4 messages, 2 authors, 2005-06-01 · open the first message on its own page
From: Jeff Garzik <hidden>
Date: 2005-05-31 15:59:06
I just updated the AHCI PCI MSI support patch to support the latest ->host_stop() semantics changes that just made it into upstream. This patch, until its merged, may always be found in the 'ahci-msi' branch of rsync://rsync.kernel.org/pub/scm/linux/kernel/git/jgarzik/libata-dev.git
From: Jens Axboe <hidden>
Date: 2005-06-01 05:43:58
On Tue, May 31 2005, Jeff Garzik wrote:
I just updated the AHCI PCI MSI support patch to support the latest ->host_stop() semantics changes that just made it into upstream. This patch, until its merged, may always be found in the 'ahci-msi' branch of rsync://rsync.kernel.org/pub/scm/linux/kernel/git/jgarzik/libata-dev.git
Tested on an ich6 based system, with this ahci controller:
centera:~ # lspci -s 0000:00:1f.2 -v
0000:00:1f.2 IDE interface: Intel Corp. I/O Controller Hub SATA cc=raid
(rev 03) (prog-if 8f [Master SecP SecO PriP PriO])
Subsystem: Tyan Computer: Unknown device 5150
Flags: bus master, 66Mhz, medium devsel, latency 0, IRQ 169
I/O ports at e900
I/O ports at ea00 [size=4]
I/O ports at eb00 [size=8]
I/O ports at ec00 [size=4]
I/O ports at ed00 [size=16]
Memory at d03c3000 (32-bit, non-prefetchable) [size=1K]
Capabilities: [70] Power Management version 2
And system boots and works fine, MSI isn't enabled of course.
Also tested on an ich7 based system (945G express chipset), with this
ahci controller:
nelson:~ # lspci -s 0000:00:1f.2 -v
0000:00:1f.2 Class 0106: Intel Corporation I/O Controller Hub SATA
cc=AHCI (rev 01) (prog-if 01)
Subsystem: Intel Corporation: Unknown device e302
Flags: bus master, 66Mhz, medium devsel, latency 0, IRQ 201
I/O ports at 40d8 [size=8]
I/O ports at 40f4 [size=4]
I/O ports at 40d0 [size=8]
I/O ports at 40f0 [size=4]
I/O ports at 4020 [size=32]
Memory at 48304000 (32-bit, non-prefetchable) [size=1K]
Capabilities: [80] Message Signalled Interrupts: 64bit- Queue=0/0 Enable+
Capabilities: [70] Power Management version 2
Capabilities: [a8] #12 [0010]
System boots and works fine (typing this message here), MSI is enabled.
I double checked with an added printk :-)
So that's at least one ACK for you. Now running NCQ and MSI enabled
ahci, I'm not sure SATA gets any better!
--
Jens Axboe
From: Jeff Garzik <hidden>
Date: 2005-06-01 05:46:54
Jens Axboe wrote:
System boots and works fine (typing this message here), MSI is enabled. I double checked with an added printk :-)
Any chance you could post a full /proc/interrupts output for this box?
So that's at least one ACK for you. Now running NCQ and MSI enabled ahci, I'm not sure SATA gets any better!
<grin> Thanks, Jeff
From: Jens Axboe <hidden>
Date: 2005-06-01 05:51:56
On Wed, Jun 01 2005, Jeff Garzik wrote:
Jens Axboe wrote:quoted
System boots and works fine (typing this message here), MSI is enabled. I double checked with an added printk :-)Any chance you could post a full /proc/interrupts output for this box?
Sure:
CPU0 CPU1
0: 349415 330112 IO-APIC-edge timer
4: 10 0 IO-APIC-edge serial
8: 0 0 IO-APIC-edge rtc
9: 0 0 IO-APIC-level acpi
14: 2 0 IO-APIC-edge ide0
169: 0 0 IO-APIC-level uhci_hcd:usb4
177: 2565 0 IO-APIC-level eth0
185: 6932 7195 IO-APIC-level uhci_hcd:usb3
201: 8991 5154 PCI-MSI libata
209: 3 0 IO-APIC-level ehci_hcd:usb1, uhci_hcd:usb2
217: 0 0 IO-APIC-level uhci_hcd:usb5
225: 345 51 IO-APIC-level HDA Intel
NMI: 150 83
LOC: 671016 671636
ERR: 1
MIS: 0
--
Jens Axboe