linux-pci.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Stephen Boyd <swboyd@chromium.org>
To: Krishna chaitanya chundru <quic_krichai@quicinc.com>, helgaas@kernel.org
Cc: linux-pci@vger.kernel.org, linux-arm-msm@vger.kernel.org,
	linux-kernel@vger.kernel.org, quic_vbadigan@quicinc.com,
	quic_hemantk@quicinc.com, quic_nitegupt@quicinc.com,
	quic_skananth@quicinc.com, quic_ramkri@quicinc.com,
	manivannan.sadhasivam@linaro.org,
	"Prasad Malisetty" <quic_pmaliset@quicinc.com>,
	"Bjorn Helgaas" <bhelgaas@google.com>,
	"Saheed O. Bolarinwa" <refactormyself@gmail.com>,
	"Krzysztof Wilczyński" <kw@linux.com>,
	"Rajat Jain" <rajatja@google.com>
Subject: Re: [PATCH v4] PCI/ASPM: Update LTR threshold based upon reported max latencies
Date: Wed, 8 Jun 2022 15:22:13 -0700	[thread overview]
Message-ID: <CAE-0n527WJxDGxJ=1Y9a15+3kQvfnWSq+V0ddS3uri_i+epxQg@mail.gmail.com> (raw)
In-Reply-To: <1654242861-15695-1-git-send-email-quic_krichai@quicinc.com>

Quoting Krishna chaitanya chundru (2022-06-03 00:54:19)
> From: Prasad Malisetty <quic_pmaliset@quicinc.com>
>
> In ASPM driver, LTR threshold scale and value are updated based on
> tcommon_mode and t_poweron values. In kioxia NVMe L1.2 is failing due to
> LTR threshold scale and value are greater values than max snoop/non-snoop
> value.
>
> Based on PCIe r4.1, sec 5.5.1, L1.2 substate must be entered when
> reported snoop/no-snoop values is greather than or equal to
> LTR_L1.2_THRESHOLD value.
>
> Signed-off-by: Prasad Malisetty  <quic_pmaliset@quicinc.com>
> Signed-off-by: Krishna chaitanya chundru <quic_krichai@quicinc.com>
> ---
>
> I am taking this patch forward as prasad is no more working with our org.

Not sure why it's a reply to the previous rounds. I didn't notice this
patch for a bit. Can you stop sending as replies to the previous round?

> changes since v3:
>         - Changed the logic to include this condition "snoop/nosnoop
>           latencies are not equal to zero and lower than LTR_L1.2_THRESHOLD"
> Changes since v2:
>         - Replaced LTRME logic with max snoop/no-snoop latencies check.
> Changes since v1:
>         - Added missing variable declaration in v1 patch
> ---
>  drivers/pci/pcie/aspm.c | 32 ++++++++++++++++++++++++++++++++
>  1 file changed, 32 insertions(+)
>
> diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
> index a96b742..c8f6253 100644
> --- a/drivers/pci/pcie/aspm.c
> +++ b/drivers/pci/pcie/aspm.c
> @@ -461,14 +461,36 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link,
>  {
>         struct pci_dev *child = link->downstream, *parent = link->pdev;
>         u32 val1, val2, scale1, scale2;
> +       u32 max_val, max_scale, max_snp_scale, max_snp_val, max_nsnp_scale, max_nsnp_val;
>         u32 t_common_mode, t_power_on, l1_2_threshold, scale, value;
>         u32 ctl1 = 0, ctl2 = 0;
>         u32 pctl1, pctl2, cctl1, cctl2;
>         u32 pl1_2_enables, cl1_2_enables;
> +       u16 ltr;
> +       u16 max_snoop_lat, max_nosnoop_lat;
>
>         if (!(link->aspm_support & ASPM_STATE_L1_2_MASK))
>                 return;
>
> +       ltr = pci_find_ext_capability(child, PCI_EXT_CAP_ID_LTR);
> +       if (!ltr)
> +               return;
> +
> +       pci_read_config_word(child, ltr + PCI_LTR_MAX_SNOOP_LAT, &max_snoop_lat);
> +       pci_read_config_word(child, ltr + PCI_LTR_MAX_NOSNOOP_LAT, &max_nosnoop_lat);
> +
> +       max_snp_scale = (max_snoop_lat & PCI_LTR_SCALE_MASK) >> PCI_LTR_SCALE_SHIFT;
> +       max_snp_val = (max_snoop_lat & PCI_LTR_VALUE_MASK);

Remove useless parenthesis please.

> +
> +       max_nsnp_scale = (max_nosnoop_lat & PCI_LTR_SCALE_MASK) >> PCI_LTR_SCALE_SHIFT;
> +       max_nsnp_val = (max_nosnoop_lat & PCI_LTR_VALUE_MASK)

Remove useless parenthesis please.

> +
> +       /* choose the greater max scale value between snoop and no snoop value*/
> +       max_scale = (max_snp_scale > max_nsnp_scale) ? max_snp_scale: max_nsnp_scale;

Use max()?

> +
> +       /* choose the greater max value between snoop and no snoop scales */
> +       max_val = (max_snp_val > max_nsnp_val) ? max_snp_val: max_nsnp_val;

Use max()?

> +
>         /* Choose the greater of the two Port Common_Mode_Restore_Times */
>         val1 = (parent_l1ss_cap & PCI_L1SS_CAP_CM_RESTORE_TIME) >> 8;
>         val2 = (child_l1ss_cap & PCI_L1SS_CAP_CM_RESTORE_TIME) >> 8;
> @@ -501,6 +523,16 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link,
>          */
>         l1_2_threshold = 2 + 4 + t_common_mode + t_power_on;
>         encode_l12_threshold(l1_2_threshold, &scale, &value);
> +
> +       /*
> +        * Based on PCIe r4.1, sec 5.5.1, L1.2 substate must be entered when reported
> +        * snoop/no-snoop values are greather than or equal to LTR_L1.2_THRESHOLD value.
> +        */
> +       if (scale > max_scale)
> +               scale = max_scale;

Use min()?

> +       if (value > max_val)
> +               value = max_val;

Use min()?

> +
>         ctl1 |= t_common_mode << 8 | scale << 29 | value << 16;
>
>         /* Some broken devices only support dword access to L1 SS */

  reply	other threads:[~2022-06-08 22:22 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-03-07 18:59 [PATCH v2] [RFC PATCH] PCI: Update LTR threshold based on LTRME bit Prasad Malisetty
2022-03-17 19:07 ` Stephen Boyd
2022-04-05  6:24   ` Prasad Malisetty (Temp)
2022-04-05 18:57     ` Stephen Boyd
2022-04-05 16:08 ` Bjorn Helgaas
2022-04-12 22:46 ` Bjorn Helgaas
2022-06-01 12:23 ` [PATCH v3] PCI/ASPM: Update LTR threshold based upon reported max latencies Krishna chaitanya chundru
2022-06-01 12:27   ` Krishna Chaitanya Chundru
2022-06-02  8:29     ` Manivannan Sadhasivam
2022-06-02  9:59       ` Krishna Chaitanya Chundru
2022-06-03  7:54 ` [PATCH v4] " Krishna chaitanya chundru
2022-06-08 22:22   ` Stephen Boyd [this message]
2022-06-10  5:08   ` [PATCH v5] " Krishna chaitanya chundru
2022-06-15 13:23     ` Krishna Chaitanya Chundru
2022-07-15  8:28       ` Manivannan Sadhasivam
2022-07-15 11:28         ` Krishna Chaitanya Chundru
2022-06-15 17:39     ` Manivannan Sadhasivam

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='CAE-0n527WJxDGxJ=1Y9a15+3kQvfnWSq+V0ddS3uri_i+epxQg@mail.gmail.com' \
    --to=swboyd@chromium.org \
    --cc=bhelgaas@google.com \
    --cc=helgaas@kernel.org \
    --cc=kw@linux.com \
    --cc=linux-arm-msm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=manivannan.sadhasivam@linaro.org \
    --cc=quic_hemantk@quicinc.com \
    --cc=quic_krichai@quicinc.com \
    --cc=quic_nitegupt@quicinc.com \
    --cc=quic_pmaliset@quicinc.com \
    --cc=quic_ramkri@quicinc.com \
    --cc=quic_skananth@quicinc.com \
    --cc=quic_vbadigan@quicinc.com \
    --cc=rajatja@google.com \
    --cc=refactormyself@gmail.com \
    /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).