diff options
author | Penchala Narasimha Reddy Chilakala, ERS-HCLTech <narasimhareddyc@hcl.in> | 2009-12-21 18:39:27 +0530 |
---|---|---|
committer | James Bottomley <James.Bottomley@suse.de> | 2010-01-17 12:16:17 -0600 |
commit | cacb6dc3d7fea751879a225c15e48228415e6359 (patch) | |
tree | f0d1b3792febab8910274e15f0076053a825e392 /drivers/scsi/aacraid | |
parent | e6622df3bb1a8e1135f4b84928e24d4c6802f6b5 (diff) | |
download | linux-cacb6dc3d7fea751879a225c15e48228415e6359.tar.gz |
[SCSI] aacraid: fix File System going into read-only mode
These particular problems were reported by Cisco and SAP and customers
as well. Cisco reported on RHEL4 U6 and SAP reported on SLES9 SP4 and
SLES10 SP2. We added these fixes on RHEL4 U6 and gave a private build
to IBM and Cisco. Cisco and IBM tested it for more than 15 days and
they reported that they did not see the issue so far. Before the fix,
Cisco used to see the issue within 5 days. We generated a patch for
SLES9 SP4 and SLES10 SP2 and submitted to Novell. Novell applied the
patch and gave a test build to SAP. SAP tested and reported that the
build is working properly.
We also tested in our lab using the tools "dishogsync", which is IO
stress tool and the tool was provided by Cisco.
Issue1: File System going into read-only mode
Root cause: The driver tends to not free the memory (FIB) when the
management request exits prematurely. The accumulation of such
un-freed memory causes the driver to fail to allocate anymore memory
(FIB) and hence return 0x70000 value to the upper layer, which puts
the file system into read only mode.
Fix details: The fix makes sure to free the memory (FIB) even if the
request exits prematurely hence ensuring the driver wouldn't run out
of memory (FIBs).
Issue2: False Raid Alert occurs
When the Physical Drives and Logical drives are reported as deleted or
added, even though there is no change done on the system
Root cause: Driver IOCTLs is signaled with EINTR while waiting on
response from the lower layers. Returning "EINTR" will never initiate
internal retry.
Fix details: The issue was fixed by replacing "EINTR" with
"ERESTARTSYS" for mid-layer retries.
Signed-off-by: Penchala Narasimha Reddy <ServeRAIDDriver@hcl.in>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
Diffstat (limited to 'drivers/scsi/aacraid')
-rw-r--r-- | drivers/scsi/aacraid/aachba.c | 52 | ||||
-rw-r--r-- | drivers/scsi/aacraid/aacraid.h | 5 | ||||
-rw-r--r-- | drivers/scsi/aacraid/commctrl.c | 28 | ||||
-rw-r--r-- | drivers/scsi/aacraid/comminit.c | 6 | ||||
-rw-r--r-- | drivers/scsi/aacraid/commsup.c | 72 | ||||
-rw-r--r-- | drivers/scsi/aacraid/dpcsup.c | 36 |
6 files changed, 154 insertions, 45 deletions
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index 2a889853a106..7e26ebc26661 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -293,7 +293,10 @@ int aac_get_config_status(struct aac_dev *dev, int commit_flag) status = -EINVAL; } } - aac_fib_complete(fibptr); + /* Do not set XferState to zero unless receives a response from F/W */ + if (status >= 0) + aac_fib_complete(fibptr); + /* Send a CT_COMMIT_CONFIG to enable discovery of devices */ if (status >= 0) { if ((aac_commit == 1) || commit_flag) { @@ -310,13 +313,18 @@ int aac_get_config_status(struct aac_dev *dev, int commit_flag) FsaNormal, 1, 1, NULL, NULL); - aac_fib_complete(fibptr); + /* Do not set XferState to zero unless + * receives a response from F/W */ + if (status >= 0) + aac_fib_complete(fibptr); } else if (aac_commit == 0) { printk(KERN_WARNING "aac_get_config_status: Foreign device configurations are being ignored\n"); } } - aac_fib_free(fibptr); + /* FIB should be freed only after getting the response from the F/W */ + if (status != -ERESTARTSYS) + aac_fib_free(fibptr); return status; } @@ -355,7 +363,9 @@ int aac_get_containers(struct aac_dev *dev) maximum_num_containers = le32_to_cpu(dresp->ContainerSwitchEntries); aac_fib_complete(fibptr); } - aac_fib_free(fibptr); + /* FIB should be freed only after getting the response from the F/W */ + if (status != -ERESTARTSYS) + aac_fib_free(fibptr); if (maximum_num_containers < MAXIMUM_NUM_CONTAINERS) maximum_num_containers = MAXIMUM_NUM_CONTAINERS; @@ -1245,8 +1255,12 @@ int aac_get_adapter_info(struct aac_dev* dev) NULL); if (rcode < 0) { - aac_fib_complete(fibptr); - aac_fib_free(fibptr); + /* FIB should be freed only after + * getting the response from the F/W */ + if (rcode != -ERESTARTSYS) { + aac_fib_complete(fibptr); + aac_fib_free(fibptr); + } return rcode; } memcpy(&dev->adapter_info, info, sizeof(*info)); @@ -1270,6 +1284,12 @@ int aac_get_adapter_info(struct aac_dev* dev) if (rcode >= 0) memcpy(&dev->supplement_adapter_info, sinfo, sizeof(*sinfo)); + if (rcode == -ERESTARTSYS) { + fibptr = aac_fib_alloc(dev); + if (!fibptr) + return -ENOMEM; + } + } @@ -1470,9 +1490,11 @@ int aac_get_adapter_info(struct aac_dev* dev) (dev->scsi_host_ptr->sg_tablesize * 8) + 112; } } - - aac_fib_complete(fibptr); - aac_fib_free(fibptr); + /* FIB should be freed only after getting the response from the F/W */ + if (rcode != -ERESTARTSYS) { + aac_fib_complete(fibptr); + aac_fib_free(fibptr); + } return rcode; } @@ -1633,6 +1655,7 @@ static int aac_read(struct scsi_cmnd * scsicmd) * Alocate and initialize a Fib */ if (!(cmd_fibcontext = aac_fib_alloc(dev))) { + printk(KERN_WARNING "aac_read: fib allocation failed\n"); return -1; } @@ -1712,9 +1735,14 @@ static int aac_write(struct scsi_cmnd * scsicmd) * Allocate and initialize a Fib then setup a BlockWrite command */ if (!(cmd_fibcontext = aac_fib_alloc(dev))) { - scsicmd->result = DID_ERROR << 16; - scsicmd->scsi_done(scsicmd); - return 0; + /* FIB temporarily unavailable,not catastrophic failure */ + + /* scsicmd->result = DID_ERROR << 16; + * scsicmd->scsi_done(scsicmd); + * return 0; + */ + printk(KERN_WARNING "aac_write: fib allocation failed\n"); + return -1; } status = aac_adapter_write(cmd_fibcontext, scsicmd, lba, count, fua); diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 83986ed86556..619c02d9c862 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -12,7 +12,7 @@ *----------------------------------------------------------------------------*/ #ifndef AAC_DRIVER_BUILD -# define AAC_DRIVER_BUILD 2461 +# define AAC_DRIVER_BUILD 24702 # define AAC_DRIVER_BRANCH "-ms" #endif #define MAXIMUM_NUM_CONTAINERS 32 @@ -1036,6 +1036,9 @@ struct aac_dev u8 printf_enabled; u8 in_reset; u8 msi; + int management_fib_count; + spinlock_t manage_lock; + }; #define aac_adapter_interrupt(dev) \ diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c index 0391d759dfdb..9c0c91178538 100644 --- a/drivers/scsi/aacraid/commctrl.c +++ b/drivers/scsi/aacraid/commctrl.c @@ -153,7 +153,7 @@ cleanup: fibptr->hw_fib_pa = hw_fib_pa; fibptr->hw_fib_va = hw_fib; } - if (retval != -EINTR) + if (retval != -ERESTARTSYS) aac_fib_free(fibptr); return retval; } @@ -322,7 +322,7 @@ return_fib: } if (f.wait) { if(down_interruptible(&fibctx->wait_sem) < 0) { - status = -EINTR; + status = -ERESTARTSYS; } else { /* Lock again and retry */ spin_lock_irqsave(&dev->fib_lock, flags); @@ -593,10 +593,10 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg) u64 addr; void* p; if (upsg->sg[i].count > - (dev->adapter_info.options & + ((dev->adapter_info.options & AAC_OPT_NEW_COMM) ? (dev->scsi_host_ptr->max_sectors << 9) : - 65536) { + 65536)) { rcode = -EINVAL; goto cleanup; } @@ -645,10 +645,10 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg) u64 addr; void* p; if (usg->sg[i].count > - (dev->adapter_info.options & + ((dev->adapter_info.options & AAC_OPT_NEW_COMM) ? (dev->scsi_host_ptr->max_sectors << 9) : - 65536) { + 65536)) { rcode = -EINVAL; goto cleanup; } @@ -695,10 +695,10 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg) uintptr_t addr; void* p; if (usg->sg[i].count > - (dev->adapter_info.options & + ((dev->adapter_info.options & AAC_OPT_NEW_COMM) ? (dev->scsi_host_ptr->max_sectors << 9) : - 65536) { + 65536)) { rcode = -EINVAL; goto cleanup; } @@ -734,10 +734,10 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg) dma_addr_t addr; void* p; if (upsg->sg[i].count > - (dev->adapter_info.options & + ((dev->adapter_info.options & AAC_OPT_NEW_COMM) ? (dev->scsi_host_ptr->max_sectors << 9) : - 65536) { + 65536)) { rcode = -EINVAL; goto cleanup; } @@ -772,8 +772,8 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg) psg->count = cpu_to_le32(sg_indx+1); status = aac_fib_send(ScsiPortCommand, srbfib, actual_fibsize, FsaNormal, 1, 1, NULL, NULL); } - if (status == -EINTR) { - rcode = -EINTR; + if (status == -ERESTARTSYS) { + rcode = -ERESTARTSYS; goto cleanup; } @@ -810,7 +810,7 @@ cleanup: for(i=0; i <= sg_indx; i++){ kfree(sg_list[i]); } - if (rcode != -EINTR) { + if (rcode != -ERESTARTSYS) { aac_fib_complete(srbfib); aac_fib_free(srbfib); } @@ -848,7 +848,7 @@ int aac_do_ioctl(struct aac_dev * dev, int cmd, void __user *arg) */ status = aac_dev_ioctl(dev, cmd, arg); - if(status != -ENOTTY) + if (status != -ENOTTY) return status; switch (cmd) { diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c index 666d5151d628..a7261486ccd4 100644 --- a/drivers/scsi/aacraid/comminit.c +++ b/drivers/scsi/aacraid/comminit.c @@ -194,7 +194,9 @@ int aac_send_shutdown(struct aac_dev * dev) if (status >= 0) aac_fib_complete(fibctx); - aac_fib_free(fibctx); + /* FIB should be freed only after getting the response from the F/W */ + if (status != -ERESTARTSYS) + aac_fib_free(fibctx); return status; } @@ -304,6 +306,8 @@ struct aac_dev *aac_init_adapter(struct aac_dev *dev) /* * Check the preferred comm settings, defaults from template. */ + dev->management_fib_count = 0; + spin_lock_init(&dev->manage_lock); dev->max_fib_size = sizeof(struct hw_fib); dev->sg_tablesize = host->sg_tablesize = (dev->max_fib_size - sizeof(struct aac_fibhdr) diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index 956261f25181..94d2954d79ae 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -189,7 +189,14 @@ struct fib *aac_fib_alloc(struct aac_dev *dev) void aac_fib_free(struct fib *fibptr) { - unsigned long flags; + unsigned long flags, flagsv; + + spin_lock_irqsave(&fibptr->event_lock, flagsv); + if (fibptr->done == 2) { + spin_unlock_irqrestore(&fibptr->event_lock, flagsv); + return; + } + spin_unlock_irqrestore(&fibptr->event_lock, flagsv); spin_lock_irqsave(&fibptr->dev->fib_lock, flags); if (unlikely(fibptr->flags & FIB_CONTEXT_FLAG_TIMED_OUT)) @@ -390,6 +397,8 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size, struct hw_fib * hw_fib = fibptr->hw_fib_va; unsigned long flags = 0; unsigned long qflags; + unsigned long mflags = 0; + if (!(hw_fib->header.XferState & cpu_to_le32(HostOwned))) return -EBUSY; @@ -471,9 +480,31 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size, if (!dev->queues) return -EBUSY; - if(wait) + if (wait) { + + spin_lock_irqsave(&dev->manage_lock, mflags); + if (dev->management_fib_count >= AAC_NUM_MGT_FIB) { + printk(KERN_INFO "No management Fibs Available:%d\n", + dev->management_fib_count); + spin_unlock_irqrestore(&dev->manage_lock, mflags); + return -EBUSY; + } + dev->management_fib_count++; + spin_unlock_irqrestore(&dev->manage_lock, mflags); spin_lock_irqsave(&fibptr->event_lock, flags); - aac_adapter_deliver(fibptr); + } + + if (aac_adapter_deliver(fibptr) != 0) { + printk(KERN_ERR "aac_fib_send: returned -EBUSY\n"); + if (wait) { + spin_unlock_irqrestore(&fibptr->event_lock, flags); + spin_lock_irqsave(&dev->manage_lock, mflags); + dev->management_fib_count--; + spin_unlock_irqrestore(&dev->manage_lock, mflags); + } + return -EBUSY; + } + /* * If the caller wanted us to wait for response wait now. @@ -516,14 +547,15 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size, udelay(5); } } else if (down_interruptible(&fibptr->event_wait)) { - fibptr->done = 2; - up(&fibptr->event_wait); + /* Do nothing ... satisfy + * down_interruptible must_check */ } + spin_lock_irqsave(&fibptr->event_lock, flags); - if ((fibptr->done == 0) || (fibptr->done == 2)) { + if (fibptr->done == 0) { fibptr->done = 2; /* Tell interrupt we aborted */ spin_unlock_irqrestore(&fibptr->event_lock, flags); - return -EINTR; + return -ERESTARTSYS; } spin_unlock_irqrestore(&fibptr->event_lock, flags); BUG_ON(fibptr->done == 0); @@ -689,6 +721,7 @@ int aac_fib_adapter_complete(struct fib *fibptr, unsigned short size) int aac_fib_complete(struct fib *fibptr) { + unsigned long flags; struct hw_fib * hw_fib = fibptr->hw_fib_va; /* @@ -709,6 +742,13 @@ int aac_fib_complete(struct fib *fibptr) * command is complete that we had sent to the adapter and this * cdb could be reused. */ + spin_lock_irqsave(&fibptr->event_lock, flags); + if (fibptr->done == 2) { + spin_unlock_irqrestore(&fibptr->event_lock, flags); + return 0; + } + spin_unlock_irqrestore(&fibptr->event_lock, flags); + if((hw_fib->header.XferState & cpu_to_le32(SentFromHost)) && (hw_fib->header.XferState & cpu_to_le32(AdapterProcessed))) { @@ -1355,7 +1395,10 @@ int aac_reset_adapter(struct aac_dev * aac, int forced) if (status >= 0) aac_fib_complete(fibctx); - aac_fib_free(fibctx); + /* FIB should be freed only after getting + * the response from the F/W */ + if (status != -ERESTARTSYS) + aac_fib_free(fibctx); } } @@ -1759,6 +1802,7 @@ int aac_command_thread(void *data) struct fib *fibptr; if ((fibptr = aac_fib_alloc(dev))) { + int status; __le32 *info; aac_fib_init(fibptr); @@ -1769,15 +1813,21 @@ int aac_command_thread(void *data) *info = cpu_to_le32(now.tv_sec); - (void)aac_fib_send(SendHostTime, + status = aac_fib_send(SendHostTime, fibptr, sizeof(*info), FsaNormal, 1, 1, NULL, NULL); - aac_fib_complete(fibptr); - aac_fib_free(fibptr); + /* Do not set XferState to zero unless + * receives a response from F/W */ + if (status >= 0) + aac_fib_complete(fibptr); + /* FIB should be freed only after + * getting the response from the F/W */ + if (status != -ERESTARTSYS) + aac_fib_free(fibptr); } difference = (long)(unsigned)update_interval*HZ; } else { diff --git a/drivers/scsi/aacraid/dpcsup.c b/drivers/scsi/aacraid/dpcsup.c index abc9ef5d1b10..9c7408fe8c7d 100644 --- a/drivers/scsi/aacraid/dpcsup.c +++ b/drivers/scsi/aacraid/dpcsup.c @@ -57,9 +57,9 @@ unsigned int aac_response_normal(struct aac_queue * q) struct hw_fib * hwfib; struct fib * fib; int consumed = 0; - unsigned long flags; + unsigned long flags, mflags; - spin_lock_irqsave(q->lock, flags); + spin_lock_irqsave(q->lock, flags); /* * Keep pulling response QEs off the response queue and waking * up the waiters until there are no more QEs. We then return @@ -125,12 +125,21 @@ unsigned int aac_response_normal(struct aac_queue * q) } else { unsigned long flagv; spin_lock_irqsave(&fib->event_lock, flagv); - if (!fib->done) + if (!fib->done) { fib->done = 1; - up(&fib->event_wait); + up(&fib->event_wait); + } spin_unlock_irqrestore(&fib->event_lock, flagv); + + spin_lock_irqsave(&dev->manage_lock, mflags); + dev->management_fib_count--; + spin_unlock_irqrestore(&dev->manage_lock, mflags); + FIB_COUNTER_INCREMENT(aac_config.NormalRecved); if (fib->done == 2) { + spin_lock_irqsave(&fib->event_lock, flagv); + fib->done = 0; + spin_unlock_irqrestore(&fib->event_lock, flagv); aac_fib_complete(fib); aac_fib_free(fib); } @@ -232,6 +241,7 @@ unsigned int aac_command_normal(struct aac_queue *q) unsigned int aac_intr_normal(struct aac_dev * dev, u32 index) { + unsigned long mflags; dprintk((KERN_INFO "aac_intr_normal(%p,%x)\n", dev, index)); if ((index & 0x00000002L)) { struct hw_fib * hw_fib; @@ -320,11 +330,25 @@ unsigned int aac_intr_normal(struct aac_dev * dev, u32 index) unsigned long flagv; dprintk((KERN_INFO "event_wait up\n")); spin_lock_irqsave(&fib->event_lock, flagv); - if (!fib->done) + if (!fib->done) { fib->done = 1; - up(&fib->event_wait); + up(&fib->event_wait); + } spin_unlock_irqrestore(&fib->event_lock, flagv); + + spin_lock_irqsave(&dev->manage_lock, mflags); + dev->management_fib_count--; + spin_unlock_irqrestore(&dev->manage_lock, mflags); + FIB_COUNTER_INCREMENT(aac_config.NormalRecved); + if (fib->done == 2) { + spin_lock_irqsave(&fib->event_lock, flagv); + fib->done = 0; + spin_unlock_irqrestore(&fib->event_lock, flagv); + aac_fib_complete(fib); + aac_fib_free(fib); + } + } return 0; } |