Skip to contentSkip to conversation

Enable parallel scan on ata_piix

PATCH In review Arjan van de Ven 3 participants 5 messages Apr 24, 2009 libata

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 Enable parallel scan on ata_piix

Hi,

This patch turns on parallel scanning for the ata_piix driver. This driver is used on most netbooks (no AHCI for cheap storage it seems). The scan is the dominating time factor in the kernel boot for these devices; with this flag it gets cut in half for the device I used for testing (eeepc).
Alan took a look at the driver source and concluded that it ought to be safe to do for this driver.

drivers/ata/ata_piix.c +1 -0
index ef8b30d..993f7af 100644
@@ -1563,6 +1563,7 @@ static int __devinit piix_init_one(struct pci_dev *pdev,
 		host->ports[1]->mwdma_mask = 0;
 		host->ports[1]->udma_mask = 0;
 	}
+	host->flags |= ATA_HOST_PARALLEL_SCAN;
 
 	pci_set_master(pdev);
 	return ata_pci_sff_activate_host(host, ata_sff_interrupt, &piix_sht);
Signature · 3 lines
Arjan van de Ven 	Intel Open Source Technology Centre
For development, discussion and tips for power savings, 
visit http://www.lesswatts.org
#1 lore raw
Quoted 11 lines · Arjan van de Ven

Hi,

This patch turns on parallel scanning for the ata_piix driver. This driver is used on most netbooks (no AHCI for cheap storage it seems). The scan is the dominating time factor in the kernel boot for these devices; with this flag it gets cut in half for the device I used for testing (eeepc).
Alan took a look at the driver source and concluded that it ought to be safe to do for this driver.

I tend to doubt "safe", given the complicated and buggy silicon state machine that recreates the legacy IDE interface on SATA...

Jeff

#2 lore raw
Quoted 4 lines
Quoted 1 line

I tend to doubt "safe", given the complicated and buggy silicon state machine that recreates the legacy IDE interface on SATA...

The two channels on the ICH and PIIX are independant. There are other controllers that have all sorts of nasty dependancies and shared state, and there is also a bug/known limitation in the case of simplex hardware
- we don't honour the can queue checks during probing.

Alan

#3 lore raw
Quoted 4 lines · Alan Cox
Quoted 2 lines
Quoted 1 line

I tend to doubt "safe", given the complicated and buggy silicon state machine that recreates the legacy IDE interface on SATA...

The two channels on the ICH and PIIX are independant. There are other

Starting with ICH5, not true. Think PATA/SATA combined mode...

Jeff

#4 lore raw
Quoted 8 lines · On Fri, 24 Apr 2009 07:33:46 -0400 Jeff Garzik <[email protected]> wrote:
Quoted 5 lines · Alan Cox
Quoted 3 lines
Quoted 1 line

I tend to doubt "safe", given the complicated and buggy silicon state machine that recreates the legacy IDE interface on SATA...

The two channels on the ICH and PIIX are independant. There are other

Starting with ICH5, not true. Think PATA/SATA combined mode...

The register sets as presented to us are independent, and there are no interactions on our side. Wecould be extra paranoid about this but testing says it works, code inspection says it works and there is nothing in the chip docs or errata saying don't do it.

So at this point I don't think assuming the worst case is actually useful because its only by trying this that we are going to find out if there are any corner cases.

Alan