mm, thp: add VM_INIT_DEF_MASK and PRCTL_THP_DISABLE

Add VM_INIT_DEF_MASK, to allow us to set the default flags for VMs.  It
also adds a prctl control which allows us to set the THP disable bit in
mm->def_flags so that VMs will pick up the setting as they are created.

Signed-off-by: Alex Thorlton <athorlton@sgi.com>
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 29 insertions, 3 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 35300f390eb6..c270fa68a32b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -177,6 +177,9 @@ extern unsigned int kobjsize(const void *objp);
  */
 #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
 
+/* This mask defines which mm->def_flags a process can inherit its parent */
+#define VM_INIT_DEF_MASK        VM_NOHUGEPAGE
+
 /*
  * mapping from the currently active vm_flags protection bits (the
  * low four bits) to a page protection mask..
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 289760f424aa..58afc04c107e 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -149,4 +149,7 @@
 
 #define PR_GET_TID_ADDRESS      40
 
+#define PR_SET_THP_DISABLE      41
+#define PR_GET_THP_DISABLE      42
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index abc45890f0a5..e40c0a01d5a6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -530,8 +530,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
         atomic_set(&mm->mm_count, 1);
         init_rwsem(&mm->mmap_sem);
         INIT_LIST_HEAD(&mm->mmlist);
-        mm->flags = (current->mm) ?
-                (current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
         mm->core_state = NULL;
         atomic_long_set(&mm->nr_ptes, 0);
         memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
@@ -540,8 +538,15 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
         mm_init_owner(mm, p);
         clear_tlb_flush_pending(mm);
 
-        if (likely(!mm_alloc_pgd(mm))) {
+        if (current->mm) {
+                mm->flags = current->mm->flags & MMF_INIT_MASK;
+                mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
+        } else {
+                mm->flags = default_dump_filter;
                 mm->def_flags = 0;
+        }
+
+        if (likely(!mm_alloc_pgd(mm))) {
                 mmu_notifier_mm_init(mm);
                 return mm;
         }
diff --git a/kernel/sys.c b/kernel/sys.c
index adaeab6f7a87..fba0f29401ea 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1996,6 +1996,21 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
                 if (arg2 || arg3 || arg4 || arg5)
                         return -EINVAL;
                 return current->no_new_privs ? 1 : 0;
+        case PR_GET_THP_DISABLE:
+                if (arg2 || arg3 || arg4 || arg5)
+                        return -EINVAL;
+                error = !!(me->mm->def_flags & VM_NOHUGEPAGE);
+                break;
+        case PR_SET_THP_DISABLE:
+                if (arg3 || arg4 || arg5)
+                        return -EINVAL;
+                down_write(&me->mm->mmap_sem);
+                if (arg2)
+                        me->mm->def_flags |= VM_NOHUGEPAGE;
+                else
+                        me->mm->def_flags &= ~VM_NOHUGEPAGE;
+                up_write(&me->mm->mmap_sem);
+                break;
         default:
                 error = -EINVAL;
                 break;