linux-kernel - Re: [PATCH 5/7] thermal: intel: hfi: Enable notification interrupt

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: <YYjo3Jx6JosHhoHM@hirez.programming.kicks-ass.net>
Date:   Mon, 8 Nov 2021 10:07:40 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Ricardo Neri <ricardo.neri-calderon@...ux.intel.com>
Cc:     "Rafael J. Wysocki" <rafael.j.wysocki@...el.com>,
        Daniel Lezcano <daniel.lezcano@...aro.org>,
        linux-pm@...r.kernel.org, x86@...nel.org,
        linux-doc@...r.kernel.org, Len Brown <len.brown@...el.com>,
        Srinivas Pandruvada <srinivas.pandruvada@...ux.intel.com>,
        Aubrey Li <aubrey.li@...ux.intel.com>,
        Amit Kucheria <amitk@...nel.org>,
        Andi Kleen <ak@...ux.intel.com>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        "Ravi V. Shankar" <ravi.v.shankar@...el.com>,
        Ricardo Neri <ricardo.neri@...el.com>,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH 5/7] thermal: intel: hfi: Enable notification interrupt

On Fri, Nov 05, 2021 at 06:33:10PM -0700, Ricardo Neri wrote:

> @@ -72,6 +78,9 @@ struct hfi_instance {
>  	u16			die_id;
>  	struct cpumask		*cpus;
>  	void			*hw_table;
> +	struct delayed_work	update_work;
> +	raw_spinlock_t		event_lock;
  +	raw_spinlock_t		interrupt_lock;
> +	u64			timestamp;
>  	bool			initialized;
>  };
>  
> @@ -114,6 +123,75 @@ static struct hfi_instance *hfi_instances;
>  static struct hfi_features hfi_features;
>  static DEFINE_MUTEX(hfi_lock);
>  
> +#define HFI_UPDATE_INTERVAL	HZ
> +
> +static void hfi_update_work_fn(struct work_struct *work)
> +{
> +	struct hfi_instance *hfi_instance;
> +
> +	hfi_instance = container_of(to_delayed_work(work), struct hfi_instance,
> +				    update_work);
> +	if (!hfi_instance)
> +		return;
> +
> +	/* TODO: Consume update here. */

	// this here uses ->event_lock to serialize against the
	// interrupt below changing the data...

> +}
> +
> +void intel_hfi_process_event(__u64 pkg_therm_status_msr_val)
> +{
> +	struct hfi_instance *hfi_instance;
> +	int cpu = smp_processor_id();
> +	struct hfi_cpu_info *info;
> +	unsigned long flags;
> +	u64 timestamp;
> +
> +	if (!pkg_therm_status_msr_val)
> +		return;
> +
> +	info = &per_cpu(hfi_cpu_info, cpu);
> +	if (!info)
> +		return;
> +
> +	/*
> +	 * It is possible that we get an HFI thermal interrupt on this CPU
> +	 * before its HFI instance is initialized. This is not a problem. The
> +	 * CPU that enabled the interrupt for this package will also get the
> +	 * interrupt and is fully initialized.
> +	 */
> +	hfi_instance = info->hfi_instance;
> +	if (!hfi_instance)
> +		return;
> +

	/*
	 * If someone is already handling the interrupt, we shouldn't be
	 * burning time waiting for them to then do more nothing.
	 */
	if (!raw_spin_trylock(&hfi_instance->interrupt_lock))
		return;


> +	raw_spin_lock_irqsave(&hfi_instance->event_lock, flags);
> +
> +	/*
> +	 * On most systems, all CPUs in the package receive a package-level
> +	 * thermal interrupt when there is an HFI update. Since they all are
> +	 * dealing with the same update (as indicated by the update timestamp),
> +	 * it is sufficient to let a single CPU to acknowledge the update and
> +	 * schedule work to process it.
> +	 */
> +	timestamp = *(u64 *)hfi_instance->hw_table;
> +	if (hfi_instance->timestamp >= timestamp)
> +		goto unlock_spinlock;

This can go the way of the dodo.

> +
> +	hfi_instance->timestamp = timestamp;
> +
> +	memcpy(hfi_instance->table_base, hfi_instance->hw_table,
> +	       hfi_features.nr_table_pages << PAGE_SHIFT);
> +	/*
> +	 * Let hardware and other CPUs know that we are done reading the HFI
> +	 * table and it is free to update it again.
> +	 */
> +	pkg_therm_status_msr_val &= THERM_STATUS_CLEAR_PKG_MASK &
> +				    ~PACKAGE_THERM_STATUS_HFI_UPDATED;
> +	wrmsrl(MSR_IA32_PACKAGE_THERM_STATUS, pkg_therm_status_msr_val);
> +	schedule_delayed_work(&hfi_instance->update_work, HFI_UPDATE_INTERVAL);
> +
> +unlock_spinlock:
> +	raw_spin_unlock_irqrestore(&hfi_instance->event_lock, flags);

	raw_spin_unlock(&hfi_instance->interrupt_lock);

> +}