summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/dev.c18
-rw-r--r--net/core/ethtool.c86
-rw-r--r--net/core/fib_rules.c2
-rw-r--r--net/core/flow_dissector.c48
-rw-r--r--net/core/neighbour.c39
-rw-r--r--net/core/net_namespace.c4
-rw-r--r--net/core/netclassid_cgroup.c47
-rw-r--r--net/core/netpoll.c6
-rw-r--r--net/core/pktgen.c11
-rw-r--r--net/core/rtnetlink.c23
-rw-r--r--net/core/skbuff.c19
-rw-r--r--net/core/sock.c13
-rw-r--r--net/core/stream.c16
-rw-r--r--net/core/sysctl_net_core.c73
-rw-r--r--net/core/utils.c20
16 files changed, 320 insertions, 107 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 146502f310ce..619c63a74594 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -96,7 +96,7 @@ int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
if (error)
goto out_err;
- if (sk->sk_receive_queue.prev != skb)
+ if (READ_ONCE(sk->sk_receive_queue.prev) != skb)
goto out;
/* Socket shut down? */
diff --git a/net/core/dev.c b/net/core/dev.c
index 8e187f90c85d..842654302110 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2997,7 +2997,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de
}
skb = next;
- if (netif_xmit_stopped(txq) && skb) {
+ if (netif_tx_queue_stopped(txq) && skb) {
rc = NETDEV_TX_BUSY;
break;
}
@@ -4828,7 +4828,6 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
skb_reset_mac_header(skb);
skb_gro_reset_offset(skb);
- eth = skb_gro_header_fast(skb, 0);
if (unlikely(skb_gro_header_hard(skb, hlen))) {
eth = skb_gro_header_slow(skb, hlen, 0);
if (unlikely(!eth)) {
@@ -4838,6 +4837,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
return NULL;
}
} else {
+ eth = (const struct ethhdr *)skb->data;
gro_pull_from_frag0(skb, hlen);
NAPI_GRO_CB(skb)->frag0 += hlen;
NAPI_GRO_CB(skb)->frag0_len -= hlen;
@@ -5083,7 +5083,10 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
goto out;
/* Note: ndo_busy_poll method is optional in linux-4.5 */
- busy_poll = napi->dev->netdev_ops->ndo_busy_poll;
+ if (napi->dev->netdev_ops)
+ busy_poll = napi->dev->netdev_ops->ndo_busy_poll;
+ else
+ busy_poll = NULL;
do {
rc = 0;
@@ -6581,7 +6584,8 @@ static int __dev_set_mtu(struct net_device *dev, int new_mtu)
if (ops->ndo_change_mtu)
return ops->ndo_change_mtu(dev, new_mtu);
- dev->mtu = new_mtu;
+ /* Pairs with all the lockless reads of dev->mtu in the stack */
+ WRITE_ONCE(dev->mtu, new_mtu);
return 0;
}
@@ -7350,6 +7354,8 @@ int register_netdevice(struct net_device *dev)
ret = notifier_to_errno(ret);
if (ret) {
rollback_registered(dev);
+ rcu_barrier();
+
dev->reg_state = NETREG_UNREGISTERED;
}
/*
@@ -7499,7 +7505,7 @@ static void netdev_wait_allrefs(struct net_device *dev)
refcnt = netdev_refcnt_read(dev);
- if (time_after(jiffies, warning_time + 10 * HZ)) {
+ if (refcnt && time_after(jiffies, warning_time + 10 * HZ)) {
pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
dev->name, refcnt);
warning_time = jiffies;
@@ -8293,6 +8299,8 @@ static void __net_exit default_device_exit(struct net *net)
/* Push remaining network devices to init_net */
snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
+ if (__dev_get_by_name(&init_net, fb_name))
+ snprintf(fb_name, IFNAMSIZ, "dev%%d");
err = dev_change_net_namespace(dev, &init_net, fb_name);
if (err) {
pr_emerg("%s: failed to move %s to init_net: %d\n",
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index a8a9938aeceb..47d2d6e2b780 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -514,6 +514,8 @@ convert_link_ksettings_to_legacy_settings(
= link_ksettings->base.eth_tp_mdix;
legacy_settings->eth_tp_mdix_ctrl
= link_ksettings->base.eth_tp_mdix_ctrl;
+ legacy_settings->transceiver
+ = link_ksettings->base.transceiver;
return retval;
}
@@ -878,8 +880,13 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev,
if (rc >= 0)
info.n_priv_flags = rc;
}
- if (ops->get_regs_len)
- info.regdump_len = ops->get_regs_len(dev);
+ if (ops->get_regs_len) {
+ int ret = ops->get_regs_len(dev);
+
+ if (ret > 0)
+ info.regdump_len = ret;
+ }
+
if (ops->get_eeprom_len)
info.eedump_len = ops->get_eeprom_len(dev);
@@ -1380,6 +1387,9 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
return -EFAULT;
reglen = ops->get_regs_len(dev);
+ if (reglen <= 0)
+ return reglen;
+
if (regs.len > reglen)
regs.len = reglen;
@@ -1390,13 +1400,16 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
return -ENOMEM;
}
+ if (regs.len < reglen)
+ reglen = regs.len;
+
ops->get_regs(dev, &regs, regbuf);
ret = -EFAULT;
if (copy_to_user(useraddr, &regs, sizeof(regs)))
goto out;
useraddr += offsetof(struct ethtool_regs, data);
- if (regbuf && copy_to_user(useraddr, regbuf, regs.len))
+ if (copy_to_user(useraddr, regbuf, reglen))
goto out;
ret = 0;
@@ -1427,11 +1440,13 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr)
static int ethtool_get_wol(struct net_device *dev, char __user *useraddr)
{
- struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
+ struct ethtool_wolinfo wol;
if (!dev->ethtool_ops->get_wol)
return -EOPNOTSUPP;
+ memset(&wol, 0, sizeof(struct ethtool_wolinfo));
+ wol.cmd = ETHTOOL_GWOL;
dev->ethtool_ops->get_wol(dev, &wol);
if (copy_to_user(useraddr, &wol, sizeof(wol)))
@@ -1801,17 +1816,22 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
gstrings.len = ret;
- data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER);
- if (!data)
- return -ENOMEM;
+ if (gstrings.len) {
+ data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER);
+ if (!data)
+ return -ENOMEM;
- __ethtool_get_strings(dev, gstrings.string_set, data);
+ __ethtool_get_strings(dev, gstrings.string_set, data);
+ } else {
+ data = NULL;
+ }
ret = -EFAULT;
if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
goto out;
useraddr += sizeof(gstrings);
- if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN))
+ if (gstrings.len &&
+ copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN))
goto out;
ret = 0;
@@ -1899,17 +1919,21 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
return -EFAULT;
stats.n_stats = n_stats;
- data = kmalloc(n_stats * sizeof(u64), GFP_USER);
- if (!data)
- return -ENOMEM;
+ if (n_stats) {
+ data = kmalloc(n_stats * sizeof(u64), GFP_USER);
+ if (!data)
+ return -ENOMEM;
- ops->get_ethtool_stats(dev, &stats, data);
+ ops->get_ethtool_stats(dev, &stats, data);
+ } else {
+ data = NULL;
+ }
ret = -EFAULT;
if (copy_to_user(useraddr, &stats, sizeof(stats)))
goto out;
useraddr += sizeof(stats);
- if (copy_to_user(useraddr, data, stats.n_stats * sizeof(u64)))
+ if (n_stats && copy_to_user(useraddr, data, n_stats * sizeof(u64)))
goto out;
ret = 0;
@@ -1938,19 +1962,23 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
return -EFAULT;
stats.n_stats = n_stats;
- data = kmalloc_array(n_stats, sizeof(u64), GFP_USER);
- if (!data)
- return -ENOMEM;
+ if (n_stats) {
+ data = kmalloc_array(n_stats, sizeof(u64), GFP_USER);
+ if (!data)
+ return -ENOMEM;
- mutex_lock(&phydev->lock);
- phydev->drv->get_stats(phydev, &stats, data);
- mutex_unlock(&phydev->lock);
+ mutex_lock(&phydev->lock);
+ phydev->drv->get_stats(phydev, &stats, data);
+ mutex_unlock(&phydev->lock);
+ } else {
+ data = NULL;
+ }
ret = -EFAULT;
if (copy_to_user(useraddr, &stats, sizeof(stats)))
goto out;
useraddr += sizeof(stats);
- if (copy_to_user(useraddr, data, stats.n_stats * sizeof(u64)))
+ if (n_stats && copy_to_user(useraddr, data, n_stats * sizeof(u64)))
goto out;
ret = 0;
@@ -2306,9 +2334,10 @@ out:
return ret;
}
-static int ethtool_get_per_queue_coalesce(struct net_device *dev,
- void __user *useraddr,
- struct ethtool_per_queue_op *per_queue_opt)
+static noinline_for_stack int
+ethtool_get_per_queue_coalesce(struct net_device *dev,
+ void __user *useraddr,
+ struct ethtool_per_queue_op *per_queue_opt)
{
u32 bit;
int ret;
@@ -2338,9 +2367,10 @@ static int ethtool_get_per_queue_coalesce(struct net_device *dev,
return 0;
}
-static int ethtool_set_per_queue_coalesce(struct net_device *dev,
- void __user *useraddr,
- struct ethtool_per_queue_op *per_queue_opt)
+static noinline_for_stack int
+ethtool_set_per_queue_coalesce(struct net_device *dev,
+ void __user *useraddr,
+ struct ethtool_per_queue_op *per_queue_opt)
{
u32 bit;
int i, ret = 0;
@@ -2397,7 +2427,7 @@ roll_back:
return ret;
}
-static int ethtool_set_per_queue(struct net_device *dev,
+static int noinline_for_stack ethtool_set_per_queue(struct net_device *dev,
void __user *useraddr, u32 sub_cmd)
{
struct ethtool_per_queue_op per_queue_opt;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index be4629c344a6..9f172906cc88 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -640,7 +640,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
frh = nlmsg_data(nlh);
frh->family = ops->family;
- frh->table = rule->table;
+ frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT;
if (nla_put_u32(skb, FRA_TABLE, rule->table))
goto nla_put_failure;
if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index ab7c50026cae..26b0f70d2f1c 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -563,45 +563,34 @@ out_bad:
}
EXPORT_SYMBOL(__skb_flow_dissect);
-static u32 hashrnd __read_mostly;
+static siphash_key_t hashrnd __read_mostly;
static __always_inline void __flow_hash_secret_init(void)
{
net_get_random_once(&hashrnd, sizeof(hashrnd));
}
-static __always_inline u32 __flow_hash_words(const u32 *words, u32 length,
- u32 keyval)
+static const void *flow_keys_hash_start(const struct flow_keys *flow)
{
- return jhash2(words, length, keyval);
-}
-
-static inline const u32 *flow_keys_hash_start(const struct flow_keys *flow)
-{
- const void *p = flow;
-
- BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32));
- return (const u32 *)(p + FLOW_KEYS_HASH_OFFSET);
+ BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT);
+ return &flow->FLOW_KEYS_HASH_START_FIELD;
}
static inline size_t flow_keys_hash_length(const struct flow_keys *flow)
{
- size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs);
- BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32));
- BUILD_BUG_ON(offsetof(typeof(*flow), addrs) !=
- sizeof(*flow) - sizeof(flow->addrs));
+ size_t len = offsetof(typeof(*flow), addrs) - FLOW_KEYS_HASH_OFFSET;
switch (flow->control.addr_type) {
case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
- diff -= sizeof(flow->addrs.v4addrs);
+ len += sizeof(flow->addrs.v4addrs);
break;
case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
- diff -= sizeof(flow->addrs.v6addrs);
+ len += sizeof(flow->addrs.v6addrs);
break;
case FLOW_DISSECTOR_KEY_TIPC_ADDRS:
- diff -= sizeof(flow->addrs.tipcaddrs);
+ len += sizeof(flow->addrs.tipcaddrs);
break;
}
- return (sizeof(*flow) - diff) / sizeof(u32);
+ return len;
}
__be32 flow_get_u32_src(const struct flow_keys *flow)
@@ -667,14 +656,15 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys)
}
}
-static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
+static inline u32 __flow_hash_from_keys(struct flow_keys *keys,
+ const siphash_key_t *keyval)
{
u32 hash;
__flow_hash_consistentify(keys);
- hash = __flow_hash_words(flow_keys_hash_start(keys),
- flow_keys_hash_length(keys), keyval);
+ hash = siphash(flow_keys_hash_start(keys),
+ flow_keys_hash_length(keys), keyval);
if (!hash)
hash = 1;
@@ -684,12 +674,13 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
u32 flow_hash_from_keys(struct flow_keys *keys)
{
__flow_hash_secret_init();
- return __flow_hash_from_keys(keys, hashrnd);
+ return __flow_hash_from_keys(keys, &hashrnd);
}
EXPORT_SYMBOL(flow_hash_from_keys);
static inline u32 ___skb_get_hash(const struct sk_buff *skb,
- struct flow_keys *keys, u32 keyval)
+ struct flow_keys *keys,
+ const siphash_key_t *keyval)
{
skb_flow_dissect_flow_keys(skb, keys,
FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
@@ -737,7 +728,7 @@ u32 __skb_get_hash_symmetric(struct sk_buff *skb)
NULL, 0, 0, 0,
FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
- return __flow_hash_from_keys(&keys, hashrnd);
+ return __flow_hash_from_keys(&keys, &hashrnd);
}
EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric);
@@ -757,13 +748,14 @@ void __skb_get_hash(struct sk_buff *skb)
__flow_hash_secret_init();
- hash = ___skb_get_hash(skb, &keys, hashrnd);
+ hash = ___skb_get_hash(skb, &keys, &hashrnd);
__skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys));
}
EXPORT_SYMBOL(__skb_get_hash);
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
+__u32 skb_get_hash_perturb(const struct sk_buff *skb,
+ const siphash_key_t *perturb)
{
struct flow_keys keys;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8eb1916b742c..6578d1f8e6c4 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -18,6 +18,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/slab.h>
+#include <linux/kmemleak.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/module.h>
@@ -30,6 +31,7 @@
#include <linux/times.h>
#include <net/net_namespace.h>
#include <net/neighbour.h>
+#include <net/arp.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/netevent.h>
@@ -324,12 +326,14 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift)
ret = kmalloc(sizeof(*ret), GFP_ATOMIC);
if (!ret)
return NULL;
- if (size <= PAGE_SIZE)
+ if (size <= PAGE_SIZE) {
buckets = kzalloc(size, GFP_ATOMIC);
- else
+ } else {
buckets = (struct neighbour __rcu **)
__get_free_pages(GFP_ATOMIC | __GFP_ZERO,
get_order(size));
+ kmemleak_alloc(buckets, size, 1, GFP_ATOMIC);
+ }
if (!buckets) {
kfree(ret);
return NULL;
@@ -349,10 +353,12 @@ static void neigh_hash_free_rcu(struct rcu_head *head)
size_t size = (1 << nht->hash_shift) * sizeof(struct neighbour *);
struct neighbour __rcu **buckets = nht->hash_buckets;
- if (size <= PAGE_SIZE)
+ if (size <= PAGE_SIZE) {
kfree(buckets);
- else
+ } else {
+ kmemleak_free(buckets);
free_pages((unsigned long)buckets, get_order(size));
+ }
kfree(nht);
}
@@ -981,6 +987,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
atomic_set(&neigh->probes,
NEIGH_VAR(neigh->parms, UCAST_PROBES));
+ neigh_del_timer(neigh);
neigh->nud_state = NUD_INCOMPLETE;
neigh->updated = now;
next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
@@ -997,6 +1004,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
}
} else if (neigh->nud_state & NUD_STALE) {
neigh_dbg(2, "neigh %p is delayed\n", neigh);
+ neigh_del_timer(neigh);
neigh->nud_state = NUD_DELAY;
neigh->updated = jiffies;
neigh_add_timer(neigh, jiffies +
@@ -1050,7 +1058,7 @@ static void neigh_update_hhs(struct neighbour *neigh)
if (update) {
hh = &neigh->hh;
- if (hh->hh_len) {
+ if (READ_ONCE(hh->hh_len)) {
write_seqlock_bh(&hh->hh_lock);
update(hh, neigh->dev, neigh->ha);
write_sequnlock_bh(&hh->hh_lock);
@@ -1311,7 +1319,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
struct net_device *dev = neigh->dev;
unsigned int seq;
- if (dev->header_ops->cache && !neigh->hh.hh_len)
+ if (dev->header_ops->cache && !READ_ONCE(neigh->hh.hh_len))
neigh_hh_init(neigh);
do {
@@ -1826,8 +1834,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
goto nla_put_failure;
{
unsigned long now = jiffies;
- unsigned int flush_delta = now - tbl->last_flush;
- unsigned int rand_delta = now - tbl->last_rand;
+ long flush_delta = now - tbl->last_flush;
+ long rand_delta = now - tbl->last_rand;
struct neigh_hash_table *nht;
struct ndt_config ndc = {
.ndtc_key_len = tbl->key_len,
@@ -2489,7 +2497,13 @@ int neigh_xmit(int index, struct net_device *dev,
if (!tbl)
goto out;
rcu_read_lock_bh();
- neigh = __neigh_lookup_noref(tbl, addr, dev);
+ if (index == NEIGH_ARP_TABLE) {
+ u32 key = *((u32 *)addr);
+
+ neigh = __ipv4_neigh_lookup_noref(dev, key);
+ } else {
+ neigh = __neigh_lookup_noref(tbl, addr, dev);
+ }
if (!neigh)
neigh = __neigh_create(tbl, addr, dev, false);
err = PTR_ERR(neigh);
@@ -2697,6 +2711,7 @@ static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos)
}
void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags)
+ __acquires(tbl->lock)
__acquires(rcu_bh)
{
struct neigh_seq_state *state = seq->private;
@@ -2707,6 +2722,7 @@ void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl
rcu_read_lock_bh();
state->nht = rcu_dereference_bh(tbl->nht);
+ read_lock(&tbl->lock);
return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN;
}
@@ -2740,8 +2756,13 @@ out:
EXPORT_SYMBOL(neigh_seq_next);
void neigh_seq_stop(struct seq_file *seq, void *v)
+ __releases(tbl->lock)
__releases(rcu_bh)
{
+ struct neigh_seq_state *state = seq->private;
+ struct neigh_table *tbl = state->tbl;
+
+ read_unlock(&tbl->lock);
rcu_read_unlock_bh();
}
EXPORT_SYMBOL(neigh_seq_stop);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 04fd04ccaa04..7630fa80db92 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -282,6 +282,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
atomic_set(&net->count, 1);
atomic_set(&net->passive, 1);
+ get_random_bytes(&net->hash_mix, sizeof(u32));
net->dev_base_seq = 1;
net->user_ns = user_ns;
idr_init(&net->netns_ids);
@@ -801,7 +802,8 @@ static int __init net_ns_init(void)
mutex_unlock(&net_mutex);
- register_pernet_subsys(&net_ns_ops);
+ if (register_pernet_subsys(&net_ns_ops))
+ panic("Could not register network namespace subsystems");
rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL, NULL);
rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid,
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 2e4eef71471d..db65b0cdfc4c 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -55,30 +55,60 @@ static void cgrp_css_free(struct cgroup_subsys_state *css)
kfree(css_cls_state(css));
}
+/*
+ * To avoid freezing of sockets creation for tasks with big number of threads
+ * and opened sockets lets release file_lock every 1000 iterated descriptors.
+ * New sockets will already have been created with new classid.
+ */
+
+struct update_classid_context {
+ u32 classid;
+ unsigned int batch;
+};
+
+#define UPDATE_CLASSID_BATCH 1000
+
static int update_classid_sock(const void *v, struct file *file, unsigned n)
{
int err;
+ struct update_classid_context *ctx = (void *)v;
struct socket *sock = sock_from_file(file, &err);
if (sock) {
spin_lock(&cgroup_sk_update_lock);
- sock_cgroup_set_classid(&sock->sk->sk_cgrp_data,
- (unsigned long)v);
+ sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid);
spin_unlock(&cgroup_sk_update_lock);
}
+ if (--ctx->batch == 0) {
+ ctx->batch = UPDATE_CLASSID_BATCH;
+ return n + 1;
+ }
return 0;
}
+static void update_classid_task(struct task_struct *p, u32 classid)
+{
+ struct update_classid_context ctx = {
+ .classid = classid,
+ .batch = UPDATE_CLASSID_BATCH
+ };
+ unsigned int fd = 0;
+
+ do {
+ task_lock(p);
+ fd = iterate_fd(p->files, fd, update_classid_sock, &ctx);
+ task_unlock(p);
+ cond_resched();
+ } while (fd);
+}
+
static void cgrp_attach(struct cgroup_taskset *tset)
{
struct cgroup_subsys_state *css;
struct task_struct *p;
cgroup_taskset_for_each(p, css, tset) {
- task_lock(p);
- iterate_fd(p->files, 0, update_classid_sock,
- (void *)(unsigned long)css_cls_state(css)->classid);
- task_unlock(p);
+ update_classid_task(p, css_cls_state(css)->classid);
}
}
@@ -100,10 +130,7 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
css_task_iter_start(css, &it);
while ((p = css_task_iter_next(&it))) {
- task_lock(p);
- iterate_fd(p->files, 0, update_classid_sock,
- (void *)(unsigned long)cs->classid);
- task_unlock(p);
+ update_classid_task(p, cs->classid);
cond_resched();
}
css_task_iter_end(&it);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 9b2d61120c0d..5de180a9b7f5 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -122,7 +122,7 @@ static void queue_process(struct work_struct *work)
txq = netdev_get_tx_queue(dev, q_index);
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (netif_xmit_frozen_or_stopped(txq) ||
- netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
+ !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) {
skb_queue_head(&npinfo->txq, skb);
HARD_TX_UNLOCK(dev, txq);
local_irq_restore(flags);
@@ -357,7 +357,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
HARD_TX_UNLOCK(dev, txq);
- if (status == NETDEV_TX_OK)
+ if (dev_xmit_complete(status))
break;
}
@@ -374,7 +374,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
}
- if (status != NETDEV_TX_OK) {
+ if (!dev_xmit_complete(status)) {
skb_queue_tail(&npinfo->txq, skb);
schedule_delayed_work(&npinfo->tx_work,0);
}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 306b8f0e03c1..433b26feb320 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3147,7 +3147,13 @@ static int pktgen_wait_thread_run(struct pktgen_thread *t)
{
while (thread_is_running(t)) {
+ /* note: 't' will still be around even after the unlock/lock
+ * cycle because pktgen_thread threads are only cleared at
+ * net exit
+ */
+ mutex_unlock(&pktgen_thread_lock);
msleep_interruptible(100);
+ mutex_lock(&pktgen_thread_lock);
if (signal_pending(current))
goto signal;
@@ -3162,6 +3168,10 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn)
struct pktgen_thread *t;
int sig = 1;
+ /* prevent from racing with rmmod */
+ if (!try_module_get(THIS_MODULE))
+ return sig;
+
mutex_lock(&pktgen_thread_lock);
list_for_each_entry(t, &pn->pktgen_threads, th_list) {
@@ -3175,6 +3185,7 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn)
t->control |= (T_STOP);
mutex_unlock(&pktgen_thread_lock);
+ module_put(THIS_MODULE);
return sig;
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index ba724576764e..ead1a32c68f7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1724,6 +1724,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_MAC]) {
struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
+ if (ivm->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_mac)
err = ops->ndo_set_vf_mac(dev, ivm->vf,
@@ -1735,6 +1737,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_VLAN]) {
struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
+ if (ivv->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_vlan)
err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
@@ -1767,6 +1771,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (len == 0)
return -EINVAL;
+ if (ivvl[0]->vf >= INT_MAX)
+ return -EINVAL;
err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan,
ivvl[0]->qos, ivvl[0]->vlan_proto);
if (err < 0)
@@ -1777,6 +1783,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
struct ifla_vf_info ivf;
+ if (ivt->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_get_vf_config)
err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf);
@@ -1795,6 +1803,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_RATE]) {
struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]);
+ if (ivt->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_rate)
err = ops->ndo_set_vf_rate(dev, ivt->vf,
@@ -1807,6 +1817,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_SPOOFCHK]) {
struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
+ if (ivs->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_spoofchk)
err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
@@ -1818,6 +1830,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_LINK_STATE]) {
struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
+ if (ivl->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_link_state)
err = ops->ndo_set_vf_link_state(dev, ivl->vf,
@@ -1831,6 +1845,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
err = -EOPNOTSUPP;
ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]);
+ if (ivrssq_en->vf >= INT_MAX)
+ return -EINVAL;
if (ops->ndo_set_vf_rss_query_en)
err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf,
ivrssq_en->setting);
@@ -1841,6 +1857,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_TRUST]) {
struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]);
+ if (ivt->vf >= INT_MAX)
+ return -EINVAL;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_trust)
err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting);
@@ -1851,15 +1869,18 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (tb[IFLA_VF_IB_NODE_GUID]) {
struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]);
+ if (ivt->vf >= INT_MAX)
+ return -EINVAL;
if (!ops->ndo_set_vf_guid)
return -EOPNOTSUPP;
-
return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID);
}
if (tb[IFLA_VF_IB_PORT_GUID]) {
struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]);
+ if (ivt->vf >= INT_MAX)
+ return -EINVAL;
if (!ops->ndo_set_vf_guid)
return -EOPNOTSUPP;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 4a71d78d0c6a..7164569c1ec8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3094,6 +3094,25 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
int pos;
int dummy;
+ if (list_skb && !list_skb->head_frag && skb_headlen(list_skb) &&
+ (skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY)) {
+ /* gso_size is untrusted, and we have a frag_list with a linear
+ * non head_frag head.
+ *
+ * (we assume checking the first list_skb member suffices;
+ * i.e if either of the list_skb members have non head_frag
+ * head, then the first one has too).
+ *
+ * If head_skb's headlen does not fit requested gso_size, it
+ * means that the frag_list members do NOT terminate on exact
+ * gso_size boundaries. Hence we cannot perform skb_frag_t page
+ * sharing. Therefore we must fallback to copying the frag_list
+ * skbs; we do so by disabling SG.
+ */
+ if (mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb))
+ features &= ~NETIF_F_SG;
+ }
+
__skb_push(head_skb, doffset);
proto = skb_network_protocol(head_skb, &dummy);
if (unlikely(!proto))
diff --git a/net/core/sock.c b/net/core/sock.c
index 3041aa6df602..41794a698da6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1426,8 +1426,6 @@ static void __sk_destruct(struct rcu_head *head)
sk_filter_uncharge(sk, filter);
RCU_INIT_POINTER(sk->sk_filter, NULL);
}
- if (rcu_access_pointer(sk->sk_reuseport_cb))
- reuseport_detach_sock(sk);
sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
@@ -1450,7 +1448,14 @@ static void __sk_destruct(struct rcu_head *head)
void sk_destruct(struct sock *sk)
{
- if (sock_flag(sk, SOCK_RCU_FREE))
+ bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
+
+ if (rcu_access_pointer(sk->sk_reuseport_cb)) {
+ reuseport_detach_sock(sk);
+ use_call_rcu = true;
+ }
+
+ if (use_call_rcu)
call_rcu(&sk->sk_rcu, __sk_destruct);
else
__sk_destruct(&sk->sk_rcu);
@@ -2151,7 +2156,7 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
}
if (sk_has_memory_pressure(sk)) {
- int alloc;
+ u64 alloc;
if (!sk_under_memory_pressure(sk))
return 1;
diff --git a/net/core/stream.c b/net/core/stream.c
index 1086c8b280a8..6e41b20bf9f8 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -118,7 +118,6 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
int err = 0;
long vm_wait = 0;
long current_timeo = *timeo_p;
- bool noblock = (*timeo_p ? false : true);
DEFINE_WAIT(wait);
if (sk_stream_memory_free(sk))
@@ -131,11 +130,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
- if (!*timeo_p) {
- if (noblock)
- set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
- goto do_nonblock;
- }
+ if (!*timeo_p)
+ goto do_eagain;
if (signal_pending(current))
goto do_interrupted;
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -167,7 +163,13 @@ out:
do_error:
err = -EPIPE;
goto out;
-do_nonblock:
+do_eagain:
+ /* Make sure that whenever EAGAIN is returned, EPOLLOUT event can
+ * be generated later.
+ * When TCP receives ACK packets that make room, tcp_check_space()
+ * only calls tcp_new_space() if SOCK_NOSPACE is set.
+ */
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
err = -EAGAIN;
goto out;
do_interrupted:
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 546ba76b35a5..b4318c1b5b96 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -24,9 +24,12 @@
static int zero = 0;
static int one = 1;
+static int two __maybe_unused = 2;
static int min_sndbuf = SOCK_MIN_SNDBUF;
static int min_rcvbuf = SOCK_MIN_RCVBUF;
static int max_skb_frags = MAX_SKB_FRAGS;
+static long long_one __maybe_unused = 1;
+static long long_max __maybe_unused = LONG_MAX;
static int net_msg_warn; /* Unused, but still a sysctl */
@@ -231,6 +234,52 @@ static int proc_do_rss_key(struct ctl_table *table, int write,
return proc_dostring(&fake_table, write, buffer, lenp, ppos);
}
+#ifdef CONFIG_BPF_JIT
+static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret, jit_enable = *(int *)table->data;
+ struct ctl_table tmp = *table;
+
+ if (write && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ tmp.data = &jit_enable;
+ ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+ if (write && !ret) {
+ *(int *)table->data = jit_enable;
+ if (jit_enable == 2)
+ pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n");
+ }
+ return ret;
+}
+
+# ifdef CONFIG_HAVE_EBPF_JIT
+static int
+proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+}
+# endif /* CONFIG_HAVE_EBPF_JIT */
+
+static int
+proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+}
+#endif
+
static struct ctl_table net_core_table[] = {
#ifdef CONFIG_NET
{
@@ -292,13 +341,14 @@ static struct ctl_table net_core_table[] = {
.data = &bpf_jit_enable,
.maxlen = sizeof(int),
.mode = 0644,
-#ifndef CONFIG_BPF_JIT_ALWAYS_ON
- .proc_handler = proc_dointvec
-#else
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_dointvec_minmax_bpf_enable,
+# ifdef CONFIG_BPF_JIT_ALWAYS_ON
.extra1 = &one,
.extra2 = &one,
-#endif
+# else
+ .extra1 = &zero,
+ .extra2 = &two,
+# endif
},
# ifdef CONFIG_HAVE_EBPF_JIT
{
@@ -306,9 +356,20 @@ static struct ctl_table net_core_table[] = {
.data = &bpf_jit_harden,
.maxlen = sizeof(int),
.mode = 0600,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax_bpf_restricted,
+ .extra1 = &zero,
+ .extra2 = &two,
},
# endif
+ {
+ .procname = "bpf_jit_limit",
+ .data = &bpf_jit_limit,
+ .maxlen = sizeof(long),
+ .mode = 0600,
+ .proc_handler = proc_dolongvec_minmax_bpf_restricted,
+ .extra1 = &long_one,
+ .extra2 = &long_max,
+ },
#endif
{
.procname = "netdev_tstamp_prequeue",
diff --git a/net/core/utils.c b/net/core/utils.c
index cf5622b9ccc4..3317f90b32eb 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -316,6 +316,23 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
}
EXPORT_SYMBOL(inet_proto_csum_replace4);
+/**
+ * inet_proto_csum_replace16 - update layer 4 header checksum field
+ * @sum: Layer 4 header checksum field
+ * @skb: sk_buff for the packet
+ * @from: old IPv6 address
+ * @to: new IPv6 address
+ * @pseudohdr: True if layer 4 header checksum includes pseudoheader
+ *
+ * Update layer 4 header as per the update in IPv6 src/dst address.
+ *
+ * There is no need to update skb->csum in this function, because update in two
+ * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other
+ * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to
+ * update skb->csum, because update in 3 fields a.) IPv4 src/dst address,
+ * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as
+ * L4 Header checksum for skb->csum calculation.
+ */
void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
const __be32 *from, const __be32 *to,
bool pseudohdr)
@@ -327,9 +344,6 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
if (skb->ip_summed != CHECKSUM_PARTIAL) {
*sum = csum_fold(csum_partial(diff, sizeof(diff),
~csum_unfold(*sum)));
- if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr)
- skb->csum = ~csum_partial(diff, sizeof(diff),
- ~skb->csum);
} else if (pseudohdr)
*sum = ~csum_fold(csum_partial(diff, sizeof(diff),
csum_unfold(*sum)));
generated by cgit v1.2.3 (git 2.0.4) at 2024-05-25 01:34:47 +0000