[RFC PATCH 09/18] pte_ref: add pte_tryget() and {__,}pte_put() helper

[Qi Zheng]

The user PTE page table page may be freed when the last
percpu_ref is dropped. So we need to try to get its
percpu_ref before accessing the PTE page to prevent it
form being freed during the access process.

This patch adds pte_tryget() and {__,}pte_put() to help us
to get and put the percpu_ref of user PTE page table pages.

Signed-off-by: Qi Zheng <zhengqi.arch@xxxxxxxxxxxxx>
---
 include/linux/pte_ref.h | 23 ++++++++++++++++
 mm/pte_ref.c            | 58 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+)

diff --git a/include/linux/pte_ref.h b/include/linux/pte_ref.h
index d3963a151ca5..bfe620038699 100644
--- a/include/linux/pte_ref.h
+++ b/include/linux/pte_ref.h
@@ -12,6 +12,10 @@
 
 bool pte_ref_init(pgtable_t pte);
 void pte_ref_free(pgtable_t pte);
+void free_user_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr);
+bool pte_tryget(struct mm_struct *mm, pmd_t *pmd, unsigned long addr);
+void __pte_put(pgtable_t page);
+void pte_put(pte_t *ptep);
 
 #else /* !CONFIG_FREE_USER_PTE */
 
@@ -24,6 +28,25 @@ static inline void pte_ref_free(pgtable_t pte)
 {
 }
 
+static inline void free_user_pte(struct mm_struct *mm, pmd_t *pmd,
+				 unsigned long addr)
+{
+}
+
+static inline bool pte_tryget(struct mm_struct *mm, pmd_t *pmd,
+			      unsigned long addr)
+{
+	return true;
+}
+
+static inline void __pte_put(pgtable_t page)
+{
+}
+
+static inline void pte_put(pte_t *ptep)
+{
+}
+
 #endif /* CONFIG_FREE_USER_PTE */
 
 #endif /* _LINUX_PTE_REF_H */
diff --git a/mm/pte_ref.c b/mm/pte_ref.c
index 52e31be00de4..5b382445561e 100644
--- a/mm/pte_ref.c
+++ b/mm/pte_ref.c
@@ -44,4 +44,62 @@ void pte_ref_free(pgtable_t pte)
 	kfree(ref);
 }
 
+void free_user_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr) {}
+
+/*
+ * pte_tryget - try to get the pte_ref of the user PTE page table page
+ * @mm: pointer the target address space
+ * @pmd: pointer to a PMD.
+ * @addr: virtual address associated with pmd.
+ *
+ * Return: true if getting the pte_ref succeeded. And false otherwise.
+ *
+ * Before accessing the user PTE page table, we need to hold a refcount to
+ * protect against the concurrent release of the PTE page table.
+ * But we will fail in the following case:
+ * 	- The content mapped in @pmd is not a PTE page
+ * 	- The pte_ref is zero, it may be reclaimed
+ */
+bool pte_tryget(struct mm_struct *mm, pmd_t *pmd, unsigned long addr)
+{
+	bool retval = true;
+	pmd_t pmdval;
+	pgtable_t pte;
+
+	rcu_read_lock();
+	pmdval = READ_ONCE(*pmd);
+	pte = pmd_pgtable(pmdval);
+	if (unlikely(pmd_none(pmdval) || pmd_leaf(pmdval))) {
+		retval = false;
+	} else if (!percpu_ref_tryget(pte->pte_ref)) {
+		rcu_read_unlock();
+		/*
+		 * Also do free_user_pte() here to prevent missed reclaim due
+		 * to race condition.
+		 */
+		free_user_pte(mm, pmd, addr & PMD_MASK);
+		return false;
+	}
+	rcu_read_unlock();
+
+	return retval;
+}
+
+void __pte_put(pgtable_t page)
+{
+	percpu_ref_put(page->pte_ref);
+}
+
+void pte_put(pte_t *ptep)
+{
+	pgtable_t page;
+
+	if (pte_huge(*ptep))
+		return;
+
+	page = pte_to_page(ptep);
+	__pte_put(page);
+}
+EXPORT_SYMBOL(pte_put);
+
 #endif /* CONFIG_FREE_USER_PTE */
-- 
2.20.1