1 files changed, 743 insertions, 563 deletions

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 52de29000c7e..c5ba1f4487bd 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -15,6 +15,8 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/mm.h>
+#include <linux/mm_inline.h>
+#include <linux/mmu_notifier.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
@@ -27,56 +29,27 @@
 #include <linux/ioctl.h>
 #include <linux/security.h>
 #include <linux/hugetlb.h>
-
-int sysctl_unprivileged_userfaultfd __read_mostly = 1;
-
-static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;
-
-enum userfaultfd_state {
-	UFFD_STATE_WAIT_API,
-	UFFD_STATE_RUNNING,
+#include <linux/leafops.h>
+#include <linux/miscdevice.h>
+#include <linux/uio.h>
+
+static int sysctl_unprivileged_userfaultfd __read_mostly;
+
+#ifdef CONFIG_SYSCTL
+static const struct ctl_table vm_userfaultfd_table[] = {
+	{
+		.procname	= "unprivileged_userfaultfd",
+		.data		= &sysctl_unprivileged_userfaultfd,
+		.maxlen		= sizeof(sysctl_unprivileged_userfaultfd),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
 };
+#endif
 
-/*
- * Start with fault_pending_wqh and fault_wqh so they're more likely
- * to be in the same cacheline.
- *
- * Locking order:
- *	fd_wqh.lock
- *		fault_pending_wqh.lock
- *			fault_wqh.lock
- *		event_wqh.lock
- *
- * To avoid deadlocks, IRQs must be disabled when taking any of the above locks,
- * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's
- * also taken in IRQ context.
- */
-struct userfaultfd_ctx {
-	/* waitqueue head for the pending (i.e. not read) userfaults */
-	wait_queue_head_t fault_pending_wqh;
-	/* waitqueue head for the userfaults */
-	wait_queue_head_t fault_wqh;
-	/* waitqueue head for the pseudo fd to wakeup poll/read */
-	wait_queue_head_t fd_wqh;
-	/* waitqueue head for events */
-	wait_queue_head_t event_wqh;
-	/* a refile sequence protected by fault_pending_wqh lock */
-	struct seqcount refile_seq;
-	/* pseudo fd refcounting */
-	refcount_t refcount;
-	/* userfaultfd syscall flags */
-	unsigned int flags;
-	/* features requested from the userspace */
-	unsigned int features;
-	/* state machine */
-	enum userfaultfd_state state;
-	/* released */
-	bool released;
-	/* memory mappings are changing because of non-cooperative event */
-	bool mmap_changing;
-	/* mm with one ore more vmas attached to this userfaultfd_ctx */
-	struct mm_struct *mm;
-};
+static struct kmem_cache *userfaultfd_ctx_cachep __ro_after_init;
 
 struct userfaultfd_fork_ctx {
 	struct userfaultfd_ctx *orig;
@@ -103,6 +76,34 @@ struct userfaultfd_wake_range {
 	unsigned long len;
 };
 
+/* internal indication that UFFD_API ioctl was successfully executed */
+#define UFFD_FEATURE_INITIALIZED		(1u << 31)
+
+static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx)
+{
+	return ctx->features & UFFD_FEATURE_INITIALIZED;
+}
+
+static bool userfaultfd_wp_async_ctx(struct userfaultfd_ctx *ctx)
+{
+	return ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC);
+}
+
+/*
+ * Whether WP_UNPOPULATED is enabled on the uffd context.  It is only
+ * meaningful when userfaultfd_wp()==true on the vma and when it's
+ * anonymous.
+ */
+bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma)
+{
+	struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
+
+	if (!ctx)
+		return false;
+
+	return ctx->features & UFFD_FEATURE_WP_UNPOPULATED;
+}
+
 static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
 				     int wake_flags, void *key)
 {
@@ -164,14 +165,14 @@ static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
 static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx)
 {
 	if (refcount_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));
-		VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock));
-		VM_BUG_ON(waitqueue_active(&ctx->event_wqh));
-		VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock));
-		VM_BUG_ON(waitqueue_active(&ctx->fd_wqh));
+		VM_WARN_ON_ONCE(spin_is_locked(&ctx->fault_pending_wqh.lock));
+		VM_WARN_ON_ONCE(waitqueue_active(&ctx->fault_pending_wqh));
+		VM_WARN_ON_ONCE(spin_is_locked(&ctx->fault_wqh.lock));
+		VM_WARN_ON_ONCE(waitqueue_active(&ctx->fault_wqh));
+		VM_WARN_ON_ONCE(spin_is_locked(&ctx->event_wqh.lock));
+		VM_WARN_ON_ONCE(waitqueue_active(&ctx->event_wqh));
+		VM_WARN_ON_ONCE(spin_is_locked(&ctx->fd_wqh.lock));
+		VM_WARN_ON_ONCE(waitqueue_active(&ctx->fd_wqh));
 		mmdrop(ctx->mm);
 		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
 	}
@@ -188,32 +189,34 @@ static inline void msg_init(struct uffd_msg *msg)
 }
 
 static inline struct uffd_msg userfault_msg(unsigned long address,
+					    unsigned long real_address,
 					    unsigned int flags,
 					    unsigned long reason,
 					    unsigned int features)
 {
 	struct uffd_msg msg;
+
 	msg_init(&msg);
 	msg.event = UFFD_EVENT_PAGEFAULT;
-	msg.arg.pagefault.address = address;
+
+	msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ?
+				    real_address : address;
+
+	/*
+	 * These flags indicate why the userfault occurred:
+	 * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
+	 * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault.
+	 * - Neither of these flags being set indicates a MISSING fault.
+	 *
+	 * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write
+	 * fault. Otherwise, it was a read fault.
+	 */
 	if (flags & FAULT_FLAG_WRITE)
-		/*
-		 * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
-		 * 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.
-		 */
 		msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE;
 	if (reason & VM_UFFD_WP)
-		/*
-		 * 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.
-		 */
 		msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP;
+	if (reason & VM_UFFD_MINOR)
+		msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR;
 	if (features & UFFD_FEATURE_THREAD_ID)
 		msg.arg.pagefault.feat.ptid = task_pid_vnr(current);
 	return msg;
@@ -225,122 +228,131 @@ static inline struct uffd_msg userfault_msg(unsigned long address,
  * hugepmd ranges.
  */
 static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
-					 struct vm_area_struct *vma,
-					 unsigned long address,
-					 unsigned long flags,
-					 unsigned long reason)
+					      struct vm_fault *vmf,
+					      unsigned long reason)
 {
-	struct mm_struct *mm = ctx->mm;
+	struct vm_area_struct *vma = vmf->vma;
 	pte_t *ptep, pte;
-	bool ret = true;
-
-	mmap_assert_locked(mm);
 
-	ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
+	assert_fault_locked(vmf);
 
+	ptep = hugetlb_walk(vma, vmf->address, vma_mmu_pagesize(vma));
 	if (!ptep)
-		goto out;
+		return true;
 
-	ret = false;
-	pte = huge_ptep_get(ptep);
+	pte = huge_ptep_get(vma->vm_mm, vmf->address, ptep);
 
 	/*
 	 * Lockless access: we're in a wait_event so it's ok if it
 	 * changes under us.
 	 */
+
+	/* Entry is still missing, wait for userspace to resolve the fault. */
 	if (huge_pte_none(pte))
-		ret = true;
+		return true;
+	/* UFFD PTE markers require userspace to resolve the fault. */
+	if (pte_is_uffd_marker(pte))
+		return true;
+	/*
+	 * If VMA has UFFD WP faults enabled and WP fault, wait for userspace to
+	 * resolve the fault.
+	 */
 	if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
-		ret = true;
-out:
-	return ret;
+		return true;
+
+	return false;
 }
 #else
 static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
-					 struct vm_area_struct *vma,
-					 unsigned long address,
-					 unsigned long flags,
-					 unsigned long reason)
+					      struct vm_fault *vmf,
+					      unsigned long reason)
 {
-	return false;	/* should never get here */
+	/* Should never get here. */
+	VM_WARN_ON_ONCE(1);
+	return false;
 }
 #endif /* CONFIG_HUGETLB_PAGE */
 
 /*
- * Verify the pagetables are still not ok after having reigstered into
+ * Verify the pagetables are still not ok after having registered into
  * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any
- * userfault that has already been resolved, if userfaultfd_read and
+ * userfault that has already been resolved, if userfaultfd_read_iter 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,
+					 struct vm_fault *vmf,
 					 unsigned long reason)
 {
 	struct mm_struct *mm = ctx->mm;
+	unsigned long address = vmf->address;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd, _pmd;
 	pte_t *pte;
-	bool ret = true;
+	pte_t ptent;
+	bool ret;
 
-	mmap_assert_locked(mm);
+	assert_fault_locked(vmf);
 
 	pgd = pgd_offset(mm, address);
 	if (!pgd_present(*pgd))
-		goto out;
+		return true;
 	p4d = p4d_offset(pgd, address);
 	if (!p4d_present(*p4d))
-		goto out;
+		return true;
 	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
-		goto out;
+		return true;
 	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);
+again:
+	_pmd = pmdp_get_lockless(pmd);
 	if (pmd_none(_pmd))
-		goto out;
+		return true;
 
-	ret = false;
+	/*
+	 * A race could arise which would result in a softleaf entry such as
+	 * migration entry unexpectedly being present in the PMD, so explicitly
+	 * check for this and bail out if so.
+	 */
 	if (!pmd_present(_pmd))
-		goto out;
+		return false;
 
-	if (pmd_trans_huge(_pmd)) {
-		if (!pmd_write(_pmd) && (reason & VM_UFFD_WP))
-			ret = true;
-		goto out;
-	}
+	if (pmd_trans_huge(_pmd))
+		return !pmd_write(_pmd) && (reason & VM_UFFD_WP);
 
-	/*
-	 * 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);
+	if (!pte)
+		goto again;
+
 	/*
 	 * Lockless access: we're in a wait_event so it's ok if it
 	 * changes under us.
 	 */
-	if (pte_none(*pte))
-		ret = true;
-	if (!pte_write(*pte) && (reason & VM_UFFD_WP))
-		ret = true;
-	pte_unmap(pte);
+	ptent = ptep_get(pte);
 
+	ret = true;
+	/* Entry is still missing, wait for userspace to resolve the fault. */
+	if (pte_none(ptent))
+		goto out;
+	/* UFFD PTE markers require userspace to resolve the fault. */
+	if (pte_is_uffd_marker(ptent))
+		goto out;
+	/*
+	 * If VMA has UFFD WP faults enabled and WP fault, wait for userspace to
+	 * resolve the fault.
+	 */
+	if (!pte_write(ptent) && (reason & VM_UFFD_WP))
+		goto out;
+
+	ret = false;
 out:
+	pte_unmap(pte);
 	return ret;
 }
 
-/* Should pair with userfaultfd_signal_pending() */
-static inline long userfaultfd_get_blocking_state(unsigned int flags)
+static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags)
 {
 	if (flags & FAULT_FLAG_INTERRUPTIBLE)
 		return TASK_INTERRUPTIBLE;
@@ -351,18 +363,6 @@ static inline long userfaultfd_get_blocking_state(unsigned int flags)
 	return TASK_UNINTERRUPTIBLE;
 }
 
-/* Should pair with userfaultfd_get_blocking_state() */
-static inline bool userfaultfd_signal_pending(unsigned int flags)
-{
-	if (flags & FAULT_FLAG_INTERRUPTIBLE)
-		return signal_pending(current);
-
-	if (flags & FAULT_FLAG_KILLABLE)
-		return fatal_signal_pending(current);
-
-	return false;
-}
-
 /*
  * The locking rules involved in returning VM_FAULT_RETRY depending on
  * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and
@@ -380,70 +380,38 @@ static inline bool userfaultfd_signal_pending(unsigned int flags)
  */
 vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 {
-	struct mm_struct *mm = vmf->vma->vm_mm;
+	struct vm_area_struct *vma = vmf->vma;
+	struct mm_struct *mm = vma->vm_mm;
 	struct userfaultfd_ctx *ctx;
 	struct userfaultfd_wait_queue uwq;
 	vm_fault_t ret = VM_FAULT_SIGBUS;
 	bool must_wait;
-	long blocking_state;
+	unsigned int blocking_state;
 
 	/*
-	 * 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_lock and it ends up here.
+	 * We don't do userfault handling for the final child pid update
+	 * and when coredumping (faults triggered by get_dump_page()).
 	 */
 	if (current->flags & (PF_EXITING|PF_DUMPCORE))
 		goto out;
 
-	/*
-	 * Coredumping runs without mmap_lock so we can only check that
-	 * the mmap_lock is held, if PF_DUMPCORE was not set.
-	 */
-	mmap_assert_locked(mm);
+	assert_fault_locked(vmf);
 
-	ctx = vmf->vma->vm_userfaultfd_ctx.ctx;
+	ctx = vma->vm_userfaultfd_ctx.ctx;
 	if (!ctx)
 		goto out;
 
-	BUG_ON(ctx->mm != mm);
+	VM_WARN_ON_ONCE(ctx->mm != mm);
 
-	VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP));
-	VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP));
+	/* Any unrecognized flag is a bug. */
+	VM_WARN_ON_ONCE(reason & ~__VM_UFFD_FLAGS);
+	/* 0 or > 1 flags set is a bug; we expect exactly 1. */
+	VM_WARN_ON_ONCE(!reason || (reason & (reason - 1)));
 
 	if (ctx->features & UFFD_FEATURE_SIGBUS)
 		goto out;
-
-	/*
-	 * 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_lock.
-	 */
-	if (unlikely(READ_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;
+	if (!(vmf->flags & FAULT_FLAG_USER) && (ctx->flags & UFFD_USER_MODE_ONLY))
 		goto out;
-	}
 
 	/*
 	 * Check that we can return VM_FAULT_RETRY.
@@ -461,12 +429,11 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 		 * to be sure not to return SIGBUS erroneously on
 		 * nowait invocations.
 		 */
-		BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT);
+		VM_WARN_ON_ONCE(vmf->flags & FAULT_FLAG_RETRY_NOWAIT);
 #ifdef CONFIG_DEBUG_VM
 		if (printk_ratelimit()) {
-			printk(KERN_WARNING
-			       "FAULT_FLAG_ALLOW_RETRY missing %x\n",
-			       vmf->flags);
+			pr_warn("FAULT_FLAG_ALLOW_RETRY missing %x\n",
+				vmf->flags);
 			dump_stack();
 		}
 #endif
@@ -481,18 +448,52 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
 		goto out;
 
+	if (unlikely(READ_ONCE(ctx->released))) {
+		/*
+		 * If a concurrent release is detected, do not return
+		 * VM_FAULT_SIGBUS or VM_FAULT_NOPAGE, but instead always
+		 * return VM_FAULT_RETRY with lock released proactively.
+		 *
+		 * 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, to avoid involuntary SIGBUS triggered.
+		 *
+		 * If we were to return VM_FAULT_NOPAGE, it would work for
+		 * the fault path, in which the lock will be released
+		 * later.  However for GUP, faultin_page() does nothing
+		 * special on NOPAGE, so GUP would spin retrying without
+		 * releasing the mmap read lock, causing possible livelock.
+		 *
+		 * Here only VM_FAULT_RETRY would make sure the mmap lock
+		 * be released immediately, so that the thread concurrently
+		 * releasing the userfault would always make progress.
+		 */
+		release_fault_lock(vmf);
+		goto out;
+	}
+
 	/* take the reference before dropping the mmap_lock */
 	userfaultfd_ctx_get(ctx);
 
 	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
 	uwq.wq.private = current;
-	uwq.msg = userfault_msg(vmf->address, vmf->flags, reason,
-			ctx->features);
+	uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags,
+				reason, ctx->features);
 	uwq.ctx = ctx;
 	uwq.waken = false;
 
 	blocking_state = userfaultfd_get_blocking_state(vmf->flags);
 
+        /*
+         * Take the vma lock now, in order to safely call
+         * userfaultfd_huge_must_wait() later. Since acquiring the
+         * (sleepable) vma lock can modify the current task state, that
+         * must be before explicitly calling set_current_state().
+         */
+	if (is_vm_hugetlb_page(vma))
+		hugetlb_vma_lock_read(vma);
+
 	spin_lock_irq(&ctx->fault_pending_wqh.lock);
 	/*
 	 * After the __add_wait_queue the uwq is visible to userland
@@ -507,42 +508,18 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	set_current_state(blocking_state);
 	spin_unlock_irq(&ctx->fault_pending_wqh.lock);
 
-	if (!is_vm_hugetlb_page(vmf->vma))
-		must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
-						  reason);
-	else
-		must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma,
-						       vmf->address,
-						       vmf->flags, reason);
-	mmap_read_unlock(mm);
+	if (is_vm_hugetlb_page(vma)) {
+		must_wait = userfaultfd_huge_must_wait(ctx, vmf, reason);
+		hugetlb_vma_unlock_read(vma);
+	} else {
+		must_wait = userfaultfd_must_wait(ctx, vmf, reason);
+	}
 
-	if (likely(must_wait && !READ_ONCE(ctx->released) &&
-		   !userfaultfd_signal_pending(vmf->flags))) {
+	release_fault_lock(vmf);
+
+	if (likely(must_wait && !READ_ONCE(ctx->released))) {
 		wake_up_poll(&ctx->fd_wqh, EPOLLIN);
 		schedule();
-		ret |= VM_FAULT_MAJOR;
-
-		/*
-		 * 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) ||
-			    userfaultfd_signal_pending(vmf->flags))
-				break;
-			schedule();
-		}
 	}
 
 	__set_current_state(TASK_RUNNING);
@@ -633,20 +610,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 	spin_unlock_irq(&ctx->event_wqh.lock);
 
 	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 */
-		mmap_write_lock(mm);
-		/* no task can run (and in turn coredump) yet */
-		VM_WARN_ON(!mmget_still_valid(mm));
-		for (vma = mm->mmap; vma; vma = vma->vm_next)
-			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
-				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-				vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
-			}
-		mmap_write_unlock(mm);
-
+		userfaultfd_release_new(release_new_ctx);
 		userfaultfd_ctx_put(release_new_ctx);
 	}
 
@@ -655,7 +619,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 	 * already released.
 	 */
 out:
-	WRITE_ONCE(ctx->mmap_changing, false);
+	atomic_dec(&ctx->mmap_changing);
+	VM_WARN_ON_ONCE(atomic_read(&ctx->mmap_changing) < 0);
 	userfaultfd_ctx_put(ctx);
 }
 
@@ -673,9 +638,11 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
 	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);
+	if (!octx)
+		return 0;
+
+	if (!(octx->features & UFFD_FEATURE_EVENT_FORK)) {
+		userfaultfd_reset_ctx(vma);
 		return 0;
 	}
 
@@ -698,15 +665,17 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
 
 		refcount_set(&ctx->refcount, 1);
 		ctx->flags = octx->flags;
-		ctx->state = UFFD_STATE_RUNNING;
 		ctx->features = octx->features;
 		ctx->released = false;
-		ctx->mmap_changing = false;
+		init_rwsem(&ctx->map_changing_lock);
+		atomic_set(&ctx->mmap_changing, 0);
 		ctx->mm = vma->vm_mm;
 		mmgrab(ctx->mm);
 
 		userfaultfd_ctx_get(octx);
-		WRITE_ONCE(octx->mmap_changing, true);
+		down_write(&octx->map_changing_lock);
+		atomic_inc(&octx->mmap_changing);
+		up_write(&octx->map_changing_lock);
 		fctx->orig = octx;
 		fctx->new = ctx;
 		list_add_tail(&fctx->list, fcs);
@@ -740,6 +709,34 @@ void dup_userfaultfd_complete(struct list_head *fcs)
 	}
 }
 
+void dup_userfaultfd_fail(struct list_head *fcs)
+{
+	struct userfaultfd_fork_ctx *fctx, *n;
+
+	/*
+	 * An error has occurred on fork, we will tear memory down, but have
+	 * allocated memory for fctx's and raised reference counts for both the
+	 * original and child contexts (and on the mm for each as a result).
+	 *
+	 * These would ordinarily be taken care of by a user handling the event,
+	 * but we are no longer doing so, so manually clean up here.
+	 *
+	 * mm tear down will take care of cleaning up VMA contexts.
+	 */
+	list_for_each_entry_safe(fctx, n, fcs, list) {
+		struct userfaultfd_ctx *octx = fctx->orig;
+		struct userfaultfd_ctx *ctx = fctx->new;
+
+		atomic_dec(&octx->mmap_changing);
+		VM_WARN_ON_ONCE(atomic_read(&octx->mmap_changing) < 0);
+		userfaultfd_ctx_put(octx);
+		userfaultfd_ctx_put(ctx);
+
+		list_del(&fctx->list);
+		kfree(fctx);
+	}
+}
+
 void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 			     struct vm_userfaultfd_ctx *vm_ctx)
 {
@@ -753,11 +750,12 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 	if (ctx->features & UFFD_FEATURE_EVENT_REMAP) {
 		vm_ctx->ctx = ctx;
 		userfaultfd_ctx_get(ctx);
-		WRITE_ONCE(ctx->mmap_changing, true);
+		down_write(&ctx->map_changing_lock);
+		atomic_inc(&ctx->mmap_changing);
+		up_write(&ctx->map_changing_lock);
 	} else {
 		/* Drop uffd context if remap feature not enabled */
-		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-		vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+		userfaultfd_reset_ctx(vma);
 	}
 }
 
@@ -771,11 +769,6 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
 	if (!ctx)
 		return;
 
-	if (to & ~PAGE_MASK) {
-		userfaultfd_ctx_put(ctx);
-		return;
-	}
-
 	msg_init(&ewq.msg);
 
 	ewq.msg.event = UFFD_EVENT_REMAP;
@@ -786,6 +779,16 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
 	userfaultfd_event_wait_completion(ctx, &ewq);
 }
 
+void mremap_userfaultfd_fail(struct vm_userfaultfd_ctx *vm_ctx)
+{
+	struct userfaultfd_ctx *ctx = vm_ctx->ctx;
+
+	if (!ctx)
+		return;
+
+	userfaultfd_ctx_put(ctx);
+}
+
 bool userfaultfd_remove(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end)
 {
@@ -798,7 +801,9 @@ bool userfaultfd_remove(struct vm_area_struct *vma,
 		return true;
 
 	userfaultfd_ctx_get(ctx);
-	WRITE_ONCE(ctx->mmap_changing, true);
+	down_write(&ctx->map_changing_lock);
+	atomic_inc(&ctx->mmap_changing);
+	up_write(&ctx->map_changing_lock);
 	mmap_read_unlock(mm);
 
 	msg_init(&ewq.msg);
@@ -825,29 +830,28 @@ static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
 	return false;
 }
 
-int userfaultfd_unmap_prep(struct vm_area_struct *vma,
-			   unsigned long start, unsigned long end,
-			   struct list_head *unmaps)
+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;
+	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;
+	if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) ||
+	    has_unmap_ctx(ctx, unmaps, start, end))
+		return 0;
 
-		unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL);
-		if (!unmap_ctx)
-			return -ENOMEM;
+	unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL);
+	if (!unmap_ctx)
+		return -ENOMEM;
 
-		userfaultfd_ctx_get(ctx);
-		WRITE_ONCE(ctx->mmap_changing, true);
-		unmap_ctx->ctx = ctx;
-		unmap_ctx->start = start;
-		unmap_ctx->end = end;
-		list_add_tail(&unmap_ctx->list, unmaps);
-	}
+	userfaultfd_ctx_get(ctx);
+	down_write(&ctx->map_changing_lock);
+	atomic_inc(&ctx->mmap_changing);
+	up_write(&ctx->map_changing_lock);
+	unmap_ctx->ctx = ctx;
+	unmap_ctx->start = start;
+	unmap_ctx->end = end;
+	list_add_tail(&unmap_ctx->list, unmaps);
 
 	return 0;
 }
@@ -875,55 +879,14 @@ 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;
-	bool still_valid;
 
 	WRITE_ONCE(ctx->released, true);
 
-	if (!mmget_not_zero(mm))
-		goto wakeup;
+	userfaultfd_release_all(mm, ctx);
 
 	/*
-	 * 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_lock. So
-	 * it's critical that released is set to true (above), before
-	 * taking the mmap_lock for writing.
-	 */
-	mmap_write_lock(mm);
-	still_valid = mmget_still_valid(mm);
-	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);
-		if (still_valid) {
-			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;
-	}
-	mmap_write_unlock(mm);
-	mmput(mm);
-wakeup:
-	/*
 	 * After no new page faults can wait on this fault_*wqh, flush
 	 * the last page faults that may have been already waiting on
 	 * the fault_*wqh.
@@ -979,50 +942,45 @@ static __poll_t userfaultfd_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, &ctx->fd_wqh, wait);
 
-	switch (ctx->state) {
-	case UFFD_STATE_WAIT_API:
+	if (!userfaultfd_is_initialized(ctx))
 		return EPOLLERR;
-	case UFFD_STATE_RUNNING:
-		/*
-		 * poll() never guarantees that read won't block.
-		 * userfaults can be waken before they're read().
-		 */
-		if (unlikely(!(file->f_flags & O_NONBLOCK)))
-			return EPOLLERR;
-		/*
-		 * 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 = EPOLLIN;
-		else if (waitqueue_active(&ctx->event_wqh))
-			ret = EPOLLIN;
 
-		return ret;
-	default:
-		WARN_ON_ONCE(1);
+	/*
+	 * poll() never guarantees that read won't block.
+	 * userfaults can be waken before they're read().
+	 */
+	if (unlikely(!(file->f_flags & O_NONBLOCK)))
 		return EPOLLERR;
-	}
+	/*
+	 * 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 = EPOLLIN;
+	else if (waitqueue_active(&ctx->event_wqh))
+		ret = EPOLLIN;
+
+	return ret;
 }
 
 static const struct file_operations userfaultfd_fops;
 
-static int resolve_userfault_fork(struct userfaultfd_ctx *ctx,
-				  struct userfaultfd_ctx *new,
+static int resolve_userfault_fork(struct userfaultfd_ctx *new,
+				  struct inode *inode,
 				  struct uffd_msg *msg)
 {
 	int fd;
 
-	fd = anon_inode_getfd("[userfaultfd]", &userfaultfd_fops, new,
-			      O_RDWR | (new->flags & UFFD_SHARED_FCNTL_FLAGS));
+	fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, new,
+			O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
 	if (fd < 0)
 		return fd;
 
@@ -1032,7 +990,7 @@ static int resolve_userfault_fork(struct userfaultfd_ctx *ctx,
 }
 
 static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
-				    struct uffd_msg *msg)
+				    struct uffd_msg *msg, struct inode *inode)
 {
 	ssize_t ret;
 	DECLARE_WAITQUEUE(wait, current);
@@ -1143,7 +1101,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 	spin_unlock_irq(&ctx->fd_wqh.lock);
 
 	if (!ret && msg->event == UFFD_EVENT_FORK) {
-		ret = resolve_userfault_fork(ctx, fork_nctx, msg);
+		ret = resolve_userfault_fork(fork_nctx, inode, msg);
 		spin_lock_irq(&ctx->event_wqh.lock);
 		if (!list_empty(&fork_event)) {
 			/*
@@ -1196,33 +1154,34 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 	return ret;
 }
 
-static ssize_t userfaultfd_read(struct file *file, char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t userfaultfd_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	struct file *file = iocb->ki_filp;
 	struct userfaultfd_ctx *ctx = file->private_data;
 	ssize_t _ret, ret = 0;
 	struct uffd_msg msg;
-	int no_wait = file->f_flags & O_NONBLOCK;
+	struct inode *inode = file_inode(file);
+	bool no_wait;
 
-	if (ctx->state == UFFD_STATE_WAIT_API)
+	if (!userfaultfd_is_initialized(ctx))
 		return -EINVAL;
 
+	no_wait = file->f_flags & O_NONBLOCK || iocb->ki_flags & IOCB_NOWAIT;
 	for (;;) {
-		if (count < sizeof(msg))
+		if (iov_iter_count(to) < sizeof(msg))
 			return ret ? ret : -EINVAL;
-		_ret = userfaultfd_ctx_read(ctx, no_wait, &msg);
+		_ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode);
 		if (_ret < 0)
 			return ret ? ret : _ret;
-		if (copy_to_user((__u64 __user *) buf, &msg, sizeof(msg)))
+		_ret = !copy_to_iter_full(&msg, sizeof(msg), to);
+		if (_ret)
 			return ret ? ret : -EFAULT;
 		ret += sizeof(msg);
-		buf += sizeof(msg);
-		count -= sizeof(msg);
 		/*
 		 * Allow to read more than one fault at time but only
 		 * block if waiting for the very first one.
 		 */
-		no_wait = O_NONBLOCK;
+		no_wait = true;
 	}
 }
 
@@ -1270,49 +1229,49 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
 		__wake_userfault(ctx, range);
 }
 
-static __always_inline int validate_range(struct mm_struct *mm,
-					  __u64 *start, __u64 len)
+static __always_inline int validate_unaligned_range(
+	struct mm_struct *mm, __u64 start, __u64 len)
 {
 	__u64 task_size = mm->task_size;
 
-	*start = untagged_addr(*start);
-
-	if (*start & ~PAGE_MASK)
-		return -EINVAL;
 	if (len & ~PAGE_MASK)
 		return -EINVAL;
 	if (!len)
 		return -EINVAL;
-	if (*start < mmap_min_addr)
+	if (start < mmap_min_addr)
 		return -EINVAL;
-	if (*start >= task_size)
+	if (start >= task_size)
 		return -EINVAL;
-	if (len > task_size - *start)
+	if (len > task_size - start)
+		return -EINVAL;
+	if (start + len <= start)
 		return -EINVAL;
 	return 0;
 }
 
-static inline bool vma_can_userfault(struct vm_area_struct *vma,
-				     unsigned long vm_flags)
+static __always_inline int validate_range(struct mm_struct *mm,
+					  __u64 start, __u64 len)
 {
-	/* FIXME: add WP support to hugetlbfs and shmem */
-	return vma_is_anonymous(vma) ||
-		((is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) &&
-		 !(vm_flags & VM_UFFD_WP));
+	if (start & ~PAGE_MASK)
+		return -EINVAL;
+
+	return validate_unaligned_range(mm, start, len);
 }
 
 static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 				unsigned long arg)
 {
 	struct mm_struct *mm = ctx->mm;
-	struct vm_area_struct *vma, *prev, *cur;
+	struct vm_area_struct *vma, *cur;
 	int ret;
 	struct uffdio_register uffdio_register;
 	struct uffdio_register __user *user_uffdio_register;
-	unsigned long vm_flags, new_flags;
+	vm_flags_t vm_flags;
 	bool found;
 	bool basic_ioctls;
-	unsigned long start, end, vma_end;
+	unsigned long start, end;
+	struct vma_iterator vmi;
+	bool wp_async = userfaultfd_wp_async_ctx(ctx);
 
 	user_uffdio_register = (struct uffdio_register __user *) arg;
 
@@ -1324,16 +1283,25 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	ret = -EINVAL;
 	if (!uffdio_register.mode)
 		goto out;
-	if (uffdio_register.mode & ~(UFFDIO_REGISTER_MODE_MISSING|
-				     UFFDIO_REGISTER_MODE_WP))
+	if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES)
 		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)
+	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) {
+		if (!pgtable_supports_uffd_wp())
+			goto out;
+
 		vm_flags |= VM_UFFD_WP;
+	}
+	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) {
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+		goto out;
+#endif
+		vm_flags |= VM_UFFD_MINOR;
+	}
 
-	ret = validate_range(mm, &uffdio_register.range.start,
+	ret = validate_range(mm, uffdio_register.range.start,
 			     uffdio_register.range.len);
 	if (ret)
 		goto out;
@@ -1345,18 +1313,13 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	if (!mmget_not_zero(mm))
 		goto out;
 
+	ret = -EINVAL;
 	mmap_write_lock(mm);
-	if (!mmget_still_valid(mm))
-		goto out_unlock;
-	vma = find_vma_prev(mm, start, &prev);
+	vma_iter_init(&vmi, mm, start);
+	vma = vma_find(&vmi, end);
 	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;
-
 	/*
 	 * If the first vma contains huge pages, make sure start address
 	 * is aligned to huge page size.
@@ -1373,15 +1336,16 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	 */
 	found = false;
 	basic_ioctls = false;
-	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
+	cur = vma;
+	do {
 		cond_resched();
 
-		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
-		       !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+		VM_WARN_ON_ONCE(!!cur->vm_userfaultfd_ctx.ctx ^
+				!!(cur->vm_flags & __VM_UFFD_FLAGS));
 
 		/* check not compatible vmas */
 		ret = -EINVAL;
-		if (!vma_can_userfault(cur, vm_flags))
+		if (!vma_can_userfault(cur, vm_flags, wp_async))
 			goto out_unlock;
 
 		/*
@@ -1430,67 +1394,12 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 			basic_ioctls = true;
 
 		found = true;
-	}
-	BUG_ON(!found);
-
-	if (vma->vm_start < start)
-		prev = vma;
-
-	ret = 0;
-	do {
-		cond_resched();
-
-		BUG_ON(!vma_can_userfault(vma, vm_flags));
-		BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
-		       vma->vm_userfaultfd_ctx.ctx != ctx);
-		WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
-
-		/*
-		 * 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);
+	} for_each_vma_range(vmi, cur, end);
+	VM_WARN_ON_ONCE(!found);
 
-		new_flags = (vma->vm_flags &
-			     ~(VM_UFFD_MISSING|VM_UFFD_WP)) | 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;
+	ret = userfaultfd_register_range(ctx, vma, vm_flags, start, end,
+					 wp_async);
 
-	skip:
-		prev = vma;
-		start = vma->vm_end;
-		vma = vma->vm_next;
-	} while (vma && vma->vm_start < end);
 out_unlock:
 	mmap_write_unlock(mm);
 	mmput(mm);
@@ -1507,6 +1416,10 @@ out_unlock:
 		if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP))
 			ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT);
 
+		/* CONTINUE ioctl is only supported for MINOR ranges. */
+		if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR))
+			ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE);
+
 		/*
 		 * Now that we scanned all vmas we can already tell
 		 * userland which ioctls methods are guaranteed to
@@ -1526,16 +1439,17 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	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;
+	struct vma_iterator vmi;
+	bool wp_async = userfaultfd_wp_async_ctx(ctx);
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
 		goto out;
 
-	ret = validate_range(mm, &uffdio_unregister.start,
+	ret = validate_range(mm, uffdio_unregister.start,
 			     uffdio_unregister.len);
 	if (ret)
 		goto out;
@@ -1548,15 +1462,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	mmap_write_lock(mm);
-	if (!mmget_still_valid(mm))
-		goto out_unlock;
-	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)
+	vma_iter_init(&vmi, mm, start);
+	vma = vma_find(&vmi, end);
+	if (!vma)
 		goto out_unlock;
 
 	/*
@@ -1574,12 +1483,20 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	 * Search for not compatible vmas.
 	 */
 	found = false;
-	ret = -EINVAL;
-	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
+	cur = vma;
+	do {
 		cond_resched();
 
-		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
-		       !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+		VM_WARN_ON_ONCE(!!cur->vm_userfaultfd_ctx.ctx ^
+				!!(cur->vm_flags & __VM_UFFD_FLAGS));
+
+		/*
+		 * Prevent unregistering through a different userfaultfd than
+		 * the one used for registration.
+		 */
+		if (cur->vm_userfaultfd_ctx.ctx &&
+		    cur->vm_userfaultfd_ctx.ctx != ctx)
+			goto out_unlock;
 
 		/*
 		 * Check not compatible vmas, not strictly required
@@ -1588,30 +1505,29 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		 * provides for more strict behavior to notice
 		 * unregistration errors.
 		 */
-		if (!vma_can_userfault(cur, cur->vm_flags))
+		if (!vma_can_userfault(cur, cur->vm_flags, wp_async))
 			goto out_unlock;
 
 		found = true;
-	}
-	BUG_ON(!found);
+	} for_each_vma_range(vmi, cur, end);
+	VM_WARN_ON_ONCE(!found);
 
+	vma_iter_set(&vmi, start);
+	prev = vma_prev(&vmi);
 	if (vma->vm_start < start)
 		prev = vma;
 
 	ret = 0;
-	do {
+	for_each_vma_range(vmi, vma, end) {
 		cond_resched();
 
-		BUG_ON(!vma_can_userfault(vma, vma->vm_flags));
-
-		/*
-		 * Nothing to do: this vma is already registered into this
-		 * userfaultfd and with the right tracking mode too.
-		 */
+		/* VMA not registered with userfaultfd. */
 		if (!vma->vm_userfaultfd_ctx.ctx)
 			goto skip;
 
-		WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
+		VM_WARN_ON_ONCE(vma->vm_userfaultfd_ctx.ctx != ctx);
+		VM_WARN_ON_ONCE(!vma_can_userfault(vma, vma->vm_flags, wp_async));
+		VM_WARN_ON_ONCE(!(vma->vm_flags & VM_MAYWRITE));
 
 		if (vma->vm_start > start)
 			start = vma->vm_start;
@@ -1630,39 +1546,18 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 			wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
 		}
 
-		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;
+		vma = userfaultfd_clear_vma(&vmi, prev, vma,
+					    start, vma_end);
+		if (IS_ERR(vma)) {
+			ret = PTR_ERR(vma);
+			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:
 	mmap_write_unlock(mm);
 	mmput(mm);
@@ -1686,7 +1581,7 @@ static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
 	if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
 		goto out;
 
-	ret = validate_range(ctx->mm, &uffdio_wake.start, uffdio_wake.len);
+	ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
 	if (ret)
 		goto out;
 
@@ -1697,7 +1592,7 @@ static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
 	 * 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);
+	VM_WARN_ON_ONCE(!range.len);
 
 	wake_userfault(ctx, &range);
 	ret = 0;
@@ -1713,12 +1608,16 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 	struct uffdio_copy uffdio_copy;
 	struct uffdio_copy __user *user_uffdio_copy;
 	struct userfaultfd_wake_range range;
+	uffd_flags_t flags = 0;
 
 	user_uffdio_copy = (struct uffdio_copy __user *) arg;
 
 	ret = -EAGAIN;
-	if (READ_ONCE(ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_copy, user_uffdio_copy,
@@ -1726,23 +1625,22 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 			   sizeof(uffdio_copy)-sizeof(__s64)))
 		goto out;
 
-	ret = validate_range(ctx->mm, &uffdio_copy.dst, uffdio_copy.len);
+	ret = validate_unaligned_range(ctx->mm, uffdio_copy.src,
+				       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)
+	ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
+	if (ret)
 		goto out;
+
+	ret = -EINVAL;
 	if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
 		goto out;
+	if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP)
+		flags |= MFILL_ATOMIC_WP;
 	if (mmget_not_zero(ctx->mm)) {
-		ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
-				   uffdio_copy.len, &ctx->mmap_changing,
-				   uffdio_copy.mode);
+		ret = mfill_atomic_copy(ctx, uffdio_copy.dst, uffdio_copy.src,
+					uffdio_copy.len, flags);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
@@ -1751,7 +1649,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 		return -EFAULT;
 	if (ret < 0)
 		goto out;
-	BUG_ON(!ret);
+	VM_WARN_ON_ONCE(!ret);
 	/* len == 0 would wake all */
 	range.len = ret;
 	if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) {
@@ -1774,8 +1672,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 	user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
 
 	ret = -EAGAIN;
-	if (READ_ONCE(ctx->mmap_changing))
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
+			return -EFAULT;
 		goto out;
+	}
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
@@ -1783,7 +1684,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 			   sizeof(uffdio_zeropage)-sizeof(__s64)))
 		goto out;
 
-	ret = validate_range(ctx->mm, &uffdio_zeropage.range.start,
+	ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
 			     uffdio_zeropage.range.len);
 	if (ret)
 		goto out;
@@ -1792,9 +1693,8 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	if (mmget_not_zero(ctx->mm)) {
-		ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
-				     uffdio_zeropage.range.len,
-				     &ctx->mmap_changing);
+		ret = mfill_atomic_zeropage(ctx, uffdio_zeropage.range.start,
+					   uffdio_zeropage.range.len);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
@@ -1804,7 +1704,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 	if (ret < 0)
 		goto out;
 	/* len == 0 would wake all */
-	BUG_ON(!ret);
+	VM_WARN_ON_ONCE(!ret);
 	range.len = ret;
 	if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) {
 		range.start = uffdio_zeropage.range.start;
@@ -1824,7 +1724,7 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
 	struct userfaultfd_wake_range range;
 	bool mode_wp, mode_dontwake;
 
-	if (READ_ONCE(ctx->mmap_changing))
+	if (atomic_read(&ctx->mmap_changing))
 		return -EAGAIN;
 
 	user_uffdio_wp = (struct uffdio_writeprotect __user *) arg;
@@ -1833,7 +1733,7 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
 			   sizeof(struct uffdio_writeprotect)))
 		return -EFAULT;
 
-	ret = validate_range(ctx->mm, &uffdio_wp.range.start,
+	ret = validate_range(ctx->mm, uffdio_wp.range.start,
 			     uffdio_wp.range.len);
 	if (ret)
 		return ret;
@@ -1848,9 +1748,14 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
 	if (mode_wp && mode_dontwake)
 		return -EINVAL;
 
-	ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
-				  uffdio_wp.range.len, mode_wp,
-				  &ctx->mmap_changing);
+	if (mmget_not_zero(ctx->mm)) {
+		ret = mwriteprotect_range(ctx, uffdio_wp.range.start,
+					  uffdio_wp.range.len, mode_wp);
+		mmput(ctx->mm);
+	} else {
+		return -ESRCH;
+	}
+
 	if (ret)
 		return ret;
 
@@ -1862,12 +1767,201 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
 	return ret;
 }
 
+static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
+{
+	__s64 ret;
+	struct uffdio_continue uffdio_continue;
+	struct uffdio_continue __user *user_uffdio_continue;
+	struct userfaultfd_wake_range range;
+	uffd_flags_t flags = 0;
+
+	user_uffdio_continue = (struct uffdio_continue __user *)arg;
+
+	ret = -EAGAIN;
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+			return -EFAULT;
+		goto out;
+	}
+
+	ret = -EFAULT;
+	if (copy_from_user(&uffdio_continue, user_uffdio_continue,
+			   /* don't copy the output fields */
+			   sizeof(uffdio_continue) - (sizeof(__s64))))
+		goto out;
+
+	ret = validate_range(ctx->mm, uffdio_continue.range.start,
+			     uffdio_continue.range.len);
+	if (ret)
+		goto out;
+
+	ret = -EINVAL;
+	if (uffdio_continue.mode & ~(UFFDIO_CONTINUE_MODE_DONTWAKE |
+				     UFFDIO_CONTINUE_MODE_WP))
+		goto out;
+	if (uffdio_continue.mode & UFFDIO_CONTINUE_MODE_WP)
+		flags |= MFILL_ATOMIC_WP;
+
+	if (mmget_not_zero(ctx->mm)) {
+		ret = mfill_atomic_continue(ctx, uffdio_continue.range.start,
+					    uffdio_continue.range.len, flags);
+		mmput(ctx->mm);
+	} else {
+		return -ESRCH;
+	}
+
+	if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+		return -EFAULT;
+	if (ret < 0)
+		goto out;
+
+	/* len == 0 would wake all */
+	VM_WARN_ON_ONCE(!ret);
+	range.len = ret;
+	if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) {
+		range.start = uffdio_continue.range.start;
+		wake_userfault(ctx, &range);
+	}
+	ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN;
+
+out:
+	return ret;
+}
+
+static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long arg)
+{
+	__s64 ret;
+	struct uffdio_poison uffdio_poison;
+	struct uffdio_poison __user *user_uffdio_poison;
+	struct userfaultfd_wake_range range;
+
+	user_uffdio_poison = (struct uffdio_poison __user *)arg;
+
+	ret = -EAGAIN;
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_poison->updated)))
+			return -EFAULT;
+		goto out;
+	}
+
+	ret = -EFAULT;
+	if (copy_from_user(&uffdio_poison, user_uffdio_poison,
+			   /* don't copy the output fields */
+			   sizeof(uffdio_poison) - (sizeof(__s64))))
+		goto out;
+
+	ret = validate_range(ctx->mm, uffdio_poison.range.start,
+			     uffdio_poison.range.len);
+	if (ret)
+		goto out;
+
+	ret = -EINVAL;
+	if (uffdio_poison.mode & ~UFFDIO_POISON_MODE_DONTWAKE)
+		goto out;
+
+	if (mmget_not_zero(ctx->mm)) {
+		ret = mfill_atomic_poison(ctx, uffdio_poison.range.start,
+					  uffdio_poison.range.len, 0);
+		mmput(ctx->mm);
+	} else {
+		return -ESRCH;
+	}
+
+	if (unlikely(put_user(ret, &user_uffdio_poison->updated)))
+		return -EFAULT;
+	if (ret < 0)
+		goto out;
+
+	/* len == 0 would wake all */
+	VM_WARN_ON_ONCE(!ret);
+	range.len = ret;
+	if (!(uffdio_poison.mode & UFFDIO_POISON_MODE_DONTWAKE)) {
+		range.start = uffdio_poison.range.start;
+		wake_userfault(ctx, &range);
+	}
+	ret = range.len == uffdio_poison.range.len ? 0 : -EAGAIN;
+
+out:
+	return ret;
+}
+
+bool userfaultfd_wp_async(struct vm_area_struct *vma)
+{
+	return userfaultfd_wp_async_ctx(vma->vm_userfaultfd_ctx.ctx);
+}
+
 static inline unsigned int uffd_ctx_features(__u64 user_features)
 {
 	/*
-	 * For the current set of features the bits just coincide
+	 * For the current set of features the bits just coincide. Set
+	 * UFFD_FEATURE_INITIALIZED to mark the features as enabled.
 	 */
-	return (unsigned int)user_features;
+	return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED;
+}
+
+static int userfaultfd_move(struct userfaultfd_ctx *ctx,
+			    unsigned long arg)
+{
+	__s64 ret;
+	struct uffdio_move uffdio_move;
+	struct uffdio_move __user *user_uffdio_move;
+	struct userfaultfd_wake_range range;
+	struct mm_struct *mm = ctx->mm;
+
+	user_uffdio_move = (struct uffdio_move __user *) arg;
+
+	ret = -EAGAIN;
+	if (unlikely(atomic_read(&ctx->mmap_changing))) {
+		if (unlikely(put_user(ret, &user_uffdio_move->move)))
+			return -EFAULT;
+		goto out;
+	}
+
+	if (copy_from_user(&uffdio_move, user_uffdio_move,
+			   /* don't copy "move" last field */
+			   sizeof(uffdio_move)-sizeof(__s64)))
+		return -EFAULT;
+
+	/* Do not allow cross-mm moves. */
+	if (mm != current->mm)
+		return -EINVAL;
+
+	ret = validate_range(mm, uffdio_move.dst, uffdio_move.len);
+	if (ret)
+		return ret;
+
+	ret = validate_range(mm, uffdio_move.src, uffdio_move.len);
+	if (ret)
+		return ret;
+
+	if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES|
+				  UFFDIO_MOVE_MODE_DONTWAKE))
+		return -EINVAL;
+
+	if (mmget_not_zero(mm)) {
+		ret = move_pages(ctx, uffdio_move.dst, uffdio_move.src,
+				 uffdio_move.len, uffdio_move.mode);
+		mmput(mm);
+	} else {
+		return -ESRCH;
+	}
+
+	if (unlikely(put_user(ret, &user_uffdio_move->move)))
+		return -EFAULT;
+	if (ret < 0)
+		goto out;
+
+	/* len == 0 would wake all */
+	VM_WARN_ON(!ret);
+	range.len = ret;
+	if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) {
+		range.start = uffdio_move.dst;
+		wake_userfault(ctx, &range);
+	}
+	ret = range.len == uffdio_move.len ? 0 : -EAGAIN;
+
+out:
+	return ret;
 }
 
 /*
@@ -1880,31 +1974,55 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 {
 	struct uffdio_api uffdio_api;
 	void __user *buf = (void __user *)arg;
+	unsigned int ctx_features;
 	int ret;
 	__u64 features;
 
-	ret = -EINVAL;
-	if (ctx->state != UFFD_STATE_WAIT_API)
-		goto out;
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
 		goto out;
 	features = uffdio_api.features;
 	ret = -EINVAL;
-	if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES))
+	if (uffdio_api.api != UFFD_API)
 		goto err_out;
 	ret = -EPERM;
 	if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
 		goto err_out;
+
+	/* WP_ASYNC relies on WP_UNPOPULATED, choose it unconditionally */
+	if (features & UFFD_FEATURE_WP_ASYNC)
+		features |= UFFD_FEATURE_WP_UNPOPULATED;
+
 	/* report all available features and ioctls to userland */
 	uffdio_api.features = UFFD_API_FEATURES;
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+	uffdio_api.features &=
+		~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM);
+#endif
+	if (!pgtable_supports_uffd_wp())
+		uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
+
+	if (!uffd_supports_wp_marker()) {
+		uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
+		uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED;
+		uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC;
+	}
+
+	ret = -EINVAL;
+	if (features & ~uffdio_api.features)
+		goto err_out;
+
 	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;
+
 	/* only enable the requested features for this uffd context */
-	ctx->features = uffd_ctx_features(features);
+	ctx_features = uffd_ctx_features(features);
+	ret = -EINVAL;
+	if (cmpxchg(&ctx->features, 0, ctx_features) != 0)
+		goto err_out;
+
 	ret = 0;
 out:
 	return ret;
@@ -1921,7 +2039,7 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
 	int ret = -EINVAL;
 	struct userfaultfd_ctx *ctx = file->private_data;
 
-	if (cmd != UFFDIO_API && ctx->state == UFFD_STATE_WAIT_API)
+	if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx))
 		return -EINVAL;
 
 	switch(cmd) {
@@ -1943,9 +2061,18 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
 	case UFFDIO_ZEROPAGE:
 		ret = userfaultfd_zeropage(ctx, arg);
 		break;
+	case UFFDIO_MOVE:
+		ret = userfaultfd_move(ctx, arg);
+		break;
 	case UFFDIO_WRITEPROTECT:
 		ret = userfaultfd_writeprotect(ctx, arg);
 		break;
+	case UFFDIO_CONTINUE:
+		ret = userfaultfd_continue(ctx, arg);
+		break;
+	case UFFDIO_POISON:
+		ret = userfaultfd_poison(ctx, arg);
+		break;
 	}
 	return ret;
 }
@@ -1984,7 +2111,7 @@ static const struct file_operations userfaultfd_fops = {
 #endif
 	.release	= userfaultfd_release,
 	.poll		= userfaultfd_poll,
-	.read		= userfaultfd_read,
+	.read_iter	= userfaultfd_read_iter,
 	.unlocked_ioctl = userfaultfd_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
 	.llseek		= noop_llseek,
@@ -1998,24 +2125,19 @@ static void init_once_userfaultfd_ctx(void *mem)
 	init_waitqueue_head(&ctx->fault_wqh);
 	init_waitqueue_head(&ctx->event_wqh);
 	init_waitqueue_head(&ctx->fd_wqh);
-	seqcount_init(&ctx->refile_seq);
+	seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock);
 }
 
-SYSCALL_DEFINE1(userfaultfd, int, flags)
+static int new_userfaultfd(int flags)
 {
-	struct userfaultfd_ctx *ctx;
-	int fd;
-
-	if (!sysctl_unprivileged_userfaultfd && !capable(CAP_SYS_PTRACE))
-		return -EPERM;
+	struct userfaultfd_ctx *ctx __free(kfree) = NULL;
 
-	BUG_ON(!current->mm);
+	VM_WARN_ON_ONCE(!current->mm);
 
 	/* Check the UFFD_* constants for consistency.  */
-	BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC);
-	BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK);
+	BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS);
 
-	if (flags & ~UFFD_SHARED_FCNTL_FLAGS)
+	if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY))
 		return -EINVAL;
 
 	ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
@@ -2025,29 +2147,87 @@ SYSCALL_DEFINE1(userfaultfd, int, flags)
 	refcount_set(&ctx->refcount, 1);
 	ctx->flags = flags;
 	ctx->features = 0;
-	ctx->state = UFFD_STATE_WAIT_API;
 	ctx->released = false;
-	ctx->mmap_changing = false;
+	init_rwsem(&ctx->map_changing_lock);
+	atomic_set(&ctx->mmap_changing, 0);
 	ctx->mm = current->mm;
+
+	FD_PREPARE(fdf, flags & UFFD_SHARED_FCNTL_FLAGS,
+		   anon_inode_create_getfile("[userfaultfd]", &userfaultfd_fops, ctx,
+					     O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS),
+					     NULL));
+	if (fdf.err)
+		return fdf.err;
+
 	/* prevent the mm struct to be freed */
 	mmgrab(ctx->mm);
+	fd_prepare_file(fdf)->f_mode |= FMODE_NOWAIT;
+	retain_and_null_ptr(ctx);
+	return fd_publish(fdf);
+}
 
-	fd = anon_inode_getfd("[userfaultfd]", &userfaultfd_fops, ctx,
-			      O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS));
-	if (fd < 0) {
-		mmdrop(ctx->mm);
-		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
-	}
-	return fd;
+static inline bool userfaultfd_syscall_allowed(int flags)
+{
+	/* Userspace-only page faults are always allowed */
+	if (flags & UFFD_USER_MODE_ONLY)
+		return true;
+
+	/*
+	 * The user is requesting a userfaultfd which can handle kernel faults.
+	 * Privileged users are always allowed to do this.
+	 */
+	if (capable(CAP_SYS_PTRACE))
+		return true;
+
+	/* Otherwise, access to kernel fault handling is sysctl controlled. */
+	return sysctl_unprivileged_userfaultfd;
+}
+
+SYSCALL_DEFINE1(userfaultfd, int, flags)
+{
+	if (!userfaultfd_syscall_allowed(flags))
+		return -EPERM;
+
+	return new_userfaultfd(flags);
+}
+
+static long userfaultfd_dev_ioctl(struct file *file, unsigned int cmd, unsigned long flags)
+{
+	if (cmd != USERFAULTFD_IOC_NEW)
+		return -EINVAL;
+
+	return new_userfaultfd(flags);
 }
 
+static const struct file_operations userfaultfd_dev_fops = {
+	.unlocked_ioctl = userfaultfd_dev_ioctl,
+	.compat_ioctl = userfaultfd_dev_ioctl,
+	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
+};
+
+static struct miscdevice userfaultfd_misc = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "userfaultfd",
+	.fops = &userfaultfd_dev_fops
+};
+
 static int __init userfaultfd_init(void)
 {
+	int ret;
+
+	ret = misc_register(&userfaultfd_misc);
+	if (ret)
+		return ret;
+
 	userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache",
 						sizeof(struct userfaultfd_ctx),
 						0,
 						SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 						init_once_userfaultfd_ctx);
+#ifdef CONFIG_SYSCTL
+	register_sysctl_init("vm", vm_userfaultfd_table);
+#endif
 	return 0;
 }
 __initcall(userfaultfd_init);