hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[libata] sata_svw: update code comments relating to data corruption 

Signed-off-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
This commit is contained in:
Pavel Machek 2008-06-23 11:01:31 +02:00 committed by Jeff Garzik
parent 18f7ba4c2f
commit ec6add9930
1 changed files with 23 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
drivers/ata/sata_svw.c
View File

@ -253,21 +253,29 @@ static void k2_bmdma_start_mmio(struct ata_queued_cmd *qc)
/* start host DMA transaction */ /* start host DMA transaction */
dmactl = readb(mmio + ATA_DMA_CMD); dmactl = readb(mmio + ATA_DMA_CMD);
writeb(dmactl | ATA_DMA_START, mmio + ATA_DMA_CMD); writeb(dmactl | ATA_DMA_START, mmio + ATA_DMA_CMD);
/* There is a race condition in certain SATA controllers that can /* This works around possible data corruption.
be seen when the r/w command is given to the controller before the
host DMA is started. On a Read command, the controller would initiate On certain SATA controllers that can be seen when the r/w
the command to the drive even before it sees the DMA start. When there command is given to the controller before the host DMA is
are very fast drives connected to the controller, or when the data request started.
hits in the drive cache, there is the possibility that the drive returns a part
or all of the requested data to the controller before the DMA start is issued. On a Read command, the controller would initiate the
In this case, the controller would become confused as to what to do with the data. command to the drive even before it sees the DMA
In the worst case when all the data is returned back to the controller, the start. When there are very fast drives connected to the
controller could hang. In other cases it could return partial data returning controller, or when the data request hits in the drive
in data corruption. This problem has been seen in PPC systems and can also appear cache, there is the possibility that the drive returns a
on an system with very fast disks, where the SATA controller is sitting behind a part or all of the requested data to the controller before
number of bridges, and hence there is significant latency between the r/w command the DMA start is issued. In this case, the controller
and the start command. */ would become confused as to what to do with the data. In
/* issue r/w command if the access is to ATA*/ the worst case when all the data is returned back to the
controller, the controller could hang. In other cases it
could return partial data returning in data
corruption. This problem has been seen in PPC systems and
can also appear on an system with very fast disks, where
the SATA controller is sitting behind a number of bridges,
and hence there is significant latency between the r/w
command and the start command. */
/* issue r/w command if the access is to ATA */
if (qc->tf.protocol == ATA_PROT_DMA) if (qc->tf.protocol == ATA_PROT_DMA)
ap->ops->sff_exec_command(ap, &qc->tf); ap->ops->sff_exec_command(ap, &qc->tf);
} }