[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>

21 files changed, 57 insertions, 4 deletions

diff --git a/include/asm-alpha/mman.h b/include/asm-alpha/mman.h
index f6439532a262..a21515c16a43 100644
--- a/include/asm-alpha/mman.h
+++ b/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
diff --git a/include/asm-arm/mman.h b/include/asm-arm/mman.h
index f0bebca2ac21..693ed859e632 100644
--- a/include/asm-arm/mman.h
+++ b/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
diff --git a/include/asm-arm26/mman.h b/include/asm-arm26/mman.h
index 0ed7780541fa..2096c50df888 100644
--- a/include/asm-arm26/mman.h
+++ b/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
diff --git a/include/asm-cris/mman.h b/include/asm-cris/mman.h
index 5a382b8bf3f7..deddfb239ff5 100644
--- a/include/asm-cris/mman.h
+++ b/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
diff --git a/include/asm-frv/mman.h b/include/asm-frv/mman.h
index 8af4a41c255e..d3bca306da82 100644
--- a/include/asm-frv/mman.h
+++ b/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
diff --git a/include/asm-h8300/mman.h b/include/asm-h8300/mman.h
index 744a8fb485c2..ac0346f7d11d 100644
--- a/include/asm-h8300/mman.h
+++ b/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
diff --git a/include/asm-i386/mman.h b/include/asm-i386/mman.h
index ba4941e6f643..ab2339a1d807 100644
--- a/include/asm-i386/mman.h
+++ b/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
diff --git a/include/asm-ia64/mman.h b/include/asm-ia64/mman.h
index 828beb24a20e..357ebb780cc0 100644
--- a/include/asm-ia64/mman.h
+++ b/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
diff --git a/include/asm-m32r/mman.h b/include/asm-m32r/mman.h
index 12e29747bc84..6b02fe3fcff2 100644
--- a/include/asm-m32r/mman.h
+++ b/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
diff --git a/include/asm-m68k/mman.h b/include/asm-m68k/mman.h
index ea262ab88b3b..efd12bc4ccb7 100644
--- a/include/asm-m68k/mman.h
+++ b/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
diff --git a/include/asm-mips/mman.h b/include/asm-mips/mman.h
index dd17c8bd62a1..6d01e26830fa 100644
--- a/include/asm-mips/mman.h
+++ b/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
diff --git a/include/asm-parisc/mman.h b/include/asm-parisc/mman.h
index 736b0abcac05..a381cf5c8f55 100644
--- a/include/asm-parisc/mman.h
+++ b/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
diff --git a/include/asm-powerpc/mman.h b/include/asm-powerpc/mman.h
index a2e34c21b44f..fcff25d13f13 100644
--- a/include/asm-powerpc/mman.h
+++ b/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
diff --git a/include/asm-s390/mman.h b/include/asm-s390/mman.h
index c8d5409b5d56..d41ca1477010 100644
--- a/include/asm-s390/mman.h
+++ b/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
diff --git a/include/asm-sh/mman.h b/include/asm-sh/mman.h
index 693bd55a3710..0e08d0573abc 100644
--- a/include/asm-sh/mman.h
+++ b/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
diff --git a/include/asm-sparc/mman.h b/include/asm-sparc/mman.h
index 98435ad8619e..4a298b2be859 100644
--- a/include/asm-sparc/mman.h
+++ b/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
diff --git a/include/asm-sparc64/mman.h b/include/asm-sparc64/mman.h
index cb4b6156194d..d705ec92da8b 100644
--- a/include/asm-sparc64/mman.h
+++ b/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
diff --git a/include/asm-v850/mman.h b/include/asm-v850/mman.h
index edc79965193a..7b851c310e41 100644
--- a/include/asm-v850/mman.h
+++ b/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
diff --git a/include/asm-x86_64/mman.h b/include/asm-x86_64/mman.h
index d0e97b74f735..b699a38c1c3c 100644
--- a/include/asm-x86_64/mman.h
+++ b/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
diff --git a/include/asm-xtensa/mman.h b/include/asm-xtensa/mman.h
index 082a7504925e..e2d7afb679c8 100644
--- a/include/asm-xtensa/mman.h
+++ b/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
diff --git a/mm/madvise.c b/mm/madvise.c
index ae0ae3ea299a..af3d573b0141 100644
--- a/mm/madvise.c
+++ b/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: