summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/inet_connection_sock.c7
-rw-r--r--net/ipv4/ip_gre.c4
-rw-r--r--net/ipv4/proc.c1
-rw-r--r--net/ipv4/sysctl_net_ipv4.c1
-rw-r--r--net/ipv4/tcp.c16
-rw-r--r--net/ipv4/tcp_bic.c11
-rw-r--r--net/ipv4/tcp_cubic.c10
-rw-r--r--net/ipv4/tcp_input.c41
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/tcp_output.c6
10 files changed, 54 insertions, 45 deletions
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 2e4e24476c4..19d66cefd7d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -123,11 +123,14 @@ again:
smallest_size = tb->num_owners;
smallest_rover = rover;
if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) {
- spin_unlock(&head->lock);
snum = smallest_rover;
- goto have_snum;
+ goto tb_found;
}
}
+ if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
+ snum = rover;
+ goto tb_found;
+ }
goto next;
}
break;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2b53a1f7abf..6b3ca5ba445 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -422,6 +422,10 @@ static struct ip_tunnel *ipgre_tunnel_locate(struct net *net,
if (register_netdevice(dev) < 0)
goto failed_free;
+ /* Can use a lockless transmit, unless we generate output sequences */
+ if (!(nt->parms.o_flags & GRE_SEQ))
+ dev->features |= NETIF_F_LLTX;
+
dev_hold(dev);
ipgre_tunnel_link(ign, nt);
return nt;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 3569d8ecaea..6afc807ee2a 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -216,7 +216,6 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPPartialUndo", LINUX_MIB_TCPPARTIALUNDO),
SNMP_MIB_ITEM("TCPDSACKUndo", LINUX_MIB_TCPDSACKUNDO),
SNMP_MIB_ITEM("TCPLossUndo", LINUX_MIB_TCPLOSSUNDO),
- SNMP_MIB_ITEM("TCPLoss", LINUX_MIB_TCPLOSS),
SNMP_MIB_ITEM("TCPLostRetransmit", LINUX_MIB_TCPLOSTRETRANSMIT),
SNMP_MIB_ITEM("TCPRenoFailures", LINUX_MIB_TCPRENOFAILURES),
SNMP_MIB_ITEM("TCPSackFailures", LINUX_MIB_TCPSACKFAILURES),
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 4aa7e9dc0cb..4cb9cd2f2c3 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -814,6 +814,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
net->ipv4.sysctl_rt_cache_rebuild_count = 4;
+ tcp_init_mem(net);
limit = nr_free_buffer_pages() / 8;
limit = max(limit, 128UL);
net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9bcdec3ad77..06373b4a449 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3216,6 +3216,16 @@ static int __init set_thash_entries(char *str)
}
__setup("thash_entries=", set_thash_entries);
+void tcp_init_mem(struct net *net)
+{
+ /* Set per-socket limits to no more than 1/128 the pressure threshold */
+ unsigned long limit = nr_free_buffer_pages() / 8;
+ limit = max(limit, 128UL);
+ net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3;
+ net->ipv4.sysctl_tcp_mem[1] = limit;
+ net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2;
+}
+
void __init tcp_init(void)
{
struct sk_buff *skb = NULL;
@@ -3276,9 +3286,9 @@ void __init tcp_init(void)
sysctl_tcp_max_orphans = cnt / 2;
sysctl_max_syn_backlog = max(128, cnt / 256);
- /* Set per-socket limits to no more than 1/128 the pressure threshold */
- limit = ((unsigned long)init_net.ipv4.sysctl_tcp_mem[1])
- << (PAGE_SHIFT - 7);
+ tcp_init_mem(&init_net);
+ limit = nr_free_buffer_pages() / 8;
+ limit = max(limit, 128UL);
max_share = min(4UL*1024*1024, limit);
sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index 6187eb4d1dc..f45e1c24244 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -63,7 +63,6 @@ static inline void bictcp_reset(struct bictcp *ca)
{
ca->cnt = 0;
ca->last_max_cwnd = 0;
- ca->loss_cwnd = 0;
ca->last_cwnd = 0;
ca->last_time = 0;
ca->epoch_start = 0;
@@ -72,7 +71,11 @@ static inline void bictcp_reset(struct bictcp *ca)
static void bictcp_init(struct sock *sk)
{
- bictcp_reset(inet_csk_ca(sk));
+ struct bictcp *ca = inet_csk_ca(sk);
+
+ bictcp_reset(ca);
+ ca->loss_cwnd = 0;
+
if (initial_ssthresh)
tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
}
@@ -127,7 +130,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
}
/* if in slow start or link utilization is very low */
- if (ca->loss_cwnd == 0) {
+ if (ca->last_max_cwnd == 0) {
if (ca->cnt > 20) /* increase cwnd 5% per RTT */
ca->cnt = 20;
}
@@ -185,7 +188,7 @@ static u32 bictcp_undo_cwnd(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct bictcp *ca = inet_csk_ca(sk);
- return max(tp->snd_cwnd, ca->last_max_cwnd);
+ return max(tp->snd_cwnd, ca->loss_cwnd);
}
static void bictcp_state(struct sock *sk, u8 new_state)
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index f376b05cca8..a9077f441cb 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -107,7 +107,6 @@ static inline void bictcp_reset(struct bictcp *ca)
{
ca->cnt = 0;
ca->last_max_cwnd = 0;
- ca->loss_cwnd = 0;
ca->last_cwnd = 0;
ca->last_time = 0;
ca->bic_origin_point = 0;
@@ -142,7 +141,10 @@ static inline void bictcp_hystart_reset(struct sock *sk)
static void bictcp_init(struct sock *sk)
{
- bictcp_reset(inet_csk_ca(sk));
+ struct bictcp *ca = inet_csk_ca(sk);
+
+ bictcp_reset(ca);
+ ca->loss_cwnd = 0;
if (hystart)
bictcp_hystart_reset(sk);
@@ -275,7 +277,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
* The initial growth of cubic function may be too conservative
* when the available bandwidth is still unknown.
*/
- if (ca->loss_cwnd == 0 && ca->cnt > 20)
+ if (ca->last_max_cwnd == 0 && ca->cnt > 20)
ca->cnt = 20; /* increase cwnd 5% per RTT */
/* TCP Friendly */
@@ -342,7 +344,7 @@ static u32 bictcp_undo_cwnd(struct sock *sk)
{
struct bictcp *ca = inet_csk_ca(sk);
- return max(tcp_sk(sk)->snd_cwnd, ca->last_max_cwnd);
+ return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
}
static void bictcp_state(struct sock *sk, u8 new_state)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2877c3e0958..976034f8232 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -105,7 +105,6 @@ int sysctl_tcp_abc __read_mostly;
#define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN. */
#define FLAG_DATA_SACKED 0x20 /* New SACK. */
#define FLAG_ECE 0x40 /* ECE in this ACK */
-#define FLAG_DATA_LOST 0x80 /* SACK detected data lossage. */
#define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/
#define FLAG_ONLY_ORIG_SACKED 0x200 /* SACKs only non-rexmit sent before RTO */
#define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
@@ -1040,13 +1039,11 @@ static void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp,
* These 6 states form finite state machine, controlled by the following events:
* 1. New ACK (+SACK) arrives. (tcp_sacktag_write_queue())
* 2. Retransmission. (tcp_retransmit_skb(), tcp_xmit_retransmit_queue())
- * 3. Loss detection event of one of three flavors:
+ * 3. Loss detection event of two flavors:
* A. Scoreboard estimator decided the packet is lost.
* A'. Reno "three dupacks" marks head of queue lost.
- * A''. Its FACK modfication, head until snd.fack is lost.
- * B. SACK arrives sacking data transmitted after never retransmitted
- * hole was sent out.
- * C. SACK arrives sacking SND.NXT at the moment, when the
+ * A''. Its FACK modification, head until snd.fack is lost.
+ * B. SACK arrives sacking SND.NXT at the moment, when the
* segment was retransmitted.
* 4. D-SACK added new rule: D-SACK changes any tag to S.
*
@@ -1153,7 +1150,7 @@ static int tcp_is_sackblock_valid(struct tcp_sock *tp, int is_dsack,
}
/* Check for lost retransmit. This superb idea is borrowed from "ratehalving".
- * Event "C". Later note: FACK people cheated me again 8), we have to account
+ * Event "B". Later note: FACK people cheated me again 8), we have to account
* for reordering! Ugly, but should help.
*
* Search retransmitted skbs from write_queue that were sent when snd_nxt was
@@ -1844,10 +1841,6 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
if (found_dup_sack && ((i + 1) == first_sack_index))
next_dup = &sp[i + 1];
- /* Event "B" in the comment above. */
- if (after(end_seq, tp->high_seq))
- state.flag |= FLAG_DATA_LOST;
-
/* Skip too early cached blocks */
while (tcp_sack_cache_ok(tp, cache) &&
!before(start_seq, cache->end_seq))
@@ -2515,8 +2508,11 @@ static void tcp_timeout_skbs(struct sock *sk)
tcp_verify_left_out(tp);
}
-/* Mark head of queue up as lost. With RFC3517 SACK, the packets is
- * is against sacked "cnt", otherwise it's against facked "cnt"
+/* Detect loss in event "A" above by marking head of queue up as lost.
+ * For FACK or non-SACK(Reno) senders, the first "packets" number of segments
+ * are considered lost. For RFC3517 SACK, a segment is considered lost if it
+ * has at least tp->reordering SACKed seqments above it; "packets" refers to
+ * the maximum SACKed segments to pass before reaching this limit.
*/
static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
{
@@ -2525,6 +2521,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
int cnt, oldcnt;
int err;
unsigned int mss;
+ /* Use SACK to deduce losses of new sequences sent during recovery */
+ const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq;
WARN_ON(packets > tp->packets_out);
if (tp->lost_skb_hint) {
@@ -2546,7 +2544,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
tp->lost_skb_hint = skb;
tp->lost_cnt_hint = cnt;
- if (after(TCP_SKB_CB(skb)->end_seq, tp->high_seq))
+ if (after(TCP_SKB_CB(skb)->end_seq, loss_high))
break;
oldcnt = cnt;
@@ -3033,19 +3031,10 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
if (tcp_check_sack_reneging(sk, flag))
return;
- /* C. Process data loss notification, provided it is valid. */
- if (tcp_is_fack(tp) && (flag & FLAG_DATA_LOST) &&
- before(tp->snd_una, tp->high_seq) &&
- icsk->icsk_ca_state != TCP_CA_Open &&
- tp->fackets_out > tp->reordering) {
- tcp_mark_head_lost(sk, tp->fackets_out - tp->reordering, 0);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSS);
- }
-
- /* D. Check consistency of the current state. */
+ /* C. Check consistency of the current state. */
tcp_verify_left_out(tp);
- /* E. Check state exit conditions. State can be terminated
+ /* D. Check state exit conditions. State can be terminated
* when high_seq is ACKed. */
if (icsk->icsk_ca_state == TCP_CA_Open) {
WARN_ON(tp->retrans_out != 0);
@@ -3077,7 +3066,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
}
}
- /* F. Process state. */
+ /* E. Process state. */
switch (icsk->icsk_ca_state) {
case TCP_CA_Recovery:
if (!(flag & FLAG_SND_UNA_ADVANCED)) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1eb4ad57670..337ba4cca05 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -631,7 +631,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
arg.iov[0].iov_len = sizeof(rep.th);
#ifdef CONFIG_TCP_MD5SIG
- key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr) : NULL;
+ key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->saddr) : NULL;
if (key) {
rep.opt[0] = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8c8de2780c7..4ff3b6dc74f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1141,11 +1141,9 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
sk_mem_uncharge(sk, len);
sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
- /* Any change of skb->len requires recalculation of tso
- * factor and mss.
- */
+ /* Any change of skb->len requires recalculation of tso factor. */
if (tcp_skb_pcount(skb) > 1)
- tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk));
+ tcp_set_skb_tso_segs(sk, skb, tcp_skb_mss(skb));
return 0;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-15 02:28:36 +0000