These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

1 files changed, 156 insertions, 128 deletions

diff --git a/kernel/mm/mmap.c b/kernel/mm/mmap.c
index bb50cacc3..455772a05 100644
--- a/kernel/mm/mmap.c
+++ b/kernel/mm/mmap.c
@@ -41,6 +41,7 @@
 #include <linux/notifier.h>
 #include <linux/memory.h>
 #include <linux/printk.h>
+#include <linux/userfaultfd_k.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -440,12 +441,16 @@ static void validate_mm(struct mm_struct *mm)
 	struct vm_area_struct *vma = mm->mmap;
 
 	while (vma) {
+		struct anon_vma *anon_vma = vma->anon_vma;
 		struct anon_vma_chain *avc;
 
-		vma_lock_anon_vma(vma);
-		list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
-			anon_vma_interval_tree_verify(avc);
-		vma_unlock_anon_vma(vma);
+		if (anon_vma) {
+			anon_vma_lock_read(anon_vma);
+			list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
+				anon_vma_interval_tree_verify(avc);
+			anon_vma_unlock_read(anon_vma);
+		}
+
 		highest_address = vma->vm_end;
 		vma = vma->vm_next;
 		i++;
@@ -919,7 +924,8 @@ again:			remove_next = 1 + (end > next->vm_end);
  * per-vma resources, so we don't attempt to merge those.
  */
 static inline int is_mergeable_vma(struct vm_area_struct *vma,
-			struct file *file, unsigned long vm_flags)
+				struct file *file, unsigned long vm_flags,
+				struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
 	/*
 	 * VM_SOFTDIRTY should not prevent from VMA merging, if we
@@ -935,6 +941,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma,
 		return 0;
 	if (vma->vm_ops && vma->vm_ops->close)
 		return 0;
+	if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx))
+		return 0;
 	return 1;
 }
 
@@ -965,9 +973,11 @@ static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1,
  */
 static int
 can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
-	struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+		     struct anon_vma *anon_vma, struct file *file,
+		     pgoff_t vm_pgoff,
+		     struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
-	if (is_mergeable_vma(vma, file, vm_flags) &&
+	if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
 	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
 		if (vma->vm_pgoff == vm_pgoff)
 			return 1;
@@ -984,9 +994,11 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
  */
 static int
 can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
-	struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+		    struct anon_vma *anon_vma, struct file *file,
+		    pgoff_t vm_pgoff,
+		    struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
-	if (is_mergeable_vma(vma, file, vm_flags) &&
+	if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
 	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
 		pgoff_t vm_pglen;
 		vm_pglen = vma_pages(vma);
@@ -1029,7 +1041,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 			struct vm_area_struct *prev, unsigned long addr,
 			unsigned long end, unsigned long vm_flags,
 			struct anon_vma *anon_vma, struct file *file,
-			pgoff_t pgoff, struct mempolicy *policy)
+			pgoff_t pgoff, struct mempolicy *policy,
+			struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
 	pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
 	struct vm_area_struct *area, *next;
@@ -1056,14 +1069,17 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 	if (prev && prev->vm_end == addr &&
 			mpol_equal(vma_policy(prev), policy) &&
 			can_vma_merge_after(prev, vm_flags,
-						anon_vma, file, pgoff)) {
+					    anon_vma, file, pgoff,
+					    vm_userfaultfd_ctx)) {
 		/*
 		 * OK, it can.  Can we now merge in the successor as well?
 		 */
 		if (next && end == next->vm_start &&
 				mpol_equal(policy, vma_policy(next)) &&
 				can_vma_merge_before(next, vm_flags,
-					anon_vma, file, pgoff+pglen) &&
+						     anon_vma, file,
+						     pgoff+pglen,
+						     vm_userfaultfd_ctx) &&
 				is_mergeable_anon_vma(prev->anon_vma,
 						      next->anon_vma, NULL)) {
 							/* cases 1, 6 */
@@ -1084,7 +1100,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 	if (next && end == next->vm_start &&
 			mpol_equal(policy, vma_policy(next)) &&
 			can_vma_merge_before(next, vm_flags,
-					anon_vma, file, pgoff+pglen)) {
+					     anon_vma, file, pgoff+pglen,
+					     vm_userfaultfd_ctx)) {
 		if (prev && addr < prev->vm_end)	/* case 4 */
 			err = vma_adjust(prev, prev->vm_start,
 				addr, prev->vm_pgoff, NULL);
@@ -1247,17 +1264,18 @@ static inline int mlock_future_check(struct mm_struct *mm,
 /*
  * The caller must hold down_write(&current->mm->mmap_sem).
  */
-
-unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
+unsigned long do_mmap(struct file *file, unsigned long addr,
 			unsigned long len, unsigned long prot,
-			unsigned long flags, unsigned long pgoff,
-			unsigned long *populate)
+			unsigned long flags, vm_flags_t vm_flags,
+			unsigned long pgoff, unsigned long *populate)
 {
 	struct mm_struct *mm = current->mm;
-	vm_flags_t vm_flags;
 
 	*populate = 0;
 
+	if (!len)
+		return -EINVAL;
+
 	/*
 	 * Does the application expect PROT_READ to imply PROT_EXEC?
 	 *
@@ -1265,12 +1283,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	 *  mounted, in which case we dont add PROT_EXEC.)
 	 */
 	if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
-		if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC)))
+		if (!(file && path_noexec(&file->f_path)))
 			prot |= PROT_EXEC;
 
-	if (!len)
-		return -EINVAL;
-
 	if (!(flags & MAP_FIXED))
 		addr = round_hint_to_min(addr);
 
@@ -1291,14 +1306,14 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	 * that it represents a valid section of the address space.
 	 */
 	addr = get_unmapped_area(file, addr, len, pgoff, flags);
-	if (addr & ~PAGE_MASK)
+	if (offset_in_page(addr))
 		return addr;
 
 	/* Do simple checking here so the lower-level routines won't have
 	 * to. we assume access permissions have been handled by the open
 	 * of the memory object, so we don't do any here.
 	 */
-	vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags) |
+	vm_flags |= calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags) |
 			mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
 
 	if (flags & MAP_LOCKED)
@@ -1337,7 +1352,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 		case MAP_PRIVATE:
 			if (!(file->f_mode & FMODE_READ))
 				return -EACCES;
-			if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
+			if (path_noexec(&file->f_path)) {
 				if (vm_flags & VM_EXEC)
 					return -EPERM;
 				vm_flags &= ~VM_MAYEXEC;
@@ -1401,13 +1416,13 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		unsigned long, fd, unsigned long, pgoff)
 {
 	struct file *file = NULL;
-	unsigned long retval = -EBADF;
+	unsigned long retval;
 
 	if (!(flags & MAP_ANONYMOUS)) {
 		audit_mmap_fd(fd, flags);
 		file = fget(fd);
 		if (!file)
-			goto out;
+			return -EBADF;
 		if (is_file_hugepages(file))
 			len = ALIGN(len, huge_page_size(hstate_file(file)));
 		retval = -EINVAL;
@@ -1442,7 +1457,6 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 out_fput:
 	if (file)
 		fput(file);
-out:
 	return retval;
 }
 
@@ -1462,7 +1476,7 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 
 	if (copy_from_user(&a, arg, sizeof(a)))
 		return -EFAULT;
-	if (a.offset & ~PAGE_MASK)
+	if (offset_in_page(a.offset))
 		return -EINVAL;
 
 	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
@@ -1479,13 +1493,14 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 int vma_wants_writenotify(struct vm_area_struct *vma)
 {
 	vm_flags_t vm_flags = vma->vm_flags;
+	const struct vm_operations_struct *vm_ops = vma->vm_ops;
 
 	/* If it was private or non-writable, the write bit is already clear */
 	if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED)))
 		return 0;
 
 	/* The backer wishes to know when pages are first written to? */
-	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
+	if (vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite))
 		return 1;
 
 	/* The open routine did something to the protections that pgprot_modify
@@ -1550,7 +1565,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	}
 
 	/* Clear old maps */
-	error = -ENOMEM;
 	while (find_vma_links(mm, addr, addr + len, &prev, &rb_link,
 			      &rb_parent)) {
 		if (do_munmap(mm, addr, len))
@@ -1570,8 +1584,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	/*
 	 * Can we just expand an old mapping?
 	 */
-	vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff,
-			NULL);
+	vma = vma_merge(mm, prev, addr, addr + len, vm_flags,
+			NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX);
 	if (vma)
 		goto out;
 
@@ -1651,7 +1665,7 @@ out:
 					vma == get_gate_vma(current->mm)))
 			mm->locked_vm += (len >> PAGE_SHIFT);
 		else
-			vma->vm_flags &= ~VM_LOCKED;
+			vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
 	}
 
 	if (file)
@@ -1977,7 +1991,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	 * can happen with large stack limits and large mmap()
 	 * allocations.
 	 */
-	if (addr & ~PAGE_MASK) {
+	if (offset_in_page(addr)) {
 		VM_BUG_ON(addr != -ENOMEM);
 		info.flags = 0;
 		info.low_limit = TASK_UNMAPPED_BASE;
@@ -2013,7 +2027,7 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 
 	if (addr > TASK_SIZE - len)
 		return -ENOMEM;
-	if (addr & ~PAGE_MASK)
+	if (offset_in_page(addr))
 		return -EINVAL;
 
 	addr = arch_rebalance_pgtables(addr, len);
@@ -2035,7 +2049,6 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 		return vma;
 
 	rb_node = mm->mm_rb.rb_node;
-	vma = NULL;
 
 	while (rb_node) {
 		struct vm_area_struct *tmp;
@@ -2127,10 +2140,6 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 	if (security_vm_enough_memory_mm(mm, grow))
 		return -ENOMEM;
 
-	/* Ok, everything looks good - let it rip */
-	if (vma->vm_flags & VM_LOCKED)
-		mm->locked_vm += grow;
-	vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow);
 	return 0;
 }
 
@@ -2141,32 +2150,28 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
  */
 int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 {
-	int error;
+	struct mm_struct *mm = vma->vm_mm;
+	int error = 0;
 
 	if (!(vma->vm_flags & VM_GROWSUP))
 		return -EFAULT;
 
-	/*
-	 * We must make sure the anon_vma is allocated
-	 * so that the anon_vma locking is not a noop.
-	 */
+	/* Guard against wrapping around to address 0. */
+	if (address < PAGE_ALIGN(address+4))
+		address = PAGE_ALIGN(address+4);
+	else
+		return -ENOMEM;
+
+	/* We must make sure the anon_vma is allocated. */
 	if (unlikely(anon_vma_prepare(vma)))
 		return -ENOMEM;
-	vma_lock_anon_vma(vma);
 
 	/*
 	 * vma->vm_start/vm_end cannot change under us because the caller
 	 * is required to hold the mmap_sem in read mode.  We need the
 	 * anon_vma lock to serialize against concurrent expand_stacks.
-	 * Also guard against wrapping around to address 0.
 	 */
-	if (address < PAGE_ALIGN(address+4))
-		address = PAGE_ALIGN(address+4);
-	else {
-		vma_unlock_anon_vma(vma);
-		return -ENOMEM;
-	}
-	error = 0;
+	anon_vma_lock_write(vma->anon_vma);
 
 	/* Somebody else might have raced and expanded it already */
 	if (address > vma->vm_end) {
@@ -2184,29 +2189,33 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 				 * updates, but we only hold a shared mmap_sem
 				 * lock here, so we need to protect against
 				 * concurrent vma expansions.
-				 * vma_lock_anon_vma() doesn't help here, as
+				 * anon_vma_lock_write() doesn't help here, as
 				 * we don't guarantee that all growable vmas
 				 * in a mm share the same root anon vma.
 				 * So, we reuse mm->page_table_lock to guard
 				 * against concurrent vma expansions.
 				 */
-				spin_lock(&vma->vm_mm->page_table_lock);
+				spin_lock(&mm->page_table_lock);
+				if (vma->vm_flags & VM_LOCKED)
+					mm->locked_vm += grow;
+				vm_stat_account(mm, vma->vm_flags,
+						vma->vm_file, grow);
 				anon_vma_interval_tree_pre_update_vma(vma);
 				vma->vm_end = address;
 				anon_vma_interval_tree_post_update_vma(vma);
 				if (vma->vm_next)
 					vma_gap_update(vma->vm_next);
 				else
-					vma->vm_mm->highest_vm_end = address;
-				spin_unlock(&vma->vm_mm->page_table_lock);
+					mm->highest_vm_end = address;
+				spin_unlock(&mm->page_table_lock);
 
 				perf_event_mmap(vma);
 			}
 		}
 	}
-	vma_unlock_anon_vma(vma);
+	anon_vma_unlock_write(vma->anon_vma);
 	khugepaged_enter_vma_merge(vma, vma->vm_flags);
-	validate_mm(vma->vm_mm);
+	validate_mm(mm);
 	return error;
 }
 #endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */
@@ -2217,27 +2226,24 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 int expand_downwards(struct vm_area_struct *vma,
 				   unsigned long address)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	int error;
 
-	/*
-	 * We must make sure the anon_vma is allocated
-	 * so that the anon_vma locking is not a noop.
-	 */
-	if (unlikely(anon_vma_prepare(vma)))
-		return -ENOMEM;
-
 	address &= PAGE_MASK;
 	error = security_mmap_addr(address);
 	if (error)
 		return error;
 
-	vma_lock_anon_vma(vma);
+	/* We must make sure the anon_vma is allocated. */
+	if (unlikely(anon_vma_prepare(vma)))
+		return -ENOMEM;
 
 	/*
 	 * vma->vm_start/vm_end cannot change under us because the caller
 	 * is required to hold the mmap_sem in read mode.  We need the
 	 * anon_vma lock to serialize against concurrent expand_stacks.
 	 */
+	anon_vma_lock_write(vma->anon_vma);
 
 	/* Somebody else might have raced and expanded it already */
 	if (address < vma->vm_start) {
@@ -2255,27 +2261,31 @@ int expand_downwards(struct vm_area_struct *vma,
 				 * updates, but we only hold a shared mmap_sem
 				 * lock here, so we need to protect against
 				 * concurrent vma expansions.
-				 * vma_lock_anon_vma() doesn't help here, as
+				 * anon_vma_lock_write() doesn't help here, as
 				 * we don't guarantee that all growable vmas
 				 * in a mm share the same root anon vma.
 				 * So, we reuse mm->page_table_lock to guard
 				 * against concurrent vma expansions.
 				 */
-				spin_lock(&vma->vm_mm->page_table_lock);
+				spin_lock(&mm->page_table_lock);
+				if (vma->vm_flags & VM_LOCKED)
+					mm->locked_vm += grow;
+				vm_stat_account(mm, vma->vm_flags,
+						vma->vm_file, grow);
 				anon_vma_interval_tree_pre_update_vma(vma);
 				vma->vm_start = address;
 				vma->vm_pgoff -= grow;
 				anon_vma_interval_tree_post_update_vma(vma);
 				vma_gap_update(vma);
-				spin_unlock(&vma->vm_mm->page_table_lock);
+				spin_unlock(&mm->page_table_lock);
 
 				perf_event_mmap(vma);
 			}
 		}
 	}
-	vma_unlock_anon_vma(vma);
+	anon_vma_unlock_write(vma->anon_vma);
 	khugepaged_enter_vma_merge(vma, vma->vm_flags);
-	validate_mm(vma->vm_mm);
+	validate_mm(mm);
 	return error;
 }
 
@@ -2442,7 +2452,7 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	      unsigned long addr, int new_below)
 {
 	struct vm_area_struct *new;
-	int err = -ENOMEM;
+	int err;
 
 	if (is_vm_hugetlb_page(vma) && (addr &
 					~(huge_page_mask(hstate_vma(vma)))))
@@ -2450,7 +2460,7 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 	if (!new)
-		goto out_err;
+		return -ENOMEM;
 
 	/* most fields are the same, copy all, and then fixup */
 	*new = *vma;
@@ -2498,7 +2508,6 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	mpol_put(vma_policy(new));
  out_free_vma:
 	kmem_cache_free(vm_area_cachep, new);
- out_err:
 	return err;
 }
 
@@ -2525,7 +2534,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	unsigned long end;
 	struct vm_area_struct *vma, *prev, *last;
 
-	if ((start & ~PAGE_MASK) || start > TASK_SIZE || len > TASK_SIZE-start)
+	if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start)
 		return -EINVAL;
 
 	len = PAGE_ALIGN(len);
@@ -2659,12 +2668,29 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (!vma || !(vma->vm_flags & VM_SHARED))
 		goto out;
 
-	if (start < vma->vm_start || start + size > vma->vm_end)
+	if (start < vma->vm_start)
 		goto out;
 
-	if (pgoff == linear_page_index(vma, start)) {
-		ret = 0;
-		goto out;
+	if (start + size > vma->vm_end) {
+		struct vm_area_struct *next;
+
+		for (next = vma->vm_next; next; next = next->vm_next) {
+			/* hole between vmas ? */
+			if (next->vm_start != next->vm_prev->vm_end)
+				goto out;
+
+			if (next->vm_file != vma->vm_file)
+				goto out;
+
+			if (next->vm_flags != vma->vm_flags)
+				goto out;
+
+			if (start + size <= next->vm_end)
+				break;
+		}
+
+		if (!next)
+			goto out;
 	}
 
 	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
@@ -2674,9 +2700,16 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	flags &= MAP_NONBLOCK;
 	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
 	if (vma->vm_flags & VM_LOCKED) {
+		struct vm_area_struct *tmp;
 		flags |= MAP_LOCKED;
+
 		/* drop PG_Mlocked flag for over-mapped range */
-		munlock_vma_pages_range(vma, start, start + size);
+		for (tmp = vma; tmp->vm_start >= start + size;
+				tmp = tmp->vm_next) {
+			munlock_vma_pages_range(tmp,
+					max(tmp->vm_start, start),
+					min(tmp->vm_end, start + size));
+		}
 	}
 
 	file = get_file(vma->vm_file);
@@ -2723,7 +2756,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
 	error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
-	if (error & ~PAGE_MASK)
+	if (offset_in_page(error))
 		return error;
 
 	error = mlock_future_check(mm, mm->def_flags, len);
@@ -2757,7 +2790,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 
 	/* Can we just expand an old private anonymous mapping? */
 	vma = vma_merge(mm, prev, addr, addr + len, flags,
-					NULL, NULL, pgoff, NULL);
+			NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX);
 	if (vma)
 		goto out;
 
@@ -2859,6 +2892,13 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
 	struct vm_area_struct *prev;
 	struct rb_node **rb_link, *rb_parent;
 
+	if (find_vma_links(mm, vma->vm_start, vma->vm_end,
+			   &prev, &rb_link, &rb_parent))
+		return -ENOMEM;
+	if ((vma->vm_flags & VM_ACCOUNT) &&
+	     security_vm_enough_memory_mm(mm, vma_pages(vma)))
+		return -ENOMEM;
+
 	/*
 	 * The vm_pgoff of a purely anonymous vma should be irrelevant
 	 * until its first write fault, when page's anon_vma and index
@@ -2871,16 +2911,10 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
 	 * using the existing file pgoff checks and manipulations.
 	 * Similarly in do_mmap_pgoff and in do_brk.
 	 */
-	if (!vma->vm_file) {
+	if (vma_is_anonymous(vma)) {
 		BUG_ON(vma->anon_vma);
 		vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT;
 	}
-	if (find_vma_links(mm, vma->vm_start, vma->vm_end,
-			   &prev, &rb_link, &rb_parent))
-		return -ENOMEM;
-	if ((vma->vm_flags & VM_ACCOUNT) &&
-	     security_vm_enough_memory_mm(mm, vma_pages(vma)))
-		return -ENOMEM;
 
 	vma_link(mm, vma, prev, rb_link, rb_parent);
 	return 0;
@@ -2905,7 +2939,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	 * If anonymous vma has not yet been faulted, update new pgoff
 	 * to match new location, to increase its chance of merging.
 	 */
-	if (unlikely(!vma->vm_file && !vma->anon_vma)) {
+	if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) {
 		pgoff = addr >> PAGE_SHIFT;
 		faulted_in_anon_vma = false;
 	}
@@ -2913,7 +2947,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent))
 		return NULL;	/* should never get here */
 	new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
-			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
+			    vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+			    vma->vm_userfaultfd_ctx);
 	if (new_vma) {
 		/*
 		 * Source vma may have been merged into new_vma
@@ -2938,30 +2973,31 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
 	} else {
 		new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
-		if (new_vma) {
-			*new_vma = *vma;
-			new_vma->vm_start = addr;
-			new_vma->vm_end = addr + len;
-			new_vma->vm_pgoff = pgoff;
-			if (vma_dup_policy(vma, new_vma))
-				goto out_free_vma;
-			INIT_LIST_HEAD(&new_vma->anon_vma_chain);
-			if (anon_vma_clone(new_vma, vma))
-				goto out_free_mempol;
-			if (new_vma->vm_file)
-				get_file(new_vma->vm_file);
-			if (new_vma->vm_ops && new_vma->vm_ops->open)
-				new_vma->vm_ops->open(new_vma);
-			vma_link(mm, new_vma, prev, rb_link, rb_parent);
-			*need_rmap_locks = false;
-		}
+		if (!new_vma)
+			goto out;
+		*new_vma = *vma;
+		new_vma->vm_start = addr;
+		new_vma->vm_end = addr + len;
+		new_vma->vm_pgoff = pgoff;
+		if (vma_dup_policy(vma, new_vma))
+			goto out_free_vma;
+		INIT_LIST_HEAD(&new_vma->anon_vma_chain);
+		if (anon_vma_clone(new_vma, vma))
+			goto out_free_mempol;
+		if (new_vma->vm_file)
+			get_file(new_vma->vm_file);
+		if (new_vma->vm_ops && new_vma->vm_ops->open)
+			new_vma->vm_ops->open(new_vma);
+		vma_link(mm, new_vma, prev, rb_link, rb_parent);
+		*need_rmap_locks = false;
 	}
 	return new_vma;
 
- out_free_mempol:
+out_free_mempol:
 	mpol_put(vma_policy(new_vma));
- out_free_vma:
+out_free_vma:
 	kmem_cache_free(vm_area_cachep, new_vma);
+out:
 	return NULL;
 }
 
@@ -3013,21 +3049,13 @@ static int special_mapping_fault(struct vm_area_struct *vma,
 	pgoff_t pgoff;
 	struct page **pages;
 
-	/*
-	 * special mappings have no vm_file, and in that case, the mm
-	 * uses vm_pgoff internally. So we have to subtract it from here.
-	 * We are allowed to do this because we are the mm; do not copy
-	 * this code into drivers!
-	 */
-	pgoff = vmf->pgoff - vma->vm_pgoff;
-
 	if (vma->vm_ops == &legacy_special_mapping_vmops)
 		pages = vma->vm_private_data;
 	else
 		pages = ((struct vm_special_mapping *)vma->vm_private_data)->
 			pages;
 
-	for (; pgoff && *pages; ++pages)
+	for (pgoff = vmf->pgoff; pgoff && *pages; ++pages)
 		pgoff--;
 
 	if (*pages) {
@@ -3043,8 +3071,8 @@ static int special_mapping_fault(struct vm_area_struct *vma,
 static struct vm_area_struct *__install_special_mapping(
 	struct mm_struct *mm,
 	unsigned long addr, unsigned long len,
-	unsigned long vm_flags, const struct vm_operations_struct *ops,
-	void *priv)
+	unsigned long vm_flags, void *priv,
+	const struct vm_operations_struct *ops)
 {
 	int ret;
 	struct vm_area_struct *vma;
@@ -3093,8 +3121,8 @@ struct vm_area_struct *_install_special_mapping(
 	unsigned long addr, unsigned long len,
 	unsigned long vm_flags, const struct vm_special_mapping *spec)
 {
-	return __install_special_mapping(mm, addr, len, vm_flags,
-					 &special_mapping_vmops, (void *)spec);
+	return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec,
+					&special_mapping_vmops);
 }
 
 int install_special_mapping(struct mm_struct *mm,
@@ -3102,8 +3130,8 @@ int install_special_mapping(struct mm_struct *mm,
 			    unsigned long vm_flags, struct page **pages)
 {
 	struct vm_area_struct *vma = __install_special_mapping(
-		mm, addr, len, vm_flags, &legacy_special_mapping_vmops,
-		(void *)pages);
+		mm, addr, len, vm_flags, (void *)pages,
+		&legacy_special_mapping_vmops);
 
 	return PTR_ERR_OR_ZERO(vma);
 }