linux-kernel - Re: [PATCH v3 6/8] remoteproc: Introduce "panic" callback in ops

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <d40e2d7a-19ae-0acf-dc73-f2edb8cb3c32@st.com>
Date:   Thu, 13 Feb 2020 17:00:36 +0100
From:   Arnaud POULIQUEN <arnaud.pouliquen@...com>
To:     Bjorn Andersson <bjorn.andersson@...aro.org>,
        Ohad Ben-Cohen <ohad@...ery.com>
CC:     Andy Gross <agross@...nel.org>, Rob Herring <robh+dt@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        <linux-arm-msm@...r.kernel.org>,
        <linux-remoteproc@...r.kernel.org>, <devicetree@...r.kernel.org>,
        <linux-kernel@...r.kernel.org>, Sibi Sankar <sibis@...eaurora.org>,
        Rishabh Bhatnagar <rishabhb@...eaurora.org>
Subject: Re: [PATCH v3 6/8] remoteproc: Introduce "panic" callback in ops


On 2/11/20 1:50 AM, Bjorn Andersson wrote:
> Introduce a "panic" function in the remoteproc ops table, to allow
> remoteproc instances to perform operations needed in order to aid in
> post mortem system debugging, such as flushing caches etc, when the
> kernel panics. The function can return a number of milliseconds needed
> by the remote to "settle" and the core will wait the longest returned
> duration before returning from the panic handler.
> 
> Signed-off-by: Bjorn Andersson <bjorn.andersson@...aro.org>
> ---
> 
> Changes since v2:
> - Replace per-rproc notifier callback with one generic
> - Move the mdelay() from the individual drivers to the core and sleep the
>   longest returned duration. Drivers that doesn't need a delay can return 0.
> - Unregister the notifier on exit
> 
>  drivers/remoteproc/remoteproc_core.c | 46 ++++++++++++++++++++++++++++
>  include/linux/remoteproc.h           |  3 ++
>  2 files changed, 49 insertions(+)
> 
> diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
> index 097f33e4f1f3..8b6932027d36 100644
> --- a/drivers/remoteproc/remoteproc_core.c
> +++ b/drivers/remoteproc/remoteproc_core.c
> @@ -16,6 +16,7 @@
>  
>  #define pr_fmt(fmt)    "%s: " fmt, __func__
>  
> +#include <linux/delay.h>
>  #include <linux/kernel.h>
>  #include <linux/module.h>
>  #include <linux/device.h>
> @@ -43,6 +44,7 @@
>  
>  static DEFINE_MUTEX(rproc_list_mutex);
>  static LIST_HEAD(rproc_list);
> +static struct notifier_block rproc_panic_nb;
>  
>  typedef int (*rproc_handle_resource_t)(struct rproc *rproc,
>  				 void *, int offset, int avail);
> @@ -2216,10 +2218,53 @@ void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type)
>  }
>  EXPORT_SYMBOL(rproc_report_crash);
>  
> +static int rproc_panic_handler(struct notifier_block *nb, unsigned long event,
> +			       void *ptr)
> +{
> +	unsigned int longest = 0;
> +	struct rproc *rproc;
> +	unsigned int d;
> +	int locked;
> +
> +	locked = mutex_trylock(&rproc_list_mutex);
> +	if (!locked) {
> +		pr_err("Failed to acquire rproc list lock, won't call panic functions\n");
> +		return NOTIFY_DONE;
> +	}
As consequence the panic is not handled for all rproc instance if the mutex is locked.
it seems to me that the first solution with the delay side effect is more safety...

> +
> +	list_for_each_entry(rproc, &rproc_list, node) {
> +		if (!rproc->ops->panic || rproc->state != RPROC_RUNNING)
> +			continue;
> +
> +		d = rproc->ops->panic(rproc);
> +		if (d > longest)
> +			longest = d;
> +	}
> +
> +	mutex_unlock(&rproc_list_mutex);
> +
> +	/* Delay panic for the longest requested duration */
> +	mdelay(longest);
> +
> +	return NOTIFY_DONE;
> +}
> +
> +static void __init rproc_init_panic(void)
> +{
> +	rproc_panic_nb.notifier_call = rproc_panic_handler;
> +	atomic_notifier_chain_register(&panic_notifier_list, &rproc_panic_nb);
> +}
> +
> +static void __exit rproc_exit_panic(void)
> +{
> +	atomic_notifier_chain_unregister(&panic_notifier_list, &rproc_panic_nb);
> +}
> +
>  static int __init remoteproc_init(void)
>  {
>  	rproc_init_sysfs();
>  	rproc_init_debugfs();
> +	rproc_init_panic();
>  
>  	return 0;
>  }
> @@ -2229,6 +2274,7 @@ static void __exit remoteproc_exit(void)
>  {
>  	ida_destroy(&rproc_dev_index);
>  
> +	rproc_exit_panic();
>  	rproc_exit_debugfs();
>  	rproc_exit_sysfs();
>  }
> diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
> index 16ad66683ad0..14f05f26cbcd 100644
> --- a/include/linux/remoteproc.h
> +++ b/include/linux/remoteproc.h
> @@ -369,6 +369,8 @@ enum rsc_handling_status {
>   *			expects to find it
>   * @sanity_check:	sanity check the fw image
>   * @get_boot_addr:	get boot address to entry point specified in firmware
> + * @panic:	optional callback to react to system panic, core will delay
> + *		panic at least the returned number of milliseconds
>   */
>  struct rproc_ops {
>  	int (*start)(struct rproc *rproc);
> @@ -383,6 +385,7 @@ struct rproc_ops {
>  	int (*load)(struct rproc *rproc, const struct firmware *fw);
>  	int (*sanity_check)(struct rproc *rproc, const struct firmware *fw);
>  	u32 (*get_boot_addr)(struct rproc *rproc, const struct firmware *fw);
> +	unsigned int (*panic)(struct rproc *rproc);
>  };
>  
>  /**
>