[PATCH 6.12.y] mm: prevent droppable mappings from being locked

[Sasha Levin <sashal@kernel.org>]

From: Anthony Yznaga <anthony.yznaga@oracle.com>

[ Upstream commit d239462787b072c78eb19fc1f155c3d411256282 ]

Droppable mappings must not be lockable.  There is a check for VMAs with
VM_DROPPABLE set in mlock_fixup() along with checks for other types of
unlockable VMAs which ensures this when calling mlock()/mlock2().

For mlockall(MCL_FUTURE), the check for unlockable VMAs is different.  In
apply_mlockall_flags(), if the flags parameter has MCL_FUTURE set, the
current task's mm's default VMA flag field mm->def_flags has VM_LOCKED
applied to it.  VM_LOCKONFAULT is also applied if MCL_ONFAULT is also set.
When these flags are set as default in this manner they are cleared in
__mmap_complete() for new mappings that do not support mlock.  A check for
VM_DROPPABLE in __mmap_complete() is missing resulting in droppable
mappings created with VM_LOCKED set.  To fix this and reduce that chance
of similar bugs in the future, introduce and use vma_supports_mlock().

Link: https://lkml.kernel.org/r/20260310155821.17869-1-anthony.yznaga@oracle.com
Fixes: 9651fcedf7b9 ("mm: add MAP_DROPPABLE for designating always lazily freeable mappings")
Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
Suggested-by: David Hildenbrand <david@kernel.org>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Tested-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Jann Horn <jannh@google.com>
Cc: Jason A. Donenfeld <jason@zx2c4.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
[ applied the mmap completion hunk to __mmap_region() in mm/mmap.c instead of __mmap_complete() in mm/vma.c ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/hugetlb_inline.h |  4 ++--
 mm/internal.h                  | 10 ++++++++++
 mm/mlock.c                     | 10 ++++++----
 mm/mmap.c                      |  4 +---
 4 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/include/linux/hugetlb_inline.h b/include/linux/hugetlb_inline.h
index 0660a03d37d98..846185ea626c7 100644
--- a/include/linux/hugetlb_inline.h
+++ b/include/linux/hugetlb_inline.h
@@ -6,14 +6,14 @@
 
 #include <linux/mm.h>
 
-static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma)
+static inline bool is_vm_hugetlb_page(const struct vm_area_struct *vma)
 {
 	return !!(vma->vm_flags & VM_HUGETLB);
 }
 
 #else
 
-static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma)
+static inline bool is_vm_hugetlb_page(const struct vm_area_struct *vma)
 {
 	return false;
 }
diff --git a/mm/internal.h b/mm/internal.h
index b7b942767c702..3bfc1dc2d7eaf 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1015,6 +1015,16 @@ static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
 	}
 	return fpin;
 }
+
+static inline bool vma_supports_mlock(const struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & (VM_SPECIAL | VM_DROPPABLE))
+		return false;
+	if (vma_is_dax(vma) || is_vm_hugetlb_page(vma))
+		return false;
+	return vma != get_gate_vma(current->mm);
+}
+
 #else /* !CONFIG_MMU */
 static inline void unmap_mapping_folio(struct folio *folio) { }
 static inline void mlock_new_folio(struct folio *folio) { }
diff --git a/mm/mlock.c b/mm/mlock.c
index 8c8d522efdd59..d16bf4dbd06dd 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -472,10 +472,12 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	int ret = 0;
 	vm_flags_t oldflags = vma->vm_flags;
 
-	if (newflags == oldflags || (oldflags & VM_SPECIAL) ||
-	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
-	    vma_is_dax(vma) || vma_is_secretmem(vma) || (oldflags & VM_DROPPABLE))
-		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
+	if (newflags == oldflags || vma_is_secretmem(vma) ||
+	    !vma_supports_mlock(vma))
+		/*
+		 * Don't set VM_LOCKED or VM_LOCKONFAULT and don't count.
+		 * For secretmem, don't allow the memory to be unlocked.
+		 */
 		goto out;
 
 	vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags);
diff --git a/mm/mmap.c b/mm/mmap.c
index 6183805f6f9e6..d361b1058da10 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1547,9 +1547,7 @@ static unsigned long __mmap_region(struct file *file, unsigned long addr,
 
 	vm_stat_account(mm, vm_flags, pglen);
 	if (vm_flags & VM_LOCKED) {
-		if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) ||
-					is_vm_hugetlb_page(vma) ||
-					vma == get_gate_vma(current->mm))
+		if (!vma_supports_mlock(vma))
 			vm_flags_clear(vma, VM_LOCKED_MASK);
 		else
 			mm->locked_vm += pglen;
-- 
2.53.0