summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/bridge/br_sysfs_if.c6
-rw-r--r--net/caif/caif_socket.c2
-rw-r--r--net/ceph/crypto.c1
-rw-r--r--net/ceph/crypto.h3
-rw-r--r--net/core/dev.c56
-rw-r--r--net/core/filter.c8
-rw-r--r--net/core/rtnetlink.c9
-rw-r--r--net/core/skbuff.c124
-rw-r--r--net/core/sock.c59
-rw-r--r--net/ipv4/Makefile2
-rw-r--r--net/ipv4/fib_frontend.c1
-rw-r--r--net/ipv4/fib_semantics.c42
-rw-r--r--net/ipv4/fib_trie.c53
-rw-r--r--net/ipv4/ip_input.c2
-rw-r--r--net/ipv4/route.c183
-rw-r--r--net/ipv4/sysctl_net_ipv4.c15
-rw-r--r--net/ipv4/tcp_input.c24
-rw-r--r--net/ipv4/tcp_ipv4.c14
-rw-r--r--net/ipv4/tcp_minisocks.c3
-rw-r--r--net/ipv4/tcp_output.c12
-rw-r--r--net/ipv4/xfrm4_policy.c1
-rw-r--r--net/ipv6/ip6_input.c2
-rw-r--r--net/ipv6/route.c8
-rw-r--r--net/ipv6/tcp_ipv6.c10
-rw-r--r--net/sctp/ulpevent.c3
-rw-r--r--net/sunrpc/Kconfig5
-rw-r--r--net/sunrpc/clnt.c9
-rw-r--r--net/sunrpc/rpcb_clnt.c4
-rw-r--r--net/sunrpc/sched.c14
-rw-r--r--net/sunrpc/xprtrdma/transport.c3
-rw-r--r--net/sunrpc/xprtsock.c53
-rw-r--r--net/unix/af_unix.c93
32 files changed, 589 insertions, 235 deletions
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 6229b62749e..13b36bdc76a 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -27,7 +27,7 @@ struct brport_attribute {
};
#define BRPORT_ATTR(_name,_mode,_show,_store) \
-struct brport_attribute brport_attr_##_name = { \
+const struct brport_attribute brport_attr_##_name = { \
.attr = {.name = __stringify(_name), \
.mode = _mode }, \
.show = _show, \
@@ -164,7 +164,7 @@ static BRPORT_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router,
store_multicast_router);
#endif
-static struct brport_attribute *brport_attrs[] = {
+static const struct brport_attribute *brport_attrs[] = {
&brport_attr_path_cost,
&brport_attr_priority,
&brport_attr_port_id,
@@ -241,7 +241,7 @@ const struct sysfs_ops brport_sysfs_ops = {
int br_sysfs_addif(struct net_bridge_port *p)
{
struct net_bridge *br = p->br;
- struct brport_attribute **a;
+ const struct brport_attribute **a;
int err;
err = sysfs_create_link(&p->kobj, &br->dev->dev.kobj,
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 78f1cdad5b3..095259f8390 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -141,7 +141,7 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
err = sk_filter(sk, skb);
if (err)
return err;
- if (!sk_rmem_schedule(sk, skb->truesize) && rx_flow_is_on(cf_sk)) {
+ if (!sk_rmem_schedule(sk, skb, skb->truesize) && rx_flow_is_on(cf_sk)) {
set_rx_flow_off(cf_sk);
net_dbg_ratelimited("sending flow OFF due to rmem_schedule\n");
caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ);
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index b780cb7947d..9da7fdd3cd8 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -466,6 +466,7 @@ void ceph_key_destroy(struct key *key) {
struct ceph_crypto_key *ckey = key->payload.data;
ceph_crypto_key_destroy(ckey);
+ kfree(ckey);
}
struct key_type key_type_ceph = {
diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h
index 1919d1550d7..3572dc518bc 100644
--- a/net/ceph/crypto.h
+++ b/net/ceph/crypto.h
@@ -16,7 +16,8 @@ struct ceph_crypto_key {
static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key)
{
- kfree(key->key);
+ if (key)
+ kfree(key->key);
}
extern int ceph_crypto_key_clone(struct ceph_crypto_key *dst,
diff --git a/net/core/dev.c b/net/core/dev.c
index 0ebaea16632..0cb3fe8d8e7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1172,6 +1172,7 @@ static int __dev_open(struct net_device *dev)
net_dmaengine_get();
dev_set_rx_mode(dev);
dev_activate(dev);
+ add_device_randomness(dev->dev_addr, dev->addr_len);
}
return ret;
@@ -3155,6 +3156,23 @@ void netdev_rx_handler_unregister(struct net_device *dev)
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
+/*
+ * Limit the use of PFMEMALLOC reserves to those protocols that implement
+ * the special handling of PFMEMALLOC skbs.
+ */
+static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
+{
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_ARP):
+ case __constant_htons(ETH_P_IP):
+ case __constant_htons(ETH_P_IPV6):
+ case __constant_htons(ETH_P_8021Q):
+ return true;
+ default:
+ return false;
+ }
+}
+
static int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
@@ -3164,14 +3182,27 @@ static int __netif_receive_skb(struct sk_buff *skb)
bool deliver_exact = false;
int ret = NET_RX_DROP;
__be16 type;
+ unsigned long pflags = current->flags;
net_timestamp_check(!netdev_tstamp_prequeue, skb);
trace_netif_receive_skb(skb);
+ /*
+ * PFMEMALLOC skbs are special, they should
+ * - be delivered to SOCK_MEMALLOC sockets only
+ * - stay away from userspace
+ * - have bounded memory usage
+ *
+ * Use PF_MEMALLOC as this saves us from propagating the allocation
+ * context down to all allocation sites.
+ */
+ if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+ current->flags |= PF_MEMALLOC;
+
/* if we've gotten here through NAPI, check netpoll */
if (netpoll_receive_skb(skb))
- return NET_RX_DROP;
+ goto out;
orig_dev = skb->dev;
@@ -3191,7 +3222,7 @@ another_round:
if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
skb = vlan_untag(skb);
if (unlikely(!skb))
- goto out;
+ goto unlock;
}
#ifdef CONFIG_NET_CLS_ACT
@@ -3201,6 +3232,9 @@ another_round:
}
#endif
+ if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+ goto skip_taps;
+
list_for_each_entry_rcu(ptype, &ptype_all, list) {
if (!ptype->dev || ptype->dev == skb->dev) {
if (pt_prev)
@@ -3209,13 +3243,18 @@ another_round:
}
}
+skip_taps:
#ifdef CONFIG_NET_CLS_ACT
skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
if (!skb)
- goto out;
+ goto unlock;
ncls:
#endif
+ if (sk_memalloc_socks() && skb_pfmemalloc(skb)
+ && !skb_pfmemalloc_protocol(skb))
+ goto drop;
+
rx_handler = rcu_dereference(skb->dev->rx_handler);
if (vlan_tx_tag_present(skb)) {
if (pt_prev) {
@@ -3225,7 +3264,7 @@ ncls:
if (vlan_do_receive(&skb, !rx_handler))
goto another_round;
else if (unlikely(!skb))
- goto out;
+ goto unlock;
}
if (rx_handler) {
@@ -3235,7 +3274,7 @@ ncls:
}
switch (rx_handler(&skb)) {
case RX_HANDLER_CONSUMED:
- goto out;
+ goto unlock;
case RX_HANDLER_ANOTHER:
goto another_round;
case RX_HANDLER_EXACT:
@@ -3268,6 +3307,7 @@ ncls:
else
ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
} else {
+drop:
atomic_long_inc(&skb->dev->rx_dropped);
kfree_skb(skb);
/* Jamal, now you will not able to escape explaining
@@ -3276,8 +3316,10 @@ ncls:
ret = NET_RX_DROP;
}
-out:
+unlock:
rcu_read_unlock();
+out:
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
return ret;
}
@@ -4801,6 +4843,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
err = ops->ndo_set_mac_address(dev, sa);
if (!err)
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ add_device_randomness(dev->dev_addr, dev->addr_len);
return err;
}
EXPORT_SYMBOL(dev_set_mac_address);
@@ -5579,6 +5622,7 @@ int register_netdevice(struct net_device *dev)
dev_init_scheduler(dev);
dev_hold(dev);
list_netdevice(dev);
+ add_device_randomness(dev->dev_addr, dev->addr_len);
/* Notify protocols, that a new device appeared. */
ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
diff --git a/net/core/filter.c b/net/core/filter.c
index d4ce2dc712e..907efd27ec7 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -83,6 +83,14 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
int err;
struct sk_filter *filter;
+ /*
+ * If the skb was allocated from pfmemalloc reserves, only
+ * allow SOCK_MEMALLOC sockets to use it as this socket is
+ * helping free memory
+ */
+ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
+ return -ENOMEM;
+
err = security_sock_rcv_skb(sk, skb);
if (err)
return err;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index bc9e380f0ab..2c5a0a06c4c 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -625,9 +625,13 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
.rta_id = id,
};
- if (expires)
- ci.rta_expires = jiffies_to_clock_t(expires);
+ if (expires) {
+ unsigned long clock;
+ clock = jiffies_to_clock_t(abs(expires));
+ clock = min_t(unsigned long, clock, INT_MAX);
+ ci.rta_expires = (expires > 0) ? clock : -clock;
+ }
return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci);
}
EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
@@ -1377,6 +1381,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
goto errout;
send_addr_notify = 1;
modified = 1;
+ add_device_randomness(dev->dev_addr, dev->addr_len);
}
if (tb[IFLA_MTU]) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 368f65c15e4..fe00d120816 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -145,6 +145,43 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
BUG();
}
+
+/*
+ * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells
+ * the caller if emergency pfmemalloc reserves are being used. If it is and
+ * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves
+ * may be used. Otherwise, the packet data may be discarded until enough
+ * memory is free
+ */
+#define kmalloc_reserve(size, gfp, node, pfmemalloc) \
+ __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc)
+void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip,
+ bool *pfmemalloc)
+{
+ void *obj;
+ bool ret_pfmemalloc = false;
+
+ /*
+ * Try a regular allocation, when that fails and we're not entitled
+ * to the reserves, fail.
+ */
+ obj = kmalloc_node_track_caller(size,
+ flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
+ node);
+ if (obj || !(gfp_pfmemalloc_allowed(flags)))
+ goto out;
+
+ /* Try again but now we are using pfmemalloc reserves */
+ ret_pfmemalloc = true;
+ obj = kmalloc_node_track_caller(size, flags, node);
+
+out:
+ if (pfmemalloc)
+ *pfmemalloc = ret_pfmemalloc;
+
+ return obj;
+}
+
/* Allocate a new skbuff. We do this ourselves so we can fill in a few
* 'private' fields and also do memory statistics to find all the
* [BEEP] leaks.
@@ -155,8 +192,10 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
* __alloc_skb - allocate a network buffer
* @size: size to allocate
* @gfp_mask: allocation mask
- * @fclone: allocate from fclone cache instead of head cache
- * and allocate a cloned (child) skb
+ * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache
+ * instead of head cache and allocate a cloned (child) skb.
+ * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
+ * allocations in case the data is required for writeback
* @node: numa node to allocate memory on
*
* Allocate a new &sk_buff. The returned buffer has no headroom and a
@@ -167,14 +206,19 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
* %GFP_ATOMIC.
*/
struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
- int fclone, int node)
+ int flags, int node)
{
struct kmem_cache *cache;
struct skb_shared_info *shinfo;
struct sk_buff *skb;
u8 *data;
+ bool pfmemalloc;
- cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;
+ cache = (flags & SKB_ALLOC_FCLONE)
+ ? skbuff_fclone_cache : skbuff_head_cache;
+
+ if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX))
+ gfp_mask |= __GFP_MEMALLOC;
/* Get the HEAD */
skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
@@ -189,7 +233,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
*/
size = SKB_DATA_ALIGN(size);
size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
- data = kmalloc_node_track_caller(size, gfp_mask, node);
+ data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc);
if (!data)
goto nodata;
/* kmalloc(size) might give us more room than requested.
@@ -207,6 +251,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
memset(skb, 0, offsetof(struct sk_buff, tail));
/* Account for allocated memory : skb + skb->head */
skb->truesize = SKB_TRUESIZE(size);
+ skb->pfmemalloc = pfmemalloc;
atomic_set(&skb->users, 1);
skb->head = data;
skb->data = data;
@@ -222,7 +267,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
atomic_set(&shinfo->dataref, 1);
kmemcheck_annotate_variable(shinfo->destructor_arg);
- if (fclone) {
+ if (flags & SKB_ALLOC_FCLONE) {
struct sk_buff *child = skb + 1;
atomic_t *fclone_ref = (atomic_t *) (child + 1);
@@ -232,6 +277,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
atomic_set(fclone_ref, 1);
child->fclone = SKB_FCLONE_UNAVAILABLE;
+ child->pfmemalloc = pfmemalloc;
}
out:
return skb;
@@ -302,14 +348,7 @@ static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
#define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES)
-/**
- * netdev_alloc_frag - allocate a page fragment
- * @fragsz: fragment size
- *
- * Allocates a frag from a page for receive buffer.
- * Uses GFP_ATOMIC allocations.
- */
-void *netdev_alloc_frag(unsigned int fragsz)
+static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
{
struct netdev_alloc_cache *nc;
void *data = NULL;
@@ -319,7 +358,7 @@ void *netdev_alloc_frag(unsigned int fragsz)
nc = &__get_cpu_var(netdev_alloc_cache);
if (unlikely(!nc->page)) {
refill:
- nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+ nc->page = alloc_page(gfp_mask);
if (unlikely(!nc->page))
goto end;
recycle:
@@ -343,6 +382,18 @@ end:
local_irq_restore(flags);
return data;
}
+
+/**
+ * netdev_alloc_frag - allocate a page fragment
+ * @fragsz: fragment size
+ *
+ * Allocates a frag from a page for receive buffer.
+ * Uses GFP_ATOMIC allocations.
+ */
+void *netdev_alloc_frag(unsigned int fragsz)
+{
+ return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
+}
EXPORT_SYMBOL(netdev_alloc_frag);
/**
@@ -366,7 +417,12 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) {
- void *data = netdev_alloc_frag(fragsz);
+ void *data;
+
+ if (sk_memalloc_socks())
+ gfp_mask |= __GFP_MEMALLOC;
+
+ data = __netdev_alloc_frag(fragsz, gfp_mask);
if (likely(data)) {
skb = build_skb(data, fragsz);
@@ -374,7 +430,8 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
put_page(virt_to_head_page(data));
}
} else {
- skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE);
+ skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
+ SKB_ALLOC_RX, NUMA_NO_NODE);
}
if (likely(skb)) {
skb_reserve(skb, NET_SKB_PAD);
@@ -656,6 +713,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
#if IS_ENABLED(CONFIG_IP_VS)
new->ipvs_property = old->ipvs_property;
#endif
+ new->pfmemalloc = old->pfmemalloc;
new->protocol = old->protocol;
new->mark = old->mark;
new->skb_iif = old->skb_iif;
@@ -814,6 +872,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
n->fclone = SKB_FCLONE_CLONE;
atomic_inc(fclone_ref);
} else {
+ if (skb_pfmemalloc(skb))
+ gfp_mask |= __GFP_MEMALLOC;
+
n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);
if (!n)
return NULL;
@@ -850,6 +911,13 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
}
+static inline int skb_alloc_rx_flag(const struct sk_buff *skb)
+{
+ if (skb_pfmemalloc(skb))
+ return SKB_ALLOC_RX;
+ return 0;
+}
+
/**
* skb_copy - create private copy of an sk_buff
* @skb: buffer to copy
@@ -871,7 +939,8 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
{
int headerlen = skb_headroom(skb);
unsigned int size = skb_end_offset(skb) + skb->data_len;
- struct sk_buff *n = alloc_skb(size, gfp_mask);
+ struct sk_buff *n = __alloc_skb(size, gfp_mask,
+ skb_alloc_rx_flag(skb), NUMA_NO_NODE);
if (!n)
return NULL;
@@ -906,7 +975,8 @@ EXPORT_SYMBOL(skb_copy);
struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
{
unsigned int size = skb_headlen(skb) + headroom;
- struct sk_buff *n = alloc_skb(size, gfp_mask);
+ struct sk_buff *n = __alloc_skb(size, gfp_mask,
+ skb_alloc_rx_flag(skb), NUMA_NO_NODE);
if (!n)
goto out;
@@ -979,8 +1049,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
size = SKB_DATA_ALIGN(size);
- data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
- gfp_mask);
+ if (skb_pfmemalloc(skb))
+ gfp_mask |= __GFP_MEMALLOC;
+ data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
+ gfp_mask, NUMA_NO_NODE, NULL);
if (!data)
goto nodata;
size = SKB_WITH_OVERHEAD(ksize(data));
@@ -1092,8 +1164,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
/*
* Allocate the copy buffer
*/
- struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
- gfp_mask);
+ struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom,
+ gfp_mask, skb_alloc_rx_flag(skb),
+ NUMA_NO_NODE);
int oldheadroom = skb_headroom(skb);
int head_copy_len, head_copy_off;
int off;
@@ -2775,8 +2848,9 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
skb_release_head_state(nskb);
__skb_push(nskb, doffset);
} else {
- nskb = alloc_skb(hsize + doffset + headroom,
- GFP_ATOMIC);
+ nskb = __alloc_skb(hsize + doffset + headroom,
+ GFP_ATOMIC, skb_alloc_rx_flag(skb),
+ NUMA_NO_NODE);
if (unlikely(!nskb))
goto err;
diff --git a/net/core/sock.c b/net/core/sock.c
index 2676a88f533..6b654b3ddfd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -142,7 +142,7 @@
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
struct proto *proto;
@@ -271,6 +271,61 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
EXPORT_SYMBOL(sysctl_optmem_max);
+struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE;
+EXPORT_SYMBOL_GPL(memalloc_socks);
+
+/**
+ * sk_set_memalloc - sets %SOCK_MEMALLOC
+ * @sk: socket to set it on
+ *
+ * Set %SOCK_MEMALLOC on a socket for access to emergency reserves.
+ * It's the responsibility of the admin to adjust min_free_kbytes
+ * to meet the requirements
+ */
+void sk_set_memalloc(struct sock *sk)
+{
+ sock_set_flag(sk, SOCK_MEMALLOC);
+ sk->sk_allocation |= __GFP_MEMALLOC;
+ static_key_slow_inc(&memalloc_socks);
+}
+EXPORT_SYMBOL_GPL(sk_set_memalloc);
+
+void sk_clear_memalloc(struct sock *sk)
+{
+ sock_reset_flag(sk, SOCK_MEMALLOC);
+ sk->sk_allocation &= ~__GFP_MEMALLOC;
+ static_key_slow_dec(&memalloc_socks);
+
+ /*
+ * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
+ * progress of swapping. However, if SOCK_MEMALLOC is cleared while
+ * it has rmem allocations there is a risk that the user of the
+ * socket cannot make forward progress due to exceeding the rmem
+ * limits. By rights, sk_clear_memalloc() should only be called
+ * on sockets being torn down but warn and reset the accounting if
+ * that assumption breaks.
+ */
+ if (WARN_ON(sk->sk_forward_alloc))
+ sk_mem_reclaim(sk);
+}
+EXPORT_SYMBOL_GPL(sk_clear_memalloc);
+
+int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ int ret;
+ unsigned long pflags = current->flags;
+
+ /* these should have been dropped before queueing */
+ BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));
+
+ current->flags |= PF_MEMALLOC;
+ ret = sk->sk_backlog_rcv(sk, skb);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
+
+ return ret;
+}
+EXPORT_SYMBOL(__sk_backlog_rcv);
+
#if defined(CONFIG_CGROUPS)
#if !defined(CONFIG_NET_CLS_CGROUP)
int net_cls_subsys_id = -1;
@@ -353,7 +408,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
if (err)
return err;
- if (!sk_rmem_schedule(sk, skb->truesize)) {
+ if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
atomic_inc(&sk->sk_drops);
return -ENOBUFS;
}
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index ae2ccf2890e..15ca63ec604 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -49,7 +49,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
-obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o
+obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o
obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 8732cc7920e..c43ae3fba79 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1046,6 +1046,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
if (event == NETDEV_UNREGISTER) {
fib_disable_ip(dev, 2, -1);
+ rt_flush_dev(dev);
return NOTIFY_DONE;
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index da0cc2e6b25..da80dc14cc7 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -140,6 +140,21 @@ const struct fib_prop fib_props[RTN_MAX + 1] = {
},
};
+static void rt_fibinfo_free(struct rtable __rcu **rtp)
+{
+ struct rtable *rt = rcu_dereference_protected(*rtp, 1);
+
+ if (!rt)
+ return;
+
+ /* Not even needed : RCU_INIT_POINTER(*rtp, NULL);
+ * because we waited an RCU grace period before calling
+ * free_fib_info_rcu()
+ */
+
+ dst_free(&rt->dst);
+}
+
static void free_nh_exceptions(struct fib_nh *nh)
{
struct fnhe_hash_bucket *hash = nh->nh_exceptions;
@@ -153,6 +168,9 @@ static void free_nh_exceptions(struct fib_nh *nh)
struct fib_nh_exception *next;
next = rcu_dereference_protected(fnhe->fnhe_next, 1);
+
+ rt_fibinfo_free(&fnhe->fnhe_rth);
+
kfree(fnhe);
fnhe = next;
@@ -161,6 +179,23 @@ static void free_nh_exceptions(struct fib_nh *nh)
kfree(hash);
}
+static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
+{
+ int cpu;
+
+ if (!rtp)
+ return;
+
+ for_each_possible_cpu(cpu) {
+ struct rtable *rt;
+
+ rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1);
+ if (rt)
+ dst_free(&rt->dst);
+ }
+ free_percpu(rtp);
+}
+
/* Release a nexthop info record */
static void free_fib_info_rcu(struct rcu_head *head)
{
@@ -171,10 +206,8 @@ static void free_fib_info_rcu(struct rcu_head *head)
dev_put(nexthop_nh->nh_dev);
if (nexthop_nh->nh_exceptions)
free_nh_exceptions(nexthop_nh);
- if (nexthop_nh->nh_rth_output)
- dst_free(&nexthop_nh->nh_rth_output->dst);
- if (nexthop_nh->nh_rth_input)
- dst_free(&nexthop_nh->nh_rth_input->dst);
+ rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
+ rt_fibinfo_free(&nexthop_nh->nh_rth_input);
} endfor_nexthops(fi);
release_net(fi->fib_net);
@@ -804,6 +837,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
fi->fib_nhs = nhs;
change_nexthops(fi) {
nexthop_nh->nh_parent = fi;
+ nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
} endfor_nexthops(fi)
if (cfg->fc_mx) {
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 18cbc15b20d..f0cdb30921c 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -159,7 +159,6 @@ struct trie {
#endif
};
-static void put_child(struct trie *t, struct tnode *tn, int i, struct rt_trie_node *n);
static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n,
int wasfull);
static struct rt_trie_node *resize(struct trie *t, struct tnode *tn);
@@ -473,7 +472,7 @@ static struct tnode *tnode_new(t_key key, int pos, int bits)
}
pr_debug("AT %p s=%zu %zu\n", tn, sizeof(struct tnode),
- sizeof(struct rt_trie_node) << bits);
+ sizeof(struct rt_trie_node *) << bits);
return tn;
}
@@ -490,7 +489,7 @@ static inline int tnode_full(const struct tnode *tn, const struct rt_trie_node *
return ((struct tnode *) n)->pos == tn->pos + tn->bits;
}
-static inline void put_child(struct trie *t, struct tnode *tn, int i,
+static inline void put_child(struct tnode *tn, int i,
struct rt_trie_node *n)
{
tnode_put_child_reorg(tn, i, n, -1);
@@ -754,8 +753,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn)
goto nomem;
}
- put_child(t, tn, 2*i, (struct rt_trie_node *) left);
- put_child(t, tn, 2*i+1, (struct rt_trie_node *) right);
+ put_child(tn, 2*i, (struct rt_trie_node *) left);
+ put_child(tn, 2*i+1, (struct rt_trie_node *) right);
}
}
@@ -776,9 +775,9 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn)
if (tkey_extract_bits(node->key,
oldtnode->pos + oldtnode->bits,
1) == 0)
- put_child(t, tn, 2*i, node);
+ put_child(tn, 2*i, node);
else
- put_child(t, tn, 2*i+1, node);
+ put_child(tn, 2*i+1, node);
continue;
}
@@ -786,8 +785,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn)
inode = (struct tnode *) node;
if (inode->bits == 1) {
- put_child(t, tn, 2*i, rtnl_dereference(inode->child[0]));
- put_child(t, tn, 2*i+1, rtnl_dereference(inode->child[1]));
+ put_child(tn, 2*i, rtnl_dereference(inode->child[0]));
+ put_child(tn, 2*i+1, rtnl_dereference(inode->child[1]));
tnode_free_safe(inode);
continue;
@@ -817,22 +816,22 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn)
*/
left = (struct tnode *) tnode_get_child(tn, 2*i);
- put_child(t, tn, 2*i, NULL);
+ put_child(tn, 2*i, NULL);
BUG_ON(!left);
right = (struct tnode *) tnode_get_child(tn, 2*i+1);
- put_child(t, tn, 2*i+1, NULL);
+ put_child(tn, 2*i+1, NULL);
BUG_ON(!right);
size = tnode_child_length(left);
for (j = 0; j < size; j++) {
- put_child(t, left, j, rtnl_dereference(inode->child[j]));
- put_child(t, right, j, rtnl_dereference(inode->child[j + size]));
+ put_child(left, j, rtnl_dereference(inode->child[j]));
+ put_child(right, j, rtnl_dereference(inode->child[j + size]));
}
- put_child(t, tn, 2*i, resize(t, left));
- put_child(t, tn, 2*i+1, resize(t, right));
+ put_child(tn, 2*i, resize(t, left));
+ put_child(tn, 2*i+1, resize(t, right));
tnode_free_safe(inode);
}
@@ -877,7 +876,7 @@ static struct tnode *halve(struct trie *t, struct tnode *tn)
if (!newn)
goto nomem;
- put_child(t, tn, i/2, (struct rt_trie_node *)newn);
+ put_child(tn, i/2, (struct rt_trie_node *)newn);
}
}
@@ -892,21 +891,21 @@ static struct tnode *halve(struct trie *t, struct tnode *tn)
if (left == NULL) {
if (right == NULL) /* Both are empty */
continue;
- put_child(t, tn, i/2, right);
+ put_child(tn, i/2, right);
continue;
}
if (right == NULL) {
- put_child(t, tn, i/2, left);
+ put_child(tn, i/2, left);
continue;
}
/* Two nonempty children */
newBinNode = (struct tnode *) tnode_get_child(tn, i/2);
- put_child(t, tn, i/2, NULL);
- put_child(t, newBinNode, 0, left);
- put_child(t, newBinNode, 1, right);
- put_child(t, tn, i/2, resize(t, newBinNode));
+ put_child(tn, i/2, NULL);
+ put_child(newBinNode, 0, left);
+ put_child(newBinNode, 1, right);
+ put_child(tn, i/2, resize(t, newBinNode));
}
tnode_free_safe(oldtnode);
return tn;
@@ -1125,7 +1124,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen)
node_set_parent((struct rt_trie_node *)l, tp);
cindex = tkey_extract_bits(key, tp->pos, tp->bits);
- put_child(t, tp, cindex, (struct rt_trie_node *)l);
+ put_child(tp, cindex, (struct rt_trie_node *)l);
} else {
/* Case 3: n is a LEAF or a TNODE and the key doesn't match. */
/*
@@ -1155,12 +1154,12 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen)
node_set_parent((struct rt_trie_node *)tn, tp);
missbit = tkey_extract_bits(key, newpos, 1);
- put_child(t, tn, missbit, (struct rt_trie_node *)l);
- put_child(t, tn, 1-missbit, n);
+ put_child(tn, missbit, (struct rt_trie_node *)l);
+ put_child(tn, 1-missbit, n);
if (tp) {
cindex = tkey_extract_bits(key, tp->pos, tp->bits);
- put_child(t, tp, cindex, (struct rt_trie_node *)tn);
+ put_child(tp, cindex, (struct rt_trie_node *)tn);
} else {
rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn);
tp = tn;
@@ -1619,7 +1618,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l)
if (tp) {
t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits);
- put_child(t, tp, cindex, NULL);
+ put_child(tp, cindex, NULL);
trie_rebalance(t, tp);
} else
RCU_INIT_POINTER(t->trie, NULL);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 981ff1eef28..f1395a6fb35 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -325,14 +325,12 @@ static int ip_rcv_finish(struct sk_buff *skb)
const struct net_protocol *ipprot;
int protocol = iph->protocol;
- rcu_read_lock();
ipprot = rcu_dereference(inet_protos[protocol]);
if (ipprot && ipprot->early_demux) {
ipprot->early_demux(skb);
/* must reload iph, skb->head might have changed */
iph = ip_hdr(skb);
}
- rcu_read_unlock();
}
/*
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index fc1a81ca79a..c035251beb0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -147,6 +147,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
static void ip_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
+static void ipv4_dst_destroy(struct dst_entry *dst);
static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int how)
@@ -170,6 +171,7 @@ static struct dst_ops ipv4_dst_ops = {
.default_advmss = ipv4_default_advmss,
.mtu = ipv4_mtu,
.cow_metrics = ipv4_cow_metrics,
+ .destroy = ipv4_dst_destroy,
.ifdown = ipv4_dst_ifdown,
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
@@ -587,11 +589,17 @@ static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk,
build_sk_flow_key(fl4, sk);
}
-static DEFINE_SEQLOCK(fnhe_seqlock);
+static inline void rt_free(struct rtable *rt)
+{
+ call_rcu(&rt->dst.rcu_head, dst_rcu_free);
+}
+
+static DEFINE_SPINLOCK(fnhe_lock);
static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
{
struct fib_nh_exception *fnhe, *oldest;
+ struct rtable *orig;
oldest = rcu_dereference(hash->chain);
for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe;
@@ -599,6 +607,11 @@ static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp))
oldest = fnhe;
}
+ orig = rcu_dereference(oldest->fnhe_rth);
+ if (orig) {
+ RCU_INIT_POINTER(oldest->fnhe_rth, NULL);
+ rt_free(orig);
+ }
return oldest;
}
@@ -620,7 +633,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
int depth;
u32 hval = fnhe_hashfun(daddr);
- write_seqlock_bh(&fnhe_seqlock);
+ spin_lock_bh(&fnhe_lock);
hash = nh->nh_exceptions;
if (!hash) {
@@ -667,7 +680,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
fnhe->fnhe_stamp = jiffies;
out_unlock:
- write_sequnlock_bh(&fnhe_seqlock);
+ spin_unlock_bh(&fnhe_lock);
return;
}
@@ -1164,53 +1177,62 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
return NULL;
}
-static void rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
+static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
__be32 daddr)
{
- __be32 fnhe_daddr, gw;
- unsigned long expires;
- unsigned int seq;
- u32 pmtu;
-
-restart:
- seq = read_seqbegin(&fnhe_seqlock);
- fnhe_daddr = fnhe->fnhe_daddr;
- gw = fnhe->fnhe_gw;
- pmtu = fnhe->fnhe_pmtu;
- expires = fnhe->fnhe_expires;
- if (read_seqretry(&fnhe_seqlock, seq))
- goto restart;
-
- if (daddr != fnhe_daddr)
- return;
+ bool ret = false;
+
+ spin_lock_bh(&fnhe_lock);
- if (pmtu) {
- unsigned long diff = expires - jiffies;
+ if (daddr == fnhe->fnhe_daddr) {
+ struct rtable *orig;
- if (time_before(jiffies, expires)) {
- rt->rt_pmtu = pmtu;
- dst_set_expires(&rt->dst, diff);
+ if (fnhe->fnhe_pmtu) {
+ unsigned long expires = fnhe->fnhe_expires;
+ unsigned long diff = expires - jiffies;
+
+ if (time_before(jiffies, expires)) {
+ rt->rt_pmtu = fnhe->fnhe_pmtu;
+ dst_set_expires(&rt->dst, diff);
+ }
}
+ if (fnhe->fnhe_gw) {
+ rt->rt_flags |= RTCF_REDIRECTED;
+ rt->rt_gateway = fnhe->fnhe_gw;
+ }
+
+ orig = rcu_dereference(fnhe->fnhe_rth);
+ rcu_assign_pointer(fnhe->fnhe_rth, rt);
+ if (orig)
+ rt_free(orig);
+
+ fnhe->fnhe_stamp = jiffies;
+ ret = true;
+ } else {
+ /* Routes we intend to cache in nexthop exception have
+ * the DST_NOCACHE bit clear. However, if we are
+ * unsuccessful at storing this route into the cache
+ * we really need to set it.
+ */
+ rt->dst.flags |= DST_NOCACHE;
}
- if (gw) {
- rt->rt_flags |= RTCF_REDIRECTED;
- rt->rt_gateway = gw;
- }
- fnhe->fnhe_stamp = jiffies;
-}
+ spin_unlock_bh(&fnhe_lock);
-static inline void rt_free(struct rtable *rt)
-{
- call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
+ return ret;
}
-static void rt_cache_route(struct fib_nh *nh, struct rtable *rt)
+static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
{
- struct rtable *orig, *prev, **p = &nh->nh_rth_output;
-
- if (rt_is_input_route(rt))
- p = &nh->nh_rth_input;
+ struct rtable *orig, *prev, **p;
+ bool ret = true;
+ if (rt_is_input_route(rt)) {
+ p = (struct rtable **)&nh->nh_rth_input;
+ } else {
+ if (!nh->nh_pcpu_rth_output)
+ goto nocache;
+ p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output);
+ }
orig = *p;
prev = cmpxchg(p, orig, rt);
@@ -1223,7 +1245,50 @@ static void rt_cache_route(struct fib_nh *nh, struct rtable *rt)
* unsuccessful at storing this route into the cache
* we really need to set it.
*/
+nocache:
rt->dst.flags |= DST_NOCACHE;
+ ret = false;
+ }
+
+ return ret;
+}
+
+static DEFINE_SPINLOCK(rt_uncached_lock);
+static LIST_HEAD(rt_uncached_list);
+
+static void rt_add_uncached_list(struct rtable *rt)
+{
+ spin_lock_bh(&rt_uncached_lock);
+ list_add_tail(&rt->rt_uncached, &rt_uncached_list);
+ spin_unlock_bh(&rt_uncached_lock);
+}
+
+static void ipv4_dst_destroy(struct dst_entry *dst)
+{
+ struct rtable *rt = (struct rtable *) dst;
+
+ if (dst->flags & DST_NOCACHE) {
+ spin_lock_bh(&rt_uncached_lock);
+ list_del(&rt->rt_uncached);
+ spin_unlock_bh(&rt_uncached_lock);
+ }
+}
+
+void rt_flush_dev(struct net_device *dev)
+{
+ if (!list_empty(&rt_uncached_list)) {
+ struct net *net = dev_net(dev);
+ struct rtable *rt;
+
+ spin_lock_bh(&rt_uncached_lock);
+ list_for_each_entry(rt, &rt_uncached_list, rt_uncached) {
+ if (rt->dst.dev != dev)
+ continue;
+ rt->dst.dev = net->loopback_dev;
+ dev_hold(rt->dst.dev);
+ dev_put(dev);
+ }
+ spin_unlock_bh(&rt_uncached_lock);
}
}
@@ -1239,20 +1304,24 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
struct fib_nh_exception *fnhe,
struct fib_info *fi, u16 type, u32 itag)
{
+ bool cached = false;
+
if (fi) {
struct fib_nh *nh = &FIB_RES_NH(*res);
if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK)
rt->rt_gateway = nh->nh_gw;
- if (unlikely(fnhe))
- rt_bind_exception(rt, fnhe, daddr);
dst_init_metrics(&rt->dst, fi->fib_metrics, true);
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
#endif
- if (!(rt->dst.flags & DST_NOCACHE))
- rt_cache_route(nh, rt);
+ if (unlikely(fnhe))
+ cached = rt_bind_exception(rt, fnhe, daddr);
+ else if (!(rt->dst.flags & DST_NOCACHE))
+ cached = rt_cache_route(nh, rt);
}
+ if (unlikely(!cached))
+ rt_add_uncached_list(rt);
#ifdef CONFIG_IP_ROUTE_CLASSID
#ifdef CONFIG_IP_MULTIPLE_TABLES
@@ -1319,6 +1388,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ INIT_LIST_HEAD(&rth->rt_uncached);
if (our) {
rth->dst.input= ip_local_deliver;
rth->rt_flags |= RTCF_LOCAL;
@@ -1420,7 +1490,7 @@ static int __mkroute_input(struct sk_buff *skb,
do_cache = false;
if (res->fi) {
if (!itag) {
- rth = FIB_RES_NH(*res).nh_rth_input;
+ rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
goto out;
@@ -1444,6 +1514,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ INIT_LIST_HEAD(&rth->rt_uncached);
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
@@ -1582,7 +1653,7 @@ local_input:
do_cache = false;
if (res.fi) {
if (!itag) {
- rth = FIB_RES_NH(res).nh_rth_input;
+ rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input);
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
err = 0;
@@ -1610,6 +1681,7 @@ local_input:
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ INIT_LIST_HEAD(&rth->rt_uncached);
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
@@ -1748,19 +1820,23 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
fnhe = NULL;
if (fi) {
+ struct rtable __rcu **prth;
+
fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr);
- if (!fnhe) {
- rth = FIB_RES_NH(*res).nh_rth_output;
- if (rt_cache_valid(rth)) {
- dst_hold(&rth->dst);
- return rth;
- }
+ if (fnhe)
+ prth = &fnhe->fnhe_rth;
+ else
+ prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output);
+ rth = rcu_dereference(*prth);
+ if (rt_cache_valid(rth)) {
+ dst_hold(&rth->dst);
+ return rth;
}
}
rth = rt_dst_alloc(dev_out,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(in_dev, NOXFRM),
- fi && !fnhe);
+ fi);
if (!rth)
return ERR_PTR(-ENOBUFS);
@@ -1773,6 +1849,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_iif = orig_oif ? : 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ INIT_LIST_HEAD(&rth->rt_uncached);
RT_CACHE_STAT_INC(out_slow_tot);
@@ -2052,6 +2129,8 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_type = ort->rt_type;
rt->rt_gateway = ort->rt_gateway;
+ INIT_LIST_HEAD(&rt->rt_uncached);
+
dst_free(new);
}
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 5840c325572..1b5ce96707a 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -184,7 +184,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write,
int ret;
unsigned long vec[3];
struct net *net = current->nsproxy->net_ns;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
struct mem_cgroup *memcg;
#endif
@@ -203,7 +203,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write,
if (ret)
return ret;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
rcu_read_lock();
memcg = mem_cgroup_from_task(current);
@@ -784,13 +784,6 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "rt_cache_rebuild_count",
- .data = &init_net.ipv4.sysctl_rt_cache_rebuild_count,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "ping_group_range",
.data = &init_net.ipv4.sysctl_ping_group_range,
.maxlen = sizeof(init_net.ipv4.sysctl_ping_group_range),
@@ -829,8 +822,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
table[5].data =
&net->ipv4.sysctl_icmp_ratemask;
table[6].data =
- &net->ipv4.sysctl_rt_cache_rebuild_count;
- table[7].data =
&net->ipv4.sysctl_ping_group_range;
}
@@ -842,8 +833,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
net->ipv4.sysctl_ping_group_range[0] = 1;
net->ipv4.sysctl_ping_group_range[1] = 0;
- net->ipv4.sysctl_rt_cache_rebuild_count = 4;
-
tcp_init_mem(net);
net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a356e1fecf9..2fd2bc9e3c6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4351,19 +4351,20 @@ static void tcp_ofo_queue(struct sock *sk)
static bool tcp_prune_ofo_queue(struct sock *sk);
static int tcp_prune_queue(struct sock *sk);
-static int tcp_try_rmem_schedule(struct sock *sk, unsigned int size)
+static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb,
+ unsigned int size)
{
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
- !sk_rmem_schedule(sk, size)) {
+ !sk_rmem_schedule(sk, skb, size)) {
if (tcp_prune_queue(sk) < 0)
return -1;
- if (!sk_rmem_schedule(sk, size)) {
+ if (!sk_rmem_schedule(sk, skb, size)) {
if (!tcp_prune_ofo_queue(sk))
return -1;
- if (!sk_rmem_schedule(sk, size))
+ if (!sk_rmem_schedule(sk, skb, size))
return -1;
}
}
@@ -4418,7 +4419,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
TCP_ECN_check_ce(tp, skb);
- if (unlikely(tcp_try_rmem_schedule(sk, skb->truesize))) {
+ if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP);
__kfree_skb(skb);
return;
@@ -4552,17 +4553,17 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
{
- struct sk_buff *skb;
+ struct sk_buff *skb = NULL;
struct tcphdr *th;
bool fragstolen;
- if (tcp_try_rmem_schedule(sk, size + sizeof(*th)))
- goto err;
-
skb = alloc_skb(size + sizeof(*th), sk->sk_allocation);
if (!skb)
goto err;
+ if (tcp_try_rmem_schedule(sk, skb, size + sizeof(*th)))
+ goto err_free;
+
th = (struct tcphdr *)skb_put(skb, sizeof(*th));
skb_reset_transport_header(skb);
memset(th, 0, sizeof(*th));
@@ -4633,7 +4634,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
if (eaten <= 0) {
queue_and_out:
if (eaten < 0 &&
- tcp_try_rmem_schedule(sk, skb->truesize))
+ tcp_try_rmem_schedule(sk, skb, skb->truesize))
goto drop;
eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
@@ -5604,8 +5605,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
tcp_set_state(sk, TCP_ESTABLISHED);
if (skb != NULL) {
- sk->sk_rx_dst = dst_clone(skb_dst(skb));
- inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+ inet_sk_rx_dst_set(sk, skb);
security_inet_conn_established(sk, skb);
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2fbd9921253..42b2a6a7309 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1617,19 +1617,19 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
#endif
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
+ struct dst_entry *dst = sk->sk_rx_dst;
+
sock_rps_save_rxhash(sk, skb);
- if (sk->sk_rx_dst) {
- struct dst_entry *dst = sk->sk_rx_dst;
+ if (dst) {
if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
dst->ops->check(dst, 0) == NULL) {
dst_release(dst);
sk->sk_rx_dst = NULL;
}
}
- if (unlikely(sk->sk_rx_dst == NULL)) {
- sk->sk_rx_dst = dst_clone(skb_dst(skb));
- inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
- }
+ if (unlikely(sk->sk_rx_dst == NULL))
+ inet_sk_rx_dst_set(sk, skb);
+
if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
rsk = sk;
goto reset;
@@ -2633,7 +2633,7 @@ struct proto tcp_prot = {
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
.init_cgroup = tcp_init_cgroup,
.destroy_cgroup = tcp_destroy_cgroup,
.proto_cgroup = tcp_proto_cgroup,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 3f1cc2028ed..232a90c3ec8 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -387,8 +387,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
struct tcp_sock *oldtp = tcp_sk(sk);
struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
- newsk->sk_rx_dst = dst_clone(skb_dst(skb));
- inet_sk(newsk)->rx_dst_ifindex = skb->skb_iif;
+ inet_sk_rx_dst_set(newsk, skb);
/* TCP Cookie Transactions require space for the cookie pair,
* as it differs for each connection. There is no need to
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 33cd065cfbd..3f1bcff0b10 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2045,7 +2045,8 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
if (unlikely(sk->sk_state == TCP_CLOSE))
return;
- if (tcp_write_xmit(sk, cur_mss, nonagle, 0, GFP_ATOMIC))
+ if (tcp_write_xmit(sk, cur_mss, nonagle, 0,
+ sk_gfp_atomic(sk, GFP_ATOMIC)))
tcp_check_probe_timer(sk);
}
@@ -2666,7 +2667,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired)
s_data_desired = cvp->s_data_desired;
- skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, GFP_ATOMIC);
+ skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired,
+ sk_gfp_atomic(sk, GFP_ATOMIC));
if (unlikely(!skb)) {
dst_release(dst);
return NULL;
@@ -3064,7 +3066,7 @@ void tcp_send_ack(struct sock *sk)
* tcp_transmit_skb() will set the ownership to this
* sock.
*/
- buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
+ buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC));
if (buff == NULL) {
inet_csk_schedule_ack(sk);
inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
@@ -3079,7 +3081,7 @@ void tcp_send_ack(struct sock *sk)
/* Send it off, this clears delayed acks for us. */
TCP_SKB_CB(buff)->when = tcp_time_stamp;
- tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC);
+ tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));
}
/* This routine sends a packet with an out of date sequence
@@ -3099,7 +3101,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
struct sk_buff *skb;
/* We don't queue it, tcp_transmit_skb() sets ownership. */
- skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
+ skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC));
if (skb == NULL)
return -1;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index c6281847f16..681ea2f413e 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -92,6 +92,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
xdst->u.rt.rt_type = rt->rt_type;
xdst->u.rt.rt_gateway = rt->rt_gateway;
xdst->u.rt.rt_pmtu = rt->rt_pmtu;
+ INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
return 0;
}
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 47975e363fc..a52d864d562 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -52,11 +52,9 @@ int ip6_rcv_finish(struct sk_buff *skb)
if (sysctl_ip_early_demux && !skb_dst(skb)) {
const struct inet6_protocol *ipprot;
- rcu_read_lock();
ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
if (ipprot && ipprot->early_demux)
ipprot->early_demux(skb);
- rcu_read_unlock();
}
if (!skb_dst(skb))
ip6_route_input(skb);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index cf02cb97bbd..8e80fd27910 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2480,12 +2480,8 @@ static int rt6_fill_node(struct net *net,
goto nla_put_failure;
if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric))
goto nla_put_failure;
- if (!(rt->rt6i_flags & RTF_EXPIRES))
- expires = 0;
- else if (rt->dst.expires - jiffies < INT_MAX)
- expires = rt->dst.expires - jiffies;
- else
- expires = INT_MAX;
+
+ expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0;
if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0)
goto nla_put_failure;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 221224e7250..c66b90f71c9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1299,7 +1299,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
/* Clone pktoptions received with SYN */
newnp->pktoptions = NULL;
if (treq->pktopts != NULL) {
- newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC);
+ newnp->pktoptions = skb_clone(treq->pktopts,
+ sk_gfp_atomic(sk, GFP_ATOMIC));
consume_skb(treq->pktopts);
treq->pktopts = NULL;
if (newnp->pktoptions)
@@ -1349,7 +1350,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
* across. Shucks.
*/
tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr,
- AF_INET6, key->key, key->keylen, GFP_ATOMIC);
+ AF_INET6, key->key, key->keylen,
+ sk_gfp_atomic(sk, GFP_ATOMIC));
}
#endif
@@ -1442,7 +1444,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
--ANK (980728)
*/
if (np->rxopt.all)
- opt_skb = skb_clone(skb, GFP_ATOMIC);
+ opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC));
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
sock_rps_save_rxhash(sk, skb);
@@ -2015,7 +2017,7 @@ struct proto tcpv6_prot = {
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
.proto_cgroup = tcp_proto_cgroup,
#endif
};
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 33d89477619..10c018a5b9f 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -702,7 +702,8 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
if (rx_count >= asoc->base.sk->sk_rcvbuf) {
if ((asoc->base.sk->sk_userlocks & SOCK_RCVBUF_LOCK) ||
- (!sk_rmem_schedule(asoc->base.sk, chunk->skb->truesize)))
+ (!sk_rmem_schedule(asoc->base.sk, chunk->skb,
+ chunk->skb->truesize)))
goto fail;
}
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 9fe8857d8d5..03d03e37a7d 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -21,6 +21,11 @@ config SUNRPC_XPRT_RDMA
If unsure, say N.
+config SUNRPC_SWAP
+ bool
+ depends on SUNRPC
+ select NETVM
+
config RPCSEC_GSS_KRB5
tristate "Secure RPC: Kerberos V mechanism"
depends on SUNRPC && CRYPTO
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index b05df36692f..fa48c60aef2 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -717,6 +717,15 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt)
atomic_inc(&clnt->cl_count);
if (clnt->cl_softrtry)
task->tk_flags |= RPC_TASK_SOFT;
+ if (sk_memalloc_socks()) {
+ struct rpc_xprt *xprt;
+
+ rcu_read_lock();
+ xprt = rcu_dereference(clnt->cl_xprt);
+ if (xprt->swapper)
+ task->tk_flags |= RPC_TASK_SWAPPER;
+ rcu_read_unlock();
+ }
/* Add to the client's list of all tasks */
spin_lock(&clnt->cl_lock);
list_add_tail(&task->tk_task, &clnt->cl_tasks);
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 92509ffe15f..a70acae496e 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -251,7 +251,7 @@ static int rpcb_create_local_unix(struct net *net)
if (IS_ERR(clnt)) {
dprintk("RPC: failed to create AF_LOCAL rpcbind "
"client (errno %ld).\n", PTR_ERR(clnt));
- result = -PTR_ERR(clnt);
+ result = PTR_ERR(clnt);
goto out;
}
@@ -298,7 +298,7 @@ static int rpcb_create_local_net(struct net *net)
if (IS_ERR(clnt)) {
dprintk("RPC: failed to create local rpcbind "
"client (errno %ld).\n", PTR_ERR(clnt));
- result = -PTR_ERR(clnt);
+ result = PTR_ERR(clnt);
goto out;
}
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 994cfea2bad..128494ec9a6 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -300,8 +300,9 @@ EXPORT_SYMBOL_GPL(__rpc_wait_for_completion_task);
/*
* Make an RPC task runnable.
*
- * Note: If the task is ASYNC, this must be called with
- * the spinlock held to protect the wait queue operation.
+ * Note: If the task is ASYNC, and is being made runnable after sitting on an
+ * rpc_wait_queue, this must be called with the queue spinlock held to protect
+ * the wait queue operation.
*/
static void rpc_make_runnable(struct rpc_task *task)
{
@@ -790,7 +791,9 @@ void rpc_execute(struct rpc_task *task)
static void rpc_async_schedule(struct work_struct *work)
{
+ current->flags |= PF_FSTRANS;
__rpc_execute(container_of(work, struct rpc_task, u.tk_work));
+ current->flags &= ~PF_FSTRANS;
}
/**
@@ -812,7 +815,10 @@ static void rpc_async_schedule(struct work_struct *work)
void *rpc_malloc(struct rpc_task *task, size_t size)
{
struct rpc_buffer *buf;
- gfp_t gfp = RPC_IS_SWAPPER(task) ? GFP_ATOMIC : GFP_NOWAIT;
+ gfp_t gfp = GFP_NOWAIT;
+
+ if (RPC_IS_SWAPPER(task))
+ gfp |= __GFP_MEMALLOC;
size += sizeof(struct rpc_buffer);
if (size <= RPC_BUFFER_MAXSIZE)
@@ -886,7 +892,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
static struct rpc_task *
rpc_alloc_task(void)
{
- return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOFS);
+ return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOIO);
}
/*
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index b446e100286..06cdbff79e4 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -200,6 +200,7 @@ xprt_rdma_connect_worker(struct work_struct *work)
int rc = 0;
if (!xprt->shutdown) {
+ current->flags |= PF_FSTRANS;
xprt_clear_connected(xprt);
dprintk("RPC: %s: %sconnect\n", __func__,
@@ -212,10 +213,10 @@ xprt_rdma_connect_worker(struct work_struct *work)
out:
xprt_wake_pending_tasks(xprt, rc);
-
out_clear:
dprintk("RPC: %s: exit\n", __func__);
xprt_clear_connecting(xprt);
+ current->flags &= ~PF_FSTRANS;
}
/*
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 62d0dac8f78..400567243f8 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1892,6 +1892,8 @@ static void xs_local_setup_socket(struct work_struct *work)
if (xprt->shutdown)
goto out;
+ current->flags |= PF_FSTRANS;
+
clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
status = __sock_create(xprt->xprt_net, AF_LOCAL,
SOCK_STREAM, 0, &sock, 1);
@@ -1925,7 +1927,47 @@ static void xs_local_setup_socket(struct work_struct *work)
out:
xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, status);
+ current->flags &= ~PF_FSTRANS;
+}
+
+#ifdef CONFIG_SUNRPC_SWAP
+static void xs_set_memalloc(struct rpc_xprt *xprt)
+{
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
+ xprt);
+
+ if (xprt->swapper)
+ sk_set_memalloc(transport->inet);
+}
+
+/**
+ * xs_swapper - Tag this transport as being used for swap.
+ * @xprt: transport to tag
+ * @enable: enable/disable
+ *
+ */
+int xs_swapper(struct rpc_xprt *xprt, int enable)
+{
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
+ xprt);
+ int err = 0;
+
+ if (enable) {
+ xprt->swapper++;
+ xs_set_memalloc(xprt);
+ } else if (xprt->swapper) {
+ xprt->swapper--;
+ sk_clear_memalloc(transport->inet);
+ }
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(xs_swapper);
+#else
+static void xs_set_memalloc(struct rpc_xprt *xprt)
+{
}
+#endif
static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
{
@@ -1951,6 +1993,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
transport->sock = sock;
transport->inet = sk;
+ xs_set_memalloc(xprt);
+
write_unlock_bh(&sk->sk_callback_lock);
}
xs_udp_do_set_buffer_size(xprt);
@@ -1967,6 +2011,8 @@ static void xs_udp_setup_socket(struct work_struct *work)
if (xprt->shutdown)
goto out;
+ current->flags |= PF_FSTRANS;
+
/* Start by resetting any existing state */
xs_reset_transport(transport);
sock = xs_create_sock(xprt, transport,
@@ -1985,6 +2031,7 @@ static void xs_udp_setup_socket(struct work_struct *work)
out:
xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, status);
+ current->flags &= ~PF_FSTRANS;
}
/*
@@ -2075,6 +2122,8 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
if (!xprt_bound(xprt))
goto out;
+ xs_set_memalloc(xprt);
+
/* Tell the socket layer to start connecting... */
xprt->stat.connect_count++;
xprt->stat.connect_start = jiffies;
@@ -2110,6 +2159,8 @@ static void xs_tcp_setup_socket(struct work_struct *work)
if (xprt->shutdown)
goto out;
+ current->flags |= PF_FSTRANS;
+
if (!sock) {
clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
sock = xs_create_sock(xprt, transport,
@@ -2159,6 +2210,7 @@ static void xs_tcp_setup_socket(struct work_struct *work)
case -EINPROGRESS:
case -EALREADY:
xprt_clear_connecting(xprt);
+ current->flags &= ~PF_FSTRANS;
return;
case -EINVAL:
/* Happens, for instance, if the user specified a link
@@ -2171,6 +2223,7 @@ out_eagain:
out:
xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, status);
+ current->flags &= ~PF_FSTRANS;
}
/**
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 79981d97bc9..e4768c180da 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -823,6 +823,34 @@ fail:
return NULL;
}
+static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
+{
+ struct dentry *dentry;
+ struct path path;
+ int err = 0;
+ /*
+ * Get the parent directory, calculate the hash for last
+ * component.
+ */
+ dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
+ err = PTR_ERR(dentry);
+ if (IS_ERR(dentry))
+ return err;
+
+ /*
+ * All right, let's create it.
+ */
+ err = security_path_mknod(&path, dentry, mode, 0);
+ if (!err) {
+ err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0);
+ if (!err) {
+ res->mnt = mntget(path.mnt);
+ res->dentry = dget(dentry);
+ }
+ }
+ done_path_create(&path, dentry);
+ return err;
+}
static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
@@ -831,8 +859,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
struct unix_sock *u = unix_sk(sk);
struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
char *sun_path = sunaddr->sun_path;
- struct dentry *dentry = NULL;
- struct path path;
int err;
unsigned int hash;
struct unix_address *addr;
@@ -869,43 +895,23 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
atomic_set(&addr->refcnt, 1);
if (sun_path[0]) {
- umode_t mode;
- err = 0;
- /*
- * Get the parent directory, calculate the hash for last
- * component.
- */
- dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
- err = PTR_ERR(dentry);
- if (IS_ERR(dentry))
- goto out_mknod_parent;
-
- /*
- * All right, let's create it.
- */
- mode = S_IFSOCK |
+ struct path path;
+ umode_t mode = S_IFSOCK |
(SOCK_INODE(sock)->i_mode & ~current_umask());
- err = mnt_want_write(path.mnt);
- if (err)
- goto out_mknod_dput;
- err = security_path_mknod(&path, dentry, mode, 0);
- if (err)
- goto out_mknod_drop_write;
- err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0);
-out_mknod_drop_write:
- mnt_drop_write(path.mnt);
- if (err)
- goto out_mknod_dput;
- mutex_unlock(&path.dentry->d_inode->i_mutex);
- dput(path.dentry);
- path.dentry = dentry;
-
+ err = unix_mknod(sun_path, mode, &path);
+ if (err) {
+ if (err == -EEXIST)
+ err = -EADDRINUSE;
+ unix_release_addr(addr);
+ goto out_up;
+ }
addr->hash = UNIX_HASH_SIZE;
- }
-
- spin_lock(&unix_table_lock);
-
- if (!sun_path[0]) {
+ hash = path.dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1);
+ spin_lock(&unix_table_lock);
+ u->path = path;
+ list = &unix_socket_table[hash];
+ } else {
+ spin_lock(&unix_table_lock);
err = -EADDRINUSE;
if (__unix_find_socket_byname(net, sunaddr, addr_len,
sk->sk_type, hash)) {
@@ -914,9 +920,6 @@ out_mknod_drop_write:
}
list = &unix_socket_table[addr->hash];
- } else {
- list = &unix_socket_table[dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1)];
- u->path = path;
}
err = 0;
@@ -930,16 +933,6 @@ out_up:
mutex_unlock(&u->readlock);
out:
return err;
-
-out_mknod_dput:
- dput(dentry);
- mutex_unlock(&path.dentry->d_inode->i_mutex);
- path_put(&path);
-out_mknod_parent:
- if (err == -EEXIST)
- err = -EADDRINUSE;
- unix_release_addr(addr);
- goto out_up;
}
static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)