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 /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _ASM_X86_KPROBES_H #define _ASM_X86_KPROBES_H /* * Kernel Probes (KProbes) * * Copyright (C) IBM Corporation, 2002, 2004 * * See arch/x86/kernel/kprobes.c for x86 kprobes history. */ #include <asm-generic/kprobes.h> #ifdef CONFIG_KPROBES #include <linux/types.h> #include <linux/ptrace.h> #include <linux/percpu.h> #include <asm/text-patching.h> #include <asm/insn.h> #define __ARCH_WANT_KPROBES_INSN_SLOT struct pt_regs; struct kprobe; typedef u8 kprobe_opcode_t; #define MAX_STACK_SIZE 64 #define CUR_STACK_SIZE(ADDR) \ (current_top_of_stack() - (unsigned long)(ADDR)) #define MIN_STACK_SIZE(ADDR) \ (MAX_STACK_SIZE < CUR_STACK_SIZE(ADDR) ? \ MAX_STACK_SIZE : CUR_STACK_SIZE(ADDR)) #define flush_insn_slot(p) do { } while (0) /* optinsn template addresses */ extern __visible kprobe_opcode_t optprobe_template_entry[]; extern __visible kprobe_opcode_t optprobe_template_clac[]; extern __visible kprobe_opcode_t optprobe_template_val[]; extern __visible kprobe_opcode_t optprobe_template_call[]; extern __visible kprobe_opcode_t optprobe_template_end[]; #define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + DISP32_SIZE) #define MAX_OPTINSN_SIZE \ (((unsigned long)optprobe_template_end - \ (unsigned long)optprobe_template_entry) + \ MAX_OPTIMIZED_LENGTH + JMP32_INSN_SIZE) extern const int kretprobe_blacklist_size; void arch_remove_kprobe(struct kprobe *p); asmlinkage void kretprobe_trampoline(void); extern void arch_kprobe_override_function(struct pt_regs *regs); /* Architecture specific copy of original instruction*/ struct arch_specific_insn { /* copy of the original instruction */ kprobe_opcode_t *insn; /* * boostable = false: This instruction type is not boostable. * boostable = true: This instruction has been boosted: we have * added a relative jump after the instruction copy in insn, * so no single-step and fixup are needed (unless there's * a post_handler). */ bool boostable; bool if_modifier; /* Number of bytes of text poked */ int tp_len; }; struct arch_optimized_insn { /* copy of the original instructions */ kprobe_opcode_t copied_insn[DISP32_SIZE]; /* detour code buffer */ kprobe_opcode_t *insn; /* the size of instructions copied to detour code buffer */ size_t size; }; /* Return true (!0) if optinsn is prepared for optimization. */ static inline int arch_prepared_optinsn(struct arch_optimized_insn *optinsn) { return optinsn->size; } struct prev_kprobe { struct kprobe *kp; unsigned long status; unsigned long old_flags; unsigned long saved_flags; }; /* per-cpu kprobe control block */ struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_old_flags; unsigned long kprobe_saved_flags; struct prev_kprobe prev_kprobe; }; extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); extern int kprobe_int3_handler(struct pt_regs *regs); extern int kprobe_debug_handler(struct pt_regs *regs); #else static inline int kprobe_debug_handler(struct pt_regs *regs) { return 0; } #endif /* CONFIG_KPROBES */ #endif /* _ASM_X86_KPROBES_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 /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ #ifndef __BLUETOOTH_H #define __BLUETOOTH_H #include <linux/poll.h> #include <net/sock.h> #include <linux/seq_file.h> #define BT_SUBSYS_VERSION 2 #define BT_SUBSYS_REVISION 22 #ifndef AF_BLUETOOTH #define AF_BLUETOOTH 31 #define PF_BLUETOOTH AF_BLUETOOTH #endif /* Bluetooth versions */ #define BLUETOOTH_VER_1_1 1 #define BLUETOOTH_VER_1_2 2 #define BLUETOOTH_VER_2_0 3 #define BLUETOOTH_VER_2_1 4 #define BLUETOOTH_VER_4_0 6 /* Reserv for core and drivers use */ #define BT_SKB_RESERVE 8 #define BTPROTO_L2CAP 0 #define BTPROTO_HCI 1 #define BTPROTO_SCO 2 #define BTPROTO_RFCOMM 3 #define BTPROTO_BNEP 4 #define BTPROTO_CMTP 5 #define BTPROTO_HIDP 6 #define BTPROTO_AVDTP 7 #define SOL_HCI 0 #define SOL_L2CAP 6 #define SOL_SCO 17 #define SOL_RFCOMM 18 #define BT_SECURITY 4 struct bt_security { __u8 level; __u8 key_size; }; #define BT_SECURITY_SDP 0 #define BT_SECURITY_LOW 1 #define BT_SECURITY_MEDIUM 2 #define BT_SECURITY_HIGH 3 #define BT_SECURITY_FIPS 4 #define BT_DEFER_SETUP 7 #define BT_FLUSHABLE 8 #define BT_FLUSHABLE_OFF 0 #define BT_FLUSHABLE_ON 1 #define BT_POWER 9 struct bt_power { __u8 force_active; }; #define BT_POWER_FORCE_ACTIVE_OFF 0 #define BT_POWER_FORCE_ACTIVE_ON 1 #define BT_CHANNEL_POLICY 10 /* BR/EDR only (default policy) * AMP controllers cannot be used. * Channel move requests from the remote device are denied. * If the L2CAP channel is currently using AMP, move the channel to BR/EDR. */ #define BT_CHANNEL_POLICY_BREDR_ONLY 0 /* BR/EDR Preferred * Allow use of AMP controllers. * If the L2CAP channel is currently on AMP, move it to BR/EDR. * Channel move requests from the remote device are allowed. */ #define BT_CHANNEL_POLICY_BREDR_PREFERRED 1 /* AMP Preferred * Allow use of AMP controllers * If the L2CAP channel is currently on BR/EDR and AMP controller * resources are available, initiate a channel move to AMP. * Channel move requests from the remote device are allowed. * If the L2CAP socket has not been connected yet, try to create * and configure the channel directly on an AMP controller rather * than BR/EDR. */ #define BT_CHANNEL_POLICY_AMP_PREFERRED 2 #define BT_VOICE 11 struct bt_voice { __u16 setting; }; #define BT_VOICE_TRANSPARENT 0x0003 #define BT_VOICE_CVSD_16BIT 0x0060 #define BT_SNDMTU 12 #define BT_RCVMTU 13 #define BT_PHY 14 #define BT_PHY_BR_1M_1SLOT 0x00000001 #define BT_PHY_BR_1M_3SLOT 0x00000002 #define BT_PHY_BR_1M_5SLOT 0x00000004 #define BT_PHY_EDR_2M_1SLOT 0x00000008 #define BT_PHY_EDR_2M_3SLOT 0x00000010 #define BT_PHY_EDR_2M_5SLOT 0x00000020 #define BT_PHY_EDR_3M_1SLOT 0x00000040 #define BT_PHY_EDR_3M_3SLOT 0x00000080 #define BT_PHY_EDR_3M_5SLOT 0x00000100 #define BT_PHY_LE_1M_TX 0x00000200 #define BT_PHY_LE_1M_RX 0x00000400 #define BT_PHY_LE_2M_TX 0x00000800 #define BT_PHY_LE_2M_RX 0x00001000 #define BT_PHY_LE_CODED_TX 0x00002000 #define BT_PHY_LE_CODED_RX 0x00004000 #define BT_MODE 15 #define BT_MODE_BASIC 0x00 #define BT_MODE_ERTM 0x01 #define BT_MODE_STREAMING 0x02 #define BT_MODE_LE_FLOWCTL 0x03 #define BT_MODE_EXT_FLOWCTL 0x04 #define BT_PKT_STATUS 16 #define BT_SCM_PKT_STATUS 0x03 __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) void bt_warn(const char *fmt, ...); __printf(1, 2) void bt_err(const char *fmt, ...); #if IS_ENABLED(CONFIG_BT_FEATURE_DEBUG) void bt_dbg_set(bool enable); bool bt_dbg_get(void); __printf(1, 2) void bt_dbg(const char *fmt, ...); #endif __printf(1, 2) void bt_warn_ratelimited(const char *fmt, ...); __printf(1, 2) void bt_err_ratelimited(const char *fmt, ...); #define BT_INFO(fmt, ...) bt_info(fmt "\n", ##__VA_ARGS__) #define BT_WARN(fmt, ...) bt_warn(fmt "\n", ##__VA_ARGS__) #define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__) #if IS_ENABLED(CONFIG_BT_FEATURE_DEBUG) #define BT_DBG(fmt, ...) bt_dbg(fmt "\n", ##__VA_ARGS__) #else #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) #endif #define bt_dev_info(hdev, fmt, ...) \ BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__) #define bt_dev_warn(hdev, fmt, ...) \ BT_WARN("%s: " fmt, (hdev)->name, ##__VA_ARGS__) #define bt_dev_err(hdev, fmt, ...) \ BT_ERR("%s: " fmt, (hdev)->name, ##__VA_ARGS__) #define bt_dev_dbg(hdev, fmt, ...) \ BT_DBG("%s: " fmt, (hdev)->name, ##__VA_ARGS__) #define bt_dev_warn_ratelimited(hdev, fmt, ...) \ bt_warn_ratelimited("%s: " fmt, (hdev)->name, ##__VA_ARGS__) #define bt_dev_err_ratelimited(hdev, fmt, ...) \ bt_err_ratelimited("%s: " fmt, (hdev)->name, ##__VA_ARGS__) /* Connection and socket states */ enum { BT_CONNECTED = 1, /* Equal to TCP_ESTABLISHED to make net code happy */ BT_OPEN, BT_BOUND, BT_LISTEN, BT_CONNECT, BT_CONNECT2, BT_CONFIG, BT_DISCONN, BT_CLOSED }; /* If unused will be removed by compiler */ static inline const char *state_to_string(int state) { switch (state) { case BT_CONNECTED: return "BT_CONNECTED"; case BT_OPEN: return "BT_OPEN"; case BT_BOUND: return "BT_BOUND"; case BT_LISTEN: return "BT_LISTEN"; case BT_CONNECT: return "BT_CONNECT"; case BT_CONNECT2: return "BT_CONNECT2"; case BT_CONFIG: return "BT_CONFIG"; case BT_DISCONN: return "BT_DISCONN"; case BT_CLOSED: return "BT_CLOSED"; } return "invalid state"; } /* BD Address */ typedef struct { __u8 b[6]; } __packed bdaddr_t; /* BD Address type */ #define BDADDR_BREDR 0x00 #define BDADDR_LE_PUBLIC 0x01 #define BDADDR_LE_RANDOM 0x02 static inline bool bdaddr_type_is_valid(u8 type) { switch (type) { case BDADDR_BREDR: case BDADDR_LE_PUBLIC: case BDADDR_LE_RANDOM: return true; } return false; } static inline bool bdaddr_type_is_le(u8 type) { switch (type) { case BDADDR_LE_PUBLIC: case BDADDR_LE_RANDOM: return true; } return false; } #define BDADDR_ANY (&(bdaddr_t) {{0, 0, 0, 0, 0, 0}}) #define BDADDR_NONE (&(bdaddr_t) {{0xff, 0xff, 0xff, 0xff, 0xff, 0xff}}) /* Copy, swap, convert BD Address */ static inline int bacmp(const bdaddr_t *ba1, const bdaddr_t *ba2) { return memcmp(ba1, ba2, sizeof(bdaddr_t)); } static inline void bacpy(bdaddr_t *dst, const bdaddr_t *src) { memcpy(dst, src, sizeof(bdaddr_t)); } void baswap(bdaddr_t *dst, const bdaddr_t *src); /* Common socket structures and functions */ #define bt_sk(__sk) ((struct bt_sock *) __sk) struct bt_sock { struct sock sk; struct list_head accept_q; struct sock *parent; unsigned long flags; void (*skb_msg_name)(struct sk_buff *, void *, int *); void (*skb_put_cmsg)(struct sk_buff *, struct msghdr *, struct sock *); }; enum { BT_SK_DEFER_SETUP, BT_SK_SUSPEND, }; struct bt_sock_list { struct hlist_head head; rwlock_t lock; #ifdef CONFIG_PROC_FS int (* custom_seq_show)(struct seq_file *, void *); #endif }; int bt_sock_register(int proto, const struct net_proto_family *ops); void bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); __poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait); int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo); int bt_sock_wait_ready(struct sock *sk, unsigned long flags); void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh); void bt_accept_unlink(struct sock *sk); struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock); /* Skb helpers */ struct l2cap_ctrl { u8 sframe:1, poll:1, final:1, fcs:1, sar:2, super:2; u16 reqseq; u16 txseq; u8 retries; __le16 psm; bdaddr_t bdaddr; struct l2cap_chan *chan; }; struct sco_ctrl { u8 pkt_status; }; struct hci_dev; typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); typedef void (*hci_req_complete_skb_t)(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb); #define HCI_REQ_START BIT(0) #define HCI_REQ_SKB BIT(1) struct hci_ctrl { u16 opcode; u8 req_flags; u8 req_event; union { hci_req_complete_t req_complete; hci_req_complete_skb_t req_complete_skb; }; }; struct bt_skb_cb { u8 pkt_type; u8 force_active; u16 expect; u8 incoming:1; union { struct l2cap_ctrl l2cap; struct sco_ctrl sco; struct hci_ctrl hci; }; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) #define hci_skb_pkt_type(skb) bt_cb((skb))->pkt_type #define hci_skb_expect(skb) bt_cb((skb))->expect #define hci_skb_opcode(skb) bt_cb((skb))->hci.opcode static inline struct sk_buff *bt_skb_alloc(unsigned int len, gfp_t how) { struct sk_buff *skb; skb = alloc_skb(len + BT_SKB_RESERVE, how); if (skb) skb_reserve(skb, BT_SKB_RESERVE); return skb; } static inline struct sk_buff *bt_skb_send_alloc(struct sock *sk, unsigned long len, int nb, int *err) { struct sk_buff *skb; skb = sock_alloc_send_skb(sk, len + BT_SKB_RESERVE, nb, err); if (skb) skb_reserve(skb, BT_SKB_RESERVE); if (!skb && *err) return NULL; *err = sock_error(sk); if (*err) goto out; if (sk->sk_shutdown) { *err = -ECONNRESET; goto out; } return skb; out: kfree_skb(skb); return NULL; } int bt_to_errno(u16 code); void hci_sock_set_flag(struct sock *sk, int nr); void hci_sock_clear_flag(struct sock *sk, int nr); int hci_sock_test_flag(struct sock *sk, int nr); unsigned short hci_sock_get_channel(struct sock *sk); u32 hci_sock_get_cookie(struct sock *sk); int hci_sock_init(void); void hci_sock_cleanup(void); int bt_sysfs_init(void); void bt_sysfs_cleanup(void); int bt_procfs_init(struct net *net, const char *name, struct bt_sock_list *sk_list, int (*seq_show)(struct seq_file *, void *)); void bt_procfs_cleanup(struct net *net, const char *name); extern struct dentry *bt_debugfs; int l2cap_init(void); void l2cap_exit(void); #if IS_ENABLED(CONFIG_BT_BREDR) int sco_init(void); void sco_exit(void); #else static inline int sco_init(void) { return 0; } static inline void sco_exit(void) { } #endif int mgmt_init(void); void mgmt_exit(void); void bt_sock_reclassify_lock(struct sock *sk, int proto); #endif /* __BLUETOOTH_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 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 // SPDX-License-Identifier: GPL-2.0 /* * fs/ext4/extents_status.c * * Written by Yongqiang Yang <xiaoqiangnk@gmail.com> * Modified by * Allison Henderson <achender@linux.vnet.ibm.com> * Hugh Dickins <hughd@google.com> * Zheng Liu <wenqing.lz@taobao.com> * * Ext4 extents status tree core functions. */ #include <linux/list_sort.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include "ext4.h" #include <trace/events/ext4.h> /* * According to previous discussion in Ext4 Developer Workshop, we * will introduce a new structure called io tree to track all extent * status in order to solve some problems that we have met * (e.g. Reservation space warning), and provide extent-level locking. * Delay extent tree is the first step to achieve this goal. It is * original built by Yongqiang Yang. At that time it is called delay * extent tree, whose goal is only track delayed extents in memory to * simplify the implementation of fiemap and bigalloc, and introduce * lseek SEEK_DATA/SEEK_HOLE support. That is why it is still called * delay extent tree at the first commit. But for better understand * what it does, it has been rename to extent status tree. * * Step1: * Currently the first step has been done. All delayed extents are * tracked in the tree. It maintains the delayed extent when a delayed * allocation is issued, and the delayed extent is written out or * invalidated. Therefore the implementation of fiemap and bigalloc * are simplified, and SEEK_DATA/SEEK_HOLE are introduced. * * The following comment describes the implemenmtation of extent * status tree and future works. * * Step2: * In this step all extent status are tracked by extent status tree. * Thus, we can first try to lookup a block mapping in this tree before * finding it in extent tree. Hence, single extent cache can be removed * because extent status tree can do a better job. Extents in status * tree are loaded on-demand. Therefore, the extent status tree may not * contain all of the extents in a file. Meanwhile we define a shrinker * to reclaim memory from extent status tree because fragmented extent * tree will make status tree cost too much memory. written/unwritten/- * hole extents in the tree will be reclaimed by this shrinker when we * are under high memory pressure. Delayed extents will not be * reclimed because fiemap, bigalloc, and seek_data/hole need it. */ /* * Extent status tree implementation for ext4. * * * ========================================================================== * Extent status tree tracks all extent status. * * 1. Why we need to implement extent status tree? * * Without extent status tree, ext4 identifies a delayed extent by looking * up page cache, this has several deficiencies - complicated, buggy, * and inefficient code. * * FIEMAP, SEEK_HOLE/DATA, bigalloc, and writeout all need to know if a * block or a range of blocks are belonged to a delayed extent. * * Let us have a look at how they do without extent status tree. * -- FIEMAP * FIEMAP looks up page cache to identify delayed allocations from holes. * * -- SEEK_HOLE/DATA * SEEK_HOLE/DATA has the same problem as FIEMAP. * * -- bigalloc * bigalloc looks up page cache to figure out if a block is * already under delayed allocation or not to determine whether * quota reserving is needed for the cluster. * * -- writeout * Writeout looks up whole page cache to see if a buffer is * mapped, If there are not very many delayed buffers, then it is * time consuming. * * With extent status tree implementation, FIEMAP, SEEK_HOLE/DATA, * bigalloc and writeout can figure out if a block or a range of * blocks is under delayed allocation(belonged to a delayed extent) or * not by searching the extent tree. * * * ========================================================================== * 2. Ext4 extent status tree impelmentation * * -- extent * A extent is a range of blocks which are contiguous logically and * physically. Unlike extent in extent tree, this extent in ext4 is * a in-memory struct, there is no corresponding on-disk data. There * is no limit on length of extent, so an extent can contain as many * blocks as they are contiguous logically and physically. * * -- extent status tree * Every inode has an extent status tree and all allocation blocks * are added to the tree with different status. The extent in the * tree are ordered by logical block no. * * -- operations on a extent status tree * There are three important operations on a delayed extent tree: find * next extent, adding a extent(a range of blocks) and removing a extent. * * -- race on a extent status tree * Extent status tree is protected by inode->i_es_lock. * * -- memory consumption * Fragmented extent tree will make extent status tree cost too much * memory. Hence, we will reclaim written/unwritten/hole extents from * the tree under a heavy memory pressure. * * * ========================================================================== * 3. Performance analysis * * -- overhead * 1. There is a cache extent for write access, so if writes are * not very random, adding space operaions are in O(1) time. * * -- gain * 2. Code is much simpler, more readable, more maintainable and * more efficient. * * * ========================================================================== * 4. TODO list * * -- Refactor delayed space reservation * * -- Extent-level locking */ static struct kmem_cache *ext4_es_cachep; static struct kmem_cache *ext4_pending_cachep; static int __es_insert_extent(struct inode *inode, struct extent_status *newes); static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, int *reserved); static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len); int __init ext4_init_es(void) { ext4_es_cachep = kmem_cache_create("ext4_extent_status", sizeof(struct extent_status), 0, (SLAB_RECLAIM_ACCOUNT), NULL); if (ext4_es_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_es(void) { kmem_cache_destroy(ext4_es_cachep); } void ext4_es_init_tree(struct ext4_es_tree *tree) { tree->root = RB_ROOT; tree->cache_es = NULL; } #ifdef ES_DEBUG__ static void ext4_es_print_tree(struct inode *inode) { struct ext4_es_tree *tree; struct rb_node *node; printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino); tree = &EXT4_I(inode)->i_es_tree; node = rb_first(&tree->root); while (node) { struct extent_status *es; es = rb_entry(node, struct extent_status, rb_node); printk(KERN_DEBUG " [%u/%u) %llu %x", es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); node = rb_next(node); } printk(KERN_DEBUG "\n"); } #else #define ext4_es_print_tree(inode) #endif static inline ext4_lblk_t ext4_es_end(struct extent_status *es) { BUG_ON(es->es_lblk + es->es_len < es->es_lblk); return es->es_lblk + es->es_len - 1; } /* * search through the tree for an delayed extent with a given offset. If * it can't be found, try to find next extent. */ static struct extent_status *__es_tree_search(struct rb_root *root, ext4_lblk_t lblk) { struct rb_node *node = root->rb_node; struct extent_status *es = NULL; while (node) { es = rb_entry(node, struct extent_status, rb_node); if (lblk < es->es_lblk) node = node->rb_left; else if (lblk > ext4_es_end(es)) node = node->rb_right; else return es; } if (es && lblk < es->es_lblk) return es; if (es && lblk > ext4_es_end(es)) { node = rb_next(&es->rb_node); return node ? rb_entry(node, struct extent_status, rb_node) : NULL; } return NULL; } /* * ext4_es_find_extent_range - find extent with specified status within block * range or next extent following block range in * extents status tree * * @inode - file containing the range * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block defining start of range * @end - logical block defining end of range * @es - extent found, if any * * Find the first extent within the block range specified by @lblk and @end * in the extents status tree that satisfies @matching_fn. If a match * is found, it's returned in @es. If not, and a matching extent is found * beyond the block range, it's returned in @es. If no match is found, an * extent is returned in @es whose es_lblk, es_len, and es_pblk components * are 0. */ static void __es_find_extent_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { struct ext4_es_tree *tree = NULL; struct extent_status *es1 = NULL; struct rb_node *node; WARN_ON(es == NULL); WARN_ON(end < lblk); tree = &EXT4_I(inode)->i_es_tree; /* see if the extent has been cached */ es->es_lblk = es->es_len = es->es_pblk = 0; if (tree->cache_es) { es1 = tree->cache_es; if (in_range(lblk, es1->es_lblk, es1->es_len)) { es_debug("%u cached by [%u/%u) %llu %x\n", lblk, es1->es_lblk, es1->es_len, ext4_es_pblock(es1), ext4_es_status(es1)); goto out; } } es1 = __es_tree_search(&tree->root, lblk); out: if (es1 && !matching_fn(es1)) { while ((node = rb_next(&es1->rb_node)) != NULL) { es1 = rb_entry(node, struct extent_status, rb_node); if (es1->es_lblk > end) { es1 = NULL; break; } if (matching_fn(es1)) break; } } if (es1 && matching_fn(es1)) { tree->cache_es = es1; es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; } } /* * Locking for __es_find_extent_range() for external use */ void ext4_es_find_extent_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; trace_ext4_es_find_extent_range_enter(inode, lblk); read_lock(&EXT4_I(inode)->i_es_lock); __es_find_extent_range(inode, matching_fn, lblk, end, es); read_unlock(&EXT4_I(inode)->i_es_lock); trace_ext4_es_find_extent_range_exit(inode, es); } /* * __es_scan_range - search block range for block with specified status * in extents status tree * * @inode - file containing the range * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block defining start of range * @end - logical block defining end of range * * Returns true if at least one block in the specified block range satisfies * the criterion specified by @matching_fn, and false if not. If at least * one extent has the specified status, then there is at least one block * in the cluster with that status. Should only be called by code that has * taken i_es_lock. */ static bool __es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t start, ext4_lblk_t end) { struct extent_status es; __es_find_extent_range(inode, matching_fn, start, end, &es); if (es.es_len == 0) return false; /* no matching extent in the tree */ else if (es.es_lblk <= start && start < es.es_lblk + es.es_len) return true; else if (start <= es.es_lblk && es.es_lblk <= end) return true; else return false; } /* * Locking for __es_scan_range() for external use */ bool ext4_es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end) { bool ret; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return false; read_lock(&EXT4_I(inode)->i_es_lock); ret = __es_scan_range(inode, matching_fn, lblk, end); read_unlock(&EXT4_I(inode)->i_es_lock); return ret; } /* * __es_scan_clu - search cluster for block with specified status in * extents status tree * * @inode - file containing the cluster * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block in cluster to be searched * * Returns true if at least one extent in the cluster containing @lblk * satisfies the criterion specified by @matching_fn, and false if not. If at * least one extent has the specified status, then there is at least one block * in the cluster with that status. Should only be called by code that has * taken i_es_lock. */ static bool __es_scan_clu(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t lblk_start, lblk_end; lblk_start = EXT4_LBLK_CMASK(sbi, lblk); lblk_end = lblk_start + sbi->s_cluster_ratio - 1; return __es_scan_range(inode, matching_fn, lblk_start, lblk_end); } /* * Locking for __es_scan_clu() for external use */ bool ext4_es_scan_clu(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk) { bool ret; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return false; read_lock(&EXT4_I(inode)->i_es_lock); ret = __es_scan_clu(inode, matching_fn, lblk); read_unlock(&EXT4_I(inode)->i_es_lock); return ret; } static void ext4_es_list_add(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (!list_empty(&ei->i_es_list)) return; spin_lock(&sbi->s_es_lock); if (list_empty(&ei->i_es_list)) { list_add_tail(&ei->i_es_list, &sbi->s_es_list); sbi->s_es_nr_inode++; } spin_unlock(&sbi->s_es_lock); } static void ext4_es_list_del(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); spin_lock(&sbi->s_es_lock); if (!list_empty(&ei->i_es_list)) { list_del_init(&ei->i_es_list); sbi->s_es_nr_inode--; WARN_ON_ONCE(sbi->s_es_nr_inode < 0); } spin_unlock(&sbi->s_es_lock); } static struct extent_status * ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk) { struct extent_status *es; es = kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC); if (es == NULL) return NULL; es->es_lblk = lblk; es->es_len = len; es->es_pblk = pblk; /* * We don't count delayed extent because we never try to reclaim them */ if (!ext4_es_is_delayed(es)) { if (!EXT4_I(inode)->i_es_shk_nr++) ext4_es_list_add(inode); percpu_counter_inc(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } EXT4_I(inode)->i_es_all_nr++; percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); return es; } static void ext4_es_free_extent(struct inode *inode, struct extent_status *es) { EXT4_I(inode)->i_es_all_nr--; percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); /* Decrease the shrink counter when this es is not delayed */ if (!ext4_es_is_delayed(es)) { BUG_ON(EXT4_I(inode)->i_es_shk_nr == 0); if (!--EXT4_I(inode)->i_es_shk_nr) ext4_es_list_del(inode); percpu_counter_dec(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } kmem_cache_free(ext4_es_cachep, es); } /* * Check whether or not two extents can be merged * Condition: * - logical block number is contiguous * - physical block number is contiguous * - status is equal */ static int ext4_es_can_be_merged(struct extent_status *es1, struct extent_status *es2) { if (ext4_es_type(es1) != ext4_es_type(es2)) return 0; if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) { pr_warn("ES assertion failed when merging extents. " "The sum of lengths of es1 (%d) and es2 (%d) " "is bigger than allowed file size (%d)\n", es1->es_len, es2->es_len, EXT_MAX_BLOCKS); WARN_ON(1); return 0; } if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk) return 0; if ((ext4_es_is_written(es1) || ext4_es_is_unwritten(es1)) && (ext4_es_pblock(es1) + es1->es_len == ext4_es_pblock(es2))) return 1; if (ext4_es_is_hole(es1)) return 1; /* we need to check delayed extent is without unwritten status */ if (ext4_es_is_delayed(es1) && !ext4_es_is_unwritten(es1)) return 1; return 0; } static struct extent_status * ext4_es_try_to_merge_left(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_prev(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es1, es)) { es1->es_len += es->es_len; if (ext4_es_is_referenced(es)) ext4_es_set_referenced(es1); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); es = es1; } return es; } static struct extent_status * ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_next(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es, es1)) { es->es_len += es1->es_len; if (ext4_es_is_referenced(es1)) ext4_es_set_referenced(es); rb_erase(node, &tree->root); ext4_es_free_extent(inode, es1); } return es; } #ifdef ES_AGGRESSIVE_TEST #include "ext4_extents.h" /* Needed when ES_AGGRESSIVE_TEST is defined */ static void ext4_es_insert_extent_ext_check(struct inode *inode, struct extent_status *es) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t ee_block; ext4_fsblk_t ee_start; unsigned short ee_len; int depth, ee_status, es_status; path = ext4_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return; depth = ext_depth(inode); ex = path[depth].p_ext; if (ex) { ee_block = le32_to_cpu(ex->ee_block); ee_start = ext4_ext_pblock(ex); ee_len = ext4_ext_get_actual_len(ex); ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0; es_status = ext4_es_is_unwritten(es) ? 1 : 0; /* * Make sure ex and es are not overlap when we try to insert * a delayed/hole extent. */ if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) { if (in_range(es->es_lblk, ee_block, ee_len)) { pr_warn("ES insert assertion failed for " "inode: %lu we can find an extent " "at block [%d/%d/%llu/%c], but we " "want to add a delayed/hole extent " "[%d/%d/%llu/%x]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } goto out; } /* * We don't check ee_block == es->es_lblk, etc. because es * might be a part of whole extent, vice versa. */ if (es->es_lblk < ee_block || ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); goto out; } if (ee_status ^ es_status) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); } } else { /* * We can't find an extent on disk. So we need to make sure * that we don't want to add an written/unwritten extent. */ if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) { pr_warn("ES insert assertion failed for inode: %lu " "can't find an extent at block %d but we want " "to add a written/unwritten extent " "[%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } } out: ext4_ext_drop_refs(path); kfree(path); } static void ext4_es_insert_extent_ind_check(struct inode *inode, struct extent_status *es) { struct ext4_map_blocks map; int retval; /* * Here we call ext4_ind_map_blocks to lookup a block mapping because * 'Indirect' structure is defined in indirect.c. So we couldn't * access direct/indirect tree from outside. It is too dirty to define * this function in indirect.c file. */ map.m_lblk = es->es_lblk; map.m_len = es->es_len; retval = ext4_ind_map_blocks(NULL, inode, &map, 0); if (retval > 0) { if (ext4_es_is_delayed(es) || ext4_es_is_hole(es)) { /* * We want to add a delayed/hole extent but this * block has been allocated. */ pr_warn("ES insert assertion failed for inode: %lu " "We can find blocks but we want to add a " "delayed/hole extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } else if (ext4_es_is_written(es)) { if (retval != es->es_len) { pr_warn("ES insert assertion failed for " "inode: %lu retval %d != es_len %d\n", inode->i_ino, retval, es->es_len); return; } if (map.m_pblk != ext4_es_pblock(es)) { pr_warn("ES insert assertion failed for " "inode: %lu m_pblk %llu != " "es_pblk %llu\n", inode->i_ino, map.m_pblk, ext4_es_pblock(es)); return; } } else { /* * We don't need to check unwritten extent because * indirect-based file doesn't have it. */ BUG(); } } else if (retval == 0) { if (ext4_es_is_written(es)) { pr_warn("ES insert assertion failed for inode: %lu " "We can't find the block but we want to add " "a written extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } } } static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { /* * We don't need to worry about the race condition because * caller takes i_data_sem locking. */ BUG_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ext4_es_insert_extent_ext_check(inode, es); else ext4_es_insert_extent_ind_check(inode, es); } #else static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { } #endif static int __es_insert_extent(struct inode *inode, struct extent_status *newes) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct rb_node **p = &tree->root.rb_node; struct rb_node *parent = NULL; struct extent_status *es; while (*p) { parent = *p; es = rb_entry(parent, struct extent_status, rb_node); if (newes->es_lblk < es->es_lblk) { if (ext4_es_can_be_merged(newes, es)) { /* * Here we can modify es_lblk directly * because it isn't overlapped. */ es->es_lblk = newes->es_lblk; es->es_len += newes->es_len; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) ext4_es_store_pblock(es, newes->es_pblk); es = ext4_es_try_to_merge_left(inode, es); goto out; } p = &(*p)->rb_left; } else if (newes->es_lblk > ext4_es_end(es)) { if (ext4_es_can_be_merged(es, newes)) { es->es_len += newes->es_len; es = ext4_es_try_to_merge_right(inode, es); goto out; } p = &(*p)->rb_right; } else { BUG(); return -EINVAL; } } es = ext4_es_alloc_extent(inode, newes->es_lblk, newes->es_len, newes->es_pblk); if (!es) return -ENOMEM; rb_link_node(&es->rb_node, parent, p); rb_insert_color(&es->rb_node, &tree->root); out: tree->cache_es = es; return 0; } /* * ext4_es_insert_extent() adds information to an inode's extent * status tree. * * Return 0 on success, error code on failure. */ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status) { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; int err = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n", lblk, len, pblk, status, inode->i_ino); if (!len) return 0; BUG_ON(end < lblk); if ((status & EXTENT_STATUS_DELAYED) && (status & EXTENT_STATUS_WRITTEN)) { ext4_warning(inode->i_sb, "Inserting extent [%u/%u] as " " delayed and written which can potentially " " cause data loss.", lblk, len); WARN_ON(1); } newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, pblk, status); trace_ext4_es_insert_extent(inode, &newes); ext4_es_insert_extent_check(inode, &newes); write_lock(&EXT4_I(inode)->i_es_lock); err = __es_remove_extent(inode, lblk, end, NULL); if (err != 0) goto error; retry: err = __es_insert_extent(inode, &newes); if (err == -ENOMEM && __es_shrink(EXT4_SB(inode->i_sb), 128, EXT4_I(inode))) goto retry; if (err == -ENOMEM && !ext4_es_is_delayed(&newes)) err = 0; if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && (status & EXTENT_STATUS_WRITTEN || status & EXTENT_STATUS_UNWRITTEN)) __revise_pending(inode, lblk, len); error: write_unlock(&EXT4_I(inode)->i_es_lock); ext4_es_print_tree(inode); return err; } /* * ext4_es_cache_extent() inserts information into the extent status * tree if and only if there isn't information about the range in * question already. */ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status) { struct extent_status *es; struct extent_status newes; ext4_lblk_t end = lblk + len - 1; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, pblk, status); trace_ext4_es_cache_extent(inode, &newes); if (!len) return; BUG_ON(end < lblk); write_lock(&EXT4_I(inode)->i_es_lock); es = __es_tree_search(&EXT4_I(inode)->i_es_tree.root, lblk); if (!es || es->es_lblk > end) __es_insert_extent(inode, &newes); write_unlock(&EXT4_I(inode)->i_es_lock); } /* * ext4_es_lookup_extent() looks up an extent in extent status tree. * * ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks. * * Return: 1 on found, 0 on not */ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t *next_lblk, struct extent_status *es) { struct ext4_es_tree *tree; struct ext4_es_stats *stats; struct extent_status *es1 = NULL; struct rb_node *node; int found = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; trace_ext4_es_lookup_extent_enter(inode, lblk); es_debug("lookup extent in block %u\n", lblk); tree = &EXT4_I(inode)->i_es_tree; read_lock(&EXT4_I(inode)->i_es_lock); /* find extent in cache firstly */ es->es_lblk = es->es_len = es->es_pblk = 0; if (tree->cache_es) { es1 = tree->cache_es; if (in_range(lblk, es1->es_lblk, es1->es_len)) { es_debug("%u cached by [%u/%u)\n", lblk, es1->es_lblk, es1->es_len); found = 1; goto out; } } node = tree->root.rb_node; while (node) { es1 = rb_entry(node, struct extent_status, rb_node); if (lblk < es1->es_lblk) node = node->rb_left; else if (lblk > ext4_es_end(es1)) node = node->rb_right; else { found = 1; break; } } out: stats = &EXT4_SB(inode->i_sb)->s_es_stats; if (found) { BUG_ON(!es1); es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; if (!ext4_es_is_referenced(es1)) ext4_es_set_referenced(es1); percpu_counter_inc(&stats->es_stats_cache_hits); if (next_lblk) { node = rb_next(&es1->rb_node); if (node) { es1 = rb_entry(node, struct extent_status, rb_node); *next_lblk = es1->es_lblk; } else *next_lblk = 0; } } else { percpu_counter_inc(&stats->es_stats_cache_misses); } read_unlock(&EXT4_I(inode)->i_es_lock); trace_ext4_es_lookup_extent_exit(inode, es, found); return found; } struct rsvd_count { int ndelonly; bool first_do_lblk_found; ext4_lblk_t first_do_lblk; ext4_lblk_t last_do_lblk; struct extent_status *left_es; bool partial; ext4_lblk_t lclu; }; /* * init_rsvd - initialize reserved count data before removing block range * in file from extent status tree * * @inode - file containing range * @lblk - first block in range * @es - pointer to first extent in range * @rc - pointer to reserved count data * * Assumes es is not NULL */ static void init_rsvd(struct inode *inode, ext4_lblk_t lblk, struct extent_status *es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct rb_node *node; rc->ndelonly = 0; /* * for bigalloc, note the first delonly block in the range has not * been found, record the extent containing the block to the left of * the region to be removed, if any, and note that there's no partial * cluster to track */ if (sbi->s_cluster_ratio > 1) { rc->first_do_lblk_found = false; if (lblk > es->es_lblk) { rc->left_es = es; } else { node = rb_prev(&es->rb_node); rc->left_es = node ? rb_entry(node, struct extent_status, rb_node) : NULL; } rc->partial = false; } } /* * count_rsvd - count the clusters containing delayed and not unwritten * (delonly) blocks in a range within an extent and add to * the running tally in rsvd_count * * @inode - file containing extent * @lblk - first block in range * @len - length of range in blocks * @es - pointer to extent containing clusters to be counted * @rc - pointer to reserved count data * * Tracks partial clusters found at the beginning and end of extents so * they aren't overcounted when they span adjacent extents */ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len, struct extent_status *es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t i, end, nclu; if (!ext4_es_is_delonly(es)) return; WARN_ON(len <= 0); if (sbi->s_cluster_ratio == 1) { rc->ndelonly += (int) len; return; } /* bigalloc */ i = (lblk < es->es_lblk) ? es->es_lblk : lblk; end = lblk + (ext4_lblk_t) len - 1; end = (end > ext4_es_end(es)) ? ext4_es_end(es) : end; /* record the first block of the first delonly extent seen */ if (!rc->first_do_lblk_found) { rc->first_do_lblk = i; rc->first_do_lblk_found = true; } /* update the last lblk in the region seen so far */ rc->last_do_lblk = end; /* * if we're tracking a partial cluster and the current extent * doesn't start with it, count it and stop tracking */ if (rc->partial && (rc->lclu != EXT4_B2C(sbi, i))) { rc->ndelonly++; rc->partial = false; } /* * if the first cluster doesn't start on a cluster boundary but * ends on one, count it */ if (EXT4_LBLK_COFF(sbi, i) != 0) { if (end >= EXT4_LBLK_CFILL(sbi, i)) { rc->ndelonly++; rc->partial = false; i = EXT4_LBLK_CFILL(sbi, i) + 1; } } /* * if the current cluster starts on a cluster boundary, count the * number of whole delonly clusters in the extent */ if ((i + sbi->s_cluster_ratio - 1) <= end) { nclu = (end - i + 1) >> sbi->s_cluster_bits; rc->ndelonly += nclu; i += nclu << sbi->s_cluster_bits; } /* * start tracking a partial cluster if there's a partial at the end * of the current extent and we're not already tracking one */ if (!rc->partial && i <= end) { rc->partial = true; rc->lclu = EXT4_B2C(sbi, i); } } /* * __pr_tree_search - search for a pending cluster reservation * * @root - root of pending reservation tree * @lclu - logical cluster to search for * * Returns the pending reservation for the cluster identified by @lclu * if found. If not, returns a reservation for the next cluster if any, * and if not, returns NULL. */ static struct pending_reservation *__pr_tree_search(struct rb_root *root, ext4_lblk_t lclu) { struct rb_node *node = root->rb_node; struct pending_reservation *pr = NULL; while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); if (lclu < pr->lclu) node = node->rb_left; else if (lclu > pr->lclu) node = node->rb_right; else return pr; } if (pr && lclu < pr->lclu) return pr; if (pr && lclu > pr->lclu) { node = rb_next(&pr->rb_node); return node ? rb_entry(node, struct pending_reservation, rb_node) : NULL; } return NULL; } /* * get_rsvd - calculates and returns the number of cluster reservations to be * released when removing a block range from the extent status tree * and releases any pending reservations within the range * * @inode - file containing block range * @end - last block in range * @right_es - pointer to extent containing next block beyond end or NULL * @rc - pointer to reserved count data * * The number of reservations to be released is equal to the number of * clusters containing delayed and not unwritten (delonly) blocks within * the range, minus the number of clusters still containing delonly blocks * at the ends of the range, and minus the number of pending reservations * within the range. */ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end, struct extent_status *right_es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct pending_reservation *pr; struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; struct rb_node *node; ext4_lblk_t first_lclu, last_lclu; bool left_delonly, right_delonly, count_pending; struct extent_status *es; if (sbi->s_cluster_ratio > 1) { /* count any remaining partial cluster */ if (rc->partial) rc->ndelonly++; if (rc->ndelonly == 0) return 0; first_lclu = EXT4_B2C(sbi, rc->first_do_lblk); last_lclu = EXT4_B2C(sbi, rc->last_do_lblk); /* * decrease the delonly count by the number of clusters at the * ends of the range that still contain delonly blocks - * these clusters still need to be reserved */ left_delonly = right_delonly = false; es = rc->left_es; while (es && ext4_es_end(es) >= EXT4_LBLK_CMASK(sbi, rc->first_do_lblk)) { if (ext4_es_is_delonly(es)) { rc->ndelonly--; left_delonly = true; break; } node = rb_prev(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } if (right_es && (!left_delonly || first_lclu != last_lclu)) { if (end < ext4_es_end(right_es)) { es = right_es; } else { node = rb_next(&right_es->rb_node); es = node ? rb_entry(node, struct extent_status, rb_node) : NULL; } while (es && es->es_lblk <= EXT4_LBLK_CFILL(sbi, rc->last_do_lblk)) { if (ext4_es_is_delonly(es)) { rc->ndelonly--; right_delonly = true; break; } node = rb_next(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } } /* * Determine the block range that should be searched for * pending reservations, if any. Clusters on the ends of the * original removed range containing delonly blocks are * excluded. They've already been accounted for and it's not * possible to determine if an associated pending reservation * should be released with the information available in the * extents status tree. */ if (first_lclu == last_lclu) { if (left_delonly | right_delonly) count_pending = false; else count_pending = true; } else { if (left_delonly) first_lclu++; if (right_delonly) last_lclu--; if (first_lclu <= last_lclu) count_pending = true; else count_pending = false; } /* * a pending reservation found between first_lclu and last_lclu * represents an allocated cluster that contained at least one * delonly block, so the delonly total must be reduced by one * for each pending reservation found and released */ if (count_pending) { pr = __pr_tree_search(&tree->root, first_lclu); while (pr && pr->lclu <= last_lclu) { rc->ndelonly--; node = rb_next(&pr->rb_node); rb_erase(&pr->rb_node, &tree->root); kmem_cache_free(ext4_pending_cachep, pr); if (!node) break; pr = rb_entry(node, struct pending_reservation, rb_node); } } } return rc->ndelonly; } /* * __es_remove_extent - removes block range from extent status tree * * @inode - file containing range * @lblk - first block in range * @end - last block in range * @reserved - number of cluster reservations released * * If @reserved is not NULL and delayed allocation is enabled, counts * block/cluster reservations freed by removing range and if bigalloc * enabled cancels pending reservations as needed. Returns 0 on success, * error code on failure. */ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, int *reserved) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct rb_node *node; struct extent_status *es; struct extent_status orig_es; ext4_lblk_t len1, len2; ext4_fsblk_t block; int err; bool count_reserved = true; struct rsvd_count rc; if (reserved == NULL || !test_opt(inode->i_sb, DELALLOC)) count_reserved = false; retry: err = 0; es = __es_tree_search(&tree->root, lblk); if (!es) goto out; if (es->es_lblk > end) goto out; /* Simply invalidate cache_es. */ tree->cache_es = NULL; if (count_reserved) init_rsvd(inode, lblk, es, &rc); orig_es.es_lblk = es->es_lblk; orig_es.es_len = es->es_len; orig_es.es_pblk = es->es_pblk; len1 = lblk > es->es_lblk ? lblk - es->es_lblk : 0; len2 = ext4_es_end(es) > end ? ext4_es_end(es) - end : 0; if (len1 > 0) es->es_len = len1; if (len2 > 0) { if (len1 > 0) { struct extent_status newes; newes.es_lblk = end + 1; newes.es_len = len2; block = 0x7FDEADBEEFULL; if (ext4_es_is_written(&orig_es) || ext4_es_is_unwritten(&orig_es)) block = ext4_es_pblock(&orig_es) + orig_es.es_len - len2; ext4_es_store_pblock_status(&newes, block, ext4_es_status(&orig_es)); err = __es_insert_extent(inode, &newes); if (err) { es->es_lblk = orig_es.es_lblk; es->es_len = orig_es.es_len; if ((err == -ENOMEM) && __es_shrink(EXT4_SB(inode->i_sb), 128, EXT4_I(inode))) goto retry; goto out; } } else { es->es_lblk = end + 1; es->es_len = len2; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) { block = orig_es.es_pblk + orig_es.es_len - len2; ext4_es_store_pblock(es, block); } } if (count_reserved) count_rsvd(inode, lblk, orig_es.es_len - len1 - len2, &orig_es, &rc); goto out; } if (len1 > 0) { if (count_reserved) count_rsvd(inode, lblk, orig_es.es_len - len1, &orig_es, &rc); node = rb_next(&es->rb_node); if (node) es = rb_entry(node, struct extent_status, rb_node); else es = NULL; } while (es && ext4_es_end(es) <= end) { if (count_reserved) count_rsvd(inode, es->es_lblk, es->es_len, es, &rc); node = rb_next(&es->rb_node); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); if (!node) { es = NULL; break; } es = rb_entry(node, struct extent_status, rb_node); } if (es && es->es_lblk < end + 1) { ext4_lblk_t orig_len = es->es_len; len1 = ext4_es_end(es) - end; if (count_reserved) count_rsvd(inode, es->es_lblk, orig_len - len1, es, &rc); es->es_lblk = end + 1; es->es_len = len1; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) { block = es->es_pblk + orig_len - len1; ext4_es_store_pblock(es, block); } } if (count_reserved) *reserved = get_rsvd(inode, end, es, &rc); out: return err; } /* * ext4_es_remove_extent - removes block range from extent status tree * * @inode - file containing range * @lblk - first block in range * @len - number of blocks to remove * * Reduces block/cluster reservation count and for bigalloc cancels pending * reservations as needed. Returns 0 on success, error code on failure. */ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { ext4_lblk_t end; int err = 0; int reserved = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; trace_ext4_es_remove_extent(inode, lblk, len); es_debug("remove [%u/%u) from extent status tree of inode %lu\n", lblk, len, inode->i_ino); if (!len) return err; end = lblk + len - 1; BUG_ON(end < lblk); /* * ext4_clear_inode() depends on us taking i_es_lock unconditionally * so that we are sure __es_shrink() is done with the inode before it * is reclaimed. */ write_lock(&EXT4_I(inode)->i_es_lock); err = __es_remove_extent(inode, lblk, end, &reserved); write_unlock(&EXT4_I(inode)->i_es_lock); ext4_es_print_tree(inode); ext4_da_release_space(inode, reserved); return err; } static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei) { struct ext4_inode_info *ei; struct ext4_es_stats *es_stats; ktime_t start_time; u64 scan_time; int nr_to_walk; int nr_shrunk = 0; int retried = 0, nr_skipped = 0; es_stats = &sbi->s_es_stats; start_time = ktime_get(); retry: spin_lock(&sbi->s_es_lock); nr_to_walk = sbi->s_es_nr_inode; while (nr_to_walk-- > 0) { if (list_empty(&sbi->s_es_list)) { spin_unlock(&sbi->s_es_lock); goto out; } ei = list_first_entry(&sbi->s_es_list, struct ext4_inode_info, i_es_list); /* Move the inode to the tail */ list_move_tail(&ei->i_es_list, &sbi->s_es_list); /* * Normally we try hard to avoid shrinking precached inodes, * but we will as a last resort. */ if (!retried && ext4_test_inode_state(&ei->vfs_inode, EXT4_STATE_EXT_PRECACHED)) { nr_skipped++; continue; } if (ei == locked_ei || !write_trylock(&ei->i_es_lock)) { nr_skipped++; continue; } /* * Now we hold i_es_lock which protects us from inode reclaim * freeing inode under us */ spin_unlock(&sbi->s_es_lock); nr_shrunk += es_reclaim_extents(ei, &nr_to_scan); write_unlock(&ei->i_es_lock); if (nr_to_scan <= 0) goto out; spin_lock(&sbi->s_es_lock); } spin_unlock(&sbi->s_es_lock); /* * If we skipped any inodes, and we weren't able to make any * forward progress, try again to scan precached inodes. */ if ((nr_shrunk == 0) && nr_skipped && !retried) { retried++; goto retry; } if (locked_ei && nr_shrunk == 0) nr_shrunk = es_reclaim_extents(locked_ei, &nr_to_scan); out: scan_time = ktime_to_ns(ktime_sub(ktime_get(), start_time)); if (likely(es_stats->es_stats_scan_time)) es_stats->es_stats_scan_time = (scan_time + es_stats->es_stats_scan_time*3) / 4; else es_stats->es_stats_scan_time = scan_time; if (scan_time > es_stats->es_stats_max_scan_time) es_stats->es_stats_max_scan_time = scan_time; if (likely(es_stats->es_stats_shrunk)) es_stats->es_stats_shrunk = (nr_shrunk + es_stats->es_stats_shrunk*3) / 4; else es_stats->es_stats_shrunk = nr_shrunk; trace_ext4_es_shrink(sbi->s_sb, nr_shrunk, scan_time, nr_skipped, retried); return nr_shrunk; } static unsigned long ext4_es_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long nr; struct ext4_sb_info *sbi; sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker); nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_count(sbi->s_sb, sc->nr_to_scan, nr); return nr; } static unsigned long ext4_es_scan(struct shrinker *shrink, struct shrink_control *sc) { struct ext4_sb_info *sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker); int nr_to_scan = sc->nr_to_scan; int ret, nr_shrunk; ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret); nr_shrunk = __es_shrink(sbi, nr_to_scan, NULL); ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret); return nr_shrunk; } int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v) { struct ext4_sb_info *sbi = EXT4_SB((struct super_block *) seq->private); struct ext4_es_stats *es_stats = &sbi->s_es_stats; struct ext4_inode_info *ei, *max = NULL; unsigned int inode_cnt = 0; if (v != SEQ_START_TOKEN) return 0; /* here we just find an inode that has the max nr. of objects */ spin_lock(&sbi->s_es_lock); list_for_each_entry(ei, &sbi->s_es_list, i_es_list) { inode_cnt++; if (max && max->i_es_all_nr < ei->i_es_all_nr) max = ei; else if (!max) max = ei; } spin_unlock(&sbi->s_es_lock); seq_printf(seq, "stats:\n %lld objects\n %lld reclaimable objects\n", percpu_counter_sum_positive(&es_stats->es_stats_all_cnt), percpu_counter_sum_positive(&es_stats->es_stats_shk_cnt)); seq_printf(seq, " %lld/%lld cache hits/misses\n", percpu_counter_sum_positive(&es_stats->es_stats_cache_hits), percpu_counter_sum_positive(&es_stats->es_stats_cache_misses)); if (inode_cnt) seq_printf(seq, " %d inodes on list\n", inode_cnt); seq_printf(seq, "average:\n %llu us scan time\n", div_u64(es_stats->es_stats_scan_time, 1000)); seq_printf(seq, " %lu shrunk objects\n", es_stats->es_stats_shrunk); if (inode_cnt) seq_printf(seq, "maximum:\n %lu inode (%u objects, %u reclaimable)\n" " %llu us max scan time\n", max->vfs_inode.i_ino, max->i_es_all_nr, max->i_es_shk_nr, div_u64(es_stats->es_stats_max_scan_time, 1000)); return 0; } int ext4_es_register_shrinker(struct ext4_sb_info *sbi) { int err; /* Make sure we have enough bits for physical block number */ BUILD_BUG_ON(ES_SHIFT < 48); INIT_LIST_HEAD(&sbi->s_es_list); sbi->s_es_nr_inode = 0; spin_lock_init(&sbi->s_es_lock); sbi->s_es_stats.es_stats_shrunk = 0; err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_hits, 0, GFP_KERNEL); if (err) return err; err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_misses, 0, GFP_KERNEL); if (err) goto err1; sbi->s_es_stats.es_stats_scan_time = 0; sbi->s_es_stats.es_stats_max_scan_time = 0; err = percpu_counter_init(&sbi->s_es_stats.es_stats_all_cnt, 0, GFP_KERNEL); if (err) goto err2; err = percpu_counter_init(&sbi->s_es_stats.es_stats_shk_cnt, 0, GFP_KERNEL); if (err) goto err3; sbi->s_es_shrinker.scan_objects = ext4_es_scan; sbi->s_es_shrinker.count_objects = ext4_es_count; sbi->s_es_shrinker.seeks = DEFAULT_SEEKS; err = register_shrinker(&sbi->s_es_shrinker); if (err) goto err4; return 0; err4: percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); err3: percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); err2: percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); err1: percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); return err; } void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi) { percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); unregister_shrinker(&sbi->s_es_shrinker); } /* * Shrink extents in given inode from ei->i_es_shrink_lblk till end. Scan at * most *nr_to_scan extents, update *nr_to_scan accordingly. * * Return 0 if we hit end of tree / interval, 1 if we exhausted nr_to_scan. * Increment *nr_shrunk by the number of reclaimed extents. Also update * ei->i_es_shrink_lblk to where we should continue scanning. */ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end, int *nr_to_scan, int *nr_shrunk) { struct inode *inode = &ei->vfs_inode; struct ext4_es_tree *tree = &ei->i_es_tree; struct extent_status *es; struct rb_node *node; es = __es_tree_search(&tree->root, ei->i_es_shrink_lblk); if (!es) goto out_wrap; while (*nr_to_scan > 0) { if (es->es_lblk > end) { ei->i_es_shrink_lblk = end + 1; return 0; } (*nr_to_scan)--; node = rb_next(&es->rb_node); /* * We can't reclaim delayed extent from status tree because * fiemap, bigallic, and seek_data/hole need to use it. */ if (ext4_es_is_delayed(es)) goto next; if (ext4_es_is_referenced(es)) { ext4_es_clear_referenced(es); goto next; } rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); (*nr_shrunk)++; next: if (!node) goto out_wrap; es = rb_entry(node, struct extent_status, rb_node); } ei->i_es_shrink_lblk = es->es_lblk; return 1; out_wrap: ei->i_es_shrink_lblk = 0; return 0; } static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan) { struct inode *inode = &ei->vfs_inode; int nr_shrunk = 0; ext4_lblk_t start = ei->i_es_shrink_lblk; static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); if (ei->i_es_shk_nr == 0) return 0; if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) && __ratelimit(&_rs)) ext4_warning(inode->i_sb, "forced shrink of precached extents"); if (!es_do_reclaim_extents(ei, EXT_MAX_BLOCKS, nr_to_scan, &nr_shrunk) && start != 0) es_do_reclaim_extents(ei, start - 1, nr_to_scan, &nr_shrunk); ei->i_es_tree.cache_es = NULL; return nr_shrunk; } /* * Called to support EXT4_IOC_CLEAR_ES_CACHE. We can only remove * discretionary entries from the extent status cache. (Some entries * must be present for proper operations.) */ void ext4_clear_inode_es(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct extent_status *es; struct ext4_es_tree *tree; struct rb_node *node; write_lock(&ei->i_es_lock); tree = &EXT4_I(inode)->i_es_tree; tree->cache_es = NULL; node = rb_first(&tree->root); while (node) { es = rb_entry(node, struct extent_status, rb_node); node = rb_next(node); if (!ext4_es_is_delayed(es)) { rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); } } ext4_clear_inode_state(inode, EXT4_STATE_EXT_PRECACHED); write_unlock(&ei->i_es_lock); } #ifdef ES_DEBUG__ static void ext4_print_pending_tree(struct inode *inode) { struct ext4_pending_tree *tree; struct rb_node *node; struct pending_reservation *pr; printk(KERN_DEBUG "pending reservations for inode %lu:", inode->i_ino); tree = &EXT4_I(inode)->i_pending_tree; node = rb_first(&tree->root); while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); printk(KERN_DEBUG " %u", pr->lclu); node = rb_next(node); } printk(KERN_DEBUG "\n"); } #else #define ext4_print_pending_tree(inode) #endif int __init ext4_init_pending(void) { ext4_pending_cachep = kmem_cache_create("ext4_pending_reservation", sizeof(struct pending_reservation), 0, (SLAB_RECLAIM_ACCOUNT), NULL); if (ext4_pending_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_pending(void) { kmem_cache_destroy(ext4_pending_cachep); } void ext4_init_pending_tree(struct ext4_pending_tree *tree) { tree->root = RB_ROOT; } /* * __get_pending - retrieve a pointer to a pending reservation * * @inode - file containing the pending cluster reservation * @lclu - logical cluster of interest * * Returns a pointer to a pending reservation if it's a member of * the set, and NULL if not. Must be called holding i_es_lock. */ static struct pending_reservation *__get_pending(struct inode *inode, ext4_lblk_t lclu) { struct ext4_pending_tree *tree; struct rb_node *node; struct pending_reservation *pr = NULL; tree = &EXT4_I(inode)->i_pending_tree; node = (&tree->root)->rb_node; while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); if (lclu < pr->lclu) node = node->rb_left; else if (lclu > pr->lclu) node = node->rb_right; else if (lclu == pr->lclu) return pr; } return NULL; } /* * __insert_pending - adds a pending cluster reservation to the set of * pending reservations * * @inode - file containing the cluster * @lblk - logical block in the cluster to be added * * Returns 0 on successful insertion and -ENOMEM on failure. If the * pending reservation is already in the set, returns successfully. */ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; struct rb_node **p = &tree->root.rb_node; struct rb_node *parent = NULL; struct pending_reservation *pr; ext4_lblk_t lclu; int ret = 0; lclu = EXT4_B2C(sbi, lblk); /* search to find parent for insertion */ while (*p) { parent = *p; pr = rb_entry(parent, struct pending_reservation, rb_node); if (lclu < pr->lclu) { p = &(*p)->rb_left; } else if (lclu > pr->lclu) { p = &(*p)->rb_right; } else { /* pending reservation already inserted */ goto out; } } pr = kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); if (pr == NULL) { ret = -ENOMEM; goto out; } pr->lclu = lclu; rb_link_node(&pr->rb_node, parent, p); rb_insert_color(&pr->rb_node, &tree->root); out: return ret; } /* * __remove_pending - removes a pending cluster reservation from the set * of pending reservations * * @inode - file containing the cluster * @lblk - logical block in the pending cluster reservation to be removed * * Returns successfully if pending reservation is not a member of the set. */ static void __remove_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct pending_reservation *pr; struct ext4_pending_tree *tree; pr = __get_pending(inode, EXT4_B2C(sbi, lblk)); if (pr != NULL) { tree = &EXT4_I(inode)->i_pending_tree; rb_erase(&pr->rb_node, &tree->root); kmem_cache_free(ext4_pending_cachep, pr); } } /* * ext4_remove_pending - removes a pending cluster reservation from the set * of pending reservations * * @inode - file containing the cluster * @lblk - logical block in the pending cluster reservation to be removed * * Locking for external use of __remove_pending. */ void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_inode_info *ei = EXT4_I(inode); write_lock(&ei->i_es_lock); __remove_pending(inode, lblk); write_unlock(&ei->i_es_lock); } /* * ext4_is_pending - determine whether a cluster has a pending reservation * on it * * @inode - file containing the cluster * @lblk - logical block in the cluster * * Returns true if there's a pending reservation for the cluster in the * set of pending reservations, and false if not. */ bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); bool ret; read_lock(&ei->i_es_lock); ret = (bool)(__get_pending(inode, EXT4_B2C(sbi, lblk)) != NULL); read_unlock(&ei->i_es_lock); return ret; } /* * ext4_es_insert_delayed_block - adds a delayed block to the extents status * tree, adding a pending reservation where * needed * * @inode - file containing the newly added block * @lblk - logical block to be added * @allocated - indicates whether a physical cluster has been allocated for * the logical cluster that contains the block * * Returns 0 on success, negative error code on failure. */ int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, bool allocated) { struct extent_status newes; int err = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; es_debug("add [%u/1) delayed to extent status tree of inode %lu\n", lblk, inode->i_ino); newes.es_lblk = lblk; newes.es_len = 1; ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED); trace_ext4_es_insert_delayed_block(inode, &newes, allocated); ext4_es_insert_extent_check(inode, &newes); write_lock(&EXT4_I(inode)->i_es_lock); err = __es_remove_extent(inode, lblk, lblk, NULL); if (err != 0) goto error; retry: err = __es_insert_extent(inode, &newes); if (err == -ENOMEM && __es_shrink(EXT4_SB(inode->i_sb), 128, EXT4_I(inode))) goto retry; if (err != 0) goto error; if (allocated) __insert_pending(inode, lblk); error: write_unlock(&EXT4_I(inode)->i_es_lock); ext4_es_print_tree(inode); ext4_print_pending_tree(inode); return err; } /* * __es_delayed_clu - count number of clusters containing blocks that * are delayed only * * @inode - file containing block range * @start - logical block defining start of range * @end - logical block defining end of range * * Returns the number of clusters containing only delayed (not delayed * and unwritten) blocks in the range specified by @start and @end. Any * cluster or part of a cluster within the range and containing a delayed * and not unwritten block within the range is counted as a whole cluster. */ static unsigned int __es_delayed_clu(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct rb_node *node; ext4_lblk_t first_lclu, last_lclu; unsigned long long last_counted_lclu; unsigned int n = 0; /* guaranteed to be unequal to any ext4_lblk_t value */ last_counted_lclu = ~0ULL; es = __es_tree_search(&tree->root, start); while (es && (es->es_lblk <= end)) { if (ext4_es_is_delonly(es)) { if (es->es_lblk <= start) first_lclu = EXT4_B2C(sbi, start); else first_lclu = EXT4_B2C(sbi, es->es_lblk); if (ext4_es_end(es) >= end) last_lclu = EXT4_B2C(sbi, end); else last_lclu = EXT4_B2C(sbi, ext4_es_end(es)); if (first_lclu == last_counted_lclu) n += last_lclu - first_lclu; else n += last_lclu - first_lclu + 1; last_counted_lclu = last_lclu; } node = rb_next(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } return n; } /* * ext4_es_delayed_clu - count number of clusters containing blocks that * are both delayed and unwritten * * @inode - file containing block range * @lblk - logical block defining start of range * @len - number of blocks in range * * Locking for external use of __es_delayed_clu(). */ unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { struct ext4_inode_info *ei = EXT4_I(inode); ext4_lblk_t end; unsigned int n; if (len == 0) return 0; end = lblk + len - 1; WARN_ON(end < lblk); read_lock(&ei->i_es_lock); n = __es_delayed_clu(inode, lblk, end); read_unlock(&ei->i_es_lock); return n; } /* * __revise_pending - makes, cancels, or leaves unchanged pending cluster * reservations for a specified block range depending * upon the presence or absence of delayed blocks * outside the range within clusters at the ends of the * range * * @inode - file containing the range * @lblk - logical block defining the start of range * @len - length of range in blocks * * Used after a newly allocated extent is added to the extents status tree. * Requires that the extents in the range have either written or unwritten * status. Must be called while holding i_es_lock. */ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t end = lblk + len - 1; ext4_lblk_t first, last; bool f_del = false, l_del = false; if (len == 0) return; /* * Two cases - block range within single cluster and block range * spanning two or more clusters. Note that a cluster belonging * to a range starting and/or ending on a cluster boundary is treated * as if it does not contain a delayed extent. The new range may * have allocated space for previously delayed blocks out to the * cluster boundary, requiring that any pre-existing pending * reservation be canceled. Because this code only looks at blocks * outside the range, it should revise pending reservations * correctly even if the extent represented by the range can't be * inserted in the extents status tree due to ENOSPC. */ if (EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) { first = EXT4_LBLK_CMASK(sbi, lblk); if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); if (f_del) { __insert_pending(inode, first); } else { last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); if (l_del) __insert_pending(inode, last); else __remove_pending(inode, last); } } else { first = EXT4_LBLK_CMASK(sbi, lblk); if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); if (f_del) __insert_pending(inode, first); else __remove_pending(inode, first); last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); if (l_del) __insert_pending(inode, last); else __remove_pending(inode, last); } }
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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Dynamic queue limits (dql) - Definitions * * Copyright (c) 2011, Tom Herbert <therbert@google.com> * * This header file contains the definitions for dynamic queue limits (dql). * dql would be used in conjunction with a producer/consumer type queue * (possibly a HW queue). Such a queue would have these general properties: * * 1) Objects are queued up to some limit specified as number of objects. * 2) Periodically a completion process executes which retires consumed * objects. * 3) Starvation occurs when limit has been reached, all queued data has * actually been consumed, but completion processing has not yet run * so queuing new data is blocked. * 4) Minimizing the amount of queued data is desirable. * * The goal of dql is to calculate the limit as the minimum number of objects * needed to prevent starvation. * * The primary functions of dql are: * dql_queued - called when objects are enqueued to record number of objects * dql_avail - returns how many objects are available to be queued based * on the object limit and how many objects are already enqueued * dql_completed - called at completion time to indicate how many objects * were retired from the queue * * The dql implementation does not implement any locking for the dql data * structures, the higher layer should provide this. dql_queued should * be serialized to prevent concurrent execution of the function; this * is also true for dql_completed. However, dql_queued and dlq_completed can * be executed concurrently (i.e. they can be protected by different locks). */ #ifndef _LINUX_DQL_H #define _LINUX_DQL_H #ifdef __KERNEL__ #include <asm/bug.h> struct dql { /* Fields accessed in enqueue path (dql_queued) */ unsigned int num_queued; /* Total ever queued */ unsigned int adj_limit; /* limit + num_completed */ unsigned int last_obj_cnt; /* Count at last queuing */ /* Fields accessed only by completion path (dql_completed) */ unsigned int limit ____cacheline_aligned_in_smp; /* Current limit */ unsigned int num_completed; /* Total ever completed */ unsigned int prev_ovlimit; /* Previous over limit */ unsigned int prev_num_queued; /* Previous queue total */ unsigned int prev_last_obj_cnt; /* Previous queuing cnt */ unsigned int lowest_slack; /* Lowest slack found */ unsigned long slack_start_time; /* Time slacks seen */ /* Configuration */ unsigned int max_limit; /* Max limit */ unsigned int min_limit; /* Minimum limit */ unsigned int slack_hold_time; /* Time to measure slack */ }; /* Set some static maximums */ #define DQL_MAX_OBJECT (UINT_MAX / 16) #define DQL_MAX_LIMIT ((UINT_MAX / 2) - DQL_MAX_OBJECT) /* * Record number of objects queued. Assumes that caller has already checked * availability in the queue with dql_avail. */ static inline void dql_queued(struct dql *dql, unsigned int count) { BUG_ON(count > DQL_MAX_OBJECT); dql->last_obj_cnt = count; /* We want to force a write first, so that cpu do not attempt * to get cache line containing last_obj_cnt, num_queued, adj_limit * in Shared state, but directly does a Request For Ownership * It is only a hint, we use barrier() only. */ barrier(); dql->num_queued += count; } /* Returns how many objects can be queued, < 0 indicates over limit. */ static inline int dql_avail(const struct dql *dql) { return READ_ONCE(dql->adj_limit) - READ_ONCE(dql->num_queued); } /* Record number of completed objects and recalculate the limit. */ void dql_completed(struct dql *dql, unsigned int count); /* Reset dql state */ void dql_reset(struct dql *dql); /* Initialize dql state */ void dql_init(struct dql *dql, unsigned int hold_time); #endif /* _KERNEL_ */ #endif /* _LINUX_DQL_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 /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/cpu.h - generic cpu definition * * This is mainly for topological representation. We define the * basic 'struct cpu' here, which can be embedded in per-arch * definitions of processors. * * Basic handling of the devices is done in drivers/base/cpu.c * * CPUs are exported via sysfs in the devices/system/cpu * directory. */ #ifndef _LINUX_CPU_H_ #define _LINUX_CPU_H_ #include <linux/node.h> #include <linux/compiler.h> #include <linux/cpumask.h> #include <linux/cpuhotplug.h> struct device; struct device_node; struct attribute_group; struct cpu { int node_id; /* The node which contains the CPU */ int hotpluggable; /* creates sysfs control file if hotpluggable */ struct device dev; }; extern void boot_cpu_init(void); extern void boot_cpu_hotplug_init(void); extern void cpu_init(void); extern void trap_init(void); extern int register_cpu(struct cpu *cpu, int num); extern struct device *get_cpu_device(unsigned cpu); extern bool cpu_is_hotpluggable(unsigned cpu); extern bool arch_match_cpu_phys_id(int cpu, u64 phys_id); extern bool arch_find_n_match_cpu_physical_id(struct device_node *cpun, int cpu, unsigned int *thread); extern int cpu_add_dev_attr(struct device_attribute *attr); extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); extern ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); #ifdef CONFIG_HOTPLUG_CPU extern void unregister_cpu(struct cpu *cpu); extern ssize_t arch_cpu_probe(const char *, size_t); extern ssize_t arch_cpu_release(const char *, size_t); #endif /* * These states are not related to the core CPU hotplug mechanism. They are * used by various (sub)architectures to track internal state */ #define CPU_ONLINE 0x0002 /* CPU is up */ #define CPU_UP_PREPARE 0x0003 /* CPU coming up */ #define CPU_DEAD 0x0007 /* CPU dead */ #define CPU_DEAD_FROZEN 0x0008 /* CPU timed out on unplug */ #define CPU_POST_DEAD 0x0009 /* CPU successfully unplugged */ #define CPU_BROKEN 0x000B /* CPU did not die properly */ #ifdef CONFIG_SMP extern bool cpuhp_tasks_frozen; int add_cpu(unsigned int cpu); int cpu_device_up(struct device *dev); void notify_cpu_starting(unsigned int cpu); extern void cpu_maps_update_begin(void); extern void cpu_maps_update_done(void); int bringup_hibernate_cpu(unsigned int sleep_cpu); void bringup_nonboot_cpus(unsigned int setup_max_cpus); #else /* CONFIG_SMP */ #define cpuhp_tasks_frozen 0 static inline void cpu_maps_update_begin(void) { } static inline void cpu_maps_update_done(void) { } #endif /* CONFIG_SMP */ extern struct bus_type cpu_subsys; #ifdef CONFIG_HOTPLUG_CPU extern void cpus_write_lock(void); extern void cpus_write_unlock(void); extern void cpus_read_lock(void); extern void cpus_read_unlock(void); extern int cpus_read_trylock(void); extern void lockdep_assert_cpus_held(void); extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); void clear_tasks_mm_cpumask(int cpu); int remove_cpu(unsigned int cpu); int cpu_device_down(struct device *dev); extern void smp_shutdown_nonboot_cpus(unsigned int primary_cpu); #else /* CONFIG_HOTPLUG_CPU */ static inline void cpus_write_lock(void) { } static inline void cpus_write_unlock(void) { } static inline void cpus_read_lock(void) { } static inline void cpus_read_unlock(void) { } static inline int cpus_read_trylock(void) { return true; } static inline void lockdep_assert_cpus_held(void) { } static inline void cpu_hotplug_disable(void) { } static inline void cpu_hotplug_enable(void) { } static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { } #endif /* !CONFIG_HOTPLUG_CPU */ /* Wrappers which go away once all code is converted */ static inline void cpu_hotplug_begin(void) { cpus_write_lock(); } static inline void cpu_hotplug_done(void) { cpus_write_unlock(); } static inline void get_online_cpus(void) { cpus_read_lock(); } static inline void put_online_cpus(void) { cpus_read_unlock(); } #ifdef CONFIG_PM_SLEEP_SMP extern int freeze_secondary_cpus(int primary); extern void thaw_secondary_cpus(void); static inline int suspend_disable_secondary_cpus(void) { int cpu = 0; if (IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) cpu = -1; return freeze_secondary_cpus(cpu); } static inline void suspend_enable_secondary_cpus(void) { return thaw_secondary_cpus(); } #else /* !CONFIG_PM_SLEEP_SMP */ static inline void thaw_secondary_cpus(void) {} static inline int suspend_disable_secondary_cpus(void) { return 0; } static inline void suspend_enable_secondary_cpus(void) { } #endif /* !CONFIG_PM_SLEEP_SMP */ void cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); /* Attach to any functions which should be considered cpuidle. */ #define __cpuidle __section(".cpuidle.text") bool cpu_in_idle(unsigned long pc); void arch_cpu_idle(void); void arch_cpu_idle_prepare(void); void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); void arch_cpu_idle_dead(void); int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); void cpu_set_state_online(int cpu); void play_idle_precise(u64 duration_ns, u64 latency_ns); static inline void play_idle(unsigned long duration_us) { play_idle_precise(duration_us * NSEC_PER_USEC, U64_MAX); } #ifdef CONFIG_HOTPLUG_CPU bool cpu_wait_death(unsigned int cpu, int seconds); bool cpu_report_death(void); void cpuhp_report_idle_dead(void); #else static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ enum cpuhp_smt_control { CPU_SMT_ENABLED, CPU_SMT_DISABLED, CPU_SMT_FORCE_DISABLED, CPU_SMT_NOT_SUPPORTED, CPU_SMT_NOT_IMPLEMENTED, }; #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); extern void cpu_smt_check_topology(void); extern bool cpu_smt_possible(void); extern int cpuhp_smt_enable(void); extern int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval); #else # define cpu_smt_control (CPU_SMT_NOT_IMPLEMENTED) static inline void cpu_smt_disable(bool force) { } static inline void cpu_smt_check_topology(void) { } static inline bool cpu_smt_possible(void) { return false; } static inline int cpuhp_smt_enable(void) { return 0; } static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; } #endif extern bool cpu_mitigations_off(void); extern bool cpu_mitigations_auto_nosmt(void); #endif /* _LINUX_CPU_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 /* SPDX-License-Identifier: GPL-2.0 */ /* * NFS internal definitions */ #include "nfs4_fs.h" #include <linux/fs_context.h> #include <linux/security.h> #include <linux/crc32.h> #include <linux/sunrpc/addr.h> #include <linux/nfs_page.h> #include <linux/wait_bit.h> #define NFS_SB_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) extern const struct export_operations nfs_export_ops; struct nfs_string; struct nfs_pageio_descriptor; static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr) { if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid)) fattr->valid |= NFS_ATTR_FATTR_MOUNTPOINT; } static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr) { if (((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) == 0) || (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) && ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0))) return 0; return 1; } static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) { if (!(NFS_SB(dentry->d_sb)->flags & NFS_MOUNT_SOFTREVAL)) return false; if (!d_is_positive(dentry) || !NFS_FH(d_inode(dentry))->size) return false; return true; } /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. */ #define NFS_MAX_SECFLAVORS (12) /* * Value used if the user did not specify a port value. */ #define NFS_UNSPEC_PORT (-1) #define NFS_UNSPEC_RETRANS (UINT_MAX) #define NFS_UNSPEC_TIMEO (UINT_MAX) /* * Maximum number of pages that readdir can use for creating * a vmapped array of pages. */ #define NFS_MAX_READDIR_PAGES 8 struct nfs_client_initdata { unsigned long init_flags; const char *hostname; /* Hostname of the server */ const struct sockaddr *addr; /* Address of the server */ const char *nodename; /* Hostname of the client */ const char *ip_addr; /* IP address of the client */ size_t addrlen; struct nfs_subversion *nfs_mod; int proto; u32 minorversion; unsigned int nconnect; struct net *net; const struct rpc_timeout *timeparms; const struct cred *cred; }; /* * In-kernel mount arguments */ struct nfs_fs_context { bool internal; bool skip_reconfig_option_check; bool need_mount; bool sloppy; unsigned int flags; /* NFS{,4}_MOUNT_* flags */ unsigned int rsize, wsize; unsigned int timeo, retrans; unsigned int acregmin, acregmax; unsigned int acdirmin, acdirmax; unsigned int namlen; unsigned int options; unsigned int bsize; struct nfs_auth_info auth_info; rpc_authflavor_t selected_flavor; char *client_address; unsigned int version; unsigned int minorversion; char *fscache_uniq; unsigned short protofamily; unsigned short mountfamily; struct { union { struct sockaddr address; struct sockaddr_storage _address; }; size_t addrlen; char *hostname; u32 version; int port; unsigned short protocol; } mount_server; struct { union { struct sockaddr address; struct sockaddr_storage _address; }; size_t addrlen; char *hostname; char *export_path; int port; unsigned short protocol; unsigned short nconnect; unsigned short export_path_len; } nfs_server; struct nfs_fh *mntfh; struct nfs_server *server; struct nfs_subversion *nfs_mod; /* Information for a cloned mount. */ struct nfs_clone_mount { struct super_block *sb; struct dentry *dentry; struct nfs_fattr *fattr; unsigned int inherited_bsize; } clone_data; }; #define nfs_errorf(fc, fmt, ...) ((fc)->log.log ? \ errorf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); })) #define nfs_ferrorf(fc, fac, fmt, ...) ((fc)->log.log ? \ errorf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) #define nfs_invalf(fc, fmt, ...) ((fc)->log.log ? \ invalf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); -EINVAL; })) #define nfs_finvalf(fc, fac, fmt, ...) ((fc)->log.log ? \ invalf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); -EINVAL; })) #define nfs_warnf(fc, fmt, ...) ((fc)->log.log ? \ warnf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); })) #define nfs_fwarnf(fc, fac, fmt, ...) ((fc)->log.log ? \ warnf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc) { return fc->fs_private; } /* mount_clnt.c */ struct nfs_mount_request { struct sockaddr *sap; size_t salen; char *hostname; char *dirpath; u32 version; unsigned short protocol; struct nfs_fh *fh; int noresvport; unsigned int *auth_flav_len; rpc_authflavor_t *auth_flavs; struct net *net; }; extern int nfs_mount(struct nfs_mount_request *info); extern void nfs_umount(const struct nfs_mount_request *info); /* client.c */ extern const struct rpc_program nfs_program; extern void nfs_clients_init(struct net *net); extern void nfs_clients_exit(struct net *net); extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *); int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t); struct nfs_client *nfs_get_client(const struct nfs_client_initdata *); int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *); void nfs_server_insert_lists(struct nfs_server *); void nfs_server_remove_lists(struct nfs_server *); void nfs_init_timeout_values(struct rpc_timeout *to, int proto, int timeo, int retrans); int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t, rpc_authflavor_t); struct nfs_server *nfs_alloc_server(void); void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *); extern void nfs_put_client(struct nfs_client *); extern void nfs_free_client(struct nfs_client *); extern struct nfs_client *nfs4_find_client_ident(struct net *, int); extern struct nfs_client * nfs4_find_client_sessionid(struct net *, const struct sockaddr *, struct nfs4_sessionid *, u32); extern struct nfs_server *nfs_create_server(struct fs_context *); extern struct nfs_server *nfs4_create_server(struct fs_context *); extern struct nfs_server *nfs4_create_referral_server(struct fs_context *); extern int nfs4_update_server(struct nfs_server *server, const char *hostname, struct sockaddr *sap, size_t salen, struct net *net); extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); extern bool nfs_client_init_is_complete(const struct nfs_client *clp); extern int nfs_client_init_status(const struct nfs_client *clp); extern int nfs_wait_client_init_complete(const struct nfs_client *clp); extern void nfs_mark_client_ready(struct nfs_client *clp, int state); extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, const struct sockaddr *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, u32 minor_version); extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, struct inode *); extern struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, const struct sockaddr *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans); #ifdef CONFIG_PROC_FS extern int __init nfs_fs_proc_init(void); extern void nfs_fs_proc_exit(void); extern int nfs_fs_proc_net_init(struct net *net); extern void nfs_fs_proc_net_exit(struct net *net); #else static inline int nfs_fs_proc_net_init(struct net *net) { return 0; } static inline void nfs_fs_proc_net_exit(struct net *net) { } static inline int nfs_fs_proc_init(void) { return 0; } static inline void nfs_fs_proc_exit(void) { } #endif /* callback_xdr.c */ extern const struct svc_version nfs4_callback_version1; extern const struct svc_version nfs4_callback_version4; /* fs_context.c */ extern struct file_system_type nfs_fs_type; /* pagelist.c */ extern int __init nfs_init_nfspagecache(void); extern void nfs_destroy_nfspagecache(void); extern int __init nfs_init_readpagecache(void); extern void nfs_destroy_readpagecache(void); extern int __init nfs_init_writepagecache(void); extern void nfs_destroy_writepagecache(void); extern int __init nfs_init_directcache(void); extern void nfs_destroy_directcache(void); extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); int nfs_iocounter_wait(struct nfs_lock_context *l_ctx); extern const struct nfs_pageio_ops nfs_pgio_rw_ops; struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); void nfs_pgio_header_free(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, const struct rpc_call_ops *call_ops, int how, int flags); void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, const struct nfs_open_context *ctx2) { return cred_fscmp(ctx1->cred, ctx2->cred) == 0 && ctx1->state == ctx2->state; } /* nfs2xdr.c */ extern const struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); /* nfs3xdr.c */ extern const struct rpc_procinfo nfs3_procedures[]; extern int nfs3_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); /* nfs4xdr.c */ #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); #endif #ifdef CONFIG_NFS_V4_1 extern const u32 nfs41_maxread_overhead; extern const u32 nfs41_maxwrite_overhead; extern const u32 nfs41_maxgetdevinfo_overhead; #endif /* nfs4proc.c */ #if IS_ENABLED(CONFIG_NFS_V4) extern const struct rpc_procinfo nfs4_procedures[]; #endif #ifdef CONFIG_NFS_V4_SECURITY_LABEL extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); static inline struct nfs4_label * nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) { if (!dst || !src) return NULL; if (src->len > NFS4_MAXLABELLEN) return NULL; dst->lfs = src->lfs; dst->pi = src->pi; dst->len = src->len; memcpy(dst->label, src->label, src->len); return dst; } static inline void nfs4_label_free(struct nfs4_label *label) { if (label) { kfree(label->label); kfree(label); } return; } static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL)) nfsi->cache_validity |= NFS_INO_INVALID_LABEL; } #else static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } static inline void nfs4_label_free(void *label) {} static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { } static inline struct nfs4_label * nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) { return NULL; } #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ /* proc.c */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync); extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); /* dir.c */ extern void nfs_advise_use_readdirplus(struct inode *dir); extern void nfs_force_use_readdirplus(struct inode *dir); extern unsigned long nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc); extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); int nfs_create(struct inode *, struct dentry *, umode_t, bool); int nfs_mkdir(struct inode *, struct dentry *, umode_t); int nfs_rmdir(struct inode *, struct dentry *); int nfs_unlink(struct inode *, struct dentry *); int nfs_symlink(struct inode *, struct dentry *, const char *); int nfs_link(struct dentry *, struct inode *, struct dentry *); int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); /* file.c */ int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); loff_t nfs_file_llseek(struct file *, loff_t, int); ssize_t nfs_file_read(struct kiocb *, struct iov_iter *); int nfs_file_mmap(struct file *, struct vm_area_struct *); ssize_t nfs_file_write(struct kiocb *, struct iov_iter *); int nfs_file_release(struct inode *, struct file *); int nfs_lock(struct file *, int, struct file_lock *); int nfs_flock(struct file *, int, struct file_lock *); int nfs_check_flags(int); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; extern struct inode *nfs_alloc_inode(struct super_block *sb); extern void nfs_free_inode(struct inode *); extern int nfs_write_inode(struct inode *, struct writeback_control *); extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); void nfs_zap_acl_cache(struct inode *inode); extern bool nfs_check_cache_invalid(struct inode *, unsigned long); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); extern int nfs_wait_atomic_killable(atomic_t *p, unsigned int mode); /* super.c */ extern const struct super_operations nfs_sops; bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); int nfs_try_get_tree(struct fs_context *); int nfs_get_tree_common(struct fs_context *); void nfs_kill_super(struct super_block *); extern struct rpc_stat nfs_rpcstat; extern int __init register_nfs_fs(void); extern void __exit unregister_nfs_fs(void); extern bool nfs_sb_active(struct super_block *sb); extern void nfs_sb_deactive(struct super_block *sb); extern int nfs_client_for_each_server(struct nfs_client *clp, int (*fn)(struct nfs_server *, void *), void *data); /* io.c */ extern void nfs_start_io_read(struct inode *inode); extern void nfs_end_io_read(struct inode *inode); extern void nfs_start_io_write(struct inode *inode); extern void nfs_end_io_write(struct inode *inode); extern void nfs_start_io_direct(struct inode *inode); extern void nfs_end_io_direct(struct inode *inode); static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi) { return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0; } /* namespace.c */ #define NFS_PATH_CANONICAL 1 extern char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen, unsigned flags); extern struct vfsmount *nfs_d_automount(struct path *path); int nfs_submount(struct fs_context *, struct nfs_server *); int nfs_do_submount(struct fs_context *); /* getroot.c */ extern int nfs_get_root(struct super_block *s, struct fs_context *fc); #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool); #endif struct nfs_pgio_completion_ops; /* read.c */ extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); /* super.c */ void nfs_umount_begin(struct super_block *); int nfs_statfs(struct dentry *, struct kstatfs *); int nfs_show_options(struct seq_file *, struct dentry *); int nfs_show_devname(struct seq_file *, struct dentry *); int nfs_show_path(struct seq_file *, struct dentry *); int nfs_show_stats(struct seq_file *, struct dentry *); int nfs_reconfigure(struct fs_context *); /* write.c */ extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_commit_free(struct nfs_commit_data *p); extern void nfs_write_prepare(struct rpc_task *task, void *calldata); extern void nfs_commit_prepare(struct rpc_task *task, void *calldata); extern int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, int how, int flags); extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo); int nfs_scan_commit_list(struct list_head *src, struct list_head *dst, struct nfs_commit_info *cinfo, int max); unsigned long nfs_reqs_to_commit(struct nfs_commit_info *); int nfs_scan_commit(struct inode *inode, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo, u32 ds_commit_idx); int nfs_write_need_commit(struct nfs_pgio_header *); void nfs_writeback_update_inode(struct nfs_pgio_header *hdr); int nfs_generic_commit_list(struct inode *inode, struct list_head *head, int how, struct nfs_commit_info *cinfo); void nfs_retry_commit(struct list_head *page_list, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo, u32 ds_commit_idx); void nfs_commitdata_release(struct nfs_commit_data *data); void nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo); void nfs_request_add_commit_list_locked(struct nfs_page *req, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_request_remove_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo); void nfs_init_cinfo(struct nfs_commit_info *cinfo, struct inode *inode, struct nfs_direct_req *dreq); int nfs_key_timeout_notify(struct file *filp, struct inode *inode); bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode); void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio); int nfs_filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); #ifdef CONFIG_NFS_V4_1 static inline void pnfs_bucket_clear_pnfs_ds_commit_verifiers(struct pnfs_commit_bucket *buckets, unsigned int nbuckets) { unsigned int i; for (i = 0; i < nbuckets; i++) buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW; } static inline void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo) { struct pnfs_commit_array *array; rcu_read_lock(); list_for_each_entry_rcu(array, &cinfo->commits, cinfo_list) pnfs_bucket_clear_pnfs_ds_commit_verifiers(array->buckets, array->nbuckets); rcu_read_unlock(); } #else static inline void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo) { } #endif #ifdef CONFIG_MIGRATION extern int nfs_migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); #endif static inline int nfs_write_verifier_cmp(const struct nfs_write_verifier *v1, const struct nfs_write_verifier *v2) { return memcmp(v1->data, v2->data, sizeof(v1->data)); } static inline bool nfs_write_match_verf(const struct nfs_writeverf *verf, struct nfs_page *req) { return verf->committed > NFS_UNSTABLE && !nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier); } /* unlink.c */ extern struct rpc_task * nfs_async_rename(struct inode *old_dir, struct inode *new_dir, struct dentry *old_dentry, struct dentry *new_dentry, void (*complete)(struct rpc_task *, struct nfs_renamedata *)); extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry); /* direct.c */ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, struct nfs_direct_req *dreq); extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq); /* nfs4proc.c */ extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); extern int nfs40_walk_client_list(struct nfs_client *clp, struct nfs_client **result, const struct cred *cred); extern int nfs41_walk_client_list(struct nfs_client *clp, struct nfs_client **result, const struct cred *cred); extern void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *data); static inline struct inode *nfs_igrab_and_active(struct inode *inode) { struct super_block *sb = inode->i_sb; if (sb && nfs_sb_active(sb)) { if (igrab(inode)) return inode; nfs_sb_deactive(sb); } return NULL; } static inline void nfs_iput_and_deactive(struct inode *inode) { if (inode != NULL) { struct super_block *sb = inode->i_sb; iput(inode); nfs_sb_deactive(sb); } } /* * Determine the device name as a string */ static inline char *nfs_devname(struct dentry *dentry, char *buffer, ssize_t buflen) { char *dummy; return nfs_path(&dummy, dentry, buffer, buflen, NFS_PATH_CANONICAL); } /* * Determine the actual block size (and log2 thereof) */ static inline unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp) { /* make sure blocksize is a power of two */ if ((bsize & (bsize - 1)) || nrbitsp) { unsigned char nrbits; for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--) ; bsize = 1 << nrbits; if (nrbitsp) *nrbitsp = nrbits; } return bsize; } /* * Calculate the number of 512byte blocks used. */ static inline blkcnt_t nfs_calc_block_size(u64 tsize) { blkcnt_t used = (tsize + 511) >> 9; return (used > ULONG_MAX) ? ULONG_MAX : used; } /* * Compute and set NFS server blocksize */ static inline unsigned long nfs_block_size(unsigned long bsize, unsigned char *nrbitsp) { if (bsize < NFS_MIN_FILE_IO_SIZE) bsize = NFS_DEF_FILE_IO_SIZE; else if (bsize >= NFS_MAX_FILE_IO_SIZE) bsize = NFS_MAX_FILE_IO_SIZE; return nfs_block_bits(bsize, nrbitsp); } /* * Determine the maximum file size for a superblock */ static inline void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) { sb->s_maxbytes = (loff_t)maxfilesize; if (sb->s_maxbytes > MAX_LFS_FILESIZE || sb->s_maxbytes <= 0) sb->s_maxbytes = MAX_LFS_FILESIZE; } /* * Record the page as unstable (an extra writeback period) and mark its * inode as dirty. */ static inline void nfs_mark_page_unstable(struct page *page, struct nfs_commit_info *cinfo) { if (!cinfo->dreq) { struct inode *inode = page_file_mapping(page)->host; /* This page is really still in write-back - just that the * writeback is happening on the server now. */ inc_node_page_state(page, NR_WRITEBACK); inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK); __mark_inode_dirty(inode, I_DIRTY_DATASYNC); } } /* * Determine the number of bytes of data the page contains */ static inline unsigned int nfs_page_length(struct page *page) { loff_t i_size = i_size_read(page_file_mapping(page)->host); if (i_size > 0) { pgoff_t index = page_index(page); pgoff_t end_index = (i_size - 1) >> PAGE_SHIFT; if (index < end_index) return PAGE_SIZE; if (index == end_index) return ((i_size - 1) & ~PAGE_MASK) + 1; } return 0; } /* * Convert a umode to a dirent->d_type */ static inline unsigned char nfs_umode_to_dtype(umode_t mode) { return (mode >> 12) & 15; } /* * Determine the number of pages in an array of length 'len' and * with a base offset of 'base' */ static inline unsigned int nfs_page_array_len(unsigned int base, size_t len) { return ((unsigned long)len + (unsigned long)base + PAGE_SIZE - 1) >> PAGE_SHIFT; } /* * Convert a struct timespec64 into a 64-bit change attribute * * This does approximately the same thing as timespec64_to_ns(), * but for calculation efficiency, we multiply the seconds by * 1024*1024*1024. */ static inline u64 nfs_timespec_to_change_attr(const struct timespec64 *ts) { return ((u64)ts->tv_sec << 30) + ts->tv_nsec; } #ifdef CONFIG_CRC32 /** * nfs_fhandle_hash - calculate the crc32 hash for the filehandle * @fh - pointer to filehandle * * returns a crc32 hash for the filehandle that is compatible with * the one displayed by "wireshark". */ static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) { return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); } static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid) { return ~crc32_le(0xFFFFFFFF, &stateid->other[0], NFS4_STATEID_OTHER_SIZE); } #else static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) { return 0; } static inline u32 nfs_stateid_hash(nfs4_stateid *stateid) { return 0; } #endif static inline bool nfs_error_is_fatal(int err) { switch (err) { case -ERESTARTSYS: case -EINTR: case -EACCES: case -EDQUOT: case -EFBIG: case -EIO: case -ENOSPC: case -EROFS: case -ESTALE: case -E2BIG: case -ENOMEM: case -ETIMEDOUT: return true; default: return false; } } static inline bool nfs_error_is_fatal_on_server(int err) { switch (err) { case 0: case -ERESTARTSYS: case -EINTR: return false; } return nfs_error_is_fatal(err); } /* * Select between a default port value and a user-specified port value. * If a zero value is set, then autobind will be used. */ static inline void nfs_set_port(struct sockaddr *sap, int *port, const unsigned short default_port) { if (*port == NFS_UNSPEC_PORT) *port = default_port; rpc_set_port(sap, *port); }
2 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 /* * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include <uapi/linux/perf_event.h> #include <uapi/linux/bpf_perf_event.h> /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> # include <asm/local64.h> #endif struct perf_guest_info_callbacks { int (*is_in_guest)(void); int (*is_user_mode)(void); unsigned long (*get_guest_ip)(void); void (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <asm/hw_breakpoint.h> #endif #include <linux/list.h> #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/pid_namespace.h> #include <linux/workqueue.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/irq_work.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/atomic.h> #include <linux/sysfs.h> #include <linux/perf_regs.h> #include <linux/cgroup.h> #include <linux/refcount.h> #include <linux/security.h> #include <asm/local.h> struct perf_callchain_entry { __u64 nr; __u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { struct perf_callchain_entry *entry; u32 max_stack; u32 nr; short contexts; bool contexts_maxed; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, unsigned long off, unsigned long len); struct perf_raw_frag { union { struct perf_raw_frag *next; unsigned long pad; }; perf_copy_f copy; void *data; u32 size; } __packed; struct perf_raw_record { struct perf_raw_frag frag; u32 size; }; /* * branch stack layout: * nr: number of taken branches stored in entries[] * hw_idx: The low level index of raw branch records * for the most recent branch. * -1ULL means invalid/unknown. * * Note that nr can vary from sample to sample * branches (to, from) are stored from most recent * to least recent, i.e., entries[0] contains the most * recent branch. * The entries[] is an abstraction of raw branch records, * which may not be stored in age order in HW, e.g. Intel LBR. * The hw_idx is to expose the low level index of raw * branch record for the most recent branch aka entries[0]. * The hw_idx index is between -1 (unknown) and max depth, * which can be retrieved in /sys/devices/cpu/caps/branches. * For the architectures whose raw branch records are * already stored in age order, the hw_idx should be 0. */ struct perf_branch_stack { __u64 nr; __u64 hw_idx; struct perf_branch_entry entries[]; }; struct task_struct; /* * extra PMU register associated with an event */ struct hw_perf_event_extra { u64 config; /* register value */ unsigned int reg; /* register address or index */ int alloc; /* extra register already allocated */ int idx; /* index in shared_regs->regs[] */ }; /** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { #ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; u64 last_tag; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; int idx; int last_cpu; int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; struct { /* software */ struct hrtimer hrtimer; }; struct { /* tracepoint */ /* for tp_event->class */ struct list_head tp_list; }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct arch_hw_breakpoint info; struct list_head bp_list; }; #endif struct { /* amd_iommu */ u8 iommu_bank; u8 iommu_cntr; u16 padding; u64 conf; u64 conf1; }; }; /* * If the event is a per task event, this will point to the task in * question. See the comment in perf_event_alloc(). */ struct task_struct *target; /* * PMU would store hardware filter configuration * here. */ void *addr_filters; /* Last sync'ed generation of filters */ unsigned long addr_filters_gen; /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ #define PERF_HES_STOPPED 0x01 /* the counter is stopped */ #define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ #define PERF_HES_ARCH 0x04 int state; /* * The last observed hardware counter value, updated with a * local64_cmpxchg() such that pmu::read() can be called nested. */ local64_t prev_count; /* * The period to start the next sample with. */ u64 sample_period; union { struct { /* Sampling */ /* * The period we started this sample with. */ u64 last_period; /* * However much is left of the current period; * note that this is a full 64bit value and * allows for generation of periods longer * than hardware might allow. */ local64_t period_left; }; struct { /* Topdown events counting for context switch */ u64 saved_metric; u64 saved_slots; }; }; /* * State for throttling the event, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 interrupts_seq; u64 interrupts; /* * State for freq target events, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 freq_time_stamp; u64 freq_count_stamp; #endif }; struct perf_event; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ #define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */ #define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */ /** * pmu::capabilities flags */ #define PERF_PMU_CAP_NO_INTERRUPT 0x01 #define PERF_PMU_CAP_NO_NMI 0x02 #define PERF_PMU_CAP_AUX_NO_SG 0x04 #define PERF_PMU_CAP_EXTENDED_REGS 0x08 #define PERF_PMU_CAP_EXCLUSIVE 0x10 #define PERF_PMU_CAP_ITRACE 0x20 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 #define PERF_PMU_CAP_NO_EXCLUDE 0x80 #define PERF_PMU_CAP_AUX_OUTPUT 0x100 struct perf_output_handle; /** * struct pmu - generic performance monitoring unit */ struct pmu { struct list_head entry; struct module *module; struct device *dev; const struct attribute_group **attr_groups; const struct attribute_group **attr_update; const char *name; int type; /* * various common per-pmu feature flags */ int capabilities; int __percpu *pmu_disable_count; struct perf_cpu_context __percpu *pmu_cpu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; /* number of address filters this PMU can do */ unsigned int nr_addr_filters; /* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. */ void (*pmu_enable) (struct pmu *pmu); /* optional */ void (*pmu_disable) (struct pmu *pmu); /* optional */ /* * Try and initialize the event for this PMU. * * Returns: * -ENOENT -- @event is not for this PMU * * -ENODEV -- @event is for this PMU but PMU not present * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * * Other error return values are allowed. */ int (*event_init) (struct perf_event *event); /* * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */ #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ /* * Adds/Removes a counter to/from the PMU, can be done inside a * transaction, see the ->*_txn() methods. * * The add/del callbacks will reserve all hardware resources required * to service the event, this includes any counter constraint * scheduling etc. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on. * * ->add() called without PERF_EF_START should result in the same state * as ->add() followed by ->stop(). * * ->del() must always PERF_EF_UPDATE stop an event. If it calls * ->stop() that must deal with already being stopped without * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags); /* * Starts/Stops a counter present on the PMU. * * The PMI handler should stop the counter when perf_event_overflow() * returns !0. ->start() will be used to continue. * * Also used to change the sample period. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on -- will be called from NMI context with the PMU generates * NMIs. * * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); /* * Updates the counter value of the event. * * For sampling capable PMUs this will also update the software period * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event); /* * Group events scheduling is treated as a transaction, add * group events as a whole and perform one schedulability test. * If the test fails, roll back the whole group * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. * * Optional. */ void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. * * Optional. */ int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. * * Optional. */ void (*cancel_txn) (struct pmu *pmu); /* * Will return the value for perf_event_mmap_page::index for this event, * if no implementation is provided it will default to: event->hw.idx + 1. */ int (*event_idx) (struct perf_event *event); /*optional */ /* * context-switches callback */ void (*sched_task) (struct perf_event_context *ctx, bool sched_in); /* * Kmem cache of PMU specific data */ struct kmem_cache *task_ctx_cache; /* * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) * can be synchronized using this function. See Intel LBR callstack support * implementation and Perf core context switch handling callbacks for usage * examples. */ void (*swap_task_ctx) (struct perf_event_context *prev, struct perf_event_context *next); /* optional */ /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */ /* * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ /* * Take a snapshot of the AUX buffer without touching the event * state, so that preempting ->start()/->stop() callbacks does * not interfere with their logic. Called in PMI context. * * Returns the size of AUX data copied to the output handle. * * Optional. */ long (*snapshot_aux) (struct perf_event *event, struct perf_output_handle *handle, unsigned long size); /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. * * Runs in the context of the ioctl()ing process and is not serialized * with the rest of the PMU callbacks. */ int (*addr_filters_validate) (struct list_head *filters); /* optional */ /* * Synchronize address range filter configuration: * translate hw-agnostic filters into hardware configuration in * event::hw::addr_filters. * * Runs as a part of filter sync sequence that is done in ->start() * callback by calling perf_event_addr_filters_sync(). * * May (and should) traverse event::addr_filters::list, for which its * caller provides necessary serialization. */ void (*addr_filters_sync) (struct perf_event *event); /* optional */ /* * Check if event can be used for aux_output purposes for * events of this PMU. * * Runs from perf_event_open(). Should return 0 for "no match" * or non-zero for "match". */ int (*aux_output_match) (struct perf_event *event); /* optional */ /* * Filter events for PMU-specific reasons. */ int (*filter_match) (struct perf_event *event); /* optional */ /* * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { PERF_ADDR_FILTER_ACTION_STOP = 0, PERF_ADDR_FILTER_ACTION_START, PERF_ADDR_FILTER_ACTION_FILTER, }; /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */ struct perf_addr_filter { struct list_head entry; struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action; }; /** * struct perf_addr_filters_head - container for address range filters * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). */ struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; unsigned int nr_file_filters; }; struct perf_addr_filter_range { unsigned long start; unsigned long size; }; /** * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, }; struct file; struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs); /* * Event capabilities. For event_caps and groups caps. * * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) struct swevent_hlist { struct hlist_head heads[SWEVENT_HLIST_SIZE]; struct rcu_head rcu_head; }; #define PERF_ATTACH_CONTEXT 0x01 #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 #define PERF_ATTACH_TASK_DATA 0x08 #define PERF_ATTACH_ITRACE 0x10 #define PERF_ATTACH_SCHED_CB 0x20 #define PERF_ATTACH_CHILD 0x40 struct perf_cgroup; struct perf_buffer; struct pmu_event_list { raw_spinlock_t lock; struct list_head list; }; #define for_each_sibling_event(sibling, event) \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) /** * struct perf_event - performance event kernel representation: */ struct perf_event { #ifdef CONFIG_PERF_EVENTS /* * entry onto perf_event_context::event_list; * modifications require ctx->lock * RCU safe iterations. */ struct list_head event_entry; /* * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ struct list_head sibling_list; struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ struct rb_node group_node; u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the * group in tact which avoids us using the other two entries. */ struct list_head migrate_entry; struct hlist_node hlist_entry; struct list_head active_entry; int nr_siblings; /* Not serialized. Only written during event initialization. */ int event_caps; /* The cumulative AND of all event_caps for events in this group. */ int group_caps; struct perf_event *group_leader; struct pmu *pmu; void *pmu_private; enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count; /* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. */ u64 total_time_enabled; u64 total_time_running; u64 tstamp; /* * timestamp shadows the actual context timing but it can * be safely used in NMI interrupt context. It reflects the * context time as it was when the event was last scheduled in, * or when ctx_sched_in failed to schedule the event because we * run out of PMC. * * ctx_time already accounts for ctx->timestamp. Therefore to * compute ctx_time for a sample, simply add perf_clock(). */ u64 shadow_ctx_time; struct perf_event_attr attr; u16 header_size; u16 id_header_size; u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; atomic_long_t refcount; /* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running; /* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent; int oncpu; int cpu; struct list_head owner_entry; struct task_struct *owner; /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending; /* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync; /* delayed work for NMIs and such */ int pending_wakeup; int pending_kill; int pending_disable; struct irq_work pending; atomic_t event_limit; /* address range filters */ struct perf_addr_filters_head addr_filters; /* vma address array for file-based filders */ struct perf_addr_filter_range *addr_filter_ranges; unsigned long addr_filters_gen; /* for aux_output events */ struct perf_event *aux_event; void (*destroy)(struct perf_event *); struct rcu_head rcu_head; struct pid_namespace *ns; u64 id; u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; #ifdef CONFIG_BPF_SYSCALL perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; #endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; struct event_filter *filter; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; #endif #endif #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif #ifdef CONFIG_SECURITY void *security; #endif struct list_head sb_list; #endif /* CONFIG_PERF_EVENTS */ }; struct perf_event_groups { struct rb_root tree; u64 index; }; /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { struct pmu *pmu; /* * Protect the states of the events in the list, * nr_active, and the list: */ raw_spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex; struct list_head active_ctx_list; struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list; struct list_head pinned_active; struct list_head flexible_active; int nr_events; int nr_active; int is_active; int nr_stat; int nr_freq; int rotate_disable; /* * Set when nr_events != nr_active, except tolerant to events not * necessary to be active due to scheduling constraints, such as cgroups. */ int rotate_necessary; refcount_t refcount; struct task_struct *task; /* * Context clock, runs when context enabled. */ u64 time; u64 timestamp; /* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count; #ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ #endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; }; /* * Number of contexts where an event can trigger: * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 /** * struct perf_event_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int active_oncpu; int exclusive; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; unsigned int hrtimer_active; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; struct list_head cgrp_cpuctx_entry; #endif struct list_head sched_cb_entry; int sched_cb_usage; int online; /* * Per-CPU storage for iterators used in visit_groups_merge. The default * storage is of size 2 to hold the CPU and any CPU event iterators. */ int heap_size; struct perf_event **heap; struct perf_event *heap_default[2]; }; struct perf_output_handle { struct perf_event *event; struct perf_buffer *rb; unsigned long wakeup; unsigned long size; u64 aux_flags; union { void *addr; unsigned long head; }; int page; }; struct bpf_perf_event_data_kern { bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF /* * perf_cgroup_info keeps track of time_enabled for a cgroup. * This is a per-cpu dynamically allocated data structure. */ struct perf_cgroup_info { u64 time; u64 timestamp; }; struct perf_cgroup { struct cgroup_subsys_state css; struct perf_cgroup_info __percpu *info; }; /* * Must ensure cgroup is pinned (css_get) before calling * this function. In other words, we cannot call this function * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { return container_of(task_css_check(task, perf_event_cgrp_id, ctx ? lockdep_is_held(&ctx->lock) : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ #ifdef CONFIG_PERF_EVENTS extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event); extern void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size); extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); extern int perf_num_counters(void); extern const char *perf_pmu_name(void); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern void perf_pmu_resched(struct pmu *pmu); extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, perf_overflow_handler_t callback, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); struct perf_sample_data { /* * Fields set by perf_sample_data_init(), group so as to * minimize the cachelines touched. */ u64 addr; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 period; u64 weight; u64 txn; union perf_mem_data_src data_src; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ u64 type; u64 ip; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 id; u64 stream_id; struct { u32 cpu; u32 reserved; } cpu_entry; struct perf_callchain_entry *callchain; u64 aux_size; struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size; u64 phys_addr; u64 cgroup; } ____cacheline_aligned; /* default value for data source */ #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA)) static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ data->addr = addr; data->raw = NULL; data->br_stack = NULL; data->period = period; data->weight = 0; data->data_src.val = PERF_MEM_NA; data->txn = 0; } extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_prepare_sample(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_forward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); static inline bool is_default_overflow_handler(struct perf_event *event) { if (likely(event->overflow_handler == perf_event_output_forward)) return true; if (unlikely(event->overflow_handler == perf_event_output_backward)) return true; return false; } extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample); extern void perf_log_lost_samples(struct perf_event *event, u64 lost); static inline bool event_has_any_exclude_flag(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; return attr->exclude_idle || attr->exclude_user || attr->exclude_kernel || attr->exclude_hv || attr->exclude_guest || attr->exclude_host; } static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; } /* * Return 1 for a software event, 0 for a hardware event */ static inline int is_software_event(struct perf_event *event) { return event->event_caps & PERF_EV_CAP_SOFTWARE; } /* * Return 1 for event in sw context, 0 for event in hw context */ static inline int in_software_context(struct perf_event *event) { return event->ctx->pmu->task_ctx_nr == perf_sw_context; } static inline int is_exclusive_pmu(struct pmu *pmu) { return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE; } extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* * When generating a perf sample in-line, instead of from an interrupt / * exception, we lack a pt_regs. This is typically used from software events * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. * * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests * - sp for PERF_SAMPLE_CALLCHAIN * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) * * NOTE: assumes @regs is otherwise already 0 filled; this is important for * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr); } DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); /* * 'Special' version for the scheduler, it hard assumes no recursion, * which is guaranteed by us not actually scheduling inside other swevents * because those disable preemption. */ static __always_inline void perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(event_id, nr, regs, addr); } } extern struct static_key_false perf_sched_events; static __always_inline bool perf_sw_migrate_enabled(void) { if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS])) return true; return false; } static inline void perf_event_task_migrate(struct task_struct *task) { if (perf_sw_migrate_enabled()) task->sched_migrated = 1; } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (perf_sw_migrate_enabled() && task->sched_migrated) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0); task->sched_migrated = 0; } } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); extern void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; } else { ctx->contexts_maxed = true; return -1; /* no more room, stop walking the stack */ } } static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; } else { return -1; /* no more room, stop walking the stack */ } } extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); int perf_proc_update_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_event_max_stack_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 /* Finer grained perf_event_open(2) access control. */ #define PERF_SECURITY_CPU 1 #define PERF_SECURITY_KERNEL 2 #define PERF_SECURITY_TRACEPOINT 3 static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } static inline int perf_allow_kernel(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_KERNEL); } static inline int perf_allow_cpu(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_CPU); } static inline int perf_allow_tracepoint(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags # define perf_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) # define perf_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif static inline bool has_branch_stack(struct perf_event *event) { return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; } static inline bool needs_branch_stack(struct perf_event *event) { return event->attr.branch_sample_type != 0; } static inline bool has_aux(struct perf_event *event) { return event->pmu->setup_aux; } static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; } static inline bool has_addr_filter(struct perf_event *event) { return event->pmu->nr_addr_filters; } /* * An inherited event uses parent's filters */ static inline struct perf_addr_filters_head * perf_event_addr_filters(struct perf_event *event) { struct perf_addr_filters_head *ifh = &event->addr_filters; if (event->parent) ifh = &event->parent->addr_filters; return ifh; } extern void perf_event_addr_filters_sync(struct perf_event *event); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, struct perf_output_handle *handle, unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } static inline void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) { } static inline int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; } static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void perf_event_task_migrate(struct task_struct *task) { } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event *perf_get_event(struct file *file) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); } static inline int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline int perf_event_refresh(struct perf_event *event, int refresh) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline int perf_register_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline int perf_unregister_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } static inline void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; } static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } static inline int perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else static inline void perf_restore_debug_store(void) { } #endif static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) { return frag->pad < sizeof(u64); } #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) struct perf_pmu_events_attr { struct device_attribute attr; u64 id; const char *event_str; }; struct perf_pmu_events_ht_attr { struct device_attribute attr; u64 id; const char *event_str_ht; const char *event_str_noht; }; ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, \ }; #define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = _str, \ }; #define PMU_FORMAT_ATTR(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ \ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) /* Performance counter hotplug functions */ #ifdef CONFIG_PERF_EVENTS int perf_event_init_cpu(unsigned int cpu); int perf_event_exit_cpu(unsigned int cpu); #else #define perf_event_init_cpu NULL #define perf_event_exit_cpu NULL #endif extern void __weak arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now); #endif /* _LINUX_PERF_EVENT_H */
21 21 21 21 21 21 21 21 21 21 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 // SPDX-License-Identifier: GPL-2.0 #include <linux/spinlock.h> #include <linux/task_work.h> #include <linux/tracehook.h> static struct callback_head work_exited; /* all we need is ->next == NULL */ /** * task_work_add - ask the @task to execute @work->func() * @task: the task which should run the callback * @work: the callback to run * @notify: how to notify the targeted task * * Queue @work for task_work_run() below and notify the @task if @notify * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the * it will interrupt the targeted task and run the task_work. @TWA_RESUME * work is run only when the task exits the kernel and returns to user mode, * or before entering guest mode. Fails if the @task is exiting/exited and thus * it can't process this @work. Otherwise @work->func() will be called when the * @task goes through one of the aforementioned transitions, or exits. * * If the targeted task is exiting, then an error is returned and the work item * is not queued. It's up to the caller to arrange for an alternative mechanism * in that case. * * Note: there is no ordering guarantee on works queued here. The task_work * list is LIFO. * * RETURNS: * 0 if succeeds or -ESRCH. */ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; unsigned long flags; do { head = READ_ONCE(task->task_works); if (unlikely(head == &work_exited)) return -ESRCH; work->next = head; } while (cmpxchg(&task->task_works, head, work) != head); switch (notify) { case TWA_NONE: break; case TWA_RESUME: set_notify_resume(task); break; case TWA_SIGNAL: /* * Only grab the sighand lock if we don't already have some * task_work pending. This pairs with the smp_store_mb() * in get_signal(), see comment there. */ if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) && lock_task_sighand(task, &flags)) { task->jobctl |= JOBCTL_TASK_WORK; signal_wake_up(task, 0); unlock_task_sighand(task, &flags); } break; default: WARN_ON_ONCE(1); break; } return 0; } /** * task_work_cancel - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @func: identifies the work to remove * * Find the last queued pending work with ->func == @func and remove * it from queue. * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel(struct task_struct *task, task_work_func_t func) { struct callback_head **pprev = &task->task_works; struct callback_head *work; unsigned long flags; if (likely(!task->task_works)) return NULL; /* * If cmpxchg() fails we continue without updating pprev. * Either we raced with task_work_add() which added the * new entry before this work, we will find it again. Or * we raced with task_work_run(), *pprev == NULL/exited. */ raw_spin_lock_irqsave(&task->pi_lock, flags); while ((work = READ_ONCE(*pprev))) { if (work->func != func) pprev = &work->next; else if (cmpxchg(pprev, work, work->next) == work) break; } raw_spin_unlock_irqrestore(&task->pi_lock, flags); return work; } /** * task_work_run - execute the works added by task_work_add() * * Flush the pending works. Should be used by the core kernel code. * Called before the task returns to the user-mode or stops, or when * it exits. In the latter case task_work_add() can no longer add the * new work after task_work_run() returns. */ void task_work_run(void) { struct task_struct *task = current; struct callback_head *work, *head, *next; for (;;) { /* * work->func() can do task_work_add(), do not set * work_exited unless the list is empty. */ do { head = NULL; work = READ_ONCE(task->task_works); if (!work) { if (task->flags & PF_EXITING) head = &work_exited; else break; } } while (cmpxchg(&task->task_works, work, head) != work); if (!work) break; /* * Synchronize with task_work_cancel(). It can not remove * the first entry == work, cmpxchg(task_works) must fail. * But it can remove another entry from the ->next list. */ raw_spin_lock_irq(&task->pi_lock); raw_spin_unlock_irq(&task->pi_lock); do { next = work->next; work->func(work); work = next; cond_resched(); } while (work); } }
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 21 21 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 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * demand-loading started 01.12.91 - seems it is high on the list of * things wanted, and it should be easy to implement. - Linus */ /* * Ok, demand-loading was easy, shared pages a little bit tricker. Shared * pages started 02.12.91, seems to work. - Linus. * * Tested sharing by executing about 30 /bin/sh: under the old kernel it * would have taken more than the 6M I have free, but it worked well as * far as I could see. * * Also corrected some "invalidate()"s - I wasn't doing enough of them. */ /* * Real VM (paging to/from disk) started 18.12.91. Much more work and * thought has to go into this. Oh, well.. * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. * Found it. Everything seems to work now. * 20.12.91 - Ok, making the swap-device changeable like the root. */ /* * 05.04.94 - Multi-page memory management added for v1.1. * Idea by Alex Bligh (alex@cconcepts.co.uk) * * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG * (Gerhard.Wichert@pdb.siemens.de) * * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) */ #include <linux/kernel_stat.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> #include <linux/delayacct.h> #include <linux/init.h> #include <linux/pfn_t.h> #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/swapops.h> #include <linux/elf.h> #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> #include <linux/dax.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/vmalloc.h> #include <trace/events/kmem.h> #include <asm/io.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include "pgalloc-track.h" #include "internal.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ unsigned long max_mapnr; EXPORT_SYMBOL(max_mapnr); struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end * of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL * and ZONE_HIGHMEM. */ void *high_memory; EXPORT_SYMBOL(high_memory); /* * Randomize the address space (stacks, mmaps, brk, etc.). * * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, * as ancient (libc5 based) binaries can segfault. ) */ int randomize_va_space __read_mostly = #ifdef CONFIG_COMPAT_BRK 1; #else 2; #endif #ifndef arch_faults_on_old_pte static inline bool arch_faults_on_old_pte(void) { /* * Those arches which don't have hw access flag feature need to * implement their own helper. By default, "true" means pagefault * will be hit on old pte. */ return true; } #endif static int __init disable_randmaps(char *s) { randomize_va_space = 0; return 1; } __setup("norandmaps", disable_randmaps); unsigned long zero_pfn __read_mostly; EXPORT_SYMBOL(zero_pfn); unsigned long highest_memmap_pfn __read_mostly; /* * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ static int __init init_zero_pfn(void) { zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } early_initcall(init_zero_pfn); void mm_trace_rss_stat(struct mm_struct *mm, int member, long count) { trace_rss_stat(mm, member, count); } #if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct mm_struct *mm) { int i; for (i = 0; i < NR_MM_COUNTERS; i++) { if (current->rss_stat.count[i]) { add_mm_counter(mm, i, current->rss_stat.count[i]); current->rss_stat.count[i] = 0; } } current->rss_stat.events = 0; } static void add_mm_counter_fast(struct mm_struct *mm, int member, int val) { struct task_struct *task = current; if (likely(task->mm == mm)) task->rss_stat.count[member] += val; else add_mm_counter(mm, member, val); } #define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1) #define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1) /* sync counter once per 64 page faults */ #define TASK_RSS_EVENTS_THRESH (64) static void check_sync_rss_stat(struct task_struct *task) { if (unlikely(task != current)) return; if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH)) sync_mm_rss(task->mm); } #else /* SPLIT_RSS_COUNTING */ #define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member) #define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member) static void check_sync_rss_stat(struct task_struct *task) { } #endif /* SPLIT_RSS_COUNTING */ /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pmd_t *pmd; unsigned long next; unsigned long start; start = addr; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; if (start < floor) return; if (ceiling) { ceiling &= PUD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pud_t *pud; unsigned long next; unsigned long start; start = addr; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); start &= P4D_MASK; if (start < floor) return; if (ceiling) { ceiling &= P4D_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pud = pud_offset(p4d, start); p4d_clear(p4d); pud_free_tlb(tlb, pud, start); mm_dec_nr_puds(tlb->mm); } static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { p4d_t *p4d; unsigned long next; unsigned long start; start = addr; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; free_pud_range(tlb, p4d, addr, next, floor, ceiling); } while (p4d++, addr = next, addr != end); start &= PGDIR_MASK; if (start < floor) return; if (ceiling) { ceiling &= PGDIR_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; p4d = p4d_offset(pgd, start); pgd_clear(pgd); p4d_free_tlb(tlb, p4d, start); } /* * This function frees user-level page tables of a process. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pgd_t *pgd; unsigned long next; /* * The next few lines have given us lots of grief... * * Why are we testing PMD* at this top level? Because often * there will be no work to do at all, and we'd prefer not to * go all the way down to the bottom just to discover that. * * Why all these "- 1"s? Because 0 represents both the bottom * of the address space and the top of it (using -1 for the * top wouldn't help much: the masks would do the wrong thing). * The rule is that addr 0 and floor 0 refer to the bottom of * the address space, but end 0 and ceiling 0 refer to the top * Comparisons need to use "end - 1" and "ceiling - 1" (though * that end 0 case should be mythical). * * Wherever addr is brought up or ceiling brought down, we must * be careful to reject "the opposite 0" before it confuses the * subsequent tests. But what about where end is brought down * by PMD_SIZE below? no, end can't go down to 0 there. * * Whereas we round start (addr) and ceiling down, by different * masks at different levels, in order to test whether a table * now has no other vmas using it, so can be freed, we don't * bother to round floor or end up - the tests don't need that. */ addr &= PMD_MASK; if (addr < floor) { addr += PMD_SIZE; if (!addr) return; } if (ceiling) { ceiling &= PMD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) end -= PMD_SIZE; if (addr > end - 1) return; /* * We add page table cache pages with PAGE_SIZE, * (see pte_free_tlb()), flush the tlb if we need */ tlb_change_page_size(tlb, PAGE_SIZE); pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long floor, unsigned long ceiling) { while (vma) { struct vm_area_struct *next = vma->vm_next; unsigned long addr = vma->vm_start; /* * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ unlink_anon_vmas(vma); unlink_file_vma(vma); if (is_vm_hugetlb_page(vma)) { hugetlb_free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } else { /* * Optimization: gather nearby vmas into one call down */ while (next && next->vm_start <= vma->vm_end + PMD_SIZE && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; unlink_anon_vmas(vma); unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } vma = next; } } int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl; pgtable_t new = pte_alloc_one(mm); if (!new) return -ENOMEM; /* * Ensure all pte setup (eg. pte page lock and page clearing) are * visible before the pte is made visible to other CPUs by being * put into page tables. * * The other side of the story is the pointer chasing in the page * table walking code (when walking the page table without locking; * ie. most of the time). Fortunately, these data accesses consist * of a chain of data-dependent loads, meaning most CPUs (alpha * being the notable exception) will already guarantee loads are * seen in-order. See the alpha page table accessors for the * smp_rmb() barriers in page table walking code. */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ ptl = pmd_lock(mm, pmd); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm_inc_nr_ptes(mm); pmd_populate(mm, pmd, new); new = NULL; } spin_unlock(ptl); if (new) pte_free(mm, new); return 0; } int __pte_alloc_kernel(pmd_t *pmd) { pte_t *new = pte_alloc_one_kernel(&init_mm); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&init_mm.page_table_lock); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; } spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); return 0; } static inline void init_rss_vec(int *rss) { memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); } static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; if (current->mm == mm) sync_mm_rss(mm); for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); } /* * This function is called to print an error when a bad pte * is found. For example, we might have a PFN-mapped pte in * a region that doesn't allow it. * * The calling function must still handle the error. */ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. */ if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; return; } if (nr_unshown) { pr_alert("BUG: Bad page map: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; } nr_shown = 0; } if (nr_shown++ == 0) resume = jiffies + 60 * HZ; mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; index = linear_page_index(vma, addr); pr_alert("BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", current->comm, (long long)pte_val(pte), (long long)pmd_val(*pmd)); if (page) dump_page(page, "bad pte"); pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, vma->vm_file ? vma->vm_file->f_op->mmap : NULL, mapping ? mapping->a_ops->readpage : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } /* * vm_normal_page -- This function gets the "struct page" associated with a pte. * * "Special" mappings do not wish to be associated with a "struct page" (either * it doesn't exist, or it exists but they don't want to touch it). In this * case, NULL is returned here. "Normal" mappings do have a struct page. * * There are 2 broad cases. Firstly, an architecture may define a pte_special() * pte bit, in which case this function is trivial. Secondly, an architecture * may not have a spare pte bit, which requires a more complicated scheme, * described below. * * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a * special mapping (even if there are underlying and valid "struct pages"). * COWed pages of a VM_PFNMAP are always normal. * * The way we recognize COWed pages within VM_PFNMAP mappings is through the * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit * set, and the vm_pgoff will point to the first PFN mapped: thus every special * mapping will always honor the rule * * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) * * And for normal mappings this is false. * * This restricts such mappings to be a linear translation from virtual address * to pfn. To get around this restriction, we allow arbitrary mappings so long * as the vma is not a COW mapping; in that case, we know that all ptes are * special (because none can have been COWed). * * * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. * * VM_MIXEDMAP mappings can likewise contain memory with or without "struct * page" backing, however the difference is that _all_ pages with a struct * page (that is, those where pfn_valid is true) are refcounted and considered * normal pages by the VM. The disadvantage is that pages are refcounted * (which can be slower and simply not an option for some PFNMAP users). The * advantage is that we don't have to follow the strict linearity rule of * PFNMAP mappings in order to support COWable mappings. * */ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { unsigned long pfn = pte_pfn(pte); if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { if (likely(!pte_special(pte))) goto check_pfn; if (vma->vm_ops && vma->vm_ops->find_special_page) return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (is_zero_pfn(pfn)) return NULL; if (pte_devmap(pte)) return NULL; print_bad_pte(vma, addr, pte, NULL); return NULL; } /* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (is_zero_pfn(pfn)) return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { unsigned long pfn = pmd_pfn(pmd); /* * There is no pmd_special() but there may be special pmds, e.g. * in a direct-access (dax) mapping, so let's just replicate the * !CONFIG_ARCH_HAS_PTE_SPECIAL case from vm_normal_page() here. */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (pmd_devmap(pmd)) return NULL; if (is_huge_zero_pmd(pmd)) return NULL; if (unlikely(pfn > highest_memmap_pfn)) return NULL; /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #endif /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range * covered by this vma. */ static unsigned long copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long addr, int *rss) { unsigned long vm_flags = dst_vma->vm_flags; pte_t pte = *src_pte; struct page *page; swp_entry_t entry = pte_to_swp_entry(pte); if (likely(!non_swap_entry(entry))) { if (swap_duplicate(entry) < 0) return entry.val; /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); if (list_empty(&dst_mm->mmlist)) list_add(&dst_mm->mmlist, &src_mm->mmlist); spin_unlock(&mmlist_lock); } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { page = migration_entry_to_page(entry); rss[mm_counter(page)]++; if (is_write_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both * parent and child to be set to read. */ make_migration_entry_read(&entry); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(*src_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_private_entry(entry)) { page = device_private_entry_to_page(entry); /* * Update rss count even for unaddressable pages, as * they should treated just like normal pages in this * respect. * * We will likely want to have some new rss counters * for unaddressable pages, at some point. But for now * keep things as they are. */ get_page(page); rss[mm_counter(page)]++; page_dup_rmap(page, false); /* * We do not preserve soft-dirty information, because so * far, checkpoint/restore is the only feature that * requires that. And checkpoint/restore does not work * when a device driver is involved (you cannot easily * save and restore device driver state). */ if (is_write_device_private_entry(entry) && is_cow_mapping(vm_flags)) { make_device_private_entry_read(&entry); pte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } if (!userfaultfd_wp(dst_vma)) pte = pte_swp_clear_uffd_wp(pte); set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } /* * Copy a present and normal page if necessary. * * NOTE! The usual case is that this doesn't need to do * anything, and can just return a positive value. That * will let the caller know that it can just increase * the page refcount and re-use the pte the traditional * way. * * But _if_ we need to copy it because it needs to be * pinned in the parent (and the child should get its own * copy rather than just a reference to the same page), * we'll do that here and return zero to let the caller * know we're done. * * And if we need a pre-allocated page but don't yet have * one, return a negative error to let the preallocation * code know so that it can do so outside the page table * lock. */ static inline int copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc, pte_t pte, struct page *page) { struct mm_struct *src_mm = src_vma->vm_mm; struct page *new_page; if (!is_cow_mapping(src_vma->vm_flags)) return 1; /* * What we want to do is to check whether this page may * have been pinned by the parent process. If so, * instead of wrprotect the pte on both sides, we copy * the page immediately so that we'll always guarantee * the pinned page won't be randomly replaced in the * future. * * The page pinning checks are just "has this mm ever * seen pinning", along with the (inexact) check of * the page count. That might give false positives for * for pinning, but it will work correctly. */ if (likely(!atomic_read(&src_mm->has_pinned))) return 1; if (likely(!page_maybe_dma_pinned(page))) return 1; new_page = *prealloc; if (!new_page) return -EAGAIN; /* * We have a prealloc page, all good! Take it * over and copy the page & arm it. */ *prealloc = NULL; copy_user_highpage(new_page, page, addr, src_vma); __SetPageUptodate(new_page); page_add_new_anon_rmap(new_page, dst_vma, addr, false); lru_cache_add_inactive_or_unevictable(new_page, dst_vma); rss[mm_counter(new_page)]++; /* All done, just insert the new page copy in the child */ pte = mk_pte(new_page, dst_vma->vm_page_prot); pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); if (userfaultfd_pte_wp(dst_vma, *src_pte)) /* Uffd-wp needs to be delivered to dest pte as well */ pte = pte_wrprotect(pte_mkuffd_wp(pte)); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } /* * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page * is required to copy this pte. */ static inline int copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc) { struct mm_struct *src_mm = src_vma->vm_mm; unsigned long vm_flags = src_vma->vm_flags; pte_t pte = *src_pte; struct page *page; page = vm_normal_page(src_vma, addr, pte); if (page) { int retval; retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, addr, rss, prealloc, pte, page); if (retval <= 0) return retval; get_page(page); page_dup_rmap(page, false); rss[mm_counter(page)]++; } /* * If it's a COW mapping, write protect it both * in the parent and the child */ if (is_cow_mapping(vm_flags) && pte_write(pte)) { ptep_set_wrprotect(src_mm, addr, src_pte); pte = pte_wrprotect(pte); } /* * If it's a shared mapping, mark it clean in * the child */ if (vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); if (!userfaultfd_wp(dst_vma)) pte = pte_clear_uffd_wp(pte); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } static inline struct page * page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, unsigned long addr) { struct page *new_page; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr); if (!new_page) return NULL; if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { put_page(new_page); return NULL; } cgroup_throttle_swaprate(new_page, GFP_KERNEL); return new_page; } static int copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; int progress, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; struct page *prealloc = NULL; again: progress = 0; init_rss_vec(rss); dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) { ret = -ENOMEM; goto out; } src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); orig_src_pte = src_pte; orig_dst_pte = dst_pte; arch_enter_lazy_mmu_mode(); do { /* * We are holding two locks at this point - either of them * could generate latencies in another task on another CPU. */ if (progress >= 32) { progress = 0; if (need_resched() || spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) break; } if (pte_none(*src_pte)) { progress++; continue; } if (unlikely(!pte_present(*src_pte))) { entry.val = copy_nonpresent_pte(dst_mm, src_mm, dst_pte, src_pte, dst_vma, src_vma, addr, rss); if (entry.val) break; progress += 8; continue; } /* copy_present_pte() will clear `*prealloc' if consumed */ ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, addr, rss, &prealloc); /* * If we need a pre-allocated page for this pte, drop the * locks, allocate, and try again. */ if (unlikely(ret == -EAGAIN)) break; if (unlikely(prealloc)) { /* * pre-alloc page cannot be reused by next time so as * to strictly follow mempolicy (e.g., alloc_page_vma() * will allocate page according to address). This * could only happen if one pinned pte changed. */ put_page(prealloc); prealloc = NULL; } progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); pte_unmap(orig_src_pte); add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); if (entry.val) { if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { ret = -ENOMEM; goto out; } entry.val = 0; } else if (ret) { WARN_ON_ONCE(ret != -EAGAIN); prealloc = page_copy_prealloc(src_mm, src_vma, addr); if (!prealloc) return -ENOMEM; /* We've captured and resolved the error. Reset, try again. */ ret = 0; } if (addr != end) goto again; out: if (unlikely(prealloc)) put_page(prealloc); return ret; } static inline int copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); if (!dst_pmd) return -ENOMEM; src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } static inline int copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } static inline int copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); if (!dst_p4d) return -ENOMEM; src_p4d = p4d_offset(src_pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; unsigned long addr = src_vma->vm_start; unsigned long end = src_vma->vm_end; struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; bool is_cow; int ret; /* * Don't copy ptes where a page fault will fill them correctly. * Fork becomes much lighter when there are big shared or private * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && !src_vma->anon_vma) return 0; if (is_vm_hugetlb_page(src_vma)) return copy_hugetlb_page_range(dst_mm, src_mm, src_vma); if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine */ ret = track_pfn_copy(src_vma); if (ret) return ret; } /* * We need to invalidate the secondary MMU mappings only when * there could be a permission downgrade on the ptes of the * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, src_vma, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); /* * Disabling preemption is not needed for the write side, as * the read side doesn't spin, but goes to the mmap_lock. * * Use the raw variant of the seqcount_t write API to avoid * lockdep complaining about preemptibility. */ mmap_assert_write_locked(src_mm); raw_write_seqcount_begin(&src_mm->write_protect_seq); } ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, addr, next))) { ret = -ENOMEM; break; } } while (dst_pgd++, src_pgd++, addr = next, addr != end); if (is_cow) { raw_write_seqcount_end(&src_mm->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } return ret; } static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) { struct mm_struct *mm = tlb->mm; int force_flush = 0; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; pte_t *start_pte; pte_t *pte; swp_entry_t entry; tlb_change_page_size(tlb, PAGE_SIZE); again: init_rss_vec(rss); start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte = start_pte; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; if (pte_none(ptent)) continue; if (need_resched()) break; if (pte_present(ptent)) { struct page *page; page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping && details->check_mapping != page_rmapping(page)) continue; } ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; if (!PageAnon(page)) { if (pte_dirty(ptent)) { force_flush = 1; set_page_dirty(page); } if (pte_young(ptent) && likely(!(vma->vm_flags & VM_SEQ_READ))) mark_page_accessed(page); } rss[mm_counter(page)]--; page_remove_rmap(page, false); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); if (unlikely(__tlb_remove_page(tlb, page))) { force_flush = 1; addr += PAGE_SIZE; break; } continue; } entry = pte_to_swp_entry(ptent); if (is_device_private_entry(entry)) { struct page *page = device_private_entry_to_page(entry); if (unlikely(details && details->check_mapping)) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping != page_rmapping(page)) continue; } pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); rss[mm_counter(page)]--; page_remove_rmap(page, false); put_page(page); continue; } /* If details->check_mapping, we leave swap entries. */ if (unlikely(details)) continue; if (!non_swap_entry(entry)) rss[MM_SWAPENTS]--; else if (is_migration_entry(entry)) { struct page *page; page = migration_entry_to_page(entry); rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) print_bad_pte(vma, addr, ptent, NULL); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); /* Do the actual TLB flush before dropping ptl */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); pte_unmap_unlock(start_pte, ptl); /* * If we forced a TLB flush (either due to running out of * batch buffers or because we needed to flush dirty TLB * entries before releasing the ptl), free the batched * memory too. Restart if we didn't do everything. */ if (force_flush) { force_flush = 0; tlb_flush_mmu(tlb); } if (addr != end) { cond_resched(); goto again; } return addr; } static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) { pmd_t *pmd; unsigned long next; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false, NULL); else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ } else if (details && details->single_page && PageTransCompound(details->single_page) && next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { spinlock_t *ptl = pmd_lock(tlb->mm, pmd); /* * Take and drop THP pmd lock so that we cannot return * prematurely, while zap_huge_pmd() has cleared *pmd, * but not yet decremented compound_mapcount(). */ spin_unlock(ptl); } /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is * none or trans huge it can change under us. This is * because MADV_DONTNEED holds the mmap_lock in read * mode. */ if (pmd_none_or_trans_huge_or_clear_bad(pmd)) goto next; next = zap_pte_range(tlb, vma, pmd, addr, next, details); next: cond_resched(); } while (pmd++, addr = next, addr != end); return addr; } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { if (next - addr != HPAGE_PUD_SIZE) { mmap_assert_locked(tlb->mm); split_huge_pud(vma, pud, addr); } else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; /* fall through */ } if (pud_none_or_clear_bad(pud)) continue; next = zap_pmd_range(tlb, vma, pud, addr, next, details); next: cond_resched(); } while (pud++, addr = next, addr != end); return addr; } static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; next = zap_pud_range(tlb, vma, p4d, addr, next, details); } while (p4d++, addr = next, addr != end); return addr; } void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details) { pgd_t *pgd; unsigned long next; BUG_ON(addr >= end); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } static void unmap_single_vma(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { unsigned long start = max(vma->vm_start, start_addr); unsigned long end; if (start >= vma->vm_end) return; end = min(vma->vm_end, end_addr); if (end <= vma->vm_start) return; if (vma->vm_file) uprobe_munmap(vma, start, end); if (unlikely(vma->vm_flags & VM_PFNMAP)) untrack_pfn(vma, 0, 0); if (start != end) { if (unlikely(is_vm_hugetlb_page(vma))) { /* * It is undesirable to test vma->vm_file as it * should be non-null for valid hugetlb area. * However, vm_file will be NULL in the error * cleanup path of mmap_region. When * hugetlbfs ->mmap method fails, * mmap_region() nullifies vma->vm_file * before calling this function to clean up. * Since no pte has actually been setup, it is * safe to do nothing in this case. */ if (vma->vm_file) { i_mmap_lock_write(vma->vm_file->f_mapping); __unmap_hugepage_range_final(tlb, vma, start, end, NULL); i_mmap_unlock_write(vma->vm_file->f_mapping); } } else unmap_page_range(tlb, vma, start, end, details); } } /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlb: address of the caller's struct mmu_gather * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping * * Unmap all pages in the vma list. * * Only addresses between `start' and `end' will be unmapped. * * The VMA list must be sorted in ascending virtual address order. * * unmap_vmas() assumes that the caller will flush the whole unmapped address * range after unmap_vmas() returns. So the only responsibility here is to * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) { struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); mmu_notifier_invalidate_range_end(&range); } /** * zap_page_range - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @start: starting address of pages to zap * @size: number of bytes to zap * * Caller must protect the VMA list */ void zap_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long size) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, start, start + size); tlb_gather_mmu(&tlb, vma->vm_mm, start, range.end); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next) unmap_single_vma(&tlb, vma, start, range.end, NULL); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, start, range.end); } /** * zap_page_range_single - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap * @details: details of shared cache invalidation * * The range must fit into one VMA. */ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, address + size); tlb_gather_mmu(&tlb, vma->vm_mm, address, range.end); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); unmap_single_vma(&tlb, vma, address, range.end, details); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, address, range.end); } /** * zap_vma_ptes - remove ptes mapping the vma * @vma: vm_area_struct holding ptes to be zapped * @address: starting address of pages to zap * @size: number of bytes to zap * * This function only unmaps ptes assigned to VM_PFNMAP vmas. * * The entire address range must be fully contained within the vma. * */ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size) { if (address < vma->vm_start || address + size > vma->vm_end || !(vma->vm_flags & VM_PFNMAP)) return; zap_page_range_single(vma, address, size, NULL); } EXPORT_SYMBOL_GPL(zap_vma_ptes); static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); return pmd; } pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pmd_t *pmd = walk_to_pmd(mm, addr); if (!pmd) return NULL; return pte_alloc_map_lock(mm, pmd, addr, ptl); } static int validate_page_before_insert(struct page *page) { if (PageAnon(page) || PageSlab(page) || page_has_type(page)) return -EINVAL; flush_dcache_page(page); return 0; } static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { if (!pte_none(*pte)) return -EBUSY; /* Ok, finally just insert the thing.. */ get_page(page); inc_mm_counter_fast(mm, mm_counter_file(page)); page_add_file_rmap(page, false); set_pte_at(mm, addr, pte, mk_pte(page, prot)); return 0; } /* * This is the old fallback for page remapping. * * For historical reasons, it only allows reserved pages. Only * old drivers should use this, and they needed to mark their * pages reserved for the old functions anyway. */ static int insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot) { struct mm_struct *mm = vma->vm_mm; int retval; pte_t *pte; spinlock_t *ptl; retval = validate_page_before_insert(page); if (retval) goto out; retval = -ENOMEM; pte = get_locked_pte(mm, addr, &ptl); if (!pte) goto out; retval = insert_page_into_pte_locked(mm, pte, addr, page, prot); pte_unmap_unlock(pte, ptl); out: return retval; } #ifdef pte_index static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; if (!page_count(page)) return -EINVAL; err = validate_page_before_insert(page); if (err) return err; return insert_page_into_pte_locked(mm, pte, addr, page, prot); } /* insert_pages() amortizes the cost of spinlock operations * when inserting pages in a loop. Arch *must* define pte_index. */ static int insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num, pgprot_t prot) { pmd_t *pmd = NULL; pte_t *start_pte, *pte; spinlock_t *pte_lock; struct mm_struct *const mm = vma->vm_mm; unsigned long curr_page_idx = 0; unsigned long remaining_pages_total = *num; unsigned long pages_to_write_in_pmd; int ret; more: ret = -EFAULT; pmd = walk_to_pmd(mm, addr); if (!pmd) goto out; pages_to_write_in_pmd = min_t(unsigned long, remaining_pages_total, PTRS_PER_PTE - pte_index(addr)); /* Allocate the PTE if necessary; takes PMD lock once only. */ ret = -ENOMEM; if (pte_alloc(mm, pmd)) goto out; while (pages_to_write_in_pmd) { int pte_idx = 0; const int batch_size = min_t(int, pages_to_write_in_pmd, 8); start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { int err = insert_page_in_batch_locked(mm, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { pte_unmap_unlock(start_pte, pte_lock); ret = err; remaining_pages_total -= pte_idx; goto out; } addr += PAGE_SIZE; ++curr_page_idx; } pte_unmap_unlock(start_pte, pte_lock); pages_to_write_in_pmd -= batch_size; remaining_pages_total -= batch_size; } if (remaining_pages_total) goto more; ret = 0; out: *num = remaining_pages_total; return ret; } #endif /* ifdef pte_index */ /** * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock. * @vma: user vma to map to * @addr: target start user address of these pages * @pages: source kernel pages * @num: in: number of pages to map. out: number of pages that were *not* * mapped. (0 means all pages were successfully mapped). * * Preferred over vm_insert_page() when inserting multiple pages. * * In case of error, we may have mapped a subset of the provided * pages. It is the caller's responsibility to account for this case. * * The same restrictions apply as in vm_insert_page(). */ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num) { #ifdef pte_index const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1; if (addr < vma->vm_start || end_addr >= vma->vm_end) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } /* Defer page refcount checking till we're about to map that page. */ return insert_pages(vma, addr, pages, num, vma->vm_page_prot); #else unsigned long idx = 0, pgcount = *num; int err = -EINVAL; for (; idx < pgcount; ++idx) { err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]); if (err) break; } *num = pgcount - idx; return err; #endif /* ifdef pte_index */ } EXPORT_SYMBOL(vm_insert_pages); /** * vm_insert_page - insert single page into user vma * @vma: user vma to map to * @addr: target user address of this page * @page: source kernel page * * This allows drivers to insert individual pages they've allocated * into a user vma. * * The page has to be a nice clean _individual_ kernel allocation. * If you allocate a compound page, you need to have marked it as * such (__GFP_COMP), or manually just split the page up yourself * (see split_page()). * * NOTE! Traditionally this was done with "remap_pfn_range()" which * took an arbitrary page protection parameter. This doesn't allow * that. Your vma protection will have to be set up correctly, which * means that if you want a shared writable mapping, you'd better * ask for a shared writable mapping! * * The page does not need to be reserved. * * Usually this function is called from f_op->mmap() handler * under mm->mmap_lock write-lock, so it can change vma->vm_flags. * Caller must set VM_MIXEDMAP on vma if it wants to call this * function from other places, for example from page-fault handler. * * Return: %0 on success, negative error code otherwise. */ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; if (!page_count(page)) return -EINVAL; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } return insert_page(vma, addr, page, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_page); /* * __vm_map_pages - maps range of kernel pages into user vma * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * @offset: user's requested vm_pgoff * * This allows drivers to map range of kernel pages into a user vma. * * Return: 0 on success and error code otherwise. */ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num, unsigned long offset) { unsigned long count = vma_pages(vma); unsigned long uaddr = vma->vm_start; int ret, i; /* Fail if the user requested offset is beyond the end of the object */ if (offset >= num) return -ENXIO; /* Fail if the user requested size exceeds available object size */ if (count > num - offset) return -ENXIO; for (i = 0; i < count; i++) { ret = vm_insert_page(vma, uaddr, pages[offset + i]); if (ret < 0) return ret; uaddr += PAGE_SIZE; } return 0; } /** * vm_map_pages - maps range of kernel pages starts with non zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Maps an object consisting of @num pages, catering for the user's * requested vm_pgoff * * If we fail to insert any page into the vma, the function will return * immediately leaving any previously inserted pages present. Callers * from the mmap handler may immediately return the error as their caller * will destroy the vma, removing any successfully inserted pages. Other * callers should make their own arrangements for calling unmap_region(). * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, vma->vm_pgoff); } EXPORT_SYMBOL(vm_map_pages); /** * vm_map_pages_zero - map range of kernel pages starts with zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Similar to vm_map_pages(), except that it explicitly sets the offset * to 0. This function is intended for the drivers that did not consider * vm_pgoff. * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, 0); } EXPORT_SYMBOL(vm_map_pages_zero); static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, entry; spinlock_t *ptl; pte = get_locked_pte(mm, addr, &ptl); if (!pte) return VM_FAULT_OOM; if (!pte_none(*pte)) { if (mkwrite) { /* * For read faults on private mappings the PFN passed * in may not match the PFN we have mapped if the * mapped PFN is a writeable COW page. In the mkwrite * case we are creating a writable PTE for a shared * mapping and we expect the PFNs to match. If they * don't match, we are likely racing with block * allocation and mapping invalidation so just skip the * update. */ if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte))); goto out_unlock; } entry = pte_mkyoung(*pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, addr, pte, entry, 1)) update_mmu_cache(vma, addr, pte); } goto out_unlock; } /* Ok, finally just insert the thing.. */ if (pfn_t_devmap(pfn)) entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); else entry = pte_mkspecial(pfn_t_pte(pfn, prot)); if (mkwrite) { entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); } set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ out_unlock: pte_unmap_unlock(pte, ptl); return VM_FAULT_NOPAGE; } /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_pfn(), except that it allows drivers * to override pgprot on a per-page basis. * * This only makes sense for IO mappings, and it makes no sense for * COW mappings. In general, using multiple vmas is preferable; * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * * See vmf_insert_mixed_prot() for a discussion of the implication of using * a value of @pgprot different from that of @vma->vm_page_prot. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like * consistency in testing and feature parity among all, so we should * try to keep these invariants in place for everybody. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (!pfn_modify_allowed(pfn, pgprot)) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, false); } EXPORT_SYMBOL(vmf_insert_pfn_prot); /** * vmf_insert_pfn - insert single pfn into user vma * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * * Similar to vm_insert_page, this allows drivers to insert individual pages * they've allocated into a user vma. Same comments apply. * * This function should only be called from a vm_ops->fault handler, and * in that case the handler should return the result of this function. * * vma cannot be a COW mapping. * * As this is called only for pages that do not currently exist, we * do not need to flush old virtual caches or the TLB. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); } EXPORT_SYMBOL(vmf_insert_pfn); static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) { /* these checks mirror the abort conditions in vm_normal_page */ if (vma->vm_flags & VM_MIXEDMAP) return true; if (pfn_t_devmap(pfn)) return true; if (pfn_t_special(pfn)) return true; if (is_zero_pfn(pfn_t_to_pfn(pfn))) return true; return false; } static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot, bool mkwrite) { int err; BUG_ON(!vm_mixed_ok(vma, pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, pfn); if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) return VM_FAULT_SIGBUS; /* * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* * refcount the page if pfn_valid is true (hence insert_page rather * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { struct page *page; /* * At this point we are committed to insert_page() * regardless of whether the caller specified flags that * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); err = insert_page(vma, addr, page, pgprot); } else { return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } /** * vmf_insert_mixed_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_mixed(), except that it allows drivers * to override pgprot on a per-page basis. * * Typically this function should be used by drivers to set caching- and * encryption bits different than those of @vma->vm_page_prot, because * the caching- or encryption mode may not be known at mmap() time. * This is ok as long as @vma->vm_page_prot is not used by the core vm * to set caching and encryption bits for those vmas (except for COW pages). * This is ensured by core vm only modifying these page table entries using * functions that don't touch caching- or encryption bits, using pte_modify() * if needed. (See for example mprotect()). * Also when new page-table entries are created, this is only done using the * fault() callback, and never using the value of vma->vm_page_prot, * except for page-table entries that point to anonymous pages as the result * of COW. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot) { return __vm_insert_mixed(vma, addr, pfn, pgprot, false); } EXPORT_SYMBOL(vmf_insert_mixed_prot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false); } EXPORT_SYMBOL(vmf_insert_mixed); /* * If the insertion of PTE failed because someone else already added a * different entry in the mean time, we treat that as success as we assume * the same entry was actually inserted. */ vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true); } EXPORT_SYMBOL(vmf_insert_mixed_mkwrite); /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results * in null mappings (currently treated as "copy-on-access") */ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pte_t *pte, *mapped_pte; spinlock_t *ptl; int err = 0; mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); if (!pfn_modify_allowed(pfn, prot)) { err = -EACCES; break; } set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(mapped_pte, ptl); return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pmd_t *pmd; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); err = remap_pte_range(mm, pmd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pmd++, addr = next, addr != end); return 0; } static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pud_t *pud; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); err = remap_pmd_range(mm, pud, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pud++, addr = next, addr != end); return 0; } static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { p4d_t *p4d; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); err = remap_pud_range(mm, p4d, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (p4d++, addr = next, addr != end); return 0; } /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to * @addr: target page aligned user address to start at * @pfn: page frame number of kernel physical memory address * @size: size of mapping area * @prot: page protection flags for this mapping * * Note: this is only safe if the mm semaphore is held when called. * * Return: %0 on success, negative error code otherwise. */ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { pgd_t *pgd; unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; unsigned long remap_pfn = pfn; int err; if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) return -EINVAL; /* * Physically remapped pages are special. Tell the * rest of the world about it: * VM_IO tells people not to look at these pages * (accesses can have side effects). * VM_PFNMAP tells the core MM that the base pages are just * raw PFN mappings, and do not have a "struct page" associated * with them. * VM_DONTEXPAND * Disable vma merging and expanding with mremap(). * VM_DONTDUMP * Omit vma from core dump, even when VM_IO turned off. * * There's a horrible special case to handle copy-on-write * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". * See vm_normal_page() for details. */ if (is_cow_mapping(vma->vm_flags)) { if (addr != vma->vm_start || end != vma->vm_end) return -EINVAL; vma->vm_pgoff = pfn; } err = track_pfn_remap(vma, &prot, remap_pfn, addr, PAGE_ALIGN(size)); if (err) return -EINVAL; vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) break; } while (pgd++, addr = next, addr != end); if (err) untrack_pfn(vma, remap_pfn, PAGE_ALIGN(size)); return err; } EXPORT_SYMBOL(remap_pfn_range); /** * vm_iomap_memory - remap memory to userspace * @vma: user vma to map to * @start: start of the physical memory to be mapped * @len: size of area * * This is a simplified io_remap_pfn_range() for common driver use. The * driver just needs to give us the physical memory range to be mapped, * we'll figure out the rest from the vma information. * * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get * whatever write-combining details or similar. * * Return: %0 on success, negative error code otherwise. */ int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) { unsigned long vm_len, pfn, pages; /* Check that the physical memory area passed in looks valid */ if (start + len < start) return -EINVAL; /* * You *really* shouldn't map things that aren't page-aligned, * but we've historically allowed it because IO memory might * just have smaller alignment. */ len += start & ~PAGE_MASK; pfn = start >> PAGE_SHIFT; pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; if (pfn + pages < pfn) return -EINVAL; /* We start the mapping 'vm_pgoff' pages into the area */ if (vma->vm_pgoff > pages) return -EINVAL; pfn += vma->vm_pgoff; pages -= vma->vm_pgoff; /* Can we fit all of the mapping? */ vm_len = vma->vm_end - vma->vm_start; if (vm_len >> PAGE_SHIFT > pages) return -EINVAL; /* Ok, let it rip */ return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); } EXPORT_SYMBOL(vm_iomap_memory); static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pte_t *pte; int err = 0; spinlock_t *ptl; if (create) { pte = (mm == &init_mm) ? pte_alloc_kernel_track(pmd, addr, mask) : pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; } else { pte = (mm == &init_mm) ? pte_offset_kernel(pmd, addr) : pte_offset_map_lock(mm, pmd, addr, &ptl); } BUG_ON(pmd_huge(*pmd)); arch_enter_lazy_mmu_mode(); if (fn) { do { if (create || !pte_none(*pte)) { err = fn(pte++, addr, data); if (err) break; } } while (addr += PAGE_SIZE, addr != end); } *mask |= PGTBL_PTE_MODIFIED; arch_leave_lazy_mmu_mode(); if (mm != &init_mm) pte_unmap_unlock(pte-1, ptl); return err; } static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int err = 0; BUG_ON(pud_huge(*pud)); if (create) { pmd = pmd_alloc_track(mm, pud, addr, mask); if (!pmd) return -ENOMEM; } else { pmd = pmd_offset(pud, addr); } do { next = pmd_addr_end(addr, end); if (create || !pmd_none_or_clear_bad(pmd)) { err = apply_to_pte_range(mm, pmd, addr, next, fn, data, create, mask); if (err) break; } } while (pmd++, addr = next, addr != end); return err; } static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int err = 0; if (create) { pud = pud_alloc_track(mm, p4d, addr, mask); if (!pud) return -ENOMEM; } else { pud = pud_offset(p4d, addr); } do { next = pud_addr_end(addr, end); if (create || !pud_none_or_clear_bad(pud)) { err = apply_to_pmd_range(mm, pud, addr, next, fn, data, create, mask); if (err) break; } } while (pud++, addr = next, addr != end); return err; } static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int err = 0; if (create) { p4d = p4d_alloc_track(mm, pgd, addr, mask); if (!p4d) return -ENOMEM; } else { p4d = p4d_offset(pgd, addr); } do { next = p4d_addr_end(addr, end); if (create || !p4d_none_or_clear_bad(p4d)) { err = apply_to_pud_range(mm, p4d, addr, next, fn, data, create, mask); if (err) break; } } while (p4d++, addr = next, addr != end); return err; } static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data, bool create) { pgd_t *pgd; unsigned long start = addr, next; unsigned long end = addr + size; pgtbl_mod_mask mask = 0; int err = 0; if (WARN_ON(addr >= end)) return -EINVAL; pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); if (!create && pgd_none_or_clear_bad(pgd)) continue; err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask); if (err) break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, start + size); return err; } /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. */ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, true); } EXPORT_SYMBOL_GPL(apply_to_page_range); /* * Scan a region of virtual memory, calling a provided function on * each leaf page table where it exists. * * Unlike apply_to_page_range, this does _not_ fill in page tables * where they are absent. */ int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, false); } EXPORT_SYMBOL_GPL(apply_to_existing_page_range); /* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures * or configurations (e.g. i386 with PAE) which might give a mix of unmatched * parts, do_swap_page must check under lock before unmapping the pte and * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, pte_t *page_table, pte_t orig_pte) { int same = 1; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) if (sizeof(pte_t) > sizeof(unsigned long)) { spinlock_t *ptl = pte_lockptr(mm, pmd); spin_lock(ptl); same = pte_same(*page_table, orig_pte); spin_unlock(ptl); } #endif pte_unmap(page_table); return same; } static inline bool cow_user_page(struct page *dst, struct page *src, struct vm_fault *vmf) { bool ret; void *kaddr; void __user *uaddr; bool locked = false; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; if (likely(src)) { copy_user_highpage(dst, src, addr, vma); return true; } /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ kaddr = kmap_atomic(dst); uaddr = (void __user *)(addr & PAGE_MASK); /* * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { pte_t entry; vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* * Other thread has already handled the fault * and update local tlb only */ update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } entry = pte_mkyoung(vmf->orig_pte); if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) update_mmu_cache(vma, addr, vmf->pte); } /* * This really shouldn't fail, because the page is there * in the page tables. But it might just be unreadable, * in which case we just give up and fill the result with * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { if (locked) goto warn; /* Re-validate under PTL if the page is still mapped */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* The PTE changed under us, update local tlb */ update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } /* * The same page can be mapped back since last copy attempt. * Try to copy again under PTL. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { /* * Give a warn in case there can be some obscure * use-case */ warn: WARN_ON_ONCE(1); clear_page(kaddr); } } ret = true; pte_unlock: if (locked) pte_unmap_unlock(vmf->pte, vmf->ptl); kunmap_atomic(kaddr); flush_dcache_page(dst); return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) { struct file *vm_file = vma->vm_file; if (vm_file) return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; /* * Special mappings (e.g. VDSO) do not have any file so fake * a default GFP_KERNEL for them. */ return GFP_KERNEL; } /* * Notify the address space that the page is about to become writable so that * it can prohibit this or wait for the page to get into an appropriate state. * * We do this without the lock held, so that it can sleep if it needs to. */ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf) { vm_fault_t ret; struct page *page = vmf->page; unsigned int old_flags = vmf->flags; vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; if (vmf->vma->vm_file && IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host)) return VM_FAULT_SIGBUS; ret = vmf->vma->vm_ops->page_mkwrite(vmf); /* Restore original flags so that caller is not surprised */ vmf->flags = old_flags; if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) return ret; if (unlikely(!(ret & VM_FAULT_LOCKED))) { lock_page(page); if (!page->mapping) { unlock_page(page); return 0; /* retry */ } ret |= VM_FAULT_LOCKED; } else VM_BUG_ON_PAGE(!PageLocked(page), page); return ret; } /* * Handle dirtying of a page in shared file mapping on a write fault. * * The function expects the page to be locked and unlocks it. */ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct address_space *mapping; struct page *page = vmf->page; bool dirtied; bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; dirtied = set_page_dirty(page); VM_BUG_ON_PAGE(PageAnon(page), page); /* * Take a local copy of the address_space - page.mapping may be zeroed * by truncate after unlock_page(). The address_space itself remains * pinned by vma->vm_file's reference. We rely on unlock_page()'s * release semantics to prevent the compiler from undoing this copying. */ mapping = page_rmapping(page); unlock_page(page); if (!page_mkwrite) file_update_time(vma->vm_file); /* * Throttle page dirtying rate down to writeback speed. * * mapping may be NULL here because some device drivers do not * set page.mapping but still dirty their pages * * Drop the mmap_lock before waiting on IO, if we can. The file * is pinning the mapping, as per above. */ if ((dirtied || page_mkwrite) && mapping) { struct file *fpin; fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); return VM_FAULT_RETRY; } } return 0; } /* * Handle write page faults for pages that can be reused in the current vma * * This can happen either due to the mapping being with the VM_SHARED flag, * or due to us being the last reference standing to the page. In either * case, all we need to do here is to mark the page as writable and update * any related book-keeping. */ static inline void wp_page_reuse(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; pte_t entry; /* * Clear the pages cpupid information as the existing * information potentially belongs to a now completely * unrelated process. */ if (page) page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1); flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = pte_mkyoung(vmf->orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); count_vm_event(PGREUSE); } /* * Handle the case of a page which we actually need to copy to a new page. * * Called with mmap_lock locked and the old page referenced, but * without the ptl held. * * High level logic flow: * * - Allocate a page, copy the content of the old page to the new one. * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. * - Take the PTL. If the pte changed, bail out and release the allocated page * - If the pte is still the way we remember it, update the page table and all * relevant references. This includes dropping the reference the page-table * held to the old page, as well as updating the rmap. * - In any case, unlock the PTL and drop the reference we took to the old page. */ static vm_fault_t wp_page_copy(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct page *old_page = vmf->page; struct page *new_page = NULL; pte_t entry; int page_copied = 0; struct mmu_notifier_range range; if (unlikely(anon_vma_prepare(vma))) goto oom; if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { new_page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!new_page) goto oom; } else { new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!new_page) goto oom; if (!cow_user_page(new_page, old_page, vmf)) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on * the same address and we will handle the fault * from the second attempt. */ put_page(new_page); if (old_page) put_page(old_page); return 0; } } if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); __SetPageUptodate(new_page); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); /* * Re-check the pte - we dropped the lock */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { dec_mm_counter_fast(mm, mm_counter_file(old_page)); inc_mm_counter_fast(mm, MM_ANONPAGES); } } else { inc_mm_counter_fast(mm, MM_ANONPAGES); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* * Clear the pte entry and flush it first, before updating the * pte with the new entry. This will avoid a race condition * seen in the presence of one thread doing SMC and another * thread doing COW. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); page_add_new_anon_rmap(new_page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary * mmu page tables (such as kvm shadow page tables), we want the * new page to be mapped directly into the secondary page table. */ set_pte_at_notify(mm, vmf->address, vmf->pte, entry); update_mmu_cache(vma, vmf->address, vmf->pte); if (old_page) { /* * Only after switching the pte to the new page may * we remove the mapcount here. Otherwise another * process may come and find the rmap count decremented * before the pte is switched to the new page, and * "reuse" the old page writing into it while our pte * here still points into it and can be read by other * threads. * * The critical issue is to order this * page_remove_rmap with the ptp_clear_flush above. * Those stores are ordered by (if nothing else,) * the barrier present in the atomic_add_negative * in page_remove_rmap. * * Then the TLB flush in ptep_clear_flush ensures that * no process can access the old page before the * decremented mapcount is visible. And the old page * cannot be reused until after the decremented * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ page_remove_rmap(old_page, false); } /* Free the old page.. */ new_page = old_page; page_copied = 1; } else { update_mmu_tlb(vma, vmf->address, vmf->pte); } if (new_page) put_page(new_page); pte_unmap_unlock(vmf->pte, vmf->ptl); /* * No need to double call mmu_notifier->invalidate_range() callback as * the above ptep_clear_flush_notify() did already call it. */ mmu_notifier_invalidate_range_only_end(&range); if (old_page) { /* * Don't let another task, with possibly unlocked vma, * keep the mlocked page. */ if (page_copied && (vma->vm_flags & VM_LOCKED)) { lock_page(old_page); /* LRU manipulation */ if (PageMlocked(old_page)) munlock_vma_page(old_page); unlock_page(old_page); } put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; oom_free_new: put_page(new_page); oom: if (old_page) put_page(old_page); return VM_FAULT_OOM; } /** * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE * writeable once the page is prepared * * @vmf: structure describing the fault * * This function handles all that is needed to finish a write page fault in a * shared mapping due to PTE being read-only once the mapped page is prepared. * It handles locking of PTE and modifying it. * * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before * we acquired PTE lock. */ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) { WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); /* * We might have raced with another page fault while we released the * pte_offset_map_lock. */ if (!pte_same(*vmf->pte, vmf->orig_pte)) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return VM_FAULT_NOPAGE; } wp_page_reuse(vmf); return 0; } /* * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED * mapping */ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { vm_fault_t ret; pte_unmap_unlock(vmf->pte, vmf->ptl); vmf->flags |= FAULT_FLAG_MKWRITE; ret = vma->vm_ops->pfn_mkwrite(vmf); if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; return finish_mkwrite_fault(vmf); } wp_page_reuse(vmf); return VM_FAULT_WRITE; } static vm_fault_t wp_page_shared(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = VM_FAULT_WRITE; get_page(vmf->page); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { vm_fault_t tmp; pte_unmap_unlock(vmf->pte, vmf->ptl); tmp = do_page_mkwrite(vmf); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { put_page(vmf->page); return tmp; } tmp = finish_mkwrite_fault(vmf); if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { unlock_page(vmf->page); put_page(vmf->page); return tmp; } } else { wp_page_reuse(vmf); lock_page(vmf->page); } ret |= fault_dirty_shared_page(vmf); put_page(vmf->page); return ret; } /* * This routine handles present pages, when users try to write * to a shared page. It is done by copying the page to a new address * and decrementing the shared-page counter for the old page. * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). * Thus we can safely just mark it writable once we've done any necessary * COW. * * We also mark the page dirty at this point even though the page will * change only once the write actually happens. This avoids a few races, * and potentially makes it more efficient. * * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), with pte both mapped and locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_wp_page(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; if (userfaultfd_pte_wp(vma, *vmf->pte)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_WP); } /* * Userfaultfd write-protect can defer flushes. Ensure the TLB * is flushed in this case before copying. */ if (unlikely(userfaultfd_wp(vmf->vma) && mm_tlb_flush_pending(vmf->vma->vm_mm))) flush_tlb_page(vmf->vma, vmf->address); vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (!vmf->page) { /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. * * We should not cow pages in a shared writeable mapping. * Just mark the pages writable and/or call ops->pfn_mkwrite. */ if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED)) return wp_pfn_shared(vmf); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } /* * Take out anonymous pages first, anonymous shared vmas are * not dirty accountable. */ if (PageAnon(vmf->page)) { struct page *page = vmf->page; /* PageKsm() doesn't necessarily raise the page refcount */ if (PageKsm(page) || page_count(page) != 1) goto copy; if (!trylock_page(page)) goto copy; if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) { unlock_page(page); goto copy; } /* * Ok, we've got the only map reference, and the only * page count reference, and the page is locked, * it's dark out, and we're wearing sunglasses. Hit it. */ unlock_page(page); wp_page_reuse(vmf); return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); } copy: /* * Ok, we need to copy. Oh, well.. */ get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } static void unmap_mapping_range_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } static inline void unmap_mapping_range_tree(struct rb_root_cached *root, struct zap_details *details) { struct vm_area_struct *vma; pgoff_t vba, vea, zba, zea; vma_interval_tree_foreach(vma, root, details->first_index, details->last_index) { vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; zba = details->first_index; if (zba < vba) zba = vba; zea = details->last_index; if (zea > vea) zea = vea; unmap_mapping_range_vma(vma, ((zba - vba) << PAGE_SHIFT) + vma->vm_start, ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, details); } } /** * unmap_mapping_page() - Unmap single page from processes. * @page: The locked page to be unmapped. * * Unmap this page from any userspace process which still has it mmaped. * Typically, for efficiency, the range of nearby pages has already been * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once * truncation or invalidation holds the lock on a page, it may find that * the page has been remapped again: and then uses unmap_mapping_page() * to unmap it finally. */ void unmap_mapping_page(struct page *page) { struct address_space *mapping = page->mapping; struct zap_details details = { }; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageTail(page)); details.check_mapping = mapping; details.first_index = page->index; details.last_index = page->index + thp_nr_pages(page) - 1; details.single_page = page; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. * @nr: Number of pages to be unmapped. 0 to unmap to end of file. * @even_cows: Whether to unmap even private COWed pages. * * Unmap the pages in this address space from any userspace process which * has them mmaped. Generally, you want to remove COWed pages as well when * a file is being truncated, but not when invalidating pages from the page * cache. */ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { struct zap_details details = { }; details.check_mapping = even_cows ? NULL : mapping; details.first_index = start; details.last_index = start + nr - 1; if (details.last_index < details.first_index) details.last_index = ULONG_MAX; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } /** * unmap_mapping_range - unmap the portion of all mmaps in the specified * address_space corresponding to the specified byte range in the underlying * file. * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded * up to a PAGE_SIZE boundary. A holelen of zero truncates to the * end of the file. * @even_cows: 1 when truncating a file, unmap even private COWed pages; * but 0 when invalidating pagecache, don't throw away private data. */ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { pgoff_t hba = holebegin >> PAGE_SHIFT; pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { long long holeend = (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; if (holeend & ~(long long)ULONG_MAX) hlen = ULONG_MAX - hba + 1; } unmap_mapping_pages(mapping, hba, hlen, even_cows); } EXPORT_SYMBOL(unmap_mapping_range); /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with pte unmapped and unlocked. * * We return with the mmap_lock locked or unlocked in the same cases * as does filemap_fault(). */ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; swp_entry_t entry; pte_t pte; int locked; int exclusive = 0; vm_fault_t ret = 0; void *shadow = NULL; if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) goto out; entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) { if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); } else if (is_device_private_entry(entry)) { vmf->page = device_private_entry_to_page(entry); ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; } goto out; } delayacct_set_flag(DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry, vma, vmf->address); swapcache = page; if (!page) { struct swap_info_struct *si = swp_swap_info(entry); if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { /* skip swapcache */ page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (page) { int err; __SetPageLocked(page); __SetPageSwapBacked(page); set_page_private(page, entry.val); /* Tell memcg to use swap ownership records */ SetPageSwapCache(page); err = mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL); ClearPageSwapCache(page); if (err) { ret = VM_FAULT_OOM; goto out_page; } shadow = get_shadow_from_swap_cache(entry); if (shadow) workingset_refault(page, shadow); lru_cache_add(page); swap_readpage(page, true); } } else { page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf); swapcache = page; } if (!page) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto unlock; } /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(vma->vm_mm, PGMAJFAULT); } else if (PageHWPoison(page)) { /* * hwpoisoned dirty swapcache pages are kept for killing * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto out_release; } locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); if (!locked) { ret |= VM_FAULT_RETRY; goto out_release; } /* * Make sure try_to_free_swap or reuse_swap_page or swapoff did not * release the swapcache from under us. The page pin, and pte_same * test below, are not enough to exclude that. Even if it is still * swapcache, we need to check that the page's swap has not changed. */ if (unlikely((!PageSwapCache(page) || page_private(page) != entry.val)) && swapcache) goto out_page; page = ksm_might_need_to_copy(page, vma, vmf->address); if (unlikely(!page)) { ret = VM_FAULT_OOM; page = swapcache; goto out_page; } cgroup_throttle_swaprate(page, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) goto out_nomap; if (unlikely(!PageUptodate(page))) { ret = VM_FAULT_SIGBUS; goto out_nomap; } /* * The page isn't present yet, go ahead with the fault. * * Be careful about the sequence of operations here. * To get its accounting right, reuse_swap_page() must be called * while the page is counted on swap but not yet in mapcount i.e. * before page_add_anon_rmap() and swap_free(); try_to_free_swap() * must be called after the swap_free(), or it will never succeed. */ inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); vmf->flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; exclusive = RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(vmf->orig_pte)) pte = pte_mksoft_dirty(pte); if (pte_swp_uffd_wp(vmf->orig_pte)) { pte = pte_mkuffd_wp(pte); pte = pte_wrprotect(pte); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); vmf->orig_pte = pte; /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); } swap_free(entry); if (mem_cgroup_swap_full(page) || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); if (page != swapcache && swapcache) { /* * Hold the lock to avoid the swap entry to be reused * until we take the PT lock for the pte_same() check * (to avoid false positives from pte_same). For * further safety release the lock after the swap_free * so that the swap count won't change under a * parallel locked swapcache. */ unlock_page(swapcache); put_page(swapcache); } if (vmf->flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(vmf); if (ret & VM_FAULT_ERROR) ret &= VM_FAULT_ERROR; goto out; } /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: return ret; out_nomap: pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: unlock_page(page); out_release: put_page(page); if (page != swapcache && swapcache) { unlock_page(swapcache); put_page(swapcache); } return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; vm_fault_t ret = 0; pte_t entry; /* File mapping without ->vm_ops ? */ if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; /* * Use pte_alloc() instead of pte_alloc_map(). We can't run * pte_offset_map() on pmds where a huge pmd might be created * from a different thread. * * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when * parallel threads are excluded by other means. * * Here we only have mmap_read_lock(mm). */ if (pte_alloc(vma->vm_mm, vmf->pmd)) return VM_FAULT_OOM; /* See the comment in pte_alloc_one_map() */ if (unlikely(pmd_trans_unstable(vmf->pmd))) return 0; /* Use the zero-page for reads */ if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm)) { entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_MISSING); } goto setpte; } /* Allocate our own private page. */ if (unlikely(anon_vma_prepare(vma))) goto oom; page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!page) goto oom; if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); /* * The memory barrier inside __SetPageUptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_cache(vma, vmf->address, vmf->pte); goto release; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto release; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: put_page(page); goto unlock; oom_free_page: put_page(page); oom: return VM_FAULT_OOM; } /* * The mmap_lock must have been held on entry, and may have been * released depending on flags and vma->vm_ops->fault() return value. * See filemap_fault() and __lock_page_retry(). */ static vm_fault_t __do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; /* * Preallocate pte before we take page_lock because this might lead to * deadlocks for memcg reclaim which waits for pages under writeback: * lock_page(A) * SetPageWriteback(A) * unlock_page(A) * lock_page(B) * lock_page(B) * pte_alloc_one * shrink_page_list * wait_on_page_writeback(A) * SetPageWriteback(B) * unlock_page(B) * # flush A, B to clear the writeback */ if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } ret = vma->vm_ops->fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | VM_FAULT_DONE_COW))) return ret; if (unlikely(PageHWPoison(vmf->page))) { if (ret & VM_FAULT_LOCKED) unlock_page(vmf->page); put_page(vmf->page); vmf->page = NULL; return VM_FAULT_HWPOISON; } if (unlikely(!(ret & VM_FAULT_LOCKED))) lock_page(vmf->page); else VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page); return ret; } /* * The ordering of these checks is important for pmds with _PAGE_DEVMAP set. * If we check pmd_trans_unstable() first we will trip the bad_pmd() check * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. */ static int pmd_devmap_trans_unstable(pmd_t *pmd) { return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); } static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (!pmd_none(*vmf->pmd)) goto map_pte; if (vmf->prealloc_pte) { vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { spin_unlock(vmf->ptl); goto map_pte; } mm_inc_nr_ptes(vma->vm_mm); pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); spin_unlock(vmf->ptl); vmf->prealloc_pte = NULL; } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { return VM_FAULT_OOM; } map_pte: /* * If a huge pmd materialized under us just retry later. Use * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge * under us and then back to pmd_none, as a result of MADV_DONTNEED * running immediately after a huge pmd fault in a different thread of * this mm, in turn leading to a misleading pmd_trans_huge() retval. * All we have to ensure is that it is a regular pmd that we can walk * with pte_offset_map() and we can do that through an atomic read in * C, which is what pmd_trans_unstable() provides. */ if (pmd_devmap_trans_unstable(vmf->pmd)) return VM_FAULT_NOPAGE; /* * At this point we know that our vmf->pmd points to a page of ptes * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge() * for the duration of the fault. If a racing MADV_DONTNEED runs and * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still * be valid and we will re-check to make sure the vmf->pte isn't * pte_none() under vmf->ptl protection when we return to * alloc_set_pte(). */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); return 0; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void deposit_prealloc_pte(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); /* * We are going to consume the prealloc table, * count that as nr_ptes. */ mm_inc_nr_ptes(vma->vm_mm); vmf->prealloc_pte = NULL; } static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t entry; int i; vm_fault_t ret = VM_FAULT_FALLBACK; if (!transhuge_vma_suitable(vma, haddr)) return ret; page = compound_head(page); if (compound_order(page) != HPAGE_PMD_ORDER) return ret; /* * Archs like ppc64 need additonal space to store information * related to pte entry. Use the preallocated table for that. */ if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) goto out; for (i = 0; i < HPAGE_PMD_NR; i++) flush_icache_page(vma, page + i); entry = mk_huge_pmd(page, vma->vm_page_prot); if (write) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR); page_add_file_rmap(page, true); /* * deposit and withdraw with pmd lock held */ if (arch_needs_pgtable_deposit()) deposit_prealloc_pte(vmf); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, haddr, vmf->pmd); /* fault is handled */ ret = 0; count_vm_event(THP_FILE_MAPPED); out: spin_unlock(vmf->ptl); return ret; } #else static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { BUILD_BUG(); return 0; } #endif /** * alloc_set_pte - setup new PTE entry for given page and add reverse page * mapping. If needed, the function allocates page table or use pre-allocated. * * @vmf: fault environment * @page: page to map * * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on * return. * * Target users are page handler itself and implementations of * vm_ops->map_pages. * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; pte_t entry; vm_fault_t ret; if (pmd_none(*vmf->pmd) && PageTransCompound(page)) { ret = do_set_pmd(vmf, page); if (ret != VM_FAULT_FALLBACK) return ret; } if (!vmf->pte) { ret = pte_alloc_one_map(vmf); if (ret) return ret; } /* Re-check under ptl */ if (unlikely(!pte_none(*vmf->pte))) { update_mmu_tlb(vma, vmf->address, vmf->pte); return VM_FAULT_NOPAGE; } flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); page_add_file_rmap(page, false); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache(vma, vmf->address, vmf->pte); return 0; } /** * finish_fault - finish page fault once we have prepared the page to fault * * @vmf: structure describing the fault * * This function handles all that is needed to finish a page fault once the * page to fault in is prepared. It handles locking of PTEs, inserts PTE for * given page, adds reverse page mapping, handles memcg charges and LRU * addition. * * The function expects the page to be locked and on success it consumes a * reference of a page being mapped (for the PTE which maps it). * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t finish_fault(struct vm_fault *vmf) { struct page *page; vm_fault_t ret = 0; /* Did we COW the page? */ if ((vmf->flags & FAULT_FLAG_WRITE) && !(vmf->vma->vm_flags & VM_SHARED)) page = vmf->cow_page; else page = vmf->page; /* * check even for read faults because we might have lost our CoWed * page */ if (!(vmf->vma->vm_flags & VM_SHARED)) ret = check_stable_address_space(vmf->vma->vm_mm); if (!ret) ret = alloc_set_pte(vmf, page); if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } static unsigned long fault_around_bytes __read_mostly = rounddown_pow_of_two(65536); #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) { *val = fault_around_bytes; return 0; } /* * fault_around_bytes must be rounded down to the nearest page order as it's * what do_fault_around() expects to see. */ static int fault_around_bytes_set(void *data, u64 val) { if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; if (val > PAGE_SIZE) fault_around_bytes = rounddown_pow_of_two(val); else fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */ return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops, fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); static int __init fault_around_debugfs(void) { debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL, &fault_around_bytes_fops); return 0; } late_initcall(fault_around_debugfs); #endif /* * do_fault_around() tries to map few pages around the fault address. The hope * is that the pages will be needed soon and this will lower the number of * faults to handle. * * It uses vm_ops->map_pages() to map the pages, which skips the page if it's * not ready to be mapped: not up-to-date, locked, etc. * * This function is called with the page table lock taken. In the split ptlock * case the page table lock only protects only those entries which belong to * the page table corresponding to the fault address. * * This function doesn't cross the VMA boundaries, in order to call map_pages() * only once. * * fault_around_bytes defines how many bytes we'll try to map. * do_fault_around() expects it to be set to a power of two less than or equal * to PTRS_PER_PTE. * * The virtual address of the area that we map is naturally aligned to * fault_around_bytes rounded down to the machine page size * (and therefore to page order). This way it's easier to guarantee * that we don't cross page table boundaries. */ static vm_fault_t do_fault_around(struct vm_fault *vmf) { unsigned long address = vmf->address, nr_pages, mask; pgoff_t start_pgoff = vmf->pgoff; pgoff_t end_pgoff; int off; vm_fault_t ret = 0; nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK; vmf->address = max(address & mask, vmf->vma->vm_start); off = ((address - vmf->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); start_pgoff -= off; /* * end_pgoff is either the end of the page table, the end of * the vma or nr_pages from start_pgoff, depending what is nearest. */ end_pgoff = start_pgoff - ((vmf->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + PTRS_PER_PTE - 1; end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1, start_pgoff + nr_pages - 1); if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); if (!vmf->prealloc_pte) goto out; smp_wmb(); /* See comment in __pte_alloc() */ } vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); /* Huge page is mapped? Page fault is solved */ if (pmd_trans_huge(*vmf->pmd)) { ret = VM_FAULT_NOPAGE; goto out; } /* ->map_pages() haven't done anything useful. Cold page cache? */ if (!vmf->pte) goto out; /* check if the page fault is solved */ vmf->pte -= (vmf->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT); if (!pte_none(*vmf->pte)) ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); out: vmf->address = address; vmf->pte = NULL; return ret; } static vm_fault_t do_read_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; /* * Let's call ->map_pages() first and use ->fault() as fallback * if page by the offset is not ready to be mapped (cold cache or * something). */ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { ret = do_fault_around(vmf); if (ret) return ret; } ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; ret |= finish_fault(vmf); unlock_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) put_page(vmf->page); return ret; } static vm_fault_t do_cow_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!vmf->cow_page) return VM_FAULT_OOM; if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL); ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; if (ret & VM_FAULT_DONE_COW) return ret; copy_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma); __SetPageUptodate(vmf->cow_page); ret |= finish_fault(vmf); unlock_page(vmf->page); put_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; return ret; uncharge_out: put_page(vmf->cow_page); return ret; } static vm_fault_t do_shared_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret, tmp; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; /* * Check if the backing address space wants to know that the page is * about to become writable */ if (vma->vm_ops->page_mkwrite) { unlock_page(vmf->page); tmp = do_page_mkwrite(vmf); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { put_page(vmf->page); return tmp; } } ret |= finish_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) { unlock_page(vmf->page); put_page(vmf->page); return ret; } ret |= fault_dirty_shared_page(vmf); return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults). * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). * If mmap_lock is released, vma may become invalid (for example * by other thread calling munmap()). */ static vm_fault_t do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *vm_mm = vma->vm_mm; vm_fault_t ret; /* * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ if (!vma->vm_ops->fault) { /* * If we find a migration pmd entry or a none pmd entry, which * should never happen, return SIGBUS */ if (unlikely(!pmd_present(*vmf->pmd))) ret = VM_FAULT_SIGBUS; else { vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); /* * Make sure this is not a temporary clearing of pte * by holding ptl and checking again. A R/M/W update * of pte involves: take ptl, clearing the pte so that * we don't have concurrent modification by hardware * followed by an update. */ if (unlikely(pte_none(*vmf->pte))) ret = VM_FAULT_SIGBUS; else ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); } } else if (!(vmf->flags & FAULT_FLAG_WRITE)) ret = do_read_fault(vmf); else if (!(vma->vm_flags & VM_SHARED)) ret = do_cow_fault(vmf); else ret = do_shared_fault(vmf); /* preallocated pagetable is unused: free it */ if (vmf->prealloc_pte) { pte_free(vm_mm, vmf->prealloc_pte); vmf->prealloc_pte = NULL; } return ret; } static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) { get_page(page); count_vm_numa_event(NUMA_HINT_FAULTS); if (page_nid == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); *flags |= TNF_FAULT_LOCAL; } return mpol_misplaced(page, vma, addr); } static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL; int page_nid = NUMA_NO_NODE; int last_cpupid; int target_nid; bool migrated = false; pte_t pte, old_pte; bool was_writable = pte_savedwrite(vmf->orig_pte); int flags = 0; /* * The "pte" at this point cannot be used safely without * validation through pte_unmap_same(). It's of NUMA type but * the pfn may be screwed if the read is non atomic. */ vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); goto out; } /* * Make it present again, Depending on how arch implementes non * accessible ptes, some can allow access by kernel mode. */ old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); pte = pte_modify(old_pte, vma->vm_page_prot); pte = pte_mkyoung(pte); if (was_writable) pte = pte_mkwrite(pte); ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte); update_mmu_cache(vma, vmf->address, vmf->pte); page = vm_normal_page(vma, vmf->address, pte); if (!page) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* TODO: handle PTE-mapped THP */ if (PageCompound(page)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * Avoid grouping on RO pages in general. RO pages shouldn't hurt as * much anyway since they can be in shared cache state. This misses * the case where a mapping is writable but the process never writes * to it but pte_write gets cleared during protection updates and * pte_dirty has unpredictable behaviour between PTE scan updates, * background writeback, dirty balancing and application behaviour. */ if (!pte_write(pte)) flags |= TNF_NO_GROUP; /* * Flag if the page is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) flags |= TNF_SHARED; last_cpupid = page_cpupid_last(page); page_nid = page_to_nid(page); target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid, &flags); pte_unmap_unlock(vmf->pte, vmf->ptl); if (target_nid == NUMA_NO_NODE) { put_page(page); goto out; } /* Migrate to the requested node */ migrated = migrate_misplaced_page(page, vma, target_nid); if (migrated) { page_nid = target_nid; flags |= TNF_MIGRATED; } else flags |= TNF_MIGRATE_FAIL; out: if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, 1, flags); return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) return do_huge_pmd_anonymous_page(vmf); if (vmf->vma->vm_ops->huge_fault) return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); return VM_FAULT_FALLBACK; } /* `inline' is required to avoid gcc 4.1.2 build error */ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) { if (vma_is_anonymous(vmf->vma)) { if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd)) return handle_userfault(vmf, VM_UFFD_WP); return do_huge_pmd_wp_page(vmf, orig_pmd); } if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); if (!(ret & VM_FAULT_FALLBACK)) return ret; } /* COW or write-notify handled on pte level: split pmd. */ __split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL); return VM_FAULT_FALLBACK; } static vm_fault_t create_huge_pud(struct vm_fault *vmf) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) goto split; if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); if (!(ret & VM_FAULT_FALLBACK)) return ret; } split: /* COW or write-notify not handled on PUD level: split pud.*/ __split_huge_pud(vmf->vma, vmf->pud, vmf->address); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ return VM_FAULT_FALLBACK; } static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) return VM_FAULT_FALLBACK; if (vmf->vma->vm_ops->huge_fault) return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ return VM_FAULT_FALLBACK; } /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most * RISC architectures). The early dirtying is also good on the i386. * * There is also a hook called "update_mmu_cache()" that architectures * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow * concurrent faults). * * The mmap_lock may have been released depending on flags and our return value. * See filemap_fault() and __lock_page_or_retry(). */ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { pte_t entry; if (unlikely(pmd_none(*vmf->pmd))) { /* * Leave __pte_alloc() until later: because vm_ops->fault may * want to allocate huge page, and if we expose page table * for an instant, it will be difficult to retract from * concurrent faults and from rmap lookups. */ vmf->pte = NULL; } else { /* See comment in pte_alloc_one_map() */ if (pmd_devmap_trans_unstable(vmf->pmd)) return 0; /* * A regular pmd is established and it can't morph into a huge * pmd from under us anymore at this point because we hold the * mmap_lock read mode and khugepaged takes it in write mode. * So now it's safe to run pte_offset_map(). */ vmf->pte = pte_offset_map(vmf->pmd, vmf->address); vmf->orig_pte = *vmf->pte; /* * some architectures can have larger ptes than wordsize, * e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and * CONFIG_32BIT=y, so READ_ONCE cannot guarantee atomic * accesses. The code below just needs a consistent view * for the ifs and we later double check anyway with the * ptl lock held. So here a barrier will do. */ barrier(); if (pte_none(vmf->orig_pte)) { pte_unmap(vmf->pte); vmf->pte = NULL; } } if (!vmf->pte) { if (vma_is_anonymous(vmf->vma)) return do_anonymous_page(vmf); else return do_fault(vmf); } if (!pte_present(vmf->orig_pte)) return do_swap_page(vmf); if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) return do_numa_page(vmf); vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); entry = vmf->orig_pte; if (unlikely(!pte_same(*vmf->pte, entry))) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; } if (vmf->flags & FAULT_FLAG_WRITE) { if (!pte_write(entry)) return do_wp_page(vmf); entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, vmf->flags & FAULT_FLAG_WRITE)) { update_mmu_cache(vmf->vma, vmf->address, vmf->pte); } else { /* Skip spurious TLB flush for retried page fault */ if (vmf->flags & FAULT_FLAG_TRIED) goto unlock; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. * This still avoids useless tlb flushes for .text page faults * with threads. */ if (vmf->flags & FAULT_FLAG_WRITE) flush_tlb_fix_spurious_fault(vmf->vma, vmf->address); } unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { struct vm_fault vmf = { .vma = vma, .address = address & PAGE_MASK, .flags = flags, .pgoff = linear_page_index(vma, address), .gfp_mask = __get_fault_gfp_mask(vma), }; unsigned int dirty = flags & FAULT_FLAG_WRITE; struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; p4d_t *p4d; vm_fault_t ret; pgd = pgd_offset(mm, address); p4d = p4d_alloc(mm, pgd, address); if (!p4d) return VM_FAULT_OOM; vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; retry_pud: if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pud_t orig_pud = *vmf.pud; barrier(); if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { /* NUMA case for anonymous PUDs would go here */ if (dirty && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pud_set_accessed(&vmf, orig_pud); return 0; } } } vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd) return VM_FAULT_OOM; /* Huge pud page fault raced with pmd_alloc? */ if (pud_trans_unstable(vmf.pud)) goto retry_pud; if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pmd_t orig_pmd = *vmf.pmd; barrier(); if (unlikely(is_swap_pmd(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(orig_pmd)); if (is_pmd_migration_entry(orig_pmd)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf, orig_pmd); if (dirty && !pmd_write(orig_pmd)) { ret = wp_huge_pmd(&vmf, orig_pmd); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pmd_set_accessed(&vmf, orig_pmd); return 0; } } } return handle_pte_fault(&vmf); } /** * mm_account_fault - Do page fault accountings * * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting * of perf event counters, but we'll still do the per-task accounting to * the task who triggered this page fault. * @address: the faulted address. * @flags: the fault flags. * @ret: the fault retcode. * * This will take care of most of the page fault accountings. Meanwhile, it * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter * updates. However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should * still be in per-arch page fault handlers at the entry of page fault. */ static inline void mm_account_fault(struct pt_regs *regs, unsigned long address, unsigned int flags, vm_fault_t ret) { bool major; /* * We don't do accounting for some specific faults: * * - Unsuccessful faults (e.g. when the address wasn't valid). That * includes arch_vma_access_permitted() failing before reaching here. * So this is not a "this many hardware page faults" counter. We * should use the hw profiling for that. * * - Incomplete faults (VM_FAULT_RETRY). They will only be counted * once they're completed. */ if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY)) return; /* * We define the fault as a major fault when the final successful fault * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't * handle it immediately previously). */ major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); if (major) current->maj_flt++; else current->min_flt++; /* * If the fault is done for GUP, regs will be NULL. We only do the * accounting for the per thread fault counters who triggered the * fault, and we skip the perf event updates. */ if (!regs) return; if (major) perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); else perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { vm_fault_t ret; __set_current_state(TASK_RUNNING); count_vm_event(PGFAULT); count_memcg_event_mm(vma->vm_mm, PGFAULT); /* do counter updates before entering really critical section. */ check_sync_rss_stat(current); if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, flags & FAULT_FLAG_REMOTE)) return VM_FAULT_SIGSEGV; /* * Enable the memcg OOM handling for faults triggered in user * space. Kernel faults are handled more gracefully. */ if (flags & FAULT_FLAG_USER) mem_cgroup_enter_user_fault(); if (unlikely(is_vm_hugetlb_page(vma))) ret = hugetlb_fault(vma->vm_mm, vma, address, flags); else ret = __handle_mm_fault(vma, address, flags); if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault(); /* * The task may have entered a memcg OOM situation but * if the allocation error was handled gracefully (no * VM_FAULT_OOM), there is no need to kill anything. * Just clean up the OOM state peacefully. */ if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) mem_cgroup_oom_synchronize(false); } mm_account_fault(regs, address, flags, ret); return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); #ifndef __PAGETABLE_P4D_FOLDED /* * Allocate p4d page table. * We've already handled the fast-path in-line. */ int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { p4d_t *new = p4d_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); if (pgd_present(*pgd)) /* Another has populated it */ p4d_free(mm, new); else pgd_populate(mm, pgd, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_P4D_FOLDED */ #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); if (!p4d_present(*p4d)) { mm_inc_nr_puds(mm); p4d_populate(mm, p4d, new); } else /* Another has populated it */ pud_free(mm, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_PMD_FOLDED /* * Allocate page middle directory. * We've already handled the fast-path in-line. */ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { spinlock_t *ptl; pmd_t *new = pmd_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ ptl = pud_lock(mm, pud); if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); pud_populate(mm, pud, new); } else /* Another has populated it */ pmd_free(mm, new); spin_unlock(ptl); return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) goto out; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d))) goto out; pud = pud_offset(p4d, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) goto out; pmd = pmd_offset(pud, address); VM_BUG_ON(pmd_trans_huge(*pmd)); if (pmd_huge(*pmd)) { if (!pmdpp) goto out; if (range) { mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address & PMD_MASK, (address & PMD_MASK) + PMD_SIZE); mmu_notifier_invalidate_range_start(range); } *ptlp = pmd_lock(mm, pmd); if (pmd_huge(*pmd)) { *pmdpp = pmd; return 0; } spin_unlock(*ptlp); if (range) mmu_notifier_invalidate_range_end(range); } if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) goto out; if (range) { mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address & PAGE_MASK, (address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(range); } ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!pte_present(*ptep)) goto unlock; *ptepp = ptep; return 0; unlock: pte_unmap_unlock(ptep, *ptlp); if (range) mmu_notifier_invalidate_range_end(range); out: return -EINVAL; } /** * follow_pte - look up PTE at a user virtual address * @mm: the mm_struct of the target address space * @address: user virtual address * @ptepp: location to store found PTE * @ptlp: location to store the lock for the PTE * * On a successful return, the pointer to the PTE is stored in @ptepp; * the corresponding lock is taken and its location is stored in @ptlp. * The contents of the PTE are only stable until @ptlp is released; * any further use, if any, must be protected against invalidation * with MMU notifiers. * * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore * should be taken for read. * * KVM uses this function. While it is arguably less bad than ``follow_pfn``, * it is not a good general-purpose API. * * Return: zero on success, -ve otherwise. */ int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp) { return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp); } EXPORT_SYMBOL_GPL(follow_pte); /** * follow_pfn - look up PFN at a user virtual address * @vma: memory mapping * @address: user virtual address * @pfn: location to store found PFN * * Only IO mappings and raw PFN mappings are allowed. * * This function does not allow the caller to read the permissions * of the PTE. Do not use it. * * Return: zero and the pfn at @pfn on success, -ve otherwise. */ int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn) { int ret = -EINVAL; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) return ret; ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); if (ret) return ret; *pfn = pte_pfn(*ptep); pte_unmap_unlock(ptep, ptl); return 0; } EXPORT_SYMBOL(follow_pfn); #ifdef CONFIG_HAVE_IOREMAP_PROT int follow_phys(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned long *prot, resource_size_t *phys) { int ret = -EINVAL; pte_t *ptep, pte; spinlock_t *ptl; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) goto out; if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) goto out; pte = *ptep; if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; *prot = pgprot_val(pte_pgprot(pte)); *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; ret = 0; unlock: pte_unmap_unlock(ptep, ptl); out: return ret; } int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { resource_size_t phys_addr; unsigned long prot = 0; void __iomem *maddr; int offset = addr & (PAGE_SIZE-1); if (follow_phys(vma, addr, write, &prot, &phys_addr)) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (!maddr) return -ENOMEM; if (write) memcpy_toio(maddr + offset, buf, len); else memcpy_fromio(buf, maddr + offset, len); iounmap(maddr); return len; } EXPORT_SYMBOL_GPL(generic_access_phys); #endif /* * Access another process' address space as given in mm. If non-NULL, use the * given task for page fault accounting. */ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct vm_area_struct *vma; void *old_buf = buf; int write = gup_flags & FOLL_WRITE; if (mmap_read_lock_killable(mm)) return 0; /* ignore errors, just check how much was successfully transferred */ while (len) { int bytes, ret, offset; void *maddr; struct page *page = NULL; ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page, &vma, NULL); if (ret <= 0) { #ifndef CONFIG_HAVE_IOREMAP_PROT break; #else /* * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ vma = find_vma(mm, addr); if (!vma || vma->vm_start > addr) break; if (vma->vm_ops && vma->vm_ops->access) ret = vma->vm_ops->access(vma, addr, buf, len, write); if (ret <= 0) break; bytes = ret; #endif } else { bytes = len; offset = addr & (PAGE_SIZE-1); if (bytes > PAGE_SIZE-offset) bytes = PAGE_SIZE-offset; maddr = kmap(page); if (write) { copy_to_user_page(vma, page, addr, maddr + offset, buf, bytes); set_page_dirty_lock(page); } else { copy_from_user_page(vma, page, addr, buf, maddr + offset, bytes); } kunmap(page); put_page(page); } len -= bytes; buf += bytes; addr += bytes; } mmap_read_unlock(mm); return buf - old_buf; } /** * access_remote_vm - access another process' address space * @mm: the mm_struct of the target address space * @addr: start address to access * @buf: source or destination buffer * @len: number of bytes to transfer * @gup_flags: flags modifying lookup behaviour * * The caller must hold a reference on @mm. * * Return: number of bytes copied from source to destination. */ int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags); } /* * Access another process' address space. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags); mmput(mm); return ret; } EXPORT_SYMBOL_GPL(access_process_vm); /* * Print the name of a VMA. */ void print_vma_addr(char *prefix, unsigned long ip) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; /* * we might be running from an atomic context so we cannot sleep */ if (!mmap_read_trylock(mm)) return; vma = find_vma(mm, ip); if (vma && vma->vm_file) { struct file *f = vma->vm_file; char *buf = (char *)__get_free_page(GFP_NOWAIT); if (buf) { char *p; p = file_path(f, buf, PAGE_SIZE); if (IS_ERR(p)) p = "?"; printk("%s%s[%lx+%lx]", prefix, kbasename(p), vma->vm_start, vma->vm_end - vma->vm_start); free_page((unsigned long)buf); } } mmap_read_unlock(mm); } #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) void __might_fault(const char *file, int line) { /* * Some code (nfs/sunrpc) uses socket ops on kernel memory while * holding the mmap_lock, this is safe because kernel memory doesn't * get paged out, therefore we'll never actually fault, and the * below annotations will generate false positives. */ if (uaccess_kernel()) return; if (pagefault_disabled()) return; __might_sleep(file, line, 0); #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) might_lock_read(&current->mm->mmap_lock); #endif } EXPORT_SYMBOL(__might_fault); #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) /* * Process all subpages of the specified huge page with the specified * operation. The target subpage will be processed last to keep its * cache lines hot. */ static inline void process_huge_page( unsigned long addr_hint, unsigned int pages_per_huge_page, void (*process_subpage)(unsigned long addr, int idx, void *arg), void *arg) { int i, n, base, l; unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); /* Process target subpage last to keep its cache lines hot */ might_sleep(); n = (addr_hint - addr) / PAGE_SIZE; if (2 * n <= pages_per_huge_page) { /* If target subpage in first half of huge page */ base = 0; l = n; /* Process subpages at the end of huge page */ for (i = pages_per_huge_page - 1; i >= 2 * n; i--) { cond_resched(); process_subpage(addr + i * PAGE_SIZE, i, arg); } } else { /* If target subpage in second half of huge page */ base = pages_per_huge_page - 2 * (pages_per_huge_page - n); l = pages_per_huge_page - n; /* Process subpages at the begin of huge page */ for (i = 0; i < base; i++) { cond_resched(); process_subpage(addr + i * PAGE_SIZE, i, arg); } } /* * Process remaining subpages in left-right-left-right pattern * towards the target subpage */ for (i = 0; i < l; i++) { int left_idx = base + i; int right_idx = base + 2 * l - 1 - i; cond_resched(); process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); cond_resched(); process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); } } static void clear_gigantic_page(struct page *page, unsigned long addr, unsigned int pages_per_huge_page) { int i; struct page *p = page; might_sleep(); for (i = 0; i < pages_per_huge_page; i++, p = mem_map_next(p, page, i)) { cond_resched(); clear_user_highpage(p, addr + i * PAGE_SIZE); } } static void clear_subpage(unsigned long addr, int idx, void *arg) { struct page *page = arg; clear_user_highpage(page + idx, addr); } void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page) { unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { clear_gigantic_page(page, addr, pages_per_huge_page); return; } process_huge_page(addr_hint, pages_per_huge_page, clear_subpage, page); } static void copy_user_gigantic_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma, unsigned int pages_per_huge_page) { int i; struct page *dst_base = dst; struct page *src_base = src; for (i = 0; i < pages_per_huge_page; ) { cond_resched(); copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); i++; dst = mem_map_next(dst, dst_base, i); src = mem_map_next(src, src_base, i); } } struct copy_subpage_arg { struct page *dst; struct page *src; struct vm_area_struct *vma; }; static void copy_subpage(unsigned long addr, int idx, void *arg) { struct copy_subpage_arg *copy_arg = arg; copy_user_highpage(copy_arg->dst + idx, copy_arg->src + idx, addr, copy_arg->vma); } void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr_hint, struct vm_area_struct *vma, unsigned int pages_per_huge_page) { unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); struct copy_subpage_arg arg = { .dst = dst, .src = src, .vma = vma, }; if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { copy_user_gigantic_page(dst, src, addr, vma, pages_per_huge_page); return; } process_huge_page(addr_hint, pages_per_huge_page, copy_subpage, &arg); } long copy_huge_page_from_user(struct page *dst_page, const void __user *usr_src, unsigned int pages_per_huge_page, bool allow_pagefault) { void *src = (void *)usr_src; void *page_kaddr; unsigned long i, rc = 0; unsigned long ret_val = pages_per_huge_page * PAGE_SIZE; struct page *subpage = dst_page; for (i = 0; i < pages_per_huge_page; i++, subpage = mem_map_next(subpage, dst_page, i)) { if (allow_pagefault) page_kaddr = kmap(subpage); else page_kaddr = kmap_atomic(subpage); rc = copy_from_user(page_kaddr, (const void __user *)(src + i * PAGE_SIZE), PAGE_SIZE); if (allow_pagefault) kunmap(subpage); else kunmap_atomic(page_kaddr); ret_val -= (PAGE_SIZE - rc); if (rc) break; cond_resched(); } return ret_val; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep; void __init ptlock_cache_init(void) { page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, SLAB_PANIC, NULL); } bool ptlock_alloc(struct page *page) { spinlock_t *ptl; ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); if (!ptl) return false; page->ptl = ptl; return true; } void ptlock_free(struct page *page) { kmem_cache_free(page_ptl_cachep, page->ptl); } #endif
2 2 2 2 2 2 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 // SPDX-License-Identifier: GPL-2.0-only /* * fs/libfs.c * Library for filesystems writers. */ #include <linux/blkdev.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/quotaops.h> #include <linux/mutex.h> #include <linux/namei.h> #include <linux/exportfs.h> #include <linux/writeback.h> #include <linux/buffer_head.h> /* sync_mapping_buffers */ #include <linux/fs_context.h> #include <linux/pseudo_fs.h> #include <linux/fsnotify.h> #include <linux/unicode.h> #include <linux/fscrypt.h> #include <linux/uaccess.h> #include "internal.h" int simple_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(inode, stat); stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9); return 0; } EXPORT_SYMBOL(simple_getattr); int simple_statfs(struct dentry *dentry, struct kstatfs *buf) { buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; return 0; } EXPORT_SYMBOL(simple_statfs); /* * Retaining negative dentries for an in-memory filesystem just wastes * memory and lookup time: arrange for them to be deleted immediately. */ int always_delete_dentry(const struct dentry *dentry) { return 1; } EXPORT_SYMBOL(always_delete_dentry); const struct dentry_operations simple_dentry_operations = { .d_delete = always_delete_dentry, }; EXPORT_SYMBOL(simple_dentry_operations); /* * Lookup the data. This is trivial - if the dentry didn't already * exist, we know it is negative. Set d_op to delete negative dentries. */ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); if (!dentry->d_sb->s_d_op) d_set_d_op(dentry, &simple_dentry_operations); d_add(dentry, NULL); return NULL; } EXPORT_SYMBOL(simple_lookup); int dcache_dir_open(struct inode *inode, struct file *file) { file->private_data = d_alloc_cursor(file->f_path.dentry); return file->private_data ? 0 : -ENOMEM; } EXPORT_SYMBOL(dcache_dir_open); int dcache_dir_close(struct inode *inode, struct file *file) { dput(file->private_data); return 0; } EXPORT_SYMBOL(dcache_dir_close); /* parent is locked at least shared */ /* * Returns an element of siblings' list. * We are looking for <count>th positive after <p>; if * found, dentry is grabbed and returned to caller. * If no such element exists, NULL is returned. */ static struct dentry *scan_positives(struct dentry *cursor, struct list_head *p, loff_t count, struct dentry *last) { struct dentry *dentry = cursor->d_parent, *found = NULL; spin_lock(&dentry->d_lock); while ((p = p->next) != &dentry->d_subdirs) { struct dentry *d = list_entry(p, struct dentry, d_child); // we must at least skip cursors, to avoid livelocks if (d->d_flags & DCACHE_DENTRY_CURSOR) continue; if (simple_positive(d) && !--count) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) found = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(found)) break; count = 1; } if (need_resched()) { list_move(&cursor->d_child, p); p = &cursor->d_child; spin_unlock(&dentry->d_lock); cond_resched(); spin_lock(&dentry->d_lock); } } spin_unlock(&dentry->d_lock); dput(last); return found; } loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) { struct dentry *dentry = file->f_path.dentry; switch (whence) { case 1: offset += file->f_pos; fallthrough; case 0: if (offset >= 0) break; fallthrough; default: return -EINVAL; } if (offset != file->f_pos) { struct dentry *cursor = file->private_data; struct dentry *to = NULL; inode_lock_shared(dentry->d_inode); if (offset > 2) to = scan_positives(cursor, &dentry->d_subdirs, offset - 2, NULL); spin_lock(&dentry->d_lock); if (to) list_move(&cursor->d_child, &to->d_child); else list_del_init(&cursor->d_child); spin_unlock(&dentry->d_lock); dput(to); file->f_pos = offset; inode_unlock_shared(dentry->d_inode); } return offset; } EXPORT_SYMBOL(dcache_dir_lseek); /* Relationship between i_mode and the DT_xxx types */ static inline unsigned char dt_type(struct inode *inode) { return (inode->i_mode >> 12) & 15; } /* * Directory is locked and all positive dentries in it are safe, since * for ramfs-type trees they can't go away without unlink() or rmdir(), * both impossible due to the lock on directory. */ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; struct list_head *anchor = &dentry->d_subdirs; struct dentry *next = NULL; struct list_head *p; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) p = anchor; else if (!list_empty(&cursor->d_child)) p = &cursor->d_child; else return 0; while ((next = scan_positives(cursor, p, 1, next)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, d_inode(next)->i_ino, dt_type(d_inode(next)))) break; ctx->pos++; p = &next->d_child; } spin_lock(&dentry->d_lock); if (next) list_move_tail(&cursor->d_child, &next->d_child); else list_del_init(&cursor->d_child); spin_unlock(&dentry->d_lock); dput(next); return 0; } EXPORT_SYMBOL(dcache_readdir); ssize_t generic_read_dir(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { return -EISDIR; } EXPORT_SYMBOL(generic_read_dir); const struct file_operations simple_dir_operations = { .open = dcache_dir_open, .release = dcache_dir_close, .llseek = dcache_dir_lseek, .read = generic_read_dir, .iterate_shared = dcache_readdir, .fsync = noop_fsync, }; EXPORT_SYMBOL(simple_dir_operations); const struct inode_operations simple_dir_inode_operations = { .lookup = simple_lookup, }; EXPORT_SYMBOL(simple_dir_inode_operations); static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev) { struct dentry *child = NULL; struct list_head *p = prev ? &prev->d_child : &parent->d_subdirs; spin_lock(&parent->d_lock); while ((p = p->next) != &parent->d_subdirs) { struct dentry *d = container_of(p, struct dentry, d_child); if (simple_positive(d)) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) child = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(child)) break; } } spin_unlock(&parent->d_lock); dput(prev); return child; } void simple_recursive_removal(struct dentry *dentry, void (*callback)(struct dentry *)) { struct dentry *this = dget(dentry); while (true) { struct dentry *victim = NULL, *child; struct inode *inode = this->d_inode; inode_lock(inode); if (d_is_dir(this)) inode->i_flags |= S_DEAD; while ((child = find_next_child(this, victim)) == NULL) { // kill and ascend // update metadata while it's still locked inode->i_ctime = current_time(inode); clear_nlink(inode); inode_unlock(inode); victim = this; this = this->d_parent; inode = this->d_inode; inode_lock(inode); if (simple_positive(victim)) { d_invalidate(victim); // avoid lost mounts if (d_is_dir(victim)) fsnotify_rmdir(inode, victim); else fsnotify_unlink(inode, victim); if (callback) callback(victim); dput(victim); // unpin it } if (victim == dentry) { inode->i_ctime = inode->i_mtime = current_time(inode); if (d_is_dir(dentry)) drop_nlink(inode); inode_unlock(inode); dput(dentry); return; } } inode_unlock(inode); this = child; } } EXPORT_SYMBOL(simple_recursive_removal); static const struct super_operations simple_super_operations = { .statfs = simple_statfs, }; static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc) { struct pseudo_fs_context *ctx = fc->fs_private; struct inode *root; s->s_maxbytes = MAX_LFS_FILESIZE; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = ctx->magic; s->s_op = ctx->ops ?: &simple_super_operations; s->s_xattr = ctx->xattr; s->s_time_gran = 1; root = new_inode(s); if (!root) return -ENOMEM; /* * since this is the first inode, make it number 1. New inodes created * after this must take care not to collide with it (by passing * max_reserved of 1 to iunique). */ root->i_ino = 1; root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR; root->i_atime = root->i_mtime = root->i_ctime = current_time(root); s->s_root = d_make_root(root); if (!s->s_root) return -ENOMEM; s->s_d_op = ctx->dops; return 0; } static int pseudo_fs_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, pseudo_fs_fill_super); } static void pseudo_fs_free(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations pseudo_fs_context_ops = { .free = pseudo_fs_free, .get_tree = pseudo_fs_get_tree, }; /* * Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that * will never be mountable) */ struct pseudo_fs_context *init_pseudo(struct fs_context *fc, unsigned long magic) { struct pseudo_fs_context *ctx; ctx = kzalloc(sizeof(struct pseudo_fs_context), GFP_KERNEL); if (likely(ctx)) { ctx->magic = magic; fc->fs_private = ctx; fc->ops = &pseudo_fs_context_ops; fc->sb_flags |= SB_NOUSER; fc->global = true; } return ctx; } EXPORT_SYMBOL(init_pseudo); int simple_open(struct inode *inode, struct file *file) { if (inode->i_private) file->private_data = inode->i_private; return 0; } EXPORT_SYMBOL(simple_open); int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); inc_nlink(inode); ihold(inode); dget(dentry); d_instantiate(dentry, inode); return 0; } EXPORT_SYMBOL(simple_link); int simple_empty(struct dentry *dentry) { struct dentry *child; int ret = 0; spin_lock(&dentry->d_lock)