Re: [libata/sata_sil] Error on startup

[Tejun Heo <tj@kernel.org>]

Hello,

Alex Gonzalez wrote:
> :<6> sda:0:msdos_partition: sector_size=1
> 0:read_dev_sector: mapping = 87946cac
> 0:__read_cache_page:cached_page=83a15580
> 0:read_cache_page: page=83a15580
> 0:lock_page
> 0:sync_page on mm/filemap.c
> 0:block_sync_page
> 0:blk_run_backing_dev()
> 0:blk_backing_dev_unplug()
> 0:scsi_request_fn
> 0:scsi_dispatch_cmd
> 0:ata_scsi_queuecmd
> 0:ata_scsi_translate
> 0:***ata_qc_prep***
> 0:***ata_check_status***
> 0:***ata_std_dev_select***
> 0:***ata_check_status***
> 0:***ata_check_status***
> 0:***ata_tf_load
> 0:***ata_bmdma_setup***
> 0:***ata_exec_command***
> 0:***ata_bmdma_start***
> 0:Dispatched cmd 8b64eba0 with rth 0
> 
> <PAUSE>
> 
> 0:***sil_freeze()***
> 0:***ata_bmdma_error_handler***

This is libata error handling kicking in after detecting command
timeout.

> 0:***ata_bmdma_status***
> 0:***ata_bmdma_stop***

And EH tries to stop the bmdma engine.

> *********************************************
> cpu_0 received a bus/cache error
> *********************************************
> Bridge: Phys Addr = 0x0000000000, Device_AERR = 0x00000000
> Bridge: The devices reporting AERR are:
> CPU: (XLR specific) Cache Error log = 0x0000007800004601, Phy Addr =
> 0x00f0000088
> CPU: epc = 0x83435dfc, errorepc = 0x835bf054, cacheerr = 0x00000000
> Can not handle bus/cache error - Halting cpu

Which triggers bus/cache error.  Hmmm... When the booting works, does
the drive keep working after boot?  ie. if you put the drive under
stress test, does the system survive.  Also, error handling shouldn't
trigger bus/cache error.  Do you know what the bus/cache error means?

Thanks.

-- 
tejun