[PATCH] madvise MADV_DONTFORK/MADV_DOFORK

Currently, copy-on-write may change the physical address of a page even if the
user requested that the page is pinned in memory (either by mlock or by
get_user_pages).  This happens if the process forks meanwhile, and the parent
writes to that page.  As a result, the page is orphaned: in case of
get_user_pages, the application will never see any data hardware DMA's into
this page after the COW.  In case of mlock'd memory, the parent is not getting
the realtime/security benefits of mlock.

In particular, this affects the Infiniband modules which do DMA from and into
user pages all the time.

This patch adds madvise options to control whether memory range is inherited
across fork.  Useful e.g.  for when hardware is doing DMA from/into these
pages.  Could also be useful to an application wanting to speed up its forks
by cutting large areas out of consideration.

Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Acked-by: Hugh Dickins <hugh@veritas.com>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/asm-alpha/mman.h

@@ -43,6 +43,8 @@
 #define	MADV_SPACEAVAIL	5		/* ensure resources are available */
 #define MADV_DONTNEED	6		/* don't need these pages */
 #define MADV_REMOVE	7		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-arm/mman.h

@@ -36,6 +36,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-arm26/mman.h

@@ -36,6 +36,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-cris/mman.h

@@ -38,6 +38,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-frv/mman.h

@@ -36,6 +36,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-h8300/mman.h

@@ -36,6 +36,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-i386/mman.h

@@ -36,6 +36,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-ia64/mman.h

@@ -44,6 +44,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-m32r/mman.h

@@ -38,6 +38,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-m68k/mman.h

@@ -36,6 +36,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-mips/mman.h

@@ -66,6 +66,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON       MAP_ANONYMOUS

include/asm-parisc/mman.h

@@ -49,6 +49,8 @@
 #define MADV_4M_PAGES   22              /* Use 4 Megabyte pages */
 #define MADV_16M_PAGES  24              /* Use 16 Megabyte pages */
 #define MADV_64M_PAGES  26              /* Use 64 Megabyte pages */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-powerpc/mman.h

@@ -45,6 +45,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-s390/mman.h

@@ -44,6 +44,8 @@
 #define MADV_WILLNEED  0x3              /* pre-fault pages */
 #define MADV_DONTNEED  0x4              /* discard these pages */
 #define MADV_REMOVE    0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-sh/mman.h

@@ -36,6 +36,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-sparc/mman.h

@@ -55,6 +55,8 @@
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_FREE	0x5		/* (Solaris) contents can be freed */
 #define MADV_REMOVE	0x6		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-sparc64/mman.h

@@ -55,6 +55,8 @@
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_FREE	0x5		/* (Solaris) contents can be freed */
 #define MADV_REMOVE	0x6		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-v850/mman.h

@@ -33,6 +33,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-x86_64/mman.h

@@ -37,6 +37,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON	MAP_ANONYMOUS

include/asm-xtensa/mman.h

@@ -73,6 +73,8 @@
 #define MADV_WILLNEED	0x3		/* pre-fault pages */
 #define MADV_DONTNEED	0x4		/* discard these pages */
 #define MADV_REMOVE	0x5		/* remove these pages & resources */
+#define MADV_DONTFORK	0x30		/* dont inherit across fork */
+#define MADV_DOFORK	0x31		/* do inherit across fork */
 
 /* compatibility flags */
 #define MAP_ANON       MAP_ANONYMOUS

mm/madvise.c

@@ -22,16 +22,23 @@ static long madvise_behavior(struct vm_area_struct * vma,
 	struct mm_struct * mm = vma->vm_mm;
 	int error = 0;
 	pgoff_t pgoff;
-	int new_flags = vma->vm_flags & ~VM_READHINTMASK;
+	int new_flags = vma->vm_flags;
 
 	switch (behavior) {
+	case MADV_NORMAL:
+		new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ;
+		break;
 	case MADV_SEQUENTIAL:
-		new_flags |= VM_SEQ_READ;
+		new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ;
 		break;
 	case MADV_RANDOM:
-		new_flags |= VM_RAND_READ;
+		new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ;
 		break;
-	default:
+	case MADV_DONTFORK:
+		new_flags |= VM_DONTCOPY;
+		break;
+	case MADV_DOFORK:
+		new_flags &= ~VM_DONTCOPY;
 		break;
 	}
 
@@ -177,6 +184,12 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	long error;
 
 	switch (behavior) {
+	case MADV_DOFORK:
+		if (vma->vm_flags & VM_IO) {
+			error = -EINVAL;
+			break;
+		}
+	case MADV_DONTFORK:
 	case MADV_NORMAL:
 	case MADV_SEQUENTIAL:
 	case MADV_RANDOM: