summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Makefile3
-rw-r--r--net/ipv4/af_inet.c3
-rw-r--r--net/ipv4/fib_rules.c7
-rw-r--r--net/ipv4/fib_semantics.c43
-rw-r--r--net/ipv4/ipconfig.c151
-rw-r--r--net/ipv4/ipmr.c3
-rw-r--r--net/ipv4/metrics.c53
-rw-r--r--net/ipv4/proc.c2
-rw-r--r--net/ipv4/tcp.c146
-rw-r--r--net/ipv4/tcp_input.c57
-rw-r--r--net/ipv4/tcp_output.c26
11 files changed, 415 insertions, 79 deletions
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index a07b7dd06def..b379520f9133 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -13,7 +13,8 @@ obj-y := route.o inetpeer.o protocol.o \
tcp_offload.o datagram.o raw.o udp.o udplite.o \
udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
- inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o
+ inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
+ metrics.o
obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index eaed0367e669..3ebf599cebae 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -994,7 +994,7 @@ const struct proto_ops inet_stream_ops = {
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
- .mmap = sock_no_mmap,
+ .mmap = tcp_mmap,
.sendpage = inet_sendpage,
.splice_read = tcp_splice_read,
.read_sock = tcp_read_sock,
@@ -1006,6 +1006,7 @@ const struct proto_ops inet_stream_ops = {
.compat_getsockopt = compat_sock_common_getsockopt,
.compat_ioctl = inet_compat_ioctl,
#endif
+ .set_rcvlowat = tcp_set_rcvlowat,
};
EXPORT_SYMBOL(inet_stream_ops);
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 737d11bc8838..f8eb78d042a4 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -213,14 +213,17 @@ static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = {
static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct fib_rule_hdr *frh,
- struct nlattr **tb)
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
int err = -EINVAL;
struct fib4_rule *rule4 = (struct fib4_rule *) rule;
- if (frh->tos & ~IPTOS_TOS_MASK)
+ if (frh->tos & ~IPTOS_TOS_MASK) {
+ NL_SET_ERR_MSG(extack, "Invalid tos");
goto errout;
+ }
/* split local/main if they are not already split */
err = fib_unmerge(net);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c27122f01b87..6608db23f54b 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1019,47 +1019,8 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
static int
fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
{
- bool ecn_ca = false;
- struct nlattr *nla;
- int remaining;
-
- if (!cfg->fc_mx)
- return 0;
-
- nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
- int type = nla_type(nla);
- u32 val;
-
- if (!type)
- continue;
- if (type > RTAX_MAX)
- return -EINVAL;
-
- if (type == RTAX_CC_ALGO) {
- char tmp[TCP_CA_NAME_MAX];
-
- nla_strlcpy(tmp, nla, sizeof(tmp));
- val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
- if (val == TCP_CA_UNSPEC)
- return -EINVAL;
- } else {
- val = nla_get_u32(nla);
- }
- if (type == RTAX_ADVMSS && val > 65535 - 40)
- val = 65535 - 40;
- if (type == RTAX_MTU && val > 65535 - 15)
- val = 65535 - 15;
- if (type == RTAX_HOPLIMIT && val > 255)
- val = 255;
- if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
- return -EINVAL;
- fi->fib_metrics->metrics[type - 1] = val;
- }
-
- if (ecn_ca)
- fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
-
- return 0;
+ return ip_metrics_convert(fi->fib_net, cfg->fc_mx, cfg->fc_mx_len,
+ fi->fib_metrics->metrics);
}
struct fib_info *fib_create_info(struct fib_config *cfg,
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 43f620feb1c4..d839d74853fc 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -28,6 +28,9 @@
*
* Multiple Nameservers in /proc/net/pnp
* -- Josef Siemes <jsiemes@web.de>, Aug 2002
+ *
+ * NTP servers in /proc/net/ipconfig/ntp_servers
+ * -- Chris Novakovic <chris@chrisn.me.uk>, April 2018
*/
#include <linux/types.h>
@@ -93,6 +96,7 @@
#define CONF_TIMEOUT_MAX (HZ*30) /* Maximum allowed timeout */
#define CONF_NAMESERVERS_MAX 3 /* Maximum number of nameservers
- '3' from resolv.h */
+#define CONF_NTP_SERVERS_MAX 3 /* Maximum number of NTP servers */
#define NONE cpu_to_be32(INADDR_NONE)
#define ANY cpu_to_be32(INADDR_ANY)
@@ -152,12 +156,16 @@ static int ic_proto_used; /* Protocol used, if any */
#define ic_proto_used 0
#endif
static __be32 ic_nameservers[CONF_NAMESERVERS_MAX]; /* DNS Server IP addresses */
+static __be32 ic_ntp_servers[CONF_NTP_SERVERS_MAX]; /* NTP server IP addresses */
static u8 ic_domain[64]; /* DNS (not NIS) domain name */
/*
* Private state.
*/
+/* proc_dir_entry for /proc/net/ipconfig */
+static struct proc_dir_entry *ipconfig_dir;
+
/* Name of user-selected boot device */
static char user_dev_name[IFNAMSIZ] __initdata = { 0, };
@@ -576,6 +584,15 @@ static inline void __init ic_nameservers_predef(void)
ic_nameservers[i] = NONE;
}
+/* Predefine NTP servers */
+static inline void __init ic_ntp_servers_predef(void)
+{
+ int i;
+
+ for (i = 0; i < CONF_NTP_SERVERS_MAX; i++)
+ ic_ntp_servers[i] = NONE;
+}
+
/*
* DHCP/BOOTP support.
*/
@@ -671,6 +688,7 @@ ic_dhcp_init_options(u8 *options, struct ic_device *d)
17, /* Boot path */
26, /* MTU */
40, /* NIS domain name */
+ 42, /* NTP servers */
};
*e++ = 55; /* Parameter request list */
@@ -721,9 +739,11 @@ static void __init ic_bootp_init_ext(u8 *e)
*e++ = 3; /* Default gateway request */
*e++ = 4;
e += 4;
- *e++ = 5; /* Name server request */
- *e++ = 8;
- e += 8;
+#if CONF_NAMESERVERS_MAX > 0
+ *e++ = 6; /* (DNS) name server request */
+ *e++ = 4 * CONF_NAMESERVERS_MAX;
+ e += 4 * CONF_NAMESERVERS_MAX;
+#endif
*e++ = 12; /* Host name request */
*e++ = 32;
e += 32;
@@ -748,7 +768,13 @@ static void __init ic_bootp_init_ext(u8 *e)
*/
static inline void __init ic_bootp_init(void)
{
+ /* Re-initialise all name servers and NTP servers to NONE, in case any
+ * were set via the "ip=" or "nfsaddrs=" kernel command line parameters:
+ * any IP addresses specified there will already have been decoded but
+ * are no longer needed
+ */
ic_nameservers_predef();
+ ic_ntp_servers_predef();
dev_add_pack(&bootp_packet_type);
}
@@ -912,6 +938,15 @@ static void __init ic_do_bootp_ext(u8 *ext)
ic_bootp_string(utsname()->domainname, ext+1, *ext,
__NEW_UTS_LEN);
break;
+ case 42: /* NTP servers */
+ servers = *ext / 4;
+ if (servers > CONF_NTP_SERVERS_MAX)
+ servers = CONF_NTP_SERVERS_MAX;
+ for (i = 0; i < servers; i++) {
+ if (ic_ntp_servers[i] == NONE)
+ memcpy(&ic_ntp_servers[i], ext+1+4*i, 4);
+ }
+ break;
}
}
@@ -1258,6 +1293,7 @@ static int __init ic_dynamic(void)
#ifdef CONFIG_PROC_FS
+/* Name servers: */
static int pnp_seq_show(struct seq_file *seq, void *v)
{
int i;
@@ -1294,6 +1330,62 @@ static const struct file_operations pnp_seq_fops = {
.llseek = seq_lseek,
.release = single_release,
};
+
+/* Create the /proc/net/ipconfig directory */
+static int __init ipconfig_proc_net_init(void)
+{
+ ipconfig_dir = proc_net_mkdir(&init_net, "ipconfig", init_net.proc_net);
+ if (!ipconfig_dir)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/* Create a new file under /proc/net/ipconfig */
+static int ipconfig_proc_net_create(const char *name,
+ const struct file_operations *fops)
+{
+ char *pname;
+ struct proc_dir_entry *p;
+
+ if (!ipconfig_dir)
+ return -ENOMEM;
+
+ pname = kasprintf(GFP_KERNEL, "%s%s", "ipconfig/", name);
+ if (!pname)
+ return -ENOMEM;
+
+ p = proc_create(pname, 0444, init_net.proc_net, fops);
+ kfree(pname);
+ if (!p)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/* Write NTP server IP addresses to /proc/net/ipconfig/ntp_servers */
+static int ntp_servers_seq_show(struct seq_file *seq, void *v)
+{
+ int i;
+
+ for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) {
+ if (ic_ntp_servers[i] != NONE)
+ seq_printf(seq, "%pI4\n", &ic_ntp_servers[i]);
+ }
+ return 0;
+}
+
+static int ntp_servers_seq_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ntp_servers_seq_show, NULL);
+}
+
+static const struct file_operations ntp_servers_seq_fops = {
+ .open = ntp_servers_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
#endif /* CONFIG_PROC_FS */
/*
@@ -1368,8 +1460,20 @@ static int __init ip_auto_config(void)
int err;
unsigned int i;
+ /* Initialise all name servers and NTP servers to NONE (but only if the
+ * "ip=" or "nfsaddrs=" kernel command line parameters weren't decoded,
+ * otherwise we'll overwrite the IP addresses specified there)
+ */
+ if (ic_set_manually == 0) {
+ ic_nameservers_predef();
+ ic_ntp_servers_predef();
+ }
+
#ifdef CONFIG_PROC_FS
proc_create("pnp", 0444, init_net.proc_net, &pnp_seq_fops);
+
+ if (ipconfig_proc_net_init() == 0)
+ ipconfig_proc_net_create("ntp_servers", &ntp_servers_seq_fops);
#endif /* CONFIG_PROC_FS */
if (!ic_enable)
@@ -1481,16 +1585,32 @@ static int __init ip_auto_config(void)
&ic_servaddr, &root_server_addr, root_server_path);
if (ic_dev_mtu)
pr_cont(", mtu=%d", ic_dev_mtu);
- for (i = 0; i < CONF_NAMESERVERS_MAX; i++)
+ /* Name servers (if any): */
+ for (i = 0; i < CONF_NAMESERVERS_MAX; i++) {
if (ic_nameservers[i] != NONE) {
- pr_cont(" nameserver%u=%pI4",
- i, &ic_nameservers[i]);
- break;
+ if (i == 0)
+ pr_info(" nameserver%u=%pI4",
+ i, &ic_nameservers[i]);
+ else
+ pr_cont(", nameserver%u=%pI4",
+ i, &ic_nameservers[i]);
}
- for (i++; i < CONF_NAMESERVERS_MAX; i++)
- if (ic_nameservers[i] != NONE)
- pr_cont(", nameserver%u=%pI4", i, &ic_nameservers[i]);
- pr_cont("\n");
+ if (i + 1 == CONF_NAMESERVERS_MAX)
+ pr_cont("\n");
+ }
+ /* NTP servers (if any): */
+ for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) {
+ if (ic_ntp_servers[i] != NONE) {
+ if (i == 0)
+ pr_info(" ntpserver%u=%pI4",
+ i, &ic_ntp_servers[i]);
+ else
+ pr_cont(", ntpserver%u=%pI4",
+ i, &ic_ntp_servers[i]);
+ }
+ if (i + 1 == CONF_NTP_SERVERS_MAX)
+ pr_cont("\n");
+ }
#endif /* !SILENT */
/*
@@ -1588,7 +1708,9 @@ static int __init ip_auto_config_setup(char *addrs)
return 1;
}
+ /* Initialise all name servers and NTP servers to NONE */
ic_nameservers_predef();
+ ic_ntp_servers_predef();
/* Parse string for static IP assignment. */
ip = addrs;
@@ -1647,6 +1769,13 @@ static int __init ip_auto_config_setup(char *addrs)
ic_nameservers[1] = NONE;
}
break;
+ case 9:
+ if (CONF_NTP_SERVERS_MAX >= 1) {
+ ic_ntp_servers[0] = in_aton(ip);
+ if (ic_ntp_servers[0] == ANY)
+ ic_ntp_servers[0] = NONE;
+ }
+ break;
}
}
ip = cp;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 2fb4de3f7f66..38e092eafc97 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -201,7 +201,8 @@ static const struct nla_policy ipmr_rule_policy[FRA_MAX + 1] = {
};
static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
- struct fib_rule_hdr *frh, struct nlattr **tb)
+ struct fib_rule_hdr *frh, struct nlattr **tb,
+ struct netlink_ext_ack *extack)
{
return 0;
}
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
new file mode 100644
index 000000000000..5121c6475e6b
--- /dev/null
+++ b/net/ipv4/metrics.c
@@ -0,0 +1,53 @@
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/types.h>
+#include <net/ip.h>
+#include <net/net_namespace.h>
+#include <net/tcp.h>
+
+int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len,
+ u32 *metrics)
+{
+ bool ecn_ca = false;
+ struct nlattr *nla;
+ int remaining;
+
+ if (!fc_mx)
+ return 0;
+
+ nla_for_each_attr(nla, fc_mx, fc_mx_len, remaining) {
+ int type = nla_type(nla);
+ u32 val;
+
+ if (!type)
+ continue;
+ if (type > RTAX_MAX)
+ return -EINVAL;
+
+ if (type == RTAX_CC_ALGO) {
+ char tmp[TCP_CA_NAME_MAX];
+
+ nla_strlcpy(tmp, nla, sizeof(tmp));
+ val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
+ if (val == TCP_CA_UNSPEC)
+ return -EINVAL;
+ } else {
+ val = nla_get_u32(nla);
+ }
+ if (type == RTAX_ADVMSS && val > 65535 - 40)
+ val = 65535 - 40;
+ if (type == RTAX_MTU && val > 65535 - 15)
+ val = 65535 - 15;
+ if (type == RTAX_HOPLIMIT && val > 255)
+ val = 255;
+ if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
+ return -EINVAL;
+ metrics[type - 1] = val;
+ }
+
+ if (ecn_ca)
+ metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_metrics_convert);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index a058de677e94..261b71d0ccc5 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -296,6 +296,8 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE),
SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL),
SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS),
+ SNMP_MIB_ITEM("TCPDelivered", LINUX_MIB_TCPDELIVERED),
+ SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9ce1c726185e..dfd090ea54ad 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1701,6 +1701,144 @@ int tcp_peek_len(struct socket *sock)
}
EXPORT_SYMBOL(tcp_peek_len);
+/* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */
+int tcp_set_rcvlowat(struct sock *sk, int val)
+{
+ sk->sk_rcvlowat = val ? : 1;
+
+ /* Check if we need to signal EPOLLIN right now */
+ tcp_data_ready(sk);
+
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
+ return 0;
+
+ /* val comes from user space and might be close to INT_MAX */
+ val <<= 1;
+ if (val < 0)
+ val = INT_MAX;
+
+ val = min(val, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ if (val > sk->sk_rcvbuf) {
+ sk->sk_rcvbuf = val;
+ tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val);
+ }
+ return 0;
+}
+EXPORT_SYMBOL(tcp_set_rcvlowat);
+
+/* When user wants to mmap X pages, we first need to perform the mapping
+ * before freeing any skbs in receive queue, otherwise user would be unable
+ * to fallback to standard recvmsg(). This happens if some data in the
+ * requested block is not exactly fitting in a page.
+ *
+ * We only support order-0 pages for the moment.
+ * mmap() on TCP is very strict, there is no point
+ * trying to accommodate with pathological layouts.
+ */
+int tcp_mmap(struct file *file, struct socket *sock,
+ struct vm_area_struct *vma)
+{
+ unsigned long size = vma->vm_end - vma->vm_start;
+ unsigned int nr_pages = size >> PAGE_SHIFT;
+ struct page **pages_array = NULL;
+ u32 seq, len, offset, nr = 0;
+ struct sock *sk = sock->sk;
+ const skb_frag_t *frags;
+ struct tcp_sock *tp;
+ struct sk_buff *skb;
+ int ret;
+
+ if (vma->vm_pgoff || !nr_pages)
+ return -EINVAL;
+
+ if (vma->vm_flags & VM_WRITE)
+ return -EPERM;
+ /* TODO: Maybe the following is not needed if pages are COW */
+ vma->vm_flags &= ~VM_MAYWRITE;
+
+ lock_sock(sk);
+
+ ret = -ENOTCONN;
+ if (sk->sk_state == TCP_LISTEN)
+ goto out;
+
+ sock_rps_record_flow(sk);
+
+ if (tcp_inq(sk) < size) {
+ ret = sock_flag(sk, SOCK_DONE) ? -EIO : -EAGAIN;
+ goto out;
+ }
+ tp = tcp_sk(sk);
+ seq = tp->copied_seq;
+ /* Abort if urgent data is in the area */
+ if (unlikely(tp->urg_data)) {
+ u32 urg_offset = tp->urg_seq - seq;
+
+ ret = -EINVAL;
+ if (urg_offset < size)
+ goto out;
+ }
+ ret = -ENOMEM;
+ pages_array = kvmalloc_array(nr_pages, sizeof(struct page *),
+ GFP_KERNEL);
+ if (!pages_array)
+ goto out;
+ skb = tcp_recv_skb(sk, seq, &offset);
+ ret = -EINVAL;
+skb_start:
+ /* We do not support anything not in page frags */
+ offset -= skb_headlen(skb);
+ if ((int)offset < 0)
+ goto out;
+ if (skb_has_frag_list(skb))
+ goto out;
+ len = skb->data_len - offset;
+ frags = skb_shinfo(skb)->frags;
+ while (offset) {
+ if (frags->size > offset)
+ goto out;
+ offset -= frags->size;
+ frags++;
+ }
+ while (nr < nr_pages) {
+ if (len) {
+ if (len < PAGE_SIZE)
+ goto out;
+ if (frags->size != PAGE_SIZE || frags->page_offset)
+ goto out;
+ pages_array[nr++] = skb_frag_page(frags);
+ frags++;
+ len -= PAGE_SIZE;
+ seq += PAGE_SIZE;
+ continue;
+ }
+ skb = skb->next;
+ offset = seq - TCP_SKB_CB(skb)->seq;
+ goto skb_start;
+ }
+ /* OK, we have a full set of pages ready to be inserted into vma */
+ for (nr = 0; nr < nr_pages; nr++) {
+ ret = vm_insert_page(vma, vma->vm_start + (nr << PAGE_SHIFT),
+ pages_array[nr]);
+ if (ret)
+ goto out;
+ }
+ /* operation is complete, we can 'consume' all skbs */
+ tp->copied_seq = seq;
+ tcp_rcv_space_adjust(sk);
+
+ /* Clean up data we have read: This will do ACK frames. */
+ tcp_recv_skb(sk, seq, &offset);
+ tcp_cleanup_rbuf(sk, size);
+
+ ret = 0;
+out:
+ release_sock(sk);
+ kvfree(pages_array);
+ return ret;
+}
+EXPORT_SYMBOL(tcp_mmap);
+
static void tcp_update_recv_tstamps(struct sk_buff *skb,
struct scm_timestamping *tss)
{
@@ -2421,6 +2559,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_cnt = 0;
tp->window_clamp = 0;
+ tp->delivered_ce = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
tp->is_sack_reneg = 0;
tcp_clear_retrans(tp);
@@ -3030,6 +3169,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
rate64 = tcp_compute_delivery_rate(tp);
if (rate64)
info->tcpi_delivery_rate = rate64;
+ info->tcpi_delivered = tp->delivered;
+ info->tcpi_delivered_ce = tp->delivered_ce;
unlock_sock_fast(sk, slow);
}
EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -3043,7 +3184,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
u32 rate;
stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) +
- 5 * nla_total_size(sizeof(u32)) +
+ 7 * nla_total_size(sizeof(u32)) +
3 * nla_total_size(sizeof(u8)), GFP_ATOMIC);
if (!stats)
return NULL;
@@ -3074,9 +3215,12 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits);
nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited);
nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh);
+ nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered);
+ nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce);
nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una);
nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state);
+
return stats;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e51c644484dc..8acbe5fd2098 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -582,6 +582,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
u32 copied;
int time;
+ trace_tcp_rcv_space_adjust(sk);
+
tcp_mstamp_refresh(tp);
time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time);
if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0)
@@ -3496,6 +3498,22 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit)
tcp_xmit_retransmit_queue(sk);
}
+/* Returns the number of packets newly acked or sacked by the current ACK */
+static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag)
+{
+ const struct net *net = sock_net(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 delivered;
+
+ delivered = tp->delivered - prior_delivered;
+ NET_ADD_STATS(net, LINUX_MIB_TCPDELIVERED, delivered);
+ if (flag & FLAG_ECE) {
+ tp->delivered_ce += delivered;
+ NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, delivered);
+ }
+ return delivered;
+}
+
/* This routine deals with incoming acks, but not outgoing ones. */
static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
{
@@ -3619,7 +3637,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
sk_dst_confirm(sk);
- delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */
+ delivered = tcp_newly_delivered(sk, delivered, flag);
lost = tp->lost - lost; /* freshly marked lost */
rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED);
tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
@@ -3629,9 +3647,11 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
no_queue:
/* If data was DSACKed, see if we can undo a cwnd reduction. */
- if (flag & FLAG_DSACKING_ACK)
+ if (flag & FLAG_DSACKING_ACK) {
tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
&rexmit);
+ tcp_newly_delivered(sk, delivered, flag);
+ }
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
* it needs to be for normal retransmission.
@@ -3655,6 +3675,7 @@ old_ack:
&sack_state);
tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
&rexmit);
+ tcp_newly_delivered(sk, delivered, flag);
tcp_xmit_recovery(sk, rexmit);
}
@@ -4573,6 +4594,17 @@ err:
}
+void tcp_data_ready(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ int avail = tp->rcv_nxt - tp->copied_seq;
+
+ if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+ return;
+
+ sk->sk_data_ready(sk);
+}
+
static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -4630,7 +4662,7 @@ queue_and_out:
if (eaten > 0)
kfree_skb_partial(skb, fragstolen);
if (!sock_flag(sk, SOCK_DEAD))
- sk->sk_data_ready(sk);
+ tcp_data_ready(sk);
return;
}
@@ -5023,9 +5055,12 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
/* More than one full frame received... */
if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss &&
/* ... and right edge of window advances far enough.
- * (tcp_recvmsg() will send ACK otherwise). Or...
+ * (tcp_recvmsg() will send ACK otherwise).
+ * If application uses SO_RCVLOWAT, we want send ack now if
+ * we have not received enough bytes to satisfy the condition.
*/
- __tcp_select_window(sk) >= tp->rcv_wnd) ||
+ (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat ||
+ __tcp_select_window(sk) >= tp->rcv_wnd)) ||
/* We ACK each frame or... */
tcp_in_quickack_mode(sk) ||
/* We have out of order data. */
@@ -5428,7 +5463,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
no_ack:
if (eaten)
kfree_skb_partial(skb, fragstolen);
- sk->sk_data_ready(sk);
+ tcp_data_ready(sk);
return;
}
}
@@ -5550,9 +5585,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
return true;
}
tp->syn_data_acked = tp->syn_data;
- if (tp->syn_data_acked)
- NET_INC_STATS(sock_net(sk),
- LINUX_MIB_TCPFASTOPENACTIVE);
+ if (tp->syn_data_acked) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
+ /* SYN-data is counted as two separate packets in tcp_ack() */
+ if (tp->delivered > 1)
+ --tp->delivered;
+ }
tcp_fastopen_add_skb(sk, synack);
@@ -5884,6 +5922,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
}
switch (sk->sk_state) {
case TCP_SYN_RECV:
+ tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */
if (!tp->srtt_us)
tcp_synack_rtt_meas(sk, req);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 383cac0ff0ec..95feffb6d53f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -585,14 +585,15 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
unsigned int remaining = MAX_TCP_OPTION_SPACE;
struct tcp_fastopen_request *fastopen = tp->fastopen_req;
+ *md5 = NULL;
#ifdef CONFIG_TCP_MD5SIG
- *md5 = tp->af_specific->md5_lookup(sk, sk);
- if (*md5) {
- opts->options |= OPTION_MD5;
- remaining -= TCPOLEN_MD5SIG_ALIGNED;
+ if (unlikely(rcu_access_pointer(tp->md5sig_info))) {
+ *md5 = tp->af_specific->md5_lookup(sk, sk);
+ if (*md5) {
+ opts->options |= OPTION_MD5;
+ remaining -= TCPOLEN_MD5SIG_ALIGNED;
+ }
}
-#else
- *md5 = NULL;
#endif
/* We always get an MSS option. The option bytes which will be seen in
@@ -720,14 +721,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
opts->options = 0;
+ *md5 = NULL;
#ifdef CONFIG_TCP_MD5SIG
- *md5 = tp->af_specific->md5_lookup(sk, sk);
- if (unlikely(*md5)) {
- opts->options |= OPTION_MD5;
- size += TCPOLEN_MD5SIG_ALIGNED;
+ if (unlikely(rcu_access_pointer(tp->md5sig_info))) {
+ *md5 = tp->af_specific->md5_lookup(sk, sk);
+ if (*md5) {
+ opts->options |= OPTION_MD5;
+ size += TCPOLEN_MD5SIG_ALIGNED;
+ }
}
-#else
- *md5 = NULL;
#endif
if (likely(tp->rx_opt.tstamp_ok)) {
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-20 23:18:32 +0100