userfaultfd: non-cooperative: add madvise() event for MADV_DONTNEED request

If the page is punched out of the address space the uffd reader should
know this and zeromap the respective area in case of the #PF event.

Link: http://lkml.kernel.org/r/20161216144821.5183-14-aarcange@redhat.comSigned-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>

fs/userfaultfd.c

@@ -633,6 +633,34 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
 	userfaultfd_event_wait_completion(ctx, &ewq);
 }
 
+void madvise_userfault_dontneed(struct vm_area_struct *vma,
+				struct vm_area_struct **prev,
+				unsigned long start, unsigned long end)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct userfaultfd_ctx *ctx;
+	struct userfaultfd_wait_queue ewq;
+
+	ctx = vma->vm_userfaultfd_ctx.ctx;
+	if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_MADVDONTNEED))
+		return;
+
+	userfaultfd_ctx_get(ctx);
+	up_read(&mm->mmap_sem);
+
+	*prev = NULL; /* We wait for ACK w/o the mmap semaphore */
+
+	msg_init(&ewq.msg);
+
+	ewq.msg.event = UFFD_EVENT_MADVDONTNEED;
+	ewq.msg.arg.madv_dn.start = start;
+	ewq.msg.arg.madv_dn.end = end;
+
+	userfaultfd_event_wait_completion(ctx, &ewq);
+
+	down_read(&mm->mmap_sem);
+}
+
 static int userfaultfd_release(struct inode *inode, struct file *file)
 {
 	struct userfaultfd_ctx *ctx = file->private_data;

include/linux/userfaultfd_k.h

@@ -61,6 +61,11 @@ extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *,
 					unsigned long from, unsigned long to,
 					unsigned long len);
 
+extern void madvise_userfault_dontneed(struct vm_area_struct *vma,
+				       struct vm_area_struct **prev,
+				       unsigned long start,
+				       unsigned long end);
+
 #else /* CONFIG_USERFAULTFD */
 
 /* mm helpers */
@@ -106,6 +111,13 @@ static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx,
 					       unsigned long len)
 {
 }
+
+static inline void madvise_userfault_dontneed(struct vm_area_struct *vma,
+					      struct vm_area_struct **prev,
+					      unsigned long start,
+					      unsigned long end)
+{
+}
 #endif /* CONFIG_USERFAULTFD */
 
 #endif /* _LINUX_USERFAULTFD_K_H */

include/uapi/linux/userfaultfd.h

@@ -19,7 +19,8 @@
  */
 #define UFFD_API ((__u64)0xAA)
 #define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK |	    \
-			   UFFD_FEATURE_EVENT_REMAP)
+			   UFFD_FEATURE_EVENT_REMAP |	    \
+			   UFFD_FEATURE_EVENT_MADVDONTNEED)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -83,6 +84,11 @@ struct uffd_msg {
 			__u64	len;
 		} remap;
 
+		struct {
+			__u64	start;
+			__u64	end;
+		} madv_dn;
+
 		struct {
 			/* unused reserved fields */
 			__u64	reserved1;
@@ -98,6 +104,7 @@ struct uffd_msg {
 #define UFFD_EVENT_PAGEFAULT	0x12
 #define UFFD_EVENT_FORK		0x13
 #define UFFD_EVENT_REMAP	0x14
+#define UFFD_EVENT_MADVDONTNEED	0x15
 
 /* flags for UFFD_EVENT_PAGEFAULT */
 #define UFFD_PAGEFAULT_FLAG_WRITE	(1<<0)	/* If this was a write fault */
@@ -119,6 +126,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
 #define UFFD_FEATURE_EVENT_REMAP		(1<<2)
+#define UFFD_FEATURE_EVENT_MADVDONTNEED		(1<<3)
 	__u64 features;
 
 	__u64 ioctls;

mm/madvise.c

@@ -10,6 +10,7 @@
 #include <linux/syscalls.h>
 #include <linux/mempolicy.h>
 #include <linux/page-isolation.h>
+#include <linux/userfaultfd_k.h>
 #include <linux/hugetlb.h>
 #include <linux/falloc.h>
 #include <linux/sched.h>
@@ -477,6 +478,7 @@ static long madvise_dontneed(struct vm_area_struct *vma,
 		return -EINVAL;
 
 	zap_page_range(vma, start, end - start, NULL);
+	madvise_userfault_dontneed(vma, prev, start, end);
 	return 0;
 }