From a621bac3044ed6f7ec5fa0326491b2d4838bfa93 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Fri, 13 May 2016 12:04:06 -0700 Subject: scsi_lib: correctly retry failed zero length REQ_TYPE_FS commands When SCSI was written, all commands coming from the filesystem (REQ_TYPE_FS commands) had data. This meant that our signal for needing to complete the command was the number of bytes completed being equal to the number of bytes in the request. Unfortunately, with the advent of flush barriers, we can now get zero length REQ_TYPE_FS commands, which confuse this logic because they satisfy the condition every time. This means they never get retried even for retryable conditions, like UNIT ATTENTION because we complete them early assuming they're done. Fix this by special casing the early completion condition to recognise zero length commands with errors and let them drop through to the retry code. Cc: stable@vger.kernel.org Reported-by: Sebastian Parschauer Signed-off-by: James E.J. Bottomley Tested-by: Jack Wang Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b2e332af0f51..c71344aebdbb 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -821,9 +821,12 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) } /* - * If we finished all bytes in the request we are done now. + * special case: failed zero length commands always need to + * drop down into the retry code. Otherwise, if we finished + * all bytes in the request we are done now. */ - if (!scsi_end_request(req, error, good_bytes, 0)) + if (!(blk_rq_bytes(req) == 0 && error) && + !scsi_end_request(req, error, good_bytes, 0)) return; /* -- cgit v1.2.3 From eb72d0bb84eee5d0dc3044fd17b75e7101dabb57 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 26 Apr 2016 08:06:58 +0200 Subject: sd: get disk reference in sd_check_events() sd_check_events() is called asynchronously, and might race with device removal. So always take a disk reference when processing the event to avoid the device being removed while the event is processed. Signed-off-by: Hannes Reinecke Reviewed-by: Ewan D. Milne Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/sd.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 428c03ef02b2..f459dff30512 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1398,11 +1398,15 @@ static int media_not_present(struct scsi_disk *sdkp, **/ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing) { - struct scsi_disk *sdkp = scsi_disk(disk); - struct scsi_device *sdp = sdkp->device; + struct scsi_disk *sdkp = scsi_disk_get(disk); + struct scsi_device *sdp; struct scsi_sense_hdr *sshdr = NULL; int retval; + if (!sdkp) + return 0; + + sdp = sdkp->device; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_check_events\n")); /* @@ -1459,6 +1463,7 @@ out: kfree(sshdr); retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0; sdp->changed = 0; + scsi_disk_put(sdkp); return retval; } -- cgit v1.2.3 From 7ebd67e0dece0ec53e5541fc600eda4e050fab72 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 12 May 2016 23:37:38 +0300 Subject: mpt3sas: add missing curly braces There are some missing curly braces on this if statement, so we end up printing when we shouldn't. Fixes: a470a51cd648 ('mpt3sas: Handle active cable exception event') Signed-off-by: Dan Carpenter Acked-by: Chaitra P B Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 6a4df5a315e9..6bff13e7afc7 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -7975,13 +7975,14 @@ mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index, ActiveCableEventData = (Mpi26EventDataActiveCableExcept_t *) mpi_reply->EventData; if (ActiveCableEventData->ReasonCode == - MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER) + MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER) { pr_info(MPT3SAS_FMT "Currently an active cable with ReceptacleID %d", ioc->name, ActiveCableEventData->ReceptacleID); pr_info("cannot be powered and devices connected to this active cable"); pr_info("will not be seen. This active cable"); pr_info("requires %d mW of power", ActiveCableEventData->ActiveCablePowerRequirement); + } break; default: /* ignore the rest */ -- cgit v1.2.3 From 787ab6e97024926f38773287d9f98a9b330bce23 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 18 May 2016 10:16:51 +0200 Subject: aacraid: do not activate events on non-SRC adapters Only SRC-based adapters support the AifReqEvent function, so there is no point in trying to activate it on older, non-SRC based adapters. Doing so lead to crashes on older adapters. Signed-off-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Raghava Aditya Renukunta Signed-off-by: Martin K. Petersen --- drivers/scsi/aacraid/aacraid.h | 5 +++++ drivers/scsi/aacraid/linit.c | 11 ++++++----- 2 files changed, 11 insertions(+), 5 deletions(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 8f90d9e77104..969c312de1be 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -620,6 +620,11 @@ struct aac_driver_ident */ #define AAC_QUIRK_SCSI_32 0x0020 +/* + * SRC based adapters support the AifReqEvent functions + */ +#define AAC_QUIRK_SRC 0x0040 + /* * The adapter interface specs all queues to be located in the same * physically contiguous block. The host structure that defines the diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index a943bd230bc2..79871f3519ff 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -236,10 +236,10 @@ static struct aac_driver_ident aac_drivers[] = { { aac_rx_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec Catch All */ { aac_rkt_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec Rocket Catch All */ { aac_nark_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec NEMER/ARK Catch All */ - { aac_src_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec PMC Series 6 (Tupelo) */ - { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec PMC Series 7 (Denali) */ - { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2 }, /* Adaptec PMC Series 8 */ - { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2 } /* Adaptec PMC Series 9 */ + { aac_src_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 6 (Tupelo) */ + { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 7 (Denali) */ + { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 8 */ + { aac_srcv_init, "aacraid", "ADAPTEC ", "RAID ", 2, AAC_QUIRK_SRC } /* Adaptec PMC Series 9 */ }; /** @@ -1299,7 +1299,8 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) else shost->this_id = shost->max_id; - aac_intr_normal(aac, 0, 2, 0, NULL); + if (aac_drivers[index].quirks & AAC_QUIRK_SRC) + aac_intr_normal(aac, 0, 2, 0, NULL); /* * dmb - we may need to move the setting of these parms somewhere else once -- cgit v1.2.3 From fbd83006e3e536fcb103228d2422ea63129ccb03 Mon Sep 17 00:00:00 2001 From: "Ewan D. Milne" Date: Tue, 31 May 2016 09:42:29 -0400 Subject: scsi: Add QEMU CD-ROM to VPD Inquiry Blacklist Linux fails to boot as a guest with a QEMU CD-ROM: [ 4.439488] ata2.00: ATAPI: QEMU CD-ROM, 0.8.2, max UDMA/100 [ 4.443649] ata2.00: configured for MWDMA2 [ 4.450267] scsi 1:0:0:0: CD-ROM QEMU QEMU CD-ROM 0.8. PQ: 0 ANSI: 5 [ 4.464317] ata2.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen [ 4.464319] ata2.00: BMDMA stat 0x5 [ 4.464339] ata2.00: cmd a0/01:00:00:00:01/00:00:00:00:00/a0 tag 0 dma 16640 in [ 4.464339] Inquiry 12 01 00 00 ff 00res 48/20:02:00:24:00/00:00:00:00:00/a0 Emask 0x2 (HSM violation) [ 4.464341] ata2.00: status: { DRDY DRQ } [ 4.465864] ata2: soft resetting link [ 4.625971] ata2.00: configured for MWDMA2 [ 4.628290] ata2: EH complete [ 4.646670] ata2.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen [ 4.646671] ata2.00: BMDMA stat 0x5 [ 4.646683] ata2.00: cmd a0/01:00:00:00:01/00:00:00:00:00/a0 tag 0 dma 16640 in [ 4.646683] Inquiry 12 01 00 00 ff 00res 48/20:02:00:24:00/00:00:00:00:00/a0 Emask 0x2 (HSM violation) [ 4.646685] ata2.00: status: { DRDY DRQ } [ 4.648193] ata2: soft resetting link ... Fix this by suppressing VPD inquiry for this device. Signed-off-by: Ewan D. Milne Reported-by: Jan Stancek Tested-by: Jan Stancek Cc: Reviewed-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_devinfo.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/scsi') diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 3408578b08d6..ff41c310c900 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -230,6 +230,7 @@ static struct { {"PIONEER", "CD-ROM DRM-624X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, {"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC}, {"Promise", "", NULL, BLIST_SPARSELUN}, + {"QEMU", "QEMU CD-ROM", NULL, BLIST_SKIP_VPD_PAGES}, {"QNAP", "iSCSI Storage", NULL, BLIST_MAX_1024}, {"SYNOLOGY", "iSCSI Storage", NULL, BLIST_MAX_1024}, {"QUANTUM", "XP34301", "1071", BLIST_NOTQ}, -- cgit v1.2.3 From 6b7e9cde49691e04314342b7dce90c67ad567fcc Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 12 May 2016 22:17:34 -0400 Subject: sd: Fix rw_max for devices that report an optimal xfer size For historic reasons, io_opt is in bytes and max_sectors in block layer sectors. This interface inconsistency is error prone and should be fixed. But for 4.4--4.7 let's make the unit difference explicit via a wrapper function. Fixes: d0eb20a863ba ("sd: Optimal I/O size is in bytes, not sectors") Cc: stable@vger.kernel.org # 4.4+ Reported-by: Fam Zheng Reviewed-by: Bart Van Assche Reviewed-by: Christoph Hellwig Tested-by: Andrew Patterson Signed-off-by: Martin K. Petersen --- drivers/scsi/sd.c | 8 ++++---- drivers/scsi/sd.h | 5 +++++ 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index f459dff30512..60bff78e9ead 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2867,10 +2867,10 @@ static int sd_revalidate_disk(struct gendisk *disk) if (sdkp->opt_xfer_blocks && sdkp->opt_xfer_blocks <= dev_max && sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS && - sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_SIZE) - rw_max = q->limits.io_opt = - sdkp->opt_xfer_blocks * sdp->sector_size; - else + logical_to_bytes(sdp, sdkp->opt_xfer_blocks) >= PAGE_SIZE) { + q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks); + rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks); + } else rw_max = BLK_DEF_MAX_SECTORS; /* Combine with controller limits */ diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 654630bb7d0e..765a6f1ac1b7 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -151,6 +151,11 @@ static inline sector_t logical_to_sectors(struct scsi_device *sdev, sector_t blo return blocks << (ilog2(sdev->sector_size) - 9); } +static inline unsigned int logical_to_bytes(struct scsi_device *sdev, sector_t blocks) +{ + return blocks * sdev->sector_size; +} + /* * A DIF-capable target device can be formatted with different * protection schemes. Currently 0 through 3 are defined: -- cgit v1.2.3 From 72d8c36ec364c82bf1bf0c64dfa1041cfaf139f7 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Tue, 7 Jun 2016 14:53:56 +0800 Subject: scsi: fix race between simultaneous decrements of ->host_failed sas_ata_strategy_handler() adds the works of the ata error handler to system_unbound_wq. This workqueue asynchronously runs work items, so the ata error handler will be performed concurrently on different CPUs. In this case, ->host_failed will be decreased simultaneously in scsi_eh_finish_cmd() on different CPUs, and become abnormal. It will lead to permanently inequality between ->host_failed and ->host_busy, and scsi error handler thread won't start running. IO errors after that won't be handled. Since all scmds must have been handled in the strategy handler, just remove the decrement in scsi_eh_finish_cmd() and zero ->host_busy after the strategy handler to fix this race. Fixes: 50824d6c5657 ("[SCSI] libsas: async ata-eh") Cc: stable@vger.kernel.org Signed-off-by: Wei Fang Reviewed-by: James Bottomley Signed-off-by: Martin K. Petersen --- Documentation/scsi/scsi_eh.txt | 8 ++++++-- drivers/ata/libata-eh.c | 2 +- drivers/scsi/scsi_error.c | 4 +++- 3 files changed, 10 insertions(+), 4 deletions(-) (limited to 'drivers/scsi') diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt index 8638f61c8c9d..37eca00796ee 100644 --- a/Documentation/scsi/scsi_eh.txt +++ b/Documentation/scsi/scsi_eh.txt @@ -263,19 +263,23 @@ scmd->allowed. 3. scmd recovered ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd - - shost->host_failed-- - clear scmd->eh_eflags - scsi_setup_cmd_retry() - move from local eh_work_q to local eh_done_q LOCKING: none + CONCURRENCY: at most one thread per separate eh_work_q to + keep queue manipulation lockless 4. EH completes ACTION: scsi_eh_flush_done_q() retries scmds or notifies upper - layer of failure. + layer of failure. May be called concurrently but must have + a no more than one thread per separate eh_work_q to + manipulate the queue locklessly - scmd is removed from eh_done_q and scmd->eh_entry is cleared - if retry is necessary, scmd is requeued using scsi_queue_insert() - otherwise, scsi_finish_command() is invoked for scmd + - zero shost->host_failed LOCKING: queue or finish function performs appropriate locking diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 961acc788f44..91a9e6af2ec4 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -606,7 +606,7 @@ void ata_scsi_error(struct Scsi_Host *host) ata_scsi_port_error_handler(host, ap); /* finish or retry handled scmd's and clean up */ - WARN_ON(host->host_failed || !list_empty(&eh_work_q)); + WARN_ON(!list_empty(&eh_work_q)); DPRINTK("EXIT\n"); } diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 984ddcb4786d..1b9c049bd5c5 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1127,7 +1127,6 @@ static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn) */ void scsi_eh_finish_cmd(struct scsi_cmnd *scmd, struct list_head *done_q) { - scmd->device->host->host_failed--; scmd->eh_eflags = 0; list_move_tail(&scmd->eh_entry, done_q); } @@ -2226,6 +2225,9 @@ int scsi_error_handler(void *data) else scsi_unjam_host(shost); + /* All scmds have been handled */ + shost->host_failed = 0; + /* * Note - if the above fails completely, the action is to take * individual devices offline and flush the queue of any -- cgit v1.2.3 From 8beb330044d0d1878c7b92290e91c0b889e92633 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Mon, 13 Jun 2016 22:00:07 -0700 Subject: 53c700: fix BUG on untagged commands The untagged command case in the 53c700 driver has been broken since host wide tags were enabled because the replaced scsi_find_tag() function had a special case for the tag value SCSI_NO_TAG to retrieve sdev->current_cmnd. The replacement function scsi_host_find_tag() has no such special case and returns NULL causing untagged commands to trigger a BUG() in the driver. Inspection shows that the 53c700 is the only driver using this SCSI_NO_TAG case, so a local fix in the driver suffices to fix this problem globally. Fixes: 64d513ac31b - "scsi: use host wide tags by default" Cc: stable@vger.kernel.org # 4.4+ Reported-by: Helge Deller Tested-by: Helge Deller Signed-off-by: James Bottomley Reviewed-by: Johannes Thumshirn Reviewed-by: Ewan D. Milne Acked-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/scsi/53c700.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index d4c285688ce9..3ddc85e6efd6 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -1122,7 +1122,7 @@ process_script_interrupt(__u32 dsps, __u32 dsp, struct scsi_cmnd *SCp, } else { struct scsi_cmnd *SCp; - SCp = scsi_host_find_tag(SDp->host, SCSI_NO_TAG); + SCp = SDp->current_cmnd; if(unlikely(SCp == NULL)) { sdev_printk(KERN_ERR, SDp, "no saved request for untagged cmd\n"); @@ -1826,7 +1826,7 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *) slot->tag, slot); } else { slot->tag = SCSI_NO_TAG; - /* must populate current_cmnd for scsi_host_find_tag to work */ + /* save current command for reselection */ SCp->device->current_cmnd = SCp; } /* sanity check: some of the commands generated by the mid-layer -- cgit v1.2.3