From d09556e9407d6e8a29c92a5c16ad32df9996400b Mon Sep 17 00:00:00 2001 From: Chris Wright Date: Fri, 2 Apr 2010 18:27:52 -0700 Subject: [PATCH] x86/amd-iommu: enable iommu before attaching devices commit 75f66533bc883f761a7adcab3281fe3323efbc90 upstream. Hit another kdump problem as reported by Neil Horman. When initializaing the IOMMU, we attach devices to their domains before the IOMMU is fully (re)initialized. Attaching a device will issue some important invalidations. In the context of the newly kexec'd kdump kernel, the IOMMU may have stale cached data from the original kernel. Because we do the attach too early, the invalidation commands are placed in the new command buffer before the IOMMU is updated w/ that buffer. This leaves the stale entries in the kdump context and can renders device unusable. Simply enable the IOMMU before we do the attach. Cc: Neil Horman Cc: Vivek Goyal Signed-off-by: Chris Wright Signed-off-by: Joerg Roedel Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/amd_iommu_init.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 362ab88c73ac..3925adfba765 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -1284,6 +1284,8 @@ int __init amd_iommu_init(void) if (ret) goto free; + enable_iommus(); + if (iommu_pass_through) ret = amd_iommu_init_passthrough(); else @@ -1294,8 +1296,6 @@ int __init amd_iommu_init(void) amd_iommu_init_api(); - enable_iommus(); - if (iommu_pass_through) goto out; @@ -1314,6 +1314,8 @@ out: return ret; free: + disable_iommus(); + free_pages((unsigned long)amd_iommu_pd_alloc_bitmap, get_order(MAX_DOMAIN_ID/8)); -- 2.34.1