summaryrefslogtreecommitdiffstats
path: root/net/core/sock.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/sock.c')
-rw-r--r--net/core/sock.c140
1 files changed, 78 insertions, 62 deletions
diff --git a/net/core/sock.c b/net/core/sock.c
index 02f8dfe320b7..9e5b71fda6ec 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -89,6 +89,8 @@
* 2 of the License, or (at your option) any later version.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
@@ -111,11 +113,11 @@
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/user_namespace.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
#include <linux/memcontrol.h>
+#include <linux/prefetch.h>
#include <asm/uaccess.h>
-#include <asm/system.h>
#include <linux/netdevice.h>
#include <net/protocol.h>
@@ -141,7 +143,7 @@ static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
-int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
+int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
struct proto *proto;
int ret = 0;
@@ -149,7 +151,7 @@ int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
mutex_lock(&proto_list_mutex);
list_for_each_entry(proto, &proto_list, node) {
if (proto->init_cgroup) {
- ret = proto->init_cgroup(cgrp, ss);
+ ret = proto->init_cgroup(memcg, ss);
if (ret)
goto out;
}
@@ -160,19 +162,19 @@ int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
out:
list_for_each_entry_continue_reverse(proto, &proto_list, node)
if (proto->destroy_cgroup)
- proto->destroy_cgroup(cgrp, ss);
+ proto->destroy_cgroup(memcg);
mutex_unlock(&proto_list_mutex);
return ret;
}
-void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
+void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
{
struct proto *proto;
mutex_lock(&proto_list_mutex);
list_for_each_entry_reverse(proto, &proto_list, node)
if (proto->destroy_cgroup)
- proto->destroy_cgroup(cgrp, ss);
+ proto->destroy_cgroup(memcg);
mutex_unlock(&proto_list_mutex);
}
#endif
@@ -184,7 +186,7 @@ void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
static struct lock_class_key af_family_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];
-struct jump_label_key memcg_socket_limit_enabled;
+struct static_key memcg_socket_limit_enabled;
EXPORT_SYMBOL(memcg_socket_limit_enabled);
/*
@@ -259,7 +261,9 @@ static struct lock_class_key af_callback_keys[AF_MAX];
/* Run time adjustable parameters. */
__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
+EXPORT_SYMBOL(sysctl_wmem_max);
__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
+EXPORT_SYMBOL(sysctl_rmem_max);
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
@@ -295,9 +299,8 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
*timeo_p = 0;
if (warned < 10 && net_ratelimit()) {
warned++;
- printk(KERN_INFO "sock_set_timeout: `%s' (pid %d) "
- "tries to set negative timeout\n",
- current->comm, task_pid_nr(current));
+ pr_info("%s: `%s' (pid %d) tries to set negative timeout\n",
+ __func__, current->comm, task_pid_nr(current));
}
return 0;
}
@@ -315,8 +318,8 @@ static void sock_warn_obsolete_bsdism(const char *name)
static char warncomm[TASK_COMM_LEN];
if (strcmp(warncomm, current->comm) && warned < 5) {
strcpy(warncomm, current->comm);
- printk(KERN_WARNING "process `%s' is using obsolete "
- "%s SO_BSDCOMPAT\n", warncomm, name);
+ pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n",
+ warncomm, name);
warned++;
}
}
@@ -390,7 +393,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
skb->dev = NULL;
- if (sk_rcvqueues_full(sk, skb)) {
+ if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) {
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
}
@@ -407,7 +410,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
rc = sk_backlog_rcv(sk, skb);
mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
- } else if (sk_add_backlog(sk, skb)) {
+ } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) {
bh_unlock_sock(sk);
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
@@ -562,7 +565,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
sock_valbool_flag(sk, SOCK_DBG, valbool);
break;
case SO_REUSEADDR:
- sk->sk_reuse = valbool;
+ sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
break;
case SO_TYPE:
case SO_PROTOCOL:
@@ -578,23 +581,15 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
break;
case SO_SNDBUF:
/* Don't error on this BSD doesn't and if you think
- about it this is right. Otherwise apps have to
- play 'guess the biggest size' games. RCVBUF/SNDBUF
- are treated in BSD as hints */
-
- if (val > sysctl_wmem_max)
- val = sysctl_wmem_max;
+ * about it this is right. Otherwise apps have to
+ * play 'guess the biggest size' games. RCVBUF/SNDBUF
+ * are treated in BSD as hints
+ */
+ val = min_t(u32, val, sysctl_wmem_max);
set_sndbuf:
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
- if ((val * 2) < SOCK_MIN_SNDBUF)
- sk->sk_sndbuf = SOCK_MIN_SNDBUF;
- else
- sk->sk_sndbuf = val * 2;
-
- /*
- * Wake up sending tasks if we
- * upped the value.
- */
+ sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF);
+ /* Wake up sending tasks if we upped the value. */
sk->sk_write_space(sk);
break;
@@ -607,12 +602,11 @@ set_sndbuf:
case SO_RCVBUF:
/* Don't error on this BSD doesn't and if you think
- about it this is right. Otherwise apps have to
- play 'guess the biggest size' games. RCVBUF/SNDBUF
- are treated in BSD as hints */
-
- if (val > sysctl_rmem_max)
- val = sysctl_rmem_max;
+ * about it this is right. Otherwise apps have to
+ * play 'guess the biggest size' games. RCVBUF/SNDBUF
+ * are treated in BSD as hints
+ */
+ val = min_t(u32, val, sysctl_rmem_max);
set_rcvbuf:
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
/*
@@ -630,10 +624,7 @@ set_rcvbuf:
* returning the value we actually used in getsockopt
* is the most desirable behavior.
*/
- if ((val * 2) < SOCK_MIN_RCVBUF)
- sk->sk_rcvbuf = SOCK_MIN_RCVBUF;
- else
- sk->sk_rcvbuf = val * 2;
+ sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF);
break;
case SO_RCVBUFFORCE:
@@ -793,6 +784,17 @@ set_rcvbuf:
sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool);
break;
+ case SO_PEEK_OFF:
+ if (sock->ops->set_peek_off)
+ sock->ops->set_peek_off(sk, val);
+ else
+ ret = -EOPNOTSUPP;
+ break;
+
+ case SO_NOFCS:
+ sock_valbool_flag(sk, SOCK_NOFCS, valbool);
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -811,8 +813,8 @@ void cred_to_ucred(struct pid *pid, const struct cred *cred,
if (cred) {
struct user_namespace *current_ns = current_user_ns();
- ucred->uid = user_ns_map_uid(current_ns, cred, cred->euid);
- ucred->gid = user_ns_map_gid(current_ns, cred, cred->egid);
+ ucred->uid = from_kuid(current_ns, cred->euid);
+ ucred->gid = from_kgid(current_ns, cred->egid);
}
}
EXPORT_SYMBOL_GPL(cred_to_ucred);
@@ -848,7 +850,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_BROADCAST:
- v.val = !!sock_flag(sk, SOCK_BROADCAST);
+ v.val = sock_flag(sk, SOCK_BROADCAST);
break;
case SO_SNDBUF:
@@ -864,7 +866,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_KEEPALIVE:
- v.val = !!sock_flag(sk, SOCK_KEEPOPEN);
+ v.val = sock_flag(sk, SOCK_KEEPOPEN);
break;
case SO_TYPE:
@@ -886,7 +888,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_OOBINLINE:
- v.val = !!sock_flag(sk, SOCK_URGINLINE);
+ v.val = sock_flag(sk, SOCK_URGINLINE);
break;
case SO_NO_CHECK:
@@ -899,7 +901,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
case SO_LINGER:
lv = sizeof(v.ling);
- v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER);
+ v.ling.l_onoff = sock_flag(sk, SOCK_LINGER);
v.ling.l_linger = sk->sk_lingertime / HZ;
break;
@@ -965,7 +967,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_PASSCRED:
- v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0;
+ v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
break;
case SO_PEERCRED:
@@ -1000,7 +1002,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_PASSSEC:
- v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0;
+ v.val = !!test_bit(SOCK_PASSSEC, &sock->flags);
break;
case SO_PEERSEC:
@@ -1011,13 +1013,22 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_RXQ_OVFL:
- v.val = !!sock_flag(sk, SOCK_RXQ_OVFL);
+ v.val = sock_flag(sk, SOCK_RXQ_OVFL);
break;
case SO_WIFI_STATUS:
- v.val = !!sock_flag(sk, SOCK_WIFI_STATUS);
+ v.val = sock_flag(sk, SOCK_WIFI_STATUS);
break;
+ case SO_PEEK_OFF:
+ if (!sock->ops->set_peek_off)
+ return -EOPNOTSUPP;
+
+ v.val = sk->sk_peek_off;
+ break;
+ case SO_NOFCS:
+ v.val = sock_flag(sk, SOCK_NOFCS);
+ break;
default:
return -ENOPROTOOPT;
}
@@ -1228,8 +1239,8 @@ static void __sk_free(struct sock *sk)
sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
if (atomic_read(&sk->sk_omem_alloc))
- printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n",
- __func__, atomic_read(&sk->sk_omem_alloc));
+ pr_debug("%s: optmem leakage (%d bytes) detected\n",
+ __func__, atomic_read(&sk->sk_omem_alloc));
if (sk->sk_peer_cred)
put_cred(sk->sk_peer_cred);
@@ -1515,7 +1526,7 @@ struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
*/
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
{
- if ((unsigned)size <= sysctl_optmem_max &&
+ if ((unsigned int)size <= sysctl_optmem_max &&
atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
void *mem;
/* First do the add, to avoid the race if kmalloc
@@ -1581,6 +1592,11 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
gfp_t gfp_mask;
long timeo;
int err;
+ int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
+
+ err = -EMSGSIZE;
+ if (npages > MAX_SKB_FRAGS)
+ goto failure;
gfp_mask = sk->sk_allocation;
if (gfp_mask & __GFP_WAIT)
@@ -1599,14 +1615,12 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
skb = alloc_skb(header_len, gfp_mask);
if (skb) {
- int npages;
int i;
/* No pages, we're done... */
if (!data_len)
break;
- npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
skb->truesize += data_len;
skb_shinfo(skb)->nr_frags = npages;
for (i = 0; i < npages; i++) {
@@ -1693,6 +1707,7 @@ static void __release_sock(struct sock *sk)
do {
struct sk_buff *next = skb->next;
+ prefetch(next);
WARN_ON_ONCE(skb_dst_is_noref(skb));
skb->next = NULL;
sk_backlog_rcv(sk, skb);
@@ -2092,6 +2107,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
+ sk->sk_peek_off = -1;
sk->sk_peer_pid = NULL;
sk->sk_peer_cred = NULL;
@@ -2412,7 +2428,7 @@ static void assign_proto_idx(struct proto *prot)
prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR);
if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) {
- printk(KERN_ERR "PROTO_INUSE_NR exhausted\n");
+ pr_err("PROTO_INUSE_NR exhausted\n");
return;
}
@@ -2442,8 +2458,8 @@ int proto_register(struct proto *prot, int alloc_slab)
NULL);
if (prot->slab == NULL) {
- printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n",
- prot->name);
+ pr_crit("%s: Can't create sock SLAB cache!\n",
+ prot->name);
goto out;
}
@@ -2457,8 +2473,8 @@ int proto_register(struct proto *prot, int alloc_slab)
SLAB_HWCACHE_ALIGN, NULL);
if (prot->rsk_prot->slab == NULL) {
- printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n",
- prot->name);
+ pr_crit("%s: Can't create request sock SLAB cache!\n",
+ prot->name);
goto out_free_request_sock_slab_name;
}
}
@@ -2556,7 +2572,7 @@ static char proto_method_implemented(const void *method)
}
static long sock_prot_memory_allocated(struct proto *proto)
{
- return proto->memory_allocated != NULL ? proto_memory_allocated(proto): -1L;
+ return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L;
}
static char *sock_prot_memory_pressure(struct proto *proto)
generated by cgit v1.2.3 (git 2.25.1) at 2025-02-25 19:21:01 +0000