mm: userfaultfd: add UFFDIO_CONTINUE_MODE_WP to install WP PTEs

UFFDIO_COPY already has UFFDIO_COPY_MODE_WP, so when installing a new PTE
to resolve a missing fault, one can install a write-protected one.  This
is useful when using UFFDIO_REGISTER_MODE_{MISSING,WP} in combination.

This was motivated by testing HugeTLB HGM [1], and in particular its
interaction with userfaultfd features.  Existing userfaultfd code supports
using WP and MINOR modes together (i.e.  you can register an area with
both enabled), but without this CONTINUE flag the combination is in
practice unusable.

So, add an analogous UFFDIO_CONTINUE_MODE_WP, which does the same thing as
UFFDIO_COPY_MODE_WP, but for *minor* faults.

Update the selftest to do some very basic exercising of the new flag.

Update Documentation/ to describe how these flags are used (neither the
COPY nor the new CONTINUE versions of this mode flag were described there
before).

[1]: https://patchwork.kernel.org/project/linux-mm/cover/20230218002819.1486479-1-jthoughton@google.com/

Link: https://lkml.kernel.org/r/20230314221250.682452-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nadav Amit <namit@vmware.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

6 files changed, 30 insertions, 5 deletions

diff --git a/Documentation/admin-guide/mm/userfaultfd.rst b/Documentation/admin-guide/mm/userfaultfd.rst
index bd2226299583..7c304e432205 100644
--- a/Documentation/admin-guide/mm/userfaultfd.rst
+++ b/Documentation/admin-guide/mm/userfaultfd.rst
@@ -236,6 +236,14 @@ newer kernels, one can also detect the feature UFFD_FEATURE_WP_UNPOPULATED
 and set the feature bit in advance to make sure none ptes will also be
 write protected even upon anonymous memory.
 
+When using ``UFFDIO_REGISTER_MODE_WP`` in combination with either
+``UFFDIO_REGISTER_MODE_MISSING`` or ``UFFDIO_REGISTER_MODE_MINOR``, when
+resolving missing / minor faults with ``UFFDIO_COPY`` or ``UFFDIO_CONTINUE``
+respectively, it may be desirable for the new page / mapping to be
+write-protected (so future writes will also result in a WP fault). These ioctls
+support a mode flag (``UFFDIO_COPY_MODE_WP`` or ``UFFDIO_CONTINUE_MODE_WP``
+respectively) to configure the mapping this way.
+
 QEMU/KVM
 ========
 
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 8971c3613cc6..8395605790f6 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1893,6 +1893,7 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
 	struct uffdio_continue uffdio_continue;
 	struct uffdio_continue __user *user_uffdio_continue;
 	struct userfaultfd_wake_range range;
+	uffd_flags_t flags = 0;
 
 	user_uffdio_continue = (struct uffdio_continue __user *)arg;
 
@@ -1917,13 +1918,16 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
 	    uffdio_continue.range.start) {
 		goto out;
 	}
-	if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE)
+	if (uffdio_continue.mode & ~(UFFDIO_CONTINUE_MODE_DONTWAKE |
+				     UFFDIO_CONTINUE_MODE_WP))
 		goto out;
+	if (uffdio_continue.mode & UFFDIO_CONTINUE_MODE_WP)
+		flags |= MFILL_ATOMIC_WP;
 
 	if (mmget_not_zero(ctx->mm)) {
 		ret = mfill_atomic_continue(ctx->mm, uffdio_continue.range.start,
 					    uffdio_continue.range.len,
-					    &ctx->mmap_changing);
+					    &ctx->mmap_changing, flags);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 4c477dece540..a2c53e98dfd6 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -83,7 +83,8 @@ extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm,
 				     unsigned long len,
 				     atomic_t *mmap_changing);
 extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst_start,
-				     unsigned long len, atomic_t *mmap_changing);
+				     unsigned long len, atomic_t *mmap_changing,
+				     uffd_flags_t flags);
 extern int mwriteprotect_range(struct mm_struct *dst_mm,
 			       unsigned long start, unsigned long len,
 			       bool enable_wp, atomic_t *mmap_changing);
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 90c958952bfc..66dd4cd277bd 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -305,6 +305,13 @@ struct uffdio_writeprotect {
 struct uffdio_continue {
 	struct uffdio_range range;
 #define UFFDIO_CONTINUE_MODE_DONTWAKE		((__u64)1<<0)
+	/*
+	 * UFFDIO_CONTINUE_MODE_WP will map the page write protected on
+	 * the fly.  UFFDIO_CONTINUE_MODE_WP is available only if the
+	 * write protected ioctl is implemented for the range
+	 * according to the uffdio_register.ioctls.
+	 */
+#define UFFDIO_CONTINUE_MODE_WP			((__u64)1<<1)
 	__u64 mode;
 
 	/*
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index a9b19b39413d..7f1b5f8b712c 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -693,10 +693,11 @@ ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, unsigned long start,
 }
 
 ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long start,
-			      unsigned long len, atomic_t *mmap_changing)
+			      unsigned long len, atomic_t *mmap_changing,
+			      uffd_flags_t flags)
 {
 	return mfill_atomic(dst_mm, start, 0, len, mmap_changing,
-			    uffd_flags_set_mode(0, MFILL_ATOMIC_CONTINUE));
+			    uffd_flags_set_mode(flags, MFILL_ATOMIC_CONTINUE));
 }
 
 long uffd_wp_range(struct vm_area_struct *dst_vma,
diff --git a/tools/testing/selftests/mm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c
index e030d63c031a..a96d126cb40e 100644
--- a/tools/testing/selftests/mm/userfaultfd.c
+++ b/tools/testing/selftests/mm/userfaultfd.c
@@ -585,6 +585,8 @@ static void continue_range(int ufd, __u64 start, __u64 len)
 	req.range.start = start;
 	req.range.len = len;
 	req.mode = 0;
+	if (test_uffdio_wp)
+		req.mode |= UFFDIO_CONTINUE_MODE_WP;
 
 	if (ioctl(ufd, UFFDIO_CONTINUE, &req))
 		err("UFFDIO_CONTINUE failed for address 0x%" PRIx64,
@@ -1332,6 +1334,8 @@ static int userfaultfd_minor_test(void)
 	uffdio_register.range.start = (unsigned long)area_dst_alias;
 	uffdio_register.range.len = nr_pages * page_size;
 	uffdio_register.mode = UFFDIO_REGISTER_MODE_MINOR;
+	if (test_uffdio_wp)
+		uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		err("register failure");