This patch adds a VM_INIT_DEF_MASK, to allow us to set the default flags
for VMs. It also adds a prctl control which alllows 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 <athorl...@sgi.com>
Suggested-by: Oleg Nesterov <o...@redhat.com>
Cc: Andrew Morton <a...@linux-foundation.org>
Cc: "Kirill A. Shutemov" <kirill.shute...@linux.intel.com>
Cc: Rik van Riel <r...@redhat.com>
Cc: Mel Gorman <mgor...@suse.de>
Cc: Jiang Liu <liu...@gmail.com>
Cc: Peter Zijlstra <pet...@infradead.org>
Cc: Oleg Nesterov <o...@redhat.com>
Cc: Ingo Molnar <mi...@kernel.org>
Cc: "Eric W. Biederman" <ebied...@xmission.com>
Cc: Robin Holt <h...@sgi.com>
Cc: Al Viro <v...@zeniv.linux.org.uk>
Cc: Kees Cook <keesc...@chromium.org>
Cc: liguang <lig.f...@cn.fujitsu.com>
Cc: linux...@kvack.org
Cc: linux-kernel@vger.kernel.org
---
include/linux/mm.h | 2 ++
include/uapi/linux/prctl.h | 3 +++
kernel/fork.c | 11 ++++++++---
kernel/sys.c | 17 +++++++++++++++++
4 files changed, 30 insertions(+), 3 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f28f46e..c0a94ad 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -177,6 +177,8 @@ extern unsigned int kobjsize(const void *objp);
*/
#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP)
+#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 289760f..58afc04 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 a17621c..9fc0a30 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -529,8 +529,6 @@ 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));
@@ -539,8 +537,15 @@ 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 c0a58be..d59524a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1996,6 +1996,23 @@ 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;
+ case PR_SET_THP_DISABLE:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ down_write(&me->mm->mmap_sem);
+ if (option == PR_SET_THP_DISABLE) {
+ if (arg2)
+ me->mm->def_flags |= VM_NOHUGEPAGE;
+ else
+ me->mm->def_flags &= ~VM_NOHUGEPAGE;
+ } else {
+ error = !!(me->mm->def_flags & VM_NOHUGEPAGE);
+ }
+ up_write(&me->mm->mmap_sem);
+ break;
default:
error = -EINVAL;
break;
--
1.7.12.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
