[PATCH] allow vma merging with mlock et. al.

Successive mlock/munlock calls can leave fragmented vmas because they can
be split but not merged.  Give mlock et.  al.  full vma merging support.
While we're at it, move *pprev assignment above first split_vma in
mprotect_fixup to keep it in step with mlock_fixup (which for mlockall
ignores errors yet still needs a valid prev pointer).
Signed-off-by: Chris Wright <chrisw@osdl.org>
Acked-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

mm/mlock.c

@@ -7,18 +7,32 @@
 
 #include <linux/mman.h>
 #include <linux/mm.h>
+#include <linux/mempolicy.h>
 #include <linux/syscalls.h>
 
 
-static int mlock_fixup(struct vm_area_struct * vma, 
+static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	unsigned long start, unsigned long end, unsigned int newflags)
 {
 	struct mm_struct * mm = vma->vm_mm;
+	pgoff_t pgoff;
 	int pages;
 	int ret = 0;
 
-	if (newflags == vma->vm_flags)
+	if (newflags == vma->vm_flags) {
+		*prev = vma;
 		goto out;
+	}
+
+	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+	*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
+			  vma->vm_file, pgoff, vma_policy(vma));
+	if (*prev) {
+		vma = *prev;
+		goto success;
+	}
+
+	*prev = vma;
 
 	if (start != vma->vm_start) {
 		ret = split_vma(mm, vma, start, 1);
@@ -32,6 +46,7 @@ static int mlock_fixup(struct vm_area_struct * vma,
 			goto out;
 	}
 
+success:
 	/*
 	 * vm_flags is protected by the mmap_sem held in write mode.
 	 * It's okay if try_to_unmap_one unmaps a page just after we
@@ -59,7 +74,7 @@ static int mlock_fixup(struct vm_area_struct * vma,
 static int do_mlock(unsigned long start, size_t len, int on)
 {
 	unsigned long nstart, end, tmp;
-	struct vm_area_struct * vma, * next;
+	struct vm_area_struct * vma, * prev;
 	int error;
 
 	len = PAGE_ALIGN(len);
@@ -68,10 +83,13 @@ static int do_mlock(unsigned long start, size_t len, int on)
 		return -EINVAL;
 	if (end == start)
 		return 0;
-	vma = find_vma(current->mm, start);
+	vma = find_vma_prev(current->mm, start, &prev);
 	if (!vma || vma->vm_start > start)
 		return -ENOMEM;
 
+	if (start > vma->vm_start)
+		prev = vma;
+
 	for (nstart = start ; ; ) {
 		unsigned int newflags;
 
@@ -81,18 +99,19 @@ static int do_mlock(unsigned long start, size_t len, int on)
 		if (!on)
 			newflags &= ~VM_LOCKED;
 
-		if (vma->vm_end >= end) {
-			error = mlock_fixup(vma, nstart, end, newflags);
-			break;
-		}
-
 		tmp = vma->vm_end;
-		next = vma->vm_next;
-		error = mlock_fixup(vma, nstart, tmp, newflags);
+		if (tmp > end)
+			tmp = end;
+		error = mlock_fixup(vma, &prev, nstart, tmp, newflags);
 		if (error)
 			break;
 		nstart = tmp;
-		vma = next;
+		if (nstart < prev->vm_end)
+			nstart = prev->vm_end;
+		if (nstart >= end)
+			break;
+
+		vma = prev->vm_next;
 		if (!vma || vma->vm_start != nstart) {
 			error = -ENOMEM;
 			break;
@@ -141,7 +160,7 @@ asmlinkage long sys_munlock(unsigned long start, size_t len)
 
 static int do_mlockall(int flags)
 {
-	struct vm_area_struct * vma;
+	struct vm_area_struct * vma, * prev = NULL;
 	unsigned int def_flags = 0;
 
 	if (flags & MCL_FUTURE)
@@ -150,7 +169,7 @@ static int do_mlockall(int flags)
 	if (flags == MCL_FUTURE)
 		goto out;
 
-	for (vma = current->mm->mmap; vma ; vma = vma->vm_next) {
+	for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
 		unsigned int newflags;
 
 		newflags = vma->vm_flags | VM_LOCKED;
@@ -158,7 +177,7 @@ static int do_mlockall(int flags)
 			newflags &= ~VM_LOCKED;
 
 		/* Ignore errors */
-		mlock_fixup(vma, vma->vm_start, vma->vm_end, newflags);
+		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
 	}
 out:
 	return 0;

mm/mprotect.c

@@ -188,16 +188,13 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 		goto success;
 	}
 
+	*pprev = vma;
+
 	if (start != vma->vm_start) {
 		error = split_vma(mm, vma, start, 1);
 		if (error)
 			goto fail;
 	}
-	/*
-	 * Unless it returns an error, this function always sets *pprev to
-	 * the first vma for which vma->vm_end >= end.
-	 */
-	*pprev = vma;
 
 	if (end != vma->vm_end) {
 		error = split_vma(mm, vma, end, 0);