Re: [PATCH v11 10/31] cxl/mem: Configure dynamic capacity interrupts

On 6/25/2026 6:04 AM, Anisa Su wrote:
> From: Ira Weiny <[email protected]>
> 
> 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 <[email protected]>
> Signed-off-by: Anisa Su <[email protected]>
> 
> ---
> 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;
>  }