[PATCH v3 hmm 04/12] mm/hmm: Simplify hmm_get_or_create and make it reliable

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Jason Gunthorpe <jgg@xxxxxxxxxxxx>

As coded this function can false-fail in various racy situations. Make it
reliable and simpler by running under the write side of the mmap_sem and
avoiding the false-failing compare/exchange pattern. Due to the mmap_sem
this no longer has to avoid racing with a 2nd parallel
hmm_get_or_create().

Unfortunately this still has to use the page_table_lock as the
non-sleeping lock protecting mm->hmm, since the contexts where we free the
hmm are incompatible with mmap_sem.

Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxxxx>
Reviewed-by: John Hubbard <jhubbard@xxxxxxxxxx>
Reviewed-by: Ralph Campbell <rcampbell@xxxxxxxxxx>
Reviewed-by: Ira Weiny <ira.weiny@xxxxxxxxx>
Tested-by: Philip Yang <Philip.Yang@xxxxxxx>
---
v2:
- Fix error unwind of mmgrab (Jerome)
- Use hmm local instead of 2nd container_of (Jerome)
v3:
- Can't use mmap_sem in the SRCU callback, keep using the
  page_table_lock (Philip)
---
 mm/hmm.c | 84 ++++++++++++++++++++++++--------------------------------
 1 file changed, 36 insertions(+), 48 deletions(-)

diff --git a/mm/hmm.c b/mm/hmm.c
index 080b17a2e87e2d..4c64d4c32f4825 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -31,16 +31,6 @@
 #if IS_ENABLED(CONFIG_HMM_MIRROR)
 static const struct mmu_notifier_ops hmm_mmu_notifier_ops;
 
-static inline struct hmm *mm_get_hmm(struct mm_struct *mm)
-{
-	struct hmm *hmm = READ_ONCE(mm->hmm);
-
-	if (hmm && kref_get_unless_zero(&hmm->kref))
-		return hmm;
-
-	return NULL;
-}
-
 /**
  * hmm_get_or_create - register HMM against an mm (HMM internal)
  *
@@ -55,11 +45,19 @@ static inline struct hmm *mm_get_hmm(struct mm_struct *mm)
  */
 static struct hmm *hmm_get_or_create(struct mm_struct *mm)
 {
-	struct hmm *hmm = mm_get_hmm(mm);
-	bool cleanup = false;
+	struct hmm *hmm;
 
-	if (hmm)
-		return hmm;
+	lockdep_assert_held_exclusive(&mm->mmap_sem);
+
+	/* Abuse the page_table_lock to also protect mm->hmm. */
+	spin_lock(&mm->page_table_lock);
+	if (mm->hmm) {
+		if (kref_get_unless_zero(&mm->hmm->kref)) {
+			spin_unlock(&mm->page_table_lock);
+			return mm->hmm;
+		}
+	}
+	spin_unlock(&mm->page_table_lock);
 
 	hmm = kmalloc(sizeof(*hmm), GFP_KERNEL);
 	if (!hmm)
@@ -74,57 +72,47 @@ static struct hmm *hmm_get_or_create(struct mm_struct *mm)
 	hmm->notifiers = 0;
 	hmm->dead = false;
 	hmm->mm = mm;
-	mmgrab(hmm->mm);
 
-	spin_lock(&mm->page_table_lock);
-	if (!mm->hmm)
-		mm->hmm = hmm;
-	else
-		cleanup = true;
-	spin_unlock(&mm->page_table_lock);
+	hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
+	if (__mmu_notifier_register(&hmm->mmu_notifier, mm)) {
+		kfree(hmm);
+		return NULL;
+	}
 
-	if (cleanup)
-		goto error;
+	mmgrab(hmm->mm);
 
 	/*
-	 * We should only get here if hold the mmap_sem in write mode ie on
-	 * registration of first mirror through hmm_mirror_register()
+	 * We hold the exclusive mmap_sem here so we know that mm->hmm is
+	 * still NULL or 0 kref, and is safe to update.
 	 */
-	hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
-	if (__mmu_notifier_register(&hmm->mmu_notifier, mm))
-		goto error_mm;
-
-	return hmm;
-
-error_mm:
 	spin_lock(&mm->page_table_lock);
-	if (mm->hmm == hmm)
-		mm->hmm = NULL;
+	mm->hmm = hmm;
 	spin_unlock(&mm->page_table_lock);
-error:
-	mmdrop(hmm->mm);
-	kfree(hmm);
-	return NULL;
+	return hmm;
 }
 
 static void hmm_free_rcu(struct rcu_head *rcu)
 {
-	kfree(container_of(rcu, struct hmm, rcu));
+	struct hmm *hmm = container_of(rcu, struct hmm, rcu);
+
+	/*
+	 * The mm->hmm pointer is kept valid while notifier ops can be running
+	 * so they don't have to deal with a NULL mm->hmm value
+	 */
+	spin_lock(&hmm->mm->page_table_lock);
+	if (hmm->mm->hmm == hmm)
+		hmm->mm->hmm = NULL;
+	spin_unlock(&hmm->mm->page_table_lock);
+	mmdrop(hmm->mm);
+
+	kfree(hmm);
 }
 
 static void hmm_free(struct kref *kref)
 {
 	struct hmm *hmm = container_of(kref, struct hmm, kref);
-	struct mm_struct *mm = hmm->mm;
-
-	mmu_notifier_unregister_no_release(&hmm->mmu_notifier, mm);
 
-	spin_lock(&mm->page_table_lock);
-	if (mm->hmm == hmm)
-		mm->hmm = NULL;
-	spin_unlock(&mm->page_table_lock);
-
-	mmdrop(hmm->mm);
+	mmu_notifier_unregister_no_release(&hmm->mmu_notifier, hmm->mm);
 	mmu_notifier_call_srcu(&hmm->rcu, hmm_free_rcu);
 }
 
-- 
2.21.0




[Index of Archives]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Photo]     [Yosemite News]     [Yosemite Photos]     [Linux Kernel]     [Linux SCSI]     [XFree86]

  Powered by Linux