Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 9c4e72e..3d8baaa 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
@@ -188,7 +189,7 @@
struct net_device *dev = dst->dev;
unsigned int hh_len = LL_RESERVED_SPACE(dev);
struct neighbour *neigh;
- u32 nexthop;
+ bool is_v6gw = false;
if (rt->rt_type == RTN_MULTICAST) {
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len);
@@ -218,16 +219,13 @@
}
rcu_read_lock_bh();
- nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
- neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
- if (unlikely(!neigh))
- neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
+ neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
if (!IS_ERR(neigh)) {
int res;
sock_confirm_neigh(skb, neigh);
- res = neigh_output(neigh, skb);
-
+ /* if crossing protocols, can not use the cached header */
+ res = neigh_output(neigh, skb, is_v6gw);
rcu_read_unlock_bh();
return res;
}
@@ -278,7 +276,7 @@
struct sk_buff *nskb = segs->next;
int err;
- segs->next = NULL;
+ skb_mark_not_on_list(segs);
err = ip_fragment(net, sk, segs, mtu, ip_finish_output2);
if (err && ret == 0)
@@ -289,16 +287,9 @@
return ret;
}
-static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
unsigned int mtu;
- int ret;
-
- ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
- if (ret) {
- kfree_skb(skb);
- return ret;
- }
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
/* Policy lookup after SNAT yielded a new policy */
@@ -317,18 +308,54 @@
return ip_finish_output2(net, sk, skb);
}
-static int ip_mc_finish_output(struct net *net, struct sock *sk,
- struct sk_buff *skb)
+static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
int ret;
ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
- if (ret) {
+ switch (ret) {
+ case NET_XMIT_SUCCESS:
+ return __ip_finish_output(net, sk, skb);
+ case NET_XMIT_CN:
+ return __ip_finish_output(net, sk, skb) ? : ret;
+ default:
+ kfree_skb(skb);
+ return ret;
+ }
+}
+
+static int ip_mc_finish_output(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ struct rtable *new_rt;
+ bool do_cn = false;
+ int ret, err;
+
+ ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
+ switch (ret) {
+ case NET_XMIT_CN:
+ do_cn = true;
+ /* fall through */
+ case NET_XMIT_SUCCESS:
+ break;
+ default:
kfree_skb(skb);
return ret;
}
- return dev_loopback_xmit(net, sk, skb);
+ /* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting
+ * this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten,
+ * see ipv4_pktinfo_prepare().
+ */
+ new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb));
+ if (new_rt) {
+ new_rt->rt_iif = 0;
+ skb_dst_drop(skb);
+ skb_dst_set(skb, &new_rt->dst);
+ }
+
+ err = dev_loopback_xmit(net, sk, skb);
+ return (do_cn && err) ? ret : err;
}
int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -519,6 +546,7 @@
to->pkt_type = from->pkt_type;
to->priority = from->priority;
to->protocol = from->protocol;
+ to->skb_iif = from->skb_iif;
skb_dst_drop(to);
skb_dst_copy(to, from);
to->dev = from->dev;
@@ -526,13 +554,11 @@
skb_copy_hash(to, from);
- /* Copy the flags to each fragment. */
- IPCB(to)->flags = IPCB(from)->flags;
-
#ifdef CONFIG_NET_SCHED
to->tc_index = from->tc_index;
#endif
nf_copy(to, from);
+ skb_ext_copy(to, from);
#if IS_ENABLED(CONFIG_IP_VS)
to->ipvs_property = from->ipvs_property;
#endif
@@ -561,6 +587,175 @@
return ip_do_fragment(net, sk, skb, output);
}
+void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph,
+ unsigned int hlen, struct ip_fraglist_iter *iter)
+{
+ unsigned int first_len = skb_pagelen(skb);
+
+ iter->frag = skb_shinfo(skb)->frag_list;
+ skb_frag_list_init(skb);
+
+ iter->offset = 0;
+ iter->iph = iph;
+ iter->hlen = hlen;
+
+ skb->data_len = first_len - skb_headlen(skb);
+ skb->len = first_len;
+ iph->tot_len = htons(first_len);
+ iph->frag_off = htons(IP_MF);
+ ip_send_check(iph);
+}
+EXPORT_SYMBOL(ip_fraglist_init);
+
+static void ip_fraglist_ipcb_prepare(struct sk_buff *skb,
+ struct ip_fraglist_iter *iter)
+{
+ struct sk_buff *to = iter->frag;
+
+ /* Copy the flags to each fragment. */
+ IPCB(to)->flags = IPCB(skb)->flags;
+
+ if (iter->offset == 0)
+ ip_options_fragment(to);
+}
+
+void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter)
+{
+ unsigned int hlen = iter->hlen;
+ struct iphdr *iph = iter->iph;
+ struct sk_buff *frag;
+
+ frag = iter->frag;
+ frag->ip_summed = CHECKSUM_NONE;
+ skb_reset_transport_header(frag);
+ __skb_push(frag, hlen);
+ skb_reset_network_header(frag);
+ memcpy(skb_network_header(frag), iph, hlen);
+ iter->iph = ip_hdr(frag);
+ iph = iter->iph;
+ iph->tot_len = htons(frag->len);
+ ip_copy_metadata(frag, skb);
+ iter->offset += skb->len - hlen;
+ iph->frag_off = htons(iter->offset >> 3);
+ if (frag->next)
+ iph->frag_off |= htons(IP_MF);
+ /* Ready, complete checksum */
+ ip_send_check(iph);
+}
+EXPORT_SYMBOL(ip_fraglist_prepare);
+
+void ip_frag_init(struct sk_buff *skb, unsigned int hlen,
+ unsigned int ll_rs, unsigned int mtu, bool DF,
+ struct ip_frag_state *state)
+{
+ struct iphdr *iph = ip_hdr(skb);
+
+ state->DF = DF;
+ state->hlen = hlen;
+ state->ll_rs = ll_rs;
+ state->mtu = mtu;
+
+ state->left = skb->len - hlen; /* Space per frame */
+ state->ptr = hlen; /* Where to start from */
+
+ state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
+ state->not_last_frag = iph->frag_off & htons(IP_MF);
+}
+EXPORT_SYMBOL(ip_frag_init);
+
+static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to,
+ bool first_frag, struct ip_frag_state *state)
+{
+ /* Copy the flags to each fragment. */
+ IPCB(to)->flags = IPCB(from)->flags;
+
+ /* ANK: dirty, but effective trick. Upgrade options only if
+ * the segment to be fragmented was THE FIRST (otherwise,
+ * options are already fixed) and make it ONCE
+ * on the initial skb, so that all the following fragments
+ * will inherit fixed options.
+ */
+ if (first_frag)
+ ip_options_fragment(from);
+}
+
+struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state)
+{
+ unsigned int len = state->left;
+ struct sk_buff *skb2;
+ struct iphdr *iph;
+
+ len = state->left;
+ /* IF: it doesn't fit, use 'mtu' - the data space left */
+ if (len > state->mtu)
+ len = state->mtu;
+ /* IF: we are not sending up to and including the packet end
+ then align the next start on an eight byte boundary */
+ if (len < state->left) {
+ len &= ~7;
+ }
+
+ /* Allocate buffer */
+ skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC);
+ if (!skb2)
+ return ERR_PTR(-ENOMEM);
+
+ /*
+ * Set up data on packet
+ */
+
+ ip_copy_metadata(skb2, skb);
+ skb_reserve(skb2, state->ll_rs);
+ skb_put(skb2, len + state->hlen);
+ skb_reset_network_header(skb2);
+ skb2->transport_header = skb2->network_header + state->hlen;
+
+ /*
+ * Charge the memory for the fragment to any owner
+ * it might possess
+ */
+
+ if (skb->sk)
+ skb_set_owner_w(skb2, skb->sk);
+
+ /*
+ * Copy the packet header into the new buffer.
+ */
+
+ skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen);
+
+ /*
+ * Copy a block of the IP datagram.
+ */
+ if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len))
+ BUG();
+ state->left -= len;
+
+ /*
+ * Fill in the new header fields.
+ */
+ iph = ip_hdr(skb2);
+ iph->frag_off = htons((state->offset >> 3));
+ if (state->DF)
+ iph->frag_off |= htons(IP_DF);
+
+ /*
+ * Added AC : If we are fragmenting a fragment that's not the
+ * last fragment then keep MF on each bit
+ */
+ if (state->left > 0 || state->not_last_frag)
+ iph->frag_off |= htons(IP_MF);
+ state->ptr += len;
+ state->offset += len;
+
+ iph->tot_len = htons(len + state->hlen);
+
+ ip_send_check(iph);
+
+ return skb2;
+}
+EXPORT_SYMBOL(ip_frag_next);
+
/*
* This IP datagram is too large to be sent in one piece. Break it up into
* smaller pieces (each of size equal to IP header plus
@@ -572,12 +767,12 @@
int (*output)(struct net *, struct sock *, struct sk_buff *))
{
struct iphdr *iph;
- int ptr;
struct sk_buff *skb2;
- unsigned int mtu, hlen, left, len, ll_rs;
- int offset;
- __be16 not_last_frag;
struct rtable *rt = skb_rtable(skb);
+ unsigned int mtu, hlen, ll_rs;
+ struct ip_fraglist_iter iter;
+ ktime_t tstamp = skb->tstamp;
+ struct ip_frag_state state;
int err = 0;
/* for offloaded checksums cleanup checksum before fragmentation */
@@ -642,49 +837,25 @@
}
/* Everything is OK. Generate! */
-
- err = 0;
- offset = 0;
- frag = skb_shinfo(skb)->frag_list;
- skb_frag_list_init(skb);
- skb->data_len = first_len - skb_headlen(skb);
- skb->len = first_len;
- iph->tot_len = htons(first_len);
- iph->frag_off = htons(IP_MF);
- ip_send_check(iph);
+ ip_fraglist_init(skb, iph, hlen, &iter);
for (;;) {
/* Prepare header of the next frame,
* before previous one went down. */
- if (frag) {
- frag->ip_summed = CHECKSUM_NONE;
- skb_reset_transport_header(frag);
- __skb_push(frag, hlen);
- skb_reset_network_header(frag);
- memcpy(skb_network_header(frag), iph, hlen);
- iph = ip_hdr(frag);
- iph->tot_len = htons(frag->len);
- ip_copy_metadata(frag, skb);
- if (offset == 0)
- ip_options_fragment(frag);
- offset += skb->len - hlen;
- iph->frag_off = htons(offset>>3);
- if (frag->next)
- iph->frag_off |= htons(IP_MF);
- /* Ready, complete checksum */
- ip_send_check(iph);
+ if (iter.frag) {
+ ip_fraglist_ipcb_prepare(skb, &iter);
+ ip_fraglist_prepare(skb, &iter);
}
+ skb->tstamp = tstamp;
err = output(net, sk, skb);
if (!err)
IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
- if (err || !frag)
+ if (err || !iter.frag)
break;
- skb = frag;
- frag = skb->next;
- skb->next = NULL;
+ skb = ip_fraglist_next(&iter);
}
if (err == 0) {
@@ -692,11 +863,8 @@
return 0;
}
- while (frag) {
- skb = frag->next;
- kfree_skb(frag);
- frag = skb;
- }
+ kfree_skb_list(iter.frag);
+
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
return err;
@@ -711,105 +879,31 @@
}
slow_path:
- iph = ip_hdr(skb);
-
- left = skb->len - hlen; /* Space per frame */
- ptr = hlen; /* Where to start from */
-
/*
* Fragment the datagram.
*/
- offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
- not_last_frag = iph->frag_off & htons(IP_MF);
+ ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU,
+ &state);
/*
* Keep copying data until we run out.
*/
- while (left > 0) {
- len = left;
- /* IF: it doesn't fit, use 'mtu' - the data space left */
- if (len > mtu)
- len = mtu;
- /* IF: we are not sending up to and including the packet end
- then align the next start on an eight byte boundary */
- if (len < left) {
- len &= ~7;
- }
+ while (state.left > 0) {
+ bool first_frag = (state.offset == 0);
- /* Allocate buffer */
- skb2 = alloc_skb(len + hlen + ll_rs, GFP_ATOMIC);
- if (!skb2) {
- err = -ENOMEM;
+ skb2 = ip_frag_next(skb, &state);
+ if (IS_ERR(skb2)) {
+ err = PTR_ERR(skb2);
goto fail;
}
-
- /*
- * Set up data on packet
- */
-
- ip_copy_metadata(skb2, skb);
- skb_reserve(skb2, ll_rs);
- skb_put(skb2, len + hlen);
- skb_reset_network_header(skb2);
- skb2->transport_header = skb2->network_header + hlen;
-
- /*
- * Charge the memory for the fragment to any owner
- * it might possess
- */
-
- if (skb->sk)
- skb_set_owner_w(skb2, skb->sk);
-
- /*
- * Copy the packet header into the new buffer.
- */
-
- skb_copy_from_linear_data(skb, skb_network_header(skb2), hlen);
-
- /*
- * Copy a block of the IP datagram.
- */
- if (skb_copy_bits(skb, ptr, skb_transport_header(skb2), len))
- BUG();
- left -= len;
-
- /*
- * Fill in the new header fields.
- */
- iph = ip_hdr(skb2);
- iph->frag_off = htons((offset >> 3));
-
- if (IPCB(skb)->flags & IPSKB_FRAG_PMTU)
- iph->frag_off |= htons(IP_DF);
-
- /* ANK: dirty, but effective trick. Upgrade options only if
- * the segment to be fragmented was THE FIRST (otherwise,
- * options are already fixed) and make it ONCE
- * on the initial skb, so that all the following fragments
- * will inherit fixed options.
- */
- if (offset == 0)
- ip_options_fragment(skb);
-
- /*
- * Added AC : If we are fragmenting a fragment that's not the
- * last fragment then keep MF on each bit
- */
- if (left > 0 || not_last_frag)
- iph->frag_off |= htons(IP_MF);
- ptr += len;
- offset += len;
+ ip_frag_ipcb(skb, skb2, first_frag, &state);
/*
* Put this fragment into the sending queue.
*/
- iph->tot_len = htons(len + hlen);
-
- ip_send_check(iph);
-
+ skb2->tstamp = tstamp;
err = output(net, sk, skb2);
if (err)
goto fail;
@@ -867,6 +961,7 @@
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
+ struct ubuf_info *uarg = NULL;
struct sk_buff *skb;
struct ip_options *opt = cork->opt;
@@ -880,8 +975,8 @@
int csummode = CHECKSUM_NONE;
struct rtable *rt = (struct rtable *)cork->dst;
unsigned int wmem_alloc_delta = 0;
+ bool paged, extra_uref = false;
u32 tskey = 0;
- bool paged;
skb = skb_peek_tail(queue);
@@ -916,6 +1011,20 @@
(!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM)))
csummode = CHECKSUM_PARTIAL;
+ if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) {
+ uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
+ if (!uarg)
+ return -ENOBUFS;
+ extra_uref = !skb_zcopy(skb); /* only ref on new uarg */
+ if (rt->dst.dev->features & NETIF_F_SG &&
+ csummode == CHECKSUM_PARTIAL) {
+ paged = true;
+ } else {
+ uarg->zerocopy = 0;
+ skb_zcopy_set(skb, uarg, &extra_uref);
+ }
+ }
+
cork->length += length;
/* So, what's going on in the loop below?
@@ -939,7 +1048,7 @@
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
- unsigned int pagedlen = 0;
+ unsigned int pagedlen;
struct sk_buff *skb_prev;
alloc_new_skb:
skb_prev = skb;
@@ -956,6 +1065,7 @@
if (datalen > mtu - fragheaderlen)
datalen = maxfraglen - fragheaderlen;
fraglen = datalen + fragheaderlen;
+ pagedlen = 0;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
@@ -1000,12 +1110,6 @@
skb->csum = 0;
skb_reserve(skb, hh_len);
- /* only the initial fragment is time stamped */
- skb_shinfo(skb)->tx_flags = cork->tx_flags;
- cork->tx_flags = 0;
- skb_shinfo(skb)->tskey = tskey;
- tskey = 0;
-
/*
* Find where to start putting bytes.
*/
@@ -1038,6 +1142,13 @@
exthdrlen = 0;
csummode = CHECKSUM_NONE;
+ /* only the initial fragment is time stamped */
+ skb_shinfo(skb)->tx_flags = cork->tx_flags;
+ cork->tx_flags = 0;
+ skb_shinfo(skb)->tskey = tskey;
+ tskey = 0;
+ skb_zcopy_set(skb, uarg, &extra_uref);
+
if ((flags & MSG_CONFIRM) && !skb_prev)
skb_set_dst_pending_confirm(skb, 1);
@@ -1067,7 +1178,7 @@
err = -EFAULT;
goto error;
}
- } else {
+ } else if (!uarg || !uarg->zerocopy) {
int i = skb_shinfo(skb)->nr_frags;
err = -ENOMEM;
@@ -1097,6 +1208,10 @@
skb->data_len += copy;
skb->truesize += copy;
wmem_alloc_delta += copy;
+ } else {
+ err = skb_zerocopy_iter_dgram(skb, from, copy);
+ if (err < 0)
+ goto error;
}
offset += copy;
length -= copy;
@@ -1109,6 +1224,8 @@
error_efault:
err = -EFAULT;
error:
+ if (uarg)
+ sock_zerocopy_put_abort(uarg, extra_uref);
cork->length -= length;
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
@@ -1153,6 +1270,7 @@
cork->length = 0;
cork->ttl = ipc->ttl;
cork->tos = ipc->tos;
+ cork->mark = ipc->sockc.mark;
cork->priority = ipc->priority;
cork->transmit_time = ipc->sockc.transmit_time;
cork->tx_flags = 0;
@@ -1416,7 +1534,7 @@
}
skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
- skb->mark = sk->sk_mark;
+ skb->mark = cork->mark;
skb->tstamp = cork->transmit_time;
/*
* Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
@@ -1536,7 +1654,7 @@
const struct ip_options *sopt,
__be32 daddr, __be32 saddr,
const struct ip_reply_arg *arg,
- unsigned int len)
+ unsigned int len, u64 transmit_time)
{
struct ip_options_data replyopts;
struct ipcm_cookie ipc;
@@ -1552,6 +1670,7 @@
ipcm_init(&ipc);
ipc.addr = daddr;
+ ipc.sockc.transmit_time = transmit_time;
if (replyopts.opt.opt.optlen) {
ipc.opt = &replyopts.opt;
@@ -1579,7 +1698,6 @@
inet_sk(sk)->tos = arg->tos;
- sk->sk_priority = skb->priority;
sk->sk_protocol = ip_hdr(skb)->protocol;
sk->sk_bound_dev_if = arg->bound_dev_if;
sk->sk_sndbuf = sysctl_wmem_default;