Linux CXL
 help / color / mirror / Atom feed
From: "Cheatham, Benjamin" <benjamin.cheatham@amd.com>
To: Anisa Su <anisa.su887@gmail.com>, <linux-cxl@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>
Cc: <nvdimm@lists.linux.dev>, Dan Williams <djbw@kernel.org>,
	Jonathan Cameron <jic23@kernel.org>,
	Davidlohr Bueso <dave@stgolabs.net>,
	Dave Jiang <dave.jiang@intel.com>,
	Vishal Verma <vishal.l.verma@intel.com>,
	Ira Weiny <iweiny@kernel.org>,
	Alison Schofield <alison.schofield@intel.com>,
	John Groves <John@Groves.net>, Gregory Price <gourry@gourry.net>,
	Anisa Su <anisa.su@samsung.com>
Subject: Re: [PATCH v11 10/31] cxl/mem: Configure dynamic capacity interrupts
Date: Tue, 7 Jul 2026 16:51:23 -0500	[thread overview]
Message-ID: <6d4b2c0e-5c05-4e92-9c9d-dba8cabe849b@amd.com> (raw)
In-Reply-To: <20260625112638.550691-11-anisa.su@samsung.com>

On 6/25/2026 6:04 AM, Anisa Su wrote:
> From: Ira Weiny <iweiny@kernel.org>
> 
> Dynamic Capacity Devices (DCD) support extent change notifications
> through the event log mechanism.  The interrupt mailbox commands were
> extended in CXL 3.1 to support these notifications.  Firmware can't
> configure DCD events to be FW controlled but can retain control of
> memory events.
> 
> Configure DCD event log interrupts on devices supporting dynamic
> capacity.  Disable DCD if interrupts are not supported.
> 
> Care is taken to preserve the interrupt policy set by the FW if FW first
> has been selected by the BIOS.
> 
> Accept the 4-byte CXL 2.0 reply on GET Event Interrupt Policy by setting
> min_out to CXL_EVENT_INT_POLICY_BASE_SIZE; pre-CXL 3.1 firmware omits
> dcd_settings and would otherwise fail the size check.
> 
> Based on an original patch by Navneet Singh.
> 
> Signed-off-by: Ira Weiny <iweiny@kernel.org>
> Signed-off-by: Anisa Su <anisa.su@samsung.com>
> 
> ---
> Changes:
> [anisa: add CXLDEV_EVENT_STATUS_DCD (bit 4) to CXLDEV_EVENT_STATUS_ALL;
> previously added in a later commit but moved to current commit]
> 
> [anisa: check native_cxl before cxl_mem_get_event_records]
> ---
>  drivers/cxl/cxl.h    |  4 +-
>  drivers/cxl/cxlmem.h |  2 +
>  drivers/cxl/pci.c    | 94 ++++++++++++++++++++++++++++++++++++--------
>  3 files changed, 83 insertions(+), 17 deletions(-)
> 
> diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
> index 1297594beaec..864f6d3c03d4 100644
> --- a/drivers/cxl/cxl.h
> +++ b/drivers/cxl/cxl.h
> @@ -180,11 +180,13 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
>  #define CXLDEV_EVENT_STATUS_WARN		BIT(1)
>  #define CXLDEV_EVENT_STATUS_FAIL		BIT(2)
>  #define CXLDEV_EVENT_STATUS_FATAL		BIT(3)
> +#define CXLDEV_EVENT_STATUS_DCD			BIT(4)
>  
>  #define CXLDEV_EVENT_STATUS_ALL (CXLDEV_EVENT_STATUS_INFO |	\
>  				 CXLDEV_EVENT_STATUS_WARN |	\
>  				 CXLDEV_EVENT_STATUS_FAIL |	\
> -				 CXLDEV_EVENT_STATUS_FATAL)
> +				 CXLDEV_EVENT_STATUS_FATAL |	\
> +				 CXLDEV_EVENT_STATUS_DCD)
>  
>  /* CXL rev 3.0 section 8.2.9.2.4; Table 8-52 */
>  #define CXLDEV_EVENT_INT_MODE_MASK	GENMASK(1, 0)
> diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
> index afc195d8c090..bcf976829c3e 100644
> --- a/drivers/cxl/cxlmem.h
> +++ b/drivers/cxl/cxlmem.h
> @@ -218,7 +218,9 @@ struct cxl_event_interrupt_policy {
>  	u8 warn_settings;
>  	u8 failure_settings;
>  	u8 fatal_settings;
> +	u8 dcd_settings;
>  } __packed;
> +#define CXL_EVENT_INT_POLICY_BASE_SIZE 4 /* info, warn, failure, fatal */
>  
>  /**
>   * struct cxl_event_state - Event log driver state
> diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
> index 8d12c684d670..95a4bf7c1e46 100644
> --- a/drivers/cxl/pci.c
> +++ b/drivers/cxl/pci.c
> @@ -514,7 +514,19 @@ static irqreturn_t cxl_event_thread(int irq, void *id)
>  	struct cxl_dev_id *dev_id = id;
>  	struct cxl_dev_state *cxlds = dev_id->cxlds;
>  	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
> +	struct pci_host_bridge *host_bridge =
> +		pci_find_host_bridge(to_pci_dev(cxlds->dev)->bus);
>  	u32 status;
> +	u32 mask;
> +
> +	/*
> +	 * Only drain logs the driver owns.  When BIOS owns event reporting
> +	 * (!native_cxl) the driver is only here for the Dynamic Capacity log;
> +	 * processing the standard logs would steal firmware-first events from
> +	 * BIOS, so mask them out.
> +	 */
> +	mask = host_bridge->native_cxl_error ? CXLDEV_EVENT_STATUS_ALL
> +					     : CXLDEV_EVENT_STATUS_DCD;
>  
>  	do {
>  		/*
> @@ -522,8 +534,8 @@ static irqreturn_t cxl_event_thread(int irq, void *id)
>  		 * ignore the reserved upper 32 bits
>  		 */
>  		status = readl(cxlds->regs.status + CXLDEV_DEV_EVENT_STATUS_OFFSET);
> -		/* Ignore logs unknown to the driver */
> -		status &= CXLDEV_EVENT_STATUS_ALL;
> +		/* Ignore logs unknown to the driver or owned by BIOS */
> +		status &= mask;
>  		if (!status)
>  			break;
>  		cxl_mem_get_event_records(mds, status);
> @@ -557,6 +569,8 @@ static int cxl_event_get_int_policy(struct cxl_memdev_state *mds,
>  		.opcode = CXL_MBOX_OP_GET_EVT_INT_POLICY,
>  		.payload_out = policy,
>  		.size_out = sizeof(*policy),
> +		/* CXL 2.0 firmware omits dcd_settings; accept the shorter reply */
> +		.min_out = CXL_EVENT_INT_POLICY_BASE_SIZE,
>  	};
>  	int rc;
>  
> @@ -569,23 +583,34 @@ static int cxl_event_get_int_policy(struct cxl_memdev_state *mds,
>  }
>  
>  static int cxl_event_config_msgnums(struct cxl_memdev_state *mds,
> -				    struct cxl_event_interrupt_policy *policy)
> +				    struct cxl_event_interrupt_policy *policy,
> +				    bool native_cxl)
>  {
>  	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
> +	size_t size_in = CXL_EVENT_INT_POLICY_BASE_SIZE;
>  	struct cxl_mbox_cmd mbox_cmd;
>  	int rc;
>  
> -	*policy = (struct cxl_event_interrupt_policy) {
> -		.info_settings = CXL_INT_MSI_MSIX,
> -		.warn_settings = CXL_INT_MSI_MSIX,
> -		.failure_settings = CXL_INT_MSI_MSIX,
> -		.fatal_settings = CXL_INT_MSI_MSIX,
> -	};
> +	/* memory event policy is left if FW has control */
> +	if (native_cxl) {
> +		*policy = (struct cxl_event_interrupt_policy) {
> +			.info_settings = CXL_INT_MSI_MSIX,
> +			.warn_settings = CXL_INT_MSI_MSIX,
> +			.failure_settings = CXL_INT_MSI_MSIX,
> +			.fatal_settings = CXL_INT_MSI_MSIX,
> +			.dcd_settings = 0,
> +		};
> +	}
> +
> +	if (cxl_dcd_supported(mds)) {
> +		policy->dcd_settings = CXL_INT_MSI_MSIX;
> +		size_in += sizeof(policy->dcd_settings);
> +	}

It seems there's a bug here that I found on one of our test machines. It's possible the card doesn't support
DCD commands but does have the policy bit for DCD (i.e. CXL card is 3.0+), so the payload still needs to be
large enough to include the DCD bit in that case. So, the size_in needs to always include dcd_settings but
the actual policy setting should stay based on whether the card supports DCD. Hopefully that makes sense, let
me know if it's not clear...


The first thing that I thought of for a solution is setting size_in based on the CXL card's DVSEC revision
(i.e. size_in = 5 for CXL 3.0+, size_in = 4 otherwise). Not exactly a clean solution, but I'm not sure there's
a way around it.

Thanks,
Ben
>  
>  	mbox_cmd = (struct cxl_mbox_cmd) {
>  		.opcode = CXL_MBOX_OP_SET_EVT_INT_POLICY,
>  		.payload_in = policy,
> -		.size_in = sizeof(*policy),
> +		.size_in = size_in,
>  	};
>  
>  	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
> @@ -632,6 +657,30 @@ static int cxl_event_irqsetup(struct cxl_memdev_state *mds,
>  	return 0;
>  }
>  
> +static int cxl_irqsetup(struct cxl_memdev_state *mds,
> +			struct cxl_event_interrupt_policy *policy,
> +			bool native_cxl)
> +{
> +	struct cxl_dev_state *cxlds = &mds->cxlds;
> +	int rc;
> +
> +	if (native_cxl) {
> +		rc = cxl_event_irqsetup(mds, policy);
> +		if (rc)
> +			return rc;
> +	}
> +
> +	if (cxl_dcd_supported(mds)) {
> +		rc = cxl_event_req_irq(cxlds, policy->dcd_settings);
> +		if (rc) {
> +			dev_err(cxlds->dev, "Failed to get interrupt for DCD event log\n");
> +			cxl_disable_dcd(mds);
> +		}
> +	}
> +
> +	return 0;
> +}
> +
>  static bool cxl_event_int_is_fw(u8 setting)
>  {
>  	u8 mode = FIELD_GET(CXLDEV_EVENT_INT_MODE_MASK, setting);
> @@ -657,18 +706,26 @@ static bool cxl_event_validate_mem_policy(struct cxl_memdev_state *mds,
>  static int cxl_event_config(struct pci_host_bridge *host_bridge,
>  			    struct cxl_memdev_state *mds, bool irq_avail)
>  {
> -	struct cxl_event_interrupt_policy policy;
> +	struct cxl_event_interrupt_policy policy = { 0 };
> +	bool native_cxl = host_bridge->native_cxl_error;
>  	int rc;
>  
>  	/*
>  	 * When BIOS maintains CXL error reporting control, it will process
>  	 * event records.  Only one agent can do so.
> +	 *
> +	 * If BIOS has control of events and DCD is not supported skip event
> +	 * configuration.
>  	 */
> -	if (!host_bridge->native_cxl_error)
> +	if (!native_cxl && !cxl_dcd_supported(mds))
>  		return 0;
>  
>  	if (!irq_avail) {
>  		dev_info(mds->cxlds.dev, "No interrupt support, disable event processing.\n");
> +		if (cxl_dcd_supported(mds)) {
> +			dev_info(mds->cxlds.dev, "DCD requires interrupts, disable DCD\n");
> +			cxl_disable_dcd(mds);
> +		}
>  		return 0;
>  	}
>  
> @@ -676,10 +733,10 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge,
>  	if (rc)
>  		return rc;
>  
> -	if (!cxl_event_validate_mem_policy(mds, &policy))
> +	if (native_cxl && !cxl_event_validate_mem_policy(mds, &policy))
>  		return -EBUSY;
>  
> -	rc = cxl_event_config_msgnums(mds, &policy);
> +	rc = cxl_event_config_msgnums(mds, &policy, native_cxl);
>  	if (rc)
>  		return rc;
>  
> @@ -687,11 +744,16 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge,
>  	if (rc)
>  		return rc;
>  
> -	rc = cxl_event_irqsetup(mds, &policy);
> +	rc = cxl_irqsetup(mds, &policy, native_cxl);
>  	if (rc)
>  		return rc;
>  
> -	cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL);
> +	if (native_cxl)
> +		cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL);
> +
> +	dev_dbg(mds->cxlds.dev, "Event config : %s DCD %s\n",
> +		native_cxl ? "OS" : "BIOS",
> +		cxl_dcd_supported(mds) ? "supported" : "not supported");
>  
>  	return 0;
>  }


  parent reply	other threads:[~2026-07-07 21:51 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-25 11:04 DCD: Add support for Dynamic Capacity Devices (DCD) Anisa Su
2026-06-25 11:04 ` [PATCH v11 01/31] cxl/mbox: Flag " Anisa Su
2026-06-26 21:43   ` Dave Jiang
2026-06-25 11:04 ` [PATCH v11 02/31] cxl/mem: Read dynamic capacity configuration from the device Anisa Su
2026-06-25 18:16   ` sashiko-bot
2026-06-26 22:26   ` Dave Jiang
2026-06-25 11:04 ` [PATCH v11 04/31] cxl/core: Enforce partition order/simplify partition calls Anisa Su
2026-06-26 22:37   ` Dave Jiang
2026-06-25 11:04 ` [PATCH v11 05/31] cxl/mem: Expose dynamic ram 1 partition in sysfs Anisa Su
2026-06-25 18:12   ` sashiko-bot
2026-06-26 23:08   ` Dave Jiang
2026-06-25 11:04 ` [PATCH v11 06/31] cxl/port: Add 'dynamic_ram_1' to endpoint decoder mode Anisa Su
2026-06-25 11:04 ` [PATCH v11 07/31] cxl/region: Add DC DAX region support Anisa Su
2026-06-25 18:16   ` sashiko-bot
2026-06-26 23:18   ` Dave Jiang
2026-06-25 11:04 ` [PATCH v11 08/31] cxl/events: Split event msgnum configuration from irq setup Anisa Su
2026-06-25 11:04 ` [PATCH v11 09/31] cxl/pci: Factor out interrupt policy check Anisa Su
2026-06-25 11:04 ` [PATCH v11 10/31] cxl/mem: Configure dynamic capacity interrupts Anisa Su
2026-06-25 18:14   ` sashiko-bot
2026-07-07 21:51   ` Cheatham, Benjamin [this message]
2026-06-25 11:04 ` [PATCH v11 11/31] cxl/core: Return endpoint decoder information from region search Anisa Su
2026-06-25 11:04 ` [PATCH v11 12/31] cxl/mem: Set up framework for handling DC Events Anisa Su
2026-06-25 18:12   ` sashiko-bot
2026-06-26 21:54   ` Dave Jiang
2026-06-25 11:04 ` [PATCH v11 13/31] cxl/mem: Add 20 second timeout for stalled DC_ADD_CAPACITY chains Anisa Su
2026-06-25 18:15   ` sashiko-bot
2026-06-30 21:11   ` Dave Jiang
2026-06-25 11:04 ` [PATCH v11 14/31] cxl/extent: Handle DC Add Capacity events Anisa Su
2026-06-25 18:16   ` sashiko-bot
2026-06-25 11:04 ` [PATCH v11 15/31] cxl/mem: Drop misaligned DCD extent groups Anisa Su
2026-06-25 18:19   ` sashiko-bot
2026-06-30 21:23   ` Dave Jiang
2026-06-25 11:04 ` [PATCH v11 16/31] cxl/extent: Validate DC extent partition Anisa Su
2026-06-25 18:20   ` sashiko-bot
2026-06-30 22:49   ` Dave Jiang
2026-06-25 11:04 ` [PATCH v11 17/31] cxl/mem: Enforce tag-group semantics Anisa Su
2026-06-25 18:24   ` sashiko-bot
2026-06-25 11:04 ` [PATCH v11 18/31] cxl/extent: Handle DC Release Capacity events Anisa Su
2026-06-25 18:23   ` sashiko-bot
2026-06-25 11:04 ` [PATCH v11 19/31] cxl/extent: Enforce cross-region tag uniqueness Anisa Su
2026-06-25 18:23   ` sashiko-bot
2026-06-25 11:04 ` [PATCH v11 20/31] cxl/region/extent: Expose dc_extent information in sysfs Anisa Su
2026-06-25 18:33   ` sashiko-bot
2026-06-25 11:04 ` [PATCH v11 21/31] cxl + dax: Surface dax_resources on DCD Add Capacity events Anisa Su
2026-06-25 18:29   ` sashiko-bot
2026-06-25 11:04 ` [PATCH v11 22/31] cxl + dax: Release dax_resources on DCD Release " Anisa Su
2026-06-25 18:36   ` sashiko-bot
2026-06-25 11:05 ` [PATCH v11 23/31] dax/bus: Factor out dev dax resize logic Anisa Su
2026-06-25 18:27   ` sashiko-bot
2026-06-25 11:05 ` [PATCH v11 24/31] dax/bus: Add uuid sysfs attribute to dax devices Anisa Su
2026-06-30 23:21   ` Dave Jiang
2026-06-25 11:05 ` [PATCH v11 25/31] dax/bus: Reject resize on DC dax devices and enforce 0-size creation Anisa Su
2026-06-25 11:05 ` [PATCH v11 26/31] dax/bus: Tag-aware uuid claim and show on DC dax devices Anisa Su
2026-06-25 18:26   ` sashiko-bot
2026-06-25 11:05 ` [PATCH v11 27/31] cxl/region: Read existing extents on region creation Anisa Su
2026-06-25 18:32   ` sashiko-bot
2026-06-25 11:05 ` [PATCH v11 28/31] cxl/mem: Trace Dynamic capacity Event Record Anisa Su
2026-06-25 18:29   ` sashiko-bot
2026-06-25 11:05 ` [PATCH v11 29/31] tools/testing/cxl: Make event logs dynamic Anisa Su
2026-06-25 18:31   ` sashiko-bot
2026-06-25 11:05 ` [PATCH v11 30/31] tools/testing/cxl: Add DC Regions to mock mem data Anisa Su
2026-06-25 18:34   ` sashiko-bot
2026-06-25 11:05 ` [PATCH v11 31/31] Documentation/cxl: Document DCD extent handling and DC-backed DAX regions Anisa Su
2026-06-25 18:24   ` sashiko-bot
2026-06-25 18:00 ` [PATCH v11 03/31] cxl/cdat: Gather DSMAS data for DCD partitions Anisa Su
2026-06-26 22:30   ` Dave Jiang

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=6d4b2c0e-5c05-4e92-9c9d-dba8cabe849b@amd.com \
    --to=benjamin.cheatham@amd.com \
    --cc=John@Groves.net \
    --cc=alison.schofield@intel.com \
    --cc=anisa.su887@gmail.com \
    --cc=anisa.su@samsung.com \
    --cc=dave.jiang@intel.com \
    --cc=dave@stgolabs.net \
    --cc=djbw@kernel.org \
    --cc=gourry@gourry.net \
    --cc=iweiny@kernel.org \
    --cc=jic23@kernel.org \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nvdimm@lists.linux.dev \
    --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