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>
return sizeof(*gh) + gh->opt_len * 4;
}
-static struct sk_buff **geneve_gro_receive(struct sock *sk,
- struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *geneve_gro_receive(struct sock *sk,
+ struct list_head *head,
+ struct sk_buff *skb)
{
- struct sk_buff *p, **pp = NULL;
+ struct sk_buff *pp = NULL;
+ struct sk_buff *p;
struct genevehdr *gh, *gh2;
unsigned int hlen, gh_len, off_gnv;
const struct packet_offload *ptype;
goto out;
}
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
return vh;
}
-static struct sk_buff **vxlan_gro_receive(struct sock *sk,
- struct sk_buff **head,
- struct sk_buff *skb)
+static struct sk_buff *vxlan_gro_receive(struct sock *sk,
+ struct list_head *head,
+ struct sk_buff *skb)
{
- struct sk_buff *p, **pp = NULL;
+ struct sk_buff *pp = NULL;
+ struct sk_buff *p;
struct vxlanhdr *vh, *vh2;
unsigned int hlen, off_vx;
int flush = 1;
skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
unsigned int rxqs);
#define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1)
-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);
int eth_gro_complete(struct sk_buff *skb, int nhoff);
/* Reserved Ethernet Addresses per IEEE 802.1Q */
int poll_owner;
#endif
struct net_device *dev;
- struct sk_buff *gro_list;
+ struct list_head gro_list;
struct sk_buff *skb;
struct hrtimer timer;
struct list_head dev_list;
return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT;
}
-typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *);
-static inline struct sk_buff **call_gro_receive(gro_receive_t cb,
- struct sk_buff **head,
- struct sk_buff *skb)
+typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *);
+static inline struct sk_buff *call_gro_receive(gro_receive_t cb,
+ struct list_head *head,
+ struct sk_buff *skb)
{
if (unlikely(gro_recursion_inc_test(skb))) {
NAPI_GRO_CB(skb)->flush |= 1;
return cb(head, skb);
}
-typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **,
- struct sk_buff *);
-static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb,
- struct sock *sk,
- struct sk_buff **head,
- struct sk_buff *skb)
+typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *,
+ struct sk_buff *);
+static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb,
+ struct sock *sk,
+ struct list_head *head,
+ struct sk_buff *skb)
{
if (unlikely(gro_recursion_inc_test(skb))) {
NAPI_GRO_CB(skb)->flush |= 1;
struct offload_callbacks {
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
netdev_features_t features);
- struct sk_buff **(*gro_receive)(struct sk_buff **head,
- struct sk_buff *skb);
+ struct sk_buff *(*gro_receive)(struct list_head *head,
+ struct sk_buff *skb);
int (*gro_complete)(struct sk_buff *skb, int nhoff);
};
struct net_device *dev_get_by_napi_id(unsigned int napi_id);
int netdev_get_name(struct net *net, char *name, int ifindex);
int dev_restart(struct net_device *dev);
-int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb);
+int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb);
static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
{
}
#ifdef CONFIG_XFRM_OFFLOAD
-static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
+static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush)
{
if (PTR_ERR(pp) != -EINPROGRESS)
NAPI_GRO_CB(skb)->flush |= flush;
}
#else
-static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
+static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush)
{
NAPI_GRO_CB(skb)->flush |= flush;
}
int ip_defrag_offset;
};
};
- struct rb_node rbnode; /* used in netem & tcp stack */
+ struct rb_node rbnode; /* used in netem & tcp stack */
+ struct list_head list;
};
struct sock *sk;
void (*encap_destroy)(struct sock *sk);
/* GRO functions for UDP socket */
- struct sk_buff ** (*gro_receive)(struct sock *sk,
- struct sk_buff **head,
+ struct sk_buff * (*gro_receive)(struct sock *sk,
+ struct list_head *head,
struct sk_buff *skb);
int (*gro_complete)(struct sock *sk,
struct sk_buff *skb,
int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
int *addr_len);
-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);
int inet_gro_complete(struct sk_buff *skb, int nhoff);
struct sk_buff *inet_gso_segment(struct sk_buff *skb,
netdev_features_t features);
struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
netdev_features_t features);
-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);
int tcp_gro_complete(struct sk_buff *skb);
void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport,
__be16 dport);
-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);
int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
-typedef struct sk_buff **(*udp_tunnel_gro_receive_t)(struct sock *sk,
- struct sk_buff **head,
- struct sk_buff *skb);
+typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
+ struct list_head *head,
+ struct sk_buff *skb);
typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb,
int nhoff);
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;
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)
*/
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;
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))
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--;
}
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++;
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:
NAPIF_STATE_IN_BUSY_POLL)))
return false;
- if (n->gro_list) {
+ if (!list_empty(&n->gro_list)) {
unsigned long timeout = 0;
if (work_done)
/* 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);
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)
}
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)
{
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);
goto out_unlock;
}
- if (n->gro_list) {
+ if (!list_empty(&n->gro_list)) {
/* flush too old packets
* If HZ < 1000, flush all packets.
*/
}
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;
}
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;
flush = 0;
- for (p = *head; p; p = p->next) {
+ list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
}
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;
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;
}
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;
#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;
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
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;
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)
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;
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)
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;
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;
goto found;
}
-
+ p = NULL;
goto out_check_final;
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;
}
TCP_FLAG_FIN));
if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
- pp = head;
+ pp = p;
out:
NAPI_GRO_CB(skb)->flush |= (flush != 0);
}
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 &&
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;
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;
}
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);
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;
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;
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> */
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 */
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 */
#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 &&
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);