aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-07-02 11:18:28 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-07-02 11:18:28 -0700
commit4e33d7d47943aaa84a5904472cf2f9c6d6b0a6ca (patch)
tree6eb46696758bee8da0e8b830db4bc6915128bf60 /net
parentLinux 4.18-rc3 (diff)
parentMerge branch 'qed-fixes' (diff)
downloadlinux-dev-4e33d7d47943aaa84a5904472cf2f9c6d6b0a6ca.tar.xz
linux-dev-4e33d7d47943aaa84a5904472cf2f9c6d6b0a6ca.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller: 1) Verify netlink attributes properly in nf_queue, from Eric Dumazet. 2) Need to bump memory lock rlimit for test_sockmap bpf test, from Yonghong Song. 3) Fix VLAN handling in lan78xx driver, from Dave Stevenson. 4) Fix uninitialized read in nf_log, from Jann Horn. 5) Fix raw command length parsing in mlx5, from Alex Vesker. 6) Cleanup loopback RDS connections upon netns deletion, from Sowmini Varadhan. 7) Fix regressions in FIB rule matching during create, from Jason A. Donenfeld and Roopa Prabhu. 8) Fix mpls ether type detection in nfp, from Pieter Jansen van Vuuren. 9) More bpfilter build fixes/adjustments from Masahiro Yamada. 10) Fix XDP_{TX,REDIRECT} flushing in various drivers, from Jesper Dangaard Brouer. 11) fib_tests.sh file permissions were broken, from Shuah Khan. 12) Make sure BH/preemption is disabled in data path of mac80211, from Denis Kenzior. 13) Don't ignore nla_parse_nested() return values in nl80211, from Johannes berg. 14) Properly account sock objects ot kmemcg, from Shakeel Butt. 15) Adjustments to setting bpf program permissions to read-only, from Daniel Borkmann. 16) TCP Fast Open key endianness was broken, it always took on the host endiannness. Whoops. Explicitly make it little endian. From Yuching Cheng. 17) Fix prefix route setting for link local addresses in ipv6, from David Ahern. 18) Potential Spectre v1 in zatm driver, from Gustavo A. R. Silva. 19) Various bpf sockmap fixes, from John Fastabend. 20) Use after free for GRO with ESP, from Sabrina Dubroca. 21) Passing bogus flags to crypto_alloc_shash() in ipv6 SR code, from Eric Biggers. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits) qede: Adverstise software timestamp caps when PHC is not available. qed: Fix use of incorrect size in memcpy call. qed: Fix setting of incorrect eswitch mode. qed: Limit msix vectors in kdump kernel to the minimum required count. ipvlan: call dev_change_flags when ipvlan mode is reset ipv6: sr: fix passing wrong flags to crypto_alloc_shash() net: fix use-after-free in GRO with ESP tcp: prevent bogus FRTO undos with non-SACK flows bpf: sockhash, add release routine bpf: sockhash fix omitted bucket lock in sock_close bpf: sockmap, fix smap_list_map_remove when psock is in many maps bpf: sockmap, fix crash when ipv6 sock is added net: fib_rules: bring back rule_exists to match rule during add hv_netvsc: split sub-channel setup into async and sync net: use dev_change_tx_queue_len() for SIOCSIFTXQLEN atm: zatm: Fix potential Spectre v1 s390/qeth: consistently re-enable device features s390/qeth: don't clobber buffer on async TX completion s390/qeth: avoid using is_multicast_ether_addr_64bits on (u8 *)[6] s390/qeth: fix race when setting MAC address ...
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c2
-rw-r--r--net/Makefile4
-rw-r--r--net/bpfilter/Kconfig2
-rw-r--r--net/bpfilter/Makefile17
-rw-r--r--net/bpfilter/bpfilter_kern.c11
-rw-r--r--net/bpfilter/bpfilter_umh_blob.S7
-rw-r--r--net/core/dev_ioctl.c11
-rw-r--r--net/core/fib_rules.c80
-rw-r--r--net/core/filter.c86
-rw-r--r--net/core/skbuff.c3
-rw-r--r--net/core/sock.c7
-rw-r--r--net/ipv4/fou.c4
-rw-r--r--net/ipv4/gre_offload.c2
-rw-r--r--net/ipv4/sysctl_net_ipv4.c18
-rw-r--r--net/ipv4/tcp_input.c13
-rw-r--r--net/ipv4/udp_offload.c2
-rw-r--r--net/ipv6/addrconf.c9
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c6
-rw-r--r--net/ipv6/seg6_hmac.c2
-rw-r--r--net/mac80211/tx.c2
-rw-r--r--net/netfilter/nf_conncount.c52
-rw-r--r--net/netfilter/nf_conntrack_helper.c5
-rw-r--r--net/netfilter/nf_log.c13
-rw-r--r--net/netfilter/nfnetlink_queue.c3
-rw-r--r--net/rds/connection.c11
-rw-r--r--net/rds/loop.c56
-rw-r--r--net/rds/loop.h2
-rw-r--r--net/smc/af_smc.c96
-rw-r--r--net/smc/smc.h8
-rw-r--r--net/strparser/strparser.c17
-rw-r--r--net/wireless/nl80211.c35
31 files changed, 415 insertions, 171 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 73a65789271b..8ccee3d01822 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -693,7 +693,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
diff --git a/net/Makefile b/net/Makefile
index 13ec0d5415c7..bdaf53925acd 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -20,11 +20,7 @@ obj-$(CONFIG_TLS) += tls/
obj-$(CONFIG_XFRM) += xfrm/
obj-$(CONFIG_UNIX) += unix/
obj-$(CONFIG_NET) += ipv6/
-ifneq ($(CC_CAN_LINK),y)
-$(warning CC cannot link executables. Skipping bpfilter.)
-else
obj-$(CONFIG_BPFILTER) += bpfilter/
-endif
obj-$(CONFIG_PACKET) += packet/
obj-$(CONFIG_NET_KEY) += key/
obj-$(CONFIG_BRIDGE) += bridge/
diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
index a948b072c28f..76deb6615883 100644
--- a/net/bpfilter/Kconfig
+++ b/net/bpfilter/Kconfig
@@ -1,6 +1,5 @@
menuconfig BPFILTER
bool "BPF based packet filtering framework (BPFILTER)"
- default n
depends on NET && BPF && INET
help
This builds experimental bpfilter framework that is aiming to
@@ -9,6 +8,7 @@ menuconfig BPFILTER
if BPFILTER
config BPFILTER_UMH
tristate "bpfilter kernel module with user mode helper"
+ depends on $(success,$(srctree)/scripts/cc-can-link.sh $(CC))
default m
help
This builds bpfilter kernel module with embedded user mode helper
diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile
index 051dc18b8ccb..39c6980b5d99 100644
--- a/net/bpfilter/Makefile
+++ b/net/bpfilter/Makefile
@@ -15,20 +15,7 @@ ifeq ($(CONFIG_BPFILTER_UMH), y)
HOSTLDFLAGS += -static
endif
-# a bit of elf magic to convert bpfilter_umh binary into a binary blob
-# inside bpfilter_umh.o elf file referenced by
-# _binary_net_bpfilter_bpfilter_umh_start symbol
-# which bpfilter_kern.c passes further into umh blob loader at run-time
-quiet_cmd_copy_umh = GEN $@
- cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \
- $(OBJCOPY) -I binary \
- `LC_ALL=C $(OBJDUMP) -f net/bpfilter/bpfilter_umh \
- |awk -F' |,' '/file format/{print "-O",$$NF} \
- /^architecture:/{print "-B",$$2}'` \
- --rename-section .data=.init.rodata $< $@
-
-$(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh
- $(call cmd,copy_umh)
+$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh
obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o
-bpfilter-objs += bpfilter_kern.o bpfilter_umh.o
+bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
index 09522573f611..f0fc182d3db7 100644
--- a/net/bpfilter/bpfilter_kern.c
+++ b/net/bpfilter/bpfilter_kern.c
@@ -10,11 +10,8 @@
#include <linux/file.h>
#include "msgfmt.h"
-#define UMH_start _binary_net_bpfilter_bpfilter_umh_start
-#define UMH_end _binary_net_bpfilter_bpfilter_umh_end
-
-extern char UMH_start;
-extern char UMH_end;
+extern char bpfilter_umh_start;
+extern char bpfilter_umh_end;
static struct umh_info info;
/* since ip_getsockopt() can run in parallel, serialize access to umh */
@@ -93,7 +90,9 @@ static int __init load_umh(void)
int err;
/* fork usermode process */
- err = fork_usermode_blob(&UMH_start, &UMH_end - &UMH_start, &info);
+ err = fork_usermode_blob(&bpfilter_umh_start,
+ &bpfilter_umh_end - &bpfilter_umh_start,
+ &info);
if (err)
return err;
pr_info("Loaded bpfilter_umh pid %d\n", info.pid);
diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S
new file mode 100644
index 000000000000..40311d10d2f2
--- /dev/null
+++ b/net/bpfilter/bpfilter_umh_blob.S
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+ .section .init.rodata, "a"
+ .global bpfilter_umh_start
+bpfilter_umh_start:
+ .incbin "net/bpfilter/bpfilter_umh"
+ .global bpfilter_umh_end
+bpfilter_umh_end:
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index a04e1e88bf3a..50537ff961a7 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -285,16 +285,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
if (ifr->ifr_qlen < 0)
return -EINVAL;
if (dev->tx_queue_len ^ ifr->ifr_qlen) {
- unsigned int orig_len = dev->tx_queue_len;
-
- dev->tx_queue_len = ifr->ifr_qlen;
- err = call_netdevice_notifiers(
- NETDEV_CHANGE_TX_QUEUE_LEN, dev);
- err = notifier_to_errno(err);
- if (err) {
- dev->tx_queue_len = orig_len;
+ err = dev_change_tx_queue_len(dev, ifr->ifr_qlen);
+ if (err)
return err;
- }
}
return 0;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 126ffc5bc630..f64aa13811ea 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -416,6 +416,14 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
if (rule->mark && r->mark != rule->mark)
continue;
+ if (rule->suppress_ifgroup != -1 &&
+ r->suppress_ifgroup != rule->suppress_ifgroup)
+ continue;
+
+ if (rule->suppress_prefixlen != -1 &&
+ r->suppress_prefixlen != rule->suppress_prefixlen)
+ continue;
+
if (rule->mark_mask && r->mark_mask != rule->mark_mask)
continue;
@@ -436,6 +444,9 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
if (rule->ip_proto && r->ip_proto != rule->ip_proto)
continue;
+ if (rule->proto && r->proto != rule->proto)
+ continue;
+
if (fib_rule_port_range_set(&rule->sport_range) &&
!fib_rule_port_range_compare(&r->sport_range,
&rule->sport_range))
@@ -645,6 +656,73 @@ errout:
return err;
}
+static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
+ struct nlattr **tb, struct fib_rule *rule)
+{
+ struct fib_rule *r;
+
+ list_for_each_entry(r, &ops->rules_list, list) {
+ if (r->action != rule->action)
+ continue;
+
+ if (r->table != rule->table)
+ continue;
+
+ if (r->pref != rule->pref)
+ continue;
+
+ if (memcmp(r->iifname, rule->iifname, IFNAMSIZ))
+ continue;
+
+ if (memcmp(r->oifname, rule->oifname, IFNAMSIZ))
+ continue;
+
+ if (r->mark != rule->mark)
+ continue;
+
+ if (r->suppress_ifgroup != rule->suppress_ifgroup)
+ continue;
+
+ if (r->suppress_prefixlen != rule->suppress_prefixlen)
+ continue;
+
+ if (r->mark_mask != rule->mark_mask)
+ continue;
+
+ if (r->tun_id != rule->tun_id)
+ continue;
+
+ if (r->fr_net != rule->fr_net)
+ continue;
+
+ if (r->l3mdev != rule->l3mdev)
+ continue;
+
+ if (!uid_eq(r->uid_range.start, rule->uid_range.start) ||
+ !uid_eq(r->uid_range.end, rule->uid_range.end))
+ continue;
+
+ if (r->ip_proto != rule->ip_proto)
+ continue;
+
+ if (r->proto != rule->proto)
+ continue;
+
+ if (!fib_rule_port_range_compare(&r->sport_range,
+ &rule->sport_range))
+ continue;
+
+ if (!fib_rule_port_range_compare(&r->dport_range,
+ &rule->dport_range))
+ continue;
+
+ if (!ops->compare(r, frh, tb))
+ continue;
+ return 1;
+ }
+ return 0;
+}
+
int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -679,7 +757,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
goto errout;
if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
- rule_find(ops, frh, tb, rule, user_priority)) {
+ rule_exists(ops, frh, tb, rule)) {
err = -EEXIST;
goto errout_free;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index e7f12e9f598c..0ca6907d7efe 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4073,8 +4073,9 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
memcpy(params->smac, dev->dev_addr, ETH_ALEN);
params->h_vlan_TCI = 0;
params->h_vlan_proto = 0;
+ params->ifindex = dev->ifindex;
- return dev->ifindex;
+ return 0;
}
#endif
@@ -4098,7 +4099,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
/* verify forwarding is enabled on this interface */
in_dev = __in_dev_get_rcu(dev);
if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
- return 0;
+ return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
fl4.flowi4_iif = 1;
@@ -4123,7 +4124,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
tb = fib_get_table(net, tbid);
if (unlikely(!tb))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
} else {
@@ -4135,8 +4136,20 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
}
- if (err || res.type != RTN_UNICAST)
- return 0;
+ if (err) {
+ /* map fib lookup errors to RTN_ type */
+ if (err == -EINVAL)
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ if (err == -EHOSTUNREACH)
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ if (err == -EACCES)
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
+
+ if (res.type != RTN_UNICAST)
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
if (res.fi->fib_nhs > 1)
fib_select_path(net, &res, &fl4, NULL);
@@ -4144,19 +4157,16 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
if (check_mtu) {
mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
if (params->tot_len > mtu)
- return 0;
+ return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
nh = &res.fi->fib_nh[res.nh_sel];
/* do not handle lwt encaps right now */
if (nh->nh_lwtstate)
- return 0;
+ return BPF_FIB_LKUP_RET_UNSUPP_LWT;
dev = nh->nh_dev;
- if (unlikely(!dev))
- return 0;
-
if (nh->nh_gw)
params->ipv4_dst = nh->nh_gw;
@@ -4166,10 +4176,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
* rcu_read_lock_bh is not needed here
*/
neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
- if (neigh)
- return bpf_fib_set_fwd_params(params, neigh, dev);
+ if (!neigh)
+ return BPF_FIB_LKUP_RET_NO_NEIGH;
- return 0;
+ return bpf_fib_set_fwd_params(params, neigh, dev);
}
#endif
@@ -4190,7 +4200,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
/* link local addresses are never forwarded */
if (rt6_need_strict(dst) || rt6_need_strict(src))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
dev = dev_get_by_index_rcu(net, params->ifindex);
if (unlikely(!dev))
@@ -4198,7 +4208,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
idev = __in6_dev_get_safely(dev);
if (unlikely(!idev || !net->ipv6.devconf_all->forwarding))
- return 0;
+ return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
fl6.flowi6_iif = 1;
@@ -4225,7 +4235,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
tb = ipv6_stub->fib6_get_table(net, tbid);
if (unlikely(!tb))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
} else {
@@ -4238,11 +4248,23 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
}
if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
- return 0;
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+
+ if (unlikely(f6i->fib6_flags & RTF_REJECT)) {
+ switch (f6i->fib6_type) {
+ case RTN_BLACKHOLE:
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ case RTN_UNREACHABLE:
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ case RTN_PROHIBIT:
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+ default:
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
+ }
- if (unlikely(f6i->fib6_flags & RTF_REJECT ||
- f6i->fib6_type != RTN_UNICAST))
- return 0;
+ if (f6i->fib6_type != RTN_UNICAST)
+ return BPF_FIB_LKUP_RET_NOT_FWDED;
if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
@@ -4252,11 +4274,11 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
if (check_mtu) {
mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src);
if (params->tot_len > mtu)
- return 0;
+ return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
if (f6i->fib6_nh.nh_lwtstate)
- return 0;
+ return BPF_FIB_LKUP_RET_UNSUPP_LWT;
if (f6i->fib6_flags & RTF_GATEWAY)
*dst = f6i->fib6_nh.nh_gw;
@@ -4270,10 +4292,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
*/
neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
ndisc_hashfn, dst, dev);
- if (neigh)
- return bpf_fib_set_fwd_params(params, neigh, dev);
+ if (!neigh)
+ return BPF_FIB_LKUP_RET_NO_NEIGH;
- return 0;
+ return bpf_fib_set_fwd_params(params, neigh, dev);
}
#endif
@@ -4315,7 +4337,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
struct bpf_fib_lookup *, params, int, plen, u32, flags)
{
struct net *net = dev_net(skb->dev);
- int index = -EAFNOSUPPORT;
+ int rc = -EAFNOSUPPORT;
if (plen < sizeof(*params))
return -EINVAL;
@@ -4326,25 +4348,25 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
switch (params->family) {
#if IS_ENABLED(CONFIG_INET)
case AF_INET:
- index = bpf_ipv4_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv4_fib_lookup(net, params, flags, false);
break;
#endif
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
- index = bpf_ipv6_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv6_fib_lookup(net, params, flags, false);
break;
#endif
}
- if (index > 0) {
+ if (!rc) {
struct net_device *dev;
- dev = dev_get_by_index_rcu(net, index);
+ dev = dev_get_by_index_rcu(net, params->ifindex);
if (!is_skb_forwardable(dev, skb))
- index = 0;
+ rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
- return index;
+ return rc;
}
static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c642304f178c..eba8dae22c25 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5276,8 +5276,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
if (npages >= 1 << order) {
page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
__GFP_COMP |
- __GFP_NOWARN |
- __GFP_NORETRY,
+ __GFP_NOWARN,
order);
if (page)
goto fill_page;
diff --git a/net/core/sock.c b/net/core/sock.c
index bcc41829a16d..9e8f65585b81 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3243,7 +3243,8 @@ static int req_prot_init(const struct proto *prot)
rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
rsk_prot->obj_size, 0,
- prot->slab_flags, NULL);
+ SLAB_ACCOUNT | prot->slab_flags,
+ NULL);
if (!rsk_prot->slab) {
pr_crit("%s: Can't create request sock SLAB cache!\n",
@@ -3258,7 +3259,8 @@ int proto_register(struct proto *prot, int alloc_slab)
if (alloc_slab) {
prot->slab = kmem_cache_create_usercopy(prot->name,
prot->obj_size, 0,
- SLAB_HWCACHE_ALIGN | prot->slab_flags,
+ SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT |
+ prot->slab_flags,
prot->useroffset, prot->usersize,
NULL);
@@ -3281,6 +3283,7 @@ int proto_register(struct proto *prot, int alloc_slab)
kmem_cache_create(prot->twsk_prot->twsk_slab_name,
prot->twsk_prot->twsk_obj_size,
0,
+ SLAB_ACCOUNT |
prot->slab_flags,
NULL);
if (prot->twsk_prot->twsk_slab == NULL)
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 1540db65241a..c9ec1603666b 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -448,9 +448,7 @@ next_proto:
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
- skb_gro_remcsum_cleanup(skb, &grc);
- skb->remcsum_offload = 0;
+ skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
return pp;
}
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 1859c473b21a..6a7d980105f6 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -223,7 +223,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d06247ba08b2..af0a857d8352 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -265,8 +265,9 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
ipv4.sysctl_tcp_fastopen);
struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
struct tcp_fastopen_context *ctxt;
- int ret;
u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
+ __le32 key[4];
+ int ret, i;
tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
if (!tbl.data)
@@ -275,11 +276,14 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
rcu_read_lock();
ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
if (ctxt)
- memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
+ memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
else
- memset(user_key, 0, sizeof(user_key));
+ memset(key, 0, sizeof(key));
rcu_read_unlock();
+ for (i = 0; i < ARRAY_SIZE(key); i++)
+ user_key[i] = le32_to_cpu(key[i]);
+
snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
user_key[0], user_key[1], user_key[2], user_key[3]);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
@@ -290,13 +294,17 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
ret = -EINVAL;
goto bad_key;
}
- tcp_fastopen_reset_cipher(net, NULL, user_key,
+
+ for (i = 0; i < ARRAY_SIZE(user_key); i++)
+ key[i] = cpu_to_le32(user_key[i]);
+
+ tcp_fastopen_reset_cipher(net, NULL, key,
TCP_FASTOPEN_KEY_LENGTH);
}
bad_key:
pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n",
- user_key[0], user_key[1], user_key[2], user_key[3],
+ user_key[0], user_key[1], user_key[2], user_key[3],
(char *)tbl.data, ret);
kfree(tbl.data);
return ret;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 355d3dffd021..8e5522c6833a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -265,7 +265,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
* it is probably a retransmit.
*/
if (tp->ecn_flags & TCP_ECN_SEEN)
- tcp_enter_quickack_mode(sk, 1);
+ tcp_enter_quickack_mode(sk, 2);
break;
case INET_ECN_CE:
if (tcp_ca_needs_ecn(sk))
@@ -273,7 +273,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
/* Better not delay acks, sender can have a very low cwnd */
- tcp_enter_quickack_mode(sk, 1);
+ tcp_enter_quickack_mode(sk, 2);
tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
}
tp->ecn_flags |= TCP_ECN_SEEN;
@@ -3181,6 +3181,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
if (tcp_is_reno(tp)) {
tcp_remove_reno_sacks(sk, pkts_acked);
+
+ /* If any of the cumulatively ACKed segments was
+ * retransmitted, non-SACK case cannot confirm that
+ * progress was due to original transmission due to
+ * lack of TCPCB_SACKED_ACKED bits even if some of
+ * the packets may have been never retransmitted.
+ */
+ if (flag & FLAG_RETRANS_DATA_ACKED)
+ flag &= ~FLAG_ORIG_SACK_ACKED;
} else {
int delta;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 92dc9e5a7ff3..69c54540d5b4 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -394,7 +394,7 @@ unflush:
out_unlock:
rcu_read_unlock();
out:
- NAPI_GRO_CB(skb)->flush |= flush;
+ skb_gro_flush_final(skb, pp, flush);
return pp;
}
EXPORT_SYMBOL(udp_gro_receive);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c134286d6a41..91580c62bb86 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4528,6 +4528,7 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
unsigned long expires, u32 flags)
{
struct fib6_info *f6i;
+ u32 prio;
f6i = addrconf_get_prefix_route(&ifp->addr,
ifp->prefix_len,
@@ -4536,13 +4537,15 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
if (!f6i)
return -ENOENT;
- if (f6i->fib6_metric != ifp->rt_priority) {
+ prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF;
+ if (f6i->fib6_metric != prio) {
+ /* delete old one */
+ ip6_del_rt(dev_net(ifp->idev->dev), f6i);
+
/* add new one */
addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
ifp->rt_priority, ifp->idev->dev,
expires, flags, GFP_KERNEL);
- /* delete old one */
- ip6_del_rt(dev_net(ifp->idev->dev), f6i);
} else {
if (!expires)
fib6_clean_expires(f6i);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 5e0332014c17..a452d99c9f52 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -107,7 +107,7 @@ static int nf_ct_frag6_sysctl_register(struct net *net)
if (hdr == NULL)
goto err_reg;
- net->nf_frag.sysctl.frags_hdr = hdr;
+ net->nf_frag_frags_hdr = hdr;
return 0;
err_reg:
@@ -121,8 +121,8 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
{
struct ctl_table *table;
- table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg;
- unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr);
+ table = net->nf_frag_frags_hdr->ctl_table_arg;
+ unregister_net_sysctl_table(net->nf_frag_frags_hdr);
if (!net_eq(net, &init_net))
kfree(table);
}
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 33fb35cbfac1..558fe8cc6d43 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -373,7 +373,7 @@ static int seg6_hmac_init_algo(void)
return -ENOMEM;
for_each_possible_cpu(cpu) {
- tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL);
+ tfm = crypto_alloc_shash(algo->name, 0, 0);
if (IS_ERR(tfm))
return PTR_ERR(tfm);
p_tfm = per_cpu_ptr(algo->tfms, cpu);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 44b5dfe8727d..fa1f1e63a264 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -4845,7 +4845,9 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
skb_reset_network_header(skb);
skb_reset_mac_header(skb);
+ local_bh_disable();
__ieee80211_subif_start_xmit(skb, skb->dev, flags);
+ local_bh_enable();
return 0;
}
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index d8383609fe28..510039862aa9 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -47,6 +47,8 @@ struct nf_conncount_tuple {
struct hlist_node node;
struct nf_conntrack_tuple tuple;
struct nf_conntrack_zone zone;
+ int cpu;
+ u32 jiffies32;
};
struct nf_conncount_rb {
@@ -91,11 +93,42 @@ bool nf_conncount_add(struct hlist_head *head,
return false;
conn->tuple = *tuple;
conn->zone = *zone;
+ conn->cpu = raw_smp_processor_id();
+ conn->jiffies32 = (u32)jiffies;
hlist_add_head(&conn->node, head);
return true;
}
EXPORT_SYMBOL_GPL(nf_conncount_add);
+static const struct nf_conntrack_tuple_hash *
+find_or_evict(struct net *net, struct nf_conncount_tuple *conn)
+{
+ const struct nf_conntrack_tuple_hash *found;
+ unsigned long a, b;
+ int cpu = raw_smp_processor_id();
+ __s32 age;
+
+ found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
+ if (found)
+ return found;
+ b = conn->jiffies32;
+ a = (u32)jiffies;
+
+ /* conn might have been added just before by another cpu and
+ * might still be unconfirmed. In this case, nf_conntrack_find()
+ * returns no result. Thus only evict if this cpu added the
+ * stale entry or if the entry is older than two jiffies.
+ */
+ age = a - b;
+ if (conn->cpu == cpu || age >= 2) {
+ hlist_del(&conn->node);
+ kmem_cache_free(conncount_conn_cachep, conn);
+ return ERR_PTR(-ENOENT);
+ }
+
+ return ERR_PTR(-EAGAIN);
+}
+
unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
const struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_zone *zone,
@@ -103,18 +136,27 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
{
const struct nf_conntrack_tuple_hash *found;
struct nf_conncount_tuple *conn;
- struct hlist_node *n;
struct nf_conn *found_ct;
+ struct hlist_node *n;
unsigned int length = 0;
*addit = tuple ? true : false;
/* check the saved connections */
hlist_for_each_entry_safe(conn, n, head, node) {
- found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
- if (found == NULL) {
- hlist_del(&conn->node);
- kmem_cache_free(conncount_conn_cachep, conn);
+ found = find_or_evict(net, conn);
+ if (IS_ERR(found)) {
+ /* Not found, but might be about to be confirmed */
+ if (PTR_ERR(found) == -EAGAIN) {
+ length++;
+ if (!tuple)
+ continue;
+
+ if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
+ nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
+ nf_ct_zone_id(zone, zone->dir))
+ *addit = false;
+ }
continue;
}
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 551a1eddf0fa..a75b11c39312 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -465,6 +465,11 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
nf_ct_expect_iterate_destroy(expect_iter_me, NULL);
nf_ct_iterate_destroy(unhelp, me);
+
+ /* Maybe someone has gotten the helper already when unhelp above.
+ * So need to wait it.
+ */
+ synchronize_rcu();
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 426457047578..a61d6df6e5f6 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -424,6 +424,10 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
if (write) {
struct ctl_table tmp = *table;
+ /* proc_dostring() can append to existing strings, so we need to
+ * initialize it as an empty string.
+ */
+ buf[0] = '\0';
tmp.data = buf;
r = proc_dostring(&tmp, write, buffer, lenp, ppos);
if (r)
@@ -442,14 +446,17 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
rcu_assign_pointer(net->nf.nf_loggers[tindex], logger);
mutex_unlock(&nf_log_mutex);
} else {
+ struct ctl_table tmp = *table;
+
+ tmp.data = buf;
mutex_lock(&nf_log_mutex);
logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
if (!logger)
- table->data = "NONE";
+ strlcpy(buf, "NONE", sizeof(buf));
else
- table->data = logger->name;
- r = proc_dostring(table, write, buffer, lenp, ppos);
+ strlcpy(buf, logger->name, sizeof(buf));
mutex_unlock(&nf_log_mutex);
+ r = proc_dostring(&tmp, write, buffer, lenp, ppos);
}
return r;
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 4ccd2988f9db..ea4ba551abb2 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1243,6 +1243,9 @@ static int nfqnl_recv_unsupp(struct net *net, struct sock *ctnl,
static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
[NFQA_CFG_CMD] = { .len = sizeof(struct nfqnl_msg_config_cmd) },
[NFQA_CFG_PARAMS] = { .len = sizeof(struct nfqnl_msg_config_params) },
+ [NFQA_CFG_QUEUE_MAXLEN] = { .type = NLA_U32 },
+ [NFQA_CFG_MASK] = { .type = NLA_U32 },
+ [NFQA_CFG_FLAGS] = { .type = NLA_U32 },
};
static const struct nf_queue_handler nfqh = {
diff --git a/net/rds/connection.c b/net/rds/connection.c
index abef75da89a7..cfb05953b0e5 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -659,11 +659,19 @@ static void rds_conn_info(struct socket *sock, unsigned int len,
int rds_conn_init(void)
{
+ int ret;
+
+ ret = rds_loop_net_init(); /* register pernet callback */
+ if (ret)
+ return ret;
+
rds_conn_slab = kmem_cache_create("rds_connection",
sizeof(struct rds_connection),
0, 0, NULL);
- if (!rds_conn_slab)
+ if (!rds_conn_slab) {
+ rds_loop_net_exit();
return -ENOMEM;
+ }
rds_info_register_func(RDS_INFO_CONNECTIONS, rds_conn_info);
rds_info_register_func(RDS_INFO_SEND_MESSAGES,
@@ -676,6 +684,7 @@ int rds_conn_init(void)
void rds_conn_exit(void)
{
+ rds_loop_net_exit(); /* unregister pernet callback */
rds_loop_exit();
WARN_ON(!hlist_empty(rds_conn_hash));
diff --git a/net/rds/loop.c b/net/rds/loop.c
index dac6218a460e..feea1f96ee2a 100644
--- a/net/rds/loop.c
+++ b/net/rds/loop.c
@@ -33,6 +33,8 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/in.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
#include "rds_single_path.h"
#include "rds.h"
@@ -40,6 +42,17 @@
static DEFINE_SPINLOCK(loop_conns_lock);
static LIST_HEAD(loop_conns);
+static atomic_t rds_loop_unloading = ATOMIC_INIT(0);
+
+static void rds_loop_set_unloading(void)
+{
+ atomic_set(&rds_loop_unloading, 1);
+}
+
+static bool rds_loop_is_unloading(struct rds_connection *conn)
+{
+ return atomic_read(&rds_loop_unloading) != 0;
+}
/*
* This 'loopback' transport is a special case for flows that originate
@@ -165,6 +178,8 @@ void rds_loop_exit(void)
struct rds_loop_connection *lc, *_lc;
LIST_HEAD(tmp_list);
+ rds_loop_set_unloading();
+ synchronize_rcu();
/* avoid calling conn_destroy with irqs off */
spin_lock_irq(&loop_conns_lock);
list_splice(&loop_conns, &tmp_list);
@@ -177,6 +192,46 @@ void rds_loop_exit(void)
}
}
+static void rds_loop_kill_conns(struct net *net)
+{
+ struct rds_loop_connection *lc, *_lc;
+ LIST_HEAD(tmp_list);
+
+ spin_lock_irq(&loop_conns_lock);
+ list_for_each_entry_safe(lc, _lc, &loop_conns, loop_node) {
+ struct net *c_net = read_pnet(&lc->conn->c_net);
+
+ if (net != c_net)
+ continue;
+ list_move_tail(&lc->loop_node, &tmp_list);
+ }
+ spin_unlock_irq(&loop_conns_lock);
+
+ list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) {
+ WARN_ON(lc->conn->c_passive);
+ rds_conn_destroy(lc->conn);
+ }
+}
+
+static void __net_exit rds_loop_exit_net(struct net *net)
+{
+ rds_loop_kill_conns(net);
+}
+
+static struct pernet_operations rds_loop_net_ops = {
+ .exit = rds_loop_exit_net,
+};
+
+int rds_loop_net_init(void)
+{
+ return register_pernet_device(&rds_loop_net_ops);
+}
+
+void rds_loop_net_exit(void)
+{
+ unregister_pernet_device(&rds_loop_net_ops);
+}
+
/*
* This is missing .xmit_* because loop doesn't go through generic
* rds_send_xmit() and doesn't call rds_recv_incoming(). .listen_stop and
@@ -194,4 +249,5 @@ struct rds_transport rds_loop_transport = {
.inc_free = rds_loop_inc_free,
.t_name = "loopback",
.t_type = RDS_TRANS_LOOP,
+ .t_unloading = rds_loop_is_unloading,
};
diff --git a/net/rds/loop.h b/net/rds/loop.h
index 469fa4b2da4f..bbc8cdd030df 100644
--- a/net/rds/loop.h
+++ b/net/rds/loop.h
@@ -5,6 +5,8 @@
/* loop.c */
extern struct rds_transport rds_loop_transport;
+int rds_loop_net_init(void);
+void rds_loop_net_exit(void);
void rds_loop_exit(void);
#endif
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 973b4471b532..e017b6a4452b 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -45,6 +45,7 @@ static DEFINE_MUTEX(smc_create_lgr_pending); /* serialize link group
*/
static void smc_tcp_listen_work(struct work_struct *);
+static void smc_connect_work(struct work_struct *);
static void smc_set_keepalive(struct sock *sk, int val)
{
@@ -122,6 +123,12 @@ static int smc_release(struct socket *sock)
goto out;
smc = smc_sk(sk);
+
+ /* cleanup for a dangling non-blocking connect */
+ flush_work(&smc->connect_work);
+ kfree(smc->connect_info);
+ smc->connect_info = NULL;
+
if (sk->sk_state == SMC_LISTEN)
/* smc_close_non_accepted() is called and acquires
* sock lock for child sockets again
@@ -186,6 +193,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
sk->sk_protocol = protocol;
smc = smc_sk(sk);
INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
+ INIT_WORK(&smc->connect_work, smc_connect_work);
INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
INIT_LIST_HEAD(&smc->accept_q);
spin_lock_init(&smc->accept_q_lock);
@@ -576,6 +584,35 @@ static int __smc_connect(struct smc_sock *smc)
return 0;
}
+static void smc_connect_work(struct work_struct *work)
+{
+ struct smc_sock *smc = container_of(work, struct smc_sock,
+ connect_work);
+ int rc;
+
+ lock_sock(&smc->sk);
+ rc = kernel_connect(smc->clcsock, &smc->connect_info->addr,
+ smc->connect_info->alen, smc->connect_info->flags);
+ if (smc->clcsock->sk->sk_err) {
+ smc->sk.sk_err = smc->clcsock->sk->sk_err;
+ goto out;
+ }
+ if (rc < 0) {
+ smc->sk.sk_err = -rc;
+ goto out;
+ }
+
+ rc = __smc_connect(smc);
+ if (rc < 0)
+ smc->sk.sk_err = -rc;
+
+out:
+ smc->sk.sk_state_change(&smc->sk);
+ kfree(smc->connect_info);
+ smc->connect_info = NULL;
+ release_sock(&smc->sk);
+}
+
static int smc_connect(struct socket *sock, struct sockaddr *addr,
int alen, int flags)
{
@@ -605,15 +642,32 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
smc_copy_sock_settings_to_clc(smc);
tcp_sk(smc->clcsock->sk)->syn_smc = 1;
- rc = kernel_connect(smc->clcsock, addr, alen, flags);
- if (rc)
- goto out;
+ if (flags & O_NONBLOCK) {
+ if (smc->connect_info) {
+ rc = -EALREADY;
+ goto out;
+ }
+ smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL);
+ if (!smc->connect_info) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ smc->connect_info->alen = alen;
+ smc->connect_info->flags = flags ^ O_NONBLOCK;
+ memcpy(&smc->connect_info->addr, addr, alen);
+ schedule_work(&smc->connect_work);
+ rc = -EINPROGRESS;
+ } else {
+ rc = kernel_connect(smc->clcsock, addr, alen, flags);
+ if (rc)
+ goto out;
- rc = __smc_connect(smc);
- if (rc < 0)
- goto out;
- else
- rc = 0; /* success cases including fallback */
+ rc = __smc_connect(smc);
+ if (rc < 0)
+ goto out;
+ else
+ rc = 0; /* success cases including fallback */
+ }
out:
release_sock(sk);
@@ -1279,40 +1333,18 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
struct sock *sk = sock->sk;
__poll_t mask = 0;
struct smc_sock *smc;
- int rc;
if (!sk)
return EPOLLNVAL;
smc = smc_sk(sock->sk);
- sock_hold(sk);
- lock_sock(sk);
if ((sk->sk_state == SMC_INIT) || smc->use_fallback) {
/* delegate to CLC child sock */
- release_sock(sk);
mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
- lock_sock(sk);
sk->sk_err = smc->clcsock->sk->sk_err;
- if (sk->sk_err) {
+ if (sk->sk_err)
mask |= EPOLLERR;
- } else {
- /* if non-blocking connect finished ... */
- if (sk->sk_state == SMC_INIT &&
- mask & EPOLLOUT &&
- smc->clcsock->sk->sk_state != TCP_CLOSE) {
- rc = __smc_connect(smc);
- if (rc < 0)
- mask |= EPOLLERR;
- /* success cases including fallback */
- mask |= EPOLLOUT | EPOLLWRNORM;
- }
- }
} else {
- if (sk->sk_state != SMC_CLOSED) {
- release_sock(sk);
- sock_poll_wait(file, sk_sleep(sk), wait);
- lock_sock(sk);
- }
if (sk->sk_err)
mask |= EPOLLERR;
if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
@@ -1340,8 +1372,6 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
mask |= EPOLLPRI;
}
- release_sock(sk);
- sock_put(sk);
return mask;
}
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 51ae1f10d81a..d7ca26570482 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -187,11 +187,19 @@ struct smc_connection {
struct work_struct close_work; /* peer sent some closing */
};
+struct smc_connect_info {
+ int flags;
+ int alen;
+ struct sockaddr addr;
+};
+
struct smc_sock { /* smc sock container */
struct sock sk;
struct socket *clcsock; /* internal tcp socket */
struct smc_connection conn; /* smc connection */
struct smc_sock *listen_smc; /* listen parent */
+ struct smc_connect_info *connect_info; /* connect address & flags */
+ struct work_struct connect_work; /* handle non-blocking connect*/
struct work_struct tcp_listen_work;/* handle tcp socket accepts */
struct work_struct smc_listen_work;/* prepare new accept socket */
struct list_head accept_q; /* sockets to be accepted */
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 373836615c57..625acb27efcc 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -35,7 +35,6 @@ struct _strp_msg {
*/
struct strp_msg strp;
int accum_len;
- int early_eaten;
};
static inline struct _strp_msg *_strp_msg(struct sk_buff *skb)
@@ -115,20 +114,6 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
head = strp->skb_head;
if (head) {
/* Message already in progress */
-
- stm = _strp_msg(head);
- if (unlikely(stm->early_eaten)) {
- /* Already some number of bytes on the receive sock
- * data saved in skb_head, just indicate they
- * are consumed.
- */
- eaten = orig_len <= stm->early_eaten ?
- orig_len : stm->early_eaten;
- stm->early_eaten -= eaten;
-
- return eaten;
- }
-
if (unlikely(orig_offset)) {
/* Getting data with a non-zero offset when a message is
* in progress is not expected. If it does happen, we
@@ -297,9 +282,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
}
stm->accum_len += cand_len;
+ eaten += cand_len;
strp->need_bytes = stm->strp.full_len -
stm->accum_len;
- stm->early_eaten = cand_len;
STRP_STATS_ADD(strp->stats.bytes, cand_len);
desc->count = 0; /* Stop reading socket */
break;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index c7bbe5f0aae8..4eece06be1e7 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6231,7 +6231,7 @@ do { \
nl80211_check_s32);
/*
* Check HT operation mode based on
- * IEEE 802.11 2012 8.4.2.59 HT Operation element.
+ * IEEE 802.11-2016 9.4.2.57 HT Operation element.
*/
if (tb[NL80211_MESHCONF_HT_OPMODE]) {
ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]);
@@ -6241,22 +6241,9 @@ do { \
IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
return -EINVAL;
- if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) &&
- (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
- return -EINVAL;
+ /* NON_HT_STA bit is reserved, but some programs set it */
+ ht_opmode &= ~IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT;
- switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) {
- case IEEE80211_HT_OP_MODE_PROTECTION_NONE:
- case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ:
- if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)
- return -EINVAL;
- break;
- case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER:
- case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED:
- if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
- return -EINVAL;
- break;
- }
cfg->ht_opmode = ht_opmode;
mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1));
}
@@ -10962,9 +10949,12 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
rem) {
u8 *mask_pat;
- nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
- nl80211_packet_pattern_policy,
- info->extack);
+ err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+ nl80211_packet_pattern_policy,
+ info->extack);
+ if (err)
+ goto error;
+
err = -EINVAL;
if (!pat_tb[NL80211_PKTPAT_MASK] ||
!pat_tb[NL80211_PKTPAT_PATTERN])
@@ -11213,8 +11203,11 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
rem) {
u8 *mask_pat;
- nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
- nl80211_packet_pattern_policy, NULL);
+ err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+ nl80211_packet_pattern_policy, NULL);
+ if (err)
+ return err;
+
if (!pat_tb[NL80211_PKTPAT_MASK] ||
!pat_tb[NL80211_PKTPAT_PATTERN])
return -EINVAL;