vmxnet3: Add XDP support.

The patch adds native-mode XDP support: XDP DROP, PASS, TX, and REDIRECT.

Background:
The vmxnet3 rx consists of three rings: ring0, ring1, and dataring.
For r0 and r1, buffers at r0 are allocated using alloc_skb APIs and dma
mapped to the ring's descriptor. If LRO is enabled and packet size larger
than 3K, VMXNET3_MAX_SKB_BUF_SIZE, then r1 is used to mapped the rest of
the buffer larger than VMXNET3_MAX_SKB_BUF_SIZE. Each buffer in r1 is
allocated using alloc_page. So for LRO packets, the payload will be in one
buffer from r0 and multiple from r1, for non-LRO packets, only one
descriptor in r0 is used for packet size less than 3k.

When receiving a packet, the first descriptor will have the sop (start of
packet) bit set, and the last descriptor will have the eop (end of packet)
bit set. Non-LRO packets will have only one descriptor with both sop and
eop set.

Other than r0 and r1, vmxnet3 dataring is specifically designed for
handling packets with small size, usually 128 bytes, defined in
VMXNET3_DEF_RXDATA_DESC_SIZE, by simply copying the packet from the backend
driver in ESXi to the ring's memory region at front-end vmxnet3 driver, in
order to avoid memory mapping/unmapping overhead. In summary, packet size:
    A. < 128B: use dataring
    B. 128B - 3K: use ring0 (VMXNET3_RX_BUF_SKB)
    C. > 3K: use ring0 and ring1 (VMXNET3_RX_BUF_SKB + VMXNET3_RX_BUF_PAGE)
As a result, the patch adds XDP support for packets using dataring
and r0 (case A and B), not the large packet size when LRO is enabled.

XDP Implementation:
When user loads and XDP prog, vmxnet3 driver checks configurations, such
as mtu, lro, and re-allocate the rx buffer size for reserving the extra
headroom, XDP_PACKET_HEADROOM, for XDP frame. The XDP prog will then be
associated with every rx queue of the device. Note that when using dataring
for small packet size, vmxnet3 (front-end driver) doesn't control the
buffer allocation, as a result we allocate a new page and copy packet
from the dataring to XDP frame.

The receive side of XDP is implemented for case A and B, by invoking the
bpf program at vmxnet3_rq_rx_complete and handle its returned action.
The vmxnet3_process_xdp(), vmxnet3_process_xdp_small() function handles
the ring0 and dataring case separately, and decides the next journey of
the packet afterward.

For TX, vmxnet3 has split header design. Outgoing packets are parsed
first and protocol headers (L2/L3/L4) are copied to the backend. The
rest of the payload are dma mapped. Since XDP_TX does not parse the
packet protocol, the entire XDP frame is dma mapped for transmission
and transmitted in a batch. Later on, the frame is freed and recycled
back to the memory pool.

Performance:
Tested using two VMs inside one ESXi vSphere 7.0 machine, using single
core on each vmxnet3 device, sender using DPDK testpmd tx-mode attached
to vmxnet3 device, sending 64B or 512B UDP packet.

VM1 txgen:
$ dpdk-testpmd -l 0-3 -n 1 -- -i --nb-cores=3 \
--forward-mode=txonly --eth-peer=0,<mac addr of vm2>
option: add "--txonly-multi-flow"
option: use --txpkts=512 or 64 byte

VM2 running XDP:
$ ./samples/bpf/xdp_rxq_info -d ens160 -a <options> --skb-mode
$ ./samples/bpf/xdp_rxq_info -d ens160 -a <options>
options: XDP_DROP, XDP_PASS, XDP_TX

To test REDIRECT to cpu 0, use
$ ./samples/bpf/xdp_redirect_cpu -d ens160 -c 0 -e drop

Single core performance comparison with skb-mode.
64B:      skb-mode -> native-mode
XDP_DROP: 1.6Mpps -> 2.4Mpps
XDP_PASS: 338Kpps -> 367Kpps
XDP_TX:   1.1Mpps -> 2.3Mpps
REDIRECT-drop: 1.3Mpps -> 2.3Mpps

512B:     skb-mode -> native-mode
XDP_DROP: 863Kpps -> 1.3Mpps
XDP_PASS: 275Kpps -> 376Kpps
XDP_TX:   554Kpps -> 1.2Mpps
REDIRECT-drop: 659Kpps -> 1.2Mpps

Demo: https://youtu.be/4lm1CSCi78Q

Future work:
- XDP frag support
- use napi_consume_skb() instead of dev_kfree_skb_any at unmap
- stats using u64_stats_t
- using bitfield macro BIT()
- optimization for DMA synchronization using actual frame length,
  instead of always max_len

Signed-off-by: William Tu <u9012063@gmail.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 419 insertions, 0 deletions

diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c
new file mode 100644
index 000000000000..80ddaff759d4
--- /dev/null
+++ b/drivers/net/vmxnet3/vmxnet3_xdp.c
@@ -0,0 +1,419 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Linux driver for VMware's vmxnet3 ethernet NIC.
+ * Copyright (C) 2008-2023, VMware, Inc. All Rights Reserved.
+ * Maintained by: pv-drivers@vmware.com
+ *
+ */
+
+#include "vmxnet3_int.h"
+#include "vmxnet3_xdp.h"
+
+static void
+vmxnet3_xdp_exchange_program(struct vmxnet3_adapter *adapter,
+			     struct bpf_prog *prog)
+{
+	rcu_assign_pointer(adapter->xdp_bpf_prog, prog);
+}
+
+static inline struct vmxnet3_tx_queue *
+vmxnet3_xdp_get_tq(struct vmxnet3_adapter *adapter)
+{
+	struct vmxnet3_tx_queue *tq;
+	int tq_number;
+	int cpu;
+
+	tq_number = adapter->num_tx_queues;
+	cpu = smp_processor_id();
+	if (likely(cpu < tq_number))
+		tq = &adapter->tx_queue[cpu];
+	else
+		tq = &adapter->tx_queue[reciprocal_scale(cpu, tq_number)];
+
+	return tq;
+}
+
+static int
+vmxnet3_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf,
+		struct netlink_ext_ack *extack)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+	struct bpf_prog *new_bpf_prog = bpf->prog;
+	struct bpf_prog *old_bpf_prog;
+	bool need_update;
+	bool running;
+	int err;
+
+	if (new_bpf_prog && netdev->mtu > VMXNET3_XDP_MAX_MTU) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "MTU %u too large for XDP",
+				       netdev->mtu);
+		return -EOPNOTSUPP;
+	}
+
+	if (adapter->netdev->features & NETIF_F_LRO) {
+		NL_SET_ERR_MSG_MOD(extack, "LRO is not supported with XDP");
+		adapter->netdev->features &= ~NETIF_F_LRO;
+	}
+
+	old_bpf_prog = rcu_dereference(adapter->xdp_bpf_prog);
+	if (!new_bpf_prog && !old_bpf_prog)
+		return 0;
+
+	running = netif_running(netdev);
+	need_update = !!old_bpf_prog != !!new_bpf_prog;
+
+	if (running && need_update)
+		vmxnet3_quiesce_dev(adapter);
+
+	vmxnet3_xdp_exchange_program(adapter, new_bpf_prog);
+	if (old_bpf_prog)
+		bpf_prog_put(old_bpf_prog);
+
+	if (!running || !need_update)
+		return 0;
+
+	if (new_bpf_prog)
+		xdp_features_set_redirect_target(netdev, false);
+	else
+		xdp_features_clear_redirect_target(netdev);
+
+	vmxnet3_reset_dev(adapter);
+	vmxnet3_rq_destroy_all(adapter);
+	vmxnet3_adjust_rx_ring_size(adapter);
+	err = vmxnet3_rq_create_all(adapter);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "failed to re-create rx queues for XDP.");
+		return -EOPNOTSUPP;
+	}
+	err = vmxnet3_activate_dev(adapter);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "failed to activate device for XDP.");
+		return -EOPNOTSUPP;
+	}
+	clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);
+
+	return 0;
+}
+
+/* This is the main xdp call used by kernel to set/unset eBPF program. */
+int
+vmxnet3_xdp(struct net_device *netdev, struct netdev_bpf *bpf)
+{
+	switch (bpf->command) {
+	case XDP_SETUP_PROG:
+		return vmxnet3_xdp_set(netdev, bpf, bpf->extack);
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
+		       struct xdp_frame *xdpf,
+		       struct vmxnet3_tx_queue *tq, bool dma_map)
+{
+	struct vmxnet3_tx_buf_info *tbi = NULL;
+	union Vmxnet3_GenericDesc *gdesc;
+	struct vmxnet3_tx_ctx ctx;
+	int tx_num_deferred;
+	struct page *page;
+	u32 buf_size;
+	u32 dw2;
+
+	dw2 = (tq->tx_ring.gen ^ 0x1) << VMXNET3_TXD_GEN_SHIFT;
+	dw2 |= xdpf->len;
+	ctx.sop_txd = tq->tx_ring.base + tq->tx_ring.next2fill;
+	gdesc = ctx.sop_txd;
+
+	buf_size = xdpf->len;
+	tbi = tq->buf_info + tq->tx_ring.next2fill;
+
+	if (vmxnet3_cmd_ring_desc_avail(&tq->tx_ring) == 0) {
+		tq->stats.tx_ring_full++;
+		return -ENOSPC;
+	}
+
+	tbi->map_type = VMXNET3_MAP_XDP;
+	if (dma_map) { /* ndo_xdp_xmit */
+		tbi->dma_addr = dma_map_single(&adapter->pdev->dev,
+					       xdpf->data, buf_size,
+					       DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
+			return -EFAULT;
+		tbi->map_type |= VMXNET3_MAP_SINGLE;
+	} else { /* XDP buffer from page pool */
+		page = virt_to_page(xdpf->data);
+		tbi->dma_addr = page_pool_get_dma_addr(page) +
+				VMXNET3_XDP_HEADROOM;
+		dma_sync_single_for_device(&adapter->pdev->dev,
+					   tbi->dma_addr, buf_size,
+					   DMA_TO_DEVICE);
+	}
+	tbi->xdpf = xdpf;
+	tbi->len = buf_size;
+
+	gdesc = tq->tx_ring.base + tq->tx_ring.next2fill;
+	WARN_ON_ONCE(gdesc->txd.gen == tq->tx_ring.gen);
+
+	gdesc->txd.addr = cpu_to_le64(tbi->dma_addr);
+	gdesc->dword[2] = cpu_to_le32(dw2);
+
+	/* Setup the EOP desc */
+	gdesc->dword[3] = cpu_to_le32(VMXNET3_TXD_CQ | VMXNET3_TXD_EOP);
+
+	gdesc->txd.om = 0;
+	gdesc->txd.msscof = 0;
+	gdesc->txd.hlen = 0;
+	gdesc->txd.ti = 0;
+
+	tx_num_deferred = le32_to_cpu(tq->shared->txNumDeferred);
+	le32_add_cpu(&tq->shared->txNumDeferred, 1);
+	tx_num_deferred++;
+
+	vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring);
+
+	/* set the last buf_info for the pkt */
+	tbi->sop_idx = ctx.sop_txd - tq->tx_ring.base;
+
+	dma_wmb();
+	gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^
+						  VMXNET3_TXD_GEN);
+
+	/* No need to handle the case when tx_num_deferred doesn't reach
+	 * threshold. Backend driver at hypervisor side will poll and reset
+	 * tq->shared->txNumDeferred to 0.
+	 */
+	if (tx_num_deferred >= le32_to_cpu(tq->shared->txThreshold)) {
+		tq->shared->txNumDeferred = 0;
+		VMXNET3_WRITE_BAR0_REG(adapter,
+				       VMXNET3_REG_TXPROD + tq->qid * 8,
+				       tq->tx_ring.next2fill);
+	}
+
+	return 0;
+}
+
+static int
+vmxnet3_xdp_xmit_back(struct vmxnet3_adapter *adapter,
+		      struct xdp_frame *xdpf)
+{
+	struct vmxnet3_tx_queue *tq;
+	struct netdev_queue *nq;
+	int err;
+
+	tq = vmxnet3_xdp_get_tq(adapter);
+	if (tq->stopped)
+		return -ENETDOWN;
+
+	nq = netdev_get_tx_queue(adapter->netdev, tq->qid);
+
+	__netif_tx_lock(nq, smp_processor_id());
+	err = vmxnet3_xdp_xmit_frame(adapter, xdpf, tq, false);
+	__netif_tx_unlock(nq);
+
+	return err;
+}
+
+/* ndo_xdp_xmit */
+int
+vmxnet3_xdp_xmit(struct net_device *dev,
+		 int n, struct xdp_frame **frames, u32 flags)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(dev);
+	struct vmxnet3_tx_queue *tq;
+	int i;
+
+	if (unlikely(test_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state)))
+		return -ENETDOWN;
+	if (unlikely(test_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state)))
+		return -EINVAL;
+
+	tq = vmxnet3_xdp_get_tq(adapter);
+	if (tq->stopped)
+		return -ENETDOWN;
+
+	for (i = 0; i < n; i++) {
+		if (vmxnet3_xdp_xmit_frame(adapter, frames[i], tq, true)) {
+			tq->stats.xdp_xmit_err++;
+			break;
+		}
+	}
+	tq->stats.xdp_xmit += i;
+
+	return i;
+}
+
+static int
+vmxnet3_run_xdp(struct vmxnet3_rx_queue *rq, struct xdp_buff *xdp,
+		struct bpf_prog *prog)
+{
+	struct xdp_frame *xdpf;
+	struct page *page;
+	int err;
+	u32 act;
+
+	rq->stats.xdp_packets++;
+	act = bpf_prog_run_xdp(prog, xdp);
+	page = virt_to_page(xdp->data_hard_start);
+
+	switch (act) {
+	case XDP_PASS:
+		return act;
+	case XDP_REDIRECT:
+		err = xdp_do_redirect(rq->adapter->netdev, xdp, prog);
+		if (!err) {
+			rq->stats.xdp_redirects++;
+		} else {
+			rq->stats.xdp_drops++;
+			page_pool_recycle_direct(rq->page_pool, page);
+		}
+		return act;
+	case XDP_TX:
+		xdpf = xdp_convert_buff_to_frame(xdp);
+		if (unlikely(!xdpf ||
+			     vmxnet3_xdp_xmit_back(rq->adapter, xdpf))) {
+			rq->stats.xdp_drops++;
+			page_pool_recycle_direct(rq->page_pool, page);
+		} else {
+			rq->stats.xdp_tx++;
+		}
+		return act;
+	default:
+		bpf_warn_invalid_xdp_action(rq->adapter->netdev, prog, act);
+		fallthrough;
+	case XDP_ABORTED:
+		trace_xdp_exception(rq->adapter->netdev, prog, act);
+		rq->stats.xdp_aborted++;
+		break;
+	case XDP_DROP:
+		rq->stats.xdp_drops++;
+		break;
+	}
+
+	page_pool_recycle_direct(rq->page_pool, page);
+
+	return act;
+}
+
+static struct sk_buff *
+vmxnet3_build_skb(struct vmxnet3_rx_queue *rq, struct page *page,
+		  const struct xdp_buff *xdp)
+{
+	struct sk_buff *skb;
+
+	skb = build_skb(page_address(page), PAGE_SIZE);
+	if (unlikely(!skb)) {
+		page_pool_recycle_direct(rq->page_pool, page);
+		rq->stats.rx_buf_alloc_failure++;
+		return NULL;
+	}
+
+	/* bpf prog might change len and data position. */
+	skb_reserve(skb, xdp->data - xdp->data_hard_start);
+	skb_put(skb, xdp->data_end - xdp->data);
+	skb_mark_for_recycle(skb);
+
+	return skb;
+}
+
+/* Handle packets from DataRing. */
+int
+vmxnet3_process_xdp_small(struct vmxnet3_adapter *adapter,
+			  struct vmxnet3_rx_queue *rq,
+			  void *data, int len,
+			  struct sk_buff **skb_xdp_pass)
+{
+	struct bpf_prog *xdp_prog;
+	struct xdp_buff xdp;
+	struct page *page;
+	int act;
+
+	page = page_pool_alloc_pages(rq->page_pool, GFP_ATOMIC);
+	if (unlikely(!page)) {
+		rq->stats.rx_buf_alloc_failure++;
+		return XDP_DROP;
+	}
+
+	xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq);
+	xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset,
+			 len, false);
+	xdp_buff_clear_frags_flag(&xdp);
+
+	/* Must copy the data because it's at dataring. */
+	memcpy(xdp.data, data, len);
+
+	xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog);
+	if (!xdp_prog) {
+		act = XDP_PASS;
+		goto out_skb;
+	}
+	act = vmxnet3_run_xdp(rq, &xdp, xdp_prog);
+	if (act != XDP_PASS)
+		return act;
+
+out_skb:
+	*skb_xdp_pass = vmxnet3_build_skb(rq, page, &xdp);
+	if (!*skb_xdp_pass)
+		return XDP_DROP;
+
+	/* No need to refill. */
+	return likely(*skb_xdp_pass) ? act : XDP_DROP;
+}
+
+int
+vmxnet3_process_xdp(struct vmxnet3_adapter *adapter,
+		    struct vmxnet3_rx_queue *rq,
+		    struct Vmxnet3_RxCompDesc *rcd,
+		    struct vmxnet3_rx_buf_info *rbi,
+		    struct Vmxnet3_RxDesc *rxd,
+		    struct sk_buff **skb_xdp_pass)
+{
+	struct bpf_prog *xdp_prog;
+	dma_addr_t new_dma_addr;
+	struct xdp_buff xdp;
+	struct page *page;
+	void *new_data;
+	int act;
+
+	page = rbi->page;
+	dma_sync_single_for_cpu(&adapter->pdev->dev,
+				page_pool_get_dma_addr(page) +
+				rq->page_pool->p.offset, rcd->len,
+				page_pool_get_dma_dir(rq->page_pool));
+
+	xdp_init_buff(&xdp, rbi->len, &rq->xdp_rxq);
+	xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset,
+			 rcd->len, false);
+	xdp_buff_clear_frags_flag(&xdp);
+
+	xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog);
+	if (!xdp_prog) {
+		act = XDP_PASS;
+		goto out_skb;
+	}
+	act = vmxnet3_run_xdp(rq, &xdp, xdp_prog);
+
+	if (act == XDP_PASS) {
+out_skb:
+		*skb_xdp_pass = vmxnet3_build_skb(rq, page, &xdp);
+		if (!*skb_xdp_pass)
+			act = XDP_DROP;
+	}
+
+	new_data = vmxnet3_pp_get_buff(rq->page_pool, &new_dma_addr,
+				       GFP_ATOMIC);
+	if (!new_data) {
+		rq->stats.rx_buf_alloc_failure++;
+		return XDP_DROP;
+	}
+	rbi->page = virt_to_page(new_data);
+	rbi->dma_addr = new_dma_addr;
+	rxd->addr = cpu_to_le64(rbi->dma_addr);
+	rxd->len = rbi->len;
+
+	return act;
+}