userfaultfd: write protection support

index ddde097cf9e4..58d282115d9b 100644
@@ -625,12 +625,12 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 }
 
 /*
- * mmap_sem must be held on entry.  If @nonblocking != NULL and
- * *@flags does not include FOLL_NOWAIT, the mmap_sem may be released.
- * If it is, *@nonblocking will be set to 0 and -EBUSY returned.
+ * mmap_sem must be held on entry.  If @locked != NULL and *@flags
+ * does not include FOLL_NOWAIT, the mmap_sem may be released.  If it
+ * is, *@locked will be set to 0 and -EBUSY returned.
  */
 static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
-		unsigned long address, unsigned int *flags, int *nonblocking)
+		unsigned long address, unsigned int *flags, int *locked)
 {
 	unsigned int fault_flags = 0;
 	vm_fault_t ret;

@@ -642,7 +642,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 		fault_flags |= FAULT_FLAG_WRITE;
 	if (*flags & FOLL_REMOTE)
 		fault_flags |= FAULT_FLAG_REMOTE;
-	if (nonblocking)
+	if (locked)
 		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
 	if (*flags & FOLL_NOWAIT)
 		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;

@@ -668,8 +668,8 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	}
 
 	if (ret & VM_FAULT_RETRY) {
-		if (nonblocking && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
-			*nonblocking = 0;
+		if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
+			*locked = 0;
 		return -EBUSY;
 	}
 

@@ -746,7 +746,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
  *		only intends to ensure the pages are faulted in.
  * @vmas:	array of pointers to vmas corresponding to each page.
  *		Or NULL if the caller does not require them.
- * @nonblocking: whether waiting for disk IO or mmap_sem contention
+ * @locked:     whether we're still with the mmap_sem held
  *
  * Returns number of pages pinned. This may be fewer than the number
  * requested. If nr_pages is 0 or negative, returns 0. If no pages

@@ -775,13 +775,11 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
  * appropriate) must be called after the page is finished with, and
  * before put_page is called.
  *
- * If @nonblocking != NULL, __get_user_pages will not wait for disk IO
- * or mmap_sem contention, and if waiting is needed to pin all pages,
- * *@nonblocking will be set to 0.  Further, if @gup_flags does not
- * include FOLL_NOWAIT, the mmap_sem will be released via up_read() in
- * this case.
+ * If @locked != NULL, *@locked will be set to 0 when mmap_sem is
+ * released by an up_read().  That can happen if @gup_flags does not
+ * have FOLL_NOWAIT.
  *
- * A caller using such a combination of @nonblocking and @gup_flags
+ * A caller using such a combination of @locked and @gup_flags
  * must therefore hold the mmap_sem for reading only, and recognize
  * when it's been released.  Otherwise, it must be held for either
  * reading or writing and will not be released.

@@ -793,7 +791,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
-		struct vm_area_struct **vmas, int *nonblocking)
+		struct vm_area_struct **vmas, int *locked)
 {
 	long ret = 0, i = 0;
 	struct vm_area_struct *vma = NULL;

@@ -837,7 +835,7 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			if (is_vm_hugetlb_page(vma)) {
 				i = follow_hugetlb_page(mm, vma, pages, vmas,
 						&start, &nr_pages, i,
-						gup_flags, nonblocking);
+						gup_flags, locked);
 				continue;
 			}
 		}

@@ -855,7 +853,7 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		page = follow_page_mask(vma, start, foll_flags, &ctx);
 		if (!page) {
 			ret = faultin_page(tsk, vma, start, &foll_flags,
-					nonblocking);
+					   locked);
 			switch (ret) {
 			case 0:
 				goto retry;

@@ -1508,7 +1506,7 @@ EXPORT_SYMBOL(get_user_pages);
  * @vma:   target vma
  * @start: start address
  * @end:   end address
- * @nonblocking:
+ * @locked: whether the mmap_sem is still held
  *
  * This takes care of mlocking the pages too if VM_LOCKED is set.
  *

@@ -1516,14 +1514,14 @@ EXPORT_SYMBOL(get_user_pages);
  *
  * vma->vm_mm->mmap_sem must be held.
  *
- * If @nonblocking is NULL, it may be held for read or write and will
+ * If @locked is NULL, it may be held for read or write and will
  * be unperturbed.
  *
- * If @nonblocking is non-NULL, it must held for read only and may be
- * released.  If it's released, *@nonblocking will be set to 0.
+ * If @locked is non-NULL, it must held for read only and may be
+ * released.  If it's released, *@locked will be set to 0.
  */
 long populate_vma_page_range(struct vm_area_struct *vma,
-		unsigned long start, unsigned long end, int *nonblocking)
+		unsigned long start, unsigned long end, int *locked)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long nr_pages = (end - start) / PAGE_SIZE;

@@ -1558,7 +1556,7 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	 * not result in a stack expansion that recurses back here.
 	 */
 	return __get_user_pages(current, mm, start, nr_pages, gup_flags,
-				NULL, NULL, nonblocking);
+				NULL, NULL, locked);
 }
 
 /*

index ac843d32b019..ba179c2fa8fb 100644
@@ -4240,7 +4240,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			 struct page **pages, struct vm_area_struct **vmas,
 			 unsigned long *position, unsigned long *nr_pages,
-			 long i, unsigned int flags, int *nonblocking)
+			 long i, unsigned int flags, int *locked)
 {
 	unsigned long pfn_offset;
 	unsigned long vaddr = *position;

@@ -4311,7 +4311,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				spin_unlock(ptl);
 			if (flags & FOLL_WRITE)
 				fault_flags |= FAULT_FLAG_WRITE;
-			if (nonblocking)
+			if (locked)
 				fault_flags |= FAULT_FLAG_ALLOW_RETRY;
 			if (flags & FOLL_NOWAIT)
 				fault_flags |= FAULT_FLAG_ALLOW_RETRY |

@@ -4328,9 +4328,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				break;
 			}
 			if (ret & VM_FAULT_RETRY) {
-				if (nonblocking &&
+				if (locked &&
 				    !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
-					*nonblocking = 0;
+					*locked = 0;
 				*nr_pages = 0;
 				/*
 				 * VM_FAULT_RETRY must not return an

index 188fc9256baf..8a2ef90b4bfc 100644
@@ -150,7 +150,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	   the fault.  */
 	fault = handle_mm_fault(vma, address, flags);
 
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current))
 		return;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {

index 6836095251ed..3517820aea07 100644
@@ -139,17 +139,14 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 	 */
 	fault = handle_mm_fault(vma, address, flags);
 
-	if (fatal_signal_pending(current)) {
-
+	if (unlikely((fault & VM_FAULT_RETRY) && signal_pending(current))) {
+		if (fatal_signal_pending(current) && !user_mode(regs))
+			goto no_context;
 		/*
 		 * if fault retry, mmap_sem already relinquished by core mm
 		 * so OK to return to user mode (with signal handled first)
 		 */
-		if (fault & VM_FAULT_RETRY) {
-			if (!user_mode(regs))
-				goto no_context;
-			return;
-		}
+		return;
 	}
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

index 58f69fa07df9..c41c021bbe40 100644
@@ -314,12 +314,12 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	fault = __do_page_fault(mm, addr, fsr, flags, tsk);
 
-	/* If we need to retry but a fatal signal is pending, handle the
+	/* If we need to retry but a signal is pending, handle the
 	 * signal first. We do not need to release the mmap_sem because
 	 * it would already be released in __lock_page_or_retry in
 	 * mm/filemap.c. */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
-		if (!user_mode(regs))
+	if (unlikely(fault & VM_FAULT_RETRY && signal_pending(current))) {
+		if (fatal_signal_pending(current) && !user_mode(regs))
 			goto no_context;
 		return 0;
 	}

index a30818ed9c60..890ec3a693e6 100644
@@ -513,13 +513,13 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 
 	if (fault & VM_FAULT_RETRY) {
 		/*
-		 * If we need to retry but a fatal signal is pending,
+		 * If we need to retry but a signal is pending,
 		 * handle the signal first. We do not need to release
 		 * the mmap_sem because it would already be released
 		 * in __lock_page_or_retry in mm/filemap.c.
 		 */
-		if (fatal_signal_pending(current)) {
-			if (!user_mode(regs))
+		if (signal_pending(current)) {
+			if (fatal_signal_pending(current) && !user_mode(regs))
 				goto no_context;
 			return 0;
 		}

index b7a99aa5b0ba..febb4f96ba6f 100644
@@ -91,7 +91,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 
 	fault = handle_mm_fault(vma, address, flags);
 
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current))
 		return;
 
 	/* The most common case -- we are done. */

index 5baeb022f474..62c2d39d2bed 100644
@@ -163,7 +163,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	 */
 	fault = handle_mm_fault(vma, address, flags);
 
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current))
 		return;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {

index 9b6163c05a75..d9808a807ab8 100644
@@ -138,7 +138,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	fault = handle_mm_fault(vma, address, flags);
 	pr_debug("handle_mm_fault returns %x\n", fault);
 
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current))
 		return 0;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {

index 202ad6a494f5..4fd2dbd0c5ca 100644
@@ -217,7 +217,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	 */
 	fault = handle_mm_fault(vma, address, flags);
 
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current))
 		return;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {

index 73d8a0f0b810..92374fd091d2 100644
@@ -154,7 +154,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	 */
 	fault = handle_mm_fault(vma, address, flags);
 
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current))
 		return;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

index 68d5f2a27f38..da777de8a62e 100644
@@ -206,12 +206,12 @@ void do_page_fault(unsigned long entry, unsigned long addr,
 	fault = handle_mm_fault(vma, addr, flags);
 
 	/*
-	 * If we need to retry but a fatal signal is pending, handle the
+	 * If we need to retry but a signal is pending, handle the
 	 * signal first. We do not need to release the mmap_sem because it
 	 * would already be released in __lock_page_or_retry in mm/filemap.c.
 	 */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
-		if (!user_mode(regs))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current)) {
+		if (fatal_signal_pending(current) && !user_mode(regs))
 			goto no_context;
 		return;
 	}

index 6a2e716b959f..bdb1f9db75ba 100644
@@ -133,7 +133,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
 	 */
 	fault = handle_mm_fault(vma, address, flags);
 
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current))
 		return;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {

index 9eee5bf3db27..f9f47dc32f94 100644
@@ -161,7 +161,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	fault = handle_mm_fault(vma, address, flags);
 
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current))
 		return;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {

index c8e8b7c05558..29422eec329d 100644
@@ -303,7 +303,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 
 	fault = handle_mm_fault(vma, address, flags);
 
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current))
 		return;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {

index ec6b7ad70659..c2168b298c82 100644
@@ -616,6 +616,8 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 			 */
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
+			if (is_user && signal_pending(current))
+				return 0;
 			if (!fatal_signal_pending(current))
 				goto retry;
 		}

index 3e2708c626a8..4aa7a2343353 100644
@@ -111,11 +111,11 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 	fault = handle_mm_fault(vma, addr, flags);
 
 	/*
-	 * If we need to retry but a fatal signal is pending, handle the
+	 * If we need to retry but a signal is pending, handle the
 	 * signal first. We do not need to release the mmap_sem because it
 	 * would already be released in __lock_page_or_retry in mm/filemap.c.
 	 */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(tsk))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(tsk))
 		return;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {

index df75d574246d..94087ba285be 100644
@@ -493,9 +493,12 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 	 * the fault.
 	 */
 	fault = handle_mm_fault(vma, address, flags);
-	/* No reason to continue if interrupted by SIGKILL. */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
-		fault = VM_FAULT_SIGNAL;
+	/* Do not continue if interrupted by signals. */
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current)) {
+		if (fatal_signal_pending(current))
+			fault = VM_FAULT_SIGNAL;
+		else
+			fault = 0;
 		if (flags & FAULT_FLAG_RETRY_NOWAIT)
 			goto out_up;
 		goto out;

index 6defd2c6d9b1..baf5d73df40c 100644
@@ -506,6 +506,10 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 			 * have already released it in __lock_page_or_retry
 			 * in mm/filemap.c.
 			 */
+
+			if (user_mode(regs) && signal_pending(tsk))
+				return;
+
 			goto retry;
 		}
 	}

index b0440b0edd97..a2c83104fe35 100644
@@ -269,6 +269,9 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 			 * in mm/filemap.c.
 			 */
 
+			if (user_mode(regs) && signal_pending(tsk))
+				return;
+
 			goto retry;
 		}
 	}

index 8f8a604c1300..cad71ec5c7b3 100644
@@ -467,6 +467,9 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 			 * in mm/filemap.c.
 			 */
 
+			if (user_mode(regs) && signal_pending(current))
+				return;
+
 			goto retry;
 		}
 	}

index 0e8b6158f224..05dcd4c5f0d5 100644
@@ -76,8 +76,11 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 
 		fault = handle_mm_fault(vma, address, flags);
 
-		if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		if ((fault & VM_FAULT_RETRY) && signal_pending(current)) {
+			if (is_user && !fatal_signal_pending(current))
+				err = 0;
 			goto out_nosemaphore;
+		}
 
 		if (unlikely(fault & VM_FAULT_ERROR)) {
 			if (fault & VM_FAULT_OOM) {

index b9a3a50644c1..3611f19234a1 100644
@@ -248,11 +248,11 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	fault = __do_pf(mm, addr, fsr, flags, tsk);
 
-	/* If we need to retry but a fatal signal is pending, handle the
+	/* If we need to retry but a signal is pending, handle the
 	 * signal first. We do not need to release the mmap_sem because
 	 * it would already be released in __lock_page_or_retry in
 	 * mm/filemap.c. */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && signal_pending(current))
 		return 0;
 
 	if (!(fault & VM_FAULT_ERROR) && (flags & FAULT_FLAG_ALLOW_RETRY)) {

index 46df4c6aae46..dcd7c1393be3 100644
@@ -1463,16 +1463,20 @@ void do_user_addr_fault(struct pt_regs *regs,
 	 * that we made any progress. Handle this case first.
 	 */
 	if (unlikely(fault & VM_FAULT_RETRY)) {
+		bool is_user = flags & FAULT_FLAG_USER;
+
 		/* Retry at most once */
 		if (flags & FAULT_FLAG_ALLOW_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
+			if (is_user && signal_pending(tsk))
+				return;
 			if (!fatal_signal_pending(tsk))
 				goto retry;
 		}
 
 		/* User mode? Just return to handle the fatal exception */
-		if (flags & FAULT_FLAG_USER)
+		if (is_user)
 			return;
 
 		/* Not returning to user mode? Handle exceptions or die: */

index 2ab0e0dcd166..792dad5e2f12 100644
@@ -136,6 +136,9 @@ void do_page_fault(struct pt_regs *regs)
 			 * in mm/filemap.c.
 			 */
 
+			if (user_mode(regs) && signal_pending(current))
+				return;
+
 			goto retry;
 		}
 	}

index 3b30301c90ec..5dbef45ecbf5 100644
@@ -516,30 +516,6 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 
 	__set_current_state(TASK_RUNNING);
 
-	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);
-			ret = VM_FAULT_NOPAGE;
-		}
-	}
-
 	/*
 	 * Here we race with the list_del; list_add in
 	 * userfaultfd_ctx_read(), however because we don't ever run

index 8a2ef90b4bfc..6a02c0fb36b9 100644
@@ -169,7 +169,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 		else
 			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			 /* No need to up_read(&mm->mmap_sem) as we would
 			 * have already released it in __lock_page_or_retry

index 3517820aea07..144d25b2e044 100644
@@ -165,7 +165,6 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 			}
 
 			if (fault & VM_FAULT_RETRY) {
-				flags &= ~FAULT_FLAG_ALLOW_RETRY;
 				flags |= FAULT_FLAG_TRIED;
 				goto retry;
 			}

index c41c021bbe40..7910b4b5205d 100644
@@ -342,9 +342,6 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 					regs, addr);
 		}
 		if (fault & VM_FAULT_RETRY) {
-			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			* of starvation. */
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}

index 890ec3a693e6..c36da19d9098 100644
@@ -524,12 +524,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 			return 0;
 		}
 
-		/*
-		 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
-		 * starvation.
-		 */
 		if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
-			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			mm_flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}

index febb4f96ba6f..21b6e9d8f2a1 100644
@@ -102,7 +102,6 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 			else
 				current->min_flt++;
 			if (fault & VM_FAULT_RETRY) {
-				flags &= ~FAULT_FLAG_ALLOW_RETRY;
 				flags |= FAULT_FLAG_TRIED;
 				goto retry;
 			}

index 62c2d39d2bed..9de95d39935e 100644
@@ -189,7 +189,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 		else
 			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			 /* No need to up_read(&mm->mmap_sem) as we would

index d9808a807ab8..b1b2109e4ab4 100644
@@ -162,9 +162,6 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 		else
 			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
-			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			 * of starvation. */
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			/*

index 4fd2dbd0c5ca..05a4847ac0bf 100644
@@ -236,7 +236,6 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 		else
 			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			/*

index 92374fd091d2..9953b5b571df 100644
@@ -178,7 +178,6 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 			tsk->min_flt++;
 		}
 		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			/*

index da777de8a62e..3642bdd7909d 100644
@@ -242,7 +242,6 @@ void do_page_fault(unsigned long entry, unsigned long addr,
 				      1, regs, addr);
 		}
 		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			/* No need to up_read(&mm->mmap_sem) as we would

index bdb1f9db75ba..9d4961d51db4 100644
@@ -157,9 +157,6 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
 		else
 			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
-			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			 * of starvation. */
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			/*

index f9f47dc32f94..05c754664fcb 100644
@@ -181,7 +181,6 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 		else
 			tsk->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			 /* No need to up_read(&mm->mmap_sem) as we would

index 29422eec329d..675b221af198 100644
@@ -327,14 +327,12 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 		else
 			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
-
 			/*
 			 * No need to up_read(&mm->mmap_sem) as we would
 			 * have already released it in __lock_page_or_retry
 			 * in mm/filemap.c.
 			 */
-
+			flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}
 	}

index c2168b298c82..63564afb24ed 100644
@@ -608,13 +608,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * case.
 	 */
 	if (unlikely(fault & VM_FAULT_RETRY)) {
-		/* We retry only once */
 		if (flags & FAULT_FLAG_ALLOW_RETRY) {
-			/*
-			 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			 * of starvation.
-			 */
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 			if (is_user && signal_pending(current))
 				return 0;

index 4aa7a2343353..cc76c8766951 100644
@@ -142,11 +142,6 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 				      1, regs, addr);
 		}
 		if (fault & VM_FAULT_RETRY) {
-			/*
-			 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			 * of starvation.
-			 */
-			flags &= ~(FAULT_FLAG_ALLOW_RETRY);
 			flags |= FAULT_FLAG_TRIED;
 
 			/*

index 94087ba285be..e460043776f3 100644
@@ -530,10 +530,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 				fault = VM_FAULT_PFAULT;
 				goto out_up;
 			}
-			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			 * of starvation. */
-			flags &= ~(FAULT_FLAG_ALLOW_RETRY |
-				   FAULT_FLAG_RETRY_NOWAIT);
+			flags &= ~FAULT_FLAG_RETRY_NOWAIT;
 			flags |= FAULT_FLAG_TRIED;
 			down_read(&mm->mmap_sem);
 			goto retry;

index baf5d73df40c..cd710e2d7c57 100644
@@ -498,7 +498,6 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 				      regs, address);
 		}
 		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			/*

index a2c83104fe35..6735cd1c09b9 100644
@@ -261,7 +261,6 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 				      1, regs, address);
 		}
 		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			/* No need to up_read(&mm->mmap_sem) as we would

index cad71ec5c7b3..28d5b4d012c6 100644
@@ -459,7 +459,6 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 				      1, regs, address);
 		}
 		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			/* No need to up_read(&mm->mmap_sem) as we would

index 05dcd4c5f0d5..e7723c133c7f 100644
@@ -99,7 +99,6 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 			else
 				current->min_flt++;
 			if (fault & VM_FAULT_RETRY) {
-				flags &= ~FAULT_FLAG_ALLOW_RETRY;
 				flags |= FAULT_FLAG_TRIED;
 
 				goto retry;

index 3611f19234a1..efca122b5ef7 100644
@@ -261,9 +261,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		else
 			tsk->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
-			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			* of starvation. */
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}
 	}

index dcd7c1393be3..8d3fbd3dca75 100644
@@ -1465,9 +1465,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	if (unlikely(fault & VM_FAULT_RETRY)) {
 		bool is_user = flags & FAULT_FLAG_USER;
 
-		/* Retry at most once */
 		if (flags & FAULT_FLAG_ALLOW_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 			if (is_user && signal_pending(tsk))
 				return;

index 792dad5e2f12..7cd55f2d66c9 100644
@@ -128,7 +128,6 @@ void do_page_fault(struct pt_regs *regs)
 		else
 			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 
 			 /* No need to up_read(&mm->mmap_sem) as we would

index 6dacff49c1cc..8f2f9ee6effa 100644
@@ -61,9 +61,10 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 
 	/*
 	 * If possible, avoid waiting for GPU with mmap_sem
-	 * held.
+	 * held.  We only do this if the fault allows retry and this
+	 * is the first attempt.
 	 */
-	if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
+	if (fault_flag_allow_retry_first(vmf->flags)) {
 		ret = VM_FAULT_RETRY;
 		if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
 			goto out_unlock;

@@ -132,7 +133,12 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 	 * for the buffer to become unreserved.
 	 */
 	if (unlikely(!reservation_object_trylock(bo->resv))) {
-		if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
+		/*
+		 * If the fault allows retry and this is the first
+		 * fault attempt, we try to release the mmap_sem
+		 * before waiting
+		 */
+		if (fault_flag_allow_retry_first(vmf->flags)) {
 			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
 				ttm_bo_get(bo);
 				up_read(&vmf->vma->vm_mm->mmap_sem);

56 lines not on this page · raw message

index df2006ba0cfa..83fdf429f795 100644
@@ -1381,7 +1381,7 @@ EXPORT_SYMBOL_GPL(__lock_page_killable);
 int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 			 unsigned int flags)
 {
-	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+	if (fault_flag_allow_retry_first(flags)) {
 		/*
 		 * CAUTION! In this case, mmap_sem is not released
 		 * even though return 0.

index 1bb3b8dc8bb2..ef3a19c83927 100644
@@ -2009,7 +2009,7 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
 			DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function);
 
 			ret = VM_FAULT_NOPAGE;
-			if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
+			if (fault_flag_allow_retry_first(vmf->flags) &&
 			   !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
 				/* It's polite to up mmap_sem if we can */
 				up_read(&vma->vm_mm->mmap_sem);

index 58d282115d9b..ac8d5b73c212 100644
@@ -647,7 +647,10 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	if (*flags & FOLL_NOWAIT)
 		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
 	if (*flags & FOLL_TRIED) {
-		VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_ALLOW_RETRY);
+		/*
+		 * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED
+		 * can co-exist
+		 */
 		fault_flags |= FAULT_FLAG_TRIED;
 	}
 

@@ -1062,17 +1065,23 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 		if (likely(pages))
 			pages += ret;
 		start += ret << PAGE_SHIFT;
+		lock_dropped = true;
 
+retry:
 		/*
 		 * Repeat on the address that fired VM_FAULT_RETRY
-		 * without FAULT_FLAG_ALLOW_RETRY but with
+		 * with both FAULT_FLAG_ALLOW_RETRY and
 		 * FAULT_FLAG_TRIED.
 		 */
 		*locked = 1;
-		lock_dropped = true;
 		down_read(&mm->mmap_sem);
 		ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED,
-				       pages, NULL, NULL);
+				       pages, NULL, locked);
+		if (!*locked) {
+			/* Continue to retry until we succeeded */
+			BUG_ON(ret != 0);
+			goto retry;
+		}
 		if (ret != 1) {
 			BUG_ON(ret > 1);
 			if (!pages_done)

index ba179c2fa8fb..d9c739f9a28e 100644
@@ -4317,8 +4317,10 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				fault_flags |= FAULT_FLAG_ALLOW_RETRY |
 					FAULT_FLAG_RETRY_NOWAIT;
 			if (flags & FOLL_TRIED) {
-				VM_WARN_ON_ONCE(fault_flags &
-						FAULT_FLAG_ALLOW_RETRY);
+				/*
+				 * Note: FAULT_FLAG_ALLOW_RETRY and
+				 * FAULT_FLAG_TRIED can co-exist
+				 */
 				fault_flags |= FAULT_FLAG_TRIED;
 			}
 			ret = hugetlb_fault(mm, vma, vaddr, fault_flags);

index ac9d71e24b81..5dc247af0f2e 100644
@@ -52,6 +52,11 @@ static inline bool userfaultfd_missing(struct vm_area_struct *vma)
 	return vma->vm_flags & VM_UFFD_MISSING;
 }
 
+static inline bool userfaultfd_wp(struct vm_area_struct *vma)
+{
+	return vma->vm_flags & VM_UFFD_WP;
+}
+
 static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 {
 	return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP);

@@ -96,6 +101,11 @@ static inline bool userfaultfd_missing(struct vm_area_struct *vma)
 	return false;
 }
 
+static inline bool userfaultfd_wp(struct vm_area_struct *vma)
+{
+	return false;
+}
+
 static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 {
 	return false;

index ddf20bd0c317..05bcd741855b 100644
@@ -2579,6 +2579,11 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 
+	if (userfaultfd_wp(vma)) {
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		return handle_userfault(vmf, VM_UFFD_WP);
+	}
+
 	vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
 	if (!vmf->page) {
 		/*

@@ -3794,8 +3799,11 @@ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
 /* `inline' is required to avoid gcc 4.1.2 build error */
 static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 {
-	if (vma_is_anonymous(vmf->vma))
+	if (vma_is_anonymous(vmf->vma)) {
+		if (userfaultfd_wp(vmf->vma))
+			return handle_userfault(vmf, VM_UFFD_WP);
 		return do_huge_pmd_wp_page(vmf, orig_pmd);
+	}
 	if (vmf->vma->vm_ops->huge_fault)
 		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
 

76 lines not on this page · raw message

index 0bb566315621..627666b1c3c0 100644
@@ -189,7 +189,7 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
+ * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|F|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above

@@ -197,9 +197,15 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
  * erratum where they can be incorrectly set by hardware on
  * non-present PTEs.
  *
+ * SD Bits 1-4 are not used in non-present format and available for
+ * special use described below:
+ *
  * SD (1) in swp entry is used to store soft dirty bit, which helps us
  * remember soft dirty over page migration
  *
+ * F (2) in swp entry is used to record when a pagetable is
+ * writeprotected by userfaultfd WP support.
+ *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
  *

index d6ff0bbdb394..dd9c6295d610 100644
@@ -32,6 +32,7 @@
 
 #define _PAGE_BIT_SPECIAL	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
+#define _PAGE_BIT_UFFD_WP	_PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
 #define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 

@@ -100,6 +101,14 @@
 #define _PAGE_SWP_SOFT_DIRTY	(_AT(pteval_t, 0))
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+#define _PAGE_UFFD_WP		(_AT(pteval_t, 1) << _PAGE_BIT_UFFD_WP)
+#define _PAGE_SWP_UFFD_WP	_PAGE_USER
+#else
+#define _PAGE_UFFD_WP		(_AT(pteval_t, 0))
+#define _PAGE_SWP_UFFD_WP	(_AT(pteval_t, 0))
+#endif
+
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #define _PAGE_DEVMAP	(_AT(u64, 1) << _PAGE_BIT_DEVMAP)

@@ -124,7 +133,7 @@
  */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |	\
-			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
+			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_UFFD_WP)
 #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 /*

index 75d9d68a6de7..1e979845e1cb 100644
@@ -10,6 +10,7 @@
 #include <linux/mm_types.h>
 #include <linux/bug.h>
 #include <linux/errno.h>
+#include <asm-generic/pgtable_uffd.h>
 
 #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
 	defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS

51 lines not on this page · raw message

index 5dc247af0f2e..7b91b76aac58 100644
@@ -14,6 +14,8 @@
 #include <linux/userfaultfd.h> /* linux/include/uapi/linux/userfaultfd.h */
 
 #include <linux/fcntl.h>
+#include <linux/mm.h>
+#include <asm-generic/pgtable_uffd.h>
 
 /*
  * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining

@@ -57,6 +59,18 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma)
 	return vma->vm_flags & VM_UFFD_WP;
 }
 
+static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma,
+				      pte_t pte)
+{
+	return userfaultfd_wp(vma) && pte_uffd_wp(pte);
+}
+
+static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma,
+					   pmd_t pmd)
+{
+	return userfaultfd_wp(vma) && pmd_uffd_wp(pmd);
+}
+
 static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 {
 	return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP);

@@ -106,6 +120,19 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma)
 	return false;
 }
 
+static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma,
+				      pte_t pte)
+{
+	return false;
+}
+
+static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma,
+					   pmd_t pmd)
+{
+	return false;
+}
+
+
 static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 {
 	return false;

index 5dbef45ecbf5..c594945ad5bf 100644
@@ -1694,11 +1694,12 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 	ret = -EINVAL;
 	if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src)
 		goto out;
-	if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE)
+	if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
 		goto out;
 	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.len, &ctx->mmap_changing,
+				   uffdio_copy.mode);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;

index 7b91b76aac58..dcd33172b728 100644
@@ -36,7 +36,7 @@ extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
 
 extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
 			    unsigned long src_start, unsigned long len,
-			    bool *mmap_changing);
+			    bool *mmap_changing, __u64 mode);
 extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
 			      unsigned long dst_start,
 			      unsigned long len,

index 48f1a7c2f1f0..340f23bc251d 100644
@@ -203,13 +203,14 @@ struct uffdio_copy {
 	__u64 dst;
 	__u64 src;
 	__u64 len;
+#define UFFDIO_COPY_MODE_DONTWAKE		((__u64)1<<0)
 	/*
-	 * There will be a wrprotection flag later that allows to map
-	 * pages wrprotected on the fly. And such a flag will be
-	 * available if the wrprotection ioctl are implemented for the
-	 * range according to the uffdio_register.ioctls.
+	 * UFFDIO_COPY_MODE_WP will map the page write protected on
+	 * the fly.  UFFDIO_COPY_MODE_WP is available only if the
+	 * write protected ioctl is implemented for the range
+	 * according to the uffdio_register.ioctls.
 	 */
-#define UFFDIO_COPY_MODE_DONTWAKE		((__u64)1<<0)
+#define UFFDIO_COPY_MODE_WP			((__u64)1<<1)
 	__u64 mode;
 
 	/*

index 9932d5755e4c..c8e7846e9b7e 100644
@@ -25,7 +25,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 			    struct vm_area_struct *dst_vma,
 			    unsigned long dst_addr,
 			    unsigned long src_addr,
-			    struct page **pagep)
+			    struct page **pagep,
+			    bool wp_copy)
 {
 	struct mem_cgroup *memcg;
 	pte_t _dst_pte, *dst_pte;

@@ -71,9 +72,9 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false))
 		goto out_release;
 
-	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
-	if (dst_vma->vm_flags & VM_WRITE)
-		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
+	_dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot));
+	if ((dst_vma->vm_flags & VM_WRITE) && !wp_copy)
+		_dst_pte = pte_mkwrite(_dst_pte);
 
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
 	if (dst_vma->vm_file) {

@@ -398,7 +399,8 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 						unsigned long dst_addr,
 						unsigned long src_addr,
 						struct page **page,
-						bool zeropage)
+						bool zeropage,
+						bool wp_copy)
 {
 	ssize_t err;
 

@@ -415,11 +417,13 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 	if (!(dst_vma->vm_flags & VM_SHARED)) {
 		if (!zeropage)
 			err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
-					       dst_addr, src_addr, page);
+					       dst_addr, src_addr, page,
+					       wp_copy);
 		else
 			err = mfill_zeropage_pte(dst_mm, dst_pmd,
 						 dst_vma, dst_addr);
 	} else {
+		VM_WARN_ON_ONCE(wp_copy);
 		if (!zeropage)
 			err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd,
 						     dst_vma, dst_addr,

@@ -437,7 +441,8 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 					      unsigned long src_start,
 					      unsigned long len,
 					      bool zeropage,
-					      bool *mmap_changing)
+					      bool *mmap_changing,
+					      __u64 mode)
 {
 	struct vm_area_struct *dst_vma;
 	ssize_t err;

@@ -445,6 +450,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 	unsigned long src_addr, dst_addr;
 	long copied;
 	struct page *page;
+	bool wp_copy;
 
 	/*
 	 * Sanitize the command parameters:

@@ -501,6 +507,14 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 	    dst_vma->vm_flags & VM_SHARED))
 		goto out_unlock;
 
+	/*
+	 * validate 'mode' now that we know the dst_vma: don't allow
+	 * a wrprotect copy if the userfaultfd didn't register as WP.
+	 */
+	wp_copy = mode & UFFDIO_COPY_MODE_WP;
+	if (wp_copy && !(dst_vma->vm_flags & VM_UFFD_WP))
+		goto out_unlock;
+
 	/*
 	 * If this is a HUGETLB vma, pass off to appropriate routine
 	 */

@@ -556,7 +570,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 		BUG_ON(pmd_trans_huge(*dst_pmd));
 
 		err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
-				       src_addr, &page, zeropage);
+				       src_addr, &page, zeropage, wp_copy);
 		cond_resched();
 
 		if (unlikely(err == -ENOENT)) {

@@ -603,14 +617,14 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 
 ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
 		     unsigned long src_start, unsigned long len,
-		     bool *mmap_changing)
+		     bool *mmap_changing, __u64 mode)
 {
 	return __mcopy_atomic(dst_mm, dst_start, src_start, len, false,
-			      mmap_changing);
+			      mmap_changing, mode);
 }
 
 ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
 		       unsigned long len, bool *mmap_changing)
 {
-	return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing);
+	return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing, 0);
 }

index 7cd5c150c21d..a81a6ed609ac 100644
@@ -46,7 +46,7 @@ extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 			 pmd_t *old_pmd, pmd_t *new_pmd);
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, pgprot_t newprot,
-			int prot_numa);
+			unsigned long cp_flags);
 vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
 vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
 enum transparent_hugepage_flag {

index dcaca899e4a8..a93ac1c37940 100644
@@ -1708,9 +1708,21 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
 		unsigned long new_addr, unsigned long len,
 		bool need_rmap_locks);
+
+/*
+ * Flags used by change_protection().  For now we make it a bitmap so
+ * that we can pass in multiple flags just like parameters.  However
+ * for now all the callers are only use one of the flags at the same
+ * time.
+ */
+/* Whether we should allow dirty bit accounting */
+#define  MM_CP_DIRTY_ACCT                  (1UL << 0)
+/* Whether this protection change is for NUMA hints */
+#define  MM_CP_PROT_NUMA                   (1UL << 1)
+
 extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 			      unsigned long end, pgprot_t newprot,
-			      int dirty_accountable, int prot_numa);
+			      unsigned long cp_flags);
 extern int mprotect_fixup(struct vm_area_struct *vma,
 			  struct vm_area_struct **pprev, unsigned long start,
 			  unsigned long end, unsigned long newflags);

index 9f8bce9a6b32..b7149a0acac1 100644
@@ -1903,13 +1903,14 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
  *  - HPAGE_PMD_NR is protections changed and TLB flush necessary
  */
 int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, pgprot_t newprot, int prot_numa)
+		unsigned long addr, pgprot_t newprot, unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
 	pmd_t entry;
 	bool preserve_write;
 	int ret;
+	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
 
 	ptl = __pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)

index 01600d80ae01..dea6a49573e3 100644
@@ -575,7 +575,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
 {
 	int nr_updated;
 
-	nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1);
+	nr_updated = change_protection(vma, addr, end, PAGE_NONE, MM_CP_PROT_NUMA);
 	if (nr_updated)
 		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
 

index bf38dfbbb4b4..ae9caa4c6562 100644
@@ -37,12 +37,14 @@
 
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa)
+		unsigned long cp_flags)
 {
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
 	unsigned long pages = 0;
 	int target_node = NUMA_NO_NODE;
+	bool dirty_accountable = cp_flags & MM_CP_DIRTY_ACCT;
+	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
 
 	/*
 	 * Can be called with only the mmap_sem for reading by

@@ -163,7 +165,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pud_t *pud, unsigned long addr, unsigned long end,
-		pgprot_t newprot, int dirty_accountable, int prot_numa)
+		pgprot_t newprot, unsigned long cp_flags)
 {
 	pmd_t *pmd;
 	unsigned long next;

@@ -195,7 +197,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 				__split_huge_pmd(vma, pmd, addr, false, NULL);
 			} else {
 				int nr_ptes = change_huge_pmd(vma, pmd, addr,
-						newprot, prot_numa);
+							      newprot, cp_flags);
 
 				if (nr_ptes) {
 					if (nr_ptes == HPAGE_PMD_NR) {

@@ -210,7 +212,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			/* fall through, the trans huge pmd just split */
 		}
 		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
-				 dirty_accountable, prot_numa);
+					      cp_flags);
 		pages += this_pages;
 next:
 		cond_resched();

@@ -226,7 +228,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 
 static inline unsigned long change_pud_range(struct vm_area_struct *vma,
 		p4d_t *p4d, unsigned long addr, unsigned long end,
-		pgprot_t newprot, int dirty_accountable, int prot_numa)
+		pgprot_t newprot, unsigned long cp_flags)
 {
 	pud_t *pud;
 	unsigned long next;

@@ -238,7 +240,7 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
 		if (pud_none_or_clear_bad(pud))
 			continue;
 		pages += change_pmd_range(vma, pud, addr, next, newprot,
-				 dirty_accountable, prot_numa);
+					  cp_flags);
 	} while (pud++, addr = next, addr != end);
 
 	return pages;

@@ -246,7 +248,7 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
 
 static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
 		pgd_t *pgd, unsigned long addr, unsigned long end,
-		pgprot_t newprot, int dirty_accountable, int prot_numa)
+		pgprot_t newprot, unsigned long cp_flags)
 {
 	p4d_t *p4d;
 	unsigned long next;

@@ -258,7 +260,7 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
 		if (p4d_none_or_clear_bad(p4d))
 			continue;
 		pages += change_pud_range(vma, p4d, addr, next, newprot,
-				 dirty_accountable, prot_numa);
+					  cp_flags);
 	} while (p4d++, addr = next, addr != end);
 
 	return pages;

@@ -266,7 +268,7 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
 
 static unsigned long change_protection_range(struct vm_area_struct *vma,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa)
+		unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;

@@ -283,7 +285,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
 		pages += change_p4d_range(vma, pgd, addr, next, newprot,
-				 dirty_accountable, prot_numa);
+					  cp_flags);
 	} while (pgd++, addr = next, addr != end);
 
 	/* Only flush the TLB if we actually modified any entries: */

@@ -296,14 +298,15 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 
 unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 		       unsigned long end, pgprot_t newprot,
-		       int dirty_accountable, int prot_numa)
+		       unsigned long cp_flags)
 {
 	unsigned long pages;
 
 	if (is_vm_hugetlb_page(vma))
 		pages = hugetlb_change_protection(vma, start, end, newprot);
 	else
-		pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa);
+		pages = change_protection_range(vma, start, end, newprot,
+						cp_flags);
 
 	return pages;
 }

@@ -431,7 +434,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	vma_set_page_prot(vma);
 
 	change_protection(vma, start, end, vma->vm_page_prot,
-			  dirty_accountable, 0);
+			  dirty_accountable ? MM_CP_DIRTY_ACCT : 0);
 
 	/*
 	 * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major

index a93ac1c37940..beca76650271 100644
@@ -1719,6 +1719,11 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 #define  MM_CP_DIRTY_ACCT                  (1UL << 0)
 /* Whether this protection change is for NUMA hints */
 #define  MM_CP_PROT_NUMA                   (1UL << 1)
+/* Whether this change is for write protecting */
+#define  MM_CP_UFFD_WP                     (1UL << 2) /* do wp */
+#define  MM_CP_UFFD_WP_RESOLVE             (1UL << 3) /* Resolve wp */
+#define  MM_CP_UFFD_WP_ALL                 (MM_CP_UFFD_WP | \
+					    MM_CP_UFFD_WP_RESOLVE)
 
 extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 			      unsigned long end, pgprot_t newprot,

index b7149a0acac1..3fda79f6746b 100644
@@ -1911,6 +1911,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	bool preserve_write;
 	int ret;
 	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
+	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
+	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 
 	ptl = __pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)

@@ -1977,6 +1979,17 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	entry = pmd_modify(entry, newprot);
 	if (preserve_write)
 		entry = pmd_mk_savedwrite(entry);
+	if (uffd_wp) {
+		entry = pmd_wrprotect(entry);
+		entry = pmd_mkuffd_wp(entry);
+	} else if (uffd_wp_resolve) {
+		/*
+		 * Leave the write bit to be handled by PF interrupt
+		 * handler, then things like COW could be properly
+		 * handled.
+		 */
+		entry = pmd_clear_uffd_wp(entry);
+	}
 	ret = HPAGE_PMD_NR;
 	set_pmd_at(mm, addr, pmd, entry);
 	BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry));

@@ -2125,7 +2138,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	struct page *page;
 	pgtable_t pgtable;
 	pmd_t old_pmd, _pmd;
-	bool young, write, soft_dirty, pmd_migration = false;
+	bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false;
 	unsigned long addr;
 	int i;
 

@@ -2207,6 +2220,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		write = pmd_write(old_pmd);
 		young = pmd_young(old_pmd);
 		soft_dirty = pmd_soft_dirty(old_pmd);
+		uffd_wp = pmd_uffd_wp(old_pmd);
 	}
 	VM_BUG_ON_PAGE(!page_count(page), page);
 	page_ref_add(page, HPAGE_PMD_NR - 1);

@@ -2240,6 +2254,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 				entry = pte_mkold(entry);
 			if (soft_dirty)
 				entry = pte_mksoft_dirty(entry);
+			if (uffd_wp)
+				entry = pte_mkuffd_wp(entry);
 		}
 		pte = pte_offset_map(&_pmd, addr);
 		BUG_ON(!pte_none(*pte));

index 05bcd741855b..d79e6d1f8c62 100644
@@ -2579,7 +2579,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 
-	if (userfaultfd_wp(vma)) {
+	if (userfaultfd_pte_wp(vma, *vmf->pte)) {
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		return handle_userfault(vmf, VM_UFFD_WP);
 	}

@@ -3800,7 +3800,7 @@ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
 static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 {
 	if (vma_is_anonymous(vmf->vma)) {
-		if (userfaultfd_wp(vmf->vma))
+		if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd))
 			return handle_userfault(vmf, VM_UFFD_WP);
 		return do_huge_pmd_wp_page(vmf, orig_pmd);
 	}

index ae9caa4c6562..c7066d7384e3 100644
@@ -45,6 +45,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	int target_node = NUMA_NO_NODE;
 	bool dirty_accountable = cp_flags & MM_CP_DIRTY_ACCT;
 	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
+	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
+	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 
 	/*
 	 * Can be called with only the mmap_sem for reading by

@@ -116,6 +118,19 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			if (preserve_write)
 				ptent = pte_mk_savedwrite(ptent);
 
+			if (uffd_wp) {
+				ptent = pte_wrprotect(ptent);
+				ptent = pte_mkuffd_wp(ptent);
+			} else if (uffd_wp_resolve) {
+				/*
+				 * Leave the write bit to be handled
+				 * by PF interrupt handler, then
+				 * things like COW could be properly
+				 * handled.
+				 */
+				ptent = pte_clear_uffd_wp(ptent);
+			}
+
 			/* Avoid taking write faults for known dirty pages */
 			if (dirty_accountable && pte_dirty(ptent) &&
 					(pte_soft_dirty(ptent) ||

@@ -302,6 +317,8 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 {
 	unsigned long pages;
 
+	BUG_ON((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL);
+
 	if (is_vm_hugetlb_page(vma))
 		pages = hugetlb_change_protection(vma, start, end, newprot);
 	else

index c8e7846e9b7e..5363376cb07a 100644
@@ -73,8 +73,12 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 		goto out_release;
 
 	_dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot));
-	if ((dst_vma->vm_flags & VM_WRITE) && !wp_copy)
-		_dst_pte = pte_mkwrite(_dst_pte);
+	if (dst_vma->vm_flags & VM_WRITE) {
+		if (wp_copy)
+			_dst_pte = pte_mkuffd_wp(_dst_pte);
+		else
+			_dst_pte = pte_mkwrite(_dst_pte);
+	}
 
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
 	if (dst_vma->vm_file) {

index 3fda79f6746b..757975920df8 100644
@@ -980,6 +980,14 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	ret = -EAGAIN;
 	pmd = *src_pmd;
 
+	/*
+	 * Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA
+	 * does not have the VM_UFFD_WP, which means that the uffd
+	 * fork event is not enabled.
+	 */
+	if (!(vma->vm_flags & VM_UFFD_WP))
+		pmd = pmd_clear_uffd_wp(pmd);
+
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
 	if (unlikely(is_swap_pmd(pmd))) {
 		swp_entry_t entry = pmd_to_swp_entry(pmd);

index d79e6d1f8c62..8c69257d6ef1 100644
@@ -790,6 +790,14 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		pte = pte_mkclean(pte);
 	pte = pte_mkold(pte);
 
+	/*
+	 * Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA
+	 * does not have the VM_UFFD_WP, which means that the uffd
+	 * fork event is not enabled.
+	 */
+	if (!(vm_flags & VM_UFFD_WP))
+		pte = pte_clear_uffd_wp(pte);
+
 	page = vm_normal_page(vma, addr, pte);
 	if (page) {
 		get_page(page);

index 5b254b851082..0120fa671914 100644
@@ -1421,6 +1421,21 @@ static inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
 {
 	return pte_clear_flags(pte, _PAGE_SWP_UFFD_WP);
 }
+
+static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd)
+{
+	return pmd_set_flags(pmd, _PAGE_SWP_UFFD_WP);
+}
+
+static inline int pmd_swp_uffd_wp(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_SWP_UFFD_WP;
+}
+
+static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd)
+{
+	return pmd_clear_flags(pmd, _PAGE_SWP_UFFD_WP);
+}
 #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
 
 #define PKRU_AD_BIT 0x1

index 643d1bf559c2..828966d4c281 100644
@@ -46,6 +46,21 @@ static __always_inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
 {
 	return pte;
 }
+
+static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd)
+{
+	return pmd;
+}
+
+static inline int pmd_swp_uffd_wp(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd)
+{
+	return pmd;
+}
 #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
 
 #endif /* _ASM_GENERIC_PGTABLE_UFFD_H */

index 4d961668e5fc..0c2923b1cdb7 100644
@@ -68,6 +68,8 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte)
 
 	if (pte_swp_soft_dirty(pte))
 		pte = pte_swp_clear_soft_dirty(pte);
+	if (pte_swp_uffd_wp(pte))
+		pte = pte_swp_clear_uffd_wp(pte);
 	arch_entry = __pte_to_swp_entry(pte);
 	return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
 }

index 757975920df8..eae25c58db9d 100644
@@ -2221,6 +2221,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		write = is_write_migration_entry(entry);
 		young = false;
 		soft_dirty = pmd_swp_soft_dirty(old_pmd);
+		uffd_wp = pmd_swp_uffd_wp(old_pmd);
 	} else {
 		page = pmd_page(old_pmd);
 		if (pmd_dirty(old_pmd))

@@ -2253,6 +2254,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			entry = swp_entry_to_pte(swp_entry);
 			if (soft_dirty)
 				entry = pte_swp_mksoft_dirty(entry);
+			if (uffd_wp)
+				entry = pte_swp_mkuffd_wp(entry);
 		} else {
 			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
 			entry = maybe_mkwrite(entry, vma);

index 8c69257d6ef1..28e9342d00cc 100644
@@ -738,6 +738,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 				pte = swp_entry_to_pte(entry);
 				if (pte_swp_soft_dirty(*src_pte))
 					pte = pte_swp_mksoft_dirty(pte);
+				if (pte_swp_uffd_wp(*src_pte))
+					pte = pte_swp_mkuffd_wp(pte);
 				set_pte_at(src_mm, addr, src_pte, pte);
 			}
 		} else if (is_device_private_entry(entry)) {

@@ -767,6 +769,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			    is_cow_mapping(vm_flags)) {
 				make_device_private_entry_read(&entry);
 				pte = swp_entry_to_pte(entry);
+				if (pte_swp_uffd_wp(*src_pte))
+					pte = pte_swp_mkuffd_wp(pte);
 				set_pte_at(src_mm, addr, src_pte, pte);
 			}
 		}

@@ -2930,6 +2934,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	flush_icache_page(vma, page);
 	if (pte_swp_soft_dirty(vmf->orig_pte))
 		pte = pte_mksoft_dirty(pte);
+	if (pte_swp_uffd_wp(vmf->orig_pte)) {
+		pte = pte_mkuffd_wp(pte);
+		pte = pte_wrprotect(pte);
+	}
 	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
 	arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte);
 	vmf->orig_pte = pte;

index f2ecc2855a12..d8f1f6d13960 100644
@@ -241,11 +241,15 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		entry = pte_to_swp_entry(*pvmw.pte);
 		if (is_write_migration_entry(entry))
 			pte = maybe_mkwrite(pte, vma);
+		else if (pte_swp_uffd_wp(*pvmw.pte))
+			pte = pte_mkuffd_wp(pte);
 
 		if (unlikely(is_zone_device_page(new))) {
 			if (is_device_private_page(new)) {
 				entry = make_device_private_entry(new, pte_write(pte));
 				pte = swp_entry_to_pte(entry);
+				if (pte_swp_uffd_wp(*pvmw.pte))
+					pte = pte_mkuffd_wp(pte);
 			} else if (is_device_public_page(new)) {
 				pte = pte_mkdevmap(pte);
 			}

@@ -2306,6 +2310,8 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_soft_dirty(pte))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
+			if (pte_uffd_wp(pte))
+				swp_pte = pte_swp_mkuffd_wp(swp_pte);
 			set_pte_at(mm, addr, ptep, swp_pte);
 
 			/*

index c7066d7384e3..a63737d9884e 100644
@@ -139,11 +139,11 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			}
 			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
 			pages++;
-		} else if (IS_ENABLED(CONFIG_MIGRATION)) {
+		} else if (is_swap_pte(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
+			pte_t newpte;
 
 			if (is_write_migration_entry(entry)) {
-				pte_t newpte;
 				/*
 				 * A protection check is difficult so
 				 * just be safe and disable write

@@ -152,22 +152,28 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				newpte = swp_entry_to_pte(entry);
 				if (pte_swp_soft_dirty(oldpte))
 					newpte = pte_swp_mksoft_dirty(newpte);
-				set_pte_at(vma->vm_mm, addr, pte, newpte);
-
-				pages++;
-			}
-
-			if (is_write_device_private_entry(entry)) {
-				pte_t newpte;
-
+				if (pte_swp_uffd_wp(oldpte))
+					newpte = pte_swp_mkuffd_wp(newpte);
+			} else if (is_write_device_private_entry(entry)) {
 				/*
 				 * We do not preserve soft-dirtiness. See
 				 * copy_one_pte() for explanation.
 				 */
 				make_device_private_entry_read(&entry);
 				newpte = swp_entry_to_pte(entry);
-				set_pte_at(vma->vm_mm, addr, pte, newpte);
+				if (pte_swp_uffd_wp(oldpte))
+					newpte = pte_swp_mkuffd_wp(newpte);
+			} else {
+				newpte = oldpte;
+			}
 
+			if (uffd_wp)
+				newpte = pte_swp_mkuffd_wp(newpte);
+			else if (uffd_wp_resolve)
+				newpte = pte_swp_clear_uffd_wp(newpte);
+
+			if (!pte_same(oldpte, newpte)) {
+				set_pte_at(vma->vm_mm, addr, pte, newpte);
 				pages++;
 			}
 		}

index e5dfe2ae6b0d..dedde54dadb7 100644
@@ -1471,6 +1471,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
+			if (pte_uffd_wp(pteval))
+				swp_pte = pte_swp_mkuffd_wp(swp_pte);
 			set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
 			/*
 			 * No need to invalidate here it will synchronize on

@@ -1563,6 +1565,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
+			if (pte_uffd_wp(pteval))
+				swp_pte = pte_swp_mkuffd_wp(swp_pte);
 			set_pte_at(mm, address, pvmw.pte, swp_pte);
 			/*
 			 * No need to invalidate here it will synchronize on

@@ -1629,6 +1633,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
+			if (pte_uffd_wp(pteval))
+				swp_pte = pte_swp_mkuffd_wp(swp_pte);
 			set_pte_at(mm, address, pvmw.pte, swp_pte);
 			/* Invalidate as we cleared the pte */
 			mmu_notifier_invalidate_range(mm, address,

index dd4db334bd63..2d7bad9cb976 100644
@@ -13,6 +13,7 @@
 	EM( SCAN_PMD_NULL,		"pmd_null")			\
 	EM( SCAN_EXCEED_NONE_PTE,	"exceed_none_pte")		\
 	EM( SCAN_PTE_NON_PRESENT,	"pte_non_present")		\
+	EM( SCAN_PTE_UFFD_WP,		"pte_uffd_wp")			\
 	EM( SCAN_PAGE_RO,		"no_writable_page")		\
 	EM( SCAN_LACK_REFERENCED_PAGE,	"lack_referenced_page")		\
 	EM( SCAN_PAGE_NULL,		"page_null")			\

index 0f7419938008..fc40aa214be7 100644
@@ -29,6 +29,7 @@ enum scan_result {
 	SCAN_PMD_NULL,
 	SCAN_EXCEED_NONE_PTE,
 	SCAN_PTE_NON_PRESENT,
+	SCAN_PTE_UFFD_WP,
 	SCAN_PAGE_RO,
 	SCAN_LACK_REFERENCED_PAGE,
 	SCAN_PAGE_NULL,

@@ -1128,6 +1129,15 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		pte_t pteval = *_pte;
 		if (is_swap_pte(pteval)) {
 			if (++unmapped <= khugepaged_max_ptes_swap) {
+				/*
+				 * Always be strict with uffd-wp
+				 * enabled swap entries.  Please see
+				 * comment below for pte_uffd_wp().
+				 */
+				if (pte_swp_uffd_wp(pteval)) {
+					result = SCAN_PTE_UFFD_WP;
+					goto out_unmap;
+				}
 				continue;
 			} else {
 				result = SCAN_EXCEED_SWAP_PTE;

@@ -1147,6 +1157,19 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 			result = SCAN_PTE_NON_PRESENT;
 			goto out_unmap;
 		}
+		if (pte_uffd_wp(pteval)) {
+			/*
+			 * Don't collapse the page if any of the small
+			 * PTEs are armed with uffd write protection.
+			 * Here we can also mark the new huge pmd as
+			 * write protected if any of the small ones is
+			 * marked but that could bring uknown
+			 * userfault messages that falls outside of
+			 * the registered range.  So, just be simple.
+			 */
+			result = SCAN_PTE_UFFD_WP;
+			goto out_unmap;
+		}
 		if (pte_write(pteval))
 			writable = true;
 

index 5363376cb07a..6b9dd5b66f64 100644
@@ -20,6 +20,34 @@
 #include <asm/tlbflush.h>
 #include "internal.h"
 
+/*
+ * Find a valid userfault enabled VMA region that covers the whole
+ * address range, or NULL on failure.  Must be called with mmap_sem
+ * held.
+ */
+static struct vm_area_struct *vma_find_uffd(struct mm_struct *mm,
+					    unsigned long start,
+					    unsigned long len)
+{
+	struct vm_area_struct *vma = find_vma(mm, start);
+
+	if (!vma)
+		return NULL;
+
+	/*
+	 * Check the vma is registered in uffd, this is required to
+	 * enforce the VM_MAYWRITE check done at uffd registration
+	 * time.
+	 */
+	if (!vma->vm_userfaultfd_ctx.ctx)
+		return NULL;
+
+	if (start < vma->vm_start || start + len > vma->vm_end)
+		return NULL;
+
+	return vma;
+}
+
 static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 			    pmd_t *dst_pmd,
 			    struct vm_area_struct *dst_vma,

@@ -228,20 +256,9 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 	 */
 	if (!dst_vma) {
 		err = -ENOENT;
-		dst_vma = find_vma(dst_mm, dst_start);
+		dst_vma = vma_find_uffd(dst_mm, dst_start, len);
 		if (!dst_vma || !is_vm_hugetlb_page(dst_vma))
 			goto out_unlock;
-		/*
-		 * Check the vma is registered in uffd, this is
-		 * required to enforce the VM_MAYWRITE check done at
-		 * uffd registration time.
-		 */
-		if (!dst_vma->vm_userfaultfd_ctx.ctx)
-			goto out_unlock;
-
-		if (dst_start < dst_vma->vm_start ||
-		    dst_start + len > dst_vma->vm_end)
-			goto out_unlock;
 
 		err = -EINVAL;
 		if (vma_hpagesize != vma_kernel_pagesize(dst_vma))

@@ -487,20 +504,9 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 	 * both valid and fully within a single existing vma.
 	 */
 	err = -ENOENT;
-	dst_vma = find_vma(dst_mm, dst_start);
+	dst_vma = vma_find_uffd(dst_mm, dst_start, len);
 	if (!dst_vma)
 		goto out_unlock;
-	/*
-	 * Check the vma is registered in uffd, this is required to
-	 * enforce the VM_MAYWRITE check done at uffd registration
-	 * time.
-	 */
-	if (!dst_vma->vm_userfaultfd_ctx.ctx)
-		goto out_unlock;
-
-	if (dst_start < dst_vma->vm_start ||
-	    dst_start + len > dst_vma->vm_end)
-		goto out_unlock;
 
 	err = -EINVAL;
 	/*

index dcd33172b728..a8e5f3ea9bb2 100644
@@ -41,6 +41,9 @@ extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
 			      unsigned long dst_start,
 			      unsigned long len,
 			      bool *mmap_changing);
+extern int mwriteprotect_range(struct mm_struct *dst_mm,
+			       unsigned long start, unsigned long len,
+			       bool enable_wp, bool *mmap_changing);
 
 /* mm helpers */
 static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,

57 lines not on this page · raw message

index c594945ad5bf..3cf19aeaa0e0 100644
@@ -306,8 +306,11 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 	if (!pmd_present(_pmd))
 		goto out;
 
-	if (pmd_trans_huge(_pmd))
+	if (pmd_trans_huge(_pmd)) {
+		if (!pmd_write(_pmd) && (reason & VM_UFFD_WP))
+			ret = true;
 		goto out;
+	}
 
 	/*
 	 * the pmd is stable (as in !pmd_trans_unstable) so we can re-read it

@@ -320,6 +323,8 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 	 */
 	if (pte_none(*pte))
 		ret = true;
+	if (!pte_write(*pte) && (reason & VM_UFFD_WP))
+		ret = true;
 	pte_unmap(pte);
 
 out:

@@ -1258,10 +1263,13 @@ static __always_inline int validate_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline bool vma_can_userfault(struct vm_area_struct *vma)
+static inline bool vma_can_userfault(struct vm_area_struct *vma,
+				     unsigned long vm_flags)
 {
-	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
-		vma_is_shmem(vma);
+	/* 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));
 }
 
 static int userfaultfd_register(struct userfaultfd_ctx *ctx,

@@ -1293,15 +1301,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	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)
 		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);

@@ -1351,7 +1352,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 
 		/* check not compatible vmas */
 		ret = -EINVAL;
-		if (!vma_can_userfault(cur))
+		if (!vma_can_userfault(cur, vm_flags))
 			goto out_unlock;
 
 		/*

@@ -1379,6 +1380,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 			if (end & (vma_hpagesize - 1))
 				goto out_unlock;
 		}
+		if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE))
+			goto out_unlock;
 
 		/*
 		 * Check that this vma isn't already owned by a

@@ -1408,7 +1411,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	do {
 		cond_resched();
 
-		BUG_ON(!vma_can_userfault(vma));
+		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));

@@ -1545,7 +1548,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		 * provides for more strict behavior to notice
 		 * unregistration errors.
 		 */
-		if (!vma_can_userfault(cur))
+		if (!vma_can_userfault(cur, cur->vm_flags))
 			goto out_unlock;
 
 		found = true;

@@ -1559,7 +1562,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	do {
 		cond_resched();
 
-		BUG_ON(!vma_can_userfault(vma));
+		BUG_ON(!vma_can_userfault(vma, vma->vm_flags));
 
 		/*
 		 * Nothing to do: this vma is already registered into this

@@ -1772,6 +1775,50 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 	return ret;
 }
 
+static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
+				    unsigned long arg)
+{
+	int ret;
+	struct uffdio_writeprotect uffdio_wp;
+	struct uffdio_writeprotect __user *user_uffdio_wp;
+	struct userfaultfd_wake_range range;
+
+	if (READ_ONCE(ctx->mmap_changing))
+		return -EAGAIN;
+
+	user_uffdio_wp = (struct uffdio_writeprotect __user *) arg;
+
+	if (copy_from_user(&uffdio_wp, user_uffdio_wp,
+			   sizeof(struct uffdio_writeprotect)))
+		return -EFAULT;
+
+	ret = validate_range(ctx->mm, uffdio_wp.range.start,
+			     uffdio_wp.range.len);
+	if (ret)
+		return ret;
+
+	if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE |
+			       UFFDIO_WRITEPROTECT_MODE_WP))
+		return -EINVAL;
+	if ((uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP) &&
+	     (uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE))
+		return -EINVAL;
+
+	ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
+				  uffdio_wp.range.len, uffdio_wp.mode &
+				  UFFDIO_WRITEPROTECT_MODE_WP,
+				  &ctx->mmap_changing);
+	if (ret)
+		return ret;
+
+	if (!(uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE)) {
+		range.start = uffdio_wp.range.start;
+		range.len = uffdio_wp.range.len;
+		wake_userfault(ctx, &range);
+	}
+	return ret;
+}
+
 static inline unsigned int uffd_ctx_features(__u64 user_features)
 {
 	/*

@@ -1849,6 +1896,9 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
 	case UFFDIO_ZEROPAGE:
 		ret = userfaultfd_zeropage(ctx, arg);
 		break;
+	case UFFDIO_WRITEPROTECT:
+		ret = userfaultfd_writeprotect(ctx, arg);
+		break;
 	}
 	return ret;
 }

index 340f23bc251d..95c4a160e5f8 100644
@@ -52,6 +52,7 @@
 #define _UFFDIO_WAKE			(0x02)
 #define _UFFDIO_COPY			(0x03)
 #define _UFFDIO_ZEROPAGE		(0x04)
+#define _UFFDIO_WRITEPROTECT		(0x06)
 #define _UFFDIO_API			(0x3F)
 
 /* userfaultfd ioctl ids */

@@ -68,6 +69,8 @@
 				      struct uffdio_copy)
 #define UFFDIO_ZEROPAGE		_IOWR(UFFDIO, _UFFDIO_ZEROPAGE,	\
 				      struct uffdio_zeropage)
+#define UFFDIO_WRITEPROTECT	_IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \
+				      struct uffdio_writeprotect)
 
 /* read() structure */
 struct uffd_msg {

@@ -232,4 +235,24 @@ struct uffdio_zeropage {
 	__s64 zeropage;
 };
 
+struct uffdio_writeprotect {
+	struct uffdio_range range;
+/*
+ * UFFDIO_WRITEPROTECT_MODE_WP: set the flag to write protect a range,
+ * unset the flag to undo protection of a range which was previously
+ * write protected.
+ *
+ * UFFDIO_WRITEPROTECT_MODE_DONTWAKE: set the flag to avoid waking up
+ * any wait thread after the operation succeeds.
+ *
+ * NOTE: Write protecting a region (WP=1) is unrelated to page faults,
+ * therefore DONTWAKE flag is meaningless with WP=1.  Removing write
+ * protection (WP=0) in response to a page fault wakes the faulting
+ * task unless DONTWAKE is set.
+ */
+#define UFFDIO_WRITEPROTECT_MODE_WP		((__u64)1<<0)
+#define UFFDIO_WRITEPROTECT_MODE_DONTWAKE	((__u64)1<<1)
+	__u64 mode;
+};
+
 #endif /* _LINUX_USERFAULTFD_H */

index 95c4a160e5f8..e7e98bde221f 100644
@@ -19,7 +19,8 @@
  * means the userland is reading).
  */
 #define UFFD_API ((__u64)0xAA)
-#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK |		\
+#define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP |	\
+			   UFFD_FEATURE_EVENT_FORK |		\
 			   UFFD_FEATURE_EVENT_REMAP |		\
 			   UFFD_FEATURE_EVENT_REMOVE |	\
 			   UFFD_FEATURE_EVENT_UNMAP |		\

@@ -34,7 +35,8 @@
 #define UFFD_API_RANGE_IOCTLS			\
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY |		\
-	 (__u64)1 << _UFFDIO_ZEROPAGE)
+	 (__u64)1 << _UFFDIO_ZEROPAGE |		\
+	 (__u64)1 << _UFFDIO_WRITEPROTECT)
 #define UFFD_API_RANGE_IOCTLS_BASIC		\
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY)

index 3cf19aeaa0e0..498971fa9163 100644
@@ -1782,6 +1782,7 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
 	struct uffdio_writeprotect uffdio_wp;
 	struct uffdio_writeprotect __user *user_uffdio_wp;
 	struct userfaultfd_wake_range range;
+	bool mode_wp, mode_dontwake;
 
 	if (READ_ONCE(ctx->mmap_changing))
 		return -EAGAIN;

@@ -1800,18 +1801,20 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
 	if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE |
 			       UFFDIO_WRITEPROTECT_MODE_WP))
 		return -EINVAL;
-	if ((uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP) &&
-	     (uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE))
+
+	mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP;
+	mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE;
+
+	if (mode_wp && mode_dontwake)
 		return -EINVAL;
 
 	ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
-				  uffdio_wp.range.len, uffdio_wp.mode &
-				  UFFDIO_WRITEPROTECT_MODE_WP,
+				  uffdio_wp.range.len, mode_wp,
 				  &ctx->mmap_changing);
 	if (ret)
 		return ret;
 
-	if (!(uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE)) {
+	if (!mode_wp && !mode_dontwake) {
 		range.start = uffdio_wp.range.start;
 		range.len = uffdio_wp.range.len;
 		wake_userfault(ctx, &range);

index 498971fa9163..4e1d7748224a 100644
@@ -1465,14 +1465,24 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	up_write(&mm->mmap_sem);
 	mmput(mm);
 	if (!ret) {
+		__u64 ioctls_out;
+
+		ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC :
+		    UFFD_API_RANGE_IOCTLS;
+
+		/*
+		 * Declare the WP ioctl only if the WP mode is
+		 * specified and all checks passed with the range
+		 */
+		if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP))
+			ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT);
+
 		/*
 		 * Now that we scanned all vmas we can already tell
 		 * userland which ioctls methods are guaranteed to
 		 * succeed on this range.
 		 */
-		if (put_user(basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC :
-			     UFFD_API_RANGE_IOCTLS,
-			     &user_uffdio_register->ioctls))
+		if (put_user(ioctls_out, &user_uffdio_register->ioctls))
 			ret = -EFAULT;
 	}
 out:

index b3e6497b080c..417dbdf4d379 100644
@@ -88,6 +88,12 @@ static char *area_src, *area_src_alias, *area_dst, *area_dst_alias;
 static char *zeropage;
 pthread_attr_t attr;
 
+/* Userfaultfd test statistics */
+struct uffd_stats {
+	int cpu;
+	unsigned long missing_faults;
+};
+
 /* pthread_mutex_t starts at page offset 0 */
 #define area_mutex(___area, ___nr)					\
 	((pthread_mutex_t *) ((___area) + (___nr)*page_size))

@@ -127,6 +133,17 @@ static void usage(void)
 	exit(1);
 }
 
+static void uffd_stats_reset(struct uffd_stats *uffd_stats,
+			     unsigned long n_cpus)
+{
+	int i;
+
+	for (i = 0; i < n_cpus; i++) {
+		uffd_stats[i].cpu = i;
+		uffd_stats[i].missing_faults = 0;
+	}
+}
+
 static int anon_release_pages(char *rel_area)
 {
 	int ret = 0;

@@ -469,8 +486,8 @@ static int uffd_read_msg(int ufd, struct uffd_msg *msg)
 	return 0;
 }
 
-/* Return 1 if page fault handled by us; otherwise 0 */
-static int uffd_handle_page_fault(struct uffd_msg *msg)
+static void uffd_handle_page_fault(struct uffd_msg *msg,
+				   struct uffd_stats *stats)
 {
 	unsigned long offset;
 

@@ -485,18 +502,19 @@ static int uffd_handle_page_fault(struct uffd_msg *msg)
 	offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
 	offset &= ~(page_size-1);
 
-	return copy_page(uffd, offset);
+	if (copy_page(uffd, offset))
+		stats->missing_faults++;
 }
 
 static void *uffd_poll_thread(void *arg)
 {
-	unsigned long cpu = (unsigned long) arg;
+	struct uffd_stats *stats = (struct uffd_stats *)arg;
+	unsigned long cpu = stats->cpu;
 	struct pollfd pollfd[2];
 	struct uffd_msg msg;
 	struct uffdio_register uffd_reg;
 	int ret;
 	char tmp_chr;
-	unsigned long userfaults = 0;
 
 	pollfd[0].fd = uffd;
 	pollfd[0].events = POLLIN;

@@ -526,7 +544,7 @@ static void *uffd_poll_thread(void *arg)
 				msg.event), exit(1);
 			break;
 		case UFFD_EVENT_PAGEFAULT:
-			userfaults += uffd_handle_page_fault(&msg);
+			uffd_handle_page_fault(&msg, stats);
 			break;
 		case UFFD_EVENT_FORK:
 			close(uffd);

@@ -545,28 +563,27 @@ static void *uffd_poll_thread(void *arg)
 			break;
 		}
 	}
-	return (void *)userfaults;
+
+	return NULL;
 }
 
 pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER;
 
 static void *uffd_read_thread(void *arg)
 {
-	unsigned long *this_cpu_userfaults;
+	struct uffd_stats *stats = (struct uffd_stats *)arg;
 	struct uffd_msg msg;
 
-	this_cpu_userfaults = (unsigned long *) arg;
-	*this_cpu_userfaults = 0;
-
 	pthread_mutex_unlock(&uffd_read_mutex);
 	/* from here cancellation is ok */
 
 	for (;;) {
 		if (uffd_read_msg(uffd, &msg))
 			continue;
-		(*this_cpu_userfaults) += uffd_handle_page_fault(&msg);
+		uffd_handle_page_fault(&msg, stats);
 	}
-	return (void *)NULL;
+
+	return NULL;
 }
 
 static void *background_thread(void *arg)

@@ -582,13 +599,12 @@ static void *background_thread(void *arg)
 	return NULL;
 }
 
-static int stress(unsigned long *userfaults)
+static int stress(struct uffd_stats *uffd_stats)
 {
 	unsigned long cpu;
 	pthread_t locking_threads[nr_cpus];
 	pthread_t uffd_threads[nr_cpus];
 	pthread_t background_threads[nr_cpus];
-	void **_userfaults = (void **) userfaults;
 
 	finished = 0;
 	for (cpu = 0; cpu < nr_cpus; cpu++) {

@@ -597,12 +613,13 @@ static int stress(unsigned long *userfaults)
 			return 1;
 		if (bounces & BOUNCE_POLL) {
 			if (pthread_create(&uffd_threads[cpu], &attr,
-					   uffd_poll_thread, (void *)cpu))
+					   uffd_poll_thread,
+					   (void *)&uffd_stats[cpu]))
 				return 1;
 		} else {
 			if (pthread_create(&uffd_threads[cpu], &attr,
 					   uffd_read_thread,
-					   &_userfaults[cpu]))
+					   (void *)&uffd_stats[cpu]))
 				return 1;
 			pthread_mutex_lock(&uffd_read_mutex);
 		}

@@ -639,7 +656,8 @@ static int stress(unsigned long *userfaults)
 				fprintf(stderr, "pipefd write error\n");
 				return 1;
 			}
-			if (pthread_join(uffd_threads[cpu], &_userfaults[cpu]))
+			if (pthread_join(uffd_threads[cpu],
+					 (void *)&uffd_stats[cpu]))
 				return 1;
 		} else {
 			if (pthread_cancel(uffd_threads[cpu]))

@@ -910,11 +928,11 @@ static int userfaultfd_events_test(void)
 {
 	struct uffdio_register uffdio_register;
 	unsigned long expected_ioctls;
-	unsigned long userfaults;
 	pthread_t uffd_mon;
 	int err, features;
 	pid_t pid;
 	char c;
+	struct uffd_stats stats = { 0 };
 
 	printf("testing events (fork, remap, remove): ");
 	fflush(stdout);

@@ -941,7 +959,7 @@ static int userfaultfd_events_test(void)
 			"unexpected missing ioctl for anon memory\n"),
 			exit(1);
 
-	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL))
+	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
 		perror("uffd_poll_thread create"), exit(1);
 
 	pid = fork();

@@ -957,13 +975,13 @@ static int userfaultfd_events_test(void)
 
 	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
 		perror("pipe write"), exit(1);
-	if (pthread_join(uffd_mon, (void **)&userfaults))
+	if (pthread_join(uffd_mon, NULL))
 		return 1;
 
 	close(uffd);
-	printf("userfaults: %ld\n", userfaults);
+	printf("userfaults: %ld\n", stats.missing_faults);
 
-	return userfaults != nr_pages;
+	return stats.missing_faults != nr_pages;
 }
 
 static int userfaultfd_sig_test(void)

@@ -975,6 +993,7 @@ static int userfaultfd_sig_test(void)
 	int err, features;
 	pid_t pid;
 	char c;
+	struct uffd_stats stats = { 0 };
 
 	printf("testing signal delivery: ");
 	fflush(stdout);

@@ -1006,7 +1025,7 @@ static int userfaultfd_sig_test(void)
 	if (uffd_test_ops->release_pages(area_dst))
 		return 1;
 
-	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL))
+	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
 		perror("uffd_poll_thread create"), exit(1);
 
 	pid = fork();

@@ -1032,6 +1051,7 @@ static int userfaultfd_sig_test(void)
 	close(uffd);
 	return userfaults != 0;
 }
+
 static int userfaultfd_stress(void)
 {
 	void *area;

@@ -1040,7 +1060,7 @@ static int userfaultfd_stress(void)
 	struct uffdio_register uffdio_register;
 	unsigned long cpu;
 	int err;
-	unsigned long userfaults[nr_cpus];
+	struct uffd_stats uffd_stats[nr_cpus];
 
 	uffd_test_ops->allocate_area((void **)&area_src);
 	if (!area_src)

@@ -1169,8 +1189,10 @@ static int userfaultfd_stress(void)
 		if (uffd_test_ops->release_pages(area_dst))
 			return 1;
 
+		uffd_stats_reset(uffd_stats, nr_cpus);
+
 		/* bounce pass */
-		if (stress(userfaults))
+		if (stress(uffd_stats))
 			return 1;
 
 		/* unregister */

@@ -1213,7 +1235,7 @@ static int userfaultfd_stress(void)
 
 		printf("userfaults:");
 		for (cpu = 0; cpu < nr_cpus; cpu++)
-			printf(" %lu", userfaults[cpu]);
+			printf(" %lu", uffd_stats[cpu].missing_faults);
 		printf("\n");
 	}
 

index 417dbdf4d379..fa362fe311e3 100644
@@ -56,6 +56,7 @@
 #include <linux/userfaultfd.h>
 #include <setjmp.h>
 #include <stdbool.h>
+#include <assert.h>
 
 #include "../kselftest.h"
 

@@ -78,6 +79,8 @@ static int test_type;
 #define ALARM_INTERVAL_SECS 10
 static volatile bool test_uffdio_copy_eexist = true;
 static volatile bool test_uffdio_zeropage_eexist = true;
+/* Whether to test uffd write-protection */
+static bool test_uffdio_wp = false;
 
 static bool map_shared;
 static int huge_fd;

@@ -92,6 +95,7 @@ pthread_attr_t attr;
 struct uffd_stats {
 	int cpu;
 	unsigned long missing_faults;
+	unsigned long wp_faults;
 };
 
 /* pthread_mutex_t starts at page offset 0 */

@@ -141,9 +145,29 @@ static void uffd_stats_reset(struct uffd_stats *uffd_stats,
 	for (i = 0; i < n_cpus; i++) {
 		uffd_stats[i].cpu = i;
 		uffd_stats[i].missing_faults = 0;
+		uffd_stats[i].wp_faults = 0;
 	}
 }
 
+static void uffd_stats_report(struct uffd_stats *stats, int n_cpus)
+{
+	int i;
+	unsigned long long miss_total = 0, wp_total = 0;
+
+	for (i = 0; i < n_cpus; i++) {
+		miss_total += stats[i].missing_faults;
+		wp_total += stats[i].wp_faults;
+	}
+
+	printf("userfaults: %llu missing (", miss_total);
+	for (i = 0; i < n_cpus; i++)
+		printf("%lu+", stats[i].missing_faults);
+	printf("\b), %llu wp (", wp_total);
+	for (i = 0; i < n_cpus; i++)
+		printf("%lu+", stats[i].wp_faults);
+	printf("\b)\n");
+}
+
 static int anon_release_pages(char *rel_area)
 {
 	int ret = 0;

@@ -264,10 +288,15 @@ struct uffd_test_ops {
 	void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset);
 };
 
-#define ANON_EXPECTED_IOCTLS		((1 << _UFFDIO_WAKE) | \
+#define SHMEM_EXPECTED_IOCTLS		((1 << _UFFDIO_WAKE) | \
 					 (1 << _UFFDIO_COPY) | \
 					 (1 << _UFFDIO_ZEROPAGE))
 
+#define ANON_EXPECTED_IOCTLS		((1 << _UFFDIO_WAKE) | \
+					 (1 << _UFFDIO_COPY) | \
+					 (1 << _UFFDIO_ZEROPAGE) | \
+					 (1 << _UFFDIO_WRITEPROTECT))
+
 static struct uffd_test_ops anon_uffd_test_ops = {
 	.expected_ioctls = ANON_EXPECTED_IOCTLS,
 	.allocate_area	= anon_allocate_area,