Darrick J. Wong ba330ffebb [SCSI] aic94xx: Don't call pci_map_sg for already-mapped scatterlists
It turns out that libata has already dma_map_sg'd the scatterlist
entries that go with an ata_queued_cmd by the time it calls
sas_ata_qc_issue.  sas_ata_qc_issue passes this scatterlist to aic94xx.
Unfortunately, aic94xx assumes that any scatterlist passed to it needs
to be pci_map_sg'd... which blows away the mapping that libata created!
This causes (on a x260) Calgary IOMMU table leaks and duplicate frees
when aic94xx and libata try to {pci,dma}_unmap_sg the scatterlist.

Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>

Key this check off ATA_PROTOCOL_STP

Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
2007-07-18 11:14:47 -05:00
..
2007-04-01 10:10:04 -05:00
2006-09-12 17:12:31 -05:00
2006-09-12 17:12:31 -05:00
2007-06-19 19:53:35 -07:00
2007-05-27 15:05:10 -05:00
2007-05-06 09:33:11 -05:00
2007-05-31 17:30:04 -04:00
2006-08-06 15:59:26 -05:00
2006-11-15 16:41:27 -06:00
2006-09-12 17:12:31 -05:00
2006-11-22 14:57:56 +00:00
2007-05-24 09:14:41 -05:00
2007-05-31 17:30:04 -04:00
2007-07-16 09:05:42 -07:00
2006-09-12 17:12:31 -05:00
2006-11-30 05:24:39 +01:00
2007-05-24 09:13:25 -05:00
2007-01-27 09:28:58 -06:00
2007-04-17 18:15:04 -04:00
2007-02-09 09:14:07 -08:00
2007-01-03 16:57:38 -06:00
2007-05-28 09:08:32 -05:00
2007-07-14 19:12:15 -05:00
2006-03-23 07:38:09 -08:00
2007-05-31 17:30:04 -04:00
2006-11-15 16:43:50 -06:00
2007-06-19 19:53:35 -07:00