From ec166f77f98e8f4d5f0284921378b48385d5c037 Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Fri, 14 May 2021 10:39:49 +1000
Subject: [PATCH] BACKPORT: FROMGIT: userfaultfd/shmem: support minor fault
 registration for shmem

This patch allows shmem-backed VMAs to be registered for minor faults.
Minor faults are appropriately relayed to userspace in the fault path, for
VMAs with the relevant flag.

This commit doesn't hook up the UFFDIO_CONTINUE ioctl for shmem-backed
minor faults, though, so userspace doesn't yet have a way to resolve such
faults.

Because of this, we also don't yet advertise this as a supported feature.
That will be done in a separate commit when the feature is fully
implemented.

Link: https://lkml.kernel.org/r/20210503180737.2487560-4-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Joe Perches <joe@perches.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Wang Qing <wangqing@vivo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
(cherry picked from commit 6867a29320b7d178feb9786856e5ea2cf40f6d33
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git akpm)
Link: https://lore.kernel.org/patchwork/patch/1420970/

Conflicts: mm/shmem.c
(Manual rebase)

Signed-off-by: Lokesh Gidra <lokeshgidra@google.com>
Bug: 187930641
Change-Id: Ib8e3fe202feab7404742814f4250a0981065368c
---
 fs/userfaultfd.c |  3 +--
 mm/memory.c      |  8 +++++---
 mm/shmem.c       | 12 +++++++++++-
 3 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 7256ce1e0b20..35db9f655a90 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1305,8 +1305,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 				     unsigned long vm_flags)
 {
 	if (vm_flags & VM_UFFD_MINOR) {
-		/* FIXME: Add minor fault interception for shmem. */
-		if (!is_vm_hugetlb_page(vma))
+		if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma)))
 			return false;
 	}
 
diff --git a/mm/memory.c b/mm/memory.c
index 37e14b073b68..2a633f7284bb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3899,9 +3899,11 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf)
 	 * something).
 	 */
 	if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
-		ret = do_fault_around(vmf);
-		if (ret)
-			return ret;
+		if (likely(!userfaultfd_minor(vmf->vma))) {
+			ret = do_fault_around(vmf);
+			if (ret)
+				return ret;
+		}
 	}
 
 	ret = __do_fault(vmf);
diff --git a/mm/shmem.c b/mm/shmem.c
index c22a2d82b302..87e736f5ebd3 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1739,7 +1739,7 @@ unlock:
  * vm. If we swap it in we mark it dirty since we also free the swap
  * entry since a page cannot live in both the swap and page cache.
  *
- * vmf and fault_type are only supplied by shmem_fault:
+ * vma, vmf, and fault_type are only supplied by shmem_fault:
  * otherwise they are NULL.
  */
 static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
@@ -1773,6 +1773,16 @@ repeat:
 	charge_mm = vma ? vma->vm_mm : current->mm;
 
 	page = find_lock_entry(mapping, index);
+
+	if (page && vma && userfaultfd_minor(vma)) {
+		if (!xa_is_value(page)) {
+			unlock_page(page);
+			put_page(page);
+		}
+		*fault_type = handle_userfault(vmf, VM_UFFD_MINOR);
+		return 0;
+	}
+
 	if (xa_is_value(page)) {
 		error = shmem_swapin_page(inode, index, &page,
 					  sgp, gfp, vma, fault_type);