Date:   Wed, 27 Jul 2022 13:04:20 +0530
From:   Pavan Kondeti <quic_pkondeti@...cinc.com>
To:     Michel Lespinasse <michel@...pinasse.org>
CC:     Linux-MM <linux-mm@...ck.org>, <linux-kernel@...r.kernel.org>,
        "Andrew Morton" <akpm@...ux-foundation.org>, <kernel-team@...com>,
        Laurent Dufour <ldufour@...ux.ibm.com>,
        Jerome Glisse <jglisse@...gle.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Michal Hocko <mhocko@...e.com>,
        Vlastimil Babka <vbabka@...e.cz>,
        Davidlohr Bueso <dave@...olabs.net>,
        Matthew Wilcox <willy@...radead.org>,
        Liam Howlett <liam.howlett@...cle.com>,
        Rik van Riel <riel@...riel.com>,
        Paul McKenney <paulmck@...nel.org>,
        Song Liu <songliubraving@...com>,
        Suren Baghdasaryan <surenb@...gle.com>,
        Minchan Kim <minchan@...gle.com>,
        Joel Fernandes <joelaf@...gle.com>,
        David Rientjes <rientjes@...gle.com>,
        Axel Rasmussen <axelrasmussen@...gle.com>,
        "Andy Lutomirski" <luto@...nel.org>
Subject: Re: [PATCH v2 23/35] mm: add mmu_notifier_lock

On Fri, Jan 28, 2022 at 05:09:54AM -0800, Michel Lespinasse wrote:
> 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@...pinasse.org>
> ---
>  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
>  }
>  

We have received a bug report from our customer running Android GKI kernel
android-13-5.15 branch where this series is included. As the callstack [1]
indicates, the non-atomic test it self is not sufficient to free the percpu
rwsem. 

The scenario deduced from the callstack:

- context switch on CPU#0 from 'A' to idle. idle thread took A's mm

- 'A' later ran on another CPU and exited. A's mm has still reference.

- Now CPU#0 is being hotplugged out. As part of this, idle thread's
mm is switched (in idle_task_exit()) but its active_mm freeing is
deferred to finish_cpu() which gets called later from the control processor
(the thread which initiated the CPU hotplug). Please see the reasoning
on why mmdrop() is not called in idle_task_exit() at
commit bf2c59fce4074('sched/core: Fix illegal RCU from offline CPUs')

- Now when finish_cpu() tries call percpu_free_rwsem() directly since we are
not in atomic path but hotplug path where cpus_write_lock() called is causing
the deadlock.

I am not sure if there is a clean way other than freeing the per-cpu
rwsemaphore asynchronously all the time.

[1]

-001|context_switch(inline)
-001|__schedule()
-002|__preempt_count_sub(inline)
-002|schedule()
-003|_raw_spin_unlock_irq(inline)
-003|spin_unlock_irq(inline)
-003|percpu_rwsem_wait()
-004|__preempt_count_add(inline)
-004|__percpu_down_read()
-005|percpu_down_read(inline)
-005|cpus_read_lock() // trying to get cpu_hotplug_lock again
-006|rcu_barrier()
-007|rcu_sync_dtor()
-008|mmu_notifier_subscriptions_destroy(inline)
-008|__mmdrop()
-009|mmdrop(inline)
-009|finish_cpu()
-010|cpuhp_invoke_callback()
-011|cpuhp_invoke_callback_range(inline)
-011|cpuhp_down_callbacks()
-012|_cpu_down() // acquired cpu_hotplug_lock (write lock)

Thanks,
Pavan

Powered by blists - more mailing lists