android/android_kernel_cmhtcleo
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

net: packported xt_qtaguid and xt_quota2 to support data usage.

Browse Source
This commit is contained in:
tytung 2011-12-10 00:00:42 +08:00
parent df93a2fc56
commit 99dbc5c163
225 changed files with 9087 additions and 2739 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
arch/arm/boot/compressed/decompress.c Normal file
View File

@ -0,0 +1,50 @@
#define _LINUX_STRING_H_
#include <linux/compiler.h> /* for inline */
#include <linux/types.h> /* for size_t */
#include <linux/stddef.h> /* for NULL */
#include <linux/linkage.h>
#include <asm/string.h>
extern unsigned long free_mem_ptr;
extern unsigned long free_mem_end_ptr;
extern void error(char *);
#define STATIC static
#define STATIC_RW_DATA /* non-static please */
#define ARCH_HAS_DECOMP_WDOG
/* Diagnostic functions */
#ifdef DEBUG
# define Assert(cond,msg) {if(!(cond)) error(msg);}
# define Trace(x) fprintf x
# define Tracev(x) {if (verbose) fprintf x ;}
# define Tracevv(x) {if (verbose>1) fprintf x ;}
# define Tracec(c,x) {if (verbose && (c)) fprintf x ;}
# define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;}
#else
# define Assert(cond,msg)
# define Trace(x)
# define Tracev(x)
# define Tracevv(x)
# define Tracec(c,x)
# define Tracecv(c,x)
#endif
#ifdef CONFIG_KERNEL_GZIP
#include "../../../../lib/decompress_inflate.c"
#endif
#ifdef CONFIG_KERNEL_BZIP2
#include "../../../../lib/decompress_bunzip2.c"
#endif
#ifdef CONFIG_KERNEL_LZMA
#include "../../../../lib/decompress_unlzma.c"
#endif
void do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x))
{
decompress(input, len, NULL, NULL, output, NULL, error);
}

348
arch/arm/boot/compressed/lib1funcs.S Normal file
View File

@ -0,0 +1,348 @@
/*
* linux/arch/arm/lib/lib1funcs.S: Optimized ARM division routines
*
* Author: Nicolas Pitre <nico@fluxnic.net>
* - contributed to gcc-3.4 on Sep 30, 2003
* - adapted for the Linux kernel on Oct 2, 2003
*/
/* Copyright 1995, 1996, 1998, 1999, 2000, 2003 Free Software Foundation, Inc.
This file 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, or (at your option) any
later version.
In addition to the permissions in the GNU General Public License, the
Free Software Foundation gives you unlimited permission to link the
compiled version of this file into combinations with other programs,
and to distribute those combinations without any restriction coming
from the use of this file. (The General Public License restrictions
do apply in other respects; for example, they cover modification of
the file, and distribution when not linked into a combine
executable.)
This file is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; see the file COPYING. If not, write to
the Free Software Foundation, 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
#include <linux/linkage.h>
#include <asm/assembler.h>
.macro ARM_DIV_BODY dividend, divisor, result, curbit
#if __LINUX_ARM_ARCH__ >= 5
clz \curbit, \divisor
clz \result, \dividend
sub \result, \curbit, \result
mov \curbit, #1
mov \divisor, \divisor, lsl \result
mov \curbit, \curbit, lsl \result
mov \result, #0
#else
@ Initially shift the divisor left 3 bits if possible,
@ set curbit accordingly. This allows for curbit to be located
@ at the left end of each 4 bit nibbles in the division loop
@ to save one loop in most cases.
tst \divisor, #0xe0000000
moveq \divisor, \divisor, lsl #3
moveq \curbit, #8
movne \curbit, #1
@ Unless the divisor is very big, shift it up in multiples of
@ four bits, since this is the amount of unwinding in the main
@ division loop. Continue shifting until the divisor is
@ larger than the dividend.
1: cmp \divisor, #0x10000000
cmplo \divisor, \dividend
movlo \divisor, \divisor, lsl #4
movlo \curbit, \curbit, lsl #4
blo 1b
@ For very big divisors, we must shift it a bit at a time, or
@ we will be in danger of overflowing.
1: cmp \divisor, #0x80000000
cmplo \divisor, \dividend
movlo \divisor, \divisor, lsl #1
movlo \curbit, \curbit, lsl #1
blo 1b
mov \result, #0
#endif
@ Division loop
1: cmp \dividend, \divisor
subhs \dividend, \dividend, \divisor
orrhs \result, \result, \curbit
cmp \dividend, \divisor, lsr #1
subhs \dividend, \dividend, \divisor, lsr #1
orrhs \result, \result, \curbit, lsr #1
cmp \dividend, \divisor, lsr #2
subhs \dividend, \dividend, \divisor, lsr #2
orrhs \result, \result, \curbit, lsr #2
cmp \dividend, \divisor, lsr #3
subhs \dividend, \dividend, \divisor, lsr #3
orrhs \result, \result, \curbit, lsr #3
cmp \dividend, #0 @ Early termination?
movnes \curbit, \curbit, lsr #4 @ No, any more bits to do?
movne \divisor, \divisor, lsr #4
bne 1b
.endm
.macro ARM_DIV2_ORDER divisor, order
#if __LINUX_ARM_ARCH__ >= 5
clz \order, \divisor
rsb \order, \order, #31
#else
cmp \divisor, #(1 << 16)
movhs \divisor, \divisor, lsr #16
movhs \order, #16
movlo \order, #0
cmp \divisor, #(1 << 8)
movhs \divisor, \divisor, lsr #8
addhs \order, \order, #8
cmp \divisor, #(1 << 4)
movhs \divisor, \divisor, lsr #4
addhs \order, \order, #4
cmp \divisor, #(1 << 2)
addhi \order, \order, #3
addls \order, \order, \divisor, lsr #1
#endif
.endm
.macro ARM_MOD_BODY dividend, divisor, order, spare
#if __LINUX_ARM_ARCH__ >= 5
clz \order, \divisor
clz \spare, \dividend
sub \order, \order, \spare
mov \divisor, \divisor, lsl \order
#else
mov \order, #0
@ Unless the divisor is very big, shift it up in multiples of
@ four bits, since this is the amount of unwinding in the main
@ division loop. Continue shifting until the divisor is
@ larger than the dividend.
1: cmp \divisor, #0x10000000
cmplo \divisor, \dividend
movlo \divisor, \divisor, lsl #4
addlo \order, \order, #4
blo 1b
@ For very big divisors, we must shift it a bit at a time, or
@ we will be in danger of overflowing.
1: cmp \divisor, #0x80000000
cmplo \divisor, \dividend
movlo \divisor, \divisor, lsl #1
addlo \order, \order, #1
blo 1b
#endif
@ Perform all needed substractions to keep only the reminder.
@ Do comparisons in batch of 4 first.
subs \order, \order, #3 @ yes, 3 is intended here
blt 2f
1: cmp \dividend, \divisor
subhs \dividend, \dividend, \divisor
cmp \dividend, \divisor, lsr #1
subhs \dividend, \dividend, \divisor, lsr #1
cmp \dividend, \divisor, lsr #2
subhs \dividend, \dividend, \divisor, lsr #2
cmp \dividend, \divisor, lsr #3
subhs \dividend, \dividend, \divisor, lsr #3
cmp \dividend, #1
mov \divisor, \divisor, lsr #4
subges \order, \order, #4
bge 1b
tst \order, #3
teqne \dividend, #0
beq 5f
@ Either 1, 2 or 3 comparison/substractions are left.
2: cmn \order, #2
blt 4f
beq 3f
cmp \dividend, \divisor
subhs \dividend, \dividend, \divisor
mov \divisor, \divisor, lsr #1
3: cmp \dividend, \divisor
subhs \dividend, \dividend, \divisor
mov \divisor, \divisor, lsr #1
4: cmp \dividend, \divisor
subhs \dividend, \dividend, \divisor
5:
.endm
ENTRY(__udivsi3)
ENTRY(__aeabi_uidiv)
subs r2, r1, #1
moveq pc, lr
bcc Ldiv0
cmp r0, r1
bls 11f
tst r1, r2
beq 12f
ARM_DIV_BODY r0, r1, r2, r3
mov r0, r2
mov pc, lr
11: moveq r0, #1
movne r0, #0
mov pc, lr
12: ARM_DIV2_ORDER r1, r2
mov r0, r0, lsr r2
mov pc, lr
ENDPROC(__udivsi3)
ENDPROC(__aeabi_uidiv)
ENTRY(__umodsi3)
subs r2, r1, #1 @ compare divisor with 1
bcc Ldiv0
cmpne r0, r1 @ compare dividend with divisor
moveq r0, #0
tsthi r1, r2 @ see if divisor is power of 2
andeq r0, r0, r2
movls pc, lr
ARM_MOD_BODY r0, r1, r2, r3
mov pc, lr
ENDPROC(__umodsi3)
ENTRY(__divsi3)
ENTRY(__aeabi_idiv)
cmp r1, #0
eor ip, r0, r1 @ save the sign of the result.
beq Ldiv0
rsbmi r1, r1, #0 @ loops below use unsigned.
subs r2, r1, #1 @ division by 1 or -1 ?
beq 10f
movs r3, r0
rsbmi r3, r0, #0 @ positive dividend value
cmp r3, r1
bls 11f
tst r1, r2 @ divisor is power of 2 ?
beq 12f
ARM_DIV_BODY r3, r1, r0, r2
cmp ip, #0
rsbmi r0, r0, #0
mov pc, lr
10: teq ip, r0 @ same sign ?
rsbmi r0, r0, #0
mov pc, lr
11: movlo r0, #0
moveq r0, ip, asr #31
orreq r0, r0, #1
mov pc, lr
12: ARM_DIV2_ORDER r1, r2
cmp ip, #0
mov r0, r3, lsr r2
rsbmi r0, r0, #0
mov pc, lr
ENDPROC(__divsi3)
ENDPROC(__aeabi_idiv)
ENTRY(__modsi3)
cmp r1, #0
beq Ldiv0
rsbmi r1, r1, #0 @ loops below use unsigned.
movs ip, r0 @ preserve sign of dividend
rsbmi r0, r0, #0 @ if negative make positive
subs r2, r1, #1 @ compare divisor with 1
cmpne r0, r1 @ compare dividend with divisor
moveq r0, #0
tsthi r1, r2 @ see if divisor is power of 2
andeq r0, r0, r2
bls 10f
ARM_MOD_BODY r0, r1, r2, r3
10: cmp ip, #0
rsbmi r0, r0, #0
mov pc, lr
ENDPROC(__modsi3)
#ifdef CONFIG_AEABI
ENTRY(__aeabi_uidivmod)
stmfd sp!, {r0, r1, ip, lr}
bl __aeabi_uidiv
ldmfd sp!, {r1, r2, ip, lr}
mul r3, r0, r2
sub r1, r1, r3
mov pc, lr
ENDPROC(__aeabi_uidivmod)
ENTRY(__aeabi_idivmod)
stmfd sp!, {r0, r1, ip, lr}
bl __aeabi_idiv
ldmfd sp!, {r1, r2, ip, lr}
mul r3, r0, r2
sub r1, r1, r3
mov pc, lr
ENDPROC(__aeabi_idivmod)
#endif
Ldiv0:
str lr, [sp, #-8]!
bl __div0
mov r0, #0 @ About as wrong as it could be.
ldr pc, [sp], #8

276
arch/arm/include/asm/atomic.h
View File

@ -40,12 +40,12 @@ static inline void atomic_add(int i, atomic_t *v)
int result;
__asm__ __volatile__("@ atomic_add\n"
"1: ldrex %0, [%2]\n"
" add %0, %0, %3\n"
" strex %1, %0, [%2]\n"
"1: ldrex %0, [%3]\n"
" add %0, %0, %4\n"
" strex %1, %0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
: "r" (&v->counter), "Ir" (i)
: "cc");
}
@ -58,12 +58,12 @@ static inline int atomic_add_return(int i, atomic_t *v)
smp_mb();
__asm__ __volatile__("@ atomic_add_return\n"
"1: ldrex %0, [%2]\n"
" add %0, %0, %3\n"
" strex %1, %0, [%2]\n"
"1: ldrex %0, [%3]\n"
" add %0, %0, %4\n"
" strex %1, %0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
: "r" (&v->counter), "Ir" (i)
: "cc");
@ -78,12 +78,12 @@ static inline void atomic_sub(int i, atomic_t *v)
int result;
__asm__ __volatile__("@ atomic_sub\n"
"1: ldrex %0, [%2]\n"
" sub %0, %0, %3\n"
" strex %1, %0, [%2]\n"
"1: ldrex %0, [%3]\n"
" sub %0, %0, %4\n"
" strex %1, %0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
: "r" (&v->counter), "Ir" (i)
: "cc");
}
@ -96,12 +96,12 @@ static inline int atomic_sub_return(int i, atomic_t *v)
smp_mb();
__asm__ __volatile__("@ atomic_sub_return\n"
"1: ldrex %0, [%2]\n"
" sub %0, %0, %3\n"
" strex %1, %0, [%2]\n"
"1: ldrex %0, [%3]\n"
" sub %0, %0, %4\n"
" strex %1, %0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
: "r" (&v->counter), "Ir" (i)
: "cc");
@ -118,11 +118,11 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
do {
__asm__ __volatile__("@ atomic_cmpxchg\n"
"ldrex %1, [%2]\n"
"ldrex %1, [%3]\n"
"mov %0, #0\n"
"teq %1, %3\n"
"strexeq %0, %4, [%2]\n"
: "=&r" (res), "=&r" (oldval)
"teq %1, %4\n"
"strexeq %0, %5, [%3]\n"
: "=&r" (res), "=&r" (oldval), "+Qo" (ptr->counter)
: "r" (&ptr->counter), "Ir" (old), "r" (new)
: "cc");
} while (res);
@ -137,12 +137,12 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
unsigned long tmp, tmp2;
__asm__ __volatile__("@ atomic_clear_mask\n"
"1: ldrex %0, [%2]\n"
" bic %0, %0, %3\n"
" strex %1, %0, [%2]\n"
"1: ldrex %0, [%3]\n"
" bic %0, %0, %4\n"
" strex %1, %0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (tmp), "=&r" (tmp2)
: "=&r" (tmp), "=&r" (tmp2), "+Qo" (*addr)
: "r" (addr), "Ir" (mask)
: "cc");
}
@ -235,6 +235,234 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
#define smp_mb__before_atomic_inc() smp_mb()
#define smp_mb__after_atomic_inc() smp_mb()
#ifndef CONFIG_GENERIC_ATOMIC64
typedef struct {
u64 __aligned(8) counter;
} atomic64_t;
#define ATOMIC64_INIT(i) { (i) }
static inline u64 atomic64_read(atomic64_t *v)
{
u64 result;
__asm__ __volatile__("@ atomic64_read\n"
" ldrexd %0, %H0, [%1]"
: "=&r" (result)
: "r" (&v->counter)
);
return result;
}
static inline void atomic64_set(atomic64_t *v, u64 i)
{
u64 tmp;
__asm__ __volatile__("@ atomic64_set\n"
"1: ldrexd %0, %H0, [%1]\n"
" strexd %0, %2, %H2, [%1]\n"
" teq %0, #0\n"
" bne 1b"
: "=&r" (tmp)
: "r" (&v->counter), "r" (i)
: "cc");
}
static inline void atomic64_add(u64 i, atomic64_t *v)
{
u64 result;
unsigned long tmp;
__asm__ __volatile__("@ atomic64_add\n"
"1: ldrexd %0, %H0, [%2]\n"
" adds %0, %0, %3\n"
" adc %H0, %H0, %H3\n"
" strexd %1, %0, %H0, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "r" (&v->counter), "r" (i)
: "cc");
}
static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
{
u64 result;
unsigned long tmp;
smp_mb();
__asm__ __volatile__("@ atomic64_add_return\n"
"1: ldrexd %0, %H0, [%2]\n"
" adds %0, %0, %3\n"
" adc %H0, %H0, %H3\n"
" strexd %1, %0, %H0, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "r" (&v->counter), "r" (i)
: "cc");
smp_mb();
return result;
}
static inline void atomic64_sub(u64 i, atomic64_t *v)
{
u64 result;
unsigned long tmp;
__asm__ __volatile__("@ atomic64_sub\n"
"1: ldrexd %0, %H0, [%2]\n"
" subs %0, %0, %3\n"
" sbc %H0, %H0, %H3\n"
" strexd %1, %0, %H0, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "r" (&v->counter), "r" (i)
: "cc");
}
static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
{
u64 result;
unsigned long tmp;
smp_mb();
__asm__ __volatile__("@ atomic64_sub_return\n"
"1: ldrexd %0, %H0, [%2]\n"
" subs %0, %0, %3\n"
" sbc %H0, %H0, %H3\n"
" strexd %1, %0, %H0, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "r" (&v->counter), "r" (i)
: "cc");
smp_mb();
return result;
}
static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
{
u64 oldval;
unsigned long res;
smp_mb();
do {
__asm__ __volatile__("@ atomic64_cmpxchg\n"
"ldrexd %1, %H1, [%2]\n"
"mov %0, #0\n"
"teq %1, %3\n"
"teqeq %H1, %H3\n"
"strexdeq %0, %4, %H4, [%2]"
: "=&r" (res), "=&r" (oldval)
: "r" (&ptr->counter), "r" (old), "r" (new)
: "cc");
} while (res);
smp_mb();
return oldval;
}
static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
{
u64 result;
unsigned long tmp;
smp_mb();
__asm__ __volatile__("@ atomic64_xchg\n"
"1: ldrexd %0, %H0, [%2]\n"
" strexd %1, %3, %H3, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "r" (&ptr->counter), "r" (new)
: "cc");
smp_mb();
return result;
}
static inline u64 atomic64_dec_if_positive(atomic64_t *v)
{
u64 result;
unsigned long tmp;
smp_mb();
__asm__ __volatile__("@ atomic64_dec_if_positive\n"
"1: ldrexd %0, %H0, [%2]\n"
" subs %0, %0, #1\n"
" sbc %H0, %H0, #0\n"
" teq %H0, #0\n"
" bmi 2f\n"
" strexd %1, %0, %H0, [%2]\n"
" teq %1, #0\n"
" bne 1b\n"
"2:"
: "=&r" (result), "=&r" (tmp)
: "r" (&v->counter)
: "cc");
smp_mb();
return result;
}
static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
{
u64 val;
unsigned long tmp;
int ret = 1;
smp_mb();
__asm__ __volatile__("@ atomic64_add_unless\n"
"1: ldrexd %0, %H0, [%3]\n"
" teq %0, %4\n"
" teqeq %H0, %H4\n"
" moveq %1, #0\n"
" beq 2f\n"
" adds %0, %0, %5\n"
" adc %H0, %H0, %H5\n"
" strexd %2, %0, %H0, [%3]\n"
" teq %2, #0\n"
" bne 1b\n"
"2:"
: "=&r" (val), "=&r" (ret), "=&r" (tmp)
: "r" (&v->counter), "r" (u), "r" (a)
: "cc");
if (ret)
smp_mb();
return ret;
}
#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
#define atomic64_inc(v) atomic64_add(1LL, (v))
#define atomic64_inc_return(v) atomic64_add_return(1LL, (v))
#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0)
#define atomic64_dec(v) atomic64_sub(1LL, (v))
#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v))
#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL)
#else /* !CONFIG_GENERIC_ATOMIC64 */
#include <asm-generic/atomic64.h>
#endif
#include <asm-generic/atomic-long.h>
#endif
#endif

5
drivers/net/ppp_deflate.c
View File

@ -306,7 +306,7 @@ static void z_decomp_free(void *arg)
if (state) {
zlib_inflateEnd(&state->strm);
vfree(state->strm.workspace);
kfree(state->strm.workspace);
kfree(state);
}
}
@ -346,7 +346,8 @@ static void *z_decomp_alloc(unsigned char *options, int opt_len)
state->w_size = w_size;
state->strm.next_out = NULL;
state->strm.workspace = vmalloc(zlib_inflate_workspacesize());
state->strm.workspace = kmalloc(zlib_inflate_workspacesize(),
GFP_KERNEL|__GFP_REPEAT);
if (state->strm.workspace == NULL)
goto out_free;

6
drivers/net/pppol2tp.c
View File

@ -756,6 +756,7 @@ static int pppol2tp_recv_core(struct sock *sock, struct sk_buff *skb)
/* Try to dequeue as many skbs from reorder_q as we can. */
pppol2tp_recv_dequeue(session);
sock_put(sock);
return 0;
@ -772,6 +773,7 @@ discard_bad_csum:
UDP_INC_STATS_USER(&init_net, UDP_MIB_INERRORS, 0);
tunnel->stats.rx_errors++;
kfree_skb(skb);
sock_put(sock);
return 0;
@ -1178,7 +1180,8 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
/* Calculate UDP checksum if configured to do so */
if (sk_tun->sk_no_check == UDP_CSUM_NOXMIT)
skb->ip_summed = CHECKSUM_NONE;
else if (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) {
else if ((skb_dst(skb) && skb_dst(skb)->dev) &&
(!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM))) {
skb->ip_summed = CHECKSUM_COMPLETE;
csum = skb_checksum(skb, 0, udp_len, 0);
uh->check = csum_tcpudp_magic(inet->saddr, inet->daddr,
@ -1657,6 +1660,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
if (tunnel_sock == NULL)
goto end;
sock_hold(tunnel_sock);
tunnel = tunnel_sock->sk_user_data;
} else {
tunnel = pppol2tp_tunnel_find(sock_net(sk), sp->pppol2tp.s_tunnel);

95
drivers/net/pppolac.c
View File

@ -15,12 +15,15 @@
*/
/* This driver handles L2TP data packets between a UDP socket and a PPP channel.
* To keep things simple, only one session per socket is permitted. Packets are
* sent via the socket, so it must keep connected to the same address. One must
* not set sequencing in ICCN but let LNS controll it. Currently this driver
* only works on IPv4 due to the lack of UDP encapsulation support in IPv6. */
* The socket must keep connected, and only one session per socket is permitted.
* Sequencing of outgoing packets is controlled by LNS. Incoming packets with
* sequences are reordered within a sliding window of one second. Currently
* reordering only happens when a packet is received. It is done for simplicity
* since no additional locks or threads are required. This driver only works on
* IPv4 due to the lack of UDP encapsulation support in IPv6. */
#include <linux/module.h>
#include <linux/jiffies.h>
#include <linux/workqueue.h>
#include <linux/skbuff.h>
#include <linux/file.h>
@ -53,14 +56,28 @@ static inline union unaligned *unaligned(void *ptr)
return (union unaligned *)ptr;
}
struct meta {
__u32 sequence;
__u32 timestamp;
};
static inline struct meta *skb_meta(struct sk_buff *skb)
{
return (struct meta *)skb->cb;
}
/******************************************************************************/
static int pppolac_recv_core(struct sock *sk_udp, struct sk_buff *skb)
{
struct sock *sk = (struct sock *)sk_udp->sk_user_data;
struct pppolac_opt *opt = &pppox_sk(sk)->proto.lac;
struct meta *meta = skb_meta(skb);
__u32 now = jiffies;
__u8 bits;
__u8 *ptr;
/* Drop the packet if it is too short. */
/* Drop the packet if L2TP header is missing. */
if (skb->len < sizeof(struct udphdr) + 6)
goto drop;
@ -99,9 +116,12 @@ static int pppolac_recv_core(struct sock *sk_udp, struct sk_buff *skb)
if (unaligned(ptr)->u32 != opt->local)
goto drop;
/* Check the sequence if it is present. According to RFC 2661 section
* 5.4, the only thing to do is to update opt->sequencing. */
opt->sequencing = bits & L2TP_SEQUENCE_BIT;
/* Check the sequence if it is present. */
if (bits & L2TP_SEQUENCE_BIT) {
meta->sequence = ptr[4] << 8 | ptr[5];
if ((__s16)(meta->sequence - opt->recv_sequence) < 0)
goto drop;
}
/* Skip PPP address and control if they are present. */
if (skb->len >= 2 && skb->data[0] == PPP_ADDR &&
@ -112,7 +132,54 @@ static int pppolac_recv_core(struct sock *sk_udp, struct sk_buff *skb)
if (skb->len >= 1 && skb->data[0] & 1)
skb_push(skb, 1)[0] = 0;
/* Finally, deliver the packet to PPP channel. */
/* Drop the packet if PPP protocol is missing. */
if (skb->len < 2)
goto drop;
/* Perform reordering if sequencing is enabled. */
atomic_set(&opt->sequencing, bits & L2TP_SEQUENCE_BIT);
if (bits & L2TP_SEQUENCE_BIT) {
struct sk_buff *skb1;
/* Insert the packet into receive queue in order. */
skb_set_owner_r(skb, sk);
skb_queue_walk(&sk->sk_receive_queue, skb1) {
struct meta *meta1 = skb_meta(skb1);
__s16 order = meta->sequence - meta1->sequence;
if (order == 0)
goto drop;
if (order < 0) {
meta->timestamp = meta1->timestamp;
skb_insert(skb1, skb, &sk->sk_receive_queue);
skb = NULL;
break;
}
}
if (skb) {
meta->timestamp = now;
skb_queue_tail(&sk->sk_receive_queue, skb);
}
/* Remove packets from receive queue as long as
* 1. the receive buffer is full,
* 2. they are queued longer than one second, or
* 3. there are no missing packets before them. */
skb_queue_walk_safe(&sk->sk_receive_queue, skb, skb1) {
meta = skb_meta(skb);
if (atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
now - meta->timestamp < HZ &&
meta->sequence != opt->recv_sequence)
break;
skb_unlink(skb, &sk->sk_receive_queue);
opt->recv_sequence = (__u16)(meta->sequence + 1);
skb_orphan(skb);
ppp_input(&pppox_sk(sk)->chan, skb);
}
return NET_RX_SUCCESS;
}
/* Flush receive queue if sequencing is disabled. */
skb_queue_purge(&sk->sk_receive_queue);
skb_orphan(skb);
ppp_input(&pppox_sk(sk)->chan, skb);
return NET_RX_SUCCESS;
@ -163,14 +230,14 @@ static int pppolac_xmit(struct ppp_channel *chan, struct sk_buff *skb)
skb->data[1] = PPP_CTRL;
/* Install L2TP header. */
if (opt->sequencing) {
if (atomic_read(&opt->sequencing)) {
skb_push(skb, 10);
skb->data[0] = L2TP_SEQUENCE_BIT;
skb->data[6] = opt->sequence >> 8;
skb->data[7] = opt->sequence;
skb->data[6] = opt->xmit_sequence >> 8;
skb->data[7] = opt->xmit_sequence;
skb->data[8] = 0;
skb->data[9] = 0;
opt->sequence++;
opt->xmit_sequence++;
} else {
skb_push(skb, 6);
skb->data[0] = 0;
@ -246,6 +313,7 @@ static int pppolac_connect(struct socket *sock, struct sockaddr *useraddr,
po->chan.mtu = PPP_MTU - 80;
po->proto.lac.local = unaligned(&addr->local)->u32;
po->proto.lac.remote = unaligned(&addr->remote)->u32;
atomic_set(&po->proto.lac.sequencing, 1);
po->proto.lac.backlog_rcv = sk_udp->sk_backlog_rcv;
error = ppp_register_channel(&po->chan);
@ -283,6 +351,7 @@ static int pppolac_release(struct socket *sock)
if (sk->sk_state != PPPOX_NONE) {
struct sock *sk_udp = (struct sock *)pppox_sk(sk)->chan.private;
lock_sock(sk_udp);
skb_queue_purge(&sk->sk_receive_queue);
pppox_unbind_sock(sk);
udp_sk(sk_udp)->encap_type = 0;
udp_sk(sk_udp)->encap_rcv = NULL;

87
drivers/net/pppopns.c
View File

@ -16,11 +16,14 @@
/* This driver handles PPTP data packets between a RAW socket and a PPP channel.
* The socket is created in the kernel space and connected to the same address
* of the control socket. To keep things simple, packets are always sent with
* sequence but without acknowledgement. This driver should work on both IPv4
* and IPv6. */
* of the control socket. Outgoing packets are always sent with sequences but
* without acknowledgements. Incoming packets with sequences are reordered
* within a sliding window of one second. Currently reordering only happens when
* a packet is received. It is done for simplicity since no additional locks or
* threads are required. This driver should work on both IPv4 and IPv6. */
#include <linux/module.h>
#include <linux/jiffies.h>
#include <linux/workqueue.h>
#include <linux/skbuff.h>
#include <linux/file.h>
@ -52,21 +55,35 @@ struct header {
__u32 sequence;
} __attribute__((packed));
struct meta {
__u32 sequence;
__u32 timestamp;
};
static inline struct meta *skb_meta(struct sk_buff *skb)
{
return (struct meta *)skb->cb;
}
/******************************************************************************/
static int pppopns_recv_core(struct sock *sk_raw, struct sk_buff *skb)
{
struct sock *sk = (struct sock *)sk_raw->sk_user_data;
struct pppopns_opt *opt = &pppox_sk(sk)->proto.pns;
struct meta *meta = skb_meta(skb);
__u32 now = jiffies;
struct header *hdr;
/* Skip transport header */
skb_pull(skb, skb_transport_header(skb) - skb->data);
/* Drop the packet if it is too short. */
/* Drop the packet if GRE header is missing. */
if (skb->len < GRE_HEADER_SIZE)
goto drop;
hdr = (struct header *)skb->data;
/* Check the header. */
hdr = (struct header *)skb->data;
if (hdr->type != PPTP_GRE_TYPE || hdr->call != opt->local ||
(hdr->bits & PPTP_GRE_BITS_MASK) != PPTP_GRE_BITS)
goto drop;
@ -81,6 +98,13 @@ static int pppopns_recv_core(struct sock *sk_raw, struct sk_buff *skb)
if (skb->len != ntohs(hdr->length))
goto drop;
/* Check the sequence if it is present. */
if (hdr->bits & PPTP_GRE_SEQ_BIT) {
meta->sequence = ntohl(hdr->sequence);
if ((__s32)(meta->sequence - opt->recv_sequence) < 0)
goto drop;
}
/* Skip PPP address and control if they are present. */
if (skb->len >= 2 && skb->data[0] == PPP_ADDR &&
skb->data[1] == PPP_CTRL)
@ -90,7 +114,53 @@ static int pppopns_recv_core(struct sock *sk_raw, struct sk_buff *skb)
if (skb->len >= 1 && skb->data[0] & 1)
skb_push(skb, 1)[0] = 0;
/* Finally, deliver the packet to PPP channel. */
/* Drop the packet if PPP protocol is missing. */
if (skb->len < 2)
goto drop;
/* Perform reordering if sequencing is enabled. */
if (hdr->bits & PPTP_GRE_SEQ_BIT) {
struct sk_buff *skb1;
/* Insert the packet into receive queue in order. */
skb_set_owner_r(skb, sk);
skb_queue_walk(&sk->sk_receive_queue, skb1) {
struct meta *meta1 = skb_meta(skb1);
__s32 order = meta->sequence - meta1->sequence;
if (order == 0)
goto drop;
if (order < 0) {
meta->timestamp = meta1->timestamp;
skb_insert(skb1, skb, &sk->sk_receive_queue);
skb = NULL;
break;
}
}
if (skb) {
meta->timestamp = now;
skb_queue_tail(&sk->sk_receive_queue, skb);
}
/* Remove packets from receive queue as long as
* 1. the receive buffer is full,
* 2. they are queued longer than one second, or
* 3. there are no missing packets before them. */
skb_queue_walk_safe(&sk->sk_receive_queue, skb, skb1) {
meta = skb_meta(skb);
if (atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
now - meta->timestamp < HZ &&
meta->sequence != opt->recv_sequence)
break;
skb_unlink(skb, &sk->sk_receive_queue);
opt->recv_sequence = meta->sequence + 1;
skb_orphan(skb);
ppp_input(&pppox_sk(sk)->chan, skb);
}
return NET_RX_SUCCESS;
}
/* Flush receive queue if sequencing is disabled. */
skb_queue_purge(&sk->sk_receive_queue);
skb_orphan(skb);
ppp_input(&pppox_sk(sk)->chan, skb);
return NET_RX_SUCCESS;
@ -151,8 +221,8 @@ static int pppopns_xmit(struct ppp_channel *chan, struct sk_buff *skb)
hdr->type = PPTP_GRE_TYPE;
hdr->length = htons(length);
hdr->call = opt->remote;
hdr->sequence = htonl(opt->sequence);
opt->sequence++;
hdr->sequence = htonl(opt->xmit_sequence);
opt->xmit_sequence++;
/* Now send the packet via the delivery queue. */
skb_set_owner_w(skb, sk_raw);
@ -261,6 +331,7 @@ static int pppopns_release(struct socket *sock)
if (sk->sk_state != PPPOX_NONE) {
struct sock *sk_raw = (struct sock *)pppox_sk(sk)->chan.private;
lock_sock(sk_raw);
skb_queue_purge(&sk->sk_receive_queue);
pppox_unbind_sock(sk);
sk_raw->sk_data_ready = pppox_sk(sk)->proto.pns.data_ready;
sk_raw->sk_backlog_rcv = pppox_sk(sk)->proto.pns.backlog_rcv;

2
include/linux/android_aid.h
View File

@ -22,5 +22,7 @@
#define AID_INET 3003
#define AID_NET_RAW 3004
#define AID_NET_ADMIN 3005
#define AID_NET_BW_STATS 3006 /* read bandwidth statistics */
#define AID_NET_BW_ACCT 3007 /* change bandwidth statistics accounting */
#endif

5
include/linux/err.h
View File

@ -34,6 +34,11 @@ static inline long IS_ERR(const void *ptr)
return IS_ERR_VALUE((unsigned long)ptr);
}
static inline long IS_ERR_OR_NULL(const void *ptr)
{
return !ptr || IS_ERR_VALUE((unsigned long)ptr);
}
/**
* ERR_CAST - Explicitly cast an error-valued pointer to another pointer type
* @ptr: The pointer to cast.

2
include/linux/if_packet.h
View File

@ -63,6 +63,7 @@ struct tpacket_auxdata
__u16 tp_mac;
__u16 tp_net;
__u16 tp_vlan_tci;
__u16 tp_padding;
};
/* Rx ring - header status */
@ -103,6 +104,7 @@ struct tpacket2_hdr
__u32 tp_sec;
__u32 tp_nsec;
__u16 tp_vlan_tci;
__u16 tp_padding;
};
#define TPACKET2_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket2_hdr)) + sizeof(struct sockaddr_ll))

22
include/linux/if_pppox.h
View File

@ -146,19 +146,21 @@ struct pppoe_opt {
};
struct pppolac_opt {
__u32 local;
__u32 remote;
__u16 sequence;
__u8 sequencing;
int (*backlog_rcv)(struct sock *sk_udp, struct sk_buff *skb);
__u32 local;
__u32 remote;
__u32 recv_sequence;
__u32 xmit_sequence;
atomic_t sequencing;
int (*backlog_rcv)(struct sock *sk_udp, struct sk_buff *skb);
};
struct pppopns_opt {
__u16 local;
__u16 remote;
__u32 sequence;
void (*data_ready)(struct sock *sk_raw, int length);
int (*backlog_rcv)(struct sock *sk_raw, struct sk_buff *skb);
__u16 local;
__u16 remote;
__u32 recv_sequence;
__u32 xmit_sequence;
void (*data_ready)(struct sock *sk_raw, int length);
int (*backlog_rcv)(struct sock *sk_raw, struct sk_buff *skb);
};
#include <net/sock.h>

11
include/linux/netdevice.h
View File

@ -1164,9 +1164,12 @@ static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen)
static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
unsigned int offset)
{
if (!pskb_may_pull(skb, hlen))
return NULL;
NAPI_GRO_CB(skb)->frag0 = NULL;
NAPI_GRO_CB(skb)->frag0_len = 0;
return pskb_may_pull(skb, hlen) ? skb->data + offset : NULL;
return skb->data + offset;
}
static inline void *skb_gro_mac_header(struct sk_buff *skb)
@ -1560,6 +1563,8 @@ extern void netif_carrier_on(struct net_device *dev);
extern void netif_carrier_off(struct net_device *dev);
extern void netif_notify_peers(struct net_device *dev);
/**
* netif_dormant_on - mark device as dormant.
* @dev: network device
@ -2013,6 +2018,10 @@ static inline u32 dev_ethtool_get_flags(struct net_device *dev)
return 0;
return dev->ethtool_ops->get_flags(dev);
}
#define MODULE_ALIAS_NETDEV(device) \
MODULE_ALIAS("netdev-" device)
#endif /* __KERNEL__ */
#endif /* _LINUX_NETDEVICE_H */

2
include/linux/netfilter/Kbuild
View File

@ -6,6 +6,7 @@ header-y += nfnetlink_queue.h
header-y += xt_CLASSIFY.h
header-y += xt_CONNMARK.h
header-y += xt_CONNSECMARK.h
header-y += xt_CT.h
header-y += xt_DSCP.h
header-y += xt_LED.h
header-y += xt_MARK.h
@ -15,6 +16,7 @@ header-y += xt_RATEEST.h
header-y += xt_SECMARK.h
header-y += xt_TCPMSS.h
header-y += xt_TCPOPTSTRIP.h
header-y += xt_TEE.h
header-y += xt_TPROXY.h
header-y += xt_comment.h
header-y += xt_connbytes.h

29
include/linux/netfilter/nf_conntrack_common.h
View File

@ -19,6 +19,9 @@ enum ip_conntrack_info
/* >= this indicates reply direction */
IP_CT_IS_REPLY,
IP_CT_ESTABLISHED_REPLY = IP_CT_ESTABLISHED + IP_CT_IS_REPLY,
IP_CT_RELATED_REPLY = IP_CT_RELATED + IP_CT_IS_REPLY,
IP_CT_NEW_REPLY = IP_CT_NEW + IP_CT_IS_REPLY,
/* Number of distinct IP_CT types (no NEW in reply dirn). */
IP_CT_NUMBER = IP_CT_IS_REPLY * 2 - 1
};
@ -73,6 +76,32 @@ enum ip_conntrack_status {
/* Connection has fixed timeout. */
IPS_FIXED_TIMEOUT_BIT = 10,
IPS_FIXED_TIMEOUT = (1 << IPS_FIXED_TIMEOUT_BIT),
/* Conntrack is a template */
IPS_TEMPLATE_BIT = 11,
IPS_TEMPLATE = (1 << IPS_TEMPLATE_BIT),
/* Conntrack is a fake untracked entry */
IPS_UNTRACKED_BIT = 12,
IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT),
};
/* Connection tracking event types */
enum ip_conntrack_events {
IPCT_NEW, /* new conntrack */
IPCT_RELATED, /* related conntrack */
IPCT_DESTROY, /* destroyed conntrack */
IPCT_REPLY, /* connection has seen two-way traffic */
IPCT_ASSURED, /* connection status has changed to assured */
IPCT_PROTOINFO, /* protocol information has changed */
IPCT_HELPER, /* new helper has been set */
IPCT_MARK, /* new mark has been set */
IPCT_NATSEQADJ, /* NAT is doing sequence adjustment */
IPCT_SECMARK, /* new security mark has been set */
};
enum ip_conntrack_expect_events {
IPEXP_NEW, /* new expectation */
};
#ifdef __KERNEL__

8
include/linux/netfilter/nfnetlink.h
View File

@ -75,11 +75,11 @@ struct nfnetlink_subsystem
extern int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n);
extern int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n);
extern int nfnetlink_has_listeners(unsigned int group);
extern int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group,
extern int nfnetlink_has_listeners(struct net *net, unsigned int group);
extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group,
int echo, gfp_t flags);
extern void nfnetlink_set_err(u32 pid, u32 group, int error);
extern int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags);
extern void nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error);
extern int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u_int32_t pid, int flags);
extern void nfnl_lock(void);
extern void nfnl_unlock(void);

74
include/linux/netfilter/x_tables.h
View File

@ -128,6 +128,7 @@ struct xt_counters_info
#define XT_INV_PROTO 0x40 /* Invert the sense of PROTO. */
#ifndef __KERNEL__
/* fn returns 0 to continue iteration */
#define XT_MATCH_ITERATE(type, e, fn, args...) \
({ \
@ -171,17 +172,37 @@ struct xt_counters_info
#define XT_ENTRY_ITERATE(type, entries, size, fn, args...) \
XT_ENTRY_ITERATE_CONTINUE(type, entries, size, 0, fn, args)
#endif /* !__KERNEL__ */
/* pos is normally a struct ipt_entry/ip6t_entry/etc. */
#define xt_entry_foreach(pos, ehead, esize) \
for ((pos) = (typeof(pos))(ehead); \
(pos) < (typeof(pos))((char *)(ehead) + (esize)); \
(pos) = (typeof(pos))((char *)(pos) + (pos)->next_offset))
/* can only be xt_entry_match, so no use of typeof here */
#define xt_ematch_foreach(pos, entry) \
for ((pos) = (struct xt_entry_match *)entry->elems; \
(pos) < (struct xt_entry_match *)((char *)(entry) + \
(entry)->target_offset); \
(pos) = (struct xt_entry_match *)((char *)(pos) + \
(pos)->u.match_size))
#ifdef __KERNEL__
#include <linux/netdevice.h>
#define xt_match_param xt_action_param
#define xt_target_param xt_action_param
/**
* struct xt_match_param - parameters for match extensions' match functions
* struct xt_action_param - parameters for matches/targets
*
* @match: the match extension
* @target: the target extension
* @matchinfo: per-match data
* @targetinfo: per-target data
* @in: input netdevice
* @out: output netdevice
* @match: struct xt_match through which this function was invoked
* @matchinfo: per-match data
* @fragoff: packet is a fragment, this is the data offset
* @thoff: position of transport header relative to skb->data
* @hook: hook number given packet came from
@ -189,10 +210,15 @@ struct xt_counters_info
* (helpful when match->family == NFPROTO_UNSPEC)
* @hotdrop: drop packet if we had inspection problems
*/
struct xt_match_param {
struct xt_action_param {
union {
const struct xt_match *match;
const struct xt_target *target;
};
union {
const void *matchinfo, *targinfo;
};
const struct net_device *in, *out;
const struct xt_match *match;
const void *matchinfo;
int fragoff;
unsigned int thoff;
unsigned int hooknum;
@ -212,6 +238,7 @@ struct xt_match_param {
* @hook_mask: via which hooks the new rule is reachable
*/
struct xt_mtchk_param {
struct net *net;
const char *table;
const void *entryinfo;
const struct xt_match *match;
@ -222,28 +249,12 @@ struct xt_mtchk_param {
/* Match destructor parameters */
struct xt_mtdtor_param {
struct net *net;
const struct xt_match *match;
void *matchinfo;
u_int8_t family;
};
/**
* struct xt_target_param - parameters for target extensions' target functions
*
* @hooknum: hook through which this target was invoked
* @target: struct xt_target through which this function was invoked
* @targinfo: per-target data
*
* Other fields see above.
*/
struct xt_target_param {
const struct net_device *in, *out;
const struct xt_target *target;
const void *targinfo;
unsigned int hooknum;
u_int8_t family;
};
/**
* struct xt_tgchk_param - parameters for target extensions'
* checkentry functions
@ -254,6 +265,7 @@ struct xt_target_param {
* Other fields see above.
*/
struct xt_tgchk_param {
struct net *net;
const char *table;
const void *entryinfo;
const struct xt_target *target;
@ -264,6 +276,7 @@ struct xt_tgchk_param {
/* Target destructor parameters */
struct xt_tgdtor_param {
struct net *net;
const struct xt_target *target;
void *targinfo;
u_int8_t family;
@ -282,10 +295,10 @@ struct xt_match
non-linear skb, using skb_header_pointer and
skb_ip_make_writable. */
bool (*match)(const struct sk_buff *skb,
const struct xt_match_param *);
const struct xt_action_param *);
/* Called when user tries to insert an entry of this type. */
bool (*checkentry)(const struct xt_mtchk_param *);
int (*checkentry)(const struct xt_mtchk_param *);
/* Called when entry of this type deleted. */
void (*destroy)(const struct xt_mtdtor_param *);
@ -320,7 +333,7 @@ struct xt_target
must now handle non-linear skbs, using skb_copy_bits and
skb_ip_make_writable. */
unsigned int (*target)(struct sk_buff *skb,
const struct xt_target_param *);
const struct xt_action_param *);
/* Called when user tries to insert an entry of this type:
hook_mask is a bitmask of hooks from which it can be
@ -384,6 +397,13 @@ struct xt_table_info
unsigned int hook_entry[NF_INET_NUMHOOKS];
unsigned int underflow[NF_INET_NUMHOOKS];
/*
* Number of user chains. Since tables cannot have loops, at most
* @stacksize jumps (number of user chains) can possibly be made.
*/
unsigned int stacksize;
unsigned int *stackptr;
void ***jumpstack;
/* ipt_entry tables: one per CPU */
/* Note : this field MUST be the last one, see XT_TABLE_INFO_SZ */
void *entries[1];
@ -419,6 +439,8 @@ extern struct xt_table_info *xt_replace_table(struct xt_table *table,
extern struct xt_match *xt_find_match(u8 af, const char *name, u8 revision);
extern struct xt_target *xt_find_target(u8 af, const char *name, u8 revision);
extern struct xt_match *xt_request_find_match(u8 af, const char *name,
u8 revision);
extern struct xt_target *xt_request_find_target(u8 af, const char *name,
u8 revision);
extern int xt_find_revision(u8 af, const char *name, u8 revision,

22
include/linux/netfilter/xt_CONNMARK.h
View File

@ -1,26 +1,6 @@
#ifndef _XT_CONNMARK_H_target
#define _XT_CONNMARK_H_target
#include <linux/types.h>
/* Copyright (C) 2002,2004 MARA Systems AB <http://www.marasystems.com>
* by Henrik Nordstrom <hno@marasystems.com>
*
* 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.
*/
enum {
XT_CONNMARK_SET = 0,
XT_CONNMARK_SAVE,
XT_CONNMARK_RESTORE
};
struct xt_connmark_tginfo1 {
__u32 ctmark, ctmask, nfmask;
__u8 mode;
};
#include <linux/netfilter/xt_connmark.h>
#endif /*_XT_CONNMARK_H_target*/

17
include/linux/netfilter/xt_CT.h Normal file
View File

@ -0,0 +1,17 @@
#ifndef _XT_CT_H
#define _XT_CT_H
#define XT_CT_NOTRACK 0x1
struct xt_ct_target_info {
u_int16_t flags;
u_int16_t zone;
u_int32_t ct_events;
u_int32_t exp_events;
char helper[16];
/* Used internally by the kernel */
struct nf_conn *ct __attribute__((aligned(8)));
};
#endif /* _XT_CT_H */

6
include/linux/netfilter/xt_MARK.h
View File

@ -1,10 +1,6 @@
#ifndef _XT_MARK_H_target
#define _XT_MARK_H_target
#include <linux/types.h>
struct xt_mark_tginfo2 {
__u32 mark, mask;
};
#include <linux/netfilter/xt_mark.h>
#endif /*_XT_MARK_H_target */

12
include/linux/netfilter/xt_TEE.h Normal file
View File

@ -0,0 +1,12 @@
#ifndef _XT_TEE_TARGET_H
#define _XT_TEE_TARGET_H
struct xt_tee_tginfo {
union nf_inet_addr gw;
char oif[16];
/* used internally by the kernel */
struct xt_tee_priv *priv __attribute__((aligned(8)));
};
#endif /* _XT_TEE_TARGET_H */

13
include/linux/netfilter/xt_TPROXY.h
View File

@ -1,5 +1,5 @@
#ifndef _XT_TPROXY_H_target
#define _XT_TPROXY_H_target
#ifndef _XT_TPROXY_H
#define _XT_TPROXY_H
/* TPROXY target is capable of marking the packet to perform
* redirection. We can get rid of that whenever we get support for
@ -11,4 +11,11 @@ struct xt_tproxy_target_info {
__be16 lport;
};
#endif /* _XT_TPROXY_H_target */
struct xt_tproxy_target_info_v1 {
u_int32_t mark_mask;
u_int32_t mark_value;
union nf_inet_addr laddr;
__be16 lport;
};
#endif /* _XT_TPROXY_H */

11
include/linux/netfilter/xt_connmark.h
View File

@ -12,6 +12,17 @@
* (at your option) any later version.
*/
enum {
XT_CONNMARK_SET = 0,
XT_CONNMARK_SAVE,
XT_CONNMARK_RESTORE
};
struct xt_connmark_tginfo1 {
__u32 ctmark, ctmask, nfmask;
__u8 mode;
};
struct xt_connmark_mtinfo1 {
__u32 mark, mask;
__u8 invert;

4
include/linux/netfilter/xt_mark.h
View File

@ -3,6 +3,10 @@
#include <linux/types.h>
struct xt_mark_tginfo2 {
__u32 mark, mask;
};
struct xt_mark_mtinfo1 {
__u32 mark, mask;
__u8 invert;

13
include/linux/netfilter/xt_qtaguid.h Normal file
View File

@ -0,0 +1,13 @@
#ifndef _XT_QTAGUID_MATCH_H
#define _XT_QTAGUID_MATCH_H
/* For now we just replace the xt_owner.
* FIXME: make iptables aware of qtaguid. */
#include <linux/netfilter/xt_owner.h>
#define XT_QTAGUID_UID XT_OWNER_UID
#define XT_QTAGUID_GID XT_OWNER_GID
#define XT_QTAGUID_SOCKET XT_OWNER_SOCKET
#define xt_qtaguid_match_info xt_owner_match_info
#endif /* _XT_QTAGUID_MATCH_H */

25
include/linux/netfilter/xt_quota2.h Normal file
View File

@ -0,0 +1,25 @@
#ifndef _XT_QUOTA_H
#define _XT_QUOTA_H
enum xt_quota_flags {
XT_QUOTA_INVERT = 1 << 0,
XT_QUOTA_GROW = 1 << 1,
XT_QUOTA_PACKET = 1 << 2,
XT_QUOTA_NO_CHANGE = 1 << 3,
XT_QUOTA_MASK = 0x0F,
};
struct xt_quota_counter;
struct xt_quota_mtinfo2 {
char name[15];
u_int8_t flags;
/* Comparison-invariant */
aligned_u64 quota;
/* Used internally by the kernel */
struct xt_quota_counter *master __attribute__((aligned(8)));
};
#endif /* _XT_QUOTA_H */

6
include/linux/netfilter/xt_socket.h
View File

@ -9,4 +9,10 @@ struct xt_socket_mtinfo1 {
__u8 flags;
};
void xt_socket_put_sk(struct sock *sk);
struct sock *xt_socket_get4_sk(const struct sk_buff *skb,
struct xt_action_param *par);
struct sock *xt_socket_get6_sk(const struct sk_buff *skb,
struct xt_action_param *par);
#endif /* _XT_SOCKET_H */

11
include/linux/netfilter_arp/arp_tables.h
View File

@ -214,9 +214,11 @@ static __inline__ struct arpt_entry_target *arpt_get_target(struct arpt_entry *e
return (void *)e + e->target_offset;
}
#ifndef __KERNEL__
/* fn returns 0 to continue iteration */
#define ARPT_ENTRY_ITERATE(entries, size, fn, args...) \
XT_ENTRY_ITERATE(struct arpt_entry, entries, size, fn, ## args)
#endif
/*
* Main firewall chains definitions and global var's definitions.
@ -264,6 +266,7 @@ struct arpt_error
.target.errorname = "ERROR", \
}
extern void *arpt_alloc_initial_table(const struct xt_table *);
extern struct xt_table *arpt_register_table(struct net *net,
const struct xt_table *table,
const struct arpt_replace *repl);
@ -297,14 +300,6 @@ compat_arpt_get_target(struct compat_arpt_entry *e)
#define COMPAT_ARPT_ALIGN(s) COMPAT_XT_ALIGN(s)
/* fn returns 0 to continue iteration */
#define COMPAT_ARPT_ENTRY_ITERATE(entries, size, fn, args...) \
XT_ENTRY_ITERATE(struct compat_arpt_entry, entries, size, fn, ## args)
#define COMPAT_ARPT_ENTRY_ITERATE_CONTINUE(entries, size, n, fn, args...) \
XT_ENTRY_ITERATE_CONTINUE(struct compat_arpt_entry, entries, size, n, \
fn, ## args)
#endif /* CONFIG_COMPAT */
#endif /*__KERNEL__*/
#endif /* _ARPTABLES_H */

2
include/linux/netfilter_bridge/ebtables.h
View File

@ -302,7 +302,7 @@ struct ebt_table
~(__alignof__(struct ebt_replace)-1))
extern struct ebt_table *ebt_register_table(struct net *net,
const struct ebt_table *table);
extern void ebt_unregister_table(struct ebt_table *table);
extern void ebt_unregister_table(struct net *net, struct ebt_table *table);
extern unsigned int ebt_do_table(unsigned int hook, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
struct ebt_table *table);

18
include/linux/netfilter_ipv4/ip_tables.h
View File

@ -228,6 +228,7 @@ ipt_get_target(struct ipt_entry *e)
return (void *)e + e->target_offset;
}
#ifndef __KERNEL__
/* fn returns 0 to continue iteration */
#define IPT_MATCH_ITERATE(e, fn, args...) \
XT_MATCH_ITERATE(struct ipt_entry, e, fn, ## args)
@ -235,6 +236,7 @@ ipt_get_target(struct ipt_entry *e)
/* fn returns 0 to continue iteration */
#define IPT_ENTRY_ITERATE(entries, size, fn, args...) \
XT_ENTRY_ITERATE(struct ipt_entry, entries, size, fn, ## args)
#endif
/*
* Main firewall chains definitions and global var's definitions.
@ -247,7 +249,7 @@ extern void ipt_init(void) __init;
extern struct xt_table *ipt_register_table(struct net *net,
const struct xt_table *table,
const struct ipt_replace *repl);
extern void ipt_unregister_table(struct xt_table *table);
extern void ipt_unregister_table(struct net *net, struct xt_table *table);
/* Standard entry. */
struct ipt_standard
@ -290,6 +292,7 @@ struct ipt_error
.target.errorname = "ERROR", \
}
extern void *ipt_alloc_initial_table(const struct xt_table *);
extern unsigned int ipt_do_table(struct sk_buff *skb,
unsigned int hook,
const struct net_device *in,
@ -321,19 +324,6 @@ compat_ipt_get_target(struct compat_ipt_entry *e)
#define COMPAT_IPT_ALIGN(s) COMPAT_XT_ALIGN(s)
/* fn returns 0 to continue iteration */
#define COMPAT_IPT_MATCH_ITERATE(e, fn, args...) \
XT_MATCH_ITERATE(struct compat_ipt_entry, e, fn, ## args)
/* fn returns 0 to continue iteration */
#define COMPAT_IPT_ENTRY_ITERATE(entries, size, fn, args...) \
XT_ENTRY_ITERATE(struct compat_ipt_entry, entries, size, fn, ## args)
/* fn returns 0 to continue iteration */
#define COMPAT_IPT_ENTRY_ITERATE_CONTINUE(entries, size, n, fn, args...) \
XT_ENTRY_ITERATE_CONTINUE(struct compat_ipt_entry, entries, size, n, \
fn, ## args)
#endif /* CONFIG_COMPAT */
#endif /*__KERNEL__*/
#endif /* _IPTABLES_H */

17
include/linux/netfilter_ipv6/ip6_tables.h
View File

@ -288,6 +288,7 @@ ip6t_get_target(struct ip6t_entry *e)
return (void *)e + e->target_offset;
}
#ifndef __KERNEL__
/* fn returns 0 to continue iteration */
#define IP6T_MATCH_ITERATE(e, fn, args...) \
XT_MATCH_ITERATE(struct ip6t_entry, e, fn, ## args)
@ -295,6 +296,7 @@ ip6t_get_target(struct ip6t_entry *e)
/* fn returns 0 to continue iteration */
#define IP6T_ENTRY_ITERATE(entries, size, fn, args...) \
XT_ENTRY_ITERATE(struct ip6t_entry, entries, size, fn, ## args)
#endif
/*
* Main firewall chains definitions and global var's definitions.
@ -305,10 +307,11 @@ ip6t_get_target(struct ip6t_entry *e)
#include <linux/init.h>
extern void ip6t_init(void) __init;
extern void *ip6t_alloc_initial_table(const struct xt_table *);
extern struct xt_table *ip6t_register_table(struct net *net,
const struct xt_table *table,
const struct ip6t_replace *repl);
extern void ip6t_unregister_table(struct xt_table *table);
extern void ip6t_unregister_table(struct net *net, struct xt_table *table);
extern unsigned int ip6t_do_table(struct sk_buff *skb,
unsigned int hook,
const struct net_device *in,
@ -349,18 +352,6 @@ compat_ip6t_get_target(struct compat_ip6t_entry *e)
#define COMPAT_IP6T_ALIGN(s) COMPAT_XT_ALIGN(s)
/* fn returns 0 to continue iteration */
#define COMPAT_IP6T_MATCH_ITERATE(e, fn, args...) \
XT_MATCH_ITERATE(struct compat_ip6t_entry, e, fn, ## args)
/* fn returns 0 to continue iteration */
#define COMPAT_IP6T_ENTRY_ITERATE(entries, size, fn, args...) \
XT_ENTRY_ITERATE(struct compat_ip6t_entry, entries, size, fn, ## args)
#define COMPAT_IP6T_ENTRY_ITERATE_CONTINUE(entries, size, n, fn, args...) \
XT_ENTRY_ITERATE_CONTINUE(struct compat_ip6t_entry, entries, size, n, \
fn, ## args)
#endif /* CONFIG_COMPAT */
#endif /*__KERNEL__*/
#endif /* _IP6_TABLES_H */

1
include/linux/notifier.h
View File

@ -201,6 +201,7 @@ static inline int notifier_to_errno(int ret)
#define NETDEV_PRE_UP 0x000D
#define NETDEV_BONDING_OLDTYPE 0x000E
#define NETDEV_BONDING_NEWTYPE 0x000F
#define NETDEV_NOTIFY_PEERS 0x0013
#define SYS_DOWN 0x0001 /* Notify of system down */
#define SYS_RESTART SYS_DOWN

165
include/linux/rcupdate.h
View File

@ -84,14 +84,122 @@ extern int rcu_scheduler_active;
} while (0)
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern struct lockdep_map rcu_lock_map;
# define rcu_read_acquire() \
lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
# define rcu_read_acquire() \
lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
# define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_)
#else
# define rcu_read_acquire() do { } while (0)
# define rcu_read_release() do { } while (0)
#endif
extern struct lockdep_map rcu_bh_lock_map;
# define rcu_read_acquire_bh() \
lock_acquire(&rcu_bh_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
# define rcu_read_release_bh() lock_release(&rcu_bh_lock_map, 1, _THIS_IP_)
extern struct lockdep_map rcu_sched_lock_map;
# define rcu_read_acquire_sched() \
lock_acquire(&rcu_sched_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
# define rcu_read_release_sched() \
lock_release(&rcu_sched_lock_map, 1, _THIS_IP_)
/**
* rcu_read_lock_held - might we be in RCU read-side critical section?
*
* If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
* an RCU read-side critical section. In absence of CONFIG_PROVE_LOCKING,
* this assumes we are in an RCU read-side critical section unless it can
* prove otherwise.
*/
static inline int rcu_read_lock_held(void)
{
if (debug_locks)
return lock_is_held(&rcu_lock_map);
return 1;
}
/**
* rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section?
*
* If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
* an RCU-bh read-side critical section. In absence of CONFIG_PROVE_LOCKING,
* this assumes we are in an RCU-bh read-side critical section unless it can
* prove otherwise.
*/
static inline int rcu_read_lock_bh_held(void)
{
if (debug_locks)
return lock_is_held(&rcu_bh_lock_map);
return 1;
}
/**
* rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section?
*
* If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in an
* RCU-sched read-side critical section. In absence of CONFIG_PROVE_LOCKING,
* this assumes we are in an RCU-sched read-side critical section unless it
* can prove otherwise. Note that disabling of preemption (including
* disabling irqs) counts as an RCU-sched read-side critical section.
*/
static inline int rcu_read_lock_sched_held(void)
{
int lockdep_opinion = 0;
if (debug_locks)
lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
return lockdep_opinion || preempt_count() != 0;
}
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
# define rcu_read_acquire() do { } while (0)
# define rcu_read_release() do { } while (0)
# define rcu_read_acquire_bh() do { } while (0)
# define rcu_read_release_bh() do { } while (0)
# define rcu_read_acquire_sched() do { } while (0)
# define rcu_read_release_sched() do { } while (0)
static inline int rcu_read_lock_held(void)
{
return 1;
}
static inline int rcu_read_lock_bh_held(void)
{
return 1;
}
static inline int rcu_read_lock_sched_held(void)
{
return preempt_count() != 0;
}
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
#ifdef CONFIG_PROVE_RCU
extern int rcu_my_thread_group_empty(void);
/**
* rcu_dereference_check - rcu_dereference with debug checking
*
* Do an rcu_dereference(), but check that the context is correct.
* For example, rcu_dereference_check(gp, rcu_read_lock_held()) to
* ensure that the rcu_dereference_check() executes within an RCU
* read-side critical section. It is also possible to check for
* locks being held, for example, by using lockdep_is_held().
*/
#define rcu_dereference_check(p, c) \
({ \
if (debug_locks && !(c)) \
lockdep_rcu_dereference(__FILE__, __LINE__); \
rcu_dereference_raw(p); \
})
#else /* #ifdef CONFIG_PROVE_RCU */
#define rcu_dereference_check(p, c) rcu_dereference_raw(p)
#endif /* #else #ifdef CONFIG_PROVE_RCU */
/**
* rcu_read_lock - mark the beginning of an RCU read-side critical section.
@ -166,7 +274,7 @@ static inline void rcu_read_lock_bh(void)
{
__rcu_read_lock_bh();
__acquire(RCU_BH);
rcu_read_acquire();
rcu_read_acquire_bh();
}
/*
@ -176,7 +284,7 @@ static inline void rcu_read_lock_bh(void)
*/
static inline void rcu_read_unlock_bh(void)
{
rcu_read_release();
rcu_read_release_bh();
__release(RCU_BH);
__rcu_read_unlock_bh();
}
@ -194,7 +302,7 @@ static inline void rcu_read_lock_sched(void)
{
preempt_disable();
__acquire(RCU_SCHED);
rcu_read_acquire();
rcu_read_acquire_sched();
}
/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
@ -211,7 +319,7 @@ static inline notrace void rcu_read_lock_sched_notrace(void)
*/
static inline void rcu_read_unlock_sched(void)
{
rcu_read_release();
rcu_read_release_sched();
__release(RCU_SCHED);
preempt_enable();
}
@ -225,21 +333,48 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
/**
* rcu_dereference - fetch an RCU-protected pointer in an
* RCU read-side critical section. This pointer may later
* be safely dereferenced.
* rcu_dereference_raw - fetch an RCU-protected pointer
*
* The caller must be within some flavor of RCU read-side critical
* section, or must be otherwise preventing the pointer from changing,
* for example, by holding an appropriate lock. This pointer may later
* be safely dereferenced. It is the caller's responsibility to have
* done the right thing, as this primitive does no checking of any kind.
*
* Inserts memory barriers on architectures that require them
* (currently only the Alpha), and, more importantly, documents
* exactly which pointers are protected by RCU.
*/
#define rcu_dereference(p) ({ \
#define rcu_dereference_raw(p) ({ \
typeof(p) _________p1 = ACCESS_ONCE(p); \
smp_read_barrier_depends(); \
(_________p1); \
})
/**
* rcu_dereference - fetch an RCU-protected pointer, checking for RCU
*
* Makes rcu_dereference_check() do the dirty work.
*/
#define rcu_dereference(p) \
rcu_dereference_check(p, rcu_read_lock_held())
/**
* rcu_dereference_bh - fetch an RCU-protected pointer, checking for RCU-bh
*
* Makes rcu_dereference_check() do the dirty work.
*/
#define rcu_dereference_bh(p) \
rcu_dereference_check(p, rcu_read_lock_bh_held())
/**
* rcu_dereference_sched - fetch RCU-protected pointer, checking for RCU-sched
*
* Makes rcu_dereference_check() do the dirty work.
*/
#define rcu_dereference_sched(p) \
rcu_dereference_check(p, rcu_read_lock_sched_held())
/**
* rcu_assign_pointer - assign (publicize) a pointer to a newly
* initialized structure that will be dereferenced by RCU read-side

3
include/linux/rtnetlink.h
View File

@ -754,6 +754,9 @@ extern void rtnl_lock(void);
extern void rtnl_unlock(void);
extern int rtnl_trylock(void);
extern int rtnl_is_locked(void);
#ifdef CONFIG_PROVE_LOCKING
extern int lockdep_rtnl_is_held(void);
#endif /* #ifdef CONFIG_PROVE_LOCKING */
extern void rtnetlink_init(void);
extern void __rtnl_unlock(void);

4
include/net/addrconf.h
View File

@ -177,7 +177,9 @@ extern int unregister_inet6addr_notifier(struct notifier_block *nb);
static inline struct inet6_dev *
__in6_dev_get(struct net_device *dev)
{
return rcu_dereference(dev->ip6_ptr);
return rcu_dereference_check(dev->ip6_ptr,
rcu_read_lock_held() ||
lockdep_rtnl_is_held());
}
static inline struct inet6_dev *

2
include/net/af_unix.h
View File

@ -10,6 +10,7 @@ extern void unix_inflight(struct file *fp);
extern void unix_notinflight(struct file *fp);
extern void unix_gc(void);
extern void wait_for_unix_gc(void);
extern struct sock *unix_get_socket(struct file *filp);
#define UNIX_HASH_SIZE 256
@ -56,6 +57,7 @@ struct unix_sock {
spinlock_t lock;
unsigned int gc_candidate : 1;
unsigned int gc_maybe_cycle : 1;
unsigned char recursion_level;
wait_queue_head_t peer_wait;
};
#define unix_sk(__sk) ((struct unix_sock *)__sk)

3
include/net/ip.h
View File

@ -341,8 +341,11 @@ enum ip_defrag_users
IP_DEFRAG_LOCAL_DELIVER,
IP_DEFRAG_CALL_RA_CHAIN,
IP_DEFRAG_CONNTRACK_IN,
__IP_DEFRAG_CONNTRACK_IN_END = IP_DEFRAG_CONNTRACK_IN + USHORT_MAX,
IP_DEFRAG_CONNTRACK_OUT,
__IP_DEFRAG_CONNTRACK_OUT_END = IP_DEFRAG_CONNTRACK_OUT + USHORT_MAX,
IP_DEFRAG_CONNTRACK_BRIDGE_IN,
__IP_DEFRAG_CONNTRACK_BRIDGE_IN = IP_DEFRAG_CONNTRACK_BRIDGE_IN + USHORT_MAX,
IP_DEFRAG_VS_IN,
IP_DEFRAG_VS_OUT,
IP_DEFRAG_VS_FWD

3
include/net/ipv6.h
View File

@ -357,8 +357,11 @@ struct inet_frag_queue;
enum ip6_defrag_users {
IP6_DEFRAG_LOCAL_DELIVER,
IP6_DEFRAG_CONNTRACK_IN,
__IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHORT_MAX,
IP6_DEFRAG_CONNTRACK_OUT,
__IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHORT_MAX,
IP6_DEFRAG_CONNTRACK_BRIDGE_IN,
__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHORT_MAX,
};
struct ip6_create_arg {

10
include/net/mac80211.h
View File

@ -908,6 +908,9 @@ enum ieee80211_tkip_key_type {
* @IEEE80211_HW_BEACON_FILTER:
* Hardware supports dropping of irrelevant beacon frames to
* avoid waking up cpu.
* @IEEE80211_HW_REPORTS_TX_ACK_STATUS:
* Hardware can provide ack status reports of Tx frames to
* the stack.
*/
enum ieee80211_hw_flags {
IEEE80211_HW_RX_INCLUDES_FCS = 1<<1,
@ -924,6 +927,7 @@ enum ieee80211_hw_flags {
IEEE80211_HW_SUPPORTS_DYNAMIC_PS = 1<<12,
IEEE80211_HW_MFP_CAPABLE = 1<<13,
IEEE80211_HW_BEACON_FILTER = 1<<14,
IEEE80211_HW_REPORTS_TX_ACK_STATUS = 1<<15,
};
/**
@ -1696,6 +1700,12 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb);
*/
void ieee80211_rx_irqsafe(struct ieee80211_hw *hw, struct sk_buff *skb);
/*
* The TX headroom reserved by mac80211 for its own tx_status functions.
* This is enough for the radiotap header.
*/
#define IEEE80211_TX_STATUS_HEADROOM 13
/**
* ieee80211_tx_status - transmit status callback
*

12
include/net/net_namespace.h
View File

@ -28,6 +28,10 @@ struct ctl_table_header;
struct net_generic;
struct sock;
#define NETDEV_HASHBITS 8
#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
struct net {
atomic_t count; /* To decided when the network
* namespace should be freed.
@ -38,7 +42,8 @@ struct net {
*/
#endif
struct list_head list; /* list of network namespaces */
struct work_struct work; /* work struct for freeing */
struct list_head cleanup_list; /* namespaces on death row */
struct list_head exit_list; /* Use only net_mutex */
struct proc_dir_entry *proc_net;
struct proc_dir_entry *proc_net_stat;
@ -76,6 +81,8 @@ struct net {
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
struct netns_ct ct;
#endif
struct sock *nfnl;
struct sock *nfnl_stash;
#endif
#ifdef CONFIG_XFRM
struct netns_xfrm xfrm;
@ -232,6 +239,9 @@ struct pernet_operations {
struct list_head list;
int (*init)(struct net *net);
void (*exit)(struct net *net);
void (*exit_batch)(struct list_head *net_exit_list);
int *id;
size_t size;
};
/*

22
include/net/netfilter/nf_conntrack.h
View File

@ -198,7 +198,8 @@ extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int null
extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size);
extern struct nf_conntrack_tuple_hash *
__nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple);
__nf_conntrack_find(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple);
extern void nf_conntrack_hash_insert(struct nf_conn *ct);
extern void nf_ct_delete_from_lists(struct nf_conn *ct);
@ -260,18 +261,29 @@ extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct,
u32 seq);
/* Fake conntrack entry for untracked connections */
extern struct nf_conn nf_conntrack_untracked;
static inline struct nf_conn *nf_ct_untracked_get(void)
{
extern struct nf_conn nf_conntrack_untracked;
return &nf_conntrack_untracked;
}
extern void nf_ct_untracked_status_or(unsigned long bits);
/* Iterate over all conntracks: if iter returns true, it's deleted. */
extern void
nf_ct_iterate_cleanup(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data);
extern void nf_conntrack_free(struct nf_conn *ct);
extern struct nf_conn *
nf_conntrack_alloc(struct net *net,
nf_conntrack_alloc(struct net *net, u16 zone,
const struct nf_conntrack_tuple *orig,
const struct nf_conntrack_tuple *repl,
gfp_t gfp);
static inline int nf_ct_is_template(const struct nf_conn *ct)
{
return test_bit(IPS_TEMPLATE_BIT, &ct->status);
}
/* It's confirmed if it is, or has been in the hash table. */
static inline int nf_ct_is_confirmed(struct nf_conn *ct)
{
@ -283,9 +295,9 @@ static inline int nf_ct_is_dying(struct nf_conn *ct)
return test_bit(IPS_DYING_BIT, &ct->status);
}
static inline int nf_ct_is_untracked(const struct sk_buff *skb)
static inline int nf_ct_is_untracked(const struct nf_conn *ct)
{
return (skb->nfct == &nf_conntrack_untracked.ct_general);
return test_bit(IPS_UNTRACKED_BIT, &ct->status);
}
extern int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp);

5
include/net/netfilter/nf_conntrack_core.h
View File

@ -49,7 +49,8 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
/* Find a connection corresponding to a tuple. */
extern struct nf_conntrack_tuple_hash *
nf_conntrack_find_get(struct net *net, const struct nf_conntrack_tuple *tuple);
nf_conntrack_find_get(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple);
extern int __nf_conntrack_confirm(struct sk_buff *skb);
@ -59,7 +60,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb)
struct nf_conn *ct = (struct nf_conn *)skb->nfct;
int ret = NF_ACCEPT;
if (ct && ct != &nf_conntrack_untracked) {
if (ct && !nf_ct_is_untracked(ct)) {
if (!nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct))
ret = __nf_conntrack_confirm(skb);
if (likely(ret == NF_ACCEPT))

59
include/net/netfilter/nf_conntrack_ecache.h
View File

@ -12,28 +12,12 @@
#include <linux/netfilter/nf_conntrack_tuple_common.h>
#include <net/netfilter/nf_conntrack_extend.h>
/* Connection tracking event types */
enum ip_conntrack_events
{
IPCT_NEW = 0, /* new conntrack */
IPCT_RELATED = 1, /* related conntrack */
IPCT_DESTROY = 2, /* destroyed conntrack */
IPCT_STATUS = 3, /* status has changed */
IPCT_PROTOINFO = 4, /* protocol information has changed */
IPCT_HELPER = 5, /* new helper has been set */
IPCT_MARK = 6, /* new mark has been set */
IPCT_NATSEQADJ = 7, /* NAT is doing sequence adjustment */
IPCT_SECMARK = 8, /* new security mark has been set */
};
enum ip_conntrack_expect_events {
IPEXP_NEW = 0, /* new expectation */
};
struct nf_conntrack_ecache {
unsigned long cache; /* bitops want long */
unsigned long missed; /* missed events */
u32 pid; /* netlink pid of destroyer */
unsigned long cache; /* bitops want long */
unsigned long missed; /* missed events */
u16 ctmask; /* bitmask of ct events to be delivered */
u16 expmask; /* bitmask of expect events to be delivered */
u32 pid; /* netlink pid of destroyer */
};
static inline struct nf_conntrack_ecache *
@ -43,14 +27,24 @@ nf_ct_ecache_find(const struct nf_conn *ct)
}
static inline struct nf_conntrack_ecache *
nf_ct_ecache_ext_add(struct nf_conn *ct, gfp_t gfp)
nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp)
{
struct net *net = nf_ct_net(ct);
struct nf_conntrack_ecache *e;
if (!net->ct.sysctl_events)
if (!ctmask && !expmask && net->ct.sysctl_events) {
ctmask = ~0;
expmask = ~0;
}
if (!ctmask && !expmask)
return NULL;
return nf_ct_ext_add(ct, NF_CT_EXT_ECACHE, gfp);
e = nf_ct_ext_add(ct, NF_CT_EXT_ECACHE, gfp);
if (e) {
e->ctmask = ctmask;
e->expmask = expmask;
}
return e;
};
#ifdef CONFIG_NF_CONNTRACK_EVENTS
@ -83,6 +77,9 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct)
if (e == NULL)
return;
if (!(e->ctmask & (1 << event)))
return;
set_bit(event, &e->cache);
}
@ -93,7 +90,6 @@ nf_conntrack_eventmask_report(unsigned int eventmask,
int report)
{
int ret = 0;
struct net *net = nf_ct_net(ct);
struct nf_ct_event_notifier *notify;
struct nf_conntrack_ecache *e;
@ -102,9 +98,6 @@ nf_conntrack_eventmask_report(unsigned int eventmask,
if (notify == NULL)
goto out_unlock;
if (!net->ct.sysctl_events)
goto out_unlock;
e = nf_ct_ecache_find(ct);
if (e == NULL)
goto out_unlock;
@ -118,6 +111,9 @@ nf_conntrack_eventmask_report(unsigned int eventmask,
/* This is a resent of a destroy event? If so, skip missed */
unsigned long missed = e->pid ? 0 : e->missed;
if (!((eventmask | missed) & e->ctmask))
goto out_unlock;
ret = notify->fcn(eventmask | missed, &item);
if (unlikely(ret < 0 || missed)) {
spin_lock_bh(&ct->lock);
@ -173,18 +169,19 @@ nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
u32 pid,
int report)
{
struct net *net = nf_ct_exp_net(exp);
struct nf_exp_event_notifier *notify;
struct nf_conntrack_ecache *e;
rcu_read_lock();
notify = rcu_dereference(nf_expect_event_cb);
if (notify == NULL)
goto out_unlock;
if (!net->ct.sysctl_events)
e = nf_ct_ecache_find(exp->master);
if (e == NULL)
goto out_unlock;
{
if (e->expmask & (1 << event)) {
struct nf_exp_event item = {
.exp = exp,
.pid = pid,

9
include/net/netfilter/nf_conntrack_expect.h
View File

@ -79,13 +79,16 @@ int nf_conntrack_expect_init(struct net *net);
void nf_conntrack_expect_fini(struct net *net);
struct nf_conntrack_expect *
__nf_ct_expect_find(struct net *net, const struct nf_conntrack_tuple *tuple);
__nf_ct_expect_find(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple);
struct nf_conntrack_expect *
nf_ct_expect_find_get(struct net *net, const struct nf_conntrack_tuple *tuple);
nf_ct_expect_find_get(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple);
struct nf_conntrack_expect *
nf_ct_find_expectation(struct net *net, const struct nf_conntrack_tuple *tuple);
nf_ct_find_expectation(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple);
void nf_ct_unlink_expect(struct nf_conntrack_expect *exp);
void nf_ct_remove_expectations(struct nf_conn *ct);

2
include/net/netfilter/nf_conntrack_extend.h
View File

@ -9,6 +9,7 @@ enum nf_ct_ext_id
NF_CT_EXT_NAT,
NF_CT_EXT_ACCT,
NF_CT_EXT_ECACHE,
NF_CT_EXT_ZONE,
NF_CT_EXT_NUM,
};
@ -16,6 +17,7 @@ enum nf_ct_ext_id
#define NF_CT_EXT_NAT_TYPE struct nf_conn_nat
#define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter
#define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache
#define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone
/* Extensions: optional stuff which isn't permanently in struct. */
struct nf_ct_ext {

8
include/net/netfilter/nf_conntrack_helper.h
View File

@ -41,14 +41,18 @@ struct nf_conntrack_helper
};
extern struct nf_conntrack_helper *
__nf_conntrack_helper_find_byname(const char *name);
__nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum);
extern struct nf_conntrack_helper *
nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum);
extern int nf_conntrack_helper_register(struct nf_conntrack_helper *);
extern void nf_conntrack_helper_unregister(struct nf_conntrack_helper *);
extern struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp);
extern int __nf_ct_try_assign_helper(struct nf_conn *ct, gfp_t flags);
extern int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
gfp_t flags);
extern void nf_ct_helper_destroy(struct nf_conn *ct);

4
include/net/netfilter/nf_conntrack_l4proto.h
View File

@ -50,8 +50,8 @@ struct nf_conntrack_l4proto
/* Called when a conntrack entry is destroyed */
void (*destroy)(struct nf_conn *ct);
int (*error)(struct net *net, struct sk_buff *skb, unsigned int dataoff,
enum ip_conntrack_info *ctinfo,
int (*error)(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
unsigned int dataoff, enum ip_conntrack_info *ctinfo,
u_int8_t pf, unsigned int hooknum);
/* Print out the per-protocol part of the tuple. Return like seq_* */

23
include/net/netfilter/nf_conntrack_zones.h Normal file
View File

@ -0,0 +1,23 @@
#ifndef _NF_CONNTRACK_ZONES_H
#define _NF_CONNTRACK_ZONES_H
#include <net/netfilter/nf_conntrack_extend.h>
#define NF_CT_DEFAULT_ZONE 0
struct nf_conntrack_zone {
u16 id;
};
static inline u16 nf_ct_zone(const struct nf_conn *ct)
{
#ifdef CONFIG_NF_CONNTRACK_ZONES
struct nf_conntrack_zone *nf_ct_zone;
nf_ct_zone = nf_ct_ext_find(ct, NF_CT_EXT_ZONE);
if (nf_ct_zone)
return nf_ct_zone->id;
#endif
return NF_CT_DEFAULT_ZONE;
}
#endif /* _NF_CONNTRACK_ZONES_H */

128
include/net/netfilter/nf_tproxy_core.h
View File

@ -8,25 +8,131 @@
#include <net/inet_sock.h>
#include <net/tcp.h>
#define NFT_LOOKUP_ANY 0
#define NFT_LOOKUP_LISTENER 1
#define NFT_LOOKUP_ESTABLISHED 2
/* look up and get a reference to a matching socket */
extern struct sock *
/* This function is used by the 'TPROXY' target and the 'socket'
* match. The following lookups are supported:
*
* Explicit TProxy target rule
* ===========================
*
* This is used when the user wants to intercept a connection matching
* an explicit iptables rule. In this case the sockets are assumed
* matching in preference order:
*
* - match: if there's a fully established connection matching the
* _packet_ tuple, it is returned, assuming the redirection
* already took place and we process a packet belonging to an
* established connection
*
* - match: if there's a listening socket matching the redirection
* (e.g. on-port & on-ip of the connection), it is returned,
* regardless if it was bound to 0.0.0.0 or an explicit
* address. The reasoning is that if there's an explicit rule, it
* does not really matter if the listener is bound to an interface
* or to 0. The user already stated that he wants redirection
* (since he added the rule).
*
* "socket" match based redirection (no specific rule)
* ===================================================
*
* There are connections with dynamic endpoints (e.g. FTP data
* connection) that the user is unable to add explicit rules
* for. These are taken care of by a generic "socket" rule. It is
* assumed that the proxy application is trusted to open such
* connections without explicit iptables rule (except of course the
* generic 'socket' rule). In this case the following sockets are
* matched in preference order:
*
* - match: if there's a fully established connection matching the
* _packet_ tuple
*
* - match: if there's a non-zero bound listener (possibly with a
* non-local address) We don't accept zero-bound listeners, since
* then local services could intercept traffic going through the
* box.
*
* Please note that there's an overlap between what a TPROXY target
* and a socket match will match. Normally if you have both rules the
* "socket" match will be the first one, effectively all packets
* belonging to established connections going through that one.
*/
static inline struct sock *
nf_tproxy_get_sock_v4(struct net *net, const u8 protocol,
const __be32 saddr, const __be32 daddr,
const __be16 sport, const __be16 dport,
const struct net_device *in, bool listening);
static inline void
nf_tproxy_put_sock(struct sock *sk)
const struct net_device *in, int lookup_type)
{
/* TIME_WAIT inet sockets have to be handled differently */
if ((sk->sk_protocol == IPPROTO_TCP) && (sk->sk_state == TCP_TIME_WAIT))
inet_twsk_put(inet_twsk(sk));
else
sock_put(sk);
struct sock *sk;
/* look up socket */
switch (protocol) {
case IPPROTO_TCP:
switch (lookup_type) {
case NFT_LOOKUP_ANY:
sk = __inet_lookup(net, &tcp_hashinfo,
saddr, sport, daddr, dport,
in->ifindex);
break;
case NFT_LOOKUP_LISTENER:
sk = inet_lookup_listener(net, &tcp_hashinfo,
daddr, dport,
in->ifindex);
/* NOTE: we return listeners even if bound to
* 0.0.0.0, those are filtered out in
* xt_socket, since xt_TPROXY needs 0 bound
* listeners too */
break;
case NFT_LOOKUP_ESTABLISHED:
sk = inet_lookup_established(net, &tcp_hashinfo,
saddr, sport, daddr, dport,
in->ifindex);
break;
default:
WARN_ON(1);
sk = NULL;
break;
}
break;
case IPPROTO_UDP:
sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
in->ifindex);
if (sk && lookup_type != NFT_LOOKUP_ANY) {
int connected = (sk->sk_state == TCP_ESTABLISHED);
int wildcard = (inet_sk(sk)->rcv_saddr == 0);
/* NOTE: we return listeners even if bound to
* 0.0.0.0, those are filtered out in
* xt_socket, since xt_TPROXY needs 0 bound
* listeners too */
if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) ||
(lookup_type == NFT_LOOKUP_LISTENER && connected)) {
sock_put(sk);
sk = NULL;
}
}
break;
default:
WARN_ON(1);
sk = NULL;
}
pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n",
protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk);
return sk;
}
/* assign a socket to the skb -- consumes sk */
int
void
nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk);
#endif

2
include/net/netlink.h
View File

@ -384,7 +384,7 @@ static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
*
* Returns the first attribute which matches the specified type.
*/
static inline struct nlattr *nlmsg_find_attr(struct nlmsghdr *nlh,
static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh,
int hdrlen, int attrtype)
{
return nla_find(nlmsg_attrdata(nlh, hdrlen),

1
include/net/sctp/command.h
View File

@ -107,6 +107,7 @@ typedef enum {
SCTP_CMD_T1_RETRAN, /* Mark for retransmission after T1 timeout */
SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */
SCTP_CMD_SEND_MSG, /* Send the whole use message */
SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */
SCTP_CMD_LAST
} sctp_verb_t;

1
include/net/sctp/sm.h
View File

@ -278,6 +278,7 @@ int sctp_do_sm(sctp_event_t event_type, sctp_subtype_t subtype,
/* 2nd level prototypes */
void sctp_generate_t3_rtx_event(unsigned long peer);
void sctp_generate_heartbeat_event(unsigned long peer);
void sctp_generate_proto_unreach_event(unsigned long peer);
void sctp_ootb_pkt_free(struct sctp_packet *);

6
include/net/sctp/structs.h
View File

@ -772,6 +772,7 @@ int sctp_user_addto_chunk(struct sctp_chunk *chunk, int off, int len,
struct iovec *data);
void sctp_chunk_free(struct sctp_chunk *);
void *sctp_addto_chunk(struct sctp_chunk *, int len, const void *data);
void *sctp_addto_chunk_fixed(struct sctp_chunk *, int len, const void *data);
struct sctp_chunk *sctp_chunkify(struct sk_buff *,
const struct sctp_association *,
struct sock *);
@ -987,7 +988,7 @@ struct sctp_transport {
int init_sent_count;
/* state : The current state of this destination,
* : i.e. SCTP_ACTIVE, SCTP_INACTIVE, SCTP_UNKOWN.
* : i.e. SCTP_ACTIVE, SCTP_INACTIVE, SCTP_UNKNOWN.
*/
int state;
@ -1007,6 +1008,9 @@ struct sctp_transport {
/* Heartbeat timer is per destination. */
struct timer_list hb_timer;
/* Timer to handle ICMP proto unreachable envets */
struct timer_list proto_unreach_timer;
/* Since we're using per-destination retransmission timers
* (see above), we're also using per-destination "transmitted"
* queues. This probably ought to be a private struct

20
include/net/secure_seq.h Normal file
View File

@ -0,0 +1,20 @@
#ifndef _NET_SECURE_SEQ
#define _NET_SECURE_SEQ
#include <linux/types.h>
extern __u32 secure_ip_id(__be32 daddr);
extern __u32 secure_ipv6_id(const __be32 daddr[4]);
extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
extern u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
__be16 dport);
extern __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
__be16 sport, __be16 dport);
extern __u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr,
__be16 sport, __be16 dport);
extern u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
__be16 sport, __be16 dport);
extern u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
__be16 sport, __be16 dport);
#endif /* _NET_SECURE_SEQ */

38
include/net/tcp.h
View File

@ -259,11 +259,21 @@ static inline int between(__u32 seq1, __u32 seq2, __u32 seq3)
return seq3 - seq2 >= seq1 - seq2;
}
static inline int tcp_too_many_orphans(struct sock *sk, int num)
static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
{
return (num > sysctl_tcp_max_orphans) ||
(sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]);
struct percpu_counter *ocp = sk->sk_prot->orphan_count;
int orphans = percpu_counter_read_positive(ocp);
if (orphans << shift > sysctl_tcp_max_orphans) {
orphans = percpu_counter_sum_positive(ocp);
if (orphans << shift > sysctl_tcp_max_orphans)
return true;
}
if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])
return true;
return false;
}
/* syncookies: remember time of last synqueue overflow */
@ -501,8 +511,22 @@ extern unsigned int tcp_current_mss(struct sock *sk);
/* Bound MSS / TSO packet size with the half of the window */
static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
{
if (tp->max_window && pktsize > (tp->max_window >> 1))
return max(tp->max_window >> 1, 68U - tp->tcp_header_len);
int cutoff;
/* When peer uses tiny windows, there is no use in packetizing
* to sub-MSS pieces for the sake of SWS or making sure there
* are enough packets in the pipe for fast recovery.
*
* On the other hand, for extremely large MSS devices, handling
* smaller than MSS windows in this way does make sense.
*/
if (tp->max_window >= 512)
cutoff = (tp->max_window >> 1);
else
cutoff = tp->max_window;
if (cutoff && pktsize > cutoff)
return max_t(int, cutoff, 68U - tp->tcp_header_len);
else
return pktsize;
}
@ -1260,7 +1284,7 @@ static inline struct sk_buff *tcp_write_queue_prev(struct sock *sk, struct sk_bu
skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp)
/* This function calculates a "timeout" which is equivalent to the timeout of a
* TCP connection after "boundary" unsucessful, exponentially backed-off
* TCP connection after "boundary" unsuccessful, exponentially backed-off
* retransmissions with an initial RTO of TCP_RTO_MIN.
*/
static inline bool retransmits_timed_out(struct sock *sk,

2
include/net/wimax.h
View File

@ -79,7 +79,7 @@
* drivers have to only report state changes due to external
* conditions.
*
* All API operations are 'atomic', serialized thorough a mutex in the
* All API operations are 'atomic', serialized through a mutex in the
* `struct wimax_dev`.
*
* EXPORTING TO USER SPACE THROUGH GENERIC NETLINK

4
include/net/x25.h
View File

@ -182,6 +182,10 @@ extern int sysctl_x25_clear_request_timeout;
extern int sysctl_x25_ack_holdback_timeout;
extern int sysctl_x25_forward;
extern int x25_parse_address_block(struct sk_buff *skb,
struct x25_address *called_addr,
struct x25_address *calling_addr);
extern int x25_addr_ntoa(unsigned char *, struct x25_address *,
struct x25_address *);
extern int x25_addr_aton(unsigned char *, struct x25_address *,

95
lib/md5.c Normal file
View File

@ -0,0 +1,95 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/cryptohash.h>
#define F1(x, y, z) (z ^ (x & (y ^ z)))
#define F2(x, y, z) F1(z, x, y)
#define F3(x, y, z) (x ^ y ^ z)
#define F4(x, y, z) (y ^ (x | ~z))
#define MD5STEP(f, w, x, y, z, in, s) \
(w += f(x, y, z) + in, w = (w<<s | w>>(32-s)) + x)
void md5_transform(__u32 *hash, __u32 const *in)
{
u32 a, b, c, d;
a = hash[0];
b = hash[1];
c = hash[2];
d = hash[3];
MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
hash[0] += a;
hash[1] += b;
hash[2] += c;
hash[3] += d;
}
EXPORT_SYMBOL(md5_transform);

3
net/ipv4/af_inet.c
View File

@ -477,6 +477,9 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
if (addr_len < sizeof(struct sockaddr_in))
goto out;
if (addr->sin_family != AF_INET)
goto out;
chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
/* Not specified by any standard per-se, however it breaks too

33
net/ipv4/devinet.c
View File

@ -54,7 +54,6 @@
#include <linux/sysctl.h>
#endif
#include <linux/kmod.h>
#include <linux/iface_stat.h>
#include <net/arp.h>
#include <net/ip.h>
@ -374,9 +373,6 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
rtmsg_ifa(RTM_NEWADDR, ifa, nlh, pid);
blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
/* Start persistent interface stat monitoring. Ignores if loopback. */
create_iface_stat(in_dev);
return 0;
}
@ -1036,6 +1032,21 @@ static inline bool inetdev_valid_mtu(unsigned mtu)
return mtu >= 68;
}
static void inetdev_send_gratuitous_arp(struct net_device *dev,
struct in_device *in_dev)
{
struct in_ifaddr *ifa = in_dev->ifa_list;
if (!ifa)
return;
arp_send(ARPOP_REQUEST, ETH_P_ARP,
ifa->ifa_address, dev,
ifa->ifa_address, NULL,
dev->dev_addr, NULL);
}
/* Called only under RTNL semaphore */
static int inetdev_event(struct notifier_block *this, unsigned long event,
@ -1088,16 +1099,12 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
ip_mc_up(in_dev);
/* fall through */
case NETDEV_CHANGEADDR:
if (!IN_DEV_ARP_NOTIFY(in_dev))
break;
/* fall through */
case NETDEV_NOTIFY_PEERS:
/* Send gratuitous ARP to notify of link change */
if (IN_DEV_ARP_NOTIFY(in_dev)) {
struct in_ifaddr *ifa = in_dev->ifa_list;
if (ifa)
arp_send(ARPOP_REQUEST, ETH_P_ARP,
ifa->ifa_address, dev,
ifa->ifa_address, NULL,
dev->dev_addr, NULL);
}
inetdev_send_gratuitous_arp(dev, in_dev);
break;
case NETDEV_DOWN:
ip_mc_down(in_dev);

5
net/ipv4/igmp.c
View File

@ -1899,8 +1899,9 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
err = -EADDRNOTAVAIL;
for (pmc=inet->mc_list; pmc; pmc=pmc->next) {
if (pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr
&& pmc->multi.imr_ifindex == imr.imr_ifindex)
if ((pmc->multi.imr_multiaddr.s_addr ==
imr.imr_multiaddr.s_addr) &&
(pmc->multi.imr_ifindex == imr.imr_ifindex))
break;
}
if (!pmc) { /* must have a prior join */

41
net/ipv4/inet_diag.c
View File

@ -436,7 +436,7 @@ static int valid_cc(const void *bc, int len, int cc)
return 0;
if (cc == len)
return 1;
if (op->yes < 4)
if (op->yes < 4 || op->yes & 3)
return 0;
len -= op->yes;
bc += op->yes;
@ -446,11 +446,11 @@ static int valid_cc(const void *bc, int len, int cc)
static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
{
const unsigned char *bc = bytecode;
const void *bc = bytecode;
int len = bytecode_len;
while (len > 0) {
struct inet_diag_bc_op *op = (struct inet_diag_bc_op *)bc;
const struct inet_diag_bc_op *op = bc;
//printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len);
switch (op->code) {
@ -461,22 +461,20 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
case INET_DIAG_BC_S_LE:
case INET_DIAG_BC_D_GE:
case INET_DIAG_BC_D_LE:
if (op->yes < 4 || op->yes > len + 4)
return -EINVAL;
case INET_DIAG_BC_JMP:
if (op->no < 4 || op->no > len + 4)
if (op->no < 4 || op->no > len + 4 || op->no & 3)
return -EINVAL;
if (op->no < len &&
!valid_cc(bytecode, bytecode_len, len - op->no))
return -EINVAL;
break;
case INET_DIAG_BC_NOP:
if (op->yes < 4 || op->yes > len + 4)
return -EINVAL;
break;
default:
return -EINVAL;
}
if (op->yes < 4 || op->yes > len + 4 || op->yes & 3)
return -EINVAL;
bc += op->yes;
len -= op->yes;
}
@ -489,9 +487,11 @@ static int inet_csk_diag_dump(struct sock *sk,
{
struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
struct inet_diag_entry entry;
struct rtattr *bc = (struct rtattr *)(r + 1);
const struct nlattr *bc = nlmsg_find_attr(cb->nlh,
sizeof(*r),
INET_DIAG_REQ_BYTECODE);
struct inet_sock *inet = inet_sk(sk);
entry.family = sk->sk_family;
@ -511,7 +511,7 @@ static int inet_csk_diag_dump(struct sock *sk,
entry.dport = ntohs(inet->dport);
entry.userlocks = sk->sk_userlocks;
if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry))
if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry))
return 0;
}
@ -526,9 +526,11 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
{
struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
struct inet_diag_entry entry;
struct rtattr *bc = (struct rtattr *)(r + 1);
const struct nlattr *bc = nlmsg_find_attr(cb->nlh,
sizeof(*r),
INET_DIAG_REQ_BYTECODE);
entry.family = tw->tw_family;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
@ -547,7 +549,7 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
entry.dport = ntohs(tw->tw_dport);
entry.userlocks = 0;
if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry))
if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry))
return 0;
}
@ -617,7 +619,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt;
struct rtattr *bc = NULL;
const struct nlattr *bc = NULL;
struct inet_sock *inet = inet_sk(sk);
int j, s_j;
int reqnum, s_reqnum;
@ -637,8 +639,9 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
if (!lopt || !lopt->qlen)
goto out;
if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
bc = (struct rtattr *)(r + 1);
if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
bc = nlmsg_find_attr(cb->nlh, sizeof(*r),
INET_DIAG_REQ_BYTECODE);
entry.sport = inet->num;
entry.userlocks = sk->sk_userlocks;
}
@ -671,8 +674,8 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
&ireq->rmt_addr;
entry.dport = ntohs(ireq->rmt_port);
if (!inet_diag_bc_run(RTA_DATA(bc),
RTA_PAYLOAD(bc), &entry))
if (!inet_diag_bc_run(nla_data(bc),
nla_len(bc), &entry))
continue;
}

1
net/ipv4/inet_hashtables.c
View File

@ -21,6 +21,7 @@
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/secure_seq.h>
#include <net/ip.h>
/*

1
net/ipv4/inetpeer.c
View File

@ -19,6 +19,7 @@
#include <linux/net.h>
#include <net/ip.h>
#include <net/inetpeer.h>
#include <net/secure_seq.h>
/*
* Theory of operations.

20
net/ipv4/ip_gre.c
View File

@ -1665,14 +1665,15 @@ static int __init ipgre_init(void)
printk(KERN_INFO "GRE over IPv4 tunneling driver\n");
if (inet_add_protocol(&ipgre_protocol, IPPROTO_GRE) < 0) {
printk(KERN_INFO "ipgre init: can't add protocol\n");
return -EAGAIN;
}
err = register_pernet_gen_device(&ipgre_net_id, &ipgre_net_ops);
if (err < 0)
goto gen_device_failed;
return err;
err = inet_add_protocol(&ipgre_protocol, IPPROTO_GRE);
if (err < 0) {
printk(KERN_INFO "ipgre init: can't add protocol\n");
goto add_proto_failed;
}
err = rtnl_link_register(&ipgre_link_ops);
if (err < 0)
@ -1688,9 +1689,9 @@ out:
tap_ops_failed:
rtnl_link_unregister(&ipgre_link_ops);
rtnl_link_failed:
unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops);
gen_device_failed:
inet_del_protocol(&ipgre_protocol, IPPROTO_GRE);
add_proto_failed:
unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops);
goto out;
}
@ -1698,9 +1699,9 @@ static void __exit ipgre_fini(void)
{
rtnl_link_unregister(&ipgre_tap_ops);
rtnl_link_unregister(&ipgre_link_ops);
unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops);
if (inet_del_protocol(&ipgre_protocol, IPPROTO_GRE) < 0)
printk(KERN_INFO "ipgre close: can't remove protocol\n");
unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops);
}
module_init(ipgre_init);
@ -1708,3 +1709,4 @@ module_exit(ipgre_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("gre");
MODULE_ALIAS_RTNL_LINK("gretap");
MODULE_ALIAS_NETDEV("gre0");

28
net/ipv4/ip_output.c
View File

@ -476,9 +476,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
* we can switch to copy when see the first bad fragment.
*/
if (skb_has_frags(skb)) {
struct sk_buff *frag;
struct sk_buff *frag, *frag2;
int first_len = skb_pagelen(skb);
int truesizes = 0;
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
@ -491,18 +490,18 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
goto slow_path;
goto slow_path_clean;
/* Partially cloned skb? */
if (skb_shared(frag))
goto slow_path;
goto slow_path_clean;
BUG_ON(frag->sk);
if (skb->sk) {
frag->sk = skb->sk;
frag->destructor = sock_wfree;
}
truesizes += frag->truesize;
skb->truesize -= frag->truesize;
}
/* Everything is OK. Generate! */
@ -512,7 +511,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
frag = skb_shinfo(skb)->frag_list;
skb_frag_list_init(skb);
skb->data_len = first_len - skb_headlen(skb);
skb->truesize -= truesizes;
skb->len = first_len;
iph->tot_len = htons(first_len);
iph->frag_off = htons(IP_MF);
@ -564,6 +562,15 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
}
IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
return err;
slow_path_clean:
skb_walk_frags(skb, frag2) {
if (frag2 == frag)
break;
frag2->sk = NULL;
frag2->destructor = NULL;
skb->truesize += frag2->truesize;
}
}
slow_path:
@ -860,8 +867,10 @@ int ip_append_data(struct sock *sk,
!exthdrlen)
csummode = CHECKSUM_PARTIAL;
skb = skb_peek_tail(&sk->sk_write_queue);
inet->cork.length += length;
if (((length> mtu) || !skb_queue_empty(&sk->sk_write_queue)) &&
if (((length > mtu) || (skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->u.dst.dev->features & NETIF_F_UFO)) {
err = ip_ufo_append_data(sk, getfrag, from, length, hh_len,
@ -879,7 +888,7 @@ int ip_append_data(struct sock *sk,
* adding appropriate IP header.
*/
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
if (!skb)
goto alloc_new_skb;
while (length > 0) {
@ -1108,7 +1117,8 @@ ssize_t ip_append_page(struct sock *sk, struct page *page,
return -EINVAL;
inet->cork.length += size;
if ((sk->sk_protocol == IPPROTO_UDP) &&
if ((size + skb->len > mtu) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->u.dst.dev->features & NETIF_F_UFO)) {
skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;

1
net/ipv4/ipip.c
View File

@ -853,3 +853,4 @@ static void __exit ipip_fini(void)
module_init(ipip_init);
module_exit(ipip_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NETDEV("tunl0");

8
net/ipv4/netfilter.c
View File

@ -155,10 +155,10 @@ static int nf_ip_reroute(struct sk_buff *skb,
if (entry->hook == NF_INET_LOCAL_OUT) {
const struct iphdr *iph = ip_hdr(skb);
if (!(iph->tos == rt_info->tos
&& skb->mark == rt_info->mark
&& iph->daddr == rt_info->daddr
&& iph->saddr == rt_info->saddr))
if (!(iph->tos == rt_info->tos &&
skb->mark == rt_info->mark &&
iph->daddr == rt_info->daddr &&
iph->saddr == rt_info->saddr))
return ip_route_me_harder(skb, RTN_UNSPEC);
}
return 0;

424
net/ipv4/netfilter/arp_tables.c
View File

@ -27,6 +27,7 @@
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_arp/arp_tables.h>
#include "../../netfilter/xt_repldata.h"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("David S. Miller <davem@redhat.com>");
@ -58,6 +59,12 @@ do { \
#define ARP_NF_ASSERT(x)
#endif
void *arpt_alloc_initial_table(const struct xt_table *info)
{
return xt_alloc_initial_table(arpt, ARPT);
}
EXPORT_SYMBOL_GPL(arpt_alloc_initial_table);
static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap,
const char *hdr_addr, int len)
{
@ -217,7 +224,7 @@ static inline int arp_checkentry(const struct arpt_arp *arp)
}
static unsigned int
arpt_error(struct sk_buff *skb, const struct xt_target_param *par)
arpt_error(struct sk_buff *skb, const struct xt_action_param *par)
{
if (net_ratelimit())
printk("arp_tables: error: '%s'\n",
@ -226,7 +233,14 @@ arpt_error(struct sk_buff *skb, const struct xt_target_param *par)
return NF_DROP;
}
static inline struct arpt_entry *get_entry(void *base, unsigned int offset)
static inline const struct arpt_entry_target *
arpt_get_target_c(const struct arpt_entry *e)
{
return arpt_get_target((struct arpt_entry *)e);
}
static inline struct arpt_entry *
get_entry(const void *base, unsigned int offset)
{
return (struct arpt_entry *)(base + offset);
}
@ -251,7 +265,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
const char *indev, *outdev;
void *table_base;
const struct xt_table_info *private;
struct xt_target_param tgpar;
struct xt_action_param acpar;
if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
return NF_DROP;
@ -266,14 +280,14 @@ unsigned int arpt_do_table(struct sk_buff *skb,
e = get_entry(table_base, private->hook_entry[hook]);
back = get_entry(table_base, private->underflow[hook]);
tgpar.in = in;
tgpar.out = out;
tgpar.hooknum = hook;
tgpar.family = NFPROTO_ARP;
acpar.in = in;
acpar.out = out;
acpar.hooknum = hook;
acpar.family = NFPROTO_ARP;
arp = arp_hdr(skb);
do {
struct arpt_entry_target *t;
const struct arpt_entry_target *t;
int hdr_len;
if (!arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) {
@ -285,7 +299,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
(2 * skb->dev->addr_len);
ADD_COUNTER(e->counters, hdr_len, 1);
t = arpt_get_target(e);
t = arpt_get_target_c(e);
/* Standard target? */
if (!t->u.kernel.target->target) {
@ -319,9 +333,9 @@ unsigned int arpt_do_table(struct sk_buff *skb,
/* Targets which reenter must return
* abs. verdicts
*/
tgpar.target = t->u.kernel.target;
tgpar.targinfo = t->data;
verdict = t->u.kernel.target->target(skb, &tgpar);
acpar.target = t->u.kernel.target;
acpar.targinfo = t->data;
verdict = t->u.kernel.target->target(skb, &acpar);
/* Target might have changed stuff. */
arp = arp_hdr(skb);
@ -351,7 +365,7 @@ static inline bool unconditional(const struct arpt_arp *arp)
/* Figures out from what hook each rule can be called: returns 0 if
* there are loops. Puts hook bitmask in comefrom.
*/
static int mark_source_chains(struct xt_table_info *newinfo,
static int mark_source_chains(const struct xt_table_info *newinfo,
unsigned int valid_hooks, void *entry0)
{
unsigned int hook;
@ -372,7 +386,7 @@ static int mark_source_chains(struct xt_table_info *newinfo,
for (;;) {
const struct arpt_standard_target *t
= (void *)arpt_get_target(e);
= (void *)arpt_get_target_c(e);
int visited = e->comefrom & (1 << hook);
if (e->comefrom & (1 << NF_ARP_NUMHOOKS)) {
@ -456,7 +470,7 @@ static int mark_source_chains(struct xt_table_info *newinfo,
return 1;
}
static inline int check_entry(struct arpt_entry *e, const char *name)
static inline int check_entry(const struct arpt_entry *e, const char *name)
{
const struct arpt_entry_target *t;
@ -468,7 +482,7 @@ static inline int check_entry(struct arpt_entry *e, const char *name)
if (e->target_offset + sizeof(struct arpt_entry_target) > e->next_offset)
return -EINVAL;
t = arpt_get_target(e);
t = arpt_get_target_c(e);
if (e->target_offset + t->u.target_size > e->next_offset)
return -EINVAL;
@ -498,8 +512,7 @@ static inline int check_target(struct arpt_entry *e, const char *name)
}
static inline int
find_check_entry(struct arpt_entry *e, const char *name, unsigned int size,
unsigned int *i)
find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
{
struct arpt_entry_target *t;
struct xt_target *target;
@ -510,13 +523,11 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size,
return ret;
t = arpt_get_target(e);
target = try_then_request_module(xt_find_target(NFPROTO_ARP,
t->u.user.name,
t->u.user.revision),
"arpt_%s", t->u.user.name);
if (IS_ERR(target) || !target) {
target = xt_request_find_target(NFPROTO_ARP, t->u.user.name,
t->u.user.revision);
if (IS_ERR(target)) {
duprintf("find_check_entry: `%s' not found\n", t->u.user.name);
ret = target ? PTR_ERR(target) : -ENOENT;
ret = PTR_ERR(target);
goto out;
}
t->u.kernel.target = target;
@ -524,8 +535,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size,
ret = check_target(e, name);
if (ret)
goto err;
(*i)++;
return 0;
err:
module_put(t->u.kernel.target->me);
@ -533,14 +542,14 @@ out:
return ret;
}
static bool check_underflow(struct arpt_entry *e)
static bool check_underflow(const struct arpt_entry *e)
{
const struct arpt_entry_target *t;
unsigned int verdict;
if (!unconditional(&e->arp))
return false;
t = arpt_get_target(e);
t = arpt_get_target_c(e);
if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
return false;
verdict = ((struct arpt_standard_target *)t)->verdict;
@ -550,12 +559,11 @@ static bool check_underflow(struct arpt_entry *e)
static inline int check_entry_size_and_hooks(struct arpt_entry *e,
struct xt_table_info *newinfo,
unsigned char *base,
unsigned char *limit,
const unsigned char *base,
const unsigned char *limit,
const unsigned int *hook_entries,
const unsigned int *underflows,
unsigned int valid_hooks,
unsigned int *i)
unsigned int valid_hooks)
{
unsigned int h;
@ -592,19 +600,14 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
/* Clear counters and comefrom */
e->counters = ((struct xt_counters) { 0, 0 });
e->comefrom = 0;
(*i)++;
return 0;
}
static inline int cleanup_entry(struct arpt_entry *e, unsigned int *i)
static inline void cleanup_entry(struct arpt_entry *e)
{
struct xt_tgdtor_param par;
struct arpt_entry_target *t;
if (i && (*i)-- == 0)
return 1;
t = arpt_get_target(e);
par.target = t->u.kernel.target;
par.targinfo = t->data;
@ -612,26 +615,20 @@ static inline int cleanup_entry(struct arpt_entry *e, unsigned int *i)
if (par.target->destroy != NULL)
par.target->destroy(&par);
module_put(par.target->me);
return 0;
}
/* Checks and translates the user-supplied table segment (held in
* newinfo).
*/
static int translate_table(const char *name,
unsigned int valid_hooks,
struct xt_table_info *newinfo,
void *entry0,
unsigned int size,
unsigned int number,
const unsigned int *hook_entries,
const unsigned int *underflows)
static int translate_table(struct xt_table_info *newinfo, void *entry0,
const struct arpt_replace *repl)
{
struct arpt_entry *iter;
unsigned int i;
int ret;
int ret = 0;
newinfo->size = size;
newinfo->number = number;
newinfo->size = repl->size;
newinfo->number = repl->num_entries;
/* Init all hooks to impossible value. */
for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
@ -643,52 +640,64 @@ static int translate_table(const char *name,
i = 0;
/* Walk through entries, checking offsets. */
ret = ARPT_ENTRY_ITERATE(entry0, newinfo->size,
check_entry_size_and_hooks,
newinfo,
entry0,
entry0 + size,
hook_entries, underflows, valid_hooks, &i);
xt_entry_foreach(iter, entry0, newinfo->size) {
ret = check_entry_size_and_hooks(iter, newinfo, entry0,
entry0 + repl->size, repl->hook_entry, repl->underflow,
repl->valid_hooks);
if (ret != 0)
break;
++i;
if (strcmp(arpt_get_target(iter)->u.user.name,
XT_ERROR_TARGET) == 0)
++newinfo->stacksize;
}
duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret);
if (ret != 0)
return ret;
if (i != number) {
if (i != repl->num_entries) {
duprintf("translate_table: %u not %u entries\n",
i, number);
i, repl->num_entries);
return -EINVAL;
}
/* Check hooks all assigned */
for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
/* Only hooks which are valid */
if (!(valid_hooks & (1 << i)))
if (!(repl->valid_hooks & (1 << i)))
continue;
if (newinfo->hook_entry[i] == 0xFFFFFFFF) {
duprintf("Invalid hook entry %u %u\n",
i, hook_entries[i]);
i, repl->hook_entry[i]);
return -EINVAL;
}
if (newinfo->underflow[i] == 0xFFFFFFFF) {
duprintf("Invalid underflow %u %u\n",
i, underflows[i]);
i, repl->underflow[i]);
return -EINVAL;
}
}
if (!mark_source_chains(newinfo, valid_hooks, entry0)) {
if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) {
duprintf("Looping hook\n");
return -ELOOP;
}
/* Finally, each sanity check must pass */
i = 0;
ret = ARPT_ENTRY_ITERATE(entry0, newinfo->size,
find_check_entry, name, size, &i);
xt_entry_foreach(iter, entry0, newinfo->size) {
ret = find_check_entry(iter, repl->name, repl->size);
if (ret != 0)
break;
++i;
}
if (ret != 0) {
ARPT_ENTRY_ITERATE(entry0, newinfo->size,
cleanup_entry, &i);
xt_entry_foreach(iter, entry0, newinfo->size) {
if (i-- == 0)
break;
cleanup_entry(iter);
}
return ret;
}
@ -701,30 +710,10 @@ static int translate_table(const char *name,
return ret;
}
/* Gets counters. */
static inline int add_entry_to_counter(const struct arpt_entry *e,
struct xt_counters total[],
unsigned int *i)
{
ADD_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt);
(*i)++;
return 0;
}
static inline int set_entry_to_counter(const struct arpt_entry *e,
struct xt_counters total[],
unsigned int *i)
{
SET_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt);
(*i)++;
return 0;
}
static void get_counters(const struct xt_table_info *t,
struct xt_counters counters[])
{
struct arpt_entry *iter;
unsigned int cpu;
unsigned int i;
unsigned int curcpu;
@ -740,32 +729,32 @@ static void get_counters(const struct xt_table_info *t,
curcpu = smp_processor_id();
i = 0;
ARPT_ENTRY_ITERATE(t->entries[curcpu],
t->size,
set_entry_to_counter,
counters,
&i);
xt_entry_foreach(iter, t->entries[curcpu], t->size) {
SET_COUNTER(counters[i], iter->counters.bcnt,
iter->counters.pcnt);
++i;
}
for_each_possible_cpu(cpu) {
if (cpu == curcpu)
continue;
i = 0;
xt_info_wrlock(cpu);
ARPT_ENTRY_ITERATE(t->entries[cpu],
t->size,
add_entry_to_counter,
counters,
&i);
xt_entry_foreach(iter, t->entries[cpu], t->size) {
ADD_COUNTER(counters[i], iter->counters.bcnt,
iter->counters.pcnt);
++i;
}
xt_info_wrunlock(cpu);
}
local_bh_enable();
}
static struct xt_counters *alloc_counters(struct xt_table *table)
static struct xt_counters *alloc_counters(const struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
struct xt_table_info *private = table->private;
const struct xt_table_info *private = table->private;
/* We need atomic snapshot of counters: rest doesn't change
* (other than comefrom, which userspace doesn't care
@ -783,11 +772,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table)
}
static int copy_entries_to_user(unsigned int total_size,
struct xt_table *table,
const struct xt_table *table,
void __user *userptr)
{
unsigned int off, num;
struct arpt_entry *e;
const struct arpt_entry *e;
struct xt_counters *counters;
struct xt_table_info *private = table->private;
int ret = 0;
@ -807,7 +796,7 @@ static int copy_entries_to_user(unsigned int total_size,
/* FIXME: use iterator macros --RR */
/* ... then go back and fix counters and names */
for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){
struct arpt_entry_target *t;
const struct arpt_entry_target *t;
e = (struct arpt_entry *)(loc_cpu_entry + off);
if (copy_to_user(userptr + off
@ -818,7 +807,7 @@ static int copy_entries_to_user(unsigned int total_size,
goto free_counters;
}
t = arpt_get_target(e);
t = arpt_get_target_c(e);
if (copy_to_user(userptr + off + e->target_offset
+ offsetof(struct arpt_entry_target,
u.user.name),
@ -853,18 +842,18 @@ static int compat_standard_to_user(void __user *dst, void *src)
return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0;
}
static int compat_calc_entry(struct arpt_entry *e,
static int compat_calc_entry(const struct arpt_entry *e,
const struct xt_table_info *info,
void *base, struct xt_table_info *newinfo)
const void *base, struct xt_table_info *newinfo)
{
struct arpt_entry_target *t;
const struct arpt_entry_target *t;
unsigned int entry_offset;
int off, i, ret;
off = sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry);
entry_offset = (void *)e - base;
t = arpt_get_target(e);
t = arpt_get_target_c(e);
off += xt_compat_target_offset(t->u.kernel.target);
newinfo->size -= off;
ret = xt_compat_add_offset(NFPROTO_ARP, entry_offset, off);
@ -885,7 +874,9 @@ static int compat_calc_entry(struct arpt_entry *e,
static int compat_table_info(const struct xt_table_info *info,
struct xt_table_info *newinfo)
{
struct arpt_entry *iter;
void *loc_cpu_entry;
int ret;
if (!newinfo || !info)
return -EINVAL;
@ -894,13 +885,17 @@ static int compat_table_info(const struct xt_table_info *info,
memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
newinfo->initial_entries = 0;
loc_cpu_entry = info->entries[raw_smp_processor_id()];
return ARPT_ENTRY_ITERATE(loc_cpu_entry, info->size,
compat_calc_entry, info, loc_cpu_entry,
newinfo);
xt_entry_foreach(iter, loc_cpu_entry, info->size) {
ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
if (ret != 0)
return ret;
}
return 0;
}
#endif
static int get_info(struct net *net, void __user *user, int *len, int compat)
static int get_info(struct net *net, void __user *user,
const int *len, int compat)
{
char name[ARPT_TABLE_MAXNAMELEN];
struct xt_table *t;
@ -959,7 +954,7 @@ static int get_info(struct net *net, void __user *user, int *len, int compat)
}
static int get_entries(struct net *net, struct arpt_get_entries __user *uptr,
int *len)
const int *len)
{
int ret;
struct arpt_get_entries get;
@ -1010,6 +1005,7 @@ static int __do_replace(struct net *net, const char *name,
struct xt_table_info *oldinfo;
struct xt_counters *counters;
void *loc_cpu_old_entry;
struct arpt_entry *iter;
ret = 0;
counters = vmalloc_node(num_counters * sizeof(struct xt_counters),
@ -1053,8 +1049,8 @@ static int __do_replace(struct net *net, const char *name,
/* Decrease module usage counts and free resource */
loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()];
ARPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,
NULL);
xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size)
cleanup_entry(iter);
xt_free_table_info(oldinfo);
if (copy_to_user(counters_ptr, counters,
@ -1073,12 +1069,14 @@ static int __do_replace(struct net *net, const char *name,
return ret;
}
static int do_replace(struct net *net, void __user *user, unsigned int len)
static int do_replace(struct net *net, const void __user *user,
unsigned int len)
{
int ret;
struct arpt_replace tmp;
struct xt_table_info *newinfo;
void *loc_cpu_entry;
struct arpt_entry *iter;
if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
return -EFAULT;
@ -1086,6 +1084,7 @@ static int do_replace(struct net *net, void __user *user, unsigned int len)
/* overflow check */
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
if (!newinfo)
@ -1099,9 +1098,7 @@ static int do_replace(struct net *net, void __user *user, unsigned int len)
goto free_newinfo;
}
ret = translate_table(tmp.name, tmp.valid_hooks,
newinfo, loc_cpu_entry, tmp.size, tmp.num_entries,
tmp.hook_entry, tmp.underflow);
ret = translate_table(newinfo, loc_cpu_entry, &tmp);
if (ret != 0)
goto free_newinfo;
@ -1114,27 +1111,15 @@ static int do_replace(struct net *net, void __user *user, unsigned int len)
return 0;
free_newinfo_untrans:
ARPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL);
xt_entry_foreach(iter, loc_cpu_entry, newinfo->size)
cleanup_entry(iter);
free_newinfo:
xt_free_table_info(newinfo);
return ret;
}
/* We're lazy, and add to the first CPU; overflow works its fey magic
* and everything is OK. */
static int
add_counter_to_entry(struct arpt_entry *e,
const struct xt_counters addme[],
unsigned int *i)
{
ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
(*i)++;
return 0;
}
static int do_add_counters(struct net *net, void __user *user, unsigned int len,
int compat)
static int do_add_counters(struct net *net, const void __user *user,
unsigned int len, int compat)
{
unsigned int i, curcpu;
struct xt_counters_info tmp;
@ -1147,6 +1132,7 @@ static int do_add_counters(struct net *net, void __user *user, unsigned int len,
const struct xt_table_info *private;
int ret = 0;
void *loc_cpu_entry;
struct arpt_entry *iter;
#ifdef CONFIG_COMPAT
struct compat_xt_counters_info compat_tmp;
@ -1204,11 +1190,10 @@ static int do_add_counters(struct net *net, void __user *user, unsigned int len,
curcpu = smp_processor_id();
loc_cpu_entry = private->entries[curcpu];
xt_info_wrlock(curcpu);
ARPT_ENTRY_ITERATE(loc_cpu_entry,
private->size,
add_counter_to_entry,
paddc,
&i);
xt_entry_foreach(iter, loc_cpu_entry, private->size) {
ADD_COUNTER(iter->counters, paddc[i].bcnt, paddc[i].pcnt);
++i;
}
xt_info_wrunlock(curcpu);
unlock_up_free:
local_bh_enable();
@ -1221,28 +1206,22 @@ static int do_add_counters(struct net *net, void __user *user, unsigned int len,
}
#ifdef CONFIG_COMPAT
static inline int
compat_release_entry(struct compat_arpt_entry *e, unsigned int *i)
static inline void compat_release_entry(struct compat_arpt_entry *e)
{
struct arpt_entry_target *t;
if (i && (*i)-- == 0)
return 1;
t = compat_arpt_get_target(e);
module_put(t->u.kernel.target->me);
return 0;
}
static inline int
check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
struct xt_table_info *newinfo,
unsigned int *size,
unsigned char *base,
unsigned char *limit,
unsigned int *hook_entries,
unsigned int *underflows,
unsigned int *i,
const unsigned char *base,
const unsigned char *limit,
const unsigned int *hook_entries,
const unsigned int *underflows,
const char *name)
{
struct arpt_entry_target *t;
@ -1273,14 +1252,12 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
entry_offset = (void *)e - (void *)base;
t = compat_arpt_get_target(e);
target = try_then_request_module(xt_find_target(NFPROTO_ARP,
t->u.user.name,
t->u.user.revision),
"arpt_%s", t->u.user.name);
if (IS_ERR(target) || !target) {
target = xt_request_find_target(NFPROTO_ARP, t->u.user.name,
t->u.user.revision);
if (IS_ERR(target)) {
duprintf("check_compat_entry_size_and_hooks: `%s' not found\n",
t->u.user.name);
ret = target ? PTR_ERR(target) : -ENOENT;
ret = PTR_ERR(target);
goto out;
}
t->u.kernel.target = target;
@ -1302,8 +1279,6 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
/* Clear counters and comefrom */
memset(&e->counters, 0, sizeof(e->counters));
e->comefrom = 0;
(*i)++;
return 0;
release_target:
@ -1347,19 +1322,6 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
return ret;
}
static inline int compat_check_entry(struct arpt_entry *e, const char *name,
unsigned int *i)
{
int ret;
ret = check_target(e, name);
if (ret)
return ret;
(*i)++;
return 0;
}
static int translate_compat_table(const char *name,
unsigned int valid_hooks,
struct xt_table_info **pinfo,
@ -1372,8 +1334,10 @@ static int translate_compat_table(const char *name,
unsigned int i, j;
struct xt_table_info *newinfo, *info;
void *pos, *entry0, *entry1;
struct compat_arpt_entry *iter0;
struct arpt_entry *iter1;
unsigned int size;
int ret;
int ret = 0;
info = *pinfo;
entry0 = *pentry0;
@ -1390,13 +1354,14 @@ static int translate_compat_table(const char *name,
j = 0;
xt_compat_lock(NFPROTO_ARP);
/* Walk through entries, checking offsets. */
ret = COMPAT_ARPT_ENTRY_ITERATE(entry0, total_size,
check_compat_entry_size_and_hooks,
info, &size, entry0,
entry0 + total_size,
hook_entries, underflows, &j, name);
if (ret != 0)
goto out_unlock;
xt_entry_foreach(iter0, entry0, total_size) {
ret = check_compat_entry_size_and_hooks(iter0, info, &size,
entry0, entry0 + total_size, hook_entries, underflows,
name);
if (ret != 0)
goto out_unlock;
++j;
}
ret = -EINVAL;
if (j != number) {
@ -1435,9 +1400,12 @@ static int translate_compat_table(const char *name,
entry1 = newinfo->entries[raw_smp_processor_id()];
pos = entry1;
size = total_size;
ret = COMPAT_ARPT_ENTRY_ITERATE(entry0, total_size,
compat_copy_entry_from_user,
&pos, &size, name, newinfo, entry1);
xt_entry_foreach(iter0, entry0, total_size) {
ret = compat_copy_entry_from_user(iter0, &pos,
&size, name, newinfo, entry1);
if (ret != 0)
break;
}
xt_compat_flush_offsets(NFPROTO_ARP);
xt_compat_unlock(NFPROTO_ARP);
if (ret)
@ -1448,13 +1416,32 @@ static int translate_compat_table(const char *name,
goto free_newinfo;
i = 0;
ret = ARPT_ENTRY_ITERATE(entry1, newinfo->size, compat_check_entry,
name, &i);
xt_entry_foreach(iter1, entry1, newinfo->size) {
ret = check_target(iter1, name);
if (ret != 0)
break;
++i;
}
if (ret) {
/*
* The first i matches need cleanup_entry (calls ->destroy)
* because they had called ->check already. The other j-i
* entries need only release.
*/
int skip = i;
j -= i;
COMPAT_ARPT_ENTRY_ITERATE_CONTINUE(entry0, newinfo->size, i,
compat_release_entry, &j);
ARPT_ENTRY_ITERATE(entry1, newinfo->size, cleanup_entry, &i);
xt_entry_foreach(iter0, entry0, newinfo->size) {
if (skip-- > 0)
continue;
if (j-- == 0)
break;
compat_release_entry(iter0);
}
xt_entry_foreach(iter1, entry1, newinfo->size) {
if (i-- == 0)
break;
cleanup_entry(iter1);
}
xt_free_table_info(newinfo);
return ret;
}
@ -1472,7 +1459,11 @@ static int translate_compat_table(const char *name,
free_newinfo:
xt_free_table_info(newinfo);
out:
COMPAT_ARPT_ENTRY_ITERATE(entry0, total_size, compat_release_entry, &j);
xt_entry_foreach(iter0, entry0, total_size) {
if (j-- == 0)
break;
compat_release_entry(iter0);
}
return ret;
out_unlock:
xt_compat_flush_offsets(NFPROTO_ARP);
@ -1499,6 +1490,7 @@ static int compat_do_replace(struct net *net, void __user *user,
struct compat_arpt_replace tmp;
struct xt_table_info *newinfo;
void *loc_cpu_entry;
struct arpt_entry *iter;
if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
return -EFAULT;
@ -1508,6 +1500,7 @@ static int compat_do_replace(struct net *net, void __user *user,
return -ENOMEM;
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
if (!newinfo)
@ -1536,7 +1529,8 @@ static int compat_do_replace(struct net *net, void __user *user,
return 0;
free_newinfo_untrans:
ARPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL);
xt_entry_foreach(iter, loc_cpu_entry, newinfo->size)
cleanup_entry(iter);
free_newinfo:
xt_free_table_info(newinfo);
return ret;
@ -1570,7 +1564,7 @@ static int compat_do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user,
static int compat_copy_entry_to_user(struct arpt_entry *e, void __user **dstptr,
compat_uint_t *size,
struct xt_counters *counters,
unsigned int *i)
unsigned int i)
{
struct arpt_entry_target *t;
struct compat_arpt_entry __user *ce;
@ -1578,14 +1572,12 @@ static int compat_copy_entry_to_user(struct arpt_entry *e, void __user **dstptr,
compat_uint_t origsize;
int ret;
ret = -EFAULT;
origsize = *size;
ce = (struct compat_arpt_entry __user *)*dstptr;
if (copy_to_user(ce, e, sizeof(struct arpt_entry)))
goto out;
if (copy_to_user(&ce->counters, &counters[*i], sizeof(counters[*i])))
goto out;
if (copy_to_user(ce, e, sizeof(struct arpt_entry)) != 0 ||
copy_to_user(&ce->counters, &counters[i],
sizeof(counters[i])) != 0)
return -EFAULT;
*dstptr += sizeof(struct compat_arpt_entry);
*size -= sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry);
@ -1595,18 +1587,12 @@ static int compat_copy_entry_to_user(struct arpt_entry *e, void __user **dstptr,
t = arpt_get_target(e);
ret = xt_compat_target_to_user(t, dstptr, size);
if (ret)
goto out;
ret = -EFAULT;
return ret;
next_offset = e->next_offset - (origsize - *size);
if (put_user(target_offset, &ce->target_offset))
goto out;
if (put_user(next_offset, &ce->next_offset))
goto out;
(*i)++;
if (put_user(target_offset, &ce->target_offset) != 0 ||
put_user(next_offset, &ce->next_offset) != 0)
return -EFAULT;
return 0;
out:
return ret;
}
static int compat_copy_entries_to_user(unsigned int total_size,
@ -1620,6 +1606,7 @@ static int compat_copy_entries_to_user(unsigned int total_size,
int ret = 0;
void *loc_cpu_entry;
unsigned int i = 0;
struct arpt_entry *iter;
counters = alloc_counters(table);
if (IS_ERR(counters))
@ -1629,9 +1616,12 @@ static int compat_copy_entries_to_user(unsigned int total_size,
loc_cpu_entry = private->entries[raw_smp_processor_id()];
pos = userptr;
size = total_size;
ret = ARPT_ENTRY_ITERATE(loc_cpu_entry, total_size,
compat_copy_entry_to_user,
&pos, &size, counters, &i);
xt_entry_foreach(iter, loc_cpu_entry, total_size) {
ret = compat_copy_entry_to_user(iter, &pos,
&size, counters, i++);
if (ret != 0)
break;
}
vfree(counters);
return ret;
}
@ -1763,6 +1753,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len
ret = -EFAULT;
break;
}
rev.name[sizeof(rev.name)-1] = 0;
try_then_request_module(xt_find_revision(NFPROTO_ARP, rev.name,
rev.revision, 1, &ret),
@ -1784,8 +1775,7 @@ struct xt_table *arpt_register_table(struct net *net,
{
int ret;
struct xt_table_info *newinfo;
struct xt_table_info bootstrap
= { 0, 0, 0, { 0 }, { 0 }, { } };
struct xt_table_info bootstrap = {0};
void *loc_cpu_entry;
struct xt_table *new_table;
@ -1799,12 +1789,7 @@ struct xt_table *arpt_register_table(struct net *net,
loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
memcpy(loc_cpu_entry, repl->entries, repl->size);
ret = translate_table(table->name, table->valid_hooks,
newinfo, loc_cpu_entry, repl->size,
repl->num_entries,
repl->hook_entry,
repl->underflow);
ret = translate_table(newinfo, loc_cpu_entry, repl);
duprintf("arpt_register_table: translate table gives %d\n", ret);
if (ret != 0)
goto out_free;
@ -1827,13 +1812,14 @@ void arpt_unregister_table(struct xt_table *table)
struct xt_table_info *private;
void *loc_cpu_entry;
struct module *table_owner = table->me;
struct arpt_entry *iter;
private = xt_unregister_table(table);
/* Decrease module usage counts and free resources */
loc_cpu_entry = private->entries[raw_smp_processor_id()];
ARPT_ENTRY_ITERATE(loc_cpu_entry, private->size,
cleanup_entry, NULL);
xt_entry_foreach(iter, loc_cpu_entry, private->size)
cleanup_entry(iter);
if (private->number > private->initial_entries)
module_put(table_owner);
xt_free_table_info(private);

2
net/ipv4/netfilter/arpt_mangle.c
View File

@ -9,7 +9,7 @@ MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>");
MODULE_DESCRIPTION("arptables arp payload mangle target");
static unsigned int
target(struct sk_buff *skb, const struct xt_target_param *par)
target(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct arpt_mangle *mangle = par->targinfo;
const struct arphdr *arp;

40
net/ipv4/netfilter/arptable_filter.c
View File

@ -6,6 +6,7 @@
*/
#include <linux/module.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_arp/arp_tables.h>
MODULE_LICENSE("GPL");
@ -15,36 +16,6 @@ MODULE_DESCRIPTION("arptables filter table");
#define FILTER_VALID_HOOKS ((1 << NF_ARP_IN) | (1 << NF_ARP_OUT) | \
(1 << NF_ARP_FORWARD))
static const struct
{
struct arpt_replace repl;
struct arpt_standard entries[3];
struct arpt_error term;
} initial_table __net_initdata = {
.repl = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
.num_entries = 4,
.size = sizeof(struct arpt_standard) * 3 + sizeof(struct arpt_error),
.hook_entry = {
[NF_ARP_IN] = 0,
[NF_ARP_OUT] = sizeof(struct arpt_standard),
[NF_ARP_FORWARD] = 2 * sizeof(struct arpt_standard),
},
.underflow = {
[NF_ARP_IN] = 0,
[NF_ARP_OUT] = sizeof(struct arpt_standard),
[NF_ARP_FORWARD] = 2 * sizeof(struct arpt_standard),
},
},
.entries = {
ARPT_STANDARD_INIT(NF_ACCEPT), /* ARP_IN */
ARPT_STANDARD_INIT(NF_ACCEPT), /* ARP_OUT */
ARPT_STANDARD_INIT(NF_ACCEPT), /* ARP_FORWARD */
},
.term = ARPT_ERROR_INIT,
};
static const struct xt_table packet_filter = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
@ -99,9 +70,14 @@ static struct nf_hook_ops arpt_ops[] __read_mostly = {
static int __net_init arptable_filter_net_init(struct net *net)
{
/* Register table */
struct arpt_replace *repl;
repl = arpt_alloc_initial_table(&packet_filter);
if (repl == NULL)
return -ENOMEM;
net->ipv4.arptable_filter =
arpt_register_table(net, &packet_filter, &initial_table.repl);
arpt_register_table(net, &packet_filter, repl);
kfree(repl);
if (IS_ERR(net->ipv4.arptable_filter))
return PTR_ERR(net->ipv4.arptable_filter);
return 0;

708
net/ipv4/netfilter/ip_tables.c
View File

File diff suppressed because it is too large Load Diff

11
net/ipv4/netfilter/ipt_CLUSTERIP.c
View File

@ -281,7 +281,7 @@ clusterip_responsible(const struct clusterip_config *config, u_int32_t hash)
***********************************************************************/
static unsigned int
clusterip_tg(struct sk_buff *skb, const struct xt_target_param *par)
clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ipt_clusterip_tgt_info *cipinfo = par->targinfo;
struct nf_conn *ct;
@ -319,12 +319,12 @@ clusterip_tg(struct sk_buff *skb, const struct xt_target_param *par)
ct->mark = hash;
break;
case IP_CT_RELATED:
case IP_CT_RELATED+IP_CT_IS_REPLY:
case IP_CT_RELATED_REPLY:
/* FIXME: we don't handle expectations at the
* moment. they can arrive on a different node than
* the master connection (e.g. FTP passive mode) */
case IP_CT_ESTABLISHED:
case IP_CT_ESTABLISHED+IP_CT_IS_REPLY:
case IP_CT_ESTABLISHED_REPLY:
break;
default:
break;
@ -666,8 +666,11 @@ static ssize_t clusterip_proc_write(struct file *file, const char __user *input,
struct clusterip_config *c = pde->data;
unsigned long nodenum;
if (copy_from_user(buffer, input, PROC_WRITELEN))
if (size > PROC_WRITELEN)
return -EIO;
if (copy_from_user(buffer, input, size))
return -EFAULT;
buffer[size] = 0;
if (*buffer == '+') {
nodenum = simple_strtoul(buffer+1, NULL, 10);

4
net/ipv4/netfilter/ipt_ECN.c
View File

@ -50,7 +50,7 @@ set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo)
struct tcphdr _tcph, *tcph;
__be16 oldval;
/* Not enought header? */
/* Not enough header? */
tcph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph);
if (!tcph)
return false;
@ -77,7 +77,7 @@ set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo)
}
static unsigned int
ecn_tg(struct sk_buff *skb, const struct xt_target_param *par)
ecn_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ipt_ECN_info *einfo = par->targinfo;

2
net/ipv4/netfilter/ipt_LOG.c
View File

@ -425,7 +425,7 @@ ipt_log_packet(u_int8_t pf,
}
static unsigned int
log_tg(struct sk_buff *skb, const struct xt_target_param *par)
log_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ipt_log_info *loginfo = par->targinfo;
struct nf_loginfo li;

4
net/ipv4/netfilter/ipt_MASQUERADE.c
View File

@ -44,7 +44,7 @@ static bool masquerade_tg_check(const struct xt_tgchk_param *par)
}
static unsigned int
masquerade_tg(struct sk_buff *skb, const struct xt_target_param *par)
masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
struct nf_conn *ct;
struct nf_conn_nat *nat;
@ -60,7 +60,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_target_param *par)
nat = nfct_nat(ct);
NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED
|| ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY));
|| ctinfo == IP_CT_RELATED_REPLY));
/* Source address is 0.0.0.0 - locally generated packet that is
* probably not supposed to be masqueraded.

2
net/ipv4/netfilter/ipt_NETMAP.c
View File

@ -38,7 +38,7 @@ static bool netmap_tg_check(const struct xt_tgchk_param *par)
}
static unsigned int
netmap_tg(struct sk_buff *skb, const struct xt_target_param *par)
netmap_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;

2
net/ipv4/netfilter/ipt_REDIRECT.c
View File

@ -42,7 +42,7 @@ static bool redirect_tg_check(const struct xt_tgchk_param *par)
}
static unsigned int
redirect_tg(struct sk_buff *skb, const struct xt_target_param *par)
redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;

5
net/ipv4/netfilter/ipt_REJECT.c
View File

@ -135,13 +135,10 @@ static inline void send_unreach(struct sk_buff *skb_in, int code)
}
static unsigned int
reject_tg(struct sk_buff *skb, const struct xt_target_param *par)
reject_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ipt_reject_info *reject = par->targinfo;
/* WARNING: This code causes reentry within iptables.
This means that the iptables jump stack is now crap. We
must return an absolute verdict. --RR */
switch (reject->with) {
case IPT_ICMP_NET_UNREACHABLE:
send_unreach(skb, ICMP_NET_UNREACH);

2
net/ipv4/netfilter/ipt_ULOG.c
View File

@ -281,7 +281,7 @@ alloc_failure:
}
static unsigned int
ulog_tg(struct sk_buff *skb, const struct xt_target_param *par)
ulog_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
ipt_ulog_packet(par->hooknum, skb, par->in, par->out,
par->targinfo, NULL);

6
net/ipv4/netfilter/ipt_addrtype.c
View File

@ -30,7 +30,7 @@ static inline bool match_type(struct net *net, const struct net_device *dev,
}
static bool
addrtype_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par)
addrtype_mt_v0(const struct sk_buff *skb, const struct xt_action_param *par)
{
struct net *net = dev_net(par->in ? par->in : par->out);
const struct ipt_addrtype_info *info = par->matchinfo;
@ -48,7 +48,7 @@ addrtype_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par)
}
static bool
addrtype_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par)
addrtype_mt_v1(const struct sk_buff *skb, const struct xt_action_param *par)
{
struct net *net = dev_net(par->in ? par->in : par->out);
const struct ipt_addrtype_info_v1 *info = par->matchinfo;
@ -70,7 +70,7 @@ addrtype_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par)
return ret;
}
static bool addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par)
static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par)
{
struct ipt_addrtype_info_v1 *info = par->matchinfo;

22
net/ipv4/netfilter/ipt_ah.c
View File

@ -5,7 +5,7 @@
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/in.h>
#include <linux/module.h>
#include <linux/skbuff.h>
@ -18,25 +18,19 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Yon Uriarte <yon@astaro.de>");
MODULE_DESCRIPTION("Xtables: IPv4 IPsec-AH SPI match");
#ifdef DEBUG_CONNTRACK
#define duprintf(format, args...) printk(format , ## args)
#else
#define duprintf(format, args...)
#endif
/* Returns 1 if the spi is matched by the range, 0 otherwise */
static inline bool
spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert)
{
bool r;
duprintf("ah spi_match:%c 0x%x <= 0x%x <= 0x%x",invert? '!':' ',
min,spi,max);
pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n",
invert ? '!' : ' ', min, spi, max);
r=(spi >= min && spi <= max) ^ invert;
duprintf(" result %s\n",r? "PASS" : "FAILED");
pr_debug(" result %s\n", r ? "PASS" : "FAILED");
return r;
}
static bool ah_mt(const struct sk_buff *skb, const struct xt_match_param *par)
static bool ah_mt(const struct sk_buff *skb, const struct xt_action_param *par)
{
struct ip_auth_hdr _ahdr;
const struct ip_auth_hdr *ah;
@ -51,7 +45,7 @@ static bool ah_mt(const struct sk_buff *skb, const struct xt_match_param *par)
/* We've been asked to examine this packet, and we
* can't. Hence, no choice but to drop.
*/
duprintf("Dropping evil AH tinygram.\n");
pr_debug("Dropping evil AH tinygram.\n");
*par->hotdrop = true;
return 0;
}
@ -61,13 +55,13 @@ static bool ah_mt(const struct sk_buff *skb, const struct xt_match_param *par)
!!(ahinfo->invflags & IPT_AH_INV_SPI));
}
static bool ah_mt_check(const struct xt_mtchk_param *par)
static int ah_mt_check(const struct xt_mtchk_param *par)
{
const struct ipt_ah *ahinfo = par->matchinfo;
/* Must specify no unknown invflags */
if (ahinfo->invflags & ~IPT_AH_INV_MASK) {
duprintf("ipt_ah: unknown flags %X\n", ahinfo->invflags);
pr_debug("unknown flags %X\n", ahinfo->invflags);
return false;
}
return true;

5
net/ipv4/netfilter/ipt_ecn.c
View File

@ -67,7 +67,8 @@ static inline bool match_tcp(const struct sk_buff *skb,
return true;
}
static bool ecn_mt(const struct sk_buff *skb, const struct xt_match_param *par)
static bool ecn_mt(const struct sk_buff *skb,
const struct xt_action_param *par)
{
const struct ipt_ecn_info *info = par->matchinfo;
@ -85,7 +86,7 @@ static bool ecn_mt(const struct sk_buff *skb, const struct xt_match_param *par)
return true;
}
static bool ecn_mt_check(const struct xt_mtchk_param *par)
static int ecn_mt_check(const struct xt_mtchk_param *par)
{
const struct ipt_ecn_info *info = par->matchinfo;
const struct ipt_ip *ip = par->entryinfo;

48
net/ipv4/netfilter/iptable_filter.c
View File

@ -23,36 +23,6 @@ MODULE_DESCRIPTION("iptables filter table");
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT))
static struct
{
struct ipt_replace repl;
struct ipt_standard entries[3];
struct ipt_error term;
} initial_table __net_initdata = {
.repl = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
.num_entries = 4,
.size = sizeof(struct ipt_standard) * 3 + sizeof(struct ipt_error),
.hook_entry = {
[NF_INET_LOCAL_IN] = 0,
[NF_INET_FORWARD] = sizeof(struct ipt_standard),
[NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2,
},
.underflow = {
[NF_INET_LOCAL_IN] = 0,
[NF_INET_FORWARD] = sizeof(struct ipt_standard),
[NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2,
},
},
.entries = {
IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */
IPT_STANDARD_INIT(NF_ACCEPT), /* FORWARD */
IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */
},
.term = IPT_ERROR_INIT, /* ERROR */
};
static const struct xt_table packet_filter = {
.name = "filter",
.valid_hooks = FILTER_VALID_HOOKS,
@ -128,9 +98,18 @@ module_param(forward, bool, 0000);
static int __net_init iptable_filter_net_init(struct net *net)
{
/* Register table */
struct ipt_replace *repl;
repl = ipt_alloc_initial_table(&packet_filter);
if (repl == NULL)
return -ENOMEM;
/* Entry 1 is the FORWARD hook */
((struct ipt_standard *)repl->entries)[1].target.verdict =
-forward - 1;
net->ipv4.iptable_filter =
ipt_register_table(net, &packet_filter, &initial_table.repl);
ipt_register_table(net, &packet_filter, repl);
kfree(repl);
if (IS_ERR(net->ipv4.iptable_filter))
return PTR_ERR(net->ipv4.iptable_filter);
return 0;
@ -138,7 +117,7 @@ static int __net_init iptable_filter_net_init(struct net *net)
static void __net_exit iptable_filter_net_exit(struct net *net)
{
ipt_unregister_table(net->ipv4.iptable_filter);
ipt_unregister_table(net, net->ipv4.iptable_filter);
}
static struct pernet_operations iptable_filter_net_ops = {
@ -155,9 +134,6 @@ static int __init iptable_filter_init(void)
return -EINVAL;
}
/* Entry 1 is the FORWARD hook */
initial_table.entries[1].target.verdict = -forward - 1;
ret = register_pernet_subsys(&iptable_filter_net_ops);
if (ret < 0)
return ret;

48
net/ipv4/netfilter/iptable_mangle.c
View File

@ -27,43 +27,6 @@ MODULE_DESCRIPTION("iptables mangle table");
(1 << NF_INET_LOCAL_OUT) | \
(1 << NF_INET_POST_ROUTING))
/* Ouch - five different hooks? Maybe this should be a config option..... -- BC */
static const struct
{
struct ipt_replace repl;
struct ipt_standard entries[5];
struct ipt_error term;
} initial_table __net_initdata = {
.repl = {
.name = "mangle",
.valid_hooks = MANGLE_VALID_HOOKS,
.num_entries = 6,
.size = sizeof(struct ipt_standard) * 5 + sizeof(struct ipt_error),
.hook_entry = {
[NF_INET_PRE_ROUTING] = 0,
[NF_INET_LOCAL_IN] = sizeof(struct ipt_standard),
[NF_INET_FORWARD] = sizeof(struct ipt_standard) * 2,
[NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 3,
[NF_INET_POST_ROUTING] = sizeof(struct ipt_standard) * 4,
},
.underflow = {
[NF_INET_PRE_ROUTING] = 0,
[NF_INET_LOCAL_IN] = sizeof(struct ipt_standard),
[NF_INET_FORWARD] = sizeof(struct ipt_standard) * 2,
[NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 3,
[NF_INET_POST_ROUTING] = sizeof(struct ipt_standard) * 4,
},
},
.entries = {
IPT_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */
IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */
IPT_STANDARD_INIT(NF_ACCEPT), /* FORWARD */
IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */
IPT_STANDARD_INIT(NF_ACCEPT), /* POST_ROUTING */
},
.term = IPT_ERROR_INIT, /* ERROR */
};
static const struct xt_table packet_mangler = {
.name = "mangle",
.valid_hooks = MANGLE_VALID_HOOKS,
@ -198,9 +161,14 @@ static struct nf_hook_ops ipt_ops[] __read_mostly = {
static int __net_init iptable_mangle_net_init(struct net *net)
{
/* Register table */
struct ipt_replace *repl;
repl = ipt_alloc_initial_table(&packet_mangler);
if (repl == NULL)
return -ENOMEM;
net->ipv4.iptable_mangle =
ipt_register_table(net, &packet_mangler, &initial_table.repl);
ipt_register_table(net, &packet_mangler, repl);
kfree(repl);
if (IS_ERR(net->ipv4.iptable_mangle))
return PTR_ERR(net->ipv4.iptable_mangle);
return 0;
@ -208,7 +176,7 @@ static int __net_init iptable_mangle_net_init(struct net *net)
static void __net_exit iptable_mangle_net_exit(struct net *net)
{
ipt_unregister_table(net->ipv4.iptable_mangle);
ipt_unregister_table(net, net->ipv4.iptable_mangle);
}
static struct pernet_operations iptable_mangle_net_ops = {

38
net/ipv4/netfilter/iptable_raw.c
View File

@ -9,33 +9,6 @@
#define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT))
static const struct
{
struct ipt_replace repl;
struct ipt_standard entries[2];
struct ipt_error term;
} initial_table __net_initdata = {
.repl = {
.name = "raw",
.valid_hooks = RAW_VALID_HOOKS,
.num_entries = 3,
.size = sizeof(struct ipt_standard) * 2 + sizeof(struct ipt_error),
.hook_entry = {
[NF_INET_PRE_ROUTING] = 0,
[NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard)
},
.underflow = {
[NF_INET_PRE_ROUTING] = 0,
[NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard)
},
},
.entries = {
IPT_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */
IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */
},
.term = IPT_ERROR_INIT, /* ERROR */
};
static const struct xt_table packet_raw = {
.name = "raw",
.valid_hooks = RAW_VALID_HOOKS,
@ -90,9 +63,14 @@ static struct nf_hook_ops ipt_ops[] __read_mostly = {
static int __net_init iptable_raw_net_init(struct net *net)
{
/* Register table */
struct ipt_replace *repl;
repl = ipt_alloc_initial_table(&packet_raw);
if (repl == NULL)
return -ENOMEM;
net->ipv4.iptable_raw =
ipt_register_table(net, &packet_raw, &initial_table.repl);
ipt_register_table(net, &packet_raw, repl);
kfree(repl);
if (IS_ERR(net->ipv4.iptable_raw))
return PTR_ERR(net->ipv4.iptable_raw);
return 0;
@ -100,7 +78,7 @@ static int __net_init iptable_raw_net_init(struct net *net)
static void __net_exit iptable_raw_net_exit(struct net *net)
{
ipt_unregister_table(net->ipv4.iptable_raw);
ipt_unregister_table(net, net->ipv4.iptable_raw);
}
static struct pernet_operations iptable_raw_net_ops = {

41
net/ipv4/netfilter/iptable_security.c
View File

@ -27,36 +27,6 @@ MODULE_DESCRIPTION("iptables security table, for MAC rules");
(1 << NF_INET_FORWARD) | \
(1 << NF_INET_LOCAL_OUT)
static const struct
{
struct ipt_replace repl;
struct ipt_standard entries[3];
struct ipt_error term;
} initial_table __net_initdata = {
.repl = {
.name = "security",
.valid_hooks = SECURITY_VALID_HOOKS,
.num_entries = 4,
.size = sizeof(struct ipt_standard) * 3 + sizeof(struct ipt_error),
.hook_entry = {
[NF_INET_LOCAL_IN] = 0,
[NF_INET_FORWARD] = sizeof(struct ipt_standard),
[NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2,
},
.underflow = {
[NF_INET_LOCAL_IN] = 0,
[NF_INET_FORWARD] = sizeof(struct ipt_standard),
[NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2,
},
},
.entries = {
IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */
IPT_STANDARD_INIT(NF_ACCEPT), /* FORWARD */
IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */
},
.term = IPT_ERROR_INIT, /* ERROR */
};
static const struct xt_table security_table = {
.name = "security",
.valid_hooks = SECURITY_VALID_HOOKS,
@ -127,9 +97,14 @@ static struct nf_hook_ops ipt_ops[] __read_mostly = {
static int __net_init iptable_security_net_init(struct net *net)
{
net->ipv4.iptable_security =
ipt_register_table(net, &security_table, &initial_table.repl);
struct ipt_replace *repl;
repl = ipt_alloc_initial_table(&security_table);
if (repl == NULL)
return -ENOMEM;
net->ipv4.iptable_security =
ipt_register_table(net, &security_table, repl);
kfree(repl);
if (IS_ERR(net->ipv4.iptable_security))
return PTR_ERR(net->ipv4.iptable_security);
@ -138,7 +113,7 @@ static int __net_init iptable_security_net_init(struct net *net)
static void __net_exit iptable_security_net_exit(struct net *net)
{
ipt_unregister_table(net->ipv4.iptable_security);
ipt_unregister_table(net, net->ipv4.iptable_security);
}
static struct pernet_operations iptable_security_net_ops = {

5
net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
View File

@ -22,6 +22,7 @@
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
#include <net/netfilter/nf_nat_helper.h>
@ -100,7 +101,7 @@ static unsigned int ipv4_confirm(unsigned int hooknum,
/* This is where we call the helper: as the packet goes out. */
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
goto out;
help = nfct_help(ct);
@ -274,7 +275,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len)
return -EINVAL;
}
h = nf_conntrack_find_get(sock_net(sk), &tuple);
h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple);
if (h) {
struct sockaddr_in sin;
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);

11
net/ipv4/netfilter/nf_conntrack_proto_icmp.c
View File

@ -18,6 +18,7 @@
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_log.h>
static unsigned int nf_ct_icmp_timeout __read_mostly = 30*HZ;
@ -114,13 +115,14 @@ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb,
/* Returns conntrack if it dealt with ICMP, and filled in skb fields */
static int
icmp_error_message(struct net *net, struct sk_buff *skb,
icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
enum ip_conntrack_info *ctinfo,
unsigned int hooknum)
{
struct nf_conntrack_tuple innertuple, origtuple;
const struct nf_conntrack_l4proto *innerproto;
const struct nf_conntrack_tuple_hash *h;
u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
NF_CT_ASSERT(skb->nfct == NULL);
@ -146,7 +148,7 @@ icmp_error_message(struct net *net, struct sk_buff *skb,
*ctinfo = IP_CT_RELATED;
h = nf_conntrack_find_get(net, &innertuple);
h = nf_conntrack_find_get(net, zone, &innertuple);
if (!h) {
pr_debug("icmp_error_message: no match\n");
return -NF_ACCEPT;
@ -163,7 +165,8 @@ icmp_error_message(struct net *net, struct sk_buff *skb,
/* Small and modified version of icmp_rcv */
static int
icmp_error(struct net *net, struct sk_buff *skb, unsigned int dataoff,
icmp_error(struct net *net, struct nf_conn *tmpl,
struct sk_buff *skb, unsigned int dataoff,
enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum)
{
const struct icmphdr *icmph;
@ -208,7 +211,7 @@ icmp_error(struct net *net, struct sk_buff *skb, unsigned int dataoff,
&& icmph->type != ICMP_REDIRECT)
return NF_ACCEPT;
return icmp_error_message(net, skb, ctinfo, hooknum);
return icmp_error_message(net, tmpl, skb, ctinfo, hooknum);
}
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)

14
net/ipv4/netfilter/nf_defrag_ipv4.c
View File

@ -16,6 +16,7 @@
#include <linux/netfilter_bridge.h>
#include <linux/netfilter_ipv4.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
/* Returns new sk_buff, or NULL */
@ -38,15 +39,20 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
struct sk_buff *skb)
{
u16 zone = NF_CT_DEFAULT_ZONE;
if (skb->nfct)
zone = nf_ct_zone((struct nf_conn *)skb->nfct);
#ifdef CONFIG_BRIDGE_NETFILTER
if (skb->nf_bridge &&
skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
return IP_DEFRAG_CONNTRACK_BRIDGE_IN;
return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
#endif
if (hooknum == NF_INET_PRE_ROUTING)
return IP_DEFRAG_CONNTRACK_IN;
return IP_DEFRAG_CONNTRACK_IN + zone;
else
return IP_DEFRAG_CONNTRACK_OUT;
return IP_DEFRAG_CONNTRACK_OUT + zone;
}
static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
@ -59,7 +65,7 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
#if !defined(CONFIG_NF_NAT) && !defined(CONFIG_NF_NAT_MODULE)
/* Previously seen (loopback)? Ignore. Do this before
fragment check. */
if (skb->nfct)
if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct))
return NF_ACCEPT;
#endif
#endif

28
net/ipv4/netfilter/nf_nat_core.c
View File

@ -30,6 +30,7 @@
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_zones.h>
static DEFINE_SPINLOCK(nf_nat_lock);
@ -69,13 +70,14 @@ EXPORT_SYMBOL_GPL(nf_nat_proto_put);
/* We keep an extra hash for each conntrack, for fast searching. */
static inline unsigned int
hash_by_src(const struct net *net, const struct nf_conntrack_tuple *tuple)
hash_by_src(const struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple)
{
unsigned int hash;
/* Original src, to ensure we map it consistently if poss. */
hash = jhash_3words((__force u32)tuple->src.u3.ip,
(__force u32)tuple->src.u.all,
(__force u32)tuple->src.u.all ^ zone,
tuple->dst.protonum, 0);
return ((u64)hash * net->ipv4.nat_htable_size) >> 32;
}
@ -139,12 +141,12 @@ same_src(const struct nf_conn *ct,
/* Only called for SRC manip */
static int
find_appropriate_src(struct net *net,
find_appropriate_src(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *result,
const struct nf_nat_range *range)
{
unsigned int h = hash_by_src(net, tuple);
unsigned int h = hash_by_src(net, zone, tuple);
const struct nf_conn_nat *nat;
const struct nf_conn *ct;
const struct hlist_node *n;
@ -152,7 +154,7 @@ find_appropriate_src(struct net *net,
rcu_read_lock();
hlist_for_each_entry_rcu(nat, n, &net->ipv4.nat_bysource[h], bysource) {
ct = nat->ct;
if (same_src(ct, tuple)) {
if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) {
/* Copy source part from reply tuple. */
nf_ct_invert_tuplepr(result,
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
@ -175,7 +177,7 @@ find_appropriate_src(struct net *net,
the ip with the lowest src-ip/dst-ip/proto usage.
*/
static void
find_best_ips_proto(struct nf_conntrack_tuple *tuple,
find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
const struct nf_conn *ct,
enum nf_nat_manip_type maniptype)
@ -209,7 +211,7 @@ find_best_ips_proto(struct nf_conntrack_tuple *tuple,
maxip = ntohl(range->max_ip);
j = jhash_2words((__force u32)tuple->src.u3.ip,
range->flags & IP_NAT_RANGE_PERSISTENT ?
0 : (__force u32)tuple->dst.u3.ip, 0);
0 : (__force u32)tuple->dst.u3.ip ^ zone, 0);
j = ((u64)j * (maxip - minip + 1)) >> 32;
*var_ipp = htonl(minip + j);
}
@ -229,6 +231,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
{
struct net *net = nf_ct_net(ct);
const struct nf_nat_protocol *proto;
u16 zone = nf_ct_zone(ct);
/* 1) If this srcip/proto/src-proto-part is currently mapped,
and that same mapping gives a unique tuple within the given
@ -239,7 +242,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
manips not an issue. */
if (maniptype == IP_NAT_MANIP_SRC &&
!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) {
if (find_appropriate_src(net, orig_tuple, tuple, range)) {
if (find_appropriate_src(net, zone, orig_tuple, tuple, range)) {
pr_debug("get_unique_tuple: Found current src map\n");
if (!nf_nat_used_tuple(tuple, ct))
return;
@ -249,7 +252,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
/* 2) Select the least-used IP/proto combination in the given
range. */
*tuple = *orig_tuple;
find_best_ips_proto(tuple, range, ct, maniptype);
find_best_ips_proto(zone, tuple, range, ct, maniptype);
/* 3) The per-protocol part of the manip is made to map into
the range to make a unique tuple. */
@ -327,7 +330,8 @@ nf_nat_setup_info(struct nf_conn *ct,
if (have_to_hash) {
unsigned int srchash;
srchash = hash_by_src(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
srchash = hash_by_src(net, nf_ct_zone(ct),
&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
spin_lock_bh(&nf_nat_lock);
/* nf_conntrack_alter_reply might re-allocate exntension aera */
nat = nfct_nat(ct);
@ -444,7 +448,7 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
/* Must be RELATED */
NF_CT_ASSERT(skb->nfctinfo == IP_CT_RELATED ||
skb->nfctinfo == IP_CT_RELATED+IP_CT_IS_REPLY);
skb->nfctinfo == IP_CT_RELATED_REPLY);
/* Redirects on non-null nats must be dropped, else they'll
start talking to each other without our translation, and be
@ -737,7 +741,7 @@ static int __init nf_nat_init(void)
spin_unlock_bh(&nf_nat_lock);
/* Initialize fake conntrack so that NAT will skip it */
nf_conntrack_untracked.status |= IPS_NAT_DONE_MASK;
nf_ct_untracked_status_or(IPS_NAT_DONE_MASK);
l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET);

3
net/ipv4/netfilter/nf_nat_pptp.c
View File

@ -25,6 +25,7 @@
#include <net/netfilter/nf_nat_rule.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <linux/netfilter/nf_conntrack_proto_gre.h>
#include <linux/netfilter/nf_conntrack_pptp.h>
@ -74,7 +75,7 @@ static void pptp_nat_expected(struct nf_conn *ct,
pr_debug("trying to unexpect other dir: ");
nf_ct_dump_tuple_ip(&t);
other_exp = nf_ct_expect_find_get(net, &t);
other_exp = nf_ct_expect_find_get(net, nf_ct_zone(ct), &t);
if (other_exp) {
nf_ct_unexpect_related(other_exp);
nf_ct_expect_put(other_exp);

1
net/ipv4/netfilter/nf_nat_proto_common.c
View File

@ -12,6 +12,7 @@
#include <linux/ip.h>
#include <linux/netfilter.h>
#include <net/secure_seq.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_rule.h>

47
net/ipv4/netfilter/nf_nat_rule.c
View File

@ -28,36 +28,6 @@
(1 << NF_INET_POST_ROUTING) | \
(1 << NF_INET_LOCAL_OUT))
static const struct
{
struct ipt_replace repl;
struct ipt_standard entries[3];
struct ipt_error term;
} nat_initial_table __net_initdata = {
.repl = {
.name = "nat",
.valid_hooks = NAT_VALID_HOOKS,
.num_entries = 4,
.size = sizeof(struct ipt_standard) * 3 + sizeof(struct ipt_error),
.hook_entry = {
[NF_INET_PRE_ROUTING] = 0,
[NF_INET_POST_ROUTING] = sizeof(struct ipt_standard),
[NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2
},
.underflow = {
[NF_INET_PRE_ROUTING] = 0,
[NF_INET_POST_ROUTING] = sizeof(struct ipt_standard),
[NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2
},
},
.entries = {
IPT_STANDARD_INIT(NF_ACCEPT), /* PRE_ROUTING */
IPT_STANDARD_INIT(NF_ACCEPT), /* POST_ROUTING */
IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */
},
.term = IPT_ERROR_INIT, /* ERROR */
};
static const struct xt_table nat_table = {
.name = "nat",
.valid_hooks = NAT_VALID_HOOKS,
@ -67,7 +37,7 @@ static const struct xt_table nat_table = {
/* Source NAT */
static unsigned int
ipt_snat_target(struct sk_buff *skb, const struct xt_target_param *par)
ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par)
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
@ -79,14 +49,14 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_target_param *par)
/* Connection must be valid and new. */
NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY));
ctinfo == IP_CT_RELATED_REPLY));
NF_CT_ASSERT(par->out != NULL);
return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_SRC);
}
static unsigned int
ipt_dnat_target(struct sk_buff *skb, const struct xt_target_param *par)
ipt_dnat_target(struct sk_buff *skb, const struct xt_action_param *par)
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
@ -186,8 +156,13 @@ static struct xt_target ipt_dnat_reg __read_mostly = {
static int __net_init nf_nat_rule_net_init(struct net *net)
{
net->ipv4.nat_table = ipt_register_table(net, &nat_table,
&nat_initial_table.repl);
struct ipt_replace *repl;
repl = ipt_alloc_initial_table(&nat_table);
if (repl == NULL)
return -ENOMEM;
net->ipv4.nat_table = ipt_register_table(net, &nat_table, repl);
kfree(repl);
if (IS_ERR(net->ipv4.nat_table))
return PTR_ERR(net->ipv4.nat_table);
return 0;
@ -195,7 +170,7 @@ static int __net_init nf_nat_rule_net_init(struct net *net)
static void __net_exit nf_nat_rule_net_exit(struct net *net)
{
ipt_unregister_table(net->ipv4.nat_table);
ipt_unregister_table(net, net->ipv4.nat_table);
}
static struct pernet_operations nf_nat_rule_net_ops = {

6
net/ipv4/netfilter/nf_nat_standalone.c
View File

@ -97,7 +97,7 @@ nf_nat_fn(unsigned int hooknum,
return NF_ACCEPT;
/* Don't try to NAT if this packet is not conntracked */
if (ct == &nf_conntrack_untracked)
if (nf_ct_is_untracked(ct))
return NF_ACCEPT;
nat = nfct_nat(ct);
@ -114,7 +114,7 @@ nf_nat_fn(unsigned int hooknum,
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED+IP_CT_IS_REPLY:
case IP_CT_RELATED_REPLY:
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(ct, ctinfo,
hooknum, skb))
@ -149,7 +149,7 @@ nf_nat_fn(unsigned int hooknum,
default:
/* ESTABLISHED */
NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY));
ctinfo == IP_CT_ESTABLISHED_REPLY);
}
return nf_nat_packet(ct, ctinfo, hooknum, skb);

22
net/ipv4/route.c
View File

@ -107,6 +107,7 @@
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <net/secure_seq.h>
#define RT_FL_TOS(oldflp) \
((u32)(oldflp->fl4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))
@ -287,12 +288,12 @@ static struct rtable *rt_cache_get_first(struct seq_file *seq)
if (!rt_hash_table[st->bucket].chain)
continue;
rcu_read_lock_bh();
r = rcu_dereference(rt_hash_table[st->bucket].chain);
r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
while (r) {
if (dev_net(r->u.dst.dev) == seq_file_net(seq) &&
r->rt_genid == st->genid)
return r;
r = rcu_dereference(r->u.dst.rt_next);
r = rcu_dereference_bh(r->u.dst.rt_next);
}
rcu_read_unlock_bh();
}
@ -314,7 +315,7 @@ static struct rtable *__rt_cache_get_next(struct seq_file *seq,
rcu_read_lock_bh();
r = rt_hash_table[st->bucket].chain;
}
return rcu_dereference(r);
return rcu_dereference_bh(r);
}
static struct rtable *rt_cache_get_next(struct seq_file *seq,
@ -2685,8 +2686,8 @@ int __ip_route_output_key(struct net *net, struct rtable **rp,
hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif, rt_genid(net));
rcu_read_lock_bh();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
rth = rcu_dereference(rth->u.dst.rt_next)) {
for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
rth = rcu_dereference_bh(rth->u.dst.rt_next)) {
if (rth->fl.fl4_dst == flp->fl4_dst &&
rth->fl.fl4_src == flp->fl4_src &&
rth->fl.iif == 0 &&
@ -2712,6 +2713,11 @@ slow_output:
EXPORT_SYMBOL_GPL(__ip_route_output_key);
static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
{
return NULL;
}
static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
{
}
@ -2720,7 +2726,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.destroy = ipv4_dst_destroy,
.check = ipv4_dst_check,
.check = ipv4_blackhole_dst_check,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
.entries = ATOMIC_INIT(0),
};
@ -3004,8 +3010,8 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb)
if (!rt_hash_table[h].chain)
continue;
rcu_read_lock_bh();
for (rt = rcu_dereference(rt_hash_table[h].chain), idx = 0; rt;
rt = rcu_dereference(rt->u.dst.rt_next), idx++) {
for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt;
rt = rcu_dereference_bh(rt->u.dst.rt_next), idx++) {
if (!net_eq(dev_net(rt->u.dst.dev), net) || idx < s_idx)
continue;
if (rt_is_expired(rt))

71
net/ipv4/tcp.c
View File

@ -265,6 +265,10 @@
#include <linux/err.h>
#include <linux/crypto.h>
#ifdef CONFIG_UID_STAT
#include <linux/uid_stat.h>
#endif
#include <net/icmp.h>
#include <net/tcp.h>
#include <net/xfrm.h>
@ -386,8 +390,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
*/
mask = 0;
if (sk->sk_err)
mask = POLLERR;
/*
* POLLHUP is certainly not done right. But poll() doesn't
@ -451,11 +453,17 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
mask |= POLLOUT | POLLWRNORM;
}
}
} else
mask |= POLLOUT | POLLWRNORM;
if (tp->urg_data & TCP_URG_VALID)
mask |= POLLPRI;
}
/* This barrier is coupled with smp_wmb() in tcp_reset() */
smp_rmb();
if (sk->sk_err)
mask |= POLLERR;
return mask;
}
@ -934,7 +942,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
goto out_err;
while (--iovlen >= 0) {
int seglen = iov->iov_len;
size_t seglen = iov->iov_len;
unsigned char __user *from = iov->iov_base;
iov++;
@ -1098,6 +1106,11 @@ out:
tcp_push(sk, flags, mss_now, tp->nonagle);
TCP_CHECK_TIMER(sk);
release_sock(sk);
#ifdef CONFIG_UID_STAT
if (copied > 0)
update_tcp_snd(current_uid(), copied);
#endif
return copied;
do_fault:
@ -1334,14 +1347,19 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
sk_eat_skb(sk, skb, 0);
if (!desc->count)
break;
tp->copied_seq = seq;
}
tp->copied_seq = seq;
tcp_rcv_space_adjust(sk);
/* Clean up data we have read: This will do ACK frames. */
if (copied > 0)
if (copied > 0) {
tcp_cleanup_rbuf(sk, copied);
#ifdef CONFIG_UID_STAT
update_tcp_rcv(current_uid(), copied);
#endif
}
return copied;
}
@ -1737,6 +1755,10 @@ skip_copy:
TCP_CHECK_TIMER(sk);
release_sock(sk);
#ifdef CONFIG_UID_STAT
if (copied > 0)
update_tcp_rcv(current_uid(), copied);
#endif
return copied;
out:
@ -1746,6 +1768,10 @@ out:
recv_urg:
err = tcp_recv_urg(sk, msg, len, flags);
#ifdef CONFIG_UID_STAT
if (err > 0)
update_tcp_rcv(current_uid(), err);
#endif
goto out;
}
@ -1975,11 +2001,8 @@ adjudge_to_death:
}
}
if (sk->sk_state != TCP_CLOSE) {
int orphan_count = percpu_counter_read_positive(
sk->sk_prot->orphan_count);
sk_mem_reclaim(sk);
if (tcp_too_many_orphans(sk, orphan_count)) {
if (tcp_too_many_orphans(sk, 0)) {
if (net_ratelimit())
printk(KERN_INFO "TCP: too many of orphaned "
"sockets\n");
@ -2115,7 +2138,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
/* Values greater than interface MTU won't take effect. However
* at the point when this call is done we typically don't yet
* know which interface is going to be used */
if (val < 8 || val > MAX_TCP_WINDOW) {
if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) {
err = -EINVAL;
break;
}
@ -2880,7 +2903,7 @@ void __init tcp_init(void)
{
struct sk_buff *skb = NULL;
unsigned long nr_pages, limit;
int order, i, max_share;
int i, max_share, cnt;
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@ -2929,31 +2952,23 @@ void __init tcp_init(void)
INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
}
/* Try to be a bit smarter and adjust defaults depending
* on available memory.
*/
for (order = 0; ((1 << order) << PAGE_SHIFT) <
(tcp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket));
order++)
;
if (order >= 4) {
tcp_death_row.sysctl_max_tw_buckets = 180000;
sysctl_tcp_max_orphans = 4096 << (order - 4);
sysctl_max_syn_backlog = 1024;
} else if (order < 3) {
tcp_death_row.sysctl_max_tw_buckets >>= (3 - order);
sysctl_tcp_max_orphans >>= (3 - order);
sysctl_max_syn_backlog = 128;
}
cnt = tcp_hashinfo.ehash_size;
tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
sysctl_tcp_max_orphans = cnt / 2;
sysctl_max_syn_backlog = max(128, cnt / 256);
/* Set the pressure threshold to be a fraction of global memory that
* is up to 1/2 at 256 MB, decreasing toward zero with the amount of
* memory, with a floor of 128 pages.
* memory, with a floor of 128 pages, and a ceiling that prevents an
* integer overflow.
*/
nr_pages = totalram_pages - totalhigh_pages;
limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT);
limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11);
limit = max(limit, 128UL);
limit = min(limit, INT_MAX * 4UL / 3 / 2);
sysctl_tcp_mem[0] = limit / 4 * 3;
sysctl_tcp_mem[1] = limit;
sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;

2
net/ipv4/tcp_input.c
View File

@ -3969,6 +3969,8 @@ static void tcp_reset(struct sock *sk)
default:
sk->sk_err = ECONNRESET;
}
/* This barrier is coupled with smp_rmb() in tcp_poll() */
smp_wmb();
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_error_report(sk);

1
net/ipv4/tcp_ipv4.c
View File

@ -71,6 +71,7 @@
#include <net/timewait_sock.h>
#include <net/xfrm.h>
#include <net/netdma.h>
#include <net/secure_seq.h>
#include <linux/inet.h>
#include <linux/ipv6.h>

5
net/ipv4/tcp_output.c
View File

@ -231,8 +231,6 @@ void tcp_select_initial_window(int __space, __u32 mss,
if (*rcv_wnd > init_cwnd * mss)
*rcv_wnd = init_cwnd * mss;
}
/* Lock the initial TCP window size to 64K*/
*rcv_wnd = 64240;
/* Set the clamp no higher than max representable value */
(*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp);
@ -2039,6 +2037,9 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
int mib_idx;
int fwd_rexmitting = 0;
if (!tp->packets_out)
return;
if (!tp->lost_out)
tp->retransmit_high = tp->snd_una;

8
net/ipv4/tcp_timer.c
View File

@ -65,18 +65,18 @@ static void tcp_write_err(struct sock *sk)
static int tcp_out_of_resources(struct sock *sk, int do_reset)
{
struct tcp_sock *tp = tcp_sk(sk);
int orphans = percpu_counter_read_positive(&tcp_orphan_count);
int shift = 0;
/* If peer does not open window for long time, or did not transmit
* anything for long time, penalize it. */
if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset)
orphans <<= 1;
shift++;
/* If some dubious ICMP arrived, penalize even more. */
if (sk->sk_err_soft)
orphans <<= 1;
shift++;
if (tcp_too_many_orphans(sk, orphans)) {
if (tcp_too_many_orphans(sk, shift)) {
if (net_ratelimit())
printk(KERN_INFO "Out of socket memory\n");

Some files were not shown because too many files have changed in this diff Show More