userfaultfd: non-cooperative: add event for memory unmaps

When a non-cooperative userfaultfd monitor copies pages in the
background, it may encounter regions that were already unmapped.
Addition of UFFD_EVENT_UNMAP allows the uffd monitor to track precisely
changes in the virtual memory layout.

Since there might be different uffd contexts for the affected VMAs, we
first should create a temporary representation for the unmap event for
each uffd context and then notify them one by one to the appropriate
userfault file descriptors.

The event notification occurs after the mmap_sem has been released.

[arnd@arndb.de: fix nommu build]
  Link: http://lkml.kernel.org/r/20170203165141.3665284-1-arnd@arndb.de
[mhocko@suse.com: fix nommu build]
  Link: http://lkml.kernel.org/r/20170202091503.GA22823@dhcp22.suse.cz
Link: http://lkml.kernel.org/r/1485542673-24387-3-git-send-email-rppt@linux.vnet.ibm.com
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 30 insertions, 5 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index c65aa43b5712..c6fcba1d1ae5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2090,18 +2090,22 @@ extern int install_special_mapping(struct mm_struct *mm,
 extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
 
 extern unsigned long mmap_region(struct file *file, unsigned long addr,
-	unsigned long len, vm_flags_t vm_flags, unsigned long pgoff);
+	unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
+	struct list_head *uf);
 extern unsigned long do_mmap(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot, unsigned long flags,
-	vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate);
-extern int do_munmap(struct mm_struct *, unsigned long, size_t);
+	vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate,
+	struct list_head *uf);
+extern int do_munmap(struct mm_struct *, unsigned long, size_t,
+		     struct list_head *uf);
 
 static inline unsigned long
 do_mmap_pgoff(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot, unsigned long flags,
-	unsigned long pgoff, unsigned long *populate)
+	unsigned long pgoff, unsigned long *populate,
+	struct list_head *uf)
 {
-	return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate);
+	return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate, uf);
 }
 
 #ifdef CONFIG_MMU
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 2521542f6c07..a40be5d0661b 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -66,6 +66,12 @@ extern void userfaultfd_remove(struct vm_area_struct *vma,
 			       unsigned long start,
 			       unsigned long end);
 
+extern int userfaultfd_unmap_prep(struct vm_area_struct *vma,
+				  unsigned long start, unsigned long end,
+				  struct list_head *uf);
+extern void userfaultfd_unmap_complete(struct mm_struct *mm,
+				       struct list_head *uf);
+
 #else /* CONFIG_USERFAULTFD */
 
 /* mm helpers */
@@ -118,6 +124,18 @@ static inline void userfaultfd_remove(struct vm_area_struct *vma,
 				      unsigned long end)
 {
 }
+
+static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma,
+					 unsigned long start, unsigned long end,
+					 struct list_head *uf)
+{
+	return 0;
+}
+
+static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
+					      struct list_head *uf)
+{
+}
 #endif /* CONFIG_USERFAULTFD */
 
 #endif /* _LINUX_USERFAULTFD_K_H */
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index b742c40c2880..3b059530dac9 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -21,6 +21,7 @@
 #define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK |		\
 			   UFFD_FEATURE_EVENT_REMAP |		\
 			   UFFD_FEATURE_EVENT_REMOVE |	\
+			   UFFD_FEATURE_EVENT_UNMAP |		\
 			   UFFD_FEATURE_MISSING_HUGETLBFS |	\
 			   UFFD_FEATURE_MISSING_SHMEM)
 #define UFFD_API_IOCTLS				\
@@ -110,6 +111,7 @@ struct uffd_msg {
 #define UFFD_EVENT_FORK		0x13
 #define UFFD_EVENT_REMAP	0x14
 #define UFFD_EVENT_REMOVE	0x15
+#define UFFD_EVENT_UNMAP	0x16
 
 /* flags for UFFD_EVENT_PAGEFAULT */
 #define UFFD_PAGEFAULT_FLAG_WRITE	(1<<0)	/* If this was a write fault */
@@ -158,6 +160,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_EVENT_REMOVE		(1<<3)
 #define UFFD_FEATURE_MISSING_HUGETLBFS		(1<<4)
 #define UFFD_FEATURE_MISSING_SHMEM		(1<<5)
+#define UFFD_FEATURE_EVENT_UNMAP		(1<<6)
 	__u64 features;
 
 	__u64 ioctls;