr_addr = 0;
 
 		rx_desc++;
-		bi++;
-		ntu++;
-
-		if (unlikely(ntu == rx_ring->count)) {
-			rx_desc = I40E_RX_DESC(rx_ring, 0);
-			bi = rx_ring->rx_bi;
-			ntu = 0;
-		}
-
-		rx_desc->wb.qword1.status_error_len = 0;
-		count--;
-	} while (count);
-
-no_buffers:
-	if (rx_ring->next_to_use != ntu)
-		i40e_release_rx_desc(rx_ring, ntu);
-
-	return ok;
-}
-
-/**
- * i40e_alloc_rx_buffers_zc - Allocates a number of Rx buffers
- * @rx_ring: Rx ring
- * @count: The number of buffers to allocate
- *
- * This function allocates a number of Rx buffers from the reuse queue
- * or fill ring and places them on the Rx ring.
- *
- * Returns true for a successful allocation, false otherwise
- **/
-bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
-{
-	return __i40e_alloc_rx_buffers_zc(rx_ring, count,
-					  i40e_alloc_buffer_slow_zc);
-}
-
-/**
- * i40e_alloc_rx_buffers_fast_zc - Allocates a number of Rx buffers
- * @rx_ring: Rx ring
- * @count: The number of buffers to allocate
- *
- * This function allocates a number of Rx buffers from the fill ring
- * or the internal recycle mechanism and places them on the Rx ring.
- *
- * Returns true for a successful allocation, false otherwise
- **/
-static bool i40e_alloc_rx_buffers_fast_zc(struct i40e_ring *rx_ring, u16 count)
-{
-	return __i40e_alloc_rx_buffers_zc(rx_ring, count,
-					  i40e_alloc_buffer_zc);
-}
-
-/**
- * i40e_get_rx_buffer_zc - Return the current Rx buffer
- * @rx_ring: Rx ring
- * @size: The size of the rx buffer (read from descriptor)
- *
- * This function returns the current, received Rx buffer, and also
- * does DMA synchronization.  the Rx ring.
- *
- * Returns the received Rx buffer
- **/
-static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring,
-						    const unsigned int size)
-{
-	struct i40e_rx_buffer *bi;
-
-	bi = &rx_ring->rx_bi[rx_ring->next_to_clean];
-
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      bi->dma, 0,
-				      size,
-				      DMA_BIDIRECTIONAL);
-
-	return bi;
-}
-
-/**
- * i40e_reuse_rx_buffer_zc - Recycle an Rx buffer
- * @rx_ring: Rx ring
- * @old_bi: The Rx buffer to recycle
- *
- * This function recycles a finished Rx buffer, and places it on the
- * recycle queue (next_to_alloc).
- **/
-static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
-				    struct i40e_rx_buffer *old_bi)
-{
-	struct i40e_rx_buffer *new_bi = &rx_ring->rx_bi[rx_ring->next_to_alloc];
-	u16 nta = rx_ring->next_to_alloc;
-
-	/* update, and store next to alloc */
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	/* transfer page from old buffer to new buffer */
-	new_bi->dma = old_bi->dma;
-	new_bi->addr = old_bi->addr;
-	new_bi->handle = old_bi->handle;
-
-	old_bi->addr = NULL;
-}
-
-/**
- * i40e_zca_free - Free callback for MEM_TYPE_ZERO_COPY allocations
- * @alloc: Zero-copy allocator
- * @handle: Buffer handle
- **/
-void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
-{
-	struct i40e_rx_buffer *bi;
-	struct i40e_ring *rx_ring;
-	u64 hr, mask;
-	u16 nta;
-
-	rx_ring = container_of(alloc, struct i40e_ring, zca);
-	hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
-	mask = rx_ring->xsk_umem->chunk_mask;
-
-	nta = rx_ring->next_to_alloc;
-	bi = &rx_ring->rx_bi[nta];
-
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	handle &= mask;
+		xdp++;
+	}
 
-	bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle);
-	bi->dma += hr;
+	ntu += nb_buffs;
+	if (ntu == rx_ring->count) {
+		rx_desc = I40E_RX_DESC(rx_ring, 0);
+		ntu = 0;
+	}
 
-	bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle);
-	bi->addr += hr;
+	/* clear the status bits for the next_to_use descriptor */
+	rx_desc->wb.qword1.status_error_len = 0;
+	i40e_release_rx_desc(rx_ring, ntu);
 
-	bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle,
-					    rx_ring->xsk_umem->headroom);
+	return count == nb_buffs;
 }
 
 /**
- * i40e_construct_skb_zc - Create skbufff from zero-copy Rx buffer
+ * i40e_construct_skb_zc - Create skbuff from zero-copy Rx buffer
  * @rx_ring: Rx ring
- * @bi: Rx buffer
  * @xdp: xdp_buff
  *
  * This functions allocates a new skb from a zero-copy Rx buffer.
@@ -484,40 +290,88 @@ void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
  * Returns the skb, or NULL on failure.
  **/
 static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
-					     struct i40e_rx_buffer *bi,
 					     struct xdp_buff *xdp)
 {
+	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
-	unsigned int datasize = xdp->data_end - xdp->data;
 	struct sk_buff *skb;
 
+	net_prefetch(xdp->data_meta);
+
 	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-			       xdp->data_end - xdp->data_hard_start,
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
 			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
-		return NULL;
+		goto out;
 
-	skb_reserve(skb, xdp->data - xdp->data_hard_start);
-	memcpy(__skb_put(skb, datasize), xdp->data, datasize);
-	if (metasize)
+	memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+	       ALIGN(totalsize, sizeof(long)));
+
+	if (metasize) {
 		skb_metadata_set(skb, metasize);
+		__skb_pull(skb, metasize);
+	}
 
-	i40e_reuse_rx_buffer_zc(rx_ring, bi);
+out:
+	xsk_buff_free(xdp);
 	return skb;
 }
 
-/**
- * i40e_inc_ntc: Advance the next_to_clean index
- * @rx_ring: Rx ring
- **/
-static void i40e_inc_ntc(struct i40e_ring *rx_ring)
+static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
+				      struct xdp_buff *xdp_buff,
+				      union i40e_rx_desc *rx_desc,
+				      unsigned int *rx_packets,
+				      unsigned int *rx_bytes,
+				      unsigned int size,
+				      unsigned int xdp_res,
+				      bool *failure)
 {
-	u32 ntc = rx_ring->next_to_clean + 1;
+	struct sk_buff *skb;
 
-	ntc = (ntc < rx_ring->count) ? ntc : 0;
-	rx_ring->next_to_clean = ntc;
-	prefetch(I40E_RX_DESC(rx_ring, ntc));
+	*rx_packets = 1;
+	*rx_bytes = size;
+
+	if (likely(xdp_res == I40E_XDP_REDIR) || xdp_res == I40E_XDP_TX)
+		return;
+
+	if (xdp_res == I40E_XDP_EXIT) {
+		*failure = true;
+		return;
+	}
+
+	if (xdp_res == I40E_XDP_CONSUMED) {
+		xsk_buff_free(xdp_buff);
+		return;
+	}
+	if (xdp_res == I40E_XDP_PASS) {
+		/* NB! We are not checking for errors using
+		 * i40e_test_staterr with
+		 * BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that
+		 * SBP is *not* set in PRT_SBPVSI (default not set).
+		 */
+		skb = i40e_construct_skb_zc(rx_ring, xdp_buff);
+		if (!skb) {
+			rx_ring->rx_stats.alloc_buff_failed++;
+			*rx_packets = 0;
+			*rx_bytes = 0;
+			return;
+		}
+
+		if (eth_skb_pad(skb)) {
+			*rx_packets = 0;
+			*rx_bytes = 0;
+			return;
+		}
+
+		*rx_bytes = skb->len;
+		i40e_process_skb_fields(rx_ring, rx_desc, skb);
+		napi_gro_receive(&rx_ring->q_vector->napi, skb);
+		return;
+	}
+
+	/* Should never get here, as all valid cases have been handled already.
+	 */
+	WARN_ON_ONCE(1);
 }
 
 /**
@@ -530,28 +384,27 @@ static void i40e_inc_ntc(struct i40e_ring *rx_ring)
 int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
-	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
+	u16 next_to_clean = rx_ring->next_to_clean;
+	u16 count_mask = rx_ring->count - 1;
 	unsigned int xdp_res, xdp_xmit = 0;
+	struct bpf_prog *xdp_prog;
 	bool failure = false;
-	struct sk_buff *skb;
-	struct xdp_buff xdp;
+	u16 cleaned_count;
 
-	xdp.rxq = &rx_ring->xdp_rxq;
+	/* NB! xdp_prog will always be !NULL, due to the fact that
+	 * this path is enabled by setting an XDP program.
+	 */
+	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
-		struct i40e_rx_buffer *bi;
 		union i40e_rx_desc *rx_desc;
+		unsigned int rx_packets;
+		unsigned int rx_bytes;
+		struct xdp_buff *bi;
 		unsigned int size;
 		u64 qword;
 
-		if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
-			failure = failure ||
-				  !i40e_alloc_rx_buffers_fast_zc(rx_ring,
-								 cleaned_count);
-			cleaned_count = 0;
-		}
-
-		rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean);
+		rx_desc = I40E_RX_DESC(rx_ring, next_to_clean);
 		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
 
 		/* This memory barrier is needed to keep us from reading
@@ -560,11 +413,13 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
-		bi = i40e_clean_programming_status(rx_ring, rx_desc,
-						   qword);
-		if (unlikely(bi)) {
-			i40e_reuse_rx_buffer_zc(rx_ring, bi);
-			cleaned_count++;
+		if (i40e_rx_is_programming_status(qword)) {
+			i40e_clean_programming_status(rx_ring,
+						      rx_desc->raw.qword[0],
+						      qword);
+			bi = *i40e_rx_bi(rx_ring, next_to_clean);
+			xsk_buff_free(bi);
+			next_to_clean = (next_to_clean + 1) & count_mask;
 			continue;
 		}
 
@@ -573,70 +428,104 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		if (!size)
 			break;
 
-		bi = i40e_get_rx_buffer_zc(rx_ring, size);
-		xdp.data = bi->addr;
-		xdp.data_meta = xdp.data;
-		xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
-		xdp.data_end = xdp.data + size;
-		xdp.handle = bi->handle;
-
-		xdp_res = i40e_run_xdp_zc(rx_ring, &xdp);
-		if (xdp_res) {
-			if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
-				xdp_xmit |= xdp_res;
-				bi->addr = NULL;
-			} else {
-				i40e_reuse_rx_buffer_zc(rx_ring, bi);
-			}
-
-			total_rx_bytes += size;
-			total_rx_packets++;
-
-			cleaned_count++;
-			i40e_inc_ntc(rx_ring);
-			continue;
-		}
-
-		/* XDP_PASS path */
+		bi = *i40e_rx_bi(rx_ring, next_to_clean);
+		xsk_buff_set_size(bi, size);
+		xsk_buff_dma_sync_for_cpu(bi, rx_ring->xsk_pool);
 
-		/* NB! We are not checking for errors using
-		 * i40e_test_staterr with
-		 * BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that
-		 * SBP is *not* set in PRT_SBPVSI (default not set).
-		 */
-		skb = i40e_construct_skb_zc(rx_ring, bi, &xdp);
-		if (!skb) {
-			rx_ring->rx_stats.alloc_buff_failed++;
+		xdp_res = i40e_run_xdp_zc(rx_ring, bi, xdp_prog);
+		i40e_handle_xdp_result_zc(rx_ring, bi, rx_desc, &rx_packets,
+					  &rx_bytes, size, xdp_res, &failure);
+		if (failure)
 			break;
-		}
-
-		cleaned_count++;
-		i40e_inc_ntc(rx_ring);
-
-		if (eth_skb_pad(skb))
-			continue;
+		total_rx_packets += rx_packets;
+		total_rx_bytes += rx_bytes;
+		xdp_xmit |= xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR);
+		next_to_clean = (next_to_clean + 1) & count_mask;
+	}
 
-		total_rx_bytes += skb->len;
-		total_rx_packets++;
+	rx_ring->next_to_clean = next_to_clean;
+	cleaned_count = (next_to_clean - rx_ring->next_to_use - 1) & count_mask;
 
-		i40e_process_skb_fields(rx_ring, rx_desc, skb);
-		napi_gro_receive(&rx_ring->q_vector->napi, skb);
-	}
+	if (cleaned_count >= I40E_RX_BUFFER_WRITE)
+		failure |= !i40e_alloc_rx_buffers_zc(rx_ring, cleaned_count);
 
 	i40e_finalize_xdp_rx(rx_ring, xdp_xmit);
 	i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);
 
-	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) {
-		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
-			xsk_set_rx_need_wakeup(rx_ring->xsk_umem);
+	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {
+		if (failure || next_to_clean == rx_ring->next_to_use)
+			xsk_set_rx_need_wakeup(rx_ring->xsk_pool);
 		else
-			xsk_clear_rx_need_wakeup(rx_ring->xsk_umem);
+			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool);
 
 		return (int)total_rx_packets;
 	}
 	return failure ? budget : (int)total_rx_packets;
 }
 
+static void i40e_xmit_pkt(struct i40e_ring *xdp_ring, struct xdp_desc *desc,
+			  unsigned int *total_bytes)
+{
+	struct i40e_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);
+
+	tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
+	tx_desc->buffer_addr = cpu_to_le64(dma);
+	tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC | I40E_TX_DESC_CMD_EOP,
+						  0, desc->len, 0);
+
+	*total_bytes += desc->len;
+}
+
+static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *desc,
+				unsigned int *total_bytes)
+{
+	u16 ntu = xdp_ring->next_to_use;
+	struct i40e_tx_desc *tx_desc;
+	dma_addr_t dma;
+	u32 i;
+
+	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc[i].len);
+
+		tx_desc = I40E_TX_DESC(xdp_ring, ntu++);
+		tx_desc->buffer_addr = cpu_to_le64(dma);
+		tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC |
+							  I40E_TX_DESC_CMD_EOP,
+							  0, desc[i].len, 0);
+
+		*total_bytes += desc[i].len;
+	}
+
+	xdp_ring->next_to_use = ntu;
+}
+
+static void i40e_fill_tx_hw_ring(struct i40e_ring *xdp_ring, struct xdp_desc *descs, u32 nb_pkts,
+				 unsigned int *total_bytes)
+{
+	u32 batched, leftover, i;
+
+	batched = nb_pkts & ~(PKTS_PER_BATCH - 1);
+	leftover = nb_pkts & (PKTS_PER_BATCH - 1);
+	for (i = 0; i < batched; i += PKTS_PER_BATCH)
+		i40e_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
+	for (i = batched; i < batched + leftover; i++)
+		i40e_xmit_pkt(xdp_ring, &descs[i], total_bytes);
+}
+
+static void i40e_set_rs_bit(struct i40e_ring *xdp_ring)
+{
+	u16 ntu = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1;
+	struct i40e_tx_desc *tx_desc;
+
+	tx_desc = I40E_TX_DESC(xdp_ring, ntu);
+	tx_desc->cmd_type_offset_bsz |= cpu_to_le64(I40E_TX_DESC_CMD_RS << I40E_TXD_QW1_CMD_SHIFT);
+}
+
 /**
  * i40e_xmit_zc - Performs zero-copy Tx AF_XDP
  * @xdp_ring: XDP Tx ring
@@ -646,52 +535,30 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
  **/
 static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 {
-	struct i40e_tx_desc *tx_desc = NULL;
-	struct i40e_tx_buffer *tx_bi;
-	bool work_done = true;
-	struct xdp_desc desc;
-	dma_addr_t dma;
-
-	while (budget-- > 0) {
-		if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) {
-			xdp_ring->tx_stats.tx_busy++;
-			work_done = false;
-			break;
-		}
-
-		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
-			break;
-
-		dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
+	struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs;
+	u32 nb_pkts, nb_processed = 0;
+	unsigned int total_bytes = 0;
 
-		dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
-					   DMA_BIDIRECTIONAL);
-
-		tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
-		tx_bi->bytecount = desc.len;
+	nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget);
+	if (!nb_pkts)
+		return true;
 
-		tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use);
-		tx_desc->buffer_addr = cpu_to_le64(dma);
-		tx_desc->cmd_type_offset_bsz =
-			build_ctob(I40E_TX_DESC_CMD_ICRC
-				   | I40E_TX_DESC_CMD_EOP,
-				   0, desc.len, 0);
-
-		xdp_ring->next_to_use++;
-		if (xdp_ring->next_to_use == xdp_ring->count)
-			xdp_ring->next_to_use = 0;
+	if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
+		nb_processed = xdp_ring->count - xdp_ring->next_to_use;
+		i40e_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
+		xdp_ring->next_to_use = 0;
 	}
 
-	if (tx_desc) {
-		/* Request an interrupt for the last frame and bump tail ptr. */
-		tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS <<
-						 I40E_TXD_QW1_CMD_SHIFT);
-		i40e_xdp_ring_update_tail(xdp_ring);
+	i40e_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
+			     &total_bytes);
 
-		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
-	}
+	/* Request an interrupt for the last frame and bump tail ptr. */
+	i40e_set_rs_bit(xdp_ring);
+	i40e_xdp_ring_update_tail(xdp_ring);
 
-	return !!budget && work_done;
+	i40e_update_tx_stats(xdp_ring, nb_pkts, total_bytes);
+
+	return nb_pkts < budget;
 }
 
 /**
@@ -703,6 +570,7 @@ static void i40e_clean_xdp_tx_buffer(struct i40e_ring *tx_ring,
 				     struct i40e_tx_buffer *tx_bi)
 {
 	xdp_return_frame(tx_bi->xdpf);
+	tx_ring->xdp_tx_active--;
 	dma_unmap_single(tx_ring->dev,
 			 dma_unmap_addr(tx_bi, dma),
 			 dma_unmap_len(tx_bi, len), DMA_TO_DEVICE);
@@ -711,32 +579,29 @@ static void i40e_clean_xdp_tx_buffer(struct i40e_ring *tx_ring,
 
 /**
  * i40e_clean_xdp_tx_irq - Completes AF_XDP entries, and cleans XDP entries
+ * @vsi: Current VSI
  * @tx_ring: XDP Tx ring
- * @tx_bi: Tx buffer info to clean
  *
  * Returns true if cleanup/tranmission is done.
  **/
-bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi,
-			   struct i40e_ring *tx_ring, int napi_budget)
+bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring)
 {
-	unsigned int ntc, total_bytes = 0, budget = vsi->work_limit;
-	u32 i, completed_frames, frames_ready, xsk_frames = 0;
-	struct xdp_umem *umem = tx_ring->xsk_umem;
+	struct xsk_buff_pool *bp = tx_ring->xsk_pool;
+	u32 i, completed_frames, xsk_frames = 0;
 	u32 head_idx = i40e_get_head(tx_ring);
-	bool work_done = true, xmit_done;
 	struct i40e_tx_buffer *tx_bi;
+	unsigned int ntc;
 
 	if (head_idx < tx_ring->next_to_clean)
 		head_idx += tx_ring->count;
-	frames_ready = head_idx - tx_ring->next_to_clean;
+	completed_frames = head_idx - tx_ring->next_to_clean;
 
-	if (frames_ready == 0) {
+	if (completed_frames == 0)
 		goto out_xmit;
-	} else if (frames_ready > budget) {
-		completed_frames = budget;
-		work_done = false;
-	} else {
-		completed_frames = frames_ready;
+
+	if (likely(!tx_ring->xdp_tx_active)) {
+		xsk_frames = completed_frames;
+		goto skip;
 	}
 
 	ntc = tx_ring->next_to_clean;
@@ -744,35 +609,32 @@ bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi,
 	for (i = 0; i < completed_frames; i++) {
 		tx_bi = &tx_ring->tx_bi[ntc];
 
-		if (tx_bi->xdpf)
+		if (tx_bi->xdpf) {
 			i40e_clean_xdp_tx_buffer(tx_ring, tx_bi);
-		else
+			tx_bi->xdpf = NULL;
+		} else {
 			xsk_frames++;
-
-		tx_bi->xdpf = NULL;
-		total_bytes += tx_bi->bytecount;
+		}
 
 		if (++ntc >= tx_ring->count)
 			ntc = 0;
 	}
 
+skip:
 	tx_ring->next_to_clean += completed_frames;
 	if (unlikely(tx_ring->next_to_clean >= tx_ring->count))
 		tx_ring->next_to_clean -= tx_ring->count;
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(umem, xsk_frames);
+		xsk_tx_completed(bp, xsk_frames);
 
-	i40e_arm_wb(tx_ring, vsi, budget);
-	i40e_update_tx_stats(tx_ring, completed_frames, total_bytes);
+	i40e_arm_wb(tx_ring, vsi, completed_frames);
 
 out_xmit:
-	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem))
-		xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
+	if (xsk_uses_need_wakeup(tx_ring->xsk_pool))
+		xsk_set_tx_need_wakeup(tx_ring->xsk_pool);
 
-	xmit_done = i40e_xmit_zc(tx_ring, budget);
-
-	return work_done && xmit_done;
+	return i40e_xmit_zc(tx_ring, I40E_DESC_UNUSED(tx_ring));
 }
 
 /**
@@ -797,13 +659,13 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 		return -ENETDOWN;
 
 	if (!i40e_enabled_xdp_vsi(vsi))
-		return -ENXIO;
+		return -EINVAL;
 
 	if (queue_id >= vsi->num_queue_pairs)
-		return -ENXIO;
+		return -EINVAL;
 
-	if (!vsi->xdp_rings[queue_id]->xsk_umem)
-		return -ENXIO;
+	if (!vsi->xdp_rings[queue_id]->xsk_pool)
+		return -EINVAL;
 
 	ring = vsi->xdp_rings[queue_id];
 
@@ -821,27 +683,25 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 
 void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
 {
-	u16 i;
+	u16 count_mask = rx_ring->count - 1;
+	u16 ntc = rx_ring->next_to_clean;
+	u16 ntu = rx_ring->next_to_use;
 
-	for (i = 0; i < rx_ring->count; i++) {
-		struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
+	for ( ; ntc != ntu; ntc = (ntc + 1)  & count_mask) {
+		struct xdp_buff *rx_bi = *i40e_rx_bi(rx_ring, ntc);
 
-		if (!rx_bi->addr)
-			continue;
-
-		xsk_umem_fq_reuse(rx_ring->xsk_umem, rx_bi->handle);
-		rx_bi->addr = NULL;
+		xsk_buff_free(rx_bi);
 	}
 }
 
 /**
- * i40e_xsk_clean_xdp_ring - Clean the XDP Tx ring on shutdown
- * @xdp_ring: XDP Tx ring
+ * i40e_xsk_clean_tx_ring - Clean the XDP Tx ring on shutdown
+ * @tx_ring: XDP Tx ring
  **/
 void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring)
 {
 	u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
-	struct xdp_umem *umem = tx_ring->xsk_umem;
+	struct xsk_buff_pool *bp = tx_ring->xsk_pool;
 	struct i40e_tx_buffer *tx_bi;
 	u32 xsk_frames = 0;
 
@@ -861,14 +721,15 @@ void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring)
 	}
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(umem, xsk_frames);
+		xsk_tx_completed(bp, xsk_frames);
 }
 
 /**
- * i40e_xsk_any_rx_ring_enabled - Checks if Rx rings have AF_XDP UMEM attached
+ * i40e_xsk_any_rx_ring_enabled - Checks if Rx rings have an AF_XDP
+ * buffer pool attached
  * @vsi: vsi
  *
- * Returns true if any of the Rx rings has an AF_XDP UMEM attached
+ * Returns true if any of the Rx rings has an AF_XDP buffer pool attached
  **/
 bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi)
 {
@@ -876,7 +737,7 @@ bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi)
 	int i;
 
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
-		if (xdp_get_umem_from_qid(netdev, i))
+		if (xsk_get_pool_from_qid(netdev, i))
 			return true;
 	}