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>

1 files changed, 15 insertions, 5 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index 09da0b264982..9b12e3047a86 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1154,12 +1154,15 @@ static inline unsigned long round_hint_to_min(unsigned long hint)
 
 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 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 		}
 	}
 
-	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 @@ out:
 
 	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);