From 8a3514d348de87a9d5e2ac00fbac4faae0b97996 Mon Sep 17 00:00:00 2001 From: Sanjeev Yadav Date: Fri, 23 May 2025 13:14:01 -0700 Subject: [PATCH 1/6] scsi: core: ufs: Fix a hang in the error handler ufshcd_err_handling_prepare() calls ufshcd_rpm_get_sync(). The latter function can only succeed if UFSHCD_EH_IN_PROGRESS is not set because resuming involves submitting a SCSI command and ufshcd_queuecommand() returns SCSI_MLQUEUE_HOST_BUSY if UFSHCD_EH_IN_PROGRESS is set. Fix this hang by setting UFSHCD_EH_IN_PROGRESS after ufshcd_rpm_get_sync() has been called instead of before. Backtrace: __switch_to+0x174/0x338 __schedule+0x600/0x9e4 schedule+0x7c/0xe8 schedule_timeout+0xa4/0x1c8 io_schedule_timeout+0x48/0x70 wait_for_common_io+0xa8/0x160 //waiting on START_STOP wait_for_completion_io_timeout+0x10/0x20 blk_execute_rq+0xe4/0x1e4 scsi_execute_cmd+0x108/0x244 ufshcd_set_dev_pwr_mode+0xe8/0x250 __ufshcd_wl_resume+0x94/0x354 ufshcd_wl_runtime_resume+0x3c/0x174 scsi_runtime_resume+0x64/0xa4 rpm_resume+0x15c/0xa1c __pm_runtime_resume+0x4c/0x90 // Runtime resume ongoing ufshcd_err_handler+0x1a0/0xd08 process_one_work+0x174/0x808 worker_thread+0x15c/0x490 kthread+0xf4/0x1ec ret_from_fork+0x10/0x20 Signed-off-by: Sanjeev Yadav [ bvanassche: rewrote patch description ] Fixes: 62694735ca95 ("[SCSI] ufs: Add runtime PM support for UFS host controller driver") Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20250523201409.1676055-1-bvanassche@acm.org Reviewed-by: Peter Wang Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index a7513f256057..a1d7c8660c1b 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -6623,9 +6623,14 @@ static void ufshcd_err_handler(struct work_struct *work) up(&hba->host_sem); return; } + spin_unlock_irqrestore(hba->host->host_lock, flags); + + ufshcd_err_handling_prepare(hba); + + spin_lock_irqsave(hba->host->host_lock, flags); ufshcd_set_eh_in_progress(hba); spin_unlock_irqrestore(hba->host->host_lock, flags); - ufshcd_err_handling_prepare(hba); + /* Complete requests that have door-bell cleared by h/w */ ufshcd_complete_requests(hba, false); spin_lock_irqsave(hba->host->host_lock, flags); From ad0f54842cd23127070d8c310dd06d8f7add025c Mon Sep 17 00:00:00 2001 From: Ankit Chauhan Date: Wed, 28 May 2025 16:36:04 +0530 Subject: [PATCH 2/6] scsi: mvsas: Fix typos in per-phy comments and SAS cmd port registers Spelling fixes: Deocder --> Decoder Memroy --> Memory This is a non-functional change aimed at improving code clarity. Signed-off-by: Ankit Chauhan Link: https://lore.kernel.org/r/20250528110604.59528-1-ankitchauhan2065@gmail.com Signed-off-by: Martin K. Petersen --- drivers/scsi/mvsas/mv_defs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/mvsas/mv_defs.h b/drivers/scsi/mvsas/mv_defs.h index 8ef174cd4d37..3e4124177b2a 100644 --- a/drivers/scsi/mvsas/mv_defs.h +++ b/drivers/scsi/mvsas/mv_defs.h @@ -215,7 +215,7 @@ enum hw_register_bits { /* MVS_Px_INT_STAT, MVS_Px_INT_MASK (per-phy events) */ PHYEV_DEC_ERR = (1U << 24), /* Phy Decoding Error */ - PHYEV_DCDR_ERR = (1U << 23), /* STP Deocder Error */ + PHYEV_DCDR_ERR = (1U << 23), /* STP Decoder Error */ PHYEV_CRC_ERR = (1U << 22), /* STP CRC Error */ PHYEV_UNASSOC_FIS = (1U << 19), /* unassociated FIS rx'd */ PHYEV_AN = (1U << 18), /* SATA async notification */ @@ -347,7 +347,7 @@ enum sas_cmd_port_registers { CMD_SATA_PORT_MEM_CTL0 = 0x158, /* SATA Port Memory Control 0 */ CMD_SATA_PORT_MEM_CTL1 = 0x15c, /* SATA Port Memory Control 1 */ CMD_XOR_MEM_BIST_CTL = 0x160, /* XOR Memory BIST Control */ - CMD_XOR_MEM_BIST_STAT = 0x164, /* XOR Memroy BIST Status */ + CMD_XOR_MEM_BIST_STAT = 0x164, /* XOR Memory BIST Status */ CMD_DMA_MEM_BIST_CTL = 0x168, /* DMA Memory BIST Control */ CMD_DMA_MEM_BIST_STAT = 0x16c, /* DMA Memory BIST Status */ CMD_PORT_MEM_BIST_CTL = 0x170, /* Port Memory BIST Control */ From 9b17621366d210ffee83262a8754086ebbde5e55 Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Fri, 30 May 2025 12:29:35 -0700 Subject: [PATCH 3/6] scsi: iscsi: Fix incorrect error path labels for flashnode operations Correct the error handling goto labels used when host lookup fails in various flashnode-related event handlers: - iscsi_new_flashnode() - iscsi_del_flashnode() - iscsi_login_flashnode() - iscsi_logout_flashnode() - iscsi_logout_flashnode_sid() scsi_host_put() is not required when shost is NULL, so jumping to the correct label avoids unnecessary operations. These functions previously jumped to the wrong goto label (put_host), which did not match the intended cleanup logic. Use the correct exit labels (exit_new_fnode, exit_del_fnode, etc.) to ensure proper error handling. Also remove the unused put_host label under iscsi_new_flashnode() as it is no longer needed. No functional changes beyond accurate error path correction. Fixes: c6a4bb2ef596 ("[SCSI] scsi_transport_iscsi: Add flash node mgmt support") Signed-off-by: Alok Tiwari Link: https://lore.kernel.org/r/20250530193012.3312911-1-alok.a.tiwari@oracle.com Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_iscsi.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 0b8c91bf793f..c75a806496d6 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -3499,7 +3499,7 @@ static int iscsi_new_flashnode(struct iscsi_transport *transport, pr_err("%s could not find host no %u\n", __func__, ev->u.new_flashnode.host_no); err = -ENODEV; - goto put_host; + goto exit_new_fnode; } index = transport->new_flashnode(shost, data, len); @@ -3509,7 +3509,6 @@ static int iscsi_new_flashnode(struct iscsi_transport *transport, else err = -EIO; -put_host: scsi_host_put(shost); exit_new_fnode: @@ -3534,7 +3533,7 @@ static int iscsi_del_flashnode(struct iscsi_transport *transport, pr_err("%s could not find host no %u\n", __func__, ev->u.del_flashnode.host_no); err = -ENODEV; - goto put_host; + goto exit_del_fnode; } idx = ev->u.del_flashnode.flashnode_idx; @@ -3576,7 +3575,7 @@ static int iscsi_login_flashnode(struct iscsi_transport *transport, pr_err("%s could not find host no %u\n", __func__, ev->u.login_flashnode.host_no); err = -ENODEV; - goto put_host; + goto exit_login_fnode; } idx = ev->u.login_flashnode.flashnode_idx; @@ -3628,7 +3627,7 @@ static int iscsi_logout_flashnode(struct iscsi_transport *transport, pr_err("%s could not find host no %u\n", __func__, ev->u.logout_flashnode.host_no); err = -ENODEV; - goto put_host; + goto exit_logout_fnode; } idx = ev->u.logout_flashnode.flashnode_idx; @@ -3678,7 +3677,7 @@ static int iscsi_logout_flashnode_sid(struct iscsi_transport *transport, pr_err("%s could not find host no %u\n", __func__, ev->u.logout_flashnode.host_no); err = -ENODEV; - goto put_host; + goto exit_logout_sid; } session = iscsi_session_lookup(ev->u.logout_flashnode_sid.sid); From 9697ca0d53e3db357be26d2414276143c4a2cd49 Mon Sep 17 00:00:00 2001 From: Peter Oberparleiter Date: Tue, 3 Jun 2025 20:21:56 +0200 Subject: [PATCH 4/6] scsi: s390: zfcp: Ensure synchronous unit_add Improve the usability of the unit_add sysfs attribute by ensuring that the associated FCP LUN scan processing is completed synchronously. This enables configuration tooling to consistently determine the end of the scan process to allow for serialization of follow-on actions. While the scan process associated with unit_add typically completes synchronously, it is deferred to an asynchronous background process if unit_add is used before initial remote port scanning has completed. This occurs when unit_add is used immediately after setting the associated FCP device online. To ensure synchronous unit_add processing, wait for remote port scanning to complete before initiating the FCP LUN scan. Cc: stable@vger.kernel.org Reviewed-by: M Nikhil Reviewed-by: Nihar Panda Signed-off-by: Peter Oberparleiter Signed-off-by: Nihar Panda Link: https://lore.kernel.org/r/20250603182252.2287285-2-niharp@linux.ibm.com Signed-off-by: Martin K. Petersen --- drivers/s390/scsi/zfcp_sysfs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c index 41e36af35488..90a84ae98b97 100644 --- a/drivers/s390/scsi/zfcp_sysfs.c +++ b/drivers/s390/scsi/zfcp_sysfs.c @@ -449,6 +449,8 @@ static ssize_t zfcp_sysfs_unit_add_store(struct device *dev, if (kstrtoull(buf, 0, (unsigned long long *) &fcp_lun)) return -EINVAL; + flush_work(&port->rport_work); + retval = zfcp_unit_add(port, fcp_lun); if (retval) return retval; From b2f966568faaad326de97481096d0f3dc0971c43 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Fri, 6 Jun 2025 13:57:39 -0700 Subject: [PATCH 5/6] scsi: storvsc: Increase the timeouts to storvsc_timeout Currently storvsc_timeout is only used in storvsc_sdev_configure(), and 5s and 10s are used elsewhere. It turns out that rarely the 5s is not enough on Azure, so let's use storvsc_timeout everywhere. In case a timeout happens and storvsc_channel_init() returns an error, close the VMBus channel so that any host-to-guest messages in the channel's ringbuffer, which might come late, can be safely ignored. Add a "const" to storvsc_timeout. Cc: stable@kernel.org Signed-off-by: Dexuan Cui Link: https://lore.kernel.org/r/1749243459-10419-1-git-send-email-decui@microsoft.com Reviewed-by: Long Li Signed-off-by: Martin K. Petersen --- drivers/scsi/storvsc_drv.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 2e6b2412d2c9..d9e59204a9c3 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -362,7 +362,7 @@ MODULE_PARM_DESC(ring_avail_percent_lowater, /* * Timeout in seconds for all devices managed by this driver. */ -static int storvsc_timeout = 180; +static const int storvsc_timeout = 180; #if IS_ENABLED(CONFIG_SCSI_FC_ATTRS) static struct scsi_transport_template *fc_transport_template; @@ -768,7 +768,7 @@ static void handle_multichannel_storage(struct hv_device *device, int max_chns) return; } - t = wait_for_completion_timeout(&request->wait_event, 10*HZ); + t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ); if (t == 0) { dev_err(dev, "Failed to create sub-channel: timed out\n"); return; @@ -833,7 +833,7 @@ static int storvsc_execute_vstor_op(struct hv_device *device, if (ret != 0) return ret; - t = wait_for_completion_timeout(&request->wait_event, 5*HZ); + t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ); if (t == 0) return -ETIMEDOUT; @@ -1350,6 +1350,8 @@ static int storvsc_connect_to_vsp(struct hv_device *device, u32 ring_size, return ret; ret = storvsc_channel_init(device, is_fc); + if (ret) + vmbus_close(device->channel); return ret; } @@ -1668,7 +1670,7 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd) if (ret != 0) return FAILED; - t = wait_for_completion_timeout(&request->wait_event, 5*HZ); + t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ); if (t == 0) return TIMEOUT_ERROR; From 5c3ba81923e02adae354ec8afd006f93289b4a3c Mon Sep 17 00:00:00 2001 From: Rajashekhar M A Date: Fri, 6 Jun 2025 15:59:24 +0200 Subject: [PATCH 6/6] scsi: error: alua: I/O errors for ALUA state transitions When a host is configured with a few LUNs and I/O is running, injecting FC faults repeatedly leads to path recovery problems. The LUNs have 4 paths each and 3 of them come back active after say an FC fault which makes 2 of the paths go down, instead of all 4. This happens after several iterations of continuous FC faults. Reason here is that we're returning an I/O error whenever we're encountering sense code 06/04/0a (LOGICAL UNIT NOT ACCESSIBLE, ASYMMETRIC ACCESS STATE TRANSITION) instead of retrying. Signed-off-by: Rajashekhar M A Signed-off-by: Hannes Reinecke Link: https://lore.kernel.org/r/20250606135924.27397-1-hare@kernel.org Reviewed-by: Lee Duncan Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_error.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 376b8897ab90..746ff6a1f309 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -665,7 +665,8 @@ enum scsi_disposition scsi_check_sense(struct scsi_cmnd *scmd) * if the device is in the process of becoming ready, we * should retry. */ - if ((sshdr.asc == 0x04) && (sshdr.ascq == 0x01)) + if ((sshdr.asc == 0x04) && + (sshdr.ascq == 0x01 || sshdr.ascq == 0x0a)) return NEEDS_RETRY; /* * if the device is not started, we need to wake