Intel IOMMU Pass Through Support

The patch adds kernel parameter intel_iommu=pt to set up pass through
mode in context mapping entry. This disables DMAR in linux kernel; but
KVM still runs on VT-d and interrupt remapping still works.

In this mode, kernel uses swiotlb for DMA API functions but other VT-d
functionalities are enabled for KVM. KVM always uses multi level
translation page table in VT-d. By default, pass though mode is disabled
in kernel.

This is useful when people don't want to enable VT-d DMAR in kernel but
still want to use KVM and interrupt remapping for reasons like DMAR
performance concern or debug purpose.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Acked-by: Weidong Han <weidong@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

5 files changed, 11 insertions, 2 deletions

diff --git a/arch/ia64/include/asm/iommu.h b/arch/ia64/include/asm/iommu.h
index 0490794fe4a..37d41ca5645 100644
--- a/arch/ia64/include/asm/iommu.h
+++ b/arch/ia64/include/asm/iommu.h
@@ -9,6 +9,7 @@ extern void pci_iommu_shutdown(void);
 extern void no_iommu_init(void);
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
+extern int iommu_pass_through;
 extern void iommu_dma_init(void);
 extern void machvec_init(const char *name);
 
diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c
index 285aae8431c..223abb13410 100644
--- a/arch/ia64/kernel/pci-swiotlb.c
+++ b/arch/ia64/kernel/pci-swiotlb.c
@@ -46,7 +46,7 @@ void __init swiotlb_dma_init(void)
 
 void __init pci_swiotlb_init(void)
 {
-        if (!iommu_detected) {
+        if (!iommu_detected || iommu_pass_through) {
 #ifdef CONFIG_IA64_GENERIC
                 swiotlb = 1;
                 printk(KERN_INFO "PCI-DMA: Re-initialize machine vector.\n");
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index af326a2975b..fd6d21bbee6 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -6,6 +6,7 @@ extern void no_iommu_init(void);
 extern struct dma_map_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
+extern int iommu_pass_through;
 
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 745579bc825..8cad0d85424 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -160,6 +160,8 @@ again:
         return page_address(page);
 }
 
+extern int iommu_pass_through;
+
 /*
  * See <Documentation/x86_64/boot-options.txt> for the iommu kernel parameter
  * documentation.
@@ -209,6 +211,10 @@ static __init int iommu_setup(char *p)
 #ifdef CONFIG_SWIOTLB
                 if (!strncmp(p, "soft", 4))
                         swiotlb = 1;
+                if (!strncmp(p, "pt", 2)) {
+                        iommu_pass_through = 1;
+                        return 1;
+                }
 #endif
 
                 gart_parse_options(p);
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 221a3853e26..3a0c51e0ba6 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -71,7 +71,8 @@ void __init pci_swiotlb_init(void)
 {
         /* don't initialize swiotlb if iommu=off (no_iommu=1) */
 #ifdef CONFIG_X86_64
-        if (!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN)
+        if ((!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN) ||
+                iommu_pass_through)
                swiotlb = 1;
 #endif
         if (swiotlb_force)