[PATCH 3/4] Revert "x86: disable IOMMUs on kernel crash"
Joerg Roedel
joro at 8bytes.org
Sat Apr 3 13:22:24 EDT 2010
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?
Joerg
More information about the kexec
mailing list