mm: mlock: add mlock flags to enable VM_LOCKONFAULT usage

The previous patch introduced a flag that specified pages in a VMA should
be placed on the unevictable LRU, but they should not be made present when
the area is created.  This patch adds the ability to set this state via
the new mlock system calls.

We add MLOCK_ONFAULT for mlock2 and MCL_ONFAULT for mlockall.
MLOCK_ONFAULT will set the VM_LOCKONFAULT modifier for VM_LOCKED.
MCL_ONFAULT should be used as a modifier to the two other mlockall flags.
When used with MCL_CURRENT, all current mappings will be marked with
VM_LOCKED | VM_LOCKONFAULT.  When used with MCL_FUTURE, the mm->def_flags
will be marked with VM_LOCKED | VM_LOCKONFAULT.  When used with both
MCL_CURRENT and MCL_FUTURE, all current mappings and mm->def_flags will be
marked with VM_LOCKED | VM_LOCKONFAULT.

Prior to this patch, mlockall() will unconditionally clear the
mm->def_flags any time it is called without MCL_FUTURE.  This behavior is
maintained after adding MCL_ONFAULT.  If a call to mlockall(MCL_FUTURE) is
followed by mlockall(MCL_CURRENT), the mm->def_flags will be cleared and
new VMAs will be unlocked.  This remains true with or without MCL_ONFAULT
in either mlockall() invocation.

munlock() will unconditionally clear both vma flags.  munlockall()
unconditionally clears for VMA flags on all VMAs and in the mm->def_flags
field.
Signed-off-by: Eric B Munson <emunson@akamai.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/alpha/include/uapi/asm/mman.h

@@ -37,6 +37,9 @@
 
 #define MCL_CURRENT	 8192		/* lock all currently mapped pages */
 #define MCL_FUTURE	16384		/* lock all additions to address space */
+#define MCL_ONFAULT	32768		/* lock all pages that are faulted in */
+
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL	0		/* no further special treatment */
 #define MADV_RANDOM	1		/* expect random page references */

arch/mips/include/uapi/asm/mman.h

@@ -61,6 +61,12 @@
  */
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL	0		/* no further special treatment */
 #define MADV_RANDOM	1		/* expect random page references */

arch/parisc/include/uapi/asm/mman.h

@@ -31,6 +31,9 @@
 
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
+
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL     0               /* no further special treatment */
 #define MADV_RANDOM     1               /* expect random page references */

arch/powerpc/include/uapi/asm/mman.h

@@ -22,6 +22,7 @@
 
 #define MCL_CURRENT     0x2000          /* lock all currently mapped pages */
 #define MCL_FUTURE      0x4000          /* lock all additions to address space */
+#define MCL_ONFAULT	0x8000		/* lock all pages that are faulted in */
 
 #define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
 #define MAP_NONBLOCK	0x10000		/* do not block on IO */

arch/sparc/include/uapi/asm/mman.h

@@ -17,6 +17,7 @@
 
 #define MCL_CURRENT     0x2000          /* lock all currently mapped pages */
 #define MCL_FUTURE      0x4000          /* lock all additions to address space */
+#define MCL_ONFAULT	0x8000		/* lock all pages that are faulted in */
 
 #define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
 #define MAP_NONBLOCK	0x10000		/* do not block on IO */

arch/tile/include/uapi/asm/mman.h

@@ -36,6 +36,7 @@
  */
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
 
 
 #endif /* _ASM_TILE_MMAN_H */

arch/xtensa/include/uapi/asm/mman.h

@@ -74,6 +74,12 @@
  */
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL	0		/* no further special treatment */
 #define MADV_RANDOM	1		/* expect random page references */

include/uapi/asm-generic/mman-common.h

@@ -25,6 +25,11 @@
 # define MAP_UNINITIALIZED 0x0		/* Don't support this flag */
 #endif
 
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
+
 #define MS_ASYNC	1		/* sync memory asynchronously */
 #define MS_INVALIDATE	2		/* invalidate the caches */
 #define MS_SYNC		4		/* synchronous memory sync */

include/uapi/asm-generic/mman.h

@@ -17,5 +17,6 @@
 
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
 
 #endif /* __ASM_GENERIC_MMAN_H */

mm/mlock.c

@@ -506,7 +506,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 
 	if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
 	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
-		goto out;	/* don't set VM_LOCKED,  don't count */
+		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
+		goto out;
 
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 	*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
@@ -577,7 +578,7 @@ static int apply_vma_lock_flags(unsigned long start, size_t len,
 		prev = vma;
 
 	for (nstart = start ; ; ) {
-		vm_flags_t newflags = vma->vm_flags & ~VM_LOCKED;
+		vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
 
 		newflags |= flags;
 
@@ -646,10 +647,15 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 
 SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
 {
-	if (flags)
+	vm_flags_t vm_flags = VM_LOCKED;
+
+	if (flags & ~MLOCK_ONFAULT)
 		return -EINVAL;
 
-	return do_mlock(start, len, VM_LOCKED);
+	if (flags & MLOCK_ONFAULT)
+		vm_flags |= VM_LOCKONFAULT;
+
+	return do_mlock(start, len, vm_flags);
 }
 
 SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
@@ -666,24 +672,43 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 	return ret;
 }
 
+/*
+ * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall)
+ * and translate into the appropriate modifications to mm->def_flags and/or the
+ * flags for all current VMAs.
+ *
+ * There are a couple of subtleties with this.  If mlockall() is called multiple
+ * times with different flags, the values do not necessarily stack.  If mlockall
+ * is called once including the MCL_FUTURE flag and then a second time without
+ * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags.
+ */
 static int apply_mlockall_flags(int flags)
 {
 	struct vm_area_struct * vma, * prev = NULL;
+	vm_flags_t to_add = 0;
 
-	if (flags & MCL_FUTURE)
+	current->mm->def_flags &= VM_LOCKED_CLEAR_MASK;
+	if (flags & MCL_FUTURE) {
 		current->mm->def_flags |= VM_LOCKED;
-	else
-		current->mm->def_flags &= ~VM_LOCKED;
 
-	if (flags == MCL_FUTURE)
-		goto out;
+		if (flags & MCL_ONFAULT)
+			current->mm->def_flags |= VM_LOCKONFAULT;
+
+		if (!(flags & MCL_CURRENT))
+			goto out;
+	}
+
+	if (flags & MCL_CURRENT) {
+		to_add |= VM_LOCKED;
+		if (flags & MCL_ONFAULT)
+			to_add |= VM_LOCKONFAULT;
+	}
 
 	for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
 		vm_flags_t newflags;
 
-		newflags = vma->vm_flags & ~VM_LOCKED;
-		if (flags & MCL_CURRENT)
-			newflags |= VM_LOCKED;
+		newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
+		newflags |= to_add;
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
@@ -698,7 +723,7 @@ SYSCALL_DEFINE1(mlockall, int, flags)
 	unsigned long lock_limit;
 	int ret;
 
-	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
+	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)))
 		return -EINVAL;
 
 	if (!can_do_mlock())