From: "Rafael J. Wysocki" <rafael@kernel.org>
To: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
Daniel Lezcano <daniel.lezcano@linaro.org>,
Linux PM <linux-pm@vger.kernel.org>,
"the arch/x86 maintainers" <x86@kernel.org>,
"open list:DOCUMENTATION" <linux-doc@vger.kernel.org>,
Len Brown <len.brown@intel.com>,
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
Aubrey Li <aubrey.li@linux.intel.com>,
Amit Kucheria <amitk@kernel.org>, Andi Kleen <ak@linux.intel.com>,
Tim Chen <tim.c.chen@linux.intel.com>,
"Ravi V. Shankar" <ravi.v.shankar@intel.com>,
Ricardo Neri <ricardo.neri@intel.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 7/7] thermal: intel: hfi: Notify user space for HFI events
Date: Wed, 24 Nov 2021 16:18:46 +0100 [thread overview]
Message-ID: <CAJZ5v0j=+QSwmwVg8chcTchPAXdbt2h1g=4+tMbLpDxstfRq6A@mail.gmail.com> (raw)
In-Reply-To: <20211106013312.26698-8-ricardo.neri-calderon@linux.intel.com>
On Sat, Nov 6, 2021 at 2:34 AM Ricardo Neri
<ricardo.neri-calderon@linux.intel.com> wrote:
>
> From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
>
> When the hardware issues an HFI event, relay a notification to user space.
> This allows user space to respond by reading performance and efficiency of
> each CPU and take appropriate action.
>
> For example, when performance and efficiency of a CPU is 0, user space can
> either offline the CPU or inject idle. Also, if user space notices a
> downward trend in performance, it may proactively adjust power limits to
> avoid future situations in which performance drops to 0.
>
> To avoid excessive notifications, the rate is limited by one HZ per event.
> To limit netlink message size, parameters for only 16 CPUs at max are sent
> in one message. If there are more than 16 CPUs, issue as many messages as
> needed to notify the status of all CPUs.
>
> Cc: Andi Kleen <ak@linux.intel.com>
> Cc: Aubrey Li <aubrey.li@linux.intel.com>
> Cc: Tim Chen <tim.c.chen@linux.intel.com>
> Cc: "Ravi V. Shankar" <ravi.v.shankar@intel.com>
> Reviewed-by: Len Brown <len.brown@intel.com>
> Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> ---
> drivers/thermal/intel/Kconfig | 1 +
> drivers/thermal/intel/intel_hfi.c | 55 ++++++++++++++++++++++++++++++-
> 2 files changed, 55 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/thermal/intel/Kconfig b/drivers/thermal/intel/Kconfig
> index d4c6bdcacddb..b6a1f777b8e7 100644
> --- a/drivers/thermal/intel/Kconfig
> +++ b/drivers/thermal/intel/Kconfig
> @@ -104,6 +104,7 @@ config INTEL_HFI
> bool "Intel Hardware Feedback Interface"
> depends on CPU_SUP_INTEL
> depends on SCHED_MC && X86_THERMAL_VECTOR
> + select THERMAL_NETLINK
> help
> Select this option to enable the Hardware Feedback Interface. If
> selected, hardware provides guidance to the operating system on
> diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c
> index 1df24b39f2e6..c669a037704e 100644
> --- a/drivers/thermal/intel/intel_hfi.c
> +++ b/drivers/thermal/intel/intel_hfi.c
> @@ -24,6 +24,7 @@
> #include <linux/io.h>
> #include <linux/slab.h>
>
> +#include "../thermal_core.h"
> #include "intel_hfi.h"
>
> #define THERM_STATUS_CLEAR_PKG_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | \
> @@ -124,6 +125,58 @@ static struct hfi_features hfi_features;
> static DEFINE_MUTEX(hfi_lock);
>
> #define HFI_UPDATE_INTERVAL HZ
> +#define HFI_MAX_THERM_NOTIFY_COUNT 16
> +
> +static int get_one_hfi_cap(struct hfi_instance *hfi_instance, int cpu,
> + struct hfi_cpu_data *hfi_caps)
> +{
> + struct hfi_cpu_data *caps;
> + unsigned long flags;
> + s16 index;
> +
> + index = per_cpu(hfi_cpu_info, cpu).index;
> + if (index < 0)
> + return -EINVAL;
When does this happen?
Can the index become negative after this check?
Could this check be done in the caller (so this function could be a void one)?
> +
> + /* Find the capabilities of @cpu */
> + raw_spin_lock_irqsave(&hfi_instance->event_lock, flags);
> + caps = hfi_instance->data + index * hfi_features.cpu_stride;
> + memcpy(hfi_caps, caps, sizeof(*hfi_caps));
> + raw_spin_unlock_irqrestore(&hfi_instance->event_lock, flags);
> +
> + return 0;
> +}
> +
> +/*
> + * Call update_capabilities() when there are changes in the HFI table.
> + */
> +static void update_capabilities(struct hfi_instance *hfi_instance)
> +{
> + struct cpu_capability cpu_caps[HFI_MAX_THERM_NOTIFY_COUNT];
> + int i = 0, cpu;
> +
> + for_each_cpu(cpu, hfi_instance->cpus) {
> + struct hfi_cpu_data caps;
> + int ret;
> +
> + ret = get_one_hfi_cap(hfi_instance, cpu, &caps);
> + if (ret)
> + continue;
> +
> + cpu_caps[i].cpu = cpu;
> + cpu_caps[i].perf = caps.perf_cap;
> + cpu_caps[i].eff = caps.ee_cap;
> + ++i;
> + if (i >= HFI_MAX_THERM_NOTIFY_COUNT) {
> + thermal_genl_cpu_capability_event(HFI_MAX_THERM_NOTIFY_COUNT,
> + cpu_caps);
> + i = 0;
> + }
> + }
> +
> + if (i)
> + thermal_genl_cpu_capability_event(i, cpu_caps);
> +}
>
> static void hfi_update_work_fn(struct work_struct *work)
> {
> @@ -134,7 +187,7 @@ static void hfi_update_work_fn(struct work_struct *work)
> if (!hfi_instance)
> return;
>
> - /* TODO: Consume update here. */
> + update_capabilities(hfi_instance);
> }
>
> void intel_hfi_process_event(__u64 pkg_therm_status_msr_val)
> --
> 2.17.1
>
next prev parent reply other threads:[~2021-11-24 15:19 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-06 1:33 [PATCH 0/7] Thermal: Introduce the Hardware Feedback Interface for thermal and performance management Ricardo Neri
2021-11-06 1:33 ` [PATCH 1/7] x86/Documentation: Describe the Intel Hardware Feedback Interface Ricardo Neri
2021-11-30 9:24 ` Daniel Lezcano
2021-11-30 10:20 ` Srinivas Pandruvada
2021-11-06 1:33 ` [PATCH 2/7] x86: Add definitions for " Ricardo Neri
2021-11-06 10:30 ` Borislav Petkov
2021-11-06 22:01 ` Ricardo Neri
2021-11-06 1:33 ` [PATCH 3/7] thermal: intel: hfi: Minimally initialize the " Ricardo Neri
2021-11-08 8:47 ` Peter Zijlstra
2021-11-09 2:28 ` Ricardo Neri
2021-11-24 14:09 ` Rafael J. Wysocki
2021-11-30 3:20 ` Ricardo Neri
2021-11-30 3:55 ` Srinivas Pandruvada
2021-11-30 13:45 ` Ricardo Neri
2021-11-06 1:33 ` [PATCH 4/7] thermal: intel: hfi: Handle CPU hotplug events Ricardo Neri
2021-11-24 14:48 ` Rafael J. Wysocki
2021-11-30 13:21 ` Ricardo Neri
2021-11-30 13:32 ` Rafael J. Wysocki
2021-12-02 23:43 ` Ricardo Neri
2021-11-06 1:33 ` [PATCH 5/7] thermal: intel: hfi: Enable notification interrupt Ricardo Neri
2021-11-08 9:01 ` Peter Zijlstra
2021-11-09 15:00 ` Ricardo Neri
2021-11-08 9:07 ` Peter Zijlstra
2021-11-09 2:26 ` Ricardo Neri
2021-11-09 8:48 ` Peter Zijlstra
2021-11-09 12:54 ` Srinivas Pandruvada
2021-11-06 1:33 ` [PATCH 6/7] thermal: netlink: Add a new event to notify CPU capabilities change Ricardo Neri
2021-11-09 12:39 ` Lukasz Luba
2021-11-09 13:23 ` Srinivas Pandruvada
2021-11-09 13:53 ` Lukasz Luba
2021-11-09 14:15 ` Srinivas Pandruvada
2021-11-09 17:51 ` Lukasz Luba
2021-11-09 21:25 ` Srinivas Pandruvada
2021-11-30 9:29 ` Daniel Lezcano
2021-12-09 16:03 ` Ricardo Neri
2021-12-09 16:57 ` Daniel Lezcano
2021-12-09 17:39 ` Srinivas Pandruvada
2021-11-06 1:33 ` [PATCH 7/7] thermal: intel: hfi: Notify user space for HFI events Ricardo Neri
2021-11-24 15:18 ` Rafael J. Wysocki [this message]
2021-11-26 6:23 ` Srinivas Pandruvada
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAJZ5v0j=+QSwmwVg8chcTchPAXdbt2h1g=4+tMbLpDxstfRq6A@mail.gmail.com' \
--to=rafael@kernel.org \
--cc=ak@linux.intel.com \
--cc=amitk@kernel.org \
--cc=aubrey.li@linux.intel.com \
--cc=daniel.lezcano@linaro.org \
--cc=len.brown@intel.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=rafael.j.wysocki@intel.com \
--cc=ravi.v.shankar@intel.com \
--cc=ricardo.neri-calderon@linux.intel.com \
--cc=ricardo.neri@intel.com \
--cc=srinivas.pandruvada@linux.intel.com \
--cc=tim.c.chen@linux.intel.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).