Re: [PATCH 13/13] scsi: core: Add implicit ALUA support

[Benjamin Marzinski <bmarzins@redhat.com>]

On Tue, Mar 17, 2026 at 12:07:03PM +0000, John Garry wrote:
> For when no device handler is used, add ALUA support.
> 
> This will be equivalent to when native SCSI multipathing is used.
> 
> Essentially all the same handling is available as DH alua driver for
> rescan, request prep, sense handling.
> 
> Signed-off-by: John Garry <john.g.garry@oracle.com>
> ---
>  drivers/scsi/scsi_alua.c  | 93 +++++++++++++++++++++++++++++++++++++++
>  drivers/scsi/scsi_error.c |  7 +++
>  drivers/scsi/scsi_lib.c   |  7 +++
>  drivers/scsi/scsi_scan.c  |  2 +
>  drivers/scsi/scsi_sysfs.c |  4 +-
>  include/scsi/scsi_alua.h  | 14 ++++++
>  6 files changed, 126 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/scsi/scsi_alua.c b/drivers/scsi/scsi_alua.c
> index d3fcd887e5018..ee0229b1a9d12 100644
> --- a/drivers/scsi/scsi_alua.c
> +++ b/drivers/scsi/scsi_alua.c
> @@ -562,6 +562,90 @@ int scsi_alua_stpg_run(struct scsi_device *sdev, bool optimize)
>  }
>  EXPORT_SYMBOL_GPL(scsi_alua_stpg_run);
>  
> +enum scsi_disposition scsi_alua_check_sense(struct scsi_device *sdev,
> +					      struct scsi_sense_hdr *sense_hdr)

This seems like it should be shareable with scsi_dh_alua as well.  In
might need to take a function to call for rescanning and have
alua_check_sense() be a wrapper around it, but since the force argument
to alua_check() is now always set to true in scsi_dh_alua, it's
unnecessary, so both it and scsi_device_alua_rescan() can have the
same arguments.

> +{
> +	switch (sense_hdr->sense_key) {
> +	case NOT_READY:
> +		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a) {
> +			/*
> +			 * LUN Not Accessible - ALUA state transition
> +			 */
> +			scsi_alua_handle_state_transition(sdev);
> +			return NEEDS_RETRY;
> +		}
> +		break;
> +	case UNIT_ATTENTION:
> +		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a) {
> +			/*
> +			 * LUN Not Accessible - ALUA state transition
> +			 */
> +			scsi_alua_handle_state_transition(sdev);
> +			return NEEDS_RETRY;
> +		}
> +		if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00) {
> +			/*
> +			 * Power On, Reset, or Bus Device Reset.
> +			 * Might have obscured a state transition,
> +			 * so schedule a recheck.
> +			 */
> +			scsi_device_alua_rescan(sdev);
> +			return ADD_TO_MLQUEUE;
> +		}
> +		if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x04)
> +			/*
> +			 * Device internal reset
> +			 */
> +			return ADD_TO_MLQUEUE;
> +		if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x01)
> +			/*
> +			 * Mode Parameters Changed
> +			 */
> +			return ADD_TO_MLQUEUE;
> +		if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x06) {
> +			/*
> +			 * ALUA state changed
> +			 */
> +			scsi_device_alua_rescan(sdev);
> +			return ADD_TO_MLQUEUE;
> +		}
> +		if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x07) {
> +			/*
> +			 * Implicit ALUA state transition failed
> +			 */
> +			scsi_device_alua_rescan(sdev);
> +			return ADD_TO_MLQUEUE;
> +		}
> +		if (sense_hdr->asc == 0x3f && sense_hdr->ascq == 0x03)
> +			/*
> +			 * Inquiry data has changed
> +			 */
> +			return ADD_TO_MLQUEUE;
> +		if (sense_hdr->asc == 0x3f && sense_hdr->ascq == 0x0e)
> +			/*
> +			 * REPORTED_LUNS_DATA_HAS_CHANGED is reported
> +			 * when switching controllers on targets like
> +			 * Intel Multi-Flex. We can just retry.
> +			 */
> +			return ADD_TO_MLQUEUE;
> +		break;
> +	}
> +
> +	return SCSI_RETURN_NOT_HANDLED;
> +}
> +
> +static void alua_rtpg_work(struct work_struct *work)
> +{
> +	struct alua_data *alua =
> +		container_of(work, struct alua_data, work.work);
> +	int ret;
> +
> +	ret = scsi_alua_rtpg_run(alua->sdev);
> +
> +	if (ret == -EAGAIN)
> +		queue_delayed_work(kalua_wq, &alua->work, alua->interval * HZ);
> +}
> +
>  int scsi_alua_sdev_init(struct scsi_device *sdev)
>  {
>  	int rel_port, ret, tpgs;
> @@ -591,6 +675,7 @@ int scsi_alua_sdev_init(struct scsi_device *sdev)
>  		goto out_free_data;
>  	}
>  
> +	INIT_DELAYED_WORK(&sdev->alua->work, alua_rtpg_work);
>  	sdev->alua->sdev = sdev;
>  	sdev->alua->tpgs = tpgs;
>  	spin_lock_init(&sdev->alua->lock);
> @@ -638,6 +723,14 @@ bool scsi_device_alua_implicit(struct scsi_device *sdev)
>  	return sdev->alua->tpgs & TPGS_MODE_IMPLICIT;
>  }
>  
> +void scsi_device_alua_rescan(struct scsi_device *sdev)
> +{
> +	struct alua_data *alua = sdev->alua;
> +
> +	queue_delayed_work(kalua_wq, &alua->work,
> +				msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS));

This code doesn't support triggering a new rtpg while the current one is
running.  I'll leave it to people with more scsi expertise to say how
important that is, but the scsi_dh_alua code now will always trigger a
new rtpg in this case (or at least it would, with the issues from patch
12 fixed).

-Ben

> +}
> +
>  int scsi_alua_init(void)
>  {
>  	kalua_wq = alloc_workqueue("kalua", WQ_MEM_RECLAIM | WQ_PERCPU, 0);
> diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
> index 147127fb4db9c..a542e7a85a24d 100644
> --- a/drivers/scsi/scsi_error.c
> +++ b/drivers/scsi/scsi_error.c
> @@ -29,6 +29,7 @@
>  #include <linux/jiffies.h>
>  
>  #include <scsi/scsi.h>
> +#include <scsi/scsi_alua.h>
>  #include <scsi/scsi_cmnd.h>
>  #include <scsi/scsi_dbg.h>
>  #include <scsi/scsi_device.h>
> @@ -578,6 +579,12 @@ enum scsi_disposition scsi_check_sense(struct scsi_cmnd *scmd)
>  		if (rc != SCSI_RETURN_NOT_HANDLED)
>  			return rc;
>  		/* handler does not care. Drop down to default handling */
> +	} else if (scsi_device_alua_implicit(sdev)) {
> +		enum scsi_disposition rc;
> +
> +		rc = scsi_alua_check_sense(sdev, &sshdr);
> +		if (rc != SCSI_RETURN_NOT_HANDLED)
> +			return rc;
>  	}
>  
>  	if (scmd->cmnd[0] == TEST_UNIT_READY &&
> diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
> index d3a8cd4166f92..e5bcee555ea10 100644
> --- a/drivers/scsi/scsi_lib.c
> +++ b/drivers/scsi/scsi_lib.c
> @@ -26,6 +26,7 @@
>  #include <linux/unaligned.h>
>  
>  #include <scsi/scsi.h>
> +#include <scsi/scsi_alua.h>
>  #include <scsi/scsi_cmnd.h>
>  #include <scsi/scsi_dbg.h>
>  #include <scsi/scsi_device.h>
> @@ -1719,6 +1720,12 @@ static blk_status_t scsi_prepare_cmd(struct request *req)
>  	if (sdev->handler && sdev->handler->prep_fn) {
>  		blk_status_t ret = sdev->handler->prep_fn(sdev, req);
>  
> +		if (ret != BLK_STS_OK)
> +			return ret;
> +	} else if (scsi_device_alua_implicit(sdev)) {
> +		/* We should be able to make this common for ALUA DH as well */
> +		blk_status_t ret = scsi_alua_prep_fn(sdev, req);
> +
>  		if (ret != BLK_STS_OK)
>  			return ret;
>  	}
> diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
> index 3af64d1231445..73caf83bd1097 100644
> --- a/drivers/scsi/scsi_scan.c
> +++ b/drivers/scsi/scsi_scan.c
> @@ -1744,6 +1744,8 @@ int scsi_rescan_device(struct scsi_device *sdev)
>  
>  	if (sdev->handler && sdev->handler->rescan)
>  		sdev->handler->rescan(sdev);
> +	else if (scsi_device_alua_implicit(sdev))
> +		scsi_device_alua_rescan(sdev);
>  
>  	if (dev->driver && try_module_get(dev->driver->owner)) {
>  		struct scsi_driver *drv = to_scsi_driver(dev->driver);
> diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
> index 6c4c3c22f6acf..71a9613898cfc 100644
> --- a/drivers/scsi/scsi_sysfs.c
> +++ b/drivers/scsi/scsi_sysfs.c
> @@ -1152,7 +1152,7 @@ sdev_show_access_state(struct device *dev,
>  	unsigned char access_state;
>  	const char *access_state_name;
>  
> -	if (!sdev->handler)
> +	if (!sdev->handler && !scsi_device_alua_implicit(sdev))
>  		return -EINVAL;
>  
>  	access_state = (sdev->access_state & SCSI_ACCESS_STATE_MASK);
> @@ -1409,6 +1409,8 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev)
>  	scsi_autopm_get_device(sdev);
>  
>  	scsi_dh_add_device(sdev);
> +	if (!sdev->handler && scsi_device_alua_implicit(sdev))
> +		scsi_device_alua_rescan(sdev);
>  
>  	error = device_add(&sdev->sdev_gendev);
>  	if (error) {
> diff --git a/include/scsi/scsi_alua.h b/include/scsi/scsi_alua.h
> index 2d5db944f75b7..8e506d1d66cce 100644
> --- a/include/scsi/scsi_alua.h
> +++ b/include/scsi/scsi_alua.h
> @@ -24,6 +24,7 @@ struct alua_data {
>  	unsigned char		transition_tmo;
>  	unsigned long		expiry;
>  	unsigned long		interval;
> +	struct delayed_work	work;
>  	struct scsi_device	*sdev;
>  	spinlock_t		lock;
>  };
> @@ -35,11 +36,15 @@ void scsi_alua_handle_state_transition(struct scsi_device *sdev);
>  
>  int scsi_alua_check_tpgs(struct scsi_device *sdev);
>  
> +enum scsi_disposition scsi_alua_check_sense(struct scsi_device *sdev,
> +				struct scsi_sense_hdr *sense_hdr);
> +
>  int scsi_alua_rtpg_run(struct scsi_device *sdev);
>  int scsi_alua_stpg_run(struct scsi_device *sdev, bool optimize);
>  
>  blk_status_t scsi_alua_prep_fn(struct scsi_device *sdev, struct request *req);
>  
> +void scsi_device_alua_rescan(struct scsi_device *sdev);
>  bool scsi_device_alua_implicit(struct scsi_device *sdev);
>  
>  int scsi_alua_init(void);
> @@ -53,6 +58,12 @@ static inline int scsi_alua_check_tpgs(struct scsi_device *sdev)
>  {
>  	return 0;
>  }
> +static inline
> +enum scsi_disposition scsi_alua_check_sense(struct scsi_device *sdev,
> +				struct scsi_sense_hdr *sense_hdr)
> +{
> +	return SCSI_RETURN_NOT_HANDLED;
> +}
>  static inline int scsi_alua_rtpg_run(struct scsi_device *sdev)
>  {
>  	return 0;
> @@ -66,6 +77,9 @@ blk_status_t scsi_alua_prep_fn(struct scsi_device *sdev, struct request *req)
>  {
>  	return BLK_STS_OK;
>  }
> +static inline void scsi_device_alua_rescan(struct scsi_device *sdev)
> +{
> +}
>  static inline bool scsi_device_alua_implicit(struct scsi_device *sdev)
>  {
>  	return false;
> -- 
> 2.43.5