summaryrefslogtreecommitdiff
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/ctrl.c68
-rw-r--r--net/mptcp/mib.c2
-rw-r--r--net/mptcp/mib.h2
-rw-r--r--net/mptcp/mptcp_diag.c1
-rw-r--r--net/mptcp/options.c198
-rw-r--r--net/mptcp/pm.c1
-rw-r--r--net/mptcp/pm_netlink.c28
-rw-r--r--net/mptcp/protocol.c281
-rw-r--r--net/mptcp/protocol.h51
-rw-r--r--net/mptcp/sockopt.c149
-rw-r--r--net/mptcp/subflow.c292
-rw-r--r--net/mptcp/token.c9
12 files changed, 669 insertions, 413 deletions
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 96ba616f59bf..7d738bd06f2c 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -4,7 +4,9 @@
* Copyright (c) 2019, Tessares SA.
*/
+#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
+#endif
#include <net/net_namespace.h>
#include <net/netns/generic.h>
@@ -15,10 +17,14 @@
static int mptcp_pernet_id;
struct mptcp_pernet {
+#ifdef CONFIG_SYSCTL
struct ctl_table_header *ctl_table_hdr;
+#endif
- int mptcp_enabled;
+ u8 mptcp_enabled;
unsigned int add_addr_timeout;
+ u8 checksum_enabled;
+ u8 allow_join_initial_addr_port;
};
static struct mptcp_pernet *mptcp_get_pernet(struct net *net)
@@ -36,15 +42,36 @@ unsigned int mptcp_get_add_addr_timeout(struct net *net)
return mptcp_get_pernet(net)->add_addr_timeout;
}
+int mptcp_is_checksum_enabled(struct net *net)
+{
+ return mptcp_get_pernet(net)->checksum_enabled;
+}
+
+int mptcp_allow_join_id0(struct net *net)
+{
+ return mptcp_get_pernet(net)->allow_join_initial_addr_port;
+}
+
+static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
+{
+ pernet->mptcp_enabled = 1;
+ pernet->add_addr_timeout = TCP_RTO_MAX;
+ pernet->checksum_enabled = 0;
+ pernet->allow_join_initial_addr_port = 1;
+}
+
+#ifdef CONFIG_SYSCTL
static struct ctl_table mptcp_sysctl_table[] = {
{
.procname = "enabled",
- .maxlen = sizeof(int),
+ .maxlen = sizeof(u8),
.mode = 0644,
/* users with CAP_NET_ADMIN or root (not and) can change this
* value, same as other sysctl or the 'net' tree.
*/
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE
},
{
.procname = "add_addr_timeout",
@@ -52,15 +79,25 @@ static struct ctl_table mptcp_sysctl_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
+ {
+ .procname = "checksum_enabled",
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE
+ },
+ {
+ .procname = "allow_join_initial_addr_port",
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE
+ },
{}
};
-static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
-{
- pernet->mptcp_enabled = 1;
- pernet->add_addr_timeout = TCP_RTO_MAX;
-}
-
static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
{
struct ctl_table_header *hdr;
@@ -75,6 +112,8 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
table[0].data = &pernet->mptcp_enabled;
table[1].data = &pernet->add_addr_timeout;
+ table[2].data = &pernet->checksum_enabled;
+ table[3].data = &pernet->allow_join_initial_addr_port;
hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
if (!hdr)
@@ -100,6 +139,17 @@ static void mptcp_pernet_del_table(struct mptcp_pernet *pernet)
kfree(table);
}
+#else
+
+static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
+{
+ return 0;
+}
+
+static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) {}
+
+#endif /* CONFIG_SYSCTL */
+
static int __net_init mptcp_net_init(struct net *net)
{
struct mptcp_pernet *pernet = mptcp_get_pernet(net);
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index eb2dc6dbe212..52ea2517e856 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -25,6 +25,8 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH),
SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX),
+ SNMP_MIB_ITEM("DSSNoMatchTCP", MPTCP_MIB_DSSTCPMISMATCH),
+ SNMP_MIB_ITEM("DataCsumErr", MPTCP_MIB_DATACSUMERR),
SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL),
SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE),
SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index f0da4f060fe1..193466c9b549 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -18,6 +18,8 @@ enum linux_mptcp_mib_field {
MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */
MPTCP_MIB_DSSNOMATCH, /* Received a new mapping that did not match the previous one */
MPTCP_MIB_INFINITEMAPRX, /* Received an infinite mapping */
+ MPTCP_MIB_DSSTCPMISMATCH, /* DSS-mapping did not map with TCP's sequence numbers */
+ MPTCP_MIB_DATACSUMERR, /* The data checksum fail */
MPTCP_MIB_OFOQUEUETAIL, /* Segments inserted into OoO queue tail */
MPTCP_MIB_OFOQUEUE, /* Segments inserted into OoO queue */
MPTCP_MIB_OFOMERGE, /* Segments merged in OoO queue */
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index f16d9b5ee978..8f88ddeab6a2 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -144,6 +144,7 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
info->mptcpi_write_seq = READ_ONCE(msk->write_seq);
info->mptcpi_snd_una = READ_ONCE(msk->snd_una);
info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq);
+ info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled);
unlock_sock_fast(sk, slow);
}
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 6b825fb3fa83..b5850afea343 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -44,7 +44,20 @@ static void mptcp_parse_option(const struct sk_buff *skb,
else
expected_opsize = TCPOLEN_MPTCP_MPC_SYN;
}
- if (opsize != expected_opsize)
+
+ /* Cfr RFC 8684 Section 3.3.0:
+ * If a checksum is present but its use had
+ * not been negotiated in the MP_CAPABLE handshake, the receiver MUST
+ * close the subflow with a RST, as it is not behaving as negotiated.
+ * If a checksum is not present when its use has been negotiated, the
+ * receiver MUST close the subflow with a RST, as it is considered
+ * broken
+ * We parse even option with mismatching csum presence, so that
+ * later in subflow_data_ready we can trigger the reset.
+ */
+ if (opsize != expected_opsize &&
+ (expected_opsize != TCPOLEN_MPTCP_MPC_ACK_DATA ||
+ opsize != TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM))
break;
/* try to be gentle vs future versions on the initial syn */
@@ -66,16 +79,12 @@ static void mptcp_parse_option(const struct sk_buff *skb,
* host requires the use of checksums, checksums MUST be used.
* In other words, the only way for checksums not to be used
* is if both hosts in their SYNs set A=0."
- *
- * Section 3.3.0:
- * "If a checksum is not present when its use has been
- * negotiated, the receiver MUST close the subflow with a RST as
- * it is considered broken."
- *
- * We don't implement DSS checksum - fall back to TCP.
*/
if (flags & MPTCP_CAP_CHECKSUM_REQD)
- break;
+ mp_opt->csum_reqd = 1;
+
+ if (flags & MPTCP_CAP_DENY_JOIN_ID0)
+ mp_opt->deny_join_id0 = 1;
mp_opt->mp_capable = 1;
if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) {
@@ -86,7 +95,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->rcvr_key = get_unaligned_be64(ptr);
ptr += 8;
}
- if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA) {
+ if (opsize >= TCPOLEN_MPTCP_MPC_ACK_DATA) {
/* Section 3.1.:
* "the data parameters in a MP_CAPABLE are semantically
* equivalent to those in a DSS option and can be used
@@ -98,9 +107,14 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->data_len = get_unaligned_be16(ptr);
ptr += 2;
}
- pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d",
+ if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) {
+ mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr);
+ mp_opt->csum_reqd = 1;
+ ptr += 2;
+ }
+ pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u",
version, flags, opsize, mp_opt->sndr_key,
- mp_opt->rcvr_key, mp_opt->data_len);
+ mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum);
break;
case MPTCPOPT_MP_JOIN:
@@ -171,10 +185,8 @@ static void mptcp_parse_option(const struct sk_buff *skb,
expected_opsize += TCPOLEN_MPTCP_DSS_MAP32;
}
- /* RFC 6824, Section 3.3:
- * If a checksum is present, but its use had
- * not been negotiated in the MP_CAPABLE handshake,
- * the checksum field MUST be ignored.
+ /* Always parse any csum presence combination, we will enforce
+ * RFC 8684 Section 3.3.0 checks later in subflow_data_ready
*/
if (opsize != expected_opsize &&
opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM)
@@ -209,9 +221,15 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->data_len = get_unaligned_be16(ptr);
ptr += 2;
- pr_debug("data_seq=%llu subflow_seq=%u data_len=%u",
+ if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) {
+ mp_opt->csum_reqd = 1;
+ mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr);
+ ptr += 2;
+ }
+
+ pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
mp_opt->data_seq, mp_opt->subflow_seq,
- mp_opt->data_len);
+ mp_opt->data_len, mp_opt->csum_reqd, mp_opt->csum);
}
break;
@@ -323,9 +341,12 @@ static void mptcp_parse_option(const struct sk_buff *skb,
}
}
-void mptcp_get_options(const struct sk_buff *skb,
+void mptcp_get_options(const struct sock *sk,
+ const struct sk_buff *skb,
struct mptcp_options_received *mp_opt)
{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct mptcp_sock *msk = mptcp_sk(subflow->conn);
const struct tcphdr *th = tcp_hdr(skb);
const unsigned char *ptr;
int length;
@@ -341,6 +362,8 @@ void mptcp_get_options(const struct sk_buff *skb,
mp_opt->dss = 0;
mp_opt->mp_prio = 0;
mp_opt->reset = 0;
+ mp_opt->csum_reqd = READ_ONCE(msk->csum_enabled);
+ mp_opt->deny_join_id0 = 0;
length = (th->doff * 4) - sizeof(struct tcphdr);
ptr = (const unsigned char *)(th + 1);
@@ -356,6 +379,8 @@ void mptcp_get_options(const struct sk_buff *skb,
length--;
continue;
default:
+ if (length < 2)
+ return;
opsize = *ptr++;
if (opsize < 2) /* "silly options" */
return;
@@ -380,6 +405,8 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
subflow->snd_isn = TCP_SKB_CB(skb)->end_seq;
if (subflow->request_mptcp) {
opts->suboptions = OPTION_MPTCP_MPC_SYN;
+ opts->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk));
+ opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk));
*size = TCPOLEN_MPTCP_MPC_SYN;
return true;
} else if (subflow->request_join) {
@@ -435,8 +462,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct mptcp_sock *msk = mptcp_sk(subflow->conn);
struct mptcp_ext *mpext;
unsigned int data_len;
+ u8 len;
/* When skb is not available, we better over-estimate the emitted
* options len. A full DSS option (28 bytes) is longer than
@@ -465,16 +494,27 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
opts->suboptions = OPTION_MPTCP_MPC_ACK;
opts->sndr_key = subflow->local_key;
opts->rcvr_key = subflow->remote_key;
+ opts->csum_reqd = READ_ONCE(msk->csum_enabled);
+ opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk));
/* Section 3.1.
* The MP_CAPABLE option is carried on the SYN, SYN/ACK, and ACK
* packets that start the first subflow of an MPTCP connection,
* as well as the first packet that carries data
*/
- if (data_len > 0)
- *size = ALIGN(TCPOLEN_MPTCP_MPC_ACK_DATA, 4);
- else
+ if (data_len > 0) {
+ len = TCPOLEN_MPTCP_MPC_ACK_DATA;
+ if (opts->csum_reqd) {
+ /* we need to propagate more info to csum the pseudo hdr */
+ opts->ext_copy.data_seq = mpext->data_seq;
+ opts->ext_copy.subflow_seq = mpext->subflow_seq;
+ opts->ext_copy.csum = mpext->csum;
+ len += TCPOLEN_MPTCP_DSS_CHECKSUM;
+ }
+ *size = ALIGN(len, 4);
+ } else {
*size = TCPOLEN_MPTCP_MPC_ACK;
+ }
pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d",
subflow, subflow->local_key, subflow->remote_key,
@@ -535,18 +575,21 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
bool ret = false;
u64 ack_seq;
+ opts->csum_reqd = READ_ONCE(msk->csum_enabled);
mpext = skb ? mptcp_get_ext(skb) : NULL;
if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
- unsigned int map_size;
+ unsigned int map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
- map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
+ if (mpext) {
+ if (opts->csum_reqd)
+ map_size += TCPOLEN_MPTCP_DSS_CHECKSUM;
- remaining -= map_size;
- dss_size = map_size;
- if (mpext)
opts->ext_copy = *mpext;
+ }
+ remaining -= map_size;
+ dss_size = map_size;
if (skb && snd_data_fin_enable)
mptcp_write_data_fin(subflow, skb, &opts->ext_copy);
ret = true;
@@ -789,6 +832,8 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
if (subflow_req->mp_capable) {
opts->suboptions = OPTION_MPTCP_MPC_SYNACK;
opts->sndr_key = subflow_req->local_key;
+ opts->csum_reqd = subflow_req->csum_reqd;
+ opts->allow_join_id0 = subflow_req->allow_join_id0;
*size = TCPOLEN_MPTCP_MPC_SYNACK;
pr_debug("subflow_req=%p, local_key=%llu",
subflow_req, subflow_req->local_key);
@@ -867,6 +912,9 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
return false;
}
+ if (mp_opt->deny_join_id0)
+ WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
+
if (unlikely(!READ_ONCE(msk->pm.server_side)))
pr_warn_once("bogus mpc option on established client sk");
mptcp_subflow_fully_established(subflow, mp_opt);
@@ -894,19 +942,20 @@ reset:
return false;
}
-static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit)
+u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq)
{
- u32 old_ack32, cur_ack32;
-
- if (use_64bit)
- return cur_ack;
-
- old_ack32 = (u32)old_ack;
- cur_ack32 = (u32)cur_ack;
- cur_ack = (old_ack & GENMASK_ULL(63, 32)) + cur_ack32;
- if (unlikely(before(cur_ack32, old_ack32)))
- return cur_ack + (1LL << 32);
- return cur_ack;
+ u32 old_seq32, cur_seq32;
+
+ old_seq32 = (u32)old_seq;
+ cur_seq32 = (u32)cur_seq;
+ cur_seq = (old_seq & GENMASK_ULL(63, 32)) + cur_seq32;
+ if (unlikely(cur_seq32 < old_seq32 && before(old_seq32, cur_seq32)))
+ return cur_seq + (1LL << 32);
+
+ /* reverse wrap could happen, too */
+ if (unlikely(cur_seq32 > old_seq32 && after(old_seq32, cur_seq32)))
+ return cur_seq - (1LL << 32);
+ return cur_seq;
}
static void ack_update_msk(struct mptcp_sock *msk,
@@ -924,7 +973,7 @@ static void ack_update_msk(struct mptcp_sock *msk,
* more dangerous than missing an ack
*/
old_snd_una = msk->snd_una;
- new_snd_una = expand_ack(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
+ new_snd_una = mptcp_expand_seq(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
/* ACK for data not even sent yet? Ignore. */
if (after64(new_snd_una, snd_nxt))
@@ -961,7 +1010,7 @@ bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool us
return false;
WRITE_ONCE(msk->rcv_data_fin_seq,
- expand_ack(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit));
+ mptcp_expand_seq(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit));
WRITE_ONCE(msk->rcv_data_fin, 1);
return true;
@@ -1007,7 +1056,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
return;
}
- mptcp_get_options(skb, &mp_opt);
+ mptcp_get_options(sk, skb, &mp_opt);
if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
return;
@@ -1099,6 +1148,10 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
}
mpext->data_len = mp_opt.data_len;
mpext->use_map = 1;
+ mpext->csum_reqd = mp_opt.csum_reqd;
+
+ if (mpext->csum_reqd)
+ mpext->csum = mp_opt.csum;
}
}
@@ -1118,25 +1171,53 @@ static void mptcp_set_rwin(const struct tcp_sock *tp)
WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
}
+static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
+{
+ struct csum_pseudo_header header;
+ __wsum csum;
+
+ /* cfr RFC 8684 3.3.1.:
+ * the data sequence number used in the pseudo-header is
+ * always the 64-bit value, irrespective of what length is used in the
+ * DSS option itself.
+ */
+ header.data_seq = cpu_to_be64(mpext->data_seq);
+ header.subflow_seq = htonl(mpext->subflow_seq);
+ header.data_len = htons(mpext->data_len);
+ header.csum = 0;
+
+ csum = csum_partial(&header, sizeof(header), ~csum_unfold(mpext->csum));
+ return (__force u16)csum_fold(csum);
+}
+
void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
struct mptcp_out_options *opts)
{
if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
- u8 len;
+ u8 len, flag = MPTCP_CAP_HMAC_SHA256;
- if (OPTION_MPTCP_MPC_SYN & opts->suboptions)
+ if (OPTION_MPTCP_MPC_SYN & opts->suboptions) {
len = TCPOLEN_MPTCP_MPC_SYN;
- else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions)
+ } else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) {
len = TCPOLEN_MPTCP_MPC_SYNACK;
- else if (opts->ext_copy.data_len)
+ } else if (opts->ext_copy.data_len) {
len = TCPOLEN_MPTCP_MPC_ACK_DATA;
- else
+ if (opts->csum_reqd)
+ len += TCPOLEN_MPTCP_DSS_CHECKSUM;
+ } else {
len = TCPOLEN_MPTCP_MPC_ACK;
+ }
+
+ if (opts->csum_reqd)
+ flag |= MPTCP_CAP_CHECKSUM_REQD;
+
+ if (!opts->allow_join_id0)
+ flag |= MPTCP_CAP_DENY_JOIN_ID0;
*ptr++ = mptcp_option(MPTCPOPT_MP_CAPABLE, len,
MPTCP_SUPPORTED_VERSION,
- MPTCP_CAP_HMAC_SHA256);
+ flag);
if (!((OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) &
opts->suboptions))
@@ -1152,8 +1233,13 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
if (!opts->ext_copy.data_len)
goto mp_capable_done;
- put_unaligned_be32(opts->ext_copy.data_len << 16 |
- TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
+ if (opts->csum_reqd) {
+ put_unaligned_be32(opts->ext_copy.data_len << 16 |
+ mptcp_make_csum(&opts->ext_copy), ptr);
+ } else {
+ put_unaligned_be32(opts->ext_copy.data_len << 16 |
+ TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
+ }
ptr += 1;
}
@@ -1305,6 +1391,9 @@ mp_capable_done:
flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64;
if (mpext->data_fin)
flags |= MPTCP_DSS_DATA_FIN;
+
+ if (opts->csum_reqd)
+ len += TCPOLEN_MPTCP_DSS_CHECKSUM;
}
*ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags);
@@ -1324,8 +1413,13 @@ mp_capable_done:
ptr += 2;
put_unaligned_be32(mpext->subflow_seq, ptr);
ptr += 1;
- put_unaligned_be32(mpext->data_len << 16 |
- TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
+ if (opts->csum_reqd) {
+ put_unaligned_be32(mpext->data_len << 16 |
+ mptcp_make_csum(mpext), ptr);
+ } else {
+ put_unaligned_be32(mpext->data_len << 16 |
+ TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
+ }
}
}
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 9d00fa6d22e9..639271e09604 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -320,6 +320,7 @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
WRITE_ONCE(msk->pm.addr_signal, 0);
WRITE_ONCE(msk->pm.accept_addr, false);
WRITE_ONCE(msk->pm.accept_subflow, false);
+ WRITE_ONCE(msk->pm.remote_deny_join_id0, false);
msk->pm.status = 0;
spin_lock_init(&msk->pm.lock);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 2469e06a3a9d..d2591ebf01d9 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -451,7 +451,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
/* check if should create a new subflow */
if (msk->pm.local_addr_used < local_addr_max &&
- msk->pm.subflows < subflows_max) {
+ msk->pm.subflows < subflows_max &&
+ !READ_ONCE(msk->pm.remote_deny_join_id0)) {
local = select_local_address(pernet, msk);
if (local) {
struct mptcp_addr_info remote = { 0 };
@@ -540,6 +541,7 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
if (subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow;
spin_unlock_bh(&msk->pm.lock);
pr_debug("send ack for %s%s%s",
@@ -547,9 +549,9 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
mptcp_pm_should_add_signal_ipv6(msk) ? " [ipv6]" : "",
mptcp_pm_should_add_signal_port(msk) ? " [port]" : "");
- lock_sock(ssk);
+ slow = lock_sock_fast(ssk);
tcp_send_ack(ssk);
- release_sock(ssk);
+ unlock_sock_fast(ssk, slow);
spin_lock_bh(&msk->pm.lock);
}
}
@@ -566,6 +568,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
struct sock *sk = (struct sock *)msk;
struct mptcp_addr_info local;
+ bool slow;
local_address((struct sock_common *)ssk, &local);
if (!addresses_equal(&local, addr, addr->port))
@@ -578,9 +581,9 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
spin_unlock_bh(&msk->pm.lock);
pr_debug("send ack for mp_prio");
- lock_sock(ssk);
+ slow = lock_sock_fast(ssk);
tcp_send_ack(ssk);
- release_sock(ssk);
+ unlock_sock_fast(ssk, slow);
spin_lock_bh(&msk->pm.lock);
return 0;
@@ -971,8 +974,14 @@ skip_family:
if (tb[MPTCP_PM_ADDR_ATTR_FLAGS])
entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]);
- if (tb[MPTCP_PM_ADDR_ATTR_PORT])
+ if (tb[MPTCP_PM_ADDR_ATTR_PORT]) {
+ if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
+ NL_SET_ERR_MSG_ATTR(info->extack, attr,
+ "flags must have signal when using port");
+ return -EINVAL;
+ }
entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT]));
+ }
return 0;
}
@@ -1913,10 +1922,13 @@ static int __net_init pm_nl_init_net(struct net *net)
struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id);
INIT_LIST_HEAD_RCU(&pernet->local_addr_list);
- __reset_counters(pernet);
pernet->next_id = 1;
- bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1);
spin_lock_init(&pernet->lock);
+
+ /* No need to initialize other pernet fields, the struct is zeroed at
+ * allocation time.
+ */
+
return 0;
}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5edc686faff1..7a5afa8c6866 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -39,10 +39,15 @@ struct mptcp_skb_cb {
u64 map_seq;
u64 end_seq;
u32 offset;
+ u8 has_rxtstamp:1;
};
#define MPTCP_SKB_CB(__skb) ((struct mptcp_skb_cb *)&((__skb)->cb[0]))
+enum {
+ MPTCP_CMSG_TS = BIT(0),
+};
+
static struct percpu_counter mptcp_sockets_allocated;
static void __mptcp_destroy_sock(struct sock *sk);
@@ -272,6 +277,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct sock *sk = (struct sock *)msk;
struct sk_buff *tail;
+ bool has_rxtstamp;
__skb_unlink(skb, &ssk->sk_receive_queue);
@@ -280,13 +286,17 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
/* try to fetch required memory from subflow */
if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
- if (ssk->sk_forward_alloc < skb->truesize)
- goto drop;
- __sk_mem_reclaim(ssk, skb->truesize);
- if (!sk_rmem_schedule(sk, skb, skb->truesize))
+ int amount = sk_mem_pages(skb->truesize) << SK_MEM_QUANTUM_SHIFT;
+
+ if (ssk->sk_forward_alloc < amount)
goto drop;
+
+ ssk->sk_forward_alloc -= amount;
+ sk->sk_forward_alloc += amount;
}
+ has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
+
/* the skb map_seq accounts for the skb offset:
* mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq
* value
@@ -294,6 +304,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow);
MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len;
MPTCP_SKB_CB(skb)->offset = offset;
+ MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp;
if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
/* in sequence */
@@ -422,56 +433,55 @@ static void mptcp_send_ack(struct mptcp_sock *msk)
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow;
- lock_sock(ssk);
+ slow = lock_sock_fast(ssk);
if (tcp_can_send_ack(ssk))
tcp_send_ack(ssk);
- release_sock(ssk);
+ unlock_sock_fast(ssk, slow);
}
}
-static bool mptcp_subflow_cleanup_rbuf(struct sock *ssk)
+static void mptcp_subflow_cleanup_rbuf(struct sock *ssk)
{
- int ret;
+ bool slow;
- lock_sock(ssk);
- ret = tcp_can_send_ack(ssk);
- if (ret)
+ slow = lock_sock_fast(ssk);
+ if (tcp_can_send_ack(ssk))
tcp_cleanup_rbuf(ssk, 1);
- release_sock(ssk);
- return ret;
+ unlock_sock_fast(ssk, slow);
+}
+
+static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty)
+{
+ const struct inet_connection_sock *icsk = inet_csk(ssk);
+ u8 ack_pending = READ_ONCE(icsk->icsk_ack.pending);
+ const struct tcp_sock *tp = tcp_sk(ssk);
+
+ return (ack_pending & ICSK_ACK_SCHED) &&
+ ((READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->rcv_wup) >
+ READ_ONCE(icsk->icsk_ack.rcv_mss)) ||
+ (rx_empty && ack_pending &
+ (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED)));
}
static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
{
- struct sock *ack_hint = READ_ONCE(msk->ack_hint);
int old_space = READ_ONCE(msk->old_wspace);
struct mptcp_subflow_context *subflow;
struct sock *sk = (struct sock *)msk;
- bool cleanup;
+ int space = __mptcp_space(sk);
+ bool cleanup, rx_empty;
- /* this is a simple superset of what tcp_cleanup_rbuf() implements
- * so that we don't have to acquire the ssk socket lock most of the time
- * to do actually nothing
- */
- cleanup = __mptcp_space(sk) - old_space >= max(0, old_space);
- if (!cleanup)
- return;
+ cleanup = (space > 0) && (space >= (old_space << 1));
+ rx_empty = !atomic_read(&sk->sk_rmem_alloc);
- /* if the hinted ssk is still active, try to use it */
- if (likely(ack_hint)) {
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- if (ack_hint == ssk && mptcp_subflow_cleanup_rbuf(ssk))
- return;
- }
+ if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty))
+ mptcp_subflow_cleanup_rbuf(ssk);
}
-
- /* otherwise pick the first active subflow */
- mptcp_for_each_subflow(msk, subflow)
- if (mptcp_subflow_cleanup_rbuf(mptcp_subflow_tcp_sock(subflow)))
- return;
}
static bool mptcp_check_data_fin(struct sock *sk)
@@ -616,7 +626,6 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
break;
}
} while (more_data_avail);
- WRITE_ONCE(msk->ack_hint, ssk);
*bytes += moved;
return done;
@@ -668,18 +677,19 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
/* In most cases we will be able to lock the mptcp socket. If its already
* owned, we need to defer to the work queue to avoid ABBA deadlock.
*/
-static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
+static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
{
struct sock *sk = (struct sock *)msk;
unsigned int moved = 0;
- if (inet_sk_state_load(sk) == TCP_CLOSE)
- return;
-
- mptcp_data_lock(sk);
-
__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
__mptcp_ofo_queue(msk);
+ if (unlikely(ssk->sk_err)) {
+ if (!sock_owned_by_user(sk))
+ __mptcp_error_report(sk);
+ else
+ set_bit(MPTCP_ERROR_REPORT, &msk->flags);
+ }
/* If the moves have caught up with the DATA_FIN sequence number
* it's time to ack the DATA_FIN and change socket state, but
@@ -688,7 +698,7 @@ static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
*/
if (mptcp_pending_data_fin(sk, NULL))
mptcp_schedule_work(sk);
- mptcp_data_unlock(sk);
+ return moved > 0;
}
void mptcp_data_ready(struct sock *sk, struct sock *ssk)
@@ -696,7 +706,6 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct mptcp_sock *msk = mptcp_sk(sk);
int sk_rbuf, ssk_rbuf;
- bool wake;
/* The peer can send data while we are shutting down this
* subflow at msk destruction time, but we must avoid enqueuing
@@ -705,28 +714,22 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
if (unlikely(subflow->disposable))
return;
- /* move_skbs_to_msk below can legitly clear the data_avail flag,
- * but we will need later to properly woke the reader, cache its
- * value
- */
- wake = subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL;
- if (wake)
- set_bit(MPTCP_DATA_READY, &msk->flags);
-
ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
if (unlikely(ssk_rbuf > sk_rbuf))
sk_rbuf = ssk_rbuf;
- /* over limit? can't append more skbs to msk */
+ /* over limit? can't append more skbs to msk, Also, no need to wake-up*/
if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
- goto wake;
-
- move_skbs_to_msk(msk, ssk);
+ return;
-wake:
- if (wake)
+ /* Wake-up the reader only for in-sequence data */
+ mptcp_data_lock(sk);
+ if (move_skbs_to_msk(msk, ssk)) {
+ set_bit(MPTCP_DATA_READY, &msk->flags);
sk->sk_data_ready(sk);
+ }
+ mptcp_data_unlock(sk);
}
static bool mptcp_do_flush_join_list(struct mptcp_sock *msk)
@@ -858,7 +861,7 @@ static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
sock_owned_by_me(sk);
mptcp_for_each_subflow(msk, subflow) {
- if (subflow->data_avail)
+ if (READ_ONCE(subflow->data_avail))
return mptcp_subflow_tcp_sock(subflow);
}
@@ -894,22 +897,14 @@ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
df->data_seq + df->data_len == msk->write_seq;
}
-static int mptcp_wmem_with_overhead(struct sock *sk, int size)
+static int mptcp_wmem_with_overhead(int size)
{
- struct mptcp_sock *msk = mptcp_sk(sk);
- int ret, skbs;
-
- ret = size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT);
- skbs = (msk->tx_pending_data + size) / msk->size_goal_cache;
- if (skbs < msk->skb_tx_cache.qlen)
- return ret;
-
- return ret + (skbs - msk->skb_tx_cache.qlen) * SKB_TRUESIZE(MAX_TCP_HEADER);
+ return size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT);
}
static void __mptcp_wmem_reserve(struct sock *sk, int size)
{
- int amount = mptcp_wmem_with_overhead(sk, size);
+ int amount = mptcp_wmem_with_overhead(size);
struct mptcp_sock *msk = mptcp_sk(sk);
WARN_ON_ONCE(msk->wmem_reserved);
@@ -1204,49 +1199,8 @@ static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp)
return NULL;
}
-static bool mptcp_tx_cache_refill(struct sock *sk, int size,
- struct sk_buff_head *skbs, int *total_ts)
-{
- struct mptcp_sock *msk = mptcp_sk(sk);
- struct sk_buff *skb;
- int space_needed;
-
- if (unlikely(tcp_under_memory_pressure(sk))) {
- mptcp_mem_reclaim_partial(sk);
-
- /* under pressure pre-allocate at most a single skb */
- if (msk->skb_tx_cache.qlen)
- return true;
- space_needed = msk->size_goal_cache;
- } else {
- space_needed = msk->tx_pending_data + size -
- msk->skb_tx_cache.qlen * msk->size_goal_cache;
- }
-
- while (space_needed > 0) {
- skb = __mptcp_do_alloc_tx_skb(sk, sk->sk_allocation);
- if (unlikely(!skb)) {
- /* under memory pressure, try to pass the caller a
- * single skb to allow forward progress
- */
- while (skbs->qlen > 1) {
- skb = __skb_dequeue_tail(skbs);
- *total_ts -= skb->truesize;
- __kfree_skb(skb);
- }
- return skbs->qlen > 0;
- }
-
- *total_ts += skb->truesize;
- __skb_queue_tail(skbs, skb);
- space_needed -= msk->size_goal_cache;
- }
- return true;
-}
-
static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
{
- struct mptcp_sock *msk = mptcp_sk(sk);
struct sk_buff *skb;
if (ssk->sk_tx_skb_cache) {
@@ -1257,22 +1211,6 @@ static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
return true;
}
- skb = skb_peek(&msk->skb_tx_cache);
- if (skb) {
- if (likely(sk_wmem_schedule(ssk, skb->truesize))) {
- skb = __skb_dequeue(&msk->skb_tx_cache);
- if (WARN_ON_ONCE(!skb))
- return false;
-
- mptcp_wmem_uncharge(sk, skb->truesize);
- ssk->sk_tx_skb_cache = skb;
- return true;
- }
-
- /* over memory limit, no point to try to allocate a new skb */
- return false;
- }
-
skb = __mptcp_do_alloc_tx_skb(sk, gfp);
if (!skb)
return false;
@@ -1288,7 +1226,6 @@ static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
static bool mptcp_must_reclaim_memory(struct sock *sk, struct sock *ssk)
{
return !ssk->sk_tx_skb_cache &&
- !skb_peek(&mptcp_sk(sk)->skb_tx_cache) &&
tcp_under_memory_pressure(sk);
}
@@ -1299,6 +1236,18 @@ static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk)
return __mptcp_alloc_tx_skb(sk, ssk, sk->sk_allocation);
}
+/* note: this always recompute the csum on the whole skb, even
+ * if we just appended a single frag. More status info needed
+ */
+static void mptcp_update_data_checksum(struct sk_buff *skb, int added)
+{
+ struct mptcp_ext *mpext = mptcp_get_ext(skb);
+ __wsum csum = ~csum_unfold(mpext->csum);
+ int offset = skb->len - added;
+
+ mpext->csum = csum_fold(csum_block_add(csum, skb_checksum(skb, offset, added, 0), offset));
+}
+
static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
struct mptcp_data_frag *dfrag,
struct mptcp_sendmsg_info *info)
@@ -1319,7 +1268,6 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
/* compute send limit */
info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
avail_size = info->size_goal;
- msk->size_goal_cache = info->size_goal;
skb = tcp_write_queue_tail(ssk);
if (skb) {
/* Limit the write to the size available in the
@@ -1393,10 +1341,14 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
if (zero_window_probe) {
mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
mpext->frozen = 1;
- ret = 0;
+ if (READ_ONCE(msk->csum_enabled))
+ mptcp_update_data_checksum(tail, ret);
tcp_push_pending_frames(ssk);
+ return 0;
}
out:
+ if (READ_ONCE(msk->csum_enabled))
+ mptcp_update_data_checksum(tail, ret);
mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
return ret;
}
@@ -1664,7 +1616,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
while (msg_data_left(msg)) {
int total_ts, frag_truesize = 0;
struct mptcp_data_frag *dfrag;
- struct sk_buff_head skbs;
bool dfrag_collapsed;
size_t psize, offset;
@@ -1697,16 +1648,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
psize = pfrag->size - offset;
psize = min_t(size_t, psize, msg_data_left(msg));
total_ts = psize + frag_truesize;
- __skb_queue_head_init(&skbs);
- if (!mptcp_tx_cache_refill(sk, psize, &skbs, &total_ts))
- goto wait_for_memory;
- if (!mptcp_wmem_alloc(sk, total_ts)) {
- __skb_queue_purge(&skbs);
+ if (!mptcp_wmem_alloc(sk, total_ts))
goto wait_for_memory;
- }
- skb_queue_splice_tail(&skbs, &msk->skb_tx_cache);
if (copy_page_from_iter(dfrag->page, offset, psize,
&msg->msg_iter) != psize) {
mptcp_wmem_uncharge(sk, psize + frag_truesize);
@@ -1763,7 +1708,7 @@ static void mptcp_wait_data(struct sock *sk, long *timeo)
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
sk_wait_event(sk, timeo,
- test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait);
+ test_bit(MPTCP_DATA_READY, &msk->flags), &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
remove_wait_queue(sk_sleep(sk), &wait);
@@ -1771,7 +1716,9 @@ static void mptcp_wait_data(struct sock *sk, long *timeo)
static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
struct msghdr *msg,
- size_t len, int flags)
+ size_t len, int flags,
+ struct scm_timestamping_internal *tss,
+ int *cmsg_flags)
{
struct sk_buff *skb, *tmp;
int copied = 0;
@@ -1791,6 +1738,11 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
}
}
+ if (MPTCP_SKB_CB(skb)->has_rxtstamp) {
+ tcp_update_recv_tstamps(skb, tss);
+ *cmsg_flags |= MPTCP_CMSG_TS;
+ }
+
copied += count;
if (count < data_len) {
@@ -1954,7 +1906,9 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
__mptcp_update_rmem(sk);
done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
mptcp_data_unlock(sk);
- tcp_cleanup_rbuf(ssk, moved);
+
+ if (unlikely(ssk->sk_err))
+ __mptcp_error_report(sk);
unlock_sock_fast(ssk, slowpath);
} while (!done);
@@ -1967,7 +1921,6 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
ret |= __mptcp_ofo_queue(msk);
__mptcp_splice_receive_queue(sk);
mptcp_data_unlock(sk);
- mptcp_cleanup_rbuf(msk);
}
if (ret)
mptcp_check_data_fin((struct sock *)msk);
@@ -1978,7 +1931,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- int copied = 0;
+ struct scm_timestamping_internal tss;
+ int copied = 0, cmsg_flags = 0;
int target;
long timeo;
@@ -2000,7 +1954,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
while (copied < len) {
int bytes_read;
- bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags);
+ bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags);
if (unlikely(bytes_read < 0)) {
if (!copied)
copied = bytes_read;
@@ -2076,11 +2030,14 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
*/
if (unlikely(__mptcp_move_skbs(msk)))
set_bit(MPTCP_DATA_READY, &msk->flags);
- } else if (unlikely(!test_bit(MPTCP_DATA_READY, &msk->flags))) {
- /* data to read but mptcp_wait_data() cleared DATA_READY */
- set_bit(MPTCP_DATA_READY, &msk->flags);
}
+
out_err:
+ if (cmsg_flags && copied >= 0) {
+ if (cmsg_flags & MPTCP_CMSG_TS)
+ tcp_recv_timestamp(msg, sk, &tss);
+ }
+
pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d",
msk, test_bit(MPTCP_DATA_READY, &msk->flags),
skb_queue_empty_lockless(&sk->sk_receive_queue), copied);
@@ -2212,9 +2169,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
if (ssk == msk->last_snd)
msk->last_snd = NULL;
- if (ssk == msk->ack_hint)
- msk->ack_hint = NULL;
-
if (ssk == msk->first)
msk->first = NULL;
@@ -2286,13 +2240,14 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
+ bool slow;
- lock_sock(tcp_sk);
+ slow = lock_sock_fast(tcp_sk);
if (tcp_sk->sk_state != TCP_CLOSE) {
tcp_send_active_reset(tcp_sk, GFP_ATOMIC);
tcp_set_state(tcp_sk, TCP_CLOSE);
}
- release_sock(tcp_sk);
+ unlock_sock_fast(tcp_sk, slow);
}
inet_sk_state_store(sk, TCP_CLOSE);
@@ -2337,8 +2292,8 @@ static void __mptcp_retrans(struct sock *sk)
/* limit retransmission to the bytes already sent on some subflows */
info.sent = 0;
- info.limit = dfrag->already_sent;
- while (info.sent < dfrag->already_sent) {
+ info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent;
+ while (info.sent < info.limit) {
if (!mptcp_alloc_tx_skb(sk, ssk))
break;
@@ -2350,9 +2305,11 @@ static void __mptcp_retrans(struct sock *sk)
copied += ret;
info.sent += ret;
}
- if (copied)
+ if (copied) {
+ dfrag->already_sent = max(dfrag->already_sent, info.sent);
tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
info.size_goal);
+ }
mptcp_set_timeout(sk, ssk);
release_sock(ssk);
@@ -2420,17 +2377,15 @@ static int __mptcp_init_sock(struct sock *sk)
INIT_LIST_HEAD(&msk->rtx_queue);
INIT_WORK(&msk->work, mptcp_worker);
__skb_queue_head_init(&msk->receive_queue);
- __skb_queue_head_init(&msk->skb_tx_cache);
msk->out_of_order_queue = RB_ROOT;
msk->first_pending = NULL;
msk->wmem_reserved = 0;
msk->rmem_released = 0;
msk->tx_pending_data = 0;
- msk->size_goal_cache = TCP_BASE_MSS;
- msk->ack_hint = NULL;
msk->first = NULL;
inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
+ WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
mptcp_pm_data_init(msk);
@@ -2482,15 +2437,10 @@ static void __mptcp_clear_xmit(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
struct mptcp_data_frag *dtmp, *dfrag;
- struct sk_buff *skb;
WRITE_ONCE(msk->first_pending, NULL);
list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list)
dfrag_clear(sk, dfrag);
- while ((skb = __skb_dequeue(&msk->skb_tx_cache)) != NULL) {
- sk->sk_forward_alloc += skb->truesize;
- kfree_skb(skb);
- }
}
static void mptcp_cancel_work(struct sock *sk)
@@ -2771,6 +2721,8 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
msk->token = subflow_req->token;
msk->subflow = NULL;
WRITE_ONCE(msk->fully_established, false);
+ if (mp_opt->csum_reqd)
+ WRITE_ONCE(msk->csum_enabled, true);
msk->write_seq = subflow_req->idsn + 1;
msk->snd_nxt = msk->write_seq;
@@ -2944,6 +2896,11 @@ static void mptcp_release_cb(struct sock *sk)
spin_lock_bh(&sk->sk_lock.slock);
}
+ /* be sure to set the current sk state before tacking actions
+ * depending on sk_state
+ */
+ if (test_and_clear_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags))
+ __mptcp_set_connected(sk);
if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags))
__mptcp_clean_una_wakeup(sk);
if (test_and_clear_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->flags))
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 0c6f99c67345..426ed80fe72f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -68,6 +68,8 @@
#define TCPOLEN_MPTCP_FASTCLOSE 12
#define TCPOLEN_MPTCP_RST 4
+#define TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM (TCPOLEN_MPTCP_DSS_CHECKSUM + TCPOLEN_MPTCP_MPC_ACK_DATA)
+
/* MPTCP MP_JOIN flags */
#define MPTCPOPT_BACKUP BIT(0)
#define MPTCPOPT_HMAC_LEN 20
@@ -77,8 +79,9 @@
#define MPTCP_VERSION_MASK (0x0F)
#define MPTCP_CAP_CHECKSUM_REQD BIT(7)
#define MPTCP_CAP_EXTENSIBILITY BIT(6)
+#define MPTCP_CAP_DENY_JOIN_ID0 BIT(5)
#define MPTCP_CAP_HMAC_SHA256 BIT(0)
-#define MPTCP_CAP_FLAG_MASK (0x3F)
+#define MPTCP_CAP_FLAG_MASK (0x1F)
/* MPTCP DSS flags */
#define MPTCP_DSS_DATA_FIN BIT(4)
@@ -109,6 +112,7 @@
#define MPTCP_ERROR_REPORT 8
#define MPTCP_RETRANSMIT 9
#define MPTCP_WORK_SYNC_SETSOCKOPT 10
+#define MPTCP_CONNECTED 11
static inline bool before64(__u64 seq1, __u64 seq2)
{
@@ -124,6 +128,7 @@ struct mptcp_options_received {
u64 data_seq;
u32 subflow_seq;
u16 data_len;
+ __sum16 csum;
u16 mp_capable : 1,
mp_join : 1,
fastclose : 1,
@@ -133,7 +138,9 @@ struct mptcp_options_received {
rm_addr : 1,
mp_prio : 1,
echo : 1,
- backup : 1;
+ csum_reqd : 1,
+ backup : 1,
+ deny_join_id0 : 1;
u32 token;
u32 nonce;
u64 thmac;
@@ -188,6 +195,7 @@ struct mptcp_pm_data {
bool work_pending;
bool accept_addr;
bool accept_subflow;
+ bool remote_deny_join_id0;
u8 add_addr_signaled;
u8 add_addr_accepted;
u8 local_addr_used;
@@ -234,15 +242,13 @@ struct mptcp_sock {
bool snd_data_fin_enable;
bool rcv_fastclose;
bool use_64bit_ack; /* Set when we received a 64-bit DSN */
+ bool csum_enabled;
spinlock_t join_list_lock;
- struct sock *ack_hint;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct rb_root out_of_order_queue;
struct sk_buff_head receive_queue;
- struct sk_buff_head skb_tx_cache; /* this is wmem accounted */
int tx_pending_data;
- int size_goal_cache;
struct list_head conn_list;
struct list_head rtx_queue;
struct mptcp_data_frag *first_pending;
@@ -335,11 +341,20 @@ static inline struct mptcp_data_frag *mptcp_rtx_head(const struct sock *sk)
return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list);
}
+struct csum_pseudo_header {
+ __be64 data_seq;
+ __be32 subflow_seq;
+ __be16 data_len;
+ __sum16 csum;
+};
+
struct mptcp_subflow_request_sock {
struct tcp_request_sock sk;
u16 mp_capable : 1,
mp_join : 1,
- backup : 1;
+ backup : 1,
+ csum_reqd : 1,
+ allow_join_id0 : 1;
u8 local_id;
u8 remote_id;
u64 local_key;
@@ -362,7 +377,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk)
enum mptcp_data_avail {
MPTCP_SUBFLOW_NODATA,
MPTCP_SUBFLOW_DATA_AVAIL,
- MPTCP_SUBFLOW_OOO_DATA
};
struct mptcp_delegated_action {
@@ -387,6 +401,8 @@ struct mptcp_subflow_context {
u32 map_subflow_seq;
u32 ssn_offset;
u32 map_data_len;
+ __wsum map_data_csum;
+ u32 map_csum_len;
u32 request_mptcp : 1, /* send MP_CAPABLE */
request_join : 1, /* send MP_JOIN */
request_bkup : 1,
@@ -396,6 +412,8 @@ struct mptcp_subflow_context {
pm_notified : 1, /* PM hook called for established status */
conn_finished : 1,
map_valid : 1,
+ map_csum_reqd : 1,
+ map_data_fin : 1,
mpc_map : 1,
backup : 1,
send_mp_prio : 1,
@@ -525,6 +543,8 @@ static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *su
int mptcp_is_enabled(struct net *net);
unsigned int mptcp_get_add_addr_timeout(struct net *net);
+int mptcp_is_checksum_enabled(struct net *net);
+int mptcp_allow_join_id0(struct net *net);
void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
struct mptcp_options_received *mp_opt);
bool mptcp_subflow_data_available(struct sock *sk);
@@ -576,10 +596,12 @@ int __init mptcp_proto_v6_init(void);
struct sock *mptcp_sk_clone(const struct sock *sk,
const struct mptcp_options_received *mp_opt,
struct request_sock *req);
-void mptcp_get_options(const struct sk_buff *skb,
+void mptcp_get_options(const struct sock *sk,
+ const struct sk_buff *skb,
struct mptcp_options_received *mp_opt);
void mptcp_finish_connect(struct sock *sk);
+void __mptcp_set_connected(struct sock *sk);
static inline bool mptcp_is_fully_established(struct sock *sk)
{
return inet_sk_state_load(sk) == TCP_ESTABLISHED &&
@@ -594,6 +616,14 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname,
int mptcp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *option);
+u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq);
+static inline u64 mptcp_expand_seq(u64 old_seq, u64 cur_seq, bool use_64bit)
+{
+ if (use_64bit)
+ return cur_seq;
+
+ return __mptcp_expand_seq(old_seq, cur_seq);
+}
void __mptcp_check_push(struct sock *sk, struct sock *ssk);
void __mptcp_data_acked(struct sock *sk);
void __mptcp_error_report(struct sock *sk);
@@ -627,6 +657,8 @@ static inline void mptcp_write_space(struct sock *sk)
void mptcp_destroy_common(struct mptcp_sock *msk);
+#define MPTCP_TOKEN_MAX_RETRIES 4
+
void __init mptcp_token_init(void);
static inline void mptcp_token_init_request(struct request_sock *req)
{
@@ -753,9 +785,6 @@ unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk);
unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk);
unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk);
-int mptcp_setsockopt(struct sock *sk, int level, int optname,
- sockptr_t optval, unsigned int optlen);
-
void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk);
void mptcp_sockopt_sync_all(struct mptcp_sock *msk);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index a79798189599..092d1f635d27 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -140,6 +140,43 @@ static void mptcp_so_incoming_cpu(struct mptcp_sock *msk, int val)
mptcp_sol_socket_sync_intval(msk, SO_INCOMING_CPU, val);
}
+static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optname, int val)
+{
+ sockptr_t optval = KERNEL_SOCKPTR(&val);
+ struct mptcp_subflow_context *subflow;
+ struct sock *sk = (struct sock *)msk;
+ int ret;
+
+ ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname,
+ optval, sizeof(val));
+ if (ret)
+ return ret;
+
+ lock_sock(sk);
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow = lock_sock_fast(ssk);
+
+ switch (optname) {
+ case SO_TIMESTAMP_OLD:
+ case SO_TIMESTAMP_NEW:
+ case SO_TIMESTAMPNS_OLD:
+ case SO_TIMESTAMPNS_NEW:
+ sock_set_timestamp(sk, optname, !!val);
+ break;
+ case SO_TIMESTAMPING_NEW:
+ case SO_TIMESTAMPING_OLD:
+ sock_set_timestamping(sk, optname, val);
+ break;
+ }
+
+ unlock_sock_fast(ssk, slow);
+ }
+
+ release_sock(sk);
+ return 0;
+}
+
static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
sockptr_t optval, unsigned int optlen)
{
@@ -164,6 +201,13 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
case SO_INCOMING_CPU:
mptcp_so_incoming_cpu(msk, val);
return 0;
+ case SO_TIMESTAMP_OLD:
+ case SO_TIMESTAMP_NEW:
+ case SO_TIMESTAMPNS_OLD:
+ case SO_TIMESTAMPNS_NEW:
+ case SO_TIMESTAMPING_OLD:
+ case SO_TIMESTAMPING_NEW:
+ return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val);
}
return -ENOPROTOOPT;
@@ -251,9 +295,23 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
case SO_MARK:
case SO_INCOMING_CPU:
case SO_DEBUG:
+ case SO_TIMESTAMP_OLD:
+ case SO_TIMESTAMP_NEW:
+ case SO_TIMESTAMPNS_OLD:
+ case SO_TIMESTAMPNS_NEW:
+ case SO_TIMESTAMPING_OLD:
+ case SO_TIMESTAMPING_NEW:
return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen);
case SO_LINGER:
return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen);
+ case SO_RCVLOWAT:
+ case SO_RCVTIMEO_OLD:
+ case SO_RCVTIMEO_NEW:
+ case SO_BUSY_POLL:
+ case SO_PREFER_BUSY_POLL:
+ case SO_BUSY_POLL_BUDGET:
+ /* No need to copy: only relevant for msk */
+ return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen);
case SO_NO_CHECK:
case SO_DONTROUTE:
case SO_BROADCAST:
@@ -267,7 +325,24 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
return 0;
}
- return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen);
+ /* SO_OOBINLINE is not supported, let's avoid the related mess
+ * SO_ATTACH_FILTER, SO_ATTACH_BPF, SO_ATTACH_REUSEPORT_CBPF,
+ * SO_DETACH_REUSEPORT_BPF, SO_DETACH_FILTER, SO_LOCK_FILTER,
+ * we must be careful with subflows
+ *
+ * SO_ATTACH_REUSEPORT_EBPF is not supported, at it checks
+ * explicitly the sk_protocol field
+ *
+ * SO_PEEK_OFF is unsupported, as it is for plain TCP
+ * SO_MAX_PACING_RATE is unsupported, we must be careful with subflows
+ * SO_CNX_ADVICE is currently unsupported, could possibly be relevant,
+ * but likely needs careful design
+ *
+ * SO_ZEROCOPY is currently unsupported, TODO in sndmsg
+ * SO_TXTIME is currently unsupported
+ */
+
+ return -EOPNOTSUPP;
}
static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
@@ -299,72 +374,6 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
static bool mptcp_supported_sockopt(int level, int optname)
{
- if (level == SOL_SOCKET) {
- switch (optname) {
- case SO_DEBUG:
- case SO_REUSEPORT:
- case SO_REUSEADDR:
-
- /* the following ones need a better implementation,
- * but are quite common we want to preserve them
- */
- case SO_BINDTODEVICE:
- case SO_SNDBUF:
- case SO_SNDBUFFORCE:
- case SO_RCVBUF:
- case SO_RCVBUFFORCE:
- case SO_KEEPALIVE:
- case SO_PRIORITY:
- case SO_LINGER:
- case SO_TIMESTAMP_OLD:
- case SO_TIMESTAMP_NEW:
- case SO_TIMESTAMPNS_OLD:
- case SO_TIMESTAMPNS_NEW:
- case SO_TIMESTAMPING_OLD:
- case SO_TIMESTAMPING_NEW:
- case SO_RCVLOWAT:
- case SO_RCVTIMEO_OLD:
- case SO_RCVTIMEO_NEW:
- case SO_SNDTIMEO_OLD:
- case SO_SNDTIMEO_NEW:
- case SO_MARK:
- case SO_INCOMING_CPU:
- case SO_BINDTOIFINDEX:
- case SO_BUSY_POLL:
- case SO_PREFER_BUSY_POLL:
- case SO_BUSY_POLL_BUDGET:
-
- /* next ones are no-op for plain TCP */
- case SO_NO_CHECK:
- case SO_DONTROUTE:
- case SO_BROADCAST:
- case SO_BSDCOMPAT:
- case SO_PASSCRED:
- case SO_PASSSEC:
- case SO_RXQ_OVFL:
- case SO_WIFI_STATUS:
- case SO_NOFCS:
- case SO_SELECT_ERR_QUEUE:
- return true;
- }
-
- /* SO_OOBINLINE is not supported, let's avoid the related mess */
- /* SO_ATTACH_FILTER, SO_ATTACH_BPF, SO_ATTACH_REUSEPORT_CBPF,
- * SO_DETACH_REUSEPORT_BPF, SO_DETACH_FILTER, SO_LOCK_FILTER,
- * we must be careful with subflows
- */
- /* SO_ATTACH_REUSEPORT_EBPF is not supported, at it checks
- * explicitly the sk_protocol field
- */
- /* SO_PEEK_OFF is unsupported, as it is for plain TCP */
- /* SO_MAX_PACING_RATE is unsupported, we must be careful with subflows */
- /* SO_CNX_ADVICE is currently unsupported, could possibly be relevant,
- * but likely needs careful design
- */
- /* SO_ZEROCOPY is currently unsupported, TODO in sndmsg */
- /* SO_TXTIME is currently unsupported */
- return false;
- }
if (level == SOL_IP) {
switch (optname) {
/* should work fine */
@@ -574,12 +583,12 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname,
pr_debug("msk=%p", msk);
- if (!mptcp_supported_sockopt(level, optname))
- return -ENOPROTOOPT;
-
if (level == SOL_SOCKET)
return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);
+ if (!mptcp_supported_sockopt(level, optname))
+ return -ENOPROTOOPT;
+
/* @@ the meaning of setsockopt() when the socket is connected and
* there are multiple subflows is not yet defined. It is up to the
* MPTCP-level socket to configure the subflows until the subflow
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index ef3d037f984a..66d0b1893d26 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -108,6 +108,8 @@ static void subflow_init_req(struct request_sock *req, const struct sock *sk_lis
subflow_req->mp_capable = 0;
subflow_req->mp_join = 0;
+ subflow_req->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk_listener));
+ subflow_req->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk_listener));
subflow_req->msk = NULL;
mptcp_token_init_request(req);
}
@@ -150,7 +152,7 @@ static int subflow_check_req(struct request_sock *req,
return -EINVAL;
#endif
- mptcp_get_options(skb, &mp_opt);
+ mptcp_get_options(sk_listener, skb, &mp_opt);
if (mp_opt.mp_capable) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
@@ -162,7 +164,7 @@ static int subflow_check_req(struct request_sock *req,
}
if (mp_opt.mp_capable && listener->request_mptcp) {
- int err, retries = 4;
+ int err, retries = MPTCP_TOKEN_MAX_RETRIES;
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
again:
@@ -247,7 +249,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
int err;
subflow_init_req(req, sk_listener);
- mptcp_get_options(skb, &mp_opt);
+ mptcp_get_options(sk_listener, skb, &mp_opt);
if (mp_opt.mp_capable && mp_opt.mp_join)
return -EINVAL;
@@ -371,6 +373,24 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc
return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport;
}
+void __mptcp_set_connected(struct sock *sk)
+{
+ if (sk->sk_state == TCP_SYN_SENT) {
+ inet_sk_state_store(sk, TCP_ESTABLISHED);
+ sk->sk_state_change(sk);
+ }
+}
+
+static void mptcp_set_connected(struct sock *sk)
+{
+ mptcp_data_lock(sk);
+ if (!sock_owned_by_user(sk))
+ __mptcp_set_connected(sk);
+ else
+ set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags);
+ mptcp_data_unlock(sk);
+}
+
static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -379,10 +399,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->icsk_af_ops->sk_rx_dst_set(sk, skb);
- if (inet_sk_state_load(parent) == TCP_SYN_SENT) {
- inet_sk_state_store(parent, TCP_ESTABLISHED);
- parent->sk_state_change(parent);
- }
/* be sure no special action on any packet other than syn-ack */
if (subflow->conn_finished)
@@ -394,7 +410,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);
- mptcp_get_options(skb, &mp_opt);
+ mptcp_get_options(sk, skb, &mp_opt);
if (subflow->request_mptcp) {
if (!mp_opt.mp_capable) {
MPTCP_INC_STATS(sock_net(sk),
@@ -404,6 +420,10 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
goto fallback;
}
+ if (mp_opt.csum_reqd)
+ WRITE_ONCE(mptcp_sk(parent)->csum_enabled, true);
+ if (mp_opt.deny_join_id0)
+ WRITE_ONCE(mptcp_sk(parent)->pm.remote_deny_join_id0, true);
subflow->mp_capable = 1;
subflow->can_ack = 1;
subflow->remote_key = mp_opt.sndr_key;
@@ -411,6 +431,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->remote_key);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
mptcp_finish_connect(sk);
+ mptcp_set_connected(parent);
} else if (subflow->request_join) {
u8 hmac[SHA256_DIGEST_SIZE];
@@ -430,15 +451,15 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
goto do_reset;
}
+ if (!mptcp_finish_join(sk))
+ goto do_reset;
+
subflow_generate_hmac(subflow->local_key, subflow->remote_key,
subflow->local_nonce,
subflow->remote_nonce,
hmac);
memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN);
- if (!mptcp_finish_join(sk))
- goto do_reset;
-
subflow->mp_join = 1;
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
@@ -451,6 +472,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
} else if (mptcp_check_fallback(sk)) {
fallback:
mptcp_rcv_space_init(mptcp_sk(parent), sk);
+ mptcp_set_connected(parent);
}
return;
@@ -558,6 +580,7 @@ static void mptcp_sock_destruct(struct sock *sk)
static void mptcp_force_close(struct sock *sk)
{
+ /* the msk is not yet exposed to user-space */
inet_sk_state_store(sk, TCP_CLOSE);
sk_common_release(sk);
}
@@ -638,7 +661,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
* reordered MPC will cause fallback, but we don't have other
* options.
*/
- mptcp_get_options(skb, &mp_opt);
+ mptcp_get_options(sk, skb, &mp_opt);
if (!mp_opt.mp_capable) {
fallback = true;
goto create_child;
@@ -648,7 +671,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
if (!new_msk)
fallback = true;
} else if (subflow_req->mp_join) {
- mptcp_get_options(skb, &mp_opt);
+ mptcp_get_options(sk, skb, &mp_opt);
if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) ||
!mptcp_can_accept_new_subflow(subflow_req->msk)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
@@ -775,19 +798,10 @@ enum mapping_status {
MAPPING_DUMMY
};
-static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq)
-{
- if ((u32)seq == (u32)old_seq)
- return old_seq;
-
- /* Assume map covers data not mapped yet. */
- return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32));
-}
-
-static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
+static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
{
- WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
- ssn, subflow->map_subflow_seq, subflow->map_data_len);
+ pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
+ ssn, subflow->map_subflow_seq, subflow->map_data_len);
}
static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb)
@@ -812,22 +826,104 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb)
/* Mapping covers data later in the subflow stream,
* currently unsupported.
*/
- warn_bad_map(subflow, ssn);
+ dbg_bad_map(subflow, ssn);
return false;
}
if (unlikely(!before(ssn, subflow->map_subflow_seq +
subflow->map_data_len))) {
/* Mapping does covers past subflow data, invalid */
- warn_bad_map(subflow, ssn + skb->len);
+ dbg_bad_map(subflow, ssn);
return false;
}
return true;
}
+static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *skb,
+ bool csum_reqd)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ struct csum_pseudo_header header;
+ u32 offset, seq, delta;
+ __wsum csum;
+ int len;
+
+ if (!csum_reqd)
+ return MAPPING_OK;
+
+ /* mapping already validated on previous traversal */
+ if (subflow->map_csum_len == subflow->map_data_len)
+ return MAPPING_OK;
+
+ /* traverse the receive queue, ensuring it contains a full
+ * DSS mapping and accumulating the related csum.
+ * Preserve the accoumlate csum across multiple calls, to compute
+ * the csum only once
+ */
+ delta = subflow->map_data_len - subflow->map_csum_len;
+ for (;;) {
+ seq = tcp_sk(ssk)->copied_seq + subflow->map_csum_len;
+ offset = seq - TCP_SKB_CB(skb)->seq;
+
+ /* if the current skb has not been accounted yet, csum its contents
+ * up to the amount covered by the current DSS
+ */
+ if (offset < skb->len) {
+ __wsum csum;
+
+ len = min(skb->len - offset, delta);
+ csum = skb_checksum(skb, offset, len, 0);
+ subflow->map_data_csum = csum_block_add(subflow->map_data_csum, csum,
+ subflow->map_csum_len);
+
+ delta -= len;
+ subflow->map_csum_len += len;
+ }
+ if (delta == 0)
+ break;
+
+ if (skb_queue_is_last(&ssk->sk_receive_queue, skb)) {
+ /* if this subflow is closed, the partial mapping
+ * will be never completed; flush the pending skbs, so
+ * that subflow_sched_work_if_closed() can kick in
+ */
+ if (unlikely(ssk->sk_state == TCP_CLOSE))
+ while ((skb = skb_peek(&ssk->sk_receive_queue)))
+ sk_eat_skb(ssk, skb);
+
+ /* not enough data to validate the csum */
+ return MAPPING_EMPTY;
+ }
+
+ /* the DSS mapping for next skbs will be validated later,
+ * when a get_mapping_status call will process such skb
+ */
+ skb = skb->next;
+ }
+
+ /* note that 'map_data_len' accounts only for the carried data, does
+ * not include the eventual seq increment due to the data fin,
+ * while the pseudo header requires the original DSS data len,
+ * including that
+ */
+ header.data_seq = cpu_to_be64(subflow->map_seq);
+ header.subflow_seq = htonl(subflow->map_subflow_seq);
+ header.data_len = htons(subflow->map_data_len + subflow->map_data_fin);
+ header.csum = 0;
+
+ csum = csum_partial(&header, sizeof(header), subflow->map_data_csum);
+ if (unlikely(csum_fold(csum))) {
+ MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR);
+ return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY;
+ }
+
+ return MAPPING_OK;
+}
+
static enum mapping_status get_mapping_status(struct sock *ssk,
struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ bool csum_reqd = READ_ONCE(msk->csum_enabled);
struct mptcp_ext *mpext;
struct sk_buff *skb;
u16 data_len;
@@ -907,22 +1003,17 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
data_len--;
}
- if (!mpext->dsn64) {
- map_seq = expand_seq(subflow->map_seq, subflow->map_data_len,
- mpext->data_seq);
- pr_debug("expanded seq=%llu", subflow->map_seq);
- } else {
- map_seq = mpext->data_seq;
- }
+ map_seq = mptcp_expand_seq(READ_ONCE(msk->ack_seq), mpext->data_seq, mpext->dsn64);
WRITE_ONCE(mptcp_sk(subflow->conn)->use_64bit_ack, !!mpext->dsn64);
if (subflow->map_valid) {
/* Allow replacing only with an identical map */
if (subflow->map_seq == map_seq &&
subflow->map_subflow_seq == mpext->subflow_seq &&
- subflow->map_data_len == data_len) {
+ subflow->map_data_len == data_len &&
+ subflow->map_csum_reqd == mpext->csum_reqd) {
skb_ext_del(skb, SKB_EXT_MPTCP);
- return MAPPING_OK;
+ goto validate_csum;
}
/* If this skb data are fully covered by the current mapping,
@@ -934,27 +1025,41 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
}
/* will validate the next map after consuming the current one */
- return MAPPING_OK;
+ goto validate_csum;
}
subflow->map_seq = map_seq;
subflow->map_subflow_seq = mpext->subflow_seq;
subflow->map_data_len = data_len;
subflow->map_valid = 1;
+ subflow->map_data_fin = mpext->data_fin;
subflow->mpc_map = mpext->mpc_map;
- pr_debug("new map seq=%llu subflow_seq=%u data_len=%u",
+ subflow->map_csum_reqd = mpext->csum_reqd;
+ subflow->map_csum_len = 0;
+ subflow->map_data_csum = csum_unfold(mpext->csum);
+
+ /* Cfr RFC 8684 Section 3.3.0 */
+ if (unlikely(subflow->map_csum_reqd != csum_reqd))
+ return MAPPING_INVALID;
+
+ pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
subflow->map_seq, subflow->map_subflow_seq,
- subflow->map_data_len);
+ subflow->map_data_len, subflow->map_csum_reqd,
+ subflow->map_data_csum);
validate_seq:
/* we revalidate valid mapping on new skb, because we must ensure
* the current skb is completely covered by the available mapping
*/
- if (!validate_mapping(ssk, skb))
+ if (!validate_mapping(ssk, skb)) {
+ MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSTCPMISMATCH);
return MAPPING_INVALID;
+ }
skb_ext_del(skb, SKB_EXT_MPTCP);
- return MAPPING_OK;
+
+validate_csum:
+ return validate_data_csum(ssk, skb, csum_reqd);
}
static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
@@ -1000,7 +1105,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
struct sk_buff *skb;
if (!skb_peek(&ssk->sk_receive_queue))
- subflow->data_avail = 0;
+ WRITE_ONCE(subflow->data_avail, 0);
if (subflow->data_avail)
return true;
@@ -1039,18 +1144,13 @@ static bool subflow_check_data_avail(struct sock *ssk)
ack_seq = mptcp_subflow_get_mapped_dsn(subflow);
pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
ack_seq);
- if (ack_seq == old_ack) {
- subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
- break;
- } else if (after64(ack_seq, old_ack)) {
- subflow->data_avail = MPTCP_SUBFLOW_OOO_DATA;
- break;
+ if (unlikely(before64(ack_seq, old_ack))) {
+ mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
+ continue;
}
- /* only accept in-sequence mapping. Old values are spurious
- * retransmission
- */
- mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
+ WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL);
+ break;
}
return true;
@@ -1065,12 +1165,11 @@ fallback:
* subflow_error_report() will introduce the appropriate barriers
*/
ssk->sk_err = EBADMSG;
- ssk->sk_error_report(ssk);
tcp_set_state(ssk, TCP_CLOSE);
subflow->reset_transient = 0;
subflow->reset_reason = MPTCP_RST_EMPTCP;
tcp_send_active_reset(ssk, GFP_ATOMIC);
- subflow->data_avail = 0;
+ WRITE_ONCE(subflow->data_avail, 0);
return false;
}
@@ -1080,7 +1179,7 @@ fallback:
subflow->map_seq = READ_ONCE(msk->ack_seq);
subflow->map_data_len = skb->len;
subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;
- subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
+ WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL);
return true;
}
@@ -1092,7 +1191,7 @@ bool mptcp_subflow_data_available(struct sock *sk)
if (subflow->map_valid &&
mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) {
subflow->map_valid = 0;
- subflow->data_avail = 0;
+ WRITE_ONCE(subflow->data_avail, 0);
pr_debug("Done with mapping: seq=%u data_len=%u",
subflow->map_subflow_seq,
@@ -1120,41 +1219,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space)
*full_space = tcp_full_space(sk);
}
-static void subflow_data_ready(struct sock *sk)
-{
- struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- u16 state = 1 << inet_sk_state_load(sk);
- struct sock *parent = subflow->conn;
- struct mptcp_sock *msk;
-
- msk = mptcp_sk(parent);
- if (state & TCPF_LISTEN) {
- /* MPJ subflow are removed from accept queue before reaching here,
- * avoid stray wakeups
- */
- if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue))
- return;
-
- set_bit(MPTCP_DATA_READY, &msk->flags);
- parent->sk_data_ready(parent);
- return;
- }
-
- WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable &&
- !subflow->mp_join && !(state & TCPF_CLOSE));
-
- if (mptcp_subflow_data_available(sk))
- mptcp_data_ready(parent, sk);
-}
-
-static void subflow_write_space(struct sock *ssk)
-{
- struct sock *sk = mptcp_subflow_ctx(ssk)->conn;
-
- mptcp_propagate_sndbuf(sk, ssk);
- mptcp_write_space(sk);
-}
-
void __mptcp_error_report(struct sock *sk)
{
struct mptcp_subflow_context *subflow;
@@ -1178,7 +1242,7 @@ void __mptcp_error_report(struct sock *sk)
/* This barrier is coupled with smp_rmb() in mptcp_poll() */
smp_wmb();
- sk->sk_error_report(sk);
+ sk_error_report(sk);
break;
}
}
@@ -1195,6 +1259,43 @@ static void subflow_error_report(struct sock *ssk)
mptcp_data_unlock(sk);
}
+static void subflow_data_ready(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ u16 state = 1 << inet_sk_state_load(sk);
+ struct sock *parent = subflow->conn;
+ struct mptcp_sock *msk;
+
+ msk = mptcp_sk(parent);
+ if (state & TCPF_LISTEN) {
+ /* MPJ subflow are removed from accept queue before reaching here,
+ * avoid stray wakeups
+ */
+ if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue))
+ return;
+
+ set_bit(MPTCP_DATA_READY, &msk->flags);
+ parent->sk_data_ready(parent);
+ return;
+ }
+
+ WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable &&
+ !subflow->mp_join && !(state & TCPF_CLOSE));
+
+ if (mptcp_subflow_data_available(sk))
+ mptcp_data_ready(parent, sk);
+ else if (unlikely(sk->sk_err))
+ subflow_error_report(sk);
+}
+
+static void subflow_write_space(struct sock *ssk)
+{
+ struct sock *sk = mptcp_subflow_ctx(ssk)->conn;
+
+ mptcp_propagate_sndbuf(sk, ssk);
+ mptcp_write_space(sk);
+}
+
static struct inet_connection_sock_af_ops *
subflow_default_af_ops(struct sock *sk)
{
@@ -1493,10 +1594,7 @@ static void subflow_state_change(struct sock *sk)
mptcp_rcv_space_init(mptcp_sk(parent), sk);
pr_fallback(mptcp_sk(parent));
subflow->conn_finished = 1;
- if (inet_sk_state_load(parent) == TCP_SYN_SENT) {
- inet_sk_state_store(parent, TCP_ESTABLISHED);
- parent->sk_state_change(parent);
- }
+ mptcp_set_connected(parent);
}
/* as recvmsg() does not acquire the subflow socket for ssk selection
@@ -1505,6 +1603,8 @@ static void subflow_state_change(struct sock *sk)
*/
if (mptcp_subflow_data_available(sk))
mptcp_data_ready(parent, sk);
+ else if (unlikely(sk->sk_err))
+ subflow_error_report(sk);
subflow_sched_work_if_closed(mptcp_sk(parent), sk);
diff --git a/net/mptcp/token.c b/net/mptcp/token.c
index 8f0270a780ce..a98e554b034f 100644
--- a/net/mptcp/token.c
+++ b/net/mptcp/token.c
@@ -33,7 +33,6 @@
#include <net/mptcp.h>
#include "protocol.h"
-#define TOKEN_MAX_RETRIES 4
#define TOKEN_MAX_CHAIN_LEN 4
struct token_bucket {
@@ -153,12 +152,9 @@ int mptcp_token_new_connect(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
- int retries = TOKEN_MAX_RETRIES;
+ int retries = MPTCP_TOKEN_MAX_RETRIES;
struct token_bucket *bucket;
- pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n",
- sk, subflow->local_key, subflow->token, subflow->idsn);
-
again:
mptcp_crypto_key_gen_sha(&subflow->local_key, &subflow->token,
&subflow->idsn);
@@ -172,6 +168,9 @@ again:
goto again;
}
+ pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n",
+ sk, subflow->local_key, subflow->token, subflow->idsn);
+
WRITE_ONCE(msk->token, subflow->token);
__sk_nulls_add_node_rcu((struct sock *)msk, &bucket->msk_chain);
bucket->chain_len++;
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-06 08:31:50 +0300