Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-09-01

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Add AF_XDP zero-copy support for i40e driver (!), from Björn and Magnus.

2) BPF verifier improvements by giving each register its own liveness
   chain which allows to simplify and getting rid of skip_callee() logic,
   from Edward.

3) Add bpf fs pretty print support for percpu arraymap, percpu hashmap
   and percpu lru hashmap. Also add generic percpu formatted print on
   bpftool so the same can be dumped there, from Yonghong.

4) Add bpf_{set,get}sockopt() helper support for TCP_SAVE_SYN and
   TCP_SAVED_SYN options to allow reflection of tos/tclass from received
   SYN packet, from Nikita.

5) Misc improvements to the BPF sockmap test cases in terms of cgroup v2
   interaction and removal of incorrect shutdown() calls, from John.

6) Few cleanups in xdp_umem_assign_dev() and xdpsock samples, from Prashant.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 1385 insertions, 93 deletions

diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
index 14397e7e9925..50590e8d1fd1 100644
--- a/drivers/net/ethernet/intel/i40e/Makefile
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -22,6 +22,7 @@ i40e-objs := i40e_main.o \
 	i40e_txrx.o	\
 	i40e_ptp.o	\
 	i40e_client.o   \
-	i40e_virtchnl_pf.o
+	i40e_virtchnl_pf.o \
+	i40e_xsk.o
 
 i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 7a80652e2500..876cac317e79 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -786,6 +786,11 @@ struct i40e_vsi {
 
 	/* VSI specific handlers */
 	irqreturn_t (*irq_handler)(int irq, void *data);
+
+	/* AF_XDP zero-copy */
+	struct xdp_umem **xsk_umems;
+	u16 num_xsk_umems_used;
+	u16 num_xsk_umems;
 } ____cacheline_internodealigned_in_smp;
 
 struct i40e_netdev_priv {
@@ -1090,6 +1095,20 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi)
 	return !!vsi->xdp_prog;
 }
 
+static inline struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
+{
+	bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
+	int qid = ring->queue_index;
+
+	if (ring_is_xdp(ring))
+		qid -= ring->vsi->alloc_queue_pairs;
+
+	if (!ring->vsi->xsk_umems || !ring->vsi->xsk_umems[qid] || !xdp_on)
+		return NULL;
+
+	return ring->vsi->xsk_umems[qid];
+}
+
 int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch);
 int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate);
 int i40e_add_del_cloud_filter(struct i40e_vsi *vsi,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 112245f32d7d..5d209d8fe9b8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -9,7 +9,9 @@
 /* Local includes */
 #include "i40e.h"
 #include "i40e_diag.h"
+#include "i40e_xsk.h"
 #include <net/udp_tunnel.h>
+#include <net/xdp_sock.h>
 /* All i40e tracepoints are defined by the include below, which
  * must be included exactly once across the whole kernel with
  * CREATE_TRACE_POINTS defined
@@ -3074,6 +3076,9 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 	i40e_status err = 0;
 	u32 qtx_ctl = 0;
 
+	if (ring_is_xdp(ring))
+		ring->xsk_umem = i40e_xsk_umem(ring);
+
 	/* some ATR related tx ring init */
 	if (vsi->back->flags & I40E_FLAG_FD_ATR_ENABLED) {
 		ring->atr_sample_rate = vsi->back->atr_sample_rate;
@@ -3183,13 +3188,46 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	struct i40e_hw *hw = &vsi->back->hw;
 	struct i40e_hmc_obj_rxq rx_ctx;
 	i40e_status err = 0;
+	bool ok;
+	int ret;
 
 	bitmap_zero(ring->state, __I40E_RING_STATE_NBITS);
 
 	/* clear the context structure first */
 	memset(&rx_ctx, 0, sizeof(rx_ctx));
 
-	ring->rx_buf_len = vsi->rx_buf_len;
+	if (ring->vsi->type == I40E_VSI_MAIN)
+		xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+
+	ring->xsk_umem = i40e_xsk_umem(ring);
+	if (ring->xsk_umem) {
+		ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr -
+				   XDP_PACKET_HEADROOM;
+		/* For AF_XDP ZC, we disallow packets to span on
+		 * multiple buffers, thus letting us skip that
+		 * handling in the fast-path.
+		 */
+		chain_len = 1;
+		ring->zca.free = i40e_zca_free;
+		ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+						 MEM_TYPE_ZERO_COPY,
+						 &ring->zca);
+		if (ret)
+			return ret;
+		dev_info(&vsi->back->pdev->dev,
+			 "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n",
+			 ring->queue_index);
+
+	} else {
+		ring->rx_buf_len = vsi->rx_buf_len;
+		if (ring->vsi->type == I40E_VSI_MAIN) {
+			ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+							 MEM_TYPE_PAGE_SHARED,
+							 NULL);
+			if (ret)
+				return ret;
+		}
+	}
 
 	rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
 				    BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
@@ -3245,7 +3283,15 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
 	writel(0, ring->tail);
 
-	i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
+	ok = ring->xsk_umem ?
+	     i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) :
+	     !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
+	if (!ok) {
+		dev_info(&vsi->back->pdev->dev,
+			 "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n",
+			 ring->xsk_umem ? "UMEM enabled " : "",
+			 ring->queue_index, pf_q);
+	}
 
 	return 0;
 }
@@ -11851,6 +11897,256 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi,
 }
 
 /**
+ * i40e_enter_busy_conf - Enters busy config state
+ * @vsi: vsi
+ *
+ * Returns 0 on success, <0 for failure.
+ **/
+static int i40e_enter_busy_conf(struct i40e_vsi *vsi)
+{
+	struct i40e_pf *pf = vsi->back;
+	int timeout = 50;
+
+	while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) {
+		timeout--;
+		if (!timeout)
+			return -EBUSY;
+		usleep_range(1000, 2000);
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_exit_busy_conf - Exits busy config state
+ * @vsi: vsi
+ **/
+static void i40e_exit_busy_conf(struct i40e_vsi *vsi)
+{
+	struct i40e_pf *pf = vsi->back;
+
+	clear_bit(__I40E_CONFIG_BUSY, pf->state);
+}
+
+/**
+ * i40e_queue_pair_reset_stats - Resets all statistics for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ **/
+static void i40e_queue_pair_reset_stats(struct i40e_vsi *vsi, int queue_pair)
+{
+	memset(&vsi->rx_rings[queue_pair]->rx_stats, 0,
+	       sizeof(vsi->rx_rings[queue_pair]->rx_stats));
+	memset(&vsi->tx_rings[queue_pair]->stats, 0,
+	       sizeof(vsi->tx_rings[queue_pair]->stats));
+	if (i40e_enabled_xdp_vsi(vsi)) {
+		memset(&vsi->xdp_rings[queue_pair]->stats, 0,
+		       sizeof(vsi->xdp_rings[queue_pair]->stats));
+	}
+}
+
+/**
+ * i40e_queue_pair_clean_rings - Cleans all the rings of a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ **/
+static void i40e_queue_pair_clean_rings(struct i40e_vsi *vsi, int queue_pair)
+{
+	i40e_clean_tx_ring(vsi->tx_rings[queue_pair]);
+	if (i40e_enabled_xdp_vsi(vsi))
+		i40e_clean_tx_ring(vsi->xdp_rings[queue_pair]);
+	i40e_clean_rx_ring(vsi->rx_rings[queue_pair]);
+}
+
+/**
+ * i40e_queue_pair_toggle_napi - Enables/disables NAPI for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ * @enable: true for enable, false for disable
+ **/
+static void i40e_queue_pair_toggle_napi(struct i40e_vsi *vsi, int queue_pair,
+					bool enable)
+{
+	struct i40e_ring *rxr = vsi->rx_rings[queue_pair];
+	struct i40e_q_vector *q_vector = rxr->q_vector;
+
+	if (!vsi->netdev)
+		return;
+
+	/* All rings in a qp belong to the same qvector. */
+	if (q_vector->rx.ring || q_vector->tx.ring) {
+		if (enable)
+			napi_enable(&q_vector->napi);
+		else
+			napi_disable(&q_vector->napi);
+	}
+}
+
+/**
+ * i40e_queue_pair_toggle_rings - Enables/disables all rings for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ * @enable: true for enable, false for disable
+ *
+ * Returns 0 on success, <0 on failure.
+ **/
+static int i40e_queue_pair_toggle_rings(struct i40e_vsi *vsi, int queue_pair,
+					bool enable)
+{
+	struct i40e_pf *pf = vsi->back;
+	int pf_q, ret = 0;
+
+	pf_q = vsi->base_queue + queue_pair;
+	ret = i40e_control_wait_tx_q(vsi->seid, pf, pf_q,
+				     false /*is xdp*/, enable);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "VSI seid %d Tx ring %d %sable timeout\n",
+			 vsi->seid, pf_q, (enable ? "en" : "dis"));
+		return ret;
+	}
+
+	i40e_control_rx_q(pf, pf_q, enable);
+	ret = i40e_pf_rxq_wait(pf, pf_q, enable);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "VSI seid %d Rx ring %d %sable timeout\n",
+			 vsi->seid, pf_q, (enable ? "en" : "dis"));
+		return ret;
+	}
+
+	/* Due to HW errata, on Rx disable only, the register can
+	 * indicate done before it really is. Needs 50ms to be sure
+	 */
+	if (!enable)
+		mdelay(50);
+
+	if (!i40e_enabled_xdp_vsi(vsi))
+		return ret;
+
+	ret = i40e_control_wait_tx_q(vsi->seid, pf,
+				     pf_q + vsi->alloc_queue_pairs,
+				     true /*is xdp*/, enable);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "VSI seid %d XDP Tx ring %d %sable timeout\n",
+			 vsi->seid, pf_q, (enable ? "en" : "dis"));
+	}
+
+	return ret;
+}
+
+/**
+ * i40e_queue_pair_enable_irq - Enables interrupts for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue_pair
+ **/
+static void i40e_queue_pair_enable_irq(struct i40e_vsi *vsi, int queue_pair)
+{
+	struct i40e_ring *rxr = vsi->rx_rings[queue_pair];
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+
+	/* All rings in a qp belong to the same qvector. */
+	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+		i40e_irq_dynamic_enable(vsi, rxr->q_vector->v_idx);
+	else
+		i40e_irq_dynamic_enable_icr0(pf);
+
+	i40e_flush(hw);
+}
+
+/**
+ * i40e_queue_pair_disable_irq - Disables interrupts for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue_pair
+ **/
+static void i40e_queue_pair_disable_irq(struct i40e_vsi *vsi, int queue_pair)
+{
+	struct i40e_ring *rxr = vsi->rx_rings[queue_pair];
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+
+	/* For simplicity, instead of removing the qp interrupt causes
+	 * from the interrupt linked list, we simply disable the interrupt, and
+	 * leave the list intact.
+	 *
+	 * All rings in a qp belong to the same qvector.
+	 */
+	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+		u32 intpf = vsi->base_vector + rxr->q_vector->v_idx;
+
+		wr32(hw, I40E_PFINT_DYN_CTLN(intpf - 1), 0);
+		i40e_flush(hw);
+		synchronize_irq(pf->msix_entries[intpf].vector);
+	} else {
+		/* Legacy and MSI mode - this stops all interrupt handling */
+		wr32(hw, I40E_PFINT_ICR0_ENA, 0);
+		wr32(hw, I40E_PFINT_DYN_CTL0, 0);
+		i40e_flush(hw);
+		synchronize_irq(pf->pdev->irq);
+	}
+}
+
+/**
+ * i40e_queue_pair_disable - Disables a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ *
+ * Returns 0 on success, <0 on failure.
+ **/
+int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair)
+{
+	int err;
+
+	err = i40e_enter_busy_conf(vsi);
+	if (err)
+		return err;
+
+	i40e_queue_pair_disable_irq(vsi, queue_pair);
+	err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */);
+	i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */);
+	i40e_queue_pair_clean_rings(vsi, queue_pair);
+	i40e_queue_pair_reset_stats(vsi, queue_pair);
+
+	return err;
+}
+
+/**
+ * i40e_queue_pair_enable - Enables a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ *
+ * Returns 0 on success, <0 on failure.
+ **/
+int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair)
+{
+	int err;
+
+	err = i40e_configure_tx_ring(vsi->tx_rings[queue_pair]);
+	if (err)
+		return err;
+
+	if (i40e_enabled_xdp_vsi(vsi)) {
+		err = i40e_configure_tx_ring(vsi->xdp_rings[queue_pair]);
+		if (err)
+			return err;
+	}
+
+	err = i40e_configure_rx_ring(vsi->rx_rings[queue_pair]);
+	if (err)
+		return err;
+
+	err = i40e_queue_pair_toggle_rings(vsi, queue_pair, true /* on */);
+	i40e_queue_pair_toggle_napi(vsi, queue_pair, true /* on */);
+	i40e_queue_pair_enable_irq(vsi, queue_pair);
+
+	i40e_exit_busy_conf(vsi);
+
+	return err;
+}
+
+/**
  * i40e_xdp - implements ndo_bpf for i40e
  * @dev: netdevice
  * @xdp: XDP command
@@ -11870,6 +12166,12 @@ static int i40e_xdp(struct net_device *dev,
 	case XDP_QUERY_PROG:
 		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
 		return 0;
+	case XDP_QUERY_XSK_UMEM:
+		return i40e_xsk_umem_query(vsi, &xdp->xsk.umem,
+					   xdp->xsk.queue_id);
+	case XDP_SETUP_XSK_UMEM:
+		return i40e_xsk_umem_setup(vsi, xdp->xsk.umem,
+					   xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
 	}
@@ -11909,6 +12211,7 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_bridge_setlink	= i40e_ndo_bridge_setlink,
 	.ndo_bpf		= i40e_xdp,
 	.ndo_xdp_xmit		= i40e_xdp_xmit,
+	.ndo_xsk_async_xmit	= i40e_xsk_async_xmit,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index b5042d1a63c0..37bd4e50ccde 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -8,16 +8,8 @@
 #include "i40e.h"
 #include "i40e_trace.h"
 #include "i40e_prototype.h"
-
-static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
-				u32 td_tag)
-{
-	return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA |
-			   ((u64)td_cmd  << I40E_TXD_QW1_CMD_SHIFT) |
-			   ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) |
-			   ((u64)size  << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) |
-			   ((u64)td_tag  << I40E_TXD_QW1_L2TAG1_SHIFT));
-}
+#include "i40e_txrx_common.h"
+#include "i40e_xsk.h"
 
 #define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS)
 /**
@@ -536,8 +528,8 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
  * This is used to verify if the FD programming or invalidation
  * requested by SW to the HW is successful or not and take actions accordingly.
  **/
-static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
-				  union i40e_rx_desc *rx_desc, u8 prog_id)
+void i40e_fd_handle_status(struct i40e_ring *rx_ring,
+			   union i40e_rx_desc *rx_desc, u8 prog_id)
 {
 	struct i40e_pf *pf = rx_ring->vsi->back;
 	struct pci_dev *pdev = pf->pdev;
@@ -767,8 +759,6 @@ void i40e_detect_recover_hung(struct i40e_vsi *vsi)
 	}
 }
 
-#define WB_STRIDE 4
-
 /**
  * i40e_clean_tx_irq - Reclaim resources after transmit completes
  * @vsi: the VSI we care about
@@ -873,27 +863,8 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 
 	i += tx_ring->count;
 	tx_ring->next_to_clean = i;
-	u64_stats_update_begin(&tx_ring->syncp);
-	tx_ring->stats.bytes += total_bytes;
-	tx_ring->stats.packets += total_packets;
-	u64_stats_update_end(&tx_ring->syncp);
-	tx_ring->q_vector->tx.total_bytes += total_bytes;
-	tx_ring->q_vector->tx.total_packets += total_packets;
-
-	if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) {
-		/* check to see if there are < 4 descriptors
-		 * waiting to be written back, then kick the hardware to force
-		 * them to be written back in case we stay in NAPI.
-		 * In this mode on X722 we do not enable Interrupt.
-		 */
-		unsigned int j = i40e_get_tx_pending(tx_ring, false);
-
-		if (budget &&
-		    ((j / WB_STRIDE) == 0) && (j > 0) &&
-		    !test_bit(__I40E_VSI_DOWN, vsi->state) &&
-		    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
-			tx_ring->arm_wb = true;
-	}
+	i40e_update_tx_stats(tx_ring, total_packets, total_bytes);
+	i40e_arm_wb(tx_ring, vsi, budget);
 
 	if (ring_is_xdp(tx_ring))
 		return !!budget;
@@ -1244,6 +1215,11 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
 	new_buff->page		= old_buff->page;
 	new_buff->page_offset	= old_buff->page_offset;
 	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
+
+	rx_ring->rx_stats.page_reuse_count++;
+
+	/* clear contents of buffer_info */
+	old_buff->page = NULL;
 }
 
 /**
@@ -1266,7 +1242,7 @@ static inline bool i40e_rx_is_programming_status(u64 qw)
 }
 
 /**
- * i40e_clean_programming_status - clean the programming status descriptor
+ * i40e_clean_programming_status - try clean the programming status descriptor
  * @rx_ring: the rx ring that has this descriptor
  * @rx_desc: the rx descriptor written back by HW
  * @qw: qword representing status_error_len in CPU ordering
@@ -1275,15 +1251,22 @@ static inline bool i40e_rx_is_programming_status(u64 qw)
  * status being successful or not and take actions accordingly. FCoE should
  * handle its context/filter programming/invalidation status and take actions.
  *
+ * Returns an i40e_rx_buffer to reuse if the cleanup occurred, otherwise NULL.
  **/
-static void i40e_clean_programming_status(struct i40e_ring *rx_ring,
-					  union i40e_rx_desc *rx_desc,
-					  u64 qw)
+struct i40e_rx_buffer *i40e_clean_programming_status(
+	struct i40e_ring *rx_ring,
+	union i40e_rx_desc *rx_desc,
+	u64 qw)
 {
 	struct i40e_rx_buffer *rx_buffer;
-	u32 ntc = rx_ring->next_to_clean;
+	u32 ntc;
 	u8 id;
 
+	if (!i40e_rx_is_programming_status(qw))
+		return NULL;
+
+	ntc = rx_ring->next_to_clean;
+
 	/* fetch, update, and store next to clean */
 	rx_buffer = &rx_ring->rx_bi[ntc++];
 	ntc = (ntc < rx_ring->count) ? ntc : 0;
@@ -1291,18 +1274,13 @@ static void i40e_clean_programming_status(struct i40e_ring *rx_ring,
 
 	prefetch(I40E_RX_DESC(rx_ring, ntc));
 
-	/* place unused page back on the ring */
-	i40e_reuse_rx_page(rx_ring, rx_buffer);
-	rx_ring->rx_stats.page_reuse_count++;
-
-	/* clear contents of buffer_info */
-	rx_buffer->page = NULL;
-
 	id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >>
 		  I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT;
 
 	if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS)
 		i40e_fd_handle_status(rx_ring, rx_desc, id);
+
+	return rx_buffer;
 }
 
 /**
@@ -1372,6 +1350,9 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 		rx_ring->skb = NULL;
 	}
 
+	if (rx_ring->xsk_umem)
+		goto skip_free;
+
 	/* Free all the Rx ring sk_buffs */
 	for (i = 0; i < rx_ring->count; i++) {
 		struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
@@ -1400,6 +1381,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 		rx_bi->page_offset = 0;
 	}
 
+skip_free:
 	bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count;
 	memset(rx_ring->rx_bi, 0, bi_size);
 
@@ -1492,7 +1474,7 @@ err:
  * @rx_ring: ring to bump
  * @val: new head index
  **/
-static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
+void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
 {
 	rx_ring->next_to_use = val;
 
@@ -1576,8 +1558,8 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
  * @skb: packet to send up
  * @vlan_tag: vlan tag for packet
  **/
-static void i40e_receive_skb(struct i40e_ring *rx_ring,
-			     struct sk_buff *skb, u16 vlan_tag)
+void i40e_receive_skb(struct i40e_ring *rx_ring,
+		      struct sk_buff *skb, u16 vlan_tag)
 {
 	struct i40e_q_vector *q_vector = rx_ring->q_vector;
 
@@ -1804,7 +1786,6 @@ static inline void i40e_rx_hash(struct i40e_ring *ring,
  * order to populate the hash, checksum, VLAN, protocol, and
  * other fields within the skb.
  **/
-static inline
 void i40e_process_skb_fields(struct i40e_ring *rx_ring,
 			     union i40e_rx_desc *rx_desc, struct sk_buff *skb,
 			     u8 rx_ptype)
@@ -2152,7 +2133,6 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
 	if (i40e_can_reuse_rx_page(rx_buffer)) {
 		/* hand second half of page back to the ring */
 		i40e_reuse_rx_page(rx_ring, rx_buffer);
-		rx_ring->rx_stats.page_reuse_count++;
 	} else {
 		/* we are not reusing the buffer so unmap it */
 		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
@@ -2160,10 +2140,9 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
 				     DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
 		__page_frag_cache_drain(rx_buffer->page,
 					rx_buffer->pagecnt_bias);
+		/* clear contents of buffer_info */
+		rx_buffer->page = NULL;
 	}
-
-	/* clear contents of buffer_info */
-	rx_buffer->page = NULL;
 }
 
 /**
@@ -2199,16 +2178,10 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring,
 	return true;
 }
 
-#define I40E_XDP_PASS		0
-#define I40E_XDP_CONSUMED	BIT(0)
-#define I40E_XDP_TX		BIT(1)
-#define I40E_XDP_REDIR		BIT(2)
-
 static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
 			      struct i40e_ring *xdp_ring);
 
-static int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp,
-				 struct i40e_ring *xdp_ring)
+int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring)
 {
 	struct xdp_frame *xdpf = convert_to_xdp_frame(xdp);
 
@@ -2287,7 +2260,13 @@ static void i40e_rx_buffer_flip(struct i40e_ring *rx_ring,
 #endif
 }
 
-static inline void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring)
+/**
+ * i40e_xdp_ring_update_tail - Updates the XDP Tx ring tail register
+ * @xdp_ring: XDP Tx ring
+ *
+ * This function updates the XDP Tx ring tail register.
+ **/
+void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring)
 {
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.
@@ -2297,6 +2276,48 @@ static inline void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring)
 }
 
 /**
+ * i40e_update_rx_stats - Update Rx ring statistics
+ * @rx_ring: rx descriptor ring
+ * @total_rx_bytes: number of bytes received
+ * @total_rx_packets: number of packets received
+ *
+ * This function updates the Rx ring statistics.
+ **/
+void i40e_update_rx_stats(struct i40e_ring *rx_ring,
+			  unsigned int total_rx_bytes,
+			  unsigned int total_rx_packets)
+{
+	u64_stats_update_begin(&rx_ring->syncp);
+	rx_ring->stats.packets += total_rx_packets;
+	rx_ring->stats.bytes += total_rx_bytes;
+	u64_stats_update_end(&rx_ring->syncp);
+	rx_ring->q_vector->rx.total_packets += total_rx_packets;
+	rx_ring->q_vector->rx.total_bytes += total_rx_bytes;
+}
+
+/**
+ * i40e_finalize_xdp_rx - Bump XDP Tx tail and/or flush redirect map
+ * @rx_ring: Rx ring
+ * @xdp_res: Result of the receive batch
+ *
+ * This function bumps XDP Tx tail and/or flush redirect map, and
+ * should be called when a batch of packets has been processed in the
+ * napi loop.
+ **/
+void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res)
+{
+	if (xdp_res & I40E_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_res & I40E_XDP_TX) {
+		struct i40e_ring *xdp_ring =
+			rx_ring->vsi->xdp_rings[rx_ring->queue_index];
+
+		i40e_xdp_ring_update_tail(xdp_ring);
+	}
+}
+
+/**
  * i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: rx descriptor ring to transact packets on
  * @budget: Total limit on number of packets to process
@@ -2349,11 +2370,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
-		if (unlikely(i40e_rx_is_programming_status(qword))) {
-			i40e_clean_programming_status(rx_ring, rx_desc, qword);
+		rx_buffer = i40e_clean_programming_status(rx_ring, rx_desc,
+							  qword);
+		if (unlikely(rx_buffer)) {
+			i40e_reuse_rx_page(rx_ring, rx_buffer);
 			cleaned_count++;
 			continue;
 		}
+
 		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
 		       I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
 		if (!size)
@@ -2432,24 +2456,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		total_rx_packets++;
 	}
 
-	if (xdp_xmit & I40E_XDP_REDIR)
-		xdp_do_flush_map();
-
-	if (xdp_xmit & I40E_XDP_TX) {
-		struct i40e_ring *xdp_ring =
-			rx_ring->vsi->xdp_rings[rx_ring->queue_index];
-
-		i40e_xdp_ring_update_tail(xdp_ring);
-	}
-
+	i40e_finalize_xdp_rx(rx_ring, xdp_xmit);
 	rx_ring->skb = skb;
 
-	u64_stats_update_begin(&rx_ring->syncp);
-	rx_ring->stats.packets += total_rx_packets;
-	rx_ring->stats.bytes += total_rx_bytes;
-	u64_stats_update_end(&rx_ring->syncp);
-	rx_ring->q_vector->rx.total_packets += total_rx_packets;
-	rx_ring->q_vector->rx.total_bytes += total_rx_bytes;
+	i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);
 
 	/* guarantee a trip back through this routine if there was a failure */
 	return failure ? budget : (int)total_rx_packets;
@@ -2587,7 +2597,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	i40e_for_each_ring(ring, q_vector->tx) {
-		if (!i40e_clean_tx_irq(vsi, ring, budget)) {
+		bool wd = ring->xsk_umem ?
+			  i40e_clean_xdp_tx_irq(vsi, ring, budget) :
+			  i40e_clean_tx_irq(vsi, ring, budget);
+
+		if (!wd) {
 			clean_complete = false;
 			continue;
 		}
@@ -2605,7 +2619,9 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	budget_per_ring = max(budget/q_vector->num_ringpairs, 1);
 
 	i40e_for_each_ring(ring, q_vector->rx) {
-		int cleaned = i40e_clean_rx_irq(ring, budget_per_ring);
+		int cleaned = ring->xsk_umem ?
+			      i40e_clean_rx_irq_zc(ring, budget_per_ring) :
+			      i40e_clean_rx_irq(ring, budget_per_ring);
 
 		work_done += cleaned;
 		/* if we clean as many as budgeted, we must not be done */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index bb04f6a731fe..100e92d2982f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -296,13 +296,17 @@ struct i40e_tx_buffer {
 
 struct i40e_rx_buffer {
 	dma_addr_t dma;
-	struct page *page;
-#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
-	__u32 page_offset;
-#else
-	__u16 page_offset;
-#endif
-	__u16 pagecnt_bias;
+	union {
+		struct {
+			struct page *page;
+			__u32 page_offset;
+			__u16 pagecnt_bias;
+		};
+		struct {
+			void *addr;
+			u64 handle;
+		};
+	};
 };
 
 struct i40e_queue_stats {
@@ -414,6 +418,8 @@ struct i40e_ring {
 
 	struct i40e_channel *ch;
 	struct xdp_rxq_info xdp_rxq;
+	struct xdp_umem *xsk_umem;
+	struct zero_copy_allocator zca; /* ZC allocator anchor */
 } ____cacheline_internodealigned_in_smp;
 
 static inline bool ring_uses_build_skb(struct i40e_ring *ring)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
new file mode 100644
index 000000000000..b5afd479a9c5
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2018 Intel Corporation. */
+
+#ifndef I40E_TXRX_COMMON_
+#define I40E_TXRX_COMMON_
+
+void i40e_fd_handle_status(struct i40e_ring *rx_ring,
+			   union i40e_rx_desc *rx_desc, u8 prog_id);
+int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring);
+struct i40e_rx_buffer *i40e_clean_programming_status(
+	struct i40e_ring *rx_ring,
+	union i40e_rx_desc *rx_desc,
+	u64 qw);
+void i40e_process_skb_fields(struct i40e_ring *rx_ring,
+			     union i40e_rx_desc *rx_desc, struct sk_buff *skb,
+			     u8 rx_ptype);
+void i40e_receive_skb(struct i40e_ring *rx_ring,
+		      struct sk_buff *skb, u16 vlan_tag);
+void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring);
+void i40e_update_rx_stats(struct i40e_ring *rx_ring,
+			  unsigned int total_rx_bytes,
+			  unsigned int total_rx_packets);
+void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res);
+void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val);
+
+#define I40E_XDP_PASS		0
+#define I40E_XDP_CONSUMED	BIT(0)
+#define I40E_XDP_TX		BIT(1)
+#define I40E_XDP_REDIR		BIT(2)
+
+/**
+ * build_ctob - Builds the Tx descriptor (cmd, offset and type) qword
+ **/
+static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
+				u32 td_tag)
+{
+	return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA |
+			   ((u64)td_cmd  << I40E_TXD_QW1_CMD_SHIFT) |
+			   ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) |
+			   ((u64)size  << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) |
+			   ((u64)td_tag  << I40E_TXD_QW1_L2TAG1_SHIFT));
+}
+
+/**
+ * i40e_update_tx_stats - Update the egress statistics for the Tx ring
+ * @tx_ring: Tx ring to update
+ * @total_packet: total packets sent
+ * @total_bytes: total bytes sent
+ **/
+static inline void i40e_update_tx_stats(struct i40e_ring *tx_ring,
+					unsigned int total_packets,
+					unsigned int total_bytes)
+{
+	u64_stats_update_begin(&tx_ring->syncp);
+	tx_ring->stats.bytes += total_bytes;
+	tx_ring->stats.packets += total_packets;
+	u64_stats_update_end(&tx_ring->syncp);
+	tx_ring->q_vector->tx.total_bytes += total_bytes;
+	tx_ring->q_vector->tx.total_packets += total_packets;
+}
+
+#define WB_STRIDE 4
+
+/**
+ * i40e_arm_wb - (Possibly) arms Tx write-back
+ * @tx_ring: Tx ring to update
+ * @vsi: the VSI
+ * @budget: the NAPI budget left
+ **/
+static inline void i40e_arm_wb(struct i40e_ring *tx_ring,
+			       struct i40e_vsi *vsi,
+			       int budget)
+{
+	if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) {
+		/* check to see if there are < 4 descriptors
+		 * waiting to be written back, then kick the hardware to force
+		 * them to be written back in case we stay in NAPI.
+		 * In this mode on X722 we do not enable Interrupt.
+		 */
+		unsigned int j = i40e_get_tx_pending(tx_ring, false);
+
+		if (budget &&
+		    ((j / WB_STRIDE) == 0) && j > 0 &&
+		    !test_bit(__I40E_VSI_DOWN, vsi->state) &&
+		    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
+			tx_ring->arm_wb = true;
+	}
+}
+
+#endif /* I40E_TXRX_COMMON_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
new file mode 100644
index 000000000000..2ebfc78bbd09
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -0,0 +1,832 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Intel Corporation. */
+
+#include <linux/bpf_trace.h>
+#include <net/xdp_sock.h>
+#include <net/xdp.h>
+
+#include "i40e.h"
+#include "i40e_txrx_common.h"
+#include "i40e_xsk.h"
+
+/**
+ * i40e_alloc_xsk_umems - Allocate an array to store per ring UMEMs
+ * @vsi: Current VSI
+ *
+ * Returns 0 on success, <0 on failure
+ **/
+static int i40e_alloc_xsk_umems(struct i40e_vsi *vsi)
+{
+	if (vsi->xsk_umems)
+		return 0;
+
+	vsi->num_xsk_umems_used = 0;
+	vsi->num_xsk_umems = vsi->alloc_queue_pairs;
+	vsi->xsk_umems = kcalloc(vsi->num_xsk_umems, sizeof(*vsi->xsk_umems),
+				 GFP_KERNEL);
+	if (!vsi->xsk_umems) {
+		vsi->num_xsk_umems = 0;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_add_xsk_umem - Store an UMEM for a certain ring/qid
+ * @vsi: Current VSI
+ * @umem: UMEM to store
+ * @qid: Ring/qid to associate with the UMEM
+ *
+ * Returns 0 on success, <0 on failure
+ **/
+static int i40e_add_xsk_umem(struct i40e_vsi *vsi, struct xdp_umem *umem,
+			     u16 qid)
+{
+	int err;
+
+	err = i40e_alloc_xsk_umems(vsi);
+	if (err)
+		return err;
+
+	vsi->xsk_umems[qid] = umem;
+	vsi->num_xsk_umems_used++;
+
+	return 0;
+}
+
+/**
+ * i40e_remove_xsk_umem - Remove an UMEM for a certain ring/qid
+ * @vsi: Current VSI
+ * @qid: Ring/qid associated with the UMEM
+ **/
+static void i40e_remove_xsk_umem(struct i40e_vsi *vsi, u16 qid)
+{
+	vsi->xsk_umems[qid] = NULL;
+	vsi->num_xsk_umems_used--;
+
+	if (vsi->num_xsk_umems == 0) {
+		kfree(vsi->xsk_umems);
+		vsi->xsk_umems = NULL;
+		vsi->num_xsk_umems = 0;
+	}
+}
+
+/**
+ * i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev
+ * @vsi: Current VSI
+ * @umem: UMEM to DMA map
+ *
+ * Returns 0 on success, <0 on failure
+ **/
+static int i40e_xsk_umem_dma_map(struct i40e_vsi *vsi, struct xdp_umem *umem)
+{
+	struct i40e_pf *pf = vsi->back;
+	struct device *dev;
+	unsigned int i, j;
+	dma_addr_t dma;
+
+	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;
+
+		umem->pages[i].dma = dma;
+	}
+
+	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
+ * @vsi: Current VSI
+ * @umem: UMEM to DMA map
+ **/
+static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem)
+{
+	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);
+
+		umem->pages[i].dma = 0;
+	}
+}
+
+/**
+ * i40e_xsk_umem_enable - Enable/associate an UMEM to a certain ring/qid
+ * @vsi: Current VSI
+ * @umem: UMEM
+ * @qid: Rx ring to associate UMEM to
+ *
+ * Returns 0 on success, <0 on failure
+ **/
+static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
+				u16 qid)
+{
+	bool if_running;
+	int err;
+
+	if (vsi->type != I40E_VSI_MAIN)
+		return -EINVAL;
+
+	if (qid >= vsi->num_queue_pairs)
+		return -EINVAL;
+
+	if (vsi->xsk_umems) {
+		if (qid >= vsi->num_xsk_umems)
+			return -EINVAL;
+		if (vsi->xsk_umems[qid])
+			return -EBUSY;
+	}
+
+	err = i40e_xsk_umem_dma_map(vsi, umem);
+	if (err)
+		return err;
+
+	if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
+
+	if (if_running) {
+		err = i40e_queue_pair_disable(vsi, qid);
+		if (err)
+			return err;
+	}
+
+	err = i40e_add_xsk_umem(vsi, umem, qid);
+	if (err)
+		return err;
+
+	if (if_running) {
+		err = i40e_queue_pair_enable(vsi, qid);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_xsk_umem_disable - Diassociate an UMEM from a certain ring/qid
+ * @vsi: Current VSI
+ * @qid: Rx ring to associate UMEM to
+ *
+ * Returns 0 on success, <0 on failure
+ **/
+static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
+{
+	bool if_running;
+	int err;
+
+	if (!vsi->xsk_umems || qid >= vsi->num_xsk_umems ||
+	    !vsi->xsk_umems[qid])
+		return -EINVAL;
+
+	if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
+
+	if (if_running) {
+		err = i40e_queue_pair_disable(vsi, qid);
+		if (err)
+			return err;
+	}
+
+	i40e_xsk_umem_dma_unmap(vsi, vsi->xsk_umems[qid]);
+	i40e_remove_xsk_umem(vsi, qid);
+
+	if (if_running) {
+		err = i40e_queue_pair_enable(vsi, qid);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM
+ * @vsi: Current VSI
+ * @umem: UMEM associated to the ring, if any
+ * @qid: Rx ring to associate UMEM to
+ *
+ * This function will store, if any, the UMEM associated to certain ring.
+ *
+ * Returns 0 on success, <0 on failure
+ **/
+int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem,
+			u16 qid)
+{
+	if (vsi->type != I40E_VSI_MAIN)
+		return -EINVAL;
+
+	if (qid >= vsi->num_queue_pairs)
+		return -EINVAL;
+
+	if (vsi->xsk_umems) {
+		if (qid >= vsi->num_xsk_umems)
+			return -EINVAL;
+		*umem = vsi->xsk_umems[qid];
+		return 0;
+	}
+
+	*umem = NULL;
+	return 0;
+}
+
+/**
+ * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM
+ * @vsi: Current VSI
+ * @umem: UMEM to enable/associate to a ring, or NULL to disable
+ * @qid: Rx ring to (dis)associate UMEM (from)to
+ *
+ * This function enables or disables an UMEM to a certain ring.
+ *
+ * Returns 0 on success, <0 on failure
+ **/
+int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
+			u16 qid)
+{
+	return umem ? i40e_xsk_umem_enable(vsi, umem, qid) :
+		i40e_xsk_umem_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 an UMEM to a certain ring.
+ *
+ * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR}
+ **/
+static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
+{
+	int err, result = I40E_XDP_PASS;
+	struct i40e_ring *xdp_ring;
+	struct bpf_prog *xdp_prog;
+	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);
+	xdp->handle += xdp->data - xdp->data_hard_start;
+	switch (act) {
+	case XDP_PASS:
+		break;
+	case XDP_TX:
+		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
+		result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
+		break;
+	case XDP_REDIRECT:
+		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
+		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+	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;
+	}
+	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 = handle + umem->headroom;
+
+	xsk_umem_discard_addr(umem);
+	return true;
+}
+
+/**
+ * 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 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)
+{
+	u16 ntu = rx_ring->next_to_use;
+	union i40e_rx_desc *rx_desc;
+	struct i40e_rx_buffer *bi;
+	bool ok = true;
+
+	rx_desc = I40E_RX_DESC(rx_ring, ntu);
+	bi = &rx_ring->rx_bi[ntu];
+	do {
+		if (!i40e_alloc_buffer_zc(rx_ring, bi)) {
+			ok = false;
+			goto no_buffers;
+		}
+
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma, 0,
+						 rx_ring->rx_buf_len,
+						 DMA_BIDIRECTIONAL);
+
+		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
+
+		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_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];
+	unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask;
+	u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
+	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 & mask;
+	new_bi->dma += hr;
+
+	new_bi->addr = (void *)((unsigned long)old_bi->addr & mask);
+	new_bi->addr += hr;
+
+	new_bi->handle = old_bi->handle & mask;
+	new_bi->handle += rx_ring->xsk_umem->headroom;
+
+	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;
+
+	bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle);
+	bi->dma += hr;
+
+	bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle);
+	bi->addr += hr;
+
+	bi->handle = (u64)handle + rx_ring->xsk_umem->headroom;
+}
+
+/**
+ * i40e_construct_skb_zc - Create skbufff 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.
+ *
+ * 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 metasize = xdp->data - xdp->data_meta;
+	unsigned int datasize = xdp->data_end - xdp->data;
+	struct sk_buff *skb;
+
+	/* allocate a skb to store the frags */
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+			       xdp->data_end - xdp->data_hard_start,
+			       GFP_ATOMIC | __GFP_NOWARN);
+	if (unlikely(!skb))
+		return NULL;
+
+	skb_reserve(skb, xdp->data - xdp->data_hard_start);
+	memcpy(__skb_put(skb, datasize), xdp->data, datasize);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
+
+	i40e_reuse_rx_buffer_zc(rx_ring, bi);
+	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)
+{
+	u32 ntc = rx_ring->next_to_clean + 1;
+
+	ntc = (ntc < rx_ring->count) ? ntc : 0;
+	rx_ring->next_to_clean = ntc;
+	prefetch(I40E_RX_DESC(rx_ring, ntc));
+}
+
+/**
+ * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring
+ * @rx_ring: Rx ring
+ * @budget: NAPI budget
+ *
+ * Returns amount of work completed
+ **/
+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);
+	unsigned int xdp_res, xdp_xmit = 0;
+	bool failure = false;
+	struct sk_buff *skb;
+	struct xdp_buff xdp;
+
+	xdp.rxq = &rx_ring->xdp_rxq;
+
+	while (likely(total_rx_packets < (unsigned int)budget)) {
+		struct i40e_rx_buffer *bi;
+		union i40e_rx_desc *rx_desc;
+		unsigned int size;
+		u16 vlan_tag;
+		u8 rx_ptype;
+		u64 qword;
+
+		if (cleaned_count >= I40E_RX_BUFFER_WRITE) {
+			failure = failure ||
+				  !i40e_alloc_rx_buffers_zc(rx_ring,
+							    cleaned_count);
+			cleaned_count = 0;
+		}
+
+		rx_desc = I40E_RX_DESC(rx_ring, 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
+		 * any other fields out of the rx_desc until we have
+		 * verified the descriptor has been written back.
+		 */
+		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++;
+			continue;
+		}
+
+		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
+		       I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+		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 */
+
+		/* 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++;
+			break;
+		}
+
+		cleaned_count++;
+		i40e_inc_ntc(rx_ring);
+
+		if (eth_skb_pad(skb))
+			continue;
+
+		total_rx_bytes += skb->len;
+		total_rx_packets++;
+
+		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+		rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >>
+			   I40E_RXD_QW1_PTYPE_SHIFT;
+		i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
+
+		vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
+			   le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0;
+		i40e_receive_skb(rx_ring, skb, vlan_tag);
+	}
+
+	i40e_finalize_xdp_rx(rx_ring, xdp_xmit);
+	i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);
+	return failure ? budget : (int)total_rx_packets;
+}
+
+/**
+ * i40e_xmit_zc - Performs zero-copy Tx AF_XDP
+ * @xdp_ring: XDP Tx ring
+ * @budget: NAPI budget
+ *
+ * Returns true if the work is finished.
+ **/
+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;
+	dma_addr_t dma;
+	u32 len;
+
+	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, &dma, &len))
+			break;
+
+		dma_sync_single_for_device(xdp_ring->dev, dma, len,
+					   DMA_BIDIRECTIONAL);
+
+		tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
+		tx_bi->bytecount = 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, len, 0);
+
+		xdp_ring->next_to_use++;
+		if (xdp_ring->next_to_use == xdp_ring->count)
+			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);
+
+		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
+	}
+
+	return !!budget && work_done;
+}
+
+/**
+ * i40e_clean_xdp_tx_buffer - Frees and unmaps an XDP Tx entry
+ * @tx_ring: XDP Tx ring
+ * @tx_bi: Tx buffer info to clean
+ **/
+static void i40e_clean_xdp_tx_buffer(struct i40e_ring *tx_ring,
+				     struct i40e_tx_buffer *tx_bi)
+{
+	xdp_return_frame(tx_bi->xdpf);
+	dma_unmap_single(tx_ring->dev,
+			 dma_unmap_addr(tx_bi, dma),
+			 dma_unmap_len(tx_bi, len), DMA_TO_DEVICE);
+	dma_unmap_len_set(tx_bi, len, 0);
+}
+
+/**
+ * i40e_clean_xdp_tx_irq - Completes AF_XDP entries, and cleans XDP entries
+ * @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)
+{
+	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;
+	u32 head_idx = i40e_get_head(tx_ring);
+	bool work_done = true, xmit_done;
+	struct i40e_tx_buffer *tx_bi;
+
+	if (head_idx < tx_ring->next_to_clean)
+		head_idx += tx_ring->count;
+	frames_ready = head_idx - tx_ring->next_to_clean;
+
+	if (frames_ready == 0) {
+		goto out_xmit;
+	} else if (frames_ready > budget) {
+		completed_frames = budget;
+		work_done = false;
+	} else {
+		completed_frames = frames_ready;
+	}
+
+	ntc = tx_ring->next_to_clean;
+
+	for (i = 0; i < completed_frames; i++) {
+		tx_bi = &tx_ring->tx_bi[ntc];
+
+		if (tx_bi->xdpf)
+			i40e_clean_xdp_tx_buffer(tx_ring, tx_bi);
+		else
+			xsk_frames++;
+
+		tx_bi->xdpf = NULL;
+		total_bytes += tx_bi->bytecount;
+
+		if (++ntc >= tx_ring->count)
+			ntc = 0;
+	}
+
+	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);
+
+	i40e_arm_wb(tx_ring, vsi, budget);
+	i40e_update_tx_stats(tx_ring, completed_frames, total_bytes);
+
+out_xmit:
+	xmit_done = i40e_xmit_zc(tx_ring, budget);
+
+	return work_done && xmit_done;
+}
+
+/**
+ * i40e_xsk_async_xmit - Implements the ndo_xsk_async_xmit
+ * @dev: the netdevice
+ * @queue_id: queue id to wake up
+ *
+ * Returns <0 for errors, 0 otherwise.
+ **/
+int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id)
+{
+	struct i40e_netdev_priv *np = netdev_priv(dev);
+	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_ring *ring;
+
+	if (test_bit(__I40E_VSI_DOWN, vsi->state))
+		return -ENETDOWN;
+
+	if (!i40e_enabled_xdp_vsi(vsi))
+		return -ENXIO;
+
+	if (queue_id >= vsi->num_queue_pairs)
+		return -ENXIO;
+
+	if (!vsi->xdp_rings[queue_id]->xsk_umem)
+		return -ENXIO;
+
+	ring = vsi->xdp_rings[queue_id];
+
+	/* The idea here is that if NAPI is running, mark a miss, so
+	 * it will run again. If not, trigger an interrupt and
+	 * schedule the NAPI from interrupt context. If NAPI would be
+	 * scheduled here, the interrupt affinity would not be
+	 * honored.
+	 */
+	if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi))
+		i40e_force_wb(vsi, ring->q_vector);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
new file mode 100644
index 000000000000..9038c5d5cf08
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2018 Intel Corporation. */
+
+#ifndef _I40E_XSK_H_
+#define _I40E_XSK_H_
+
+struct i40e_vsi;
+struct xdp_umem;
+struct zero_copy_allocator;
+
+int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair);
+int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair);
+int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem,
+			u16 qid);
+int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
+			u16 qid);
+void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
+bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count);
+int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget);
+
+bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi,
+			   struct i40e_ring *tx_ring, int napi_budget);
+int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id);
+
+#endif /* _I40E_XSK_H_ */