public inbox for linux-cxl@vger.kernel.org
 help / color / mirror / Atom feed
From: Dave Jiang <dave.jiang@intel.com>
To: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>,
	linux-cxl@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Alison Schofield <alison.schofield@intel.com>,
	Vishal Verma <vishal.l.verma@intel.com>,
	Ira Weiny <ira.weiny@intel.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Jonathan Cameron <jonathan.cameron@huawei.com>,
	Yazen Ghannam <yazen.ghannam@amd.com>,
	Davidlohr Bueso <dave@stgolabs.net>,
	Terry Bowman <terry.bowman@amd.com>,
	Robert Richter <rrichter@amd.com>,
	Benjamin Cheatham <benjamin.cheatham@amd.com>
Subject: Re: [PATCH] cxl/hdm: Avoid DVSEC fallback after region teardown
Date: Tue, 17 Feb 2026 15:29:22 -0700	[thread overview]
Message-ID: <24dad014-2f0e-4b1f-9307-94f59b201e06@intel.com> (raw)
In-Reply-To: <20260212223800.23624-1-Smita.KoralahalliChannabasappa@amd.com>



On 2/12/26 3:38 PM, Smita Koralahalli wrote:
> After destroy-region, cxl_region_decode_reset() clears the HDM decoder
> registers (base/size/commit). If the memdev is subsequently bounced
> (disable/enable), port probe re-evaluates decoder capability via
> should_emulate_decoders().
> 
> The existing logic checks each decoder's COMMITTED bit. Since those bits
> are cleared by region teardown, should_emulate_decoders() incorrectly
> falls back to DVSEC range emulation, even though HDM capability is still
> present.
> 
> DVSEC fallback marks the endpoint decoder as AUTO, which triggers
> cxl_add_to_region() -> construct_region(). That path copies the default
> interleave_granularity (4096) into the region parameters. The resulting
> spurious autodiscovered region consumes the CFMWS HPA space and causes a
> subsequent create-region to fail in hpa_alloc().
> 
> Use the global CXL_HDM_DECODER_ENABLE bit instead of per-decoder COMMITTED
> bits to detect HDM capability. If the HDM decoder block is enabled, zeroed
> registers indicate teardown, not absence of HDM support. This prevents the
> unintended DVSEC fallback and subsequent region creation failure.
> 
> Based on cxl/fixes.
> base-commit: 8441c7d3bd6c5a52ab2ecf77e43a5bf262004f5c

This block should go under the '---'

DJ

> 
> Fixes: 52cc48ad2a76 ("cxl/hdm: Limit emulation to the number of range registers")
> Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
> ---
>  drivers/cxl/core/hdm.c | 25 +++++++++----------------
>  1 file changed, 9 insertions(+), 16 deletions(-)
> 
> diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
> index eb5a3a7640c6..a0718cbcc355 100644
> --- a/drivers/cxl/core/hdm.c
> +++ b/drivers/cxl/core/hdm.c
> @@ -94,7 +94,6 @@ static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info)
>  	struct cxl_hdm *cxlhdm;
>  	void __iomem *hdm;
>  	u32 ctrl;
> -	int i;
>  
>  	if (!info)
>  		return false;
> @@ -113,22 +112,16 @@ static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info)
>  		return false;
>  
>  	/*
> -	 * If any decoders are committed already, there should not be any
> -	 * emulated DVSEC decoders.
> +	 * If HDM decoders are globally enabled, do not fall back to DVSEC
> +	 * range emulation. Zeroed decoder registers after region teardown
> +	 * do not imply absence of HDM capability.
> +	 *
> +	 * Falling back to DVSEC here would treat the decoder as AUTO and
> +	 * may incorrectly latch default interleave settings.
>  	 */
> -	for (i = 0; i < cxlhdm->decoder_count; i++) {
> -		ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i));
> -		dev_dbg(&info->port->dev,
> -			"decoder%d.%d: committed: %ld base: %#x_%.8x size: %#x_%.8x\n",
> -			info->port->id, i,
> -			FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl),
> -			readl(hdm + CXL_HDM_DECODER0_BASE_HIGH_OFFSET(i)),
> -			readl(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(i)),
> -			readl(hdm + CXL_HDM_DECODER0_SIZE_HIGH_OFFSET(i)),
> -			readl(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(i)));
> -		if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl))
> -			return false;
> -	}
> +	ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET);
> +	if (ctrl & CXL_HDM_DECODER_ENABLE)
> +		return false;
>  
>  	return true;
>  }


  parent reply	other threads:[~2026-02-17 22:29 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-12 22:38 [PATCH] cxl/hdm: Avoid DVSEC fallback after region teardown Smita Koralahalli
2026-02-13  4:32 ` Alison Schofield
2026-02-17 21:27   ` Koralahalli Channabasappa, Smita
2026-02-17 22:29 ` Dave Jiang [this message]
2026-03-11  1:59 ` Alison Schofield
2026-03-11  3:22 ` Dan Williams
2026-03-12 17:37   ` Koralahalli Channabasappa, Smita
2026-03-12 19:42     ` Dan Williams
2026-03-12 20:55       ` Koralahalli Channabasappa, Smita

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=24dad014-2f0e-4b1f-9307-94f59b201e06@intel.com \
    --to=dave.jiang@intel.com \
    --cc=Smita.KoralahalliChannabasappa@amd.com \
    --cc=alison.schofield@intel.com \
    --cc=benjamin.cheatham@amd.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave@stgolabs.net \
    --cc=ira.weiny@intel.com \
    --cc=jonathan.cameron@huawei.com \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rrichter@amd.com \
    --cc=terry.bowman@amd.com \
    --cc=vishal.l.verma@intel.com \
    --cc=yazen.ghannam@amd.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