[PATCH v2 1/9] mm: add find_vma()-like API but RCU protected and taking VMA lock

[Andrii Nakryiko]

Existing lock_vma_under_rcu() API assumes exact VMA match, so it's not
a 100% equivalent of find_vma(). There are use cases that do want
find_vma() semantics of finding an exact VMA or the next one.

Also, it's important for such an API to let user distinguish between not
being able to get per-VMA lock and not having any VMAs at or after
provided address.

As such, this patch adds a new find_vma()-like API,
find_and_lock_vma_rcu(), which finds exact or next VMA, attempts to take
per-VMA lock, and if that fails, returns ERR_PTR(-EBUSY). It still
returns NULL if there is no VMA at or after address. In successfuly case
it will return valid and non-isolated VMA with VMA lock taken.

This API will be used in subsequent patch in this patch set to implement
a new user-facing API for querying process VMAs.

Cc: Mike Rapoport <rppt@xxxxxxxxxx>
Cc: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Cc: Liam Howlett <liam.howlett@xxxxxxxxxx>
Signed-off-by: Andrii Nakryiko <andrii@xxxxxxxxxx>
---
 include/linux/mm.h |  8 ++++++
 mm/memory.c        | 62 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9849dfda44d4..a6846401da77 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -776,6 +776,8 @@ static inline void assert_fault_locked(struct vm_fault *vmf)
 		mmap_assert_locked(vmf->vma->vm_mm);
 }
 
+struct vm_area_struct *find_and_lock_vma_rcu(struct mm_struct *mm,
+					  unsigned long address);
 struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
 					  unsigned long address);
 
@@ -790,6 +792,12 @@ static inline void vma_assert_write_locked(struct vm_area_struct *vma)
 static inline void vma_mark_detached(struct vm_area_struct *vma,
 				     bool detached) {}
 
+struct vm_area_struct *find_and_lock_vma_rcu(struct mm_struct *mm,
+					     unsigned long address)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
 		unsigned long address)
 {
diff --git a/mm/memory.c b/mm/memory.c
index b5453b86ec4b..9d0413e98d8b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5824,6 +5824,68 @@ struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm,
 #endif
 
 #ifdef CONFIG_PER_VMA_LOCK
+/*
+ * find_and_lock_vma_rcu() - Find and lock the VMA for a given address, or the
+ * next VMA. Search is done under RCU protection, without taking or assuming
+ * mmap_lock. Returned VMA is guaranteed to be stable and not isolated.
+
+ * @mm: The mm_struct to check
+ * @addr: The address
+ *
+ * Returns: The VMA associated with addr, or the next VMA.
+ * May return %NULL in the case of no VMA at addr or above.
+ * If the VMA is being modified and can't be locked, -EBUSY is returned.
+ */
+struct vm_area_struct *find_and_lock_vma_rcu(struct mm_struct *mm,
+					     unsigned long address)
+{
+	MA_STATE(mas, &mm->mm_mt, address, address);
+	struct vm_area_struct *vma;
+	int err;
+
+	rcu_read_lock();
+retry:
+	vma = mas_find(&mas, ULONG_MAX);
+	if (!vma) {
+		err = 0; /* no VMA, return NULL */
+		goto inval;
+	}
+
+	if (!vma_start_read(vma)) {
+		err = -EBUSY;
+		goto inval;
+	}
+
+	/*
+	 * Check since vm_start/vm_end might change before we lock the VMA.
+	 * Note, unlike lock_vma_under_rcu() we are searching for VMA covering
+	 * address or the next one, so we only make sure VMA wasn't updated to
+	 * end before the address.
+	 */
+	if (unlikely(vma->vm_end <= address)) {
+		err = -EBUSY;
+		goto inval_end_read;
+	}
+
+	/* Check if the VMA got isolated after we found it */
+	if (vma->detached) {
+		vma_end_read(vma);
+		count_vm_vma_lock_event(VMA_LOCK_MISS);
+		/* The area was replaced with another one */
+		goto retry;
+	}
+
+	rcu_read_unlock();
+	return vma;
+
+inval_end_read:
+	vma_end_read(vma);
+inval:
+	rcu_read_unlock();
+	count_vm_vma_lock_event(VMA_LOCK_ABORT);
+	return ERR_PTR(err);
+}
+
 /*
  * Lookup and lock a VMA under RCU protection. Returned VMA is guaranteed to be
  * stable and not isolated. If the VMA is not found or is being modified the
-- 
2.43.0