userfaultfd: non-cooperative: Add fork() event

When the mm with uffd-ed vmas fork()-s the respective vmas notify their
uffds with the event which contains a descriptor with new uffd.  This
new descriptor can then be used to get events from the child and
populate its mm with data.  Note, that there can be different uffd-s
controlling different vmas within one mm, so first we should collect all
those uffds (and ctx-s) in a list and then notify them all one by one
but only once per fork().

The context is created at fork() time but the descriptor, file struct
and anon inode object is created at event read time.  So some trickery
is added to the userfaultfd_ctx_read() to handle the ctx queues' locking
vs file creation.

Another thing worth noticing is that the task that fork()-s waits for
the uffd event to get processed WITHOUT the mmap sem.

[aarcange@redhat.com: build warning fix]
  Link: http://lkml.kernel.org/r/20161216144821.5183-10-aarcange@redhat.com
Link: http://lkml.kernel.org/r/20161216144821.5183-9-aarcange@redhat.com
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Michael Rapoport <RAPOPORT@il.ibm.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 18 insertions, 10 deletions

diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 11b92b047a1e..79002bca1f43 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -52,6 +52,9 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 	return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP);
 }
 
+extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
+extern void dup_userfaultfd_complete(struct list_head *);
+
 #else /* CONFIG_USERFAULTFD */
 
 /* mm helpers */
@@ -76,6 +79,16 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 	return false;
 }
 
+static inline int dup_userfaultfd(struct vm_area_struct *vma,
+				  struct list_head *l)
+{
+	return 0;
+}
+
+static inline void dup_userfaultfd_complete(struct list_head *l)
+{
+}
+
 #endif /* CONFIG_USERFAULTFD */
 
 #endif /* _LINUX_USERFAULTFD_K_H */
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 94046b8aa6ad..c8953c84fdcc 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -18,12 +18,7 @@
  * means the userland is reading).
  */
 #define UFFD_API ((__u64)0xAA)
-/*
- * After implementing the respective features it will become:
- * #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \
- *			      UFFD_FEATURE_EVENT_FORK)
- */
-#define UFFD_API_FEATURES (0)
+#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -78,6 +73,10 @@ struct uffd_msg {
 		} pagefault;
 
 		struct {
+			__u32	ufd;
+		} fork;
+
+		struct {
 			/* unused reserved fields */
 			__u64	reserved1;
 			__u64	reserved2;
@@ -90,9 +89,7 @@ struct uffd_msg {
  * Start at 0x12 and not at 0 to be more strict against bugs.
  */
 #define UFFD_EVENT_PAGEFAULT	0x12
-#if 0 /* not available yet */
 #define UFFD_EVENT_FORK		0x13
-#endif
 
 /* flags for UFFD_EVENT_PAGEFAULT */
 #define UFFD_PAGEFAULT_FLAG_WRITE	(1<<0)	/* If this was a write fault */
@@ -111,10 +108,8 @@ struct uffdio_api {
 	 * are to be considered implicitly always enabled in all kernels as
 	 * long as the uffdio_api.api requested matches UFFD_API.
 	 */
-#if 0 /* not available yet */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
-#endif
 	__u64 features;
 
 	__u64 ioctls;