aboutsummaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c10
-rw-r--r--net/core/dev.c623
-rw-r--r--net/core/dev_addr_lists.c12
-rw-r--r--net/core/devlink.c45
-rw-r--r--net/core/ethtool.c4
-rw-r--r--net/core/filter.c8
-rw-r--r--net/core/flow_dissector.c38
-rw-r--r--net/core/lwt_bpf.c7
-rw-r--r--net/core/net-sysfs.c25
-rw-r--r--net/core/net_namespace.c23
-rw-r--r--net/core/request_sock.c2
-rw-r--r--net/core/rtnetlink.c40
-rw-r--r--net/core/skbuff.c23
-rw-r--r--net/core/skmsg.c20
-rw-r--r--net/core/sock.c38
15 files changed, 662 insertions, 256 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 4cc8dc5db2b7..da3c24ed129c 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -97,7 +97,7 @@ 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? */
@@ -278,7 +278,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
break;
sk_busy_loop(sk, flags & MSG_DONTWAIT);
- } while (sk->sk_receive_queue.prev != *last);
+ } while (READ_ONCE(sk->sk_receive_queue.prev) != *last);
error = -EAGAIN;
@@ -640,7 +640,7 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
skb->len += copied;
skb->truesize += truesize;
if (sk && sk->sk_type == SOCK_STREAM) {
- sk->sk_wmem_queued += truesize;
+ sk_wmem_queued_add(sk, truesize);
sk_mem_charge(sk, truesize);
} else {
refcount_add(truesize, &skb->sk->sk_wmem_alloc);
@@ -767,7 +767,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
mask = 0;
/* exceptional events? */
- if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+ if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
mask |= EPOLLERR |
(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
@@ -777,7 +777,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
mask |= EPOLLHUP;
/* readable? */
- if (!skb_queue_empty(&sk->sk_receive_queue))
+ if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
diff --git a/net/core/dev.c b/net/core/dev.c
index bf3ed413abaf..99ac84ff398f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -146,6 +146,7 @@
#include "net-sysfs.h"
#define MAX_GRO_SKBS 8
+#define MAX_NEST_DEV 8
/* This should be increased if a protocol with a bigger head is added. */
#define GRO_MAX_HEAD (MAX_HEADER + 128)
@@ -276,88 +277,6 @@ static RAW_NOTIFIER_HEAD(netdev_chain);
DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
EXPORT_PER_CPU_SYMBOL(softnet_data);
-#ifdef CONFIG_LOCKDEP
-/*
- * register_netdevice() inits txq->_xmit_lock and sets lockdep class
- * according to dev->type
- */
-static const unsigned short netdev_lock_type[] = {
- ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
- ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,
- ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,
- ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
- ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,
- ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,
- ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,
- ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
- ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,
- ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
- ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
- ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
- ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,
- ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
- ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
-
-static const char *const netdev_lock_name[] = {
- "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
- "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
- "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
- "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
- "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
- "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
- "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
- "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
- "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
- "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
- "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
- "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
- "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
- "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
- "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
-
-static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
-static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
-
-static inline unsigned short netdev_lock_pos(unsigned short dev_type)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++)
- if (netdev_lock_type[i] == dev_type)
- return i;
- /* the last key is used by default */
- return ARRAY_SIZE(netdev_lock_type) - 1;
-}
-
-static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
- unsigned short dev_type)
-{
- int i;
-
- i = netdev_lock_pos(dev_type);
- lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
- netdev_lock_name[i]);
-}
-
-static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
-{
- int i;
-
- i = netdev_lock_pos(dev->type);
- lockdep_set_class_and_name(&dev->addr_list_lock,
- &netdev_addr_lock_key[i],
- netdev_lock_name[i]);
-}
-#else
-static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
- unsigned short dev_type)
-{
-}
-static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
-{
-}
-#endif
-
/*******************************************************************************
*
* Protocol management and registration routines
@@ -6489,6 +6408,9 @@ struct netdev_adjacent {
/* upper master flag, there can only be one master device per list */
bool master;
+ /* lookup ignore flag */
+ bool ignore;
+
/* counter for the number of times this device was added to us */
u16 ref_nr;
@@ -6511,7 +6433,7 @@ static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev,
return NULL;
}
-static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
+static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data)
{
struct net_device *dev = data;
@@ -6532,7 +6454,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
{
ASSERT_RTNL();
- return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+ return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
upper_dev);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
@@ -6550,7 +6472,7 @@ EXPORT_SYMBOL(netdev_has_upper_dev);
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev)
{
- return !!netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+ return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
upper_dev);
}
EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
@@ -6594,6 +6516,22 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
}
EXPORT_SYMBOL(netdev_master_upper_dev_get);
+static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev)
+{
+ struct netdev_adjacent *upper;
+
+ ASSERT_RTNL();
+
+ if (list_empty(&dev->adj_list.upper))
+ return NULL;
+
+ upper = list_first_entry(&dev->adj_list.upper,
+ struct netdev_adjacent, list);
+ if (likely(upper->master) && !upper->ignore)
+ return upper->dev;
+ return NULL;
+}
+
/**
* netdev_has_any_lower_dev - Check if device is linked to some device
* @dev: device
@@ -6644,6 +6582,23 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+static struct net_device *__netdev_next_upper_dev(struct net_device *dev,
+ struct list_head **iter,
+ bool *ignore)
+{
+ struct netdev_adjacent *upper;
+
+ upper = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+ if (&upper->list == &dev->adj_list.upper)
+ return NULL;
+
+ *iter = &upper->list;
+ *ignore = upper->ignore;
+
+ return upper->dev;
+}
+
static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
@@ -6661,34 +6616,111 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
return upper->dev;
}
+static int __netdev_walk_all_upper_dev(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
+ bool ignore;
+
+ now = dev;
+ iter = &dev->adj_list.upper;
+
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ udev = __netdev_next_upper_dev(now, &iter, &ignore);
+ if (!udev)
+ break;
+ if (ignore)
+ continue;
+
+ next = udev;
+ niter = &udev->adj_list.upper;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
+ }
+
+ return 0;
+}
+
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *dev,
void *data),
void *data)
{
- struct net_device *udev;
- struct list_head *iter;
- int ret;
+ struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
- for (iter = &dev->adj_list.upper,
- udev = netdev_next_upper_dev_rcu(dev, &iter);
- udev;
- udev = netdev_next_upper_dev_rcu(dev, &iter)) {
- /* first is the upper device itself */
- ret = fn(udev, data);
- if (ret)
- return ret;
+ now = dev;
+ iter = &dev->adj_list.upper;
- /* then look at all of its upper devices */
- ret = netdev_walk_all_upper_dev_rcu(udev, fn, data);
- if (ret)
- return ret;
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ udev = netdev_next_upper_dev_rcu(now, &iter);
+ if (!udev)
+ break;
+
+ next = udev;
+ niter = &udev->adj_list.upper;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
}
return 0;
}
EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu);
+static bool __netdev_has_upper_dev(struct net_device *dev,
+ struct net_device *upper_dev)
+{
+ ASSERT_RTNL();
+
+ return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev,
+ upper_dev);
+}
+
/**
* netdev_lower_get_next_private - Get the next ->private from the
* lower neighbour list
@@ -6785,34 +6817,119 @@ static struct net_device *netdev_next_lower_dev(struct net_device *dev,
return lower->dev;
}
+static struct net_device *__netdev_next_lower_dev(struct net_device *dev,
+ struct list_head **iter,
+ bool *ignore)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->adj_list.lower)
+ return NULL;
+
+ *iter = &lower->list;
+ *ignore = lower->ignore;
+
+ return lower->dev;
+}
+
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
void *data),
void *data)
{
- struct net_device *ldev;
- struct list_head *iter;
- int ret;
+ struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
- for (iter = &dev->adj_list.lower,
- ldev = netdev_next_lower_dev(dev, &iter);
- ldev;
- ldev = netdev_next_lower_dev(dev, &iter)) {
- /* first is the lower device itself */
- ret = fn(ldev, data);
- if (ret)
- return ret;
+ now = dev;
+ iter = &dev->adj_list.lower;
- /* then look at all of its lower devices */
- ret = netdev_walk_all_lower_dev(ldev, fn, data);
- if (ret)
- return ret;
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ ldev = netdev_next_lower_dev(now, &iter);
+ if (!ldev)
+ break;
+
+ next = ldev;
+ niter = &ldev->adj_list.lower;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
}
return 0;
}
EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);
+static int __netdev_walk_all_lower_dev(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
+ bool ignore;
+
+ now = dev;
+ iter = &dev->adj_list.lower;
+
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ ldev = __netdev_next_lower_dev(now, &iter, &ignore);
+ if (!ldev)
+ break;
+ if (ignore)
+ continue;
+
+ next = ldev;
+ niter = &ldev->adj_list.lower;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
+ }
+
+ return 0;
+}
+
static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
@@ -6827,28 +6944,99 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
return lower->dev;
}
-int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
- int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+static u8 __netdev_upper_depth(struct net_device *dev)
+{
+ struct net_device *udev;
+ struct list_head *iter;
+ u8 max_depth = 0;
+ bool ignore;
+
+ for (iter = &dev->adj_list.upper,
+ udev = __netdev_next_upper_dev(dev, &iter, &ignore);
+ udev;
+ udev = __netdev_next_upper_dev(dev, &iter, &ignore)) {
+ if (ignore)
+ continue;
+ if (max_depth < udev->upper_level)
+ max_depth = udev->upper_level;
+ }
+
+ return max_depth;
+}
+
+static u8 __netdev_lower_depth(struct net_device *dev)
{
struct net_device *ldev;
struct list_head *iter;
- int ret;
+ u8 max_depth = 0;
+ bool ignore;
for (iter = &dev->adj_list.lower,
- ldev = netdev_next_lower_dev_rcu(dev, &iter);
+ ldev = __netdev_next_lower_dev(dev, &iter, &ignore);
ldev;
- ldev = netdev_next_lower_dev_rcu(dev, &iter)) {
- /* first is the lower device itself */
- ret = fn(ldev, data);
- if (ret)
- return ret;
+ ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) {
+ if (ignore)
+ continue;
+ if (max_depth < ldev->lower_level)
+ max_depth = ldev->lower_level;
+ }
- /* then look at all of its lower devices */
- ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data);
- if (ret)
- return ret;
+ return max_depth;
+}
+
+static int __netdev_update_upper_level(struct net_device *dev, void *data)
+{
+ dev->upper_level = __netdev_upper_depth(dev) + 1;
+ return 0;
+}
+
+static int __netdev_update_lower_level(struct net_device *dev, void *data)
+{
+ dev->lower_level = __netdev_lower_depth(dev) + 1;
+ return 0;
+}
+
+int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
+
+ now = dev;
+ iter = &dev->adj_list.lower;
+
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ ldev = netdev_next_lower_dev_rcu(now, &iter);
+ if (!ldev)
+ break;
+
+ next = ldev;
+ niter = &ldev->adj_list.lower;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
}
return 0;
@@ -6952,6 +7140,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
adj->master = master;
adj->ref_nr = 1;
adj->private = private;
+ adj->ignore = false;
dev_hold(adj_dev);
pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n",
@@ -7102,14 +7291,17 @@ static int __netdev_upper_dev_link(struct net_device *dev,
return -EBUSY;
/* To prevent loops, check if dev is not upper device to upper_dev. */
- if (netdev_has_upper_dev(upper_dev, dev))
+ if (__netdev_has_upper_dev(upper_dev, dev))
return -EBUSY;
+ if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV)
+ return -EMLINK;
+
if (!master) {
- if (netdev_has_upper_dev(dev, upper_dev))
+ if (__netdev_has_upper_dev(dev, upper_dev))
return -EEXIST;
} else {
- master_dev = netdev_master_upper_dev_get(dev);
+ master_dev = __netdev_master_upper_dev_get(dev);
if (master_dev)
return master_dev == upper_dev ? -EEXIST : -EBUSY;
}
@@ -7131,6 +7323,13 @@ static int __netdev_upper_dev_link(struct net_device *dev,
if (ret)
goto rollback;
+ __netdev_update_upper_level(dev, NULL);
+ __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+
+ __netdev_update_lower_level(upper_dev, NULL);
+ __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
+ NULL);
+
return 0;
rollback:
@@ -7213,9 +7412,96 @@ void netdev_upper_dev_unlink(struct net_device *dev,
call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
&changeupper_info.info);
+
+ __netdev_update_upper_level(dev, NULL);
+ __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+
+ __netdev_update_lower_level(upper_dev, NULL);
+ __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
+ NULL);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
+static void __netdev_adjacent_dev_set(struct net_device *upper_dev,
+ struct net_device *lower_dev,
+ bool val)
+{
+ struct netdev_adjacent *adj;
+
+ adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower);
+ if (adj)
+ adj->ignore = val;
+
+ adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper);
+ if (adj)
+ adj->ignore = val;
+}
+
+static void netdev_adjacent_dev_disable(struct net_device *upper_dev,
+ struct net_device *lower_dev)
+{
+ __netdev_adjacent_dev_set(upper_dev, lower_dev, true);
+}
+
+static void netdev_adjacent_dev_enable(struct net_device *upper_dev,
+ struct net_device *lower_dev)
+{
+ __netdev_adjacent_dev_set(upper_dev, lower_dev, false);
+}
+
+int netdev_adjacent_change_prepare(struct net_device *old_dev,
+ struct net_device *new_dev,
+ struct net_device *dev,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ if (!new_dev)
+ return 0;
+
+ if (old_dev && new_dev != old_dev)
+ netdev_adjacent_dev_disable(dev, old_dev);
+
+ err = netdev_upper_dev_link(new_dev, dev, extack);
+ if (err) {
+ if (old_dev && new_dev != old_dev)
+ netdev_adjacent_dev_enable(dev, old_dev);
+ return err;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_adjacent_change_prepare);
+
+void netdev_adjacent_change_commit(struct net_device *old_dev,
+ struct net_device *new_dev,
+ struct net_device *dev)
+{
+ if (!new_dev || !old_dev)
+ return;
+
+ if (new_dev == old_dev)
+ return;
+
+ netdev_adjacent_dev_enable(dev, old_dev);
+ netdev_upper_dev_unlink(old_dev, dev);
+}
+EXPORT_SYMBOL(netdev_adjacent_change_commit);
+
+void netdev_adjacent_change_abort(struct net_device *old_dev,
+ struct net_device *new_dev,
+ struct net_device *dev)
+{
+ if (!new_dev)
+ return;
+
+ if (old_dev && new_dev != old_dev)
+ netdev_adjacent_dev_enable(dev, old_dev);
+
+ netdev_upper_dev_unlink(new_dev, dev);
+}
+EXPORT_SYMBOL(netdev_adjacent_change_abort);
+
/**
* netdev_bonding_info_change - Dispatch event about slave change
* @dev: device
@@ -7329,25 +7615,6 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
EXPORT_SYMBOL(netdev_lower_dev_get_private);
-int dev_get_nest_level(struct net_device *dev)
-{
- struct net_device *lower = NULL;
- struct list_head *iter;
- int max_nest = -1;
- int nest;
-
- ASSERT_RTNL();
-
- netdev_for_each_lower_dev(dev, lower, iter) {
- nest = dev_get_nest_level(lower);
- if (max_nest < nest)
- max_nest = nest;
- }
-
- return max_nest + 1;
-}
-EXPORT_SYMBOL(dev_get_nest_level);
-
/**
* netdev_lower_change - Dispatch event about lower device state change
* @lower_dev: device
@@ -8154,7 +8421,8 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
return -EINVAL;
}
- if (prog->aux->id == prog_id) {
+ /* prog->aux->id may be 0 for orphaned device-bound progs */
+ if (prog->aux->id && prog->aux->id == prog_id) {
bpf_prog_put(prog);
return 0;
}
@@ -8619,7 +8887,7 @@ static void netdev_init_one_queue(struct net_device *dev,
{
/* Initialize queue lock */
spin_lock_init(&queue->_xmit_lock);
- netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type);
+ lockdep_set_class(&queue->_xmit_lock, &dev->qdisc_xmit_lock_key);
queue->xmit_lock_owner = -1;
netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
queue->dev = dev;
@@ -8666,6 +8934,43 @@ void netif_tx_stop_all_queues(struct net_device *dev)
}
EXPORT_SYMBOL(netif_tx_stop_all_queues);
+static void netdev_register_lockdep_key(struct net_device *dev)
+{
+ lockdep_register_key(&dev->qdisc_tx_busylock_key);
+ lockdep_register_key(&dev->qdisc_running_key);
+ lockdep_register_key(&dev->qdisc_xmit_lock_key);
+ lockdep_register_key(&dev->addr_list_lock_key);
+}
+
+static void netdev_unregister_lockdep_key(struct net_device *dev)
+{
+ lockdep_unregister_key(&dev->qdisc_tx_busylock_key);
+ lockdep_unregister_key(&dev->qdisc_running_key);
+ lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
+ lockdep_unregister_key(&dev->addr_list_lock_key);
+}
+
+void netdev_update_lockdep_key(struct net_device *dev)
+{
+ struct netdev_queue *queue;
+ int i;
+
+ lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
+ lockdep_unregister_key(&dev->addr_list_lock_key);
+
+ lockdep_register_key(&dev->qdisc_xmit_lock_key);
+ lockdep_register_key(&dev->addr_list_lock_key);
+
+ lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
+ for (i = 0; i < dev->num_tx_queues; i++) {
+ queue = netdev_get_tx_queue(dev, i);
+
+ lockdep_set_class(&queue->_xmit_lock,
+ &dev->qdisc_xmit_lock_key);
+ }
+}
+EXPORT_SYMBOL(netdev_update_lockdep_key);
+
/**
* register_netdevice - register a network device
* @dev: device to register
@@ -8700,7 +9005,7 @@ int register_netdevice(struct net_device *dev)
BUG_ON(!net);
spin_lock_init(&dev->addr_list_lock);
- netdev_set_addr_lockdep_class(dev);
+ lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
ret = dev_get_valid_name(net, dev, dev->name);
if (ret < 0)
@@ -9210,8 +9515,12 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
dev_net_set(dev, &init_net);
+ netdev_register_lockdep_key(dev);
+
dev->gso_max_size = GSO_MAX_SIZE;
dev->gso_max_segs = GSO_MAX_SEGS;
+ dev->upper_level = 1;
+ dev->lower_level = 1;
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
@@ -9292,6 +9601,8 @@ void free_netdev(struct net_device *dev)
free_percpu(dev->pcpu_refcnt);
dev->pcpu_refcnt = NULL;
+ netdev_unregister_lockdep_key(dev);
+
/* Compatibility with error handling in drivers */
if (dev->reg_state == NETREG_UNINITIALIZED) {
netdev_freemem(dev);
@@ -9460,7 +9771,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
rcu_barrier();
- new_nsid = peernet2id_alloc(dev_net(dev), net);
+ new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL);
/* If there is an ifindex conflict assign a new one */
if (__dev_get_by_index(net, dev->ifindex))
new_ifindex = dev_new_index(net);
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 6393ba930097..2f949b5a1eb9 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -637,7 +637,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
@@ -667,7 +667,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
@@ -691,7 +691,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from)
return;
netif_addr_lock_bh(from);
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
__hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
__dev_set_rx_mode(to);
netif_addr_unlock(to);
@@ -858,7 +858,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
@@ -888,7 +888,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return -EINVAL;
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
@@ -912,7 +912,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from)
return;
netif_addr_lock_bh(from);
- netif_addr_lock_nested(to);
+ netif_addr_lock(to);
__hw_addr_unsync(&to->mc, &from->mc, to->addr_len);
__dev_set_rx_mode(to);
netif_addr_unlock(to);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index f80151eeaf51..93905dc7c179 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2699,7 +2699,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
struct devlink *devlink = info->user_ptr[0];
int err;
- if (!devlink_reload_supported(devlink))
+ if (!devlink_reload_supported(devlink) || !devlink->reload_enabled)
return -EOPNOTSUPP;
err = devlink_resources_validate(devlink, NULL, info);
@@ -4618,6 +4618,7 @@ struct devlink_health_reporter {
bool auto_recover;
u8 health_state;
u64 dump_ts;
+ u64 dump_real_ts;
u64 error_count;
u64 recovery_count;
u64 last_recovery_ts;
@@ -4790,6 +4791,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter,
goto dump_err;
reporter->dump_ts = jiffies;
+ reporter->dump_real_ts = ktime_get_real_ns();
return 0;
@@ -4952,6 +4954,10 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg,
jiffies_to_msecs(reporter->dump_ts),
DEVLINK_ATTR_PAD))
goto reporter_nest_cancel;
+ if (reporter->dump_fmsg &&
+ nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS,
+ reporter->dump_real_ts, DEVLINK_ATTR_PAD))
+ goto reporter_nest_cancel;
nla_nest_end(msg, reporter_attr);
genlmsg_end(msg, hdr);
@@ -6196,6 +6202,8 @@ EXPORT_SYMBOL_GPL(devlink_register);
void devlink_unregister(struct devlink *devlink)
{
mutex_lock(&devlink_mutex);
+ WARN_ON(devlink_reload_supported(devlink) &&
+ devlink->reload_enabled);
devlink_notify(devlink, DEVLINK_CMD_DEL);
list_del(&devlink->list);
mutex_unlock(&devlink_mutex);
@@ -6203,6 +6211,41 @@ void devlink_unregister(struct devlink *devlink)
EXPORT_SYMBOL_GPL(devlink_unregister);
/**
+ * devlink_reload_enable - Enable reload of devlink instance
+ *
+ * @devlink: devlink
+ *
+ * Should be called at end of device initialization
+ * process when reload operation is supported.
+ */
+void devlink_reload_enable(struct devlink *devlink)
+{
+ mutex_lock(&devlink_mutex);
+ devlink->reload_enabled = true;
+ mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_reload_enable);
+
+/**
+ * devlink_reload_disable - Disable reload of devlink instance
+ *
+ * @devlink: devlink
+ *
+ * Should be called at the beginning of device cleanup
+ * process when reload operation is supported.
+ */
+void devlink_reload_disable(struct devlink *devlink)
+{
+ mutex_lock(&devlink_mutex);
+ /* Mutex is taken which ensures that no reload operation is in
+ * progress while setting up forbidded flag.
+ */
+ devlink->reload_enabled = false;
+ mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_reload_disable);
+
+/**
* devlink_free - Free devlink instance resources
*
* @devlink: devlink
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index c763106c73fc..cd9bc67381b2 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1396,11 +1396,13 @@ 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)))
diff --git a/net/core/filter.c b/net/core/filter.c
index ed6563622ce3..3fed5755494b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4252,12 +4252,14 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
case SO_RCVBUF:
val = min_t(u32, val, sysctl_rmem_max);
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
- sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
+ WRITE_ONCE(sk->sk_rcvbuf,
+ max_t(int, val * 2, SOCK_MIN_RCVBUF));
break;
case SO_SNDBUF:
val = min_t(u32, val, sysctl_wmem_max);
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
- sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
+ WRITE_ONCE(sk->sk_sndbuf,
+ max_t(int, val * 2, SOCK_MIN_SNDBUF));
break;
case SO_MAX_PACING_RATE: /* 32bit version */
if (val != ~0U)
@@ -4274,7 +4276,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
case SO_RCVLOWAT:
if (val < 0)
val = INT_MAX;
- sk->sk_rcvlowat = val ? : 1;
+ WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
break;
case SO_MARK:
if (sk->sk_mark != val) {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 7c09d87d3269..68eda10d0680 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1350,30 +1350,21 @@ 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));
@@ -1388,7 +1379,7 @@ static inline size_t flow_keys_hash_length(const struct flow_keys *flow)
diff -= sizeof(flow->addrs.tipckey);
break;
}
- return (sizeof(*flow) - diff) / sizeof(u32);
+ return sizeof(*flow) - diff;
}
__be32 flow_get_u32_src(const struct flow_keys *flow)
@@ -1454,14 +1445,15 @@ 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;
@@ -1471,12 +1463,13 @@ 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);
@@ -1524,7 +1517,7 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
&keys, 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);
@@ -1544,13 +1537,14 @@ 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/lwt_bpf.c b/net/core/lwt_bpf.c
index f93785e5833c..74cfb8b5ab33 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -88,11 +88,16 @@ static int bpf_lwt_input_reroute(struct sk_buff *skb)
int err = -EINVAL;
if (skb->protocol == htons(ETH_P_IP)) {
+ struct net_device *dev = skb_dst(skb)->dev;
struct iphdr *iph = ip_hdr(skb);
+ dev_hold(dev);
+ skb_dst_drop(skb);
err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
- iph->tos, skb_dst(skb)->dev);
+ iph->tos, dev);
+ dev_put(dev);
} else if (skb->protocol == htons(ETH_P_IPV6)) {
+ skb_dst_drop(skb);
err = ipv6_stub->ipv6_route_input(skb);
} else {
err = -EAFNOSUPPORT;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 865ba6ca16eb..ae3bcb1540ec 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -923,21 +923,23 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL,
"rx-%u", index);
if (error)
- return error;
+ goto err;
dev_hold(queue->dev);
if (dev->sysfs_rx_queue_group) {
error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group);
- if (error) {
- kobject_put(kobj);
- return error;
- }
+ if (error)
+ goto err;
}
kobject_uevent(kobj, KOBJ_ADD);
return error;
+
+err:
+ kobject_put(kobj);
+ return error;
}
#endif /* CONFIG_SYSFS */
@@ -1461,21 +1463,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL,
"tx-%u", index);
if (error)
- return error;
+ goto err;
dev_hold(queue->dev);
#ifdef CONFIG_BQL
error = sysfs_create_group(kobj, &dql_group);
- if (error) {
- kobject_put(kobj);
- return error;
- }
+ if (error)
+ goto err;
#endif
kobject_uevent(kobj, KOBJ_ADD);
-
return 0;
+
+err:
+ kobject_put(kobj);
+ return error;
}
#endif /* CONFIG_SYSFS */
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index a0e0d298c991..39402840025e 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -245,11 +245,12 @@ static int __peernet2id(struct net *net, struct net *peer)
return __peernet2id_alloc(net, peer, &no);
}
-static void rtnl_net_notifyid(struct net *net, int cmd, int id);
+static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
+ struct nlmsghdr *nlh, gfp_t gfp);
/* This function returns the id of a peer netns. If no id is assigned, one will
* be allocated and returned.
*/
-int peernet2id_alloc(struct net *net, struct net *peer)
+int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp)
{
bool alloc = false, alive = false;
int id;
@@ -268,7 +269,7 @@ int peernet2id_alloc(struct net *net, struct net *peer)
id = __peernet2id_alloc(net, peer, &alloc);
spin_unlock_bh(&net->nsid_lock);
if (alloc && id >= 0)
- rtnl_net_notifyid(net, RTM_NEWNSID, id);
+ rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp);
if (alive)
put_net(peer);
return id;
@@ -478,6 +479,7 @@ struct net *copy_net_ns(unsigned long flags,
if (rv < 0) {
put_userns:
+ key_remove_domain(net->key_domain);
put_user_ns(user_ns);
net_drop_ns(net);
dec_ucounts:
@@ -532,7 +534,8 @@ static void unhash_nsid(struct net *net, struct net *last)
idr_remove(&tmp->netns_ids, id);
spin_unlock_bh(&tmp->nsid_lock);
if (id >= 0)
- rtnl_net_notifyid(tmp, RTM_DELNSID, id);
+ rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL,
+ GFP_KERNEL);
if (tmp == last)
break;
}
@@ -764,7 +767,8 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
err = alloc_netid(net, peer, nsid);
spin_unlock_bh(&net->nsid_lock);
if (err >= 0) {
- rtnl_net_notifyid(net, RTM_NEWNSID, err);
+ rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid,
+ nlh, GFP_KERNEL);
err = 0;
} else if (err == -ENOSPC && nsid >= 0) {
err = -EEXIST;
@@ -1051,16 +1055,19 @@ end:
return err < 0 ? err : skb->len;
}
-static void rtnl_net_notifyid(struct net *net, int cmd, int id)
+static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
+ struct nlmsghdr *nlh, gfp_t gfp)
{
struct net_fill_args fillargs = {
+ .portid = portid,
+ .seq = nlh ? nlh->nlmsg_seq : 0,
.cmd = cmd,
.nsid = id,
};
struct sk_buff *msg;
int err = -ENOMEM;
- msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
+ msg = nlmsg_new(rtnl_net_get_size(), gfp);
if (!msg)
goto out;
@@ -1068,7 +1075,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id)
if (err < 0)
goto err_out;
- rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, 0);
+ rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, gfp);
return;
err_out:
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index c9bb00008528..f35c2e998406 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -96,7 +96,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq;
- tcp_sk(sk)->fastopen_rsk = NULL;
+ RCU_INIT_POINTER(tcp_sk(sk)->fastopen_rsk, NULL);
spin_lock_bh(&fastopenq->lock);
fastopenq->qlen--;
tcp_rsk(req)->tfo_listener = false;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1ee6460f8275..e4ec575c1fba 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1523,7 +1523,7 @@ static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb,
static int rtnl_fill_link_netnsid(struct sk_buff *skb,
const struct net_device *dev,
- struct net *src_net)
+ struct net *src_net, gfp_t gfp)
{
bool put_iflink = false;
@@ -1531,7 +1531,7 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb,
struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
if (!net_eq(dev_net(dev), link_net)) {
- int id = peernet2id_alloc(src_net, link_net);
+ int id = peernet2id_alloc(src_net, link_net, gfp);
if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
return -EMSGSIZE;
@@ -1589,7 +1589,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
int type, u32 pid, u32 seq, u32 change,
unsigned int flags, u32 ext_filter_mask,
u32 event, int *new_nsid, int new_ifindex,
- int tgt_netnsid)
+ int tgt_netnsid, gfp_t gfp)
{
struct ifinfomsg *ifm;
struct nlmsghdr *nlh;
@@ -1681,7 +1681,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
goto nla_put_failure;
}
- if (rtnl_fill_link_netnsid(skb, dev, src_net))
+ if (rtnl_fill_link_netnsid(skb, dev, src_net, gfp))
goto nla_put_failure;
if (new_nsid &&
@@ -2001,7 +2001,7 @@ walk_entries:
NETLINK_CB(cb->skb).portid,
nlh->nlmsg_seq, 0, flags,
ext_filter_mask, 0, NULL, 0,
- netnsid);
+ netnsid, GFP_KERNEL);
if (err < 0) {
if (likely(skb->len))
@@ -2195,6 +2195,8 @@ 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,
@@ -2206,6 +2208,8 @@ 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,
@@ -2238,6 +2242,8 @@ 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)
@@ -2248,6 +2254,8 @@ 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);
@@ -2266,6 +2274,8 @@ 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,
@@ -2278,6 +2288,8 @@ 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,
@@ -2289,6 +2301,8 @@ 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,
@@ -2302,6 +2316,8 @@ 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);
@@ -2312,6 +2328,8 @@ 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);
@@ -2322,15 +2340,18 @@ 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;
@@ -2355,6 +2376,7 @@ static int do_set_master(struct net_device *dev, int ifindex,
err = ops->ndo_del_slave(upper_dev, dev);
if (err)
return err;
+ netdev_update_lockdep_key(dev);
} else {
return -EOPNOTSUPP;
}
@@ -3359,7 +3381,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
err = rtnl_fill_ifinfo(nskb, dev, net,
RTM_NEWLINK, NETLINK_CB(skb).portid,
nlh->nlmsg_seq, 0, 0, ext_filter_mask,
- 0, NULL, 0, netnsid);
+ 0, NULL, 0, netnsid, GFP_KERNEL);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size */
WARN_ON(err == -EMSGSIZE);
@@ -3471,7 +3493,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
err = rtnl_fill_ifinfo(skb, dev, dev_net(dev),
type, 0, 0, change, 0, 0, event,
- new_nsid, new_ifindex, -1);
+ new_nsid, new_ifindex, -1, flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -3916,7 +3938,7 @@ static int valid_fdb_dump_strict(const struct nlmsghdr *nlh,
ndm = nlmsg_data(nlh);
if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_state ||
ndm->ndm_flags || ndm->ndm_type) {
- NL_SET_ERR_MSG(extack, "Invalid values in header for fbd dump request");
+ NL_SET_ERR_MSG(extack, "Invalid values in header for fdb dump request");
return -EINVAL;
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 529133611ea2..867e61df00db 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4415,7 +4415,7 @@ static void skb_set_err_queue(struct sk_buff *skb)
int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
{
if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
- (unsigned int)sk->sk_rcvbuf)
+ (unsigned int)READ_ONCE(sk->sk_rcvbuf))
return -ENOMEM;
skb_orphan(skb);
@@ -5477,12 +5477,14 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
* @skb: buffer
* @mpls_lse: MPLS label stack entry to push
* @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848)
+ * @mac_len: length of the MAC header
*
* Expects skb->data at mac header.
*
* Returns 0 on success, -errno otherwise.
*/
-int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto)
+int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
+ int mac_len)
{
struct mpls_shim_hdr *lse;
int err;
@@ -5499,15 +5501,15 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto)
return err;
if (!skb->inner_protocol) {
- skb_set_inner_network_header(skb, skb->mac_len);
+ skb_set_inner_network_header(skb, mac_len);
skb_set_inner_protocol(skb, skb->protocol);
}
skb_push(skb, MPLS_HLEN);
memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
- skb->mac_len);
+ mac_len);
skb_reset_mac_header(skb);
- skb_set_network_header(skb, skb->mac_len);
+ skb_set_network_header(skb, mac_len);
lse = mpls_hdr(skb);
lse->label_stack_entry = mpls_lse;
@@ -5526,29 +5528,30 @@ EXPORT_SYMBOL_GPL(skb_mpls_push);
*
* @skb: buffer
* @next_proto: ethertype of header after popped MPLS header
+ * @mac_len: length of the MAC header
*
* Expects skb->data at mac header.
*
* Returns 0 on success, -errno otherwise.
*/
-int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto)
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len)
{
int err;
if (unlikely(!eth_p_mpls(skb->protocol)))
- return -EINVAL;
+ return 0;
- err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
+ err = skb_ensure_writable(skb, mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
- skb->mac_len);
+ mac_len);
__skb_pull(skb, MPLS_HLEN);
skb_reset_mac_header(skb);
- skb_set_network_header(skb, skb->mac_len);
+ skb_set_network_header(skb, mac_len);
if (skb->dev && skb->dev->type == ARPHRD_ETHER) {
struct ethhdr *hdr;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index cf390e0aa73d..ad31e4e53d0a 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -270,18 +270,28 @@ void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len)
msg->sg.data[i].length -= trim;
sk_mem_uncharge(sk, trim);
+ /* Adjust copybreak if it falls into the trimmed part of last buf */
+ if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length)
+ msg->sg.copybreak = msg->sg.data[i].length;
out:
- /* If we trim data before curr pointer update copybreak and current
- * so that any future copy operations start at new copy location.
+ sk_msg_iter_var_next(i);
+ msg->sg.end = i;
+
+ /* If we trim data a full sg elem before curr pointer update
+ * copybreak and current so that any future copy operations
+ * start at new copy location.
* However trimed data that has not yet been used in a copy op
* does not require an update.
*/
- if (msg->sg.curr >= i) {
+ if (!msg->sg.size) {
+ msg->sg.curr = msg->sg.start;
+ msg->sg.copybreak = 0;
+ } else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >=
+ sk_msg_iter_dist(msg->sg.start, msg->sg.end)) {
+ sk_msg_iter_var_prev(i);
msg->sg.curr = i;
msg->sg.copybreak = msg->sg.data[i].length;
}
- sk_msg_iter_var_next(i);
- msg->sg.end = i;
}
EXPORT_SYMBOL_GPL(sk_msg_trim);
diff --git a/net/core/sock.c b/net/core/sock.c
index fac2b4d80de5..ac78a570e43a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -522,7 +522,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
rc = sk_backlog_rcv(sk, skb);
mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
- } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) {
+ } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) {
bh_unlock_sock(sk);
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
@@ -785,7 +785,8 @@ set_sndbuf:
*/
val = min_t(int, val, INT_MAX / 2);
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
- sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
+ WRITE_ONCE(sk->sk_sndbuf,
+ max_t(int, val * 2, SOCK_MIN_SNDBUF));
/* Wake up sending tasks if we upped the value. */
sk->sk_write_space(sk);
break;
@@ -831,7 +832,8 @@ set_rcvbuf:
* returning the value we actually used in getsockopt
* is the most desirable behavior.
*/
- sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
+ WRITE_ONCE(sk->sk_rcvbuf,
+ max_t(int, val * 2, SOCK_MIN_RCVBUF));
break;
case SO_RCVBUFFORCE:
@@ -974,7 +976,7 @@ set_rcvbuf:
if (sock->ops->set_rcvlowat)
ret = sock->ops->set_rcvlowat(sk, val);
else
- sk->sk_rcvlowat = val ? : 1;
+ WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
break;
case SO_RCVTIMEO_OLD:
@@ -1125,7 +1127,7 @@ set_rcvbuf:
break;
}
case SO_INCOMING_CPU:
- sk->sk_incoming_cpu = val;
+ WRITE_ONCE(sk->sk_incoming_cpu, val);
break;
case SO_CNX_ADVICE:
@@ -1474,7 +1476,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_INCOMING_CPU:
- v.val = sk->sk_incoming_cpu;
+ v.val = READ_ONCE(sk->sk_incoming_cpu);
break;
case SO_MEMINFO:
@@ -2088,8 +2090,10 @@ EXPORT_SYMBOL(sock_i_ino);
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
gfp_t priority)
{
- if (force || refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
+ if (force ||
+ refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) {
struct sk_buff *skb = alloc_skb(size, priority);
+
if (skb) {
skb_set_owner_w(skb, sk);
return skb;
@@ -2190,7 +2194,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
break;
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
+ if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf))
break;
if (sk->sk_shutdown & SEND_SHUTDOWN)
break;
@@ -2225,7 +2229,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
if (sk->sk_shutdown & SEND_SHUTDOWN)
goto failure;
- if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
+ if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf))
break;
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -2334,8 +2338,8 @@ static void sk_leave_memory_pressure(struct sock *sk)
} else {
unsigned long *memory_pressure = sk->sk_prot->memory_pressure;
- if (memory_pressure && *memory_pressure)
- *memory_pressure = 0;
+ if (memory_pressure && READ_ONCE(*memory_pressure))
+ WRITE_ONCE(*memory_pressure, 0);
}
}
@@ -2806,7 +2810,7 @@ static void sock_def_write_space(struct sock *sk)
/* Do not wake up a writer until he can make "significant"
* progress. --DaveM
*/
- if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
+ if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) {
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
@@ -3204,13 +3208,13 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem)
memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS);
mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
- mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+ mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf);
mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
- mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+ mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf);
mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
- mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+ mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued);
mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
- mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+ mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
}
@@ -3596,7 +3600,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time)
{
struct sock *sk = p;
- return !skb_queue_empty(&sk->sk_receive_queue) ||
+ return !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
sk_busy_loop_timeout(sk, start_time);
}
EXPORT_SYMBOL(sk_busy_loop_end);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.