summaryrefslogtreecommitdiff
path: root/include/net/sock.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/net/sock.h')
-rw-r--r--include/net/sock.h63
1 files changed, 51 insertions, 12 deletions
diff --git a/include/net/sock.h b/include/net/sock.h
index 7c0632c7e870..79e1a2c7912c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -60,7 +60,7 @@
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/cgroup-defs.h>
-
+#include <linux/rbtree.h>
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
#include <linux/poll.h>
@@ -267,6 +267,7 @@ struct sock_common {
* @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
* @sk_gso_max_size: Maximum GSO segment size to build
* @sk_gso_max_segs: Maximum number of GSO segments
+ * @sk_pacing_shift: scaling factor for TCP Small Queues
* @sk_lingertime: %SO_LINGER l_linger setting
* @sk_backlog: always used with the per-socket spinlock held
* @sk_callback_lock: used with the callbacks in the end of this struct
@@ -294,6 +295,7 @@ struct sock_common {
* @sk_stamp: time stamp of last packet received
* @sk_tsflags: SO_TIMESTAMPING socket options
* @sk_tskey: counter to disambiguate concurrent tstamp requests
+ * @sk_zckey: counter to order MSG_ZEROCOPY notifications
* @sk_socket: Identd and reporting IO signals
* @sk_user_data: RPC layer private data
* @sk_frag: cached page frag
@@ -396,7 +398,10 @@ struct sock {
int sk_wmem_queued;
refcount_t sk_wmem_alloc;
unsigned long sk_tsq_flags;
- struct sk_buff *sk_send_head;
+ union {
+ struct sk_buff *sk_send_head;
+ struct rb_root tcp_rtx_queue;
+ };
struct sk_buff_head sk_write_queue;
__s32 sk_peek_off;
int sk_write_pending;
@@ -435,7 +440,6 @@ struct sock {
#define SK_FL_TYPE_MASK 0xffff0000
#endif
- kmemcheck_bitfield_begin(flags);
unsigned int sk_padding : 1,
sk_kern_sock : 1,
sk_no_check_tx : 1,
@@ -444,9 +448,8 @@ struct sock {
sk_protocol : 8,
sk_type : 16;
#define SK_PROTOCOL_MAX U8_MAX
- kmemcheck_bitfield_end(flags);
-
u16 sk_gso_max_segs;
+ u8 sk_pacing_shift;
unsigned long sk_lingertime;
struct proto *sk_prot_creator;
rwlock_t sk_callback_lock;
@@ -462,6 +465,7 @@ struct sock {
u16 sk_tsflags;
u8 sk_shutdown;
u32 sk_tskey;
+ atomic_t sk_zckey;
struct socket *sk_socket;
void *sk_user_data;
#ifdef CONFIG_SECURITY
@@ -507,9 +511,7 @@ int sk_set_peek_off(struct sock *sk, int val);
static inline int sk_peek_offset(struct sock *sk, int flags)
{
if (unlikely(flags & MSG_PEEK)) {
- s32 off = READ_ONCE(sk->sk_peek_off);
- if (off >= 0)
- return off;
+ return READ_ONCE(sk->sk_peek_off);
}
return 0;
@@ -734,10 +736,10 @@ static inline void sk_add_bind_node(struct sock *sk,
*
*/
#define sk_for_each_entry_offset_rcu(tpos, pos, head, offset) \
- for (pos = rcu_dereference((head)->first); \
+ for (pos = rcu_dereference(hlist_first_rcu(head)); \
pos != NULL && \
({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \
- pos = rcu_dereference(pos->next))
+ pos = rcu_dereference(hlist_next_rcu(pos)))
static inline struct user_namespace *sk_user_ns(struct sock *sk)
{
@@ -856,7 +858,7 @@ void sk_stream_write_space(struct sock *sk);
static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{
/* dont let skb dst not refcounted, we are going to leave rcu lock */
- skb_dst_force_safe(skb);
+ skb_dst_force(skb);
if (!sk->sk_backlog.tail)
sk->sk_backlog.head = skb;
@@ -1098,14 +1100,18 @@ struct proto {
*/
unsigned long *memory_pressure;
long *sysctl_mem;
+
int *sysctl_wmem;
int *sysctl_rmem;
+ u32 sysctl_wmem_offset;
+ u32 sysctl_rmem_offset;
+
int max_header;
bool no_autobind;
struct kmem_cache *slab;
unsigned int obj_size;
- int slab_flags;
+ slab_flags_t slab_flags;
struct percpu_counter *orphan_count;
@@ -1531,6 +1537,8 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
gfp_t priority);
void __sock_wfree(struct sk_buff *skb);
void sock_wfree(struct sk_buff *skb);
+struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
+ gfp_t priority);
void skb_orphan_partial(struct sk_buff *skb);
void sock_rfree(struct sk_buff *skb);
void sock_efree(struct sk_buff *skb);
@@ -1582,11 +1590,14 @@ int sock_no_shutdown(struct socket *, int);
int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *);
int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int);
int sock_no_sendmsg(struct socket *, struct msghdr *, size_t);
+int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len);
int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int);
int sock_no_mmap(struct file *file, struct socket *sock,
struct vm_area_struct *vma);
ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset,
size_t size, int flags);
+ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page,
+ int offset, size_t size, int flags);
/*
* Functions to fill in entries in struct proto_ops when a protocol
@@ -2363,6 +2374,16 @@ bool sk_net_capable(const struct sock *sk, int cap);
void sk_get_meminfo(const struct sock *sk, u32 *meminfo);
+/* Take into consideration the size of the struct sk_buff overhead in the
+ * determination of these values, since that is non-constant across
+ * platforms. This makes socket queueing behavior and performance
+ * not depend upon such differences.
+ */
+#define _SK_MEM_PACKETS 256
+#define _SK_MEM_OVERHEAD SKB_TRUESIZE(256)
+#define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
+#define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
+
extern __u32 sysctl_wmem_max;
extern __u32 sysctl_rmem_max;
@@ -2372,4 +2393,22 @@ extern int sysctl_optmem_max;
extern __u32 sysctl_wmem_default;
extern __u32 sysctl_rmem_default;
+static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
+{
+ /* Does this proto have per netns sysctl_wmem ? */
+ if (proto->sysctl_wmem_offset)
+ return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset);
+
+ return *proto->sysctl_wmem;
+}
+
+static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
+{
+ /* Does this proto have per netns sysctl_rmem ? */
+ if (proto->sysctl_rmem_offset)
+ return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset);
+
+ return *proto->sysctl_rmem;
+}
+
#endif /* _SOCK_H */