[PATCH 3/4] Revert "x86: disable IOMMUs on kernel crash"

[Eric W. Biederman]

Joerg Roedel <joro at 8bytes.org> writes:

> On Fri, Apr 02, 2010 at 06:27:54PM -0700, Chris Wright wrote:
>> This effectively reverts commit 61d047be99757fd9b0af900d7abce9a13a337488.
>> 
>> Disabling the IOMMU can potetially allow DMA transactions to
>> complete without being translated.  Leave it enabled, and allow
>> crash kernel to do the IOMMU reinitialization properly.
>> 
>> Cc: Joerg Roedel <joerg.roedel at amd.com>
>> Cc: Eric Biederman <ebiederm at xmission.com>
>> Cc: Neil Horman <nhorman at tuxdriver.com>
>> Cc: Vivek Goyal <vgoyal at redhat.com>
>> Signed-off-by: Chris Wright <chrisw at sous-sol.org>
>> ---
>>  arch/x86/kernel/crash.c |    6 ------
>>  1 file changed, 6 deletions(-)
>> 
>> --- a/arch/x86/kernel/crash.c
>> +++ b/arch/x86/kernel/crash.c
>> @@ -27,7 +27,6 @@
>>  #include <asm/cpu.h>
>>  #include <asm/reboot.h>
>>  #include <asm/virtext.h>
>> -#include <asm/x86_init.h>
>>  
>>  #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
>>  
>> @@ -103,10 +102,5 @@ void native_machine_crash_shutdown(struc
>>  #ifdef CONFIG_HPET_TIMER
>>  	hpet_disable();
>>  #endif
>> -
>> -#ifdef CONFIG_X86_64
>> -	x86_platform.iommu_shutdown();
>> -#endif
>> -
>>  	crash_save_cpu(regs, safe_smp_processor_id());
>
> Hmm, I think for this we need to change the gart code too and disable
> the gart before its initialization runs to not re-introduce issues fixed
> in commit bc2cea6a34fdb30f118ec75db39a46a191870607, no?

That is a different code path with a different set of assumptions and
restrictions.  On a normal kexec of course we want to do an orderly shutdown.

For the gart with a little luck we can just ignore it on kexec on
panic.  Unlike a virtualization capable iommu it doesn't prevent access
to devices, when it is enabled.   Worst case is that we have to start
including iommu=off for gart systems. The best case is that we can
figure out how to have the gart code reinitialize itself sanely,
starting from some arbitrary point.

machine_crash_shutdown is about doing those things that we can not do
in any other way.

Eric