Re: [PATCH v10 13/31] cxl/mem: Add 20 second timeout for stalled DC_ADD_CAPACITY chains

[Dave Jiang <dave.jiang@intel.com>]

On 5/23/26 2:43 AM, Anisa Su wrote:
> A DC_ADD_CAPACITY event can span multiple event records grouped together
> by the CXL_DCD_EVENT_MORE flag. Extents are staged in the pending list until
> the last event record ('More'=0) is received, at which point the pending
> list is processed. If the device opens such a chain (More=1) but never
> sends the closing record, the staged list sits indefinitely.
> 
> Add a delayed-work watchdog that, on expiry, refuses the chain with an
> empty ADD_DC_RESPONSE and drops the staged list.
> 
> The 20s timeout is a conservative upper bound and may be tightened
> later. The timeout is purely defensive — the spec does not require it,
> but prevents issues from a lost mailbox response or a crashed fabric manager.
> 
> Signed-off-by: Anisa Su <anisa.su@samsung.com>
> ---
>  drivers/cxl/core/mbox.c | 73 ++++++++++++++++++++++++++++++++++++++++-
>  drivers/cxl/cxlmem.h    | 23 ++++++++++---
>  2 files changed, 91 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
> index 1b38f34538f3..c376492fa166 100644
> --- a/drivers/cxl/core/mbox.c
> +++ b/drivers/cxl/core/mbox.c
> @@ -1219,6 +1219,48 @@ static void clear_pending_extents(void *_mds)
>  	mds->add_ctx.group = NULL;
>  }
>  
> +/*
> + * Bound on how long the host will wait for a device to finish a
> + * multi-record DC_ADD_CAPACITY chain (More=1 ... More=0) before
> + * refusing the chain.
> + * The timeout is not defined in the spec, but added for defensive purposes.
> + * Since there is no spec-defined timeout, 20s is chosen as a generous
> + * upper bound and matches the GPF timeout.
> + */
> +#define CXL_DC_ADD_TIMEOUT	(20 * HZ)
> +
> +static void cxl_dc_add_timeout(struct work_struct *work)
> +{
> +	struct pending_add_ctx *ctx = container_of(to_delayed_work(work),
> +						   struct pending_add_ctx,
> +						   timeout_work);
> +	struct cxl_memdev_state *mds = container_of(ctx,
> +						    struct cxl_memdev_state,
> +						    add_ctx);
> +	struct device *dev = mds->cxlds.dev;
> +
> +	guard(mutex)(&ctx->lock);
> +
> +	if (!ctx->armed)
> +		return;
> +
> +	dev_warn(dev, "DC add chain timed out; refusing staged extents\n");
> +
> +	if (cxl_send_dc_response(mds, CXL_MBOX_OP_ADD_DC_RESPONSE,
> +				 &ctx->pending_extents, 0))
> +		dev_dbg(dev, "Failed to send empty ADD_DC_RESPONSE on timeout\n");
> +
> +	clear_pending_extents(mds);
> +	ctx->armed = false;
> +}
> +
> +static void cxl_cancel_dcd_add_chain_work(void *_mds)
> +{
> +	struct cxl_memdev_state *mds = _mds;
> +
> +	cancel_delayed_work_sync(&mds->add_ctx.timeout_work);
> +}
> +
>  static int add_to_pending_list(struct list_head *pending_list,
>  			       struct cxl_extent *to_add)
>  {
> @@ -1246,18 +1288,34 @@ static int add_to_pending_list(struct list_head *pending_list,
>  static int handle_add_event(struct cxl_memdev_state *mds,
>  			    struct cxl_event_dcd *event)
>  {
> +	struct pending_add_ctx *ctx = &mds->add_ctx;
>  	struct device *dev = mds->cxlds.dev;
>  	int rc;
>  
> -	rc = add_to_pending_list(&mds->add_ctx.pending_extents, &event->extent);
> +	guard(mutex)(&ctx->lock);
> +
> +	rc = add_to_pending_list(&ctx->pending_extents, &event->extent);
>  	if (rc)
>  		return rc;
>  
>  	if (event->flags & CXL_DCD_EVENT_MORE) {
>  		dev_dbg(dev, "more bit set; delay the surfacing of extent\n");
> +		mod_delayed_work(system_wq, &ctx->timeout_work,
> +						 CXL_DC_ADD_TIMEOUT);
> +		ctx->armed = true;
>  		return 0;
>  	}
>  
> +	/*
> +	 * Chain is closing.  Disarm before flushing so a pending watchdog
> +	 * (queued but blocked on @ctx->lock) sees !armed and bails out.
> +	 * cancel_delayed_work() — not _sync — because handle_add_event()
> +	 * itself runs on system_wq and a sync cancel of same-wq work can
> +	 * deadlock.
> +	 */

Don't think this comment is correct. handle_add_event() is launched from threaded irq and does not run in system_wq. Just drop that second part of the comments.

> +	ctx->armed = false;
> +	cancel_delayed_work(&ctx->timeout_work);
> +
>  	rc = cxl_send_dc_response(mds, CXL_MBOX_OP_ADD_DC_RESPONSE,
>  				  &mds->add_ctx.pending_extents, 0);
>  	clear_pending_extents(mds);
> @@ -2009,11 +2067,24 @@ struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev, u64 serial,
>  
>  	mutex_init(&mds->event.log_lock);
>  	INIT_LIST_HEAD(&mds->add_ctx.pending_extents);
> +	mutex_init(&mds->add_ctx.lock);
> +	INIT_DELAYED_WORK(&mds->add_ctx.timeout_work,
> +			  cxl_dc_add_timeout);
> +	mds->add_ctx.armed = false;

Not needed. Allocated memory zeroed.

DJ

>  
>  	rc = devm_add_action_or_reset(dev, clear_pending_extents, mds);
>  	if (rc)
>  		return ERR_PTR(rc);
>  
> +	/*
> +	 * Registered after clear_pending_extents so devm's reverse-order
> +	 * unwind cancels (and waits for) the watchdog first, then the list
> +	 * cleanup runs with the watchdog guaranteed not to refire.
> +	 */
> +	rc = devm_add_action_or_reset(dev, cxl_cancel_dcd_add_chain_work, mds);
> +	if (rc)
> +		return ERR_PTR(rc);
> +
>  	rc = devm_cxl_register_mce_notifier(dev, &mds->mce_notifier);
>  	if (rc == -EOPNOTSUPP)
>  		dev_warn(dev, "CXL MCE unsupported\n");
> diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
> index 592c8e3b611c..d992cc9b7811 100644
> --- a/drivers/cxl/cxlmem.h
> +++ b/drivers/cxl/cxlmem.h
> @@ -8,6 +8,8 @@
>  #include <linux/uuid.h>
>  #include <linux/node.h>
>  #include <linux/list.h>
> +#include <linux/mutex.h>
> +#include <linux/workqueue.h>
>  #include <cxl/event.h>
>  #include <cxl/mailbox.h>
>  #include "cxl.h"
> @@ -402,19 +404,32 @@ static inline struct cxl_dev_state *mbox_to_cxlds(struct cxl_mailbox *cxl_mbox)
>  
>  /**
>   * struct pending_add_ctx - Staging state for an in-progress
> - *			    DCD_ADD_CAPACITY event chain
> + *							DCD_ADD_CAPACITY event chain
>   * @pending_extents: extents received so far in the chain; flushed when
> - *		     the chain closes (More=0)
> + *					 the chain closes (More=0)
>   * @group: tag group being assembled from the chain
> + * @timeout_work: watchdog that fires if a chain is opened with
> + *				  CXL_DCD_EVENT_MORE but the closing record never arrives
> + * @lock: serialises updates to the chain state against the watchdog
> + * @armed: set when a More=1 chain opens; cleared when the chain closes,
> + *		   either by a More=0 event record or by the watchdog firing.
>   *
>   * A DCD_ADD_CAPACITY notification can span multiple event records
>   * stitched together by the CXL_DCD_EVENT_MORE flag.  Records are staged
> - * here until the device clears More, at which point the staged batch is
> - * processed and responded to as a single Add_DC_Response.
> + * here until an event record with 'More'=0 is received, at which point the
> + * staged batch is processed and responded to as a single Add_DC_Response.
> + *
> + * If a chain is opened (More=1) but the device never sends the closing
> + * record, the staged list would otherwise sit indefinitely.  @timeout_work
> + * is a defensive watchdog that refuses such a chain with an empty response
> + * and drops the staged list.
>   */
>  struct pending_add_ctx {
>  	struct list_head pending_extents;
>  	struct cxl_dc_tag_group *group;
> +	struct delayed_work timeout_work;
> +	struct mutex lock;
> +	bool armed;
>  };
>  
>  /**