diff options
author | Linus Torvalds <torvalds@g5.osdl.org> | 2005-08-29 17:36:46 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@g5.osdl.org> | 2005-08-29 17:36:46 -0700 |
commit | 826509f8110049663799bc20f2b5b6170e2f78ca (patch) | |
tree | 9d8823cf283592625b882125b4b13988f2934cc6 /include | |
parent | d992895ba2b27cf5adf1ba0ad6d27662adc54c5e (diff) | |
parent | c530cfb1ce1e8f230744c3f3bd86771f50725053 (diff) |
Merge HEAD from master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6.git
Diffstat (limited to 'include')
119 files changed, 3449 insertions, 1038 deletions
diff --git a/include/asm-alpha/socket.h b/include/asm-alpha/socket.h index d00259d3dc7..b5193229132 100644 --- a/include/asm-alpha/socket.h +++ b/include/asm-alpha/socket.h @@ -25,6 +25,8 @@ #define SO_ERROR 0x1007 #define SO_SNDBUF 0x1001 #define SO_RCVBUF 0x1002 +#define SO_SNDBUFFORCE 0x100a +#define SO_RCVBUFFORCE 0x100b #define SO_RCVLOWAT 0x1010 #define SO_SNDLOWAT 0x1011 #define SO_RCVTIMEO 0x1012 diff --git a/include/asm-arm/socket.h b/include/asm-arm/socket.h index 46d20585d95..3c51da6438c 100644 --- a/include/asm-arm/socket.h +++ b/include/asm-arm/socket.h @@ -14,6 +14,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-arm26/socket.h b/include/asm-arm26/socket.h index 46d20585d95..3c51da6438c 100644 --- a/include/asm-arm26/socket.h +++ b/include/asm-arm26/socket.h @@ -14,6 +14,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-cris/socket.h b/include/asm-cris/socket.h index f159b4f165f..8b1da3e58c5 100644 --- a/include/asm-cris/socket.h +++ b/include/asm-cris/socket.h @@ -16,6 +16,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-frv/socket.h b/include/asm-frv/socket.h index c3be17c7de4..7177f8b9817 100644 --- a/include/asm-frv/socket.h +++ b/include/asm-frv/socket.h @@ -14,6 +14,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-h8300/socket.h b/include/asm-h8300/socket.h index af33b8525dc..d98cf85bafc 100644 --- a/include/asm-h8300/socket.h +++ b/include/asm-h8300/socket.h @@ -14,6 +14,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-i386/checksum.h b/include/asm-i386/checksum.h index f949e44c2a3..67d3630c4e8 100644 --- a/include/asm-i386/checksum.h +++ b/include/asm-i386/checksum.h @@ -83,7 +83,7 @@ static inline unsigned short ip_fast_csum(unsigned char * iph, "adcl $0, %0 ;\n" "notl %0 ;\n" "2: ;\n" - /* Since the input registers which are loaded with iph and ipl + /* Since the input registers which are loaded with iph and ihl are modified, we must also specify them as outputs, or gcc will assume they contain their original values. */ : "=r" (sum), "=r" (iph), "=r" (ihl) diff --git a/include/asm-i386/socket.h b/include/asm-i386/socket.h index 07f6b38ad14..802ae76195b 100644 --- a/include/asm-i386/socket.h +++ b/include/asm-i386/socket.h @@ -14,6 +14,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-ia64/socket.h b/include/asm-ia64/socket.h index 21a9f10d6ba..a255006fb7b 100644 --- a/include/asm-ia64/socket.h +++ b/include/asm-ia64/socket.h @@ -23,6 +23,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-m32r/checksum.h b/include/asm-m32r/checksum.h index 99f37dbf255..877ebf46e9f 100644 --- a/include/asm-m32r/checksum.h +++ b/include/asm-m32r/checksum.h @@ -105,7 +105,7 @@ static inline unsigned short ip_fast_csum(unsigned char * iph, " addx %0, %3 \n" " .fillinsn\n" "2: \n" - /* Since the input registers which are loaded with iph and ipl + /* Since the input registers which are loaded with iph and ihl are modified, we must also specify them as outputs, or gcc will assume they contain their original values. */ : "=&r" (sum), "=r" (iph), "=r" (ihl), "=&r" (tmpreg0), "=&r" (tmpreg1) diff --git a/include/asm-m32r/socket.h b/include/asm-m32r/socket.h index 159519d9904..8b6680f223c 100644 --- a/include/asm-m32r/socket.h +++ b/include/asm-m32r/socket.h @@ -14,6 +14,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-m68k/socket.h b/include/asm-m68k/socket.h index 8d0b9fc2d07..f578ca4b776 100644 --- a/include/asm-m68k/socket.h +++ b/include/asm-m68k/socket.h @@ -14,6 +14,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-mips/socket.h b/include/asm-mips/socket.h index 020b4db70ee..d478a86294e 100644 --- a/include/asm-mips/socket.h +++ b/include/asm-mips/socket.h @@ -37,6 +37,8 @@ To add: #define SO_REUSEPORT 0x0200 /* Allow local address and port reuse. */ #define SO_ERROR 0x1007 /* get error status and clear */ #define SO_SNDBUF 0x1001 /* Send buffer size. */ #define SO_RCVBUF 0x1002 /* Receive buffer. */ +#define SO_SNDBUFFORCE 0x100a +#define SO_RCVBUFFORCE 0x100b #define SO_SNDLOWAT 0x1003 /* send low-water mark */ #define SO_RCVLOWAT 0x1004 /* receive low-water mark */ #define SO_SNDTIMEO 0x1005 /* send timeout */ diff --git a/include/asm-parisc/socket.h b/include/asm-parisc/socket.h index 4a77996c186..1bf54dc53c1 100644 --- a/include/asm-parisc/socket.h +++ b/include/asm-parisc/socket.h @@ -16,6 +16,8 @@ /* To add :#define SO_REUSEPORT 0x0200 */ #define SO_SNDBUF 0x1001 #define SO_RCVBUF 0x1002 +#define SO_SNDBUFFORCE 0x100a +#define SO_RCVBUFFORCE 0x100b #define SO_SNDLOWAT 0x1003 #define SO_RCVLOWAT 0x1004 #define SO_SNDTIMEO 0x1005 diff --git a/include/asm-ppc/socket.h b/include/asm-ppc/socket.h index 4134376b0f6..296e1a3469d 100644 --- a/include/asm-ppc/socket.h +++ b/include/asm-ppc/socket.h @@ -20,6 +20,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-ppc64/socket.h b/include/asm-ppc64/socket.h index 59e00dfc8b8..9e1af8eb2d9 100644 --- a/include/asm-ppc64/socket.h +++ b/include/asm-ppc64/socket.h @@ -21,6 +21,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-s390/socket.h b/include/asm-s390/socket.h index 0e96eeca4e6..15a5298c874 100644 --- a/include/asm-s390/socket.h +++ b/include/asm-s390/socket.h @@ -22,6 +22,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-sh/socket.h b/include/asm-sh/socket.h index dde696c3b4c..553904ff933 100644 --- a/include/asm-sh/socket.h +++ b/include/asm-sh/socket.h @@ -14,6 +14,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_RCVBUFFORCE 32 +#define SO_SNDBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-sparc/socket.h b/include/asm-sparc/socket.h index c1154e3ecfd..09575b608ad 100644 --- a/include/asm-sparc/socket.h +++ b/include/asm-sparc/socket.h @@ -29,6 +29,8 @@ #define SO_SNDBUF 0x1001 #define SO_RCVBUF 0x1002 +#define SO_SNDBUFFORCE 0x100a +#define SO_RCVBUFFORCE 0x100b #define SO_ERROR 0x1007 #define SO_TYPE 0x1008 diff --git a/include/asm-sparc64/socket.h b/include/asm-sparc64/socket.h index 865547a2390..59987dad335 100644 --- a/include/asm-sparc64/socket.h +++ b/include/asm-sparc64/socket.h @@ -29,6 +29,8 @@ #define SO_SNDBUF 0x1001 #define SO_RCVBUF 0x1002 +#define SO_SNDBUFFORCE 0x100a +#define SO_RCVBUFFORCE 0x100b #define SO_ERROR 0x1007 #define SO_TYPE 0x1008 diff --git a/include/asm-v850/socket.h b/include/asm-v850/socket.h index 213b852af53..0240d366a0a 100644 --- a/include/asm-v850/socket.h +++ b/include/asm-v850/socket.h @@ -14,6 +14,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-x86_64/checksum.h b/include/asm-x86_64/checksum.h index d01356f0144..989469e8e0b 100644 --- a/include/asm-x86_64/checksum.h +++ b/include/asm-x86_64/checksum.h @@ -64,7 +64,7 @@ static inline unsigned short ip_fast_csum(unsigned char *iph, unsigned int ihl) " adcl $0, %0\n" " notl %0\n" "2:" - /* Since the input registers which are loaded with iph and ipl + /* Since the input registers which are loaded with iph and ihl are modified, we must also specify them as outputs, or gcc will assume they contain their original values. */ : "=r" (sum), "=r" (iph), "=r" (ihl) diff --git a/include/asm-x86_64/socket.h b/include/asm-x86_64/socket.h index d9a252ea821..f2cdbeae5d5 100644 --- a/include/asm-x86_64/socket.h +++ b/include/asm-x86_64/socket.h @@ -14,6 +14,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/asm-xtensa/socket.h b/include/asm-xtensa/socket.h index daccd05a14c..00f83f3a6d7 100644 --- a/include/asm-xtensa/socket.h +++ b/include/asm-xtensa/socket.h @@ -24,6 +24,8 @@ #define SO_BROADCAST 6 #define SO_SNDBUF 7 #define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 #define SO_KEEPALIVE 9 #define SO_OOBINLINE 10 #define SO_NO_CHECK 11 diff --git a/include/linux/dccp.h b/include/linux/dccp.h new file mode 100644 index 00000000000..007c290f74d --- /dev/null +++ b/include/linux/dccp.h @@ -0,0 +1,456 @@ +#ifndef _LINUX_DCCP_H +#define _LINUX_DCCP_H + +#include <linux/types.h> +#include <asm/byteorder.h> + +/* Structure describing an Internet (DCCP) socket address. */ +struct sockaddr_dccp { + __u16 sdccp_family; /* Address family */ + __u16 sdccp_port; /* Port number */ + __u32 sdccp_addr; /* Internet address */ + __u32 sdccp_service; /* Service */ + /* Pad to size of `struct sockaddr': 16 bytes . */ + __u32 sdccp_pad; +}; + +/** + * struct dccp_hdr - generic part of DCCP packet header + * + * @dccph_sport - Relevant port on the endpoint that sent this packet + * @dccph_dport - Relevant port on the other endpoint + * @dccph_doff - Data Offset from the start of the DCCP header, in 32-bit words + * @dccph_ccval - Used by the HC-Sender CCID + * @dccph_cscov - Parts of the packet that are covered by the Checksum field + * @dccph_checksum - Internet checksum, depends on dccph_cscov + * @dccph_x - 0 = 24 bit sequence number, 1 = 48 + * @dccph_type - packet type, see DCCP_PKT_ prefixed macros + * @dccph_seq - sequence number high or low order 24 bits, depends on dccph_x + */ +struct dccp_hdr { + __u16 dccph_sport, + dccph_dport; + __u8 dccph_doff; +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u8 dccph_cscov:4, + dccph_ccval:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u8 dccph_ccval:4, + dccph_cscov:4; +#else +#error "Adjust your <asm/byteorder.h> defines" +#endif + __u16 dccph_checksum; +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u32 dccph_x:1, + dccph_type:4, + dccph_reserved:3, + dccph_seq:24; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u32 dccph_reserved:3, + dccph_type:4, + dccph_x:1, + dccph_seq:24; +#else +#error "Adjust your <asm/byteorder.h> defines" +#endif +}; + +/** + * struct dccp_hdr_ext - the low bits of a 48 bit seq packet + * + * @dccph_seq_low - low 24 bits of a 48 bit seq packet + */ +struct dccp_hdr_ext { + __u32 dccph_seq_low; +}; + +/** + * struct dccp_hdr_request - Conection initiation request header + * + * @dccph_req_service - Service to which the client app wants to connect + * @dccph_req_options - list of options (must be a multiple of 32 bits + */ +struct dccp_hdr_request { + __u32 dccph_req_service; +}; +/** + * struct dccp_hdr_ack_bits - acknowledgment bits common to most packets + * + * @dccph_resp_ack_nr_high - 48 bit ack number high order bits, contains GSR + * @dccph_resp_ack_nr_low - 48 bit ack number low order bits, contains GSR + */ +struct dccp_hdr_ack_bits { + __u32 dccph_reserved1:8, + dccph_ack_nr_high:24; + __u32 dccph_ack_nr_low; +}; +/** + * struct dccp_hdr_response - Conection initiation response header + * + * @dccph_resp_ack_nr_high - 48 bit ack number high order bits, contains GSR + * @dccph_resp_ack_nr_low - 48 bit ack number low order bits, contains GSR + * @dccph_resp_service - Echoes the Service Code on a received DCCP-Request + * @dccph_resp_options - list of options (must be a multiple of 32 bits + */ +struct dccp_hdr_response { + struct dccp_hdr_ack_bits dccph_resp_ack; + __u32 dccph_resp_service; +}; + +/** + * struct dccp_hdr_reset - Unconditionally shut down a connection + * + * @dccph_reset_service - Echoes the Service Code on a received DCCP-Request + * @dccph_reset_options - list of options (must be a multiple of 32 bits + */ +struct dccp_hdr_reset { + struct dccp_hdr_ack_bits dccph_reset_ack; + __u8 dccph_reset_code, + dccph_reset_data[3]; +}; + +enum dccp_pkt_type { + DCCP_PKT_REQUEST = 0, + DCCP_PKT_RESPONSE, + DCCP_PKT_DATA, + DCCP_PKT_ACK, + DCCP_PKT_DATAACK, + DCCP_PKT_CLOSEREQ, + DCCP_PKT_CLOSE, + DCCP_PKT_RESET, + DCCP_PKT_SYNC, + DCCP_PKT_SYNCACK, + DCCP_PKT_INVALID, +}; + +#define DCCP_NR_PKT_TYPES DCCP_PKT_INVALID + +static inline unsigned int dccp_packet_hdr_len(const __u8 type) +{ + if (type == DCCP_PKT_DATA) + return 0; + if (type == DCCP_PKT_DATAACK || + type == DCCP_PKT_ACK || + type == DCCP_PKT_SYNC || + type == DCCP_PKT_SYNCACK || + type == DCCP_PKT_CLOSE || + type == DCCP_PKT_CLOSEREQ) + return sizeof(struct dccp_hdr_ack_bits); + if (type == DCCP_PKT_REQUEST) + return sizeof(struct dccp_hdr_request); + if (type == DCCP_PKT_RESPONSE) + return sizeof(struct dccp_hdr_response); + return sizeof(struct dccp_hdr_reset); +} +enum dccp_reset_codes { + DCCP_RESET_CODE_UNSPECIFIED = 0, + DCCP_RESET_CODE_CLOSED, + DCCP_RESET_CODE_ABORTED, + DCCP_RESET_CODE_NO_CONNECTION, + DCCP_RESET_CODE_PACKET_ERROR, + DCCP_RESET_CODE_OPTION_ERROR, + DCCP_RESET_CODE_MANDATORY_ERROR, + DCCP_RESET_CODE_CONNECTION_REFUSED, + DCCP_RESET_CODE_BAD_SERVICE_CODE, + DCCP_RESET_CODE_TOO_BUSY, + DCCP_RESET_CODE_BAD_INIT_COOKIE, + DCCP_RESET_CODE_AGGRESSION_PENALTY, +}; + +/* DCCP options */ +enum { + DCCPO_PADDING = 0, + DCCPO_MANDATORY = 1, + DCCPO_MIN_RESERVED = 3, + DCCPO_MAX_RESERVED = 31, + DCCPO_NDP_COUNT = 37, + DCCPO_ACK_VECTOR_0 = 38, + DCCPO_ACK_VECTOR_1 = 39, + DCCPO_TIMESTAMP = 41, + DCCPO_TIMESTAMP_ECHO = 42, + DCCPO_ELAPSED_TIME = 43, + DCCPO_MAX = 45, + DCCPO_MIN_CCID_SPECIFIC = 128, + DCCPO_MAX_CCID_SPECIFIC = 255, +}; + +/* DCCP features */ +enum { + DCCPF_RESERVED = 0, + DCCPF_SEQUENCE_WINDOW = 3, + DCCPF_SEND_ACK_VECTOR = 6, + DCCPF_SEND_NDP_COUNT = 7, + /* 10-127 reserved */ + DCCPF_MIN_CCID_SPECIFIC = 128, + DCCPF_MAX_CCID_SPECIFIC = 255, +}; + +/* DCCP socket options */ +#define DCCP_SOCKOPT_PACKET_SIZE 1 + +#ifdef __KERNEL__ + +#include <linux/in.h> +#include <linux/list.h> +#include <linux/uio.h> +#include <linux/workqueue.h> + +#include <net/inet_connection_sock.h> +#include <net/inet_timewait_sock.h> +#include <net/sock.h> +#include <net/tcp_states.h> +#include <net/tcp.h> + +enum dccp_state { + DCCP_OPEN = TCP_ESTABLISHED, + DCCP_REQUESTING = TCP_SYN_SENT, + DCCP_PARTOPEN = TCP_FIN_WAIT1, /* FIXME: + This mapping is horrible, but TCP has + no matching state for DCCP_PARTOPEN, + as TCP_SYN_RECV is already used by + DCCP_RESPOND, why don't stop using TCP + mapping of states? OK, now we don't use + sk_stream_sendmsg anymore, so doesn't + seem to exist any reason for us to + do the TCP mapping here */ + DCCP_LISTEN = TCP_LISTEN, + DCCP_RESPOND = TCP_SYN_RECV, + DCCP_CLOSING = TCP_CLOSING, + DCCP_TIME_WAIT = TCP_TIME_WAIT, + DCCP_CLOSED = TCP_CLOSE, + DCCP_MAX_STATES = TCP_MAX_STATES, +}; + +#define DCCP_STATE_MASK 0xf +#define DCCP_ACTION_FIN (1<<7) + +enum { + DCCPF_OPEN = TCPF_ESTABLISHED, + DCCPF_REQUESTING = TCPF_SYN_SENT, + DCCPF_PARTOPEN = TCPF_FIN_WAIT1, + DCCPF_LISTEN = TCPF_LISTEN, + DCCPF_RESPOND = TCPF_SYN_RECV, + DCCPF_CLOSING = TCPF_CLOSING, + DCCPF_TIME_WAIT = TCPF_TIME_WAIT, + DCCPF_CLOSED = TCPF_CLOSE, +}; + +static inline struct dccp_hdr *dccp_hdr(const struct sk_buff *skb) +{ + return (struct dccp_hdr *)skb->h.raw; +} + +static inline struct dccp_hdr_ext *dccp_hdrx(const struct sk_buff *skb) +{ + return (struct dccp_hdr_ext *)(skb->h.raw + sizeof(struct dccp_hdr)); +} + +static inline unsigned int __dccp_basic_hdr_len(const struct dccp_hdr *dh) +{ + return sizeof(*dh) + (dh->dccph_x ? sizeof(struct dccp_hdr_ext) : 0); +} + +static inline unsigned int dccp_basic_hdr_len(const struct sk_buff *skb) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); + return __dccp_basic_hdr_len(dh); +} + +static inline __u64 dccp_hdr_seq(const struct sk_buff *skb) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u64 seq_nr = ntohl(dh->dccph_seq << 8); +#elif defined(__BIG_ENDIAN_BITFIELD) + __u64 seq_nr = ntohl(dh->dccph_seq); +#else +#error "Adjust your <asm/byteorder.h> defines" +#endif + + if (dh->dccph_x != 0) + seq_nr = (seq_nr << 32) + ntohl(dccp_hdrx(skb)->dccph_seq_low); + + return seq_nr; +} + +static inline struct dccp_hdr_request *dccp_hdr_request(struct sk_buff *skb) +{ + return (struct dccp_hdr_request *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +static inline struct dccp_hdr_ack_bits *dccp_hdr_ack_bits(const struct sk_buff *skb) +{ + return (struct dccp_hdr_ack_bits *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +static inline u64 dccp_hdr_ack_seq(const struct sk_buff *skb) +{ + const struct dccp_hdr_ack_bits *dhack = dccp_hdr_ack_bits(skb); +#if defined(__LITTLE_ENDIAN_BITFIELD) + return (((u64)ntohl(dhack->dccph_ack_nr_high << 8)) << 32) + ntohl(dhack->dccph_ack_nr_low); +#elif defined(__BIG_ENDIAN_BITFIELD) + return (((u64)ntohl(dhack->dccph_ack_nr_high)) << 32) + ntohl(dhack->dccph_ack_nr_low); +#else +#error "Adjust your <asm/byteorder.h> defines" +#endif +} + +static inline struct dccp_hdr_response *dccp_hdr_response(struct sk_buff *skb) +{ + return (struct dccp_hdr_response *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +static inline struct dccp_hdr_reset *dccp_hdr_reset(struct sk_buff *skb) +{ + return (struct dccp_hdr_reset *)(skb->h.raw + dccp_basic_hdr_len(skb)); +} + +static inline unsigned int __dccp_hdr_len(const struct dccp_hdr *dh) +{ + return __dccp_basic_hdr_len(dh) + + dccp_packet_hdr_len(dh->dccph_type); +} + +static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) +{ + return __dccp_hdr_len(dccp_hdr(skb)); +} + + +/* initial values for each feature */ +#define DCCPF_INITIAL_SEQUENCE_WINDOW 100 +/* FIXME: for now we're using CCID 3 (TFRC) */ +#define DCCPF_INITIAL_CCID 3 +#define DCCPF_INITIAL_SEND_ACK_VECTOR 0 +/* FIXME: for now we're default to 1 but it should really be 0 */ +#define DCCPF_INITIAL_SEND_NDP_COUNT 1 + +#define DCCP_NDP_LIMIT 0xFFFFFF + +/** + * struct dccp_options - option values for a DCCP connection + * @dccpo_sequence_window - Sequence Window Feature (section 7.5.2) + * @dccpo_ccid - Congestion Control Id (CCID) (section 10) + * @dccpo_send_ack_vector - Send Ack Vector Feature (section 11.5) + * @dccpo_send_ndp_count - Send NDP Count Feature (7.7.2) + */ +struct dccp_options { + __u64 dccpo_sequence_window; + __u8 dccpo_ccid; + __u8 dccpo_send_ack_vector; + __u8 dccpo_send_ndp_count; +}; + +extern void __dccp_options_init(struct dccp_options *dccpo); +extern void dccp_options_init(struct dccp_options *dccpo); +extern int dccp_parse_options(struct sock *sk, struct sk_buff *skb); + +struct dccp_request_sock { + struct inet_request_sock dreq_inet_rsk; + __u64 dreq_iss; + __u64 dreq_isr; + __u32 dreq_service; +}; + +static inline struct dccp_request_sock *dccp_rsk(const struct request_sock *req) +{ + return (struct dccp_request_sock *)req; +} + +extern struct inet_timewait_death_row dccp_death_row; + +/* Read about the ECN nonce to see why it is 253 */ +#define DCCP_MAX_ACK_VECTOR_LEN 253 + +struct dccp_options_received { + u32 dccpor_ndp:24, + dccpor_ack_vector_len:8; + u32 dccpor_ack_vector_idx:10; + /* 22 bits hole, try to pack */ + u32 dccpor_timestamp; + u32 dccpor_timestamp_echo; + u32 dccpor_elapsed_time; +}; + +struct ccid; + +enum dccp_role { + DCCP_ROLE_UNDEFINED, + DCCP_ROLE_LISTEN, + DCCP_ROLE_CLIENT, + DCCP_ROLE_SERVER, +}; + +/** + * struct dccp_sock - DCCP socket state + * + * @dccps_swl - sequence number window low + * @dccps_swh - sequence number window high + * @dccps_awl - acknowledgement number window low + * @dccps_awh - acknowledgement number window high + * @dccps_iss - initial sequence number sent + * @dccps_isr - initial sequence number received + * @dccps_osr - first OPEN sequence number received + * @dccps_gss - greatest sequence number sent + * @dccps_gsr - greatest valid sequence number received + * @dccps_gar - greatest valid ack number received on a non-Sync; initialized to %dccps_iss + * @dccps_timestamp_time - time of latest TIMESTAMP option + * @dccps_timestamp_echo - latest timestamp received on a TIMESTAMP option + * @dccps_ext_header_len - network protocol overhead (IP/IPv6 options) + * @dccps_pmtu_cookie - Last pmtu seen by socket + * @dccps_packet_size - Set thru setsockopt + * @dccps_role - Role of this sock, one of %dccp_role + * @dccps_ndp_count - number of Non Data Packets since last data packet + * @dccps_hc_rx_ackpkts - receiver half connection acked packets + */ +struct dccp_sock { + /* inet_connection_sock has to be the first member of dccp_sock */ + struct inet_connection_sock dccps_inet_connection; + __u64 dccps_swl; + __u64 dccps_swh; + __u64 dccps_awl; + __u64 dccps_awh; + __u64 dccps_iss; + __u64 dccps_isr; + __u64 dccps_osr; + __u64 dccps_gss; + __u64 dccps_gsr; + __u64 dccps_gar; + unsigned long dccps_service; + struct timeval dccps_timestamp_time; + __u32 dccps_timestamp_echo; + __u32 dccps_packet_size; + unsigned long dccps_ndp_count; + __u16 dccps_ext_header_len; + __u32 dccps_pmtu_cookie; + __u32 dccps_mss_cache; + struct dccp_options dccps_options; + struct dccp_ackpkts *dccps_hc_rx_ackpkts; + void *dccps_hc_rx_ccid_private; + void *dccps_hc_tx_ccid_private; + struct ccid *dccps_hc_rx_ccid; + struct ccid *dccps_hc_tx_ccid; + struct dccp_options_received dccps_options_received; + enum dccp_role dccps_role:2; +}; + +static inline struct dccp_sock *dccp_sk(const struct sock *sk) +{ + return (struct dccp_sock *)sk; +} + +static inline const char *dccp_role(const struct sock *sk) +{ + switch (dccp_sk(sk)->dccps_role) { + case DCCP_ROLE_UNDEFINED: return "undefined"; + case DCCP_ROLE_LISTEN: return "listen"; + case DCCP_ROLE_SERVER: return "server"; + case DCCP_ROLE_CLIENT: return "client"; + } + return NULL; +} + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_DCCP_H */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index d7021c391b2..ed1440ea4c9 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -250,6 +250,12 @@ struct ethtool_stats { u64 data[0]; }; +struct ethtool_perm_addr { + u32 cmd; /* ETHTOOL_GPERMADDR */ + u32 size; + u8 data[0]; +}; + struct net_device; /* Some generic methods drivers may use in their ethtool_ops */ @@ -261,6 +267,8 @@ u32 ethtool_op_get_sg(struct net_device *dev); int ethtool_op_set_sg(struct net_device *dev, u32 data); u32 ethtool_op_get_tso(struct net_device *dev); int ethtool_op_set_tso(struct net_device *dev, u32 data); +int ethtool_op_get_perm_addr(struct net_device *dev, + struct ethtool_perm_addr *addr, u8 *data); /** * ðtool_ops - Alter and report network device settings @@ -294,7 +302,8 @@ int ethtool_op_set_tso(struct net_device *dev, u32 data); * get_strings: Return a set of strings that describe the requested objects * phys_id: Identify the device * get_stats: Return statistics about the device - * + * get_perm_addr: Gets the permanent hardware address + * * Description: * * get_settings: @@ -352,6 +361,7 @@ struct ethtool_ops { int (*phys_id)(struct net_device *, u32); int (*get_stats_count)(struct net_device *); void (*get_ethtool_stats)(struct net_device *, struct ethtool_stats *, u64 *); + int (*get_perm_addr)(struct net_device *, struct ethtool_perm_addr *, u8 *); int (*begin)(struct net_device *); void (*complete)(struct net_device *); }; @@ -389,6 +399,7 @@ struct ethtool_ops { #define ETHTOOL_GSTATS 0x0000001d /* get NIC-specific statistics */ #define ETHTOOL_GTSO 0x0000001e /* Get TSO enable (ethtool_value) */ #define ETHTOOL_STSO 0x0000001f /* Set TSO enable (ethtool_value) */ +#define ETHTOOL_GPERMADDR 0x00000020 /* Get permanent hardware address */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET diff --git a/include/linux/hippidevice.h b/include/linux/hippidevice.h index 9debe6bbe5f..bab303dafd6 100644 --- a/include/linux/hippidevice.h +++ b/include/linux/hippidevice.h @@ -26,8 +26,12 @@ #include <linux/if_hippi.h> #ifdef __KERNEL__ -extern unsigned short hippi_type_trans(struct sk_buff *skb, - struct net_device *dev); + +struct hippi_cb { + __u32 ifield; +}; + +extern __be16 hippi_type_trans(struct sk_buff *skb, struct net_device *dev); extern struct net_device *alloc_hippi_dev(int sizeof_priv); #endif diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index b5b58e9c054..fc2d4c8225a 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -110,6 +110,8 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb->mac.raw; } + +extern struct ctl_table ether_table[]; #endif #endif /* _LINUX_IF_ETHER_H */ diff --git a/include/linux/if_fc.h b/include/linux/if_fc.h index 33330b458b9..376a34ea472 100644 --- a/include/linux/if_fc.h +++ b/include/linux/if_fc.h @@ -44,7 +44,7 @@ struct fcllc { __u8 ssap; /* source SAP */ __u8 llc; /* LLC control field */ __u8 protid[3]; /* protocol id */ - __u16 ethertype; /* ether type field */ + __be16 ethertype; /* ether type field */ }; #endif /* _LINUX_IF_FC_H */ diff --git a/include/linux/if_fddi.h b/include/linux/if_fddi.h index a912818e636..1288a161bc0 100644 --- a/include/linux/if_fddi.h +++ b/include/linux/if_fddi.h @@ -85,7 +85,7 @@ struct fddi_snap_hdr __u8 ssap; /* always 0xAA */ __u8 ctrl; /* always 0x03 */ __u8 oui[FDDI_K_OUI_LEN]; /* organizational universal id */ - __u16 ethertype; /* packet type ID field */ + __be16 ethertype; /* packet type ID field */ } __attribute__ ((packed)); /* Define FDDI LLC frame header */ diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h index 3c94b173657..511999c7eed 100644 --- a/include/linux/if_frad.h +++ b/include/linux/if_frad.h @@ -191,10 +191,12 @@ struct frad_local int buffer; /* current buffer for S508 firmware */ }; -extern void dlci_ioctl_set(int (*hook)(unsigned int, void __user *)); - #endif /* __KERNEL__ */ #endif /* CONFIG_DLCI || CONFIG_DLCI_MODULE */ +#ifdef __KERNEL__ +extern void dlci_ioctl_set(int (*hook)(unsigned int, void __user *)); +#endif + #endif diff --git a/include/linux/if_hippi.h b/include/linux/if_hippi.h index c8ca72c46f7..94d31ca7d71 100644 --- a/include/linux/if_hippi.h +++ b/include/linux/if_hippi.h @@ -102,9 +102,9 @@ struct hippi_fp_hdr #error "Please fix <asm/byteorder.h>" #endif #else - __u32 fixed; + __be32 fixed; #endif - __u32 d2_size; + __be32 d2_size; } __attribute__ ((packed)); struct hippi_le_hdr @@ -144,7 +144,7 @@ struct hippi_snap_hdr __u8 ssap; /* always 0xAA */ __u8 ctrl; /* always 0x03 */ __u8 oui[HIPPI_OUI_LEN]; /* organizational universal id (zero)*/ - __u16 ethertype; /* packet type ID field */ + __be16 ethertype; /* packet type ID field */ } __attribute__ ((packed)); struct hippi_hdr diff --git a/include/linux/if_tr.h b/include/linux/if_tr.h index 3fba9e2f542..5502f597cf0 100644 --- a/include/linux/if_tr.h +++ b/include/linux/if_tr.h @@ -43,12 +43,16 @@ struct trh_hdr { }; #ifdef __KERNEL__ +#include <linux/config.h> #include <linux/skbuff.h> static inline struct trh_hdr *tr_hdr(const struct sk_buff *skb) { return (struct trh_hdr *)skb->mac.raw; } +#ifdef CONFIG_SYSCTL +extern struct ctl_table tr_table[]; +#endif #endif /* This is an Token-Ring LLC structure */ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 62a9d89dfbe..17d0c0d40b0 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -155,7 +155,6 @@ static inline int __vlan_hwaccel_rx(struct sk_buff *skb, { struct net_device_stats *stats; - skb->real_dev = skb->dev; skb->dev = grp->vlan_devices[vlan_tag & VLAN_VID_MASK]; if (skb->dev == NULL) { dev_kfree_skb_any(skb); diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 0c31ef0b5ba..28f4f3b3695 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -129,6 +129,9 @@ struct igmpv3_query { #include <linux/skbuff.h> #include <linux/in.h> +extern int sysctl_igmp_max_memberships; +extern int sysctl_igmp_max_msf; + struct ip_sf_socklist { unsigned int sl_max; diff --git a/include/linux/in.h b/include/linux/in.h index fb88c66d748..ba355384016 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -32,6 +32,7 @@ enum { IPPROTO_PUP = 12, /* PUP protocol */ IPPROTO_UDP = 17, /* User Datagram Protocol */ IPPROTO_IDP = 22, /* XNS IDP protocol */ + IPPROTO_DCCP = 33, /* Datagram Congestion Control Protocol */ IPPROTO_RSVP = 46, /* RSVP protocol */ IPPROTO_GRE = 47, /* Cisco GRE tunnels (rfc 1701,1702) */ diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h new file mode 100644 index 00000000000..a4606e5810e --- /dev/null +++ b/include/linux/inet_diag.h @@ -0,0 +1,138 @@ +#ifndef _INET_DIAG_H_ +#define _INET_DIAG_H_ 1 + +/* Just some random number */ +#define TCPDIAG_GETSOCK 18 +#define DCCPDIAG_GETSOCK 19 + +#define INET_DIAG_GETSOCK_MAX 24 + +/* Socket identity */ +struct inet_diag_sockid { + __u16 idiag_sport; + __u16 idiag_dport; + __u32 idiag_src[4]; + __u32 idiag_dst[4]; + __u32 idiag_if; + __u32 idiag_cookie[2]; +#define INET_DIAG_NOCOOKIE (~0U) +}; + +/* Request structure */ + +struct inet_diag_req { + __u8 idiag_family; /* Family of addresses. */ + __u8 idiag_src_len; + __u8 idiag_dst_len; + __u8 idiag_ext; /* Query extended information */ + + struct inet_diag_sockid id; + + __u32 idiag_states; /* States to dump */ + __u32 idiag_dbs; /* Tables to dump (NI) */ +}; + +enum { + INET_DIAG_REQ_NONE, + INET_DIAG_REQ_BYTECODE, +}; + +#define INET_DIAG_REQ_MAX INET_DIAG_REQ_BYTECODE + +/* Bytecode is sequence of 4 byte commands followed by variable arguments. + * All the commands identified by "code" are conditional jumps forward: + * to offset cc+"yes" or to offset cc+"no". "yes" is supposed to be + * length of the command and its arguments. + */ + +struct inet_diag_bc_op { + unsigned char code; + unsigned char yes; + unsigned short no; +}; + +enum { + INET_DIAG_BC_NOP, + INET_DIAG_BC_JMP, + INET_DIAG_BC_S_GE, + INET_DIAG_BC_S_LE, + INET_DIAG_BC_D_GE, + INET_DIAG_BC_D_LE, + INET_DIAG_BC_AUTO, + INET_DIAG_BC_S_COND, + INET_DIAG_BC_D_COND, +}; + +struct inet_diag_hostcond { + __u8 family; + __u8 prefix_len; + int port; + __u32 addr[0]; +}; + +/* Base info structure. It contains socket identity (addrs/ports/cookie) + * and, alas, the information shown by netstat. */ +struct inet_diag_msg { + __u8 idiag_family; + __u8 idiag_state; + __u8 idiag_timer; + __u8 idiag_retrans; + + struct inet_diag_sockid id; + + __u32 idiag_expires; + __u32 idiag_rqueue; + __u32 idiag_wqueue; + __u32 idiag_uid; + __u32 idiag_inode; +}; + +/* Extensions */ + +enum { + INET_DIAG_NONE, + INET_DIAG_MEMINFO, + INET_DIAG_INFO, + INET_DIAG_VEGASINFO, + INET_DIAG_CONG, +}; + +#define INET_DIAG_MAX INET_DIAG_CONG + + +/* INET_DIAG_MEM */ + +struct inet_diag_meminfo { + __u32 idiag_rmem; + __u32 idiag_wmem; + __u32 idiag_fmem; + __u32 idiag_tmem; +}; + +/* INET_DIAG_VEGASINFO */ + +struct tcpvegas_info { + __u32 tcpv_enabled; + __u32 tcpv_rttcnt; + __u32 tcpv_rtt; + __u32 tcpv_minrtt; +}; + +#ifdef __KERNEL__ +struct sock; +struct inet_hashinfo; + +struct inet_diag_handler { + struct inet_hashinfo *idiag_hashinfo; + void (*idiag_get_info)(struct sock *sk, + struct inet_diag_msg *r, + void *info); + __u16 idiag_info_size; + __u16 idiag_type; +}; + +extern int inet_diag_register(const struct inet_diag_handler *handler); +extern void inet_diag_unregister(const struct inet_diag_handler *handler); +#endif /* __KERNEL__ */ + +#endif /* _INET_DIAG_H_ */ diff --git a/include/linux/ip.h b/include/linux/ip.h index 31e7cedd9f8..33e8a19a1a0 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -196,6 +196,8 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to, #endif #endif +extern int inet_sk_rebuild_header(struct sock *sk); + struct iphdr { #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 ihl:4, diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 6fcd6a0ade2..3c7dbc6a0a7 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -193,6 +193,11 @@ struct inet6_skb_parm { #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) +static inline int inet6_iif(const struct sk_buff *skb) +{ + return IP6CB(skb)->iif; +} + struct tcp6_request_sock { struct tcp_request_sock req; struct in6_addr loc_addr; @@ -308,6 +313,36 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to, #define __ipv6_only_sock(sk) (inet6_sk(sk)->ipv6only) #define ipv6_only_sock(sk) ((sk)->sk_family == PF_INET6 && __ipv6_only_sock(sk)) + +#include <linux/tcp.h> + +struct tcp6_timewait_sock { + struct tcp_timewait_sock tw_v6_sk; + struct in6_addr tw_v6_daddr; + struct in6_addr tw_v6_rcv_saddr; +}; + +static inline struct tcp6_timewait_sock *tcp6_twsk(const struct sock *sk) +{ + return (struct tcp6_timewait_sock *)sk; +} + +static inline struct in6_addr *__tcp_v6_rcv_saddr(const struct sock *sk) +{ + return likely(sk->sk_state != TCP_TIME_WAIT) ? + &inet6_sk(sk)->rcv_saddr : &tcp6_twsk(sk)->tw_v6_rcv_saddr; +} + +static inline struct in6_addr *tcp_v6_rcv_saddr(const struct sock *sk) +{ + return sk->sk_family == AF_INET6 ? __tcp_v6_rcv_saddr(sk) : NULL; +} + +static inline int inet_v6_ipv6only(const struct sock *sk) +{ + return likely(sk->sk_state != TCP_TIME_WAIT) ? + ipv6_only_sock(sk) : inet_twsk(sk)->tw_ipv6only; +} #else #define __ipv6_only_sock(sk) 0 #define ipv6_only_sock(sk) 0 @@ -322,8 +357,19 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) return NULL; } -#endif +#define __tcp_v6_rcv_saddr(__sk) NULL +#define tcp_v6_rcv_saddr(__sk) NULL +#define tcp_twsk_ipv6only(__sk) 0 +#define inet_v6_ipv6only(__sk) 0 +#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ -#endif +#define INET6_MATCH(__sk, __saddr, __daddr, __ports, __dif) \ + (((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ + ((__sk)->sk_family == AF_INET6) && \ + ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr)) && \ + ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \ + (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) -#endif +#endif /* __KERNEL__ */ + +#endif /* _IPV6_H */ diff --git a/include/linux/list.h b/include/linux/list.h index aab2db21b01..e6ec5968227 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -419,6 +419,20 @@ static inline void list_splice_init(struct list_head *list, pos = n, n = list_entry(n->member.next, typeof(*n), member)) /** + * list_for_each_entry_safe_continue - iterate over list of given type + * continuing after existing point safe against removal of list entry + * @pos: the type * to use as a loop counter. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + */ +#define list_for_each_entry_safe_continue(pos, n, head, member) \ + for (pos = list_entry(pos->member.next, typeof(*pos), member), \ + n = list_entry(pos->member.next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = n, n = list_entry(n->member.next, typeof(*n), member)) + +/** * list_for_each_rcu - iterate over an rcu-protected list * @pos: the &struct list_head to use as a loop counter. * @head: the head for your list. @@ -620,6 +634,57 @@ static inline void hlist_add_after(struct hlist_node *n, next->next->pprev = &next->next; } +/** + * hlist_add_before_rcu - adds the specified element to the specified hlist + * before the specified node while permitting racing traversals. + * @n: the new element to add to the hash list. + * @next: the existing element to add the new element before. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_add_head_rcu() + * or hlist_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_for_each_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. + */ +static inline void hlist_add_before_rcu(struct hlist_node *n, + struct hlist_node *next) +{ + n->pprev = next->pprev; + n->next = next; + smp_wmb(); + next->pprev = &n->next; + *(n->pprev) = n; +} + +/** + * hlist_add_after_rcu - adds the specified element to the specified hlist + * after the specified node while permitting racing traversals. + * @prev: the existing element to add the new element after. + * @n: the new element to add to the hash list. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_add_head_rcu() + * or hlist_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_for_each_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. + */ +static inline void hlist_add_after_rcu(struct hlist_node *prev, + struct hlist_node *n) +{ + n->next = prev->next; + n->pprev = &prev->next; + smp_wmb(); + prev->next = n; + if (n->next) + n->next->pprev = &n->next; +} + #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ diff --git a/include/linux/net.h b/include/linux/net.h index 20cb226b226..4e981585a89 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -84,6 +84,7 @@ enum sock_type { SOCK_RAW = 3, SOCK_RDM = 4, SOCK_SEQPACKET = 5, + SOCK_DCCP = 6, SOCK_PACKET = 10, }; @@ -282,5 +283,15 @@ static struct proto_ops name##_ops = { \ #define MODULE_ALIAS_NETPROTO(proto) \ MODULE_ALIAS("net-pf-" __stringify(proto)) +#define MODULE_ALIAS_NET_PF_PROTO(pf, proto) \ + MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto)) + +#ifdef CONFIG_SYSCTL +#include <linux/sysctl.h> +extern ctl_table net_table[]; +extern int net_msg_cost; +extern int net_msg_burst; +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_NET_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3a0ed7f9e80..7c717907896 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -244,6 +244,7 @@ struct netdev_boot_setup { }; #define NETDEV_BOOT_SETUP_MAX 8 +extern int __init netdev_boot_setup(char *str); /* * The DEVICE structure. @@ -336,6 +337,7 @@ struct net_device /* Interface address info. */ unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ unsigned char dev_addr[MAX_ADDR_LEN]; /* hw address */ + unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ unsigned char addr_len; /* hardware address length */ unsigned short dev_id; /* for shared network cards */ @@ -497,10 +499,12 @@ static inline void *netdev_priv(struct net_device *dev) #define SET_NETDEV_DEV(net, pdev) ((net)->class_dev.dev = (pdev)) struct packet_type { - __be16 type; /* This is really htons(ether_type). */ - struct net_device *dev; /* NULL is wildcarded here */ - int (*func) (struct sk_buff *, struct net_device *, - struct packet_type *); + __be16 type; /* This is really htons(ether_type). */ + struct net_device *dev; /* NULL is wildcarded here */ + int (*func) (struct sk_buff *, + struct net_device *, + struct packet_type *, + struct net_device *); void *af_packet_priv; struct list_head list; }; @@ -671,6 +675,7 @@ extern void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern void dev_init(void); extern int netdev_nit; +extern int netdev_budget; /* Called by rtnetlink.c:rtnl_unlock() */ extern void netdev_run_todo(void); @@ -697,19 +702,9 @@ static inline int netif_carrier_ok(const struct net_device *dev) extern void __netdev_watchdog_up(struct net_device *dev); -static inline void netif_carrier_on(struct net_device *dev) -{ - if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) - linkwatch_fire_event(dev); - if (netif_running(dev)) - __netdev_watchdog_up(dev); -} +extern void netif_carrier_on(struct net_device *dev); -static inline void netif_carrier_off(struct net_device *dev) -{ - if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) - linkwatch_fire_event(dev); -} +extern void netif_carrier_off(struct net_device *dev); /* Hot-plugging. */ static inline int netif_device_present(struct net_device *dev) @@ -916,6 +911,14 @@ extern int skb_checksum_help(struct sk_buff *skb, int inward); extern void net_enable_timestamp(void); extern void net_disable_timestamp(void); +#ifdef CONFIG_PROC_FS +extern void *dev_seq_start(struct seq_file *seq, loff_t *pos); +extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos); +extern void dev_seq_stop(struct seq_file *seq, void *v); +#endif + +extern void linkwatch_run_queue(void); + #endif /* __KERNEL__ */ #endif /* _LINUX_DEV_H */ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 2e2045482cb..be365e70ee9 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -21,10 +21,23 @@ #define NF_STOP 5 #define NF_MAX_VERDICT NF_STOP +/* we overload the higher bits for encoding auxiliary data such as the queue + * number. Not nice, but better than additional function arguments. */ +#define NF_VERDICT_MASK 0x0000ffff +#define NF_VERDICT_BITS 16 + +#define NF_VERDICT_QMASK 0xffff0000 +#define NF_VERDICT_QBITS 16 + +#define NF_QUEUE_NR(x) (((x << NF_VERDICT_QBITS) & NF_VERDICT_QMASK) | NF_QUEUE) + +/* only for userspace compatibility */ +#ifndef __KERNEL__ /* Generic cache responses from hook functions. <= 0x2000 is used for protocol-flags. */ #define NFC_UNKNOWN 0x4000 #define NFC_ALTERED 0x8000 +#endif #ifdef __KERNEL__ #include <linux/config.h> @@ -101,15 +114,51 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg); extern struct list_head nf_hooks[NPROTO][NF_MAX_HOOKS]; -typedef void nf_logfn(unsigned int hooknum, +/* those NF_LOG_* defines and struct nf_loginfo are legacy definitios that will + * disappear once iptables is replaced with pkttables. Please DO NOT use them + * for any new code! */ +#define NF_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ +#define NF_LOG_TCPOPT 0x02 /* Log TCP options */ +#define NF_LOG_IPOPT 0x04 /* Log IP options */ +#define NF_LOG_UID 0x08 /* Log UID owning local socket */ +#define NF_LOG_MASK 0x0f + +#define NF_LOG_TYPE_LOG 0x01 +#define NF_LOG_TYPE_ULOG 0x02 + +struct nf_loginfo { + u_int8_t type; + union { + struct { + u_int32_t copy_len; + u_int16_t group; + u_int16_t qthreshold; + } ulog; + struct { + u_int8_t level; + u_int8_t logflags; + } log; + } u; +}; + +typedef void nf_logfn(unsigned int pf, + unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct nf_loginfo *li, const char *prefix); +struct nf_logger { + struct module *me; + nf_logfn *logfn; + char *name; +}; + /* Function to register/unregister log function. */ -int nf_log_register(int pf, nf_logfn *logfn); -void nf_log_unregister(int pf, nf_logfn *logfn); +int nf_log_register(int pf, struct nf_logger *logger); +int nf_log_unregister_pf(int pf); +void nf_log_unregister_logger(struct nf_logger *logger); /* Calls the registered backend logging function */ void nf_log_packet(int pf, @@ -117,6 +166,7 @@ void nf_log_packet(int pf, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + struct nf_loginfo *li, const char *fmt, ...); /* Activate hook; either okfn or kfree_skb called, unless a hook @@ -175,11 +225,16 @@ int nf_getsockopt(struct sock *sk, int pf, int optval, char __user *opt, int *len); /* Packet queuing */ -typedef int (*nf_queue_outfn_t)(struct sk_buff *skb, - struct nf_info *info, void *data); +struct nf_queue_handler { + int (*outfn)(struct sk_buff *skb, struct nf_info *info, + unsigned int queuenum, void *data); + void *data; + char *name; +}; extern int nf_register_queue_handler(int pf, - nf_queue_outfn_t outfn, void *data); + struct nf_queue_handler *qh); extern int nf_unregister_queue_handler(int pf); +extern void nf_unregister_queue_handlers(struct nf_queue_handler *qh); extern void nf_reinject(struct sk_buff *skb, struct nf_info *info, unsigned int verdict); @@ -190,6 +245,27 @@ extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); /* FIXME: Before cache is ever used, this must be implemented for real. */ extern void nf_invalidate_cache(int pf); +/* Call this before modifying an existing packet: ensures it is + modifiable and linear to the point you care about (writable_len). + Returns true or false. */ +extern int skb_make_writable(struct sk_buff **pskb, unsigned int writable_len); + +struct nf_queue_rerouter { + void (*save)(const struct sk_buff *skb, struct nf_info *info); + int (*reroute)(struct sk_buff **skb, const struct nf_info *info); + int rer_size; +}; + +#define nf_info_reroute(x) ((void *)x + sizeof(struct nf_info)) + +extern int nf_register_queue_rerouter(int pf, struct nf_queue_rerouter *rer); +extern int nf_unregister_queue_rerouter(int pf); + +#ifdef CONFIG_PROC_FS +#include <linux/proc_fs.h> +extern struct proc_dir_entry *proc_net_netfilter; +#endif + #else /* !CONFIG_NETFILTER */ #define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb) static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h new file mode 100644 index 00000000000..1d5b10ae239 --- /dev/null +++ b/include/linux/netfilter/nfnetlink.h @@ -0,0 +1,169 @@ +#ifndef _NFNETLINK_H +#define _NFNETLINK_H +#include <linux/types.h> + +#ifndef __KERNEL__ +/* nfnetlink groups: Up to 32 maximum - backwards compatibility for userspace */ +#define NF_NETLINK_CONNTRACK_NEW 0x00000001 +#define NF_NETLINK_CONNTRACK_UPDATE 0x00000002 +#define NF_NETLINK_CONNTRACK_DESTROY 0x00000004 +#define NF_NETLINK_CONNTRACK_EXP_NEW 0x00000008 +#define NF_NETLINK_CONNTRACK_EXP_UPDATE 0x00000010 +#define NF_NETLINK_CONNTRACK_EXP_DESTROY 0x00000020 +#endif + +enum nfnetlink_groups { + NFNLGRP_NONE, +#define NFNLGRP_NONE NFNLGRP_NONE + NFNLGRP_CONNTRACK_NEW, +#define NFNLGRP_CONNTRACK_NEW NFNLGRP_CONNTRACK_NEW + NFNLGRP_CONNTRACK_UPDATE, +#define NFNLGRP_CONNTRACK_UPDATE NFNLGRP_CONNTRACK_UPDATE + NFNLGRP_CONNTRACK_DESTROY, +#define NFNLGRP_CONNTRACK_DESTROY NFNLGRP_CONNTRACK_DESTROY + NFNLGRP_CONNTRACK_EXP_NEW, +#define NFNLGRP_CONNTRACK_EXP_NEW NFNLGRP_CONNTRACK_EXP_NEW + NFNLGRP_CONNTRACK_EXP_UPDATE, +#define NFNLGRP_CONNTRACK_EXP_UPDATE NFNLGRP_CONNTRACK_EXP_UPDATE + NFNLGRP_CONNTRACK_EXP_DESTROY, +#define NFNLGRP_CONNTRACK_EXP_DESTROY NFNLGRP_CONNTRACK_EXP_DESTROY + __NFNLGRP_MAX, +}; +#define NFNLGRP_MAX (__NFNLGRP_MAX - 1) + +/* Generic structure for encapsulation optional netfilter information. + * It is reminiscent of sockaddr, but with sa_family replaced + * with attribute type. + * ! This should someday be put somewhere generic as now rtnetlink and + * ! nfnetlink use the same attributes methods. - J. Schulist. + */ + +struct nfattr +{ + u_int16_t nfa_len; + u_int16_t nfa_type; +} __attribute__ ((packed)); + +/* FIXME: Shamelessly copy and pasted from rtnetlink.h, it's time + * to put this in a generic file */ + +#define NFA_ALIGNTO 4 +#define NFA_ALIGN(len) (((len) + NFA_ALIGNTO - 1) & ~(NFA_ALIGNTO - 1)) +#define NFA_OK(nfa,len) ((len) > 0 && (nfa)->nfa_len >= sizeof(struct nfattr) \ + && (nfa)->nfa_len <= (len)) +#define NFA_NEXT(nfa,attrlen) ((attrlen) -= NFA_ALIGN((nfa)->nfa_len), \ + (struct nfattr *)(((char *)(nfa)) + NFA_ALIGN((nfa)->nfa_len))) +#define NFA_LENGTH(len) (NFA_ALIGN(sizeof(struct nfattr)) + (len)) +#define NFA_SPACE(len) NFA_ALIGN(NFA_LENGTH(len)) +#define NFA_DATA(nfa) ((void *)(((char *)(nfa)) + NFA_LENGTH(0))) +#define NFA_PAYLOAD(nfa) ((int)((nfa)->nfa_len) - NFA_LENGTH(0)) +#define NFA_NEST(skb, type) \ +({ struct nfattr *__start = (struct nfattr *) (skb)->tail; \ + NFA_PUT(skb, type, 0, NULL); \ + __start; }) +#define NFA_NEST_END(skb, start) \ +({ (start)->nfa_len = ((skb)->tail - (unsigned char *) (start)); \ + (skb)->len; }) +#define NFA_NEST_CANCEL(skb, start) \ +({ if (start) \ + skb_trim(skb, (unsigned char *) (start) - (skb)->data); \ + -1; }) + +/* General form of address family dependent message. + */ +struct nfgenmsg { + u_int8_t nfgen_family; /* AF_xxx */ + u_int8_t version; /* nfnetlink version */ + u_int16_t res_id; /* resource id */ +} __attribute__ ((packed)); + +#define NFNETLINK_V0 0 + +#define NFM_NFA(n) ((struct nfattr *)(((char *)(n)) \ + + NLMSG_ALIGN(sizeof(struct nfgenmsg)))) +#define NFM_PAYLOAD(n) NLMSG_PAYLOAD(n, sizeof(struct nfgenmsg)) + +/* netfilter netlink message types are split in two pieces: + * 8 bit subsystem, 8bit operation. + */ + +#define NFNL_SUBSYS_ID(x) ((x & 0xff00) >> 8) +#define NFNL_MSG_TYPE(x) (x & 0x00ff) + +/* No enum here, otherwise __stringify() trick of MODULE_ALIAS_NFNL_SUBSYS() + * won't work anymore */ +#define NFNL_SUBSYS_NONE 0 +#define NFNL_SUBSYS_CTNETLINK 1 +#define NFNL_SUBSYS_CTNETLINK_EXP 2 +#define NFNL_SUBSYS_QUEUE 3 +#define NFNL_SUBSYS_ULOG 4 +#define NFNL_SUBSYS_COUNT 5 + +#ifdef __KERNEL__ + +#include <linux/netlink.h> +#include <linux/capability.h> + +struct nfnl_callback +{ + int (*call)(struct sock *nl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp); + kernel_cap_t cap_required; /* capabilities required for this msg */ + u_int16_t attr_count; /* number of nfattr's */ +}; + +struct nfnetlink_subsystem +{ + const char *name; + __u8 subsys_id; /* nfnetlink subsystem ID */ + __u8 cb_count; /* number of callbacks */ + struct nfnl_callback *cb; /* callback for individual types */ +}; + +extern void __nfa_fill(struct sk_buff *skb, int attrtype, + int attrlen, const void *data); +#define NFA_PUT(skb, attrtype, attrlen, data) \ +({ if (skb_tailroom(skb) < (int)NFA_SPACE(attrlen)) goto nfattr_failure; \ + __nfa_fill(skb, attrtype, attrlen, data); }) + +extern struct semaphore nfnl_sem; + +#define nfnl_shlock() down(&nfnl_sem) +#define nfnl_shlock_nowait() down_trylock(&nfnl_sem) + +#define nfnl_shunlock() do { up(&nfnl_sem); \ + if(nfnl && nfnl->sk_receive_queue.qlen) \ + nfnl->sk_data_ready(nfnl, 0); \ + } while(0) + +extern void nfnl_lock(void); +extern void nfnl_unlock(void); + +extern int nfnetlink_subsys_register(struct nfnetlink_subsystem *n); +extern int nfnetlink_subsys_unregister(struct nfnetlink_subsystem *n); + +extern int nfattr_parse(struct nfattr *tb[], int maxattr, + struct nfattr *nfa, int len); + +#define nfattr_parse_nested(tb, max, nfa) \ + nfattr_parse((tb), (max), NFA_DATA((nfa)), NFA_PAYLOAD((nfa))) + +#define nfattr_bad_size(tb, max, cta_min) \ +({ int __i, __res = 0; \ + for (__i=0; __i<max; __i++) \ + if (tb[__i] && NFA_PAYLOAD(tb[__i]) < cta_min[__i]){ \ + __res = 1; \ + break; \ + } \ + __res; \ +}) + +extern int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, + int echo); +extern int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags); + +#define MODULE_ALIAS_NFNL_SUBSYS(subsys) \ + MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys)) + +#endif /* __KERNEL__ */ +#endif /* _NFNETLINK_H */ diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h new file mode 100644 index 00000000000..5c55751c78e --- /dev/null +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -0,0 +1,124 @@ +#ifndef _IPCONNTRACK_NETLINK_H +#define _IPCONNTRACK_NETLINK_H +#include <linux/netfilter/nfnetlink.h> + +enum cntl_msg_types { + IPCTNL_MSG_CT_NEW, + IPCTNL_MSG_CT_GET, + IPCTNL_MSG_CT_DELETE, + IPCTNL_MSG_CT_GET_CTRZERO, + + IPCTNL_MSG_MAX +}; + +enum ctnl_exp_msg_types { + IPCTNL_MSG_EXP_NEW, + IPCTNL_MSG_EXP_GET, + IPCTNL_MSG_EXP_DELETE, + + IPCTNL_MSG_EXP_MAX +}; + + +enum ctattr_type { + CTA_UNSPEC, + CTA_TUPLE_ORIG, + CTA_TUPLE_REPLY, + CTA_STATUS, + CTA_PROTOINFO, + CTA_HELP, + CTA_NAT, + CTA_TIMEOUT, + CTA_MARK, + CTA_COUNTERS_ORIG, + CTA_COUNTERS_REPLY, + CTA_USE, + CTA_ID, + __CTA_MAX +}; +#define CTA_MAX (__CTA_MAX - 1) + +enum ctattr_tuple { + CTA_TUPLE_UNSPEC, + CTA_TUPLE_IP, + CTA_TUPLE_PROTO, + __CTA_TUPLE_MAX +}; +#define CTA_TUPLE_MAX (__CTA_TUPLE_MAX - 1) + +enum ctattr_ip { + CTA_IP_UNSPEC, + CTA_IP_V4_SRC, + CTA_IP_V4_DST, + CTA_IP_V6_SRC, + CTA_IP_V6_DST, + __CTA_IP_MAX +}; +#define CTA_IP_MAX (__CTA_IP_MAX - 1) + +enum ctattr_l4proto { + CTA_PROTO_UNSPEC, + CTA_PROTO_NUM, + CTA_PROTO_SRC_PORT, + CTA_PROTO_DST_PORT, + CTA_PROTO_ICMP_ID, + CTA_PROTO_ICMP_TYPE, + CTA_PROTO_ICMP_CODE, + __CTA_PROTO_MAX +}; +#define CTA_PROTO_MAX (__CTA_PROTO_MAX - 1) + +enum ctattr_protoinfo { + CTA_PROTOINFO_UNSPEC, + CTA_PROTOINFO_TCP_STATE, + __CTA_PROTOINFO_MAX +}; +#define CTA_PROTOINFO_MAX (__CTA_PROTOINFO_MAX - 1) + +enum ctattr_counters { + CTA_COUNTERS_UNSPEC, + CTA_COUNTERS_PACKETS, + CTA_COUNTERS_BYTES, + __CTA_COUNTERS_MAX +}; +#define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1) + +enum ctattr_nat { + CTA_NAT_UNSPEC, + CTA_NAT_MINIP, + CTA_NAT_MAXIP, + CTA_NAT_PROTO, + __CTA_NAT_MAX +}; +#define CTA_NAT_MAX (__CTA_NAT_MAX - 1) + +enum ctattr_protonat { + CTA_PROTONAT_UNSPEC, + CTA_PROTONAT_PORT_MIN, + CTA_PROTONAT_PORT_MAX, + __CTA_PROTONAT_MAX +}; +#define CTA_PROTONAT_MAX (__CTA_PROTONAT_MAX - 1) + +enum ctattr_expect { + CTA_EXPECT_UNSPEC, + CTA_EXPECT_MASTER, + CTA_EXPECT_TUPLE, + CTA_EXPECT_MASK, + CTA_EXPECT_TIMEOUT, + CTA_EXPECT_ID, + CTA_EXPECT_HELP_NAME, + __CTA_EXPECT_MAX +}; +#define CTA_EXPECT_MAX (__CTA_EXPECT_MAX - 1) + +enum ctattr_help { + CTA_HELP_UNSPEC, + CTA_HELP_NAME, + __CTA_HELP_MAX +}; +#define CTA_HELP_MAX (__CTA_HELP_MAX - 1) + +#define CTA_HELP_MAXNAMESIZE 32 + +#endif /* _IPCONNTRACK_NETLINK_H */ diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h new file mode 100644 index 00000000000..b04b0388059 --- /dev/null +++ b/include/linux/netfilter/nfnetlink_log.h @@ -0,0 +1,88 @@ +#ifndef _NFNETLINK_LOG_H +#define _NFNETLINK_LOG_H + +/* This file describes the netlink messages (i.e. 'protocol packets'), + * and not any kind of function definitions. It is shared between kernel and + * userspace. Don't put kernel specific stuff in here */ + +#include <linux/types.h> +#include <linux/netfilter/nfnetlink.h> + +enum nfulnl_msg_types { + NFULNL_MSG_PACKET, /* packet from kernel to userspace */ + NFULNL_MSG_CONFIG, /* connect to a particular queue */ + + NFULNL_MSG_MAX +}; + +struct nfulnl_msg_packet_hdr { + u_int16_t hw_protocol; /* hw protocol (network order) */ + u_int8_t hook; /* netfilter hook */ + u_int8_t _pad; +} __attribute__ ((packed)); + +struct nfulnl_msg_packet_hw { + u_int16_t hw_addrlen; + u_int16_t _pad; + u_int8_t hw_addr[8]; +} __attribute__ ((packed)); + +struct nfulnl_msg_packet_timestamp { + aligned_u64 sec; + aligned_u64 usec; +} __attribute__ ((packed)); + +#define NFULNL_PREFIXLEN 30 /* just like old log target */ + +enum nfulnl_attr_type { + NFULA_UNSPEC, + NFULA_PACKET_HDR, + NFULA_MARK, /* u_int32_t nfmark */ + NFULA_TIMESTAMP, /* nfulnl_msg_packet_timestamp */ + NFULA_IFINDEX_INDEV, /* u_int32_t ifindex */ + NFULA_IFINDEX_OUTDEV, /* u_int32_t ifindex */ + NFULA_IFINDEX_PHYSINDEV, /* u_int32_t ifindex */ + NFULA_IFINDEX_PHYSOUTDEV, /* u_int32_t ifindex */ + NFULA_HWADDR, /* nfulnl_msg_packet_hw */ + NFULA_PAYLOAD, /* opaque data payload */ + NFULA_PREFIX, /* string prefix */ + NFULA_UID, /* user id of socket */ + + __NFULA_MAX +}; +#define NFULA_MAX (__NFULA_MAX - 1) + +enum nfulnl_msg_config_cmds { + NFULNL_CFG_CMD_NONE, + NFULNL_CFG_CMD_BIND, + NFULNL_CFG_CMD_UNBIND, + NFULNL_CFG_CMD_PF_BIND, + NFULNL_CFG_CMD_PF_UNBIND, +}; + +struct nfulnl_msg_config_cmd { + u_int8_t command; /* nfulnl_msg_config_cmds */ +} __attribute__ ((packed)); + +struct nfulnl_msg_config_mode { + u_int32_t copy_range; + u_int8_t copy_mode; + u_int8_t _pad; +} __attribute__ ((packed)); + +enum nfulnl_attr_config { + NFULA_CFG_UNSPEC, + NFULA_CFG_CMD, /* nfulnl_msg_config_cmd */ + NFULA_CFG_MODE, /* nfulnl_msg_config_mode */ + NFULA_CFG_NLBUFSIZ, /* u_int32_t buffer size */ + NFULA_CFG_TIMEOUT, /* u_int32_t in 1/100 s */ + NFULA_CFG_QTHRESH, /* u_int32_t */ + __NFULA_CFG_MAX +}; +#define NFULA_CFG_MAX (__NFULA_CFG_MAX -1) + +#define NFULNL_COPY_NONE 0x00 +#define NFULNL_COPY_META 0x01 +#define NFULNL_COPY_PACKET 0x02 + +#endif /* _NFNETLINK_LOG_H */ diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h new file mode 100644 index 00000000000..9e774373244 --- /dev/null +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -0,0 +1,89 @@ +#ifndef _NFNETLINK_QUEUE_H +#define _NFNETLINK_QUEUE_H + +#include <linux/types.h> +#include <linux/netfilter/nfnetlink.h> + +enum nfqnl_msg_types { + NFQNL_MSG_PACKET, /* packet from kernel to userspace */ + NFQNL_MSG_VERDICT, /* verdict from userspace to kernel */ + NFQNL_MSG_CONFIG, /* connect to a particular queue */ + + NFQNL_MSG_MAX +}; + +struct nfqnl_msg_packet_hdr { + u_int32_t packet_id; /* unique ID of packet in queue */ + u_int16_t hw_protocol; /* hw protocol (network order) */ + u_int8_t hook; /* netfilter hook */ +} __attribute__ ((packed)); + +struct nfqnl_msg_packet_hw { + u_int16_t hw_addrlen; + u_int16_t _pad; + u_int8_t hw_addr[8]; +} __attribute__ ((packed)); + +struct nfqnl_msg_packet_timestamp { + aligned_u64 sec; + aligned_u64 usec; +} __attribute__ ((packed)); + +enum nfqnl_attr_type { + NFQA_UNSPEC, + NFQA_PACKET_HDR, + NFQA_VERDICT_HDR, /* nfqnl_msg_verdict_hrd */ + NFQA_MARK, /* u_int32_t nfmark */ + NFQA_TIMESTAMP, /* nfqnl_msg_packet_timestamp */ + NFQA_IFINDEX_INDEV, /* u_int32_t ifindex */ + NFQA_IFINDEX_OUTDEV, /* u_int32_t ifindex */ + NFQA_IFINDEX_PHYSINDEV, /* u_int32_t ifindex */ + NFQA_IFINDEX_PHYSOUTDEV, /* u_int32_t ifindex */ + NFQA_HWADDR, /* nfqnl_msg_packet_hw */ + NFQA_PAYLOAD, /* opaque data payload */ + + __NFQA_MAX +}; +#define NFQA_MAX (__NFQA_MAX - 1) + +struct nfqnl_msg_verdict_hdr { + u_int32_t verdict; + u_int32_t id; +} __attribute__ ((packed)); + + +enum nfqnl_msg_config_cmds { + NFQNL_CFG_CMD_NONE, + NFQNL_CFG_CMD_BIND, + NFQNL_CFG_CMD_UNBIND, + NFQNL_CFG_CMD_PF_BIND, + NFQNL_CFG_CMD_PF_UNBIND, +}; + +struct nfqnl_msg_config_cmd { + u_int8_t command; /* nfqnl_msg_config_cmds */ + u_int8_t _pad; + u_int16_t pf; /* AF_xxx for PF_[UN]BIND */ +} __attribute__ ((packed)); + +enum nfqnl_config_mode { + NFQNL_COPY_NONE, + NFQNL_COPY_META, + NFQNL_COPY_PACKET, +}; + +struct nfqnl_msg_config_params { + u_int32_t copy_range; + u_int8_t copy_mode; /* enum nfqnl_config_mode */ +} __attribute__ ((packed)); + + +enum nfqnl_attr_config { + NFQA_CFG_UNSPEC, + NFQA_CFG_CMD, /* nfqnl_msg_config_cmd */ + NFQA_CFG_PARAMS, /* nfqnl_msg_config_params */ + __NFQA_CFG_MAX +}; +#define NFQA_CFG_MAX (__NFQA_CFG_MAX-1) + +#endif /* _NFNETLINK_QUEUE_H */ diff --git a/include/linux/netfilter_decnet.h b/include/linux/netfilter_decnet.h index 3064eec9cb8..6f425369ee2 100644 --- a/include/linux/netfilter_decnet.h +++ b/include/linux/netfilter_decnet.h @@ -9,6 +9,8 @@ #include <linux/netfilter.h> +/* only for userspace compatibility */ +#ifndef __KERNEL__ /* IP Cache bits. */ /* Src IP address. */ #define NFC_DN_SRC 0x0001 @@ -18,6 +20,7 @@ #define NFC_DN_IF_IN 0x0004 /* Output device. */ #define NFC_DN_IF_OUT 0x0008 +#endif /* ! __KERNEL__ */ /* DECnet Hooks */ /* After promisc drops, checksum checks. */ @@ -53,7 +56,21 @@ struct nf_dn_rtmsg { #define NFDN_RTMSG(r) ((unsigned char *)(r) + NLMSG_ALIGN(sizeof(struct nf_dn_rtmsg))) +#ifndef __KERNEL__ +/* backwards compatibility for userspace */ #define DNRMG_L1_GROUP 0x01 #define DNRMG_L2_GROUP 0x02 +#endif + +enum { + DNRNG_NLGRP_NONE, +#define DNRNG_NLGRP_NONE DNRNG_NLGRP_NONE + DNRNG_NLGRP_L1, +#define DNRNG_NLGRP_L1 DNRNG_NLGRP_L1 + DNRNG_NLGRP_L2, +#define DNRNG_NLGRP_L2 DNRNG_NLGRP_L2 + __DNRNG_NLGRP_MAX +}; +#define DNRNG_NLGRP_MAX (__DNRNG_NLGRP_MAX - 1) #endif /*__LINUX_DECNET_NETFILTER_H*/ diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 3ebc36afae1..fdc4a952734 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -8,6 +8,8 @@ #include <linux/config.h> #include <linux/netfilter.h> +/* only for userspace compatibility */ +#ifndef __KERNEL__ /* IP Cache bits. */ /* Src IP address. */ #define NFC_IP_SRC 0x0001 @@ -35,6 +37,7 @@ #define NFC_IP_DST_PT 0x0400 /* Something else about the proto */ #define NFC_IP_PROTO_UNKNOWN 0x2000 +#endif /* ! __KERNEL__ */ /* IP Hooks */ /* After promisc drops, checksum checks. */ @@ -77,11 +80,6 @@ enum nf_ip_hook_priorities { #ifdef __KERNEL__ extern int ip_route_me_harder(struct sk_buff **pskb); -/* Call this before modifying an existing IP packet: ensures it is - modifiable and linear to the point you care about (writable_len). - Returns true or false. */ -extern int skb_ip_make_writable(struct sk_buff **pskb, - unsigned int writable_len); #endif /*__KERNEL__*/ #endif /*__LINUX_IP_NETFILTER_H*/ diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index 08fe5f7d14a..088742befe4 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -65,6 +65,63 @@ enum ip_conntrack_status { /* Both together */ IPS_NAT_DONE_MASK = (IPS_DST_NAT_DONE | IPS_SRC_NAT_DONE), + + /* Connection is dying (removed from lists), can not be unset. */ + IPS_DYING_BIT = 9, + IPS_DYING = (1 << IPS_DYING_BIT), +}; + +/* Connection tracking event bits */ +enum ip_conntrack_events +{ + /* New conntrack */ + IPCT_NEW_BIT = 0, + IPCT_NEW = (1 << IPCT_NEW_BIT), + + /* Expected connection */ + IPCT_RELATED_BIT = 1, + IPCT_RELATED = (1 << IPCT_RELATED_BIT), + + /* Destroyed conntrack */ + IPCT_DESTROY_BIT = 2, + IPCT_DESTROY = (1 << IPCT_DESTROY_BIT), + + /* Timer has been refreshed */ + IPCT_REFRESH_BIT = 3, + IPCT_REFRESH = (1 << IPCT_REFRESH_BIT), + + /* Status has changed */ + IPCT_STATUS_BIT = 4, + IPCT_STATUS = (1 << IPCT_STATUS_BIT), + + /* Update of protocol info */ + IPCT_PROTOINFO_BIT = 5, + IPCT_PROTOINFO = (1 << IPCT_PROTOINFO_BIT), + + /* Volatile protocol info */ + IPCT_PROTOINFO_VOLATILE_BIT = 6, + IPCT_PROTOINFO_VOLATILE = (1 << IPCT_PROTOINFO_VOLATILE_BIT), + + /* New helper for conntrack */ + IPCT_HELPER_BIT = 7, + IPCT_HELPER = (1 << IPCT_HELPER_BIT), + + /* Update of helper info */ + IPCT_HELPINFO_BIT = 8, + IPCT_HELPINFO = (1 << IPCT_HELPINFO_BIT), + + /* Volatile helper info */ + IPCT_HELPINFO_VOLATILE_BIT = 9, + IPCT_HELPINFO_VOLATILE = (1 << IPCT_HELPINFO_VOLATILE_BIT), + + /* NAT info */ + IPCT_NATINFO_BIT = 10, + IPCT_NATINFO = (1 << IPCT_NATINFO_BIT), +}; + +enum ip_conntrack_expect_events { + IPEXP_NEW_BIT = 0, + IPEXP_NEW = (1 << IPEXP_NEW_BIT), }; #ifdef __KERNEL__ @@ -152,6 +209,9 @@ struct ip_conntrack /* Current number of expected connections */ unsigned int expecting; + /* Unique ID that identifies this conntrack*/ + unsigned int id; + /* Helper, if any. */ struct ip_conntrack_helper *helper; @@ -171,7 +231,7 @@ struct ip_conntrack #endif /* CONFIG_IP_NF_NAT_NEEDED */ #if defined(CONFIG_IP_NF_CONNTRACK_MARK) - unsigned long mark; + u_int32_t mark; #endif /* Traversed often, so hopefully in different cacheline to top */ @@ -200,6 +260,9 @@ struct ip_conntrack_expect /* Usage count. */ atomic_t use; + /* Unique ID */ + unsigned int id; + #ifdef CONFIG_IP_NF_NAT_NEEDED /* This is the original per-proto part, used to map the * expected connection the way the recipient expects. */ @@ -239,7 +302,12 @@ ip_conntrack_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo) } /* decrement reference count on a conntrack */ -extern void ip_conntrack_put(struct ip_conntrack *ct); +static inline void +ip_conntrack_put(struct ip_conntrack *ct) +{ + IP_NF_ASSERT(ct); + nf_conntrack_put(&ct->ct_general); +} /* call to create an explicit dependency on ip_conntrack. */ extern void need_ip_conntrack(void); @@ -274,12 +342,50 @@ extern void ip_ct_iterate_cleanup(int (*iter)(struct ip_conntrack *i, void *data), void *data); +extern struct ip_conntrack_helper * +__ip_conntrack_helper_find_byname(const char *); +extern struct ip_conntrack_helper * +ip_conntrack_helper_find_get(const struct ip_conntrack_tuple *tuple); +extern void ip_conntrack_helper_put(struct ip_conntrack_helper *helper); + +extern struct ip_conntrack_protocol * +__ip_conntrack_proto_find(u_int8_t protocol); +extern struct ip_conntrack_protocol * +ip_conntrack_proto_find_get(u_int8_t protocol); +extern void ip_conntrack_proto_put(struct ip_conntrack_protocol *proto); + +extern void ip_ct_remove_expectations(struct ip_conntrack *ct); + +extern struct ip_conntrack *ip_conntrack_alloc(struct ip_conntrack_tuple *, + struct ip_conntrack_tuple *); + +extern void ip_conntrack_free(struct ip_conntrack *ct); + +extern void ip_conntrack_hash_insert(struct ip_conntrack *ct); + +extern struct ip_conntrack_expect * +__ip_conntrack_expect_find(const struct ip_conntrack_tuple *tuple); + +extern struct ip_conntrack_expect * +ip_conntrack_expect_find_get(const struct ip_conntrack_tuple *tuple); + +extern struct ip_conntrack_tuple_hash * +__ip_conntrack_find(const struct ip_conntrack_tuple *tuple, + const struct ip_conntrack *ignored_conntrack); + +extern void ip_conntrack_flush(void); + /* It's confirmed if it is, or has been in the hash table. */ static inline int is_confirmed(struct ip_conntrack *ct) { return test_bit(IPS_CONFIRMED_BIT, &ct->status); } +static inline int is_dying(struct ip_conntrack *ct) +{ + return test_bit(IPS_DYING_BIT, &ct->status); +} + extern unsigned int ip_conntrack_htable_size; struct ip_conntrack_stat @@ -303,6 +409,85 @@ struct ip_conntrack_stat #define CONNTRACK_STAT_INC(count) (__get_cpu_var(ip_conntrack_stat).count++) +#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS +#include <linux/notifier.h> +#include <linux/interrupt.h> + +struct ip_conntrack_ecache { + struct ip_conntrack *ct; + unsigned int events; +}; +DECLARE_PER_CPU(struct ip_conntrack_ecache, ip_conntrack_ecache); + +#define CONNTRACK_ECACHE(x) (__get_cpu_var(ip_conntrack_ecache).x) + +extern struct notifier_block *ip_conntrack_chain; +extern struct notifier_block *ip_conntrack_expect_chain; + +static inline int ip_conntrack_register_notifier(struct notifier_block *nb) +{ + return notifier_chain_register(&ip_conntrack_chain, nb); +} + +static inline int ip_conntrack_unregister_notifier(struct notifier_block *nb) +{ + return notifier_chain_unregister(&ip_conntrack_chain, nb); +} + +static inline int +ip_conntrack_expect_register_notifier(struct notifier_block *nb) +{ + return notifier_chain_register(&ip_conntrack_expect_chain, nb); +} + +static inline int +ip_conntrack_expect_unregister_notifier(struct notifier_block *nb) +{ + return notifier_chain_unregister(&ip_conntrack_expect_chain, nb); +} + +extern void ip_ct_deliver_cached_events(const struct ip_conntrack *ct); +extern void __ip_ct_event_cache_init(struct ip_conntrack *ct); + +static inline void +ip_conntrack_event_cache(enum ip_conntrack_events event, + const struct sk_buff *skb) +{ + struct ip_conntrack *ct = (struct ip_conntrack *)skb->nfct; + struct ip_conntrack_ecache *ecache; + + local_bh_disable(); + ecache = &__get_cpu_var(ip_conntrack_ecache); + if (ct != ecache->ct) + __ip_ct_event_cache_init(ct); + ecache->events |= event; + local_bh_enable(); +} + +static inline void ip_conntrack_event(enum ip_conntrack_events event, + struct ip_conntrack *ct) +{ + if (is_confirmed(ct) && !is_dying(ct)) + notifier_call_chain(&ip_conntrack_chain, event, ct); +} + +static inline void +ip_conntrack_expect_event(enum ip_conntrack_expect_events event, + struct ip_conntrack_expect *exp) +{ + notifier_call_chain(&ip_conntrack_expect_chain, event, exp); +} +#else /* CONFIG_IP_NF_CONNTRACK_EVENTS */ +static inline void ip_conntrack_event_cache(enum ip_conntrack_events event, + const struct sk_buff *skb) {} +static inline void ip_conntrack_event(enum ip_conntrack_events event, + struct ip_conntrack *ct) {} +static inline void ip_ct_deliver_cached_events(const struct ip_conntrack *ct) {} +static inline void +ip_conntrack_expect_event(enum ip_conntrack_expect_events event, + struct ip_conntrack_expect *exp) {} +#endif /* CONFIG_IP_NF_CONNTRACK_EVENTS */ + #ifdef CONFIG_IP_NF_NAT_NEEDED static inline int ip_nat_initialized(struct ip_conntrack *conntrack, enum ip_nat_manip_type manip) diff --git a/include/linux/netfilter_ipv4/ip_conntrack_core.h b/include/linux/netfilter_ipv4/ip_conntrack_core.h index 694aec9b478..dc4d2a0575d 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_core.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_core.h @@ -2,6 +2,9 @@ #define _IP_CONNTRACK_CORE_H #include <linux/netfilter.h> +#define MAX_IP_CT_PROTO 256 +extern struct ip_conntrack_protocol *ip_ct_protos[MAX_IP_CT_PROTO]; + /* This header is used to share core functionality between the standalone connection tracking module, and the compatibility layer's use of connection tracking. */ @@ -38,12 +41,19 @@ extern int __ip_conntrack_confirm(struct sk_buff **pskb); /* Confirm a connection: returns NF_DROP if packet must be dropped. */ static inline int ip_conntrack_confirm(struct sk_buff **pskb) { - if ((*pskb)->nfct - && !is_confirmed((struct ip_conntrack *)(*pskb)->nfct)) - return __ip_conntrack_confirm(pskb); - return NF_ACCEPT; + struct ip_conntrack *ct = (struct ip_conntrack *)(*pskb)->nfct; + int ret = NF_ACCEPT; + + if (ct) { + if (!is_confirmed(ct)) + ret = __ip_conntrack_confirm(pskb); + ip_ct_deliver_cached_events(ct); + } + return ret; } +extern void __ip_ct_expect_unlink_destroy(struct ip_conntrack_expect *exp); + extern struct list_head *ip_conntrack_hash; extern struct list_head ip_conntrack_expect_list; extern rwlock_t ip_conntrack_lock; diff --git a/include/linux/netfilter_ipv4/ip_conntrack_helper.h b/include/linux/netfilter_ipv4/ip_conntrack_helper.h index 3692daa93de..8d69279ccfe 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_helper.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_helper.h @@ -24,6 +24,8 @@ struct ip_conntrack_helper int (*help)(struct sk_buff **pskb, struct ip_conntrack *ct, enum ip_conntrack_info conntrackinfo); + + int (*to_nfattr)(struct sk_buff *skb, const struct ip_conntrack *ct); }; extern int ip_conntrack_helper_register(struct ip_conntrack_helper *); diff --git a/include/linux/netfilter_ipv4/ip_conntrack_protocol.h b/include/linux/netfilter_ipv4/ip_conntrack_protocol.h index e20b57c5e1b..b6b99be8632 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_protocol.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_protocol.h @@ -2,6 +2,7 @@ #ifndef _IP_CONNTRACK_PROTOCOL_H #define _IP_CONNTRACK_PROTOCOL_H #include <linux/netfilter_ipv4/ip_conntrack.h> +#include <linux/netfilter/nfnetlink_conntrack.h> struct seq_file; @@ -47,22 +48,22 @@ struct ip_conntrack_protocol int (*error)(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, unsigned int hooknum); + /* convert protoinfo to nfnetink attributes */ + int (*to_nfattr)(struct sk_buff *skb, struct nfattr *nfa, + const struct ip_conntrack *ct); + + int (*tuple_to_nfattr)(struct sk_buff *skb, + const struct ip_conntrack_tuple *t); + int (*nfattr_to_tuple)(struct nfattr *tb[], + struct ip_conntrack_tuple *t); + /* Module (if any) which this is connected to. */ struct module *me; }; -#define MAX_IP_CT_PROTO 256 -extern struct ip_conntrack_protocol *ip_ct_protos[MAX_IP_CT_PROTO]; - /* Protocol registration. */ extern int ip_conntrack_protocol_register(struct ip_conntrack_protocol *proto); extern void ip_conntrack_protocol_unregister(struct ip_conntrack_protocol *proto); - -static inline struct ip_conntrack_protocol *ip_ct_find_proto(u_int8_t protocol) -{ - return ip_ct_protos[protocol]; -} - /* Existing built-in protocols */ extern struct ip_conntrack_protocol ip_conntrack_protocol_tcp; extern struct ip_conntrack_protocol ip_conntrack_protocol_udp; @@ -73,6 +74,11 @@ extern int ip_conntrack_protocol_tcp_init(void); /* Log invalid packets */ extern unsigned int ip_ct_log_invalid; +extern int ip_ct_port_tuple_to_nfattr(struct sk_buff *, + const struct ip_conntrack_tuple *); +extern int ip_ct_port_nfattr_to_tuple(struct nfattr *tb[], + struct ip_conntrack_tuple *); + #ifdef CONFIG_SYSCTL #ifdef DEBUG_INVALID_PACKETS #define LOG_INVALID(proto) \ diff --git a/include/linux/netfilter_ipv4/ip_logging.h b/include/linux/netfilter_ipv4/ip_logging.h deleted file mode 100644 index 0c5c52cb658..00000000000 --- a/include/linux/netfilter_ipv4/ip_logging.h +++ /dev/null @@ -1,20 +0,0 @@ -/* IPv4 macros for the internal logging interface. */ -#ifndef __IP_LOGGING_H -#define __IP_LOGGING_H - -#ifdef __KERNEL__ -#include <linux/socket.h> -#include <linux/netfilter_logging.h> - -#define nf_log_ip_packet(pskb,hooknum,in,out,fmt,args...) \ - nf_log_packet(AF_INET,pskb,hooknum,in,out,fmt,##args) - -#define nf_log_ip(pfh,len,fmt,args...) \ - nf_log(AF_INET,pfh,len,fmt,##args) - -#define nf_ip_log_register(logging) nf_log_register(AF_INET,logging) -#define nf_ip_log_unregister(logging) nf_log_unregister(AF_INET,logging) - -#endif /*__KERNEL__*/ - -#endif /*__IP_LOGGING_H*/ diff --git a/include/linux/netfilter_ipv4/ip_nat_protocol.h b/include/linux/netfilter_ipv4/ip_nat_protocol.h index 129708c2238..ef63aa991a0 100644 --- a/include/linux/netfilter_ipv4/ip_nat_protocol.h +++ b/include/linux/netfilter_ipv4/ip_nat_protocol.h @@ -4,6 +4,9 @@ #include <linux/init.h> #include <linux/list.h> +#include <linux/netfilter_ipv4/ip_nat.h> +#include <linux/netfilter/nfnetlink_conntrack.h> + struct iphdr; struct ip_nat_range; @@ -15,6 +18,8 @@ struct ip_nat_protocol /* Protocol number. */ unsigned int protonum; + struct module *me; + /* Translate a packet to the target according to manip type. Return true if succeeded. */ int (*manip_pkt)(struct sk_buff **pskb, @@ -43,19 +48,20 @@ struct ip_nat_protocol unsigned int (*print_range)(char *buffer, const struct ip_nat_range *range); -}; -#define MAX_IP_NAT_PROTO 256 -extern struct ip_nat_protocol *ip_nat_protos[MAX_IP_NAT_PROTO]; + int (*range_to_nfattr)(struct sk_buff *skb, + const struct ip_nat_range *range); + + int (*nfattr_to_range)(struct nfattr *tb[], + struct ip_nat_range *range); +}; /* Protocol registration. */ extern int ip_nat_protocol_register(struct ip_nat_protocol *proto); extern void ip_nat_protocol_unregister(struct ip_nat_protocol *proto); -static inline struct ip_nat_protocol *ip_nat_find_proto(u_int8_t protocol) -{ - return ip_nat_protos[protocol]; -} +extern struct ip_nat_protocol *ip_nat_proto_find_get(u_int8_t protocol); +extern void ip_nat_proto_put(struct ip_nat_protocol *proto); /* Built-in protocols. */ extern struct ip_nat_protocol ip_nat_protocol_tcp; @@ -67,4 +73,9 @@ extern int init_protocols(void) __init; extern void cleanup_protocols(void); extern struct ip_nat_protocol *find_nat_proto(u_int16_t protonum); +extern int ip_nat_port_range_to_nfattr(struct sk_buff *skb, + const struct ip_nat_range *range); +extern int ip_nat_port_nfattr_to_range(struct nfattr *tb[], + struct ip_nat_range *range); + #endif /*_IP_NAT_PROTO_H*/ diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 12ce47808e7..d19d65cf453 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -109,7 +109,8 @@ struct ipt_counters /* Values for "flag" field in struct ipt_ip (general ip structure). */ #define IPT_F_FRAG 0x01 /* Set if rule is a fragment rule */ -#define IPT_F_MASK 0x01 /* All possible flag bits mask. */ +#define IPT_F_GOTO 0x02 /* Set if jump is a goto */ +#define IPT_F_MASK 0x03 /* All possible flag bits mask. */ /* Values for "inv" field in struct ipt_ip. */ #define IPT_INV_VIA_IN 0x01 /* Invert the sense of IN IFACE. */ diff --git a/include/linux/netfilter_ipv4/ipt_LOG.h b/include/linux/netfilter_ipv4/ipt_LOG.h index d25f782e57d..22d16177319 100644 --- a/include/linux/netfilter_ipv4/ipt_LOG.h +++ b/include/linux/netfilter_ipv4/ipt_LOG.h @@ -1,6 +1,7 @@ #ifndef _IPT_LOG_H #define _IPT_LOG_H +/* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */ #define IPT_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ #define IPT_LOG_TCPOPT 0x02 /* Log TCP options */ #define IPT_LOG_IPOPT 0x04 /* Log IP options */ diff --git a/include/linux/netfilter_ipv4/ipt_NFQUEUE.h b/include/linux/netfilter_ipv4/ipt_NFQUEUE.h new file mode 100644 index 00000000000..b5b2943b0c6 --- /dev/null +++ b/include/linux/netfilter_ipv4/ipt_NFQUEUE.h @@ -0,0 +1,16 @@ +/* iptables module for using NFQUEUE mechanism + * + * (C) 2005 Harald Welte <laforge@netfilter.org> + * + * This software is distributed under GNU GPL v2, 1991 + * +*/ +#ifndef _IPT_NFQ_TARGET_H +#define _IPT_NFQ_TARGET_H + +/* target info */ +struct ipt_NFQ_info { + u_int16_t queuenum; +}; + +#endif /* _IPT_DSCP_TARGET_H */ diff --git a/include/linux/netfilter_ipv4/ipt_TTL.h b/include/linux/netfilter_ipv4/ipt_TTL.h new file mode 100644 index 00000000000..ee6611edc11 --- /dev/null +++ b/include/linux/netfilter_ipv4/ipt_TTL.h @@ -0,0 +1,21 @@ +/* TTL modification module for IP tables + * (C) 2000 by Harald Welte <laforge@netfilter.org> */ + +#ifndef _IPT_TTL_H +#define _IPT_TTL_H + +enum { + IPT_TTL_SET = 0, + IPT_TTL_INC, + IPT_TTL_DEC +}; + +#define IPT_TTL_MAXMODE IPT_TTL_DEC + +struct ipt_TTL_info { + u_int8_t mode; + u_int8_t ttl; +}; + + +#endif diff --git a/include/linux/netfilter_ipv4/ipt_connbytes.h b/include/linux/netfilter_ipv4/ipt_connbytes.h new file mode 100644 index 00000000000..9e5532f8d8a --- /dev/null +++ b/include/linux/netfilter_ipv4/ipt_connbytes.h @@ -0,0 +1,25 @@ +#ifndef _IPT_CONNBYTES_H +#define _IPT_CONNBYTES_H + +enum ipt_connbytes_what { + IPT_CONNBYTES_PKTS, + IPT_CONNBYTES_BYTES, + IPT_CONNBYTES_AVGPKT, +}; + +enum ipt_connbytes_direction { + IPT_CONNBYTES_DIR_ORIGINAL, + IPT_CONNBYTES_DIR_REPLY, + IPT_CONNBYTES_DIR_BOTH, +}; + +struct ipt_connbytes_info +{ + struct { + aligned_u64 from; /* count to be matched */ + aligned_u64 to; /* count to be matched */ + } count; + u_int8_t what; /* ipt_connbytes_what */ + u_int8_t direction; /* ipt_connbytes_direction */ +}; +#endif diff --git a/include/linux/netfilter_ipv4/ipt_dccp.h b/include/linux/netfilter_ipv4/ipt_dccp.h new file mode 100644 index 00000000000..3cb3a522e62 --- /dev/null +++ b/include/linux/netfilter_ipv4/ipt_dccp.h @@ -0,0 +1,23 @@ +#ifndef _IPT_DCCP_H_ +#define _IPT_DCCP_H_ + +#define IPT_DCCP_SRC_PORTS 0x01 +#define IPT_DCCP_DEST_PORTS 0x02 +#define IPT_DCCP_TYPE 0x04 +#define IPT_DCCP_OPTION 0x08 + +#define IPT_DCCP_VALID_FLAGS 0x0f + +struct ipt_dccp_info { + u_int16_t dpts[2]; /* Min, Max */ + u_int16_t spts[2]; /* Min, Max */ + + u_int16_t flags; + u_int16_t invflags; + + u_int16_t typemask; + u_int8_t option; +}; + +#endif /* _IPT_DCCP_H_ */ + diff --git a/include/linux/netfilter_ipv4/ipt_string.h b/include/linux/netfilter_ipv4/ipt_string.h new file mode 100644 index 00000000000..a265f6e44ea --- /dev/null +++ b/include/linux/netfilter_ipv4/ipt_string.h @@ -0,0 +1,18 @@ +#ifndef _IPT_STRING_H +#define _IPT_STRING_H + +#define IPT_STRING_MAX_PATTERN_SIZE 128 +#define IPT_STRING_MAX_ALGO_NAME_SIZE 16 + +struct ipt_string_info +{ + u_int16_t from_offset; + u_int16_t to_offset; + char algo[IPT_STRING_MAX_ALGO_NAME_SIZE]; + char pattern[IPT_STRING_MAX_PATTERN_SIZE]; + u_int8_t patlen; + u_int8_t invert; + struct ts_config __attribute__((aligned(8))) *config; +}; + +#endif /*_IPT_STRING_H*/ diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index bee7a5ec7c6..edcc2c6eb5c 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -10,6 +10,8 @@ #include <linux/netfilter.h> +/* only for userspace compatibility */ +#ifndef __KERNEL__ /* IP Cache bits. */ /* Src IP address. */ #define NFC_IP6_SRC 0x0001 @@ -38,6 +40,7 @@ #define NFC_IP6_DST_PT 0x0400 /* Something else about the proto */ #define NFC_IP6_PROTO_UNKNOWN 0x2000 +#endif /* ! __KERNEL__ */ /* IP6 Hooks */ @@ -68,4 +71,7 @@ enum nf_ip6_hook_priorities { NF_IP6_PRI_LAST = INT_MAX, }; +extern int ipv6_netfilter_init(void); +extern void ipv6_netfilter_fini(void); + #endif /*__LINUX_IP6_NETFILTER_H*/ diff --git a/include/linux/netfilter_ipv6/ip6_logging.h b/include/linux/netfilter_ipv6/ip6_logging.h deleted file mode 100644 index a0b2ee3043a..00000000000 --- a/include/linux/netfilter_ipv6/ip6_logging.h +++ /dev/null @@ -1,20 +0,0 @@ -/* IPv6 macros for the nternal logging interface. */ -#ifndef __IP6_LOGGING_H -#define __IP6_LOGGING_H - -#ifdef __KERNEL__ -#include <linux/socket.h> -#include <linux/netfilter_logging.h> - -#define nf_log_ip6_packet(pskb,hooknum,in,out,fmt,args...) \ - nf_log_packet(AF_INET6,pskb,hooknum,in,out,fmt,##args) - -#define nf_log_ip6(pfh,len,fmt,args...) \ - nf_log(AF_INET6,pfh,len,fmt,##args) - -#define nf_ip6_log_register(logging) nf_log_register(AF_INET6,logging) -#define nf_ip6_log_unregister(logging) nf_log_unregister(AF_INET6,logging) - -#endif /*__KERNEL__*/ - -#endif /*__IP6_LOGGING_H*/ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index f1ce3b00985..58c72a52dc6 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -111,7 +111,8 @@ struct ip6t_counters #define IP6T_F_PROTO 0x01 /* Set if rule cares about upper protocols */ #define IP6T_F_TOS 0x02 /* Match the TOS. */ -#define IP6T_F_MASK 0x03 /* All possible flag bits mask. */ +#define IP6T_F_GOTO 0x04 /* Set if jump is a goto */ +#define IP6T_F_MASK 0x07 /* All possible flag bits mask. */ /* Values for "inv" field in struct ip6t_ip6. */ #define IP6T_INV_VIA_IN 0x01 /* Invert the sense of IN IFACE. */ diff --git a/include/linux/netfilter_ipv6/ip6t_HL.h b/include/linux/netfilter_ipv6/ip6t_HL.h new file mode 100644 index 00000000000..afb7813d45a --- /dev/null +++ b/include/linux/netfilter_ipv6/ip6t_HL.h @@ -0,0 +1,22 @@ +/* Hop Limit modification module for ip6tables + * Maciej Soltysiak <solt@dns.toxicfilms.tv> + * Based on HW's TTL module */ + +#ifndef _IP6T_HL_H +#define _IP6T_HL_H + +enum { + IP6T_HL_SET = 0, + IP6T_HL_INC, + IP6T_HL_DEC +}; + +#define IP6T_HL_MAXMODE IP6T_HL_DEC + +struct ip6t_HL_info { + u_int8_t mode; + u_int8_t hop_limit; +}; + + +#endif diff --git a/include/linux/netfilter_ipv6/ip6t_LOG.h b/include/linux/netfilter_ipv6/ip6t_LOG.h index 42996a43bb3..9008ff5c40a 100644 --- a/include/linux/netfilter_ipv6/ip6t_LOG.h +++ b/include/linux/netfilter_ipv6/ip6t_LOG.h @@ -1,6 +1,7 @@ #ifndef _IP6T_LOG_H #define _IP6T_LOG_H +/* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */ #define IP6T_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ #define IP6T_LOG_TCPOPT 0x02 /* Log TCP options */ #define IP6T_LOG_IPOPT 0x04 /* Log IP options */ diff --git a/include/linux/netfilter_ipv6/ip6t_REJECT.h b/include/linux/netfilter_ipv6/ip6t_REJECT.h new file mode 100644 index 00000000000..6be6504162b --- /dev/null +++ b/include/linux/netfilter_ipv6/ip6t_REJECT.h @@ -0,0 +1,18 @@ +#ifndef _IP6T_REJECT_H +#define _IP6T_REJECT_H + +enum ip6t_reject_with { + IP6T_ICMP6_NO_ROUTE, + IP6T_ICMP6_ADM_PROHIBITED, + IP6T_ICMP6_NOT_NEIGHBOUR, + IP6T_ICMP6_ADDR_UNREACH, + IP6T_ICMP6_PORT_UNREACH, + IP6T_ICMP6_ECHOREPLY, + IP6T_TCP_RESET +}; + +struct ip6t_reject_info { + u_int32_t with; /* reject type */ +}; + +#endif /*_IP6T_REJECT_H*/ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 6552b71bfa7..16751866893 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -8,7 +8,7 @@ #define NETLINK_W1 1 /* 1-wire subsystem */ #define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */ #define NETLINK_FIREWALL 3 /* Firewalling hook */ -#define NETLINK_TCPDIAG 4 /* TCP socket monitoring */ +#define NETLINK_INET_DIAG 4 /* INET socket monitoring */ #define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */ #define NETLINK_XFRM 6 /* ipsec */ #define NETLINK_SELINUX 7 /* SELinux event notifications */ @@ -90,6 +90,15 @@ struct nlmsgerr struct nlmsghdr msg; }; +#define NETLINK_ADD_MEMBERSHIP 1 +#define NETLINK_DROP_MEMBERSHIP 2 +#define NETLINK_PKTINFO 3 + +struct nl_pktinfo +{ + __u32 group; +}; + #define NET_MAJOR 36 /* Major 36 is reserved for networking */ enum { @@ -106,9 +115,8 @@ struct netlink_skb_parms { struct ucred creds; /* Skb credentials */ __u32 pid; - __u32 groups; __u32 dst_pid; - __u32 dst_groups; + __u32 dst_group; kernel_cap_t eff_cap; __u32 loginuid; /* Login (audit) uid */ }; @@ -117,11 +125,11 @@ struct netlink_skb_parms #define NETLINK_CREDS(skb) (&NETLINK_CB((skb)).creds) -extern struct sock *netlink_kernel_create(int unit, void (*input)(struct sock *sk, int len)); +extern struct sock *netlink_kernel_create(int unit, unsigned int groups, void (*input)(struct sock *sk, int len), struct module *module); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid, - __u32 group, int allocation); + __u32 group, unsigned int __nocast allocation); extern void netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code); extern int netlink_register_notifier(struct notifier_block *nb); extern int netlink_unregister_notifier(struct notifier_block *nb); diff --git a/include/linux/random.h b/include/linux/random.h index cc670344991..7b2adb3322d 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -59,6 +59,8 @@ extern __u32 secure_tcp_sequence_number(__u32 saddr, __u32 daddr, __u16 sport, __u16 dport); extern __u32 secure_tcpv6_sequence_number(__u32 *saddr, __u32 *daddr, __u16 sport, __u16 dport); +extern u64 secure_dccp_sequence_number(__u32 saddr, __u32 daddr, + __u16 sport, __u16 dport); #ifndef MODULE extern struct file_operations random_fops, urandom_fops; diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 657c05ab8f9..c231e9a08f0 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -826,9 +826,8 @@ enum #define TCA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg)))) #define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg)) - -/* RTnetlink multicast groups */ - +#ifndef __KERNEL__ +/* RTnetlink multicast groups - backwards compatibility for userspace */ #define RTMGRP_LINK 1 #define RTMGRP_NOTIFY 2 #define RTMGRP_NEIGH 4 @@ -847,6 +846,43 @@ enum #define RTMGRP_DECnet_ROUTE 0x4000 #define RTMGRP_IPV6_PREFIX 0x20000 +#endif + +/* RTnetlink multicast groups */ +enum rtnetlink_groups { + RTNLGRP_NONE, +#define RTNLGRP_NONE RTNLGRP_NONE + RTNLGRP_LINK, +#define RTNLGRP_LINK RTNLGRP_LINK + RTNLGRP_NOTIFY, +#define RTNLGRP_NOTIFY RTNLGRP_NOTIFY + RTNLGRP_NEIGH, +#define RTNLGRP_NEIGH RTNLGRP_NEIGH + RTNLGRP_TC, +#define RTNLGRP_TC RTNLGRP_TC + RTNLGRP_IPV4_IFADDR, +#define RTNLGRP_IPV4_IFADDR RTNLGRP_IPV4_IFADDR + RTNLGRP_IPV4_MROUTE, +#define RTNLGRP_IPV4_MROUTE RTNLGRP_IPV4_MROUTE + RTNLGRP_IPV4_ROUTE, +#define RTNLGRP_IPV4_ROUTE RTNLGRP_IPV4_ROUTE + RTNLGRP_IPV6_IFADDR, +#define RTNLGRP_IPV6_IFADDR RTNLGRP_IPV6_IFADDR + RTNLGRP_IPV6_MROUTE, +#define RTNLGRP_IPV6_MROUTE RTNLGRP_IPV6_MROUTE + RTNLGRP_IPV6_ROUTE, +#define RTNLGRP_IPV6_ROUTE RTNLGRP_IPV6_ROUTE + RTNLGRP_IPV6_IFINFO, +#define RTNLGRP_IPV6_IFINFO RTNLGRP_IPV6_IFINFO + RTNLGRP_DECnet_IFADDR, +#define RTNLGRP_DECnet_IFADDR RTNLGRP_DECnet_IFADDR + RTNLGRP_DECnet_ROUTE, +#define RTNLGRP_DECnet_ROUTE RTNLGRP_DECnet_ROUTE + RTNLGRP_IPV6_PREFIX, +#define RTNLGRP_IPV6_PREFIX RTNLGRP_IPV6_PREFIX + __RTNLGRP_MAX +}; +#define RTNLGRP_MAX (__RTNLGRP_MAX - 1) /* TC action piece */ struct tcamsg diff --git a/include/linux/security.h b/include/linux/security.h index b42095a68b1..7aab6ab7c57 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2727,7 +2727,8 @@ static inline int security_socket_getpeersec(struct socket *sock, char __user *o return security_ops->socket_getpeersec(sock, optval, optlen, len); } -static inline int security_sk_alloc(struct sock *sk, int family, int priority) +static inline int security_sk_alloc(struct sock *sk, int family, + unsigned int __nocast priority) { return security_ops->sk_alloc_security(sk, family, priority); } @@ -2844,7 +2845,8 @@ static inline int security_socket_getpeersec(struct socket *sock, char __user *o return -ENOPROTOOPT; } -static inline int security_sk_alloc(struct sock *sk, int family, int priority) +static inline int security_sk_alloc(struct sock *sk, int family, + unsigned int __nocast priority) { return 0; } diff --git a/include/linux/selinux_netlink.h b/include/linux/selinux_netlink.h index 957e6ebca4e..bbf489decd8 100644 --- a/include/linux/selinux_netlink.h +++ b/include/linux/selinux_netlink.h @@ -20,10 +20,21 @@ enum { SELNL_MSG_MAX }; -/* Multicast groups */ +#ifndef __KERNEL__ +/* Multicast groups - backwards compatiblility for userspace */ #define SELNL_GRP_NONE 0x00000000 #define SELNL_GRP_AVC 0x00000001 /* AVC notifications */ #define SELNL_GRP_ALL 0xffffffff +#endif + +enum selinux_nlgroups { + SELNLGRP_NONE, +#define SELNLGRP_NONE SELNLGRP_NONE + SELNLGRP_AVC, +#define SELNLGRP_AVC SELNLGRP_AVC + __SELNLGRP_MAX +}; +#define SELNLGRP_MAX (__SELNLGRP_MAX - 1) /* Message structures */ struct selnl_msg_setenforce { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 948527e42a6..42edce6abe2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -155,16 +155,29 @@ struct skb_shared_info { #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) +extern struct timeval skb_tv_base; + +struct skb_timeval { + u32 off_sec; + u32 off_usec; +}; + + +enum { + SKB_FCLONE_UNAVAILABLE, + SKB_FCLONE_ORIG, + SKB_FCLONE_CLONE, +}; + /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list * @list: List we are on * @sk: Socket we are owned by - * @stamp: Time we arrived + * @tstamp: Time we arrived stored as offset to skb_tv_base * @dev: Device we arrived on/are leaving by * @input_dev: Device we arrived on - * @real_dev: The real device we are using * @h: Transport layer header * @nh: Network layer header * @mac: Link layer header @@ -190,14 +203,11 @@ struct skb_shared_info { * @end: End pointer * @destructor: Destruct function * @nfmark: Can be used for communication between hooks - * @nfcache: Cache info * @nfct: Associated connection, if any * @nfctinfo: Relationship of this skb to the connection * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c - * @private: Data which is private to the HIPPI implementation * @tc_index: Traffic control index * @tc_verd: traffic control verdict - * @tc_classid: traffic control classid */ struct sk_buff { @@ -205,12 +215,10 @@ struct sk_buff { struct sk_buff *next; struct sk_buff *prev; - struct sk_buff_head *list; struct sock *sk; - struct timeval stamp; + struct skb_timeval tstamp; struct net_device *dev; struct net_device *input_dev; - struct net_device *real_dev; union { struct tcphdr *th; @@ -252,33 +260,28 @@ struct sk_buff { __u8 local_df:1, cloned:1, ip_summed:2, - nohdr:1; - /* 3 bits spare */ - __u8 pkt_type; + nohdr:1, + nfctinfo:3; + __u8 pkt_type:3, + fclone:2; __be16 protocol; void (*destructor)(struct sk_buff *skb); #ifdef CONFIG_NETFILTER - unsigned long nfmark; - __u32 nfcache; - __u32 nfctinfo; + __u32 nfmark; struct nf_conntrack *nfct; +#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) + __u8 ipvs_property:1; +#endif #ifdef CONFIG_BRIDGE_NETFILTER struct nf_bridge_info *nf_bridge; #endif #endif /* CONFIG_NETFILTER */ -#if defined(CONFIG_HIPPI) - union { - __u32 ifield; - } private; -#endif #ifdef CONFIG_NET_SCHED - __u32 tc_index; /* traffic control index */ + __u16 tc_index; /* traffic control index */ #ifdef CONFIG_NET_CLS_ACT - __u32 tc_verd; /* traffic control verdict */ - __u32 tc_classid; /* traffic control classid */ + __u16 tc_verd; /* traffic control verdict */ #endif - #endif @@ -300,8 +303,20 @@ struct sk_buff { #include <asm/system.h> extern void __kfree_skb(struct sk_buff *skb); -extern struct sk_buff *alloc_skb(unsigned int size, - unsigned int __nocast priority); +extern struct sk_buff *__alloc_skb(unsigned int size, + unsigned int __nocast priority, int fclone); +static inline struct sk_buff *alloc_skb(unsigned int size, + unsigned int __nocast priority) +{ + return __alloc_skb(size, priority, 0); +} + +static inline struct sk_buff *alloc_skb_fclone(unsigned int size, + unsigned int __nocast priority) +{ + return __alloc_skb(size, priority, 1); +} + extern struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp, unsigned int size, unsigned int __nocast priority); @@ -597,7 +612,6 @@ static inline void __skb_queue_head(struct sk_buff_head *list, { struct sk_buff *prev, *next; - newsk->list = list; list->qlen++; prev = (struct sk_buff *)list; next = prev->next; @@ -622,7 +636,6 @@ static inline void __skb_queue_tail(struct sk_buff_head *list, { struct sk_buff *prev, *next; - newsk->list = list; list->qlen++; next = (struct sk_buff *)list; prev = next->prev; @@ -655,7 +668,6 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) next->prev = prev; prev->next = next; result->next = result->prev = NULL; - result->list = NULL; } return result; } @@ -664,7 +676,7 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) /* * Insert a packet on a list. */ -extern void skb_insert(struct sk_buff *old, struct sk_buff *newsk); +extern void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) @@ -672,24 +684,23 @@ static inline void __skb_insert(struct sk_buff *newsk, newsk->next = next; newsk->prev = prev; next->prev = prev->next = newsk; - newsk->list = list; list->qlen++; } /* * Place a packet after a given packet in a list. */ -extern void skb_append(struct sk_buff *old, struct sk_buff *newsk); -static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk) +extern void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); +static inline void __skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list) { - __skb_insert(newsk, old, old->next, old->list); + __skb_insert(newsk, old, old->next, list); } /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ -extern void skb_unlink(struct sk_buff *skb); +extern void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list); static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; @@ -698,7 +709,6 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; - skb->list = NULL; next->prev = prev; prev->next = next; } @@ -1213,6 +1223,8 @@ extern void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); extern void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); +extern void skb_release_data(struct sk_buff *skb); + static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { @@ -1230,6 +1242,42 @@ static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, extern void skb_init(void); extern void skb_add_mtu(int mtu); +/** + * skb_get_timestamp - get timestamp from a skb + * @skb: skb to get stamp from + * @stamp: pointer to struct timeval to store stamp in + * + * Timestamps are stored in the skb as offsets to a base timestamp. + * This function converts the offset back to a struct timeval and stores + * it in stamp. + */ +static inline void skb_get_timestamp(struct sk_buff *skb, struct timeval *stamp) +{ + stamp->tv_sec = skb->tstamp.off_sec; + stamp->tv_usec = skb->tstamp.off_usec; + if (skb->tstamp.off_sec) { + stamp->tv_sec += skb_tv_base.tv_sec; + stamp->tv_usec += skb_tv_base.tv_usec; + } +} + +/** + * skb_set_timestamp - set timestamp of a skb + * @skb: skb to set stamp of + * @stamp: pointer to struct timeval to get stamp from + * + * Timestamps are stored in the skb as offsets to a base timestamp. + * This function converts a struct timeval to an offset and stores + * it in the skb. + */ +static inline void skb_set_timestamp(struct sk_buff *skb, struct timeval *stamp) +{ + skb->tstamp.off_sec = stamp->tv_sec - skb_tv_base.tv_sec; + skb->tstamp.off_usec = stamp->tv_usec - skb_tv_base.tv_usec; +} + +extern void __net_timestamp(struct sk_buff *skb); + #ifdef CONFIG_NETFILTER static inline void nf_conntrack_put(struct nf_conntrack *nfct) { diff --git a/include/linux/socket.h b/include/linux/socket.h index a5c7d96e4d2..1739c2d5b95 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -26,6 +26,13 @@ struct __kernel_sockaddr_storage { #include <linux/types.h> /* pid_t */ #include <linux/compiler.h> /* __user */ +extern int sysctl_somaxconn; +extern void sock_init(void); +#ifdef CONFIG_PROC_FS +struct seq_file; +extern void socket_seq_show(struct seq_file *seq); +#endif + typedef unsigned short sa_family_t; /* @@ -271,6 +278,8 @@ struct ucred { #define SOL_IRDA 266 #define SOL_NETBEUI 267 #define SOL_LLC 268 +#define SOL_DCCP 269 +#define SOL_NETLINK 270 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e4fd82e4210..ac4ca44c75c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -55,24 +55,6 @@ struct tcphdr { __u16 urg_ptr; }; - -enum { - TCP_ESTABLISHED = 1, - TCP_SYN_SENT, - TCP_SYN_RECV, - TCP_FIN_WAIT1, - TCP_FIN_WAIT2, - TCP_TIME_WAIT, - TCP_CLOSE, - TCP_CLOSE_WAIT, - TCP_LAST_ACK, - TCP_LISTEN, - TCP_CLOSING, /* now a valid state */ - - TCP_MAX_STATES /* Leave at the end! */ -}; - -#define TCP_STATE_MASK 0xF #define TCP_ACTION_FIN (1 << 7) enum { @@ -195,8 +177,9 @@ struct tcp_info #include <linux/config.h> #include <linux/skbuff.h> -#include <linux/ip.h> #include <net/sock.h> +#include <net/inet_connection_sock.h> +#include <net/inet_timewait_sock.h> /* This defines a selective acknowledgement block. */ struct tcp_sack_block { @@ -236,8 +219,8 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) } struct tcp_sock { - /* inet_sock has to be the first member of tcp_sock */ - struct inet_sock inet; + /* inet_connection_sock has to be the first member of tcp_sock */ + struct inet_connection_sock inet_conn; int tcp_header_len; /* Bytes of tcp header to send */ /* @@ -258,19 +241,6 @@ struct tcp_sock { __u32 snd_sml; /* Last byte of the most recently transmitted small packet */ __u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ __u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ - struct tcp_bind_bucket *bind_hash; - /* Delayed ACK control data */ - struct { - __u8 pending; /* ACK is pending */ - __u8 quick; /* Scheduled number of quick acks */ - __u8 pingpong; /* The session is interactive */ - __u8 blocked; /* Delayed ACK was blocked by socket lock*/ - __u32 ato; /* Predicted tick of soft clock */ - unsigned long timeout; /* Currently scheduled timeout */ - __u32 lrcvtime; /* timestamp of last received data packet*/ - __u16 last_seg_size; /* Size of last incoming segment */ - __u16 rcv_mss; /* MSS used for delayed ACK decisions */ - } ack; /* Data for direct copy to user */ struct { @@ -288,19 +258,15 @@ struct tcp_sock { __u32 mss_cache; /* Cached effective mss, not including SACKS */ __u16 xmit_size_goal; /* Goal for segmenting output packets */ __u16 ext_header_len; /* Network protocol overhead (IP/IPv6 options) */ - __u8 ca_state; /* State of fast-retransmit machine */ - __u8 retransmits; /* Number of unrecovered RTO timeouts. */ - __u16 advmss; /* Advertised MSS */ __u32 window_clamp; /* Maximal window to advertise */ __u32 rcv_ssthresh; /* Current window clamp */ __u32 frto_highmark; /* snd_nxt when RTO occurred */ __u8 reordering; /* Packet reordering metric. */ __u8 frto_counter; /* Number of new acks after RTO */ - - __u8 unused; - __u8 defer_accept; /* User waits for some data after accept() */ + __u8 nonagle; /* Disable Nagle algorithm? */ + __u8 keepalive_probes; /* num of allowed keep alive probes */ /* RTT measurement */ __u32 srtt; /* smoothed round trip time << 3 */ @@ -308,19 +274,13 @@ struct tcp_sock { __u32 mdev_max; /* maximal mdev for the last rtt period */ __u32 rttvar; /* smoothed mdev_max */ __u32 rtt_seq; /* sequence number to update rttvar */ - __u32 rto; /* retransmit timeout */ __u32 packets_out; /* Packets which are "in flight" */ __u32 left_out; /* Packets which leaved network */ __u32 retrans_out; /* Retransmitted packets out */ - __u8 backoff; /* backoff */ /* * Options received (usually on last packet, some only on SYN packets). */ - __u8 nonagle; /* Disable Nagle algorithm? */ - __u8 keepalive_probes; /* num of allowed keep alive probes */ - - __u8 probes_out; /* unanswered 0 window probes */ struct tcp_options_received rx_opt; /* @@ -333,11 +293,6 @@ struct tcp_sock { __u32 snd_cwnd_used; __u32 snd_cwnd_stamp; - /* Two commonly used timers in both sender and receiver paths. */ - unsigned long timeout; - struct timer_list retransmit_timer; /* Resend (no ack) */ - struct timer_list delack_timer; /* Ack delay */ - struct sk_buff_head out_of_order_queue; /* Out of order segments go here */ struct tcp_func *af_specific; /* Operations which are AF_INET{4,6} specific */ @@ -352,8 +307,7 @@ struct tcp_sock { struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */ struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/ - __u8 syn_retries; /* num of allowed syn retries */ - __u8 ecn_flags; /* ECN status bits. */ + __u16 advmss; /* Advertised MSS */ __u16 prior_ssthresh; /* ssthresh saved at recovery start */ __u32 lost_out; /* Lost packets */ __u32 sacked_out; /* SACK'd packets */ @@ -367,14 +321,12 @@ struct tcp_sock { int undo_retrans; /* number of undoable retransmissions. */ __u32 urg_seq; /* Seq of received urgent pointer */ __u16 urg_data; /* Saved octet of OOB data and control flags */ - __u8 pending; /* Scheduled timer event */ __u8 urg_mode; /* In urgent mode */ + __u8 ecn_flags; /* ECN status bits. */ __u32 snd_up; /* Urgent pointer */ __u32 total_retrans; /* Total retransmits for entire connection */ - struct request_sock_queue accept_queue; /* FIFO of established children */ - unsigned int keepalive_time; /* time before keep alive takes place */ unsigned int keepalive_intvl; /* time interval between keep alive probes */ int linger2; @@ -394,11 +346,6 @@ struct tcp_sock { __u32 seq; __u32 time; } rcvq_space; - - /* Pluggable TCP congestion control hook */ - struct tcp_congestion_ops *ca_ops; - u32 ca_priv[16]; -#define TCP_CA_PRIV_SIZE (16*sizeof(u32)) }; static inline struct tcp_sock *tcp_sk(const struct sock *sk) @@ -406,9 +353,18 @@ static inline struct tcp_sock *tcp_sk(const struct sock *sk) return (struct tcp_sock *)sk; } -static inline void *tcp_ca(const struct tcp_sock *tp) +struct tcp_timewait_sock { + struct inet_timewait_sock tw_sk; + __u32 tw_rcv_nxt; + __u32 tw_snd_nxt; + __u32 tw_rcv_wnd; + __u32 tw_ts_recent; + long tw_ts_recent_stamp; +}; + +static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) { - return (void *) tp->ca_priv; + return (struct tcp_timewait_sock *)sk; } #endif diff --git a/include/linux/tcp_diag.h b/include/linux/tcp_diag.h deleted file mode 100644 index 7a599674394..00000000000 --- a/include/linux/tcp_diag.h +++ /dev/null @@ -1,127 +0,0 @@ -#ifndef _TCP_DIAG_H_ -#define _TCP_DIAG_H_ 1 - -/* Just some random number */ -#define TCPDIAG_GETSOCK 18 - -/* Socket identity */ -struct tcpdiag_sockid -{ - __u16 tcpdiag_sport; - __u16 tcpdiag_dport; - __u32 tcpdiag_src[4]; - __u32 tcpdiag_dst[4]; - __u32 tcpdiag_if; - __u32 tcpdiag_cookie[2]; -#define TCPDIAG_NOCOOKIE (~0U) -}; - -/* Request structure */ - -struct tcpdiagreq -{ - __u8 tcpdiag_family; /* Family of addresses. */ - __u8 tcpdiag_src_len; - __u8 tcpdiag_dst_len; - __u8 tcpdiag_ext; /* Query extended information */ - - struct tcpdiag_sockid id; - - __u32 tcpdiag_states; /* States to dump */ - __u32 tcpdiag_dbs; /* Tables to dump (NI) */ -}; - -enum -{ - TCPDIAG_REQ_NONE, - TCPDIAG_REQ_BYTECODE, -}; - -#define TCPDIAG_REQ_MAX TCPDIAG_REQ_BYTECODE - -/* Bytecode is sequence of 4 byte commands followed by variable arguments. - * All the commands identified by "code" are conditional jumps forward: - * to offset cc+"yes" or to offset cc+"no". "yes" is supposed to be - * length of the command and its arguments. - */ - -struct tcpdiag_bc_op -{ - unsigned char code; - unsigned char yes; - unsigned short no; -}; - -enum -{ - TCPDIAG_BC_NOP, - TCPDIAG_BC_JMP, - TCPDIAG_BC_S_GE, - TCPDIAG_BC_S_LE, - TCPDIAG_BC_D_GE, - TCPDIAG_BC_D_LE, - TCPDIAG_BC_AUTO, - TCPDIAG_BC_S_COND, - TCPDIAG_BC_D_COND, -}; - -struct tcpdiag_hostcond -{ - __u8 family; - __u8 prefix_len; - int port; - __u32 addr[0]; -}; - -/* Base info structure. It contains socket identity (addrs/ports/cookie) - * and, alas, the information shown by netstat. */ -struct tcpdiagmsg -{ - __u8 tcpdiag_family; - __u8 tcpdiag_state; - __u8 tcpdiag_timer; - __u8 tcpdiag_retrans; - - struct tcpdiag_sockid id; - - __u32 tcpdiag_expires; - __u32 tcpdiag_rqueue; - __u32 tcpdiag_wqueue; - __u32 tcpdiag_uid; - __u32 tcpdiag_inode; -}; - -/* Extensions */ - -enum -{ - TCPDIAG_NONE, - TCPDIAG_MEMINFO, - TCPDIAG_INFO, - TCPDIAG_VEGASINFO, - TCPDIAG_CONG, -}; - -#define TCPDIAG_MAX TCPDIAG_CONG - - -/* TCPDIAG_MEM */ - -struct tcpdiag_meminfo -{ - __u32 tcpdiag_rmem; - __u32 tcpdiag_wmem; - __u32 tcpdiag_fmem; - __u32 tcpdiag_tmem; -}; - -/* TCPDIAG_VEGASINFO */ - -struct tcpvegas_info { - __u32 tcpv_enabled; - __u32 tcpv_rttcnt; - __u32 tcpv_rtt; - __u32 tcpv_minrtt; -}; - -#endif /* _TCP_DIAG_H_ */ diff --git a/include/linux/types.h b/include/linux/types.h index dcb13f865df..2b678c22ca4 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -123,6 +123,9 @@ typedef __u64 u_int64_t; typedef __s64 int64_t; #endif +/* this is a special 64bit data type that is 8-byte aligned */ +#define aligned_u64 unsigned long long __attribute__((aligned(8))) + /* * The type used for indexing onto a disc or disc partition. * If required, asm/types.h can override it and define diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index f0d423300d8..0fb077d6844 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -258,9 +258,27 @@ struct xfrm_usersa_flush { __u8 proto; }; +#ifndef __KERNEL__ +/* backwards compatibility for userspace */ #define XFRMGRP_ACQUIRE 1 #define XFRMGRP_EXPIRE 2 #define XFRMGRP_SA 4 #define XFRMGRP_POLICY 8 +#endif + +enum xfrm_nlgroups { + XFRMNLGRP_NONE, +#define XFRMNLGRP_NONE XFRMNLGRP_NONE + XFRMNLGRP_ACQUIRE, +#define XFRMNLGRP_ACQUIRE XFRMNLGRP_ACQUIRE + XFRMNLGRP_EXPIRE, +#define XFRMNLGRP_EXPIRE XFRMNLGRP_EXPIRE + XFRMNLGRP_SA, +#define XFRMNLGRP_SA XFRMNLGRP_SA + XFRMNLGRP_POLICY, +#define XFRMNLGRP_POLICY XFRMNLGRP_POLICY + __XFRMNLGRP_MAX +}; +#define XFRMNLGRP_MAX (__XFRMNLGRP_MAX - 1) #endif /* _LINUX_XFRM_H */ diff --git a/include/net/act_api.h b/include/net/act_api.h index ed00a995f57..b55eb7c7f03 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -63,7 +63,7 @@ struct tc_action_ops __u32 type; /* TBD to match kind */ __u32 capab; /* capabilities includes 4 bit version */ struct module *owner; - int (*act)(struct sk_buff **, struct tc_action *); + int (*act)(struct sk_buff **, struct tc_action *, struct tcf_result *); int (*get_stats)(struct sk_buff *, struct tc_action *); int (*dump)(struct sk_buff *, struct tc_action *,int , int); int (*cleanup)(struct tc_action *, int bind); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index a0ed9367217..750e2508dd9 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -45,6 +45,7 @@ struct prefix_info { #ifdef __KERNEL__ +#include <linux/config.h> #include <linux/netdevice.h> #include <net/if_inet6.h> #include <net/ipv6.h> @@ -238,5 +239,10 @@ static inline int ipv6_addr_is_ll_all_routers(const struct in6_addr *addr) addr->s6_addr32[3] == htonl(0x00000002)); } +#ifdef CONFIG_PROC_FS +extern int if6_proc_init(void); +extern void if6_proc_exit(void); +#endif + #endif #endif diff --git a/include/net/af_unix.h b/include/net/af_unix.h index b60b3846b9d..b5d785ab4a0 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -1,5 +1,11 @@ #ifndef __LINUX_NET_AFUNIX_H #define __LINUX_NET_AFUNIX_H + +#include <linux/config.h> +#include <linux/socket.h> +#include <linux/un.h> +#include <net/sock.h> + extern void unix_inflight(struct file *fp); extern void unix_notinflight(struct file *fp); extern void unix_gc(void); @@ -74,5 +80,14 @@ struct unix_sock { wait_queue_head_t peer_wait; }; #define unix_sk(__sk) ((struct unix_sock *)__sk) + +#ifdef CONFIG_SYSCTL +extern int sysctl_unix_max_dgram_qlen; +extern void unix_sysctl_register(void); +extern void unix_sysctl_unregister(void); +#else +static inline void unix_sysctl_register(void) {} +static inline void unix_sysctl_unregister(void) {} +#endif #endif #endif diff --git a/include/net/arp.h b/include/net/arp.h index a1f09fad6a5..a13e30c35f4 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -11,7 +11,7 @@ extern struct neigh_table arp_tbl; extern void arp_init(void); extern int arp_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt); + struct packet_type *pt, struct net_device *orig_dev); extern int arp_find(unsigned char *haddr, struct sk_buff *skb); extern int arp_ioctl(unsigned int cmd, void __user *arg); extern void arp_send(int type, int ptype, u32 dest_ip, diff --git a/include/net/ax25.h b/include/net/ax25.h index 3696f988a9f..926eed54302 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -316,7 +316,7 @@ extern int ax25_protocol_is_registered(unsigned int); /* ax25_in.c */ extern int ax25_rx_iframe(ax25_cb *, struct sk_buff *); -extern int ax25_kiss_rcv(struct sk_buff *, struct net_device *, struct packet_type *); +extern int ax25_kiss_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); /* ax25_ip.c */ extern int ax25_encapsulate(struct sk_buff *, struct net_device *, unsigned short, void *, void *, unsigned int); diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 06b24f63702..6dfa4a61ffd 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -131,11 +131,12 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock); /* Skb helpers */ struct bt_skb_cb { - int incoming; + __u8 pkt_type; + __u8 incoming; }; #define bt_cb(skb) ((struct bt_skb_cb *)(skb->cb)) -static inline struct sk_buff *bt_skb_alloc(unsigned int len, int how) +static inline struct sk_buff *bt_skb_alloc(unsigned int len, unsigned int __nocast how) { struct sk_buff *skb; diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 6f0706f4af6..371e7d3f2e6 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -453,6 +453,15 @@ struct inquiry_info_with_rssi { __u16 clock_offset; __s8 rssi; } __attribute__ ((packed)); +struct inquiry_info_with_rssi_and_pscan_mode { + bdaddr_t bdaddr; + __u8 pscan_rep_mode; + __u8 pscan_period_mode; + __u8 pscan_mode; + __u8 dev_class[3]; + __u16 clock_offset; + __s8 rssi; +} __attribute__ ((packed)); #define HCI_EV_CONN_COMPLETE 0x03 struct hci_ev_conn_complete { @@ -584,6 +593,12 @@ struct hci_ev_clock_offset { __u16 clock_offset; } __attribute__ ((packed)); +#define HCI_EV_PSCAN_REP_MODE 0x20 +struct hci_ev_pscan_rep_mode { + bdaddr_t bdaddr; + __u8 pscan_rep_mode; +} __attribute__ ((packed)); + /* Internal events generated by Bluetooth stack */ #define HCI_EV_STACK_INTERNAL 0xFD struct hci_ev_stack_internal { diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 6d63a47c731..7f933f30207 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -404,7 +404,7 @@ static inline int hci_recv_frame(struct sk_buff *skb) bt_cb(skb)->incoming = 1; /* Time stamp */ - do_gettimeofday(&skb->stamp); + __net_timestamp(skb); /* Queue frame for rx task */ skb_queue_tail(&hdev->rx_q, skb); diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h index 13669bad00b..ffea9d54071 100644 --- a/include/net/bluetooth/rfcomm.h +++ b/include/net/bluetooth/rfcomm.h @@ -80,9 +80,9 @@ #define RFCOMM_RPN_STOP_15 1 #define RFCOMM_RPN_PARITY_NONE 0x0 -#define RFCOMM_RPN_PARITY_ODD 0x4 -#define RFCOMM_RPN_PARITY_EVEN 0x5 -#define RFCOMM_RPN_PARITY_MARK 0x6 +#define RFCOMM_RPN_PARITY_ODD 0x1 +#define RFCOMM_RPN_PARITY_EVEN 0x3 +#define RFCOMM_RPN_PARITY_MARK 0x5 #define RFCOMM_RPN_PARITY_SPACE 0x7 #define RFCOMM_RPN_FLOW_NONE 0x00 @@ -223,8 +223,14 @@ struct rfcomm_dlc { #define RFCOMM_CFC_DISABLED 0 #define RFCOMM_CFC_ENABLED RFCOMM_MAX_CREDITS +/* ---- RFCOMM SEND RPN ---- */ +int rfcomm_send_rpn(struct rfcomm_session *s, int cr, u8 dlci, + u8 bit_rate, u8 data_bits, u8 stop_bits, + u8 parity, u8 flow_ctrl_settings, + u8 xon_char, u8 xoff_char, u16 param_mask); + /* ---- RFCOMM DLCs (channels) ---- */ -struct rfcomm_dlc *rfcomm_dlc_alloc(int prio); +struct rfcomm_dlc *rfcomm_dlc_alloc(unsigned int __nocast prio); void rfcomm_dlc_free(struct rfcomm_dlc *d); int rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 channel); int rfcomm_dlc_close(struct rfcomm_dlc *d, int reason); diff --git a/include/net/datalink.h b/include/net/datalink.h index 5797ba3d2eb..deb7ca75db4 100644 --- a/include/net/datalink.h +++ b/include/net/datalink.h @@ -9,7 +9,7 @@ struct datalink_proto { unsigned short header_length; int (*rcvfunc)(struct sk_buff *, struct net_device *, - struct packet_type *); + struct packet_type *, struct net_device *); int (*request)(struct datalink_proto *, struct sk_buff *, unsigned char *); struct list_head node; diff --git a/include/net/dn.h b/include/net/dn.h index 5551c46db39..c1dbbd22279 100644 --- a/include/net/dn.h +++ b/include/net/dn.h @@ -3,6 +3,7 @@ #include <linux/dn.h> #include <net/sock.h> +#include <net/tcp.h> #include <asm/byteorder.h> typedef unsigned short dn_address; diff --git a/include/net/icmp.h b/include/net/icmp.h index e5ef0d15fb4..6cdebeee5f9 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -57,4 +57,11 @@ static inline struct raw_sock *raw_sk(const struct sock *sk) return (struct raw_sock *)sk; } +extern int sysctl_icmp_echo_ignore_all; +extern int sysctl_icmp_echo_ignore_broadcasts; +extern int sysctl_icmp_ignore_bogus_error_responses; +extern int sysctl_icmp_errors_use_inbound_ifaddr; +extern int sysctl_icmp_ratelimit; +extern int sysctl_icmp_ratemask; + #endif /* _ICMP_H */ diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h new file mode 100644 index 00000000000..03df3b15796 --- /dev/null +++ b/include/net/inet6_hashtables.h @@ -0,0 +1,130 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Authors: Lotsa people, from code originally in tcp + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _INET6_HASHTABLES_H +#define _INET6_HASHTABLES_H + +#include <linux/config.h> + +#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#include <linux/in6.h> +#include <linux/ipv6.h> +#include <linux/types.h> + +#include <net/ipv6.h> + +struct inet_hashinfo; + +/* I have no idea if this is a good hash for v6 or not. -DaveM */ +static inline int inet6_ehashfn(const struct in6_addr *laddr, const u16 lport, + const struct in6_addr *faddr, const u16 fport, + const int ehash_size) +{ + int hashent = (lport ^ fport); + + hashent ^= (laddr->s6_addr32[3] ^ faddr->s6_addr32[3]); + hashent ^= hashent >> 16; + hashent ^= hashent >> 8; + return (hashent & (ehash_size - 1)); +} + +static inline int inet6_sk_ehashfn(const struct sock *sk, const int ehash_size) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); + const struct in6_addr *laddr = &np->rcv_saddr; + const struct in6_addr *faddr = &np->daddr; + const __u16 lport = inet->num; + const __u16 fport = inet->dport; + return inet6_ehashfn(laddr, lport, faddr, fport, ehash_size); +} + +/* + * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so + * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM + * + * The sockhash lock must be held as a reader here. + */ +static inline struct sock * + __inet6_lookup_established(struct inet_hashinfo *hashinfo, + const struct in6_addr *saddr, + const u16 sport, + const struct in6_addr *daddr, + const u16 hnum, + const int dif) +{ + struct sock *sk; + const struct hlist_node *node; + const __u32 ports = INET_COMBINED_PORTS(sport, hnum); + /* Optimize here for direct hit, only listening connections can + * have wildcards anyways. + */ + const int hash = inet6_ehashfn(daddr, hnum, saddr, sport, + hashinfo->ehash_size); + struct inet_ehash_bucket *head = &hashinfo->ehash[hash]; + + read_lock(&head->lock); + sk_for_each(sk, node, &head->chain) { + /* For IPV6 do the cheaper port and family tests first. */ + if (INET6_MATCH(sk, saddr, daddr, ports, dif)) + goto hit; /* You sunk my battleship! */ + } + /* Must check for a TIME_WAIT'er before going to listener hash. */ + sk_for_each(sk, node, &(head + hashinfo->ehash_size)->chain) { + const struct inet_timewait_sock *tw = inet_twsk(sk); + + if(*((__u32 *)&(tw->tw_dport)) == ports && + sk->sk_family == PF_INET6) { + const struct tcp6_timewait_sock *tcp6tw = tcp6_twsk(sk); + + if (ipv6_addr_equal(&tcp6tw->tw_v6_daddr, saddr) && + ipv6_addr_equal(&tcp6tw->tw_v6_rcv_saddr, daddr) && + (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif)) + goto hit; + } + } + read_unlock(&head->lock); + return NULL; + +hit: + sock_hold(sk); + read_unlock(&head->lock); + return sk; +} + +extern struct sock *inet6_lookup_listener(struct inet_hashinfo *hashinfo, + const struct in6_addr *daddr, + const unsigned short hnum, + const int dif); + +static inline struct sock *__inet6_lookup(struct inet_hashinfo *hashinfo, + const struct in6_addr *saddr, + const u16 sport, + const struct in6_addr *daddr, + const u16 hnum, + const int dif) +{ + struct sock *sk = __inet6_lookup_established(hashinfo, saddr, sport, + daddr, hnum, dif); + if (sk) + return sk; + + return inet6_lookup_listener(hashinfo, daddr, hnum, dif); +} + +extern struct sock *inet6_lookup(struct inet_hashinfo *hashinfo, + const struct in6_addr *saddr, const u16 sport, + const struct in6_addr *daddr, const u16 dport, + const int dif); +#endif /* defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) */ +#endif /* _INET6_HASHTABLES_H */ diff --git a/include/net/inet_common.h b/include/net/inet_common.h index fbc1f4d140d..f943306ce5f 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -8,6 +8,11 @@ extern struct proto_ops inet_dgram_ops; * INET4 prototypes used by INET6 */ +struct msghdr; +struct sock; +struct sockaddr; +struct socket; + extern void inet_remove_sock(struct sock *sk1); extern void inet_put_sock(unsigned short num, struct sock *sk); @@ -29,7 +34,6 @@ extern unsigned int inet_poll(struct file * file, struct socket *sock, struct p extern int inet_listen(struct socket *sock, int backlog); extern void inet_sock_destruct(struct sock *sk); -extern atomic_t inet_sock_nr; extern int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h new file mode 100644 index 00000000000..8a87a3a4f10 --- /dev/null +++ b/include/net/inet_connection_sock.h @@ -0,0 +1,276 @@ +/* + * NET Generic infrastructure for INET connection oriented protocols. + * + * Definitions for inet_connection_sock + * + * Authors: Many people, see the TCP sources + * + * From code originally in TCP + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _INET_CONNECTION_SOCK_H +#define _INET_CONNECTION_SOCK_H + +#include <linux/ip.h> +#include <linux/string.h> +#include <linux/timer.h> +#include <net/request_sock.h> + +#define INET_CSK_DEBUG 1 + +/* Cancel timers, when they are not required. */ +#undef INET_CSK_CLEAR_TIMERS + +struct inet_bind_bucket; +struct inet_hashinfo; +struct tcp_congestion_ops; + +/** inet_connection_sock - INET connection oriented sock + * + * @icsk_accept_queue: FIFO of established children + * @icsk_bind_hash: Bind node + * @icsk_timeout: Timeout + * @icsk_retransmit_timer: Resend (no ack) + * @icsk_rto: Retransmit timeout + * @icsk_ca_ops Pluggable congestion control hook + * @icsk_ca_state: Congestion control state + * @icsk_retransmits: Number of unrecovered [RTO] timeouts + * @icsk_pending: Scheduled timer event + * @icsk_backoff: Backoff + * @icsk_syn_retries: Number of allowed SYN (or equivalent) retries + * @icsk_probes_out: unanswered 0 window probes + * @icsk_ack: Delayed ACK control data + */ +struct inet_connection_sock { + /* inet_sock has to be the first member! */ + struct inet_sock icsk_inet; + struct request_sock_queue icsk_accept_queue; + struct inet_bind_bucket *icsk_bind_hash; + unsigned long icsk_timeout; + struct timer_list icsk_retransmit_timer; + struct timer_list icsk_delack_timer; + __u32 icsk_rto; + struct tcp_congestion_ops *icsk_ca_ops; + __u8 icsk_ca_state; + __u8 icsk_retransmits; + __u8 icsk_pending; + __u8 icsk_backoff; + __u8 icsk_syn_retries; + __u8 icsk_probes_out; + /* 2 BYTES HOLE, TRY TO PACK! */ + struct { + __u8 pending; /* ACK is pending */ + __u8 quick; /* Scheduled number of quick acks */ + __u8 pingpong; /* The session is interactive */ + __u8 blocked; /* Delayed ACK was blocked by socket lock */ + __u32 ato; /* Predicted tick of soft clock */ + unsigned long timeout; /* Currently scheduled timeout */ + __u32 lrcvtime; /* timestamp of last received data packet */ + __u16 last_seg_size; /* Size of last incoming segment */ + __u16 rcv_mss; /* MSS used for delayed ACK decisions */ + } icsk_ack; + u32 icsk_ca_priv[16]; +#define ICSK_CA_PRIV_SIZE (16 * sizeof(u32)) +}; + +#define ICSK_TIME_RETRANS 1 /* Retransmit timer */ +#define ICSK_TIME_DACK 2 /* Delayed ack timer */ +#define ICSK_TIME_PROBE0 3 /* Zero window probe timer */ +#define ICSK_TIME_KEEPOPEN 4 /* Keepalive timer */ + +static inline struct inet_connection_sock *inet_csk(const struct sock *sk) +{ + return (struct inet_connection_sock *)sk; +} + +static inline void *inet_csk_ca(const struct sock *sk) +{ + return (void *)inet_csk(sk)->icsk_ca_priv; +} + +extern struct sock *inet_csk_clone(struct sock *sk, + const struct request_sock *req, + const unsigned int __nocast priority); + +enum inet_csk_ack_state_t { + ICSK_ACK_SCHED = 1, + ICSK_ACK_TIMER = 2, + ICSK_ACK_PUSHED = 4 +}; + +extern void inet_csk_init_xmit_timers(struct sock *sk, + void (*retransmit_handler)(unsigned long), + void (*delack_handler)(unsigned long), + void (*keepalive_handler)(unsigned long)); +extern void inet_csk_clear_xmit_timers(struct sock *sk); + +static inline void inet_csk_schedule_ack(struct sock *sk) +{ + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED; +} + +static inline int inet_csk_ack_scheduled(const struct sock *sk) +{ + return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED; +} + +static inline void inet_csk_delack_init(struct sock *sk) +{ + memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack)); +} + +extern void inet_csk_delete_keepalive_timer(struct sock *sk); +extern void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout); + +#ifdef INET_CSK_DEBUG +extern const char inet_csk_timer_bug_msg[]; +#endif + +static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) { + icsk->icsk_pending = 0; +#ifdef INET_CSK_CLEAR_TIMERS + sk_stop_timer(sk, &icsk->icsk_retransmit_timer); +#endif + } else if (what == ICSK_TIME_DACK) { + icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0; +#ifdef INET_CSK_CLEAR_TIMERS + sk_stop_timer(sk, &icsk->icsk_delack_timer); +#endif + } +#ifdef INET_CSK_DEBUG + else { + pr_debug(inet_csk_timer_bug_msg); + } +#endif +} + +/* + * Reset the retransmission timer + */ +static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, + unsigned long when, + const unsigned long max_when) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (when > max_when) { +#ifdef INET_CSK_DEBUG + pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n", + sk, what, when, current_text_addr()); +#endif + when = max_when; + } + + if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) { + icsk->icsk_pending = what; + icsk->icsk_timeout = jiffies + when; + sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); + } else if (what == ICSK_TIME_DACK) { + icsk->icsk_ack.pending |= ICSK_ACK_TIMER; + icsk->icsk_ack.timeout = jiffies + when; + sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); + } +#ifdef INET_CSK_DEBUG + else { + pr_debug(inet_csk_timer_bug_msg); + } +#endif +} + +extern struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); + +extern struct request_sock *inet_csk_search_req(const struct sock *sk, + struct request_sock ***prevp, + const __u16 rport, + const __u32 raddr, + const __u32 laddr); +extern int inet_csk_get_port(struct inet_hashinfo *hashinfo, + struct sock *sk, unsigned short snum); + +extern struct dst_entry* inet_csk_route_req(struct sock *sk, + const struct request_sock *req); + +static inline void inet_csk_reqsk_queue_add(struct sock *sk, + struct request_sock *req, + struct sock *child) +{ + reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child); +} + +extern void inet_csk_reqsk_queue_hash_add(struct sock *sk, + struct request_sock *req, + const unsigned timeout); + +static inline void inet_csk_reqsk_queue_removed(struct sock *sk, + struct request_sock *req) +{ + if (reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req) == 0) + inet_csk_delete_keepalive_timer(sk); +} + +static inline void inet_csk_reqsk_queue_added(struct sock *sk, + const unsigned long timeout) +{ + if (reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue) == 0) + inet_csk_reset_keepalive_timer(sk, timeout); +} + +static inline int inet_csk_reqsk_queue_len(const struct sock *sk) +{ + return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue); +} + +static inline int inet_csk_reqsk_queue_young(const struct sock *sk) +{ + return reqsk_queue_len_young(&inet_csk(sk)->icsk_accept_queue); +} + +static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) +{ + return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue); +} + +static inline void inet_csk_reqsk_queue_unlink(struct sock *sk, + struct request_sock *req, + struct request_sock **prev) +{ + reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev); +} + +static inline void inet_csk_reqsk_queue_drop(struct sock *sk, + struct request_sock *req, + struct request_sock **prev) +{ + inet_csk_reqsk_queue_unlink(sk, req, prev); + inet_csk_reqsk_queue_removed(sk, req); + reqsk_free(req); +} + +extern void inet_csk_reqsk_queue_prune(struct sock *parent, + const unsigned long interval, + const unsigned long timeout, + const unsigned long max_rto); + +extern void inet_csk_destroy_sock(struct sock *sk); + +/* + * LISTEN is a special case for poll.. + */ +static inline unsigned int inet_csk_listen_poll(const struct sock *sk) +{ + return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ? + (POLLIN | POLLRDNORM) : 0; +} + +extern int inet_csk_listen_start(struct sock *sk, const int nr_table_entries); +extern void inet_csk_listen_stop(struct sock *sk); + +#endif /* _INET_CONNECTION_SOCK_H */ diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h new file mode 100644 index 00000000000..646b6ea7fe2 --- /dev/null +++ b/include/net/inet_hashtables.h @@ -0,0 +1,427 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Authors: Lotsa people, from code originally in tcp + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _INET_HASHTABLES_H +#define _INET_HASHTABLES_H + +#include <linux/config.h> + +#include <linux/interrupt.h> +#include <linux/ipv6.h> +#include <linux/list.h> +#include <linux/slab.h> +#include <linux/socket.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/wait.h> + +#include <net/inet_connection_sock.h> +#include <net/route.h> +#include <net/sock.h> +#include <net/tcp_states.h> + +#include <asm/atomic.h> +#include <asm/byteorder.h> + +/* This is for all connections with a full identity, no wildcards. + * New scheme, half the table is for TIME_WAIT, the other half is + * for the rest. I'll experiment with dynamic table growth later. + */ +struct inet_ehash_bucket { + rwlock_t lock; + struct hlist_head chain; +} __attribute__((__aligned__(8))); + +/* There are a few simple rules, which allow for local port reuse by + * an application. In essence: + * + * 1) Sockets bound to different interfaces may share a local port. + * Failing that, goto test 2. + * 2) If all sockets have sk->sk_reuse set, and none of them are in + * TCP_LISTEN state, the port may be shared. + * Failing that, goto test 3. + * 3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local + * address, and none of them are the same, the port may be + * shared. + * Failing this, the port cannot be shared. + * + * The interesting point, is test #2. This is what an FTP server does + * all day. To optimize this case we use a specific flag bit defined + * below. As we add sockets to a bind bucket list, we perform a + * check of: (newsk->sk_reuse && (newsk->sk_state != TCP_LISTEN)) + * As long as all sockets added to a bind bucket pass this test, + * the flag bit will be set. + * The resulting situation is that tcp_v[46]_verify_bind() can just check + * for this flag bit, if it is set and the socket trying to bind has + * sk->sk_reuse set, we don't even have to walk the owners list at all, + * we return that it is ok to bind this socket to the requested local port. + * + * Sounds like a lot of work, but it is worth it. In a more naive + * implementation (ie. current FreeBSD etc.) the entire list of ports + * must be walked for each data port opened by an ftp server. Needless + * to say, this does not scale at all. With a couple thousand FTP + * users logged onto your box, isn't it nice to know that new data + * ports are created in O(1) time? I thought so. ;-) -DaveM + */ +struct inet_bind_bucket { + unsigned short port; + signed short fastreuse; + struct hlist_node node; + struct hlist_head owners; +}; + +#define inet_bind_bucket_for_each(tb, node, head) \ + hlist_for_each_entry(tb, node, head, node) + +struct inet_bind_hashbucket { + spinlock_t lock; + struct hlist_head chain; +}; + +/* This is for listening sockets, thus all sockets which possess wildcards. */ +#define INET_LHTABLE_SIZE 32 /* Yes, really, this is all you need. */ + +struct inet_hashinfo { + /* This is for sockets with full identity only. Sockets here will + * always be without wildcards and will have the following invariant: + * + * TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE + * + * First half of the table is for sockets not in TIME_WAIT, second half + * is for TIME_WAIT sockets only. + */ + struct inet_ehash_bucket *ehash; + + /* Ok, let's try this, I give up, we do need a local binding + * TCP hash as well as the others for fast bind/connect. + */ + struct inet_bind_hashbucket *bhash; + + int bhash_size; + int ehash_size; + + /* All sockets in TCP_LISTEN state will be in here. This is the only + * table where wildcard'd TCP sockets can exist. Hash function here + * is just local port number. + */ + struct hlist_head listening_hash[INET_LHTABLE_SIZE]; + + /* All the above members are written once at bootup and + * never written again _or_ are predominantly read-access. + * + * Now align to a new cache line as all the following members + * are often dirty. + */ + rwlock_t lhash_lock ____cacheline_aligned; + atomic_t lhash_users; + wait_queue_head_t lhash_wait; + spinlock_t portalloc_lock; + kmem_cache_t *bind_bucket_cachep; + int port_rover; +}; + +static inline int inet_ehashfn(const __u32 laddr, const __u16 lport, + const __u32 faddr, const __u16 fport, + const int ehash_size) +{ + int h = (laddr ^ lport) ^ (faddr ^ fport); + h ^= h >> 16; + h ^= h >> 8; + return h & (ehash_size - 1); +} + +static inline int inet_sk_ehashfn(const struct sock *sk, const int ehash_size) +{ + const struct inet_sock *inet = inet_sk(sk); + const __u32 laddr = inet->rcv_saddr; + const __u16 lport = inet->num; + const __u32 faddr = inet->daddr; + const __u16 fport = inet->dport; + + return inet_ehashfn(laddr, lport, faddr, fport, ehash_size); +} + +extern struct inet_bind_bucket * + inet_bind_bucket_create(kmem_cache_t *cachep, + struct inet_bind_hashbucket *head, + const unsigned short snum); +extern void inet_bind_bucket_destroy(kmem_cache_t *cachep, + struct inet_bind_bucket *tb); + +static inline int inet_bhashfn(const __u16 lport, const int bhash_size) +{ + return lport & (bhash_size - 1); +} + +extern void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, + const unsigned short snum); + +/* These can have wildcards, don't try too hard. */ +static inline int inet_lhashfn(const unsigned short num) +{ + return num & (INET_LHTABLE_SIZE - 1); +} + +static inline int inet_sk_listen_hashfn(const struct sock *sk) +{ + return inet_lhashfn(inet_sk(sk)->num); +} + +/* Caller must disable local BH processing. */ +static inline void __inet_inherit_port(struct inet_hashinfo *table, + struct sock *sk, struct sock *child) +{ + const int bhash = inet_bhashfn(inet_sk(child)->num, table->bhash_size); + struct inet_bind_hashbucket *head = &table->bhash[bhash]; + struct inet_bind_bucket *tb; + + spin_lock(&head->lock); + tb = inet_csk(sk)->icsk_bind_hash; + sk_add_bind_node(child, &tb->owners); + inet_csk(child)->icsk_bind_hash = tb; + spin_unlock(&head->lock); +} + +static inline void inet_inherit_port(struct inet_hashinfo *table, + struct sock *sk, struct sock *child) +{ + local_bh_disable(); + __inet_inherit_port(table, sk, child); + local_bh_enable(); +} + +extern void inet_put_port(struct inet_hashinfo *table, struct sock *sk); + +extern void inet_listen_wlock(struct inet_hashinfo *hashinfo); + +/* + * - We may sleep inside this lock. + * - If sleeping is not required (or called from BH), + * use plain read_(un)lock(&inet_hashinfo.lhash_lock). + */ +static inline void inet_listen_lock(struct inet_hashinfo *hashinfo) +{ + /* read_lock synchronizes to candidates to writers */ + read_lock(&hashinfo->lhash_lock); + atomic_inc(&hashinfo->lhash_users); + read_unlock(&hashinfo->lhash_lock); +} + +static inline void inet_listen_unlock(struct inet_hashinfo *hashinfo) +{ + if (atomic_dec_and_test(&hashinfo->lhash_users)) + wake_up(&hashinfo->lhash_wait); +} + +static inline void __inet_hash(struct inet_hashinfo *hashinfo, + struct sock *sk, const int listen_possible) +{ + struct hlist_head *list; + rwlock_t *lock; + + BUG_TRAP(sk_unhashed(sk)); + if (listen_possible && sk->sk_state == TCP_LISTEN) { + list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; + lock = &hashinfo->lhash_lock; + inet_listen_wlock(hashinfo); + } else { + sk->sk_hashent = inet_sk_ehashfn(sk, hashinfo->ehash_size); + list = &hashinfo->ehash[sk->sk_hashent].chain; + lock = &hashinfo->ehash[sk->sk_hashent].lock; + write_lock(lock); + } + __sk_add_node(sk, list); + sock_prot_inc_use(sk->sk_prot); + write_unlock(lock); + if (listen_possible && sk->sk_state == TCP_LISTEN) + wake_up(&hashinfo->lhash_wait); +} + +static inline void inet_hash(struct inet_hashinfo *hashinfo, struct sock *sk) +{ + if (sk->sk_state != TCP_CLOSE) { + local_bh_disable(); + __inet_hash(hashinfo, sk, 1); + local_bh_enable(); + } +} + +static inline void inet_unhash(struct inet_hashinfo *hashinfo, struct sock *sk) +{ + rwlock_t *lock; + + if (sk_unhashed(sk)) + goto out; + + if (sk->sk_state == TCP_LISTEN) { + local_bh_disable(); + inet_listen_wlock(hashinfo); + lock = &hashinfo->lhash_lock; + } else { + struct inet_ehash_bucket *head = &hashinfo->ehash[sk->sk_hashent]; + lock = &head->lock; + write_lock_bh(&head->lock); + } + + if (__sk_del_node_init(sk)) + sock_prot_dec_use(sk->sk_prot); + write_unlock_bh(lock); +out: + if (sk->sk_state == TCP_LISTEN) + wake_up(&hashinfo->lhash_wait); +} + +static inline int inet_iif(const struct sk_buff *skb) +{ + return ((struct rtable *)skb->dst)->rt_iif; +} + +extern struct sock *__inet_lookup_listener(const struct hlist_head *head, + const u32 daddr, + const unsigned short hnum, + const int dif); + +/* Optimize the common listener case. */ +static inline struct sock * + inet_lookup_listener(struct inet_hashinfo *hashinfo, + const u32 daddr, + const unsigned short hnum, const int dif) +{ + struct sock *sk = NULL; + const struct hlist_head *head; + + read_lock(&hashinfo->lhash_lock); + head = &hashinfo->listening_hash[inet_lhashfn(hnum)]; + if (!hlist_empty(head)) { + const struct inet_sock *inet = inet_sk((sk = __sk_head(head))); + + if (inet->num == hnum && !sk->sk_node.next && + (!inet->rcv_saddr || inet->rcv_saddr == daddr) && + (sk->sk_family == PF_INET || !ipv6_only_sock(sk)) && + !sk->sk_bound_dev_if) + goto sherry_cache; + sk = __inet_lookup_listener(head, daddr, hnum, dif); + } + if (sk) { +sherry_cache: + sock_hold(sk); + } + read_unlock(&hashinfo->lhash_lock); + return sk; +} + +/* Socket demux engine toys. */ +#ifdef __BIG_ENDIAN +#define INET_COMBINED_PORTS(__sport, __dport) \ + (((__u32)(__sport) << 16) | (__u32)(__dport)) +#else /* __LITTLE_ENDIAN */ +#define INET_COMBINED_PORTS(__sport, __dport) \ + (((__u32)(__dport) << 16) | (__u32)(__sport)) +#endif + +#if (BITS_PER_LONG == 64) +#ifdef __BIG_ENDIAN +#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ + const __u64 __name = (((__u64)(__saddr)) << 32) | ((__u64)(__daddr)); +#else /* __LITTLE_ENDIAN */ +#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ + const __u64 __name = (((__u64)(__daddr)) << 32) | ((__u64)(__saddr)); +#endif /* __BIG_ENDIAN */ +#define INET_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\ + (((*((__u64 *)&(inet_sk(__sk)->daddr))) == (__cookie)) && \ + ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ + (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) +#define INET_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\ + (((*((__u64 *)&(inet_twsk(__sk)->tw_daddr))) == (__cookie)) && \ + ((*((__u32 *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) && \ + (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) +#else /* 32-bit arch */ +#define INET_ADDR_COOKIE(__name, __saddr, __daddr) +#define INET_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif) \ + ((inet_sk(__sk)->daddr == (__saddr)) && \ + (inet_sk(__sk)->rcv_saddr == (__daddr)) && \ + ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ + (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) +#define INET_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif) \ + ((inet_twsk(__sk)->tw_daddr == (__saddr)) && \ + (inet_twsk(__sk)->tw_rcv_saddr == (__daddr)) && \ + ((*((__u32 *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) && \ + (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) +#endif /* 64-bit arch */ + +/* + * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need + * not check it for lookups anymore, thanks Alexey. -DaveM + * + * Local BH must be disabled here. + */ +static inline struct sock * + __inet_lookup_established(struct inet_hashinfo *hashinfo, + const u32 saddr, const u16 sport, + const u32 daddr, const u16 hnum, + const int dif) +{ + INET_ADDR_COOKIE(acookie, saddr, daddr) + const __u32 ports = INET_COMBINED_PORTS(sport, hnum); + struct sock *sk; + const struct hlist_node *node; + /* Optimize here for direct hit, only listening connections can + * have wildcards anyways. + */ + const int hash = inet_ehashfn(daddr, hnum, saddr, sport, hashinfo->ehash_size); + struct inet_ehash_bucket *head = &hashinfo->ehash[hash]; + + read_lock(&head->lock); + sk_for_each(sk, node, &head->chain) { + if (INET_MATCH(sk, acookie, saddr, daddr, ports, dif)) + goto hit; /* You sunk my battleship! */ + } + + /* Must check for a TIME_WAIT'er before going to listener hash. */ + sk_for_each(sk, node, &(head + hashinfo->ehash_size)->chain) { + if (INET_TW_MATCH(sk, acookie, saddr, daddr, ports, dif)) + goto hit; + } + sk = NULL; +out: + read_unlock(&head->lock); + return sk; +hit: + sock_hold(sk); + goto out; +} + +static inline struct sock *__inet_lookup(struct inet_hashinfo *hashinfo, + const u32 saddr, const u16 sport, + const u32 daddr, const u16 hnum, + const int dif) +{ + struct sock *sk = __inet_lookup_established(hashinfo, saddr, sport, daddr, + hnum, dif); + return sk ? : inet_lookup_listener(hashinfo, daddr, hnum, dif); +} + +static inline struct sock *inet_lookup(struct inet_hashinfo *hashinfo, + const u32 saddr, const u16 sport, + const u32 daddr, const u16 dport, + const int dif) +{ + struct sock *sk; + + local_bh_disable(); + sk = __inet_lookup(hashinfo, saddr, sport, daddr, ntohs(dport), dif); + local_bh_enable(); + + return sk; +} +#endif /* _INET_HASHTABLES_H */ diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h new file mode 100644 index 00000000000..3b070352e86 --- /dev/null +++ b/include/net/inet_timewait_sock.h @@ -0,0 +1,219 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions for a generic INET TIMEWAIT sock + * + * From code originally in net/tcp.h + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _INET_TIMEWAIT_SOCK_ +#define _INET_TIMEWAIT_SOCK_ + +#include <linux/config.h> + +#include <linux/ip.h> +#include <linux/list.h> +#include <linux/timer.h> +#include <linux/types.h> +#include <linux/workqueue.h> + +#include <net/sock.h> +#include <net/tcp_states.h> + +#include <asm/atomic.h> + +struct inet_hashinfo; + +#define INET_TWDR_RECYCLE_SLOTS_LOG 5 +#define INET_TWDR_RECYCLE_SLOTS (1 << INET_TWDR_RECYCLE_SLOTS_LOG) + +/* + * If time > 4sec, it is "slow" path, no recycling is required, + * so that we select tick to get range about 4 seconds. + */ +#if HZ <= 16 || HZ > 4096 +# error Unsupported: HZ <= 16 or HZ > 4096 +#elif HZ <= 32 +# define INET_TWDR_RECYCLE_TICK (5 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) +#elif HZ <= 64 +# define INET_TWDR_RECYCLE_TICK (6 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) +#elif HZ <= 128 +# define INET_TWDR_RECYCLE_TICK (7 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) +#elif HZ <= 256 +# define INET_TWDR_RECYCLE_TICK (8 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) +#elif HZ <= 512 +# define INET_TWDR_RECYCLE_TICK (9 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) +#elif HZ <= 1024 +# define INET_TWDR_RECYCLE_TICK (10 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) +#elif HZ <= 2048 +# define INET_TWDR_RECYCLE_TICK (11 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) +#else +# define INET_TWDR_RECYCLE_TICK (12 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) +#endif + +/* TIME_WAIT reaping mechanism. */ +#define INET_TWDR_TWKILL_SLOTS 8 /* Please keep this a power of 2. */ + +#define INET_TWDR_TWKILL_QUOTA 100 + +struct inet_timewait_death_row { + /* Short-time timewait calendar */ + int twcal_hand; + int twcal_jiffie; + struct timer_list twcal_timer; + struct hlist_head twcal_row[INET_TWDR_RECYCLE_SLOTS]; + + spinlock_t death_lock; + int tw_count; + int period; + u32 thread_slots; + struct work_struct twkill_work; + struct timer_list tw_timer; + int slot; + struct hlist_head cells[INET_TWDR_TWKILL_SLOTS]; + struct inet_hashinfo *hashinfo; + int sysctl_tw_recycle; + int sysctl_max_tw_buckets; +}; + +extern void inet_twdr_hangman(unsigned long data); +extern void inet_twdr_twkill_work(void *data); +extern void inet_twdr_twcal_tick(unsigned long data); + +#if (BITS_PER_LONG == 64) +#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 8 +#else +#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 4 +#endif + +struct inet_bind_bucket; + +/* + * This is a TIME_WAIT sock. It works around the memory consumption + * problems of sockets in such a state on heavily loaded servers, but + * without violating the protocol specification. + */ +struct inet_timewait_sock { + /* + * Now struct sock also uses sock_common, so please just + * don't add nothing before this first member (__tw_common) --acme + */ + struct sock_common __tw_common; +#define tw_family __tw_common.skc_family +#define tw_state __tw_common.skc_state +#define tw_reuse __tw_common.skc_reuse +#define tw_bound_dev_if __tw_common.skc_bound_dev_if +#define tw_node __tw_common.skc_node +#define tw_bind_node __tw_common.skc_bind_node +#define tw_refcnt __tw_common.skc_refcnt +#define tw_prot __tw_common.skc_prot + volatile unsigned char tw_substate; + /* 3 bits hole, try to pack */ + unsigned char tw_rcv_wscale; + /* Socket demultiplex comparisons on incoming packets. */ + /* these five are in inet_sock */ + __u16 tw_sport; + __u32 tw_daddr __attribute__((aligned(INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES))); + __u32 tw_rcv_saddr; + __u16 tw_dport; + __u16 tw_num; + /* And these are ours. */ + __u8 tw_ipv6only:1; + /* 31 bits hole, try to pack */ + int tw_hashent; + int tw_timeout; + unsigned long tw_ttd; + struct inet_bind_bucket *tw_tb; + struct hlist_node tw_death_node; +}; + +static inline void inet_twsk_add_node(struct inet_timewait_sock *tw, + struct hlist_head *list) +{ + hlist_add_head(&tw->tw_node, list); +} + +static inline void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, + struct hlist_head *list) +{ + hlist_add_head(&tw->tw_bind_node, list); +} + +static inline int inet_twsk_dead_hashed(const struct inet_timewait_sock *tw) +{ + return tw->tw_death_node.pprev != NULL; +} + +static inline void inet_twsk_dead_node_init(struct inet_timewait_sock *tw) +{ + tw->tw_death_node.pprev = NULL; +} + +static inline void __inet_twsk_del_dead_node(struct inet_timewait_sock *tw) +{ + __hlist_del(&tw->tw_death_node); + inet_twsk_dead_node_init(tw); +} + +static inline int inet_twsk_del_dead_node(struct inet_timewait_sock *tw) +{ + if (inet_twsk_dead_hashed(tw)) { + __inet_twsk_del_dead_node(tw); + return 1; + } + return 0; +} + +#define inet_twsk_for_each(tw, node, head) \ + hlist_for_each_entry(tw, node, head, tw_node) + +#define inet_twsk_for_each_inmate(tw, node, jail) \ + hlist_for_each_entry(tw, node, jail, tw_death_node) + +#define inet_twsk_for_each_inmate_safe(tw, node, safe, jail) \ + hlist_for_each_entry_safe(tw, node, safe, jail, tw_death_node) + +static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk) +{ + return (struct inet_timewait_sock *)sk; +} + +static inline u32 inet_rcv_saddr(const struct sock *sk) +{ + return likely(sk->sk_state != TCP_TIME_WAIT) ? + inet_sk(sk)->rcv_saddr : inet_twsk(sk)->tw_rcv_saddr; +} + +static inline void inet_twsk_put(struct inet_timewait_sock *tw) +{ + if (atomic_dec_and_test(&tw->tw_refcnt)) { +#ifdef SOCK_REFCNT_DEBUG + printk(KERN_DEBUG "%s timewait_sock %p released\n", + tw->tw_prot->name, tw); +#endif + kmem_cache_free(tw->tw_prot->twsk_slab, tw); + } +} + +extern struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, + const int state); + +extern void __inet_twsk_kill(struct inet_timewait_sock *tw, + struct inet_hashinfo *hashinfo); + +extern void __inet_twsk_hashdance(struct inet_timewait_sock *tw, + struct sock *sk, + struct inet_hashinfo *hashinfo); + +extern void inet_twsk_schedule(struct inet_timewait_sock *tw, + struct inet_timewait_death_row *twdr, + const int timeo, const int timewait_len); +extern void inet_twsk_deschedule(struct inet_timewait_sock *tw, + struct inet_timewait_death_row *twdr); +#endif /* _INET_TIMEWAIT_SOCK_ */ diff --git a/include/net/ip.h b/include/net/ip.h index 32360bbe143..e4563bbee6e 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -86,7 +86,7 @@ extern int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, u32 saddr, u32 daddr, struct ip_options *opt); extern int ip_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt); + struct packet_type *pt, struct net_device *orig_dev); extern int ip_local_deliver(struct sk_buff *skb); extern int ip_mr_input(struct sk_buff *skb); extern int ip_output(struct sk_buff *skb); @@ -140,8 +140,6 @@ struct ip_reply_arg { void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *arg, unsigned int len); -extern int ip_finish_output(struct sk_buff *skb); - struct ipv4_config { int log_martians; @@ -165,6 +163,24 @@ extern int sysctl_local_port_range[2]; extern int sysctl_ip_default_ttl; extern int sysctl_ip_nonlocal_bind; +/* From ip_fragment.c */ +extern int sysctl_ipfrag_high_thresh; +extern int sysctl_ipfrag_low_thresh; +extern int sysctl_ipfrag_time; +extern int sysctl_ipfrag_secret_interval; + +/* From inetpeer.c */ +extern int inet_peer_threshold; +extern int inet_peer_minttl; +extern int inet_peer_maxttl; +extern int inet_peer_gc_mintime; +extern int inet_peer_gc_maxtime; + +/* From ip_output.c */ +extern int sysctl_ip_dynaddr; + +extern void ipfrag_init(void); + #ifdef CONFIG_INET /* The function in 2.2 was invalid, producing wrong result for * check=0xFEFF. It was noticed by Arthur Skawina _year_ ago. --ANK(000625) */ @@ -319,7 +335,10 @@ extern void ip_options_build(struct sk_buff *skb, struct ip_options *opt, u32 da extern int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb); extern void ip_options_fragment(struct sk_buff *skb); extern int ip_options_compile(struct ip_options *opt, struct sk_buff *skb); -extern int ip_options_get(struct ip_options **optp, unsigned char *data, int optlen, int user); +extern int ip_options_get(struct ip_options **optp, + unsigned char *data, int optlen); +extern int ip_options_get_from_user(struct ip_options **optp, + unsigned char __user *data, int optlen); extern void ip_options_undo(struct ip_options * opt); extern void ip_forward_options(struct sk_buff *skb); extern int ip_options_rcv_srr(struct sk_buff *skb); @@ -350,5 +369,10 @@ int ipv4_doint_and_flush_strategy(ctl_table *table, int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen, void **context); +#ifdef CONFIG_PROC_FS +extern int ip_misc_proc_init(void); +#endif + +extern struct ctl_table ipv4_table[]; #endif /* _IP_H */ diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f920706d526..1f2e428ca36 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -12,7 +12,6 @@ #include <net/flow.h> #include <net/ip6_fib.h> #include <net/sock.h> -#include <linux/tcp.h> #include <linux/ip.h> #include <linux/ipv6.h> diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index a4208a336ac..14de4ebd121 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -295,4 +295,9 @@ static inline void fib_res_put(struct fib_result *res) #endif } +#ifdef CONFIG_PROC_FS +extern int fib_proc_init(void); +extern void fib_proc_exit(void); +#endif + #endif /* _NET_FIB_H */ diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 52da5d26617..7a3c43711a1 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -255,7 +255,6 @@ struct ip_vs_daemon_user { #include <asm/atomic.h> /* for struct atomic_t */ #include <linux/netdevice.h> /* for struct neighbour */ #include <net/dst.h> /* for struct dst_entry */ -#include <net/tcp.h> #include <net/udp.h> #include <linux/compiler.h> diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 69324465e8b..3203eaff4bd 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -104,6 +104,7 @@ struct frag_hdr { #ifdef __KERNEL__ +#include <linux/config.h> #include <net/sock.h> /* sysctls */ @@ -145,7 +146,6 @@ DECLARE_SNMP_STAT(struct udp_mib, udp_stats_in6); #define UDP6_INC_STATS(field) SNMP_INC_STATS(udp_stats_in6, field) #define UDP6_INC_STATS_BH(field) SNMP_INC_STATS_BH(udp_stats_in6, field) #define UDP6_INC_STATS_USER(field) SNMP_INC_STATS_USER(udp_stats_in6, field) -extern atomic_t inet6_sock_nr; int snmp6_register_dev(struct inet6_dev *idev); int snmp6_unregister_dev(struct inet6_dev *idev); @@ -346,7 +346,8 @@ static inline int ipv6_addr_any(const struct in6_addr *a) extern int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt); + struct packet_type *pt, + struct net_device *orig_dev); /* * upper-layer output functions @@ -464,8 +465,38 @@ extern int sysctl_ip6frag_low_thresh; extern int sysctl_ip6frag_time; extern int sysctl_ip6frag_secret_interval; -#endif /* __KERNEL__ */ -#endif /* _NET_IPV6_H */ +extern struct proto_ops inet6_stream_ops; +extern struct proto_ops inet6_dgram_ops; + +extern int ip6_mc_source(int add, int omode, struct sock *sk, + struct group_source_req *pgsr); +extern int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf); +extern int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, + struct group_filter __user *optval, + int __user *optlen); + +#ifdef CONFIG_PROC_FS +extern int ac6_proc_init(void); +extern void ac6_proc_exit(void); +extern int raw6_proc_init(void); +extern void raw6_proc_exit(void); +extern int tcp6_proc_init(void); +extern void tcp6_proc_exit(void); +extern int udp6_proc_init(void); +extern void udp6_proc_exit(void); +extern int ipv6_misc_proc_init(void); +extern void ipv6_misc_proc_exit(void); + +extern struct rt6_statistics rt6_stats; +#endif +#ifdef CONFIG_SYSCTL +extern ctl_table ipv6_route_table[]; +extern ctl_table ipv6_icmp_table[]; +extern void ipv6_sysctl_register(void); +extern void ipv6_sysctl_unregister(void); +#endif +#endif /* __KERNEL__ */ +#endif /* _NET_IPV6_H */ diff --git a/include/net/llc.h b/include/net/llc.h index c9aed2a8b4e..71769a5aeef 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -46,7 +46,8 @@ struct llc_sap { unsigned char f_bit; int (*rcv_func)(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt); + struct packet_type *pt, + struct net_device *orig_dev); struct llc_addr laddr; struct list_head node; struct { @@ -64,7 +65,7 @@ extern rwlock_t llc_sap_list_lock; extern unsigned char llc_station_mac_sa[ETH_ALEN]; extern int llc_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt); + struct packet_type *pt, struct net_device *orig_dev); extern int llc_mac_hdr_init(struct sk_buff *skb, unsigned char *sa, unsigned char *da); @@ -78,7 +79,8 @@ extern void llc_set_station_handler(void (*handler)(struct sk_buff *skb)); extern struct llc_sap *llc_sap_open(unsigned char lsap, int (*rcv)(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt)); + struct packet_type *pt, + struct net_device *orig_dev)); extern void llc_sap_close(struct llc_sap *sap); extern struct llc_sap *llc_sap_find(unsigned char sap_value); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 89809891e5a..34c07731933 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -363,7 +363,14 @@ __neigh_lookup_errno(struct neigh_table *tbl, const void *pkey, return neigh_create(tbl, pkey, dev); } -#define LOCALLY_ENQUEUED -2 +struct neighbour_cb { + unsigned long sched_next; + unsigned int flags; +}; + +#define LOCALLY_ENQUEUED 0x1 + +#define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) #endif #endif diff --git a/include/net/p8022.h b/include/net/p8022.h index 3c99a86c358..42e9fac51b3 100644 --- a/include/net/p8022.h +++ b/include/net/p8022.h @@ -4,7 +4,10 @@ extern struct datalink_proto * register_8022_client(unsigned char type, int (*func)(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt)); + struct packet_type *pt, + struct net_device *orig_dev)); extern void unregister_8022_client(struct datalink_proto *proto); +extern struct datalink_proto *make_8023_client(void); +extern void destroy_8023_client(struct datalink_proto *dl); #endif diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 4abda6aec05..b902d24a325 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -352,10 +352,10 @@ tcf_change_indev(struct tcf_proto *tp, char *indev, struct rtattr *indev_tlv) static inline int tcf_match_indev(struct sk_buff *skb, char *indev) { - if (0 != indev[0]) { - if (NULL == skb->input_dev) + if (indev[0]) { + if (!skb->input_dev) return 0; - else if (0 != strcmp(indev, skb->input_dev->name)) + if (strcmp(indev, skb->input_dev->name)) return 0; } diff --git a/include/net/psnap.h b/include/net/psnap.h index 9c94e8f98b3..b2e01cc3fc8 100644 --- a/include/net/psnap.h +++ b/include/net/psnap.h @@ -1,7 +1,7 @@ #ifndef _NET_PSNAP_H #define _NET_PSNAP_H -extern struct datalink_proto *register_snap_client(unsigned char *desc, int (*rcvfunc)(struct sk_buff *, struct net_device *, struct packet_type *)); +extern struct datalink_proto *register_snap_client(unsigned char *desc, int (*rcvfunc)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *orig_dev)); extern void unregister_snap_client(struct datalink_proto *proto); #endif diff --git a/include/net/raw.h b/include/net/raw.h index 1c411c45587..f47917469b1 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -17,10 +17,10 @@ #ifndef _RAW_H #define _RAW_H +#include <linux/config.h> extern struct proto raw_prot; - extern void raw_err(struct sock *, struct sk_buff *, u32 info); extern int raw_rcv(struct sock *, struct sk_buff *); @@ -37,6 +37,11 @@ extern struct sock *__raw_v4_lookup(struct sock *sk, unsigned short num, unsigned long raddr, unsigned long laddr, int dif); -extern void raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash); +extern int raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash); + +#ifdef CONFIG_PROC_FS +extern int raw_proc_init(void); +extern void raw_proc_exit(void); +#endif #endif /* _RAW_H */ diff --git a/include/net/rawv6.h b/include/net/rawv6.h index 23fd9a6a221..14476a71725 100644 --- a/include/net/rawv6.h +++ b/include/net/rawv6.h @@ -7,10 +7,11 @@ extern struct hlist_head raw_v6_htable[RAWV6_HTABLE_SIZE]; extern rwlock_t raw_v6_lock; -extern void ipv6_raw_deliver(struct sk_buff *skb, int nexthdr); +extern int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr); extern struct sock *__raw_v6_lookup(struct sock *sk, unsigned short num, - struct in6_addr *loc_addr, struct in6_addr *rmt_addr); + struct in6_addr *loc_addr, struct in6_addr *rmt_addr, + int dif); extern int rawv6_rcv(struct sock *sk, struct sk_buff *skb); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 72fd6f5e86b..b52cc52ffe3 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -89,6 +89,7 @@ struct listen_sock { int qlen_young; int clock_hand; u32 hash_rnd; + u32 nr_table_entries; struct request_sock *syn_table[0]; }; @@ -96,6 +97,7 @@ struct listen_sock { * * @rskq_accept_head - FIFO head of established children * @rskq_accept_tail - FIFO tail of established children + * @rskq_defer_accept - User waits for some data after accept() * @syn_wait_lock - serializer * * %syn_wait_lock is necessary only to avoid proc interface having to grab the main @@ -111,6 +113,8 @@ struct request_sock_queue { struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; rwlock_t syn_wait_lock; + u8 rskq_defer_accept; + /* 3 bytes hole, try to pack */ struct listen_sock *listen_opt; }; @@ -129,11 +133,13 @@ static inline struct listen_sock *reqsk_queue_yank_listen_sk(struct request_sock return lopt; } -static inline void reqsk_queue_destroy(struct request_sock_queue *queue) +static inline void __reqsk_queue_destroy(struct request_sock_queue *queue) { kfree(reqsk_queue_yank_listen_sk(queue)); } +extern void reqsk_queue_destroy(struct request_sock_queue *queue); + static inline struct request_sock * reqsk_queue_yank_acceptq(struct request_sock_queue *queue) { @@ -221,17 +227,17 @@ static inline int reqsk_queue_added(struct request_sock_queue *queue) return prev_qlen; } -static inline int reqsk_queue_len(struct request_sock_queue *queue) +static inline int reqsk_queue_len(const struct request_sock_queue *queue) { return queue->listen_opt != NULL ? queue->listen_opt->qlen : 0; } -static inline int reqsk_queue_len_young(struct request_sock_queue *queue) +static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) { return queue->listen_opt->qlen_young; } -static inline int reqsk_queue_is_full(struct request_sock_queue *queue) +static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) { return queue->listen_opt->qlen >> queue->listen_opt->max_qlen_log; } diff --git a/include/net/route.h b/include/net/route.h index c3cd069a9ac..dbe79ca67d3 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -105,10 +105,6 @@ struct rt_cache_stat unsigned int out_hlist_search; }; -extern struct rt_cache_stat *rt_cache_stat; -#define RT_CACHE_STAT_INC(field) \ - (per_cpu_ptr(rt_cache_stat, raw_smp_processor_id())->field++) - extern struct ip_rt_acct *ip_rt_acct; struct in_device; @@ -199,4 +195,6 @@ static inline struct inet_peer *rt_get_peer(struct rtable *rt) return rt->peer; } +extern ctl_table ipv4_route_table[]; + #endif /* _ROUTE_H */ diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 5999e5684bb..c51541ee024 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -47,10 +47,10 @@ #ifndef __sctp_constants_h__ #define __sctp_constants_h__ -#include <linux/tcp.h> /* For TCP states used in sctp_sock_state_t */ #include <linux/sctp.h> #include <linux/ipv6.h> /* For ipv6hdr. */ #include <net/sctp/user.h> +#include <net/tcp_states.h> /* For TCP states used in sctp_sock_state_t */ /* Value used for stream negotiation. */ enum { SCTP_MAX_STREAM = 0xffff }; diff --git a/include/net/sock.h b/include/net/sock.h index e9b1dbab90d..312cb25cbd1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -88,6 +88,7 @@ do { spin_lock_init(&((__sk)->sk_lock.slock)); \ } while(0) struct sock; +struct proto; /** * struct sock_common - minimal network layer representation of sockets @@ -98,10 +99,11 @@ struct sock; * @skc_node: main hash linkage for various protocol lookup tables * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_refcnt: reference count + * @skc_prot: protocol handlers inside a network family * * This is the minimal network layer representation of sockets, the header - * for struct sock and struct tcp_tw_bucket. - */ + * for struct sock and struct inet_timewait_sock. + */ struct sock_common { unsigned short skc_family; volatile unsigned char skc_state; @@ -110,11 +112,12 @@ struct sock_common { struct hlist_node skc_node; struct hlist_node skc_bind_node; atomic_t skc_refcnt; + struct proto *skc_prot; }; /** * struct sock - network layer representation of sockets - * @__sk_common: shared layout with tcp_tw_bucket + * @__sk_common: shared layout with inet_timewait_sock * @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer @@ -136,11 +139,10 @@ struct sock_common { * @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_lingertime: %SO_LINGER l_linger setting - * @sk_hashent: hash entry in several tables (e.g. tcp_ehash) + * @sk_hashent: hash entry in several tables (e.g. inet_hashinfo.ehash) * @sk_backlog: always used with the per-socket spinlock held * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used - * @sk_prot: protocol handlers inside a network family * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, IPV6_ADDRFORM for instance) * @sk_err: last error * @sk_err_soft: errors that don't cause failure but are the cause of a persistent failure not just 'timed out' @@ -173,7 +175,7 @@ struct sock_common { */ struct sock { /* - * Now struct tcp_tw_bucket also uses sock_common, so please just + * Now struct inet_timewait_sock also uses sock_common, so please just * don't add nothing before this first member (__sk_common) --acme */ struct sock_common __sk_common; @@ -184,6 +186,7 @@ struct sock { #define sk_node __sk_common.skc_node #define sk_bind_node __sk_common.skc_bind_node #define sk_refcnt __sk_common.skc_refcnt +#define sk_prot __sk_common.skc_prot unsigned char sk_shutdown : 2, sk_no_check : 2, sk_userlocks : 4; @@ -218,7 +221,6 @@ struct sock { struct sk_buff *tail; } sk_backlog; struct sk_buff_head sk_error_queue; - struct proto *sk_prot; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; int sk_err, @@ -253,28 +255,28 @@ struct sock { /* * Hashed lists helper routines */ -static inline struct sock *__sk_head(struct hlist_head *head) +static inline struct sock *__sk_head(const struct hlist_head *head) { return hlist_entry(head->first, struct sock, sk_node); } -static inline struct sock *sk_head(struct hlist_head *head) +static inline struct sock *sk_head(const struct hlist_head *head) { return hlist_empty(head) ? NULL : __sk_head(head); } -static inline struct sock *sk_next(struct sock *sk) +static inline struct sock *sk_next(const struct sock *sk) { return sk->sk_node.next ? hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL; } -static inline int sk_unhashed(struct sock *sk) +static inline int sk_unhashed(const struct sock *sk) { return hlist_unhashed(&sk->sk_node); } -static inline int sk_hashed(struct sock *sk) +static inline int sk_hashed(const struct sock *sk) { return sk->sk_node.pprev != NULL; } @@ -554,6 +556,10 @@ struct proto { kmem_cache_t *slab; unsigned int obj_size; + kmem_cache_t *twsk_slab; + unsigned int twsk_obj_size; + atomic_t *orphan_count; + struct request_sock_ops *rsk_prot; struct module *owner; @@ -561,7 +567,9 @@ struct proto { char name[32]; struct list_head node; - +#ifdef SOCK_REFCNT_DEBUG + atomic_t socks; +#endif struct { int inuse; u8 __pad[SMP_CACHE_BYTES - sizeof(int)]; @@ -571,6 +579,31 @@ struct proto { extern int proto_register(struct proto *prot, int alloc_slab); extern void proto_unregister(struct proto *prot); +#ifdef SOCK_REFCNT_DEBUG +static inline void sk_refcnt_debug_inc(struct sock *sk) +{ + atomic_inc(&sk->sk_prot->socks); +} + +static inline void sk_refcnt_debug_dec(struct sock *sk) +{ + atomic_dec(&sk->sk_prot->socks); + printk(KERN_DEBUG "%s socket %p released, %d are still alive\n", + sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks)); +} + +static inline void sk_refcnt_debug_release(const struct sock *sk) +{ + if (atomic_read(&sk->sk_refcnt) != 1) + printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n", + sk->sk_prot->name, sk, atomic_read(&sk->sk_refcnt)); +} +#else /* SOCK_REFCNT_DEBUG */ +#define sk_refcnt_debug_inc(sk) do { } while (0) +#define sk_refcnt_debug_dec(sk) do { } while (0) +#define sk_refcnt_debug_release(sk) do { } while (0) +#endif /* SOCK_REFCNT_DEBUG */ + /* Called with local bh disabled */ static __inline__ void sock_prot_inc_use(struct proto *prot) { @@ -582,6 +615,15 @@ static __inline__ void sock_prot_dec_use(struct proto *prot) prot->stats[smp_processor_id()].inuse--; } +/* With per-bucket locks this operation is not-atomic, so that + * this version is not worse. + */ +static inline void __sk_prot_rehash(struct sock *sk) +{ + sk->sk_prot->unhash(sk); + sk->sk_prot->hash(sk); +} + /* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ) @@ -693,6 +735,8 @@ extern struct sock *sk_alloc(int family, unsigned int __nocast priority, struct proto *prot, int zero_it); extern void sk_free(struct sock *sk); +extern struct sock *sk_clone(const struct sock *sk, + const unsigned int __nocast priority); extern struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, @@ -986,6 +1030,16 @@ sk_dst_check(struct sock *sk, u32 cookie) return dst; } +static inline void sk_setup_caps(struct sock *sk, struct dst_entry *dst) +{ + __sk_dst_set(sk, dst); + sk->sk_route_caps = dst->dev->features; + if (sk->sk_route_caps & NETIF_F_TSO) { + if (sock_flag(sk, SOCK_NO_LARGESEND) || dst->header_len) + sk->sk_route_caps &= ~NETIF_F_TSO; + } +} + static inline void sk_charge_skb(struct sock *sk, struct sk_buff *skb) { sk->sk_wmem_queued += skb->truesize; @@ -1146,7 +1200,7 @@ static inline struct sk_buff *sk_stream_alloc_pskb(struct sock *sk, int hdr_len; hdr_len = SKB_DATA_ALIGN(sk->sk_prot->max_header); - skb = alloc_skb(size + hdr_len, gfp); + skb = alloc_skb_fclone(size + hdr_len, gfp); if (skb) { skb->truesize += mem; if (sk->sk_forward_alloc >= (int)skb->truesize || @@ -1228,16 +1282,19 @@ static inline int sock_intr_errno(long timeo) static __inline__ void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { - struct timeval *stamp = &skb->stamp; + struct timeval stamp; + + skb_get_timestamp(skb, &stamp); if (sock_flag(sk, SOCK_RCVTSTAMP)) { /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ - if (stamp->tv_sec == 0) - do_gettimeofday(stamp); + if (stamp.tv_sec == 0) + do_gettimeofday(&stamp); + skb_set_timestamp(skb, &stamp); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP, sizeof(struct timeval), - stamp); + &stamp); } else - sk->sk_stamp = *stamp; + sk->sk_stamp = stamp; } /** @@ -1262,11 +1319,11 @@ extern int sock_get_timestamp(struct sock *, struct timeval __user *); */ #if 0 -#define NETDEBUG(x) do { } while (0) -#define LIMIT_NETDEBUG(x) do {} while(0) +#define NETDEBUG(fmt, args...) do { } while (0) +#define LIMIT_NETDEBUG(fmt, args...) do { } while(0) #else -#define NETDEBUG(x) do { x; } while (0) -#define LIMIT_NETDEBUG(x) do { if (net_ratelimit()) { x; } } while(0) +#define NETDEBUG(fmt, args...) printk(fmt,##args) +#define LIMIT_NETDEBUG(fmt, args...) do { if (net_ratelimit()) printk(fmt,##args); } while(0) #endif /* @@ -1313,4 +1370,14 @@ static inline int siocdevprivate_ioctl(unsigned int fd, unsigned int cmd, unsign } #endif +extern void sk_init(void); + +#ifdef CONFIG_SYSCTL +extern struct ctl_table core_table[]; +extern int sysctl_optmem_max; +#endif + +extern __u32 sysctl_wmem_default; +extern __u32 sysctl_rmem_default; + #endif /* _SOCK_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 5010f0c5a56..d6bcf1317a6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -21,360 +21,29 @@ #define TCP_DEBUG 1 #define FASTRETRANS_DEBUG 1 -/* Cancel timers, when they are not required. */ -#undef TCP_CLEAR_TIMERS - #include <linux/config.h> #include <linux/list.h> #include <linux/tcp.h> #include <linux/slab.h> #include <linux/cache.h> #include <linux/percpu.h> + +#include <net/inet_connection_sock.h> +#include <net/inet_timewait_sock.h> +#include <net/inet_hashtables.h> #include <net/checksum.h> #include <net/request_sock.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) -#include <linux/ipv6.h> -#endif -#include <linux/seq_file.h> - -/* This is for all connections with a full identity, no wildcards. - * New scheme, half the table is for TIME_WAIT, the other half is - * for the rest. I'll experiment with dynamic table growth later. - */ -struct tcp_ehash_bucket { - rwlock_t lock; - struct hlist_head chain; -} __attribute__((__aligned__(8))); - -/* This is for listening sockets, thus all sockets which possess wildcards. */ -#define TCP_LHTABLE_SIZE 32 /* Yes, really, this is all you need. */ - -/* There are a few simple rules, which allow for local port reuse by - * an application. In essence: - * - * 1) Sockets bound to different interfaces may share a local port. - * Failing that, goto test 2. - * 2) If all sockets have sk->sk_reuse set, and none of them are in - * TCP_LISTEN state, the port may be shared. - * Failing that, goto test 3. - * 3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local - * address, and none of them are the same, the port may be - * shared. - * Failing this, the port cannot be shared. - * - * The interesting point, is test #2. This is what an FTP server does - * all day. To optimize this case we use a specific flag bit defined - * below. As we add sockets to a bind bucket list, we perform a - * check of: (newsk->sk_reuse && (newsk->sk_state != TCP_LISTEN)) - * As long as all sockets added to a bind bucket pass this test, - * the flag bit will be set. - * The resulting situation is that tcp_v[46]_verify_bind() can just check - * for this flag bit, if it is set and the socket trying to bind has - * sk->sk_reuse set, we don't even have to walk the owners list at all, - * we return that it is ok to bind this socket to the requested local port. - * - * Sounds like a lot of work, but it is worth it. In a more naive - * implementation (ie. current FreeBSD etc.) the entire list of ports - * must be walked for each data port opened by an ftp server. Needless - * to say, this does not scale at all. With a couple thousand FTP - * users logged onto your box, isn't it nice to know that new data - * ports are created in O(1) time? I thought so. ;-) -DaveM - */ -struct tcp_bind_bucket { - unsigned short port; - signed short fastreuse; - struct hlist_node node; - struct hlist_head owners; -}; - -#define tb_for_each(tb, node, head) hlist_for_each_entry(tb, node, head, node) - -struct tcp_bind_hashbucket { - spinlock_t lock; - struct hlist_head chain; -}; - -static inline struct tcp_bind_bucket *__tb_head(struct tcp_bind_hashbucket *head) -{ - return hlist_entry(head->chain.first, struct tcp_bind_bucket, node); -} - -static inline struct tcp_bind_bucket *tb_head(struct tcp_bind_hashbucket *head) -{ - return hlist_empty(&head->chain) ? NULL : __tb_head(head); -} - -extern struct tcp_hashinfo { - /* This is for sockets with full identity only. Sockets here will - * always be without wildcards and will have the following invariant: - * - * TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE - * - * First half of the table is for sockets not in TIME_WAIT, second half - * is for TIME_WAIT sockets only. - */ - struct tcp_ehash_bucket *__tcp_ehash; - - /* Ok, let's try this, I give up, we do need a local binding - * TCP hash as well as the others for fast bind/connect. - */ - struct tcp_bind_hashbucket *__tcp_bhash; +#include <net/tcp_states.h> - int __tcp_bhash_size; - int __tcp_ehash_size; - - /* All sockets in TCP_LISTEN state will be in here. This is the only - * table where wildcard'd TCP sockets can exist. Hash function here - * is just local port number. - */ - struct hlist_head __tcp_listening_hash[TCP_LHTABLE_SIZE]; - - /* All the above members are written once at bootup and - * never written again _or_ are predominantly read-access. - * - * Now align to a new cache line as all the following members - * are often dirty. - */ - rwlock_t __tcp_lhash_lock ____cacheline_aligned; - atomic_t __tcp_lhash_users; - wait_queue_head_t __tcp_lhash_wait; - spinlock_t __tcp_portalloc_lock; -} tcp_hashinfo; - -#define tcp_ehash (tcp_hashinfo.__tcp_ehash) -#define tcp_bhash (tcp_hashinfo.__tcp_bhash) -#define tcp_ehash_size (tcp_hashinfo.__tcp_ehash_size) -#define tcp_bhash_size (tcp_hashinfo.__tcp_bhash_size) -#define tcp_listening_hash (tcp_hashinfo.__tcp_listening_hash) -#define tcp_lhash_lock (tcp_hashinfo.__tcp_lhash_lock) -#define tcp_lhash_users (tcp_hashinfo.__tcp_lhash_users) -#define tcp_lhash_wait (tcp_hashinfo.__tcp_lhash_wait) -#define tcp_portalloc_lock (tcp_hashinfo.__tcp_portalloc_lock) - -extern kmem_cache_t *tcp_bucket_cachep; -extern struct tcp_bind_bucket *tcp_bucket_create(struct tcp_bind_hashbucket *head, - unsigned short snum); -extern void tcp_bucket_destroy(struct tcp_bind_bucket *tb); -extern void tcp_bucket_unlock(struct sock *sk); -extern int tcp_port_rover; - -/* These are AF independent. */ -static __inline__ int tcp_bhashfn(__u16 lport) -{ - return (lport & (tcp_bhash_size - 1)); -} - -extern void tcp_bind_hash(struct sock *sk, struct tcp_bind_bucket *tb, - unsigned short snum); - -#if (BITS_PER_LONG == 64) -#define TCP_ADDRCMP_ALIGN_BYTES 8 -#else -#define TCP_ADDRCMP_ALIGN_BYTES 4 -#endif - -/* This is a TIME_WAIT bucket. It works around the memory consumption - * problems of sockets in such a state on heavily loaded servers, but - * without violating the protocol specification. - */ -struct tcp_tw_bucket { - /* - * Now struct sock also uses sock_common, so please just - * don't add nothing before this first member (__tw_common) --acme - */ - struct sock_common __tw_common; -#define tw_family __tw_common.skc_family -#define tw_state __tw_common.skc_state -#define tw_reuse __tw_common.skc_reuse -#define tw_bound_dev_if __tw_common.skc_bound_dev_if -#define tw_node __tw_common.skc_node -#define tw_bind_node __tw_common.skc_bind_node -#define tw_refcnt __tw_common.skc_refcnt - volatile unsigned char tw_substate; - unsigned char tw_rcv_wscale; - __u16 tw_sport; - /* Socket demultiplex comparisons on incoming packets. */ - /* these five are in inet_sock */ - __u32 tw_daddr - __attribute__((aligned(TCP_ADDRCMP_ALIGN_BYTES))); - __u32 tw_rcv_saddr; - __u16 tw_dport; - __u16 tw_num; - /* And these are ours. */ - int tw_hashent; - int tw_timeout; - __u32 tw_rcv_nxt; - __u32 tw_snd_nxt; - __u32 tw_rcv_wnd; - __u32 tw_ts_recent; - long tw_ts_recent_stamp; - unsigned long tw_ttd; - struct tcp_bind_bucket *tw_tb; - struct hlist_node tw_death_node; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) - struct in6_addr tw_v6_daddr; - struct in6_addr tw_v6_rcv_saddr; - int tw_v6_ipv6only; -#endif -}; - -static __inline__ void tw_add_node(struct tcp_tw_bucket *tw, - struct hlist_head *list) -{ - hlist_add_head(&tw->tw_node, list); -} - -static __inline__ void tw_add_bind_node(struct tcp_tw_bucket *tw, - struct hlist_head *list) -{ - hlist_add_head(&tw->tw_bind_node, list); -} - -static inline int tw_dead_hashed(struct tcp_tw_bucket *tw) -{ - return tw->tw_death_node.pprev != NULL; -} - -static __inline__ void tw_dead_node_init(struct tcp_tw_bucket *tw) -{ - tw->tw_death_node.pprev = NULL; -} - -static __inline__ void __tw_del_dead_node(struct tcp_tw_bucket *tw) -{ - __hlist_del(&tw->tw_death_node); - tw_dead_node_init(tw); -} - -static __inline__ int tw_del_dead_node(struct tcp_tw_bucket *tw) -{ - if (tw_dead_hashed(tw)) { - __tw_del_dead_node(tw); - return 1; - } - return 0; -} - -#define tw_for_each(tw, node, head) \ - hlist_for_each_entry(tw, node, head, tw_node) - -#define tw_for_each_inmate(tw, node, jail) \ - hlist_for_each_entry(tw, node, jail, tw_death_node) - -#define tw_for_each_inmate_safe(tw, node, safe, jail) \ - hlist_for_each_entry_safe(tw, node, safe, jail, tw_death_node) - -#define tcptw_sk(__sk) ((struct tcp_tw_bucket *)(__sk)) - -static inline u32 tcp_v4_rcv_saddr(const struct sock *sk) -{ - return likely(sk->sk_state != TCP_TIME_WAIT) ? - inet_sk(sk)->rcv_saddr : tcptw_sk(sk)->tw_rcv_saddr; -} - -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static inline struct in6_addr *__tcp_v6_rcv_saddr(const struct sock *sk) -{ - return likely(sk->sk_state != TCP_TIME_WAIT) ? - &inet6_sk(sk)->rcv_saddr : &tcptw_sk(sk)->tw_v6_rcv_saddr; -} - -static inline struct in6_addr *tcp_v6_rcv_saddr(const struct sock *sk) -{ - return sk->sk_family == AF_INET6 ? __tcp_v6_rcv_saddr(sk) : NULL; -} - -#define tcptw_sk_ipv6only(__sk) (tcptw_sk(__sk)->tw_v6_ipv6only) - -static inline int tcp_v6_ipv6only(const struct sock *sk) -{ - return likely(sk->sk_state != TCP_TIME_WAIT) ? - ipv6_only_sock(sk) : tcptw_sk_ipv6only(sk); -} -#else -# define __tcp_v6_rcv_saddr(__sk) NULL -# define tcp_v6_rcv_saddr(__sk) NULL -# define tcptw_sk_ipv6only(__sk) 0 -# define tcp_v6_ipv6only(__sk) 0 -#endif +#include <linux/seq_file.h> -extern kmem_cache_t *tcp_timewait_cachep; - -static inline void tcp_tw_put(struct tcp_tw_bucket *tw) -{ - if (atomic_dec_and_test(&tw->tw_refcnt)) { -#ifdef INET_REFCNT_DEBUG - printk(KERN_DEBUG "tw_bucket %p released\n", tw); -#endif - kmem_cache_free(tcp_timewait_cachep, tw); - } -} +extern struct inet_hashinfo tcp_hashinfo; extern atomic_t tcp_orphan_count; -extern int tcp_tw_count; extern void tcp_time_wait(struct sock *sk, int state, int timeo); -extern void tcp_tw_deschedule(struct tcp_tw_bucket *tw); - - -/* Socket demux engine toys. */ -#ifdef __BIG_ENDIAN -#define TCP_COMBINED_PORTS(__sport, __dport) \ - (((__u32)(__sport)<<16) | (__u32)(__dport)) -#else /* __LITTLE_ENDIAN */ -#define TCP_COMBINED_PORTS(__sport, __dport) \ - (((__u32)(__dport)<<16) | (__u32)(__sport)) -#endif - -#if (BITS_PER_LONG == 64) -#ifdef __BIG_ENDIAN -#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr) \ - __u64 __name = (((__u64)(__saddr))<<32)|((__u64)(__daddr)); -#else /* __LITTLE_ENDIAN */ -#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr) \ - __u64 __name = (((__u64)(__daddr))<<32)|((__u64)(__saddr)); -#endif /* __BIG_ENDIAN */ -#define TCP_IPV4_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\ - (((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie)) && \ - ((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports)) && \ - (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) -#define TCP_IPV4_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\ - (((*((__u64 *)&(tcptw_sk(__sk)->tw_daddr))) == (__cookie)) && \ - ((*((__u32 *)&(tcptw_sk(__sk)->tw_dport))) == (__ports)) && \ - (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) -#else /* 32-bit arch */ -#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr) -#define TCP_IPV4_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\ - ((inet_sk(__sk)->daddr == (__saddr)) && \ - (inet_sk(__sk)->rcv_saddr == (__daddr)) && \ - ((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports)) && \ - (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) -#define TCP_IPV4_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\ - ((tcptw_sk(__sk)->tw_daddr == (__saddr)) && \ - (tcptw_sk(__sk)->tw_rcv_saddr == (__daddr)) && \ - ((*((__u32 *)&(tcptw_sk(__sk)->tw_dport))) == (__ports)) && \ - (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) -#endif /* 64-bit arch */ - -#define TCP_IPV6_MATCH(__sk, __saddr, __daddr, __ports, __dif) \ - (((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports)) && \ - ((__sk)->sk_family == AF_INET6) && \ - ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr)) && \ - ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \ - (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) - -/* These can have wildcards, don't try too hard. */ -static __inline__ int tcp_lhashfn(unsigned short num) -{ - return num & (TCP_LHTABLE_SIZE - 1); -} - -static __inline__ int tcp_sk_listen_hashfn(struct sock *sk) -{ - return tcp_lhashfn(inet_sk(sk)->num); -} #define MAX_TCP_HEADER (128 + MAX_HEADER) @@ -478,33 +147,6 @@ static __inline__ int tcp_sk_listen_hashfn(struct sock *sk) * timestamps. It must be less than * minimal timewait lifetime. */ - -#define TCP_TW_RECYCLE_SLOTS_LOG 5 -#define TCP_TW_RECYCLE_SLOTS (1<<TCP_TW_RECYCLE_SLOTS_LOG) - -/* If time > 4sec, it is "slow" path, no recycling is required, - so that we select tick to get range about 4 seconds. - */ - -#if HZ <= 16 || HZ > 4096 -# error Unsupported: HZ <= 16 or HZ > 4096 -#elif HZ <= 32 -# define TCP_TW_RECYCLE_TICK (5+2-TCP_TW_RECYCLE_SLOTS_LOG) -#elif HZ <= 64 -# define TCP_TW_RECYCLE_TICK (6+2-TCP_TW_RECYCLE_SLOTS_LOG) -#elif HZ <= 128 -# define TCP_TW_RECYCLE_TICK (7+2-TCP_TW_RECYCLE_SLOTS_LOG) -#elif HZ <= 256 -# define TCP_TW_RECYCLE_TICK (8+2-TCP_TW_RECYCLE_SLOTS_LOG) -#elif HZ <= 512 -# define TCP_TW_RECYCLE_TICK (9+2-TCP_TW_RECYCLE_SLOTS_LOG) -#elif HZ <= 1024 -# define TCP_TW_RECYCLE_TICK (10+2-TCP_TW_RECYCLE_SLOTS_LOG) -#elif HZ <= 2048 -# define TCP_TW_RECYCLE_TICK (11+2-TCP_TW_RECYCLE_SLOTS_LOG) -#else -# define TCP_TW_RECYCLE_TICK (12+2-TCP_TW_RECYCLE_SLOTS_LOG) -#endif /* * TCP option */ @@ -534,22 +176,18 @@ static __inline__ int tcp_sk_listen_hashfn(struct sock *sk) #define TCPOLEN_SACK_BASE_ALIGNED 4 #define TCPOLEN_SACK_PERBLOCK 8 -#define TCP_TIME_RETRANS 1 /* Retransmit timer */ -#define TCP_TIME_DACK 2 /* Delayed ack timer */ -#define TCP_TIME_PROBE0 3 /* Zero window probe timer */ -#define TCP_TIME_KEEPOPEN 4 /* Keepalive timer */ - /* Flags in tp->nonagle */ #define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */ #define TCP_NAGLE_CORK 2 /* Socket is corked */ #define TCP_NAGLE_PUSH 4 /* Cork is overriden for already queued data */ +extern struct inet_timewait_death_row tcp_death_row; + /* sysctl variables for tcp */ extern int sysctl_tcp_timestamps; extern int sysctl_tcp_window_scaling; extern int sysctl_tcp_sack; extern int sysctl_tcp_fin_timeout; -extern int sysctl_tcp_tw_recycle; extern int sysctl_tcp_keepalive_time; extern int sysctl_tcp_keepalive_probes; extern int sysctl_tcp_keepalive_intvl; @@ -564,7 +202,6 @@ extern int sysctl_tcp_stdurg; extern int sysctl_tcp_rfc1337; extern int sysctl_tcp_abort_on_overflow; extern int sysctl_tcp_max_orphans; -extern int sysctl_tcp_max_tw_buckets; extern int sysctl_tcp_fack; extern int sysctl_tcp_reordering; extern int sysctl_tcp_ecn; @@ -585,12 +222,6 @@ extern atomic_t tcp_memory_allocated; extern atomic_t tcp_sockets_allocated; extern int tcp_memory_pressure; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -#define TCP_INET_FAMILY(fam) ((fam) == AF_INET) -#else -#define TCP_INET_FAMILY(fam) 1 -#endif - /* * Pointers to address related TCP functions * (i.e. things that depend on the address family) @@ -671,9 +302,6 @@ DECLARE_SNMP_STAT(struct tcp_mib, tcp_statistics); #define TCP_ADD_STATS_BH(field, val) SNMP_ADD_STATS_BH(tcp_statistics, field, val) #define TCP_ADD_STATS_USER(field, val) SNMP_ADD_STATS_USER(tcp_statistics, field, val) -extern void tcp_put_port(struct sock *sk); -extern void tcp_inherit_port(struct sock *sk, struct sock *child); - extern void tcp_v4_err(struct sk_buff *skb, u32); extern void tcp_shutdown (struct sock *sk, int how); @@ -682,7 +310,7 @@ extern int tcp_v4_rcv(struct sk_buff *skb); extern int tcp_v4_remember_stamp(struct sock *sk); -extern int tcp_v4_tw_remember_stamp(struct tcp_tw_bucket *tw); +extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size); @@ -704,42 +332,22 @@ extern int tcp_rcv_established(struct sock *sk, extern void tcp_rcv_space_adjust(struct sock *sk); -enum tcp_ack_state_t -{ - TCP_ACK_SCHED = 1, - TCP_ACK_TIMER = 2, - TCP_ACK_PUSHED= 4 -}; - -static inline void tcp_schedule_ack(struct tcp_sock *tp) +static inline void tcp_dec_quickack_mode(struct sock *sk, + const unsigned int pkts) { - tp->ack.pending |= TCP_ACK_SCHED; -} - -static inline int tcp_ack_scheduled(struct tcp_sock *tp) -{ - return tp->ack.pending&TCP_ACK_SCHED; -} - -static __inline__ void tcp_dec_quickack_mode(struct tcp_sock *tp, unsigned int pkts) -{ - if (tp->ack.quick) { - if (pkts >= tp->ack.quick) { - tp->ack.quick = 0; + struct inet_connection_sock *icsk = inet_csk(sk); + if (icsk->icsk_ack.quick) { + if (pkts >= icsk->icsk_ack.quick) { + icsk->icsk_ack.quick = 0; /* Leaving quickack mode we deflate ATO. */ - tp->ack.ato = TCP_ATO_MIN; + icsk->icsk_ack.ato = TCP_ATO_MIN; } else - tp->ack.quick -= pkts; + icsk->icsk_ack.quick -= pkts; } } -extern void tcp_enter_quickack_mode(struct tcp_sock *tp); - -static __inline__ void tcp_delack_init(struct tcp_sock *tp) -{ - memset(&tp->ack, 0, sizeof(tp->ack)); -} +extern void tcp_enter_quickack_mode(struct sock *sk); static inline void tcp_clear_options(struct tcp_options_received *rx_opt) { @@ -755,10 +363,9 @@ enum tcp_tw_status }; -extern enum tcp_tw_status tcp_timewait_state_process(struct tcp_tw_bucket *tw, +extern enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, - struct tcphdr *th, - unsigned len); + const struct tcphdr *th); extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb, struct request_sock *req, @@ -773,7 +380,6 @@ extern void tcp_update_metrics(struct sock *sk); extern void tcp_close(struct sock *sk, long timeout); -extern struct sock * tcp_accept(struct sock *sk, int flags, int *err); extern unsigned int tcp_poll(struct file * file, struct socket *sock, struct poll_table_struct *wait); extern int tcp_getsockopt(struct sock *sk, int level, @@ -789,8 +395,6 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, size_t len, int nonblock, int flags, int *addr_len); -extern int tcp_listen_start(struct sock *sk); - extern void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab); @@ -799,11 +403,6 @@ extern void tcp_parse_options(struct sk_buff *skb, * TCP v4 functions exported for the inet6 API */ -extern int tcp_v4_rebuild_header(struct sock *sk); - -extern int tcp_v4_build_header(struct sock *sk, - struct sk_buff *skb); - extern void tcp_v4_send_check(struct sock *sk, struct tcphdr *th, int len, struct sk_buff *skb); @@ -872,18 +471,15 @@ extern void tcp_cwnd_application_limited(struct sock *sk); /* tcp_timer.c */ extern void tcp_init_xmit_timers(struct sock *); -extern void tcp_clear_xmit_timers(struct sock *); +static inline void tcp_clear_xmit_timers(struct sock *sk) +{ + inet_csk_clear_xmit_timers(sk); +} -extern void tcp_delete_keepalive_timer(struct sock *); -extern void tcp_reset_keepalive_timer(struct sock *, unsigned long); extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); extern unsigned int tcp_current_mss(struct sock *sk, int large); -#ifdef TCP_DEBUG -extern const char tcp_timer_bug_msg[]; -#endif - -/* tcp_diag.c */ +/* tcp.c */ extern void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ @@ -892,72 +488,6 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); -static inline void tcp_clear_xmit_timer(struct sock *sk, int what) -{ - struct tcp_sock *tp = tcp_sk(sk); - - switch (what) { - case TCP_TIME_RETRANS: - case TCP_TIME_PROBE0: - tp->pending = 0; - -#ifdef TCP_CLEAR_TIMERS - sk_stop_timer(sk, &tp->retransmit_timer); -#endif - break; - case TCP_TIME_DACK: - tp->ack.blocked = 0; - tp->ack.pending = 0; - -#ifdef TCP_CLEAR_TIMERS - sk_stop_timer(sk, &tp->delack_timer); -#endif - break; - default: -#ifdef TCP_DEBUG - printk(tcp_timer_bug_msg); -#endif - return; - }; - -} - -/* - * Reset the retransmission timer - */ -static inline void tcp_reset_xmit_timer(struct sock *sk, int what, unsigned long when) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (when > TCP_RTO_MAX) { -#ifdef TCP_DEBUG - printk(KERN_DEBUG "reset_xmit_timer sk=%p %d when=0x%lx, caller=%p\n", sk, what, when, current_text_addr()); -#endif - when = TCP_RTO_MAX; - } - - switch (what) { - case TCP_TIME_RETRANS: - case TCP_TIME_PROBE0: - tp->pending = what; - tp->timeout = jiffies+when; - sk_reset_timer(sk, &tp->retransmit_timer, tp->timeout); - break; - - case TCP_TIME_DACK: - tp->ack.pending |= TCP_ACK_TIMER; - tp->ack.timeout = jiffies+when; - sk_reset_timer(sk, &tp->delack_timer, tp->ack.timeout); - break; - - default: -#ifdef TCP_DEBUG - printk(tcp_timer_bug_msg); -#endif - return; - }; -} - /* Initialize RCV_MSS value. * RCV_MSS is an our guess about MSS used by the peer. * We haven't any direct information about the MSS. @@ -975,7 +505,7 @@ static inline void tcp_initialize_rcv_mss(struct sock *sk) hint = min(hint, TCP_MIN_RCVMSS); hint = max(hint, TCP_MIN_MSS); - tp->ack.rcv_mss = hint; + inet_csk(sk)->icsk_ack.rcv_mss = hint; } static __inline__ void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) @@ -1110,7 +640,8 @@ static inline void tcp_packets_out_inc(struct sock *sk, tp->packets_out += tcp_skb_pcount(skb); if (!orig) - tcp_reset_xmit_timer(sk, TCP_TIME_RETRANS, tp->rto); + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + inet_csk(sk)->icsk_rto, TCP_RTO_MAX); } static inline void tcp_packets_out_dec(struct tcp_sock *tp, @@ -1138,29 +669,29 @@ struct tcp_congestion_ops { struct list_head list; /* initialize private data (optional) */ - void (*init)(struct tcp_sock *tp); + void (*init)(struct sock *sk); /* cleanup private data (optional) */ - void (*release)(struct tcp_sock *tp); + void (*release)(struct sock *sk); /* return slow start threshold (required) */ - u32 (*ssthresh)(struct tcp_sock *tp); + u32 (*ssthresh)(struct sock *sk); /* lower bound for congestion window (optional) */ - u32 (*min_cwnd)(struct tcp_sock *tp); + u32 (*min_cwnd)(struct sock *sk); /* do new cwnd calculation (required) */ - void (*cong_avoid)(struct tcp_sock *tp, u32 ack, + void (*cong_avoid)(struct sock *sk, u32 ack, u32 rtt, u32 in_flight, int good_ack); /* round trip time sample per acked packet (optional) */ - void (*rtt_sample)(struct tcp_sock *tp, u32 usrtt); + void (*rtt_sample)(struct sock *sk, u32 usrtt); /* call before changing ca_state (optional) */ - void (*set_state)(struct tcp_sock *tp, u8 new_state); + void (*set_state)(struct sock *sk, u8 new_state); /* call when cwnd event occurs (optional) */ - void (*cwnd_event)(struct tcp_sock *tp, enum tcp_ca_event ev); + void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); /* new value of cwnd after loss (optional) */ - u32 (*undo_cwnd)(struct tcp_sock *tp); + u32 (*undo_cwnd)(struct sock *sk); /* hook for packet ack accounting (optional) */ - void (*pkts_acked)(struct tcp_sock *tp, u32 num_acked); - /* get info for tcp_diag (optional) */ - void (*get_info)(struct tcp_sock *tp, u32 ext, struct sk_buff *skb); + void (*pkts_acked)(struct sock *sk, u32 num_acked); + /* get info for inet_diag (optional) */ + void (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb); char name[TCP_CA_NAME_MAX]; struct module *owner; @@ -1169,30 +700,34 @@ struct tcp_congestion_ops { extern int tcp_register_congestion_control(struct tcp_congestion_ops *type); extern void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); -extern void tcp_init_congestion_control(struct tcp_sock *tp); -extern void tcp_cleanup_congestion_control(struct tcp_sock *tp); +extern void tcp_init_congestion_control(struct sock *sk); +extern void tcp_cleanup_congestion_control(struct sock *sk); extern int tcp_set_default_congestion_control(const char *name); extern void tcp_get_default_congestion_control(char *name); -extern int tcp_set_congestion_control(struct tcp_sock *tp, const char *name); +extern int tcp_set_congestion_control(struct sock *sk, const char *name); extern struct tcp_congestion_ops tcp_init_congestion_ops; -extern u32 tcp_reno_ssthresh(struct tcp_sock *tp); -extern void tcp_reno_cong_avoid(struct tcp_sock *tp, u32 ack, +extern u32 tcp_reno_ssthresh(struct sock *sk); +extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 rtt, u32 in_flight, int flag); -extern u32 tcp_reno_min_cwnd(struct tcp_sock *tp); +extern u32 tcp_reno_min_cwnd(struct sock *sk); extern struct tcp_congestion_ops tcp_reno; -static inline void tcp_set_ca_state(struct tcp_sock *tp, u8 ca_state) +static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state) { - if (tp->ca_ops->set_state) - tp->ca_ops->set_state(tp, ca_state); - tp->ca_state = ca_state; + struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_ca_ops->set_state) + icsk->icsk_ca_ops->set_state(sk, ca_state); + icsk->icsk_ca_state = ca_state; } -static inline void tcp_ca_event(struct tcp_sock *tp, enum tcp_ca_event event) +static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { - if (tp->ca_ops->cwnd_event) - tp->ca_ops->cwnd_event(tp, event); + const struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_ca_ops->cwnd_event) + icsk->icsk_ca_ops->cwnd_event(sk, event); } /* This determines how many packets are "in the network" to the best @@ -1218,9 +753,10 @@ static __inline__ unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) * The exception is rate halving phase, when cwnd is decreasing towards * ssthresh. */ -static inline __u32 tcp_current_ssthresh(struct tcp_sock *tp) +static inline __u32 tcp_current_ssthresh(const struct sock *sk) { - if ((1<<tp->ca_state)&(TCPF_CA_CWR|TCPF_CA_Recovery)) + const struct tcp_sock *tp = tcp_sk(sk); + if ((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_CWR | TCPF_CA_Recovery)) return tp->snd_ssthresh; else return max(tp->snd_ssthresh, @@ -1237,10 +773,13 @@ static inline void tcp_sync_left_out(struct tcp_sock *tp) } /* Set slow start threshold and cwnd not falling to slow start */ -static inline void __tcp_enter_cwr(struct tcp_sock *tp) +static inline void __tcp_enter_cwr(struct sock *sk) { + const struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + tp->undo_marker = 0; - tp->snd_ssthresh = tp->ca_ops->ssthresh(tp); + tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp) + 1U); tp->snd_cwnd_cnt = 0; @@ -1249,12 +788,14 @@ static inline void __tcp_enter_cwr(struct tcp_sock *tp) TCP_ECN_queue_cwr(tp); } -static inline void tcp_enter_cwr(struct tcp_sock *tp) +static inline void tcp_enter_cwr(struct sock *sk) { + struct tcp_sock *tp = tcp_sk(sk); + tp->prior_ssthresh = 0; - if (tp->ca_state < TCP_CA_CWR) { - __tcp_enter_cwr(tp); - tcp_set_ca_state(tp, TCP_CA_CWR); + if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { + __tcp_enter_cwr(sk); + tcp_set_ca_state(sk, TCP_CA_CWR); } } @@ -1277,8 +818,10 @@ static __inline__ void tcp_minshall_update(struct tcp_sock *tp, int mss, static __inline__ void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *tp) { - if (!tp->packets_out && !tp->pending) - tcp_reset_xmit_timer(sk, TCP_TIME_PROBE0, tp->rto); + const struct inet_connection_sock *icsk = inet_csk(sk); + if (!tp->packets_out && !icsk->icsk_pending) + inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, + icsk->icsk_rto, TCP_RTO_MAX); } static __inline__ void tcp_push_pending_frames(struct sock *sk, @@ -1297,9 +840,6 @@ static __inline__ void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq) tp->snd_wl1 = seq; } -extern void tcp_destroy_sock(struct sock *sk); - - /* * Calculate(/check) TCP checksum */ @@ -1359,8 +899,10 @@ static __inline__ int tcp_prequeue(struct sock *sk, struct sk_buff *skb) tp->ucopy.memory = 0; } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) { wake_up_interruptible(sk->sk_sleep); - if (!tcp_ack_scheduled(tp)) - tcp_reset_xmit_timer(sk, TCP_TIME_DACK, (3*TCP_RTO_MIN)/4); + if (!inet_csk_ack_scheduled(sk)) + inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, + (3 * TCP_RTO_MIN) / 4, + TCP_RTO_MAX); } return 1; } @@ -1393,9 +935,9 @@ static __inline__ void tcp_set_state(struct sock *sk, int state) TCP_INC_STATS(TCP_MIB_ESTABRESETS); sk->sk_prot->unhash(sk); - if (tcp_sk(sk)->bind_hash && + if (inet_csk(sk)->icsk_bind_hash && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) - tcp_put_port(sk); + inet_put_port(&tcp_hashinfo, sk); /* fall through */ default: if (oldstate==TCP_ESTABLISHED) @@ -1422,7 +964,7 @@ static __inline__ void tcp_done(struct sock *sk) if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); else - tcp_destroy_sock(sk); + inet_csk_destroy_sock(sk); } static __inline__ void tcp_sack_reset(struct tcp_options_received *rx_opt) @@ -1524,54 +1066,6 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk->sk_rcvbuf); } -static inline void tcp_acceptq_queue(struct sock *sk, struct request_sock *req, - struct sock *child) -{ - reqsk_queue_add(&tcp_sk(sk)->accept_queue, req, sk, child); -} - -static inline void -tcp_synq_removed(struct sock *sk, struct request_sock *req) -{ - if (reqsk_queue_removed(&tcp_sk(sk)->accept_queue, req) == 0) - tcp_delete_keepalive_timer(sk); -} - -static inline void tcp_synq_added(struct sock *sk) -{ - if (reqsk_queue_added(&tcp_sk(sk)->accept_queue) == 0) - tcp_reset_keepalive_timer(sk, TCP_TIMEOUT_INIT); -} - -static inline int tcp_synq_len(struct sock *sk) -{ - return reqsk_queue_len(&tcp_sk(sk)->accept_queue); -} - -static inline int tcp_synq_young(struct sock *sk) -{ - return reqsk_queue_len_young(&tcp_sk(sk)->accept_queue); -} - -static inline int tcp_synq_is_full(struct sock *sk) -{ - return reqsk_queue_is_full(&tcp_sk(sk)->accept_queue); -} - -static inline void tcp_synq_unlink(struct tcp_sock *tp, struct request_sock *req, - struct request_sock **prev) -{ - reqsk_queue_unlink(&tp->accept_queue, req, prev); -} - -static inline void tcp_synq_drop(struct sock *sk, struct request_sock *req, - struct request_sock **prev) -{ - tcp_synq_unlink(tcp_sk(sk), req, prev); - tcp_synq_removed(sk, req); - reqsk_free(req); -} - static __inline__ void tcp_openreq_init(struct request_sock *req, struct tcp_options_received *rx_opt, struct sk_buff *skb) @@ -1593,27 +1087,6 @@ static __inline__ void tcp_openreq_init(struct request_sock *req, extern void tcp_enter_memory_pressure(void); -extern void tcp_listen_wlock(void); - -/* - We may sleep inside this lock. - * - If sleeping is not required (or called from BH), - * use plain read_(un)lock(&tcp_lhash_lock). - */ - -static inline void tcp_listen_lock(void) -{ - /* read_lock synchronizes to candidates to writers */ - read_lock(&tcp_lhash_lock); - atomic_inc(&tcp_lhash_users); - read_unlock(&tcp_lhash_lock); -} - -static inline void tcp_listen_unlock(void) -{ - if (atomic_dec_and_test(&tcp_lhash_users)) - wake_up(&tcp_lhash_wait); -} - static inline int keepalive_intvl_when(const struct tcp_sock *tp) { return tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl; @@ -1624,12 +1097,13 @@ static inline int keepalive_time_when(const struct tcp_sock *tp) return tp->keepalive_time ? : sysctl_tcp_keepalive_time; } -static inline int tcp_fin_time(const struct tcp_sock *tp) +static inline int tcp_fin_time(const struct sock *sk) { - int fin_timeout = tp->linger2 ? : sysctl_tcp_fin_timeout; + int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout; + const int rto = inet_csk(sk)->icsk_rto; - if (fin_timeout < (tp->rto<<2) - (tp->rto>>1)) - fin_timeout = (tp->rto<<2) - (tp->rto>>1); + if (fin_timeout < (rto << 2) - (rto >> 1)) + fin_timeout = (rto << 2) - (rto >> 1); return fin_timeout; } @@ -1658,15 +1132,6 @@ static inline int tcp_paws_check(const struct tcp_options_received *rx_opt, int return 1; } -static inline void tcp_v4_setup_caps(struct sock *sk, struct dst_entry *dst) -{ - sk->sk_route_caps = dst->dev->features; - if (sk->sk_route_caps & NETIF_F_TSO) { - if (sock_flag(sk, SOCK_NO_LARGESEND) || dst->header_len) - sk->sk_route_caps &= ~NETIF_F_TSO; - } -} - #define TCP_CHECK_TIMER(sk) do { } while (0) static inline int tcp_use_frto(const struct sock *sk) @@ -1718,4 +1183,16 @@ struct tcp_iter_state { extern int tcp_proc_register(struct tcp_seq_afinfo *afinfo); extern void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo); +extern struct request_sock_ops tcp_request_sock_ops; + +extern int tcp_v4_destroy_sock(struct sock *sk); + +#ifdef CONFIG_PROC_FS +extern int tcp4_proc_init(void); +extern void tcp4_proc_exit(void); +#endif + +extern void tcp_v4_init(struct net_proto_family *ops); +extern void tcp_init(void); + #endif /* _TCP_H */ diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index 64980ee8c92..c6b84397448 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -88,7 +88,7 @@ static inline void TCP_ECN_check_ce(struct tcp_sock *tp, struct sk_buff *skb) * it is surely retransmit. It is not in ECN RFC, * but Linux follows this rule. */ else if (INET_ECN_is_not_ect((TCP_SKB_CB(skb)->flags))) - tcp_enter_quickack_mode(tp); + tcp_enter_quickack_mode((struct sock *)tp); } } diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h new file mode 100644 index 00000000000..b9d4176b2d1 --- /dev/null +++ b/include/net/tcp_states.h @@ -0,0 +1,34 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions for the TCP protocol sk_state field. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _LINUX_TCP_STATES_H +#define _LINUX_TCP_STATES_H + +enum { + TCP_ESTABLISHED = 1, + TCP_SYN_SENT, + TCP_SYN_RECV, + TCP_FIN_WAIT1, + TCP_FIN_WAIT2, + TCP_TIME_WAIT, + TCP_CLOSE, + TCP_CLOSE_WAIT, + TCP_LAST_ACK, + TCP_LISTEN, + TCP_CLOSING, /* Now a valid state */ + + TCP_MAX_STATES /* Leave at the end! */ +}; + +#define TCP_STATE_MASK 0xF + +#endif /* _LINUX_TCP_STATES_H */ diff --git a/include/net/udp.h b/include/net/udp.h index ac229b761db..107b9d791a1 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -94,6 +94,11 @@ struct udp_iter_state { struct seq_operations seq_ops; }; +#ifdef CONFIG_PROC_FS extern int udp_proc_register(struct udp_seq_afinfo *afinfo); extern void udp_proc_unregister(struct udp_seq_afinfo *afinfo); + +extern int udp4_proc_init(void); +extern void udp4_proc_exit(void); +#endif #endif /* _UDP_H */ diff --git a/include/net/x25.h b/include/net/x25.h index 8b39b98876e..fee62ff8c19 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -175,7 +175,7 @@ extern void x25_kill_by_neigh(struct x25_neigh *); /* x25_dev.c */ extern void x25_send_frame(struct sk_buff *, struct x25_neigh *); -extern int x25_lapb_receive_frame(struct sk_buff *, struct net_device *, struct packet_type *); +extern int x25_lapb_receive_frame(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); extern void x25_establish_link(struct x25_neigh *); extern void x25_terminate_link(struct x25_neigh *); diff --git a/include/net/x25device.h b/include/net/x25device.h index d45ae883bd1..1a318374fae 100644 --- a/include/net/x25device.h +++ b/include/net/x25device.h @@ -8,7 +8,6 @@ static inline __be16 x25_type_trans(struct sk_buff *skb, struct net_device *dev) { skb->mac.raw = skb->data; - skb->input_dev = skb->dev = dev; skb->pkt_type = PACKET_HOST; return htons(ETH_P_X25); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 868ef88ef97..a9d0d8c5dfb 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -818,7 +818,6 @@ extern void xfrm6_init(void); extern void xfrm6_fini(void); extern void xfrm_state_init(void); extern void xfrm4_state_init(void); -extern void xfrm4_state_fini(void); extern void xfrm6_state_init(void); extern void xfrm6_state_fini(void); |