1 files changed, 201 insertions, 177 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index f681e1842fa..129b847d30c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -6,10 +6,13 @@
  * Address space accounting code	<alan@lxorguk.ukuu.org.uk>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/backing-dev.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/shm.h>
 #include <linux/mman.h>
 #include <linux/pagemap.h>
@@ -36,6 +39,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/notifier.h>
 #include <linux/memory.h>
+#include <linux/printk.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -86,6 +90,7 @@ EXPORT_SYMBOL(vm_get_page_prot);
 
 int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;  /* heuristic overcommit */
 int sysctl_overcommit_ratio __read_mostly = 50;	/* default is 50% */
+unsigned long sysctl_overcommit_kbytes __read_mostly;
 int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
 unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
 unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
@@ -179,14 +184,12 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		goto error;
 	}
 
-	allowed = (totalram_pages - hugetlb_total_pages())
-	       	* sysctl_overcommit_ratio / 100;
+	allowed = vm_commit_limit();
 	/*
 	 * Reserve some for root
 	 */
 	if (!cap_sys_admin)
 		allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
-	allowed += total_swap_pages;
 
 	/*
 	 * Don't let a single process grow so big a user can't recover
@@ -361,20 +364,20 @@ static int browse_rb(struct rb_root *root)
 		struct vm_area_struct *vma;
 		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
 		if (vma->vm_start < prev) {
-			printk("vm_start %lx prev %lx\n", vma->vm_start, prev);
+			pr_info("vm_start %lx prev %lx\n", vma->vm_start, prev);
 			bug = 1;
 		}
 		if (vma->vm_start < pend) {
-			printk("vm_start %lx pend %lx\n", vma->vm_start, pend);
+			pr_info("vm_start %lx pend %lx\n", vma->vm_start, pend);
 			bug = 1;
 		}
 		if (vma->vm_start > vma->vm_end) {
-			printk("vm_end %lx < vm_start %lx\n",
+			pr_info("vm_end %lx < vm_start %lx\n",
 				vma->vm_end, vma->vm_start);
 			bug = 1;
 		}
 		if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) {
-			printk("free gap %lx, correct %lx\n",
+			pr_info("free gap %lx, correct %lx\n",
 			       vma->rb_subtree_gap,
 			       vma_compute_subtree_gap(vma));
 			bug = 1;
@@ -388,7 +391,7 @@ static int browse_rb(struct rb_root *root)
 	for (nd = pn; nd; nd = rb_prev(nd))
 		j++;
 	if (i != j) {
-		printk("backwards %d, forwards %d\n", j, i);
+		pr_info("backwards %d, forwards %d\n", j, i);
 		bug = 1;
 	}
 	return bug ? -1 : i;
@@ -406,7 +409,7 @@ static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore)
 	}
 }
 
-void validate_mm(struct mm_struct *mm)
+static void validate_mm(struct mm_struct *mm)
 {
 	int bug = 0;
 	int i = 0;
@@ -423,17 +426,17 @@ void validate_mm(struct mm_struct *mm)
 		i++;
 	}
 	if (i != mm->map_count) {
-		printk("map_count %d vm_next %d\n", mm->map_count, i);
+		pr_info("map_count %d vm_next %d\n", mm->map_count, i);
 		bug = 1;
 	}
 	if (highest_address != mm->highest_vm_end) {
-		printk("mm->highest_vm_end %lx, found %lx\n",
+		pr_info("mm->highest_vm_end %lx, found %lx\n",
 		       mm->highest_vm_end, highest_address);
 		bug = 1;
 	}
 	i = browse_rb(&mm->mm_rb);
 	if (i != mm->map_count) {
-		printk("map_count %d rb %d\n", mm->map_count, i);
+		pr_info("map_count %d rb %d\n", mm->map_count, i);
 		bug = 1;
 	}
 	BUG_ON(bug);
@@ -640,11 +643,10 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct address_space *mapping = NULL;
 
-	if (vma->vm_file)
+	if (vma->vm_file) {
 		mapping = vma->vm_file->f_mapping;
-
-	if (mapping)
 		mutex_lock(&mapping->i_mmap_mutex);
+	}
 
 	__vma_link(mm, vma, prev, rb_link, rb_parent);
 	__vma_link_file(vma);
@@ -682,8 +684,9 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
 	prev->vm_next = next = vma->vm_next;
 	if (next)
 		next->vm_prev = prev;
-	if (mm->mmap_cache == vma)
-		mm->mmap_cache = prev;
+
+	/* Kill the cache */
+	vmacache_invalidate(mm);
 }
 
 /*
@@ -865,7 +868,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 		if (next->anon_vma)
 			anon_vma_merge(vma, next);
 		mm->map_count--;
-		vma_set_policy(vma, vma_policy(next));
+		mpol_put(vma_policy(next));
 		kmem_cache_free(vm_area_cachep, next);
 		/*
 		 * In mprotect's case 6 (see comments on vma_merge),
@@ -895,7 +898,15 @@ again:			remove_next = 1 + (end > next->vm_end);
 static inline int is_mergeable_vma(struct vm_area_struct *vma,
 			struct file *file, unsigned long vm_flags)
 {
-	if (vma->vm_flags ^ vm_flags)
+	/*
+	 * VM_SOFTDIRTY should not prevent from VMA merging, if we
+	 * match the flags but dirty bit -- the caller should mark
+	 * merged VMA as dirty. If dirty bit won't be excluded from
+	 * comparison, we increase pressue on the memory system forcing
+	 * the kernel to generate new VMAs when old one could be
+	 * extended instead.
+	 */
+	if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY)
 		return 0;
 	if (vma->vm_file != file)
 		return 0;
@@ -955,7 +966,7 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
 	if (is_mergeable_vma(vma, file, vm_flags) &&
 	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
 		pgoff_t vm_pglen;
-		vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+		vm_pglen = vma_pages(vma);
 		if (vma->vm_pgoff + vm_pglen == vm_pgoff)
 			return 1;
 	}
@@ -1084,7 +1095,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *
 	return a->vm_end == b->vm_start &&
 		mpol_equal(vma_policy(a), vma_policy(b)) &&
 		a->vm_file == b->vm_file &&
-		!((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC)) &&
+		!((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC|VM_SOFTDIRTY)) &&
 		b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT);
 }
 
@@ -1192,6 +1203,24 @@ static inline unsigned long round_hint_to_min(unsigned long hint)
 	return hint;
 }
 
+static inline int mlock_future_check(struct mm_struct *mm,
+				     unsigned long flags,
+				     unsigned long len)
+{
+	unsigned long locked, lock_limit;
+
+	/*  mlock MCL_FUTURE? */
+	if (flags & VM_LOCKED) {
+		locked = len >> PAGE_SHIFT;
+		locked += mm->locked_vm;
+		lock_limit = rlimit(RLIMIT_MEMLOCK);
+		lock_limit >>= PAGE_SHIFT;
+		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+			return -EAGAIN;
+	}
+	return 0;
+}
+
 /*
  * The caller must hold down_write(&current->mm->mmap_sem).
  */
@@ -1202,7 +1231,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			unsigned long *populate)
 {
 	struct mm_struct * mm = current->mm;
-	struct inode *inode;
 	vm_flags_t vm_flags;
 
 	*populate = 0;
@@ -1254,20 +1282,12 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 		if (!can_do_mlock())
 			return -EPERM;
 
-	/* mlock MCL_FUTURE? */
-	if (vm_flags & VM_LOCKED) {
-		unsigned long locked, lock_limit;
-		locked = len >> PAGE_SHIFT;
-		locked += mm->locked_vm;
-		lock_limit = rlimit(RLIMIT_MEMLOCK);
-		lock_limit >>= PAGE_SHIFT;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			return -EAGAIN;
-	}
-
-	inode = file ? file_inode(file) : NULL;
+	if (mlock_future_check(mm, vm_flags, len))
+		return -EAGAIN;
 
 	if (file) {
+		struct inode *inode = file_inode(file);
+
 		switch (flags & MAP_TYPE) {
 		case MAP_SHARED:
 			if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE))
@@ -1283,7 +1303,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			/*
 			 * Make sure there are no mandatory locks on the file.
 			 */
-			if (locks_verify_locked(inode))
+			if (locks_verify_locked(file))
 				return -EAGAIN;
 
 			vm_flags |= VM_SHARED | VM_MAYSHARE;
@@ -1300,8 +1320,10 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 				vm_flags &= ~VM_MAYEXEC;
 			}
 
-			if (!file->f_op || !file->f_op->mmap)
+			if (!file->f_op->mmap)
 				return -ENODEV;
+			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
+				return -EINVAL;
 			break;
 
 		default:
@@ -1310,6 +1332,8 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	} else {
 		switch (flags & MAP_TYPE) {
 		case MAP_SHARED:
+			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
+				return -EINVAL;
 			/*
 			 * Ignore pgoff.
 			 */
@@ -1358,18 +1382,19 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 
 	if (!(flags & MAP_ANONYMOUS)) {
 		audit_mmap_fd(fd, flags);
-		if (unlikely(flags & MAP_HUGETLB))
-			return -EINVAL;
 		file = fget(fd);
 		if (!file)
 			goto out;
 		if (is_file_hugepages(file))
 			len = ALIGN(len, huge_page_size(hstate_file(file)));
+		retval = -EINVAL;
+		if (unlikely(flags & MAP_HUGETLB && !is_file_hugepages(file)))
+			goto out_fput;
 	} else if (flags & MAP_HUGETLB) {
 		struct user_struct *user = NULL;
-		struct hstate *hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) &
-						   SHM_HUGE_MASK);
+		struct hstate *hs;
 
+		hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & SHM_HUGE_MASK);
 		if (!hs)
 			return -EINVAL;
 
@@ -1391,6 +1416,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
 
 	retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+out_fput:
 	if (file)
 		fput(file);
 out:
@@ -1474,11 +1500,9 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
-	int correct_wcount = 0;
 	int error;
 	struct rb_node **rb_link, *rb_parent;
 	unsigned long charged = 0;
-	struct inode *inode =  file ? file_inode(file) : NULL;
 
 	/* Check against address space limit. */
 	if (!may_expand_vm(mm, len >> PAGE_SHIFT)) {
@@ -1542,16 +1566,11 @@ munmap_back:
 	vma->vm_pgoff = pgoff;
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
-	error = -EINVAL;	/* when rejecting VM_GROWSDOWN|VM_GROWSUP */
-
 	if (file) {
-		if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
-			goto free_vma;
 		if (vm_flags & VM_DENYWRITE) {
 			error = deny_write_access(file);
 			if (error)
 				goto free_vma;
-			correct_wcount = 1;
 		}
 		vma->vm_file = get_file(file);
 		error = file->f_op->mmap(file, vma);
@@ -1568,11 +1587,8 @@ munmap_back:
 		WARN_ON_ONCE(addr != vma->vm_start);
 
 		addr = vma->vm_start;
-		pgoff = vma->vm_pgoff;
 		vm_flags = vma->vm_flags;
 	} else if (vm_flags & VM_SHARED) {
-		if (unlikely(vm_flags & (VM_GROWSDOWN|VM_GROWSUP)))
-			goto free_vma;
 		error = shmem_zero_setup(vma);
 		if (error)
 			goto free_vma;
@@ -1594,11 +1610,10 @@ munmap_back:
 	}
 
 	vma_link(mm, vma, prev, rb_link, rb_parent);
-	file = vma->vm_file;
-
 	/* Once vma denies write, undo our temporary denial count */
-	if (correct_wcount)
-		atomic_inc(&inode->i_writecount);
+	if (vm_flags & VM_DENYWRITE)
+		allow_write_access(file);
+	file = vma->vm_file;
 out:
 	perf_event_mmap(vma);
 
@@ -1614,11 +1629,20 @@ out:
 	if (file)
 		uprobe_mmap(vma);
 
+	/*
+	 * New (or expanded) vma always get soft dirty status.
+	 * Otherwise user-space soft-dirty page tracker won't
+	 * be able to distinguish situation when vma area unmapped,
+	 * then new mapped in-place (which must be aimed as
+	 * a completely new data area).
+	 */
+	vma->vm_flags |= VM_SOFTDIRTY;
+
 	return addr;
 
 unmap_and_free_vma:
-	if (correct_wcount)
-		atomic_inc(&inode->i_writecount);
+	if (vm_flags & VM_DENYWRITE)
+		allow_write_access(file);
 	vma->vm_file = NULL;
 	fput(file);
 
@@ -1853,7 +1877,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct vm_area_struct *vma;
 	struct vm_unmapped_area_info info;
 
-	if (len > TASK_SIZE)
+	if (len > TASK_SIZE - mmap_min_addr)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED)
@@ -1862,29 +1886,20 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
+		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
 		    (!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
 
 	info.flags = 0;
 	info.length = len;
-	info.low_limit = TASK_UNMAPPED_BASE;
+	info.low_limit = mm->mmap_base;
 	info.high_limit = TASK_SIZE;
 	info.align_mask = 0;
 	return vm_unmapped_area(&info);
 }
 #endif	
 
-void arch_unmap_area(struct mm_struct *mm, unsigned long addr)
-{
-	/*
-	 * Is this a new hole at the lowest possible address?
-	 */
-	if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache)
-		mm->free_area_cache = addr;
-}
-
 /*
  * This mmap-allocator allocates new areas top-down from below the
  * stack's low limit (the base):
@@ -1901,7 +1916,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	struct vm_unmapped_area_info info;
 
 	/* requested length too big for entire address space */
-	if (len > TASK_SIZE)
+	if (len > TASK_SIZE - mmap_min_addr)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED)
@@ -1911,14 +1926,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
+		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
 				(!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
-	info.low_limit = PAGE_SIZE;
+	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
 	info.high_limit = mm->mmap_base;
 	info.align_mask = 0;
 	addr = vm_unmapped_area(&info);
@@ -1941,19 +1956,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 }
 #endif
 
-void arch_unmap_area_topdown(struct mm_struct *mm, unsigned long addr)
-{
-	/*
-	 * Is this a new hole at the highest possible address?
-	 */
-	if (addr > mm->free_area_cache)
-		mm->free_area_cache = addr;
-
-	/* dont allow allocations above current base */
-	if (mm->free_area_cache > mm->mmap_base)
-		mm->free_area_cache = mm->mmap_base;
-}
-
 unsigned long
 get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
@@ -1970,7 +1972,7 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		return -ENOMEM;
 
 	get_area = current->mm->get_unmapped_area;
-	if (file && file->f_op && file->f_op->get_unmapped_area)
+	if (file && file->f_op->get_unmapped_area)
 		get_area = file->f_op->get_unmapped_area;
 	addr = get_area(file, addr, len, pgoff, flags);
 	if (IS_ERR_VALUE(addr))
@@ -1991,34 +1993,33 @@ EXPORT_SYMBOL(get_unmapped_area);
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
 struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 {
-	struct vm_area_struct *vma = NULL;
+	struct rb_node *rb_node;
+	struct vm_area_struct *vma;
 
 	/* Check the cache first. */
-	/* (Cache hit rate is typically around 35%.) */
-	vma = ACCESS_ONCE(mm->mmap_cache);
-	if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
-		struct rb_node *rb_node;
+	vma = vmacache_find(mm, addr);
+	if (likely(vma))
+		return vma;
 
-		rb_node = mm->mm_rb.rb_node;
-		vma = NULL;
+	rb_node = mm->mm_rb.rb_node;
+	vma = NULL;
 
-		while (rb_node) {
-			struct vm_area_struct *vma_tmp;
-
-			vma_tmp = rb_entry(rb_node,
-					   struct vm_area_struct, vm_rb);
-
-			if (vma_tmp->vm_end > addr) {
-				vma = vma_tmp;
-				if (vma_tmp->vm_start <= addr)
-					break;
-				rb_node = rb_node->rb_left;
-			} else
-				rb_node = rb_node->rb_right;
-		}
-		if (vma)
-			mm->mmap_cache = vma;
+	while (rb_node) {
+		struct vm_area_struct *tmp;
+
+		tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb);
+
+		if (tmp->vm_end > addr) {
+			vma = tmp;
+			if (tmp->vm_start <= addr)
+				break;
+			rb_node = rb_node->rb_left;
+		} else
+			rb_node = rb_node->rb_right;
 	}
+
+	if (vma)
+		vmacache_update(addr, vma);
 	return vma;
 }
 
@@ -2356,7 +2357,7 @@ static void unmap_region(struct mm_struct *mm,
 	struct mmu_gather tlb;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, start, end);
 	update_hiwater_rss(mm);
 	unmap_vmas(&tlb, vma, start, end);
 	free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
@@ -2374,7 +2375,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct vm_area_struct **insertion_point;
 	struct vm_area_struct *tail_vma = NULL;
-	unsigned long addr;
 
 	insertion_point = (prev ? &prev->vm_next : &mm->mmap);
 	vma->vm_prev = NULL;
@@ -2391,12 +2391,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 	} else
 		mm->highest_vm_end = prev ? prev->vm_end : 0;
 	tail_vma->vm_next = NULL;
-	if (mm->unmap_area == arch_unmap_area)
-		addr = prev ? prev->vm_end : mm->mmap_base;
-	else
-		addr = vma ?  vma->vm_start : mm->mmap_base;
-	mm->unmap_area(mm, addr);
-	mm->mmap_cache = NULL;		/* Kill the cache. */
+
+	/* Kill the cache */
+	vmacache_invalidate(mm);
 }
 
 /*
@@ -2406,7 +2403,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 	      unsigned long addr, int new_below)
 {
-	struct mempolicy *pol;
 	struct vm_area_struct *new;
 	int err = -ENOMEM;
 
@@ -2430,12 +2426,9 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 		new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT);
 	}
 
-	pol = mpol_dup(vma_policy(vma));
-	if (IS_ERR(pol)) {
-		err = PTR_ERR(pol);
+	err = vma_dup_policy(vma, new);
+	if (err)
 		goto out_free_vma;
-	}
-	vma_set_policy(new, pol);
 
 	if (anon_vma_clone(new, vma))
 		goto out_free_mpol;
@@ -2463,7 +2456,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 		fput(new->vm_file);
 	unlink_anon_vmas(new);
  out_free_mpol:
-	mpol_put(pol);
+	mpol_put(vma_policy(new));
  out_free_vma:
 	kmem_cache_free(vm_area_cachep, new);
  out_err:
@@ -2622,18 +2615,9 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 	if (error & ~PAGE_MASK)
 		return error;
 
-	/*
-	 * mlock MCL_FUTURE?
-	 */
-	if (mm->def_flags & VM_LOCKED) {
-		unsigned long locked, lock_limit;
-		locked = len >> PAGE_SHIFT;
-		locked += mm->locked_vm;
-		lock_limit = rlimit(RLIMIT_MEMLOCK);
-		lock_limit >>= PAGE_SHIFT;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			return -EAGAIN;
-	}
+	error = mlock_future_check(mm, mm->def_flags, len);
+	if (error)
+		return error;
 
 	/*
 	 * mm->mmap_sem is required to protect against another thread
@@ -2689,6 +2673,7 @@ out:
 	mm->total_vm += len >> PAGE_SHIFT;
 	if (flags & VM_LOCKED)
 		mm->locked_vm += (len >> PAGE_SHIFT);
+	vma->vm_flags |= VM_SOFTDIRTY;
 	return addr;
 }
 
@@ -2735,7 +2720,7 @@ void exit_mmap(struct mm_struct *mm)
 
 	lru_add_drain();
 	flush_cache_mm(mm);
-	tlb_gather_mmu(&tlb, mm, 1);
+	tlb_gather_mmu(&tlb, mm, 0, -1);
 	/* update_hiwater_rss(mm) here? but nobody should be looking */
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	unmap_vmas(&tlb, vma, 0, -1);
@@ -2754,7 +2739,8 @@ void exit_mmap(struct mm_struct *mm)
 	}
 	vm_unacct_memory(nr_accounted);
 
-	WARN_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
+	WARN_ON(atomic_long_read(&mm->nr_ptes) >
+			(FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
 }
 
 /* Insert vm structure into process list sorted by address
@@ -2806,7 +2792,6 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *new_vma, *prev;
 	struct rb_node **rb_link, *rb_parent;
-	struct mempolicy *pol;
 	bool faulted_in_anon_vma = true;
 
 	/*
@@ -2851,10 +2836,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 			new_vma->vm_start = addr;
 			new_vma->vm_end = addr + len;
 			new_vma->vm_pgoff = pgoff;
-			pol = mpol_dup(vma_policy(vma));
-			if (IS_ERR(pol))
+			if (vma_dup_policy(vma, new_vma))
 				goto out_free_vma;
-			vma_set_policy(new_vma, pol);
 			INIT_LIST_HEAD(&new_vma->anon_vma_chain);
 			if (anon_vma_clone(new_vma, vma))
 				goto out_free_mempol;
@@ -2869,7 +2852,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	return new_vma;
 
  out_free_mempol:
-	mpol_put(pol);
+	mpol_put(vma_policy(new_vma));
  out_free_vma:
 	kmem_cache_free(vm_area_cachep, new_vma);
 	return NULL;
@@ -2891,6 +2874,31 @@ int may_expand_vm(struct mm_struct *mm, unsigned long npages)
 	return 1;
 }
 
+static int special_mapping_fault(struct vm_area_struct *vma,
+				 struct vm_fault *vmf);
+
+/*
+ * Having a close hook prevents vma merging regardless of flags.
+ */
+static void special_mapping_close(struct vm_area_struct *vma)
+{
+}
+
+static const char *special_mapping_name(struct vm_area_struct *vma)
+{
+	return ((struct vm_special_mapping *)vma->vm_private_data)->name;
+}
+
+static const struct vm_operations_struct special_mapping_vmops = {
+	.close = special_mapping_close,
+	.fault = special_mapping_fault,
+	.name = special_mapping_name,
+};
+
+static const struct vm_operations_struct legacy_special_mapping_vmops = {
+	.close = special_mapping_close,
+	.fault = special_mapping_fault,
+};
 
 static int special_mapping_fault(struct vm_area_struct *vma,
 				struct vm_fault *vmf)
@@ -2906,7 +2914,13 @@ static int special_mapping_fault(struct vm_area_struct *vma,
 	 */
 	pgoff = vmf->pgoff - vma->vm_pgoff;
 
-	for (pages = vma->vm_private_data; pgoff && *pages; ++pages)
+	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)
 		pgoff--;
 
 	if (*pages) {
@@ -2919,48 +2933,29 @@ static int special_mapping_fault(struct vm_area_struct *vma,
 	return VM_FAULT_SIGBUS;
 }
 
-/*
- * Having a close hook prevents vma merging regardless of flags.
- */
-static void special_mapping_close(struct vm_area_struct *vma)
-{
-}
-
-static const struct vm_operations_struct special_mapping_vmops = {
-	.close = special_mapping_close,
-	.fault = special_mapping_fault,
-};
-
-/*
- * Called with mm->mmap_sem held for writing.
- * Insert a new vma covering the given region, with the given flags.
- * Its pages are supplied by the given array of struct page *.
- * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated.
- * The region past the last page supplied will always produce SIGBUS.
- * The array pointer and the pages it points to are assumed to stay alive
- * for as long as this mapping might exist.
- */
-int install_special_mapping(struct mm_struct *mm,
-			    unsigned long addr, unsigned long len,
-			    unsigned long vm_flags, struct page **pages)
+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)
 {
 	int ret;
 	struct vm_area_struct *vma;
 
 	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
 	if (unlikely(vma == NULL))
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
 	vma->vm_mm = mm;
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 
-	vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND;
+	vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY;
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 
-	vma->vm_ops = &special_mapping_vmops;
-	vma->vm_private_data = pages;
+	vma->vm_ops = ops;
+	vma->vm_private_data = priv;
 
 	ret = insert_vm_struct(mm, vma);
 	if (ret)
@@ -2970,11 +2965,40 @@ int install_special_mapping(struct mm_struct *mm,
 
 	perf_event_mmap(vma);
 
-	return 0;
+	return vma;
 
 out:
 	kmem_cache_free(vm_area_cachep, vma);
-	return ret;
+	return ERR_PTR(ret);
+}
+
+/*
+ * Called with mm->mmap_sem held for writing.
+ * Insert a new vma covering the given region, with the given flags.
+ * Its pages are supplied by the given array of struct page *.
+ * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated.
+ * The region past the last page supplied will always produce SIGBUS.
+ * The array pointer and the pages it points to are assumed to stay alive
+ * for as long as this mapping might exist.
+ */
+struct vm_area_struct *_install_special_mapping(
+	struct mm_struct *mm,
+	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);
+}
+
+int install_special_mapping(struct mm_struct *mm,
+			    unsigned long addr, unsigned long len,
+			    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);
+
+	return PTR_ERR_OR_ZERO(vma);
 }
 
 static DEFINE_MUTEX(mm_all_locks_mutex);
@@ -3172,7 +3196,7 @@ static int init_user_reserve(void)
 	sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17);
 	return 0;
 }
-module_init(init_user_reserve)
+subsys_initcall(init_user_reserve);
 
 /*
  * Initialise sysctl_admin_reserve_kbytes.
@@ -3193,7 +3217,7 @@ static int init_admin_reserve(void)
 	sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13);
 	return 0;
 }
-module_init(init_admin_reserve)
+subsys_initcall(init_admin_reserve);
 
 /*
  * Reinititalise user and admin reserves if memory is added or removed.
@@ -3259,8 +3283,8 @@ static struct notifier_block reserve_mem_nb = {
 static int __meminit init_reserve_notifier(void)
 {
 	if (register_hotmemory_notifier(&reserve_mem_nb))
-		printk("Failed registering memory add/remove notifier for admin reserve");
+		pr_err("Failed registering memory add/remove notifier for admin reserve\n");
 
 	return 0;
 }
-module_init(init_reserve_notifier)
+subsys_initcall(init_reserve_notifier);