diff options
Diffstat (limited to 'include/linux/net.h')
| -rw-r--r-- | include/linux/net.h | 100 |
1 files changed, 74 insertions, 26 deletions
diff --git a/include/linux/net.h b/include/linux/net.h index d48ff1180879..ec09620f40f7 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -21,6 +21,7 @@ #include <linux/rcupdate.h> #include <linux/once.h> #include <linux/fs.h> +#include <linux/mm.h> #include <linux/sockptr.h> #include <uapi/linux/net.h> @@ -35,11 +36,13 @@ struct net; * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. * Eventually all flags will be in sk->sk_wq->flags. */ -#define SOCKWQ_ASYNC_NOSPACE 0 -#define SOCKWQ_ASYNC_WAITDATA 1 -#define SOCK_NOSPACE 2 -#define SOCK_PASSCRED 3 -#define SOCK_PASSSEC 4 +enum socket_flags { + SOCKWQ_ASYNC_NOSPACE, + SOCKWQ_ASYNC_WAITDATA, + SOCK_NOSPACE, + SOCK_SUPPORT_ZC, + SOCK_CUSTOM_SOCKOPT, +}; #ifndef ARCH_HAS_SOCKET_TYPES /** @@ -66,6 +69,7 @@ enum sock_type { SOCK_DCCP = 6, SOCK_PACKET = 10, }; +#endif /* ARCH_HAS_SOCKET_TYPES */ #define SOCK_MAX (SOCK_PACKET + 1) /* Mask which covers at least up to SOCK_MASK-1. The @@ -77,8 +81,7 @@ enum sock_type { #ifndef SOCK_NONBLOCK #define SOCK_NONBLOCK O_NONBLOCK #endif - -#endif /* ARCH_HAS_SOCKET_TYPES */ +#define SOCK_COREDUMP O_NOCTTY /** * enum sock_shutdown_cmd - Shutdown types @@ -119,19 +122,41 @@ struct socket { struct file *file; struct sock *sk; - const struct proto_ops *ops; + const struct proto_ops *ops; /* Might change with IPV6_ADDRFORM or MPTCP. */ struct socket_wq wq; }; +/* + * "descriptor" for what we're up to with a read. + * This allows us to use the same read code yet + * have multiple different users of the data that + * we read from a file. + * + * The simplest case just copies the data to user + * mode. + */ +typedef struct { + size_t written; + size_t count; + union { + char __user *buf; + void *data; + } arg; + int error; +} read_descriptor_t; + struct vm_area_struct; struct page; struct sockaddr; struct msghdr; struct module; struct sk_buff; +struct proto_accept_arg; typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, unsigned int, size_t); +typedef int (*skb_read_actor_t)(struct sock *, struct sk_buff *); + struct proto_ops { int family; @@ -146,7 +171,8 @@ struct proto_ops { int (*socketpair)(struct socket *sock1, struct socket *sock2); int (*accept) (struct socket *sock, - struct socket *newsock, int flags, bool kern); + struct socket *newsock, + struct proto_accept_arg *arg); int (*getname) (struct socket *sock, struct sockaddr *addr, int peer); @@ -182,10 +208,9 @@ struct proto_ops { size_t total_len, int flags); int (*mmap) (struct file *file, struct socket *sock, struct vm_area_struct * vma); - ssize_t (*sendpage) (struct socket *sock, struct page *page, - int offset, size_t size, int flags); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); + void (*splice_eof)(struct socket *sock); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); @@ -194,8 +219,8 @@ struct proto_ops { */ int (*read_sock)(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); - int (*sendpage_locked)(struct sock *sk, struct page *page, - int offset, size_t size, int flags); + /* This is different from read_sock(), it reads an entire skb at a time. */ + int (*read_skb)(struct sock *sk, skb_read_actor_t recv_actor); int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, size_t size); int (*set_rcvlowat)(struct sock *sk, int val); @@ -236,7 +261,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg); int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags); struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname); struct socket *sockfd_lookup(int fd, int *err); -struct socket *sock_from_file(struct file *file, int *err); +struct socket *sock_from_file(struct file *file); #define sockfd_put(sock) fput(sock->file) int net_ratelimit(void); @@ -275,21 +300,48 @@ do { \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) #else #define net_dbg_ratelimited(fmt, ...) \ - do { \ - if (0) \ - no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ - } while (0) + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif #define net_get_random_once(buf, nbytes) \ get_random_once((buf), (nbytes)) -#define net_get_random_once_wait(buf, nbytes) \ - get_random_once_wait((buf), (nbytes)) + +/* + * E.g. XFS meta- & log-data is in slab pages, or bcache meta + * data pages, or other high order pages allocated by + * __get_free_pages() without __GFP_COMP, which have a page_count + * of 0 and/or have PageSlab() set. We cannot use send_page for + * those, as that does get_page(); put_page(); and would cause + * either a VM_BUG directly, or __page_cache_release a page that + * would actually still be referenced by someone, leading to some + * obscure delayed Oops somewhere else. + */ +static inline bool sendpage_ok(struct page *page) +{ + return !PageSlab(page) && page_count(page) >= 1; +} + +/* + * Check sendpage_ok on contiguous pages. + */ +static inline bool sendpages_ok(struct page *page, size_t len, size_t offset) +{ + struct page *p = page + (offset >> PAGE_SHIFT); + size_t count = 0; + + while (count < len) { + if (!sendpage_ok(p)) + return false; + + p++; + count += PAGE_SIZE; + } + + return true; +} int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); -int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, - struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); @@ -300,10 +352,6 @@ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags); int kernel_getsockname(struct socket *sock, struct sockaddr *addr); int kernel_getpeername(struct socket *sock, struct sockaddr *addr); -int kernel_sendpage(struct socket *sock, struct page *page, int offset, - size_t size, int flags); -int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, - size_t size, int flags); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how); /* Routine returns the IP overhead imposed by a (caller-protected) socket. */ |