[PATCH v5 6/8] mm: Introduce deferred freeing for kernel page tables

[Lu Baolu <baolu.lu@linux.intel.com>]

From: Dave Hansen <dave.hansen@linux.intel.com>

This introduces a conditional asynchronous mechanism, enabled by
CONFIG_ASYNC_PGTABLE_FREE. When enabled, this mechanism defers the freeing
of pages that are used as page tables for kernel address mappings. These
pages are now queued to a work struct instead of being freed immediately.

This deferred freeing provides a safe context for a future patch to add
an IOMMU-specific callback, which might be expensive on large-scale
systems. This ensures the necessary IOMMU cache invalidation is performed
before the page is finally returned to the page allocator outside of any
critical, non-sleepable path.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
---
 include/linux/mm.h   | 16 +++++++++++++---
 mm/pgtable-generic.c | 37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 50 insertions(+), 3 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 668d519edc0f..2d7b4af40442 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2891,6 +2891,14 @@ static inline void __pagetable_free(struct ptdesc *pt)
 	__free_pages(page, compound_order(page));
 }
 
+#ifdef CONFIG_ASYNC_PGTABLE_FREE
+void pagetable_free_kernel(struct ptdesc *pt);
+#else
+static inline void pagetable_free_kernel(struct ptdesc *pt)
+{
+	__pagetable_free(pt);
+}
+#endif
 /**
  * pagetable_free - Free pagetables
  * @pt:	The page table descriptor
@@ -2900,10 +2908,12 @@ static inline void __pagetable_free(struct ptdesc *pt)
  */
 static inline void pagetable_free(struct ptdesc *pt)
 {
-	if (ptdesc_test_kernel(pt))
+	if (ptdesc_test_kernel(pt)) {
 		ptdesc_clear_kernel(pt);
-
-	__pagetable_free(pt);
+		pagetable_free_kernel(pt);
+	} else {
+		__pagetable_free(pt);
+	}
 }
 
 #if defined(CONFIG_SPLIT_PTE_PTLOCKS)
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 567e2d084071..0279399d4910 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -406,3 +406,40 @@ pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
 	pte_unmap_unlock(pte, ptl);
 	goto again;
 }
+
+#ifdef CONFIG_ASYNC_PGTABLE_FREE
+static void kernel_pgtable_work_func(struct work_struct *work);
+
+static struct {
+	struct list_head list;
+	/* protect above ptdesc lists */
+	spinlock_t lock;
+	struct work_struct work;
+} kernel_pgtable_work = {
+	.list = LIST_HEAD_INIT(kernel_pgtable_work.list),
+	.lock = __SPIN_LOCK_UNLOCKED(kernel_pgtable_work.lock),
+	.work = __WORK_INITIALIZER(kernel_pgtable_work.work, kernel_pgtable_work_func),
+};
+
+static void kernel_pgtable_work_func(struct work_struct *work)
+{
+	struct ptdesc *pt, *next;
+	LIST_HEAD(page_list);
+
+	spin_lock(&kernel_pgtable_work.lock);
+	list_splice_tail_init(&kernel_pgtable_work.list, &page_list);
+	spin_unlock(&kernel_pgtable_work.lock);
+
+	list_for_each_entry_safe(pt, next, &page_list, pt_list)
+		__pagetable_free(pt);
+}
+
+void pagetable_free_kernel(struct ptdesc *pt)
+{
+	spin_lock(&kernel_pgtable_work.lock);
+	list_add(&pt->pt_list, &kernel_pgtable_work.list);
+	spin_unlock(&kernel_pgtable_work.lock);
+
+	schedule_work(&kernel_pgtable_work.work);
+}
+#endif
-- 
2.43.0