Re: [dpdk-dev] [PATCH v2 3/3] eal/linux: handle uio read failure in interrupt handler

[Thomas Monjalon <thomas@monjalon.net>]

Looking for someone to review this patch please


19/09/2018 14:57, Luca Boccassi:
> If a device is unplugged while an interrupt is pending, the
> read call to the uio device to remove it from the poll wait list
> can fail resulting in it being continually polled forever. This
> change checks for the read failing and if so, unregisters the device
> as an interrupt source and causes the wait list to be rebuilt.
> 
> This race has been reported and observed in production.
> 
> Fixes: 0a45657a6794 ("pci: rework interrupt handling")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Brian Russell <brussell@brocade.com>
> Signed-off-by: Luca Boccassi <bluca@debian.org>
> ---
>  lib/librte_eal/linuxapp/eal/eal_interrupts.c | 19 ++++++++++++++++++-
>  1 file changed, 18 insertions(+), 1 deletion(-)
> 
> diff --git a/lib/librte_eal/linuxapp/eal/eal_interrupts.c b/lib/librte_eal/linuxapp/eal/eal_interrupts.c
> index 4076c6d6ca..34584db883 100644
> --- a/lib/librte_eal/linuxapp/eal/eal_interrupts.c
> +++ b/lib/librte_eal/linuxapp/eal/eal_interrupts.c
> @@ -627,7 +627,7 @@ eal_intr_process_interrupts(struct epoll_event *events, int nfds)
>  	bool call = false;
>  	int n, bytes_read;
>  	struct rte_intr_source *src;
> -	struct rte_intr_callback *cb;
> +	struct rte_intr_callback *cb, *next;
>  	union rte_intr_read_buffer buf;
>  	struct rte_intr_callback active_cb;
>  
> @@ -701,6 +701,23 @@ eal_intr_process_interrupts(struct epoll_event *events, int nfds)
>  					"descriptor %d: %s\n",
>  					events[n].data.fd,
>  					strerror(errno));
> +				/*
> +				 * The device is unplugged or buggy, remove
> +				 * it as an interrupt source and return to
> +				 * force the wait list to be rebuilt.
> +				 */
> +				rte_spinlock_lock(&intr_lock);
> +				TAILQ_REMOVE(&intr_sources, src, next);
> +				rte_spinlock_unlock(&intr_lock);
> +
> +				for (cb = TAILQ_FIRST(&src->callbacks); cb;
> +							cb = next) {
> +					next = TAILQ_NEXT(cb, next);
> +					TAILQ_REMOVE(&src->callbacks, cb, next);
> +					free(cb);
> +				}
> +				free(src);
> +				return -1;
>  			} else if (bytes_read == 0)
>  				RTE_LOG(ERR, EAL, "Read nothing from file "
>  					"descriptor %d\n", events[n].data.fd);
>