7 files changed, 112 insertions, 211 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 1e0a1847c3bb..09cb3f6dc40c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3300,18 +3300,18 @@ ncls:
                                 && !skb_pfmemalloc_protocol(skb))
                 goto drop;
 
-        rx_handler = rcu_dereference(skb->dev->rx_handler);
         if (vlan_tx_tag_present(skb)) {
                 if (pt_prev) {
                         ret = deliver_skb(skb, pt_prev, orig_dev);
                         pt_prev = NULL;
                 }
-                if (vlan_do_receive(&skb, !rx_handler))
+                if (vlan_do_receive(&skb))
                         goto another_round;
                 else if (unlikely(!skb))
                         goto unlock;
         }
 
+        rx_handler = rcu_dereference(skb->dev->rx_handler);
         if (rx_handler) {
                 if (pt_prev) {
                         ret = deliver_skb(skb, pt_prev, orig_dev);
@@ -3331,6 +3331,9 @@ ncls:
                 }
         }
 
+        if (vlan_tx_nonzero_tag_present(skb))
+                skb->pkt_type = PACKET_OTHERHOST;
+
         /* deliver only exact match when indicated */
         null_or_dev = deliver_exact ? skb->dev : NULL;
 
@@ -3471,17 +3474,31 @@ out:
         return netif_receive_skb(skb);
 }
 
-inline void napi_gro_flush(struct napi_struct *napi)
+/* napi->gro_list contains packets ordered by age.
+ * youngest packets at the head of it.
+ * Complete skbs in reverse order to reduce latencies.
+ */
+void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
-        struct sk_buff *skb, *next;
+        struct sk_buff *skb, *prev = NULL;
 
-        for (skb = napi->gro_list; skb; skb = next) {
-                next = skb->next;
+        /* 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;
+
+                if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
+                        return;
+
+                prev = skb->prev;
                 napi_gro_complete(skb);
+                napi->gro_count--;
         }
 
-        napi->gro_count = 0;
         napi->gro_list = NULL;
 }
 EXPORT_SYMBOL(napi_gro_flush);
@@ -3542,6 +3559,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 
         napi->gro_count++;
         NAPI_GRO_CB(skb)->count = 1;
+        NAPI_GRO_CB(skb)->age = jiffies;
         skb_shinfo(skb)->gso_size = skb_gro_len(skb);
         skb->next = napi->gro_list;
         napi->gro_list = skb;
@@ -3631,20 +3649,22 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(napi_skb_finish);
 
-void skb_gro_reset_offset(struct sk_buff *skb)
+static void skb_gro_reset_offset(struct sk_buff *skb)
 {
+        const struct skb_shared_info *pinfo = skb_shinfo(skb);
+        const skb_frag_t *frag0 = &pinfo->frags[0];
+
         NAPI_GRO_CB(skb)->data_offset = 0;
         NAPI_GRO_CB(skb)->frag0 = NULL;
         NAPI_GRO_CB(skb)->frag0_len = 0;
 
         if (skb->mac_header == skb->tail &&
-            !PageHighMem(skb_frag_page(&skb_shinfo(skb)->frags[0]))) {
-                NAPI_GRO_CB(skb)->frag0 =
-                        skb_frag_address(&skb_shinfo(skb)->frags[0]);
-                NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(&skb_shinfo(skb)->frags[0]);
+            pinfo->nr_frags &&
+            !PageHighMem(skb_frag_page(frag0))) {
+                NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
+                NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
         }
 }
-EXPORT_SYMBOL(skb_gro_reset_offset);
 
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
@@ -3876,7 +3896,7 @@ void napi_complete(struct napi_struct *n)
         if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
                 return;
 
-        napi_gro_flush(n);
+        napi_gro_flush(n, false);
         local_irq_save(flags);
         __napi_complete(n);
         local_irq_restore(flags);
@@ -3981,8 +4001,17 @@ static void net_rx_action(struct softirq_action *h)
                                 local_irq_enable();
                                 napi_complete(n);
                                 local_irq_disable();
-                        } else
+                        } else {
+                                if (n->gro_list) {
+                                        /* flush too old packets
+                                         * If HZ < 1000, flush all packets.
+                                         */
+                                        local_irq_enable();
+                                        napi_gro_flush(n, HZ >= 1000);
+                                        local_irq_disable();
+                                }
                                 list_move_tail(&n->poll_list, &sd->poll_list);
+                        }
                 }
 
                 netpoll_poll_unlock(have);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index baca771caae2..22571488730a 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1301,8 +1301,6 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
         if (!dst)
                 goto discard;
 
-        __skb_pull(skb, skb_network_offset(skb));
-
         if (!neigh_event_send(neigh, skb)) {
                 int err;
                 struct net_device *dev = neigh->dev;
@@ -1312,6 +1310,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
                         neigh_hh_init(neigh, dst);
 
                 do {
+                        __skb_pull(skb, skb_network_offset(skb));
                         seq = read_seqbegin(&neigh->ha_lock);
                         err = dev_hard_header(skb, dev, ntohs(skb->protocol),
                                               neigh->ha, NULL, skb->len);
@@ -1342,9 +1341,8 @@ int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb)
         unsigned int seq;
         int err;
 
-        __skb_pull(skb, skb_network_offset(skb));
-
         do {
+                __skb_pull(skb, skb_network_offset(skb));
                 seq = read_seqbegin(&neigh->ha_lock);
                 err = dev_hard_header(skb, dev, ntohs(skb->protocol),
                                       neigh->ha, NULL, skb->len);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 4a83fb3c8e87..79285a36035f 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -239,38 +239,24 @@ out_free_devname:
         return ret;
 }
 
+static int update_netprio(const void *v, struct file *file, unsigned n)
+{
+        int err;
+        struct socket *sock = sock_from_file(file, &err);
+        if (sock)
+                sock->sk->sk_cgrp_prioidx = (u32)(unsigned long)v;
+        return 0;
+}
+
 void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 {
         struct task_struct *p;
+        void *v;
 
         cgroup_taskset_for_each(p, cgrp, tset) {
-                unsigned int fd;
-                struct fdtable *fdt;
-                struct files_struct *files;
-
                 task_lock(p);
-                files = p->files;
-                if (!files) {
-                        task_unlock(p);
-                        continue;
-                }
-
-                spin_lock(&files->file_lock);
-                fdt = files_fdtable(files);
-                for (fd = 0; fd < fdt->max_fds; fd++) {
-                        struct file *file;
-                        struct socket *sock;
-                        int err;
-
-                        file = fcheck_files(files, fd);
-                        if (!file)
-                                continue;
-
-                        sock = sock_from_file(file, &err);
-                        if (sock)
-                                sock_update_netprioidx(sock->sk, p);
-                }
-                spin_unlock(&files->file_lock);
+                v = (void *)(unsigned long)task_netprioidx(p);
+                iterate_fd(p->files, 0, update_netprio, v);
                 task_unlock(p);
         }
 }
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 148e73d2c451..d1dc14c2aac4 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -248,8 +248,8 @@ struct pktgen_dev {
         int removal_mark;       /* non-zero => the device is marked for
                                  * removal by worker thread */
 
-        int min_pkt_size;       /* = ETH_ZLEN; */
-        int max_pkt_size;       /* = ETH_ZLEN; */
+        int min_pkt_size;
+        int max_pkt_size;
         int pkt_overhead;       /* overhead for MPLS, VLANs, IPSEC etc */
         int nfrags;
         struct page *page;
@@ -449,8 +449,6 @@ static void pktgen_stop_all_threads_ifs(void);
 static void pktgen_stop(struct pktgen_thread *t);
 static void pktgen_clear_counters(struct pktgen_dev *pkt_dev);
 
-static unsigned int scan_ip6(const char *s, char ip[16]);
-
 /* Module parameters, defaults. */
 static int pg_count_d __read_mostly = 1000;
 static int pg_delay_d __read_mostly;
@@ -702,8 +700,8 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
                                 &pkt_dev->cur_in6_saddr,
                                 &pkt_dev->cur_in6_daddr);
         } else
-                seq_printf(seq, "     cur_saddr: 0x%x  cur_daddr: 0x%x\n",
-                           pkt_dev->cur_saddr, pkt_dev->cur_daddr);
+                seq_printf(seq, "     cur_saddr: %pI4  cur_daddr: %pI4\n",
+                           &pkt_dev->cur_saddr, &pkt_dev->cur_daddr);
 
         seq_printf(seq, "     cur_udp_dst: %d  cur_udp_src: %d\n",
                    pkt_dev->cur_udp_dst, pkt_dev->cur_udp_src);
@@ -1299,7 +1297,7 @@ static ssize_t pktgen_if_write(struct file *file,
                         return -EFAULT;
                 buf[len] = 0;
 
-                scan_ip6(buf, pkt_dev->in6_daddr.s6_addr);
+                in6_pton(buf, -1, pkt_dev->in6_daddr.s6_addr, -1, NULL);
                 snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_daddr);
 
                 pkt_dev->cur_in6_daddr = pkt_dev->in6_daddr;
@@ -1322,7 +1320,7 @@ static ssize_t pktgen_if_write(struct file *file,
                         return -EFAULT;
                 buf[len] = 0;
 
-                scan_ip6(buf, pkt_dev->min_in6_daddr.s6_addr);
+                in6_pton(buf, -1, pkt_dev->min_in6_daddr.s6_addr, -1, NULL);
                 snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_daddr);
 
                 pkt_dev->cur_in6_daddr = pkt_dev->min_in6_daddr;
@@ -1344,7 +1342,7 @@ static ssize_t pktgen_if_write(struct file *file,
                         return -EFAULT;
                 buf[len] = 0;
 
-                scan_ip6(buf, pkt_dev->max_in6_daddr.s6_addr);
+                in6_pton(buf, -1, pkt_dev->max_in6_daddr.s6_addr, -1, NULL);
                 snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->max_in6_daddr);
 
                 if (debug)
@@ -1365,7 +1363,7 @@ static ssize_t pktgen_if_write(struct file *file,
                         return -EFAULT;
                 buf[len] = 0;
 
-                scan_ip6(buf, pkt_dev->in6_saddr.s6_addr);
+                in6_pton(buf, -1, pkt_dev->in6_saddr.s6_addr, -1, NULL);
                 snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_saddr);
 
                 pkt_dev->cur_in6_saddr = pkt_dev->in6_saddr;
@@ -2036,19 +2034,17 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
         /* Set up Dest MAC */
         memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN);
 
-        /* Set up pkt size */
-        pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size;
-
         if (pkt_dev->flags & F_IPV6) {
-                /*
-                 * Skip this automatic address setting until locks or functions
-                 * gets exported
-                 */
-
-#ifdef NOTNOW
                 int i, set = 0, err = 1;
                 struct inet6_dev *idev;
 
+                if (pkt_dev->min_pkt_size == 0) {
+                        pkt_dev->min_pkt_size = 14 + sizeof(struct ipv6hdr)
+                                                + sizeof(struct udphdr)
+                                                + sizeof(struct pktgen_hdr)
+                                                + pkt_dev->pkt_overhead;
+                }
+
                 for (i = 0; i < IN6_ADDR_HSIZE; i++)
                         if (pkt_dev->cur_in6_saddr.s6_addr[i]) {
                                 set = 1;
@@ -2069,9 +2065,8 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
                                 struct inet6_ifaddr *ifp;
 
                                 read_lock_bh(&idev->lock);
-                                for (ifp = idev->addr_list; ifp;
-                                     ifp = ifp->if_next) {
-                                        if (ifp->scope == IFA_LINK &&
+                                list_for_each_entry(ifp, &idev->addr_list, if_list) {
+                                        if ((ifp->scope & IFA_LINK) &&
                                             !(ifp->flags & IFA_F_TENTATIVE)) {
                                                 pkt_dev->cur_in6_saddr = ifp->addr;
                                                 err = 0;
@@ -2084,8 +2079,14 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
                         if (err)
                                 pr_err("ERROR: IPv6 link address not available\n");
                 }
-#endif
         } else {
+                if (pkt_dev->min_pkt_size == 0) {
+                        pkt_dev->min_pkt_size = 14 + sizeof(struct iphdr)
+                                                + sizeof(struct udphdr)
+                                                + sizeof(struct pktgen_hdr)
+                                                + pkt_dev->pkt_overhead;
+                }
+
                 pkt_dev->saddr_min = 0;
                 pkt_dev->saddr_max = 0;
                 if (strlen(pkt_dev->src_min) == 0) {
@@ -2111,6 +2112,10 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
                 pkt_dev->daddr_max = in_aton(pkt_dev->dst_max);
         }
         /* Initialize current values. */
+        pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size;
+        if (pkt_dev->min_pkt_size > pkt_dev->max_pkt_size)
+                pkt_dev->max_pkt_size = pkt_dev->min_pkt_size;
+
         pkt_dev->cur_dst_mac_offset = 0;
         pkt_dev->cur_src_mac_offset = 0;
         pkt_dev->cur_saddr = pkt_dev->saddr_min;
@@ -2758,97 +2763,6 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
         return skb;
 }
 
-/*
- * scan_ip6, fmt_ip taken from dietlibc-0.21
- * Author Felix von Leitner <felix-dietlibc@fefe.de>
- *
- * Slightly modified for kernel.
- * Should be candidate for net/ipv4/utils.c
- * --ro
- */
-
-static unsigned int scan_ip6(const char *s, char ip[16])
-{
-        unsigned int i;
-        unsigned int len = 0;
-        unsigned long u;
-        char suffix[16];
-        unsigned int prefixlen = 0;
-        unsigned int suffixlen = 0;
-        __be32 tmp;
-        char *pos;
-
-        for (i = 0; i < 16; i++)
-                ip[i] = 0;
-
-        for (;;) {
-                if (*s == ':') {
-                        len++;
-                        if (s[1] == ':') {      /* Found "::", skip to part 2 */
-                                s += 2;
-                                len++;
-                                break;
-                        }
-                        s++;
-                }
-
-                u = simple_strtoul(s, &pos, 16);
-                i = pos - s;
-                if (!i)
-                        return 0;
-                if (prefixlen == 12 && s[i] == '.') {
-
-                        /* the last 4 bytes may be written as IPv4 address */
-
-                        tmp = in_aton(s);
-                        memcpy((struct in_addr *)(ip + 12), &tmp, sizeof(tmp));
-                        return i + len;
-                }
-                ip[prefixlen++] = (u >> 8);
-                ip[prefixlen++] = (u & 255);
-                s += i;
-                len += i;
-                if (prefixlen == 16)
-                        return len;
-        }
-
-/* part 2, after "::" */
-        for (;;) {
-                if (*s == ':') {
-                        if (suffixlen == 0)
-                                break;
-                        s++;
-                        len++;
-                } else if (suffixlen != 0)
-                        break;
-
-                u = simple_strtol(s, &pos, 16);
-                i = pos - s;
-                if (!i) {
-                        if (*s)
-                                len--;
-                        break;
-                }
-                if (suffixlen + prefixlen <= 12 && s[i] == '.') {
-                        tmp = in_aton(s);
-                        memcpy((struct in_addr *)(suffix + suffixlen), &tmp,
-                               sizeof(tmp));
-                        suffixlen += 4;
-                        len += strlen(s);
-                        break;
-                }
-                suffix[suffixlen++] = (u >> 8);
-                suffix[suffixlen++] = (u & 255);
-                s += i;
-                len += i;
-                if (prefixlen + suffixlen == 16)
-                        break;
-        }
-        for (i = 0; i < suffixlen; i++)
-                ip[16 - suffixlen + i] = suffix[i];
-        return len;
-}
-
 static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
                                         struct pktgen_dev *pkt_dev)
 {
@@ -2927,7 +2841,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
                   sizeof(struct ipv6hdr) - sizeof(struct udphdr) -
                   pkt_dev->pkt_overhead;
 
-        if (datalen < sizeof(struct pktgen_hdr)) {
+        if (datalen < 0 || datalen < sizeof(struct pktgen_hdr)) {
                 datalen = sizeof(struct pktgen_hdr);
                 net_info_ratelimited("increased datalen to %d\n", datalen);
         }
@@ -3548,8 +3462,6 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
         }
 
         pkt_dev->removal_mark = 0;
-        pkt_dev->min_pkt_size = ETH_ZLEN;
-        pkt_dev->max_pkt_size = ETH_ZLEN;
         pkt_dev->nfrags = 0;
         pkt_dev->delay = pg_delay_d;
         pkt_dev->count = pg_count_d;
diff --git a/net/core/scm.c b/net/core/scm.c
index 9c1c63da3ca8..ab570841a532 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -301,11 +301,10 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
                         break;
                 }
                 /* Bump the usage count and install the file. */
-                get_file(fp[i]);
                 sock = sock_from_file(fp[i], &err);
                 if (sock)
                         sock_update_netprioidx(sock->sk, current);
-                fd_install(new_fd, fp[i]);
+                fd_install(new_fd, get_file(fp[i]));
         }
 
         if (i > 0)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index cdc28598f4ef..6e04b1fa11f2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -655,53 +655,6 @@ void consume_skb(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(consume_skb);
 
-/**
- *      skb_recycle - clean up an skb for reuse
- *      @skb: buffer
- *
- *      Recycles the skb to be reused as a receive buffer. This
- *      function does any necessary reference count dropping, and
- *      cleans up the skbuff as if it just came from __alloc_skb().
- */
-void skb_recycle(struct sk_buff *skb)
-{
-        struct skb_shared_info *shinfo;
-
-        skb_release_head_state(skb);
-
-        shinfo = skb_shinfo(skb);
-        memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
-        atomic_set(&shinfo->dataref, 1);
-
-        memset(skb, 0, offsetof(struct sk_buff, tail));
-        skb->data = skb->head + NET_SKB_PAD;
-        skb_reset_tail_pointer(skb);
-}
-EXPORT_SYMBOL(skb_recycle);
-
-/**
- *      skb_recycle_check - check if skb can be reused for receive
- *      @skb: buffer
- *      @skb_size: minimum receive buffer size
- *
- *      Checks that the skb passed in is not shared or cloned, and
- *      that it is linear and its head portion at least as large as
- *      skb_size so that it can be recycled as a receive buffer.
- *      If these conditions are met, this function does any necessary
- *      reference count dropping and cleans up the skbuff as if it
- *      just came from __alloc_skb().
- */
-bool skb_recycle_check(struct sk_buff *skb, int skb_size)
-{
-        if (!skb_is_recycleable(skb, skb_size))
-                return false;
-
-        skb_recycle(skb);
-
-        return true;
-}
-EXPORT_SYMBOL(skb_recycle_check);
-
 static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 {
         new->tstamp             = old->tstamp;
diff --git a/net/core/utils.c b/net/core/utils.c
index f5613d569c23..e3487e461939 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -107,6 +107,18 @@ static inline int xdigit2bin(char c, int delim)
         return IN6PTON_UNKNOWN;
 }
 
+/**
+ * in4_pton - convert an IPv4 address from literal to binary representation
+ * @src: the start of the IPv4 address string
+ * @srclen: the length of the string, -1 means strlen(src)
+ * @dst: the binary (u8[4] array) representation of the IPv4 address
+ * @delim: the delimiter of the IPv4 address in @src, -1 means no delimiter
+ * @end: A pointer to the end of the parsed string will be placed here
+ *
+ * Return one on success, return zero when any error occurs
+ * and @end will point to the end of the parsed string.
+ *
+ */
 int in4_pton(const char *src, int srclen,
              u8 *dst,
              int delim, const char **end)
@@ -161,6 +173,18 @@ out:
 }
 EXPORT_SYMBOL(in4_pton);
 
+/**
+ * in6_pton - convert an IPv6 address from literal to binary representation
+ * @src: the start of the IPv6 address string
+ * @srclen: the length of the string, -1 means strlen(src)
+ * @dst: the binary (u8[16] array) representation of the IPv6 address
+ * @delim: the delimiter of the IPv6 address in @src, -1 means no delimiter
+ * @end: A pointer to the end of the parsed string will be placed here
+ *
+ * Return one on success, return zero when any error occurs
+ * and @end will point to the end of the parsed string.
+ *
+ */
 int in6_pton(const char *src, int srclen,
              u8 *dst,
              int delim, const char **end)