[PATCH v2 23/35] mm: add mmu_notifier_lock

[Michel Lespinasse <michel@xxxxxxxxxxxxxx>]

Introduce mmu_notifier_lock as a per-mm percpu_rw_semaphore,
as well as the code to initialize and destroy it together with the mm.

This lock will be used to prevent races between mmu_notifier_register()
and speculative fault handlers that need to fire MMU notifications
without holding any of the mmap or rmap locks.

Signed-off-by: Michel Lespinasse <michel@xxxxxxxxxxxxxx>
---
 include/linux/mm_types.h     |  6 +++++-
 include/linux/mmu_notifier.h | 27 +++++++++++++++++++++++++--
 kernel/fork.c                |  3 ++-
 3 files changed, 32 insertions(+), 4 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 305f05d2a4bc..f77e2dec038d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -462,6 +462,7 @@ struct vm_area_struct {
 } __randomize_layout;
 
 struct kioctx_table;
+struct percpu_rw_semaphore;
 struct mm_struct {
 	struct {
 		struct vm_area_struct *mmap;		/* list of VMAs */
@@ -608,7 +609,10 @@ struct mm_struct {
 		struct file __rcu *exe_file;
 #ifdef CONFIG_MMU_NOTIFIER
 		struct mmu_notifier_subscriptions *notifier_subscriptions;
-#endif
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+		struct percpu_rw_semaphore *mmu_notifier_lock;
+#endif	/* CONFIG_SPECULATIVE_PAGE_FAULT */
+#endif	/* CONFIG_MMU_NOTIFIER */
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 		pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 45fc2c81e370..ace76fe91c0c 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -6,6 +6,8 @@
 #include <linux/spinlock.h>
 #include <linux/mm_types.h>
 #include <linux/mmap_lock.h>
+#include <linux/percpu-rwsem.h>
+#include <linux/slab.h>
 #include <linux/srcu.h>
 #include <linux/interval_tree.h>
 
@@ -499,15 +501,35 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
 		__mmu_notifier_invalidate_range(mm, start, end);
 }
 
-static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm)
+static inline bool mmu_notifier_subscriptions_init(struct mm_struct *mm)
 {
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+	mm->mmu_notifier_lock = kzalloc(sizeof(struct percpu_rw_semaphore), GFP_KERNEL);
+	if (!mm->mmu_notifier_lock)
+		return false;
+	if (percpu_init_rwsem(mm->mmu_notifier_lock)) {
+		kfree(mm->mmu_notifier_lock);
+		return false;
+	}
+#endif
+
 	mm->notifier_subscriptions = NULL;
+	return true;
 }
 
 static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
 {
 	if (mm_has_notifiers(mm))
 		__mmu_notifier_subscriptions_destroy(mm);
+
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+	if (!in_atomic()) {
+		percpu_free_rwsem(mm->mmu_notifier_lock);
+		kfree(mm->mmu_notifier_lock);
+	} else {
+		percpu_rwsem_async_destroy(mm->mmu_notifier_lock);
+	}
+#endif
 }
 
 
@@ -724,8 +746,9 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
 {
 }
 
-static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm)
+static inline bool mmu_notifier_subscriptions_init(struct mm_struct *mm)
 {
+	return true;
 }
 
 static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
diff --git a/kernel/fork.c b/kernel/fork.c
index 2e5f2e8de31a..db92e42d0087 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1069,7 +1069,8 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm_init_owner(mm, p);
 	mm_init_pasid(mm);
 	RCU_INIT_POINTER(mm->exe_file, NULL);
-	mmu_notifier_subscriptions_init(mm);
+	if (!mmu_notifier_subscriptions_init(mm))
+		goto fail_nopgd;
 	init_tlb_flush_pending(mm);
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	mm->pmd_huge_pte = NULL;
-- 
2.20.1