iommu/vt-d: Add initial support for PASID tables

Add CONFIG_INTEL_IOMMU_SVM, and allocate PASID tables on supported hardware.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

drivers/iommu/Kconfig

@@ -135,6 +135,14 @@ config INTEL_IOMMU
 	  and include PCI device scope covered by these DMA
 	  remapping devices.
 
+config INTEL_IOMMU_SVM
+	bool "Support for Shared Virtual Memory with Intel IOMMU"
+	depends on INTEL_IOMMU && X86
+	help
+	  Shared Virtual Memory (SVM) provides a facility for devices
+	  to access DMA resources through process address space by
+	  means of a Process Address Space ID (PASID).
+
 config INTEL_IOMMU_DEFAULT_ON
 	def_bool y
 	prompt "Enable Intel DMA Remapping Devices by default"

drivers/iommu/Makefile

@@ -12,6 +12,7 @@ obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
 obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o
+obj-$(CONFIG_INTEL_IOMMU_SVM) += intel-svm.o
 obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
 obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o
 obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o

drivers/iommu/intel-iommu.c

@@ -1680,6 +1680,11 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 
 	/* free context mapping */
 	free_context_table(iommu);
+
+#ifdef CONFIG_INTEL_IOMMU_SVM
+	if (pasid_enabled(iommu))
+		intel_svm_free_pasid_tables(iommu);
+#endif
 }
 
 static struct dmar_domain *alloc_domain(int flags)
@@ -3107,6 +3112,10 @@ static int __init init_dmars(void)
 
 		if (!ecap_pass_through(iommu->ecap))
 			hw_pass_through = 0;
+#ifdef CONFIG_INTEL_IOMMU_SVM
+		if (pasid_enabled(iommu))
+			intel_svm_alloc_pasid_tables(iommu);
+#endif
 	}
 
 	if (iommu_pass_through)
@@ -4122,6 +4131,11 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 	if (ret)
 		goto out;
 
+#ifdef CONFIG_INTEL_IOMMU_SVM
+	if (pasid_enabled(iommu))
+		intel_svm_alloc_pasid_tables(iommu);
+#endif
+
 	if (dmaru->ignored) {
 		/*
 		 * we always have to disable PMRs or DMA may fail on this device

drivers/iommu/intel-svm.c

+/*
+ * Copyright © 2015 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * Authors: David Woodhouse <dwmw2@infradead.org>
+ */
+
+#include <linux/intel-iommu.h>
+
+int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
+{
+	struct page *pages;
+	int order;
+
+	order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT;
+	if (order < 0)
+		order = 0;
+
+	pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
+	if (!pages) {
+		pr_warn("IOMMU: %s: Failed to allocate PASID table\n",
+			iommu->name);
+		return -ENOMEM;
+	}
+	iommu->pasid_table = page_address(pages);
+	pr_info("%s: Allocated order %d PASID table.\n", iommu->name, order);
+
+	if (ecap_dis(iommu->ecap)) {
+		pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
+		if (pages)
+			iommu->pasid_state_table = page_address(pages);
+		else
+			pr_warn("IOMMU: %s: Failed to allocate PASID state table\n",
+				iommu->name);
+	}
+
+	return 0;
+}
+
+int intel_svm_free_pasid_tables(struct intel_iommu *iommu)
+{
+	int order;
+
+	order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT;
+	if (order < 0)
+		order = 0;
+
+	if (iommu->pasid_table) {
+		free_pages((unsigned long)iommu->pasid_table, order);
+		iommu->pasid_table = NULL;
+	}
+	if (iommu->pasid_state_table) {
+		free_pages((unsigned long)iommu->pasid_state_table, order);
+		iommu->pasid_state_table = NULL;
+	}
+	return 0;
+}

include/linux/intel-iommu.h

@@ -325,6 +325,9 @@ enum {
 #define VTD_FLAG_TRANS_PRE_ENABLED	(1 << 0)
 #define VTD_FLAG_IRQ_REMAP_PRE_ENABLED	(1 << 1)
 
+struct pasid_entry;
+struct pasid_state_entry;
+
 struct intel_iommu {
 	void __iomem	*reg; /* Pointer to hardware regs, virtual addr */
 	u64 		reg_phys; /* physical address of hw register set */
@@ -347,6 +350,15 @@ struct intel_iommu {
 	struct root_entry *root_entry; /* virtual address */
 
 	struct iommu_flush flush;
+#endif
+#ifdef CONFIG_INTEL_IOMMU_SVM
+	/* These are large and need to be contiguous, so we allocate just
+	 * one for now. We'll maybe want to rethink that if we truly give
+	 * devices away to userspace processes (e.g. for DPDK) and don't
+	 * want to trust that userspace will use *only* the PASID it was
+	 * told to. But while it's all driver-arbitrated, we're fine. */
+	struct pasid_entry *pasid_table;
+	struct pasid_state_entry *pasid_state_table;
 #endif
 	struct q_inval  *qi;            /* Queued invalidation info */
 	u32 *iommu_state; /* Store iommu states between suspend and resume.*/
@@ -387,6 +399,9 @@ extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);
 
 extern int dmar_ir_support(void);
 
+extern int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu);
+extern int intel_svm_free_pasid_tables(struct intel_iommu *iommu);
+
 extern const struct attribute_group *intel_iommu_groups[];
 
 #endif