net: low latency Ethernet device polling

index 8f967e3..39bbd46 100644
@@ -324,12 +324,15 @@ struct napi_struct {
 	struct sk_buff		*gro_list;
 	struct sk_buff		*skb;
 	struct list_head	dev_list;
+	struct hlist_node	napi_hash_node;
+	unsigned int		napi_id;
 };
 
 enum {
 	NAPI_STATE_SCHED,	/* Poll is scheduled */
 	NAPI_STATE_DISABLE,	/* Disable pending */
 	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
+	NAPI_STATE_HASHED,	/* In NAPI hash */
 };
 
 enum gro_result {

@@ -446,6 +449,32 @@ extern void __napi_complete(struct napi_struct *n);
 extern void napi_complete(struct napi_struct *n);
 
 /**
+ *	napi_by_id - lookup a NAPI by napi_id
+ *	@napi_id: hashed napi_id
+ *
+ * lookup @napi_id in napi_hash table
+ * must be called under rcu_read_lock()
+ */
+extern struct napi_struct *napi_by_id(unsigned int napi_id);
+
+/**
+ *	napi_hash_add - add a NAPI to global hashtable
+ *	@napi: napi context
+ *
+ * generate a new napi_id and store a @napi under it in napi_hash
+ */
+extern void napi_hash_add(struct napi_struct *napi);
+
+/**
+ *	napi_hash_del - remove a NAPI from global table
+ *	@napi: napi context
+ *
+ * Warning: caller must observe rcu grace period
+ * before freeing memory containing @napi
+ */
+extern void napi_hash_del(struct napi_struct *napi);
+
+/**
  *	napi_disable - prevent NAPI from scheduling
  *	@n: napi context
  *

77 lines not on this page · raw message

index 39bbd46..2ecb96d 100644
@@ -972,6 +972,9 @@ struct net_device_ops {
 						     gfp_t gfp);
 	void			(*ndo_netpoll_cleanup)(struct net_device *dev);
 #endif
+#ifdef CONFIG_NET_LL_RX_POLL
+	int			(*ndo_ll_poll)(struct napi_struct *dev);
+#endif
 	int			(*ndo_set_vf_mac)(struct net_device *dev,
 						  int queue, u8 *mac);
 	int			(*ndo_set_vf_vlan)(struct net_device *dev,

index b999790..908246b 100644
@@ -386,6 +386,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@no_fcs:  Request NIC to treat last 4 bytes as Ethernet FCS
  *	@dma_cookie: a cookie to one of several possible DMA operations
  *		done by skb DMA functions
+  *	@napi_id: id of the NAPI struct this skb came from
  *	@secmark: security marking
  *	@mark: Generic packet mark
  *	@dropcount: total number of sk_receive_queue overflows

@@ -500,8 +501,11 @@ struct sk_buff {
 	/* 7/9 bit hole (depending on ndisc_nodetype presence) */
 	kmemcheck_bitfield_end(flags2);
 
-#ifdef CONFIG_NET_DMA
-	dma_cookie_t		dma_cookie;
+#if defined CONFIG_NET_DMA || defined CONFIG_NET_LL_RX_POLL
+	union {
+		unsigned int	napi_id;
+		dma_cookie_t	dma_cookie;
+	};
 #endif
 #ifdef CONFIG_NETWORK_SECMARK
 	__u32			secmark;

148 lines not on this page · raw message

index 66772cf..ac8e181 100644
@@ -229,6 +229,7 @@ struct cg_proto;
   *	@sk_omem_alloc: "o" is "option" or "other"
   *	@sk_wmem_queued: persistent queue size
   *	@sk_forward_alloc: space allocated forward
+  *	@sk_napi_id: id of the last napi context to receive data for sk
   *	@sk_allocation: allocation mode
   *	@sk_sndbuf: size of send buffer in bytes
   *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,

@@ -325,6 +326,9 @@ struct sock {
 #ifdef CONFIG_RPS
 	__u32			sk_rxhash;
 #endif
+#ifdef CONFIG_NET_LL_RX_POLL
+	unsigned int		sk_napi_id;
+#endif
 	atomic_t		sk_drops;
 	int			sk_rcvbuf;
 

index df2e8b4..26cbf76 100644
@@ -253,6 +253,7 @@ enum
 	LINUX_MIB_TCPFASTOPENLISTENOVERFLOW,	/* TCPFastOpenListenOverflow */
 	LINUX_MIB_TCPFASTOPENCOOKIEREQD,	/* TCPFastOpenCookieReqd */
 	LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES, /* TCPSpuriousRtxHostQueues */
+	LINUX_MIB_LOWLATENCYRXPACKETS,		/* LowLatencyRxPackets */
 	__LINUX_MIB_MAX
 };
 

index 6b1b52c..73ef74d 100644
@@ -733,6 +733,10 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->vlan_tci		= old->vlan_tci;
 
 	skb_copy_secmark(new, old);
+
+#ifdef CONFIG_NET_LL_RX_POLL
+	new->napi_id	= old->napi_id;
+#endif
 }
 
 /*

index 6ba327d..804fd5b 100644
@@ -139,6 +139,8 @@
 #include <net/tcp.h>
 #endif
 
+#include <net/ll_poll.h>
+
 static DEFINE_MUTEX(proto_list_mutex);
 static LIST_HEAD(proto_list);
 

@@ -2284,6 +2286,10 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 	sk->sk_stamp = ktime_set(-1L, 0);
 
+#ifdef CONFIG_NET_LL_RX_POLL
+	sk->sk_napi_id		=	0;
+#endif
+
 	/*
 	 * Before updating sk_refcnt, we must commit prior changes to memory
 	 * (Documentation/RCU/rculist_nulls.txt for details)

index 741db5fc..ae98c95 100644
@@ -19,6 +19,7 @@
 #include <net/ip.h>
 #include <net/sock.h>
 #include <net/net_ratelimit.h>
+#include <net/ll_poll.h>
 
 static int one = 1;
 

@@ -284,6 +285,15 @@ static struct ctl_table net_core_table[] = {
 		.proc_handler	= flow_limit_table_len_sysctl
 	},
 #endif /* CONFIG_NET_FLOW_LIMIT */
+#ifdef CONFIG_NET_LL_RX_POLL
+	{
+		.procname	= "low_latency_poll",
+		.data		= &sysctl_net_ll_poll,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+#endif
 #endif /* CONFIG_NET */
 	{
 		.procname	= "netdev_budget",

index 2a5bf86..6577a11 100644
@@ -273,6 +273,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
 	SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD),
 	SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
+	SNMP_MIB_ITEM("LowLatencyRxPackets", LINUX_MIB_LOWLATENCYRXPACKETS),
 	SNMP_MIB_SENTINEL
 };
 

index 6b94633..721f4e7 100644
@@ -104,6 +104,12 @@
 #include <linux/route.h>
 #include <linux/sockios.h>
 #include <linux/atalk.h>
+#include <net/ll_poll.h>
+
+#ifdef CONFIG_NET_LL_RX_POLL
+unsigned long sysctl_net_ll_poll __read_mostly;
+EXPORT_SYMBOL_GPL(sysctl_net_ll_poll);
+#endif
 
 static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
 static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,

index b71423d..9cbaba9 100644
@@ -56,6 +56,7 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 #include <trace/events/skb.h>
+#include <net/ll_poll.h>
 
 /*
  *	Is a socket 'connection oriented' ?

@@ -207,6 +208,9 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 		}
 		spin_unlock_irqrestore(&queue->lock, cpu_flags);
 
+		if (sk_valid_ll(sk) && sk_poll_ll(sk, flags & MSG_DONTWAIT))
+			continue;
+
 		/* User doesn't want to wait */
 		error = -EAGAIN;
 		if (!timeo)

index c7338ec..2955b25 100644
@@ -109,6 +109,7 @@
 #include <trace/events/udp.h>
 #include <linux/static_key.h>
 #include <trace/events/skb.h>
+#include <net/ll_poll.h>
 #include "udp_impl.h"
 
 struct udp_table udp_table __read_mostly;

@@ -1709,7 +1710,10 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 
 	if (sk != NULL) {
-		int ret = udp_queue_rcv_skb(sk, skb);
+		int ret;
+
+		sk_mark_ll(sk, skb);
+		ret = udp_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
 		/* a return value > 0 means to resubmit the input, but

index 42923b1..4035997 100644
@@ -46,6 +46,7 @@
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
 #include <net/inet6_hashtables.h>
+#include <net/ll_poll.h>
 
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>

@@ -841,7 +842,10 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	 */
 	sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 	if (sk != NULL) {
-		int ret = udpv6_queue_rcv_skb(sk, skb);
+		int ret;
+
+		sk_mark_ll(sk, skb);
+		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
 		/* a return value > 0 means to resubmit the input, but

index b5d4ad9..bf09f6b 100644
@@ -279,6 +279,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
+#include <net/ll_poll.h>
 
 int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 

@@ -1553,6 +1554,10 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	struct sk_buff *skb;
 	u32 urg_hole = 0;
 
+	if (sk_valid_ll(sk) && skb_queue_empty(&sk->sk_receive_queue)
+	    && (sk->sk_state == TCP_ESTABLISHED))
+		sk_poll_ll(sk, nonblock);
+
 	lock_sock(sk);
 
 	err = -ENOTCONN;

index d20ede0..35fd8bc 100644
@@ -75,6 +75,7 @@
 #include <net/netdma.h>
 #include <net/secure_seq.h>
 #include <net/tcp_memcontrol.h>
+#include <net/ll_poll.h>
 
 #include <linux/inet.h>
 #include <linux/ipv6.h>

@@ -2011,6 +2012,7 @@ process:
 	if (sk_filter(sk, skb))
 		goto discard_and_relse;
 
+	sk_mark_ll(sk, skb);
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);

index 0a17ed9..5cffa5c 100644
@@ -63,6 +63,7 @@
 #include <net/inet_common.h>
 #include <net/secure_seq.h>
 #include <net/tcp_memcontrol.h>
+#include <net/ll_poll.h>
 
 #include <asm/uaccess.h>
 

@@ -1498,6 +1499,7 @@ process:
 	if (sk_filter(sk, skb))
 		goto discard_and_relse;
 
+	sk_mark_ll(sk, skb);
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);

index 8c1c96c..f116bf0 100644
@@ -27,6 +27,7 @@
 #include <linux/rcupdate.h>
 #include <linux/hrtimer.h>
 #include <linux/sched/rt.h>
+#include <net/ll_poll.h>
 
 #include <asm/uaccess.h>
 

@@ -400,6 +401,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
 	poll_table *wait;
 	int retval, i, timed_out = 0;
 	unsigned long slack = 0;
+	cycles_t ll_time = ll_end_time();
 
 	rcu_read_lock();
 	retval = max_select_fd(n, fds);

@@ -486,6 +488,8 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
 			break;
 		}
 
+		if (can_poll_ll(ll_time))
+			continue;
 		/*
 		 * If this is the first loop and we have a timeout
 		 * given, then we convert to ktime_t and set the to

@@ -750,6 +754,7 @@ static int do_poll(unsigned int nfds,  struct poll_list *list,
 	ktime_t expire, *to = NULL;
 	int timed_out = 0, count = 0;
 	unsigned long slack = 0;
+	cycles_t ll_time = ll_end_time();
 
 	/* Optimise the no-wait case */
 	if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {

@@ -795,6 +800,8 @@ static int do_poll(unsigned int nfds,  struct poll_list *list,
 		if (count || timed_out)
 			break;
 
+		if (can_poll_ll(ll_time))
+			continue;
 		/*
 		 * If this is the first loop and we have a timeout
 		 * given, then we convert to ktime_t and set the to

index 721f4e7..02d0e15 100644
@@ -1148,13 +1148,21 @@ EXPORT_SYMBOL(sock_create_lite);
 /* No kernel lock held - perfect */
 static unsigned int sock_poll(struct file *file, poll_table *wait)
 {
+	unsigned int poll_result;
 	struct socket *sock;
 
 	/*
 	 *      We can't return errors to poll, so it's either yes or no.
 	 */
 	sock = file->private_data;
-	return sock->ops->poll(file, sock, wait);
+
+	poll_result = sock->ops->poll(file, sock, wait);
+
+	if (!(poll_result & (POLLRDNORM | POLLERR | POLLRDHUP | POLLHUP)) &&
+		sk_valid_ll(sock->sk) && sk_poll_ll(sock->sk, 1))
+			poll_result = sock->ops->poll(file, sock, NULL);
+
+	return poll_result;
 }
 
 static int sock_mmap(struct file *file, struct vm_area_struct *vma)

index ca93238..046196c 100644
@@ -52,6 +52,8 @@
 #include <linux/dca.h>
 #endif
 
+#include <net/ll_poll.h>
+
 /* common prefix used by pr_<> macros */
 #undef pr_fmt
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

@@ -356,9 +358,127 @@ struct ixgbe_q_vector {
 	struct rcu_head rcu;	/* to avoid race with update stats on free */
 	char name[IFNAMSIZ + 9];
 
+#ifdef CONFIG_NET_LL_RX_POLL
+	unsigned int state;
+#define IXGBE_QV_STATE_IDLE        0
+#define IXGBE_QV_STATE_NAPI	   1    /* NAPI owns this QV */
+#define IXGBE_QV_STATE_POLL	   2    /* poll owns this QV */
+#define IXGBE_QV_LOCKED (IXGBE_QV_STATE_NAPI | IXGBE_QV_STATE_POLL)
+#define IXGBE_QV_STATE_NAPI_YIELD  4    /* NAPI yielded this QV */
+#define IXGBE_QV_STATE_POLL_YIELD  8    /* poll yielded this QV */
+#define IXGBE_QV_YIELD (IXGBE_QV_STATE_NAPI_YIELD | IXGBE_QV_STATE_POLL_YIELD)
+#define IXGBE_QV_USER_PEND (IXGBE_QV_STATE_POLL | IXGBE_QV_STATE_POLL_YIELD)
+	spinlock_t lock;
+#endif  /* CONFIG_NET_LL_RX_POLL */
+
 	/* for dynamic allocation of rings associated with this q_vector */
 	struct ixgbe_ring ring[0] ____cacheline_internodealigned_in_smp;
 };
+#ifdef CONFIG_NET_LL_RX_POLL
+static inline void ixgbe_qv_init_lock(struct ixgbe_q_vector *q_vector)
+{
+
+	spin_lock_init(&q_vector->lock);
+	q_vector->state = IXGBE_QV_STATE_IDLE;
+}
+
+/* called from the device poll rutine to get ownership of a q_vector */
+static inline bool ixgbe_qv_lock_napi(struct ixgbe_q_vector *q_vector)
+{
+	int rc = true;
+	spin_lock(&q_vector->lock);
+	if (q_vector->state & IXGBE_QV_LOCKED) {
+		WARN_ON(q_vector->state & IXGBE_QV_STATE_NAPI);
+		q_vector->state |= IXGBE_QV_STATE_NAPI_YIELD;
+		rc = false;
+	} else
+		/* we don't care if someone yielded */
+		q_vector->state = IXGBE_QV_STATE_NAPI;
+	spin_unlock(&q_vector->lock);
+	return rc;
+}
+
+/* returns true is someone tried to get the qv while napi had it */
+static inline bool ixgbe_qv_unlock_napi(struct ixgbe_q_vector *q_vector)
+{
+	int rc = false;
+	spin_lock(&q_vector->lock);
+	WARN_ON(q_vector->state & (IXGBE_QV_STATE_POLL |
+			       IXGBE_QV_STATE_NAPI_YIELD));
+
+	if (q_vector->state & IXGBE_QV_STATE_POLL_YIELD)
+		rc = true;
+	q_vector->state = IXGBE_QV_STATE_IDLE;
+	spin_unlock(&q_vector->lock);
+	return rc;
+}
+
+/* called from ixgbe_low_latency_poll() */
+static inline bool ixgbe_qv_lock_poll(struct ixgbe_q_vector *q_vector)
+{
+	int rc = true;
+	spin_lock_bh(&q_vector->lock);
+	if ((q_vector->state & IXGBE_QV_LOCKED)) {
+		q_vector->state |= IXGBE_QV_STATE_POLL_YIELD;
+		rc = false;
+	} else
+		/* preserve yield marks */
+		q_vector->state |= IXGBE_QV_STATE_POLL;
+	spin_unlock_bh(&q_vector->lock);
+	return rc;
+}
+
+/* returns true if someone tried to get the qv while it was locked */
+static inline bool ixgbe_qv_unlock_poll(struct ixgbe_q_vector *q_vector)
+{
+	int rc = false;
+	spin_lock_bh(&q_vector->lock);
+	WARN_ON(q_vector->state & (IXGBE_QV_STATE_NAPI));
+
+	if (q_vector->state & IXGBE_QV_STATE_POLL_YIELD)
+		rc = true;
+	q_vector->state = IXGBE_QV_STATE_IDLE;
+	spin_unlock_bh(&q_vector->lock);
+	return rc;
+}
+
+/* true if a socket is polling, even if it did not get the lock */
+static inline bool ixgbe_qv_ll_polling(struct ixgbe_q_vector *q_vector)
+{
+	WARN_ON(!(q_vector->state & IXGBE_QV_LOCKED));
+	return q_vector->state & IXGBE_QV_USER_PEND;
+}
+#else /* CONFIG_NET_LL_RX_POLL */
+static inline void ixgbe_qv_init_lock(struct ixgbe_q_vector *q_vector)
+{
+}
+
+static inline bool ixgbe_qv_lock_napi(struct ixgbe_q_vector *q_vector)
+{
+	return true;
+}
+
+static inline bool ixgbe_qv_unlock_napi(struct ixgbe_q_vector *q_vector)
+{
+	return false;
+}
+
+static inline bool ixgbe_qv_lock_poll(struct ixgbe_q_vector *q_vector)
+{
+	return false;
+}
+
+static inline bool ixgbe_qv_unlock_poll(struct ixgbe_q_vector *q_vector)
+{
+	return false;
+}
+
+static inline bool ixgbe_qv_ll_polling(struct ixgbe_q_vector *q_vector)
+{
+	return false;
+}
+#endif /* CONFIG_NET_LL_RX_POLL */
+
 #ifdef CONFIG_IXGBE_HWMON
 
 #define IXGBE_HWMON_TYPE_LOC		0

index ef5f7a6..90b4e10 100644
@@ -811,6 +811,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 	/* initialize NAPI */
 	netif_napi_add(adapter->netdev, &q_vector->napi,
 		       ixgbe_poll, 64);
+	napi_hash_add(&q_vector->napi);
 
 	/* tie q_vector and adapter together */
 	adapter->q_vector[v_idx] = q_vector;

@@ -931,6 +932,7 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx)
 		adapter->rx_ring[ring->queue_index] = NULL;
 
 	adapter->q_vector[v_idx] = NULL;
+	napi_hash_del(&q_vector->napi);
 	netif_napi_del(&q_vector->napi);
 
 	/*

123 lines not on this page · raw message

index 046196c..afacabb 100644
@@ -54,6 +54,9 @@
 
 #include <net/ll_poll.h>
 
+#ifdef CONFIG_NET_LL_RX_POLL
+#define LL_EXTENDED_STATS
+#endif
 /* common prefix used by pr_<> macros */
 #undef pr_fmt
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

@@ -184,6 +187,11 @@ struct ixgbe_rx_buffer {
 struct ixgbe_queue_stats {
 	u64 packets;
 	u64 bytes;
+#ifdef LL_EXTENDED_STATS
+	u64 yields;
+	u64 misses;
+	u64 cleaned;
+#endif  /* LL_EXTENDED_STATS */
 };
 
 struct ixgbe_tx_queue_stats {

@@ -391,6 +399,9 @@ static inline bool ixgbe_qv_lock_napi(struct ixgbe_q_vector *q_vector)
 		WARN_ON(q_vector->state & IXGBE_QV_STATE_NAPI);
 		q_vector->state |= IXGBE_QV_STATE_NAPI_YIELD;
 		rc = false;
+#ifdef LL_EXTENDED_STATS
+		q_vector->tx.ring->stats.yields++;
+#endif
 	} else
 		/* we don't care if someone yielded */
 		q_vector->state = IXGBE_QV_STATE_NAPI;

@@ -421,6 +432,9 @@ static inline bool ixgbe_qv_lock_poll(struct ixgbe_q_vector *q_vector)
 	if ((q_vector->state & IXGBE_QV_LOCKED)) {
 		q_vector->state |= IXGBE_QV_STATE_POLL_YIELD;
 		rc = false;
+#ifdef LL_EXTENDED_STATS
+		q_vector->rx.ring->stats.yields++;
+#endif
 	} else
 		/* preserve yield marks */
 		q_vector->state |= IXGBE_QV_STATE_POLL;

index d375472..24e2e7a 100644
@@ -1054,6 +1054,12 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev,
 			data[i] = 0;
 			data[i+1] = 0;
 			i += 2;
+#ifdef LL_EXTENDED_STATS
+			data[i] = 0;
+			data[i+1] = 0;
+			data[i+2] = 0;
+			i += 3;
+#endif
 			continue;
 		}
 

@@ -1063,6 +1069,12 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev,
 			data[i+1] = ring->stats.bytes;
 		} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
 		i += 2;
+#ifdef LL_EXTENDED_STATS
+		data[i] = ring->stats.yields;
+		data[i+1] = ring->stats.misses;
+		data[i+2] = ring->stats.cleaned;
+		i += 3;
+#endif
 	}
 	for (j = 0; j < IXGBE_NUM_RX_QUEUES; j++) {
 		ring = adapter->rx_ring[j];

@@ -1070,6 +1082,12 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev,
 			data[i] = 0;
 			data[i+1] = 0;
 			i += 2;
+#ifdef LL_EXTENDED_STATS
+			data[i] = 0;
+			data[i+1] = 0;
+			data[i+2] = 0;
+			i += 3;
+#endif
 			continue;
 		}
 

@@ -1079,6 +1097,12 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev,
 			data[i+1] = ring->stats.bytes;
 		} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
 		i += 2;
+#ifdef LL_EXTENDED_STATS
+		data[i] = ring->stats.yields;
+		data[i+1] = ring->stats.misses;
+		data[i+2] = ring->stats.cleaned;
+		i += 3;
+#endif
 	}
 
 	for (j = 0; j < IXGBE_MAX_PACKET_BUFFERS; j++) {

@@ -1115,12 +1139,28 @@ static void ixgbe_get_strings(struct net_device *netdev, u32 stringset,
 			p += ETH_GSTRING_LEN;
 			sprintf(p, "tx_queue_%u_bytes", i);
 			p += ETH_GSTRING_LEN;
+#ifdef LL_EXTENDED_STATS
+			sprintf(p, "tx_q_%u_napi_yield", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "tx_q_%u_misses", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "tx_q_%u_cleaned", i);
+			p += ETH_GSTRING_LEN;
+#endif /* LL_EXTENDED_STATS */
 		}
 		for (i = 0; i < IXGBE_NUM_RX_QUEUES; i++) {
 			sprintf(p, "rx_queue_%u_packets", i);
 			p += ETH_GSTRING_LEN;
 			sprintf(p, "rx_queue_%u_bytes", i);
 			p += ETH_GSTRING_LEN;
+#ifdef LL_EXTENDED_STATS
+			sprintf(p, "rx_q_%u_ll_poll_yield", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "rx_q_%u_misses", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "rx_q_%u_cleaned", i);
+			p += ETH_GSTRING_LEN;
+#endif /* LL_EXTENDED_STATS */
 		}
 		for (i = 0; i < IXGBE_MAX_PACKET_BUFFERS; i++) {
 			sprintf(p, "tx_pb_%u_pxon", i);

index 9a7dc40..047ebaa 100644
@@ -2016,6 +2016,12 @@ static int ixgbe_low_latency_recv(struct napi_struct *napi)
 
 	ixgbe_for_each_ring(ring, q_vector->rx) {
 		found = ixgbe_clean_rx_irq(q_vector, ring, 4);
+#ifdef LL_EXTENDED_STATS
+		if (found)
+			ring->stats.cleaned += found;
+		else
+			ring->stats.misses++;
+#endif
 		if (found)
 			break;
 	}