[RFC PATCH 2/4] mm/mmu_notifier: add MMU_NOTIFIER_RANGE_PERM_UPGRADE

["Carlos López" <clopez@suse.de>]

Add a range flag marking an invalidation that only upgrades permissions
(that is, no PFN change and no revoked access). change_protection() sets
it for MM_CP_PERM_UPGRADE and for the userfaultfd permission resolves,
which unprotect a page and thus only restore access.

A secondary MMU can use the flag to keep its mappings rather than zap
them. Consumers that ignore it are unaffected.

Signed-off-by: Carlos López <clopez@suse.de>
---
 include/linux/mm.h           | 6 ++++++
 include/linux/mmu_notifier.h | 5 +++++
 mm/hugetlb.c                 | 6 +++++-
 mm/mprotect.c                | 7 ++++++-
 4 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f406ce9d1032..c4fc3876a4b7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3418,6 +3418,12 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen);
 /* Whether this change only upgrades/adds permissions */
 #define  MM_CP_PERM_UPGRADE                (1UL << 6)
 
+static inline bool mm_cp_is_perm_upgrade(unsigned long cp_flags)
+{
+	return cp_flags & (MM_CP_PERM_UPGRADE | MM_CP_UFFD_WP_RESOLVE |
+			   MM_CP_UFFD_RWP_RESOLVE);
+}
+
 bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t pte);
 extern long change_protection(struct mmu_gather *tlb,
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index a11a44eef521..112be28cdf6b 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -60,6 +60,11 @@ enum mmu_notifier_event {
 };
 
 #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
+/*
+ * Set on an invalidation that only expands permissions without
+ * revoking any existing access, nor freeing/moving the underlying page.
+ */
+#define MMU_NOTIFIER_RANGE_PERM_UPGRADE (1 << 1)
 
 struct mmu_notifier_ops {
 	/*
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b017ae1dfd6f..68d44044fdd2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6548,19 +6548,23 @@ long hugetlb_change_protection(struct vm_area_struct *vma,
 	long pages = 0, psize = huge_page_size(h);
 	struct mmu_notifier_range range;
 	unsigned long last_addr_mask;
+	unsigned int mn_flags = 0;
 	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
 	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
 	bool uffd_rwp = cp_flags & MM_CP_UFFD_RWP;
 	bool uffd_rwp_resolve = cp_flags & MM_CP_UFFD_RWP_RESOLVE;
 	struct mmu_gather tlb;
 
+	if (mm_cp_is_perm_upgrade(cp_flags))
+		mn_flags |= MMU_NOTIFIER_RANGE_PERM_UPGRADE;
+
 	/*
 	 * In the case of shared PMDs, the area to flush could be beyond
 	 * start/end.  Set range.start/range.end to cover the maximum possible
 	 * range if PMD sharing is possible.
 	 */
 	mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA,
-				0, mm, start, end);
+				mn_flags, mm, start, end);
 	adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
 
 	BUG_ON(address >= end);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index e9b636809c42..b48d2fd3b7b5 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -597,8 +597,13 @@ static inline long change_pud_range(struct mmu_gather *tlb,
 			continue;
 
 		if (!range.start) {
+			unsigned int mn_flags = 0;
+
+			if (mm_cp_is_perm_upgrade(cp_flags))
+				mn_flags |= MMU_NOTIFIER_RANGE_PERM_UPGRADE;
+
 			mmu_notifier_range_init(&range,
-						MMU_NOTIFY_PROTECTION_VMA, 0,
+						MMU_NOTIFY_PROTECTION_VMA, mn_flags,
 						vma->vm_mm, addr, end);
 			mmu_notifier_invalidate_range_start(&range);
 		}
-- 
2.51.0