ksm: the mm interface to ksm

This patch presents the mm interface to a dummy version of ksm.c, for
better scrutiny of that interface: the real ksm.c follows later.

When CONFIG_KSM is not set, madvise(2) reject MADV_MERGEABLE and
MADV_UNMERGEABLE with EINVAL, since that seems more helpful than
pretending that they can be serviced.  But when CONFIG_KSM=y, accept them
even if KSM is not currently running, and even on areas which KSM will not
touch (e.g.  hugetlb or shared file or special driver mappings).

Like other madvices, report ENOMEM despite success if any area in the
range is unmapped, and use EAGAIN to report out of memory.

Define vma flag VM_MERGEABLE to identify an area on which KSM may try
merging pages: leave it to ksm_madvise() to decide whether to set it.
Define mm flag MMF_VM_MERGEABLE to identify an mm which might contain
VM_MERGEABLE areas, to minimize callouts when forking or exiting.

Based upon earlier patches by Chris Wright and Izik Eidus.

Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Signed-off-by: Chris Wright <chrisw@redhat.com>
Signed-off-by: Izik Eidus <ieidus@redhat.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 56 insertions, 0 deletions

diff --git a/mm/ksm.c b/mm/ksm.c
new file mode 100644
index 00000000000..8b76008fcd3
--- /dev/null
+++ b/mm/ksm.c
@@ -0,0 +1,56 @@
+/*
+ * Initial dummy version just to illustrate KSM's interface to other files.
+ */
+
+#include <linux/errno.h>
+#include <linux/mman.h>
+#include <linux/ksm.h>
+
+int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
+		unsigned long end, int advice, unsigned long *vm_flags)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	switch (advice) {
+	case MADV_MERGEABLE:
+		/*
+		 * Be somewhat over-protective for now!
+		 */
+		if (*vm_flags & (VM_MERGEABLE | VM_SHARED  | VM_MAYSHARE   |
+				 VM_PFNMAP    | VM_IO      | VM_DONTEXPAND |
+				 VM_RESERVED  | VM_HUGETLB | VM_INSERTPAGE |
+				 VM_MIXEDMAP  | VM_SAO))
+			return 0;		/* just ignore the advice */
+
+		if (!test_bit(MMF_VM_MERGEABLE, &mm->flags))
+			if (__ksm_enter(mm) < 0)
+				return -EAGAIN;
+
+		*vm_flags |= VM_MERGEABLE;
+		break;
+
+	case MADV_UNMERGEABLE:
+		if (!(*vm_flags & VM_MERGEABLE))
+			return 0;		/* just ignore the advice */
+
+		/* Unmerge any merged pages here */
+
+		*vm_flags &= ~VM_MERGEABLE;
+		break;
+	}
+
+	return 0;
+}
+
+int __ksm_enter(struct mm_struct *mm)
+{
+	/* Allocate a structure to track mm and link it into KSM's list */
+	set_bit(MMF_VM_MERGEABLE, &mm->flags);
+	return 0;
+}
+
+void __ksm_exit(struct mm_struct *mm)
+{
+	/* Unlink and free all KSM's structures which track this mm */
+	clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+}