[PATCH 00/21] RFC: userfaultfd v3

@@ -1902,6 +1902,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 {
 	struct anon_vma *anon_vma;
 	int ret = 1;
+	struct address_space *mapping;
 
 	BUG_ON(is_huge_zero_page(page));
 	BUG_ON(!PageAnon(page));

@@ -1913,10 +1914,24 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	 * page_lock_anon_vma_read except the write lock is taken to serialise
 	 * against parallel split or collapse operations.
 	 */
-	anon_vma = page_get_anon_vma(page);
-	if (!anon_vma)
-		goto out;
-	anon_vma_lock_write(anon_vma);
+	for (;;) {
+		mapping = ACCESS_ONCE(page->mapping);
+		anon_vma = page_get_anon_vma(page);
+		if (!anon_vma)
+			goto out;
+		anon_vma_lock_write(anon_vma);
+		/*
+		 * We don't hold the page lock here so
+		 * remap_pages_huge_pmd can change the anon_vma from
+		 * under us until we obtain the anon_vma lock. Verify
+		 * that we obtained the anon_vma lock before
+		 * remap_pages did.
+		 */
+		if (likely(mapping == ACCESS_ONCE(page->mapping)))
+			break;
+		anon_vma_unlock_write(anon_vma);
+		put_anon_vma(anon_vma);
+	}
 
 	ret = 0;
 	if (!PageCompound(page))

@@ -492,6 +492,7 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page)
 	struct anon_vma *root_anon_vma;
 	unsigned long anon_mapping;
 
+repeat:
 	rcu_read_lock();
 	anon_mapping = (unsigned long) ACCESS_ONCE(page->mapping);
 	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)

@@ -530,6 +531,14 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page)
 	rcu_read_unlock();
 	anon_vma_lock_read(anon_vma);
 
+	/* check if remap_anon_pages changed the anon_vma */
+	if (unlikely((unsigned long) ACCESS_ONCE(page->mapping) != anon_mapping)) {
+		anon_vma_unlock_read(anon_vma);
+		put_anon_vma(anon_vma);
+		anon_vma = NULL;
+		goto repeat;
+	}
+
 	if (atomic_dec_and_test(&anon_vma->refcount)) {
 		/*
 		 * Oops, we held the last refcount, release the lock

@@ -23,6 +23,7 @@
 #include <linux/pagemap.h>
 #include <linux/migrate.h>
 #include <linux/hashtable.h>
+#include <linux/userfaultfd_k.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>

@@ -708,7 +709,7 @@ static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
 static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 					struct vm_area_struct *vma,
 					unsigned long haddr, pmd_t *pmd,
-					struct page *page)
+					struct page *page, unsigned int flags)
 {
 	struct mem_cgroup *memcg;
 	pgtable_t pgtable;

@@ -716,12 +717,16 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge(page, mm, GFP_TRANSHUGE, &memcg))
-		return VM_FAULT_OOM;
+	if (mem_cgroup_try_charge(page, mm, GFP_TRANSHUGE, &memcg)) {
+		put_page(page);
+		count_vm_event(THP_FAULT_FALLBACK);
+		return VM_FAULT_FALLBACK;
+	}
 
 	pgtable = pte_alloc_one(mm, haddr);
 	if (unlikely(!pgtable)) {
 		mem_cgroup_cancel_charge(page, memcg);
+		put_page(page);
 		return VM_FAULT_OOM;
 	}
 

@@ -741,6 +746,21 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		pte_free(mm, pgtable);
 	} else {
 		pmd_t entry;
+
+		/* Deliver the page fault to userland */
+		if (userfaultfd_missing(vma)) {
+			int ret;
+
+			spin_unlock(ptl);
+			mem_cgroup_cancel_charge(page, memcg);
+			put_page(page);
+			pte_free(mm, pgtable);
+			ret = handle_userfault(vma, haddr, flags,
+					       VM_UFFD_MISSING);
+			VM_BUG_ON(ret & VM_FAULT_FALLBACK);
+			return ret;
+		}
+
 		entry = mk_huge_pmd(page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		page_add_new_anon_rmap(page, vma, haddr);

@@ -751,6 +771,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		atomic_long_inc(&mm->nr_ptes);
 		spin_unlock(ptl);
+		count_vm_event(THP_FAULT_ALLOC);
 	}
 
 	return 0;

@@ -762,19 +783,16 @@ static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp)
 }
 
 /* Caller must hold page table lock. */
-static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
+static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 		struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
 		struct page *zero_page)
 {
 	pmd_t entry;
-	if (!pmd_none(*pmd))
-		return false;
 	entry = mk_pmd(zero_page, vma->vm_page_prot);
 	entry = pmd_mkhuge(entry);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
 	atomic_long_inc(&mm->nr_ptes);
-	return true;
 }
 
 int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,

@@ -797,6 +815,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		pgtable_t pgtable;
 		struct page *zero_page;
 		bool set;
+		int ret;
 		pgtable = pte_alloc_one(mm, haddr);
 		if (unlikely(!pgtable))
 			return VM_FAULT_OOM;

@@ -807,14 +826,28 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			return VM_FAULT_FALLBACK;
 		}
 		ptl = pmd_lock(mm, pmd);
-		set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
-				zero_page);
-		spin_unlock(ptl);
+		ret = 0;
+		set = false;
+		if (pmd_none(*pmd)) {
+			if (userfaultfd_missing(vma)) {
+				spin_unlock(ptl);
+				ret = handle_userfault(vma, haddr, flags,
+						       VM_UFFD_MISSING);
+				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
+			} else {
+				set_huge_zero_page(pgtable, mm, vma,
+						   haddr, pmd,
+						   zero_page);
+				spin_unlock(ptl);
+				set = true;
+			}
+		} else
+			spin_unlock(ptl);
 		if (!set) {
 			pte_free(mm, pgtable);
 			put_huge_zero_page();
 		}
-		return 0;
+		return ret;
 	}
 	gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0);
 	page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);

@@ -822,14 +855,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
 	}
-	if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) {
-		put_page(page);
-		count_vm_event(THP_FAULT_FALLBACK);
-		return VM_FAULT_FALLBACK;
-	}
-
-	count_vm_event(THP_FAULT_ALLOC);
-	return 0;
+	return __do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page, flags);
 }
 
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,

@@ -864,16 +890,14 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 */
 	if (is_huge_zero_pmd(pmd)) {
 		struct page *zero_page;
-		bool set;
 		/*
 		 * get_huge_zero_page() will never allocate a new page here,
 		 * since we already have a zero page to copy. It just takes a
 		 * reference.
 		 */
 		zero_page = get_huge_zero_page();
-		set = set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,
+		set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,
 				zero_page);
-		BUG_ON(!set); /* unexpected !pmd_none(dst_pmd) */
 		ret = 0;
 		goto out_unlock;
 	}

@@ -61,6 +61,7 @@
 #include <linux/string.h>
 #include <linux/dma-debug.h>
 #include <linux/debugfs.h>
+#include <linux/userfaultfd_k.h>
 
 #include <asm/io.h>
 #include <asm/pgalloc.h>

@@ -2585,6 +2586,12 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
 		if (!pte_none(*page_table))
 			goto unlock;
+		/* Deliver the page fault to userland, check inside PT lock */
+		if (userfaultfd_missing(vma)) {
+			pte_unmap_unlock(page_table, ptl);
+			return handle_userfault(vma, address, flags,
+						VM_UFFD_MISSING);
+		}
 		goto setpte;
 	}
 

@@ -2612,6 +2619,15 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!pte_none(*page_table))
 		goto release;
 
+	/* Deliver the page fault to userland, check inside PT lock */
+	if (userfaultfd_missing(vma)) {
+		pte_unmap_unlock(page_table, ptl);
+		mem_cgroup_cancel_charge(page, memcg);
+		page_cache_release(page);
+		return handle_userfault(vma, address, flags,
+					VM_UFFD_MISSING);
+	}
+
 	inc_mm_counter_fast(mm, MM_ANONPAGES);
 	page_add_new_anon_rmap(page, vma, address);
 	mem_cgroup_commit_charge(page, memcg, false);

--

@@ -367,3 +367,4 @@ SYSCALL_SPU(getrandom)
 SYSCALL_SPU(memfd_create)
 SYSCALL_SPU(bpf)
 COMPAT_SYS(execveat)
+SYSCALL_SPU(userfaultfd)

@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define __NR_syscalls		363
+#define __NR_syscalls		364
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls

@@ -385,5 +385,6 @@
 #define __NR_memfd_create	360
 #define __NR_bpf		361
 #define __NR_execveat		362
+#define __NR_userfaultfd	363
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */

@@ -365,3 +365,4 @@
 356	i386	memfd_create		sys_memfd_create
 357	i386	bpf			sys_bpf
 358	i386	execveat		sys_execveat			stub32_execveat
+359	i386	userfaultfd		sys_userfaultfd

@@ -329,6 +329,7 @@
 320	common	kexec_file_load		sys_kexec_file_load
 321	common	bpf			sys_bpf
 322	64	execveat		stub_execveat
+323	common	userfaultfd		sys_userfaultfd
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

@@ -810,6 +810,7 @@ asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr);
 asmlinkage long sys_eventfd(unsigned int count);
 asmlinkage long sys_eventfd2(unsigned int count, int flags);
 asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags);
+asmlinkage long sys_userfaultfd(int flags);
 asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len);
 asmlinkage long sys_old_readdir(unsigned int, struct old_linux_dirent __user *, unsigned int);
 asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *,

@@ -204,6 +204,7 @@ cond_syscall(compat_sys_timerfd_gettime);
 cond_syscall(sys_eventfd);
 cond_syscall(sys_eventfd2);
 cond_syscall(sys_memfd_create);
+cond_syscall(sys_userfaultfd);
 
 /* performance counters: */
 cond_syscall(sys_perf_event_open);

@@ -30,6 +30,12 @@
 extern int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 			    unsigned int flags, unsigned long reason);
 
+extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
+			    unsigned long src_start, unsigned long len);
+extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
+			      unsigned long dst_start,
+			      unsigned long len);
+
 /* mm helpers */
 static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
 					struct vm_userfaultfd_ctx vm_ctx)

@@ -76,3 +76,4 @@ obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o
 obj-$(CONFIG_CMA)	+= cma.o
 obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o
 obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o
+obj-$(CONFIG_USERFAULTFD) += userfaultfd.o

@@ -0,0 +1,267 @@
+/*
+ *  mm/userfaultfd.c
+ *
+ *  Copyright (C) 2015  Red Hat, Inc.
+ *
+ *  This work is licensed under the terms of the GNU GPL, version 2. See
+ *  the COPYING file in the top-level directory.
+ */
+
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/userfaultfd_k.h>
+#include <linux/mmu_notifier.h>
+#include <asm/tlbflush.h>
+#include "internal.h"
+
+static int mcopy_atomic_pte(struct mm_struct *dst_mm,
+			    pmd_t *dst_pmd,
+			    struct vm_area_struct *dst_vma,
+			    unsigned long dst_addr,
+			    unsigned long src_addr)
+{
+	struct mem_cgroup *memcg;
+	pte_t _dst_pte, *dst_pte;
+	spinlock_t *ptl;
+	struct page *page;
+	void *page_kaddr;
+	int ret;
+
+	ret = -ENOMEM;
+	page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, dst_vma, dst_addr);
+	if (!page)
+		goto out;
+
+	page_kaddr = kmap(page);
+	ret = -EFAULT;
+	if (copy_from_user(page_kaddr, (const void __user *) src_addr,
+			   PAGE_SIZE))
+		goto out_kunmap_release;
+	kunmap(page);
+
+	/*
+	 * The memory barrier inside __SetPageUptodate makes sure that
+	 * preceeding stores to the page contents become visible before
+	 * the set_pte_at() write.
+	 */
+	__SetPageUptodate(page);
+
+	ret = -ENOMEM;
+	if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg))
+		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));
+
+	ret = -EEXIST;
+	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+	if (!pte_none(*dst_pte))
+		goto out_release_uncharge_unlock;
+
+	inc_mm_counter(dst_mm, MM_ANONPAGES);
+	page_add_new_anon_rmap(page, dst_vma, dst_addr);
+	mem_cgroup_commit_charge(page, memcg, false);
+	lru_cache_add_active_or_unevictable(page, dst_vma);
+
+	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+
+	/* No need to invalidate - it was non-present before */
+	update_mmu_cache(dst_vma, dst_addr, dst_pte);
+
+	pte_unmap_unlock(dst_pte, ptl);
+	ret = 0;
+out:
+	return ret;
+out_release_uncharge_unlock:
+	pte_unmap_unlock(dst_pte, ptl);
+	mem_cgroup_cancel_charge(page, memcg);
+out_release:
+	page_cache_release(page);
+	goto out;
+out_kunmap_release:
+	kunmap(page);
+	goto out_release;
+}
+
+static int mfill_zeropage_pte(struct mm_struct *dst_mm,
+			      pmd_t *dst_pmd,
+			      struct vm_area_struct *dst_vma,
+			      unsigned long dst_addr)
+{
+	pte_t _dst_pte, *dst_pte;
+	spinlock_t *ptl;
+	int ret;
+
+	_dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr),
+					 dst_vma->vm_page_prot));
+	ret = -EEXIST;
+	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+	if (!pte_none(*dst_pte))
+		goto out_unlock;
+	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
+	/* No need to invalidate - it was non-present before */
+	update_mmu_cache(dst_vma, dst_addr, dst_pte);
+	ret = 0;
+out_unlock:
+	pte_unmap_unlock(dst_pte, ptl);
+	return ret;
+}
+
+static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd = NULL;
+
+	pgd = pgd_offset(mm, address);
+	pud = pud_alloc(mm, pgd, address);
+	if (pud)
+		/*
+		 * Note that we didn't run this because the pmd was
+		 * missing, the *pmd may be already established and in
+		 * turn it may also be a trans_huge_pmd.
+		 */
+		pmd = pmd_alloc(mm, pud, address);
+	return pmd;
+}
+
+static ssize_t __mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
+			      unsigned long src_start, unsigned long len,
+			      bool zeropage)
+{
+	struct vm_area_struct *dst_vma;
+	ssize_t err;
+	pmd_t *dst_pmd;
+	unsigned long src_addr, dst_addr;
+	long copied = 0;
+
+	/*
+	 * Sanitize the command parameters:
+	 */
+	BUG_ON(dst_start & ~PAGE_MASK);
+	BUG_ON(len & ~PAGE_MASK);
+
+	/* Does the address range wrap, or is the span zero-sized? */
+	BUG_ON(src_start + len <= src_start);
+	BUG_ON(dst_start + len <= dst_start);
+
+	down_read(&dst_mm->mmap_sem);
+
+	/*
+	 * Make sure the vma is not shared, that the dst range is
+	 * both valid and fully within a single existing vma.
+	 */
+	err = -EINVAL;
+	dst_vma = find_vma(dst_mm, dst_start);
+	if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
+		goto out;
+	if (dst_start < dst_vma->vm_start ||
+	    dst_start + len > dst_vma->vm_end)
+		goto out;
+
+	/*
+	 * Be strict and only allow __mcopy_atomic on userfaultfd
+	 * registered ranges to prevent userland errors going
+	 * unnoticed. As far as the VM consistency is concerned, it
+	 * would be perfectly safe to remove this check, but there's
+	 * no useful usage for __mcopy_atomic ouside of userfaultfd
+	 * registered ranges. This is after all why these are ioctls
+	 * belonging to the userfaultfd and not syscalls.
+	 */
+	if (!dst_vma->vm_userfaultfd_ctx.ctx)
+		goto out;
+
+	/*
+	 * FIXME: only allow copying on anonymous vmas, tmpfs should
+	 * be added.
+	 */
+	if (dst_vma->vm_ops)
+		goto out;
+
+	/*
+	 * Ensure the dst_vma has a anon_vma or this page
+	 * would get a NULL anon_vma when moved in the
+	 * dst_vma.
+	 */
+	err = -ENOMEM;
+	if (unlikely(anon_vma_prepare(dst_vma)))
+		goto out;
+
+	for (src_addr = src_start, dst_addr = dst_start;
+	     src_addr < src_start + len; ) {
+		pmd_t dst_pmdval;
+		BUG_ON(dst_addr >= dst_start + len);
+		dst_pmd = mm_alloc_pmd(dst_mm, dst_addr);
+		if (unlikely(!dst_pmd)) {
+			err = -ENOMEM;
+			break;
+		}
+
+		dst_pmdval = pmd_read_atomic(dst_pmd);
+		/*
+		 * If the dst_pmd is mapped as THP don't
+		 * override it and just be strict.
+		 */
+		if (unlikely(pmd_trans_huge(dst_pmdval))) {
+			err = -EEXIST;
+			break;
+		}
+		if (unlikely(pmd_none(dst_pmdval)) &&
+		    unlikely(__pte_alloc(dst_mm, dst_vma, dst_pmd,
+					 dst_addr))) {
+			err = -ENOMEM;
+			break;
+		}
+		/* If an huge pmd materialized from under us fail */
+		if (unlikely(pmd_trans_huge(*dst_pmd))) {
+			err = -EFAULT;
+			break;
+		}
+
+		BUG_ON(pmd_none(*dst_pmd));
+		BUG_ON(pmd_trans_huge(*dst_pmd));
+
+		if (!zeropage)
+			err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
+					       dst_addr, src_addr);
+		else
+			err = mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma,
+						 dst_addr);
+
+		cond_resched();
+
+		if (!err) {
+			dst_addr += PAGE_SIZE;
+			src_addr += PAGE_SIZE;
+			copied += PAGE_SIZE;
+
+			if (fatal_signal_pending(current))
+				err = -EINTR;
+		}
+		if (err)
+			break;
+	}
+
+out:
+	up_read(&dst_mm->mmap_sem);
+	BUG_ON(copied < 0);
+	BUG_ON(err > 0);
+	BUG_ON(!copied && !err);
+	return copied ? copied : err;
+}
+
+ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
+		     unsigned long src_start, unsigned long len)
+{
+	return __mcopy_atomic(dst_mm, dst_start, src_start, len, false);
+}
+
+ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
+		       unsigned long len)
+{
+	return __mcopy_atomic(dst_mm, start, 0, len, true);
+}

@@ -798,6 +798,100 @@ out:
 	return ret;
 }
 
+static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
+			    unsigned long arg)
+{
+	__s64 ret;
+	struct uffdio_copy uffdio_copy;
+	struct uffdio_copy __user *user_uffdio_copy;
+	struct userfaultfd_wake_range range;
+
+	user_uffdio_copy = (struct uffdio_copy __user *) arg;
+
+	ret = -EFAULT;
+	if (copy_from_user(&uffdio_copy, user_uffdio_copy,
+			   /* don't copy "copy" and "wake" last field */
+			   sizeof(uffdio_copy)-sizeof(__s64)*2))
+		goto out;
+
+	ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
+	if (ret)
+		goto out;
+	/*
+	 * double check for wraparound just in case. copy_from_user()
+	 * will later check uffdio_copy.src + uffdio_copy.len to fit
+	 * in the userland range.
+	 */
+	ret = -EINVAL;
+	if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src)
+		goto out;
+	if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE)
+		goto out;
+
+	ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
+			   uffdio_copy.len);
+	if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
+		return -EFAULT;
+	if (ret < 0)
+		goto out;
+	BUG_ON(!ret);
+	/* len == 0 would wake all */
+	range.len = ret;
+	if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) {
+		range.start = uffdio_copy.dst;
+		ret = wake_userfault(ctx, &range);
+		if (unlikely(put_user(ret, &user_uffdio_copy->wake)))
+			return -EFAULT;
+	}
+	ret = range.len == uffdio_copy.len ? 0 : -EAGAIN;
+out:
+	return ret;
+}
+
+static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
+				unsigned long arg)
+{
+	__s64 ret;
+	struct uffdio_zeropage uffdio_zeropage;
+	struct uffdio_zeropage __user *user_uffdio_zeropage;
+	struct userfaultfd_wake_range range;
+
+	user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
+
+	ret = -EFAULT;
+	if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
+			   /* don't copy "zeropage" and "wake" last field */
+			   sizeof(uffdio_zeropage)-sizeof(__s64)*2))
+		goto out;
+
+	ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
+			     uffdio_zeropage.range.len);
+	if (ret)
+		goto out;
+	ret = -EINVAL;
+	if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE)
+		goto out;
+
+	ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
+			     uffdio_zeropage.range.len);
+	if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
+		return -EFAULT;
+	if (ret < 0)
+		goto out;
+	/* len == 0 would wake all */
+	BUG_ON(!ret);
+	range.len = ret;
+	if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) {
+		range.start = uffdio_zeropage.range.start;
+		ret = wake_userfault(ctx, &range);
+		if (unlikely(put_user(ret, &user_uffdio_zeropage->wake)))
+			return -EFAULT;
+	}
+	ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN;
+out:
+	return ret;
+}
+
 /*
  * userland asks for a certain API version and we return which bits
  * and ioctl commands are implemented in this kernel for such API

@@ -855,6 +949,12 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
 	case UFFDIO_WAKE:
 		ret = userfaultfd_wake(ctx, arg);
 		break;
+	case UFFDIO_COPY:
+		ret = userfaultfd_copy(ctx, arg);
+		break;
+	case UFFDIO_ZEROPAGE:
+		ret = userfaultfd_zeropage(ctx, arg);
+		break;
 	}
 	return ret;
 }

--

@@ -0,0 +1,977 @@
+/*
+ *  fs/userfaultfd.c
+ *
+ *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
+ *  Copyright (C) 2008-2009 Red Hat, Inc.
+ *  Copyright (C) 2015  Red Hat, Inc.
+ *
+ *  This work is licensed under the terms of the GNU GPL, version 2. See
+ *  the COPYING file in the top-level directory.
+ *
+ *  Some part derived from fs/eventfd.c (anon inode setup) and
+ *  mm/ksm.c (mm hashing).
+ */
+
+#include <linux/hashtable.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+#include <linux/file.h>
+#include <linux/bug.h>
+#include <linux/anon_inodes.h>
+#include <linux/syscalls.h>
+#include <linux/userfaultfd_k.h>
+#include <linux/mempolicy.h>
+#include <linux/ioctl.h>
+#include <linux/security.h>
+
+enum userfaultfd_state {
+	UFFD_STATE_WAIT_API,
+	UFFD_STATE_RUNNING,
+};
+
+struct userfaultfd_ctx {
+	/* pseudo fd refcounting */
+	atomic_t refcount;
+	/* waitqueue head for the userfaultfd page faults */
+	wait_queue_head_t fault_wqh;
+	/* waitqueue head for the pseudo fd to wakeup poll/read */
+	wait_queue_head_t fd_wqh;
+	/* userfaultfd syscall flags */
+	unsigned int flags;
+	/* state machine */
+	enum userfaultfd_state state;
+	/* released */
+	bool released;
+	/* mm with one ore more vmas attached to this userfaultfd_ctx */
+	struct mm_struct *mm;
+};
+
+struct userfaultfd_wait_queue {
+	unsigned long address;
+	wait_queue_t wq;
+	bool pending;
+	struct userfaultfd_ctx *ctx;
+};
+
+struct userfaultfd_wake_range {
+	unsigned long start;
+	unsigned long len;
+};
+
+static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode,
+				     int wake_flags, void *key)
+{
+	struct userfaultfd_wake_range *range = key;
+	int ret;
+	struct userfaultfd_wait_queue *uwq;
+	unsigned long start, len;
+
+	uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
+	ret = 0;
+	/* don't wake the pending ones to avoid reads to block */
+	if (uwq->pending && !ACCESS_ONCE(uwq->ctx->released))
+		goto out;
+	/* len == 0 means wake all */
+	start = range->start;
+	len = range->len;
+	if (len && (start > uwq->address || start + len <= uwq->address))
+		goto out;
+	ret = wake_up_state(wq->private, mode);
+	if (ret)
+		/* wake only once, autoremove behavior */
+		list_del_init(&wq->task_list);
+out:
+	return ret;
+}
+
+/**
+ * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
+ * context.
+ * @ctx: [in] Pointer to the userfaultfd context.
+ *
+ * Returns: In case of success, returns not zero.
+ */
+static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
+{
+	if (!atomic_inc_not_zero(&ctx->refcount))
+		BUG();
+}
+
+/**
+ * userfaultfd_ctx_put - Releases a reference to the internal userfaultfd
+ * context.
+ * @ctx: [in] Pointer to userfaultfd context.
+ *
+ * The userfaultfd context reference must have been previously acquired either
+ * with userfaultfd_ctx_get() or userfaultfd_ctx_fdget().
+ */
+static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx)
+{
+	if (atomic_dec_and_test(&ctx->refcount)) {
+		mmdrop(ctx->mm);
+		kfree(ctx);
+	}
+}
+
+static inline unsigned long userfault_address(unsigned long address,
+					      unsigned int flags,
+					      unsigned long reason)
+{
+	BUILD_BUG_ON(PAGE_SHIFT < UFFD_BITS);
+	address &= PAGE_MASK;
+	if (flags & FAULT_FLAG_WRITE)
+		/*
+		 * Encode "write" fault information in the LSB of the
+		 * address read by userland, without depending on
+		 * FAULT_FLAG_WRITE kernel internal value.
+		 */
+		address |= UFFD_BIT_WRITE;
+	if (reason & VM_UFFD_WP)
+		/*
+		 * Encode "reason" fault information as bit number 1
+		 * in the address read by userland. If bit number 1 is
+		 * clear it means the reason is a VM_FAULT_MISSING
+		 * fault.
+		 */
+		address |= UFFD_BIT_WP;
+	return address;
+}
+
+/*
+ * The locking rules involved in returning VM_FAULT_RETRY depending on
+ * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and
+ * FAULT_FLAG_KILLABLE are not straightforward. The "Caution"
+ * recommendation in __lock_page_or_retry is not an understatement.
+ *
+ * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_sem must be released
+ * before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is
+ * not set.
+ *
+ * If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not
+ * set, VM_FAULT_RETRY can still be returned if and only if there are
+ * fatal_signal_pending()s, and the mmap_sem must be released before
+ * returning it.
+ */
+int handle_userfault(struct vm_area_struct *vma, unsigned long address,
+		     unsigned int flags, unsigned long reason)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct userfaultfd_ctx *ctx;
+	struct userfaultfd_wait_queue uwq;
+
+	BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
+
+	ctx = vma->vm_userfaultfd_ctx.ctx;
+	if (!ctx)
+		return VM_FAULT_SIGBUS;
+
+	BUG_ON(ctx->mm != mm);
+
+	VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP));
+	VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP));
+
+	/*
+	 * If it's already released don't get it. This avoids to loop
+	 * in __get_user_pages if userfaultfd_release waits on the
+	 * caller of handle_userfault to release the mmap_sem.
+	 */
+	if (unlikely(ACCESS_ONCE(ctx->released)))
+		return VM_FAULT_SIGBUS;
+
+	/* check that we can return VM_FAULT_RETRY */
+	if (unlikely(!(flags & FAULT_FLAG_ALLOW_RETRY))) {
+		/*
+		 * Validate the invariant that nowait must allow retry
+		 * to be sure not to return SIGBUS erroneously on
+		 * nowait invocations.
+		 */
+		BUG_ON(flags & FAULT_FLAG_RETRY_NOWAIT);
+#ifdef CONFIG_DEBUG_VM
+		if (printk_ratelimit()) {
+			printk(KERN_WARNING
+			       "FAULT_FLAG_ALLOW_RETRY missing %x\n", flags);
+			dump_stack();
+		}
+#endif
+		return VM_FAULT_SIGBUS;
+	}
+
+	/*
+	 * Handle nowait, not much to do other than tell it to retry
+	 * and wait.
+	 */
+	if (flags & FAULT_FLAG_RETRY_NOWAIT)
+		return VM_FAULT_RETRY;
+
+	/* take the reference before dropping the mmap_sem */
+	userfaultfd_ctx_get(ctx);
+
+	/* be gentle and immediately relinquish the mmap_sem */
+	up_read(&mm->mmap_sem);
+
+	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
+	uwq.wq.private = current;
+	uwq.address = userfault_address(address, flags, reason);
+	uwq.pending = true;
+	uwq.ctx = ctx;
+
+	spin_lock(&ctx->fault_wqh.lock);
+	/*
+	 * After the __add_wait_queue the uwq is visible to userland
+	 * through poll/read().
+	 */
+	__add_wait_queue(&ctx->fault_wqh, &uwq.wq);
+	for (;;) {
+		set_current_state(TASK_KILLABLE);
+		if (!uwq.pending || ACCESS_ONCE(ctx->released) ||
+		    fatal_signal_pending(current))
+			break;
+		spin_unlock(&ctx->fault_wqh.lock);
+
+		wake_up_poll(&ctx->fd_wqh, POLLIN);
+		schedule();
+
+		spin_lock(&ctx->fault_wqh.lock);
+	}
+	__remove_wait_queue(&ctx->fault_wqh, &uwq.wq);
+	__set_current_state(TASK_RUNNING);
+	spin_unlock(&ctx->fault_wqh.lock);
+
+	/*
+	 * ctx may go away after this if the userfault pseudo fd is
+	 * already released.
+	 */
+	userfaultfd_ctx_put(ctx);
+
+	return VM_FAULT_RETRY;
+}
+
+static int userfaultfd_release(struct inode *inode, struct file *file)
+{
+	struct userfaultfd_ctx *ctx = file->private_data;
+	struct mm_struct *mm = ctx->mm;
+	struct vm_area_struct *vma, *prev;
+	/* len == 0 means wake all */
+	struct userfaultfd_wake_range range = { .len = 0, };
+	unsigned long new_flags;
+
+	ACCESS_ONCE(ctx->released) = true;
+
+	/*
+	 * Flush page faults out of all CPUs. NOTE: all page faults
+	 * must be retried without returning VM_FAULT_SIGBUS if
+	 * userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx
+	 * changes while handle_userfault released the mmap_sem. So
+	 * it's critical that released is set to true (above), before
+	 * taking the mmap_sem for writing.
+	 */
+	down_write(&mm->mmap_sem);
+	prev = NULL;
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		cond_resched();
+		BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^
+		       !!(vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+		if (vma->vm_userfaultfd_ctx.ctx != ctx) {
+			prev = vma;
+			continue;
+		}
+		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
+		prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
+				 new_flags, vma->anon_vma,
+				 vma->vm_file, vma->vm_pgoff,
+				 vma_policy(vma),
+				 NULL_VM_UFFD_CTX);
+		if (prev)
+			vma = prev;
+		else
+			prev = vma;
+		vma->vm_flags = new_flags;
+		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+	}
+	up_write(&mm->mmap_sem);
+
+	/*
+	 * After no new page faults can wait on this fault_wqh, flush
+	 * the last page faults that may have been already waiting on
+	 * the fault_wqh.
+	 */
+	spin_lock(&ctx->fault_wqh.lock);
+	__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, &range);
+	spin_unlock(&ctx->fault_wqh.lock);
+
+	wake_up_poll(&ctx->fd_wqh, POLLHUP);
+	userfaultfd_ctx_put(ctx);
+	return 0;
+}
+
+static inline unsigned int find_userfault(struct userfaultfd_ctx *ctx,
+					  struct userfaultfd_wait_queue **uwq)
+{
+	wait_queue_t *wq;
+	struct userfaultfd_wait_queue *_uwq;
+	unsigned int ret = 0;
+
+	spin_lock(&ctx->fault_wqh.lock);
+	list_for_each_entry(wq, &ctx->fault_wqh.task_list, task_list) {
+		_uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
+		if (_uwq->pending) {
+			ret = POLLIN;
+			if (uwq)
+				*uwq = _uwq;
+			break;
+		}
+	}
+	spin_unlock(&ctx->fault_wqh.lock);
+
+	return ret;
+}
+
+static unsigned int userfaultfd_poll(struct file *file, poll_table *wait)
+{
+	struct userfaultfd_ctx *ctx = file->private_data;
+
+	poll_wait(file, &ctx->fd_wqh, wait);
+
+	switch (ctx->state) {
+	case UFFD_STATE_WAIT_API:
+		return POLLERR;
+	case UFFD_STATE_RUNNING:
+		return find_userfault(ctx, NULL);
+	default:
+		BUG();
+	}
+}
+
+static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
+				    __u64 *addr)
+{
+	ssize_t ret;
+	DECLARE_WAITQUEUE(wait, current);
+	struct userfaultfd_wait_queue *uwq = NULL;
+
+	/* always take the fd_wqh lock before the fault_wqh lock */
+	spin_lock(&ctx->fd_wqh.lock);
+	__add_wait_queue(&ctx->fd_wqh, &wait);
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (find_userfault(ctx, &uwq)) {
+			uwq->pending = false;
+			/* careful to always initialize addr if ret == 0 */
+			*addr = uwq->address;
+			ret = 0;
+			break;
+		}
+		if (signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+		if (no_wait) {
+			ret = -EAGAIN;
+			break;
+		}
+		spin_unlock(&ctx->fd_wqh.lock);
+		schedule();
+		spin_lock_irq(&ctx->fd_wqh.lock);
+	}
+	__remove_wait_queue(&ctx->fd_wqh, &wait);
+	__set_current_state(TASK_RUNNING);
+	spin_unlock_irq(&ctx->fd_wqh.lock);
+
+	return ret;
+}
+
+static ssize_t userfaultfd_read(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct userfaultfd_ctx *ctx = file->private_data;
+	ssize_t _ret, ret = 0;
+	/* careful to always initialize addr if ret == 0 */
+	__u64 uninitialized_var(addr);
+	int no_wait = file->f_flags & O_NONBLOCK;
+
+	if (ctx->state == UFFD_STATE_WAIT_API)
+		return -EINVAL;
+	BUG_ON(ctx->state != UFFD_STATE_RUNNING);
+
+	for (;;) {
+		if (count < sizeof(addr))
+			return ret ? ret : -EINVAL;
+		_ret = userfaultfd_ctx_read(ctx, no_wait, &addr);
+		if (_ret < 0)
+			return ret ? ret : _ret;
+		if (put_user(addr, (__u64 __user *) buf))
+			return ret ? ret : -EFAULT;
+		ret += sizeof(addr);
+		buf += sizeof(addr);
+		count -= sizeof(addr);
+		/*
+		 * Allow to read more than one fault at time but only
+		 * block if waiting for the very first one.
+		 */
+		no_wait = O_NONBLOCK;
+	}
+}
+
+static int __wake_userfault(struct userfaultfd_ctx *ctx,
+			    struct userfaultfd_wake_range *range)
+{
+	wait_queue_t *wq;
+	struct userfaultfd_wait_queue *uwq;
+	int ret;
+	unsigned long start, end;
+
+	start = range->start;
+	end = range->start + range->len;
+
+	ret = -ENOENT;
+	spin_lock(&ctx->fault_wqh.lock);
+	list_for_each_entry(wq, &ctx->fault_wqh.task_list, task_list) {
+		uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
+		if (uwq->pending)
+			continue;
+		if (uwq->address >= start && uwq->address < end) {
+			ret = 0;
+			/* wake all in the range and autoremove */
+			__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0,
+					     range);
+			break;
+		}
+	}
+	spin_unlock(&ctx->fault_wqh.lock);
+
+	return ret;
+}
+
+static __always_inline int wake_userfault(struct userfaultfd_ctx *ctx,
+					  struct userfaultfd_wake_range *range)
+{
+	if (!waitqueue_active(&ctx->fault_wqh))
+		return -ENOENT;
+
+	return __wake_userfault(ctx, range);
+}
+
+static __always_inline int validate_range(struct mm_struct *mm,
+					  __u64 start, __u64 len)
+{
+	__u64 task_size = mm->task_size;
+
+	if (start & ~PAGE_MASK)
+		return -EINVAL;
+	if (len & ~PAGE_MASK)
+		return -EINVAL;
+	if (!len)
+		return -EINVAL;
+	if (start < mmap_min_addr)
+		return -EINVAL;
+	if (start >= task_size)
+		return -EINVAL;
+	if (len > task_size - start)
+		return -EINVAL;
+	return 0;
+}
+
+static int userfaultfd_register(struct userfaultfd_ctx *ctx,
+				unsigned long arg)
+{
+	struct mm_struct *mm = ctx->mm;
+	struct vm_area_struct *vma, *prev, *cur;
+	int ret;
+	struct uffdio_register uffdio_register;
+	struct uffdio_register __user *user_uffdio_register;
+	unsigned long vm_flags, new_flags;
+	bool found;
+	unsigned long start, end, vma_end;
+
+	user_uffdio_register = (struct uffdio_register __user *) arg;
+
+	ret = -EFAULT;
+	if (copy_from_user(&uffdio_register, user_uffdio_register,
+			   sizeof(uffdio_register)-sizeof(__u64)))
+		goto out;
+
+	ret = -EINVAL;
+	if (!uffdio_register.mode)
+		goto out;
+	if (uffdio_register.mode & ~(UFFDIO_REGISTER_MODE_MISSING|
+				     UFFDIO_REGISTER_MODE_WP))
+		goto out;
+	vm_flags = 0;
+	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
+		vm_flags |= VM_UFFD_MISSING;
+	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) {
+		vm_flags |= VM_UFFD_WP;
+		/*
+		 * FIXME: remove the below error constraint by
+		 * implementing the wprotect tracking mode.
+		 */
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = validate_range(mm, uffdio_register.range.start,
+			     uffdio_register.range.len);
+	if (ret)
+		goto out;
+
+	start = uffdio_register.range.start;
+	end = start + uffdio_register.range.len;
+
+	down_write(&mm->mmap_sem);
+	vma = find_vma_prev(mm, start, &prev);
+
+	ret = -ENOMEM;
+	if (!vma)
+		goto out_unlock;
+
+	/* check that there's at least one vma in the range */
+	ret = -EINVAL;
+	if (vma->vm_start >= end)
+		goto out_unlock;
+
+	/*
+	 * Search for not compatible vmas.
+	 *
+	 * FIXME: this shall be relaxed later so that it doesn't fail
+	 * on tmpfs backed vmas (in addition to the current allowance
+	 * on anonymous vmas).
+	 */
+	found = false;
+	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
+		cond_resched();
+
+		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
+		       !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+
+		/* check not compatible vmas */
+		ret = -EINVAL;
+		if (cur->vm_ops)
+			goto out_unlock;
+
+		/*
+		 * Check that this vma isn't already owned by a
+		 * different userfaultfd. We can't allow more than one
+		 * userfaultfd to own a single vma simultaneously or we
+		 * wouldn't know which one to deliver the userfaults to.
+		 */
+		ret = -EBUSY;
+		if (cur->vm_userfaultfd_ctx.ctx &&
+		    cur->vm_userfaultfd_ctx.ctx != ctx)
+			goto out_unlock;
+
+		found = true;
+	}
+	BUG_ON(!found);
+
+	/*
+	 * Now that we scanned all vmas we can already tell userland which
+	 * ioctls methods are guaranteed to succeed on this range.
+	 */
+	ret = -EFAULT;
+	if (put_user(UFFD_API_RANGE_IOCTLS, &user_uffdio_register->ioctls))
+		goto out_unlock;
+
+	if (vma->vm_start < start)
+		prev = vma;
+
+	ret = 0;
+	do {
+		cond_resched();
+
+		BUG_ON(vma->vm_ops);
+		BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
+		       vma->vm_userfaultfd_ctx.ctx != ctx);
+
+		/*
+		 * Nothing to do: this vma is already registered into this
+		 * userfaultfd and with the right tracking mode too.
+		 */
+		if (vma->vm_userfaultfd_ctx.ctx == ctx &&
+		    (vma->vm_flags & vm_flags) == vm_flags)
+			goto skip;
+
+		if (vma->vm_start > start)
+			start = vma->vm_start;
+		vma_end = min(end, vma->vm_end);
+
+		new_flags = (vma->vm_flags & ~vm_flags) | vm_flags;
+		prev = vma_merge(mm, prev, start, vma_end, new_flags,
+				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
+				 vma_policy(vma),
+				 ((struct vm_userfaultfd_ctx){ ctx }));
+		if (prev) {
+			vma = prev;
+			goto next;
+		}
+		if (vma->vm_start < start) {
+			ret = split_vma(mm, vma, start, 1);
+			if (ret)
+				break;
+		}
+		if (vma->vm_end > end) {
+			ret = split_vma(mm, vma, end, 0);
+			if (ret)
+				break;
+		}
+	next:
+		/*
+		 * In the vma_merge() successful mprotect-like case 8:
+		 * the next vma was merged into the current one and
+		 * the current one has not been updated yet.
+		 */
+		vma->vm_flags = new_flags;
+		vma->vm_userfaultfd_ctx.ctx = ctx;
+
+	skip:
+		prev = vma;
+		start = vma->vm_end;
+		vma = vma->vm_next;
+	} while (vma && vma->vm_start < end);
+out_unlock:
+	up_write(&mm->mmap_sem);
+out:
+	return ret;
+}
+
+static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
+				  unsigned long arg)
+{
+	struct mm_struct *mm = ctx->mm;
+	struct vm_area_struct *vma, *prev, *cur;
+	int ret;
+	struct uffdio_range uffdio_unregister;
+	unsigned long new_flags;
+	bool found;
+	unsigned long start, end, vma_end;
+	const void __user *buf = (void __user *)arg;
+
+	ret = -EFAULT;
+	if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
+		goto out;
+
+	ret = validate_range(mm, uffdio_unregister.start,
+			     uffdio_unregister.len);
+	if (ret)
+		goto out;
+
+	start = uffdio_unregister.start;
+	end = start + uffdio_unregister.len;
+
+	down_write(&mm->mmap_sem);
+	vma = find_vma_prev(mm, start, &prev);
+
+	ret = -ENOMEM;
+	if (!vma)
+		goto out_unlock;
+
+	/* check that there's at least one vma in the range */
+	ret = -EINVAL;
+	if (vma->vm_start >= end)
+		goto out_unlock;
+
+	/*
+	 * Search for not compatible vmas.
+	 *
+	 * FIXME: this shall be relaxed later so that it doesn't fail
+	 * on tmpfs backed vmas (in addition to the current allowance
+	 * on anonymous vmas).
+	 */
+	found = false;
+	ret = -EINVAL;
+	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
+		cond_resched();
+
+		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
+		       !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+
+		/*
+		 * Check not compatible vmas, not strictly required
+		 * here as not compatible vmas cannot have an
+		 * userfaultfd_ctx registered on them, but this
+		 * provides for more strict behavior to notice
+		 * unregistration errors.
+		 */
+		if (cur->vm_ops)
+			goto out_unlock;
+
+		found = true;
+	}
+	BUG_ON(!found);
+
+	if (vma->vm_start < start)
+		prev = vma;
+
+	ret = 0;
+	do {
+		cond_resched();
+
+		BUG_ON(vma->vm_ops);
+
+		/*
+		 * Nothing to do: this vma is already registered into this
+		 * userfaultfd and with the right tracking mode too.
+		 */
+		if (!vma->vm_userfaultfd_ctx.ctx)
+			goto skip;
+
+		if (vma->vm_start > start)
+			start = vma->vm_start;
+		vma_end = min(end, vma->vm_end);
+
+		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
+		prev = vma_merge(mm, prev, start, vma_end, new_flags,
+				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
+				 vma_policy(vma),
+				 NULL_VM_UFFD_CTX);
+		if (prev) {
+			vma = prev;
+			goto next;
+		}
+		if (vma->vm_start < start) {
+			ret = split_vma(mm, vma, start, 1);
+			if (ret)
+				break;
+		}
+		if (vma->vm_end > end) {
+			ret = split_vma(mm, vma, end, 0);
+			if (ret)
+				break;
+		}
+	next:
+		/*
+		 * In the vma_merge() successful mprotect-like case 8:
+		 * the next vma was merged into the current one and
+		 * the current one has not been updated yet.
+		 */
+		vma->vm_flags = new_flags;
+		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+
+	skip:
+		prev = vma;
+		start = vma->vm_end;
+		vma = vma->vm_next;
+	} while (vma && vma->vm_start < end);
+out_unlock:
+	up_write(&mm->mmap_sem);
+out:
+	return ret;
+}
+
+/*
+ * This is mostly needed to re-wakeup those userfaults that were still
+ * pending when userland wake them up the first time. We don't wake
+ * the pending one to avoid blocking reads to block, or non blocking
+ * read to return -EAGAIN, if used with POLLIN, to avoid userland
+ * doubts on why POLLIN wasn't reliable.
+ */
+static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
+			    unsigned long arg)
+{
+	int ret;
+	struct uffdio_range uffdio_wake;
+	struct userfaultfd_wake_range range;
+	const void __user *buf = (void __user *)arg;
+
+	ret = -EFAULT;
+	if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
+		goto out;
+
+	ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
+	if (ret)
+		goto out;
+
+	range.start = uffdio_wake.start;
+	range.len = uffdio_wake.len;
+
+	/*
+	 * len == 0 means wake all and we don't want to wake all here,
+	 * so check it again to be sure.
+	 */
+	VM_BUG_ON(!range.len);
+
+	ret = wake_userfault(ctx, &range);
+
+out:
+	return ret;
+}
+
+/*
+ * userland asks for a certain API version and we return which bits
+ * and ioctl commands are implemented in this kernel for such API
+ * version or -EINVAL if unknown.
+ */
+static int userfaultfd_api(struct userfaultfd_ctx *ctx,
+			   unsigned long arg)
+{
+	struct uffdio_api uffdio_api;
+	void __user *buf = (void __user *)arg;
+	int ret;
+
+	ret = -EINVAL;
+	if (ctx->state != UFFD_STATE_WAIT_API)
+		goto out;
+	ret = -EFAULT;
+	if (copy_from_user(&uffdio_api, buf, sizeof(__u64)))
+		goto out;
+	if (uffdio_api.api != UFFD_API) {
+		/* careful not to leak info, we only read the first 8 bytes */
+		memset(&uffdio_api, 0, sizeof(uffdio_api));
+		if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
+			goto out;
+		ret = -EINVAL;
+		goto out;
+	}
+	/* careful not to leak info, we only read the first 8 bytes */
+	uffdio_api.bits = UFFD_API_BITS;
+	uffdio_api.ioctls = UFFD_API_IOCTLS;
+	ret = -EFAULT;
+	if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
+		goto out;
+	ctx->state = UFFD_STATE_RUNNING;
+	ret = 0;
+out:
+	return ret;
+}
+
+static long userfaultfd_ioctl(struct file *file, unsigned cmd,
+			      unsigned long arg)
+{
+	int ret = -EINVAL;
+	struct userfaultfd_ctx *ctx = file->private_data;
+
+	switch(cmd) {
+	case UFFDIO_API:
+		ret = userfaultfd_api(ctx, arg);
+		break;
+	case UFFDIO_REGISTER:
+		ret = userfaultfd_register(ctx, arg);
+		break;
+	case UFFDIO_UNREGISTER:
+		ret = userfaultfd_unregister(ctx, arg);
+		break;
+	case UFFDIO_WAKE:
+		ret = userfaultfd_wake(ctx, arg);
+		break;
+	}
+	return ret;
+}
+
+#ifdef CONFIG_PROC_FS
+static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct userfaultfd_ctx *ctx = f->private_data;
+	wait_queue_t *wq;
+	struct userfaultfd_wait_queue *uwq;
+	unsigned long pending = 0, total = 0;
+
+	spin_lock(&ctx->fault_wqh.lock);
+	list_for_each_entry(wq, &ctx->fault_wqh.task_list, task_list) {
+		uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
+		if (uwq->pending)
+			pending++;
+		total++;
+	}
+	spin_unlock(&ctx->fault_wqh.lock);
+
+	/*
+	 * If more protocols will be added, there will be all shown
+	 * separated by a space. Like this:
+	 *	protocols: 0xaa 0xbb
+	 */
+	seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n",
+		   pending, total, UFFD_API, UFFD_API_BITS,
+		   UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS);
+}
+#endif
+
+static const struct file_operations userfaultfd_fops = {
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= userfaultfd_show_fdinfo,
+#endif
+	.release	= userfaultfd_release,
+	.poll		= userfaultfd_poll,
+	.read		= userfaultfd_read,
+	.unlocked_ioctl = userfaultfd_ioctl,
+	.compat_ioctl	= userfaultfd_ioctl,
+	.llseek		= noop_llseek,
+};
+
+/**
+ * userfaultfd_file_create - Creates an userfaultfd file pointer.
+ * @flags: Flags for the userfaultfd file.
+ *
+ * This function creates an userfaultfd file pointer, w/out installing
+ * it into the fd table. This is useful when the userfaultfd file is
+ * used during the initialization of data structures that require
+ * extra setup after the userfaultfd creation. So the userfaultfd
+ * creation is split into the file pointer creation phase, and the
+ * file descriptor installation phase.  In this way races with
+ * userspace closing the newly installed file descriptor can be
+ * avoided.  Returns an userfaultfd file pointer, or a proper error
+ * pointer.
+ */
+static struct file *userfaultfd_file_create(int flags)
+{
+	struct file *file;
+	struct userfaultfd_ctx *ctx;
+
+	BUG_ON(!current->mm);
+
+	/* Check the UFFD_* constants for consistency.  */
+	BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC);
+	BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK);
+
+	file = ERR_PTR(-EINVAL);
+	if (flags & ~UFFD_SHARED_FCNTL_FLAGS)
+		goto out;
+
+	file = ERR_PTR(-ENOMEM);
+	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		goto out;
+
+	atomic_set(&ctx->refcount, 1);
+	init_waitqueue_head(&ctx->fault_wqh);
+	init_waitqueue_head(&ctx->fd_wqh);
+	ctx->flags = flags;
+	ctx->state = UFFD_STATE_WAIT_API;
+	ctx->released = false;
+	ctx->mm = current->mm;
+	/* prevent the mm struct to be freed */
+	atomic_inc(&ctx->mm->mm_count);
+
+	file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, ctx,
+				  O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS));
+	if (IS_ERR(file))
+		kfree(ctx);
+out:
+	return file;
+}
+
+SYSCALL_DEFINE1(userfaultfd, int, flags)
+{
+	int fd, error;
+	struct file *file;
+
+	error = get_unused_fd_flags(flags & UFFD_SHARED_FCNTL_FLAGS);
+	if (error < 0)
+		return error;
+	fd = error;
+
+	file = userfaultfd_file_create(flags);
+	if (IS_ERR(file)) {
+		error = PTR_ERR(file);
+		goto err_put_unused_fd;
+	}
+	fd_install(fd, file);
+
+	return fd;
+
+err_put_unused_fd:
+	put_unused_fd(fd);
+
+	return error;
+}