[v3,07/10] mmap locking API: add mmap_read_release() and mmap_read_unlock_non_owner()
diff mbox series

Message ID 20200327225102.25061-8-walken@google.com
State New
Headers show
Series
  • Add a new mmap locking API wrapping mmap_sem calls
Related show

Commit Message

Michel Lespinasse March 27, 2020, 10:50 p.m. UTC
Add a couple APIs to allow splitting mmap_read_unlock() into two calls:
- mmap_read_release(), called by the task that had taken the mmap lock;
- mmap_read_unlock_non_owner(), called from a work queue.

These apis are used by kernel/bpf/stackmap.c only.

Signed-off-by: Michel Lespinasse <walken@google.com>
---
 include/linux/mmap_lock.h | 10 ++++++++++
 kernel/bpf/stackmap.c     |  9 ++++-----
 2 files changed, 14 insertions(+), 5 deletions(-)

Comments

Peter Zijlstra April 1, 2020, 1:46 p.m. UTC | #1
On Fri, Mar 27, 2020 at 03:50:59PM -0700, Michel Lespinasse wrote:
> Add a couple APIs to allow splitting mmap_read_unlock() into two calls:
> - mmap_read_release(), called by the task that had taken the mmap lock;
> - mmap_read_unlock_non_owner(), called from a work queue.
> 
> These apis are used by kernel/bpf/stackmap.c only.

That code is an absolute abomination and should never have gotten
merged.

That said; I would prefer a mmap_read_trylock_nonowner() over
mmap_read_release() existing.

> Signed-off-by: Michel Lespinasse <walken@google.com>
> ---
>  include/linux/mmap_lock.h | 10 ++++++++++
>  kernel/bpf/stackmap.c     |  9 ++++-----
>  2 files changed, 14 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
> index 36fb758401d6..a80cf9695514 100644
> --- a/include/linux/mmap_lock.h
> +++ b/include/linux/mmap_lock.h
> @@ -62,4 +62,14 @@ static inline void mmap_read_unlock(struct mm_struct *mm)
>  	up_read(&mm->mmap_sem);
>  }
>  
> +static inline void mmap_read_release(struct mm_struct *mm, unsigned long ip)
> +{
> +	rwsem_release(&mm->mmap_sem.dep_map, ip);
> +}
> +
> +static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)
> +{
> +	up_read_non_owner(&mm->mmap_sem);
> +}
> +
>  #endif /* _LINUX_MMAP_LOCK_H */
Michel Lespinasse April 6, 2020, 3:39 p.m. UTC | #2
On Wed, Apr 1, 2020 at 6:46 AM Peter Zijlstra <peterz@infradead.org> wrote:
> On Fri, Mar 27, 2020 at 03:50:59PM -0700, Michel Lespinasse wrote:
> > Add a couple APIs to allow splitting mmap_read_unlock() into two calls:
> > - mmap_read_release(), called by the task that had taken the mmap lock;
> > - mmap_read_unlock_non_owner(), called from a work queue.
> >
> > These apis are used by kernel/bpf/stackmap.c only.
>
> That code is an absolute abomination and should never have gotten
> merged.

I have to say, it's causing me some grief too :/

> That said; I would prefer a mmap_read_trylock_nonowner() over
> mmap_read_release() existing.

It only addresses part of the issue, but I suppose I could do that. Is
this something I could append to the end of this series, or do I need
to prepare a v4 for such changes ?

Patch
diff mbox series

diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index 36fb758401d6..a80cf9695514 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -62,4 +62,14 @@  static inline void mmap_read_unlock(struct mm_struct *mm)
 	up_read(&mm->mmap_sem);
 }
 
+static inline void mmap_read_release(struct mm_struct *mm, unsigned long ip)
+{
+	rwsem_release(&mm->mmap_sem.dep_map, ip);
+}
+
+static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)
+{
+	up_read_non_owner(&mm->mmap_sem);
+}
+
 #endif /* _LINUX_MMAP_LOCK_H */
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index f2115f691577..413b512a99eb 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -33,7 +33,7 @@  struct bpf_stack_map {
 /* irq_work to run up_read() for build_id lookup in nmi context */
 struct stack_map_irq_work {
 	struct irq_work irq_work;
-	struct rw_semaphore *sem;
+	struct mm_struct *mm;
 };
 
 static void do_up_read(struct irq_work *entry)
@@ -41,8 +41,7 @@  static void do_up_read(struct irq_work *entry)
 	struct stack_map_irq_work *work;
 
 	work = container_of(entry, struct stack_map_irq_work, irq_work);
-	up_read_non_owner(work->sem);
-	work->sem = NULL;
+	mmap_read_unlock_non_owner(work->mm);
 }
 
 static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work);
@@ -332,14 +331,14 @@  static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	if (!work) {
 		mmap_read_unlock(current->mm);
 	} else {
-		work->sem = &current->mm->mmap_sem;
+		work->mm = current->mm;
 		irq_work_queue(&work->irq_work);
 		/*
 		 * The irq_work will release the mmap_sem with
 		 * up_read_non_owner(). The rwsem_release() is called
 		 * here to release the lock from lockdep's perspective.
 		 */
-		rwsem_release(&current->mm->mmap_sem.dep_map, _RET_IP_);
+		mmap_read_release(current->mm, _RET_IP_);
 	}
 }