net: Convert GRO SKB handling to list_head.

Manage pending per-NAPI GRO packets via list_head.

Return an SKB pointer from the GRO receive handlers.  When GRO receive
handlers return non-NULL, it means that this SKB needs to be completed
at this time and removed from the NAPI queue.

Several operations are greatly simplified by this transformation,
especially timing out the oldest SKB in the list when gro_count
exceeds MAX_GRO_SKBS, and napi_gro_flush() which walks the queue
in reverse order.

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

14 files changed, 93 insertions, 103 deletions

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 73a65789271b..99141986efa0 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -647,13 +647,14 @@ out:
 	return err;
 }
 
-static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *vlan_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
-	struct sk_buff *p, **pp = NULL;
-	struct vlan_hdr *vhdr;
-	unsigned int hlen, off_vlan;
 	const struct packet_offload *ptype;
+	unsigned int hlen, off_vlan;
+	struct sk_buff *pp = NULL;
+	struct vlan_hdr *vhdr;
+	struct sk_buff *p;
 	__be16 type;
 	int flush = 1;
 
@@ -675,7 +676,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
 
 	flush = 0;
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		struct vlan_hdr *vhdr2;
 
 		if (!NAPI_GRO_CB(p)->same_flow)
diff --git a/net/core/dev.c b/net/core/dev.c
index a5aa1c7444e6..aa61b9344b46 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4881,36 +4881,25 @@ out:
  */
 void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
-	struct sk_buff *skb, *prev = NULL;
-
-	/* scan list and build reverse chain */
-	for (skb = napi->gro_list; skb != NULL; skb = skb->next) {
-		skb->prev = prev;
-		prev = skb;
-	}
-
-	for (skb = prev; skb; skb = prev) {
-		skb->next = NULL;
+	struct sk_buff *skb, *p;
 
+	list_for_each_entry_safe_reverse(skb, p, &napi->gro_list, list) {
 		if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
 			return;
-
-		prev = skb->prev;
+		list_del_init(&skb->list);
 		napi_gro_complete(skb);
 		napi->gro_count--;
 	}
-
-	napi->gro_list = NULL;
 }
 EXPORT_SYMBOL(napi_gro_flush);
 
 static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
 {
-	struct sk_buff *p;
 	unsigned int maclen = skb->dev->hard_header_len;
 	u32 hash = skb_get_hash_raw(skb);
+	struct sk_buff *p;
 
-	for (p = napi->gro_list; p; p = p->next) {
+	list_for_each_entry(p, &napi->gro_list, list) {
 		unsigned long diffs;
 
 		NAPI_GRO_CB(p)->flush = 0;
@@ -4977,12 +4966,12 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
 
 static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
-	struct sk_buff **pp = NULL;
+	struct list_head *head = &offload_base;
 	struct packet_offload *ptype;
 	__be16 type = skb->protocol;
-	struct list_head *head = &offload_base;
-	int same_flow;
+	struct sk_buff *pp = NULL;
 	enum gro_result ret;
+	int same_flow;
 	int grow;
 
 	if (netif_elide_gro(skb->dev))
@@ -5039,11 +5028,8 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
 
 	if (pp) {
-		struct sk_buff *nskb = *pp;
-
-		*pp = nskb->next;
-		nskb->next = NULL;
-		napi_gro_complete(nskb);
+		list_del_init(&pp->list);
+		napi_gro_complete(pp);
 		napi->gro_count--;
 	}
 
@@ -5054,15 +5040,10 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		goto normal;
 
 	if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) {
-		struct sk_buff *nskb = napi->gro_list;
+		struct sk_buff *nskb;
 
-		/* locate the end of the list to select the 'oldest' flow */
-		while (nskb->next) {
-			pp = &nskb->next;
-			nskb = *pp;
-		}
-		*pp = NULL;
-		nskb->next = NULL;
+		nskb = list_last_entry(&napi->gro_list, struct sk_buff, list);
+		list_del(&nskb->list);
 		napi_gro_complete(nskb);
 	} else {
 		napi->gro_count++;
@@ -5071,8 +5052,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	NAPI_GRO_CB(skb)->age = jiffies;
 	NAPI_GRO_CB(skb)->last = skb;
 	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
-	skb->next = napi->gro_list;
-	napi->gro_list = skb;
+	list_add(&skb->list, &napi->gro_list);
 	ret = GRO_HELD;
 
 pull:
@@ -5478,7 +5458,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 				 NAPIF_STATE_IN_BUSY_POLL)))
 		return false;
 
-	if (n->gro_list) {
+	if (!list_empty(&n->gro_list)) {
 		unsigned long timeout = 0;
 
 		if (work_done)
@@ -5687,7 +5667,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	/* Note : we use a relaxed variant of napi_schedule_prep() not setting
 	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
 	 */
-	if (napi->gro_list && !napi_disable_pending(napi) &&
+	if (!list_empty(&napi->gro_list) && !napi_disable_pending(napi) &&
 	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
 		__napi_schedule_irqoff(napi);
 
@@ -5701,7 +5681,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
 	napi->gro_count = 0;
-	napi->gro_list = NULL;
+	INIT_LIST_HEAD(&napi->gro_list);
 	napi->skb = NULL;
 	napi->poll = poll;
 	if (weight > NAPI_POLL_WEIGHT)
@@ -5734,6 +5714,14 @@ void napi_disable(struct napi_struct *n)
 }
 EXPORT_SYMBOL(napi_disable);
 
+static void gro_list_free(struct list_head *head)
+{
+	struct sk_buff *skb, *p;
+
+	list_for_each_entry_safe(skb, p, head, list)
+		kfree_skb(skb);
+}
+
 /* Must be called in process context */
 void netif_napi_del(struct napi_struct *napi)
 {
@@ -5743,8 +5731,8 @@ void netif_napi_del(struct napi_struct *napi)
 	list_del_init(&napi->dev_list);
 	napi_free_frags(napi);
 
-	kfree_skb_list(napi->gro_list);
-	napi->gro_list = NULL;
+	gro_list_free(&napi->gro_list);
+	INIT_LIST_HEAD(&napi->gro_list);
 	napi->gro_count = 0;
 }
 EXPORT_SYMBOL(netif_napi_del);
@@ -5787,7 +5775,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		goto out_unlock;
 	}
 
-	if (n->gro_list) {
+	if (!list_empty(&n->gro_list)) {
 		/* flush too old packets
 		 * If HZ < 1000, flush all packets.
 		 */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c642304f178c..b1f274f22d85 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3815,14 +3815,14 @@ err:
 }
 EXPORT_SYMBOL_GPL(skb_segment);
 
-int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 {
 	struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb);
 	unsigned int offset = skb_gro_offset(skb);
 	unsigned int headlen = skb_headlen(skb);
 	unsigned int len = skb_gro_len(skb);
-	struct sk_buff *lp, *p = *head;
 	unsigned int delta_truesize;
+	struct sk_buff *lp;
 
 	if (unlikely(p->len + len >= 65536))
 		return -E2BIG;
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index ee28440f57c5..fd8faa0dfa61 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -427,13 +427,13 @@ ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len)
 }
 EXPORT_SYMBOL(sysfs_format_mac);
 
-struct sk_buff **eth_gro_receive(struct sk_buff **head,
-				 struct sk_buff *skb)
+struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
-	struct sk_buff *p, **pp = NULL;
-	struct ethhdr *eh, *eh2;
-	unsigned int hlen, off_eth;
 	const struct packet_offload *ptype;
+	unsigned int hlen, off_eth;
+	struct sk_buff *pp = NULL;
+	struct ethhdr *eh, *eh2;
+	struct sk_buff *p;
 	__be16 type;
 	int flush = 1;
 
@@ -448,7 +448,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head,
 
 	flush = 0;
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 15e125558c76..06b218a2870f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1384,12 +1384,12 @@ out:
 }
 EXPORT_SYMBOL(inet_gso_segment);
 
-struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	const struct net_offload *ops;
-	struct sk_buff **pp = NULL;
-	struct sk_buff *p;
+	struct sk_buff *pp = NULL;
 	const struct iphdr *iph;
+	struct sk_buff *p;
 	unsigned int hlen;
 	unsigned int off;
 	unsigned int id;
@@ -1425,7 +1425,7 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF));
 	id >>= 16;
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		struct iphdr *iph2;
 		u16 flush_id;
 
@@ -1505,8 +1505,8 @@ out:
 }
 EXPORT_SYMBOL(inet_gro_receive);
 
-static struct sk_buff **ipip_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *ipip_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	if (NAPI_GRO_CB(skb)->encap_mark) {
 		NAPI_GRO_CB(skb)->flush = 1;
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 7cf755ef9efb..bbeecd13e534 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -28,8 +28,8 @@
 #include <linux/spinlock.h>
 #include <net/udp.h>
 
-static struct sk_buff **esp4_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *esp4_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	int offset = skb_gro_offset(skb);
 	struct xfrm_offload *xo;
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 1540db65241a..efdc9e1f741e 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -224,14 +224,14 @@ drop:
 	return 0;
 }
 
-static struct sk_buff **fou_gro_receive(struct sock *sk,
-					struct sk_buff **head,
-					struct sk_buff *skb)
+static struct sk_buff *fou_gro_receive(struct sock *sk,
+				       struct list_head *head,
+				       struct sk_buff *skb)
 {
-	const struct net_offload *ops;
-	struct sk_buff **pp = NULL;
 	u8 proto = fou_from_sock(sk)->protocol;
 	const struct net_offload **offloads;
+	const struct net_offload *ops;
+	struct sk_buff *pp = NULL;
 
 	/* We can clear the encap_mark for FOU as we are essentially doing
 	 * one of two possible things.  We are either adding an L4 tunnel
@@ -305,13 +305,13 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
 	return guehdr;
 }
 
-static struct sk_buff **gue_gro_receive(struct sock *sk,
-					struct sk_buff **head,
-					struct sk_buff *skb)
+static struct sk_buff *gue_gro_receive(struct sock *sk,
+				       struct list_head *head,
+				       struct sk_buff *skb)
 {
 	const struct net_offload **offloads;
 	const struct net_offload *ops;
-	struct sk_buff **pp = NULL;
+	struct sk_buff *pp = NULL;
 	struct sk_buff *p;
 	struct guehdr *guehdr;
 	size_t len, optlen, hdrlen, off;
@@ -397,7 +397,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk,
 
 	skb_gro_pull(skb, hdrlen);
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		const struct guehdr *guehdr2;
 
 		if (!NAPI_GRO_CB(p)->same_flow)
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 1859c473b21a..b9673c21be45 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -108,10 +108,10 @@ out:
 	return segs;
 }
 
-static struct sk_buff **gre_gro_receive(struct sk_buff **head,
-					struct sk_buff *skb)
+static struct sk_buff *gre_gro_receive(struct list_head *head,
+				       struct sk_buff *skb)
 {
-	struct sk_buff **pp = NULL;
+	struct sk_buff *pp = NULL;
 	struct sk_buff *p;
 	const struct gre_base_hdr *greh;
 	unsigned int hlen, grehlen;
@@ -182,7 +182,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 					     null_compute_pseudo);
 	}
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		const struct gre_base_hdr *greh2;
 
 		if (!NAPI_GRO_CB(p)->same_flow)
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 8cc7c3487330..f5aee641f825 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -180,9 +180,9 @@ out:
 	return segs;
 }
 
-struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
-	struct sk_buff **pp = NULL;
+	struct sk_buff *pp = NULL;
 	struct sk_buff *p;
 	struct tcphdr *th;
 	struct tcphdr *th2;
@@ -220,7 +220,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	len = skb_gro_len(skb);
 	flags = tcp_flag_word(th);
 
-	for (; (p = *head); head = &p->next) {
+	list_for_each_entry(p, head, list) {
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
@@ -233,7 +233,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 
 		goto found;
 	}
-
+	p = NULL;
 	goto out_check_final;
 
 found:
@@ -263,7 +263,7 @@ found:
 	flush |= (len - 1) >= mss;
 	flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
 
-	if (flush || skb_gro_receive(head, skb)) {
+	if (flush || skb_gro_receive(p, skb)) {
 		mss = 1;
 		goto out_check_final;
 	}
@@ -277,7 +277,7 @@ out_check_final:
 					TCP_FLAG_FIN));
 
 	if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
-		pp = head;
+		pp = p;
 
 out:
 	NAPI_GRO_CB(skb)->flush |= (flush != 0);
@@ -302,7 +302,7 @@ int tcp_gro_complete(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_gro_complete);
 
-static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+static struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	/* Don't bother verifying checksum if we're going to flush anyway. */
 	if (!NAPI_GRO_CB(skb)->flush &&
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 92dc9e5a7ff3..ac46c1c55c99 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -343,10 +343,11 @@ out:
 	return segs;
 }
 
-struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
-				 struct udphdr *uh, udp_lookup_t lookup)
+struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
+				struct udphdr *uh, udp_lookup_t lookup)
 {
-	struct sk_buff *p, **pp = NULL;
+	struct sk_buff *pp = NULL;
+	struct sk_buff *p;
 	struct udphdr *uh2;
 	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
@@ -371,7 +372,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
 unflush:
 	flush = 0;
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
@@ -399,8 +400,8 @@ out:
 }
 EXPORT_SYMBOL(udp_gro_receive);
 
-static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *udp4_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 27f59b61f70f..ddfa533a84e5 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -49,8 +49,8 @@ static __u16 esp6_nexthdr_esp_offset(struct ipv6hdr *ipv6_hdr, int nhlen)
 	return 0;
 }
 
-static struct sk_buff **esp6_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *esp6_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	int offset = skb_gro_offset(skb);
 	struct xfrm_offload *xo;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 5b3f2f89ef41..37ff4805b20c 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -163,11 +163,11 @@ static int ipv6_exthdrs_len(struct ipv6hdr *iph,
 	return len;
 }
 
-static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *ipv6_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	const struct net_offload *ops;
-	struct sk_buff **pp = NULL;
+	struct sk_buff *pp = NULL;
 	struct sk_buff *p;
 	struct ipv6hdr *iph;
 	unsigned int nlen;
@@ -214,7 +214,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	flush--;
 	nlen = skb_network_header_len(skb);
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		const struct ipv6hdr *iph2;
 		__be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */
 
@@ -263,8 +263,8 @@ out:
 	return pp;
 }
 
-static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head,
-					       struct sk_buff *skb)
+static struct sk_buff *sit_ip6ip6_gro_receive(struct list_head *head,
+					      struct sk_buff *skb)
 {
 	/* Common GRO receive for SIT and IP6IP6 */
 
@@ -278,8 +278,8 @@ static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head,
 	return ipv6_gro_receive(head, skb);
 }
 
-static struct sk_buff **ip4ip6_gro_receive(struct sk_buff **head,
-					   struct sk_buff *skb)
+static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
+					  struct sk_buff *skb)
 {
 	/* Common GRO receive for SIT and IP6IP6 */
 
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 278e49cd67d4..e72947c99454 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -15,8 +15,8 @@
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
-static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *tcp6_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	/* Don't bother verifying checksum if we're going to flush anyway. */
 	if (!NAPI_GRO_CB(skb)->flush &&
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 03a2ff3fe1e6..95dee9ca8d22 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -114,8 +114,8 @@ out:
 	return segs;
 }
 
-static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *udp6_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);