[v4,hmm,12/12] mm/hmm: Fix error flows in hmm_invalidate_range_start

Submitted by Jason Gunthorpe on June 24, 2019, 9:01 p.m.

Details

Message ID 20190624210110.5098-13-jgg@ziepe.ca
State New
Headers show
Series "Series without cover letter" ( rev: 1 ) in AMD X.Org drivers

Not browsing as part of any series.

Commit Message

Jason Gunthorpe June 24, 2019, 9:01 p.m.
From: Jason Gunthorpe <jgg@mellanox.com>

If the trylock on the hmm->mirrors_sem fails the function will return
without decrementing the notifiers that were previously incremented. Since
the caller will not call invalidate_range_end() on EAGAIN this will result
in notifiers becoming permanently incremented and deadlock.

If the sync_cpu_device_pagetables() required blocking the function will
not return EAGAIN even though the device continues to touch the
pages. This is a violation of the mmu notifier contract.

Switch, and rename, the ranges_lock to a spin lock so we can reliably
obtain it without blocking during error unwind.

The error unwind is necessary since the notifiers count must be held
incremented across the call to sync_cpu_device_pagetables() as we cannot
allow the range to become marked valid by a parallel
invalidate_start/end() pair while doing sync_cpu_device_pagetables().

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Philip Yang <Philip.Yang@amd.com>
---
 include/linux/hmm.h |  2 +-
 mm/hmm.c            | 72 +++++++++++++++++++++++++++------------------
 2 files changed, 45 insertions(+), 29 deletions(-)

Patch hide | download patch | download mbox

diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index bf013e96525771..0fa8ea34ccef6d 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -86,7 +86,7 @@ 
 struct hmm {
 	struct mm_struct	*mm;
 	struct kref		kref;
-	struct mutex		lock;
+	spinlock_t		ranges_lock;
 	struct list_head	ranges;
 	struct list_head	mirrors;
 	struct mmu_notifier	mmu_notifier;
diff --git a/mm/hmm.c b/mm/hmm.c
index b224ea635a7716..89549eac03d506 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -64,7 +64,7 @@  static struct hmm *hmm_get_or_create(struct mm_struct *mm)
 	init_rwsem(&hmm->mirrors_sem);
 	hmm->mmu_notifier.ops = NULL;
 	INIT_LIST_HEAD(&hmm->ranges);
-	mutex_init(&hmm->lock);
+	spin_lock_init(&hmm->ranges_lock);
 	kref_init(&hmm->kref);
 	hmm->notifiers = 0;
 	hmm->mm = mm;
@@ -144,6 +144,23 @@  static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	hmm_put(hmm);
 }
 
+static void notifiers_decrement(struct hmm *hmm)
+{
+	lockdep_assert_held(&hmm->ranges_lock);
+
+	hmm->notifiers--;
+	if (!hmm->notifiers) {
+		struct hmm_range *range;
+
+		list_for_each_entry(range, &hmm->ranges, list) {
+			if (range->valid)
+				continue;
+			range->valid = true;
+		}
+		wake_up_all(&hmm->wq);
+	}
+}
+
 static int hmm_invalidate_range_start(struct mmu_notifier *mn,
 			const struct mmu_notifier_range *nrange)
 {
@@ -151,6 +168,7 @@  static int hmm_invalidate_range_start(struct mmu_notifier *mn,
 	struct hmm_mirror *mirror;
 	struct hmm_update update;
 	struct hmm_range *range;
+	unsigned long flags;
 	int ret = 0;
 
 	if (!kref_get_unless_zero(&hmm->kref))
@@ -161,12 +179,7 @@  static int hmm_invalidate_range_start(struct mmu_notifier *mn,
 	update.event = HMM_UPDATE_INVALIDATE;
 	update.blockable = mmu_notifier_range_blockable(nrange);
 
-	if (mmu_notifier_range_blockable(nrange))
-		mutex_lock(&hmm->lock);
-	else if (!mutex_trylock(&hmm->lock)) {
-		ret = -EAGAIN;
-		goto out;
-	}
+	spin_lock_irqsave(&hmm->ranges_lock, flags);
 	hmm->notifiers++;
 	list_for_each_entry(range, &hmm->ranges, list) {
 		if (update.end < range->start || update.start >= range->end)
@@ -174,7 +187,7 @@  static int hmm_invalidate_range_start(struct mmu_notifier *mn,
 
 		range->valid = false;
 	}
-	mutex_unlock(&hmm->lock);
+	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
 
 	if (mmu_notifier_range_blockable(nrange))
 		down_read(&hmm->mirrors_sem);
@@ -182,16 +195,26 @@  static int hmm_invalidate_range_start(struct mmu_notifier *mn,
 		ret = -EAGAIN;
 		goto out;
 	}
+
 	list_for_each_entry(mirror, &hmm->mirrors, list) {
-		int ret;
+		int rc;
 
-		ret = mirror->ops->sync_cpu_device_pagetables(mirror, &update);
-		if (!update.blockable && ret == -EAGAIN)
+		rc = mirror->ops->sync_cpu_device_pagetables(mirror, &update);
+		if (rc) {
+			if (WARN_ON(update.blockable || rc != -EAGAIN))
+				continue;
+			ret = -EAGAIN;
 			break;
+		}
 	}
 	up_read(&hmm->mirrors_sem);
 
 out:
+	if (ret) {
+		spin_lock_irqsave(&hmm->ranges_lock, flags);
+		notifiers_decrement(hmm);
+		spin_unlock_irqrestore(&hmm->ranges_lock, flags);
+	}
 	hmm_put(hmm);
 	return ret;
 }
@@ -200,23 +223,14 @@  static void hmm_invalidate_range_end(struct mmu_notifier *mn,
 			const struct mmu_notifier_range *nrange)
 {
 	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
+	unsigned long flags;
 
 	if (!kref_get_unless_zero(&hmm->kref))
 		return;
 
-	mutex_lock(&hmm->lock);
-	hmm->notifiers--;
-	if (!hmm->notifiers) {
-		struct hmm_range *range;
-
-		list_for_each_entry(range, &hmm->ranges, list) {
-			if (range->valid)
-				continue;
-			range->valid = true;
-		}
-		wake_up_all(&hmm->wq);
-	}
-	mutex_unlock(&hmm->lock);
+	spin_lock_irqsave(&hmm->ranges_lock, flags);
+	notifiers_decrement(hmm);
+	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
 
 	hmm_put(hmm);
 }
@@ -868,6 +882,7 @@  int hmm_range_register(struct hmm_range *range,
 {
 	unsigned long mask = ((1UL << page_shift) - 1UL);
 	struct hmm *hmm = mirror->hmm;
+	unsigned long flags;
 
 	range->valid = false;
 	range->hmm = NULL;
@@ -886,7 +901,7 @@  int hmm_range_register(struct hmm_range *range,
 		return -EFAULT;
 
 	/* Initialize range to track CPU page table updates. */
-	mutex_lock(&hmm->lock);
+	spin_lock_irqsave(&hmm->ranges_lock, flags);
 
 	range->hmm = hmm;
 	kref_get(&hmm->kref);
@@ -898,7 +913,7 @@  int hmm_range_register(struct hmm_range *range,
 	 */
 	if (!hmm->notifiers)
 		range->valid = true;
-	mutex_unlock(&hmm->lock);
+	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
 
 	return 0;
 }
@@ -914,10 +929,11 @@  EXPORT_SYMBOL(hmm_range_register);
 void hmm_range_unregister(struct hmm_range *range)
 {
 	struct hmm *hmm = range->hmm;
+	unsigned long flags;
 
-	mutex_lock(&hmm->lock);
+	spin_lock_irqsave(&hmm->ranges_lock, flags);
 	list_del_init(&range->list);
-	mutex_unlock(&hmm->lock);
+	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
 
 	/* Drop reference taken by hmm_range_register() */
 	mmput(hmm->mm);

Comments

On 6/24/19 2:01 PM, Jason Gunthorpe wrote:
> From: Jason Gunthorpe <jgg@mellanox.com>
> 
> If the trylock on the hmm->mirrors_sem fails the function will return
> without decrementing the notifiers that were previously incremented. Since
> the caller will not call invalidate_range_end() on EAGAIN this will result
> in notifiers becoming permanently incremented and deadlock.
> 
> If the sync_cpu_device_pagetables() required blocking the function will
> not return EAGAIN even though the device continues to touch the
> pages. This is a violation of the mmu notifier contract.
> 
> Switch, and rename, the ranges_lock to a spin lock so we can reliably
> obtain it without blocking during error unwind.
> 
> The error unwind is necessary since the notifiers count must be held
> incremented across the call to sync_cpu_device_pagetables() as we cannot
> allow the range to become marked valid by a parallel
> invalidate_start/end() pair while doing sync_cpu_device_pagetables().
> 
> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Tested-by: Philip Yang <Philip.Yang@amd.com>
> ---
>   include/linux/hmm.h |  2 +-
>   mm/hmm.c            | 72 +++++++++++++++++++++++++++------------------
>   2 files changed, 45 insertions(+), 29 deletions(-)
> 
> diff --git a/include/linux/hmm.h b/include/linux/hmm.h
> index bf013e96525771..0fa8ea34ccef6d 100644
> --- a/include/linux/hmm.h
> +++ b/include/linux/hmm.h
> @@ -86,7 +86,7 @@
>   struct hmm {
>   	struct mm_struct	*mm;
>   	struct kref		kref;
> -	struct mutex		lock;
> +	spinlock_t		ranges_lock;
>   	struct list_head	ranges;
>   	struct list_head	mirrors;
>   	struct mmu_notifier	mmu_notifier;
> diff --git a/mm/hmm.c b/mm/hmm.c
> index b224ea635a7716..89549eac03d506 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -64,7 +64,7 @@ static struct hmm *hmm_get_or_create(struct mm_struct *mm)
>   	init_rwsem(&hmm->mirrors_sem);
>   	hmm->mmu_notifier.ops = NULL;
>   	INIT_LIST_HEAD(&hmm->ranges);
> -	mutex_init(&hmm->lock);
> +	spin_lock_init(&hmm->ranges_lock);
>   	kref_init(&hmm->kref);
>   	hmm->notifiers = 0;
>   	hmm->mm = mm;
> @@ -144,6 +144,23 @@ static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
>   	hmm_put(hmm);
>   }
>   
> +static void notifiers_decrement(struct hmm *hmm)
> +{
> +	lockdep_assert_held(&hmm->ranges_lock);
> +

Why not acquire the lock here and release at the end instead
of asserting the lock is held?
It looks like everywhere notifiers_decrement() is called does
that.

> +	hmm->notifiers--;
> +	if (!hmm->notifiers) {
> +		struct hmm_range *range;
> +
> +		list_for_each_entry(range, &hmm->ranges, list) {
> +			if (range->valid)
> +				continue;
> +			range->valid = true;
> +		}
> +		wake_up_all(&hmm->wq);
> +	}
> +}
> +
>   static int hmm_invalidate_range_start(struct mmu_notifier *mn,
>   			const struct mmu_notifier_range *nrange)
>   {
> @@ -151,6 +168,7 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn,
>   	struct hmm_mirror *mirror;
>   	struct hmm_update update;
>   	struct hmm_range *range;
> +	unsigned long flags;
>   	int ret = 0;
>   
>   	if (!kref_get_unless_zero(&hmm->kref))
> @@ -161,12 +179,7 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn,
>   	update.event = HMM_UPDATE_INVALIDATE;
>   	update.blockable = mmu_notifier_range_blockable(nrange);
>   
> -	if (mmu_notifier_range_blockable(nrange))
> -		mutex_lock(&hmm->lock);
> -	else if (!mutex_trylock(&hmm->lock)) {
> -		ret = -EAGAIN;
> -		goto out;
> -	}
> +	spin_lock_irqsave(&hmm->ranges_lock, flags);
>   	hmm->notifiers++;
>   	list_for_each_entry(range, &hmm->ranges, list) {
>   		if (update.end < range->start || update.start >= range->end)
> @@ -174,7 +187,7 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn,
>   
>   		range->valid = false;
>   	}
> -	mutex_unlock(&hmm->lock);
> +	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
>   
>   	if (mmu_notifier_range_blockable(nrange))
>   		down_read(&hmm->mirrors_sem);
> @@ -182,16 +195,26 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn,
>   		ret = -EAGAIN;
>   		goto out;
>   	}
> +
>   	list_for_each_entry(mirror, &hmm->mirrors, list) {
> -		int ret;
> +		int rc;
>   
> -		ret = mirror->ops->sync_cpu_device_pagetables(mirror, &update);
> -		if (!update.blockable && ret == -EAGAIN)
> +		rc = mirror->ops->sync_cpu_device_pagetables(mirror, &update);
> +		if (rc) {
> +			if (WARN_ON(update.blockable || rc != -EAGAIN))
> +				continue;
> +			ret = -EAGAIN;
>   			break;
> +		}
>   	}
>   	up_read(&hmm->mirrors_sem);
>   
>   out:
> +	if (ret) {
> +		spin_lock_irqsave(&hmm->ranges_lock, flags);
> +		notifiers_decrement(hmm);
> +		spin_unlock_irqrestore(&hmm->ranges_lock, flags);
> +	}
>   	hmm_put(hmm);
>   	return ret;
>   }
> @@ -200,23 +223,14 @@ static void hmm_invalidate_range_end(struct mmu_notifier *mn,
>   			const struct mmu_notifier_range *nrange)
>   {
>   	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
> +	unsigned long flags;
>   
>   	if (!kref_get_unless_zero(&hmm->kref))
>   		return;
>   
> -	mutex_lock(&hmm->lock);
> -	hmm->notifiers--;
> -	if (!hmm->notifiers) {
> -		struct hmm_range *range;
> -
> -		list_for_each_entry(range, &hmm->ranges, list) {
> -			if (range->valid)
> -				continue;
> -			range->valid = true;
> -		}
> -		wake_up_all(&hmm->wq);
> -	}
> -	mutex_unlock(&hmm->lock);
> +	spin_lock_irqsave(&hmm->ranges_lock, flags);
> +	notifiers_decrement(hmm);
> +	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
>   
>   	hmm_put(hmm);
>   }
> @@ -868,6 +882,7 @@ int hmm_range_register(struct hmm_range *range,
>   {
>   	unsigned long mask = ((1UL << page_shift) - 1UL);
>   	struct hmm *hmm = mirror->hmm;
> +	unsigned long flags;
>   
>   	range->valid = false;
>   	range->hmm = NULL;
> @@ -886,7 +901,7 @@ int hmm_range_register(struct hmm_range *range,
>   		return -EFAULT;
>   
>   	/* Initialize range to track CPU page table updates. */
> -	mutex_lock(&hmm->lock);
> +	spin_lock_irqsave(&hmm->ranges_lock, flags);
>   
>   	range->hmm = hmm;
>   	kref_get(&hmm->kref);
> @@ -898,7 +913,7 @@ int hmm_range_register(struct hmm_range *range,
>   	 */
>   	if (!hmm->notifiers)
>   		range->valid = true;
> -	mutex_unlock(&hmm->lock);
> +	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
>   
>   	return 0;
>   }
> @@ -914,10 +929,11 @@ EXPORT_SYMBOL(hmm_range_register);
>   void hmm_range_unregister(struct hmm_range *range)
>   {
>   	struct hmm *hmm = range->hmm;
> +	unsigned long flags;
>   
> -	mutex_lock(&hmm->lock);
> +	spin_lock_irqsave(&hmm->ranges_lock, flags);
>   	list_del_init(&range->list);
> -	mutex_unlock(&hmm->lock);
> +	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
>   
>   	/* Drop reference taken by hmm_range_register() */
>   	mmput(hmm->mm);
>