From 21e3d6c81179bbdfa279efc8de456c34b814cfd2 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Tue, 3 Sep 2019 12:18:39 +0200 Subject: scsi: sd: Ignore a failure to sync cache due to lack of authorization I've got a report about a UAS drive enclosure reporting back Sense: Logical unit access not authorized if the drive it holds is password protected. While the drive is obviously unusable in that state as a mass storage device, it still exists as a sd device and when the system is asked to perform a suspend of the drive, it will be sent a SYNCHRONIZE CACHE. If that fails due to password protection, the error must be ignored. Cc: Link: https://lore.kernel.org/r/20190903101840.16483-1-oneukum@suse.com Signed-off-by: Oliver Neukum Signed-off-by: Martin K. Petersen --- drivers/scsi/sd.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 91af598f2f53..0f96eb0ddbfa 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1655,7 +1655,8 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) /* we need to evaluate the error return */ if (scsi_sense_valid(sshdr) && (sshdr->asc == 0x3a || /* medium not present */ - sshdr->asc == 0x20)) /* invalid command */ + sshdr->asc == 0x20 || /* invalid command */ + (sshdr->asc == 0x74 && sshdr->ascq == 0x71))) /* drive is password locked */ /* this is no error here */ return 0; -- cgit v1.2.3-58-ga151 From 9bc6157f5fd0e898c94f3018d088a3419bde0d8f Mon Sep 17 00:00:00 2001 From: Daniel Wagner Date: Fri, 27 Sep 2019 09:30:31 +0200 Subject: scsi: qla2xxx: Remove WARN_ON_ONCE in qla2x00_status_cont_entry() Commit 88263208dd23 ("scsi: qla2xxx: Complain if sp->done() is not called from the completion path") introduced the WARN_ON_ONCE in qla2x00_status_cont_entry(). The assumption was that there is only one status continuations element. According to the firmware documentation it is possible that multiple status continuations are emitted by the firmware. Fixes: 88263208dd23 ("scsi: qla2xxx: Complain if sp->done() is not called from the completion path") Link: https://lore.kernel.org/r/20190927073031.62296-1-dwagner@suse.de Cc: Bart Van Assche Reviewed-by: Hannes Reinecke Reviewed-by: Bart Van Assche Signed-off-by: Daniel Wagner Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_isr.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 4c26630c1c3e..009fd5a33fcd 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2837,8 +2837,6 @@ qla2x00_status_cont_entry(struct rsp_que *rsp, sts_cont_entry_t *pkt) if (sense_len == 0) { rsp->status_srb = NULL; sp->done(sp, cp->result); - } else { - WARN_ON_ONCE(true); } } -- cgit v1.2.3-58-ga151 From 8f8fed0cdbbd6cdbf28d9ebe662f45765d2f7d39 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 1 Oct 2019 16:48:39 +0900 Subject: scsi: core: save/restore command resid for error handling When a non-passthrough command is terminated with CHECK CONDITION, request sense is executed by hijacking the command descriptor. Since scsi_eh_prep_cmnd() and scsi_eh_restore_cmnd() do not save/restore the original command resid, the value returned on failure of the original command is lost and replaced with the value set by the execution of the request sense command. This value may in many instances be unaligned to the device sector size, causing sd_done() to print a warning message about the incorrect unaligned resid before the command is retried. Fix this problem by saving the original command residual in struct scsi_eh_save using scsi_eh_prep_cmnd() and restoring it in scsi_eh_restore_cmnd(). In addition, to make sure that the request sense command is executed with a correctly initialized command structure, also reset the residual to 0 in scsi_eh_prep_cmnd() after saving the original command value in struct scsi_eh_save. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20191001074839.1994-1-damien.lemoal@wdc.com Signed-off-by: Damien Le Moal Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_error.c | 3 +++ include/scsi/scsi_eh.h | 1 + 2 files changed, 4 insertions(+) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 1c470e31ae81..ae2fa170f6ad 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -967,6 +967,7 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, ses->data_direction = scmd->sc_data_direction; ses->sdb = scmd->sdb; ses->result = scmd->result; + ses->resid_len = scmd->req.resid_len; ses->underflow = scmd->underflow; ses->prot_op = scmd->prot_op; ses->eh_eflags = scmd->eh_eflags; @@ -977,6 +978,7 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, memset(scmd->cmnd, 0, BLK_MAX_CDB); memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->result = 0; + scmd->req.resid_len = 0; if (sense_bytes) { scmd->sdb.length = min_t(unsigned, SCSI_SENSE_BUFFERSIZE, @@ -1029,6 +1031,7 @@ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) scmd->sc_data_direction = ses->data_direction; scmd->sdb = ses->sdb; scmd->result = ses->result; + scmd->req.resid_len = ses->resid_len; scmd->underflow = ses->underflow; scmd->prot_op = ses->prot_op; scmd->eh_eflags = ses->eh_eflags; diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h index 3810b340551c..6bd5ed695a5e 100644 --- a/include/scsi/scsi_eh.h +++ b/include/scsi/scsi_eh.h @@ -32,6 +32,7 @@ extern int scsi_ioctl_reset(struct scsi_device *, int __user *); struct scsi_eh_save { /* saved state */ int result; + unsigned int resid_len; int eh_eflags; enum dma_data_direction data_direction; unsigned underflow; -- cgit v1.2.3-58-ga151 From 2190168aaea42c31bff7b9a967e7b045f07df095 Mon Sep 17 00:00:00 2001 From: Steffen Maier Date: Tue, 1 Oct 2019 12:49:49 +0200 Subject: scsi: zfcp: fix reaction on bit error threshold notification On excessive bit errors for the FCP channel ingress fibre path, the channel notifies us. Previously, we only emitted a kernel message and a trace record. Since performance can become suboptimal with I/O timeouts due to bit errors, we now stop using an FCP device by default on channel notification so multipath on top can timely failover to other paths. A new module parameter zfcp.ber_stop can be used to get zfcp old behavior. User explanation of new kernel message: * Description: * The FCP channel reported that its bit error threshold has been exceeded. * These errors might result from a problem with the physical components * of the local fibre link into the FCP channel. * The problem might be damage or malfunction of the cable or * cable connection between the FCP channel and * the adjacent fabric switch port or the point-to-point peer. * Find details about the errors in the HBA trace for the FCP device. * The zfcp device driver closed down the FCP device * to limit the performance impact from possible I/O command timeouts. * User action: * Check for problems on the local fibre link, ensure that fibre optics are * clean and functional, and all cables are properly plugged. * After the repair action, you can manually recover the FCP device by * writing "0" into its "failed" sysfs attribute. * If recovery through sysfs is not possible, set the CHPID of the device * offline and back online on the service element. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: #2.6.30+ Link: https://lore.kernel.org/r/20191001104949.42810-1-maier@linux.ibm.com Reviewed-by: Jens Remus Reviewed-by: Benjamin Block Signed-off-by: Steffen Maier Signed-off-by: Martin K. Petersen --- drivers/s390/scsi/zfcp_fsf.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 296bbc3c4606..cf63916814cc 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -27,6 +27,11 @@ struct kmem_cache *zfcp_fsf_qtcb_cache; +static bool ber_stop = true; +module_param(ber_stop, bool, 0600); +MODULE_PARM_DESC(ber_stop, + "Shuts down FCP devices for FCP channels that report a bit-error count in excess of its threshold (default on)"); + static void zfcp_fsf_request_timeout_handler(struct timer_list *t) { struct zfcp_fsf_req *fsf_req = from_timer(fsf_req, t, timer); @@ -236,10 +241,15 @@ static void zfcp_fsf_status_read_handler(struct zfcp_fsf_req *req) case FSF_STATUS_READ_SENSE_DATA_AVAIL: break; case FSF_STATUS_READ_BIT_ERROR_THRESHOLD: - dev_warn(&adapter->ccw_device->dev, - "The error threshold for checksum statistics " - "has been exceeded\n"); zfcp_dbf_hba_bit_err("fssrh_3", req); + if (ber_stop) { + dev_warn(&adapter->ccw_device->dev, + "All paths over this FCP device are disused because of excessive bit errors\n"); + zfcp_erp_adapter_shutdown(adapter, 0, "fssrh_b"); + } else { + dev_warn(&adapter->ccw_device->dev, + "The error threshold for checksum statistics has been exceeded\n"); + } break; case FSF_STATUS_READ_LINK_DOWN: zfcp_fsf_status_read_link_down(req); -- cgit v1.2.3-58-ga151 From b23f330d5145b92f90cf16f1adc5444ad06764b4 Mon Sep 17 00:00:00 2001 From: Himanshu Madhani Date: Tue, 1 Oct 2019 08:33:38 -0700 Subject: scsi: MAINTAINERS: Update qla2xxx driver Update maintainer entry for qla2xxx driver now that email addresses have been changed to Marvell. Link: https://lore.kernel.org/r/20191001153338.28765-1-hmadhani@marvell.com Signed-off-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 783569e3c4b4..91f33522393a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13184,7 +13184,7 @@ S: Maintained F: drivers/scsi/qla1280.[ch] QLOGIC QLA2XXX FC-SCSI DRIVER -M: qla2xxx-upstream@qlogic.com +M: hmadhani@marvell.com L: linux-scsi@vger.kernel.org S: Supported F: Documentation/scsi/LICENSE.qla2xxx -- cgit v1.2.3-58-ga151