mm: introduce mm_populate() for populating new vmas

When creating new mappings using the MAP_POPULATE / MAP_LOCKED flags (or
with MCL_FUTURE in effect), we want to populate the pages within the
newly created vmas.  This may take a while as we may have to read pages
from disk, so ideally we want to do this outside of the write-locked
mmap_sem region.

This change introduces mm_populate(), which is used to defer populating
such mappings until after the mmap_sem write lock has been released.
This is implemented as a generalization of the former do_mlock_pages(),
which accomplished the same task but was using during mlock() /
mlockall().

Signed-off-by: Michel Lespinasse <walken@google.com>
Reported-by: Andy Lutomirski <luto@amacapital.net>
Acked-by: Rik van Riel <riel@redhat.com>
Tested-by: Andy Lutomirski <luto@amacapital.net>
Cc: Greg Ungerer <gregungerer@westnet.com.au>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/mlock.c b/mm/mlock.c
index c9bd528..a296a49 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -416,7 +416,14 @@
 	return error;
 }
 
-static int do_mlock_pages(unsigned long start, size_t len, int ignore_errors)
+/*
+ * __mm_populate - populate and/or mlock pages within a range of address space.
+ *
+ * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
+ * flags. VMAs must be already marked with the desired vm_flags, and
+ * mmap_sem must not be held.
+ */
+int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long end, nstart, nend;
@@ -498,7 +505,7 @@
 		error = do_mlock(start, len, 1);
 	up_write(&current->mm->mmap_sem);
 	if (!error)
-		error = do_mlock_pages(start, len, 0);
+		error = __mm_populate(start, len, 0);
 	return error;
 }
 
@@ -564,10 +571,8 @@
 	    capable(CAP_IPC_LOCK))
 		ret = do_mlockall(flags);
 	up_write(&current->mm->mmap_sem);
-	if (!ret && (flags & MCL_CURRENT)) {
-		/* Ignore errors */
-		do_mlock_pages(0, TASK_SIZE, 1);
-	}
+	if (!ret && (flags & MCL_CURRENT))
+		mm_populate(0, TASK_SIZE);
 out:
 	return ret;
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index 09da0b2..9b12e30 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1154,12 +1154,15 @@
 
 unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			unsigned long len, unsigned long prot,
-			unsigned long flags, unsigned long pgoff)
+			unsigned long flags, unsigned long pgoff,
+			bool *populate)
 {
 	struct mm_struct * mm = current->mm;
 	struct inode *inode;
 	vm_flags_t vm_flags;
 
+	*populate = false;
+
 	/*
 	 * Does the application expect PROT_READ to imply PROT_EXEC?
 	 *
@@ -1280,7 +1283,12 @@
 		}
 	}
 
-	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
+	addr = mmap_region(file, addr, len, flags, vm_flags, pgoff);
+	if (!IS_ERR_VALUE(addr) &&
+	    ((vm_flags & VM_LOCKED) ||
+	     (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
+		*populate = true;
+	return addr;
 }
 
 SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
@@ -1531,10 +1539,12 @@
 
 	vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
 	if (vm_flags & VM_LOCKED) {
-		if (!mlock_vma_pages_range(vma, addr, addr + len))
+		if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) ||
+					vma == get_gate_vma(current->mm)))
 			mm->locked_vm += (len >> PAGE_SHIFT);
-	} else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK))
-		make_pages_present(addr, addr + len);
+		else
+			vma->vm_flags &= ~VM_LOCKED;
+	}
 
 	if (file)
 		uprobe_mmap(vma);
diff --git a/mm/nommu.c b/mm/nommu.c
index b20db4e..7296a5a 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1250,7 +1250,8 @@
 			    unsigned long len,
 			    unsigned long prot,
 			    unsigned long flags,
-			    unsigned long pgoff)
+			    unsigned long pgoff,
+			    bool *populate)
 {
 	struct vm_area_struct *vma;
 	struct vm_region *region;
@@ -1260,6 +1261,8 @@
 
 	kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff);
 
+	*populate = false;
+
 	/* decide whether we should attempt the mapping, and if so what sort of
 	 * mapping */
 	ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
diff --git a/mm/util.c b/mm/util.c
index c55e26b..13467e0 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -355,12 +355,16 @@
 {
 	unsigned long ret;
 	struct mm_struct *mm = current->mm;
+	bool populate;
 
 	ret = security_mmap_file(file, prot, flag);
 	if (!ret) {
 		down_write(&mm->mmap_sem);
-		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff);
+		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
+				    &populate);
 		up_write(&mm->mmap_sem);
+		if (!IS_ERR_VALUE(ret) && populate)
+			mm_populate(ret, len);
 	}
 	return ret;
 }