Free Electrons

Embedded Linux Experts

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
#ifndef _X_TABLES_H
#define _X_TABLES_H


#include <linux/netdevice.h>
#include <linux/static_key.h>
#include <uapi/linux/netfilter/x_tables.h>

/**
 * struct xt_action_param - parameters for matches/targets
 *
 * @match:	the match extension
 * @target:	the target extension
 * @matchinfo:	per-match data
 * @targetinfo:	per-target data
 * @net		network namespace through which the action was invoked
 * @in:		input netdevice
 * @out:	output netdevice
 * @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
 * @family:	Actual NFPROTO_* through which the function is invoked
 * 		(helpful when match->family == NFPROTO_UNSPEC)
 *
 * Fields written to by extensions:
 *
 * @hotdrop:	drop packet if we had inspection problems
 */
struct xt_action_param {
	union {
		const struct xt_match *match;
		const struct xt_target *target;
	};
	union {
		const void *matchinfo, *targinfo;
	};
	struct net *net;
	const struct net_device *in, *out;
	int fragoff;
	unsigned int thoff;
	unsigned int hooknum;
	u_int8_t family;
	bool hotdrop;
};

/**
 * struct xt_mtchk_param - parameters for match extensions'
 * checkentry functions
 *
 * @net:	network namespace through which the check was invoked
 * @table:	table the rule is tried to be inserted into
 * @entryinfo:	the family-specific rule data
 * 		(struct ipt_ip, ip6t_ip, arpt_arp or (note) ebt_entry)
 * @match:	struct xt_match through which this function was invoked
 * @matchinfo:	per-match data
 * @hook_mask:	via which hooks the new rule is reachable
 * Other fields as above.
 */
struct xt_mtchk_param {
	struct net *net;
	const char *table;
	const void *entryinfo;
	const struct xt_match *match;
	void *matchinfo;
	unsigned int hook_mask;
	u_int8_t family;
	bool nft_compat;
};

/**
 * struct xt_mdtor_param - match destructor parameters
 * Fields as above.
 */
struct xt_mtdtor_param {
	struct net *net;
	const struct xt_match *match;
	void *matchinfo;
	u_int8_t family;
};

/**
 * struct xt_tgchk_param - parameters for target extensions'
 * checkentry functions
 *
 * @entryinfo:	the family-specific rule data
 * 		(struct ipt_entry, ip6t_entry, arpt_entry, ebt_entry)
 *
 * Other fields see above.
 */
struct xt_tgchk_param {
	struct net *net;
	const char *table;
	const void *entryinfo;
	const struct xt_target *target;
	void *targinfo;
	unsigned int hook_mask;
	u_int8_t family;
	bool nft_compat;
};

/* Target destructor parameters */
struct xt_tgdtor_param {
	struct net *net;
	const struct xt_target *target;
	void *targinfo;
	u_int8_t family;
};

struct xt_match {
	struct list_head list;

	const char name[XT_EXTENSION_MAXNAMELEN];
	u_int8_t revision;

	/* Return true or false: return FALSE and set *hotdrop = 1 to
           force immediate packet drop. */
	/* Arguments changed since 2.6.9, as this must now handle
	   non-linear skb, using skb_header_pointer and
	   skb_ip_make_writable. */
	bool (*match)(const struct sk_buff *skb,
		      struct xt_action_param *);

	/* Called when user tries to insert an entry of this type. */
	int (*checkentry)(const struct xt_mtchk_param *);

	/* Called when entry of this type deleted. */
	void (*destroy)(const struct xt_mtdtor_param *);
#ifdef CONFIG_COMPAT
	/* Called when userspace align differs from kernel space one */
	void (*compat_from_user)(void *dst, const void *src);
	int (*compat_to_user)(void __user *dst, const void *src);
#endif
	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
	struct module *me;

	const char *table;
	unsigned int matchsize;
#ifdef CONFIG_COMPAT
	unsigned int compatsize;
#endif
	unsigned int hooks;
	unsigned short proto;

	unsigned short family;
};

/* Registration hooks for targets. */
struct xt_target {
	struct list_head list;

	const char name[XT_EXTENSION_MAXNAMELEN];
	u_int8_t revision;

	/* Returns verdict. Argument order changed since 2.6.9, as this
	   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_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
           called. */
	/* Should return 0 on success or an error code otherwise (-Exxxx). */
	int (*checkentry)(const struct xt_tgchk_param *);

	/* Called when entry of this type deleted. */
	void (*destroy)(const struct xt_tgdtor_param *);
#ifdef CONFIG_COMPAT
	/* Called when userspace align differs from kernel space one */
	void (*compat_from_user)(void *dst, const void *src);
	int (*compat_to_user)(void __user *dst, const void *src);
#endif
	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
	struct module *me;

	const char *table;
	unsigned int targetsize;
#ifdef CONFIG_COMPAT
	unsigned int compatsize;
#endif
	unsigned int hooks;
	unsigned short proto;

	unsigned short family;
};

/* Furniture shopping... */
struct xt_table {
	struct list_head list;

	/* What hooks you will enter on */
	unsigned int valid_hooks;

	/* Man behind the curtain... */
	struct xt_table_info *private;

	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
	struct module *me;

	u_int8_t af;		/* address/protocol family */
	int priority;		/* hook order */

	/* A unique name... */
	const char name[XT_TABLE_MAXNAMELEN];
};

#include <linux/netfilter_ipv4.h>

/* The table itself */
struct xt_table_info {
	/* Size per table */
	unsigned int size;
	/* Number of entries: FIXME. --RR */
	unsigned int number;
	/* Initial number of entries. Needed for module usage count */
	unsigned int initial_entries;

	/* Entry points and underflows */
	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;
	void ***jumpstack;

	unsigned char entries[0] __aligned(8);
};

int xt_register_target(struct xt_target *target);
void xt_unregister_target(struct xt_target *target);
int xt_register_targets(struct xt_target *target, unsigned int n);
void xt_unregister_targets(struct xt_target *target, unsigned int n);

int xt_register_match(struct xt_match *target);
void xt_unregister_match(struct xt_match *target);
int xt_register_matches(struct xt_match *match, unsigned int n);
void xt_unregister_matches(struct xt_match *match, unsigned int n);

int xt_check_entry_offsets(const void *base, const char *elems,
			   unsigned int target_offset,
			   unsigned int next_offset);

int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto,
		   bool inv_proto);
int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto,
		    bool inv_proto);

void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
				 struct xt_counters_info *info, bool compat);

struct xt_table *xt_register_table(struct net *net,
				   const struct xt_table *table,
				   struct xt_table_info *bootstrap,
				   struct xt_table_info *newinfo);
void *xt_unregister_table(struct xt_table *table);

struct xt_table_info *xt_replace_table(struct xt_table *table,
				       unsigned int num_counters,
				       struct xt_table_info *newinfo,
				       int *error);

struct xt_match *xt_find_match(u8 af, const char *name, u8 revision);
struct xt_target *xt_find_target(u8 af, const char *name, u8 revision);
struct xt_match *xt_request_find_match(u8 af, const char *name, u8 revision);
struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision);
int xt_find_revision(u8 af, const char *name, u8 revision, int target,
		     int *err);

struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
				    const char *name);
void xt_table_unlock(struct xt_table *t);

int xt_proto_init(struct net *net, u_int8_t af);
void xt_proto_fini(struct net *net, u_int8_t af);

struct xt_table_info *xt_alloc_table_info(unsigned int size);
void xt_free_table_info(struct xt_table_info *info);

/**
 * xt_recseq - recursive seqcount for netfilter use
 * 
 * Packet processing changes the seqcount only if no recursion happened
 * get_counters() can use read_seqcount_begin()/read_seqcount_retry(),
 * because we use the normal seqcount convention :
 * Low order bit set to 1 if a writer is active.
 */
DECLARE_PER_CPU(seqcount_t, xt_recseq);

/* xt_tee_enabled - true if x_tables needs to handle reentrancy
 *
 * Enabled if current ip(6)tables ruleset has at least one -j TEE rule.
 */
extern struct static_key xt_tee_enabled;

/**
 * xt_write_recseq_begin - start of a write section
 *
 * Begin packet processing : all readers must wait the end
 * 1) Must be called with preemption disabled
 * 2) softirqs must be disabled too (or we should use this_cpu_add())
 * Returns :
 *  1 if no recursion on this cpu
 *  0 if recursion detected
 */
static inline unsigned int xt_write_recseq_begin(void)
{
	unsigned int addend;

	/*
	 * Low order bit of sequence is set if we already
	 * called xt_write_recseq_begin().
	 */
	addend = (__this_cpu_read(xt_recseq.sequence) + 1) & 1;

	/*
	 * This is kind of a write_seqcount_begin(), but addend is 0 or 1
	 * We dont check addend value to avoid a test and conditional jump,
	 * since addend is most likely 1
	 */
	__this_cpu_add(xt_recseq.sequence, addend);
	smp_wmb();

	return addend;
}

/**
 * xt_write_recseq_end - end of a write section
 * @addend: return value from previous xt_write_recseq_begin()
 *
 * End packet processing : all readers can proceed
 * 1) Must be called with preemption disabled
 * 2) softirqs must be disabled too (or we should use this_cpu_add())
 */
static inline void xt_write_recseq_end(unsigned int addend)
{
	/* this is kind of a write_seqcount_end(), but addend is 0 or 1 */
	smp_wmb();
	__this_cpu_add(xt_recseq.sequence, addend);
}

/*
 * This helper is performance critical and must be inlined
 */
static inline unsigned long ifname_compare_aligned(const char *_a,
						   const char *_b,
						   const char *_mask)
{
	const unsigned long *a = (const unsigned long *)_a;
	const unsigned long *b = (const unsigned long *)_b;
	const unsigned long *mask = (const unsigned long *)_mask;
	unsigned long ret;

	ret = (a[0] ^ b[0]) & mask[0];
	if (IFNAMSIZ > sizeof(unsigned long))
		ret |= (a[1] ^ b[1]) & mask[1];
	if (IFNAMSIZ > 2 * sizeof(unsigned long))
		ret |= (a[2] ^ b[2]) & mask[2];
	if (IFNAMSIZ > 3 * sizeof(unsigned long))
		ret |= (a[3] ^ b[3]) & mask[3];
	BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long));
	return ret;
}


/* On SMP, ip(6)t_entry->counters.pcnt holds address of the
 * real (percpu) counter.  On !SMP, its just the packet count,
 * so nothing needs to be done there.
 *
 * xt_percpu_counter_alloc returns the address of the percpu
 * counter, or 0 on !SMP. We force an alignment of 16 bytes
 * so that bytes/packets share a common cache line.
 *
 * Hence caller must use IS_ERR_VALUE to check for error, this
 * allows us to return 0 for single core systems without forcing
 * callers to deal with SMP vs. NONSMP issues.
 */
static inline u64 xt_percpu_counter_alloc(void)
{
	if (nr_cpu_ids > 1) {
		void __percpu *res = __alloc_percpu(sizeof(struct xt_counters),
						    sizeof(struct xt_counters));

		if (res == NULL)
			return (u64) -ENOMEM;

		return (u64) (__force unsigned long) res;
	}

	return 0;
}
static inline void xt_percpu_counter_free(u64 pcnt)
{
	if (nr_cpu_ids > 1)
		free_percpu((void __percpu *) (unsigned long) pcnt);
}

static inline struct xt_counters *
xt_get_this_cpu_counter(struct xt_counters *cnt)
{
	if (nr_cpu_ids > 1)
		return this_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt);

	return cnt;
}

static inline struct xt_counters *
xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu)
{
	if (nr_cpu_ids > 1)
		return per_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt, cpu);

	return cnt;
}

struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *);
void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *);

#ifdef CONFIG_COMPAT
#include <net/compat.h>

struct compat_xt_entry_match {
	union {
		struct {
			u_int16_t match_size;
			char name[XT_FUNCTION_MAXNAMELEN - 1];
			u_int8_t revision;
		} user;
		struct {
			u_int16_t match_size;
			compat_uptr_t match;
		} kernel;
		u_int16_t match_size;
	} u;
	unsigned char data[0];
};

struct compat_xt_entry_target {
	union {
		struct {
			u_int16_t target_size;
			char name[XT_FUNCTION_MAXNAMELEN - 1];
			u_int8_t revision;
		} user;
		struct {
			u_int16_t target_size;
			compat_uptr_t target;
		} kernel;
		u_int16_t target_size;
	} u;
	unsigned char data[0];
};

/* FIXME: this works only on 32 bit tasks
 * need to change whole approach in order to calculate align as function of
 * current task alignment */

struct compat_xt_counters {
	compat_u64 pcnt, bcnt;			/* Packet and byte counters */
};

struct compat_xt_counters_info {
	char name[XT_TABLE_MAXNAMELEN];
	compat_uint_t num_counters;
	struct compat_xt_counters counters[0];
};

struct _compat_xt_align {
	__u8 u8;
	__u16 u16;
	__u32 u32;
	compat_u64 u64;
};

#define COMPAT_XT_ALIGN(s) __ALIGN_KERNEL((s), __alignof__(struct _compat_xt_align))

void xt_compat_lock(u_int8_t af);
void xt_compat_unlock(u_int8_t af);

int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta);
void xt_compat_flush_offsets(u_int8_t af);
void xt_compat_init_offsets(u_int8_t af, unsigned int number);
int xt_compat_calc_jump(u_int8_t af, unsigned int offset);

int xt_compat_match_offset(const struct xt_match *match);
void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
			      unsigned int *size);
int xt_compat_match_to_user(const struct xt_entry_match *m,
			    void __user **dstptr, unsigned int *size);

int xt_compat_target_offset(const struct xt_target *target);
void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
				unsigned int *size);
int xt_compat_target_to_user(const struct xt_entry_target *t,
			     void __user **dstptr, unsigned int *size);
int xt_compat_check_entry_offsets(const void *base, const char *elems,
				  unsigned int target_offset,
				  unsigned int next_offset);

#endif /* CONFIG_COMPAT */
#endif /* _X_TABLES_H */