linux-kernel - Re: 2.6.24.X: SATA/AHCI related boot delay.

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Mon, 10 Mar 2008 22:05:18 +0900
From:	Tejun Heo <htejun@...il.com>
To:	Volker Armin Hemmann <volker.armin.hemmann@...clausthal.de>
CC:	linux-kernel@...r.kernel.org, linux-ide@...r.kernel.org
Subject: Re: 2.6.24.X: SATA/AHCI related boot delay.

Volker Armin Hemmann wrote:
> Hi,
> 
> I have an Alive -NF5-esata2+. AM2 board with dual core AMD64 cpu.
> 
> Problem exists with latest bios 1.90 and its predecessor 1.80.
> 
> This board with nforce 520 chipset (MCP65) has three possible settings for the 
> sata controller:
> non-raid
> raid
> ahci.
> 
> My default is non-raid.
> 
> With 2.6.24 based kernels I get this on cold boot:
> 
> [   50.808824] ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
> [   80.743754] ata1.00: qc timeout (cmd 0xec)
> [   80.743792] ata1.00: failed to IDENTIFY (I/O error, err_mask=0x4)

Does "irqpoll" make any difference?  Also, does the attached patch help?

> and this on reboots:
> 
> [   36.619135] ata1: port is slow to respond, please be patient (Status 0xd0)
> [   40.982984] ata1: softreset failed (device not ready)

Is this consistent?  Do you always get IDENTIFY timeout on cold boots
and softreset failure on reboots?

> with 2.6.23.11 it looks like this:

Hmmm...

> I removed the pata-disk and the drivers some days ago - but that has had no 
> influence on the problem. The delay was there with the pata-drive and drivers 
> too. There are some changes in the config - but even with the 2.6.3.11 config 
> on a 2.6.24 and make oldconfig showed the delays.
> 
> If I change from 'non raid' to AHCI (because the handbook says that is the way 
> to get NCQ working) boot hangs for looong time and no harddisks are found:
> (dmesg from systemrescuecd 1.0)
> ahci 0000:00:0a.0: version 3.0
> ACPI: PCI Interrupt Link [LSA0] enabled at IRQ 23
> ACPI: PCI Interrupt 0000:00:0a.0[A] -> Link [LSA0] -> GSI 23 (level, low) -> 
> IRQ 18
> ahci 0000:00:0a.0: AHCI 0001.0100 32 slots 4 ports 3 Gbps 0xf impl SATA mode
> ahci 0000:00:0a.0: flags: 64bit sntf led clo pmp pio 
> PCI: Setting latency timer of device 0000:00:0a.0 to 64
> scsi3 : ahci
> scsi4 : ahci
> scsi5 : ahci
> scsi6 : ahci
> ata1: SATA max UDMA/133 abar m8192@...9dfc000 port 0xf9dfc100 irq 218
> ata2: SATA max UDMA/133 abar m8192@...9dfc000 port 0xf9dfc180 irq 218
> ata3: SATA max UDMA/133 abar m8192@...9dfc000 port 0xf9dfc200 irq 218
> ata4: SATA max UDMA/133 abar m8192@...9dfc000 port 0xf9dfc280 irq 218
> ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
> APIC error on CPU0: 00(40)
> scsi_scan_2 used greatest stack depth: 2868 bytes left
> ata1.00: qc timeout (cmd 0xec)
> ata1.00: failed to IDENTIFY (I/O error, err_mask=0x4)
> ata1: failed to recover some devices, retrying in 5 secs

This one definitely looks like a misrouted IRQ.  irqpoll should help.
This failure is the same for 2.6.23 and 24, right?

-- 
tejun

View attachment "debug" of type "text/plain" (507 bytes)