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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_NULLS_H #define _LINUX_LIST_NULLS_H #include <linux/poison.h> #include <linux/const.h> /* * Special version of lists, where end of list is not a NULL pointer, * but a 'nulls' marker, which can have many different values. * (up to 2^31 different values guaranteed on all platforms) * * In the standard hlist, termination of a list is the NULL pointer. * In this special 'nulls' variant, we use the fact that objects stored in * a list are aligned on a word (4 or 8 bytes alignment). * We therefore use the last significant bit of 'ptr' : * Set to 1 : This is a 'nulls' end-of-list marker (ptr >> 1) * Set to 0 : This is a pointer to some object (ptr) */ struct hlist_nulls_head { struct hlist_nulls_node *first; }; struct hlist_nulls_node { struct hlist_nulls_node *next, **pprev; }; #define NULLS_MARKER(value) (1UL | (((long)value) << 1)) #define INIT_HLIST_NULLS_HEAD(ptr, nulls) \ ((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls)) #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_nulls_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \ }) /** * ptr_is_a_nulls - Test if a ptr is a nulls * @ptr: ptr to be tested * */ static inline int is_a_nulls(const struct hlist_nulls_node *ptr) { return ((unsigned long)ptr & 1); } /** * get_nulls_value - Get the 'nulls' value of the end of chain * @ptr: end of chain * * Should be called only if is_a_nulls(ptr); */ static inline unsigned long get_nulls_value(const struct hlist_nulls_node *ptr) { return ((unsigned long)ptr) >> 1; } /** * hlist_nulls_unhashed - Has node been removed and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed state. * For example, hlist_del_init_rcu() leaves the node in unhashed state, * but hlist_nulls_del() does not. */ static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h) { return !h->pprev; } /** * hlist_nulls_unhashed_lockless - Has node been removed and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed state. * For example, hlist_del_init_rcu() leaves the node in unhashed state, * but hlist_nulls_del() does not. Unlike hlist_nulls_unhashed(), this * function may be used locklessly. */ static inline int hlist_nulls_unhashed_lockless(const struct hlist_nulls_node *h) { return !READ_ONCE(h->pprev); } static inline int hlist_nulls_empty(const struct hlist_nulls_head *h) { return is_a_nulls(READ_ONCE(h->first)); } static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); h->first = n; if (!is_a_nulls(first)) WRITE_ONCE(first->pprev, &n->next); } static inline void __hlist_nulls_del(struct hlist_nulls_node *n) { struct hlist_nulls_node *next = n->next; struct hlist_nulls_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (!is_a_nulls(next)) WRITE_ONCE(next->pprev, pprev); } static inline void hlist_nulls_del(struct hlist_nulls_node *n) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_nulls_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_nulls_for_each_entry(tpos, pos, head, member) \ for (pos = (head)->first; \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_nulls_for_each_entry_from - iterate over a hlist continuing from current point * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @member: the name of the hlist_node within the struct. * */ #define hlist_nulls_for_each_entry_from(tpos, pos, member) \ for (; (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) #endif
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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM random #if !defined(_TRACE_RANDOM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RANDOM_H #include <linux/writeback.h> #include <linux/tracepoint.h> TRACE_EVENT(add_device_randomness, TP_PROTO(int bytes, unsigned long IP), TP_ARGS(bytes, IP), TP_STRUCT__entry( __field( int, bytes ) __field(unsigned long, IP ) ), TP_fast_assign( __entry->bytes = bytes; __entry->IP = IP; ), TP_printk("bytes %d caller %pS", __entry->bytes, (void *)__entry->IP) ); DECLARE_EVENT_CLASS(random__mix_pool_bytes, TP_PROTO(const char *pool_name, int bytes, unsigned long IP), TP_ARGS(pool_name, bytes, IP), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, bytes ) __field(unsigned long, IP ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->bytes = bytes; __entry->IP = IP; ), TP_printk("%s pool: bytes %d caller %pS", __entry->pool_name, __entry->bytes, (void *)__entry->IP) ); DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes, TP_PROTO(const char *pool_name, int bytes, unsigned long IP), TP_ARGS(pool_name, bytes, IP) ); DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes_nolock, TP_PROTO(const char *pool_name, int bytes, unsigned long IP), TP_ARGS(pool_name, bytes, IP) ); TRACE_EVENT(credit_entropy_bits, TP_PROTO(const char *pool_name, int bits, int entropy_count, unsigned long IP), TP_ARGS(pool_name, bits, entropy_count, IP), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, bits ) __field( int, entropy_count ) __field(unsigned long, IP ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->bits = bits; __entry->entropy_count = entropy_count; __entry->IP = IP; ), TP_printk("%s pool: bits %d entropy_count %d caller %pS", __entry->pool_name, __entry->bits, __entry->entropy_count, (void *)__entry->IP) ); TRACE_EVENT(push_to_pool, TP_PROTO(const char *pool_name, int pool_bits, int input_bits), TP_ARGS(pool_name, pool_bits, input_bits), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, pool_bits ) __field( int, input_bits ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->pool_bits = pool_bits; __entry->input_bits = input_bits; ), TP_printk("%s: pool_bits %d input_pool_bits %d", __entry->pool_name, __entry->pool_bits, __entry->input_bits) ); TRACE_EVENT(debit_entropy, TP_PROTO(const char *pool_name, int debit_bits), TP_ARGS(pool_name, debit_bits), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, debit_bits ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->debit_bits = debit_bits; ), TP_printk("%s: debit_bits %d", __entry->pool_name, __entry->debit_bits) ); TRACE_EVENT(add_input_randomness, TP_PROTO(int input_bits), TP_ARGS(input_bits), TP_STRUCT__entry( __field( int, input_bits ) ), TP_fast_assign( __entry->input_bits = input_bits; ), TP_printk("input_pool_bits %d", __entry->input_bits) ); TRACE_EVENT(add_disk_randomness, TP_PROTO(dev_t dev, int input_bits), TP_ARGS(dev, input_bits), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, input_bits ) ), TP_fast_assign( __entry->dev = dev; __entry->input_bits = input_bits; ), TP_printk("dev %d,%d input_pool_bits %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->input_bits) ); TRACE_EVENT(xfer_secondary_pool, TP_PROTO(const char *pool_name, int xfer_bits, int request_bits, int pool_entropy, int input_entropy), TP_ARGS(pool_name, xfer_bits, request_bits, pool_entropy, input_entropy), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, xfer_bits ) __field( int, request_bits ) __field( int, pool_entropy ) __field( int, input_entropy ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->xfer_bits = xfer_bits; __entry->request_bits = request_bits; __entry->pool_entropy = pool_entropy; __entry->input_entropy = input_entropy; ), TP_printk("pool %s xfer_bits %d request_bits %d pool_entropy %d " "input_entropy %d", __entry->pool_name, __entry->xfer_bits, __entry->request_bits, __entry->pool_entropy, __entry->input_entropy) ); DECLARE_EVENT_CLASS(random__get_random_bytes, TP_PROTO(int nbytes, unsigned long IP), TP_ARGS(nbytes, IP), TP_STRUCT__entry( __field( int, nbytes ) __field(unsigned long, IP ) ), TP_fast_assign( __entry->nbytes = nbytes; __entry->IP = IP; ), TP_printk("nbytes %d caller %pS", __entry->nbytes, (void *)__entry->IP) ); DEFINE_EVENT(random__get_random_bytes, get_random_bytes, TP_PROTO(int nbytes, unsigned long IP), TP_ARGS(nbytes, IP) ); DEFINE_EVENT(random__get_random_bytes, get_random_bytes_arch, TP_PROTO(int nbytes, unsigned long IP), TP_ARGS(nbytes, IP) ); DECLARE_EVENT_CLASS(random__extract_entropy, TP_PROTO(const char *pool_name, int nbytes, int entropy_count, unsigned long IP), TP_ARGS(pool_name, nbytes, entropy_count, IP), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, nbytes ) __field( int, entropy_count ) __field(unsigned long, IP ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->nbytes = nbytes; __entry->entropy_count = entropy_count; __entry->IP = IP; ), TP_printk("%s pool: nbytes %d entropy_count %d caller %pS", __entry->pool_name, __entry->nbytes, __entry->entropy_count, (void *)__entry->IP) ); DEFINE_EVENT(random__extract_entropy, extract_entropy, TP_PROTO(const char *pool_name, int nbytes, int entropy_count, unsigned long IP), TP_ARGS(pool_name, nbytes, entropy_count, IP) ); DEFINE_EVENT(random__extract_entropy, extract_entropy_user, TP_PROTO(const char *pool_name, int nbytes, int entropy_count, unsigned long IP), TP_ARGS(pool_name, nbytes, entropy_count, IP) ); TRACE_EVENT(random_read, TP_PROTO(int got_bits, int need_bits, int pool_left, int input_left), TP_ARGS(got_bits, need_bits, pool_left, input_left), TP_STRUCT__entry( __field( int, got_bits ) __field( int, need_bits ) __field( int, pool_left ) __field( int, input_left ) ), TP_fast_assign( __entry->got_bits = got_bits; __entry->need_bits = need_bits; __entry->pool_left = pool_left; __entry->input_left = input_left; ), TP_printk("got_bits %d still_needed_bits %d " "blocking_pool_entropy_left %d input_entropy_left %d", __entry->got_bits, __entry->got_bits, __entry->pool_left, __entry->input_left) ); TRACE_EVENT(urandom_read, TP_PROTO(int got_bits, int pool_left, int input_left), TP_ARGS(got_bits, pool_left, input_left), TP_STRUCT__entry( __field( int, got_bits ) __field( int, pool_left ) __field( int, input_left ) ), TP_fast_assign( __entry->got_bits = got_bits; __entry->pool_left = pool_left; __entry->input_left = input_left; ), TP_printk("got_bits %d nonblocking_pool_entropy_left %d " "input_entropy_left %d", __entry->got_bits, __entry->pool_left, __entry->input_left) ); TRACE_EVENT(prandom_u32, TP_PROTO(unsigned int ret), TP_ARGS(ret), TP_STRUCT__entry( __field( unsigned int, ret) ), TP_fast_assign( __entry->ret = ret; ), TP_printk("ret=%u" , __entry->ret) ); #endif /* _TRACE_RANDOM_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _ASM_X86_APIC_H #define _ASM_X86_APIC_H #include <linux/cpumask.h> #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/apicdef.h> #include <linux/atomic.h> #include <asm/fixmap.h> #include <asm/mpspec.h> #include <asm/msr.h> #include <asm/hardirq.h> #define ARCH_APICTIMER_STOPS_ON_C3 1 /* * Debugging macros */ #define APIC_QUIET 0 #define APIC_VERBOSE 1 #define APIC_DEBUG 2 /* Macros for apic_extnmi which controls external NMI masking */ #define APIC_EXTNMI_BSP 0 /* Default */ #define APIC_EXTNMI_ALL 1 #define APIC_EXTNMI_NONE 2 /* * Define the default level of output to be very little * This can be turned up by using apic=verbose for more * information and apic=debug for _lots_ of information. * apic_verbosity is defined in apic.c */ #define apic_printk(v, s, a...) do { \ if ((v) <= apic_verbosity) \ printk(s, ##a); \ } while (0) #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) extern void generic_apic_probe(void); #else static inline void generic_apic_probe(void) { } #endif #ifdef CONFIG_X86_LOCAL_APIC extern int apic_verbosity; extern int local_apic_timer_c2_ok; extern int disable_apic; extern unsigned int lapic_timer_period; extern enum apic_intr_mode_id apic_intr_mode; enum apic_intr_mode_id { APIC_PIC, APIC_VIRTUAL_WIRE, APIC_VIRTUAL_WIRE_NO_CONFIG, APIC_SYMMETRIC_IO, APIC_SYMMETRIC_IO_NO_ROUTING }; #ifdef CONFIG_SMP extern void __inquire_remote_apic(int apicid); #else /* CONFIG_SMP */ static inline void __inquire_remote_apic(int apicid) { } #endif /* CONFIG_SMP */ static inline void default_inquire_remote_apic(int apicid) { if (apic_verbosity >= APIC_DEBUG) __inquire_remote_apic(apicid); } /* * With 82489DX we can't rely on apic feature bit * retrieved via cpuid but still have to deal with * such an apic chip so we assume that SMP configuration * is found from MP table (64bit case uses ACPI mostly * which set smp presence flag as well so we are safe * to use this helper too). */ static inline bool apic_from_smp_config(void) { return smp_found_config && !disable_apic; } /* * Basic functions accessing APICs. */ #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #endif extern int setup_profiling_timer(unsigned int); static inline void native_apic_mem_write(u32 reg, u32 v) { volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg); alternative_io("movl %0, %P1", "xchgl %0, %P1", X86_BUG_11AP, ASM_OUTPUT2("=r" (v), "=m" (*addr)), ASM_OUTPUT2("0" (v), "m" (*addr))); } static inline u32 native_apic_mem_read(u32 reg) { return *((volatile u32 *)(APIC_BASE + reg)); } extern void native_apic_wait_icr_idle(void); extern u32 native_safe_apic_wait_icr_idle(void); extern void native_apic_icr_write(u32 low, u32 id); extern u64 native_apic_icr_read(void); static inline bool apic_is_x2apic_enabled(void) { u64 msr; if (rdmsrl_safe(MSR_IA32_APICBASE, &msr)) return false; return msr & X2APIC_ENABLE; } extern void enable_IR_x2apic(void); extern int get_physical_broadcast(void); extern int lapic_get_maxlvt(void); extern void clear_local_APIC(void); extern void disconnect_bsp_APIC(int virt_wire_setup); extern void disable_local_APIC(void); extern void apic_soft_disable(void); extern void lapic_shutdown(void); extern void sync_Arb_IDs(void); extern void init_bsp_APIC(void); extern void apic_intr_mode_select(void); extern void apic_intr_mode_init(void); extern void init_apic_mappings(void); void register_lapic_address(unsigned long address); extern void setup_boot_APIC_clock(void); extern void setup_secondary_APIC_clock(void); extern void lapic_update_tsc_freq(void); #ifdef CONFIG_X86_64 static inline int apic_force_enable(unsigned long addr) { return -1; } #else extern int apic_force_enable(unsigned long addr); #endif extern void apic_ap_setup(void); /* * On 32bit this is mach-xxx local */ #ifdef CONFIG_X86_64 extern int apic_is_clustered_box(void); #else static inline int apic_is_clustered_box(void) { return 0; } #endif extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask); extern void lapic_assign_system_vectors(void); extern void lapic_assign_legacy_vector(unsigned int isairq, bool replace); extern void lapic_update_legacy_vectors(void); extern void lapic_online(void); extern void lapic_offline(void); extern bool apic_needs_pit(void); extern void apic_send_IPI_allbutself(unsigned int vector); #else /* !CONFIG_X86_LOCAL_APIC */ static inline void lapic_shutdown(void) { } #define local_apic_timer_c2_ok 1 static inline void init_apic_mappings(void) { } static inline void disable_local_APIC(void) { } # define setup_boot_APIC_clock x86_init_noop # define setup_secondary_APIC_clock x86_init_noop static inline void lapic_update_tsc_freq(void) { } static inline void init_bsp_APIC(void) { } static inline void apic_intr_mode_select(void) { } static inline void apic_intr_mode_init(void) { } static inline void lapic_assign_system_vectors(void) { } static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { } static inline bool apic_needs_pit(void) { return true; } #endif /* !CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_X2APIC static inline void native_apic_msr_write(u32 reg, u32 v) { if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR || reg == APIC_LVR) return; wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0); } static inline void native_apic_msr_eoi_write(u32 reg, u32 v) { __wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0); } static inline u32 native_apic_msr_read(u32 reg) { u64 msr; if (reg == APIC_DFR) return -1; rdmsrl(APIC_BASE_MSR + (reg >> 4), msr); return (u32)msr; } static inline void native_x2apic_wait_icr_idle(void) { /* no need to wait for icr idle in x2apic */ return; } static inline u32 native_safe_x2apic_wait_icr_idle(void) { /* no need to wait for icr idle in x2apic */ return 0; } static inline void native_x2apic_icr_write(u32 low, u32 id) { wrmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low); } static inline u64 native_x2apic_icr_read(void) { unsigned long val; rdmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), val); return val; } extern int x2apic_mode; extern int x2apic_phys; extern void __init x2apic_set_max_apicid(u32 apicid); extern void __init check_x2apic(void); extern void x2apic_setup(void); static inline int x2apic_enabled(void) { return boot_cpu_has(X86_FEATURE_X2APIC) && apic_is_x2apic_enabled(); } #define x2apic_supported() (boot_cpu_has(X86_FEATURE_X2APIC)) #else /* !CONFIG_X86_X2APIC */ static inline void check_x2apic(void) { } static inline void x2apic_setup(void) { } static inline int x2apic_enabled(void) { return 0; } #define x2apic_mode (0) #define x2apic_supported() (0) #endif /* !CONFIG_X86_X2APIC */ struct irq_data; /* * Copyright 2004 James Cleverdon, IBM. * * Generic APIC sub-arch data struct. * * Hacked for x86-64 by James Cleverdon from i386 architecture code by * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and * James Cleverdon. */ struct apic { /* Hotpath functions first */ void (*eoi_write)(u32 reg, u32 v); void (*native_eoi_write)(u32 reg, u32 v); void (*write)(u32 reg, u32 v); u32 (*read)(u32 reg); /* IPI related functions */ void (*wait_icr_idle)(void); u32 (*safe_wait_icr_idle)(void); void (*send_IPI)(int cpu, int vector); void (*send_IPI_mask)(const struct cpumask *mask, int vector); void (*send_IPI_mask_allbutself)(const struct cpumask *msk, int vec); void (*send_IPI_allbutself)(int vector); void (*send_IPI_all)(int vector); void (*send_IPI_self)(int vector); /* dest_logical is used by the IPI functions */ u32 dest_logical; u32 disable_esr; u32 irq_delivery_mode; u32 irq_dest_mode; u32 (*calc_dest_apicid)(unsigned int cpu); /* ICR related functions */ u64 (*icr_read)(void); void (*icr_write)(u32 low, u32 high); /* Probe, setup and smpboot functions */ int (*probe)(void); int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id); int (*apic_id_valid)(u32 apicid); int (*apic_id_registered)(void); bool (*check_apicid_used)(physid_mask_t *map, int apicid); void (*init_apic_ldr)(void); void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap); void (*setup_apic_routing)(void); int (*cpu_present_to_apicid)(int mps_cpu); void (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap); int (*check_phys_apicid_present)(int phys_apicid); int (*phys_pkg_id)(int cpuid_apic, int index_msb); u32 (*get_apic_id)(unsigned long x); u32 (*set_apic_id)(unsigned int id); /* wakeup_secondary_cpu */ int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); void (*inquire_remote_apic)(int apicid); #ifdef CONFIG_X86_32 /* * Called very early during boot from get_smp_config(). It should * return the logical apicid. x86_[bios]_cpu_to_apicid is * initialized before this function is called. * * If logical apicid can't be determined that early, the function * may return BAD_APICID. Logical apicid will be configured after * init_apic_ldr() while bringing up CPUs. Note that NUMA affinity * won't be applied properly during early boot in this case. */ int (*x86_32_early_logical_apicid)(int cpu); #endif char *name; }; /* * Pointer to the local APIC driver in use on this system (there's * always just one such driver in use - the kernel decides via an * early probing process which one it picks - and then sticks to it): */ extern struct apic *apic; /* * APIC drivers are probed based on how they are listed in the .apicdrivers * section. So the order is important and enforced by the ordering * of different apic driver files in the Makefile. * * For the files having two apic drivers, we use apic_drivers() * to enforce the order with in them. */ #define apic_driver(sym) \ static const struct apic *__apicdrivers_##sym __used \ __aligned(sizeof(struct apic *)) \ __section(".apicdrivers") = { &sym } #define apic_drivers(sym1, sym2) \ static struct apic *__apicdrivers_##sym1##sym2[2] __used \ __aligned(sizeof(struct apic *)) \ __section(".apicdrivers") = { &sym1, &sym2 } extern struct apic *__apicdrivers[], *__apicdrivers_end[]; /* * APIC functionality to boot other CPUs - only used on SMP: */ #ifdef CONFIG_SMP extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); extern int lapic_can_unplug_cpu(void); #endif #ifdef CONFIG_X86_LOCAL_APIC static inline u32 apic_read(u32 reg) { return apic->read(reg); } static inline void apic_write(u32 reg, u32 val) { apic->write(reg, val); } static inline void apic_eoi(void) { apic->eoi_write(APIC_EOI, APIC_EOI_ACK); } static inline u64 apic_icr_read(void) { return apic->icr_read(); } static inline void apic_icr_write(u32 low, u32 high) { apic->icr_write(low, high); } static inline void apic_wait_icr_idle(void) { apic->wait_icr_idle(); } static inline u32 safe_apic_wait_icr_idle(void) { return apic->safe_wait_icr_idle(); } extern void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)); #else /* CONFIG_X86_LOCAL_APIC */ static inline u32 apic_read(u32 reg) { return 0; } static inline void apic_write(u32 reg, u32 val) { } static inline void apic_eoi(void) { } static inline u64 apic_icr_read(void) { return 0; } static inline void apic_icr_write(u32 low, u32 high) { } static inline void apic_wait_icr_idle(void) { } static inline u32 safe_apic_wait_icr_idle(void) { return 0; } static inline void apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)) {} #endif /* CONFIG_X86_LOCAL_APIC */ extern void apic_ack_irq(struct irq_data *data); static inline void ack_APIC_irq(void) { /* * ack_APIC_irq() actually gets compiled as a single instruction * ... yummie. */ apic_eoi(); } static inline bool lapic_vector_set_in_irr(unsigned int vector) { u32 irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); return !!(irr & (1U << (vector % 32))); } static inline unsigned default_get_apic_id(unsigned long x) { unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); if (APIC_XAPIC(ver) || boot_cpu_has(X86_FEATURE_EXTD_APICID)) return (x >> 24) & 0xFF; else return (x >> 24) & 0x0F; } /* * Warm reset vector position: */ #define TRAMPOLINE_PHYS_LOW 0x467 #define TRAMPOLINE_PHYS_HIGH 0x469 extern void generic_bigsmp_probe(void); #ifdef CONFIG_X86_LOCAL_APIC #include <asm/smp.h> #define APIC_DFR_VALUE (APIC_DFR_FLAT) DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid); extern struct apic apic_noop; static inline unsigned int read_apic_id(void) { unsigned int reg = apic_read(APIC_ID); return apic->get_apic_id(reg); } extern int default_apic_id_valid(u32 apicid); extern int default_acpi_madt_oem_check(char *, char *); extern void default_setup_apic_routing(void); extern u32 apic_default_calc_apicid(unsigned int cpu); extern u32 apic_flat_calc_apicid(unsigned int cpu); extern bool default_check_apicid_used(physid_mask_t *map, int apicid); extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap); extern int default_cpu_present_to_apicid(int mps_cpu); extern int default_check_phys_apicid_present(int phys_apicid); #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_SMP bool apic_id_is_primary_thread(unsigned int id); void apic_smt_update(void); #else static inline bool apic_id_is_primary_thread(unsigned int id) { return false; } static inline void apic_smt_update(void) { } #endif struct msi_msg; #ifdef CONFIG_PCI_MSI void x86_vector_msi_compose_msg(struct irq_data *data, struct msi_msg *msg); #else # define x86_vector_msi_compose_msg NULL #endif extern void ioapic_zap_locks(void); #endif /* _ASM_X86_APIC_H */
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 /* SPDX-License-Identifier: GPL-2.0-only */ /* * A policy database (policydb) specifies the * configuration data for the security policy. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * * Support for enhanced MLS infrastructure. * * Updated: Frank Mayer <mayerf@tresys.com> and Karl MacMillan <kmacmillan@tresys.com> * * Added conditional policy language extensions * * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. * Copyright (C) 2003 - 2004 Tresys Technology, LLC */ #ifndef _SS_POLICYDB_H_ #define _SS_POLICYDB_H_ #include "symtab.h" #include "avtab.h" #include "sidtab.h" #include "ebitmap.h" #include "mls_types.h" #include "context.h" #include "constraint.h" /* * A datum type is defined for each kind of symbol * in the configuration data: individual permissions, * common prefixes for access vectors, classes, * users, roles, types, sensitivities, categories, etc. */ /* Permission attributes */ struct perm_datum { u32 value; /* permission bit + 1 */ }; /* Attributes of a common prefix for access vectors */ struct common_datum { u32 value; /* internal common value */ struct symtab permissions; /* common permissions */ }; /* Class attributes */ struct class_datum { u32 value; /* class value */ char *comkey; /* common name */ struct common_datum *comdatum; /* common datum */ struct symtab permissions; /* class-specific permission symbol table */ struct constraint_node *constraints; /* constraints on class permissions */ struct constraint_node *validatetrans; /* special transition rules */ /* Options how a new object user, role, and type should be decided */ #define DEFAULT_SOURCE 1 #define DEFAULT_TARGET 2 char default_user; char default_role; char default_type; /* Options how a new object range should be decided */ #define DEFAULT_SOURCE_LOW 1 #define DEFAULT_SOURCE_HIGH 2 #define DEFAULT_SOURCE_LOW_HIGH 3 #define DEFAULT_TARGET_LOW 4 #define DEFAULT_TARGET_HIGH 5 #define DEFAULT_TARGET_LOW_HIGH 6 #define DEFAULT_GLBLUB 7 char default_range; }; /* Role attributes */ struct role_datum { u32 value; /* internal role value */ u32 bounds; /* boundary of role */ struct ebitmap dominates; /* set of roles dominated by this role */ struct ebitmap types; /* set of authorized types for role */ }; struct role_trans_key { u32 role; /* current role */ u32 type; /* program executable type, or new object type */ u32 tclass; /* process class, or new object class */ }; struct role_trans_datum { u32 new_role; /* new role */ }; struct filename_trans_key { u32 ttype; /* parent dir context */ u16 tclass; /* class of new object */ const char *name; /* last path component */ }; struct filename_trans_datum { struct ebitmap stypes; /* bitmap of source types for this otype */ u32 otype; /* resulting type of new object */ struct filename_trans_datum *next; /* record for next otype*/ }; struct role_allow { u32 role; /* current role */ u32 new_role; /* new role */ struct role_allow *next; }; /* Type attributes */ struct type_datum { u32 value; /* internal type value */ u32 bounds; /* boundary of type */ unsigned char primary; /* primary name? */ unsigned char attribute;/* attribute ?*/ }; /* User attributes */ struct user_datum { u32 value; /* internal user value */ u32 bounds; /* bounds of user */ struct ebitmap roles; /* set of authorized roles for user */ struct mls_range range; /* MLS range (min - max) for user */ struct mls_level dfltlevel; /* default login MLS level for user */ }; /* Sensitivity attributes */ struct level_datum { struct mls_level *level; /* sensitivity and associated categories */ unsigned char isalias; /* is this sensitivity an alias for another? */ }; /* Category attributes */ struct cat_datum { u32 value; /* internal category bit + 1 */ unsigned char isalias; /* is this category an alias for another? */ }; struct range_trans { u32 source_type; u32 target_type; u32 target_class; }; /* Boolean data type */ struct cond_bool_datum { __u32 value; /* internal type value */ int state; }; struct cond_node; /* * type set preserves data needed to determine constraint info from * policy source. This is not used by the kernel policy but allows * utilities such as audit2allow to determine constraint denials. */ struct type_set { struct ebitmap types; struct ebitmap negset; u32 flags; }; /* * The configuration data includes security contexts for * initial SIDs, unlabeled file systems, TCP and UDP port numbers, * network interfaces, and nodes. This structure stores the * relevant data for one such entry. Entries of the same kind * (e.g. all initial SIDs) are linked together into a list. */ struct ocontext { union { char *name; /* name of initial SID, fs, netif, fstype, path */ struct { u8 protocol; u16 low_port; u16 high_port; } port; /* TCP or UDP port information */ struct { u32 addr; u32 mask; } node; /* node information */ struct { u32 addr[4]; u32 mask[4]; } node6; /* IPv6 node information */ struct { u64 subnet_prefix; u16 low_pkey; u16 high_pkey; } ibpkey; struct { char *dev_name; u8 port; } ibendport; } u; union { u32 sclass; /* security class for genfs */ u32 behavior; /* labeling behavior for fs_use */ } v; struct context context[2]; /* security context(s) */ u32 sid[2]; /* SID(s) */ struct ocontext *next; }; struct genfs { char *fstype; struct ocontext *head; struct genfs *next; }; /* symbol table array indices */ #define SYM_COMMONS 0 #define SYM_CLASSES 1 #define SYM_ROLES 2 #define SYM_TYPES 3 #define SYM_USERS 4 #define SYM_BOOLS 5 #define SYM_LEVELS 6 #define SYM_CATS 7 #define SYM_NUM 8 /* object context array indices */ #define OCON_ISID 0 /* initial SIDs */ #define OCON_FS 1 /* unlabeled file systems */ #define OCON_PORT 2 /* TCP and UDP port numbers */ #define OCON_NETIF 3 /* network interfaces */ #define OCON_NODE 4 /* nodes */ #define OCON_FSUSE 5 /* fs_use */ #define OCON_NODE6 6 /* IPv6 nodes */ #define OCON_IBPKEY 7 /* Infiniband PKeys */ #define OCON_IBENDPORT 8 /* Infiniband end ports */ #define OCON_NUM 9 /* The policy database */ struct policydb { int mls_enabled; /* symbol tables */ struct symtab symtab[SYM_NUM]; #define p_commons symtab[SYM_COMMONS] #define p_classes symtab[SYM_CLASSES] #define p_roles symtab[SYM_ROLES] #define p_types symtab[SYM_TYPES] #define p_users symtab[SYM_USERS] #define p_bools symtab[SYM_BOOLS] #define p_levels symtab[SYM_LEVELS] #define p_cats symtab[SYM_CATS] /* symbol names indexed by (value - 1) */ char **sym_val_to_name[SYM_NUM]; /* class, role, and user attributes indexed by (value - 1) */ struct class_datum **class_val_to_struct; struct role_datum **role_val_to_struct; struct user_datum **user_val_to_struct; struct type_datum **type_val_to_struct; /* type enforcement access vectors and transitions */ struct avtab te_avtab; /* role transitions */ struct hashtab role_tr; /* file transitions with the last path component */ /* quickly exclude lookups when parent ttype has no rules */ struct ebitmap filename_trans_ttypes; /* actual set of filename_trans rules */ struct hashtab filename_trans; /* only used if policyvers < POLICYDB_VERSION_COMP_FTRANS */ u32 compat_filename_trans_count; /* bools indexed by (value - 1) */ struct cond_bool_datum **bool_val_to_struct; /* type enforcement conditional access vectors and transitions */ struct avtab te_cond_avtab; /* array indexing te_cond_avtab by conditional */ struct cond_node *cond_list; u32 cond_list_len; /* role allows */ struct role_allow *role_allow; /* security contexts of initial SIDs, unlabeled file systems, TCP or UDP port numbers, network interfaces and nodes */ struct ocontext *ocontexts[OCON_NUM]; /* security contexts for files in filesystems that cannot support a persistent label mapping or use another fixed labeling behavior. */ struct genfs *genfs; /* range transitions table (range_trans_key -> mls_range) */ struct hashtab range_tr; /* type -> attribute reverse mapping */ struct ebitmap *type_attr_map_array; struct ebitmap policycaps; struct ebitmap permissive_map; /* length of this policy when it was loaded */ size_t len; unsigned int policyvers; unsigned int reject_unknown : 1; unsigned int allow_unknown : 1; u16 process_class; u32 process_trans_perms; } __randomize_layout; extern void policydb_destroy(struct policydb *p); extern int policydb_load_isids(struct policydb *p, struct sidtab *s); extern int policydb_context_isvalid(struct policydb *p, struct context *c); extern int policydb_class_isvalid(struct policydb *p, unsigned int class); extern int policydb_type_isvalid(struct policydb *p, unsigned int type); extern int policydb_role_isvalid(struct policydb *p, unsigned int role); extern int policydb_read(struct policydb *p, void *fp); extern int policydb_write(struct policydb *p, void *fp); extern struct filename_trans_datum *policydb_filenametr_search( struct policydb *p, struct filename_trans_key *key); extern struct mls_range *policydb_rangetr_search( struct policydb *p, struct range_trans *key); extern struct role_trans_datum *policydb_roletr_search( struct policydb *p, struct role_trans_key *key); #define POLICYDB_CONFIG_MLS 1 /* the config flags related to unknown classes/perms are bits 2 and 3 */ #define REJECT_UNKNOWN 0x00000002 #define ALLOW_UNKNOWN 0x00000004 #define OBJECT_R "object_r" #define OBJECT_R_VAL 1 #define POLICYDB_MAGIC SELINUX_MAGIC #define POLICYDB_STRING "SE Linux" struct policy_file { char *data; size_t len; }; struct policy_data { struct policydb *p; void *fp; }; static inline int next_entry(void *buf, struct policy_file *fp, size_t bytes) { if (bytes > fp->len) return -EINVAL; memcpy(buf, fp->data, bytes); fp->data += bytes; fp->len -= bytes; return 0; } static inline int put_entry(const void *buf, size_t bytes, int num, struct policy_file *fp) { size_t len = bytes * num; memcpy(fp->data, buf, len); fp->data += len; fp->len -= len; return 0; } static inline char *sym_name(struct policydb *p, unsigned int sym_num, unsigned int element_nr) { return p->sym_val_to_name[sym_num][element_nr]; } extern u16 string_to_security_class(struct policydb *p, const char *name); extern u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name); #endif /* _SS_POLICYDB_H_ */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 // SPDX-License-Identifier: GPL-2.0-or-later /* * TUN - Universal TUN/TAP device driver. * Copyright (C) 1999-2002 Maxim Krasnyansky <maxk@qualcomm.com> * * $Id: tun.c,v 1.15 2002/03/01 02:44:24 maxk Exp $ */ /* * Changes: * * Mike Kershaw <dragorn@kismetwireless.net> 2005/08/14 * Add TUNSETLINK ioctl to set the link encapsulation * * Mark Smith <markzzzsmith@yahoo.com.au> * Use eth_random_addr() for tap MAC address. * * Harald Roelle <harald.roelle@ifi.lmu.de> 2004/04/20 * Fixes in packet dropping, queue length setting and queue wakeup. * Increased default tx queue length. * Added ethtool API. * Minor cleanups * * Daniel Podlejski <underley@underley.eu.org> * Modifications for 2.3.99-pre5 kernel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "tun" #define DRV_VERSION "1.6" #define DRV_DESCRIPTION "Universal TUN/TAP device driver" #define DRV_COPYRIGHT "(C) 1999-2004 Max Krasnyansky <maxk@qualcomm.com>" #include <linux/module.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/major.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/fcntl.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/miscdevice.h> #include <linux/ethtool.h> #include <linux/rtnetlink.h> #include <linux/compat.h> #include <linux/if.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/if_tun.h> #include <linux/if_vlan.h> #include <linux/crc32.h> #include <linux/nsproxy.h> #include <linux/virtio_net.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <net/xdp.h> #include <net/ip_tunnels.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/skb_array.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/mutex.h> #include <linux/ieee802154.h> #include <linux/if_ltalk.h> #include <uapi/linux/if_fddi.h> #include <uapi/linux/if_hippi.h> #include <uapi/linux/if_fc.h> #include <net/ax25.h> #include <net/rose.h> #include <net/6lowpan.h> #include <linux/uaccess.h> #include <linux/proc_fs.h> static void tun_default_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd); #define TUN_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) /* TUN device flags */ /* IFF_ATTACH_QUEUE is never stored in device flags, * overload it to mean fasync when stored there. */ #define TUN_FASYNC IFF_ATTACH_QUEUE /* High bits in flags field are unused. */ #define TUN_VNET_LE 0x80000000 #define TUN_VNET_BE 0x40000000 #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \ IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS) #define GOODCOPY_LEN 128 #define FLT_EXACT_COUNT 8 struct tap_filter { unsigned int count; /* Number of addrs. Zero means disabled */ u32 mask[2]; /* Mask of the hashed addrs */ unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN]; }; /* MAX_TAP_QUEUES 256 is chosen to allow rx/tx queues to be equal * to max number of VCPUs in guest. */ #define MAX_TAP_QUEUES 256 #define MAX_TAP_FLOWS 4096 #define TUN_FLOW_EXPIRE (3 * HZ) struct tun_pcpu_stats { u64_stats_t rx_packets; u64_stats_t rx_bytes; u64_stats_t tx_packets; u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_dropped; u32 tx_dropped; u32 rx_frame_errors; }; /* A tun_file connects an open character device to a tuntap netdevice. It * also contains all socket related structures (except sock_fprog and tap_filter) * to serve as one transmit queue for tuntap device. The sock_fprog and * tap_filter were kept in tun_struct since they were used for filtering for the * netdevice not for a specific queue (at least I didn't see the requirement for * this). * * RCU usage: * The tun_file and tun_struct are loosely coupled, the pointer from one to the * other can only be read while rcu_read_lock or rtnl_lock is held. */ struct tun_file { struct sock sk; struct socket socket; struct tun_struct __rcu *tun; struct fasync_struct *fasync; /* only used for fasnyc */ unsigned int flags; union { u16 queue_index; unsigned int ifindex; }; struct napi_struct napi; bool napi_enabled; bool napi_frags_enabled; struct mutex napi_mutex; /* Protects access to the above napi */ struct list_head next; struct tun_struct *detached; struct ptr_ring tx_ring; struct xdp_rxq_info xdp_rxq; }; struct tun_page { struct page *page; int count; }; struct tun_flow_entry { struct hlist_node hash_link; struct rcu_head rcu; struct tun_struct *tun; u32 rxhash; u32 rps_rxhash; int queue_index; unsigned long updated ____cacheline_aligned_in_smp; }; #define TUN_NUM_FLOW_ENTRIES 1024 #define TUN_MASK_FLOW_ENTRIES (TUN_NUM_FLOW_ENTRIES - 1) struct tun_prog { struct rcu_head rcu; struct bpf_prog *prog; }; /* Since the socket were moved to tun_file, to preserve the behavior of persist * device, socket filter, sndbuf and vnet header size were restore when the * file were attached to a persist device. */ struct tun_struct { struct tun_file __rcu *tfiles[MAX_TAP_QUEUES]; unsigned int numqueues; unsigned int flags; kuid_t owner; kgid_t group; struct net_device *dev; netdev_features_t set_features; #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ NETIF_F_TSO6) int align; int vnet_hdr_sz; int sndbuf; struct tap_filter txflt; struct sock_fprog fprog; /* protected by rtnl lock */ bool filter_attached; u32 msg_enable; spinlock_t lock; struct hlist_head flows[TUN_NUM_FLOW_ENTRIES]; struct timer_list flow_gc_timer; unsigned long ageing_time; unsigned int numdisabled; struct list_head disabled; void *security; u32 flow_count; u32 rx_batched; struct tun_pcpu_stats __percpu *pcpu_stats; struct bpf_prog __rcu *xdp_prog; struct tun_prog __rcu *steering_prog; struct tun_prog __rcu *filter_prog; struct ethtool_link_ksettings link_ksettings; }; struct veth { __be16 h_vlan_proto; __be16 h_vlan_TCI; }; static int tun_napi_receive(struct napi_struct *napi, int budget) { struct tun_file *tfile = container_of(napi, struct tun_file, napi); struct sk_buff_head *queue = &tfile->sk.sk_write_queue; struct sk_buff_head process_queue; struct sk_buff *skb; int received = 0; __skb_queue_head_init(&process_queue); spin_lock(&queue->lock); skb_queue_splice_tail_init(queue, &process_queue); spin_unlock(&queue->lock); while (received < budget && (skb = __skb_dequeue(&process_queue))) { napi_gro_receive(napi, skb); ++received; } if (!skb_queue_empty(&process_queue)) { spin_lock(&queue->lock); skb_queue_splice(&process_queue, queue); spin_unlock(&queue->lock); } return received; } static int tun_napi_poll(struct napi_struct *napi, int budget) { unsigned int received; received = tun_napi_receive(napi, budget); if (received < budget) napi_complete_done(napi, received); return received; } static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, bool napi_en, bool napi_frags) { tfile->napi_enabled = napi_en; tfile->napi_frags_enabled = napi_en && napi_frags; if (napi_en) { netif_tx_napi_add(tun->dev, &tfile->napi, tun_napi_poll, NAPI_POLL_WEIGHT); napi_enable(&tfile->napi); } } static void tun_napi_disable(struct tun_file *tfile) { if (tfile->napi_enabled) napi_disable(&tfile->napi); } static void tun_napi_del(struct tun_file *tfile) { if (tfile->napi_enabled) netif_napi_del(&tfile->napi); } static bool tun_napi_frags_enabled(const struct tun_file *tfile) { return tfile->napi_frags_enabled; } #ifdef CONFIG_TUN_VNET_CROSS_LE static inline bool tun_legacy_is_little_endian(struct tun_struct *tun) { return tun->flags & TUN_VNET_BE ? false : virtio_legacy_is_little_endian(); } static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp) { int be = !!(tun->flags & TUN_VNET_BE); if (put_user(be, argp)) return -EFAULT; return 0; } static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp) { int be; if (get_user(be, argp)) return -EFAULT; if (be) tun->flags |= TUN_VNET_BE; else tun->flags &= ~TUN_VNET_BE; return 0; } #else static inline bool tun_legacy_is_little_endian(struct tun_struct *tun) { return virtio_legacy_is_little_endian(); } static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp) { return -EINVAL; } static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp) { return -EINVAL; } #endif /* CONFIG_TUN_VNET_CROSS_LE */ static inline bool tun_is_little_endian(struct tun_struct *tun) { return tun->flags & TUN_VNET_LE || tun_legacy_is_little_endian(tun); } static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val) { return __virtio16_to_cpu(tun_is_little_endian(tun), val); } static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val) { return __cpu_to_virtio16(tun_is_little_endian(tun), val); } static inline u32 tun_hashfn(u32 rxhash) { return rxhash & TUN_MASK_FLOW_ENTRIES; } static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash) { struct tun_flow_entry *e; hlist_for_each_entry_rcu(e, head, hash_link) { if (e->rxhash == rxhash) return e; } return NULL; } static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun, struct hlist_head *head, u32 rxhash, u16 queue_index) { struct tun_flow_entry *e = kmalloc(sizeof(*e), GFP_ATOMIC); if (e) { netif_info(tun, tx_queued, tun->dev, "create flow: hash %u index %u\n", rxhash, queue_index); e->updated = jiffies; e->rxhash = rxhash; e->rps_rxhash = 0; e->queue_index = queue_index; e->tun = tun; hlist_add_head_rcu(&e->hash_link, head); ++tun->flow_count; } return e; } static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e) { netif_info(tun, tx_queued, tun->dev, "delete flow: hash %u index %u\n", e->rxhash, e->queue_index); hlist_del_rcu(&e->hash_link); kfree_rcu(e, rcu); --tun->flow_count; } static void tun_flow_flush(struct tun_struct *tun) { int i; spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) tun_flow_delete(tun, e); } spin_unlock_bh(&tun->lock); } static void tun_flow_delete_by_queue(struct tun_struct *tun, u16 queue_index) { int i; spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { if (e->queue_index == queue_index) tun_flow_delete(tun, e); } } spin_unlock_bh(&tun->lock); } static void tun_flow_cleanup(struct timer_list *t) { struct tun_struct *tun = from_timer(tun, t, flow_gc_timer); unsigned long delay = tun->ageing_time; unsigned long next_timer = jiffies + delay; unsigned long count = 0; int i; spin_lock(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { unsigned long this_timer; this_timer = e->updated + delay; if (time_before_eq(this_timer, jiffies)) { tun_flow_delete(tun, e); continue; } count++; if (time_before(this_timer, next_timer)) next_timer = this_timer; } } if (count) mod_timer(&tun->flow_gc_timer, round_jiffies_up(next_timer)); spin_unlock(&tun->lock); } static void tun_flow_update(struct tun_struct *tun, u32 rxhash, struct tun_file *tfile) { struct hlist_head *head; struct tun_flow_entry *e; unsigned long delay = tun->ageing_time; u16 queue_index = tfile->queue_index; head = &tun->flows[tun_hashfn(rxhash)]; rcu_read_lock(); e = tun_flow_find(head, rxhash); if (likely(e)) { /* TODO: keep queueing to old queue until it's empty? */ if (READ_ONCE(e->queue_index) != queue_index) WRITE_ONCE(e->queue_index, queue_index); if (e->updated != jiffies) e->updated = jiffies; sock_rps_record_flow_hash(e->rps_rxhash); } else { spin_lock_bh(&tun->lock); if (!tun_flow_find(head, rxhash) && tun->flow_count < MAX_TAP_FLOWS) tun_flow_create(tun, head, rxhash, queue_index); if (!timer_pending(&tun->flow_gc_timer)) mod_timer(&tun->flow_gc_timer, round_jiffies_up(jiffies + delay)); spin_unlock_bh(&tun->lock); } rcu_read_unlock(); } /* Save the hash received in the stack receive path and update the * flow_hash table accordingly. */ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) { if (unlikely(e->rps_rxhash != hash)) e->rps_rxhash = hash; } /* We try to identify a flow through its rxhash. The reason that * we do not check rxq no. is because some cards(e.g 82599), chooses * the rxq based on the txq where the last packet of the flow comes. As * the userspace application move between processors, we may get a * different rxq no. here. */ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb) { struct tun_flow_entry *e; u32 txq = 0; u32 numqueues = 0; numqueues = READ_ONCE(tun->numqueues); txq = __skb_get_hash_symmetric(skb); e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq); if (e) { tun_flow_save_rps_rxhash(e, txq); txq = e->queue_index; } else { /* use multiply and shift instead of expensive divide */ txq = ((u64)txq * numqueues) >> 32; } return txq; } static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb) { struct tun_prog *prog; u32 numqueues; u16 ret = 0; numqueues = READ_ONCE(tun->numqueues); if (!numqueues) return 0; prog = rcu_dereference(tun->steering_prog); if (prog) ret = bpf_prog_run_clear_cb(prog->prog, skb); return ret % numqueues; } static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { struct tun_struct *tun = netdev_priv(dev); u16 ret; rcu_read_lock(); if (rcu_dereference(tun->steering_prog)) ret = tun_ebpf_select_queue(tun, skb); else ret = tun_automq_select_queue(tun, skb); rcu_read_unlock(); return ret; } static inline bool tun_not_capable(struct tun_struct *tun) { const struct cred *cred = current_cred(); struct net *net = dev_net(tun->dev); return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) || (gid_valid(tun->group) && !in_egroup_p(tun->group))) && !ns_capable(net->user_ns, CAP_NET_ADMIN); } static void tun_set_real_num_queues(struct tun_struct *tun) { netif_set_real_num_tx_queues(tun->dev, tun->numqueues); netif_set_real_num_rx_queues(tun->dev, tun->numqueues); } static void tun_disable_queue(struct tun_struct *tun, struct tun_file *tfile) { tfile->detached = tun; list_add_tail(&tfile->next, &tun->disabled); ++tun->numdisabled; } static struct tun_struct *tun_enable_queue(struct tun_file *tfile) { struct tun_struct *tun = tfile->detached; tfile->detached = NULL; list_del_init(&tfile->next); --tun->numdisabled; return tun; } void tun_ptr_free(void *ptr) { if (!ptr) return; if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); xdp_return_frame(xdpf); } else { __skb_array_destroy_skb(ptr); } } EXPORT_SYMBOL_GPL(tun_ptr_free); static void tun_queue_purge(struct tun_file *tfile) { void *ptr; while ((ptr = ptr_ring_consume(&tfile->tx_ring)) != NULL) tun_ptr_free(ptr); skb_queue_purge(&tfile->sk.sk_write_queue); skb_queue_purge(&tfile->sk.sk_error_queue); } static void __tun_detach(struct tun_file *tfile, bool clean) { struct tun_file *ntfile; struct tun_struct *tun; tun = rtnl_dereference(tfile->tun); if (tun && clean) { tun_napi_disable(tfile); tun_napi_del(tfile); } if (tun && !tfile->detached) { u16 index = tfile->queue_index; BUG_ON(index >= tun->numqueues); rcu_assign_pointer(tun->tfiles[index], tun->tfiles[tun->numqueues - 1]); ntfile = rtnl_dereference(tun->tfiles[index]); ntfile->queue_index = index; rcu_assign_pointer(tun->tfiles[tun->numqueues - 1], NULL); --tun->numqueues; if (clean) { RCU_INIT_POINTER(tfile->tun, NULL); sock_put(&tfile->sk); } else tun_disable_queue(tun, tfile); synchronize_net(); tun_flow_delete_by_queue(tun, tun->numqueues + 1); /* Drop read queue */ tun_queue_purge(tfile); tun_set_real_num_queues(tun); } else if (tfile->detached && clean) { tun = tun_enable_queue(tfile); sock_put(&tfile->sk); } if (clean) { if (tun && tun->numqueues == 0 && tun->numdisabled == 0) { netif_carrier_off(tun->dev); if (!(tun->flags & IFF_PERSIST) && tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); } if (tun) xdp_rxq_info_unreg(&tfile->xdp_rxq); ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free); sock_put(&tfile->sk); } } static void tun_detach(struct tun_file *tfile, bool clean) { struct tun_struct *tun; struct net_device *dev; rtnl_lock(); tun = rtnl_dereference(tfile->tun); dev = tun ? tun->dev : NULL; __tun_detach(tfile, clean); if (dev) netdev_state_change(dev); rtnl_unlock(); } static void tun_detach_all(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile, *tmp; int i, n = tun->numqueues; for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); BUG_ON(!tfile); tun_napi_disable(tfile); tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); --tun->numqueues; } list_for_each_entry(tfile, &tun->disabled, next) { tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); } BUG_ON(tun->numqueues != 0); synchronize_net(); for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); tun_napi_del(tfile); /* Drop read queue */ tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { tun_enable_queue(tfile); tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } BUG_ON(tun->numdisabled != 0); if (tun->flags & IFF_PERSIST) module_put(THIS_MODULE); } static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter, bool napi, bool napi_frags, bool publish_tun) { struct tun_file *tfile = file->private_data; struct net_device *dev = tun->dev; int err; err = security_tun_dev_attach(tfile->socket.sk, tun->security); if (err < 0) goto out; err = -EINVAL; if (rtnl_dereference(tfile->tun) && !tfile->detached) goto out; err = -EBUSY; if (!(tun->flags & IFF_MULTI_QUEUE) && tun->numqueues == 1) goto out; err = -E2BIG; if (!tfile->detached && tun->numqueues + tun->numdisabled == MAX_TAP_QUEUES) goto out; err = 0; /* Re-attach the filter to persist device */ if (!skip_filter && (tun->filter_attached == true)) { lock_sock(tfile->socket.sk); err = sk_attach_filter(&tun->fprog, tfile->socket.sk); release_sock(tfile->socket.sk); if (!err) goto out; } if (!tfile->detached && ptr_ring_resize(&tfile->tx_ring, dev->tx_queue_len, GFP_KERNEL, tun_ptr_free)) { err = -ENOMEM; goto out; } tfile->queue_index = tun->numqueues; tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN; if (tfile->detached) { /* Re-attach detached tfile, updating XDP queue_index */ WARN_ON(!xdp_rxq_info_is_reg(&tfile->xdp_rxq)); if (tfile->xdp_rxq.queue_index != tfile->queue_index) tfile->xdp_rxq.queue_index = tfile->queue_index; } else { /* Setup XDP RX-queue info, for new tfile getting attached */ err = xdp_rxq_info_reg(&tfile->xdp_rxq, tun->dev, tfile->queue_index); if (err < 0) goto out; err = xdp_rxq_info_reg_mem_model(&tfile->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err < 0) { xdp_rxq_info_unreg(&tfile->xdp_rxq); goto out; } err = 0; } if (tfile->detached) { tun_enable_queue(tfile); } else { sock_hold(&tfile->sk); tun_napi_init(tun, tfile, napi, napi_frags); } if (rtnl_dereference(tun->xdp_prog)) sock_set_flag(&tfile->sk, SOCK_XDP); /* device is allowed to go away first, so no need to hold extra * refcnt. */ /* Publish tfile->tun and tun->tfiles only after we've fully * initialized tfile; otherwise we risk using half-initialized * object. */ if (publish_tun) rcu_assign_pointer(tfile->tun, tun); rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); tun->numqueues++; tun_set_real_num_queues(tun); out: return err; } static struct tun_struct *tun_get(struct tun_file *tfile) { struct tun_struct *tun; rcu_read_lock(); tun = rcu_dereference(tfile->tun); if (tun) dev_hold(tun->dev); rcu_read_unlock(); return tun; } static void tun_put(struct tun_struct *tun) { dev_put(tun->dev); } /* TAP filtering */ static void addr_hash_set(u32 *mask, const u8 *addr) { int n = ether_crc(ETH_ALEN, addr) >> 26; mask[n >> 5] |= (1 << (n & 31)); } static unsigned int addr_hash_test(const u32 *mask, const u8 *addr) { int n = ether_crc(ETH_ALEN, addr) >> 26; return mask[n >> 5] & (1 << (n & 31)); } static int update_filter(struct tap_filter *filter, void __user *arg) { struct { u8 u[ETH_ALEN]; } *addr; struct tun_filter uf; int err, alen, n, nexact; if (copy_from_user(&uf, arg, sizeof(uf))) return -EFAULT; if (!uf.count) { /* Disabled */ filter->count = 0; return 0; } alen = ETH_ALEN * uf.count; addr = memdup_user(arg + sizeof(uf), alen); if (IS_ERR(addr)) return PTR_ERR(addr); /* The filter is updated without holding any locks. Which is * perfectly safe. We disable it first and in the worst * case we'll accept a few undesired packets. */ filter->count = 0; wmb(); /* Use first set of addresses as an exact filter */ for (n = 0; n < uf.count && n < FLT_EXACT_COUNT; n++) memcpy(filter->addr[n], addr[n].u, ETH_ALEN); nexact = n; /* Remaining multicast addresses are hashed, * unicast will leave the filter disabled. */ memset(filter->mask, 0, sizeof(filter->mask)); for (; n < uf.count; n++) { if (!is_multicast_ether_addr(addr[n].u)) { err = 0; /* no filter */ goto free_addr; } addr_hash_set(filter->mask, addr[n].u); } /* For ALLMULTI just set the mask to all ones. * This overrides the mask populated above. */ if ((uf.flags & TUN_FLT_ALLMULTI)) memset(filter->mask, ~0, sizeof(filter->mask)); /* Now enable the filter */ wmb(); filter->count = nexact; /* Return the number of exact filters */ err = nexact; free_addr: kfree(addr); return err; } /* Returns: 0 - drop, !=0 - accept */ static int run_filter(struct tap_filter *filter, const struct sk_buff *skb) { /* Cannot use eth_hdr(skb) here because skb_mac_hdr() is incorrect * at this point. */ struct ethhdr *eh = (struct ethhdr *) skb->data; int i; /* Exact match */ for (i = 0; i < filter->count; i++) if (ether_addr_equal(eh->h_dest, filter->addr[i])) return 1; /* Inexact match (multicast only) */ if (is_multicast_ether_addr(eh->h_dest)) return addr_hash_test(filter->mask, eh->h_dest); return 0; } /* * Checks whether the packet is accepted or not. * Returns: 0 - drop, !=0 - accept */ static int check_filter(struct tap_filter *filter, const struct sk_buff *skb) { if (!filter->count) return 1; return run_filter(filter, skb); } /* Network device part of the driver */ static const struct ethtool_ops tun_ethtool_ops; /* Net device detach from fd. */ static void tun_net_uninit(struct net_device *dev) { tun_detach_all(dev); } /* Net device open. */ static int tun_net_open(struct net_device *dev) { netif_tx_start_all_queues(dev); return 0; } /* Net device close. */ static int tun_net_close(struct net_device *dev) { netif_tx_stop_all_queues(dev); return 0; } /* Net device start xmit */ static void tun_automq_xmit(struct tun_struct *tun, struct sk_buff *skb) { #ifdef CONFIG_RPS if (tun->numqueues == 1 && static_branch_unlikely(&rps_needed)) { /* Select queue was not called for the skbuff, so we extract the * RPS hash and save it into the flow_table here. */ struct tun_flow_entry *e; __u32 rxhash; rxhash = __skb_get_hash_symmetric(skb); e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)], rxhash); if (e) tun_flow_save_rps_rxhash(e, rxhash); } #endif } static unsigned int run_ebpf_filter(struct tun_struct *tun, struct sk_buff *skb, int len) { struct tun_prog *prog = rcu_dereference(tun->filter_prog); if (prog) len = bpf_prog_run_clear_cb(prog->prog, skb); return len; } /* Net device start xmit */ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); int txq = skb->queue_mapping; struct netdev_queue *queue; struct tun_file *tfile; int len = skb->len; rcu_read_lock(); tfile = rcu_dereference(tun->tfiles[txq]); /* Drop packet if interface is not attached */ if (!tfile) goto drop; if (!rcu_dereference(tun->steering_prog)) tun_automq_xmit(tun, skb); netif_info(tun, tx_queued, tun->dev, "%s %d\n", __func__, skb->len); /* Drop if the filter does not like it. * This is a noop if the filter is disabled. * Filter can be enabled only for the TAP devices. */ if (!check_filter(&tun->txflt, skb)) goto drop; if (tfile->socket.sk->sk_filter && sk_filter(tfile->socket.sk, skb)) goto drop; len = run_ebpf_filter(tun, skb, len); if (len == 0 || pskb_trim(skb, len)) goto drop; if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) goto drop; skb_tx_timestamp(skb); /* Orphan the skb - required as we might hang on to it * for indefinite time. */ skb_orphan(skb); nf_reset_ct(skb); if (ptr_ring_produce(&tfile->tx_ring, skb)) goto drop; /* NETIF_F_LLTX requires to do our own update of trans_start */ queue = netdev_get_tx_queue(dev, txq); queue->trans_start = jiffies; /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); tfile->socket.sk->sk_data_ready(tfile->socket.sk); rcu_read_unlock(); return NETDEV_TX_OK; drop: this_cpu_inc(tun->pcpu_stats->tx_dropped); skb_tx_error(skb); kfree_skb(skb); rcu_read_unlock(); return NET_XMIT_DROP; } static void tun_net_mclist(struct net_device *dev) { /* * This callback is supposed to deal with mc filter in * _rx_ path and has nothing to do with the _tx_ path. * In rx path we always accept everything userspace gives us. */ } static netdev_features_t tun_net_fix_features(struct net_device *dev, netdev_features_t features) { struct tun_struct *tun = netdev_priv(dev); return (features & tun->set_features) | (features & ~TUN_USER_FEATURES); } static void tun_set_headroom(struct net_device *dev, int new_hr) { struct tun_struct *tun = netdev_priv(dev); if (new_hr < NET_SKB_PAD) new_hr = NET_SKB_PAD; tun->align = new_hr; } static void tun_net_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { u32 rx_dropped = 0, tx_dropped = 0, rx_frame_errors = 0; struct tun_struct *tun = netdev_priv(dev); struct tun_pcpu_stats *p; int i; for_each_possible_cpu(i) { u64 rxpackets, rxbytes, txpackets, txbytes; unsigned int start; p = per_cpu_ptr(tun->pcpu_stats, i); do { start = u64_stats_fetch_begin(&p->syncp); rxpackets = u64_stats_read(&p->rx_packets); rxbytes = u64_stats_read(&p->rx_bytes); txpackets = u64_stats_read(&p->tx_packets); txbytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += rxpackets; stats->rx_bytes += rxbytes; stats->tx_packets += txpackets; stats->tx_bytes += txbytes; /* u32 counters */ rx_dropped += p->rx_dropped; rx_frame_errors += p->rx_frame_errors; tx_dropped += p->tx_dropped; } stats->rx_dropped = rx_dropped; stats->rx_frame_errors = rx_frame_errors; stats->tx_dropped = tx_dropped; } static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile; struct bpf_prog *old_prog; int i; old_prog = rtnl_dereference(tun->xdp_prog); rcu_assign_pointer(tun->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); if (prog) sock_set_flag(&tfile->sk, SOCK_XDP); else sock_reset_flag(&tfile->sk, SOCK_XDP); } list_for_each_entry(tfile, &tun->disabled, next) { if (prog) sock_set_flag(&tfile->sk, SOCK_XDP); else sock_reset_flag(&tfile->sk, SOCK_XDP); } return 0; } static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return tun_xdp_set(dev, xdp->prog, xdp->extack); default: return -EINVAL; } } static int tun_net_change_carrier(struct net_device *dev, bool new_carrier) { if (new_carrier) { struct tun_struct *tun = netdev_priv(dev); if (!tun->numqueues) return -EPERM; netif_carrier_on(dev); } else { netif_carrier_off(dev); } return 0; } static const struct net_device_ops tun_netdev_ops = { .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, .ndo_fix_features = tun_net_fix_features, .ndo_select_queue = tun_select_queue, .ndo_set_rx_headroom = tun_set_headroom, .ndo_get_stats64 = tun_net_get_stats64, .ndo_change_carrier = tun_net_change_carrier, }; static void __tun_xdp_flush_tfile(struct tun_file *tfile) { /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); tfile->socket.sk->sk_data_ready(tfile->socket.sk); } static int tun_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile; u32 numqueues; int drops = 0; int cnt = n; int i; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; rcu_read_lock(); resample: numqueues = READ_ONCE(tun->numqueues); if (!numqueues) { rcu_read_unlock(); return -ENXIO; /* Caller will free/return all frames */ } tfile = rcu_dereference(tun->tfiles[smp_processor_id() % numqueues]); if (unlikely(!tfile)) goto resample; spin_lock(&tfile->tx_ring.producer_lock); for (i = 0; i < n; i++) { struct xdp_frame *xdp = frames[i]; /* Encode the XDP flag into lowest bit for consumer to differ * XDP buffer from sk_buff. */ void *frame = tun_xdp_to_ptr(xdp); if (__ptr_ring_produce(&tfile->tx_ring, frame)) { this_cpu_inc(tun->pcpu_stats->tx_dropped); xdp_return_frame_rx_napi(xdp); drops++; } } spin_unlock(&tfile->tx_ring.producer_lock); if (flags & XDP_XMIT_FLUSH) __tun_xdp_flush_tfile(tfile); rcu_read_unlock(); return cnt - drops; } static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp) { struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp); if (unlikely(!frame)) return -EOVERFLOW; return tun_xdp_xmit(dev, 1, &frame, XDP_XMIT_FLUSH); } static const struct net_device_ops tap_netdev_ops = { .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, .ndo_fix_features = tun_net_fix_features, .ndo_set_rx_mode = tun_net_mclist, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_select_queue = tun_select_queue, .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = tun_set_headroom, .ndo_get_stats64 = tun_net_get_stats64, .ndo_bpf = tun_xdp, .ndo_xdp_xmit = tun_xdp_xmit, .ndo_change_carrier = tun_net_change_carrier, }; static void tun_flow_init(struct tun_struct *tun) { int i; for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) INIT_HLIST_HEAD(&tun->flows[i]); tun->ageing_time = TUN_FLOW_EXPIRE; timer_setup(&tun->flow_gc_timer, tun_flow_cleanup, 0); mod_timer(&tun->flow_gc_timer, round_jiffies_up(jiffies + tun->ageing_time)); } static void tun_flow_uninit(struct tun_struct *tun) { del_timer_sync(&tun->flow_gc_timer); tun_flow_flush(tun); } #define MIN_MTU 68 #define MAX_MTU 65535 /* Initialize net device. */ static void tun_net_init(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: dev->netdev_ops = &tun_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; /* Point-to-Point TUN Device */ dev->hard_header_len = 0; dev->addr_len = 0; dev->mtu = 1500; /* Zero header length */ dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; break; case IFF_TAP: dev->netdev_ops = &tap_netdev_ops; /* Ethernet TAP Device */ ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; eth_hw_addr_random(dev); break; } dev->min_mtu = MIN_MTU; dev->max_mtu = MAX_MTU - dev->hard_header_len; } static bool tun_sock_writeable(struct tun_struct *tun, struct tun_file *tfile) { struct sock *sk = tfile->socket.sk; return (tun->dev->flags & IFF_UP) && sock_writeable(sk); } /* Character device part */ /* Poll */ static __poll_t tun_chr_poll(struct file *file, poll_table *wait) { struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); struct sock *sk; __poll_t mask = 0; if (!tun) return EPOLLERR; sk = tfile->socket.sk; poll_wait(file, sk_sleep(sk), wait); if (!ptr_ring_empty(&tfile->tx_ring)) mask |= EPOLLIN | EPOLLRDNORM; /* Make sure SOCKWQ_ASYNC_NOSPACE is set if not writable to * guarantee EPOLLOUT to be raised by either here or * tun_sock_write_space(). Then process could get notification * after it writes to a down device and meets -EIO. */ if (tun_sock_writeable(tun, tfile) || (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && tun_sock_writeable(tun, tfile))) mask |= EPOLLOUT | EPOLLWRNORM; if (tun->dev->reg_state != NETREG_REGISTERED) mask = EPOLLERR; tun_put(tun); return mask; } static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, size_t len, const struct iov_iter *it) { struct sk_buff *skb; size_t linear; int err; int i; if (it->nr_segs > MAX_SKB_FRAGS + 1) return ERR_PTR(-EMSGSIZE); local_bh_disable(); skb = napi_get_frags(&tfile->napi); local_bh_enable(); if (!skb) return ERR_PTR(-ENOMEM); linear = iov_iter_single_seg_count(it); err = __skb_grow(skb, linear); if (err) goto free; skb->len = len; skb->data_len = len - linear; skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { size_t fragsz = it->iov[i].iov_len; struct page *page; void *frag; if (fragsz == 0 || fragsz > PAGE_SIZE) { err = -EINVAL; goto free; } frag = netdev_alloc_frag(fragsz); if (!frag) { err = -ENOMEM; goto free; } page = virt_to_head_page(frag); skb_fill_page_desc(skb, i - 1, page, frag - page_address(page), fragsz); } return skb; free: /* frees skb and all frags allocated with napi_alloc_frag() */ napi_free_frags(&tfile->napi); return ERR_PTR(err); } /* prepad is the amount to reserve at front. len is length after that. * linear is a hint as to how much to copy (usually headers). */ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile, size_t prepad, size_t len, size_t linear, int noblock) { struct sock *sk = tfile->socket.sk; struct sk_buff *skb; int err; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE || !linear) linear = len; skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, &err, 0); if (!skb) return ERR_PTR(err); skb_reserve(skb, prepad); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile, struct sk_buff *skb, int more) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; struct sk_buff_head process_queue; u32 rx_batched = tun->rx_batched; bool rcv = false; if (!rx_batched || (!more && skb_queue_empty(queue))) { local_bh_disable(); skb_record_rx_queue(skb, tfile->queue_index); netif_receive_skb(skb); local_bh_enable(); return; } spin_lock(&queue->lock); if (!more || skb_queue_len(queue) == rx_batched) { __skb_queue_head_init(&process_queue); skb_queue_splice_tail_init(queue, &process_queue); rcv = true; } else { __skb_queue_tail(queue, skb); } spin_unlock(&queue->lock); if (rcv) { struct sk_buff *nskb; local_bh_disable(); while ((nskb = __skb_dequeue(&process_queue))) { skb_record_rx_queue(nskb, tfile->queue_index); netif_receive_skb(nskb); } skb_record_rx_queue(skb, tfile->queue_index); netif_receive_skb(skb); local_bh_enable(); } } static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, int len, int noblock, bool zerocopy) { if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) return false; if (tfile->socket.sk->sk_sndbuf != INT_MAX) return false; if (!noblock) return false; if (zerocopy) return false; if (SKB_DATA_ALIGN(len + TUN_RX_PAD) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return false; return true; } static struct sk_buff *__tun_build_skb(struct tun_file *tfile, struct page_frag *alloc_frag, char *buf, int buflen, int len, int pad) { struct sk_buff *skb = build_skb(buf, buflen); if (!skb) return ERR_PTR(-ENOMEM); skb_reserve(skb, pad); skb_put(skb, len); skb_set_owner_w(skb, tfile->socket.sk); get_page(alloc_frag->page); alloc_frag->offset += buflen; return skb; } static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog, struct xdp_buff *xdp, u32 act) { int err; switch (act) { case XDP_REDIRECT: err = xdp_do_redirect(tun->dev, xdp, xdp_prog); if (err) return err; break; case XDP_TX: err = tun_xdp_tx(tun->dev, xdp); if (err < 0) return err; break; case XDP_PASS: break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: trace_xdp_exception(tun->dev, xdp_prog, act); fallthrough; case XDP_DROP: this_cpu_inc(tun->pcpu_stats->rx_dropped); break; } return act; } static struct sk_buff *tun_build_skb(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *from, struct virtio_net_hdr *hdr, int len, int *skb_xdp) { struct page_frag *alloc_frag = &current->task_frag; struct bpf_prog *xdp_prog; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); char *buf; size_t copied; int pad = TUN_RX_PAD; int err = 0; rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) pad += XDP_PACKET_HEADROOM; buflen += SKB_DATA_ALIGN(len + pad); rcu_read_unlock(); alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL))) return ERR_PTR(-ENOMEM); buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; copied = copy_page_from_iter(alloc_frag->page, alloc_frag->offset + pad, len, from); if (copied != len) return ERR_PTR(-EFAULT); /* There's a small window that XDP may be set after the check * of xdp_prog above, this should be rare and for simplicity * we do XDP on skb in case the headroom is not enough. */ if (hdr->gso_type || !xdp_prog) { *skb_xdp = 1; return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad); } *skb_xdp = 0; local_bh_disable(); rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { struct xdp_buff xdp; u32 act; xdp.data_hard_start = buf; xdp.data = buf + pad; xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; xdp.rxq = &tfile->xdp_rxq; xdp.frame_sz = buflen; act = bpf_prog_run_xdp(xdp_prog, &xdp); if (act == XDP_REDIRECT || act == XDP_TX) { get_page(alloc_frag->page); alloc_frag->offset += buflen; } err = tun_xdp_act(tun, xdp_prog, &xdp, act); if (err < 0) { if (act == XDP_REDIRECT || act == XDP_TX) put_page(alloc_frag->page); goto out; } if (err == XDP_REDIRECT) xdp_do_flush(); if (err != XDP_PASS) goto out; pad = xdp.data - xdp.data_hard_start; len = xdp.data_end - xdp.data; } rcu_read_unlock(); local_bh_enable(); return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad); out: rcu_read_unlock(); local_bh_enable(); return NULL; } /* Get packet from user space buffer */ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, void *msg_control, struct iov_iter *from, int noblock, bool more) { struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) }; struct sk_buff *skb; size_t total_len = iov_iter_count(from); size_t len = total_len, align = tun->align, linear; struct virtio_net_hdr gso = { 0 }; struct tun_pcpu_stats *stats; int good_linear; int copylen; bool zerocopy = false; int err; u32 rxhash = 0; int skb_xdp = 1; bool frags = tun_napi_frags_enabled(tfile); if (!(tun->flags & IFF_NO_PI)) { if (len < sizeof(pi)) return -EINVAL; len -= sizeof(pi); if (!copy_from_iter_full(&pi, sizeof(pi), from)) return -EFAULT; } if (tun->flags & IFF_VNET_HDR) { int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); if (len < vnet_hdr_sz) return -EINVAL; len -= vnet_hdr_sz; if (!copy_from_iter_full(&gso, sizeof(gso), from)) return -EFAULT; if ((gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2 > tun16_to_cpu(tun, gso.hdr_len)) gso.hdr_len = cpu_to_tun16(tun, tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2); if (tun16_to_cpu(tun, gso.hdr_len) > len) return -EINVAL; iov_iter_advance(from, vnet_hdr_sz - sizeof(gso)); } if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) { align += NET_IP_ALIGN; if (unlikely(len < ETH_HLEN || (gso.hdr_len && tun16_to_cpu(tun, gso.hdr_len) < ETH_HLEN))) return -EINVAL; } good_linear = SKB_MAX_HEAD(align); if (msg_control) { struct iov_iter i = *from; /* There are 256 bytes to be copied in skb, so there is * enough room for skb expand head in case it is used. * The rest of the buffer is mapped from userspace. */ copylen = gso.hdr_len ? tun16_to_cpu(tun, gso.hdr_len) : GOODCOPY_LEN; if (copylen > good_linear) copylen = good_linear; linear = copylen; iov_iter_advance(&i, copylen); if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS) zerocopy = true; } if (!frags && tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) { /* For the packet that is not easy to be processed * (e.g gso or jumbo packet), we will do it at after * skb was created with generic XDP routine. */ skb = tun_build_skb(tun, tfile, from, &gso, len, &skb_xdp); if (IS_ERR(skb)) { this_cpu_inc(tun->pcpu_stats->rx_dropped); return PTR_ERR(skb); } if (!skb) return total_len; } else { if (!zerocopy) { copylen = len; if (tun16_to_cpu(tun, gso.hdr_len) > good_linear) linear = good_linear; else linear = tun16_to_cpu(tun, gso.hdr_len); } if (frags) { mutex_lock(&tfile->napi_mutex); skb = tun_napi_alloc_frags(tfile, copylen, from); /* tun_napi_alloc_frags() enforces a layout for the skb. * If zerocopy is enabled, then this layout will be * overwritten by zerocopy_sg_from_iter(). */ zerocopy = false; } else { skb = tun_alloc_skb(tfile, align, copylen, linear, noblock); } if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EAGAIN) this_cpu_inc(tun->pcpu_stats->rx_dropped); if (frags) mutex_unlock(&tfile->napi_mutex); return PTR_ERR(skb); } if (zerocopy) err = zerocopy_sg_from_iter(skb, from); else err = skb_copy_datagram_from_iter(skb, 0, from, len); if (err) { err = -EFAULT; drop: this_cpu_inc(tun->pcpu_stats->rx_dropped); kfree_skb(skb); if (frags) { tfile->napi.skb = NULL; mutex_unlock(&tfile->napi_mutex); } return err; } } if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun))) { this_cpu_inc(tun->pcpu_stats->rx_frame_errors); kfree_skb(skb); if (frags) { tfile->napi.skb = NULL; mutex_unlock(&tfile->napi_mutex); } return -EINVAL; } switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: if (tun->flags & IFF_NO_PI) { u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0; switch (ip_version) { case 4: pi.proto = htons(ETH_P_IP); break; case 6: pi.proto = htons(ETH_P_IPV6); break; default: this_cpu_inc(tun->pcpu_stats->rx_dropped); kfree_skb(skb); return -EINVAL; } } skb_reset_mac_header(skb); skb->protocol = pi.proto; skb->dev = tun->dev; break; case IFF_TAP: if (frags && !pskb_may_pull(skb, ETH_HLEN)) { err = -ENOMEM; goto drop; } skb->protocol = eth_type_trans(skb, tun->dev); break; } /* copy skb_ubuf_info for callback when skb has no error */ if (zerocopy) { skb_shinfo(skb)->destructor_arg = msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; } else if (msg_control) { struct ubuf_info *uarg = msg_control; uarg->callback(uarg, false); } skb_reset_network_header(skb); skb_probe_transport_header(skb); skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { struct bpf_prog *xdp_prog; int ret; local_bh_disable(); rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { ret = do_xdp_generic(xdp_prog, skb); if (ret != XDP_PASS) { rcu_read_unlock(); local_bh_enable(); if (frags) { tfile->napi.skb = NULL; mutex_unlock(&tfile->napi_mutex); } return total_len; } } rcu_read_unlock(); local_bh_enable(); } /* Compute the costly rx hash only if needed for flow updates. * We may get a very small possibility of OOO during switching, not * worth to optimize. */ if (!rcu_access_pointer(tun->steering_prog) && tun->numqueues > 1 && !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); rcu_read_lock(); if (unlikely(!(tun->dev->flags & IFF_UP))) { err = -EIO; rcu_read_unlock(); goto drop; } if (frags) { u32 headlen; /* Exercise flow dissector code path. */ skb_push(skb, ETH_HLEN); headlen = eth_get_headlen(tun->dev, skb->data, skb_headlen(skb)); if (unlikely(headlen > skb_headlen(skb))) { this_cpu_inc(tun->pcpu_stats->rx_dropped); napi_free_frags(&tfile->napi); rcu_read_unlock(); mutex_unlock(&tfile->napi_mutex); WARN_ON(1); return -ENOMEM; } local_bh_disable(); napi_gro_frags(&tfile->napi); local_bh_enable(); mutex_unlock(&tfile->napi_mutex); } else if (tfile->napi_enabled) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; int queue_len; spin_lock_bh(&queue->lock); __skb_queue_tail(queue, skb); queue_len = skb_queue_len(queue); spin_unlock(&queue->lock); if (!more || queue_len > NAPI_POLL_WEIGHT) napi_schedule(&tfile->napi); local_bh_enable(); } else if (!IS_ENABLED(CONFIG_4KSTACKS)) { tun_rx_batched(tun, tfile, skb, more); } else { netif_rx_ni(skb); } rcu_read_unlock(); stats = get_cpu_ptr(tun->pcpu_stats); u64_stats_update_begin(&stats->syncp); u64_stats_inc(&stats->rx_packets); u64_stats_add(&stats->rx_bytes, len); u64_stats_update_end(&stats->syncp); put_cpu_ptr(stats); if (rxhash) tun_flow_update(tun, rxhash, tfile); return total_len; } static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t result; int noblock = 0; if (!tun) return -EBADFD; if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) noblock = 1; result = tun_get_user(tun, tfile, NULL, from, noblock, false); tun_put(tun); return result; } static ssize_t tun_put_user_xdp(struct tun_struct *tun, struct tun_file *tfile, struct xdp_frame *xdp_frame, struct iov_iter *iter) { int vnet_hdr_sz = 0; size_t size = xdp_frame->len; struct tun_pcpu_stats *stats; size_t ret; if (tun->flags & IFF_VNET_HDR) { struct virtio_net_hdr gso = { 0 }; vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); if (unlikely(iov_iter_count(iter) < vnet_hdr_sz)) return -EINVAL; if (unlikely(copy_to_iter(&gso, sizeof(gso), iter) != sizeof(gso))) return -EFAULT; iov_iter_advance(iter, vnet_hdr_sz - sizeof(gso)); } ret = copy_to_iter(xdp_frame->data, size, iter) + vnet_hdr_sz; stats = get_cpu_ptr(tun->pcpu_stats); u64_stats_update_begin(&stats->syncp); u64_stats_inc(&stats->tx_packets); u64_stats_add(&stats->tx_bytes, ret); u64_stats_update_end(&stats->syncp); put_cpu_ptr(tun->pcpu_stats); return ret; } /* Put packet to the user space buffer */ static ssize_t tun_put_user(struct tun_struct *tun, struct tun_file *tfile, struct sk_buff *skb, struct iov_iter *iter) { struct tun_pi pi = { 0, skb->protocol }; struct tun_pcpu_stats *stats; ssize_t total; int vlan_offset = 0; int vlan_hlen = 0; int vnet_hdr_sz = 0; if (skb_vlan_tag_present(skb)) vlan_hlen = VLAN_HLEN; if (tun->flags & IFF_VNET_HDR) vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); total = skb->len + vlan_hlen + vnet_hdr_sz; if (!(tun->flags & IFF_NO_PI)) { if (iov_iter_count(iter) < sizeof(pi)) return -EINVAL; total += sizeof(pi); if (iov_iter_count(iter) < total) { /* Packet will be striped */ pi.flags |= TUN_PKT_STRIP; } if (copy_to_iter(&pi, sizeof(pi), iter) != sizeof(pi)) return -EFAULT; } if (vnet_hdr_sz) { struct virtio_net_hdr gso; if (iov_iter_count(iter) < vnet_hdr_sz) return -EINVAL; if (virtio_net_hdr_from_skb(skb, &gso, tun_is_little_endian(tun), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); pr_err("unexpected GSO type: " "0x%x, gso_size %d, hdr_len %d\n", sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), tun16_to_cpu(tun, gso.hdr_len)); print_hex_dump(KERN_ERR, "tun: ", DUMP_PREFIX_NONE, 16, 1, skb->head, min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); WARN_ON_ONCE(1); return -EINVAL; } if (copy_to_iter(&gso, sizeof(gso), iter) != sizeof(gso)) return -EFAULT; iov_iter_advance(iter, vnet_hdr_sz - sizeof(gso)); } if (vlan_hlen) { int ret; struct veth veth; veth.h_vlan_proto = skb->vlan_proto; veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto); ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset); if (ret || !iov_iter_count(iter)) goto done; ret = copy_to_iter(&veth, sizeof(veth), iter); if (ret != sizeof(veth) || !iov_iter_count(iter)) goto done; } skb_copy_datagram_iter(skb, vlan_offset, iter, skb->len - vlan_offset); done: /* caller is in process context, */ stats = get_cpu_ptr(tun->pcpu_stats); u64_stats_update_begin(&stats->syncp); u64_stats_inc(&stats->tx_packets); u64_stats_add(&stats->tx_bytes, skb->len + vlan_hlen); u64_stats_update_end(&stats->syncp); put_cpu_ptr(tun->pcpu_stats); return total; } static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err) { DECLARE_WAITQUEUE(wait, current); void *ptr = NULL; int error = 0; ptr = ptr_ring_consume(&tfile->tx_ring); if (ptr) goto out; if (noblock) { error = -EAGAIN; goto out; } add_wait_queue(&tfile->socket.wq.wait, &wait); while (1) { set_current_state(TASK_INTERRUPTIBLE); ptr = ptr_ring_consume(&tfile->tx_ring); if (ptr) break; if (signal_pending(current)) { error = -ERESTARTSYS; break; } if (tfile->socket.sk->sk_shutdown & RCV_SHUTDOWN) { error = -EFAULT; break; } schedule(); } __set_current_state(TASK_RUNNING); remove_wait_queue(&tfile->socket.wq.wait, &wait); out: *err = error; return ptr; } static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *to, int noblock, void *ptr) { ssize_t ret; int err; if (!iov_iter_count(to)) { tun_ptr_free(ptr); return 0; } if (!ptr) { /* Read frames from ring */ ptr = tun_ring_recv(tfile, noblock, &err); if (!ptr) return err; } if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); ret = tun_put_user_xdp(tun, tfile, xdpf, to); xdp_return_frame(xdpf); } else { struct sk_buff *skb = ptr; ret = tun_put_user(tun, tfile, skb, to); if (unlikely(ret < 0)) kfree_skb(skb); else consume_skb(skb); } return ret; } static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t len = iov_iter_count(to), ret; int noblock = 0; if (!tun) return -EBADFD; if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) noblock = 1; ret = tun_do_read(tun, tfile, to, noblock, NULL); ret = min_t(ssize_t, ret, len); if (ret > 0) iocb->ki_pos = ret; tun_put(tun); return ret; } static void tun_prog_free(struct rcu_head *rcu) { struct tun_prog *prog = container_of(rcu, struct tun_prog, rcu); bpf_prog_destroy(prog->prog); kfree(prog); } static int __tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, struct bpf_prog *prog) { struct tun_prog *old, *new = NULL; if (prog) { new = kmalloc(sizeof(*new), GFP_KERNEL); if (!new) return -ENOMEM; new->prog = prog; } spin_lock_bh(&tun->lock); old = rcu_dereference_protected(*prog_p, lockdep_is_held(&tun->lock)); rcu_assign_pointer(*prog_p, new); spin_unlock_bh(&tun->lock); if (old) call_rcu(&old->rcu, tun_prog_free); return 0; } static void tun_free_netdev(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); BUG_ON(!(list_empty(&tun->disabled))); free_percpu(tun->pcpu_stats); /* We clear pcpu_stats so that tun_set_iff() can tell if * tun_free_netdev() has been called from register_netdevice(). */ tun->pcpu_stats = NULL; tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); __tun_set_ebpf(tun, &tun->steering_prog, NULL); __tun_set_ebpf(tun, &tun->filter_prog, NULL); } static void tun_setup(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); tun->owner = INVALID_UID; tun->group = INVALID_GID; tun_default_link_ksettings(dev, &tun->link_ksettings); dev->ethtool_ops = &tun_ethtool_ops; dev->needs_free_netdev = true; dev->priv_destructor = tun_free_netdev; /* We prefer our own queue length */ dev->tx_queue_len = TUN_READQ_SIZE; } /* Trivial set of netlink ops to allow deleting tun or tap * device with netlink. */ static int tun_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "tun/tap creation via rtnetlink is not supported."); return -EOPNOTSUPP; } static size_t tun_get_size(const struct net_device *dev) { BUILD_BUG_ON(sizeof(u32) != sizeof(uid_t)); BUILD_BUG_ON(sizeof(u32) != sizeof(gid_t)); return nla_total_size(sizeof(uid_t)) + /* OWNER */ nla_total_size(sizeof(gid_t)) + /* GROUP */ nla_total_size(sizeof(u8)) + /* TYPE */ nla_total_size(sizeof(u8)) + /* PI */ nla_total_size(sizeof(u8)) + /* VNET_HDR */ nla_total_size(sizeof(u8)) + /* PERSIST */ nla_total_size(sizeof(u8)) + /* MULTI_QUEUE */ nla_total_size(sizeof(u32)) + /* NUM_QUEUES */ nla_total_size(sizeof(u32)) + /* NUM_DISABLED_QUEUES */ 0; } static int tun_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); if (nla_put_u8(skb, IFLA_TUN_TYPE, tun->flags & TUN_TYPE_MASK)) goto nla_put_failure; if (uid_valid(tun->owner) && nla_put_u32(skb, IFLA_TUN_OWNER, from_kuid_munged(current_user_ns(), tun->owner))) goto nla_put_failure; if (gid_valid(tun->group) && nla_put_u32(skb, IFLA_TUN_GROUP, from_kgid_munged(current_user_ns(), tun->group))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_PI, !(tun->flags & IFF_NO_PI))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_VNET_HDR, !!(tun->flags & IFF_VNET_HDR))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_PERSIST, !!(tun->flags & IFF_PERSIST))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_MULTI_QUEUE, !!(tun->flags & IFF_MULTI_QUEUE))) goto nla_put_failure; if (tun->flags & IFF_MULTI_QUEUE) { if (nla_put_u32(skb, IFLA_TUN_NUM_QUEUES, tun->numqueues)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_TUN_NUM_DISABLED_QUEUES, tun->numdisabled)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops tun_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct tun_struct), .setup = tun_setup, .validate = tun_validate, .get_size = tun_get_size, .fill_info = tun_fill_info, }; static void tun_sock_write_space(struct sock *sk) { struct tun_file *tfile; wait_queue_head_t *wqueue; if (!sock_writeable(sk)) return; if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; wqueue = sk_sleep(sk); if (wqueue && waitqueue_active(wqueue)) wake_up_interruptible_sync_poll(wqueue, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); tfile = container_of(sk, struct tun_file, sk); kill_fasync(&tfile->fasync, SIGIO, POLL_OUT); } static void tun_put_page(struct tun_page *tpage) { if (tpage->page) __page_frag_cache_drain(tpage->page, tpage->count); } static int tun_xdp_one(struct tun_struct *tun, struct tun_file *tfile, struct xdp_buff *xdp, int *flush, struct tun_page *tpage) { unsigned int datasize = xdp->data_end - xdp->data; struct tun_xdp_hdr *hdr = xdp->data_hard_start; struct virtio_net_hdr *gso = &hdr->gso; struct tun_pcpu_stats *stats; struct bpf_prog *xdp_prog; struct sk_buff *skb = NULL; u32 rxhash = 0, act; int buflen = hdr->buflen; int err = 0; bool skb_xdp = false; struct page *page; xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { if (gso->gso_type) { skb_xdp = true; goto build; } xdp_set_data_meta_invalid(xdp); xdp->rxq = &tfile->xdp_rxq; xdp->frame_sz = buflen; act = bpf_prog_run_xdp(xdp_prog, xdp); err = tun_xdp_act(tun, xdp_prog, xdp, act); if (err < 0) { put_page(virt_to_head_page(xdp->data)); return err; } switch (err) { case XDP_REDIRECT: *flush = true; fallthrough; case XDP_TX: return 0; case XDP_PASS: break; default: page = virt_to_head_page(xdp->data); if (tpage->page == page) { ++tpage->count; } else { tun_put_page(tpage); tpage->page = page; tpage->count = 1; } return 0; } } build: skb = build_skb(xdp->data_hard_start, buflen); if (!skb) { err = -ENOMEM; goto out; } skb_reserve(skb, xdp->data - xdp->data_hard_start); skb_put(skb, xdp->data_end - xdp->data); if (virtio_net_hdr_to_skb(skb, gso, tun_is_little_endian(tun))) { this_cpu_inc(tun->pcpu_stats->rx_frame_errors); kfree_skb(skb); err = -EINVAL; goto out; } skb->protocol = eth_type_trans(skb, tun->dev); skb_reset_network_header(skb); skb_probe_transport_header(skb); skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { err = do_xdp_generic(xdp_prog, skb); if (err != XDP_PASS) goto out; } if (!rcu_dereference(tun->steering_prog) && tun->numqueues > 1 && !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); netif_receive_skb(skb); /* No need for get_cpu_ptr() here since this function is * always called with bh disabled */ stats = this_cpu_ptr(tun->pcpu_stats); u64_stats_update_begin(&stats->syncp); u64_stats_inc(&stats->rx_packets); u64_stats_add(&stats->rx_bytes, datasize); u64_stats_update_end(&stats->syncp); if (rxhash) tun_flow_update(tun, rxhash, tfile); out: return err; } static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { int ret, i; struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); struct tun_msg_ctl *ctl = m->msg_control; struct xdp_buff *xdp; if (!tun) return -EBADFD; if (ctl && (ctl->type == TUN_MSG_PTR)) { struct tun_page tpage; int n = ctl->num; int flush = 0; memset(&tpage, 0, sizeof(tpage)); local_bh_disable(); rcu_read_lock(); for (i = 0; i < n; i++) { xdp = &((struct xdp_buff *)ctl->ptr)[i]; tun_xdp_one(tun, tfile, xdp, &flush, &tpage); } if (flush) xdp_do_flush(); rcu_read_unlock(); local_bh_enable(); tun_put_page(&tpage); ret = total_len; goto out; } ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter, m->msg_flags & MSG_DONTWAIT, m->msg_flags & MSG_MORE); out: tun_put(tun); return ret; } static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len, int flags) { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); void *ptr = m->msg_control; int ret; if (!tun) { ret = -EBADFD; goto out_free; } if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) { ret = -EINVAL; goto out_put_tun; } if (flags & MSG_ERRQUEUE) { ret = sock_recv_errqueue(sock->sk, m, total_len, SOL_PACKET, TUN_TX_TIMESTAMP); goto out; } ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, ptr); if (ret > (ssize_t)total_len) { m->msg_flags |= MSG_TRUNC; ret = flags & MSG_TRUNC ? ret : total_len; } out: tun_put(tun); return ret; out_put_tun: tun_put(tun); out_free: tun_ptr_free(ptr); return ret; } static int tun_ptr_peek_len(void *ptr) { if (likely(ptr)) { if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); return xdpf->len; } return __skb_array_len_with_tag(ptr); } else { return 0; } } static int tun_peek_len(struct socket *sock) { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun; int ret = 0; tun = tun_get(tfile); if (!tun) return 0; ret = PTR_RING_PEEK_CALL(&tfile->tx_ring, tun_ptr_peek_len); tun_put(tun); return ret; } /* Ops structure to mimic raw sockets with tun */ static const struct proto_ops tun_socket_ops = { .peek_len = tun_peek_len, .sendmsg = tun_sendmsg, .recvmsg = tun_recvmsg, }; static struct proto tun_proto = { .name = "tun", .owner = THIS_MODULE, .obj_size = sizeof(struct tun_file), }; static int tun_flags(struct tun_struct *tun) { return tun->flags & (TUN_FEATURES | IFF_PERSIST | IFF_TUN | IFF_TAP); } static ssize_t tun_show_flags(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return sprintf(buf, "0x%x\n", tun_flags(tun)); } static ssize_t tun_show_owner(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return uid_valid(tun->owner)? sprintf(buf, "%u\n", from_kuid_munged(current_user_ns(), tun->owner)): sprintf(buf, "-1\n"); } static ssize_t tun_show_group(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return gid_valid(tun->group) ? sprintf(buf, "%u\n", from_kgid_munged(current_user_ns(), tun->group)): sprintf(buf, "-1\n"); } static DEVICE_ATTR(tun_flags, 0444, tun_show_flags, NULL); static DEVICE_ATTR(owner, 0444, tun_show_owner, NULL); static DEVICE_ATTR(group, 0444, tun_show_group, NULL); static struct attribute *tun_dev_attrs[] = { &dev_attr_tun_flags.attr, &dev_attr_owner.attr, &dev_attr_group.attr, NULL }; static const struct attribute_group tun_attr_group = { .attrs = tun_dev_attrs }; static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) { struct tun_struct *tun; struct tun_file *tfile = file->private_data; struct net_device *dev; int err; if (tfile->detached) return -EINVAL; if ((ifr->ifr_flags & IFF_NAPI_FRAGS)) { if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!(ifr->ifr_flags & IFF_NAPI) || (ifr->ifr_flags & TUN_TYPE_MASK) != IFF_TAP) return -EINVAL; } dev = __dev_get_by_name(net, ifr->ifr_name); if (dev) { if (ifr->ifr_flags & IFF_TUN_EXCL) return -EBUSY; if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops) tun = netdev_priv(dev); else if ((ifr->ifr_flags & IFF_TAP) && dev->netdev_ops == &tap_netdev_ops) tun = netdev_priv(dev); else return -EINVAL; if (!!(ifr->ifr_flags & IFF_MULTI_QUEUE) != !!(tun->flags & IFF_MULTI_QUEUE)) return -EINVAL; if (tun_not_capable(tun)) return -EPERM; err = security_tun_dev_open(tun->security); if (err < 0) return err; err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER, ifr->ifr_flags & IFF_NAPI, ifr->ifr_flags & IFF_NAPI_FRAGS, true); if (err < 0) return err; if (tun->flags & IFF_MULTI_QUEUE && (tun->numqueues + tun->numdisabled > 1)) { /* One or more queue has already been attached, no need * to initialize the device again. */ netdev_state_change(dev); return 0; } tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); netdev_state_change(dev); } else { char *name; unsigned long flags = 0; int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; err = security_tun_dev_create(); if (err < 0) return err; /* Set dev type */ if (ifr->ifr_flags & IFF_TUN) { /* TUN device */ flags |= IFF_TUN; name = "tun%d"; } else if (ifr->ifr_flags & IFF_TAP) { /* TAP device */ flags |= IFF_TAP; name = "tap%d"; } else return -EINVAL; if (*ifr->ifr_name) name = ifr->ifr_name; dev = alloc_netdev_mqs(sizeof(struct tun_struct), name, NET_NAME_UNKNOWN, tun_setup, queues, queues); if (!dev) return -ENOMEM; dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; dev->ifindex = tfile->ifindex; dev->sysfs_groups[0] = &tun_attr_group; tun = netdev_priv(dev); tun->dev = dev; tun->flags = flags; tun->txflt.count = 0; tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr); tun->align = NET_SKB_PAD; tun->filter_attached = false; tun->sndbuf = tfile->socket.sk->sk_sndbuf; tun->rx_batched = 0; RCU_INIT_POINTER(tun->steering_prog, NULL); tun->pcpu_stats = netdev_alloc_pcpu_stats(struct tun_pcpu_stats); if (!tun->pcpu_stats) { err = -ENOMEM; goto err_free_dev; } spin_lock_init(&tun->lock); err = security_tun_dev_alloc_security(&tun->security); if (err < 0) goto err_free_stat; tun_net_init(dev); tun_flow_init(tun); dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->features = dev->hw_features | NETIF_F_LLTX; dev->vlan_features = dev->features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); INIT_LIST_HEAD(&tun->disabled); err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI, ifr->ifr_flags & IFF_NAPI_FRAGS, false); if (err < 0) goto err_free_flow; err = register_netdevice(tun->dev); if (err < 0) goto err_detach; /* free_netdev() won't check refcnt, to aovid race * with dev_put() we need publish tun after registration. */ rcu_assign_pointer(tfile->tun, tun); } netif_carrier_on(tun->dev); /* Make sure persistent devices do not get stuck in * xoff state. */ if (netif_running(tun->dev)) netif_tx_wake_all_queues(tun->dev); strcpy(ifr->ifr_name, tun->dev->name); return 0; err_detach: tun_detach_all(dev); /* We are here because register_netdevice() has failed. * If register_netdevice() already called tun_free_netdev() * while dealing with the error, tun->pcpu_stats has been cleared. */ if (!tun->pcpu_stats) goto err_free_dev; err_free_flow: tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); err_free_stat: free_percpu(tun->pcpu_stats); err_free_dev: free_netdev(dev); return err; } static void tun_get_iff(struct tun_struct *tun, struct ifreq *ifr) { strcpy(ifr->ifr_name, tun->dev->name); ifr->ifr_flags = tun_flags(tun); } /* This is like a cut-down ethtool ops, except done via tun fd so no * privs required. */ static int set_offload(struct tun_struct *tun, unsigned long arg) { netdev_features_t features = 0; if (arg & TUN_F_CSUM) { features |= NETIF_F_HW_CSUM; arg &= ~TUN_F_CSUM; if (arg & (TUN_F_TSO4|TUN_F_TSO6)) { if (arg & TUN_F_TSO_ECN) { features |= NETIF_F_TSO_ECN; arg &= ~TUN_F_TSO_ECN; } if (arg & TUN_F_TSO4) features |= NETIF_F_TSO; if (arg & TUN_F_TSO6) features |= NETIF_F_TSO6; arg &= ~(TUN_F_TSO4|TUN_F_TSO6); } arg &= ~TUN_F_UFO; } /* This gives the user a way to test for new features in future by * trying to set them. */ if (arg) return -EINVAL; tun->set_features = features; tun->dev->wanted_features &= ~TUN_USER_FEATURES; tun->dev->wanted_features |= features; netdev_update_features(tun->dev); return 0; } static void tun_detach_filter(struct tun_struct *tun, int n) { int i; struct tun_file *tfile; for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); lock_sock(tfile->socket.sk); sk_detach_filter(tfile->socket.sk); release_sock(tfile->socket.sk); } tun->filter_attached = false; } static int tun_attach_filter(struct tun_struct *tun) { int i, ret = 0; struct tun_file *tfile; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); lock_sock(tfile->socket.sk); ret = sk_attach_filter(&tun->fprog, tfile->socket.sk); release_sock(tfile->socket.sk); if (ret) { tun_detach_filter(tun, i); return ret; } } tun->filter_attached = true; return ret; } static void tun_set_sndbuf(struct tun_struct *tun) { struct tun_file *tfile; int i; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); tfile->socket.sk->sk_sndbuf = tun->sndbuf; } } static int tun_set_queue(struct file *file, struct ifreq *ifr) { struct tun_file *tfile = file->private_data; struct tun_struct *tun; int ret = 0; rtnl_lock(); if (ifr->ifr_flags & IFF_ATTACH_QUEUE) { tun = tfile->detached; if (!tun) { ret = -EINVAL; goto unlock; } ret = security_tun_dev_attach_queue(tun->security); if (ret < 0) goto unlock; ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI, tun->flags & IFF_NAPI_FRAGS, true); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached) ret = -EINVAL; else __tun_detach(tfile, false); } else ret = -EINVAL; if (ret >= 0) netdev_state_change(tun->dev); unlock: rtnl_unlock(); return ret; } static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, void __user *data) { struct bpf_prog *prog; int fd; if (copy_from_user(&fd, data, sizeof(fd))) return -EFAULT; if (fd == -1) { prog = NULL; } else { prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(prog)) return PTR_ERR(prog); } return __tun_set_ebpf(tun, prog_p, prog); } /* Return correct value for tun->dev->addr_len based on tun->dev->type. */ static unsigned char tun_get_addr_len(unsigned short type) { switch (type) { case ARPHRD_IP6GRE: case ARPHRD_TUNNEL6: return sizeof(struct in6_addr); case ARPHRD_IPGRE: case ARPHRD_TUNNEL: case ARPHRD_SIT: return 4; case ARPHRD_ETHER: return ETH_ALEN; case ARPHRD_IEEE802154: case ARPHRD_IEEE802154_MONITOR: return IEEE802154_EXTENDED_ADDR_LEN; case ARPHRD_PHONET_PIPE: case ARPHRD_PPP: case ARPHRD_NONE: return 0; case ARPHRD_6LOWPAN: return EUI64_ADDR_LEN; case ARPHRD_FDDI: return FDDI_K_ALEN; case ARPHRD_HIPPI: return HIPPI_ALEN; case ARPHRD_IEEE802: return FC_ALEN; case ARPHRD_ROSE: return ROSE_ADDR_LEN; case ARPHRD_NETROM: return AX25_ADDR_LEN; case ARPHRD_LOCALTLK: return LTALK_ALEN; default: return 0; } } static long __tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg, int ifreq_len) { struct tun_file *tfile = file->private_data; struct net *net = sock_net(&tfile->sk); struct tun_struct *tun; void __user* argp = (void __user*)arg; unsigned int ifindex, carrier; struct ifreq ifr; kuid_t owner; kgid_t group; int sndbuf; int vnet_hdr_sz; int le; int ret; bool do_notify = false; if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || (_IOC_TYPE(cmd) == SOCK_IOC_TYPE && cmd != SIOCGSKNS)) { if (copy_from_user(&ifr, argp, ifreq_len)) return -EFAULT; } else { memset(&ifr, 0, sizeof(ifr)); } if (cmd == TUNGETFEATURES) { /* Currently this just means: "what IFF flags are valid?". * This is needed because we never checked for invalid flags on * TUNSETIFF. */ return put_user(IFF_TUN | IFF_TAP | TUN_FEATURES, (unsigned int __user*)argp); } else if (cmd == TUNSETQUEUE) { return tun_set_queue(file, &ifr); } else if (cmd == SIOCGSKNS) { if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; return open_related_ns(&net->ns, get_net_ns); } ret = 0; rtnl_lock(); tun = tun_get(tfile); if (cmd == TUNSETIFF) { ret = -EEXIST; if (tun) goto unlock; ifr.ifr_name[IFNAMSIZ-1] = '\0'; ret = tun_set_iff(net, file, &ifr); if (ret) goto unlock; if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; goto unlock; } if (cmd == TUNSETIFINDEX) { ret = -EPERM; if (tun) goto unlock; ret = -EFAULT; if (copy_from_user(&ifindex, argp, sizeof(ifindex))) goto unlock; ret = 0; tfile->ifindex = ifindex; goto unlock; } ret = -EBADFD; if (!tun) goto unlock; netif_info(tun, drv, tun->dev, "tun_chr_ioctl cmd %u\n", cmd); net = dev_net(tun->dev); ret = 0; switch (cmd) { case TUNGETIFF: tun_get_iff(tun, &ifr); if (tfile->detached) ifr.ifr_flags |= IFF_DETACH_QUEUE; if (!tfile->socket.sk->sk_filter) ifr.ifr_flags |= IFF_NOFILTER; if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; case TUNSETNOCSUM: /* Disable/Enable checksum */ /* [unimplemented] */ netif_info(tun, drv, tun->dev, "ignored: set checksum %s\n", arg ? "disabled" : "enabled"); break; case TUNSETPERSIST: /* Disable/Enable persist mode. Keep an extra reference to the * module to prevent the module being unprobed. */ if (arg && !(tun->flags & IFF_PERSIST)) { tun->flags |= IFF_PERSIST; __module_get(THIS_MODULE); do_notify = true; } if (!arg && (tun->flags & IFF_PERSIST)) { tun->flags &= ~IFF_PERSIST; module_put(THIS_MODULE); do_notify = true; } netif_info(tun, drv, tun->dev, "persist %s\n", arg ? "enabled" : "disabled"); break; case TUNSETOWNER: /* Set owner of the device */ owner = make_kuid(current_user_ns(), arg); if (!uid_valid(owner)) { ret = -EINVAL; break; } tun->owner = owner; do_notify = true; netif_info(tun, drv, tun->dev, "owner set to %u\n", from_kuid(&init_user_ns, tun->owner)); break; case TUNSETGROUP: /* Set group of the device */ group = make_kgid(current_user_ns(), arg); if (!gid_valid(group)) { ret = -EINVAL; break; } tun->group = group; do_notify = true; netif_info(tun, drv, tun->dev, "group set to %u\n", from_kgid(&init_user_ns, tun->group)); break; case TUNSETLINK: /* Only allow setting the type when the interface is down */ if (tun->dev->flags & IFF_UP) { netif_info(tun, drv, tun->dev, "Linktype set failed because interface is up\n"); ret = -EBUSY; } else { tun->dev->type = (int) arg; tun->dev->addr_len = tun_get_addr_len(tun->dev->type); netif_info(tun, drv, tun->dev, "linktype set to %d\n", tun->dev->type); ret = 0; } break; case TUNSETDEBUG: tun->msg_enable = (u32)arg; break; case TUNSETOFFLOAD: ret = set_offload(tun, arg); break; case TUNSETTXFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = update_filter(&tun->txflt, (void __user *)arg); break; case SIOCGIFHWADDR: /* Get hw address */ dev_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name); if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; case SIOCSIFHWADDR: /* Set hw address */ ret = dev_set_mac_address_user(tun->dev, &ifr.ifr_hwaddr, NULL); break; case TUNGETSNDBUF: sndbuf = tfile->socket.sk->sk_sndbuf; if (copy_to_user(argp, &sndbuf, sizeof(sndbuf))) ret = -EFAULT; break; case TUNSETSNDBUF: if (copy_from_user(&sndbuf, argp, sizeof(sndbuf))) { ret = -EFAULT; break; } if (sndbuf <= 0) { ret = -EINVAL; break; } tun->sndbuf = sndbuf; tun_set_sndbuf(tun); break; case TUNGETVNETHDRSZ: vnet_hdr_sz = tun->vnet_hdr_sz; if (copy_to_user(argp, &vnet_hdr_sz, sizeof(vnet_hdr_sz))) ret = -EFAULT; break; case TUNSETVNETHDRSZ: if (copy_from_user(&vnet_hdr_sz, argp, sizeof(vnet_hdr_sz))) { ret = -EFAULT; break; } if (vnet_hdr_sz < (int)sizeof(struct virtio_net_hdr)) { ret = -EINVAL; break; } tun->vnet_hdr_sz = vnet_hdr_sz; break; case TUNGETVNETLE: le = !!(tun->flags & TUN_VNET_LE); if (put_user(le, (int __user *)argp)) ret = -EFAULT; break; case TUNSETVNETLE: if (get_user(le, (int __user *)argp)) { ret = -EFAULT; break; } if (le) tun->flags |= TUN_VNET_LE; else tun->flags &= ~TUN_VNET_LE; break; case TUNGETVNETBE: ret = tun_get_vnet_be(tun, argp); break; case TUNSETVNETBE: ret = tun_set_vnet_be(tun, argp); break; case TUNATTACHFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = -EFAULT; if (copy_from_user(&tun->fprog, argp, sizeof(tun->fprog))) break; ret = tun_attach_filter(tun); break; case TUNDETACHFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = 0; tun_detach_filter(tun, tun->numqueues); break; case TUNGETFILTER: ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = -EFAULT; if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog))) break; ret = 0; break; case TUNSETSTEERINGEBPF: ret = tun_set_ebpf(tun, &tun->steering_prog, argp); break; case TUNSETFILTEREBPF: ret = tun_set_ebpf(tun, &tun->filter_prog, argp); break; case TUNSETCARRIER: ret = -EFAULT; if (copy_from_user(&carrier, argp, sizeof(carrier))) goto unlock; ret = tun_net_change_carrier(tun->dev, (bool)carrier); break; case TUNGETDEVNETNS: ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto unlock; ret = open_related_ns(&net->ns, get_net_ns); break; default: ret = -EINVAL; break; } if (do_notify) netdev_state_change(tun->dev); unlock: rtnl_unlock(); if (tun) tun_put(tun); return ret; } static long tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return __tun_chr_ioctl(file, cmd, arg, sizeof (struct ifreq)); } #ifdef CONFIG_COMPAT static long tun_chr_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { switch (cmd) { case TUNSETIFF: case TUNGETIFF: case TUNSETTXFILTER: case TUNGETSNDBUF: case TUNSETSNDBUF: case SIOCGIFHWADDR: case SIOCSIFHWADDR: arg = (unsigned long)compat_ptr(arg); break; default: arg = (compat_ulong_t)arg; break; } /* * compat_ifreq is shorter than ifreq, so we must not access beyond * the end of that structure. All fields that are used in this * driver are compatible though, we don't need to convert the * contents. */ return __tun_chr_ioctl(file, cmd, arg, sizeof(struct compat_ifreq)); } #endif /* CONFIG_COMPAT */ static int tun_chr_fasync(int fd, struct file *file, int on) { struct tun_file *tfile = file->private_data; int ret; if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0) goto out; if (on) { __f_setown(file, task_pid(current), PIDTYPE_TGID, 0); tfile->flags |= TUN_FASYNC; } else tfile->flags &= ~TUN_FASYNC; ret = 0; out: return ret; } static int tun_chr_open(struct inode *inode, struct file * file) { struct net *net = current->nsproxy->net_ns; struct tun_file *tfile; tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL, &tun_proto, 0); if (!tfile) return -ENOMEM; if (ptr_ring_init(&tfile->tx_ring, 0, GFP_KERNEL)) { sk_free(&tfile->sk); return -ENOMEM; } mutex_init(&tfile->napi_mutex); RCU_INIT_POINTER(tfile->tun, NULL); tfile->flags = 0; tfile->ifindex = 0; init_waitqueue_head(&tfile->socket.wq.wait); tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; sock_init_data(&tfile->socket, &tfile->sk); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; file->private_data = tfile; INIT_LIST_HEAD(&tfile->next); sock_set_flag(&tfile->sk, SOCK_ZEROCOPY); return 0; } static int tun_chr_close(struct inode *inode, struct file *file) { struct tun_file *tfile = file->private_data; tun_detach(tfile, true); return 0; } #ifdef CONFIG_PROC_FS static void tun_chr_show_fdinfo(struct seq_file *m, struct file *file) { struct tun_file *tfile = file->private_data; struct tun_struct *tun; struct ifreq ifr; memset(&ifr, 0, sizeof(ifr)); rtnl_lock(); tun = tun_get(tfile); if (tun) tun_get_iff(tun, &ifr); rtnl_unlock(); if (tun) tun_put(tun); seq_printf(m, "iff:\t%s\n", ifr.ifr_name); } #endif static const struct file_operations tun_fops = { .owner = THIS_MODULE, .llseek = no_llseek, .read_iter = tun_chr_read_iter, .write_iter = tun_chr_write_iter, .poll = tun_chr_poll, .unlocked_ioctl = tun_chr_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = tun_chr_compat_ioctl, #endif .open = tun_chr_open, .release = tun_chr_close, .fasync = tun_chr_fasync, #ifdef CONFIG_PROC_FS .show_fdinfo = tun_chr_show_fdinfo, #endif }; static struct miscdevice tun_miscdev = { .minor = TUN_MINOR, .name = "tun", .nodename = "net/tun", .fops = &tun_fops, }; /* ethtool interface */ static void tun_default_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { ethtool_link_ksettings_zero_link_mode(cmd, supported); ethtool_link_ksettings_zero_link_mode(cmd, advertising); cmd->base.speed = SPEED_10; cmd->base.duplex = DUPLEX_FULL; cmd->base.port = PORT_TP; cmd->base.phy_address = 0; cmd->base.autoneg = AUTONEG_DISABLE; } static int tun_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct tun_struct *tun = netdev_priv(dev); memcpy(cmd, &tun->link_ksettings, sizeof(*cmd)); return 0; } static int tun_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct tun_struct *tun = netdev_priv(dev); memcpy(&tun->link_ksettings, cmd, sizeof(*cmd)); return 0; } static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct tun_struct *tun = netdev_priv(dev); strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); strlcpy(info->version, DRV_VERSION, sizeof(info->version)); switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: strlcpy(info->bus_info, "tun", sizeof(info->bus_info)); break; case IFF_TAP: strlcpy(info->bus_info, "tap", sizeof(info->bus_info)); break; } } static u32 tun_get_msglevel(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); return tun->msg_enable; } static void tun_set_msglevel(struct net_device *dev, u32 value) { struct tun_struct *tun = netdev_priv(dev); tun->msg_enable = value; } static int tun_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) { struct tun_struct *tun = netdev_priv(dev); ec->rx_max_coalesced_frames = tun->rx_batched; return 0; } static int tun_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) { struct tun_struct *tun = netdev_priv(dev); if (ec->rx_max_coalesced_frames > NAPI_POLL_WEIGHT) tun->rx_batched = NAPI_POLL_WEIGHT; else tun->rx_batched = ec->rx_max_coalesced_frames; return 0; } static const struct ethtool_ops tun_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_RX_MAX_FRAMES, .get_drvinfo = tun_get_drvinfo, .get_msglevel = tun_get_msglevel, .set_msglevel = tun_set_msglevel, .get_link = ethtool_op_get_link, .get_ts_info = ethtool_op_get_ts_info, .get_coalesce = tun_get_coalesce, .set_coalesce = tun_set_coalesce, .get_link_ksettings = tun_get_link_ksettings, .set_link_ksettings = tun_set_link_ksettings, }; static int tun_queue_resize(struct tun_struct *tun) { struct net_device *dev = tun->dev; struct tun_file *tfile; struct ptr_ring **rings; int n = tun->numqueues + tun->numdisabled; int ret, i; rings = kmalloc_array(n, sizeof(*rings), GFP_KERNEL); if (!rings) return -ENOMEM; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); rings[i] = &tfile->tx_ring; } list_for_each_entry(tfile, &tun->disabled, next) rings[i++] = &tfile->tx_ring; ret = ptr_ring_resize_multiple(rings, n, dev->tx_queue_len, GFP_KERNEL, tun_ptr_free); kfree(rings); return ret; } static int tun_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tun_struct *tun = netdev_priv(dev); int i; if (dev->rtnl_link_ops != &tun_link_ops) return NOTIFY_DONE; switch (event) { case NETDEV_CHANGE_TX_QUEUE_LEN: if (tun_queue_resize(tun)) return NOTIFY_BAD; break; case NETDEV_UP: for (i = 0; i < tun->numqueues; i++) { struct tun_file *tfile; tfile = rtnl_dereference(tun->tfiles[i]); tfile->socket.sk->sk_write_space(tfile->socket.sk); } break; default: break; } return NOTIFY_DONE; } static struct notifier_block tun_notifier_block __read_mostly = { .notifier_call = tun_device_event, }; static int __init tun_init(void) { int ret = 0; pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION); ret = rtnl_link_register(&tun_link_ops); if (ret) { pr_err("Can't register link_ops\n"); goto err_linkops; } ret = misc_register(&tun_miscdev); if (ret) { pr_err("Can't register misc device %d\n", TUN_MINOR); goto err_misc; } ret = register_netdevice_notifier(&tun_notifier_block); if (ret) { pr_err("Can't register netdevice notifier\n"); goto err_notifier; } return 0; err_notifier: misc_deregister(&tun_miscdev); err_misc: rtnl_link_unregister(&tun_link_ops); err_linkops: return ret; } static void tun_cleanup(void) { misc_deregister(&tun_miscdev); rtnl_link_unregister(&tun_link_ops); unregister_netdevice_notifier(&tun_notifier_block); } /* Get an underlying socket object from tun file. Returns error unless file is * attached to a device. The returned object works like a packet socket, it * can be used for sock_sendmsg/sock_recvmsg. The caller is responsible for * holding a reference to the file for as long as the socket is in use. */ struct socket *tun_get_socket(struct file *file) { struct tun_file *tfile; if (file->f_op != &tun_fops) return ERR_PTR(-EINVAL); tfile = file->private_data; if (!tfile) return ERR_PTR(-EBADFD); return &tfile->socket; } EXPORT_SYMBOL_GPL(tun_get_socket); struct ptr_ring *tun_get_tx_ring(struct file *file) { struct tun_file *tfile; if (file->f_op != &tun_fops) return ERR_PTR(-EINVAL); tfile = file->private_data; if (!tfile) return ERR_PTR(-EBADFD); return &tfile->tx_ring; } EXPORT_SYMBOL_GPL(tun_get_tx_ring); module_init(tun_init); module_exit(tun_cleanup); MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR(DRV_COPYRIGHT); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(TUN_MINOR); MODULE_ALIAS("devname:net/tun");
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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* delayacct.h - per-task delay accounting * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 */ #ifndef _LINUX_DELAYACCT_H #define _LINUX_DELAYACCT_H #include <uapi/linux/taskstats.h> /* * Per-task flags relevant to delay accounting * maintained privately to avoid exhausting similar flags in sched.h:PF_* * Used to set current->delays->flags */ #define DELAYACCT_PF_SWAPIN 0x00000001 /* I am doing a swapin */ #define DELAYACCT_PF_BLKIO 0x00000002 /* I am waiting on IO */ #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { raw_spinlock_t lock; unsigned int flags; /* Private per-task flags */ /* For each stat XXX, add following, aligned appropriately * * struct timespec XXX_start, XXX_end; * u64 XXX_delay; * u32 XXX_count; * * Atomicity of updates to XXX_delay, XXX_count protected by * single lock above (split into XXX_lock if contention is an issue). */ /* * XXX_count is incremented on every XXX operation, the delay * associated with the operation is added to XXX_delay. * XXX_delay contains the accumulated delay time in nanoseconds. */ u64 blkio_start; /* Shared by blkio, swapin */ u64 blkio_delay; /* wait for sync block io completion */ u64 swapin_delay; /* wait for swapin block io completion */ u32 blkio_count; /* total count of the number of sync block */ /* io operations performed */ u32 swapin_count; /* total count of the number of swapin block */ /* io operations performed */ u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ u64 thrashing_start; u64 thrashing_delay; /* wait for thrashing page */ u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ }; #endif #include <linux/sched.h> #include <linux/slab.h> #ifdef CONFIG_TASK_DELAY_ACCT extern int delayacct_on; /* Delay accounting turned on/off */ extern struct kmem_cache *delayacct_cache; extern void delayacct_init(void); extern void __delayacct_tsk_init(struct task_struct *); extern void __delayacct_tsk_exit(struct task_struct *); extern void __delayacct_blkio_start(void); extern void __delayacct_blkio_end(struct task_struct *); extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); extern void __delayacct_thrashing_start(void); extern void __delayacct_thrashing_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { if (p->delays) return (p->delays->flags & DELAYACCT_PF_BLKIO); else return 0; } static inline void delayacct_set_flag(int flag) { if (current->delays) current->delays->flags |= flag; } static inline void delayacct_clear_flag(int flag) { if (current->delays) current->delays->flags &= ~flag; } static inline void delayacct_tsk_init(struct task_struct *tsk) { /* reinitialize in case parent's non-null pointer was dup'ed*/ tsk->delays = NULL; if (delayacct_on) __delayacct_tsk_init(tsk); } /* Free tsk->delays. Called from bad fork and __put_task_struct * where there's no risk of tsk->delays being accessed elsewhere */ static inline void delayacct_tsk_free(struct task_struct *tsk) { if (tsk->delays) kmem_cache_free(delayacct_cache, tsk->delays); tsk->delays = NULL; } static inline void delayacct_blkio_start(void) { delayacct_set_flag(DELAYACCT_PF_BLKIO); if (current->delays) __delayacct_blkio_start(); } static inline void delayacct_blkio_end(struct task_struct *p) { if (p->delays) __delayacct_blkio_end(p); delayacct_clear_flag(DELAYACCT_PF_BLKIO); } static inline int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) { if (!delayacct_on || !tsk->delays) return 0; return __delayacct_add_tsk(d, tsk); } static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) { if (tsk->delays) return __delayacct_blkio_ticks(tsk); return 0; } static inline void delayacct_freepages_start(void) { if (current->delays) __delayacct_freepages_start(); } static inline void delayacct_freepages_end(void) { if (current->delays) __delayacct_freepages_end(); } static inline void delayacct_thrashing_start(void) { if (current->delays) __delayacct_thrashing_start(); } static inline void delayacct_thrashing_end(void) { if (current->delays) __delayacct_thrashing_end(); } #else static inline void delayacct_set_flag(int flag) {} static inline void delayacct_clear_flag(int flag) {} static inline void delayacct_init(void) {} static inline void delayacct_tsk_init(struct task_struct *tsk) {} static inline void delayacct_tsk_free(struct task_struct *tsk) {} static inline void delayacct_blkio_start(void) {} static inline void delayacct_blkio_end(struct task_struct *p) {} static inline int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) { return 0; } static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) { return 0; } static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { return 0; } static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} static inline void delayacct_thrashing_start(void) {} static inline void delayacct_thrashing_end(void) {} #endif /* CONFIG_TASK_DELAY_ACCT */ #endif
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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM libata #if !defined(_TRACE_LIBATA_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_LIBATA_H #include <linux/ata.h> #include <linux/libata.h> #include <linux/tracepoint.h> #include <linux/trace_seq.h> #define ata_opcode_name(opcode) { opcode, #opcode } #define show_opcode_name(val) \ __print_symbolic(val, \ ata_opcode_name(ATA_CMD_DEV_RESET), \ ata_opcode_name(ATA_CMD_CHK_POWER), \ ata_opcode_name(ATA_CMD_STANDBY), \ ata_opcode_name(ATA_CMD_IDLE), \ ata_opcode_name(ATA_CMD_EDD), \ ata_opcode_name(ATA_CMD_DOWNLOAD_MICRO), \ ata_opcode_name(ATA_CMD_DOWNLOAD_MICRO_DMA), \ ata_opcode_name(ATA_CMD_NOP), \ ata_opcode_name(ATA_CMD_FLUSH), \ ata_opcode_name(ATA_CMD_FLUSH_EXT), \ ata_opcode_name(ATA_CMD_ID_ATA), \ ata_opcode_name(ATA_CMD_ID_ATAPI), \ ata_opcode_name(ATA_CMD_SERVICE), \ ata_opcode_name(ATA_CMD_READ), \ ata_opcode_name(ATA_CMD_READ_EXT), \ ata_opcode_name(ATA_CMD_READ_QUEUED), \ ata_opcode_name(ATA_CMD_READ_STREAM_EXT), \ ata_opcode_name(ATA_CMD_READ_STREAM_DMA_EXT), \ ata_opcode_name(ATA_CMD_WRITE), \ ata_opcode_name(ATA_CMD_WRITE_EXT), \ ata_opcode_name(ATA_CMD_WRITE_QUEUED), \ ata_opcode_name(ATA_CMD_WRITE_STREAM_EXT), \ ata_opcode_name(ATA_CMD_WRITE_STREAM_DMA_EXT), \ ata_opcode_name(ATA_CMD_WRITE_FUA_EXT), \ ata_opcode_name(ATA_CMD_WRITE_QUEUED_FUA_EXT), \ ata_opcode_name(ATA_CMD_FPDMA_READ), \ ata_opcode_name(ATA_CMD_FPDMA_WRITE), \ ata_opcode_name(ATA_CMD_NCQ_NON_DATA), \ ata_opcode_name(ATA_CMD_FPDMA_SEND), \ ata_opcode_name(ATA_CMD_FPDMA_RECV), \ ata_opcode_name(ATA_CMD_PIO_READ), \ ata_opcode_name(ATA_CMD_PIO_READ_EXT), \ ata_opcode_name(ATA_CMD_PIO_WRITE), \ ata_opcode_name(ATA_CMD_PIO_WRITE_EXT), \ ata_opcode_name(ATA_CMD_READ_MULTI), \ ata_opcode_name(ATA_CMD_READ_MULTI_EXT), \ ata_opcode_name(ATA_CMD_WRITE_MULTI), \ ata_opcode_name(ATA_CMD_WRITE_MULTI_EXT), \ ata_opcode_name(ATA_CMD_WRITE_MULTI_FUA_EXT), \ ata_opcode_name(ATA_CMD_SET_FEATURES), \ ata_opcode_name(ATA_CMD_SET_MULTI), \ ata_opcode_name(ATA_CMD_PACKET), \ ata_opcode_name(ATA_CMD_VERIFY), \ ata_opcode_name(ATA_CMD_VERIFY_EXT), \ ata_opcode_name(ATA_CMD_WRITE_UNCORR_EXT), \ ata_opcode_name(ATA_CMD_STANDBYNOW1), \ ata_opcode_name(ATA_CMD_IDLEIMMEDIATE), \ ata_opcode_name(ATA_CMD_SLEEP), \ ata_opcode_name(ATA_CMD_INIT_DEV_PARAMS), \ ata_opcode_name(ATA_CMD_READ_NATIVE_MAX), \ ata_opcode_name(ATA_CMD_READ_NATIVE_MAX_EXT), \ ata_opcode_name(ATA_CMD_SET_MAX), \ ata_opcode_name(ATA_CMD_SET_MAX_EXT), \ ata_opcode_name(ATA_CMD_READ_LOG_EXT), \ ata_opcode_name(ATA_CMD_WRITE_LOG_EXT), \ ata_opcode_name(ATA_CMD_READ_LOG_DMA_EXT), \ ata_opcode_name(ATA_CMD_WRITE_LOG_DMA_EXT), \ ata_opcode_name(ATA_CMD_TRUSTED_NONDATA), \ ata_opcode_name(ATA_CMD_TRUSTED_RCV), \ ata_opcode_name(ATA_CMD_TRUSTED_RCV_DMA), \ ata_opcode_name(ATA_CMD_TRUSTED_SND), \ ata_opcode_name(ATA_CMD_TRUSTED_SND_DMA), \ ata_opcode_name(ATA_CMD_PMP_READ), \ ata_opcode_name(ATA_CMD_PMP_READ_DMA), \ ata_opcode_name(ATA_CMD_PMP_WRITE), \ ata_opcode_name(ATA_CMD_PMP_WRITE_DMA), \ ata_opcode_name(ATA_CMD_CONF_OVERLAY), \ ata_opcode_name(ATA_CMD_SEC_SET_PASS), \ ata_opcode_name(ATA_CMD_SEC_UNLOCK), \ ata_opcode_name(ATA_CMD_SEC_ERASE_PREP), \ ata_opcode_name(ATA_CMD_SEC_ERASE_UNIT), \ ata_opcode_name(ATA_CMD_SEC_FREEZE_LOCK), \ ata_opcode_name(ATA_CMD_SEC_DISABLE_PASS), \ ata_opcode_name(ATA_CMD_CONFIG_STREAM), \ ata_opcode_name(ATA_CMD_SMART), \ ata_opcode_name(ATA_CMD_MEDIA_LOCK), \ ata_opcode_name(ATA_CMD_MEDIA_UNLOCK), \ ata_opcode_name(ATA_CMD_DSM), \ ata_opcode_name(ATA_CMD_CHK_MED_CRD_TYP), \ ata_opcode_name(ATA_CMD_CFA_REQ_EXT_ERR), \ ata_opcode_name(ATA_CMD_CFA_WRITE_NE), \ ata_opcode_name(ATA_CMD_CFA_TRANS_SECT), \ ata_opcode_name(ATA_CMD_CFA_ERASE), \ ata_opcode_name(ATA_CMD_CFA_WRITE_MULT_NE), \ ata_opcode_name(ATA_CMD_REQ_SENSE_DATA), \ ata_opcode_name(ATA_CMD_SANITIZE_DEVICE), \ ata_opcode_name(ATA_CMD_ZAC_MGMT_IN), \ ata_opcode_name(ATA_CMD_ZAC_MGMT_OUT), \ ata_opcode_name(ATA_CMD_RESTORE), \ ata_opcode_name(ATA_CMD_READ_LONG), \ ata_opcode_name(ATA_CMD_READ_LONG_ONCE), \ ata_opcode_name(ATA_CMD_WRITE_LONG), \ ata_opcode_name(ATA_CMD_WRITE_LONG_ONCE)) #define ata_error_name(result) { result, #result } #define show_error_name(val) \ __print_symbolic(val, \ ata_error_name(ATA_ICRC), \ ata_error_name(ATA_UNC), \ ata_error_name(ATA_MC), \ ata_error_name(ATA_IDNF), \ ata_error_name(ATA_MCR), \ ata_error_name(ATA_ABORTED), \ ata_error_name(ATA_TRK0NF), \ ata_error_name(ATA_AMNF)) #define ata_protocol_name(proto) { proto, #proto } #define show_protocol_name(val) \ __print_symbolic(val, \ ata_protocol_name(ATA_PROT_UNKNOWN), \ ata_protocol_name(ATA_PROT_NODATA), \ ata_protocol_name(ATA_PROT_PIO), \ ata_protocol_name(ATA_PROT_DMA), \ ata_protocol_name(ATA_PROT_NCQ), \ ata_protocol_name(ATA_PROT_NCQ_NODATA), \ ata_protocol_name(ATAPI_PROT_NODATA), \ ata_protocol_name(ATAPI_PROT_PIO), \ ata_protocol_name(ATAPI_PROT_DMA)) const char *libata_trace_parse_status(struct trace_seq*, unsigned char); #define __parse_status(s) libata_trace_parse_status(p, s) const char *libata_trace_parse_eh_action(struct trace_seq *, unsigned int); #define __parse_eh_action(a) libata_trace_parse_eh_action(p, a) const char *libata_trace_parse_eh_err_mask(struct trace_seq *, unsigned int); #define __parse_eh_err_mask(m) libata_trace_parse_eh_err_mask(p, m) const char *libata_trace_parse_qc_flags(struct trace_seq *, unsigned int); #define __parse_qc_flags(f) libata_trace_parse_qc_flags(p, f) const char *libata_trace_parse_subcmd(struct trace_seq *, unsigned char, unsigned char, unsigned char); #define __parse_subcmd(c,f,h) libata_trace_parse_subcmd(p, c, f, h) TRACE_EVENT(ata_qc_issue, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, tag ) __field( unsigned char, cmd ) __field( unsigned char, dev ) __field( unsigned char, lbal ) __field( unsigned char, lbam ) __field( unsigned char, lbah ) __field( unsigned char, nsect ) __field( unsigned char, feature ) __field( unsigned char, hob_lbal ) __field( unsigned char, hob_lbam ) __field( unsigned char, hob_lbah ) __field( unsigned char, hob_nsect ) __field( unsigned char, hob_feature ) __field( unsigned char, ctl ) __field( unsigned char, proto ) __field( unsigned long, flags ) ), TP_fast_assign( __entry->ata_port = qc->ap->print_id; __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno; __entry->tag = qc->tag; __entry->proto = qc->tf.protocol; __entry->cmd = qc->tf.command; __entry->dev = qc->tf.device; __entry->lbal = qc->tf.lbal; __entry->lbam = qc->tf.lbam; __entry->lbah = qc->tf.lbah; __entry->hob_lbal = qc->tf.hob_lbal; __entry->hob_lbam = qc->tf.hob_lbam; __entry->hob_lbah = qc->tf.hob_lbah; __entry->feature = qc->tf.feature; __entry->hob_feature = qc->tf.hob_feature; __entry->nsect = qc->tf.nsect; __entry->hob_nsect = qc->tf.hob_nsect; ), TP_printk("ata_port=%u ata_dev=%u tag=%d proto=%s cmd=%s%s " \ " tf=(%02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x)", __entry->ata_port, __entry->ata_dev, __entry->tag, show_protocol_name(__entry->proto), show_opcode_name(__entry->cmd), __parse_subcmd(__entry->cmd, __entry->feature, __entry->hob_nsect), __entry->cmd, __entry->feature, __entry->nsect, __entry->lbal, __entry->lbam, __entry->lbah, __entry->hob_feature, __entry->hob_nsect, __entry->hob_lbal, __entry->hob_lbam, __entry->hob_lbah, __entry->dev) ); DECLARE_EVENT_CLASS(ata_qc_complete_template, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, tag ) __field( unsigned char, status ) __field( unsigned char, dev ) __field( unsigned char, lbal ) __field( unsigned char, lbam ) __field( unsigned char, lbah ) __field( unsigned char, nsect ) __field( unsigned char, error ) __field( unsigned char, hob_lbal ) __field( unsigned char, hob_lbam ) __field( unsigned char, hob_lbah ) __field( unsigned char, hob_nsect ) __field( unsigned char, hob_feature ) __field( unsigned char, ctl ) __field( unsigned long, flags ) ), TP_fast_assign( __entry->ata_port = qc->ap->print_id; __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno; __entry->tag = qc->tag; __entry->status = qc->result_tf.command; __entry->dev = qc->result_tf.device; __entry->lbal = qc->result_tf.lbal; __entry->lbam = qc->result_tf.lbam; __entry->lbah = qc->result_tf.lbah; __entry->hob_lbal = qc->result_tf.hob_lbal; __entry->hob_lbam = qc->result_tf.hob_lbam; __entry->hob_lbah = qc->result_tf.hob_lbah; __entry->error = qc->result_tf.feature; __entry->hob_feature = qc->result_tf.hob_feature; __entry->nsect = qc->result_tf.nsect; __entry->hob_nsect = qc->result_tf.hob_nsect; ), TP_printk("ata_port=%u ata_dev=%u tag=%d flags=%s status=%s " \ " res=(%02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x)", __entry->ata_port, __entry->ata_dev, __entry->tag, __parse_qc_flags(__entry->flags), __parse_status(__entry->status), __entry->status, __entry->error, __entry->nsect, __entry->lbal, __entry->lbam, __entry->lbah, __entry->hob_feature, __entry->hob_nsect, __entry->hob_lbal, __entry->hob_lbam, __entry->hob_lbah, __entry->dev) ); DEFINE_EVENT(ata_qc_complete_template, ata_qc_complete_internal, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc)); DEFINE_EVENT(ata_qc_complete_template, ata_qc_complete_failed, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc)); DEFINE_EVENT(ata_qc_complete_template, ata_qc_complete_done, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc)); TRACE_EVENT(ata_eh_link_autopsy, TP_PROTO(struct ata_device *dev, unsigned int eh_action, unsigned int eh_err_mask), TP_ARGS(dev, eh_action, eh_err_mask), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, eh_action ) __field( unsigned int, eh_err_mask) ), TP_fast_assign( __entry->ata_port = dev->link->ap->print_id; __entry->ata_dev = dev->link->pmp + dev->devno; __entry->eh_action = eh_action; __entry->eh_err_mask = eh_err_mask; ), TP_printk("ata_port=%u ata_dev=%u eh_action=%s err_mask=%s", __entry->ata_port, __entry->ata_dev, __parse_eh_action(__entry->eh_action), __parse_eh_err_mask(__entry->eh_err_mask)) ); TRACE_EVENT(ata_eh_link_autopsy_qc, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, tag ) __field( unsigned int, qc_flags ) __field( unsigned int, eh_err_mask) ), TP_fast_assign( __entry->ata_port = qc->ap->print_id; __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno; __entry->tag = qc->tag; __entry->qc_flags = qc->flags; __entry->eh_err_mask = qc->err_mask; ), TP_printk("ata_port=%u ata_dev=%u tag=%d flags=%s err_mask=%s", __entry->ata_port, __entry->ata_dev, __entry->tag, __parse_qc_flags(__entry->qc_flags), __parse_eh_err_mask(__entry->eh_err_mask)) ); #endif /* _TRACE_LIBATA_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the UDP module. * * Version: @(#)udp.h 1.0.2 05/07/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Fixes: * Alan Cox : Turned on udp checksums. I don't want to * chase 'memory corruption' bugs that aren't! */ #ifndef _UDP_H #define _UDP_H #include <linux/list.h> #include <linux/bug.h> #include <net/inet_sock.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> #include <linux/ipv6.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/indirect_call_wrapper.h> /** * struct udp_skb_cb - UDP(-Lite) private variables * * @header: private variables used by IPv4/IPv6 * @cscov: checksum coverage length (UDP-Lite only) * @partial_cov: if set indicates partial csum coverage */ struct udp_skb_cb { union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; __u16 cscov; __u8 partial_cov; }; #define UDP_SKB_CB(__skb) ((struct udp_skb_cb *)((__skb)->cb)) /** * struct udp_hslot - UDP hash slot * * @head: head of list of sockets * @count: number of sockets in 'head' list * @lock: spinlock protecting changes to head/count */ struct udp_hslot { struct hlist_head head; int count; spinlock_t lock; } __attribute__((aligned(2 * sizeof(long)))); /** * struct udp_table - UDP table * * @hash: hash table, sockets are hashed on (local port) * @hash2: hash table, sockets are hashed on (local port, local address) * @mask: number of slots in hash tables, minus 1 * @log: log2(number of slots in hash table) */ struct udp_table { struct udp_hslot *hash; struct udp_hslot *hash2; unsigned int mask; unsigned int log; }; extern struct udp_table udp_table; void udp_table_init(struct udp_table *, const char *); static inline struct udp_hslot *udp_hashslot(struct udp_table *table, struct net *net, unsigned int num) { return &table->hash[udp_hashfn(net, num, table->mask)]; } /* * For secondary hash, net_hash_mix() is performed before calling * udp_hashslot2(), this explains difference with udp_hashslot() */ static inline struct udp_hslot *udp_hashslot2(struct udp_table *table, unsigned int hash) { return &table->hash2[hash & table->mask]; } extern struct proto udp_prot; extern atomic_long_t udp_memory_allocated; /* sysctl variables for udp */ extern long sysctl_udp_mem[3]; extern int sysctl_udp_rmem_min; extern int sysctl_udp_wmem_min; struct sk_buff; /* * Generic checksumming routines for UDP(-Lite) v4 and v6 */ static inline __sum16 __udp_lib_checksum_complete(struct sk_buff *skb) { return (UDP_SKB_CB(skb)->cscov == skb->len ? __skb_checksum_complete(skb) : __skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov)); } static inline int udp_lib_checksum_complete(struct sk_buff *skb) { return !skb_csum_unnecessary(skb) && __udp_lib_checksum_complete(skb); } /** * udp_csum_outgoing - compute UDPv4/v6 checksum over fragments * @sk: socket we are writing to * @skb: sk_buff containing the filled-in UDP header * (checksum field must be zeroed out) */ static inline __wsum udp_csum_outgoing(struct sock *sk, struct sk_buff *skb) { __wsum csum = csum_partial(skb_transport_header(skb), sizeof(struct udphdr), 0); skb_queue_walk(&sk->sk_write_queue, skb) { csum = csum_add(csum, skb->csum); } return csum; } static inline __wsum udp_csum(struct sk_buff *skb) { __wsum csum = csum_partial(skb_transport_header(skb), sizeof(struct udphdr), skb->csum); for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next) { csum = csum_add(csum, skb->csum); } return csum; } static inline __sum16 udp_v4_check(int len, __be32 saddr, __be32 daddr, __wsum base) { return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_UDP, base); } void udp_set_csum(bool nocheck, struct sk_buff *skb, __be32 saddr, __be32 daddr, int len); static inline void udp_csum_pull_header(struct sk_buff *skb) { if (!skb->csum_valid && skb->ip_summed == CHECKSUM_NONE) skb->csum = csum_partial(skb->data, sizeof(struct udphdr), skb->csum); skb_pull_rcsum(skb, sizeof(struct udphdr)); UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr); } typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport, __be16 dport); INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, struct udphdr *uh, struct sock *sk); int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6); static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) { struct udphdr *uh; unsigned int hlen, off; off = skb_gro_offset(skb); hlen = off + sizeof(*uh); uh = skb_gro_header_fast(skb, off); if (skb_gro_header_hard(skb, hlen)) uh = skb_gro_header_slow(skb, hlen, off); return uh; } /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ static inline int udp_lib_hash(struct sock *sk) { BUG(); return 0; } void udp_lib_unhash(struct sock *sk); void udp_lib_rehash(struct sock *sk, u16 new_hash); static inline void udp_lib_close(struct sock *sk, long timeout) { sk_common_release(sk); } int udp_lib_get_port(struct sock *sk, unsigned short snum, unsigned int hash2_nulladdr); u32 udp_flow_hashrnd(void); static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, int min, int max, bool use_eth) { u32 hash; if (min >= max) { /* Use default range */ inet_get_local_port_range(net, &min, &max); } hash = skb_get_hash(skb); if (unlikely(!hash)) { if (use_eth) { /* Can't find a normal hash, caller has indicated an * Ethernet packet so use that to compute a hash. */ hash = jhash(skb->data, 2 * ETH_ALEN, (__force u32) skb->protocol); } else { /* Can't derive any sort of hash for the packet, set * to some consistent random value. */ hash = udp_flow_hashrnd(); } } /* Since this is being sent on the wire obfuscate hash a bit * to minimize possbility that any useful information to an * attacker is leaked. Only upper 16 bits are relevant in the * computation for 16 bit port value. */ hash ^= hash << 16; return htons((((u64) hash * (max - min)) >> 32) + min); } static inline int udp_rqueue_get(struct sock *sk) { return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); } static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) return inet_bound_dev_eq(!!net->ipv4.sysctl_udp_l3mdev_accept, bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); #endif } /* net/ipv4/udp.c */ void udp_destruct_sock(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int noblock, int *off, int *err); static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, int noblock, int *err) { int off = 0; return __skb_recv_udp(sk, flags, noblock, &off, err); } int udp_v4_early_demux(struct sk_buff *skb); bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, const struct sock *)); int udp_err(struct sk_buff *, u32); int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udp_push_pending_frames(struct sock *sk); void udp_flush_pending_frames(struct sock *sk); int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size); void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst); int udp_rcv(struct sk_buff *skb); int udp_ioctl(struct sock *sk, int cmd, unsigned long arg); int udp_init_sock(struct sock *sk); int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int __udp_disconnect(struct sock *sk, int flags); int udp_disconnect(struct sock *sk, int flags); __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait); struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, bool is_ipv6); int udp_lib_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int udp_lib_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)); struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp4_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport); struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif); struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport); /* UDP uses skb->dev_scratch to cache as much information as possible and avoid * possibly multiple cache miss on dequeue() */ struct udp_dev_scratch { /* skb->truesize and the stateless bit are embedded in a single field; * do not use a bitfield since the compiler emits better/smaller code * this way */ u32 _tsize_state; #if BITS_PER_LONG == 64 /* len and the bit needed to compute skb_csum_unnecessary * will be on cold cache lines at recvmsg time. * skb->len can be stored on 16 bits since the udp header has been * already validated and pulled. */ u16 len; bool is_linear; bool csum_unnecessary; #endif }; static inline struct udp_dev_scratch *udp_skb_scratch(struct sk_buff *skb) { return (struct udp_dev_scratch *)&skb->dev_scratch; } #if BITS_PER_LONG == 64 static inline unsigned int udp_skb_len(struct sk_buff *skb) { return udp_skb_scratch(skb)->len; } static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb) { return udp_skb_scratch(skb)->csum_unnecessary; } static inline bool udp_skb_is_linear(struct sk_buff *skb) { return udp_skb_scratch(skb)->is_linear; } #else static inline unsigned int udp_skb_len(struct sk_buff *skb) { return skb->len; } static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb) { return skb_csum_unnecessary(skb); } static inline bool udp_skb_is_linear(struct sk_buff *skb) { return !skb_is_nonlinear(skb); } #endif static inline int copy_linear_skb(struct sk_buff *skb, int len, int off, struct iov_iter *to) { int n; n = copy_to_iter(skb->data + off, len, to); if (n == len) return 0; iov_iter_revert(to, n); return -EFAULT; } /* * SNMP statistics for UDP and UDP-Lite */ #define UDP_INC_STATS(net, field, is_udplite) do { \ if (is_udplite) SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ else SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) #define __UDP_INC_STATS(net, field, is_udplite) do { \ if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ else __SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) #define __UDP6_INC_STATS(net, field, is_udplite) do { \ if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_stats_in6, field);\ else __SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) #define UDP6_INC_STATS(net, field, __lite) do { \ if (__lite) SNMP_INC_STATS((net)->mib.udplite_stats_in6, field); \ else SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) #if IS_ENABLED(CONFIG_IPV6) #define __UDPX_MIB(sk, ipv4) \ ({ \ ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ sock_net(sk)->mib.udp_statistics) : \ (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 : \ sock_net(sk)->mib.udp_stats_in6); \ }) #else #define __UDPX_MIB(sk, ipv4) \ ({ \ IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ sock_net(sk)->mib.udp_statistics; \ }) #endif #define __UDPX_INC_STATS(sk, field) \ __SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field) #ifdef CONFIG_PROC_FS struct udp_seq_afinfo { sa_family_t family; struct udp_table *udp_table; }; struct udp_iter_state { struct seq_net_private p; int bucket; struct udp_seq_afinfo *bpf_seq_afinfo; }; void *udp_seq_start(struct seq_file *seq, loff_t *pos); void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos); void udp_seq_stop(struct seq_file *seq, void *v); extern const struct seq_operations udp_seq_ops; extern const struct seq_operations udp6_seq_ops; int udp4_proc_init(void); void udp4_proc_exit(void); #endif /* CONFIG_PROC_FS */ int udpv4_offload_init(void); void udp_init(void); DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); void udp_encap_enable(void); #if IS_ENABLED(CONFIG_IPV6) DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void); #endif static inline struct sk_buff *udp_rcv_segment(struct sock *sk, struct sk_buff *skb, bool ipv4) { netdev_features_t features = NETIF_F_SG; struct sk_buff *segs; /* Avoid csum recalculation by skb_segment unless userspace explicitly * asks for the final checksum values */ if (!inet_get_convert_csum(sk)) features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; /* UDP segmentation expects packets of type CHECKSUM_PARTIAL or * CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial * packets in udp_gro_complete_segment. As does UDP GSO, verified by * udp_send_skb. But when those packets are looped in dev_loopback_xmit * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY. * Reset in this specific case, where PARTIAL is both correct and * required. */ if (skb->pkt_type == PACKET_LOOPBACK) skb->ip_summed = CHECKSUM_PARTIAL; /* the GSO CB lays after the UDP one, no need to save and restore any * CB fragment */ segs = __skb_gso_segment(skb, features, false); if (IS_ERR_OR_NULL(segs)) { int segs_nr = skb_shinfo(skb)->gso_segs; atomic_add(segs_nr, &sk->sk_drops); SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr); kfree_skb(skb); return NULL; } consume_skb(skb); return segs; } #ifdef CONFIG_BPF_STREAM_PARSER struct sk_psock; struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); #endif /* BPF_STREAM_PARSER */ #endif /* _UDP_H */
1 1 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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_PREEMPT_H #define __ASM_PREEMPT_H #include <asm/rmwcc.h> #include <asm/percpu.h> #include <linux/thread_info.h> DECLARE_PER_CPU(int, __preempt_count); /* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 /* * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such * that a decrement hitting 0 means we can and should reschedule. */ #define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) /* * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users * that think a non-zero value indicates we cannot preempt. */ static __always_inline int preempt_count(void) { return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED; } static __always_inline void preempt_count_set(int pc) { int old, new; do { old = raw_cpu_read_4(__preempt_count); new = (old & PREEMPT_NEED_RESCHED) | (pc & ~PREEMPT_NEED_RESCHED); } while (raw_cpu_cmpxchg_4(__preempt_count, old, new) != old); } /* * must be macros to avoid header recursion hell */ #define init_task_preempt_count(p) do { } while (0) #define init_idle_preempt_count(p, cpu) do { \ per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \ } while (0) /* * We fold the NEED_RESCHED bit into the preempt count such that * preempt_enable() can decrement and test for needing to reschedule with a * single instruction. * * We invert the actual bit, so that when the decrement hits 0 we know we both * need to resched (the bit is cleared) and can resched (no preempt count). */ static __always_inline void set_preempt_need_resched(void) { raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED); } static __always_inline void clear_preempt_need_resched(void) { raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED); } static __always_inline bool test_preempt_need_resched(void) { return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED); } /* * The various preempt_count add/sub methods */ static __always_inline void __preempt_count_add(int val) { raw_cpu_add_4(__preempt_count, val); } static __always_inline void __preempt_count_sub(int val) { raw_cpu_add_4(__preempt_count, -val); } /* * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule * a decrement which hits zero means we have no preempt_count and should * reschedule. */ static __always_inline bool __preempt_count_dec_and_test(void) { return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var])); } /* * Returns true when we need to resched and can (barring IRQ state). */ static __always_inline bool should_resched(int preempt_offset) { return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); } #ifdef CONFIG_PREEMPTION extern asmlinkage void preempt_schedule_thunk(void); # define __preempt_schedule() \ asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule(void); extern asmlinkage void preempt_schedule_notrace_thunk(void); # define __preempt_schedule_notrace() \ asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule_notrace(void); #endif #endif /* __ASM_PREEMPT_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_DAX_H #define _LINUX_DAX_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/radix-tree.h> /* Flag for synchronous flush */ #define DAXDEV_F_SYNC (1UL << 0) typedef unsigned long dax_entry_t; struct iomap_ops; struct iomap; struct dax_device; struct dax_operations { /* * direct_access: translate a device-relative * logical-page-offset into an absolute physical pfn. Return the * number of pages available for DAX at that pfn. */ long (*direct_access)(struct dax_device *, pgoff_t, long, void **, pfn_t *); /* * Validate whether this device is usable as an fsdax backing * device. */ bool (*dax_supported)(struct dax_device *, struct block_device *, int, sector_t, sector_t); /* copy_from_iter: required operation for fs-dax direct-i/o */ size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, struct iov_iter *); /* copy_to_iter: required operation for fs-dax direct-i/o */ size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t, struct iov_iter *); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); }; extern struct attribute_group dax_attribute_group; #if IS_ENABLED(CONFIG_DAX) struct dax_device *dax_get_by_host(const char *host); struct dax_device *alloc_dax(void *private, const char *host, const struct dax_operations *ops, unsigned long flags); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); bool __dax_synchronous(struct dax_device *dax_dev); static inline bool dax_synchronous(struct dax_device *dax_dev) { return __dax_synchronous(dax_dev); } void __set_dax_synchronous(struct dax_device *dax_dev); static inline void set_dax_synchronous(struct dax_device *dax_dev) { __set_dax_synchronous(dax_dev); } bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t len); /* * Check if given mapping is supported by the file / underlying device. */ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { if (!(vma->vm_flags & VM_SYNC)) return true; if (!IS_DAX(file_inode(vma->vm_file))) return false; return dax_synchronous(dax_dev); } #else static inline struct dax_device *dax_get_by_host(const char *host) { return NULL; } static inline struct dax_device *alloc_dax(void *private, const char *host, const struct dax_operations *ops, unsigned long flags) { /* * Callers should check IS_ENABLED(CONFIG_DAX) to know if this * NULL is an error or expected. */ return NULL; } static inline void put_dax(struct dax_device *dax_dev) { } static inline void kill_dax(struct dax_device *dax_dev) { } static inline void dax_write_cache(struct dax_device *dax_dev, bool wc) { } static inline bool dax_write_cache_enabled(struct dax_device *dax_dev) { return false; } static inline bool dax_synchronous(struct dax_device *dax_dev) { return true; } static inline void set_dax_synchronous(struct dax_device *dax_dev) { } static inline bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t len) { return false; } static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { return !(vma->vm_flags & VM_SYNC); } #endif struct writeback_control; int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) bool __bdev_dax_supported(struct block_device *bdev, int blocksize); static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) { return __bdev_dax_supported(bdev, blocksize); } bool __generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors); static inline bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors) { return __generic_fsdax_supported(dax_dev, bdev, blocksize, start, sectors); } static inline void fs_put_dax(struct dax_device *dax_dev) { put_dax(dax_dev); } struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); #else static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) { return false; } static inline bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors) { return false; } static inline void fs_put_dax(struct dax_device *dax_dev) { } static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) { return NULL; } static inline struct page *dax_layout_busy_page(struct address_space *mapping) { return NULL; } static inline struct page *dax_layout_busy_page_range(struct address_space *mapping, pgoff_t start, pgoff_t nr_pages) { return NULL; } static inline int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc) { return -EOPNOTSUPP; } static inline dax_entry_t dax_lock_page(struct page *page) { if (IS_DAX(page->mapping->host)) return ~0UL; return 0; } static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) { } #endif #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); #else static inline int dax_read_lock(void) { return 0; } static inline void dax_read_unlock(int id) { } #endif /* CONFIG_DAX */ bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, pfn_t *pfnp, int *errp, const struct iomap_ops *ops); vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, enum page_entry_size pe_size, pfn_t pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } #ifdef CONFIG_DEV_DAX_HMEM_DEVICES void hmem_register_device(int target_nid, struct resource *r); #else static inline void hmem_register_device(int target_nid, struct resource *r) { } #endif #endif
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NLS_H #define _LINUX_NLS_H #include <linux/init.h> /* Unicode has changed over the years. Unicode code points no longer * fit into 16 bits; as of Unicode 5 valid code points range from 0 * to 0x10ffff (17 planes, where each plane holds 65536 code points). * * The original decision to represent Unicode characters as 16-bit * wchar_t values is now outdated. But plane 0 still includes the * most commonly used characters, so we will retain it. The newer * 32-bit unicode_t type can be used when it is necessary to * represent the full Unicode character set. */ /* Plane-0 Unicode character */ typedef u16 wchar_t; #define MAX_WCHAR_T 0xffff /* Arbitrary Unicode character */ typedef u32 unicode_t; struct nls_table { const char *charset; const char *alias; int (*uni2char) (wchar_t uni, unsigned char *out, int boundlen); int (*char2uni) (const unsigned char *rawstring, int boundlen, wchar_t *uni); const unsigned char *charset2lower; const unsigned char *charset2upper; struct module *owner; struct nls_table *next; }; /* this value hold the maximum octet of charset */ #define NLS_MAX_CHARSET_SIZE 6 /* for UTF-8 */ /* Byte order for UTF-16 strings */ enum utf16_endian { UTF16_HOST_ENDIAN, UTF16_LITTLE_ENDIAN, UTF16_BIG_ENDIAN }; /* nls_base.c */ extern int __register_nls(struct nls_table *, struct module *); extern int unregister_nls(struct nls_table *); extern struct nls_table *load_nls(char *); extern void unload_nls(struct nls_table *); extern struct nls_table *load_nls_default(void); #define register_nls(nls) __register_nls((nls), THIS_MODULE) extern int utf8_to_utf32(const u8 *s, int len, unicode_t *pu); extern int utf32_to_utf8(unicode_t u, u8 *s, int maxlen); extern int utf8s_to_utf16s(const u8 *s, int len, enum utf16_endian endian, wchar_t *pwcs, int maxlen); extern int utf16s_to_utf8s(const wchar_t *pwcs, int len, enum utf16_endian endian, u8 *s, int maxlen); static inline unsigned char nls_tolower(struct nls_table *t, unsigned char c) { unsigned char nc = t->charset2lower[c]; return nc ? nc : c; } static inline unsigned char nls_toupper(struct nls_table *t, unsigned char c) { unsigned char nc = t->charset2upper[c]; return nc ? nc : c; } static inline int nls_strnicmp(struct nls_table *t, const unsigned char *s1, const unsigned char *s2, int len) { while (len--) { if (nls_tolower(t, *s1++) != nls_tolower(t, *s2++)) return 1; } return 0; } /* * nls_nullsize - return length of null character for codepage * @codepage - codepage for which to return length of NULL terminator * * Since we can't guarantee that the null terminator will be a particular * length, we have to check against the codepage. If there's a problem * determining it, assume a single-byte NULL terminator. */ static inline int nls_nullsize(const struct nls_table *codepage) { int charlen; char tmp[NLS_MAX_CHARSET_SIZE]; charlen = codepage->uni2char(0, tmp, NLS_MAX_CHARSET_SIZE); return charlen > 0 ? charlen : 1; } #define MODULE_ALIAS_NLS(name) MODULE_ALIAS("nls_" __stringify(name)) #endif /* _LINUX_NLS_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ /* * This file provides wrappers with sanitizer instrumentation for non-atomic * bit operations. * * To use this functionality, an arch's bitops.h file needs to define each of * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), * arch___set_bit(), etc.). */ #ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H #define _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H #include <linux/instrumented.h> /** * __set_bit - Set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * Unlike set_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static inline void __set_bit(long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___set_bit(nr, addr); } /** * __clear_bit - Clears a bit in memory * @nr: the bit to clear * @addr: the address to start counting from * * Unlike clear_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static inline void __clear_bit(long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___clear_bit(nr, addr); } /** * __change_bit - Toggle a bit in memory * @nr: the bit to change * @addr: the address to start counting from * * Unlike change_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static inline void __change_bit(long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___change_bit(nr, addr); } static inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr) { if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) { /* * We treat non-atomic read-write bitops a little more special. * Given the operations here only modify a single bit, assuming * non-atomicity of the writer is sufficient may be reasonable * for certain usage (and follows the permissible nature of the * assume-plain-writes-atomic rule): * 1. report read-modify-write races -> check read; * 2. do not report races with marked readers, but do report * races with unmarked readers -> check "atomic" write. */ kcsan_check_read(addr + BIT_WORD(nr), sizeof(long)); /* * Use generic write instrumentation, in case other sanitizers * or tools are enabled alongside KCSAN. */ instrument_write(addr + BIT_WORD(nr), sizeof(long)); } else { instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); } } /** * __test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_set_bit(nr, addr); } /** * __test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_clear_bit(nr, addr); } /** * __test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_change_bit(nr, addr); } /** * test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static inline bool test_bit(long nr, const volatile unsigned long *addr) { instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); return arch_test_bit(nr, addr); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __INCLUDE_LINUX_OOM_H #define __INCLUDE_LINUX_OOM_H #include <linux/sched/signal.h> #include <linux/types.h> #include <linux/nodemask.h> #include <uapi/linux/oom.h> #include <linux/sched/coredump.h> /* MMF_* */ #include <linux/mm.h> /* VM_FAULT* */ struct zonelist; struct notifier_block; struct mem_cgroup; struct task_struct; enum oom_constraint { CONSTRAINT_NONE, CONSTRAINT_CPUSET, CONSTRAINT_MEMORY_POLICY, CONSTRAINT_MEMCG, }; /* * Details of the page allocation that triggered the oom killer that are used to * determine what should be killed. */ struct oom_control { /* Used to determine cpuset */ struct zonelist *zonelist; /* Used to determine mempolicy */ nodemask_t *nodemask; /* Memory cgroup in which oom is invoked, or NULL for global oom */ struct mem_cgroup *memcg; /* Used to determine cpuset and node locality requirement */ const gfp_t gfp_mask; /* * order == -1 means the oom kill is required by sysrq, otherwise only * for display purposes. */ const int order; /* Used by oom implementation, do not set */ unsigned long totalpages; struct task_struct *chosen; long chosen_points; /* Used to print the constraint info. */ enum oom_constraint constraint; }; extern struct mutex oom_lock; extern struct mutex oom_adj_mutex; static inline void set_current_oom_origin(void) { current->signal->oom_flag_origin = true; } static inline void clear_current_oom_origin(void) { current->signal->oom_flag_origin = false; } static inline bool oom_task_origin(const struct task_struct *p) { return p->signal->oom_flag_origin; } static inline bool tsk_is_oom_victim(struct task_struct * tsk) { return tsk->signal->oom_mm; } /* * Use this helper if tsk->mm != mm and the victim mm needs a special * handling. This is guaranteed to stay true after once set. */ static inline bool mm_is_oom_victim(struct mm_struct *mm) { return test_bit(MMF_OOM_VICTIM, &mm->flags); } /* * Checks whether a page fault on the given mm is still reliable. * This is no longer true if the oom reaper started to reap the * address space which is reflected by MMF_UNSTABLE flag set in * the mm. At that moment any !shared mapping would lose the content * and could cause a memory corruption (zero pages instead of the * original content). * * User should call this before establishing a page table entry for * a !shared mapping and under the proper page table lock. * * Return 0 when the PF is safe VM_FAULT_SIGBUS otherwise. */ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm) { if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags))) return VM_FAULT_SIGBUS; return 0; } bool __oom_reap_task_mm(struct mm_struct *mm); long oom_badness(struct task_struct *p, unsigned long totalpages); extern bool out_of_memory(struct oom_control *oc); extern void exit_oom_victim(void); extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); extern bool oom_killer_disable(signed long timeout); extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); /* sysctls */ extern int sysctl_oom_dump_tasks; extern int sysctl_oom_kill_allocating_task; extern int sysctl_panic_on_oom; #endif /* _INCLUDE_LINUX_OOM_H */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 // SPDX-License-Identifier: GPL-2.0-or-later /* * * Robert Olsson <robert.olsson@its.uu.se> Uppsala Universitet * & Swedish University of Agricultural Sciences. * * Jens Laas <jens.laas@data.slu.se> Swedish University of * Agricultural Sciences. * * Hans Liss <hans.liss@its.uu.se> Uppsala Universitet * * This work is based on the LPC-trie which is originally described in: * * An experimental study of compression methods for dynamic tries * Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. * https://www.csc.kth.se/~snilsson/software/dyntrie2/ * * IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson * IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, June 1999 * * Code from fib_hash has been reused which includes the following header: * * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IPv4 FIB: lookup engine and maintenance routines. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Substantial contributions to this work comes from: * * David S. Miller, <davem@davemloft.net> * Stephen Hemminger <shemminger@osdl.org> * Paul E. McKenney <paulmck@us.ibm.com> * Patrick McHardy <kaber@trash.net> */ #include <linux/cache.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/vmalloc.h> #include <linux/notifier.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/fib_notifier.h> #include <trace/events/fib.h> #include "fib_lookup.h" static int call_fib_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa, struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, .tos = fa->fa_tos, .type = fa->fa_type, .tb_id = fa->tb_id, }; return call_fib4_notifier(nb, event_type, &info.info); } static int call_fib_entry_notifiers(struct net *net, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa, struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, .tos = fa->fa_tos, .type = fa->fa_type, .tb_id = fa->tb_id, }; return call_fib4_notifiers(net, event_type, &info.info); } #define MAX_STAT_DEPTH 32 #define KEYLENGTH (8*sizeof(t_key)) #define KEY_MAX ((t_key)~0) typedef unsigned int t_key; #define IS_TRIE(n) ((n)->pos >= KEYLENGTH) #define IS_TNODE(n) ((n)->bits) #define IS_LEAF(n) (!(n)->bits) struct key_vector { t_key key; unsigned char pos; /* 2log(KEYLENGTH) bits needed */ unsigned char bits; /* 2log(KEYLENGTH) bits needed */ unsigned char slen; union { /* This list pointer if valid if (pos | bits) == 0 (LEAF) */ struct hlist_head leaf; /* This array is valid if (pos | bits) > 0 (TNODE) */ struct key_vector __rcu *tnode[0]; }; }; struct tnode { struct rcu_head rcu; t_key empty_children; /* KEYLENGTH bits needed */ t_key full_children; /* KEYLENGTH bits needed */ struct key_vector __rcu *parent; struct key_vector kv[1]; #define tn_bits kv[0].bits }; #define TNODE_SIZE(n) offsetof(struct tnode, kv[0].tnode[n]) #define LEAF_SIZE TNODE_SIZE(1) #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats { unsigned int gets; unsigned int backtrack; unsigned int semantic_match_passed; unsigned int semantic_match_miss; unsigned int null_node_hit; unsigned int resize_node_skipped; }; #endif struct trie_stat { unsigned int totdepth; unsigned int maxdepth; unsigned int tnodes; unsigned int leaves; unsigned int nullpointers; unsigned int prefixes; unsigned int nodesizes[MAX_STAT_DEPTH]; }; struct trie { struct key_vector kv[1]; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats; #endif }; static struct key_vector *resize(struct trie *t, struct key_vector *tn); static unsigned int tnode_free_size; /* * synchronize_rcu after call_rcu for outstanding dirty memory; it should be * especially useful before resizing the root node with PREEMPT_NONE configs; * the value was obtained experimentally, aiming to avoid visible slowdown. */ unsigned int sysctl_fib_sync_mem = 512 * 1024; unsigned int sysctl_fib_sync_mem_min = 64 * 1024; unsigned int sysctl_fib_sync_mem_max = 64 * 1024 * 1024; static struct kmem_cache *fn_alias_kmem __ro_after_init; static struct kmem_cache *trie_leaf_kmem __ro_after_init; static inline struct tnode *tn_info(struct key_vector *kv) { return container_of(kv, struct tnode, kv[0]); } /* caller must hold RTNL */ #define node_parent(tn) rtnl_dereference(tn_info(tn)->parent) #define get_child(tn, i) rtnl_dereference((tn)->tnode[i]) /* caller must hold RCU read lock or RTNL */ #define node_parent_rcu(tn) rcu_dereference_rtnl(tn_info(tn)->parent) #define get_child_rcu(tn, i) rcu_dereference_rtnl((tn)->tnode[i]) /* wrapper for rcu_assign_pointer */ static inline void node_set_parent(struct key_vector *n, struct key_vector *tp) { if (n) rcu_assign_pointer(tn_info(n)->parent, tp); } #define NODE_INIT_PARENT(n, p) RCU_INIT_POINTER(tn_info(n)->parent, p) /* This provides us with the number of children in this node, in the case of a * leaf this will return 0 meaning none of the children are accessible. */ static inline unsigned long child_length(const struct key_vector *tn) { return (1ul << tn->bits) & ~(1ul); } #define get_cindex(key, kv) (((key) ^ (kv)->key) >> (kv)->pos) static inline unsigned long get_index(t_key key, struct key_vector *kv) { unsigned long index = key ^ kv->key; if ((BITS_PER_LONG <= KEYLENGTH) && (KEYLENGTH == kv->pos)) return 0; return index >> kv->pos; } /* To understand this stuff, an understanding of keys and all their bits is * necessary. Every node in the trie has a key associated with it, but not * all of the bits in that key are significant. * * Consider a node 'n' and its parent 'tp'. * * If n is a leaf, every bit in its key is significant. Its presence is * necessitated by path compression, since during a tree traversal (when * searching for a leaf - unless we are doing an insertion) we will completely * ignore all skipped bits we encounter. Thus we need to verify, at the end of * a potentially successful search, that we have indeed been walking the * correct key path. * * Note that we can never "miss" the correct key in the tree if present by * following the wrong path. Path compression ensures that segments of the key * that are the same for all keys with a given prefix are skipped, but the * skipped part *is* identical for each node in the subtrie below the skipped * bit! trie_insert() in this implementation takes care of that. * * if n is an internal node - a 'tnode' here, the various parts of its key * have many different meanings. * * Example: * _________________________________________________________________ * | i | i | i | i | i | i | i | N | N | N | S | S | S | S | S | C | * ----------------------------------------------------------------- * 31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 * * _________________________________________________________________ * | C | C | C | u | u | u | u | u | u | u | u | u | u | u | u | u | * ----------------------------------------------------------------- * 15 14 13 12 11 10 9 8 7 6 5 4 3 2 1 0 * * tp->pos = 22 * tp->bits = 3 * n->pos = 13 * n->bits = 4 * * First, let's just ignore the bits that come before the parent tp, that is * the bits from (tp->pos + tp->bits) to 31. They are *known* but at this * point we do not use them for anything. * * The bits from (tp->pos) to (tp->pos + tp->bits - 1) - "N", above - are the * index into the parent's child array. That is, they will be used to find * 'n' among tp's children. * * The bits from (n->pos + n->bits) to (tp->pos - 1) - "S" - are skipped bits * for the node n. * * All the bits we have seen so far are significant to the node n. The rest * of the bits are really not needed or indeed known in n->key. * * The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into * n's child array, and will of course be different for each child. * * The rest of the bits, from 0 to (n->pos -1) - "u" - are completely unknown * at this point. */ static const int halve_threshold = 25; static const int inflate_threshold = 50; static const int halve_threshold_root = 15; static const int inflate_threshold_root = 30; static void __alias_free_mem(struct rcu_head *head) { struct fib_alias *fa = container_of(head, struct fib_alias, rcu); kmem_cache_free(fn_alias_kmem, fa); } static inline void alias_free_mem_rcu(struct fib_alias *fa) { call_rcu(&fa->rcu, __alias_free_mem); } #define TNODE_VMALLOC_MAX \ ilog2((SIZE_MAX - TNODE_SIZE(0)) / sizeof(struct key_vector *)) static void __node_free_rcu(struct rcu_head *head) { struct tnode *n = container_of(head, struct tnode, rcu); if (!n->tn_bits) kmem_cache_free(trie_leaf_kmem, n); else kvfree(n); } #define node_free(n) call_rcu(&tn_info(n)->rcu, __node_free_rcu) static struct tnode *tnode_alloc(int bits) { size_t size; /* verify bits is within bounds */ if (bits > TNODE_VMALLOC_MAX) return NULL; /* determine size and verify it is non-zero and didn't overflow */ size = TNODE_SIZE(1ul << bits); if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); else return vzalloc(size); } static inline void empty_child_inc(struct key_vector *n) { tn_info(n)->empty_children++; if (!tn_info(n)->empty_children) tn_info(n)->full_children++; } static inline void empty_child_dec(struct key_vector *n) { if (!tn_info(n)->empty_children) tn_info(n)->full_children--; tn_info(n)->empty_children--; } static struct key_vector *leaf_new(t_key key, struct fib_alias *fa) { struct key_vector *l; struct tnode *kv; kv = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL); if (!kv) return NULL; /* initialize key vector */ l = kv->kv; l->key = key; l->pos = 0; l->bits = 0; l->slen = fa->fa_slen; /* link leaf to fib alias */ INIT_HLIST_HEAD(&l->leaf); hlist_add_head(&fa->fa_list, &l->leaf); return l; } static struct key_vector *tnode_new(t_key key, int pos, int bits) { unsigned int shift = pos + bits; struct key_vector *tn; struct tnode *tnode; /* verify bits and pos their msb bits clear and values are valid */ BUG_ON(!bits || (shift > KEYLENGTH)); tnode = tnode_alloc(bits); if (!tnode) return NULL; pr_debug("AT %p s=%zu %zu\n", tnode, TNODE_SIZE(0), sizeof(struct key_vector *) << bits); if (bits == KEYLENGTH) tnode->full_children = 1; else tnode->empty_children = 1ul << bits; tn = tnode->kv; tn->key = (shift < KEYLENGTH) ? (key >> shift) << shift : 0; tn->pos = pos; tn->bits = bits; tn->slen = pos; return tn; } /* Check whether a tnode 'n' is "full", i.e. it is an internal node * and no bits are skipped. See discussion in dyntree paper p. 6 */ static inline int tnode_full(struct key_vector *tn, struct key_vector *n) { return n && ((n->pos + n->bits) == tn->pos) && IS_TNODE(n); } /* Add a child at position i overwriting the old value. * Update the value of full_children and empty_children. */ static void put_child(struct key_vector *tn, unsigned long i, struct key_vector *n) { struct key_vector *chi = get_child(tn, i); int isfull, wasfull; BUG_ON(i >= child_length(tn)); /* update emptyChildren, overflow into fullChildren */ if (!n && chi) empty_child_inc(tn); if (n && !chi) empty_child_dec(tn); /* update fullChildren */ wasfull = tnode_full(tn, chi); isfull = tnode_full(tn, n); if (wasfull && !isfull) tn_info(tn)->full_children--; else if (!wasfull && isfull) tn_info(tn)->full_children++; if (n && (tn->slen < n->slen)) tn->slen = n->slen; rcu_assign_pointer(tn->tnode[i], n); } static void update_children(struct key_vector *tn) { unsigned long i; /* update all of the child parent pointers */ for (i = child_length(tn); i;) { struct key_vector *inode = get_child(tn, --i); if (!inode) continue; /* Either update the children of a tnode that * already belongs to us or update the child * to point to ourselves. */ if (node_parent(inode) == tn) update_children(inode); else node_set_parent(inode, tn); } } static inline void put_child_root(struct key_vector *tp, t_key key, struct key_vector *n) { if (IS_TRIE(tp)) rcu_assign_pointer(tp->tnode[0], n); else put_child(tp, get_index(key, tp), n); } static inline void tnode_free_init(struct key_vector *tn) { tn_info(tn)->rcu.next = NULL; } static inline void tnode_free_append(struct key_vector *tn, struct key_vector *n) { tn_info(n)->rcu.next = tn_info(tn)->rcu.next; tn_info(tn)->rcu.next = &tn_info(n)->rcu; } static void tnode_free(struct key_vector *tn) { struct callback_head *head = &tn_info(tn)->rcu; while (head) { head = head->next; tnode_free_size += TNODE_SIZE(1ul << tn->bits); node_free(tn); tn = container_of(head, struct tnode, rcu)->kv; } if (tnode_free_size >= sysctl_fib_sync_mem) { tnode_free_size = 0; synchronize_rcu(); } } static struct key_vector *replace(struct trie *t, struct key_vector *oldtnode, struct key_vector *tn) { struct key_vector *tp = node_parent(oldtnode); unsigned long i; /* setup the parent pointer out of and back into this node */ NODE_INIT_PARENT(tn, tp); put_child_root(tp, tn->key, tn); /* update all of the child parent pointers */ update_children(tn); /* all pointers should be clean so we are done */ tnode_free(oldtnode); /* resize children now that oldtnode is freed */ for (i = child_length(tn); i;) { struct key_vector *inode = get_child(tn, --i); /* resize child node */ if (tnode_full(tn, inode)) tn = resize(t, inode); } return tp; } static struct key_vector *inflate(struct trie *t, struct key_vector *oldtnode) { struct key_vector *tn; unsigned long i; t_key m; pr_debug("In inflate\n"); tn = tnode_new(oldtnode->key, oldtnode->pos - 1, oldtnode->bits + 1); if (!tn) goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); /* Assemble all of the pointers in our cluster, in this case that * represents all of the pointers out of our allocated nodes that * point to existing tnodes and the links between our allocated * nodes. */ for (i = child_length(oldtnode), m = 1u << tn->pos; i;) { struct key_vector *inode = get_child(oldtnode, --i); struct key_vector *node0, *node1; unsigned long j, k; /* An empty child */ if (!inode) continue; /* A leaf or an internal node with skipped bits */ if (!tnode_full(oldtnode, inode)) { put_child(tn, get_index(inode->key, tn), inode); continue; } /* drop the node in the old tnode free list */ tnode_free_append(oldtnode, inode); /* An internal node with two children */ if (inode->bits == 1) { put_child(tn, 2 * i + 1, get_child(inode, 1)); put_child(tn, 2 * i, get_child(inode, 0)); continue; } /* We will replace this node 'inode' with two new * ones, 'node0' and 'node1', each with half of the * original children. The two new nodes will have * a position one bit further down the key and this * means that the "significant" part of their keys * (see the discussion near the top of this file) * will differ by one bit, which will be "0" in * node0's key and "1" in node1's key. Since we are * moving the key position by one step, the bit that * we are moving away from - the bit at position * (tn->pos) - is the one that will differ between * node0 and node1. So... we synthesize that bit in the * two new keys. */ node1 = tnode_new(inode->key | m, inode->pos, inode->bits - 1); if (!node1) goto nomem; node0 = tnode_new(inode->key, inode->pos, inode->bits - 1); tnode_free_append(tn, node1); if (!node0) goto nomem; tnode_free_append(tn, node0); /* populate child pointers in new nodes */ for (k = child_length(inode), j = k / 2; j;) { put_child(node1, --j, get_child(inode, --k)); put_child(node0, j, get_child(inode, j)); put_child(node1, --j, get_child(inode, --k)); put_child(node0, j, get_child(inode, j)); } /* link new nodes to parent */ NODE_INIT_PARENT(node1, tn); NODE_INIT_PARENT(node0, tn); /* link parent to nodes */ put_child(tn, 2 * i + 1, node1); put_child(tn, 2 * i, node0); } /* setup the parent pointers into and out of this node */ return replace(t, oldtnode, tn); nomem: /* all pointers should be clean so we are done */ tnode_free(tn); notnode: return NULL; } static struct key_vector *halve(struct trie *t, struct key_vector *oldtnode) { struct key_vector *tn; unsigned long i; pr_debug("In halve\n"); tn = tnode_new(oldtnode->key, oldtnode->pos + 1, oldtnode->bits - 1); if (!tn) goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); /* Assemble all of the pointers in our cluster, in this case that * represents all of the pointers out of our allocated nodes that * point to existing tnodes and the links between our allocated * nodes. */ for (i = child_length(oldtnode); i;) { struct key_vector *node1 = get_child(oldtnode, --i); struct key_vector *node0 = get_child(oldtnode, --i); struct key_vector *inode; /* At least one of the children is empty */ if (!node1 || !node0) { put_child(tn, i / 2, node1 ? : node0); continue; } /* Two nonempty children */ inode = tnode_new(node0->key, oldtnode->pos, 1); if (!inode) goto nomem; tnode_free_append(tn, inode); /* initialize pointers out of node */ put_child(inode, 1, node1); put_child(inode, 0, node0); NODE_INIT_PARENT(inode, tn); /* link parent to node */ put_child(tn, i / 2, inode); } /* setup the parent pointers into and out of this node */ return replace(t, oldtnode, tn); nomem: /* all pointers should be clean so we are done */ tnode_free(tn); notnode: return NULL; } static struct key_vector *collapse(struct trie *t, struct key_vector *oldtnode) { struct key_vector *n, *tp; unsigned long i; /* scan the tnode looking for that one child that might still exist */ for (n = NULL, i = child_length(oldtnode); !n && i;) n = get_child(oldtnode, --i); /* compress one level */ tp = node_parent(oldtnode); put_child_root(tp, oldtnode->key, n); node_set_parent(n, tp); /* drop dead node */ node_free(oldtnode); return tp; } static unsigned char update_suffix(struct key_vector *tn) { unsigned char slen = tn->pos; unsigned long stride, i; unsigned char slen_max; /* only vector 0 can have a suffix length greater than or equal to * tn->pos + tn->bits, the second highest node will have a suffix * length at most of tn->pos + tn->bits - 1 */ slen_max = min_t(unsigned char, tn->pos + tn->bits - 1, tn->slen); /* search though the list of children looking for nodes that might * have a suffix greater than the one we currently have. This is * why we start with a stride of 2 since a stride of 1 would * represent the nodes with suffix length equal to tn->pos */ for (i = 0, stride = 0x2ul ; i < child_length(tn); i += stride) { struct key_vector *n = get_child(tn, i); if (!n || (n->slen <= slen)) continue; /* update stride and slen based on new value */ stride <<= (n->slen - slen); slen = n->slen; i &= ~(stride - 1); /* stop searching if we have hit the maximum possible value */ if (slen >= slen_max) break; } tn->slen = slen; return slen; } /* From "Implementing a dynamic compressed trie" by Stefan Nilsson of * the Helsinki University of Technology and Matti Tikkanen of Nokia * Telecommunications, page 6: * "A node is doubled if the ratio of non-empty children to all * children in the *doubled* node is at least 'high'." * * 'high' in this instance is the variable 'inflate_threshold'. It * is expressed as a percentage, so we multiply it with * child_length() and instead of multiplying by 2 (since the * child array will be doubled by inflate()) and multiplying * the left-hand side by 100 (to handle the percentage thing) we * multiply the left-hand side by 50. * * The left-hand side may look a bit weird: child_length(tn) * - tn->empty_children is of course the number of non-null children * in the current node. tn->full_children is the number of "full" * children, that is non-null tnodes with a skip value of 0. * All of those will be doubled in the resulting inflated tnode, so * we just count them one extra time here. * * A clearer way to write this would be: * * to_be_doubled = tn->full_children; * not_to_be_doubled = child_length(tn) - tn->empty_children - * tn->full_children; * * new_child_length = child_length(tn) * 2; * * new_fill_factor = 100 * (not_to_be_doubled + 2*to_be_doubled) / * new_child_length; * if (new_fill_factor >= inflate_threshold) * * ...and so on, tho it would mess up the while () loop. * * anyway, * 100 * (not_to_be_doubled + 2*to_be_doubled) / new_child_length >= * inflate_threshold * * avoid a division: * 100 * (not_to_be_doubled + 2*to_be_doubled) >= * inflate_threshold * new_child_length * * expand not_to_be_doubled and to_be_doubled, and shorten: * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= inflate_threshold * new_child_length * * expand new_child_length: * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= * inflate_threshold * child_length(tn) * 2 * * shorten again: * 50 * (tn->full_children + child_length(tn) - * tn->empty_children) >= inflate_threshold * * child_length(tn) * */ static inline bool should_inflate(struct key_vector *tp, struct key_vector *tn) { unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ threshold *= IS_TRIE(tp) ? inflate_threshold_root : inflate_threshold; used -= tn_info(tn)->empty_children; used += tn_info(tn)->full_children; /* if bits == KEYLENGTH then pos = 0, and will fail below */ return (used > 1) && tn->pos && ((50 * used) >= threshold); } static inline bool should_halve(struct key_vector *tp, struct key_vector *tn) { unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ threshold *= IS_TRIE(tp) ? halve_threshold_root : halve_threshold; used -= tn_info(tn)->empty_children; /* if bits == KEYLENGTH then used = 100% on wrap, and will fail below */ return (used > 1) && (tn->bits > 1) && ((100 * used) < threshold); } static inline bool should_collapse(struct key_vector *tn) { unsigned long used = child_length(tn); used -= tn_info(tn)->empty_children; /* account for bits == KEYLENGTH case */ if ((tn->bits == KEYLENGTH) && tn_info(tn)->full_children) used -= KEY_MAX; /* One child or none, time to drop us from the trie */ return used < 2; } #define MAX_WORK 10 static struct key_vector *resize(struct trie *t, struct key_vector *tn) { #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats = t->stats; #endif struct key_vector *tp = node_parent(tn); unsigned long cindex = get_index(tn->key, tp); int max_work = MAX_WORK; pr_debug("In tnode_resize %p inflate_threshold=%d threshold=%d\n", tn, inflate_threshold, halve_threshold); /* track the tnode via the pointer from the parent instead of * doing it ourselves. This way we can let RCU fully do its * thing without us interfering */ BUG_ON(tn != get_child(tp, cindex)); /* Double as long as the resulting node has a number of * nonempty nodes that are above the threshold. */ while (should_inflate(tp, tn) && max_work) { tp = inflate(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; tn = get_child(tp, cindex); } /* update parent in case inflate failed */ tp = node_parent(tn); /* Return if at least one inflate is run */ if (max_work != MAX_WORK) return tp; /* Halve as long as the number of empty children in this * node is above threshold. */ while (should_halve(tp, tn) && max_work) { tp = halve(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; tn = get_child(tp, cindex); } /* Only one child remains */ if (should_collapse(tn)) return collapse(t, tn); /* update parent in case halve failed */ return node_parent(tn); } static void node_pull_suffix(struct key_vector *tn, unsigned char slen) { unsigned char node_slen = tn->slen; while ((node_slen > tn->pos) && (node_slen > slen)) { slen = update_suffix(tn); if (node_slen == slen) break; tn = node_parent(tn); node_slen = tn->slen; } } static void node_push_suffix(struct key_vector *tn, unsigned char slen) { while (tn->slen < slen) { tn->slen = slen; tn = node_parent(tn); } } /* rcu_read_lock needs to be hold by caller from readside */ static struct key_vector *fib_find_node(struct trie *t, struct key_vector **tp, u32 key) { struct key_vector *pn, *n = t->kv; unsigned long index = 0; do { pn = n; n = get_child_rcu(n, index); if (!n) break; index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the bits in the cindex. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex * * This check is safe even if bits == KEYLENGTH due to the * fact that we can only allocate a node with 32 bits if a * long is greater than 32 bits. */ if (index >= (1ul << n->bits)) { n = NULL; break; } /* keep searching until we find a perfect match leaf or NULL */ } while (IS_TNODE(n)); *tp = pn; return n; } /* Return the first fib alias matching TOS with * priority less than or equal to PRIO. * If 'find_first' is set, return the first matching * fib alias, regardless of TOS and priority. */ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, u8 tos, u32 prio, u32 tb_id, bool find_first) { struct fib_alias *fa; if (!fah) return NULL; hlist_for_each_entry(fa, fah, fa_list) { if (fa->fa_slen < slen) continue; if (fa->fa_slen != slen) break; if (fa->tb_id > tb_id) continue; if (fa->tb_id != tb_id) break; if (find_first) return fa; if (fa->fa_tos > tos) continue; if (fa->fa_info->fib_priority >= prio || fa->fa_tos < tos) return fa; } return NULL; } static struct fib_alias * fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) { u8 slen = KEYLENGTH - fri->dst_len; struct key_vector *l, *tp; struct fib_table *tb; struct fib_alias *fa; struct trie *t; tb = fib_get_table(net, fri->tb_id); if (!tb) return NULL; t = (struct trie *)tb->tb_data; l = fib_find_node(t, &tp, be32_to_cpu(fri->dst)); if (!l) return NULL; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { if (fa->fa_slen == slen && fa->tb_id == fri->tb_id && fa->fa_tos == fri->tos && fa->fa_info == fri->fi && fa->fa_type == fri->type) return fa; } return NULL; } void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) { struct fib_alias *fa_match; rcu_read_lock(); fa_match = fib_find_matching_alias(net, fri); if (!fa_match) goto out; fa_match->offload = fri->offload; fa_match->trap = fri->trap; out: rcu_read_unlock(); } EXPORT_SYMBOL_GPL(fib_alias_hw_flags_set); static void trie_rebalance(struct trie *t, struct key_vector *tn) { while (!IS_TRIE(tn)) tn = resize(t, tn); } static int fib_insert_node(struct trie *t, struct key_vector *tp, struct fib_alias *new, t_key key) { struct key_vector *n, *l; l = leaf_new(key, new); if (!l) goto noleaf; /* retrieve child from parent node */ n = get_child(tp, get_index(key, tp)); /* Case 2: n is a LEAF or a TNODE and the key doesn't match. * * Add a new tnode here * first tnode need some special handling * leaves us in position for handling as case 3 */ if (n) { struct key_vector *tn; tn = tnode_new(key, __fls(key ^ n->key), 1); if (!tn) goto notnode; /* initialize routes out of node */ NODE_INIT_PARENT(tn, tp); put_child(tn, get_index(key, tn) ^ 1, n); /* start adding routes into the node */ put_child_root(tp, key, tn); node_set_parent(n, tn); /* parent now has a NULL spot where the leaf can go */ tp = tn; } /* Case 3: n is NULL, and will just insert a new leaf */ node_push_suffix(tp, new->fa_slen); NODE_INIT_PARENT(l, tp); put_child_root(tp, key, l); trie_rebalance(t, tp); return 0; notnode: node_free(l); noleaf: return -ENOMEM; } static int fib_insert_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *new, struct fib_alias *fa, t_key key) { if (!l) return fib_insert_node(t, tp, new, key); if (fa) { hlist_add_before_rcu(&new->fa_list, &fa->fa_list); } else { struct fib_alias *last; hlist_for_each_entry(last, &l->leaf, fa_list) { if (new->fa_slen < last->fa_slen) break; if ((new->fa_slen == last->fa_slen) && (new->tb_id > last->tb_id)) break; fa = last; } if (fa) hlist_add_behind_rcu(&new->fa_list, &fa->fa_list); else hlist_add_head_rcu(&new->fa_list, &l->leaf); } /* if we added to the tail node then we need to update slen */ if (l->slen < new->fa_slen) { l->slen = new->fa_slen; node_push_suffix(tp, new->fa_slen); } return 0; } static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) { if (plen > KEYLENGTH) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); return false; } if ((plen < KEYLENGTH) && (key << plen)) { NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length"); return false; } return true; } static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old); /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct fib_alias *fa, *new_fa; struct key_vector *l, *tp; u16 nlflags = NLM_F_EXCL; struct fib_info *fi; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; u8 tos = cfg->fc_tos; u32 key; int err; key = ntohl(cfg->fc_dst); if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); fi = fib_create_info(cfg, extack); if (IS_ERR(fi)) { err = PTR_ERR(fi); goto err; } l = fib_find_node(t, &tp, key); fa = l ? fib_find_alias(&l->leaf, slen, tos, fi->fib_priority, tb->tb_id, false) : NULL; /* Now fa, if non-NULL, points to the first fib alias * with the same keys [prefix,tos,priority], if such key already * exists or to the node before which we will insert new one. * * If fa is NULL, we will need to allocate a new one and * insert to the tail of the section matching the suffix length * of the new alias. */ if (fa && fa->fa_tos == tos && fa->fa_info->fib_priority == fi->fib_priority) { struct fib_alias *fa_first, *fa_match; err = -EEXIST; if (cfg->fc_nlflags & NLM_F_EXCL) goto out; nlflags &= ~NLM_F_EXCL; /* We have 2 goals: * 1. Find exact match for type, scope, fib_info to avoid * duplicate routes * 2. Find next 'fa' (or head), NLM_F_APPEND inserts before it */ fa_match = NULL; fa_first = fa; hlist_for_each_entry_from(fa, fa_list) { if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || (fa->fa_tos != tos)) break; if (fa->fa_info->fib_priority != fi->fib_priority) break; if (fa->fa_type == cfg->fc_type && fa->fa_info == fi) { fa_match = fa; break; } } if (cfg->fc_nlflags & NLM_F_REPLACE) { struct fib_info *fi_drop; u8 state; nlflags |= NLM_F_REPLACE; fa = fa_first; if (fa_match) { if (fa == fa_match) err = 0; goto out; } err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; fi_drop = fa->fa_info; new_fa->fa_tos = fa->fa_tos; new_fa->fa_info = fi; new_fa->fa_type = cfg->fc_type; state = fa->fa_state; new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { enum fib_event_type fib_event; fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib_entry_notifiers(net, fib_event, key, plen, new_fa, extack); if (err) { hlist_replace_rcu(&new_fa->fa_list, &fa->fa_list); goto out_free_new_fa; } } rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); alias_free_mem_rcu(fa); fib_release_info(fi_drop); if (state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); goto succeeded; } /* Error if we find a perfect match which * uses the same scope, type, and nexthop * information. */ if (fa_match) goto out; if (cfg->fc_nlflags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; else fa = fa_first; } err = -ENOENT; if (!(cfg->fc_nlflags & NLM_F_CREATE)) goto out; nlflags |= NLM_F_CREATE; err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; new_fa->fa_info = fi; new_fa->fa_tos = tos; new_fa->fa_type = cfg->fc_type; new_fa->fa_state = 0; new_fa->fa_slen = slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); if (err) goto out_free_new_fa; /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); if (WARN_ON_ONCE(!l)) goto out_free_new_fa; if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { enum fib_event_type fib_event; fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib_entry_notifiers(net, fib_event, key, plen, new_fa, extack); if (err) goto out_remove_new_fa; } if (!plen) tb->tb_num_default++; rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id, &cfg->fc_nlinfo, nlflags); succeeded: return 0; out_remove_new_fa: fib_remove_alias(t, tp, l, new_fa); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: fib_release_info(fi); err: return err; } static inline t_key prefix_mismatch(t_key key, struct key_vector *n) { t_key prefix = n->key; return (key ^ prefix) & (prefix | -prefix); } bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, const struct flowi4 *flp) { if (nhc->nhc_flags & RTNH_F_DEAD) return false; if (ip_ignore_linkdown(nhc->nhc_dev) && nhc->nhc_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) return false; if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) { if (flp->flowi4_oif && flp->flowi4_oif != nhc->nhc_oif) return false; } return true; } /* should be called with rcu_read_lock */ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags) { struct trie *t = (struct trie *) tb->tb_data; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats = t->stats; #endif const t_key key = ntohl(flp->daddr); struct key_vector *n, *pn; struct fib_alias *fa; unsigned long index; t_key cindex; pn = t->kv; cindex = 0; n = get_child_rcu(pn, cindex); if (!n) { trace_fib_table_lookup(tb->tb_id, flp, NULL, -EAGAIN); return -EAGAIN; } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->gets); #endif /* Step 1: Travel to the longest prefix match in the trie */ for (;;) { index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the "bits" in the prefix. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex * * This check is safe even if bits == KEYLENGTH due to the * fact that we can only allocate a node with 32 bits if a * long is greater than 32 bits. */ if (index >= (1ul << n->bits)) break; /* we have found a leaf. Prefixes have already been compared */ if (IS_LEAF(n)) goto found; /* only record pn and cindex if we are going to be chopping * bits later. Otherwise we are just wasting cycles. */ if (n->slen > n->pos) { pn = n; cindex = index; } n = get_child_rcu(n, index); if (unlikely(!n)) goto backtrace; } /* Step 2: Sort out leaves and begin backtracing for longest prefix */ for (;;) { /* record the pointer where our next node pointer is stored */ struct key_vector __rcu **cptr = n->tnode; /* This test verifies that none of the bits that differ * between the key and the prefix exist in the region of * the lsb and higher in the prefix. */ if (unlikely(prefix_mismatch(key, n)) || (n->slen == n->pos)) goto backtrace; /* exit out and process leaf */ if (unlikely(IS_LEAF(n))) break; /* Don't bother recording parent info. Since we are in * prefix match mode we will have to come back to wherever * we started this traversal anyway */ while ((n = rcu_dereference(*cptr)) == NULL) { backtrace: #ifdef CONFIG_IP_FIB_TRIE_STATS if (!n) this_cpu_inc(stats->null_node_hit); #endif /* If we are at cindex 0 there are no more bits for * us to strip at this level so we must ascend back * up one level to see if there are any more bits to * be stripped there. */ while (!cindex) { t_key pkey = pn->key; /* If we don't have a parent then there is * nothing for us to do as we do not have any * further nodes to parse. */ if (IS_TRIE(pn)) { trace_fib_table_lookup(tb->tb_id, flp, NULL, -EAGAIN); return -EAGAIN; } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->backtrack); #endif /* Get Child's index */ pn = node_parent_rcu(pn); cindex = get_index(pkey, pn); } /* strip the least significant bit from the cindex */ cindex &= cindex - 1; /* grab pointer for next child node */ cptr = &pn->tnode[cindex]; } } found: /* this line carries forward the xor from earlier in the function */ index = key ^ n->key; /* Step 3: Process the leaf, if that fails fall back to backtracing */ hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; struct fib_nh_common *nhc; int nhsel, err; if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) { if (index >= (1ul << fa->fa_slen)) continue; } if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) continue; if (fi->fib_dead) continue; if (fa->fa_info->fib_scope < flp->flowi4_scope) continue; fib_alias_accessed(fa); err = fib_props[fa->fa_type].error; if (unlikely(err < 0)) { out_reject: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif trace_fib_table_lookup(tb->tb_id, flp, NULL, err); return err; } if (fi->fib_flags & RTNH_F_DEAD) continue; if (unlikely(fi->nh)) { if (nexthop_is_blackhole(fi->nh)) { err = fib_props[RTN_BLACKHOLE].error; goto out_reject; } nhc = nexthop_get_nhc_lookup(fi->nh, fib_flags, flp, &nhsel); if (nhc) goto set_result; goto miss; } for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { nhc = fib_info_nhc(fi, nhsel); if (!fib_lookup_good_nhc(nhc, fib_flags, flp)) continue; set_result: if (!(fib_flags & FIB_LOOKUP_NOREF)) refcount_inc(&fi->fib_clntref); res->prefix = htonl(n->key); res->prefixlen = KEYLENGTH - fa->fa_slen; res->nh_sel = nhsel; res->nhc = nhc; res->type = fa->fa_type; res->scope = fi->fib_scope; res->fi = fi; res->table = tb; res->fa_head = &n->leaf; #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif trace_fib_table_lookup(tb->tb_id, flp, nhc, err); return err; } } miss: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_miss); #endif goto backtrace; } EXPORT_SYMBOL_GPL(fib_table_lookup); static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old) { /* record the location of the previous list_info entry */ struct hlist_node **pprev = old->fa_list.pprev; struct fib_alias *fa = hlist_entry(pprev, typeof(*fa), fa_list.next); /* remove the fib_alias from the list */ hlist_del_rcu(&old->fa_list); /* if we emptied the list this leaf will be freed and we can sort * out parent suffix lengths as a part of trie_rebalance */ if (hlist_empty(&l->leaf)) { if (tp->slen == l->slen) node_pull_suffix(tp, tp->pos); put_child_root(tp, l->key, NULL); node_free(l); trie_rebalance(t, tp); return; } /* only access fa if it is pointing at the last valid hlist_node */ if (*pprev) return; /* update the trie with the latest suffix length */ l->slen = fa->fa_slen; node_pull_suffix(tp, fa->fa_slen); } static void fib_notify_alias_delete(struct net *net, u32 key, struct hlist_head *fah, struct fib_alias *fa_to_delete, struct netlink_ext_ack *extack) { struct fib_alias *fa_next, *fa_to_notify; u32 tb_id = fa_to_delete->tb_id; u8 slen = fa_to_delete->fa_slen; enum fib_event_type fib_event; /* Do not notify if we do not care about the route. */ if (fib_find_alias(fah, slen, 0, 0, tb_id, true) != fa_to_delete) return; /* Determine if the route should be replaced by the next route in the * list. */ fa_next = hlist_entry_safe(fa_to_delete->fa_list.next, struct fib_alias, fa_list); if (fa_next && fa_next->fa_slen == slen && fa_next->tb_id == tb_id) { fib_event = FIB_EVENT_ENTRY_REPLACE; fa_to_notify = fa_next; } else { fib_event = FIB_EVENT_ENTRY_DEL; fa_to_notify = fa_to_delete; } call_fib_entry_notifiers(net, fib_event, key, KEYLENGTH - slen, fa_to_notify, extack); } /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *fa_to_delete; struct key_vector *l, *tp; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; u8 tos = cfg->fc_tos; u32 key; key = ntohl(cfg->fc_dst); if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; l = fib_find_node(t, &tp, key); if (!l) return -ESRCH; fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id, false); if (!fa) return -ESRCH; pr_debug("Deleting %08x/%d tos=%d t=%p\n", key, plen, tos, t); fa_to_delete = NULL; hlist_for_each_entry_from(fa, fa_list) { struct fib_info *fi = fa->fa_info; if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || (fa->fa_tos != tos)) break; if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && (cfg->fc_scope == RT_SCOPE_NOWHERE || fa->fa_info->fib_scope == cfg->fc_scope) && (!cfg->fc_prefsrc || fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && fib_nh_match(net, cfg, fi, extack) == 0 && fib_metrics_match(cfg, fi)) { fa_to_delete = fa; break; } } if (!fa_to_delete) return -ESRCH; fib_notify_alias_delete(net, key, &l->leaf, fa_to_delete, extack); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); if (!plen) tb->tb_num_default--; fib_remove_alias(t, tp, l, fa_to_delete); if (fa_to_delete->fa_state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); fib_release_info(fa_to_delete->fa_info); alias_free_mem_rcu(fa_to_delete); return 0; } /* Scan for the next leaf starting at the provided key value */ static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key) { struct key_vector *pn, *n = *tn; unsigned long cindex; /* this loop is meant to try and find the key in the trie */ do { /* record parent and next child index */ pn = n; cindex = (key > pn->key) ? get_index(key, pn) : 0; if (cindex >> pn->bits) break; /* descend into the next child */ n = get_child_rcu(pn, cindex++); if (!n) break; /* guarantee forward progress on the keys */ if (IS_LEAF(n) && (n->key >= key)) goto found; } while (IS_TNODE(n)); /* this loop will search for the next leaf with a greater key */ while (!IS_TRIE(pn)) { /* if we exhausted the parent node we will need to climb */ if (cindex >= (1ul << pn->bits)) { t_key pkey = pn->key; pn = node_parent_rcu(pn); cindex = get_index(pkey, pn) + 1; continue; } /* grab the next available node */ n = get_child_rcu(pn, cindex++); if (!n) continue; /* no need to compare keys since we bumped the index */ if (IS_LEAF(n)) goto found; /* Rescan start scanning in new node */ pn = n; cindex = 0; } *tn = pn; return NULL; /* Root of trie */ found: /* if we are at the limit for keys just return NULL for the tnode */ *tn = pn; return n; } static void fib_trie_free(struct fib_table *tb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; /* walk trie in reverse order and free everything */ for (;;) { struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; if (IS_TRIE(pn)) break; n = pn; pn = node_parent(pn); /* drop emptied tnode */ put_child_root(pn, n->key, NULL); node_free(n); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { hlist_del_rcu(&fa->fa_list); alias_free_mem_rcu(fa); } put_child_root(pn, n->key, NULL); node_free(n); } #ifdef CONFIG_IP_FIB_TRIE_STATS free_percpu(t->stats); #endif kfree(tb); } struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) { struct trie *ot = (struct trie *)oldtb->tb_data; struct key_vector *l, *tp = ot->kv; struct fib_table *local_tb; struct fib_alias *fa; struct trie *lt; t_key key = 0; if (oldtb->tb_data == oldtb->__data) return oldtb; local_tb = fib_trie_table(RT_TABLE_LOCAL, NULL); if (!local_tb) return NULL; lt = (struct trie *)local_tb->tb_data; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { struct key_vector *local_l = NULL, *local_tp; hlist_for_each_entry(fa, &l->leaf, fa_list) { struct fib_alias *new_fa; if (local_tb->tb_id != fa->tb_id) continue; /* clone fa for new local table */ new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; memcpy(new_fa, fa, sizeof(*fa)); /* insert clone into table */ if (!local_l) local_l = fib_find_node(lt, &local_tp, l->key); if (fib_insert_alias(lt, local_tp, local_l, new_fa, NULL, l->key)) { kmem_cache_free(fn_alias_kmem, new_fa); goto out; } } /* stop loop if key wrapped back to 0 */ key = l->key + 1; if (key < l->key) break; } return local_tb; out: fib_trie_free(local_tb); return NULL; } /* Caller must hold RTNL */ void fib_table_flush_external(struct fib_table *tb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; /* walk trie in reverse order */ for (;;) { unsigned char slen = 0; struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; /* cannot resize the trie vector */ if (IS_TRIE(pn)) break; /* update the suffix to address pulled leaves */ if (pn->slen > pn->pos) update_suffix(pn); /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { /* if alias was cloned to local then we just * need to remove the local copy from main */ if (tb->tb_id != fa->tb_id) { hlist_del_rcu(&fa->fa_list); alias_free_mem_rcu(fa); continue; } /* record local slen */ slen = fa->fa_slen; } /* update leaf slen */ n->slen = slen; if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); } } } /* Caller must hold RTNL. */ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; int found = 0; /* walk trie in reverse order */ for (;;) { unsigned char slen = 0; struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; /* cannot resize the trie vector */ if (IS_TRIE(pn)) break; /* update the suffix to address pulled leaves */ if (pn->slen > pn->pos) update_suffix(pn); /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi || tb->tb_id != fa->tb_id || (!(fi->fib_flags & RTNH_F_DEAD) && !fib_props[fa->fa_type].error)) { slen = fa->fa_slen; continue; } /* Do not flush error routes if network namespace is * not being dismantled */ if (!flush_all && fib_props[fa->fa_type].error) { slen = fa->fa_slen; continue; } fib_notify_alias_delete(net, n->key, &n->leaf, fa, NULL); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); found++; } /* update leaf slen */ n->slen = slen; if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); } } pr_debug("trie_flush found=%d\n", found); return found; } /* derived from fib_trie_free */ static void __fib_info_notify_update(struct net *net, struct fib_table *tb, struct nl_info *info) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct fib_alias *fa; for (;;) { struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; if (IS_TRIE(pn)) break; pn = node_parent(pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi || !fi->nh_updated || fa->tb_id != tb->tb_id) continue; rtmsg_fib(RTM_NEWROUTE, htonl(n->key), fa, KEYLENGTH - fa->fa_slen, tb->tb_id, info, NLM_F_REPLACE); /* call_fib_entry_notifiers will be removed when * in-kernel notifier is implemented and supported * for nexthop objects */ call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, n->key, KEYLENGTH - fa->fa_slen, fa, NULL); } } } void fib_info_notify_update(struct net *net, struct nl_info *info) { unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) __fib_info_notify_update(net, tb, info); } } static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib_alias *fa; int last_slen = -1; int err; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi) continue; /* local and main table can share the same trie, * so don't notify twice for the same entry. */ if (tb->tb_id != fa->tb_id) continue; if (fa->fa_slen == last_slen) continue; last_slen = fa->fa_slen; err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_REPLACE, l->key, KEYLENGTH - fa->fa_slen, fa, extack); if (err) return err; } return 0; } static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; t_key key = 0; int err; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { err = fib_leaf_notify(l, tb, nb, extack); if (err) return err; key = l->key + 1; /* stop in case of wrap around */ if (key < l->key) break; } return 0; } int fib_notify(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { unsigned int h; int err; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { err = fib_table_notify(tb, nb, extack); if (err) return err; } } return 0; } static void __trie_free_rcu(struct rcu_head *head) { struct fib_table *tb = container_of(head, struct fib_table, rcu); #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie *t = (struct trie *)tb->tb_data; if (tb->tb_data == tb->__data) free_percpu(t->stats); #endif /* CONFIG_IP_FIB_TRIE_STATS */ kfree(tb); } void fib_free_table(struct fib_table *tb) { call_rcu(&tb->rcu, __trie_free_rcu); } static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter) { unsigned int flags = NLM_F_MULTI; __be32 xkey = htonl(l->key); int i, s_i, i_fa, s_fa, err; struct fib_alias *fa; if (filter->filter_set || !filter->dump_exceptions || !filter->dump_routes) flags |= NLM_F_DUMP_FILTERED; s_i = cb->args[4]; s_fa = cb->args[5]; i = 0; /* rcu_read_lock is hold by caller */ hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (i < s_i) goto next; i_fa = 0; if (tb->tb_id != fa->tb_id) goto next; if (filter->filter_set) { if (filter->rt_type && fa->fa_type != filter->rt_type) goto next; if ((filter->protocol && fi->fib_protocol != filter->protocol)) goto next; if (filter->dev && !fib_info_nh_uses_dev(fi, filter->dev)) goto next; } if (filter->dump_routes) { if (!s_fa) { struct fib_rt_info fri; fri.fi = fi; fri.tb_id = tb->tb_id; fri.dst = xkey; fri.dst_len = KEYLENGTH - fa->fa_slen; fri.tos = fa->fa_tos; fri.type = fa->fa_type; fri.offload = fa->offload; fri.trap = fa->trap; err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, &fri, flags); if (err < 0) goto stop; } i_fa++; } if (filter->dump_exceptions) { err = fib_dump_info_fnhe(skb, cb, tb->tb_id, fi, &i_fa, s_fa, flags); if (err < 0) goto stop; } next: i++; } cb->args[4] = i; return skb->len; stop: cb->args[4] = i; cb->args[5] = i_fa; return err; } /* rcu_read_lock needs to be hold by caller from readside */ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; /* Dump starting at last key. * Note: 0.0.0.0/0 (ie default) is first key. */ int count = cb->args[2]; t_key key = cb->args[3]; /* First time here, count and key are both always 0. Count > 0 * and key == 0 means the dump has wrapped around and we are done. */ if (count && !key) return skb->len; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { int err; err = fn_trie_dump_leaf(l, tb, skb, cb, filter); if (err < 0) { cb->args[3] = key; cb->args[2] = count; return err; } ++count; key = l->key + 1; memset(&cb->args[4], 0, sizeof(cb->args) - 4*sizeof(cb->args[0])); /* stop loop if key wrapped back to 0 */ if (key < l->key) break; } cb->args[3] = key; cb->args[2] = count; return skb->len; } void __init fib_trie_init(void) { fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), 0, SLAB_PANIC, NULL); trie_leaf_kmem = kmem_cache_create("ip_fib_trie", LEAF_SIZE, 0, SLAB_PANIC, NULL); } struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) { struct fib_table *tb; struct trie *t; size_t sz = sizeof(*tb); if (!alias) sz += sizeof(struct trie); tb = kzalloc(sz, GFP_KERNEL); if (!tb) return NULL; tb->tb_id = id; tb->tb_num_default = 0; tb->tb_data = (alias ? alias->__data : tb->__data); if (alias) return tb; t = (struct trie *) tb->tb_data; t->kv[0].pos = KEYLENGTH; t->kv[0].slen = KEYLENGTH; #ifdef CONFIG_IP_FIB_TRIE_STATS t->stats = alloc_percpu(struct trie_use_stats); if (!t->stats) { kfree(tb); tb = NULL; } #endif return tb; } #ifdef CONFIG_PROC_FS /* Depth first Trie walk iterator */ struct fib_trie_iter { struct seq_net_private p; struct fib_table *tb; struct key_vector *tnode; unsigned int index; unsigned int depth; }; static struct key_vector *fib_trie_get_next(struct fib_trie_iter *iter) { unsigned long cindex = iter->index; struct key_vector *pn = iter->tnode; t_key pkey; pr_debug("get_next iter={node=%p index=%d depth=%d}\n", iter->tnode, iter->index, iter->depth); while (!IS_TRIE(pn)) { while (cindex < child_length(pn)) { struct key_vector *n = get_child_rcu(pn, cindex++); if (!n) continue; if (IS_LEAF(n)) { iter->tnode = pn; iter->index = cindex; } else { /* push down one level */ iter->tnode = n; iter->index = 0; ++iter->depth; } return n; } /* Current node exhausted, pop back up */ pkey = pn->key; pn = node_parent_rcu(pn); cindex = get_index(pkey, pn) + 1; --iter->depth; } /* record root node so further searches know we are done */ iter->tnode = pn; iter->index = 0; return NULL; } static struct key_vector *fib_trie_get_first(struct fib_trie_iter *iter, struct trie *t) { struct key_vector *n, *pn; if (!t) return NULL; pn = t->kv; n = rcu_dereference(pn->tnode[0]); if (!n) return NULL; if (IS_TNODE(n)) { iter->tnode = n; iter->index = 0; iter->depth = 1; } else { iter->tnode = pn; iter->index = 0; iter->depth = 0; } return n; } static void trie_collect_stats(struct trie *t, struct trie_stat *s) { struct key_vector *n; struct fib_trie_iter iter; memset(s, 0, sizeof(*s)); rcu_read_lock(); for (n = fib_trie_get_first(&iter, t); n; n = fib_trie_get_next(&iter)) { if (IS_LEAF(n)) { struct fib_alias *fa; s->leaves++; s->totdepth += iter.depth; if (iter.depth > s->maxdepth) s->maxdepth = iter.depth; hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) ++s->prefixes; } else { s->tnodes++; if (n->bits < MAX_STAT_DEPTH) s->nodesizes[n->bits]++; s->nullpointers += tn_info(n)->empty_children; } } rcu_read_unlock(); } /* * This outputs /proc/net/fib_triestats */ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) { unsigned int i, max, pointers, bytes, avdepth; if (stat->leaves) avdepth = stat->totdepth*100 / stat->leaves; else avdepth = 0; seq_printf(seq, "\tAver depth: %u.%02d\n", avdepth / 100, avdepth % 100); seq_printf(seq, "\tMax depth: %u\n", stat->maxdepth); seq_printf(seq, "\tLeaves: %u\n", stat->leaves); bytes = LEAF_SIZE * stat->leaves; seq_printf(seq, "\tPrefixes: %u\n", stat->prefixes); bytes += sizeof(struct fib_alias) * stat->prefixes; seq_printf(seq, "\tInternal nodes: %u\n\t", stat->tnodes); bytes += TNODE_SIZE(0) * stat->tnodes; max = MAX_STAT_DEPTH; while (max > 0 && stat->nodesizes[max-1] == 0) max--; pointers = 0; for (i = 1; i < max; i++) if (stat->nodesizes[i] != 0) { seq_printf(seq, " %u: %u", i, stat->nodesizes[i]); pointers += (1<<i) * stat->nodesizes[i]; } seq_putc(seq, '\n'); seq_printf(seq, "\tPointers: %u\n", pointers); bytes += sizeof(struct key_vector *) * pointers; seq_printf(seq, "Null ptrs: %u\n", stat->nullpointers); seq_printf(seq, "Total size: %u kB\n", (bytes + 1023) / 1024); } #ifdef CONFIG_IP_FIB_TRIE_STATS static void trie_show_usage(struct seq_file *seq, const struct trie_use_stats __percpu *stats) { struct trie_use_stats s = { 0 }; int cpu; /* loop through all of the CPUs and gather up the stats */ for_each_possible_cpu(cpu) { const struct trie_use_stats *pcpu = per_cpu_ptr(stats, cpu); s.gets += pcpu->gets; s.backtrack += pcpu->backtrack; s.semantic_match_passed += pcpu->semantic_match_passed; s.semantic_match_miss += pcpu->semantic_match_miss; s.null_node_hit += pcpu->null_node_hit; s.resize_node_skipped += pcpu->resize_node_skipped; } seq_printf(seq, "\nCounters:\n---------\n"); seq_printf(seq, "gets = %u\n", s.gets); seq_printf(seq, "backtracks = %u\n", s.backtrack); seq_printf(seq, "semantic match passed = %u\n", s.semantic_match_passed); seq_printf(seq, "semantic match miss = %u\n", s.semantic_match_miss); seq_printf(seq, "null node hit= %u\n", s.null_node_hit); seq_printf(seq, "skipped node resize = %u\n\n", s.resize_node_skipped); } #endif /* CONFIG_IP_FIB_TRIE_STATS */ static void fib_table_print(struct seq_file *seq, struct fib_table *tb) { if (tb->tb_id == RT_TABLE_LOCAL) seq_puts(seq, "Local:\n"); else if (tb->tb_id == RT_TABLE_MAIN) seq_puts(seq, "Main:\n"); else seq_printf(seq, "Id %d:\n", tb->tb_id); } static int fib_triestat_seq_show(struct seq_file *seq, void *v) { struct net *net = (struct net *)seq->private; unsigned int h; seq_printf(seq, "Basic info: size of leaf:" " %zd bytes, size of tnode: %zd bytes.\n", LEAF_SIZE, TNODE_SIZE(0)); rcu_read_lock(); for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct trie *t = (struct trie *) tb->tb_data; struct trie_stat stat; if (!t) continue; fib_table_print(seq, tb); trie_collect_stats(t, &stat); trie_show_stats(seq, &stat); #ifdef CONFIG_IP_FIB_TRIE_STATS trie_show_usage(seq, t->stats); #endif } cond_resched_rcu(); } rcu_read_unlock(); return 0; } static struct key_vector *fib_trie_get_idx(struct seq_file *seq, loff_t pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); loff_t idx = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct key_vector *n; for (n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); n; n = fib_trie_get_next(iter)) if (pos == idx++) { iter->tb = tb; return n; } } } return NULL; } static void *fib_trie_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return fib_trie_get_idx(seq, *pos); } static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct fib_table *tb = iter->tb; struct hlist_node *tb_node; unsigned int h; struct key_vector *n; ++*pos; /* next node in same table */ n = fib_trie_get_next(iter); if (n) return n; /* walk rest of this hash chain */ h = tb->tb_id & (FIB_TABLE_HASHSZ - 1); while ((tb_node = rcu_dereference(hlist_next_rcu(&tb->tb_hlist)))) { tb = hlist_entry(tb_node, struct fib_table, tb_hlist); n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; } /* new hash chain */ while (++h < FIB_TABLE_HASHSZ) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist) { n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; } } return NULL; found: iter->tb = tb; return n; } static void fib_trie_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static void seq_indent(struct seq_file *seq, int n) { while (n-- > 0) seq_puts(seq, " "); } static inline const char *rtn_scope(char *buf, size_t len, enum rt_scope_t s) { switch (s) { case RT_SCOPE_UNIVERSE: return "universe"; case RT_SCOPE_SITE: return "site"; case RT_SCOPE_LINK: return "link"; case RT_SCOPE_HOST: return "host"; case RT_SCOPE_NOWHERE: return "nowhere"; default: snprintf(buf, len, "scope=%d", s); return buf; } } static const char *const rtn_type_names[__RTN_MAX] = { [RTN_UNSPEC] = "UNSPEC", [RTN_UNICAST] = "UNICAST", [RTN_LOCAL] = "LOCAL", [RTN_BROADCAST] = "BROADCAST", [RTN_ANYCAST] = "ANYCAST", [RTN_MULTICAST] = "MULTICAST", [RTN_BLACKHOLE] = "BLACKHOLE", [RTN_UNREACHABLE] = "UNREACHABLE", [RTN_PROHIBIT] = "PROHIBIT", [RTN_THROW] = "THROW", [RTN_NAT] = "NAT", [RTN_XRESOLVE] = "XRESOLVE", }; static inline const char *rtn_type(char *buf, size_t len, unsigned int t) { if (t < __RTN_MAX && rtn_type_names[t]) return rtn_type_names[t]; snprintf(buf, len, "type %u", t); return buf; } /* Pretty print the trie */ static int fib_trie_seq_show(struct seq_file *seq, void *v) { const struct fib_trie_iter *iter = seq->private; struct key_vector *n = v; if (IS_TRIE(node_parent_rcu(n))) fib_table_print(seq, iter->tb); if (IS_TNODE(n)) { __be32 prf = htonl(n->key); seq_indent(seq, iter->depth-1); seq_printf(seq, " +-- %pI4/%zu %u %u %u\n", &prf, KEYLENGTH - n->pos - n->bits, n->bits, tn_info(n)->full_children, tn_info(n)->empty_children); } else { __be32 val = htonl(n->key); struct fib_alias *fa; seq_indent(seq, iter->depth); seq_printf(seq, " |-- %pI4\n", &val); hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { char buf1[32], buf2[32]; seq_indent(seq, iter->depth + 1); seq_printf(seq, " /%zu %s %s", KEYLENGTH - fa->fa_slen, rtn_scope(buf1, sizeof(buf1), fa->fa_info->fib_scope), rtn_type(buf2, sizeof(buf2), fa->fa_type)); if (fa->fa_tos) seq_printf(seq, " tos=%d", fa->fa_tos); seq_putc(seq, '\n'); } } return 0; } static const struct seq_operations fib_trie_seq_ops = { .start = fib_trie_seq_start, .next = fib_trie_seq_next, .stop = fib_trie_seq_stop, .show = fib_trie_seq_show, }; struct fib_route_iter { struct seq_net_private p; struct fib_table *main_tb; struct key_vector *tnode; loff_t pos; t_key key; }; static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos) { struct key_vector *l, **tp = &iter->tnode; t_key key; /* use cached location of previously found key */ if (iter->pos > 0 && pos >= iter->pos) { key = iter->key; } else { iter->pos = 1; key = 0; } pos -= iter->pos; while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) { key = l->key + 1; iter->pos++; l = NULL; /* handle unlikely case of a key wrap */ if (!key) break; } if (l) iter->key = l->key; /* remember it */ else iter->pos = 0; /* forget it */ return l; } static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct fib_route_iter *iter = seq->private; struct fib_table *tb; struct trie *t; rcu_read_lock(); tb = fib_get_table(seq_file_net(seq), RT_TABLE_MAIN); if (!tb) return NULL; iter->main_tb = tb; t = (struct trie *)tb->tb_data; iter->tnode = t->kv; if (*pos != 0) return fib_route_get_idx(iter, *pos); iter->pos = 0; iter->key = KEY_MAX; return SEQ_START_TOKEN; } static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_route_iter *iter = seq->private; struct key_vector *l = NULL; t_key key = iter->key + 1; ++*pos; /* only allow key of 0 for start of sequence */ if ((v == SEQ_START_TOKEN) || key) l = leaf_walk_rcu(&iter->tnode, key); if (l) { iter->key = l->key; iter->pos++; } else { iter->pos = 0; } return l; } static void fib_route_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static unsigned int fib_flag_trans(int type, __be32 mask, struct fib_info *fi) { unsigned int flags = 0; if (type == RTN_UNREACHABLE || type == RTN_PROHIBIT) flags = RTF_REJECT; if (fi) { const struct fib_nh_common *nhc = fib_info_nhc(fi, 0); if (nhc->nhc_gw.ipv4) flags |= RTF_GATEWAY; } if (mask == htonl(0xFFFFFFFF)) flags |= RTF_HOST; flags |= RTF_UP; return flags; } /* * This outputs /proc/net/route. * The format of the file is not supposed to be changed * and needs to be same as fib_hash output to avoid breaking * legacy utilities */ static int fib_route_seq_show(struct seq_file *seq, void *v) { struct fib_route_iter *iter = seq->private; struct fib_table *tb = iter->main_tb; struct fib_alias *fa; struct key_vector *l = v; __be32 prefix; if (v == SEQ_START_TOKEN) { seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway " "\tFlags\tRefCnt\tUse\tMetric\tMask\t\tMTU" "\tWindow\tIRTT"); return 0; } prefix = htonl(l->key); hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; __be32 mask = inet_make_mask(KEYLENGTH - fa->fa_slen); unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi); if ((fa->fa_type == RTN_BROADCAST) || (fa->fa_type == RTN_MULTICAST)) continue; if (fa->tb_id != tb->tb_id) continue; seq_setwidth(seq, 127); if (fi) { struct fib_nh_common *nhc = fib_info_nhc(fi, 0); __be32 gw = 0; if (nhc->nhc_gw_family == AF_INET) gw = nhc->nhc_gw.ipv4; seq_printf(seq, "%s\t%08X\t%08X\t%04X\t%d\t%u\t" "%d\t%08X\t%d\t%u\t%u", nhc->nhc_dev ? nhc->nhc_dev->name : "*", prefix, gw, flags, 0, 0, fi->fib_priority, mask, (fi->fib_advmss ? fi->fib_advmss + 40 : 0), fi->fib_window, fi->fib_rtt >> 3); } else { seq_printf(seq, "*\t%08X\t%08X\t%04X\t%d\t%u\t" "%d\t%08X\t%d\t%u\t%u", prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0); } seq_pad(seq, '\n'); } return 0; } static const struct seq_operations fib_route_seq_ops = { .start = fib_route_seq_start, .next = fib_route_seq_next, .stop = fib_route_seq_stop, .show = fib_route_seq_show, }; int __net_init fib_proc_init(struct net *net) { if (!proc_create_net("fib_trie", 0444, net->proc_net, &fib_trie_seq_ops, sizeof(struct fib_trie_iter))) goto out1; if (!proc_create_net_single("fib_triestat", 0444, net->proc_net, fib_triestat_seq_show, NULL)) goto out2; if (!proc_create_net("route", 0444, net->proc_net, &fib_route_seq_ops, sizeof(struct fib_route_iter))) goto out3; return 0; out3: remove_proc_entry("fib_triestat", net->proc_net); out2: remove_proc_entry("fib_trie", net->proc_net); out1: return -ENOMEM; } void __net_exit fib_proc_exit(struct net *net) { remove_proc_entry("fib_trie", net->proc_net); remove_proc_entry("fib_triestat", net->proc_net); remove_proc_entry("route", net->proc_net); } #endif /* CONFIG_PROC_FS */
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 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * 25-Jul-1998 Major changes to allow for ip chain table * * 3-Jan-2000 Named tables to allow packet selection for different uses. */ /* * Format of an IP6 firewall descriptor * * src, dst, src_mask, dst_mask are always stored in network byte order. * flags are stored in host byte order (of course). * Port numbers are stored in HOST byte order. */ #ifndef _UAPI_IP6_TABLES_H #define _UAPI_IP6_TABLES_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/if.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter/x_tables.h> #ifndef __KERNEL__ #define IP6T_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN #define IP6T_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN #define ip6t_match xt_match #define ip6t_target xt_target #define ip6t_table xt_table #define ip6t_get_revision xt_get_revision #define ip6t_entry_match xt_entry_match #define ip6t_entry_target xt_entry_target #define ip6t_standard_target xt_standard_target #define ip6t_error_target xt_error_target #define ip6t_counters xt_counters #define IP6T_CONTINUE XT_CONTINUE #define IP6T_RETURN XT_RETURN /* Pre-iptables-1.4.0 */ #include <linux/netfilter/xt_tcpudp.h> #define ip6t_tcp xt_tcp #define ip6t_udp xt_udp #define IP6T_TCP_INV_SRCPT XT_TCP_INV_SRCPT #define IP6T_TCP_INV_DSTPT XT_TCP_INV_DSTPT #define IP6T_TCP_INV_FLAGS XT_TCP_INV_FLAGS #define IP6T_TCP_INV_OPTION XT_TCP_INV_OPTION #define IP6T_TCP_INV_MASK XT_TCP_INV_MASK #define IP6T_UDP_INV_SRCPT XT_UDP_INV_SRCPT #define IP6T_UDP_INV_DSTPT XT_UDP_INV_DSTPT #define IP6T_UDP_INV_MASK XT_UDP_INV_MASK #define ip6t_counters_info xt_counters_info #define IP6T_STANDARD_TARGET XT_STANDARD_TARGET #define IP6T_ERROR_TARGET XT_ERROR_TARGET #define IP6T_MATCH_ITERATE(e, fn, args...) \ XT_MATCH_ITERATE(struct ip6t_entry, e, fn, ## args) #define IP6T_ENTRY_ITERATE(entries, size, fn, args...) \ XT_ENTRY_ITERATE(struct ip6t_entry, entries, size, fn, ## args) #endif /* Yes, Virginia, you have to zero the padding. */ struct ip6t_ip6 { /* Source and destination IP6 addr */ struct in6_addr src, dst; /* Mask for src and dest IP6 addr */ struct in6_addr smsk, dmsk; char iniface[IFNAMSIZ], outiface[IFNAMSIZ]; unsigned char iniface_mask[IFNAMSIZ], outiface_mask[IFNAMSIZ]; /* Upper protocol number * - The allowed value is 0 (any) or protocol number of last parsable * header, which is 50 (ESP), 59 (No Next Header), 135 (MH), or * the non IPv6 extension headers. * - The protocol numbers of IPv6 extension headers except of ESP and * MH do not match any packets. * - You also need to set IP6T_FLAGS_PROTO to "flags" to check protocol. */ __u16 proto; /* TOS to match iff flags & IP6T_F_TOS */ __u8 tos; /* Flags word */ __u8 flags; /* Inverse flags */ __u8 invflags; }; /* Values for "flag" field in struct ip6t_ip6 (general ip6 structure). */ #define IP6T_F_PROTO 0x01 /* Set if rule cares about upper protocols */ #define IP6T_F_TOS 0x02 /* Match the TOS. */ #define IP6T_F_GOTO 0x04 /* Set if jump is a goto */ #define IP6T_F_MASK 0x07 /* All possible flag bits mask. */ /* Values for "inv" field in struct ip6t_ip6. */ #define IP6T_INV_VIA_IN 0x01 /* Invert the sense of IN IFACE. */ #define IP6T_INV_VIA_OUT 0x02 /* Invert the sense of OUT IFACE */ #define IP6T_INV_TOS 0x04 /* Invert the sense of TOS. */ #define IP6T_INV_SRCIP 0x08 /* Invert the sense of SRC IP. */ #define IP6T_INV_DSTIP 0x10 /* Invert the sense of DST OP. */ #define IP6T_INV_FRAG 0x20 /* Invert the sense of FRAG. */ #define IP6T_INV_PROTO XT_INV_PROTO #define IP6T_INV_MASK 0x7F /* All possible flag bits mask. */ /* This structure defines each of the firewall rules. Consists of 3 parts which are 1) general IP header stuff 2) match specific stuff 3) the target to perform if the rule matches */ struct ip6t_entry { struct ip6t_ip6 ipv6; /* Mark with fields that we care about. */ unsigned int nfcache; /* Size of ipt_entry + matches */ __u16 target_offset; /* Size of ipt_entry + matches + target */ __u16 next_offset; /* Back pointer */ unsigned int comefrom; /* Packet and byte counters. */ struct xt_counters counters; /* The matches (if any), then the target. */ unsigned char elems[0]; }; /* Standard entry */ struct ip6t_standard { struct ip6t_entry entry; struct xt_standard_target target; }; struct ip6t_error { struct ip6t_entry entry; struct xt_error_target target; }; #define IP6T_ENTRY_INIT(__size) \ { \ .target_offset = sizeof(struct ip6t_entry), \ .next_offset = (__size), \ } #define IP6T_STANDARD_INIT(__verdict) \ { \ .entry = IP6T_ENTRY_INIT(sizeof(struct ip6t_standard)), \ .target = XT_TARGET_INIT(XT_STANDARD_TARGET, \ sizeof(struct xt_standard_target)), \ .target.verdict = -(__verdict) - 1, \ } #define IP6T_ERROR_INIT \ { \ .entry = IP6T_ENTRY_INIT(sizeof(struct ip6t_error)), \ .target = XT_TARGET_INIT(XT_ERROR_TARGET, \ sizeof(struct xt_error_target)), \ .target.errorname = "ERROR", \ } /* * New IP firewall options for [gs]etsockopt at the RAW IP level. * Unlike BSD Linux inherits IP options so you don't have to use * a raw socket for this. Instead we check rights in the calls. * * ATTENTION: check linux/in6.h before adding new number here. */ #define IP6T_BASE_CTL 64 #define IP6T_SO_SET_REPLACE (IP6T_BASE_CTL) #define IP6T_SO_SET_ADD_COUNTERS (IP6T_BASE_CTL + 1) #define IP6T_SO_SET_MAX IP6T_SO_SET_ADD_COUNTERS #define IP6T_SO_GET_INFO (IP6T_BASE_CTL) #define IP6T_SO_GET_ENTRIES (IP6T_BASE_CTL + 1) #define IP6T_SO_GET_REVISION_MATCH (IP6T_BASE_CTL + 4) #define IP6T_SO_GET_REVISION_TARGET (IP6T_BASE_CTL + 5) #define IP6T_SO_GET_MAX IP6T_SO_GET_REVISION_TARGET /* obtain original address if REDIRECT'd connection */ #define IP6T_SO_ORIGINAL_DST 80 /* ICMP matching stuff */ struct ip6t_icmp { __u8 type; /* type to match */ __u8 code[2]; /* range of code */ __u8 invflags; /* Inverse flags */ }; /* Values for "inv" field for struct ipt_icmp. */ #define IP6T_ICMP_INV 0x01 /* Invert the sense of type/code test */ /* The argument to IP6T_SO_GET_INFO */ struct ip6t_getinfo { /* Which table: caller fills this in. */ char name[XT_TABLE_MAXNAMELEN]; /* Kernel fills these in. */ /* Which hook entry points are valid: bitmask */ unsigned int valid_hooks; /* Hook entry points: one per netfilter hook. */ unsigned int hook_entry[NF_INET_NUMHOOKS]; /* Underflow points. */ unsigned int underflow[NF_INET_NUMHOOKS]; /* Number of entries */ unsigned int num_entries; /* Size of entries. */ unsigned int size; }; /* The argument to IP6T_SO_SET_REPLACE. */ struct ip6t_replace { /* Which table. */ char name[XT_TABLE_MAXNAMELEN]; /* Which hook entry points are valid: bitmask. You can't change this. */ unsigned int valid_hooks; /* Number of entries */ unsigned int num_entries; /* Total size of new entries */ unsigned int size; /* Hook entry points. */ unsigned int hook_entry[NF_INET_NUMHOOKS]; /* Underflow points. */ unsigned int underflow[NF_INET_NUMHOOKS]; /* Information about old entries: */ /* Number of counters (must be equal to current number of entries). */ unsigned int num_counters; /* The old entries' counters. */ struct xt_counters __user *counters; /* The entries (hang off end: not really an array). */ struct ip6t_entry entries[0]; }; /* The argument to IP6T_SO_GET_ENTRIES. */ struct ip6t_get_entries { /* Which table: user fills this in. */ char name[XT_TABLE_MAXNAMELEN]; /* User fills this in: total entry size. */ unsigned int size; /* The entries. */ struct ip6t_entry entrytable[0]; }; /* Helper functions */ static __inline__ struct xt_entry_target * ip6t_get_target(struct ip6t_entry *e) { return (struct xt_entry_target *)((char *)e + e->target_offset); } /* * Main firewall chains definitions and global var's definitions. */ #endif /* _UAPI_IP6_TABLES_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H #define ARCH_DEFAULT_PKEY 0 /* * If more than 16 keys are ever supported, a thorough audit * will be necessary to ensure that the types that store key * numbers and masks have sufficient capacity. */ #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); static inline bool arch_pkeys_enabled(void) { return boot_cpu_has(X86_FEATURE_OSPKE); } /* * Try to dedicate one of the protection keys to be used as an * execute-only protection key. */ extern int __execute_only_pkey(struct mm_struct *mm); static inline int execute_only_pkey(struct mm_struct *mm) { if (!boot_cpu_has(X86_FEATURE_OSPKE)) return ARCH_DEFAULT_PKEY; return __execute_only_pkey(mm); } extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey); static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey) { if (!boot_cpu_has(X86_FEATURE_OSPKE)) return 0; return __arch_override_mprotect_pkey(vma, prot, pkey); } extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3) #define mm_pkey_allocation_map(mm) (mm->context.pkey_allocation_map) #define mm_set_pkey_allocated(mm, pkey) do { \ mm_pkey_allocation_map(mm) |= (1U << pkey); \ } while (0) #define mm_set_pkey_free(mm, pkey) do { \ mm_pkey_allocation_map(mm) &= ~(1U << pkey); \ } while (0) static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { /* * "Allocated" pkeys are those that have been returned * from pkey_alloc() or pkey 0 which is allocated * implicitly when the mm is created. */ if (pkey < 0) return false; if (pkey >= arch_max_pkey()) return false; /* * The exec-only pkey is set in the allocation map, but * is not available to any of the user interfaces like * mprotect_pkey(). */ if (pkey == mm->context.execute_only_pkey) return false; return mm_pkey_allocation_map(mm) & (1U << pkey); } /* * Returns a positive, 4-bit key on success, or -1 on failure. */ static inline int mm_pkey_alloc(struct mm_struct *mm) { /* * Note: this is the one and only place we make sure * that the pkey is valid as far as the hardware is * concerned. The rest of the kernel trusts that * only good, valid pkeys come out of here. */ u16 all_pkeys_mask = ((1U << arch_max_pkey()) - 1); int ret; /* * Are we out of pkeys? We must handle this specially * because ffz() behavior is undefined if there are no * zeros. */ if (mm_pkey_allocation_map(mm) == all_pkeys_mask) return -1; ret = ffz(mm_pkey_allocation_map(mm)); mm_set_pkey_allocated(mm, ret); return ret; } static inline int mm_pkey_free(struct mm_struct *mm, int pkey) { if (!mm_pkey_is_allocated(mm, pkey)) return -EINVAL; mm_set_pkey_free(mm, pkey); return 0; } extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); extern void copy_init_pkru_to_fpregs(void); static inline int vma_pkey(struct vm_area_struct *vma) { unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3; return (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT; } #endif /*_ASM_X86_PKEYS_H */
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_IP_TUNNELS_H #define __NET_IP_TUNNELS_H 1 #include <linux/if_tunnel.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/types.h> #include <linux/u64_stats_sync.h> #include <linux/bitops.h> #include <net/dsfield.h> #include <net/gro_cells.h> #include <net/inet_ecn.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/lwtunnel.h> #include <net/dst_cache.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #endif /* Keep error state on tunnel for 30 sec */ #define IPTUNNEL_ERR_TIMEO (30*HZ) /* Used to memset ip_tunnel padding. */ #define IP_TUNNEL_KEY_SIZE offsetofend(struct ip_tunnel_key, tp_dst) /* Used to memset ipv4 address padding. */ #define IP_TUNNEL_KEY_IPV4_PAD offsetofend(struct ip_tunnel_key, u.ipv4.dst) #define IP_TUNNEL_KEY_IPV4_PAD_LEN \ (sizeof_field(struct ip_tunnel_key, u) - \ sizeof_field(struct ip_tunnel_key, u.ipv4)) struct ip_tunnel_key { __be64 tun_id; union { struct { __be32 src; __be32 dst; } ipv4; struct { struct in6_addr src; struct in6_addr dst; } ipv6; } u; __be16 tun_flags; u8 tos; /* TOS for IPv4, TC for IPv6 */ u8 ttl; /* TTL for IPv4, HL for IPv6 */ __be32 label; /* Flow Label for IPv6 */ __be16 tp_src; __be16 tp_dst; }; /* Flags for ip_tunnel_info mode. */ #define IP_TUNNEL_INFO_TX 0x01 /* represents tx tunnel parameters */ #define IP_TUNNEL_INFO_IPV6 0x02 /* key contains IPv6 addresses */ #define IP_TUNNEL_INFO_BRIDGE 0x04 /* represents a bridged tunnel id */ /* Maximum tunnel options length. */ #define IP_TUNNEL_OPTS_MAX \ GENMASK((sizeof_field(struct ip_tunnel_info, \ options_len) * BITS_PER_BYTE) - 1, 0) struct ip_tunnel_info { struct ip_tunnel_key key; #ifdef CONFIG_DST_CACHE struct dst_cache dst_cache; #endif u8 options_len; u8 mode; }; /* 6rd prefix/relay information */ #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd_parm { struct in6_addr prefix; __be32 relay_prefix; u16 prefixlen; u16 relay_prefixlen; }; #endif struct ip_tunnel_encap { u16 type; u16 flags; __be16 sport; __be16 dport; }; struct ip_tunnel_prl_entry { struct ip_tunnel_prl_entry __rcu *next; __be32 addr; u16 flags; struct rcu_head rcu_head; }; struct metadata_dst; struct ip_tunnel { struct ip_tunnel __rcu *next; struct hlist_node hash_node; struct net_device *dev; struct net *net; /* netns for packet i/o */ unsigned long err_time; /* Time when the last ICMP error * arrived */ int err_count; /* Number of arrived ICMP errors */ /* These four fields used only by GRE */ u32 i_seqno; /* The last seen seqno */ u32 o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ /* These four fields used only by ERSPAN */ u32 index; /* ERSPAN type II index */ u8 erspan_ver; /* ERSPAN version */ u8 dir; /* ERSPAN direction */ u16 hwid; /* ERSPAN hardware ID */ struct dst_cache dst_cache; struct ip_tunnel_parm parms; int mlink; int encap_hlen; /* Encap header length (FOU,GUE) */ int hlen; /* tun_hlen + encap_hlen */ struct ip_tunnel_encap encap; /* for SIT */ #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd_parm ip6rd; #endif struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */ unsigned int prl_count; /* # of entries in PRL */ unsigned int ip_tnl_net_id; struct gro_cells gro_cells; __u32 fwmark; bool collect_md; bool ignore_df; }; struct tnl_ptk_info { __be16 flags; __be16 proto; __be32 key; __be32 seq; int hdr_len; }; #define PACKET_RCVD 0 #define PACKET_REJECT 1 #define PACKET_NEXT 2 #define IP_TNL_HASH_BITS 7 #define IP_TNL_HASH_SIZE (1 << IP_TNL_HASH_BITS) struct ip_tunnel_net { struct net_device *fb_tunnel_dev; struct rtnl_link_ops *rtnl_link_ops; struct hlist_head tunnels[IP_TNL_HASH_SIZE]; struct ip_tunnel __rcu *collect_md_tun; int type; }; static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, __be32 saddr, __be32 daddr, u8 tos, u8 ttl, __be32 label, __be16 tp_src, __be16 tp_dst, __be64 tun_id, __be16 tun_flags) { key->tun_id = tun_id; key->u.ipv4.src = saddr; key->u.ipv4.dst = daddr; memset((unsigned char *)key + IP_TUNNEL_KEY_IPV4_PAD, 0, IP_TUNNEL_KEY_IPV4_PAD_LEN); key->tos = tos; key->ttl = ttl; key->label = label; key->tun_flags = tun_flags; /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of * the upper tunnel are used. * E.g: GRE over IPSEC, the tp_src and tp_port are zero. */ key->tp_src = tp_src; key->tp_dst = tp_dst; /* Clear struct padding. */ if (sizeof(*key) != IP_TUNNEL_KEY_SIZE) memset((unsigned char *)key + IP_TUNNEL_KEY_SIZE, 0, sizeof(*key) - IP_TUNNEL_KEY_SIZE); } static inline bool ip_tunnel_dst_cache_usable(const struct sk_buff *skb, const struct ip_tunnel_info *info) { if (skb->mark) return false; if (!info) return true; if (info->key.tun_flags & TUNNEL_NOCACHE) return false; return true; } static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info *tun_info) { return tun_info->mode & IP_TUNNEL_INFO_IPV6 ? AF_INET6 : AF_INET; } static inline __be64 key32_to_tunnel_id(__be32 key) { #ifdef __BIG_ENDIAN return (__force __be64)key; #else return (__force __be64)((__force u64)key << 32); #endif } /* Returns the least-significant 32 bits of a __be64. */ static inline __be32 tunnel_id_to_key32(__be64 tun_id) { #ifdef __BIG_ENDIAN return (__force __be32)tun_id; #else return (__force __be32)((__force u64)tun_id >> 32); #endif } #ifdef CONFIG_INET static inline void ip_tunnel_init_flow(struct flowi4 *fl4, int proto, __be32 daddr, __be32 saddr, __be32 key, __u8 tos, int oif, __u32 mark, __u32 tun_inner_hash) { memset(fl4, 0, sizeof(*fl4)); fl4->flowi4_oif = oif; fl4->daddr = daddr; fl4->saddr = saddr; fl4->flowi4_tos = tos; fl4->flowi4_proto = proto; fl4->fl4_gre_key = key; fl4->flowi4_mark = mark; fl4->flowi4_multipath_hash = tun_inner_hash; } int ip_tunnel_init(struct net_device *dev); void ip_tunnel_uninit(struct net_device *dev); void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); struct net *ip_tunnel_get_link_net(const struct net_device *dev); int ip_tunnel_get_iflink(const struct net_device *dev); int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname); void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id, struct rtnl_link_ops *ops); void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol); void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const u8 proto, int tunnel_hlen); int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); int ip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); void ip_tunnel_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot); struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, int link, __be16 flags, __be32 remote, __be32 local, __be32 key); int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark); void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); extern const struct header_ops ip_tunnel_header_ops; __be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); struct ip_tunnel_encap_ops { size_t (*encap_hlen)(struct ip_tunnel_encap *e); int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4); int (*err_handler)(struct sk_buff *skb, u32 info); }; #define MAX_IPTUN_ENCAP_OPS 8 extern const struct ip_tunnel_encap_ops __rcu * iptun_encaps[MAX_IPTUN_ENCAP_OPS]; int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op, unsigned int num); int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, unsigned int num); int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap); static inline bool pskb_inet_may_pull(struct sk_buff *skb) { int nhlen; switch (skb->protocol) { #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): nhlen = sizeof(struct ipv6hdr); break; #endif case htons(ETH_P_IP): nhlen = sizeof(struct iphdr); break; default: nhlen = 0; } return pskb_network_may_pull(skb, nhlen); } static inline int ip_encap_hlen(struct ip_tunnel_encap *e) { const struct ip_tunnel_encap_ops *ops; int hlen = -EINVAL; if (e->type == TUNNEL_ENCAP_NONE) return 0; if (e->type >= MAX_IPTUN_ENCAP_OPS) return -EINVAL; rcu_read_lock(); ops = rcu_dereference(iptun_encaps[e->type]); if (likely(ops && ops->encap_hlen)) hlen = ops->encap_hlen(e); rcu_read_unlock(); return hlen; } static inline int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t, u8 *protocol, struct flowi4 *fl4) { const struct ip_tunnel_encap_ops *ops; int ret = -EINVAL; if (t->encap.type == TUNNEL_ENCAP_NONE) return 0; if (t->encap.type >= MAX_IPTUN_ENCAP_OPS) return -EINVAL; rcu_read_lock(); ops = rcu_dereference(iptun_encaps[t->encap.type]); if (likely(ops && ops->build_header)) ret = ops->build_header(skb, &t->encap, protocol, fl4); rcu_read_unlock(); return ret; } /* Extract dsfield from inner protocol */ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, const struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) return iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) return ipv6_get_dsfield((const struct ipv6hdr *)iph); else return 0; } static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, const struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) return iph->ttl; else if (skb->protocol == htons(ETH_P_IPV6)) return ((const struct ipv6hdr *)iph)->hop_limit; else return 0; } /* Propogate ECN bits out */ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, const struct sk_buff *skb) { u8 inner = ip_tunnel_get_dsfield(iph, skb); return INET_ECN_encapsulate(tos, inner); } int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, bool raw_proto, bool xnet); static inline int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, bool xnet) { return __iptunnel_pull_header(skb, hdr_len, inner_proto, false, xnet); } void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, u8 proto, u8 tos, u8 ttl, __be16 df, bool xnet); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags); int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, int headroom, bool reply); int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask); static inline int iptunnel_pull_offloads(struct sk_buff *skb) { if (skb_is_gso(skb)) { int err; err = skb_unclone(skb, GFP_ATOMIC); if (unlikely(err)) return err; skb_shinfo(skb)->gso_type &= ~(NETIF_F_GSO_ENCAP_ALL >> NETIF_F_GSO_SHIFT); } skb->encapsulation = 0; return 0; } static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) { if (pkt_len > 0) { struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += pkt_len; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); put_cpu_ptr(tstats); } else { struct net_device_stats *err_stats = &dev->stats; if (pkt_len < 0) { err_stats->tx_errors++; err_stats->tx_aborted_errors++; } else { err_stats->tx_dropped++; } } } static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info) { return info + 1; } static inline void ip_tunnel_info_opts_get(void *to, const struct ip_tunnel_info *info) { memcpy(to, info + 1, info->options_len); } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, __be16 flags) { info->options_len = len; if (len > 0) { memcpy(ip_tunnel_info_opts(info), from, len); info->key.tun_flags |= flags; } } static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) { return (struct ip_tunnel_info *)lwtstate->data; } DECLARE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt); /* Returns > 0 if metadata should be collected */ static inline int ip_tunnel_collect_metadata(void) { return static_branch_unlikely(&ip_tunnel_metadata_cnt); } void __init ip_tunnel_core_init(void); void ip_tunnel_need_metadata(void); void ip_tunnel_unneed_metadata(void); #else /* CONFIG_INET */ static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) { return NULL; } static inline void ip_tunnel_need_metadata(void) { } static inline void ip_tunnel_unneed_metadata(void) { } static inline void ip_tunnel_info_opts_get(void *to, const struct ip_tunnel_info *info) { } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, __be16 flags) { info->options_len = 0; } #endif /* CONFIG_INET */ #endif /* __NET_IP_TUNNELS_H */
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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Descending-priority-sorted double-linked list * * (C) 2002-2003 Intel Corp * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>. * * 2001-2005 (c) MontaVista Software, Inc. * Daniel Walker <dwalker@mvista.com> * * (C) 2005 Thomas Gleixner <tglx@linutronix.de> * * Simplifications of the original code by * Oleg Nesterov <oleg@tv-sign.ru> * * Based on simple lists (include/linux/list.h). * * This is a priority-sorted list of nodes; each node has a * priority from INT_MIN (highest) to INT_MAX (lowest). * * Addition is O(K), removal is O(1), change of priority of a node is * O(K) and K is the number of RT priority levels used in the system. * (1 <= K <= 99) * * This list is really a list of lists: * * - The tier 1 list is the prio_list, different priority nodes. * * - The tier 2 list is the node_list, serialized nodes. * * Simple ASCII art explanation: * * pl:prio_list (only for plist_node) * nl:node_list * HEAD| NODE(S) * | * ||------------------------------------| * ||->|pl|<->|pl|<--------------->|pl|<-| * | |10| |21| |21| |21| |40| (prio) * | | | | | | | | | | | * | | | | | | | | | | | * |->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-| * |-------------------------------------------| * * The nodes on the prio_list list are sorted by priority to simplify * the insertion of new nodes. There are no nodes with duplicate * priorites on the list. * * The nodes on the node_list are ordered by priority and can contain * entries which have the same priority. Those entries are ordered * FIFO * * Addition means: look for the prio_list node in the prio_list * for the priority of the node and insert it before the node_list * entry of the next prio_list node. If it is the first node of * that priority, add it to the prio_list in the right position and * insert it into the serialized node_list list * * Removal means remove it from the node_list and remove it from * the prio_list if the node_list list_head is non empty. In case * of removal from the prio_list it must be checked whether other * entries of the same priority are on the list or not. If there * is another entry of the same priority then this entry has to * replace the removed entry on the prio_list. If the entry which * is removed is the only entry of this priority then a simple * remove from both list is sufficient. * * INT_MIN is the highest priority, 0 is the medium highest, INT_MAX * is lowest priority. * * No locking is done, up to the caller. */ #ifndef _LINUX_PLIST_H_ #define _LINUX_PLIST_H_ #include <linux/kernel.h> #include <linux/list.h> struct plist_head { struct list_head node_list; }; struct plist_node { int prio; struct list_head prio_list; struct list_head node_list; }; /** * PLIST_HEAD_INIT - static struct plist_head initializer * @head: struct plist_head variable name */ #define PLIST_HEAD_INIT(head) \ { \ .node_list = LIST_HEAD_INIT((head).node_list) \ } /** * PLIST_HEAD - declare and init plist_head * @head: name for struct plist_head variable */ #define PLIST_HEAD(head) \ struct plist_head head = PLIST_HEAD_INIT(head) /** * PLIST_NODE_INIT - static struct plist_node initializer * @node: struct plist_node variable name * @__prio: initial node priority */ #define PLIST_NODE_INIT(node, __prio) \ { \ .prio = (__prio), \ .prio_list = LIST_HEAD_INIT((node).prio_list), \ .node_list = LIST_HEAD_INIT((node).node_list), \ } /** * plist_head_init - dynamic struct plist_head initializer * @head: &struct plist_head pointer */ static inline void plist_head_init(struct plist_head *head) { INIT_LIST_HEAD(&head->node_list); } /** * plist_node_init - Dynamic struct plist_node initializer * @node: &struct plist_node pointer * @prio: initial node priority */ static inline void plist_node_init(struct plist_node *node, int prio) { node->prio = prio; INIT_LIST_HEAD(&node->prio_list); INIT_LIST_HEAD(&node->node_list); } extern void plist_add(struct plist_node *node, struct plist_head *head); extern void plist_del(struct plist_node *node, struct plist_head *head); extern void plist_requeue(struct plist_node *node, struct plist_head *head); /** * plist_for_each - iterate over the plist * @pos: the type * to use as a loop counter * @head: the head for your list */ #define plist_for_each(pos, head) \ list_for_each_entry(pos, &(head)->node_list, node_list) /** * plist_for_each_continue - continue iteration over the plist * @pos: the type * to use as a loop cursor * @head: the head for your list * * Continue to iterate over plist, continuing after the current position. */ #define plist_for_each_continue(pos, head) \ list_for_each_entry_continue(pos, &(head)->node_list, node_list) /** * plist_for_each_safe - iterate safely over a plist of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage * @head: the head for your list * * Iterate over a plist of given type, safe against removal of list entry. */ #define plist_for_each_safe(pos, n, head) \ list_for_each_entry_safe(pos, n, &(head)->node_list, node_list) /** * plist_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop counter * @head: the head for your list * @mem: the name of the list_head within the struct */ #define plist_for_each_entry(pos, head, mem) \ list_for_each_entry(pos, &(head)->node_list, mem.node_list) /** * plist_for_each_entry_continue - continue iteration over list of given type * @pos: the type * to use as a loop cursor * @head: the head for your list * @m: the name of the list_head within the struct * * Continue to iterate over list of given type, continuing after * the current position. */ #define plist_for_each_entry_continue(pos, head, m) \ list_for_each_entry_continue(pos, &(head)->node_list, m.node_list) /** * plist_for_each_entry_safe - iterate safely over list of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage * @head: the head for your list * @m: the name of the list_head within the struct * * Iterate over list of given type, safe against removal of list entry. */ #define plist_for_each_entry_safe(pos, n, head, m) \ list_for_each_entry_safe(pos, n, &(head)->node_list, m.node_list) /** * plist_head_empty - return !0 if a plist_head is empty * @head: &struct plist_head pointer */ static inline int plist_head_empty(const struct plist_head *head) { return list_empty(&head->node_list); } /** * plist_node_empty - return !0 if plist_node is not on a list * @node: &struct plist_node pointer */ static inline int plist_node_empty(const struct plist_node *node) { return list_empty(&node->node_list); } /* All functions below assume the plist_head is not empty. */ /** * plist_first_entry - get the struct for the first entry * @head: the &struct plist_head pointer * @type: the type of the struct this is embedded in * @member: the name of the list_head within the struct */ #ifdef CONFIG_DEBUG_PLIST # define plist_first_entry(head, type, member) \ ({ \ WARN_ON(plist_head_empty(head)); \ container_of(plist_first(head), type, member); \ }) #else # define plist_first_entry(head, type, member) \ container_of(plist_first(head), type, member) #endif /** * plist_last_entry - get the struct for the last entry * @head: the &struct plist_head pointer * @type: the type of the struct this is embedded in * @member: the name of the list_head within the struct */ #ifdef CONFIG_DEBUG_PLIST # define plist_last_entry(head, type, member) \ ({ \ WARN_ON(plist_head_empty(head)); \ container_of(plist_last(head), type, member); \ }) #else # define plist_last_entry(head, type, member) \ container_of(plist_last(head), type, member) #endif /** * plist_next - get the next entry in list * @pos: the type * to cursor */ #define plist_next(pos) \ list_next_entry(pos, node_list) /** * plist_prev - get the prev entry in list * @pos: the type * to cursor */ #define plist_prev(pos) \ list_prev_entry(pos, node_list) /** * plist_first - return the first node (and thus, highest priority) * @head: the &struct plist_head pointer * * Assumes the plist is _not_ empty. */ static inline struct plist_node *plist_first(const struct plist_head *head) { return list_entry(head->node_list.next, struct plist_node, node_list); } /** * plist_last - return the last node (and thus, lowest priority) * @head: the &struct plist_head pointer * * Assumes the plist is _not_ empty. */ static inline struct plist_node *plist_last(const struct plist_head *head) { return list_entry(head->node_list.prev, struct plist_node, node_list); } #endif
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BLKDEV_H #define _LINUX_BLKDEV_H #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/major.h> #include <linux/genhd.h> #include <linux/list.h> #include <linux/llist.h> #include <linux/minmax.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/pagemap.h> #include <linux/backing-dev-defs.h> #include <linux/wait.h> #include <linux/mempool.h> #include <linux/pfn.h> #include <linux/bio.h> #include <linux/stringify.h> #include <linux/gfp.h> #include <linux/bsg.h> #include <linux/smp.h> #include <linux/rcupdate.h> #include <linux/percpu-refcount.h> #include <linux/scatterlist.h> #include <linux/blkzoned.h> #include <linux/pm.h> struct module; struct scsi_ioctl_command; struct request_queue; struct elevator_queue; struct blk_trace; struct request; struct sg_io_hdr; struct bsg_job; struct blkcg_gq; struct blk_flush_queue; struct pr_ops; struct rq_qos; struct blk_queue_stats; struct blk_stat_callback; struct blk_keyslot_manager; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ /* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 /* Doing classic polling */ #define BLK_MQ_POLL_CLASSIC -1 /* * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ #define BLKCG_MAX_POLS 5 static inline int blk_validate_block_size(unsigned int bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) return -EINVAL; return 0; } typedef void (rq_end_io_fn)(struct request *, blk_status_t); /* * request flags */ typedef __u32 __bitwise req_flags_t; /* elevator knows about this request */ #define RQF_SORTED ((__force req_flags_t)(1 << 0)) /* drive already may have started this one */ #define RQF_STARTED ((__force req_flags_t)(1 << 1)) /* may not be passed by ioscheduler */ #define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) /* request for flush sequence */ #define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) /* merge of different types, fail separately */ #define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5)) /* track inflight for MQ */ #define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) /* don't call prep for this one */ #define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) /* vaguely specified driver internal error. Ignored by the block layer */ #define RQF_FAILED ((__force req_flags_t)(1 << 10)) /* don't warn about errors */ #define RQF_QUIET ((__force req_flags_t)(1 << 11)) /* elevator private data attached */ #define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) /* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) /* request came from our alloc pool */ #define RQF_ALLOCED ((__force req_flags_t)(1 << 14)) /* runtime pm request */ #define RQF_PM ((__force req_flags_t)(1 << 15)) /* on IO scheduler merge hash */ #define RQF_HASHED ((__force req_flags_t)(1 << 16)) /* track IO completion time */ #define RQF_STATS ((__force req_flags_t)(1 << 17)) /* Look at ->special_vec for the actual data payload instead of the bio chain. */ #define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) /* The per-zone write lock is held for this request */ #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) /* already slept for hybrid poll */ #define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) /* * Request state for blk-mq. */ enum mq_rq_state { MQ_RQ_IDLE = 0, MQ_RQ_IN_FLIGHT = 1, MQ_RQ_COMPLETE = 2, }; /* * Try to put the fields that are referenced together in the same cacheline. * * If you modify this structure, make sure to update blk_rq_init() and * especially blk_mq_rq_ctx_init() to take care of the added fields. */ struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; struct blk_mq_hw_ctx *mq_hctx; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; int tag; int internal_tag; /* the following two fields are internal, NEVER access directly */ unsigned int __data_len; /* total data len */ sector_t __sector; /* sector cursor */ struct bio *bio; struct bio *biotail; struct list_head queuelist; /* * The hash is used inside the scheduler, and killed once the * request reaches the dispatch list. The ipi_list is only used * to queue the request for softirq completion, which is long * after the request has been unhashed (and even removed from * the dispatch list). */ union { struct hlist_node hash; /* merge hash */ struct list_head ipi_list; }; /* * The rb_node is only used inside the io scheduler, requests * are pruned when moved to the dispatch queue. So let the * completion_data share space with the rb_node. */ union { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; int error_count; /* for legacy drivers, don't use */ }; /* * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. Flush requests are * never put on the IO scheduler. So let the flush fields share * space with the elevator data. */ union { struct { struct io_cq *icq; void *priv[2]; } elv; struct { unsigned int seq; struct list_head list; rq_end_io_fn *saved_end_io; } flush; }; struct gendisk *rq_disk; struct hd_struct *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ u64 alloc_time_ns; #endif /* Time that this request was allocated for this IO. */ u64 start_time_ns; /* Time that I/O was submitted to the device. */ u64 io_start_time_ns; #ifdef CONFIG_BLK_WBT unsigned short wbt_flags; #endif /* * rq sectors used for blk stats. It has the same value * with blk_rq_sectors(rq), except that it never be zeroed * by completion. */ unsigned short stats_sectors; /* * Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ unsigned short nr_phys_segments; #if defined(CONFIG_BLK_DEV_INTEGRITY) unsigned short nr_integrity_segments; #endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; struct blk_ksm_keyslot *crypt_keyslot; #endif unsigned short write_hint; unsigned short ioprio; enum mq_rq_state state; refcount_t ref; unsigned int timeout; unsigned long deadline; union { struct __call_single_data csd; u64 fifo_time; }; /* * completion callback. */ rq_end_io_fn *end_io; void *end_io_data; }; static inline bool blk_op_is_scsi(unsigned int op) { return op == REQ_OP_SCSI_IN || op == REQ_OP_SCSI_OUT; } static inline bool blk_op_is_private(unsigned int op) { return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; } static inline bool blk_rq_is_scsi(struct request *rq) { return blk_op_is_scsi(req_op(rq)); } static inline bool blk_rq_is_private(struct request *rq) { return blk_op_is_private(req_op(rq)); } static inline bool blk_rq_is_passthrough(struct request *rq) { return blk_rq_is_scsi(rq) || blk_rq_is_private(rq); } static inline bool bio_is_passthrough(struct bio *bio) { unsigned op = bio_op(bio); return blk_op_is_scsi(op) || blk_op_is_private(op); } static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; } #include <linux/elevator.h> struct blk_queue_ctx; struct bio_vec; enum blk_eh_timer_return { BLK_EH_DONE, /* drivers has completed the command */ BLK_EH_RESET_TIMER, /* reset timer and try again */ }; enum blk_queue_state { Queue_down, Queue_up, }; #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ #define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ #define BLK_SCSI_MAX_CMDS (256) #define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) /* * Zoned block device models (zoned limit). * * Note: This needs to be ordered from the least to the most severe * restrictions for the inheritance in blk_stack_limits() to work. */ enum blk_zoned_model { BLK_ZONED_NONE = 0, /* Regular block device */ BLK_ZONED_HA, /* Host-aware zoned block device */ BLK_ZONED_HM, /* Host-managed zoned block device */ }; struct queue_limits { unsigned long bounce_pfn; unsigned long seg_boundary_mask; unsigned long virt_boundary_mask; unsigned int max_hw_sectors; unsigned int max_dev_sectors; unsigned int chunk_sectors; unsigned int max_sectors; unsigned int max_segment_size; unsigned int physical_block_size; unsigned int logical_block_size; unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; unsigned int max_write_same_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; unsigned char misaligned; unsigned char discard_misaligned; unsigned char raid_partial_stripes_expensive; enum blk_zoned_model zoned; }; typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model); #ifdef CONFIG_BLK_DEV_ZONED #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); unsigned int blkdev_nr_zones(struct gendisk *disk); extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); int blk_revalidate_disk_zones(struct gendisk *disk, void (*update_driver_data)(struct gendisk *disk)); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blkdev_nr_zones(struct gendisk *disk) { return 0; } static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { return -ENOTTY; } static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { return -ENOTTY; } #endif /* CONFIG_BLK_DEV_ZONED */ struct request_queue { struct request *last_merge; struct elevator_queue *elevator; struct percpu_ref q_usage_counter; struct blk_queue_stats *stats; struct rq_qos *rq_qos; const struct blk_mq_ops *mq_ops; /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; unsigned int queue_depth; /* hw dispatch queues */ struct blk_mq_hw_ctx **queue_hw_ctx; unsigned int nr_hw_queues; struct backing_dev_info *backing_dev_info; /* * The queue owner gets to use this for whatever they like. * ll_rw_blk doesn't touch it. */ void *queuedata; /* * various queue flags, see QUEUE_* below */ unsigned long queue_flags; /* * Number of contexts that have called blk_set_pm_only(). If this * counter is above zero then only RQF_PM requests are processed. */ atomic_t pm_only; /* * ida allocated id for this queue. Used to index queues from * ioctx. */ int id; /* * queue needs bounce pages for pages above this limit */ gfp_t bounce_gfp; spinlock_t queue_lock; /* * queue kobject */ struct kobject kobj; /* * mq queue kobject */ struct kobject *mq_kobj; #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity integrity; #endif /* CONFIG_BLK_DEV_INTEGRITY */ #ifdef CONFIG_PM struct device *dev; enum rpm_status rpm_status; unsigned int nr_pending; #endif /* * queue settings */ unsigned long nr_requests; /* Max # of requests */ unsigned int dma_pad_mask; unsigned int dma_alignment; #ifdef CONFIG_BLK_INLINE_ENCRYPTION /* Inline crypto capabilities */ struct blk_keyslot_manager *ksm; #endif unsigned int rq_timeout; int poll_nsec; struct blk_stat_callback *poll_cb; struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS]; struct timer_list timeout; struct work_struct timeout_work; atomic_t nr_active_requests_shared_sbitmap; struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); struct blkcg_gq *root_blkg; struct list_head blkg_list; #endif struct queue_limits limits; unsigned int required_elevator_features; #ifdef CONFIG_BLK_DEV_ZONED /* * Zoned block device information for request dispatch control. * nr_zones is the total number of zones of the device. This is always * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones * bits which indicates if a zone is conventional (bit set) or * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones * bits which indicates if a zone is write locked, that is, if a write * request targeting the zone was dispatched. All three fields are * initialized by the low level device driver (e.g. scsi/sd.c). * Stacking drivers (device mappers) may or may not initialize * these fields. * * Reads of this information must be protected with blk_queue_enter() / * blk_queue_exit(). Modifying this information is only allowed while * no requests are being processed. See also blk_mq_freeze_queue() and * blk_mq_unfreeze_queue(). */ unsigned int nr_zones; unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; unsigned int max_open_zones; unsigned int max_active_zones; #endif /* CONFIG_BLK_DEV_ZONED */ /* * sg stuff */ unsigned int sg_timeout; unsigned int sg_reserved_size; int node; struct mutex debugfs_mutex; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; #endif /* * for flush operations */ struct blk_flush_queue *fq; struct list_head requeue_list; spinlock_t requeue_lock; struct delayed_work requeue_work; struct mutex sysfs_lock; struct mutex sysfs_dir_lock; /* * for reusing dead hctx instance in case of updating * nr_hw_queues */ struct list_head unused_hctx_list; spinlock_t unused_hctx_lock; int mq_freeze_depth; #if defined(CONFIG_BLK_DEV_BSG) struct bsg_class_device bsg_dev; #endif #ifdef CONFIG_BLK_DEV_THROTTLING /* Throttle data */ struct throtl_data *td; #endif struct rcu_head rcu_head; wait_queue_head_t mq_freeze_wq; /* * Protect concurrent access to q_usage_counter by * percpu_ref_kill() and percpu_ref_reinit(). */ struct mutex mq_freeze_lock; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; struct bio_set bio_split; struct dentry *debugfs_dir; #ifdef CONFIG_BLK_DEBUG_FS struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; #endif bool mq_sysfs_init_done; size_t cmd_size; #define BLK_MAX_WRITE_HINTS 5 u64 write_hints[BLK_MAX_WRITE_HINTS]; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ #define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ #define QUEUE_FLAG_DYING 1 /* queue being torn down */ #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ #define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ #define QUEUE_FLAG_WC 17 /* Write back caching */ #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ #define QUEUE_FLAG_DAX 19 /* device supports DAX */ #define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ #define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 23 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ #define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ #define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_NOWAIT)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) #define blk_queue_stable_writes(q) \ test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) #define blk_queue_secure_erase(q) \ (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_scsi_passthrough(q) \ test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) #ifdef CONFIG_BLK_RQ_ALLOC_TIME #define blk_queue_rq_alloc_time(q) \ test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags) #else #define blk_queue_rq_alloc_time(q) false #endif #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); static inline bool blk_account_rq(struct request *rq) { return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); } #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) #define dma_map_bvec(dev, bv, dir, attrs) \ dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \ (dir), (attrs)) static inline bool queue_is_mq(struct request_queue *q) { return q->mq_ops; } #ifdef CONFIG_PM static inline enum rpm_status queue_rpm_status(struct request_queue *q) { return q->rpm_status; } #else static inline enum rpm_status queue_rpm_status(struct request_queue *q) { return RPM_ACTIVE; } #endif static inline enum blk_zoned_model blk_queue_zoned_model(struct request_queue *q) { if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) return q->limits.zoned; return BLK_ZONED_NONE; } static inline bool blk_queue_is_zoned(struct request_queue *q) { switch (blk_queue_zoned_model(q)) { case BLK_ZONED_HA: case BLK_ZONED_HM: return true; default: return false; } } static inline sector_t blk_queue_zone_sectors(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } #ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->nr_zones : 0; } static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { if (!blk_queue_is_zoned(q)) return 0; return sector >> ilog2(q->limits.chunk_sectors); } static inline bool blk_queue_zone_is_seq(struct request_queue *q, sector_t sector) { if (!blk_queue_is_zoned(q)) return false; if (!q->conv_zones_bitmap) return true; return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap); } static inline void blk_queue_max_open_zones(struct request_queue *q, unsigned int max_open_zones) { q->max_open_zones = max_open_zones; } static inline unsigned int queue_max_open_zones(const struct request_queue *q) { return q->max_open_zones; } static inline void blk_queue_max_active_zones(struct request_queue *q, unsigned int max_active_zones) { q->max_active_zones = max_active_zones; } static inline unsigned int queue_max_active_zones(const struct request_queue *q) { return q->max_active_zones; } #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { return 0; } static inline bool blk_queue_zone_is_seq(struct request_queue *q, sector_t sector) { return false; } static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { return 0; } static inline unsigned int queue_max_open_zones(const struct request_queue *q) { return 0; } static inline unsigned int queue_max_active_zones(const struct request_queue *q) { return 0; } #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) { return op_is_sync(rq->cmd_flags); } static inline bool rq_mergeable(struct request *rq) { if (blk_rq_is_passthrough(rq)) return false; if (req_op(rq) == REQ_OP_FLUSH) return false; if (req_op(rq) == REQ_OP_WRITE_ZEROES) return false; if (req_op(rq) == REQ_OP_ZONE_APPEND) return false; if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; if (rq->rq_flags & RQF_NOMERGE_FLAGS) return false; return true; } static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) { if (bio_page(a) == bio_page(b) && bio_offset(a) == bio_offset(b)) return true; return false; } static inline unsigned int blk_queue_depth(struct request_queue *q) { if (q->queue_depth) return q->queue_depth; return q->nr_requests; } extern unsigned long blk_max_low_pfn, blk_max_pfn; /* * standard bounce addresses: * * BLK_BOUNCE_HIGH : bounce all highmem pages * BLK_BOUNCE_ANY : don't bounce anything * BLK_BOUNCE_ISA : bounce pages above ISA DMA boundary */ #if BITS_PER_LONG == 32 #define BLK_BOUNCE_HIGH ((u64)blk_max_low_pfn << PAGE_SHIFT) #else #define BLK_BOUNCE_HIGH -1ULL #endif #define BLK_BOUNCE_ANY (-1ULL) #define BLK_BOUNCE_ISA (DMA_BIT_MASK(24)) /* * default timeout for SG_IO if none specified */ #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) #define BLK_MIN_SG_TIMEOUT (7 * HZ) struct rq_map_data { struct page **pages; int page_order; int nr_entries; unsigned long offset; int null_mapped; int from_user; }; struct req_iterator { struct bvec_iter iter; struct bio *bio; }; /* This should not be used directly - use rq_for_each_segment */ #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) #define __rq_for_each_bio(_bio, rq) \ if ((rq->bio)) \ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) #define rq_for_each_segment(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_segment(bvl, _iter.bio, _iter.iter) #define rq_for_each_bvec(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_bvec(bvl, _iter.bio, _iter.iter) #define rq_iter_last(bvec, _iter) \ (_iter.bio->bi_next == NULL && \ bio_iter_last(bvec, _iter.iter)) #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE # error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" #endif #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE extern void rq_flush_dcache_pages(struct request *rq); #else static inline void rq_flush_dcache_pages(struct request *rq) { } #endif extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); blk_qc_t submit_bio_noacct(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern struct request *blk_get_request(struct request_queue *, unsigned int op, blk_mq_req_flags_t flags); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); extern void blk_rq_unprep_clone(struct request *rq); extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern int blk_rq_append_bio(struct request *rq, struct bio **bio); extern void blk_queue_split(struct bio **); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, unsigned int, void __user *); extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, unsigned int, void __user *); extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, struct scsi_ioctl_command __user *); extern int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp); extern int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp); extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); extern int blk_rq_unmap_user(struct bio *); extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); extern int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); extern void blk_execute_rq(struct request_queue *, struct gendisk *, struct request *, int); extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, struct request *, int, rq_end_io_fn *); /* Helper to convert REQ_OP_XXX to its string format XXX */ extern const char *blk_op_str(unsigned int op); int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { return bdev->bd_disk->queue; /* this is never NULL */ } /* * The basic unit of block I/O is a sector. It is used in a number of contexts * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 * bytes. Variables of type sector_t represent an offset or size that is a * multiple of 512 bytes. Hence these two constants. */ #ifndef SECTOR_SHIFT #define SECTOR_SHIFT 9 #endif #ifndef SECTOR_SIZE #define SECTOR_SIZE (1 << SECTOR_SHIFT) #endif /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request * blk_rq_cur_bytes() : bytes left in the current segment * blk_rq_err_bytes() : bytes left till the next error boundary * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment * blk_rq_stats_sectors() : sectors of the entire request used for stats */ static inline sector_t blk_rq_pos(const struct request *rq) { return rq->__sector; } static inline unsigned int blk_rq_bytes(const struct request *rq) { return rq->__data_len; } static inline int blk_rq_cur_bytes(const struct request *rq) { return rq->bio ? bio_cur_bytes(rq->bio) : 0; } extern unsigned int blk_rq_err_bytes(const struct request *rq); static inline unsigned int blk_rq_sectors(const struct request *rq) { return blk_rq_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_cur_sectors(const struct request *rq) { return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_stats_sectors(const struct request *rq) { return rq->stats_sectors; } #ifdef CONFIG_BLK_DEV_ZONED /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond); static inline unsigned int blk_rq_zone_no(struct request *rq) { return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); } static inline unsigned int blk_rq_zone_is_seq(struct request *rq) { return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq)); } #endif /* CONFIG_BLK_DEV_ZONED */ /* * Some commands like WRITE SAME have a payload or data transfer size which * is different from the size of the request. Any driver that supports such * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to * calculate the data transfer size. */ static inline unsigned int blk_rq_payload_bytes(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec.bv_len; return blk_rq_bytes(rq); } /* * Return the first full biovec in the request. The caller needs to check that * there are any bvecs before calling this helper. */ static inline struct bio_vec req_bvec(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec; return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter); } static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) return min(q->limits.max_discard_sectors, UINT_MAX >> SECTOR_SHIFT); if (unlikely(op == REQ_OP_WRITE_SAME)) return q->limits.max_write_same_sectors; if (unlikely(op == REQ_OP_WRITE_ZEROES)) return q->limits.max_write_zeroes_sectors; return q->limits.max_sectors; } /* * Return maximum size of a request at given offset. Only valid for * file system requests. */ static inline unsigned int blk_max_size_offset(struct request_queue *q, sector_t offset, unsigned int chunk_sectors) { if (!chunk_sectors) { if (q->limits.chunk_sectors) chunk_sectors = q->limits.chunk_sectors; else return q->limits.max_sectors; } if (likely(is_power_of_2(chunk_sectors))) chunk_sectors -= offset & (chunk_sectors - 1); else chunk_sectors -= sector_div(offset, chunk_sectors); return min(q->limits.max_sectors, chunk_sectors); } static inline unsigned int blk_rq_get_max_sectors(struct request *rq, sector_t offset) { struct request_queue *q = rq->q; if (blk_rq_is_passthrough(rq)) return q->limits.max_hw_sectors; if (!q->limits.chunk_sectors || req_op(rq) == REQ_OP_DISCARD || req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); return min(blk_max_size_offset(q, offset, 0), blk_queue_get_max_sectors(q, req_op(rq))); } static inline unsigned int blk_rq_count_bios(struct request *rq) { unsigned int nr_bios = 0; struct bio *bio; __rq_for_each_bio(bio, rq) nr_bios++; return nr_bios; } void blk_steal_bios(struct bio_list *list, struct request *rq); /* * Request completion related functions. * * blk_update_request() completes given number of bytes and updates * the request without completing it. */ extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); extern void blk_abort_request(struct request *); /* * Access functions for manipulating queue properties */ extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_bounce_limit(struct request_queue *, u64); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_discard_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); extern void blk_queue_max_write_same_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); extern void blk_queue_max_zone_append_sectors(struct request_queue *q, unsigned int max_zone_append_sectors); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); void blk_queue_update_readahead(struct request_queue *q); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_default_limits(struct queue_limits *lim); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); extern void blk_queue_required_elevator_features(struct request_queue *q, unsigned int features); extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, struct device *dev); /* * Number of physical segments as sent to the device. * * Normally this is the number of discontiguous data segments sent by the * submitter. But for data-less command like discard we might have no * actual data segments submitted, but the driver might have to add it's * own special payload. In that case we still return 1 here so that this * special payload will be mapped. */ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return 1; return rq->nr_phys_segments; } /* * Number of discard segments (or ranges) the driver needs to fill in. * Each discard bio merged into a request is counted as one segment. */ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) { return max_t(unsigned short, rq->nr_phys_segments, 1); } int __blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist, struct scatterlist **last_sg); static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist) { struct scatterlist *last_sg = NULL; return __blk_rq_map_sg(q, rq, sglist, &last_sg); } extern void blk_dump_rq_flags(struct request *, char *); bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); #ifdef CONFIG_BLOCK /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests * into single larger request. As the requests are moved from a per-task list to * the device's request_queue in a batch, this results in improved scalability * as the lock contention for request_queue lock is reduced. * * It is ok not to disable preemption when adding the request to the plug list * or when attempting a merge, because blk_schedule_flush_list() will only flush * the plug list when the task sleeps by itself. For details, please see * schedule() where blk_schedule_flush_plug() is called. */ struct blk_plug { struct list_head mq_list; /* blk-mq requests */ struct list_head cb_list; /* md requires an unplug callback */ unsigned short rq_count; bool multiple_queues; bool nowait; }; struct blk_plug_cb; typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool); struct blk_plug_cb { struct list_head list; blk_plug_cb_fn callback; void *data; }; extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size); extern void blk_start_plug(struct blk_plug *); extern void blk_finish_plug(struct blk_plug *); extern void blk_flush_plug_list(struct blk_plug *, bool); static inline void blk_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; if (plug) blk_flush_plug_list(plug, false); } static inline void blk_schedule_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; if (plug) blk_flush_plug_list(plug, true); } static inline bool blk_needs_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; return plug && (!list_empty(&plug->mq_list) || !list_empty(&plug->cb_list)); } int blkdev_issue_flush(struct block_device *, gfp_t); long nr_blockdev_pages(void); #else /* CONFIG_BLOCK */ struct blk_plug { }; static inline void blk_start_plug(struct blk_plug *plug) { } static inline void blk_finish_plug(struct blk_plug *plug) { } static inline void blk_flush_plug(struct task_struct *task) { } static inline void blk_schedule_flush_plug(struct task_struct *task) { } static inline bool blk_needs_flush_plug(struct task_struct *tsk) { return false; } static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) { return 0; } static inline long nr_blockdev_pages(void) { return 0; } #endif /* CONFIG_BLOCK */ extern void blk_io_schedule(void); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); #define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, int flags, struct bio **biop); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned flags); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) { return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), gfp_mask, flags); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) { return blkdev_issue_zeroout(sb->s_bdev, block << (sb->s_blocksize_bits - SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), gfp_mask, 0); } extern int blk_verify_command(unsigned char *cmd, fmode_t mode); static inline bool bdev_is_partition(struct block_device *bdev) { return bdev->bd_partno; } enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, BLK_DEF_MAX_SECTORS = 2560, BLK_MAX_SEGMENT_SIZE = 65536, BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; static inline unsigned long queue_segment_boundary(const struct request_queue *q) { return q->limits.seg_boundary_mask; } static inline unsigned long queue_virt_boundary(const struct request_queue *q) { return q->limits.virt_boundary_mask; } static inline unsigned int queue_max_sectors(const struct request_queue *q) { return q->limits.max_sectors; } static inline unsigned int queue_max_hw_sectors(const struct request_queue *q) { return q->limits.max_hw_sectors; } static inline unsigned short queue_max_segments(const struct request_queue *q) { return q->limits.max_segments; } static inline unsigned short queue_max_discard_segments(const struct request_queue *q) { return q->limits.max_discard_segments; } static inline unsigned int queue_max_segment_size(const struct request_queue *q) { return q->limits.max_segment_size; } static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) { const struct queue_limits *l = &q->limits; return min(l->max_zone_append_sectors, l->max_sectors); } static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; if (q && q->limits.logical_block_size) retval = q->limits.logical_block_size; return retval; } static inline unsigned int bdev_logical_block_size(struct block_device *bdev) { return queue_logical_block_size(bdev_get_queue(bdev)); } static inline unsigned int queue_physical_block_size(const struct request_queue *q) { return q->limits.physical_block_size; } static inline unsigned int bdev_physical_block_size(struct block_device *bdev) { return queue_physical_block_size(bdev_get_queue(bdev)); } static inline unsigned int queue_io_min(const struct request_queue *q) { return q->limits.io_min; } static inline int bdev_io_min(struct block_device *bdev) { return queue_io_min(bdev_get_queue(bdev)); } static inline unsigned int queue_io_opt(const struct request_queue *q) { return q->limits.io_opt; } static inline int bdev_io_opt(struct block_device *bdev) { return queue_io_opt(bdev_get_queue(bdev)); } static inline int queue_alignment_offset(const struct request_queue *q) { if (q->limits.misaligned) return -1; return q->limits.alignment_offset; } static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) << SECTOR_SHIFT; return (granularity + lim->alignment_offset - alignment) % granularity; } static inline int bdev_alignment_offset(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q->limits.misaligned) return -1; if (bdev_is_partition(bdev)) return queue_limit_alignment_offset(&q->limits, bdev->bd_part->start_sect); return q->limits.alignment_offset; } static inline int queue_discard_alignment(const struct request_queue *q) { if (q->limits.discard_misaligned) return -1; return q->limits.discard_alignment; } static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) { unsigned int alignment, granularity, offset; if (!lim->max_discard_sectors) return 0; /* Why are these in bytes, not sectors? */ alignment = lim->discard_alignment >> SECTOR_SHIFT; granularity = lim->discard_granularity >> SECTOR_SHIFT; if (!granularity) return 0; /* Offset of the partition start in 'granularity' sectors */ offset = sector_div(sector, granularity); /* And why do we do this modulus *again* in blkdev_issue_discard()? */ offset = (granularity + alignment - offset) % granularity; /* Turn it back into bytes, gaah */ return offset << SECTOR_SHIFT; } /* * Two cases of handling DISCARD merge: * If max_discard_segments > 1, the driver takes every bio * as a range and send them to controller together. The ranges * needn't to be contiguous. * Otherwise, the bios/requests will be handled as same as * others which should be contiguous. */ static inline bool blk_discard_mergable(struct request *req) { if (req_op(req) == REQ_OP_DISCARD && queue_max_discard_segments(req->q) > 1) return true; return false; } static inline int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (bdev_is_partition(bdev)) return queue_limit_discard_alignment(&q->limits, bdev->bd_part->start_sect); return q->limits.discard_alignment; } static inline unsigned int bdev_write_same(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return q->limits.max_write_same_sectors; return 0; } static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return q->limits.max_write_zeroes_sectors; return 0; } static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_zoned_model(q); return BLK_ZONED_NONE; } static inline bool bdev_is_zoned(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_is_zoned(q); return false; } static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_zone_sectors(q); return 0; } static inline unsigned int bdev_max_open_zones(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return queue_max_open_zones(q); return 0; } static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return queue_max_active_zones(q); return 0; } static inline int queue_dma_alignment(const struct request_queue *q) { return q ? q->dma_alignment : 511; } static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr, unsigned int len) { unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask; return !(addr & alignment) && !(len & alignment); } /* assumes size > 256 */ static inline unsigned int blksize_bits(unsigned int size) { unsigned int bits = 8; do { bits++; size >>= 1; } while (size > 256); return bits; } static inline unsigned int block_size(struct block_device *bdev) { return 1 << bdev->bd_inode->i_blkbits; } int kblockd_schedule_work(struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ MODULE_ALIAS("block-major-" __stringify(major) "-*") #if defined(CONFIG_BLK_DEV_INTEGRITY) enum blk_integrity_flags { BLK_INTEGRITY_VERIFY = 1 << 0, BLK_INTEGRITY_GENERATE = 1 << 1, BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, BLK_INTEGRITY_IP_CHECKSUM = 1 << 3, }; struct blk_integrity_iter { void *prot_buf; void *data_buf; sector_t seed; unsigned int data_size; unsigned short interval; const char *disk_name; }; typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); typedef void (integrity_prepare_fn) (struct request *); typedef void (integrity_complete_fn) (struct request *, unsigned int); struct blk_integrity_profile { integrity_processing_fn *generate_fn; integrity_processing_fn *verify_fn; integrity_prepare_fn *prepare_fn; integrity_complete_fn *complete_fn; const char *name; }; extern void blk_integrity_register(struct gendisk *, struct blk_integrity *); extern void blk_integrity_unregister(struct gendisk *); extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { struct blk_integrity *bi = &disk->queue->integrity; if (!bi->profile) return NULL; return bi; } static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev) { return blk_get_integrity(bdev->bd_disk); } static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { return q->integrity.profile; } static inline bool blk_integrity_rq(struct request *rq) { return rq->cmd_flags & REQ_INTEGRITY; } static inline void blk_queue_max_integrity_segments(struct request_queue *q, unsigned int segs) { q->limits.max_integrity_segments = segs; } static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { return q->limits.max_integrity_segments; } /** * bio_integrity_intervals - Return number of integrity intervals for a bio * @bi: blk_integrity profile for device * @sectors: Size of the bio in 512-byte sectors * * Description: The block layer calculates everything in 512 byte * sectors but integrity metadata is done in terms of the data integrity * interval size of the storage device. Convert the block layer sectors * to the appropriate number of integrity intervals. */ static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { return sectors >> (bi->interval_exp - 9); } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { return bio_integrity_intervals(bi, sectors) * bi->tuple_size; } /* * Return the first bvec that contains integrity data. Only drivers that are * limited to a single integrity segment should use this helper. */ static inline struct bio_vec *rq_integrity_vec(struct request *rq) { if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1)) return NULL; return rq->bio->bi_integrity->bip_vec; } #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; struct block_device; struct gendisk; struct blk_integrity; static inline int blk_integrity_rq(struct request *rq) { return 0; } static inline int blk_rq_count_integrity