Message-Id: <20230711114705.22428-3-sriram.yagnaraman@est.tech>
Date: Tue, 11 Jul 2023 13:47:03 +0200
From: Sriram Yagnaraman <sriram.yagnaraman@....tech>
To:
Cc: intel-wired-lan@...ts.osuosl.org, bpf@...r.kernel.org,
        netdev@...r.kernel.org, Jesse Brandeburg <jesse.brandeburg@...el.com>,
        Tony Nguyen <anthony.l.nguyen@...el.com>,
        "David S . Miller" <davem@...emloft.net>,
        Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>, Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Jesper Dangaard Brouer <hawk@...nel.org>,
        John Fastabend <john.fastabend@...il.com>,
        Björn Töpel <bjorn@...nel.org>,
        Magnus Karlsson <magnus.karlsson@...el.com>,
        Maciej Fijalkowski <maciej.fijalkowski@...el.com>,
        Jonathan Lemon <jonathan.lemon@...il.com>,
        Sriram Yagnaraman <sriram.yagnaraman@....tech>
Subject: [PATCH iwl-next v2 2/4] igb: Introduce XSK data structures and helpers

Add the following ring flags
- IGB_RING_FLAG_TX_DISABLED (when xsk pool is being setup)
- IGB_RING_FLAG_AF_XDP_ZC (xsk pool is active)

Add a xdp_buff array for use with XSK receive batch API, and a pointer
to xsk_pool in igb_adapter.

Add enable/disable functions for TX and RX rings
Add enable/disable functions for XSK pool
Add xsk wakeup function

None of the above functionality will be active until
NETDEV_XDP_ACT_XSK_ZEROCOPY is advertised in netdev->xdp_features.

Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@....tech>
---
 drivers/net/ethernet/intel/igb/Makefile   |   2 +-
 drivers/net/ethernet/intel/igb/igb.h      |  14 +-
 drivers/net/ethernet/intel/igb/igb_main.c |   9 +
 drivers/net/ethernet/intel/igb/igb_xsk.c  | 210 ++++++++++++++++++++++
 4 files changed, 233 insertions(+), 2 deletions(-)
 create mode 100644 drivers/net/ethernet/intel/igb/igb_xsk.c

diff --git a/drivers/net/ethernet/intel/igb/Makefile b/drivers/net/ethernet/intel/igb/Makefile
index 394c1e0656b9..86d25dba507d 100644
--- a/drivers/net/ethernet/intel/igb/Makefile
+++ b/drivers/net/ethernet/intel/igb/Makefile
@@ -8,4 +8,4 @@ obj-$(CONFIG_IGB) += igb.o
 
 igb-objs := igb_main.o igb_ethtool.o e1000_82575.o \
 	    e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \
-	    e1000_i210.o igb_ptp.o igb_hwmon.o
+	    e1000_i210.o igb_ptp.o igb_hwmon.o igb_xsk.o
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 58e79eb69f92..1af1a0423fba 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -20,6 +20,7 @@
 #include <linux/mdio.h>
 
 #include <net/xdp.h>
+#include <net/xdp_sock_drv.h>
 
 struct igb_adapter;
 
@@ -320,6 +321,7 @@ struct igb_ring {
 	union {				/* array of buffer info structs */
 		struct igb_tx_buffer *tx_buffer_info;
 		struct igb_rx_buffer *rx_buffer_info;
+		struct xdp_buff **rx_buffer_info_zc;
 	};
 	void *desc;			/* descriptor ring memory */
 	unsigned long flags;		/* ring specific flags */
@@ -357,6 +359,7 @@ struct igb_ring {
 		};
 	};
 	struct xdp_rxq_info xdp_rxq;
+	struct xsk_buff_pool *xsk_pool;
 } ____cacheline_internodealigned_in_smp;
 
 struct igb_q_vector {
@@ -384,7 +387,9 @@ enum e1000_ring_flags_t {
 	IGB_RING_FLAG_RX_SCTP_CSUM,
 	IGB_RING_FLAG_RX_LB_VLAN_BSWAP,
 	IGB_RING_FLAG_TX_CTX_IDX,
-	IGB_RING_FLAG_TX_DETECT_HANG
+	IGB_RING_FLAG_TX_DETECT_HANG,
+	IGB_RING_FLAG_TX_DISABLED,
+	IGB_RING_FLAG_AF_XDP_ZC
 };
 
 #define ring_uses_large_buffer(ring) \
@@ -822,4 +827,11 @@ int igb_add_mac_steering_filter(struct igb_adapter *adapter,
 int igb_del_mac_steering_filter(struct igb_adapter *adapter,
 				const u8 *addr, u8 queue, u8 flags);
 
+struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter,
+				   struct igb_ring *ring);
+int igb_xsk_pool_setup(struct igb_adapter *adapter,
+		       struct xsk_buff_pool *pool,
+		       u16 qid);
+int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags);
+
 #endif /* _IGB_H_ */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 775c78df73fb..2c1e1d70bcf9 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2929,9 +2929,14 @@ static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf)
 
 static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
+	struct igb_adapter *adapter = netdev_priv(dev);
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return igb_xdp_setup(dev, xdp);
+	case XDP_SETUP_XSK_POOL:
+		return igb_xsk_pool_setup(adapter, xdp->xsk.pool,
+					  xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
 	}
@@ -3058,6 +3063,7 @@ static const struct net_device_ops igb_netdev_ops = {
 	.ndo_setup_tc		= igb_setup_tc,
 	.ndo_bpf		= igb_xdp,
 	.ndo_xdp_xmit		= igb_xdp_xmit,
+	.ndo_xsk_wakeup         = igb_xsk_wakeup,
 };
 
 /**
@@ -4376,6 +4382,8 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
 	u64 tdba = ring->dma;
 	int reg_idx = ring->reg_idx;
 
+	ring->xsk_pool = igb_xsk_pool(adapter, ring);
+
 	wr32(E1000_TDLEN(reg_idx),
 	     ring->count * sizeof(union e1000_adv_tx_desc));
 	wr32(E1000_TDBAL(reg_idx),
@@ -4771,6 +4779,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 	WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 					   MEM_TYPE_PAGE_SHARED, NULL));
+	ring->xsk_pool = igb_xsk_pool(adapter, ring);
 
 	/* disable the queue */
 	wr32(E1000_RXDCTL(reg_idx), 0);
diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c
new file mode 100644
index 000000000000..925bf97f7caa
--- /dev/null
+++ b/drivers/net/ethernet/intel/igb/igb_xsk.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Intel Corporation. */
+
+#include <linux/bpf_trace.h>
+#include <net/xdp_sock_drv.h>
+#include <net/xdp.h>
+
+#include "e1000_hw.h"
+#include "igb.h"
+
+static int igb_realloc_rx_buffer_info(struct igb_ring *ring, bool pool_present)
+{
+	int size = pool_present ?
+		sizeof(*ring->rx_buffer_info_zc) * ring->count :
+		sizeof(*ring->rx_buffer_info) * ring->count;
+	void *buff_info = vmalloc(size);
+
+	if (!buff_info)
+		return -ENOMEM;
+
+	if (pool_present) {
+		vfree(ring->rx_buffer_info);
+		ring->rx_buffer_info = NULL;
+		ring->rx_buffer_info_zc = buff_info;
+	} else {
+		vfree(ring->rx_buffer_info_zc);
+		ring->rx_buffer_info_zc = NULL;
+		ring->rx_buffer_info = buff_info;
+	}
+
+	return 0;
+}
+
+static void igb_txrx_ring_disable(struct igb_adapter *adapter, u16 qid)
+{
+	struct igb_ring *tx_ring = adapter->tx_ring[qid];
+	struct igb_ring *rx_ring = adapter->rx_ring[qid];
+	struct e1000_hw *hw = &adapter->hw;
+
+	set_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags);
+
+	wr32(E1000_TXDCTL(tx_ring->reg_idx), 0);
+	wr32(E1000_RXDCTL(rx_ring->reg_idx), 0);
+
+	/* Rx/Tx share the same napi context. */
+	napi_disable(&rx_ring->q_vector->napi);
+
+	igb_clean_tx_ring(tx_ring);
+	igb_clean_rx_ring(rx_ring);
+
+	memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats));
+	memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats));
+}
+
+static void igb_txrx_ring_enable(struct igb_adapter *adapter, u16 qid)
+{
+	struct igb_ring *tx_ring = adapter->tx_ring[qid];
+	struct igb_ring *rx_ring = adapter->rx_ring[qid];
+
+	igb_configure_tx_ring(adapter, tx_ring);
+	igb_configure_rx_ring(adapter, rx_ring);
+
+	clear_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags);
+
+	/* call igb_desc_unused which always leaves
+	 * at least 1 descriptor unused to make sure
+	 * next_to_use != next_to_clean
+	 */
+	igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring));
+
+	/* Rx/Tx share the same napi context. */
+	napi_enable(&rx_ring->q_vector->napi);
+}
+
+struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter,
+				   struct igb_ring *ring)
+{
+	int qid = ring->queue_index;
+
+	if (!igb_xdp_is_enabled(adapter) ||
+	    !test_bit(IGB_RING_FLAG_AF_XDP_ZC, &ring->flags))
+		return NULL;
+
+	return xsk_get_pool_from_qid(adapter->netdev, qid);
+}
+
+static int igb_xsk_pool_enable(struct igb_adapter *adapter,
+			       struct xsk_buff_pool *pool,
+			       u16 qid)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct igb_ring *tx_ring, *rx_ring;
+	bool if_running;
+	int err;
+
+	if (qid >= adapter->num_rx_queues)
+		return -EINVAL;
+
+	if (qid >= netdev->real_num_rx_queues ||
+	    qid >= netdev->real_num_tx_queues)
+		return -EINVAL;
+
+	err = xsk_pool_dma_map(pool, &adapter->pdev->dev, IGB_RX_DMA_ATTR);
+	if (err)
+		return err;
+
+	tx_ring = adapter->tx_ring[qid];
+	rx_ring = adapter->rx_ring[qid];
+	if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter);
+	if (if_running)
+		igb_txrx_ring_disable(adapter, qid);
+
+	set_bit(IGB_RING_FLAG_AF_XDP_ZC, &tx_ring->flags);
+	set_bit(IGB_RING_FLAG_AF_XDP_ZC, &rx_ring->flags);
+
+	if (if_running) {
+		err = igb_realloc_rx_buffer_info(rx_ring, true);
+		if (!err) {
+			igb_txrx_ring_enable(adapter, qid);
+			/* Kick start the NAPI context so that receiving will start */
+			err = igb_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX);
+		}
+
+		if (err) {
+			clear_bit(IGB_RING_FLAG_AF_XDP_ZC, &tx_ring->flags);
+			clear_bit(IGB_RING_FLAG_AF_XDP_ZC, &rx_ring->flags);
+			xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int igb_xsk_pool_disable(struct igb_adapter *adapter, u16 qid)
+{
+	struct igb_ring *tx_ring, *rx_ring;
+	struct xsk_buff_pool *pool;
+	bool if_running;
+	int err;
+
+	pool = xsk_get_pool_from_qid(adapter->netdev, qid);
+	if (!pool)
+		return -EINVAL;
+
+	tx_ring = adapter->tx_ring[qid];
+	rx_ring = adapter->rx_ring[qid];
+	if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter);
+	if (if_running)
+		igb_txrx_ring_disable(adapter, qid);
+
+	xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR);
+	clear_bit(IGB_RING_FLAG_AF_XDP_ZC, &tx_ring->flags);
+	clear_bit(IGB_RING_FLAG_AF_XDP_ZC, &rx_ring->flags);
+
+	if (if_running) {
+		err = igb_realloc_rx_buffer_info(rx_ring, false);
+		if (err)
+			return err;
+
+		igb_txrx_ring_enable(adapter, qid);
+	}
+
+	return 0;
+}
+
+int igb_xsk_pool_setup(struct igb_adapter *adapter,
+		       struct xsk_buff_pool *pool,
+		       u16 qid)
+{
+	return pool ? igb_xsk_pool_enable(adapter, pool, qid) :
+		igb_xsk_pool_disable(adapter, qid);
+}
+
+int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
+{
+	struct igb_adapter *adapter = netdev_priv(dev);
+	struct e1000_hw *hw = &adapter->hw;
+	struct igb_ring *ring;
+	u32 eics = 0;
+
+	if (test_bit(__IGB_DOWN, &adapter->state))
+		return -ENETDOWN;
+
+	if (!igb_xdp_is_enabled(adapter))
+		return -EINVAL;
+
+	if (qid >= adapter->num_tx_queues)
+		return -EINVAL;
+
+	ring = adapter->tx_ring[qid];
+
+	if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags))
+		return -ENETDOWN;
+
+	if (!ring->xsk_pool)
+		return -EINVAL;
+
+	if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) {
+		/* Cause software interrupt to ensure Rx ring is cleaned */
+		if (adapter->flags & IGB_FLAG_HAS_MSIX) {
+			eics |= ring->q_vector->eims_value;
+			wr32(E1000_EICS, eics);
+		} else {
+			wr32(E1000_ICS, E1000_ICS_RXDMT0);
+		}
+	}
+
+	return 0;
+}
-- 
2.34.1

Powered by blists - more mailing lists