mm: add atomic VMA flags and set VM_MAYBE_GUARD as such

This patch adds the ability to atomically set VMA flags with only the mmap
read/VMA read lock held.

As this could be hugely problematic for VMA flags in general given that
all other accesses are non-atomic and serialised by the mmap/VMA locks, we
implement this with a strict allow-list - that is, only designated flags
are allowed to do this.

We make VM_MAYBE_GUARD one of these flags.

Link: https://lkml.kernel.org/r/97e57abed09f2663077ed7a36fb8206e243171a9.1763460113.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand (Red Hat) <david@kernel.org>
Reviewed-by: Lance Yang <lance.yang@linux.dev>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 36b9418c00fcaed72e9519bdad45cc5020aa3b47..03776aab38377bc87cafbc5a627890c42915f245 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -518,6 +518,9 @@ extern unsigned int kobjsize(const void *objp);
 /* This mask represents all the VMA flag bits used by mlock */
 #define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT)
 
+/* These flags can be updated atomically via VMA/mmap read lock. */
+#define VM_ATOMIC_SET_ALLOWED VM_MAYBE_GUARD
+
 /* Arch-specific flags to clear when updating VM flags on protection change */
 #ifndef VM_ARCH_CLEAR
 # define VM_ARCH_CLEAR VM_NONE
@@ -860,6 +863,47 @@ static inline void vm_flags_mod(struct vm_area_struct *vma,
        __vm_flags_mod(vma, set, clear);
 }
 
+static inline bool __vma_flag_atomic_valid(struct vm_area_struct *vma,
+                                      int bit)
+{
+       const vm_flags_t mask = BIT(bit);
+
+       /* Only specific flags are permitted */
+       if (WARN_ON_ONCE(!(mask & VM_ATOMIC_SET_ALLOWED)))
+               return false;
+
+       return true;
+}
+
+/*
+ * Set VMA flag atomically. Requires only VMA/mmap read lock. Only specific
+ * valid flags are allowed to do this.
+ */
+static inline void vma_flag_set_atomic(struct vm_area_struct *vma, int bit)
+{
+       /* mmap read lock/VMA read lock must be held. */
+       if (!rwsem_is_locked(&vma->vm_mm->mmap_lock))
+               vma_assert_locked(vma);
+
+       if (__vma_flag_atomic_valid(vma, bit))
+               set_bit(bit, &ACCESS_PRIVATE(vma, __vm_flags));
+}
+
+/*
+ * Test for VMA flag atomically. Requires no locks. Only specific valid flags
+ * are allowed to do this.
+ *
+ * This is necessarily racey, so callers must ensure that serialisation is
+ * achieved through some other means, or that races are permissible.
+ */
+static inline bool vma_flag_test_atomic(struct vm_area_struct *vma, int bit)
+{
+       if (__vma_flag_atomic_valid(vma, bit))
+               return test_bit(bit, &vma->vm_flags);
+
+       return false;
+}
+
 static inline void vma_set_anonymous(struct vm_area_struct *vma)
 {
        vma->vm_ops = NULL;