From aec49a34d928a0ecdea85bd9f6b4114b668b68b8 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 24 Jul 2026 18:52:09 -0700 Subject: ata: libata: avoid kernel-doc warnings Modify comments to prevent kernel-doc warnings: - use "/*" for a non-kernel-doc comment - add a Returns: section for ata_id_major_version() Warning: include/linux/ata.h:770 Cannot find identifier on line: * Warning: include/linux/ata.h:782 function parameter 'id' not described in 'ata_id_sct_data_tables' Warning: include/linux/ata.h:782 expecting prototype for Word(). Prototype was for ata_id_sct_data_tables() instead Warning: include/linux/ata.h:820 No description found for return value of 'ata_id_major_version' Signed-off-by: Randy Dunlap Signed-off-by: Damien Le Moal --- include/linux/ata.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ata.h b/include/linux/ata.h index 8fd48bcb2a46..7daad4cad985 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -762,8 +762,7 @@ static inline bool ata_id_sense_reporting_enabled(const u16 *id) return id[ATA_ID_COMMAND_SET_4] & BIT(6); } -/** - * +/* * Word: 206 - SCT Command Transport * 15:12 - Vendor Specific * 11:6 - Reserved @@ -810,8 +809,9 @@ static inline bool ata_id_sct_supported(const u16 *id) * * The practical impact of this is that ata_id_major_version cannot * reliably report on drives below ATA3. + * + * Returns: major version of ATA drive level or %0 if unknown */ - static inline unsigned int ata_id_major_version(const u16 *id) { unsigned int mver; -- cgit From 1e024d2b41ee32bc06818f7f09a3562c58842cf9 Mon Sep 17 00:00:00 2001 From: Matt Vollrath Date: Fri, 24 Jul 2026 03:39:42 -0400 Subject: ata: libata-eh: Increase STANDBY IMMEDIATE timeout Correct a previous change (see Fixes) which reduced the standby timeout from 30 to 5 seconds. Increase it to 15 seconds. I was troubleshooting an error spotted during system suspend: [ 1217.152867] ata1.00: Entering standby power mode [ 1222.322948] ata1.00: qc timeout after 5000 msecs (cmd 0xe0) [ 1222.324010] ata1.00: STANDBY IMMEDIATE failed (err_mask=0x4) This drive is a Samsung 870 EVO SSD in good SMART standing, and I wasn't aware of any reason it should be taking so long to standby. The issue is intermittent, but I observed it sometimes taking 7 seconds to manually standby. I assume this was interruption of background maintenance after a power outage. As a desktop user, I would prefer to wait the extra 2 seconds at suspend to let the drive finish its business rather than drop the rails from under it. The change from 30 to 5 seconds was implicit when switching suspend from START STOP UNIT to an internal command with no timeout table entry. No reason was stated for the change. Fixes: aa3998dbeb3a ("ata: libata-scsi: Disable scsi device manage_system_start_stop") Cc: stable@vger.kernel.org Signed-off-by: Matt Vollrath Assisted-by: Claude:claude-5-fable Signed-off-by: Damien Le Moal --- drivers/ata/libata-eh.c | 8 ++++++++ include/linux/libata.h | 2 +- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 05df7ea6954a..46947ed0c657 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -106,6 +106,12 @@ static const unsigned int ata_eh_flush_timeouts[] = { UINT_MAX, }; +static const unsigned int ata_eh_standby_timeouts[] = { + 15000, /* Some drives may be slow to standby */ + /* but don't hold up a suspend too long waiting for them */ + UINT_MAX, +}; + static const unsigned int ata_eh_other_timeouts[] = { 5000, /* same rationale as identify timeout */ 10000, /* ditto */ @@ -147,6 +153,8 @@ ata_eh_cmd_timeout_table[ATA_EH_CMD_TIMEOUT_TABLE_SIZE] = { .timeouts = ata_eh_other_timeouts, }, { .commands = CMDS(ATA_CMD_FLUSH, ATA_CMD_FLUSH_EXT), .timeouts = ata_eh_flush_timeouts }, + { .commands = CMDS(ATA_CMD_STANDBYNOW1), + .timeouts = ata_eh_standby_timeouts }, { .commands = CMDS(ATA_CMD_VERIFY), .timeouts = ata_eh_reset_timeouts }, }; diff --git a/include/linux/libata.h b/include/linux/libata.h index 96e626d6a7ca..6c0d385b2cde 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -425,7 +425,7 @@ enum { /* This should match the actual table size of * ata_eh_cmd_timeout_table in libata-eh.c. */ - ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 8, + ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 9, /* User visible DMA mask for DMA control. DO NOT renumber. */ ATA_DMA_MASK_ATA = (1 << 0), /* DMA on ATA Disk */ -- cgit From 2e1d2e65e773d67dab163127f11a47dab0fbca9f Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 9 Jul 2026 10:01:33 +0900 Subject: ata: libata-scsi: terminate deferred commands on time out If a command times out while we have deferred non-NCQ commands waiting to be issued, the SCSI EH task is not immediately woken up as the waiting deferred commands are never issued nor completed, thus leaving the SCSI host in a busy state (shost->host_failed != scsi_host_busy(shost)) which prevents the SCSI EH task from being woken up. Eventually, when the deferred commands also time out, the SCSI EH task is woken up and the timeout processing occurs. Avoid this unnecessary SCSI EH task wake-up additional time by scheduling a retry of all waiting deferred QCs, using the eh_timed_out SCSI host template operation. The function ata_scsi_eh_timed_out() is introduced to implement this operation. However, terminating deferred commands with DID_REQUEUE to force a retry by calling the function ata_scsi_requeue_deferred_qc() may still keep the SCSI host in a busy state because the block layer may immediately re-issue these commands. The solution to this is to schedule libata EH for the port which suffered the command timeout to prevent accepting any new command. ata_scsi_requeue_deferred_qc() is modified to add a call to ata_port_schedule_eh() for this purpose. In addition to this change, ata_scsi_requeue_deferred_qc() is also modified to take a new timedout_scmd scsi command argument which indicates the SCSI command that timed out. With this additional argument, ata_scsi_requeue_deferred_qc() can now also terminate with DID_TIME_OUT any timed out deferred qc, which simplifies ata_scsi_cmd_error_handler(). In this case, ata_scsi_requeue_deferred_qc() returns SCSI_EH_DONE, with this return value propagated back to the ata_scsi_eh_timed_out() operation to indicate to scsi_timeout() that the timed out command was handled and no further processing is needed. For non-timed out deferred qc that need to be retried, ata_scsi_requeue_deferred_qc() returns SCSI_EH_NOT_HANDLED, thus indicating to scsi_timeout() that the timed out command needs to go through the SCSI EH (and libata EH) processing by adding it to the EH work queue with scsi_eh_scmd_add(). One side effect of these changes is that the function atapi_qc_complete() needs to be modified to ensure that a deferred ATAPI command that needs to be retried is completed with DID_REQUEUE instead of the default SAM_STAT_GOOD status, and a command that timed out is completed with DID_TIME_OUT instead of SAM_STAT_CHECK_CONDITION. Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Igor Pylypiv Tested-by: Igor Pylypiv Reviewed-by: Niklas Cassel Reviewed-by: Martin K. Petersen --- drivers/ata/libata-eh.c | 29 +++--------- drivers/ata/libata-scsi.c | 112 +++++++++++++++++++++++++++++++++++++++++----- drivers/ata/libata.h | 3 +- include/linux/libata.h | 2 + 4 files changed, 111 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 46947ed0c657..c154103d892c 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -658,29 +658,12 @@ int ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, set_host_byte(scmd, DID_OK); ata_qc_for_each_raw(ap, qc, i) { - if (qc->scsicmd != scmd) - continue; - if ((qc->flags & ATA_QCFLAG_ACTIVE) || - qc == qc->dev->link->deferred_qc) + if (qc->scsicmd == scmd && + qc->flags & ATA_QCFLAG_ACTIVE) break; } - if (i < ATA_MAX_QUEUE && qc == qc->dev->link->deferred_qc) { - /* - * This is a deferred command that timed out while - * waiting for the command queue to drain. Since the qc - * is not active yet (deferred_qc is still set, so the - * deferred qc work has not issued the command yet), - * simply signal the timeout by finishing the SCSI - * command and clear the deferred qc to prevent the - * deferred qc work from issuing this qc. - */ - WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE); - qc->dev->link->deferred_qc = NULL; - cancel_work(&qc->dev->link->deferred_qc_work); - set_host_byte(scmd, DID_TIME_OUT); - scsi_eh_finish_cmd(scmd, &ap->eh_done_q); - } else if (i < ATA_MAX_QUEUE) { + if (i < ATA_MAX_QUEUE) { /* the scmd has an associated qc */ if (!(qc->flags & ATA_QCFLAG_EH)) { /* which hasn't failed yet, timeout */ @@ -956,10 +939,10 @@ static void ata_eh_set_pending(struct ata_port *ap, bool fastdrain) ap->pflags |= ATA_PFLAG_EH_PENDING; /* - * If we have a deferred qc, requeue it so that it is retried once EH - * completes. + * If we have deferred QCs, requeue them so that the SCSI EH task can + * run. */ - ata_scsi_requeue_deferred_qc(ap); + ata_scsi_requeue_deferred_qc(ap, NULL); if (!fastdrain) return; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 5868526301a2..02b04de925f9 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1685,26 +1685,80 @@ void ata_scsi_deferred_qc_work(struct work_struct *work) spin_unlock_irqrestore(ap->lock, flags); } -void ata_scsi_requeue_deferred_qc(struct ata_port *ap) +enum scsi_timeout_action ata_scsi_requeue_deferred_qc(struct ata_port *ap, + struct scsi_cmnd *timedout_scmd) { + enum scsi_timeout_action action = SCSI_EH_NOT_HANDLED; + struct ata_queued_cmd *qc; struct ata_link *link; + u32 host_byte; lockdep_assert_held(ap->lock); /* - * If we have a deferred qc when a reset occurs or NCQ commands fail, - * do not try to be smart about what to do with this deferred command - * and simply requeue it by completing it with DID_REQUEUE. + * If we have deferred QCs when a reset, a timeout or an NCQ command + * fails, do not try to be smart about what to do with the deferred + * commands and simply terminate them and let the SCSI layer decide + * what to do. */ ata_for_each_link(link, ap, PMP_FIRST) { - struct ata_queued_cmd *qc = link->deferred_qc; + qc = link->deferred_qc; + if (!qc) + continue; + + /* + * Clear the deferred QC so that the deferred work does not try + * to issue it. + */ + link->deferred_qc = NULL; + cancel_work(&link->deferred_qc_work); + + /* + * We are going to complete some scsi command, either with + * DID_TIME_OUT if the command timed out while waiting for being + * issued, or with DID_REQUEUE if another command timed out or + * we had a failed command. However, the block layer may re-issue + * these commands immediately, keeping the scsi host busy and + * thus preventing the SCSI EH task from running. + * So schedule EH on the port to prevent accepting new commands + * until everything is sorted out with the error or timeout that + * got us here in the first place. Note that we set EH pending + * on the port before calling ata_port_schedule_eh() so that we + * do not reenter this function from ata_eh_set_pending() with + * timedout_scmd being NULL and erroneously retry deferred QCs + * that have timed out on other links. + */ + if (!ata_port_eh_scheduled(ap)) { + ap->pflags |= ATA_PFLAG_EH_PENDING; + ata_port_schedule_eh(ap); + } - if (qc) { - link->deferred_qc = NULL; - cancel_work(&link->deferred_qc_work); - ata_scsi_qc_done(qc, true, DID_REQUEUE << 16); + /* + * If we are being called from scsi_timeout(), then we have a + * non-NULL timedout_scmd. If the timed out command is for a + * deferred QC, terminate that deferred QC with DID_TIME_OUT and + * requeue all other deferred QCs. In this case we need to + * return SCSI_EH_DONE, because the timed out command was + * handled. + * If the timed out command is not for a deferred QC, we need to + * requeue all deferred QCs, and return SCSI_EH_NOT_HANDLED so + * that the timed out command gets added to the EH work queue + * with scsi_eh_scmd_add(), for later handling with libata EH + * ata_scsi_cmd_error_handler(). + * If timedout_scmd is NULL, we simply need to requeue all + * deferred QCs and the return value does not matter as we were + * not called from scsi_timeout(). + */ + if (timedout_scmd && qc->scsicmd == timedout_scmd) { + host_byte = DID_TIME_OUT; + action = SCSI_EH_DONE; + } else { + host_byte = DID_REQUEUE; } + ata_scsi_qc_done(qc, true, host_byte << 16); } + + return action; } static void ata_scsi_schedule_deferred_qc(struct ata_link *link) @@ -1723,13 +1777,41 @@ static void ata_scsi_schedule_deferred_qc(struct ata_link *link) return; if (ata_port_eh_scheduled(ap)) { - ata_scsi_requeue_deferred_qc(ap); + ata_scsi_requeue_deferred_qc(ap, NULL); return; } if (!ap->ops->qc_defer(qc)) queue_work(system_highpri_wq, &link->deferred_qc_work); } +static enum scsi_timeout_action +ata_scsi_retry_deferred_qc(struct ata_port *ap, struct scsi_cmnd *scmd) +{ + enum scsi_timeout_action action; + unsigned long flags; + + spin_lock_irqsave(ap->lock, flags); + action = ata_scsi_requeue_deferred_qc(ap, scmd); + spin_unlock_irqrestore(ap->lock, flags); + + return action; +} + +enum scsi_timeout_action ata_scsi_eh_timed_out(struct scsi_cmnd *scmd) +{ + struct ata_port *ap = ata_shost_to_port(scmd->device->host); + + /* + * ata_scsi_cmd_error_handler() takes care of commands that timed out + * while executing. However, if we have deferred QCs while a timeout + * triggers, we must requeue these commands for retry so that we do not + * unnecessarily delay starting the SCSI EH task until these deferred + * commands also time out. + */ + return ata_scsi_retry_deferred_qc(ap, scmd); +} +EXPORT_SYMBOL_GPL(ata_scsi_eh_timed_out); + static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) { struct ata_link *link = qc->dev->link; @@ -2936,7 +3018,15 @@ static void atapi_qc_complete(struct ata_queued_cmd *qc) if (qc->cdb[0] == ALLOW_MEDIUM_REMOVAL && qc->dev->sdev) qc->dev->sdev->locked = 0; - ata_scsi_qc_done(qc, true, SAM_STAT_CHECK_CONDITION); + if (cmd->result) + ata_scsi_qc_done(qc, false, 0); + else + ata_scsi_qc_done(qc, true, SAM_STAT_CHECK_CONDITION); + return; + } + + if (cmd->result) { + ata_scsi_qc_done(qc, false, 0); return; } diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 700627596ce1..8dacc1daabf0 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -180,7 +180,8 @@ enum scsi_qc_status __ata_scsi_queuecmd(struct scsi_cmnd *scmd, struct ata_port *ap) __must_hold(ap->lock); void ata_scsi_deferred_qc_work(struct work_struct *work); -void ata_scsi_requeue_deferred_qc(struct ata_port *ap); +enum scsi_timeout_action ata_scsi_requeue_deferred_qc(struct ata_port *ap, + struct scsi_cmnd *scmd); /* libata-eh.c */ extern unsigned int ata_internal_cmd_timeout(struct ata_device *dev, u8 cmd); diff --git a/include/linux/libata.h b/include/linux/libata.h index 6c0d385b2cde..f10b3287b507 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1153,6 +1153,7 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd, #endif extern enum scsi_qc_status ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd); +enum scsi_timeout_action ata_scsi_eh_timed_out(struct scsi_cmnd *cmd); #if IS_REACHABLE(CONFIG_ATA) bool ata_scsi_dma_need_drain(struct request *rq); #else @@ -1464,6 +1465,7 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .ioctl = ata_scsi_ioctl, \ ATA_SCSI_COMPAT_IOCTL \ .queuecommand = ata_scsi_queuecmd, \ + .eh_timed_out = ata_scsi_eh_timed_out, \ .dma_need_drain = ata_scsi_dma_need_drain, \ .this_id = ATA_SHT_THIS_ID, \ .emulated = ATA_SHT_EMULATED, \ -- cgit From de202d2251bc181c6019b1ad3c0ba8133e5ec68d Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 9 Jul 2026 16:02:23 +0900 Subject: scsi: libsas: terminate deferred commands on time out If a command times out while we have deferred non-NCQ commands waiting to be issued, the SCSI EH task is not immediately woken up as the waiting deferred commands are never issued nor completed, thus leaving the SCSI host in a busy state (shost->host_failed != scsi_host_busy(shost)) which prevents the SCSI EH task from being woken up. Eventually, when the deferred commands also time out, the SCSI EH task is woken up and the timeout processing occurs. Avoid this unnecessary additional SCSI EH wake up time with the same method as implemented in libata-scsi, using the eh_timed_out SCSI host template operation. The function sas_eh_timed_out() implements this operation and executes the function ata_scsi_retry_deferred_qc() for SATA devices. Co-developed-by: Igor Pylypiv Signed-off-by: Igor Pylypiv Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: John Garry Reviewed-by: Hannes Reinecke Tested-by: Igor Pylypiv Reviewed-by: Niklas Cassel Reviewed-by: Martin K. Petersen --- drivers/ata/libata-scsi.c | 5 +++-- drivers/scsi/libsas/sas_scsi_host.c | 15 +++++++++++++++ include/linux/libata.h | 2 ++ include/scsi/libsas.h | 2 ++ 4 files changed, 22 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index cd64787c4772..d2160ee7ca7d 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1784,8 +1784,8 @@ static void ata_scsi_schedule_deferred_qc(struct ata_link *link) queue_work(system_highpri_wq, &link->deferred_qc_work); } -static enum scsi_timeout_action -ata_scsi_retry_deferred_qc(struct ata_port *ap, struct scsi_cmnd *scmd) +enum scsi_timeout_action ata_scsi_retry_deferred_qc(struct ata_port *ap, + struct scsi_cmnd *scmd) { enum scsi_timeout_action action; unsigned long flags; @@ -1796,6 +1796,7 @@ ata_scsi_retry_deferred_qc(struct ata_port *ap, struct scsi_cmnd *scmd) return action; } +EXPORT_SYMBOL_GPL(ata_scsi_retry_deferred_qc); enum scsi_timeout_action ata_scsi_eh_timed_out(struct scsi_cmnd *scmd) { diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c index c83282733ec4..97ac3db5dccb 100644 --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -502,6 +502,21 @@ int sas_eh_target_reset_handler(struct scsi_cmnd *cmd) } EXPORT_SYMBOL_GPL(sas_eh_target_reset_handler); +/* + * Handle deferred QCs in case of a command timeout. + * See ata_scsi_eh_timed_out() for details. + */ +enum scsi_timeout_action sas_eh_timed_out(struct scsi_cmnd *cmd) +{ + struct domain_device *dev = cmd_to_domain_dev(cmd); + + if (dev_is_sata(dev)) + return ata_scsi_retry_deferred_qc(dev->sata_dev.ap, cmd); + + return SCSI_EH_NOT_HANDLED; +} +EXPORT_SYMBOL_GPL(sas_eh_timed_out); + /* Try to reset a device */ static int try_to_reset_cmd_device(struct scsi_cmnd *cmd) { diff --git a/include/linux/libata.h b/include/linux/libata.h index f10b3287b507..1827502b9cf2 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1153,6 +1153,8 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd, #endif extern enum scsi_qc_status ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd); +enum scsi_timeout_action ata_scsi_retry_deferred_qc(struct ata_port *ap, + struct scsi_cmnd *scmd); enum scsi_timeout_action ata_scsi_eh_timed_out(struct scsi_cmnd *cmd); #if IS_REACHABLE(CONFIG_ATA) bool ata_scsi_dma_need_drain(struct request *rq); diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 163f23c92b41..c7017ae76c61 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -705,6 +705,7 @@ void sas_task_abort(struct sas_task *); int sas_eh_abort_handler(struct scsi_cmnd *cmd); int sas_eh_device_reset_handler(struct scsi_cmnd *cmd); int sas_eh_target_reset_handler(struct scsi_cmnd *cmd); +enum scsi_timeout_action sas_eh_timed_out(struct scsi_cmnd *cmd); extern void sas_target_destroy(struct scsi_target *); extern int sas_sdev_init(struct scsi_device *); @@ -743,6 +744,7 @@ void sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, .this_id = -1, \ .eh_device_reset_handler = sas_eh_device_reset_handler, \ .eh_target_reset_handler = sas_eh_target_reset_handler, \ + .eh_timed_out = sas_eh_timed_out, \ .target_destroy = sas_target_destroy, \ .ioctl = sas_ioctl, \ -- cgit