linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Dan Williams <dan.j.williams@intel.com>
To: Robert Richter <rrichter@amd.com>,
	Alison Schofield <alison.schofield@intel.com>,
	Vishal Verma <vishal.l.verma@intel.com>,
	"Ira Weiny" <ira.weiny@intel.com>,
	Ben Widawsky <bwidawsk@kernel.org>,
	Dan Williams <dan.j.williams@intel.com>
Cc: <linux-cxl@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	Bjorn Helgaas <bhelgaas@google.com>,
	"Rafael J. Wysocki" <rafael@kernel.org>,
	Len Brown <lenb@kernel.org>, Robert Richter <rrichter@amd.com>
Subject: RE: [PATCH 05/15] cxl/acpi: Add probe function to detect restricted CXL hosts in RCD mode
Date: Wed, 7 Sep 2022 23:00:22 -0700	[thread overview]
Message-ID: <631984f6d7c92_58016294e6@dwillia2-xfh.jf.intel.com.notmuch> (raw)
In-Reply-To: <20220831081603.3415-6-rrichter@amd.com>

Robert Richter wrote:
> Restricted CXL device (RCD) mode (formerly CXL 1.1) uses a different
> enumeration scheme other than CXL VH (formerly CXL 2.0). In RCD mode a
> host/device (RCH-RCD) pair shows up as a legal PCIe hierarchy with an
> ACPI host bridge ("PNP0A08" or "ACPI0016" HID) and RCiEP connected to
> it with a description of the CXL device.
> 
> Add function cxl_restricted_host_probe() to probe RCD enumerated
> devices. The function implements a loop that detects all CXL capable
> ACPI PCI root bridges in the system (RCD mode only). The iterator
> function cxl_find_next_rch() is introduced to walk through all of the
> CXL hosts. The loop will then enable all CXL devices connected to the
> host. For now, only implement an empty loop with an iterator that
> returns all pci host bridges in the system.
> 
> The probe function is triggered by adding an own root device for RCHs.
> This is different to CXL VH where an ACPI "ACPI0017" root device
> exists. Its detection starts the CXL host detection. In RCD mode such
> a device does not necessarily exists, so solve this by creating a
> plain platform device that is not an ACPI device and is root only for
> RCHs.

As I mentioned in the cover letter a BIOS that does not provide an
ACPI0017 device is opting out of the possibility OS first error handling
and other OS CXL services. ACPI0017 is mandatory.

Otherwise, its odd to have a module create the device that its driver is
going to drive. That's a backwards driver model and why we proposed
ACPI0017 in the first instance.

> 
> Signed-off-by: Robert Richter <rrichter@amd.com>
> ---
>  drivers/cxl/acpi.c | 71 +++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 70 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
> index 31e104f0210f..a19e3154dd44 100644
> --- a/drivers/cxl/acpi.c
> +++ b/drivers/cxl/acpi.c
> @@ -312,6 +312,33 @@ static int add_root_nvdimm_bridge(struct device *match, void *data)
>  	return 1;
>  }
>  
> +struct pci_host_bridge *cxl_find_next_rch(struct pci_host_bridge *host)
> +{
> +	struct pci_bus *bus = host ? host->bus : NULL;
> +
> +	while ((bus = pci_find_next_bus(bus)) != NULL) {
> +		host = bus ? to_pci_host_bridge(bus->bridge) : NULL;
> +		if (!host)
> +			continue;
> +
> +		dev_dbg(&host->dev, "PCI bridge found\n");
> +
> +		return host;
> +	}
> +
> +	return NULL;
> +}
> +
> +static int __init cxl_restricted_host_probe(struct platform_device *pdev)
> +{
> +	struct pci_host_bridge *host = NULL;
> +
> +	while ((host = cxl_find_next_rch(host)) != NULL) {
> +	}
> +
> +	return 0;
> +}
> +
>  static struct lock_class_key cxl_root_key;
>  
>  static void cxl_acpi_lock_reset_class(void *dev)
> @@ -445,6 +472,13 @@ static int cxl_acpi_probe(struct platform_device *pdev)
>  	struct acpi_device *adev = ACPI_COMPANION(host);
>  	struct cxl_cfmws_context ctx;
>  
> +	/*
> +	 * For RCH (CXL 1.1 hosts) the probe is triggered by a plain
> +	 * platform dev which does not have an acpi companion.
> +	 */
> +	if (!adev)
> +		return cxl_restricted_host_probe(pdev);
> +
>  	device_lock_set_class(&pdev->dev, &cxl_root_key);
>  	rc = devm_add_action_or_reset(&pdev->dev, cxl_acpi_lock_reset_class,
>  				      &pdev->dev);
> @@ -518,6 +552,7 @@ MODULE_DEVICE_TABLE(acpi, cxl_acpi_ids);
>  
>  static const struct platform_device_id cxl_test_ids[] = {
>  	{ "cxl_acpi" },
> +	{ "cxl_root" },
>  	{ },
>  };
>  MODULE_DEVICE_TABLE(platform, cxl_test_ids);
> @@ -531,7 +566,41 @@ static struct platform_driver cxl_acpi_driver = {
>  	.id_table = cxl_test_ids,
>  };
>  
> -module_platform_driver(cxl_acpi_driver);
> +static void cxl_acpi_device_release(struct device *dev) { }
> +
> +static struct platform_device cxl_acpi_device = {
> +	.name = "cxl_root",
> +	.id = PLATFORM_DEVID_NONE,
> +	.dev = {
> +		.release = cxl_acpi_device_release,
> +	}
> +};
> +
> +static int __init cxl_host_init(void)
> +{
> +	int rc;
> +
> +	/* Kick off restricted host (CXL 1.1) detection */
> +	rc = platform_device_register(&cxl_acpi_device);
> +	if (rc) {
> +		platform_device_put(&cxl_acpi_device);
> +		return rc;
> +	}
> +	rc = platform_driver_register(&cxl_acpi_driver);
> +	if (rc)
> +		platform_device_unregister(&cxl_acpi_device);
> +	return rc;
> +}
> +
> +static void __exit cxl_host_exit(void)
> +{
> +	platform_driver_unregister(&cxl_acpi_driver);
> +	platform_device_unregister(&cxl_acpi_device);
> +}
> +
> +module_init(cxl_host_init);
> +module_exit(cxl_host_exit);
> +
>  MODULE_LICENSE("GPL v2");
>  MODULE_IMPORT_NS(CXL);
>  MODULE_IMPORT_NS(ACPI);
> -- 
> 2.30.2
> 




  parent reply	other threads:[~2022-09-08  6:00 UTC|newest]

Thread overview: 102+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-31  8:15 [PATCH 00/15] cxl: Add support for Restricted CXL hosts (RCD mode) Robert Richter
2022-08-31  8:15 ` [PATCH 01/15] cxl/core: Remove duplicate declaration of devm_cxl_iomap_block() Robert Richter
2022-08-31  8:54   ` Jonathan Cameron
2022-09-01  5:21     ` Robert Richter
2022-08-31  9:39   ` kernel test robot
2022-09-07 16:11   ` [PATCH 1/15] " Davidlohr Bueso
2022-09-09 10:38     ` Robert Richter
2022-09-08  5:44   ` [PATCH 01/15] " Dan Williams
2022-09-08 14:51     ` Robert Richter
2022-09-08 19:47       ` Dan Williams
2022-08-31  8:15 ` [PATCH 02/15] cxl/core: Check physical address before mapping it in devm_cxl_iomap_block() Robert Richter
2022-08-31  8:56   ` Jonathan Cameron
2022-09-01  5:31     ` Robert Richter
2022-09-08  5:48   ` Dan Williams
2022-09-09 12:19     ` Robert Richter
2022-09-16 18:04       ` Dan Williams
2022-09-28 10:28         ` Robert Richter
2022-09-30 19:07           ` Dan Williams
2022-08-31  8:15 ` [PATCH 03/15] cxl: Unify debug messages when calling devm_cxl_add_port() Robert Richter
2022-08-31  9:59   ` Jonathan Cameron
2022-09-01  5:36     ` Robert Richter
2022-09-06  7:30     ` Robert Richter
2022-09-06  8:52       ` Jonathan Cameron
2022-09-07 16:21   ` [PATCH 3/15] " Davidlohr Bueso
2022-09-08  5:53   ` [PATCH 03/15] " Dan Williams
2022-09-28 10:32     ` Robert Richter
2022-08-31  8:15 ` [PATCH 04/15] cxl: Unify debug messages when calling devm_cxl_add_dport() Robert Richter
2022-09-07 16:29   ` [PATCH 4/15] " Davidlohr Bueso
2022-09-08  5:55   ` [PATCH 04/15] " Dan Williams
2022-08-31  8:15 ` [PATCH 05/15] cxl/acpi: Add probe function to detect restricted CXL hosts in RCD mode Robert Richter
2022-08-31 10:08   ` Jonathan Cameron
2022-09-01  6:01     ` Robert Richter
2022-09-01 10:10       ` Jonathan Cameron
2022-09-06  7:19         ` Robert Richter
2022-09-06  8:53           ` Jonathan Cameron
2022-09-07 18:22   ` Bjorn Helgaas
2022-09-08  6:00   ` Dan Williams [this message]
2022-09-08  6:11   ` Dan Williams
2022-08-31  8:15 ` [PATCH 06/15] PCI/ACPI: Link host bridge to its ACPI fw node Robert Richter
2022-08-31 10:11   ` Jonathan Cameron
2022-09-07 18:37   ` Bjorn Helgaas
2022-09-07 20:15     ` Rafael J. Wysocki
2022-09-08  6:05   ` Dan Williams
2022-09-08 13:06     ` Rafael J. Wysocki
2022-09-08 19:45       ` Dan Williams
2022-09-09 10:20         ` Robert Richter
2022-09-14 22:11           ` Bjorn Helgaas
2022-09-16 23:16             ` Dan Williams
2022-09-08 13:04   ` Rafael J. Wysocki
2022-08-31  8:15 ` [PATCH 07/15] cxl/acpi: Check RCH's PCIe Host Bridge ACPI ID Robert Richter
2022-08-31 10:20   ` Jonathan Cameron
2022-09-01  6:16     ` Robert Richter
2022-09-01 10:14       ` Jonathan Cameron
2022-09-08  6:11   ` Dan Williams
2022-08-31  8:15 ` [PATCH 08/15] cxl/acpi: Check RCH's CXL DVSEC capabilities Robert Richter
2022-08-31 10:52   ` Jonathan Cameron
2022-08-31 11:12     ` Jonathan Cameron
2022-09-01  6:38       ` Robert Richter
2022-09-01 10:37         ` Jonathan Cameron
2022-09-06 10:20           ` Robert Richter
2022-09-01  6:30     ` Robert Richter
2022-09-01 10:23       ` Jonathan Cameron
2022-09-08  6:18   ` Dan Williams
2022-08-31  8:15 ` [PATCH 09/15] cxl/acpi: Determine PCI host bridge's ACPI UID Robert Richter
2022-08-31 11:00   ` Jonathan Cameron
2022-09-01  6:53     ` Robert Richter
2022-09-01 10:41       ` Jonathan Cameron
2022-09-08  6:18   ` Dan Williams
2022-09-08 20:47   ` Jonathan Zhang (Infra)
2022-09-08 21:10     ` Dan Williams
2022-09-08 21:35       ` Jonathan Zhang (Infra)
2022-09-08 22:31         ` Dan Williams
2022-09-08 22:41           ` Jonathan Zhang (Infra)
2022-08-31  8:15 ` [PATCH 10/15] cxl/acpi: Extract the RCH's RCRB base address from CEDT Robert Richter
2022-08-31 11:09   ` Jonathan Cameron
2022-09-01  7:04     ` Robert Richter
2022-08-31  8:15 ` [PATCH 11/15] cxl/acpi: Extract the host's component register base address from RCRB Robert Richter
2022-08-31 11:56   ` Jonathan Cameron
2022-09-01  7:38     ` Robert Richter
2022-09-01 11:00       ` Jonathan Cameron
2022-09-06 11:32         ` Robert Richter
2022-09-08 20:59   ` Jonathan Zhang (Infra)
2022-08-31  8:16 ` [PATCH 12/15] cxl/acpi: Skip devm_cxl_port_enumerate_dports() when in RCD mode Robert Richter
2022-08-31 11:58   ` Jonathan Cameron
2022-09-01  7:40     ` Robert Richter
2022-08-31  8:16 ` [PATCH 13/15] cxl/acpi: Rework devm_cxl_enumerate_ports() to support " Robert Richter
2022-08-31 12:11   ` Jonathan Cameron
2022-09-01  7:50     ` Robert Richter
2022-08-31  8:16 ` [PATCH 14/15] cxl/acpi: Enumerate ports in RCD mode to enable RCHs and RCDs Robert Richter
2022-08-31 12:16   ` Jonathan Cameron
2022-09-01  7:54     ` Robert Richter
2022-08-31  8:16 ` [PATCH 15/15] cxl/acpi: Specify module load order dependency for the cxl_acpi module Robert Richter
2022-09-16 18:12   ` Dan Williams
2022-08-31 12:23 ` [PATCH 00/15] cxl: Add support for Restricted CXL hosts (RCD mode) Jonathan Cameron
2022-09-01  8:19   ` Robert Richter
2022-09-08  6:41     ` Dan Williams
2022-09-08  5:43 ` Dan Williams
2022-09-08 18:52   ` Jonathan Zhang (Infra)
2022-09-08 19:51     ` Dan Williams
2022-09-08 20:36       ` Jonathan Zhang (Infra)
2022-09-08 21:02         ` Dan Williams
2022-09-16 18:16 ` Dan Williams

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=631984f6d7c92_58016294e6@dwillia2-xfh.jf.intel.com.notmuch \
    --to=dan.j.williams@intel.com \
    --cc=alison.schofield@intel.com \
    --cc=bhelgaas@google.com \
    --cc=bwidawsk@kernel.org \
    --cc=ira.weiny@intel.com \
    --cc=lenb@kernel.org \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rafael@kernel.org \
    --cc=rrichter@amd.com \
    --cc=vishal.l.verma@intel.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).