[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ecf4d4f8-8232-44bc-b1a0-c6bd4b579949@collabora.com>
Date: Wed, 13 Dec 2023 11:59:53 +0100
From: AngeloGioacchino Del Regno
<angelogioacchino.delregno@...labora.com>
To: Maramaina Naresh <quic_mnaresh@...cinc.com>,
"James E.J. Bottomley" <jejb@...ux.ibm.com>,
"Martin K. Petersen" <martin.petersen@...cle.com>,
Peter Wang <peter.wang@...iatek.com>,
Matthias Brugger <matthias.bgg@...il.com>,
stanley.chu@...iatek.com
Cc: Alim Akhtar <alim.akhtar@...sung.com>,
Avri Altman <avri.altman@....com>,
Bart Van Assche <bvanassche@....org>,
Stanley Jhu <chu.stanley@...il.com>,
linux-scsi@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-mediatek@...ts.infradead.org,
linux-arm-kernel@...ts.infradead.org, quic_cang@...cinc.com,
quic_nguyenb@...cinc.com
Subject: Re: [PATCH V4 1/2] ufs: core: Add CPU latency QoS support for ufs
driver
Il 13/12/23 11:36, Maramaina Naresh ha scritto:
> Register ufs driver to CPU latency PM QoS framework to improve
> ufs device random io performance.
>
> PM QoS initialization will insert new QoS request into the CPU
> latency QoS list with the maximum latency PM_QOS_DEFAULT_VALUE
> value.
>
> UFS driver will vote for performance mode on scale up and power
> save mode for scale down.
>
> If clock scaling feature is not enabled then voting will be based
> on clock on or off condition.
>
> Provided sysfs interface to enable/disable PM QoS feature.
>
> tiotest benchmark tool io performance results on sm8550 platform:
>
> 1. Without PM QoS support
> Type (Speed in) | Average of 18 iterations
> Random Write(IPOS) | 41065.13
> Random Read(IPOS) | 37101.3
>
> 2. With PM QoS support
> Type (Speed in) | Average of 18 iterations
> Random Write(IPOS) | 46784.9
> Random Read(IPOS) | 42943.4
> (Improvement with PM QoS = ~15%).
>
> Co-developed-by: Nitin Rawat <quic_nitirawa@...cinc.com>
> Signed-off-by: Nitin Rawat <quic_nitirawa@...cinc.com>
> Signed-off-by: Naveen Kumar Goud Arepalli <quic_narepall@...cinc.com>
> Signed-off-by: Maramaina Naresh <quic_mnaresh@...cinc.com>
> ---
> drivers/ufs/core/ufshcd.c | 127 ++++++++++++++++++++++++++++++++++++++
> include/ufs/ufshcd.h | 6 ++
> 2 files changed, 133 insertions(+)
>
> diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
> index ae9936fc6ffb..7318fa480706 100644
> --- a/drivers/ufs/core/ufshcd.c
> +++ b/drivers/ufs/core/ufshcd.c
> @@ -1001,6 +1001,20 @@ static bool ufshcd_is_unipro_pa_params_tuning_req(struct ufs_hba *hba)
> return ufshcd_get_local_unipro_ver(hba) < UFS_UNIPRO_VER_1_6;
> }
>
> +/**
> + * ufshcd_pm_qos_update - update PM QoS request
> + * @hba: per adapter instance
> + * @on: If True, vote for perf PM QoS mode otherwise power save mode
> + */
> +static void ufshcd_pm_qos_update(struct ufs_hba *hba, bool on)
> +{
> + if (!hba->pm_qos_enabled)
> + return;
> +
> + cpu_latency_qos_update_request(&hba->pm_qos_req, on ? 0
> + : PM_QOS_DEFAULT_VALUE);
This fits in one line.
> +}
> +
> /**
> * ufshcd_set_clk_freq - set UFS controller clock frequencies
> * @hba: per adapter instance
> @@ -1147,8 +1161,11 @@ static int ufshcd_scale_clks(struct ufs_hba *hba, unsigned long freq,
> hba->devfreq->previous_freq);
> else
> ufshcd_set_clk_freq(hba, !scale_up);
> + goto out;
> }
>
> + ufshcd_pm_qos_update(hba, scale_up);
> +
> out:
> trace_ufshcd_profile_clk_scaling(dev_name(hba->dev),
> (scale_up ? "up" : "down"),
> @@ -8615,6 +8632,109 @@ static void ufshcd_set_timestamp_attr(struct ufs_hba *hba)
> ufshcd_release(hba);
> }
>
> +/**
> + * ufshcd_pm_qos_init - initialize PM QoS request
> + * @hba: per adapter instance
> + */
> +static void ufshcd_pm_qos_init(struct ufs_hba *hba)
> +{
> +
> + if (hba->pm_qos_enabled)
> + return;
> +
> + cpu_latency_qos_add_request(&hba->pm_qos_req,
> + PM_QOS_DEFAULT_VALUE);
same here.
> +
> + if (cpu_latency_qos_request_active(&hba->pm_qos_req))
> + hba->pm_qos_enabled = true;
> +}
> +
Apart from that,
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@...labora.com>
Powered by blists - more mailing lists