From 338b131a3269881c7431234855c93c219b0979b6 Mon Sep 17 00:00:00 2001 From: "sreekanth.reddy@lsi.com" Date: Tue, 17 Jul 2012 15:57:05 +0530 Subject: [SCSI] mpt2sas: Fix for Driver oops, when loading driver with max_queue_depth command line option to a very small value If the specified max_queue_depth setting is less than the expected number of internal commands, then driver will calculate the queue depth size to a negitive number. This negitive number is actually a very large number because variable is unsigned 16bit integer. So, the driver will ask for a very large amount of memory for message frames and resulting into oops as memory allocation routines will not able to handle such a large request. So, in order to limit this kind of oops, The driver need to set the max_queue_depth to a scsi mid layer's can_queue value. Then the overall message frames required for IO is minimum of either (max_queue_depth plus internal commands) or the IOC global credits. Signed-off-by: Sreekanth Reddy Cc: Signed-off-by: James Bottomley diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c index 9d46fcb..b25757d 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_base.c +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c @@ -2424,10 +2424,13 @@ _base_allocate_memory_pools(struct MPT2SAS_ADAPTER *ioc, int sleep_flag) } /* command line tunables for max controller queue depth */ - if (max_queue_depth != -1) - max_request_credit = (max_queue_depth < facts->RequestCredit) - ? max_queue_depth : facts->RequestCredit; - else + if (max_queue_depth != -1 && max_queue_depth != 0) { + max_request_credit = min_t(u16, max_queue_depth + + ioc->hi_priority_depth + ioc->internal_depth, + facts->RequestCredit); + if (max_request_credit > MAX_HBA_QUEUE_DEPTH) + max_request_credit = MAX_HBA_QUEUE_DEPTH; + } else max_request_credit = min_t(u16, facts->RequestCredit, MAX_HBA_QUEUE_DEPTH); @@ -2502,7 +2505,7 @@ _base_allocate_memory_pools(struct MPT2SAS_ADAPTER *ioc, int sleep_flag) /* set the scsi host can_queue depth * with some internal commands that could be outstanding */ - ioc->shost->can_queue = ioc->scsiio_depth - (2); + ioc->shost->can_queue = ioc->scsiio_depth; dinitprintk(ioc, printk(MPT2SAS_INFO_FMT "scsi host: " "can_queue depth (%d)\n", ioc->name, ioc->shost->can_queue)); -- cgit v0.10.2 From bd8d6dd43a77bfd2b8fef5b094b9d6095e169dee Mon Sep 17 00:00:00 2001 From: Kashyap Desai Date: Tue, 17 Jul 2012 18:20:44 -0700 Subject: [SCSI] megaraid_sas: Move poll_aen_lock initializer The following patch moves the poll_aen_lock initializer from megasas_probe_one() to megasas_init(). This prevents a crash when a user loads the driver and tries to issue a poll() system call on the ioctl interface with no adapters present. Signed-off-by: Kashyap Desai Signed-off-by: Adam Radford Cc: Signed-off-by: James Bottomley diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index dc27598..ed38454 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -4066,7 +4066,6 @@ megasas_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) spin_lock_init(&instance->cmd_pool_lock); spin_lock_init(&instance->hba_lock); spin_lock_init(&instance->completion_lock); - spin_lock_init(&poll_aen_lock); mutex_init(&instance->aen_mutex); mutex_init(&instance->reset_mutex); @@ -5392,6 +5391,8 @@ static int __init megasas_init(void) printk(KERN_INFO "megasas: %s %s\n", MEGASAS_VERSION, MEGASAS_EXT_VERSION); + spin_lock_init(&poll_aen_lock); + support_poll_for_event = 2; support_device_change = 1; -- cgit v0.10.2 From 27c419739b67decced4650440829b8d51bef954b Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 31 May 2012 15:05:33 -0400 Subject: [SCSI] scsi_lib: fix scsi_io_completion's SG_IO error propagation The following v3.4-rc1 commit unmasked an existing bug in scsi_io_completion's SG_IO error handling: 47ac56d [SCSI] scsi_error: classify some ILLEGAL_REQUEST sense as a permanent TARGET_ERROR Given that certain ILLEGAL_REQUEST are now properly categorized as TARGET_ERROR the host_byte is being set (before host_byte wasn't ever set for these ILLEGAL_REQUEST). In scsi_io_completion, initialize req->errors with cmd->result _after_ the SG_IO block that calls __scsi_error_from_host_byte (which may modify the host_byte). Before this fix: cdb to send: 12 01 01 00 00 00 ioctl(3, SG_IO, {'S', SG_DXFER_NONE, cmd[6]=[12, 01, 01, 00, 00, 00], mx_sb_len=32, iovec_count=0, dxfer_len=0, timeout=20000, flags=0, status=02, masked_status=01, sb[19]=[70, 00, 05, 00, 00, 00, 00, 0b, 00, 00, 00, 00, 24, 00, 00, 00, 00, 00, 00], host_status=0x10, driver_status=0x8, resid=0, duration=0, info=0x1}) = 0 SCSI Status: Check Condition Sense Information: sense buffer empty After: cdb to send: 12 01 01 00 00 00 ioctl(3, SG_IO, {'S', SG_DXFER_NONE, cmd[6]=[12, 01, 01, 00, 00, 00], mx_sb_len=32, iovec_count=0, dxfer_len=0, timeout=20000, flags=0, status=02, masked_status=01, sb[19]=[70, 00, 05, 00, 00, 00, 00, 0b, 00, 00, 00, 00, 24, 00, 00, 00, 00, 00, 00], host_status=0, driver_status=0x8, resid=0, duration=0, info=0x1}) = 0 SCSI Status: Check Condition Sense Information: Fixed format, current; Sense key: Illegal Request Additional sense: Invalid field in cdb Raw sense data (in hex): 70 00 05 00 00 00 00 0b 00 00 00 00 24 00 00 00 00 00 00 Reported-by: Paolo Bonzini Tested-by: Paolo Bonzini Signed-off-by: Mike Snitzer Reviewed-by: Babu Moger Cc: stable@vger.kernel.org # 3.4 Signed-off-by: James Bottomley diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index ffd7773..faa790f 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -776,7 +776,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) } if (req->cmd_type == REQ_TYPE_BLOCK_PC) { /* SG_IO ioctl from block level */ - req->errors = result; if (result) { if (sense_valid && req->sense) { /* @@ -792,6 +791,10 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) if (!sense_deferred) error = __scsi_error_from_host_byte(cmd, result); } + /* + * __scsi_error_from_host_byte may have reset the host_byte + */ + req->errors = cmd->result; req->resid_len = scsi_get_resid(cmd); -- cgit v0.10.2 From 14216561e164671ce147458653b1fea06a4ada1e Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 25 Jul 2012 23:55:55 +0400 Subject: [SCSI] Fix 'Device not ready' issue on mpt2sas This is a particularly nasty SCSI ATA Translation Layer (SATL) problem. SAT-2 says (section 8.12.2) if the device is in the stopped state as the result of processing a START STOP UNIT command (see 9.11), then the SATL shall terminate the TEST UNIT READY command with CHECK CONDITION status with the sense key set to NOT READY and the additional sense code of LOGICAL UNIT NOT READY, INITIALIZING COMMAND REQUIRED; mpt2sas internal SATL seems to implement this. The result is very confusing standby behaviour (using hdparm -y). If you suspend a drive and then send another command, usually it wakes up. However, if the next command is a TEST UNIT READY, the SATL sees that the drive is suspended and proceeds to follow the SATL rules for this, returning NOT READY to all subsequent commands. This means that the ordering of TEST UNIT READY is crucial: if you send TUR and then a command, you get a NOT READY to both back. If you send a command and then a TUR, you get GOOD status because the preceeding command woke the drive. This bit us badly because commit 85ef06d1d252f6a2e73b678591ab71caad4667bb Author: Tejun Heo Date: Fri Jul 1 16:17:47 2011 +0200 block: flush MEDIA_CHANGE from drivers on close(2) Changed our ordering on TEST UNIT READY commands meaning that SATA drives connected to an mpt2sas now suspend and refuse to wake (because the mpt2sas SATL sees the suspend *before* the drives get awoken by the next ATA command) resulting in lots of failed commands. The standard is completely nuts forcing this inconsistent behaviour, but we have to work around it. The fix for this is twofold: 1. Set the allow_restart flag so we wake the drive when we see it has been suspended 2. Return all TEST UNIT READY status directly to the mid layer without any further error handling which prevents us causing error handling which may offline the device just because of a media check TUR. Reported-by: Matthias Prager Cc: stable@vger.kernel.org Signed-off-by: James Bottomley diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 4a6381c..de2337f 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -42,6 +42,8 @@ #include +static void scsi_eh_done(struct scsi_cmnd *scmd); + #define SENSE_TIMEOUT (10*HZ) /* @@ -241,6 +243,14 @@ static int scsi_check_sense(struct scsi_cmnd *scmd) if (! scsi_command_normalize_sense(scmd, &sshdr)) return FAILED; /* no valid sense data */ + if (scmd->cmnd[0] == TEST_UNIT_READY && scmd->scsi_done != scsi_eh_done) + /* + * nasty: for mid-layer issued TURs, we need to return the + * actual sense data without any recovery attempt. For eh + * issued ones, we need to try to recover and interpret + */ + return SUCCESS; + if (scsi_sense_is_deferred(&sshdr)) return NEEDS_RETRY; diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 56a9379..d947ffc 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -764,6 +764,16 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, sdev->model = (char *) (sdev->inquiry + 16); sdev->rev = (char *) (sdev->inquiry + 32); + if (strncmp(sdev->vendor, "ATA ", 8) == 0) { + /* + * sata emulation layer device. This is a hack to work around + * the SATL power management specifications which state that + * when the SATL detects the device has gone into standby + * mode, it shall respond with NOT READY. + */ + sdev->allow_restart = 1; + } + if (*bflags & BLIST_ISROM) { sdev->type = TYPE_ROM; sdev->removable = 1; -- cgit v0.10.2