[IA64] Add Variable Page Size and IA64 Support in Intel IOMMU

The patch contains Intel IOMMU IA64 specific code. It defines new
machvec dig_vtd, hooks for IOMMU, DMAR table detection, cache line flush
function, etc.

For a generic kernel with CONFIG_DMAR=y, if Intel IOMMU is detected,
dig_vtd is used for machinve vector. Otherwise, kernel falls back to
dig machine vector. Kernel parameter "machvec=dig" or "intel_iommu=off"
can be used to force kernel to boot dig machine vector.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

9 files changed, 171 insertions, 0 deletions

diff --git a/arch/ia64/include/asm/cacheflush.h b/arch/ia64/include/asm/cacheflush.h
index afcfbda76e2..c8ce2719fee 100644
--- a/arch/ia64/include/asm/cacheflush.h
+++ b/arch/ia64/include/asm/cacheflush.h
@@ -34,6 +34,8 @@ do {						\
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
 extern void flush_icache_range (unsigned long start, unsigned long end);
+extern void clflush_cache_range(void *addr, int size);
+
 
 #define flush_icache_user_range(vma, page, user_addr, len)					\
 do {												\
diff --git a/arch/ia64/include/asm/device.h b/arch/ia64/include/asm/device.h
index 3db6daf7f25..41ab85d66f3 100644
--- a/arch/ia64/include/asm/device.h
+++ b/arch/ia64/include/asm/device.h
@@ -10,6 +10,9 @@ struct dev_archdata {
 #ifdef CONFIG_ACPI
 	void	*acpi_handle;
 #endif
+#ifdef CONFIG_DMAR
+	void *iommu; /* hook for IOMMU specific extension */
+#endif
 };
 
 #endif /* _ASM_IA64_DEVICE_H */
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 06ff1ba2146..bbab7e2b0fc 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -7,6 +7,49 @@
  */
 #include <asm/machvec.h>
 #include <linux/scatterlist.h>
+#include <asm/swiotlb.h>
+
+struct dma_mapping_ops {
+	int             (*mapping_error)(struct device *dev,
+					 dma_addr_t dma_addr);
+	void*           (*alloc_coherent)(struct device *dev, size_t size,
+				dma_addr_t *dma_handle, gfp_t gfp);
+	void            (*free_coherent)(struct device *dev, size_t size,
+				void *vaddr, dma_addr_t dma_handle);
+	dma_addr_t      (*map_single)(struct device *hwdev, unsigned long ptr,
+				size_t size, int direction);
+	void            (*unmap_single)(struct device *dev, dma_addr_t addr,
+				size_t size, int direction);
+	void            (*sync_single_for_cpu)(struct device *hwdev,
+				dma_addr_t dma_handle, size_t size,
+				int direction);
+	void            (*sync_single_for_device)(struct device *hwdev,
+				dma_addr_t dma_handle, size_t size,
+				int direction);
+	void            (*sync_single_range_for_cpu)(struct device *hwdev,
+				dma_addr_t dma_handle, unsigned long offset,
+				size_t size, int direction);
+	void            (*sync_single_range_for_device)(struct device *hwdev,
+				dma_addr_t dma_handle, unsigned long offset,
+				size_t size, int direction);
+	void            (*sync_sg_for_cpu)(struct device *hwdev,
+				struct scatterlist *sg, int nelems,
+				int direction);
+	void            (*sync_sg_for_device)(struct device *hwdev,
+				struct scatterlist *sg, int nelems,
+				int direction);
+	int             (*map_sg)(struct device *hwdev, struct scatterlist *sg,
+				int nents, int direction);
+	void            (*unmap_sg)(struct device *hwdev,
+				struct scatterlist *sg, int nents,
+				int direction);
+	int             (*dma_supported_op)(struct device *hwdev, u64 mask);
+	int		is_phys;
+};
+
+extern struct dma_mapping_ops *dma_ops;
+extern struct ia64_machine_vector ia64_mv;
+extern void set_iommu_machvec(void);
 
 #define dma_alloc_coherent(dev, size, handle, gfp)	\
 	platform_dma_alloc_coherent(dev, size, handle, (gfp) | GFP_DMA)
@@ -96,4 +139,11 @@ dma_cache_sync (struct device *dev, void *vaddr, size_t size,
 
 #define dma_is_consistent(d, h)	(1)	/* all we do is coherent memory... */
 
+static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
+{
+	return dma_ops;
+}
+
+
+
 #endif /* _ASM_IA64_DMA_MAPPING_H */
diff --git a/arch/ia64/include/asm/iommu.h b/arch/ia64/include/asm/iommu.h
new file mode 100644
index 00000000000..5fb2bb93de3
--- /dev/null
+++ b/arch/ia64/include/asm/iommu.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_IA64_IOMMU_H
+#define _ASM_IA64_IOMMU_H 1
+
+#define cpu_has_x2apic 0
+/* 10 seconds */
+#define DMAR_OPERATION_TIMEOUT (((cycles_t) local_cpu_data->itc_freq)*10)
+
+extern void pci_iommu_shutdown(void);
+extern void no_iommu_init(void);
+extern int force_iommu, no_iommu;
+extern int iommu_detected;
+extern void iommu_dma_init(void);
+extern void machvec_init(const char *name);
+extern int forbid_dac;
+
+#endif
diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h
index 2b850ccafef..ce9b1d05083 100644
--- a/arch/ia64/include/asm/machvec.h
+++ b/arch/ia64/include/asm/machvec.h
@@ -120,6 +120,8 @@ extern void machvec_tlb_migrate_finish (struct mm_struct *);
 #  include <asm/machvec_hpsim.h>
 # elif defined (CONFIG_IA64_DIG)
 #  include <asm/machvec_dig.h>
+# elif defined(CONFIG_IA64_DIG_VTD)
+#  include <asm/machvec_dig_vtd.h>
 # elif defined (CONFIG_IA64_HP_ZX1)
 #  include <asm/machvec_hpzx1.h>
 # elif defined (CONFIG_IA64_HP_ZX1_SWIOTLB)
diff --git a/arch/ia64/include/asm/machvec_dig_vtd.h b/arch/ia64/include/asm/machvec_dig_vtd.h
new file mode 100644
index 00000000000..3400b561e71
--- /dev/null
+++ b/arch/ia64/include/asm/machvec_dig_vtd.h
@@ -0,0 +1,38 @@
+#ifndef _ASM_IA64_MACHVEC_DIG_VTD_h
+#define _ASM_IA64_MACHVEC_DIG_VTD_h
+
+extern ia64_mv_setup_t			dig_setup;
+extern ia64_mv_dma_alloc_coherent	vtd_alloc_coherent;
+extern ia64_mv_dma_free_coherent	vtd_free_coherent;
+extern ia64_mv_dma_map_single_attrs	vtd_map_single_attrs;
+extern ia64_mv_dma_unmap_single_attrs	vtd_unmap_single_attrs;
+extern ia64_mv_dma_map_sg_attrs		vtd_map_sg_attrs;
+extern ia64_mv_dma_unmap_sg_attrs	vtd_unmap_sg_attrs;
+extern ia64_mv_dma_supported		iommu_dma_supported;
+extern ia64_mv_dma_mapping_error	vtd_dma_mapping_error;
+extern ia64_mv_dma_init			pci_iommu_alloc;
+
+/*
+ * This stuff has dual use!
+ *
+ * For a generic kernel, the macros are used to initialize the
+ * platform's machvec structure.  When compiling a non-generic kernel,
+ * the macros are used directly.
+ */
+#define platform_name				"dig_vtd"
+#define platform_setup				dig_setup
+#define platform_dma_init			pci_iommu_alloc
+#define platform_dma_alloc_coherent		vtd_alloc_coherent
+#define platform_dma_free_coherent		vtd_free_coherent
+#define platform_dma_map_single_attrs		vtd_map_single_attrs
+#define platform_dma_unmap_single_attrs		vtd_unmap_single_attrs
+#define platform_dma_map_sg_attrs		vtd_map_sg_attrs
+#define platform_dma_unmap_sg_attrs		vtd_unmap_sg_attrs
+#define platform_dma_sync_single_for_cpu	machvec_dma_sync_single
+#define platform_dma_sync_sg_for_cpu		machvec_dma_sync_sg
+#define platform_dma_sync_single_for_device	machvec_dma_sync_single
+#define platform_dma_sync_sg_for_device		machvec_dma_sync_sg
+#define platform_dma_supported			iommu_dma_supported
+#define platform_dma_mapping_error		vtd_dma_mapping_error
+
+#endif /* _ASM_IA64_MACHVEC_DIG_VTD_h */
diff --git a/arch/ia64/include/asm/machvec_init.h b/arch/ia64/include/asm/machvec_init.h
index 7f21249fba3..ef964b28684 100644
--- a/arch/ia64/include/asm/machvec_init.h
+++ b/arch/ia64/include/asm/machvec_init.h
@@ -1,3 +1,4 @@
+#include <asm/iommu.h>
 #include <asm/machvec.h>
 
 extern ia64_mv_send_ipi_t ia64_send_ipi;
diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h
index 0149097b736..645ef06ddaa 100644
--- a/arch/ia64/include/asm/pci.h
+++ b/arch/ia64/include/asm/pci.h
@@ -164,4 +164,7 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 	return channel ? isa_irq_to_vector(15) : isa_irq_to_vector(14);
 }
 
+#ifdef CONFIG_DMAR
+extern void pci_iommu_alloc(void);
+#endif
 #endif /* _ASM_IA64_PCI_H */
diff --git a/arch/ia64/include/asm/swiotlb.h b/arch/ia64/include/asm/swiotlb.h
new file mode 100644
index 00000000000..fb79423834d
--- /dev/null
+++ b/arch/ia64/include/asm/swiotlb.h
@@ -0,0 +1,56 @@
+#ifndef ASM_IA64__SWIOTLB_H
+#define ASM_IA64__SWIOTLB_H
+
+#include <linux/dma-mapping.h>
+
+/* SWIOTLB interface */
+
+extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr,
+				     size_t size, int dir);
+extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flags);
+extern void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+				 size_t size, int dir);
+extern void swiotlb_sync_single_for_cpu(struct device *hwdev,
+					dma_addr_t dev_addr,
+					size_t size, int dir);
+extern void swiotlb_sync_single_for_device(struct device *hwdev,
+					   dma_addr_t dev_addr,
+					   size_t size, int dir);
+extern void swiotlb_sync_single_range_for_cpu(struct device *hwdev,
+					      dma_addr_t dev_addr,
+					      unsigned long offset,
+					      size_t size, int dir);
+extern void swiotlb_sync_single_range_for_device(struct device *hwdev,
+						 dma_addr_t dev_addr,
+						 unsigned long offset,
+						 size_t size, int dir);
+extern void swiotlb_sync_sg_for_cpu(struct device *hwdev,
+				    struct scatterlist *sg, int nelems,
+				    int dir);
+extern void swiotlb_sync_sg_for_device(struct device *hwdev,
+				       struct scatterlist *sg, int nelems,
+				       int dir);
+extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg,
+			  int nents, int direction);
+extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg,
+			     int nents, int direction);
+extern int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr);
+extern void swiotlb_free_coherent(struct device *hwdev, size_t size,
+				  void *vaddr, dma_addr_t dma_handle);
+extern int swiotlb_dma_supported(struct device *hwdev, u64 mask);
+extern void swiotlb_init(void);
+
+extern int swiotlb_force;
+
+#ifdef CONFIG_SWIOTLB
+extern int swiotlb;
+extern void pci_swiotlb_init(void);
+#else
+#define swiotlb 0
+static inline void pci_swiotlb_init(void)
+{
+}
+#endif
+
+#endif /* ASM_IA64__SWIOTLB_H */