diff mbox series

[v2,hmm,06/11] mm/hmm: Hold on to the mmget for the lifetime of the range

Message ID 20190606184438.31646-7-jgg@ziepe.ca (mailing list archive)
State Superseded
Delegated to: Jason Gunthorpe
Headers show
Series Various revisions from a locking/code review | expand

Commit Message

Jason Gunthorpe June 6, 2019, 6:44 p.m. UTC 
From: Jason Gunthorpe <jgg@mellanox.com>

Range functions like hmm_range_snapshot() and hmm_range_fault() call
find_vma, which requires hodling the mmget() and the mmap_sem for the mm.

Make this simpler for the callers by holding the mmget() inside the range
for the lifetime of the range. Other functions that accept a range should
only be called if the range is registered.

This has the side effect of directly preventing hmm_release() from
happening while a range is registered. That means range->dead cannot be
false during the lifetime of the range, so remove dead and
hmm_mirror_mm_is_alive() entirely.

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
v2:
 - Use Jerome's idea of just holding the mmget() for the range lifetime,
   rework the patch to use that as as simplification to remove dead in
   one step
---
 include/linux/hmm.h | 26 --------------------------
 mm/hmm.c            | 28 ++++++++++------------------
 2 files changed, 10 insertions(+), 44 deletions(-)

Comments

John Hubbard June 7, 2019, 3:15 a.m. UTC | #1 
On 6/6/19 11:44 AM, Jason Gunthorpe wrote:
> From: Jason Gunthorpe <jgg@mellanox.com>
> 
> Range functions like hmm_range_snapshot() and hmm_range_fault() call
> find_vma, which requires hodling the mmget() and the mmap_sem for the mm.
> 
> Make this simpler for the callers by holding the mmget() inside the range
> for the lifetime of the range. Other functions that accept a range should
> only be called if the range is registered.
> 
> This has the side effect of directly preventing hmm_release() from
> happening while a range is registered. That means range->dead cannot be
> false during the lifetime of the range, so remove dead and
> hmm_mirror_mm_is_alive() entirely.
> 
> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
> ---
> v2:
>  - Use Jerome's idea of just holding the mmget() for the range lifetime,
>    rework the patch to use that as as simplification to remove dead in
>    one step
> ---
>  include/linux/hmm.h | 26 --------------------------
>  mm/hmm.c            | 28 ++++++++++------------------
>  2 files changed, 10 insertions(+), 44 deletions(-)
> 
> diff --git a/include/linux/hmm.h b/include/linux/hmm.h
> index 2ab35b40992b24..0e20566802967a 100644
> --- a/include/linux/hmm.h
> +++ b/include/linux/hmm.h
> @@ -91,7 +91,6 @@
>   * @mirrors_sem: read/write semaphore protecting the mirrors list
>   * @wq: wait queue for user waiting on a range invalidation
>   * @notifiers: count of active mmu notifiers
> - * @dead: is the mm dead ?
>   */
>  struct hmm {
>  	struct mm_struct	*mm;
> @@ -104,7 +103,6 @@ struct hmm {
>  	wait_queue_head_t	wq;
>  	struct rcu_head		rcu;
>  	long			notifiers;
> -	bool			dead;
>  };
>  
>  /*
> @@ -469,30 +467,6 @@ struct hmm_mirror {
>  int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm);
>  void hmm_mirror_unregister(struct hmm_mirror *mirror);
>  
> -/*
> - * hmm_mirror_mm_is_alive() - test if mm is still alive
> - * @mirror: the HMM mm mirror for which we want to lock the mmap_sem
> - * Return: false if the mm is dead, true otherwise
> - *
> - * This is an optimization, it will not always accurately return false if the
> - * mm is dead; i.e., there can be false negatives (process is being killed but
> - * HMM is not yet informed of that). It is only intended to be used to optimize
> - * out cases where the driver is about to do something time consuming and it
> - * would be better to skip it if the mm is dead.
> - */
> -static inline bool hmm_mirror_mm_is_alive(struct hmm_mirror *mirror)
> -{
> -	struct mm_struct *mm;
> -
> -	if (!mirror || !mirror->hmm)
> -		return false;
> -	mm = READ_ONCE(mirror->hmm->mm);
> -	if (mirror->hmm->dead || !mm)
> -		return false;
> -
> -	return true;
> -}
> -
>  /*
>   * Please see Documentation/vm/hmm.rst for how to use the range API.
>   */
> diff --git a/mm/hmm.c b/mm/hmm.c
> index dc30edad9a8a02..f67ba32983d9f1 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -80,7 +80,6 @@ static struct hmm *hmm_get_or_create(struct mm_struct *mm)
>  	mutex_init(&hmm->lock);
>  	kref_init(&hmm->kref);
>  	hmm->notifiers = 0;
> -	hmm->dead = false;
>  	hmm->mm = mm;
>  
>  	hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
> @@ -124,20 +123,17 @@ static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
>  {
>  	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
>  	struct hmm_mirror *mirror;
> -	struct hmm_range *range;
>  
>  	/* hmm is in progress to free */
>  	if (!kref_get_unless_zero(&hmm->kref))
>  		return;
>  
> -	/* Report this HMM as dying. */
> -	hmm->dead = true;
> -
> -	/* Wake-up everyone waiting on any range. */
>  	mutex_lock(&hmm->lock);
> -	list_for_each_entry(range, &hmm->ranges, list)
> -		range->valid = false;
> -	wake_up_all(&hmm->wq);
> +	/*
> +	 * Since hmm_range_register() holds the mmget() lock hmm_release() is
> +	 * prevented as long as a range exists.
> +	 */
> +	WARN_ON(!list_empty(&hmm->ranges));
>  	mutex_unlock(&hmm->lock);
>  
>  	down_write(&hmm->mirrors_sem);
> @@ -909,8 +905,8 @@ int hmm_range_register(struct hmm_range *range,
>  	range->start = start;
>  	range->end = end;
>  
> -	/* Check if hmm_mm_destroy() was call. */
> -	if (hmm->mm == NULL || hmm->dead)
> +	/* Prevent hmm_release() from running while the range is valid */
> +	if (!mmget_not_zero(hmm->mm))
>  		return -EFAULT;
>  
>  	range->hmm = hmm;
> @@ -955,6 +951,7 @@ void hmm_range_unregister(struct hmm_range *range)
>  
>  	/* Drop reference taken by hmm_range_register() */
>  	range->valid = false;
> +	mmput(hmm->mm);
>  	hmm_put(hmm);
>  	range->hmm = NULL;
>  }
> @@ -982,10 +979,7 @@ long hmm_range_snapshot(struct hmm_range *range)
>  	struct vm_area_struct *vma;
>  	struct mm_walk mm_walk;
>  
> -	/* Check if hmm_mm_destroy() was call. */
> -	if (hmm->mm == NULL || hmm->dead)
> -		return -EFAULT;
> -
> +	lockdep_assert_held(&hmm->mm->mmap_sem);
>  	do {
>  		/* If range is no longer valid force retry. */
>  		if (!range->valid)
> @@ -1080,9 +1074,7 @@ long hmm_range_fault(struct hmm_range *range, bool block)
>  	struct mm_walk mm_walk;
>  	int ret;
>  
> -	/* Check if hmm_mm_destroy() was call. */
> -	if (hmm->mm == NULL || hmm->dead)
> -		return -EFAULT;
> +	lockdep_assert_held(&hmm->mm->mmap_sem);
>  
>  	do {
>  		/* If range is no longer valid force retry. */
> 

Nice cleanup.

    Reviewed-by: John Hubbard <jhubbard@nvidia.com>


thanks,
Ralph Campbell June 7, 2019, 8:29 p.m. UTC | #2 
On 6/6/19 11:44 AM, Jason Gunthorpe wrote:
> From: Jason Gunthorpe <jgg@mellanox.com>
> 
> Range functions like hmm_range_snapshot() and hmm_range_fault() call
> find_vma, which requires hodling the mmget() and the mmap_sem for the mm.
> 
> Make this simpler for the callers by holding the mmget() inside the range
> for the lifetime of the range. Other functions that accept a range should
> only be called if the range is registered.
> 
> This has the side effect of directly preventing hmm_release() from
> happening while a range is registered. That means range->dead cannot be
> false during the lifetime of the range, so remove dead and
> hmm_mirror_mm_is_alive() entirely.
> 
> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

Looks good to me.
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>

> ---
> v2:
>   - Use Jerome's idea of just holding the mmget() for the range lifetime,
>     rework the patch to use that as as simplification to remove dead in
>     one step
> ---
>   include/linux/hmm.h | 26 --------------------------
>   mm/hmm.c            | 28 ++++++++++------------------
>   2 files changed, 10 insertions(+), 44 deletions(-)
> 
> diff --git a/include/linux/hmm.h b/include/linux/hmm.h
> index 2ab35b40992b24..0e20566802967a 100644
> --- a/include/linux/hmm.h
> +++ b/include/linux/hmm.h
> @@ -91,7 +91,6 @@
>    * @mirrors_sem: read/write semaphore protecting the mirrors list
>    * @wq: wait queue for user waiting on a range invalidation
>    * @notifiers: count of active mmu notifiers
> - * @dead: is the mm dead ?
>    */
>   struct hmm {
>   	struct mm_struct	*mm;
> @@ -104,7 +103,6 @@ struct hmm {
>   	wait_queue_head_t	wq;
>   	struct rcu_head		rcu;
>   	long			notifiers;
> -	bool			dead;
>   };
>   
>   /*
> @@ -469,30 +467,6 @@ struct hmm_mirror {
>   int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm);
>   void hmm_mirror_unregister(struct hmm_mirror *mirror);
>   
> -/*
> - * hmm_mirror_mm_is_alive() - test if mm is still alive
> - * @mirror: the HMM mm mirror for which we want to lock the mmap_sem
> - * Return: false if the mm is dead, true otherwise
> - *
> - * This is an optimization, it will not always accurately return false if the
> - * mm is dead; i.e., there can be false negatives (process is being killed but
> - * HMM is not yet informed of that). It is only intended to be used to optimize
> - * out cases where the driver is about to do something time consuming and it
> - * would be better to skip it if the mm is dead.
> - */
> -static inline bool hmm_mirror_mm_is_alive(struct hmm_mirror *mirror)
> -{
> -	struct mm_struct *mm;
> -
> -	if (!mirror || !mirror->hmm)
> -		return false;
> -	mm = READ_ONCE(mirror->hmm->mm);
> -	if (mirror->hmm->dead || !mm)
> -		return false;
> -
> -	return true;
> -}
> -
>   /*
>    * Please see Documentation/vm/hmm.rst for how to use the range API.
>    */
> diff --git a/mm/hmm.c b/mm/hmm.c
> index dc30edad9a8a02..f67ba32983d9f1 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -80,7 +80,6 @@ static struct hmm *hmm_get_or_create(struct mm_struct *mm)
>   	mutex_init(&hmm->lock);
>   	kref_init(&hmm->kref);
>   	hmm->notifiers = 0;
> -	hmm->dead = false;
>   	hmm->mm = mm;
>   
>   	hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
> @@ -124,20 +123,17 @@ static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
>   {
>   	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
>   	struct hmm_mirror *mirror;
> -	struct hmm_range *range;
>   
>   	/* hmm is in progress to free */
>   	if (!kref_get_unless_zero(&hmm->kref))
>   		return;
>   
> -	/* Report this HMM as dying. */
> -	hmm->dead = true;
> -
> -	/* Wake-up everyone waiting on any range. */
>   	mutex_lock(&hmm->lock);
> -	list_for_each_entry(range, &hmm->ranges, list)
> -		range->valid = false;
> -	wake_up_all(&hmm->wq);
> +	/*
> +	 * Since hmm_range_register() holds the mmget() lock hmm_release() is
> +	 * prevented as long as a range exists.
> +	 */
> +	WARN_ON(!list_empty(&hmm->ranges));
>   	mutex_unlock(&hmm->lock);
>   
>   	down_write(&hmm->mirrors_sem);
> @@ -909,8 +905,8 @@ int hmm_range_register(struct hmm_range *range,
>   	range->start = start;
>   	range->end = end;
>   
> -	/* Check if hmm_mm_destroy() was call. */
> -	if (hmm->mm == NULL || hmm->dead)
> +	/* Prevent hmm_release() from running while the range is valid */
> +	if (!mmget_not_zero(hmm->mm))
>   		return -EFAULT;
>   
>   	range->hmm = hmm;
> @@ -955,6 +951,7 @@ void hmm_range_unregister(struct hmm_range *range)
>   
>   	/* Drop reference taken by hmm_range_register() */
>   	range->valid = false;
> +	mmput(hmm->mm);
>   	hmm_put(hmm);
>   	range->hmm = NULL;
>   }
> @@ -982,10 +979,7 @@ long hmm_range_snapshot(struct hmm_range *range)
>   	struct vm_area_struct *vma;
>   	struct mm_walk mm_walk;
>   
> -	/* Check if hmm_mm_destroy() was call. */
> -	if (hmm->mm == NULL || hmm->dead)
> -		return -EFAULT;
> -
> +	lockdep_assert_held(&hmm->mm->mmap_sem);
>   	do {
>   		/* If range is no longer valid force retry. */
>   		if (!range->valid)
> @@ -1080,9 +1074,7 @@ long hmm_range_fault(struct hmm_range *range, bool block)
>   	struct mm_walk mm_walk;
>   	int ret;
>   
> -	/* Check if hmm_mm_destroy() was call. */
> -	if (hmm->mm == NULL || hmm->dead)
> -		return -EFAULT;
> +	lockdep_assert_held(&hmm->mm->mmap_sem);
>   
>   	do {
>   		/* If range is no longer valid force retry. */
>
diff mbox series

Patch

diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 2ab35b40992b24..0e20566802967a 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -91,7 +91,6 @@ 
  * @mirrors_sem: read/write semaphore protecting the mirrors list
  * @wq: wait queue for user waiting on a range invalidation
  * @notifiers: count of active mmu notifiers
- * @dead: is the mm dead ?
  */
 struct hmm {
 	struct mm_struct	*mm;
@@ -104,7 +103,6 @@  struct hmm {
 	wait_queue_head_t	wq;
 	struct rcu_head		rcu;
 	long			notifiers;
-	bool			dead;
 };
 
 /*
@@ -469,30 +467,6 @@  struct hmm_mirror {
 int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm);
 void hmm_mirror_unregister(struct hmm_mirror *mirror);
 
-/*
- * hmm_mirror_mm_is_alive() - test if mm is still alive
- * @mirror: the HMM mm mirror for which we want to lock the mmap_sem
- * Return: false if the mm is dead, true otherwise
- *
- * This is an optimization, it will not always accurately return false if the
- * mm is dead; i.e., there can be false negatives (process is being killed but
- * HMM is not yet informed of that). It is only intended to be used to optimize
- * out cases where the driver is about to do something time consuming and it
- * would be better to skip it if the mm is dead.
- */
-static inline bool hmm_mirror_mm_is_alive(struct hmm_mirror *mirror)
-{
-	struct mm_struct *mm;
-
-	if (!mirror || !mirror->hmm)
-		return false;
-	mm = READ_ONCE(mirror->hmm->mm);
-	if (mirror->hmm->dead || !mm)
-		return false;
-
-	return true;
-}
-
 /*
  * Please see Documentation/vm/hmm.rst for how to use the range API.
  */
diff --git a/mm/hmm.c b/mm/hmm.c
index dc30edad9a8a02..f67ba32983d9f1 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -80,7 +80,6 @@  static struct hmm *hmm_get_or_create(struct mm_struct *mm)
 	mutex_init(&hmm->lock);
 	kref_init(&hmm->kref);
 	hmm->notifiers = 0;
-	hmm->dead = false;
 	hmm->mm = mm;
 
 	hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
@@ -124,20 +123,17 @@  static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 {
 	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
 	struct hmm_mirror *mirror;
-	struct hmm_range *range;
 
 	/* hmm is in progress to free */
 	if (!kref_get_unless_zero(&hmm->kref))
 		return;
 
-	/* Report this HMM as dying. */
-	hmm->dead = true;
-
-	/* Wake-up everyone waiting on any range. */
 	mutex_lock(&hmm->lock);
-	list_for_each_entry(range, &hmm->ranges, list)
-		range->valid = false;
-	wake_up_all(&hmm->wq);
+	/*
+	 * Since hmm_range_register() holds the mmget() lock hmm_release() is
+	 * prevented as long as a range exists.
+	 */
+	WARN_ON(!list_empty(&hmm->ranges));
 	mutex_unlock(&hmm->lock);
 
 	down_write(&hmm->mirrors_sem);
@@ -909,8 +905,8 @@  int hmm_range_register(struct hmm_range *range,
 	range->start = start;
 	range->end = end;
 
-	/* Check if hmm_mm_destroy() was call. */
-	if (hmm->mm == NULL || hmm->dead)
+	/* Prevent hmm_release() from running while the range is valid */
+	if (!mmget_not_zero(hmm->mm))
 		return -EFAULT;
 
 	range->hmm = hmm;
@@ -955,6 +951,7 @@  void hmm_range_unregister(struct hmm_range *range)
 
 	/* Drop reference taken by hmm_range_register() */
 	range->valid = false;
+	mmput(hmm->mm);
 	hmm_put(hmm);
 	range->hmm = NULL;
 }
@@ -982,10 +979,7 @@  long hmm_range_snapshot(struct hmm_range *range)
 	struct vm_area_struct *vma;
 	struct mm_walk mm_walk;
 
-	/* Check if hmm_mm_destroy() was call. */
-	if (hmm->mm == NULL || hmm->dead)
-		return -EFAULT;
-
+	lockdep_assert_held(&hmm->mm->mmap_sem);
 	do {
 		/* If range is no longer valid force retry. */
 		if (!range->valid)
@@ -1080,9 +1074,7 @@  long hmm_range_fault(struct hmm_range *range, bool block)
 	struct mm_walk mm_walk;
 	int ret;
 
-	/* Check if hmm_mm_destroy() was call. */
-	if (hmm->mm == NULL || hmm->dead)
-		return -EFAULT;
+	lockdep_assert_held(&hmm->mm->mmap_sem);
 
 	do {
 		/* If range is no longer valid force retry. */