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>

arch/mips/kernel/vdso.c

@@ -111,7 +111,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	base = mmap_region(NULL, STACK_TOP, PAGE_SIZE,
 			   VM_READ|VM_WRITE|VM_EXEC|
 			   VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-			   0);
+			   0, NULL);
 	if (IS_ERR_VALUE(base)) {
 		ret = base;
 		goto out;

arch/tile/mm/elf.c

@@ -143,7 +143,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 		unsigned long addr = MEM_USER_INTRPT;
 		addr = mmap_region(NULL, addr, INTRPT_SIZE,
 				   VM_READ|VM_EXEC|
-				   VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, 0);
+				   VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, 0, NULL);
 		if (addr > (unsigned long) -PAGE_SIZE)
 			retval = (int) addr;
 	}

arch/x86/entry/vdso/vma.c

@@ -186,7 +186,7 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
-		do_munmap(mm, text_start, image->size);
+		do_munmap(mm, text_start, image->size, NULL);
 	} else {
 		current->mm->context.vdso = (void __user *)text_start;
 		current->mm->context.vdso_image = image;

arch/x86/mm/mpx.c

@@ -51,7 +51,7 @@ static unsigned long mpx_mmap(unsigned long len)
 
 	down_write(&mm->mmap_sem);
 	addr = do_mmap(NULL, 0, len, PROT_READ | PROT_WRITE,
-			MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate);
+		       MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate, NULL);
 	up_write(&mm->mmap_sem);
 	if (populate)
 		mm_populate(addr, populate);
@@ -893,7 +893,7 @@ static int unmap_entire_bt(struct mm_struct *mm,
 	 * avoid recursion, do_munmap() will check whether it comes
 	 * from one bounds table through VM_MPX flag.
 	 */
-	return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm));
+	return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm), NULL);
 }
 
 static int try_unmap_single_bt(struct mm_struct *mm,

fs/aio.c

@@ -512,7 +512,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 
 	ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
 				       PROT_READ | PROT_WRITE,
-				       MAP_SHARED, 0, &unused);
+				       MAP_SHARED, 0, &unused, NULL);
 	up_write(&mm->mmap_sem);
 	if (IS_ERR((void *)ctx->mmap_base)) {
 		ctx->mmap_size = 0;

fs/proc/vmcore.c

@@ -388,7 +388,7 @@ static int remap_oldmem_pfn_checked(struct vm_area_struct *vma,
 	}
 	return 0;
 fail:
-	do_munmap(vma->vm_mm, from, len);
+	do_munmap(vma->vm_mm, from, len, NULL);
 	return -EAGAIN;
 }
 
@@ -481,7 +481,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 
 	return 0;
 fail:
-	do_munmap(vma->vm_mm, vma->vm_start, len);
+	do_munmap(vma->vm_mm, vma->vm_start, len, NULL);
 	return -EAGAIN;
 }
 #else

fs/userfaultfd.c

@@ -71,6 +71,13 @@ struct userfaultfd_fork_ctx {
 	struct list_head list;
 };
 
+struct userfaultfd_unmap_ctx {
+	struct userfaultfd_ctx *ctx;
+	unsigned long start;
+	unsigned long end;
+	struct list_head list;
+};
+
 struct userfaultfd_wait_queue {
 	struct uffd_msg msg;
 	wait_queue_t wq;
@@ -709,6 +716,64 @@ void userfaultfd_remove(struct vm_area_struct *vma,
 	down_read(&mm->mmap_sem);
 }
 
+static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
+			  unsigned long start, unsigned long end)
+{
+	struct userfaultfd_unmap_ctx *unmap_ctx;
+
+	list_for_each_entry(unmap_ctx, unmaps, list)
+		if (unmap_ctx->ctx == ctx && unmap_ctx->start == start &&
+		    unmap_ctx->end == end)
+			return true;
+
+	return false;
+}
+
+int userfaultfd_unmap_prep(struct vm_area_struct *vma,
+			   unsigned long start, unsigned long end,
+			   struct list_head *unmaps)
+{
+	for ( ; vma && vma->vm_start < end; vma = vma->vm_next) {
+		struct userfaultfd_unmap_ctx *unmap_ctx;
+		struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
+
+		if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) ||
+		    has_unmap_ctx(ctx, unmaps, start, end))
+			continue;
+
+		unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL);
+		if (!unmap_ctx)
+			return -ENOMEM;
+
+		userfaultfd_ctx_get(ctx);
+		unmap_ctx->ctx = ctx;
+		unmap_ctx->start = start;
+		unmap_ctx->end = end;
+		list_add_tail(&unmap_ctx->list, unmaps);
+	}
+
+	return 0;
+}
+
+void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
+{
+	struct userfaultfd_unmap_ctx *ctx, *n;
+	struct userfaultfd_wait_queue ewq;
+
+	list_for_each_entry_safe(ctx, n, uf, list) {
+		msg_init(&ewq.msg);
+
+		ewq.msg.event = UFFD_EVENT_UNMAP;
+		ewq.msg.arg.remove.start = ctx->start;
+		ewq.msg.arg.remove.end = ctx->end;
+
+		userfaultfd_event_wait_completion(ctx->ctx, &ewq);
+
+		list_del(&ctx->list);
+		kfree(ctx);
+	}
+}
+
 static int userfaultfd_release(struct inode *inode, struct file *file)
 {
 	struct userfaultfd_ctx *ctx = file->private_data;

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

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 */

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;

ipc/shm.c

@@ -1222,7 +1222,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
 			goto invalid;
 	}
 
-	addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate);
+	addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate, NULL);
 	*raddr = addr;
 	err = 0;
 	if (IS_ERR_VALUE(addr))
@@ -1329,7 +1329,7 @@ SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
 			 */
 			file = vma->vm_file;
 			size = i_size_read(file_inode(vma->vm_file));
-			do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
+			do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL);
 			/*
 			 * We discovered the size of the shm segment, so
 			 * break out of here and fall through to the next
@@ -1356,7 +1356,7 @@ SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
 		if ((vma->vm_ops == &shm_vm_ops) &&
 		    ((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) &&
 		    (vma->vm_file == file))
-			do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
+			do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL);
 		vma = next;
 	}
 
@@ -1365,7 +1365,7 @@ SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
 	 * given
 	 */
 	if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
-		do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
+		do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL);
 		retval = 0;
 	}