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>

1 files changed, 15 insertions, 0 deletions

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;