[PATCH RFC 25/30] hugetlb/userfaultfd: Unshare all pmds for hugetlbfs when register wp

[Peter Xu <peterx@redhat.com>]

Huge pmd sharing for hugetlbfs is racy with userfaultfd-wp because
userfaultfd-wp is always based on pgtable entries, so they cannot be shared.

Walk the hugetlb range and unshare all such mappings if there is, right before
UFFDIO_REGISTER will succeed and return to userspace.

This will pair with want_pmd_share() in hugetlb code so that huge pmd sharing
is completely disabled for userfaultfd-wp registered range.

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 fs/userfaultfd.c             | 43 ++++++++++++++++++++++++++++++++++++
 include/linux/mmu_notifier.h |  1 +
 2 files changed, 44 insertions(+)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 3537a43b69c9..3190dff39d6c 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -15,6 +15,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/mm.h>
+#include <linux/mmu_notifier.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
@@ -1198,6 +1199,45 @@ static ssize_t userfaultfd_read(struct file *file, char __user *buf,
 	}
 }
 
+/*
+ * This function will unconditionally remove all the shared pmd pgtable entries
+ * within the specific vma for a hugetlbfs memory range.
+ */
+static void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+{
+	struct hstate *h = hstate_vma(vma);
+	unsigned long sz = huge_page_size(h);
+	struct mm_struct *mm = vma->vm_mm;
+	struct mmu_notifier_range range;
+	unsigned long address;
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	/*
+	 * No need to call adjust_range_if_pmd_sharing_possible(), because
+	 * we're going to operate on the whole vma
+	 */
+	mmu_notifier_range_init(&range, MMU_NOTIFY_HUGETLB_UNSHARE,
+				0, vma, mm, vma->vm_start, vma->vm_end);
+	mmu_notifier_invalidate_range_start(&range);
+	i_mmap_lock_write(vma->vm_file->f_mapping);
+	for (address = vma->vm_start; address < vma->vm_end; address += sz) {
+		ptep = huge_pte_offset(mm, address, sz);
+		if (!ptep)
+			continue;
+		ptl = huge_pte_lock(h, mm, ptep);
+		huge_pmd_unshare(mm, vma, &address, ptep);
+		spin_unlock(ptl);
+	}
+	flush_hugetlb_tlb_range(vma, vma->vm_start, vma->vm_end);
+	i_mmap_unlock_write(vma->vm_file->f_mapping);
+	/*
+	 * No need to call mmu_notifier_invalidate_range(), see
+	 * Documentation/vm/mmu_notifier.rst.
+	 */
+	mmu_notifier_invalidate_range_end(&range);
+}
+
 static void __wake_userfault(struct userfaultfd_ctx *ctx,
 			     struct userfaultfd_wake_range *range)
 {
@@ -1456,6 +1496,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		vma->vm_flags = new_flags;
 		vma->vm_userfaultfd_ctx.ctx = ctx;
 
+		if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
+			hugetlb_unshare_all_pmds(vma);
+
 	skip:
 		prev = vma;
 		start = vma->vm_end;
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index b8200782dede..ff50c8528113 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -51,6 +51,7 @@ enum mmu_notifier_event {
 	MMU_NOTIFY_SOFT_DIRTY,
 	MMU_NOTIFY_RELEASE,
 	MMU_NOTIFY_MIGRATE,
+	MMU_NOTIFY_HUGETLB_UNSHARE,
 };
 
 #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
-- 
2.26.2