[RFC,v2,06/19] mm: add new prctl option to get and set ksm for a process

Commit Message

Stefan Roesch Feb. 10, 2023, 9:50 p.m. UTC

This adds two new options to the prctl system call
- enable ksm for all vmas of a process (if the vmas support it).
- query if ksm has been enabled for a process.

Signed-off-by: Stefan Roesch <[e-mail]>
---
 include/uapi/linux/prctl.h |  2 ++
 kernel/sys.c               | 29 +++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

Patch

diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 1312a137f7fb..759b3f53e53f 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -290,4 +290,6 @@  struct prctl_mm_map {
 #define PR_SET_VMA		0x53564d41
 # define PR_SET_VMA_ANON_NAME		0
 
+#define PR_SET_MEMORY_MERGE		67
+#define PR_GET_MEMORY_MERGE		68
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index b3cab94545ed..495bab3ed2ad 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -15,6 +15,7 @@ 
 #include <linux/highuid.h>
 #include <linux/fs.h>
 #include <linux/kmod.h>
+#include <linux/ksm.h>
 #include <linux/perf_event.h>
 #include <linux/resource.h>
 #include <linux/kernel.h>
@@ -2659,6 +2660,34 @@  SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_SET_VMA:
 		error = prctl_set_vma(arg2, arg3, arg4, arg5);
 		break;
+#ifdef CONFIG_KSM
+	case PR_SET_MEMORY_MERGE:
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (arg2) {
+			if (mmap_write_lock_killable(me->mm))
+				return -EINTR;
+
+			if (test_bit(MMF_VM_MERGEABLE, &me->mm->flags))
+				error = -EINVAL;
+			else if (!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags))
+				error = __ksm_enter(me->mm, MMF_VM_MERGE_ANY);
+			mmap_write_unlock(me->mm);
+		} else {
+			__ksm_exit(me->mm, MMF_VM_MERGE_ANY);
+		}
+		break;
+	case PR_GET_MEMORY_MERGE:
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+
+		error = !!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags);
+		break;
+#endif
 	default:
 		error = -EINVAL;
 		break;