userfaultfd.c 51.2 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14
/*
 *  fs/userfaultfd.c
 *
 *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
 *  Copyright (C) 2008-2009 Red Hat, Inc.
 *  Copyright (C) 2015  Red Hat, Inc.
 *
 *  This work is licensed under the terms of the GNU GPL, version 2. See
 *  the COPYING file in the top-level directory.
 *
 *  Some part derived from fs/eventfd.c (anon inode setup) and
 *  mm/ksm.c (mm hashing).
 */

15
#include <linux/list.h>
16
#include <linux/hashtable.h>
17
#include <linux/sched/signal.h>
18
#include <linux/sched/mm.h>
19 20 21 22 23 24 25 26 27 28 29 30
#include <linux/mm.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/seq_file.h>
#include <linux/file.h>
#include <linux/bug.h>
#include <linux/anon_inodes.h>
#include <linux/syscalls.h>
#include <linux/userfaultfd_k.h>
#include <linux/mempolicy.h>
#include <linux/ioctl.h>
#include <linux/security.h>
31
#include <linux/hugetlb.h>
32

33 34
static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;

35 36 37 38 39
enum userfaultfd_state {
	UFFD_STATE_WAIT_API,
	UFFD_STATE_RUNNING,
};

40 41 42 43
/*
 * Start with fault_pending_wqh and fault_wqh so they're more likely
 * to be in the same cacheline.
 */
44
struct userfaultfd_ctx {
45 46 47
	/* waitqueue head for the pending (i.e. not read) userfaults */
	wait_queue_head_t fault_pending_wqh;
	/* waitqueue head for the userfaults */
48 49 50
	wait_queue_head_t fault_wqh;
	/* waitqueue head for the pseudo fd to wakeup poll/read */
	wait_queue_head_t fd_wqh;
51 52
	/* waitqueue head for events */
	wait_queue_head_t event_wqh;
53 54
	/* a refile sequence protected by fault_pending_wqh lock */
	struct seqcount refile_seq;
55 56
	/* pseudo fd refcounting */
	atomic_t refcount;
57 58
	/* userfaultfd syscall flags */
	unsigned int flags;
59 60
	/* features requested from the userspace */
	unsigned int features;
61 62 63 64 65 66 67 68
	/* state machine */
	enum userfaultfd_state state;
	/* released */
	bool released;
	/* mm with one ore more vmas attached to this userfaultfd_ctx */
	struct mm_struct *mm;
};

69 70 71 72 73 74
struct userfaultfd_fork_ctx {
	struct userfaultfd_ctx *orig;
	struct userfaultfd_ctx *new;
	struct list_head list;
};

75 76 77 78 79 80 81
struct userfaultfd_unmap_ctx {
	struct userfaultfd_ctx *ctx;
	unsigned long start;
	unsigned long end;
	struct list_head list;
};

82
struct userfaultfd_wait_queue {
83
	struct uffd_msg msg;
84
	wait_queue_entry_t wq;
85
	struct userfaultfd_ctx *ctx;
86
	bool waken;
87 88 89 90 91 92 93
};

struct userfaultfd_wake_range {
	unsigned long start;
	unsigned long len;
};

94
static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
95 96 97 98 99 100 101 102 103 104 105 106
				     int wake_flags, void *key)
{
	struct userfaultfd_wake_range *range = key;
	int ret;
	struct userfaultfd_wait_queue *uwq;
	unsigned long start, len;

	uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
	ret = 0;
	/* len == 0 means wake all */
	start = range->start;
	len = range->len;
107 108
	if (len && (start > uwq->msg.arg.pagefault.address ||
		    start + len <= uwq->msg.arg.pagefault.address))
109
		goto out;
110 111
	WRITE_ONCE(uwq->waken, true);
	/*
112 113
	 * The Program-Order guarantees provided by the scheduler
	 * ensure uwq->waken is visible before the task is woken.
114
	 */
115
	ret = wake_up_state(wq->private, mode);
116
	if (ret) {
117 118 119
		/*
		 * Wake only once, autoremove behavior.
		 *
120 121 122 123 124 125 126
		 * After the effect of list_del_init is visible to the other
		 * CPUs, the waitqueue may disappear from under us, see the
		 * !list_empty_careful() in handle_userfault().
		 *
		 * try_to_wake_up() has an implicit smp_mb(), and the
		 * wq->private is read before calling the extern function
		 * "wake_up_state" (which in turns calls try_to_wake_up).
127
		 */
128
		list_del_init(&wq->entry);
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
out:
	return ret;
}

/**
 * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
 * context.
 * @ctx: [in] Pointer to the userfaultfd context.
 */
static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
{
	if (!atomic_inc_not_zero(&ctx->refcount))
		BUG();
}

/**
 * userfaultfd_ctx_put - Releases a reference to the internal userfaultfd
 * context.
 * @ctx: [in] Pointer to userfaultfd context.
 *
 * The userfaultfd context reference must have been previously acquired either
 * with userfaultfd_ctx_get() or userfaultfd_ctx_fdget().
 */
static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx)
{
	if (atomic_dec_and_test(&ctx->refcount)) {
		VM_BUG_ON(spin_is_locked(&ctx->fault_pending_wqh.lock));
		VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh));
		VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock));
		VM_BUG_ON(waitqueue_active(&ctx->fault_wqh));
160 161
		VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock));
		VM_BUG_ON(waitqueue_active(&ctx->event_wqh));
162 163
		VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock));
		VM_BUG_ON(waitqueue_active(&ctx->fd_wqh));
164
		mmdrop(ctx->mm);
165
		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
166 167 168
	}
}

169
static inline void msg_init(struct uffd_msg *msg)
170
{
171 172 173 174 175 176 177 178 179 180
	BUILD_BUG_ON(sizeof(struct uffd_msg) != 32);
	/*
	 * Must use memset to zero out the paddings or kernel data is
	 * leaked to userland.
	 */
	memset(msg, 0, sizeof(struct uffd_msg));
}

static inline struct uffd_msg userfault_msg(unsigned long address,
					    unsigned int flags,
181 182
					    unsigned long reason,
					    unsigned int features)
183 184 185 186 187
{
	struct uffd_msg msg;
	msg_init(&msg);
	msg.event = UFFD_EVENT_PAGEFAULT;
	msg.arg.pagefault.address = address;
188 189
	if (flags & FAULT_FLAG_WRITE)
		/*
190
		 * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
191 192 193 194
		 * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE
		 * was not set in a UFFD_EVENT_PAGEFAULT, it means it
		 * was a read fault, otherwise if set it means it's
		 * a write fault.
195
		 */
196
		msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE;
197 198
	if (reason & VM_UFFD_WP)
		/*
199 200 201 202 203
		 * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
		 * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WP was
		 * not set in a UFFD_EVENT_PAGEFAULT, it means it was
		 * a missing fault, otherwise if set it means it's a
		 * write protect fault.
204
		 */
205
		msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP;
206
	if (features & UFFD_FEATURE_THREAD_ID)
207
		msg.arg.pagefault.feat.ptid = task_pid_vnr(current);
208
	return msg;
209 210
}

211 212 213 214 215 216
#ifdef CONFIG_HUGETLB_PAGE
/*
 * Same functionality as userfaultfd_must_wait below with modifications for
 * hugepmd ranges.
 */
static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
217
					 struct vm_area_struct *vma,
218 219 220 221 222
					 unsigned long address,
					 unsigned long flags,
					 unsigned long reason)
{
	struct mm_struct *mm = ctx->mm;
223
	pte_t *ptep, pte;
224 225 226 227
	bool ret = true;

	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));

228 229 230
	ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));

	if (!ptep)
231 232 233
		goto out;

	ret = false;
234
	pte = huge_ptep_get(ptep);
235 236 237 238 239

	/*
	 * Lockless access: we're in a wait_event so it's ok if it
	 * changes under us.
	 */
240
	if (huge_pte_none(pte))
241
		ret = true;
242
	if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
243 244 245 246 247 248
		ret = true;
out:
	return ret;
}
#else
static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
249
					 struct vm_area_struct *vma,
250 251 252 253 254 255 256 257
					 unsigned long address,
					 unsigned long flags,
					 unsigned long reason)
{
	return false;	/* should never get here */
}
#endif /* CONFIG_HUGETLB_PAGE */

258 259 260 261 262 263 264 265 266 267 268 269 270 271
/*
 * Verify the pagetables are still not ok after having reigstered into
 * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any
 * userfault that has already been resolved, if userfaultfd_read and
 * UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different
 * threads.
 */
static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
					 unsigned long address,
					 unsigned long flags,
					 unsigned long reason)
{
	struct mm_struct *mm = ctx->mm;
	pgd_t *pgd;
272
	p4d_t *p4d;
273 274 275 276 277 278 279 280 281 282
	pud_t *pud;
	pmd_t *pmd, _pmd;
	pte_t *pte;
	bool ret = true;

	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));

	pgd = pgd_offset(mm, address);
	if (!pgd_present(*pgd))
		goto out;
283 284 285 286
	p4d = p4d_offset(pgd, address);
	if (!p4d_present(*p4d))
		goto out;
	pud = pud_offset(p4d, address);
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
	if (!pud_present(*pud))
		goto out;
	pmd = pmd_offset(pud, address);
	/*
	 * READ_ONCE must function as a barrier with narrower scope
	 * and it must be equivalent to:
	 *	_pmd = *pmd; barrier();
	 *
	 * This is to deal with the instability (as in
	 * pmd_trans_unstable) of the pmd.
	 */
	_pmd = READ_ONCE(*pmd);
	if (!pmd_present(_pmd))
		goto out;

	ret = false;
	if (pmd_trans_huge(_pmd))
		goto out;

	/*
	 * the pmd is stable (as in !pmd_trans_unstable) so we can re-read it
	 * and use the standard pte_offset_map() instead of parsing _pmd.
	 */
	pte = pte_offset_map(pmd, address);
	/*
	 * Lockless access: we're in a wait_event so it's ok if it
	 * changes under us.
	 */
	if (pte_none(*pte))
		ret = true;
	pte_unmap(pte);

out:
	return ret;
}

323 324 325 326 327 328 329 330 331 332 333 334 335 336 337
/*
 * The locking rules involved in returning VM_FAULT_RETRY depending on
 * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and
 * FAULT_FLAG_KILLABLE are not straightforward. The "Caution"
 * recommendation in __lock_page_or_retry is not an understatement.
 *
 * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_sem must be released
 * before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is
 * not set.
 *
 * If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not
 * set, VM_FAULT_RETRY can still be returned if and only if there are
 * fatal_signal_pending()s, and the mmap_sem must be released before
 * returning it.
 */
338
int handle_userfault(struct vm_fault *vmf, unsigned long reason)
339
{
340
	struct mm_struct *mm = vmf->vma->vm_mm;
341 342
	struct userfaultfd_ctx *ctx;
	struct userfaultfd_wait_queue uwq;
343
	int ret;
344
	bool must_wait, return_to_userland;
345
	long blocking_state;
346

347
	ret = VM_FAULT_SIGBUS;
348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368

	/*
	 * We don't do userfault handling for the final child pid update.
	 *
	 * We also don't do userfault handling during
	 * coredumping. hugetlbfs has the special
	 * follow_hugetlb_page() to skip missing pages in the
	 * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with
	 * the no_page_table() helper in follow_page_mask(), but the
	 * shmem_vm_ops->fault method is invoked even during
	 * coredumping without mmap_sem and it ends up here.
	 */
	if (current->flags & (PF_EXITING|PF_DUMPCORE))
		goto out;

	/*
	 * Coredumping runs without mmap_sem so we can only check that
	 * the mmap_sem is held, if PF_DUMPCORE was not set.
	 */
	WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem));

369
	ctx = vmf->vma->vm_userfaultfd_ctx.ctx;
370
	if (!ctx)
371
		goto out;
372 373 374 375 376 377

	BUG_ON(ctx->mm != mm);

	VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP));
	VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP));

378 379 380
	if (ctx->features & UFFD_FEATURE_SIGBUS)
		goto out;

381 382 383 384 385
	/*
	 * If it's already released don't get it. This avoids to loop
	 * in __get_user_pages if userfaultfd_release waits on the
	 * caller of handle_userfault to release the mmap_sem.
	 */
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403
	if (unlikely(ACCESS_ONCE(ctx->released))) {
		/*
		 * Don't return VM_FAULT_SIGBUS in this case, so a non
		 * cooperative manager can close the uffd after the
		 * last UFFDIO_COPY, without risking to trigger an
		 * involuntary SIGBUS if the process was starting the
		 * userfaultfd while the userfaultfd was still armed
		 * (but after the last UFFDIO_COPY). If the uffd
		 * wasn't already closed when the userfault reached
		 * this point, that would normally be solved by
		 * userfaultfd_must_wait returning 'false'.
		 *
		 * If we were to return VM_FAULT_SIGBUS here, the non
		 * cooperative manager would be instead forced to
		 * always call UFFDIO_UNREGISTER before it can safely
		 * close the uffd.
		 */
		ret = VM_FAULT_NOPAGE;
404
		goto out;
405
	}
406 407 408 409 410 411 412 413 414 415 416

	/*
	 * Check that we can return VM_FAULT_RETRY.
	 *
	 * NOTE: it should become possible to return VM_FAULT_RETRY
	 * even if FAULT_FLAG_TRIED is set without leading to gup()
	 * -EBUSY failures, if the userfaultfd is to be extended for
	 * VM_UFFD_WP tracking and we intend to arm the userfault
	 * without first stopping userland access to the memory. For
	 * VM_UFFD_MISSING userfaults this is enough for now.
	 */
417
	if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) {
418 419 420 421 422
		/*
		 * Validate the invariant that nowait must allow retry
		 * to be sure not to return SIGBUS erroneously on
		 * nowait invocations.
		 */
423
		BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT);
424 425 426
#ifdef CONFIG_DEBUG_VM
		if (printk_ratelimit()) {
			printk(KERN_WARNING
427 428
			       "FAULT_FLAG_ALLOW_RETRY missing %x\n",
			       vmf->flags);
429 430 431
			dump_stack();
		}
#endif
432
		goto out;
433 434 435 436 437 438
	}

	/*
	 * Handle nowait, not much to do other than tell it to retry
	 * and wait.
	 */
439
	ret = VM_FAULT_RETRY;
440
	if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
441
		goto out;
442 443 444 445 446 447

	/* take the reference before dropping the mmap_sem */
	userfaultfd_ctx_get(ctx);

	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
	uwq.wq.private = current;
448 449
	uwq.msg = userfault_msg(vmf->address, vmf->flags, reason,
			ctx->features);
450
	uwq.ctx = ctx;
451
	uwq.waken = false;
452

453
	return_to_userland =
454
		(vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
455
		(FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
456 457
	blocking_state = return_to_userland ? TASK_INTERRUPTIBLE :
			 TASK_KILLABLE;
458

459
	spin_lock(&ctx->fault_pending_wqh.lock);
460 461 462 463
	/*
	 * After the __add_wait_queue the uwq is visible to userland
	 * through poll/read().
	 */
464 465 466 467 468 469
	__add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq);
	/*
	 * The smp_mb() after __set_current_state prevents the reads
	 * following the spin_unlock to happen before the list_add in
	 * __add_wait_queue.
	 */
470
	set_current_state(blocking_state);
471
	spin_unlock(&ctx->fault_pending_wqh.lock);
472

473 474 475 476
	if (!is_vm_hugetlb_page(vmf->vma))
		must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
						  reason);
	else
477 478
		must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma,
						       vmf->address,
479
						       vmf->flags, reason);
480 481 482
	up_read(&mm->mmap_sem);

	if (likely(must_wait && !ACCESS_ONCE(ctx->released) &&
483 484
		   (return_to_userland ? !signal_pending(current) :
		    !fatal_signal_pending(current)))) {
485 486
		wake_up_poll(&ctx->fd_wqh, POLLIN);
		schedule();
487
		ret |= VM_FAULT_MAJOR;
488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510

		/*
		 * False wakeups can orginate even from rwsem before
		 * up_read() however userfaults will wait either for a
		 * targeted wakeup on the specific uwq waitqueue from
		 * wake_userfault() or for signals or for uffd
		 * release.
		 */
		while (!READ_ONCE(uwq.waken)) {
			/*
			 * This needs the full smp_store_mb()
			 * guarantee as the state write must be
			 * visible to other CPUs before reading
			 * uwq.waken from other CPUs.
			 */
			set_current_state(blocking_state);
			if (READ_ONCE(uwq.waken) ||
			    READ_ONCE(ctx->released) ||
			    (return_to_userland ? signal_pending(current) :
			     fatal_signal_pending(current)))
				break;
			schedule();
		}
511
	}
512

513
	__set_current_state(TASK_RUNNING);
514

515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
	if (return_to_userland) {
		if (signal_pending(current) &&
		    !fatal_signal_pending(current)) {
			/*
			 * If we got a SIGSTOP or SIGCONT and this is
			 * a normal userland page fault, just let
			 * userland return so the signal will be
			 * handled and gdb debugging works.  The page
			 * fault code immediately after we return from
			 * this function is going to release the
			 * mmap_sem and it's not depending on it
			 * (unlike gup would if we were not to return
			 * VM_FAULT_RETRY).
			 *
			 * If a fatal signal is pending we still take
			 * the streamlined VM_FAULT_RETRY failure path
			 * and there's no need to retake the mmap_sem
			 * in such case.
			 */
			down_read(&mm->mmap_sem);
535
			ret = VM_FAULT_NOPAGE;
536 537 538
		}
	}

539 540 541 542 543 544 545 546 547 548 549 550 551
	/*
	 * Here we race with the list_del; list_add in
	 * userfaultfd_ctx_read(), however because we don't ever run
	 * list_del_init() to refile across the two lists, the prev
	 * and next pointers will never point to self. list_add also
	 * would never let any of the two pointers to point to
	 * self. So list_empty_careful won't risk to see both pointers
	 * pointing to self at any time during the list refile. The
	 * only case where list_del_init() is called is the full
	 * removal in the wake function and there we don't re-list_add
	 * and it's fine not to block on the spinlock. The uwq on this
	 * kernel stack can be released after the list_del_init.
	 */
552
	if (!list_empty_careful(&uwq.wq.entry)) {
553 554 555 556 557
		spin_lock(&ctx->fault_pending_wqh.lock);
		/*
		 * No need of list_del_init(), the uwq on the stack
		 * will be freed shortly anyway.
		 */
558
		list_del(&uwq.wq.entry);
559
		spin_unlock(&ctx->fault_pending_wqh.lock);
560 561 562 563 564 565 566 567
	}

	/*
	 * ctx may go away after this if the userfault pseudo fd is
	 * already released.
	 */
	userfaultfd_ctx_put(ctx);

568 569
out:
	return ret;
570 571
}

572 573
static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
					      struct userfaultfd_wait_queue *ewq)
574
{
575 576
	struct userfaultfd_ctx *release_new_ctx;

577 578
	if (WARN_ON_ONCE(current->flags & PF_EXITING))
		goto out;
579 580 581

	ewq->ctx = ctx;
	init_waitqueue_entry(&ewq->wq, current);
582
	release_new_ctx = NULL;
583 584 585 586 587 588 589 590 591 592 593 594 595

	spin_lock(&ctx->event_wqh.lock);
	/*
	 * After the __add_wait_queue the uwq is visible to userland
	 * through poll/read().
	 */
	__add_wait_queue(&ctx->event_wqh, &ewq->wq);
	for (;;) {
		set_current_state(TASK_KILLABLE);
		if (ewq->msg.event == 0)
			break;
		if (ACCESS_ONCE(ctx->released) ||
		    fatal_signal_pending(current)) {
596 597 598 599 600 601
			/*
			 * &ewq->wq may be queued in fork_event, but
			 * __remove_wait_queue ignores the head
			 * parameter. It would be a problem if it
			 * didn't.
			 */
602
			__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
603 604 605 606 607 608
			if (ewq->msg.event == UFFD_EVENT_FORK) {
				struct userfaultfd_ctx *new;

				new = (struct userfaultfd_ctx *)
					(unsigned long)
					ewq->msg.arg.reserved.reserved1;
609
				release_new_ctx = new;
610
			}
611 612 613 614 615 616 617 618 619 620 621 622 623
			break;
		}

		spin_unlock(&ctx->event_wqh.lock);

		wake_up_poll(&ctx->fd_wqh, POLLIN);
		schedule();

		spin_lock(&ctx->event_wqh.lock);
	}
	__set_current_state(TASK_RUNNING);
	spin_unlock(&ctx->event_wqh.lock);

624 625 626 627 628 629 630
	if (release_new_ctx) {
		struct vm_area_struct *vma;
		struct mm_struct *mm = release_new_ctx->mm;

		/* the various vma->vm_userfaultfd_ctx still points to it */
		down_write(&mm->mmap_sem);
		for (vma = mm->mmap; vma; vma = vma->vm_next)
631
			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
632
				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
633 634
				vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
			}
635 636 637 638 639
		up_write(&mm->mmap_sem);

		userfaultfd_ctx_put(release_new_ctx);
	}

640 641 642 643
	/*
	 * ctx may go away after this if the userfault pseudo fd is
	 * already released.
	 */
644
out:
645 646 647 648 649 650 651 652 653 654 655
	userfaultfd_ctx_put(ctx);
}

static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx,
				       struct userfaultfd_wait_queue *ewq)
{
	ewq->msg.event = 0;
	wake_up_locked(&ctx->event_wqh);
	__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
}

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
int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
{
	struct userfaultfd_ctx *ctx = NULL, *octx;
	struct userfaultfd_fork_ctx *fctx;

	octx = vma->vm_userfaultfd_ctx.ctx;
	if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
		vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
		return 0;
	}

	list_for_each_entry(fctx, fcs, list)
		if (fctx->orig == octx) {
			ctx = fctx->new;
			break;
		}

	if (!ctx) {
		fctx = kmalloc(sizeof(*fctx), GFP_KERNEL);
		if (!fctx)
			return -ENOMEM;

		ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
		if (!ctx) {
			kfree(fctx);
			return -ENOMEM;
		}

		atomic_set(&ctx->refcount, 1);
		ctx->flags = octx->flags;
		ctx->state = UFFD_STATE_RUNNING;
		ctx->features = octx->features;
		ctx->released = false;
		ctx->mm = vma->vm_mm;
691
		atomic_inc(&ctx->mm->mm_count);
692 693 694 695 696 697 698 699 700 701 702

		userfaultfd_ctx_get(octx);
		fctx->orig = octx;
		fctx->new = ctx;
		list_add_tail(&fctx->list, fcs);
	}

	vma->vm_userfaultfd_ctx.ctx = ctx;
	return 0;
}

703
static void dup_fctx(struct userfaultfd_fork_ctx *fctx)
704 705 706 707 708 709 710 711 712
{
	struct userfaultfd_ctx *ctx = fctx->orig;
	struct userfaultfd_wait_queue ewq;

	msg_init(&ewq.msg);

	ewq.msg.event = UFFD_EVENT_FORK;
	ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new;

713
	userfaultfd_event_wait_completion(ctx, &ewq);
714 715 716 717 718 719 720
}

void dup_userfaultfd_complete(struct list_head *fcs)
{
	struct userfaultfd_fork_ctx *fctx, *n;

	list_for_each_entry_safe(fctx, n, fcs, list) {
721
		dup_fctx(fctx);
722 723 724 725 726
		list_del(&fctx->list);
		kfree(fctx);
	}
}

727 728 729 730 731 732 733 734 735 736 737 738
void mremap_userfaultfd_prep(struct vm_area_struct *vma,
			     struct vm_userfaultfd_ctx *vm_ctx)
{
	struct userfaultfd_ctx *ctx;

	ctx = vma->vm_userfaultfd_ctx.ctx;
	if (ctx && (ctx->features & UFFD_FEATURE_EVENT_REMAP)) {
		vm_ctx->ctx = ctx;
		userfaultfd_ctx_get(ctx);
	}
}

739
void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
740 741 742
				 unsigned long from, unsigned long to,
				 unsigned long len)
{
743
	struct userfaultfd_ctx *ctx = vm_ctx->ctx;
744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763
	struct userfaultfd_wait_queue ewq;

	if (!ctx)
		return;

	if (to & ~PAGE_MASK) {
		userfaultfd_ctx_put(ctx);
		return;
	}

	msg_init(&ewq.msg);

	ewq.msg.event = UFFD_EVENT_REMAP;
	ewq.msg.arg.remap.from = from;
	ewq.msg.arg.remap.to = to;
	ewq.msg.arg.remap.len = len;

	userfaultfd_event_wait_completion(ctx, &ewq);
}

764
bool userfaultfd_remove(struct vm_area_struct *vma,
765
			unsigned long start, unsigned long end)
766 767 768 769 770 771
{
	struct mm_struct *mm = vma->vm_mm;
	struct userfaultfd_ctx *ctx;
	struct userfaultfd_wait_queue ewq;

	ctx = vma->vm_userfaultfd_ctx.ctx;
772
	if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
773
		return true;
774 775 776 777 778 779

	userfaultfd_ctx_get(ctx);
	up_read(&mm->mmap_sem);

	msg_init(&ewq.msg);

780 781 782
	ewq.msg.event = UFFD_EVENT_REMOVE;
	ewq.msg.arg.remove.start = start;
	ewq.msg.arg.remove.end = end;
783 784 785

	userfaultfd_event_wait_completion(ctx, &ewq);

786
	return false;
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
static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
			  unsigned long start, unsigned long end)
{
	struct userfaultfd_unmap_ctx *unmap_ctx;

	list_for_each_entry(unmap_ctx, unmaps, list)
		if (unmap_ctx->ctx == ctx && unmap_ctx->start == start &&
		    unmap_ctx->end == end)
			return true;

	return false;
}

int userfaultfd_unmap_prep(struct vm_area_struct *vma,
			   unsigned long start, unsigned long end,
			   struct list_head *unmaps)
{
	for ( ; vma && vma->vm_start < end; vma = vma->vm_next) {
		struct userfaultfd_unmap_ctx *unmap_ctx;
		struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;

		if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) ||
		    has_unmap_ctx(ctx, unmaps, start, end))
			continue;

		unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL);
		if (!unmap_ctx)
			return -ENOMEM;

		userfaultfd_ctx_get(ctx);
		unmap_ctx->ctx = ctx;
		unmap_ctx->start = start;
		unmap_ctx->end = end;
		list_add_tail(&unmap_ctx->list, unmaps);
	}

	return 0;
}

void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
{
	struct userfaultfd_unmap_ctx *ctx, *n;
	struct userfaultfd_wait_queue ewq;

	list_for_each_entry_safe(ctx, n, uf, list) {
		msg_init(&ewq.msg);

		ewq.msg.event = UFFD_EVENT_UNMAP;
		ewq.msg.arg.remove.start = ctx->start;
		ewq.msg.arg.remove.end = ctx->end;

		userfaultfd_event_wait_completion(ctx->ctx, &ewq);

		list_del(&ctx->list);
		kfree(ctx);
	}
}

847 848 849 850 851 852 853 854 855 856 857
static int userfaultfd_release(struct inode *inode, struct file *file)
{
	struct userfaultfd_ctx *ctx = file->private_data;
	struct mm_struct *mm = ctx->mm;
	struct vm_area_struct *vma, *prev;
	/* len == 0 means wake all */
	struct userfaultfd_wake_range range = { .len = 0, };
	unsigned long new_flags;

	ACCESS_ONCE(ctx->released) = true;

858 859 860
	if (!mmget_not_zero(mm))
		goto wakeup;

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
	/*
	 * Flush page faults out of all CPUs. NOTE: all page faults
	 * must be retried without returning VM_FAULT_SIGBUS if
	 * userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx
	 * changes while handle_userfault released the mmap_sem. So
	 * it's critical that released is set to true (above), before
	 * taking the mmap_sem for writing.
	 */
	down_write(&mm->mmap_sem);
	prev = NULL;
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		cond_resched();
		BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^
		       !!(vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
		if (vma->vm_userfaultfd_ctx.ctx != ctx) {
			prev = vma;
			continue;
		}
		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
		prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
				 new_flags, vma->anon_vma,
				 vma->vm_file, vma->vm_pgoff,
				 vma_policy(vma),
				 NULL_VM_UFFD_CTX);
		if (prev)
			vma = prev;
		else
			prev = vma;
		vma->vm_flags = new_flags;
		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
	}
	up_write(&mm->mmap_sem);
893 894
	mmput(mm);
wakeup:
895
	/*
896
	 * After no new page faults can wait on this fault_*wqh, flush
897
	 * the last page faults that may have been already waiting on
898
	 * the fault_*wqh.
899
	 */
900
	spin_lock(&ctx->fault_pending_wqh.lock);
901 902
	__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range);
	__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, &range);
903
	spin_unlock(&ctx->fault_pending_wqh.lock);
904

905 906 907
	/* Flush pending events that may still wait on event_wqh */
	wake_up_all(&ctx->event_wqh);

908 909 910 911 912
	wake_up_poll(&ctx->fd_wqh, POLLHUP);
	userfaultfd_ctx_put(ctx);
	return 0;
}

913
/* fault_pending_wqh.lock must be hold by the caller */
914 915
static inline struct userfaultfd_wait_queue *find_userfault_in(
		wait_queue_head_t *wqh)
916
{
917
	wait_queue_entry_t *wq;
918
	struct userfaultfd_wait_queue *uwq;
919

920
	VM_BUG_ON(!spin_is_locked(&wqh->lock));
921

922
	uwq = NULL;
923
	if (!waitqueue_active(wqh))
924 925
		goto out;
	/* walk in reverse to provide FIFO behavior to read userfaults */
926
	wq = list_last_entry(&wqh->head, typeof(*wq), entry);
927 928 929
	uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
out:
	return uwq;
930
}
931 932 933 934 935 936

static inline struct userfaultfd_wait_queue *find_userfault(
		struct userfaultfd_ctx *ctx)
{
	return find_userfault_in(&ctx->fault_pending_wqh);
}
937

938 939 940 941 942 943
static inline struct userfaultfd_wait_queue *find_userfault_evt(
		struct userfaultfd_ctx *ctx)
{
	return find_userfault_in(&ctx->event_wqh);
}

944 945 946 947 948 949 950 951 952 953 954
static unsigned int userfaultfd_poll(struct file *file, poll_table *wait)
{
	struct userfaultfd_ctx *ctx = file->private_data;
	unsigned int ret;

	poll_wait(file, &ctx->fd_wqh, wait);

	switch (ctx->state) {
	case UFFD_STATE_WAIT_API:
		return POLLERR;
	case UFFD_STATE_RUNNING:
955 956 957 958 959 960
		/*
		 * poll() never guarantees that read won't block.
		 * userfaults can be waken before they're read().
		 */
		if (unlikely(!(file->f_flags & O_NONBLOCK)))
			return POLLERR;
961 962 963 964 965 966 967 968 969 970 971 972 973 974
		/*
		 * lockless access to see if there are pending faults
		 * __pollwait last action is the add_wait_queue but
		 * the spin_unlock would allow the waitqueue_active to
		 * pass above the actual list_add inside
		 * add_wait_queue critical section. So use a full
		 * memory barrier to serialize the list_add write of
		 * add_wait_queue() with the waitqueue_active read
		 * below.
		 */
		ret = 0;
		smp_mb();
		if (waitqueue_active(&ctx->fault_pending_wqh))
			ret = POLLIN;
975 976 977
		else if (waitqueue_active(&ctx->event_wqh))
			ret = POLLIN;

978 979
		return ret;
	default:
980 981
		WARN_ON_ONCE(1);
		return POLLERR;
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
static const struct file_operations userfaultfd_fops;

static int resolve_userfault_fork(struct userfaultfd_ctx *ctx,
				  struct userfaultfd_ctx *new,
				  struct uffd_msg *msg)
{
	int fd;
	struct file *file;
	unsigned int flags = new->flags & UFFD_SHARED_FCNTL_FLAGS;

	fd = get_unused_fd_flags(flags);
	if (fd < 0)
		return fd;

	file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, new,
				  O_RDWR | flags);
	if (IS_ERR(file)) {
		put_unused_fd(fd);
		return PTR_ERR(file);
	}

	fd_install(fd, file);
	msg->arg.reserved.reserved1 = 0;
	msg->arg.fork.ufd = fd;

	return 0;
}

1013
static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
1014
				    struct uffd_msg *msg)
1015 1016 1017
{
	ssize_t ret;
	DECLARE_WAITQUEUE(wait, current);
1018
	struct userfaultfd_wait_queue *uwq;
1019 1020 1021 1022 1023 1024 1025 1026 1027
	/*
	 * Handling fork event requires sleeping operations, so
	 * we drop the event_wqh lock, then do these ops, then
	 * lock it back and wake up the waiter. While the lock is
	 * dropped the ewq may go away so we keep track of it
	 * carefully.
	 */
	LIST_HEAD(fork_event);
	struct userfaultfd_ctx *fork_nctx = NULL;
1028

1029
	/* always take the fd_wqh lock before the fault_pending_wqh lock */
1030 1031 1032 1033
	spin_lock(&ctx->fd_wqh.lock);
	__add_wait_queue(&ctx->fd_wqh, &wait);
	for (;;) {
		set_current_state(TASK_INTERRUPTIBLE);
1034 1035 1036
		spin_lock(&ctx->fault_pending_wqh.lock);
		uwq = find_userfault(ctx);
		if (uwq) {
1037 1038 1039 1040 1041 1042 1043 1044 1045
			/*
			 * Use a seqcount to repeat the lockless check
			 * in wake_userfault() to avoid missing
			 * wakeups because during the refile both
			 * waitqueue could become empty if this is the
			 * only userfault.
			 */
			write_seqcount_begin(&ctx->refile_seq);

1046
			/*
1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059
			 * The fault_pending_wqh.lock prevents the uwq
			 * to disappear from under us.
			 *
			 * Refile this userfault from
			 * fault_pending_wqh to fault_wqh, it's not
			 * pending anymore after we read it.
			 *
			 * Use list_del() by hand (as
			 * userfaultfd_wake_function also uses
			 * list_del_init() by hand) to be sure nobody
			 * changes __remove_wait_queue() to use
			 * list_del_init() in turn breaking the
			 * !list_empty_careful() check in
1060
			 * handle_userfault(). The uwq->wq.head list
1061 1062 1063 1064 1065
			 * must never be empty at any time during the
			 * refile, or the waitqueue could disappear
			 * from under us. The "wait_queue_head_t"
			 * parameter of __remove_wait_queue() is unused
			 * anyway.
1066
			 */
1067
			list_del(&uwq->wq.entry);
1068 1069
			__add_wait_queue(&ctx->fault_wqh, &uwq->wq);

1070 1071
			write_seqcount_end(&ctx->refile_seq);

1072 1073
			/* careful to always initialize msg if ret == 0 */
			*msg = uwq->msg;
1074
			spin_unlock(&ctx->fault_pending_wqh.lock);
1075 1076 1077
			ret = 0;
			break;
		}
1078
		spin_unlock(&ctx->fault_pending_wqh.lock);
1079 1080 1081 1082 1083 1084

		spin_lock(&ctx->event_wqh.lock);
		uwq = find_userfault_evt(ctx);
		if (uwq) {
			*msg = uwq->msg;

1085 1086 1087 1088
			if (uwq->msg.event == UFFD_EVENT_FORK) {
				fork_nctx = (struct userfaultfd_ctx *)
					(unsigned long)
					uwq->msg.arg.reserved.reserved1;
1089
				list_move(&uwq->wq.entry, &fork_event);
1090 1091 1092 1093 1094 1095
				/*
				 * fork_nctx can be freed as soon as
				 * we drop the lock, unless we take a
				 * reference on it.
				 */
				userfaultfd_ctx_get(fork_nctx);
1096 1097 1098 1099 1100
				spin_unlock(&ctx->event_wqh.lock);
				ret = 0;
				break;
			}

1101 1102 1103 1104 1105 1106 1107
			userfaultfd_event_complete(ctx, uwq);
			spin_unlock(&ctx->event_wqh.lock);
			ret = 0;
			break;
		}
		spin_unlock(&ctx->event_wqh.lock);

1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123
		if (signal_pending(current)) {
			ret = -ERESTARTSYS;
			break;
		}
		if (no_wait) {
			ret = -EAGAIN;
			break;
		}
		spin_unlock(&ctx->fd_wqh.lock);
		schedule();
		spin_lock(&ctx->fd_wqh.lock);
	}
	__remove_wait_queue(&ctx->fd_wqh, &wait);
	__set_current_state(TASK_RUNNING);
	spin_unlock(&ctx->fd_wqh.lock);

1124 1125
	if (!ret && msg->event == UFFD_EVENT_FORK) {
		ret = resolve_userfault_fork(ctx, fork_nctx, msg);
1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148
		spin_lock(&ctx->event_wqh.lock);
		if (!list_empty(&fork_event)) {
			/*
			 * The fork thread didn't abort, so we can
			 * drop the temporary refcount.
			 */
			userfaultfd_ctx_put(fork_nctx);

			uwq = list_first_entry(&fork_event,
					       typeof(*uwq),
					       wq.entry);
			/*
			 * If fork_event list wasn't empty and in turn
			 * the event wasn't already released by fork
			 * (the event is allocated on fork kernel
			 * stack), put the event back to its place in
			 * the event_wq. fork_event head will be freed
			 * as soon as we return so the event cannot
			 * stay queued there no matter the current
			 * "ret" value.
			 */
			list_del(&uwq->wq.entry);
			__add_wait_queue(&ctx->event_wqh, &uwq->wq);
1149

1150 1151 1152 1153 1154 1155
			/*
			 * Leave the event in the waitqueue and report
			 * error to userland if we failed to resolve
			 * the userfault fork.
			 */
			if (likely(!ret))
1156
				userfaultfd_event_complete(ctx, uwq);
1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170
		} else {
			/*
			 * Here the fork thread aborted and the
			 * refcount from the fork thread on fork_nctx
			 * has already been released. We still hold
			 * the reference we took before releasing the
			 * lock above. If resolve_userfault_fork
			 * failed we've to drop it because the
			 * fork_nctx has to be freed in such case. If
			 * it succeeded we'll hold it because the new
			 * uffd references it.
			 */
			if (ret)
				userfaultfd_ctx_put(fork_nctx);
1171
		}
1172
		spin_unlock(&ctx->event_wqh.lock);
1173 1174
	}

1175 1176 1177 1178 1179 1180 1181 1182
	return ret;
}

static ssize_t userfaultfd_read(struct file *file, char __user *buf,
				size_t count, loff_t *ppos)
{
	struct userfaultfd_ctx *ctx = file->private_data;
	ssize_t _ret, ret = 0;
1183
	struct uffd_msg msg;
1184 1185 1186 1187 1188 1189
	int no_wait = file->f_flags & O_NONBLOCK;

	if (ctx->state == UFFD_STATE_WAIT_API)
		return -EINVAL;

	for (;;) {
1190
		if (count < sizeof(msg))
1191
			return ret ? ret : -EINVAL;
1192
		_ret = userfaultfd_ctx_read(ctx, no_wait, &msg);
1193 1194
		if (_ret < 0)
			return ret ? ret : _ret;
1195
		if (copy_to_user((__u64 __user *) buf, &msg, sizeof(msg)))
1196
			return ret ? ret : -EFAULT;
1197 1198 1199
		ret += sizeof(msg);
		buf += sizeof(msg);
		count -= sizeof(msg);
1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210
		/*
		 * Allow to read more than one fault at time but only
		 * block if waiting for the very first one.
		 */
		no_wait = O_NONBLOCK;
	}
}

static void __wake_userfault(struct userfaultfd_ctx *ctx,
			     struct userfaultfd_wake_range *range)
{
1211
	spin_lock(&ctx->fault_pending_wqh.lock);
1212
	/* wake all in the range and autoremove */
1213
	if (waitqueue_active(&ctx->fault_pending_wqh))
1214
		__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL,
1215 1216
				     range);
	if (waitqueue_active(&ctx->fault_wqh))
1217
		__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, range);
1218
	spin_unlock(&ctx->fault_pending_wqh.lock);
1219 1220 1221 1222 1223
}

static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
					   struct userfaultfd_wake_range *range)
{
1224 1225 1226
	unsigned seq;
	bool need_wakeup;

1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241
	/*
	 * To be sure waitqueue_active() is not reordered by the CPU
	 * before the pagetable update, use an explicit SMP memory
	 * barrier here. PT lock release or up_read(mmap_sem) still
	 * have release semantics that can allow the
	 * waitqueue_active() to be reordered before the pte update.
	 */
	smp_mb();

	/*
	 * Use waitqueue_active because it's very frequent to
	 * change the address space atomically even if there are no
	 * userfaults yet. So we take the spinlock only when we're
	 * sure we've userfaults to wake.
	 */
1242 1243 1244 1245 1246 1247 1248
	do {
		seq = read_seqcount_begin(&ctx->refile_seq);
		need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) ||
			waitqueue_active(&ctx->fault_wqh);
		cond_resched();
	} while (read_seqcount_retry(&ctx->refile_seq, seq));
	if (need_wakeup)
1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271
		__wake_userfault(ctx, range);
}

static __always_inline int validate_range(struct mm_struct *mm,
					  __u64 start, __u64 len)
{
	__u64 task_size = mm->task_size;

	if (start & ~PAGE_MASK)
		return -EINVAL;
	if (len & ~PAGE_MASK)
		return -EINVAL;
	if (!len)
		return -EINVAL;
	if (start < mmap_min_addr)
		return -EINVAL;
	if (start >= task_size)
		return -EINVAL;
	if (len > task_size - start)
		return -EINVAL;
	return 0;
}

1272 1273
static inline bool vma_can_userfault(struct vm_area_struct *vma)
{
1274 1275
	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
		vma_is_shmem(vma);
1276 1277
}

1278 1279 1280 1281 1282 1283 1284 1285 1286 1287
static int userfaultfd_register(struct userfaultfd_ctx *ctx,
				unsigned long arg)
{
	struct mm_struct *mm = ctx->mm;
	struct vm_area_struct *vma, *prev, *cur;
	int ret;
	struct uffdio_register uffdio_register;
	struct uffdio_register __user *user_uffdio_register;
	unsigned long vm_flags, new_flags;
	bool found;
1288
	bool basic_ioctls;
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
	unsigned long start, end, vma_end;

	user_uffdio_register = (struct uffdio_register __user *) arg;

	ret = -EFAULT;
	if (copy_from_user(&uffdio_register, user_uffdio_register,
			   sizeof(uffdio_register)-sizeof(__u64)))
		goto out;

	ret = -EINVAL;
	if (!uffdio_register.mode)
		goto out;
	if (uffdio_register.mode & ~(UFFDIO_REGISTER_MODE_MISSING|
				     UFFDIO_REGISTER_MODE_WP))
		goto out;
	vm_flags = 0;
	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
		vm_flags |= VM_UFFD_MISSING;
	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) {
		vm_flags |= VM_UFFD_WP;
		/*
		 * FIXME: remove the below error constraint by
		 * implementing the wprotect tracking mode.
		 */
		ret = -EINVAL;
		goto out;
	}

	ret = validate_range(mm, uffdio_register.range.start,
			     uffdio_register.range.len);
	if (ret)
		goto out;

	start = uffdio_register.range.start;
	end = start + uffdio_register.range.len;

1325 1326 1327 1328
	ret = -ENOMEM;
	if (!mmget_not_zero(mm))
		goto out;

1329 1330 1331 1332 1333 1334 1335 1336 1337 1338
	down_write(&mm->mmap_sem);
	vma = find_vma_prev(mm, start, &prev);
	if (!vma)
		goto out_unlock;

	/* check that there's at least one vma in the range */
	ret = -EINVAL;
	if (vma->vm_start >= end)
		goto out_unlock;

1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349
	/*
	 * If the first vma contains huge pages, make sure start address
	 * is aligned to huge page size.
	 */
	if (is_vm_hugetlb_page(vma)) {
		unsigned long vma_hpagesize = vma_kernel_pagesize(vma);

		if (start & (vma_hpagesize - 1))
			goto out_unlock;
	}

1350 1351 1352 1353
	/*
	 * Search for not compatible vmas.
	 */
	found = false;
1354
	basic_ioctls = false;
1355 1356 1357 1358 1359 1360 1361 1362
	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
		cond_resched();

		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
		       !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));

		/* check not compatible vmas */
		ret = -EINVAL;
1363
		if (!vma_can_userfault(cur))
1364
			goto out_unlock;
1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377

		/*
		 * UFFDIO_COPY will fill file holes even without
		 * PROT_WRITE. This check enforces that if this is a
		 * MAP_SHARED, the process has write permission to the backing
		 * file. If VM_MAYWRITE is set it also enforces that on a
		 * MAP_SHARED vma: there is no F_WRITE_SEAL and no further
		 * F_WRITE_SEAL can be taken until the vma is destroyed.
		 */
		ret = -EPERM;
		if (unlikely(!(cur->vm_flags & VM_MAYWRITE)))
			goto out_unlock;

1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390
		/*
		 * If this vma contains ending address, and huge pages
		 * check alignment.
		 */
		if (is_vm_hugetlb_page(cur) && end <= cur->vm_end &&
		    end > cur->vm_start) {
			unsigned long vma_hpagesize = vma_kernel_pagesize(cur);

			ret = -EINVAL;

			if (end & (vma_hpagesize - 1))
				goto out_unlock;
		}
1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402

		/*
		 * Check that this vma isn't already owned by a
		 * different userfaultfd. We can't allow more than one
		 * userfaultfd to own a single vma simultaneously or we
		 * wouldn't know which one to deliver the userfaults to.
		 */
		ret = -EBUSY;
		if (cur->vm_userfaultfd_ctx.ctx &&
		    cur->vm_userfaultfd_ctx.ctx != ctx)
			goto out_unlock;

1403 1404 1405
		/*
		 * Note vmas containing huge pages
		 */
1406 1407
		if (is_vm_hugetlb_page(cur))
			basic_ioctls = true;
1408

1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419
		found = true;
	}
	BUG_ON(!found);

	if (vma->vm_start < start)
		prev = vma;

	ret = 0;
	do {
		cond_resched();

1420
		BUG_ON(!vma_can_userfault(vma));
1421 1422
		BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
		       vma->vm_userfaultfd_ctx.ctx != ctx);
1423
		WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
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

		/*
		 * Nothing to do: this vma is already registered into this
		 * userfaultfd and with the right tracking mode too.
		 */
		if (vma->vm_userfaultfd_ctx.ctx == ctx &&
		    (vma->vm_flags & vm_flags) == vm_flags)
			goto skip;

		if (vma->vm_start > start)
			start = vma->vm_start;
		vma_end = min(end, vma->vm_end);

		new_flags = (vma->vm_flags & ~vm_flags) | vm_flags;
		prev = vma_merge(mm, prev, start, vma_end, new_flags,
				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
				 vma_policy(vma),
				 ((struct vm_userfaultfd_ctx){ ctx }));
		if (prev) {
			vma = prev;
			goto next;
		}
		if (vma->vm_start < start) {
			ret = split_vma(mm, vma, start, 1);
			if (ret)
				break;
		}
		if (vma->vm_end > end) {
			ret = split_vma(mm, vma, end, 0);
			if (ret)
				break;
		}
	next:
		/*
		 * In the vma_merge() successful mprotect-like case 8:
		 * the next vma was merged into the current one and
		 * the current one has not been updated yet.
		 */
		vma->vm_flags = new_flags;
		vma->vm_userfaultfd_ctx.ctx = ctx;

	skip:
		prev = vma;
		start = vma->vm_end;
		vma = vma->vm_next;
	} while (vma && vma->vm_start < end);
out_unlock:
	up_write(&mm->mmap_sem);
1472
	mmput(mm);
1473 1474 1475 1476 1477 1478
	if (!ret) {
		/*
		 * Now that we scanned all vmas we can already tell
		 * userland which ioctls methods are guaranteed to
		 * succeed on this range.
		 */
1479
		if (put_user(basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC :
1480
			     UFFD_API_RANGE_IOCTLS,
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
			     &user_uffdio_register->ioctls))
			ret = -EFAULT;
	}
out:
	return ret;
}

static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
				  unsigned long arg)
{
	struct mm_struct *mm = ctx->mm;
	struct vm_area_struct *vma, *prev, *cur;
	int ret;
	struct uffdio_range uffdio_unregister;
	unsigned long new_flags;
	bool found;
	unsigned long start, end, vma_end;
	const void __user *buf = (void __user *)arg;

	ret = -EFAULT;
	if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
		goto out;

	ret = validate_range(mm, uffdio_unregister.start,
			     uffdio_unregister.len);
	if (ret)
		goto out;

	start = uffdio_unregister.start;
	end = start + uffdio_unregister.len;

1512 1513 1514 1515
	ret = -ENOMEM;
	if (!mmget_not_zero(mm))
		goto out;

1516 1517 1518 1519 1520 1521 1522 1523 1524 1525
	down_write(&mm->mmap_sem);
	vma = find_vma_prev(mm, start, &prev);
	if (!vma)
		goto out_unlock;

	/* check that there's at least one vma in the range */
	ret = -EINVAL;
	if (vma->vm_start >= end)
		goto out_unlock;

1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536
	/*
	 * If the first vma contains huge pages, make sure start address
	 * is aligned to huge page size.
	 */
	if (is_vm_hugetlb_page(vma)) {
		unsigned long vma_hpagesize = vma_kernel_pagesize(vma);

		if (start & (vma_hpagesize - 1))
			goto out_unlock;
	}

1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554
	/*
	 * Search for not compatible vmas.
	 */
	found = false;
	ret = -EINVAL;
	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
		cond_resched();

		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
		       !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));

		/*
		 * Check not compatible vmas, not strictly required
		 * here as not compatible vmas cannot have an
		 * userfaultfd_ctx registered on them, but this
		 * provides for more strict behavior to notice
		 * unregistration errors.
		 */
1555
		if (!vma_can_userfault(cur))
1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568
			goto out_unlock;

		found = true;
	}
	BUG_ON(!found);

	if (vma->vm_start < start)
		prev = vma;

	ret = 0;
	do {
		cond_resched();

1569
		BUG_ON(!vma_can_userfault(vma));
1570 1571 1572 1573 1574 1575 1576 1577

		/*
		 * Nothing to do: this vma is already registered into this
		 * userfaultfd and with the right tracking mode too.
		 */
		if (!vma->vm_userfaultfd_ctx.ctx)
			goto skip;

1578 1579
		WARN_ON(!(vma->vm_flags & VM_MAYWRITE));

1580 1581 1582 1583
		if (vma->vm_start > start)
			start = vma->vm_start;
		vma_end = min(end, vma->vm_end);

1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596
		if (userfaultfd_missing(vma)) {
			/*
			 * Wake any concurrent pending userfault while
			 * we unregister, so they will not hang
			 * permanently and it avoids userland to call
			 * UFFDIO_WAKE explicitly.
			 */
			struct userfaultfd_wake_range range;
			range.start = start;
			range.len = vma_end - start;
			wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
		}

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
		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
		prev = vma_merge(mm, prev, start, vma_end, new_flags,
				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
				 vma_policy(vma),
				 NULL_VM_UFFD_CTX);
		if (prev) {
			vma = prev;
			goto next;
		}
		if (vma->vm_start < start) {
			ret = split_vma(mm, vma, start, 1);
			if (ret)
				break;
		}
		if (vma->vm_end > end) {
			ret = split_vma(mm, vma, end, 0);
			if (ret)
				break;
		}
	next:
		/*
		 * In the vma_merge() successful mprotect-like case 8:
		 * the next vma was merged into the current one and
		 * the current one has not been updated yet.
		 */
		vma->vm_flags = new_flags;
		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;

	skip:
		prev = vma;
		start = vma->vm_end;
		vma = vma->vm_next;
	} while (vma && vma->vm_start < end);
out_unlock:
	up_write(&mm->mmap_sem);
1632
	mmput(mm);
1633 1634 1635 1636 1637
out:
	return ret;
}

/*
1638 1639
 * userfaultfd_wake may be used in combination with the
 * UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches.
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
 */
static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
			    unsigned long arg)
{
	int ret;
	struct uffdio_range uffdio_wake;
	struct userfaultfd_wake_range range;
	const void __user *buf = (void __user *)arg;

	ret = -EFAULT;
	if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
		goto out;

	ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
	if (ret)
		goto out;

	range.start = uffdio_wake.start;
	range.len = uffdio_wake.len;

	/*
	 * len == 0 means wake all and we don't want to wake all here,
	 * so check it again to be sure.
	 */
	VM_BUG_ON(!range.len);

	wake_userfault(ctx, &range);
	ret = 0;

out:
	return ret;
}

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
static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
			    unsigned long arg)
{
	__s64 ret;
	struct uffdio_copy uffdio_copy;
	struct uffdio_copy __user *user_uffdio_copy;
	struct userfaultfd_wake_range range;

	user_uffdio_copy = (struct uffdio_copy __user *) arg;

	ret = -EFAULT;
	if (copy_from_user(&uffdio_copy, user_uffdio_copy,
			   /* don't copy "copy" last field */
			   sizeof(uffdio_copy)-sizeof(__s64)))
		goto out;

	ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
	if (ret)
		goto out;
	/*
	 * double check for wraparound just in case. copy_from_user()
	 * will later check uffdio_copy.src + uffdio_copy.len to fit
	 * in the userland range.
	 */
	ret = -EINVAL;
	if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src)
		goto out;
	if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE)
		goto out;
1702 1703 1704 1705
	if (mmget_not_zero(ctx->mm)) {
		ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
				   uffdio_copy.len);
		mmput(ctx->mm);
1706
	} else {
1707
		return -ESRCH;
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
	if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
		return -EFAULT;
	if (ret < 0)
		goto out;
	BUG_ON(!ret);
	/* len == 0 would wake all */
	range.len = ret;
	if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) {
		range.start = uffdio_copy.dst;
		wake_userfault(ctx, &range);
	}
	ret = range.len == uffdio_copy.len ? 0 : -EAGAIN;
out:
	return ret;
}

static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
				unsigned long arg)
{
	__s64 ret;
	struct uffdio_zeropage uffdio_zeropage;
	struct uffdio_zeropage __user *user_uffdio_zeropage;
	struct userfaultfd_wake_range range;

	user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;

	ret = -EFAULT;
	if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
			   /* don't copy "zeropage" last field */
			   sizeof(uffdio_zeropage)-sizeof(__s64)))
		goto out;

	ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
			     uffdio_zeropage.range.len);
	if (ret)
		goto out;
	ret = -EINVAL;
	if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE)
		goto out;

1749 1750 1751 1752
	if (mmget_not_zero(ctx->mm)) {
		ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
				     uffdio_zeropage.range.len);
		mmput(ctx->mm);
1753
	} else {
1754
		return -ESRCH;
1755
	}
1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771
	if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
		return -EFAULT;
	if (ret < 0)
		goto out;
	/* len == 0 would wake all */
	BUG_ON(!ret);
	range.len = ret;
	if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) {
		range.start = uffdio_zeropage.range.start;
		wake_userfault(ctx, &range);
	}
	ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN;
out:
	return ret;
}

1772 1773 1774 1775 1776 1777 1778 1779
static inline unsigned int uffd_ctx_features(__u64 user_features)
{
	/*
	 * For the current set of features the bits just coincide
	 */
	return (unsigned int)user_features;
}

1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790
/*
 * userland asks for a certain API version and we return which bits
 * and ioctl commands are implemented in this kernel for such API
 * version or -EINVAL if unknown.
 */
static int userfaultfd_api(struct userfaultfd_ctx *ctx,
			   unsigned long arg)
{
	struct uffdio_api uffdio_api;
	void __user *buf = (void __user *)arg;
	int ret;
1791
	__u64 features;
1792 1793 1794 1795 1796

	ret = -EINVAL;
	if (ctx->state != UFFD_STATE_WAIT_API)
		goto out;
	ret = -EFAULT;
1797
	if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
1798
		goto out;
1799 1800
	features = uffdio_api.features;
	if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) {
1801 1802 1803 1804 1805 1806
		memset(&uffdio_api, 0, sizeof(uffdio_api));
		if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
			goto out;
		ret = -EINVAL;
		goto out;
	}
1807 1808
	/* report all available features and ioctls to userland */
	uffdio_api.features = UFFD_API_FEATURES;
1809 1810 1811 1812 1813
	uffdio_api.ioctls = UFFD_API_IOCTLS;
	ret = -EFAULT;
	if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
		goto out;
	ctx->state = UFFD_STATE_RUNNING;
1814 1815
	/* only enable the requested features for this uffd context */
	ctx->features = uffd_ctx_features(features);
1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826
	ret = 0;
out:
	return ret;
}

static long userfaultfd_ioctl(struct file *file, unsigned cmd,
			      unsigned long arg)
{
	int ret = -EINVAL;
	struct userfaultfd_ctx *ctx = file->private_data;

1827 1828 1829
	if (cmd != UFFDIO_API && ctx->state == UFFD_STATE_WAIT_API)
		return -EINVAL;

1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842
	switch(cmd) {
	case UFFDIO_API:
		ret = userfaultfd_api(ctx, arg);
		<