Re: 5.13-rt1 + KVM = WARNING: at fs/eventfd.c:74 eventfd_signal()

[He Zhe <zhe.he@windriver.com>]

On 7/15/21 4:22 PM, Daniel Bristot de Oliveira wrote:
> On 7/14/21 12:35 PM, Paolo Bonzini wrote:
>> On 14/07/21 11:23, Jason Wang wrote:
>>>> This was added in 2020, so it's unlikely to be the direct cause of the
>>>> change.  What is a known-good version for the host?
>>>>
>>>> Since it is not KVM stuff, I'm CCing Michael and Jason.
>>> I think this can be probably fixed here:
>>>
>>> https://lore.kernel.org/lkml/20210618084412.18257-1-zhe.he@windriver.com/
>> That seems wrong; in particular it wouldn't protect against AB/BA deadlocks.
>> In fact, the bug is with the locking; the code assumes that
>> spin_lock_irqsave/spin_unlock_irqrestore is non-preemptable and therefore
>> increments and decrements the percpu variable inside the critical section.
>>
>> This obviously does not fly with PREEMPT_RT; the right fix should be
>> using a local_lock.  Something like this (untested!!):
> the lock needs to be per-pcu... but so far, so good. I will continue using the
> system in the next days to see if it blows on another way.

The original patch was created before preempt-rt was fully introduced into
mainline. It was to increase the recursion depth to 2 so that vhost_worker and
kvm_vcpu_ioctl syscall could work in parallel, as shown in the original commit
log.

So the event_fd_recursion.count should still be 2 to fix the original issue,
no matter how locks would be tweaked accordingly.

Zhe

>
> The patch looks like this now:
>
> ------------------------- 8< ---------------------
> Subject: [PATCH] eventfd: protect eventfd_wake_count with a local_lock
>
> eventfd_signal assumes that spin_lock_irqsave/spin_unlock_irqrestore is
> non-preemptable and therefore increments and decrements the percpu
> variable inside the critical section.
>
> This obviously does not fly with PREEMPT_RT. If eventfd_signal is
> preempted and an unrelated thread calls eventfd_signal, the result is
> a spurious WARN. To avoid this, protect the percpu variable with a
> local_lock.
>
> Reported-by: Daniel Bristot de Oliveira <bristot@redhat.com>
> Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
> Fixes: b5e683d5cab8 ("eventfd: track eventfd_signal() recursion depth")
> Cc: stable@vger.kernel.org
> Cc: He Zhe <zhe.he@windriver.com>
> Cc: Jens Axboe <axboe@kernel.dk>
> Co-developed-by: Paolo Bonzini <pbonzini@redhat.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> Co-developed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
> Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
> ---
>  fs/eventfd.c            | 27 ++++++++++++++++++++++-----
>  include/linux/eventfd.h |  7 +------
>  2 files changed, 23 insertions(+), 11 deletions(-)
>
> diff --git a/fs/eventfd.c b/fs/eventfd.c
> index e265b6dd4f34..9754fcd38690 100644
> --- a/fs/eventfd.c
> +++ b/fs/eventfd.c
> @@ -12,6 +12,7 @@
>  #include <linux/fs.h>
>  #include <linux/sched/signal.h>
>  #include <linux/kernel.h>
> +#include <linux/local_lock.h>
>  #include <linux/slab.h>
>  #include <linux/list.h>
>  #include <linux/spinlock.h>
> @@ -25,8 +26,6 @@
>  #include <linux/idr.h>
>  #include <linux/uio.h>
>
> -DEFINE_PER_CPU(int, eventfd_wake_count);
> -
>  static DEFINE_IDA(eventfd_ida);
>
>  struct eventfd_ctx {
> @@ -45,6 +44,20 @@ struct eventfd_ctx {
>  	int id;
>  };
>
> +struct event_fd_recursion {
> +	local_lock_t lock;
> +	int count;
> +};
> +
> +static DEFINE_PER_CPU(struct event_fd_recursion, event_fd_recursion) = {
> +	.lock = INIT_LOCAL_LOCK(lock),
> +};
> +
> +bool eventfd_signal_count(void)
> +{
> +	return this_cpu_read(event_fd_recursion.count);
> +}
> +
>  /**
>   * eventfd_signal - Adds @n to the eventfd counter.
>   * @ctx: [in] Pointer to the eventfd context.
> @@ -71,18 +84,22 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
>  	 * it returns true, the eventfd_signal() call should be deferred to a
>  	 * safe context.
>  	 */
> -	if (WARN_ON_ONCE(this_cpu_read(eventfd_wake_count)))
> +	local_lock(&event_fd_recursion.lock);
> +	if (WARN_ON_ONCE(this_cpu_read(event_fd_recursion.count))) {
> +		local_unlock(&event_fd_recursion.lock);
>  		return 0;
> +	}
>
>  	spin_lock_irqsave(&ctx->wqh.lock, flags);
> -	this_cpu_inc(eventfd_wake_count);
> +	this_cpu_inc(event_fd_recursion.count);
>  	if (ULLONG_MAX - ctx->count < n)
>  		n = ULLONG_MAX - ctx->count;
>  	ctx->count += n;
>  	if (waitqueue_active(&ctx->wqh))
>  		wake_up_locked_poll(&ctx->wqh, EPOLLIN);
> -	this_cpu_dec(eventfd_wake_count);
> +	this_cpu_dec(event_fd_recursion.count);
>  	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
> +	local_unlock(&event_fd_recursion.lock);
>
>  	return n;
>  }
> diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
> index fa0a524baed0..ca89d6c409c1 100644
> --- a/include/linux/eventfd.h
> +++ b/include/linux/eventfd.h
> @@ -43,12 +43,7 @@ int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx,
> wait_queue_entry_t *w
>  				  __u64 *cnt);
>  void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
>
> -DECLARE_PER_CPU(int, eventfd_wake_count);
> -
> -static inline bool eventfd_signal_count(void)
> -{
> -	return this_cpu_read(eventfd_wake_count);
> -}
> +bool eventfd_signal_count(void);
>
>  #else /* CONFIG_EVENTFD */
>