mm: Allow user to control COW PTE via prctl

Add a new prctl, PR_SET_COW_PTE, to allow the user to enable COW PTE.
Since it has a time gap between using the prctl to enable the COW PTE
and doing the fork, we use two states (MMF_COW_PTE_READY and MMF_COW_PTE)
to determine the task that wants to do COW PTE or already doing it.

The MMF_COW_PTE_READY flag marks the task to do COW PTE in the next time
of fork(). During fork(), if MMF_COW_PTE_READY set, fork() will unset the
flag and set the MMF_COW_PTE flag. After that, fork() might shares PTEs
instead of duplicates it.

Signed-off-by: Chih-En Lin <shiyn.lin@gmail.com>

include/linux/sched/coredump.h

@@ -83,7 +83,17 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_HAS_PINNED		27	/* FOLL_PIN has run, never cleared */
 #define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 
+/*
+ * MMF_COW_PTE_READY: Marking the task to do COW PTE in the next time of
+ * fork(). During fork(), if MMF_COW_PTE_READY set, fork() will unset the
+ * flag and set the MMF_COW_PTE flag. After that, fork() might shares PTEs
+ * rather than duplicates it.
+ */
+#define MMF_COW_PTE_READY	29 /* Share PTE tables in next time of fork() */
+#define MMF_COW_PTE		30 /* PTE tables are shared between processes */
+#define MMF_COW_PTE_MASK	(1 << MMF_COW_PTE)
+
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
-				 MMF_DISABLE_THP_MASK)
+				 MMF_DISABLE_THP_MASK | MMF_COW_PTE_MASK)
 
 #endif /* _LINUX_SCHED_COREDUMP_H */

include/uapi/linux/prctl.h

@@ -284,4 +284,10 @@ struct prctl_mm_map {
 #define PR_SET_VMA		0x53564d41
 # define PR_SET_VMA_ANON_NAME		0
 
+/*
+ * Set the prepare flag, MMF_COW_PTE_READY, to do the share (copy-on-write)
+ * page table in the next time of fork.
+ */
+#define PR_SET_COW_PTE			65
+
 #endif /* _LINUX_PRCTL_H */

kernel/sys.c

@@ -2348,6 +2348,14 @@ static int prctl_set_vma(unsigned long opt, unsigned long start,
 }
 #endif /* CONFIG_ANON_VMA_NAME */
 
+static int prctl_set_cow_pte(struct mm_struct *mm)
+{
+	if (test_bit(MMF_COW_PTE, &mm->flags))
+		return -EINVAL;
+	set_bit(MMF_COW_PTE_READY, &mm->flags);
+	return 0;
+}
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
@@ -2626,6 +2634,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_SET_VMA:
 		error = prctl_set_vma(arg2, arg3, arg4, arg5);
 		break;
+	case PR_SET_COW_PTE:
+		error = prctl_set_cow_pte(me->mm);
+		break;
 	default:
 		error = -EINVAL;
 		break;