Patch to fix latest kernels issue with FW83
We have root caused the stability problem with latest kernels and FW83 (LION platform). The following patch (based on 2.4.17) fixes the problem. Please let me know if you still see a problem after applying this patch.
Thanks,
Asit
<<patch.FW83>>
include/asm-ia64/spinlock.h Wed Jan 23 15:52:45 2002 renamed from home1/src/linux/include/asm-ia64/spinlock.h Wed Jan 9 19:25:05 2002 +1 -1
@@ -84,7 +84,7 @@ "mov r29 = 1\n" \ ";;\n" \ "1:\n" \ - "ld4.bias r2 = [%0]\n" \ + "ld4 r2 = [%0]\n" \ ";;\n" \ "cmp4.eq p0,p7 = r0,r2\n" \ "(p7) br.cond.spnt.few 1b \n" \
"Mallick, Asit K" <[email protected]> writes:
|> We have root caused the stability problem with latest kernels and FW83 (LION |> platform). The following patch (based on 2.4.17) fixes the problem. Please |> let me know if you still see a problem after applying this patch.
I'm getting an infinite stream of "ia64_log_get: Failed to retrieve SAL error record type 3", rendering the machine useless.
Andreas.
Signature · 4 lines
Andreas Schwab, SuSE Labs, [email protected] SuSE GmbH, Deutschherrnstr. 15-19, D-90429 Nürnberg Key fingerprint = 58CA 54C7 6D53 942B 1756 01D3 44D5 214B 8276 4ED5 "And now for something completely different."
Quoted 3 lines · Asit K
We have root caused the stability problem with latest kernels and FW83 (LION platform). The following patch (based on 2.4.17) fixes the problem.
...
include/asm-ia64/spinlock.h Wed Jan 23 15:52:45 2002 line 87
Quoted 2 lines
include/asm-ia64/spinlock.h Wed Jan 23 15:52:45 2002 renamed from home1/src/linux/include/asm-ia64/spinlock.h Wed Jan 9 19:25:05 2002 +1
-1- "ld4.bias r2 = [%0]\n" \ + "ld4 r2 = [%0]\n" \
Can you elaborate on this a bit? All I know about ld.bias is the statement in section 4.4.6.1 of Vol 1 that
[ld.bias] is a hint to the implementation to acquire exclusive ownership of the line containing the addressed data. The bias hint does not affect program functionality and may be ignored by the implementation.
I can believe the patch is a performance optimization (my intuition is that when the holder writes the lock to release it, the waiter will merely invalidate its shared line, where it previously had to invalidate and copyout its exclusive line), but I don't see how this should improve stability. What am I missing?
Signature · 3 lines
Bjorn Helgaas - [email protected] Linux Systems Operation R&D Hewlett-Packard
This is yet another symptom of running old firmware. To avoid this, turn of "Enable IA-64 Machine Check Abort" under General Setup in your config.
In short, the older firmware releases contain MCA support that is either broken or nonexistent. In this case the firmware is falsely reporting corrected platform errors to the OS, in an endless stream that debilitates the OS if OS MCA reporting is enabled.
Jenna
-----Original Message-----
From: Andreas Schwab [mailto:[email protected]]
Sent: Friday, January 25, 2002 7:12 AM
To: Mallick, Asit K
Cc: [email protected]
Subject: Re: [Linux-ia64] Patch to fix latest kernels issue with FW83
"Mallick, Asit K" <[email protected]> writes:
|> We have root caused the stability problem with latest kernels and FW83 (LION
|> platform). The following patch (based on 2.4.17) fixes the problem. Please
|> let me know if you still see a problem after applying this patch.
I'm getting an infinite stream of "ia64_log_get: Failed to retrieve SAL error record type 3", rendering the machine useless.
Andreas.
--
Andreas Schwab, SuSE Labs, [email protected]
SuSE GmbH, Deutschherrnstr. 15-19, D-90429 Nürnberg
Key fingerprint = 58CA 54C7 6D53 942B 1756 01D3 44D5 214B 8276 4ED5 "And now for something completely different."
_______________________________________________
Linux-IA64 mailing list
[email protected]
http://lists.linuxia64.org/lists/listinfo/linux-ia64
Quoted 17 lines
-----Original Message-----
From: Bjorn Helgaas [mailto:[email protected]]
Sent: Friday, January 25, 2002 8:08 AM
To: Mallick, Asit K; [email protected]
Subject: Re: [Linux-ia64] Patch to fix latest kernels issue with FW83Quoted 1 line · Asit K
We have root caused the stability problem with latest
kernels and FW83
Quoted 2 lines
(LION platform). The following patch (based on 2.4.17) fixes the problem.
...
include/asm-ia64/spinlock.h Wed Jan 23 15:52:45 2002 line 87
Quoted 2 lines
include/asm-ia64/spinlock.h Wed Jan 23 15:52:45 2002 renamed from home1/src/linux/include/asm-ia64/spinlock.h Wed Jan 9 19:25:05 2002 +1
-1- "ld4.bias r2 = [%0]\n" \ + "ld4 r2 = [%0]\n" \
Quoted 8 lines
Can you elaborate on this a bit? All I know about ld.bias is the statement
in section 4.4.6.1 of Vol 1 that[ld.bias] is a hint to the implementation to acquire exclusive ownership of the line containing the addressed data. The bias hint does not affect program functionality and may be ignored by the implementation.
This is correcnt.
Quoted 7 lines
I can believe the patch is a performance optimization (my intuition is that
when the holder writes the lock to release it, the waiter will merely invalidate its shared line, where it previously had to invalidate and copyout its exclusive line), but I don't see how this should improve stability. What am I missing?
FW83 does not have a workaround for a chipset issue (chipset SAC errata#2 in 460GX specification update) that could cause a livelock with ld.bias loops and no modification. The later version of the FWs have the workaround and will not see this problem.
Thanks,
Asit