x86/ia64: intel-iommu: move to drivers/iommu/

This should ease finding similarities with different platforms,
with the intention of solving problems once in a generic framework
which everyone can use.

Note: to move intel-iommu.c, the declaration of pci_find_upstream_pcie_bridge()
has to move from drivers/pci/pci.h to include/linux/pci.h. This is handled
in this patch, too.

As suggested, also drop DMAR's EXPERIMENTAL tag while we're at it.

Compile-tested on x86_64.

Signed-off-by: Ohad Ben-Cohen <ohad@wizery.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

arch/ia64/Kconfig

@@ -627,27 +627,6 @@ source "drivers/pci/hotplug/Kconfig"
 
 source "drivers/pcmcia/Kconfig"
 
-config DMAR
-        bool "Support for DMA Remapping Devices (EXPERIMENTAL)"
-        depends on IA64_GENERIC && ACPI && EXPERIMENTAL
-	help
-	  DMA remapping (DMAR) devices support enables independent address
-	  translations for Direct Memory Access (DMA) from devices.
-	  These DMA remapping devices are reported via ACPI tables
-	  and include PCI device scope covered by these DMA
-	  remapping devices.
-
-config DMAR_DEFAULT_ON
-	def_bool y
-	prompt "Enable DMA Remapping Devices by default"
-	depends on DMAR
-	help
-	  Selecting this option will enable a DMAR device at boot time if
-	  one is found. If this option is not selected, DMAR support can
-	  be enabled by passing intel_iommu=on to the kernel. It is
-	  recommended you say N here while the DMAR code remains
-	  experimental.
-
 endmenu
 
 endif

arch/x86/Kconfig

@@ -1912,56 +1912,6 @@ config PCI_CNB20LE_QUIRK
 
 	  You should say N unless you know you need this.
 
-config DMAR
-	bool "Support for DMA Remapping Devices (EXPERIMENTAL)"
-	depends on PCI_MSI && ACPI && EXPERIMENTAL
-	select IOMMU_API
-	help
-	  DMA remapping (DMAR) devices support enables independent address
-	  translations for Direct Memory Access (DMA) from devices.
-	  These DMA remapping devices are reported via ACPI tables
-	  and include PCI device scope covered by these DMA
-	  remapping devices.
-
-config DMAR_DEFAULT_ON
-	def_bool y
-	prompt "Enable DMA Remapping Devices by default"
-	depends on DMAR
-	help
-	  Selecting this option will enable a DMAR device at boot time if
-	  one is found. If this option is not selected, DMAR support can
-	  be enabled by passing intel_iommu=on to the kernel. It is
-	  recommended you say N here while the DMAR code remains
-	  experimental.
-
-config DMAR_BROKEN_GFX_WA
-	bool "Workaround broken graphics drivers (going away soon)"
-	depends on DMAR && BROKEN
-	---help---
-	  Current Graphics drivers tend to use physical address
-	  for DMA and avoid using DMA APIs. Setting this config
-	  option permits the IOMMU driver to set a unity map for
-	  all the OS-visible memory. Hence the driver can continue
-	  to use physical addresses for DMA, at least until this
-	  option is removed in the 2.6.32 kernel.
-
-config DMAR_FLOPPY_WA
-	def_bool y
-	depends on DMAR
-	---help---
-	  Floppy disk drivers are known to bypass DMA API calls
-	  thereby failing to work when IOMMU is enabled. This
-	  workaround will setup a 1:1 mapping for the first
-	  16MiB to make floppy (an ISA device) work.
-
-config INTR_REMAP
-	bool "Support for Interrupt Remapping (EXPERIMENTAL)"
-	depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL
-	---help---
-	  Supports Interrupt remapping for IO-APIC and MSI devices.
-	  To use x2apic mode in the CPU's which support x2APIC enhancements or
-	  to support platforms with CPU's having > 8 bit APIC ID, say Y.
-
 source "drivers/pci/pcie/Kconfig"
 
 source "drivers/pci/Kconfig"

drivers/iommu/Kconfig

@@ -46,3 +46,52 @@ config AMD_IOMMU_STATS
 	  statistics about whats happening in the driver and exports that
 	  information to userspace via debugfs.
 	  If unsure, say N.
+
+# Intel IOMMU support
+config DMAR
+	bool "Support for DMA Remapping Devices"
+	depends on PCI_MSI && ACPI && (X86 || IA64_GENERIC)
+	select IOMMU_API
+	help
+	  DMA remapping (DMAR) devices support enables independent address
+	  translations for Direct Memory Access (DMA) from devices.
+	  These DMA remapping devices are reported via ACPI tables
+	  and include PCI device scope covered by these DMA
+	  remapping devices.
+
+config DMAR_DEFAULT_ON
+	def_bool y
+	prompt "Enable DMA Remapping Devices by default"
+	depends on DMAR
+	help
+	  Selecting this option will enable a DMAR device at boot time if
+	  one is found. If this option is not selected, DMAR support can
+	  be enabled by passing intel_iommu=on to the kernel.
+
+config DMAR_BROKEN_GFX_WA
+	bool "Workaround broken graphics drivers (going away soon)"
+	depends on DMAR && BROKEN && X86
+	---help---
+	  Current Graphics drivers tend to use physical address
+	  for DMA and avoid using DMA APIs. Setting this config
+	  option permits the IOMMU driver to set a unity map for
+	  all the OS-visible memory. Hence the driver can continue
+	  to use physical addresses for DMA, at least until this
+	  option is removed in the 2.6.32 kernel.
+
+config DMAR_FLOPPY_WA
+	def_bool y
+	depends on DMAR && X86
+	---help---
+	  Floppy disk drivers are known to bypass DMA API calls
+	  thereby failing to work when IOMMU is enabled. This
+	  workaround will setup a 1:1 mapping for the first
+	  16MiB to make floppy (an ISA device) work.
+
+config INTR_REMAP
+	bool "Support for Interrupt Remapping (EXPERIMENTAL)"
+	depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL
+	---help---
+	  Supports Interrupt remapping for IO-APIC and MSI devices.
+	  To use x2apic mode in the CPU's which support x2APIC enhancements or
+	  to support platforms with CPU's having > 8 bit APIC ID, say Y.

drivers/iommu/Makefile

@@ -1,3 +1,5 @@
 obj-$(CONFIG_IOMMU_API) += iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o
+obj-$(CONFIG_DMAR) += dmar.o iova.o intel-iommu.o
+obj-$(CONFIG_INTR_REMAP) += dmar.o intr_remapping.o

drivers/iommu/intr_remapping.c

@@ -0,0 +1,797 @@
+#include <linux/interrupt.h>
+#include <linux/dmar.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/jiffies.h>
+#include <linux/hpet.h>
+#include <linux/pci.h>
+#include <linux/irq.h>
+#include <asm/io_apic.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <linux/intel-iommu.h>
+#include "intr_remapping.h"
+#include <acpi/acpi.h>
+#include <asm/pci-direct.h>
+
+static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
+static struct hpet_scope ir_hpet[MAX_HPET_TBS];
+static int ir_ioapic_num, ir_hpet_num;
+int intr_remapping_enabled;
+
+static int disable_intremap;
+static int disable_sourceid_checking;
+
+static __init int setup_nointremap(char *str)
+{
+	disable_intremap = 1;
+	return 0;
+}
+early_param("nointremap", setup_nointremap);
+
+static __init int setup_intremap(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strncmp(str, "on", 2))
+		disable_intremap = 0;
+	else if (!strncmp(str, "off", 3))
+		disable_intremap = 1;
+	else if (!strncmp(str, "nosid", 5))
+		disable_sourceid_checking = 1;
+
+	return 0;
+}
+early_param("intremap", setup_intremap);
+
+static DEFINE_SPINLOCK(irq_2_ir_lock);
+
+static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
+{
+	struct irq_cfg *cfg = irq_get_chip_data(irq);
+	return cfg ? &cfg->irq_2_iommu : NULL;
+}
+
+int get_irte(int irq, struct irte *entry)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	unsigned long flags;
+	int index;
+
+	if (!entry || !irq_iommu)
+		return -1;
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+	*entry = *(irq_iommu->iommu->ir_table->base + index);
+
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+	return 0;
+}
+
+int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
+{
+	struct ir_table *table = iommu->ir_table;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	u16 index, start_index;
+	unsigned int mask = 0;
+	unsigned long flags;
+	int i;
+
+	if (!count || !irq_iommu)
+		return -1;
+
+	/*
+	 * start the IRTE search from index 0.
+	 */
+	index = start_index = 0;
+
+	if (count > 1) {
+		count = __roundup_pow_of_two(count);
+		mask = ilog2(count);
+	}
+
+	if (mask > ecap_max_handle_mask(iommu->ecap)) {
+		printk(KERN_ERR
+		       "Requested mask %x exceeds the max invalidation handle"
+		       " mask value %Lx\n", mask,
+		       ecap_max_handle_mask(iommu->ecap));
+		return -1;
+	}
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+	do {
+		for (i = index; i < index + count; i++)
+			if  (table->base[i].present)
+				break;
+		/* empty index found */
+		if (i == index + count)
+			break;
+
+		index = (index + count) % INTR_REMAP_TABLE_ENTRIES;
+
+		if (index == start_index) {
+			spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+			printk(KERN_ERR "can't allocate an IRTE\n");
+			return -1;
+		}
+	} while (1);
+
+	for (i = index; i < index + count; i++)
+		table->base[i].present = 1;
+
+	irq_iommu->iommu = iommu;
+	irq_iommu->irte_index =  index;
+	irq_iommu->sub_handle = 0;
+	irq_iommu->irte_mask = mask;
+
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return index;
+}
+
+static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
+{
+	struct qi_desc desc;
+
+	desc.low = QI_IEC_IIDEX(index) | QI_IEC_TYPE | QI_IEC_IM(mask)
+		   | QI_IEC_SELECTIVE;
+	desc.high = 0;
+
+	return qi_submit_sync(&desc, iommu);
+}
+
+int map_irq_to_irte_handle(int irq, u16 *sub_handle)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	unsigned long flags;
+	int index;
+
+	if (!irq_iommu)
+		return -1;
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+	*sub_handle = irq_iommu->sub_handle;
+	index = irq_iommu->irte_index;
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+	return index;
+}
+
+int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	unsigned long flags;
+
+	if (!irq_iommu)
+		return -1;
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	irq_iommu->iommu = iommu;
+	irq_iommu->irte_index = index;
+	irq_iommu->sub_handle = subhandle;
+	irq_iommu->irte_mask = 0;
+
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return 0;
+}
+
+int modify_irte(int irq, struct irte *irte_modified)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	struct intel_iommu *iommu;
+	unsigned long flags;
+	struct irte *irte;
+	int rc, index;
+
+	if (!irq_iommu)
+		return -1;
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	iommu = irq_iommu->iommu;
+
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+	irte = &iommu->ir_table->base[index];
+
+	set_64bit(&irte->low, irte_modified->low);
+	set_64bit(&irte->high, irte_modified->high);
+	__iommu_flush_cache(iommu, irte, sizeof(*irte));
+
+	rc = qi_flush_iec(iommu, index, 0);
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return rc;
+}
+
+struct intel_iommu *map_hpet_to_ir(u8 hpet_id)
+{
+	int i;
+
+	for (i = 0; i < MAX_HPET_TBS; i++)
+		if (ir_hpet[i].id == hpet_id)
+			return ir_hpet[i].iommu;
+	return NULL;
+}
+
+struct intel_iommu *map_ioapic_to_ir(int apic)
+{
+	int i;
+
+	for (i = 0; i < MAX_IO_APICS; i++)
+		if (ir_ioapic[i].id == apic)
+			return ir_ioapic[i].iommu;
+	return NULL;
+}
+
+struct intel_iommu *map_dev_to_ir(struct pci_dev *dev)
+{
+	struct dmar_drhd_unit *drhd;
+
+	drhd = dmar_find_matched_drhd_unit(dev);
+	if (!drhd)
+		return NULL;
+
+	return drhd->iommu;
+}
+
+static int clear_entries(struct irq_2_iommu *irq_iommu)
+{
+	struct irte *start, *entry, *end;
+	struct intel_iommu *iommu;
+	int index;
+
+	if (irq_iommu->sub_handle)
+		return 0;
+
+	iommu = irq_iommu->iommu;
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+
+	start = iommu->ir_table->base + index;
+	end = start + (1 << irq_iommu->irte_mask);
+
+	for (entry = start; entry < end; entry++) {
+		set_64bit(&entry->low, 0);
+		set_64bit(&entry->high, 0);
+	}
+
+	return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
+}
+
+int free_irte(int irq)
+{
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
+	unsigned long flags;
+	int rc;
+
+	if (!irq_iommu)
+		return -1;
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
+
+	rc = clear_entries(irq_iommu);
+
+	irq_iommu->iommu = NULL;
+	irq_iommu->irte_index = 0;
+	irq_iommu->sub_handle = 0;
+	irq_iommu->irte_mask = 0;
+
+	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+
+	return rc;
+}
+
+/*
+ * source validation type
+ */
+#define SVT_NO_VERIFY		0x0  /* no verification is required */
+#define SVT_VERIFY_SID_SQ	0x1  /* verify using SID and SQ fields */
+#define SVT_VERIFY_BUS		0x2  /* verify bus of request-id */
+
+/*
+ * source-id qualifier
+ */
+#define SQ_ALL_16	0x0  /* verify all 16 bits of request-id */
+#define SQ_13_IGNORE_1	0x1  /* verify most significant 13 bits, ignore
+			      * the third least significant bit
+			      */
+#define SQ_13_IGNORE_2	0x2  /* verify most significant 13 bits, ignore
+			      * the second and third least significant bits
+			      */
+#define SQ_13_IGNORE_3	0x3  /* verify most significant 13 bits, ignore
+			      * the least three significant bits
+			      */
+
+/*
+ * set SVT, SQ and SID fields of irte to verify
+ * source ids of interrupt requests
+ */
+static void set_irte_sid(struct irte *irte, unsigned int svt,
+			 unsigned int sq, unsigned int sid)
+{
+	if (disable_sourceid_checking)
+		svt = SVT_NO_VERIFY;
+	irte->svt = svt;
+	irte->sq = sq;
+	irte->sid = sid;
+}
+
+int set_ioapic_sid(struct irte *irte, int apic)
+{
+	int i;
+	u16 sid = 0;
+
+	if (!irte)
+		return -1;
+
+	for (i = 0; i < MAX_IO_APICS; i++) {
+		if (ir_ioapic[i].id == apic) {
+			sid = (ir_ioapic[i].bus << 8) | ir_ioapic[i].devfn;
+			break;
+		}
+	}
+
+	if (sid == 0) {
+		pr_warning("Failed to set source-id of IOAPIC (%d)\n", apic);
+		return -1;
+	}
+
+	set_irte_sid(irte, 1, 0, sid);
+
+	return 0;
+}
+
+int set_hpet_sid(struct irte *irte, u8 id)
+{
+	int i;
+	u16 sid = 0;
+
+	if (!irte)
+		return -1;
+
+	for (i = 0; i < MAX_HPET_TBS; i++) {
+		if (ir_hpet[i].id == id) {
+			sid = (ir_hpet[i].bus << 8) | ir_hpet[i].devfn;
+			break;
+		}
+	}
+
+	if (sid == 0) {
+		pr_warning("Failed to set source-id of HPET block (%d)\n", id);
+		return -1;
+	}
+
+	/*
+	 * Should really use SQ_ALL_16. Some platforms are broken.
+	 * While we figure out the right quirks for these broken platforms, use
+	 * SQ_13_IGNORE_3 for now.
+	 */
+	set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_13_IGNORE_3, sid);
+
+	return 0;
+}
+
+int set_msi_sid(struct irte *irte, struct pci_dev *dev)
+{
+	struct pci_dev *bridge;
+
+	if (!irte || !dev)
+		return -1;
+
+	/* PCIe device or Root Complex integrated PCI device */
+	if (pci_is_pcie(dev) || !dev->bus->parent) {
+		set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16,
+			     (dev->bus->number << 8) | dev->devfn);
+		return 0;
+	}
+
+	bridge = pci_find_upstream_pcie_bridge(dev);
+	if (bridge) {
+		if (pci_is_pcie(bridge))/* this is a PCIe-to-PCI/PCIX bridge */
+			set_irte_sid(irte, SVT_VERIFY_BUS, SQ_ALL_16,
+				(bridge->bus->number << 8) | dev->bus->number);
+		else /* this is a legacy PCI bridge */
+			set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16,
+				(bridge->bus->number << 8) | bridge->devfn);
+	}
+
+	return 0;
+}
+
+static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode)
+{
+	u64 addr;
+	u32 sts;
+	unsigned long flags;
+
+	addr = virt_to_phys((void *)iommu->ir_table->base);
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	dmar_writeq(iommu->reg + DMAR_IRTA_REG,
+		    (addr) | IR_X2APIC_MODE(mode) | INTR_REMAP_TABLE_REG_SIZE);
+
+	/* Set interrupt-remapping table pointer */
+	iommu->gcmd |= DMA_GCMD_SIRTP;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_IRTPS), sts);
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	/*
+	 * global invalidation of interrupt entry cache before enabling
+	 * interrupt-remapping.
+	 */
+	qi_global_iec(iommu);
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	/* Enable interrupt-remapping */
+	iommu->gcmd |= DMA_GCMD_IRE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, (sts & DMA_GSTS_IRES), sts);
+
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+
+static int setup_intr_remapping(struct intel_iommu *iommu, int mode)
+{
+	struct ir_table *ir_table;
+	struct page *pages;
+
+	ir_table = iommu->ir_table = kzalloc(sizeof(struct ir_table),
+					     GFP_ATOMIC);
+
+	if (!iommu->ir_table)
+		return -ENOMEM;
+
+	pages = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO,
+				 INTR_REMAP_PAGE_ORDER);
+
+	if (!pages) {
+		printk(KERN_ERR "failed to allocate pages of order %d\n",
+		       INTR_REMAP_PAGE_ORDER);
+		kfree(iommu->ir_table);
+		return -ENOMEM;
+	}
+
+	ir_table->base = page_address(pages);
+
+	iommu_set_intr_remapping(iommu, mode);
+	return 0;
+}
+
+/*
+ * Disable Interrupt Remapping.
+ */
+static void iommu_disable_intr_remapping(struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	u32 sts;
+
+	if (!ecap_ir_support(iommu->ecap))
+		return;
+
+	/*
+	 * global invalidation of interrupt entry cache before disabling
+	 * interrupt-remapping.
+	 */
+	qi_global_iec(iommu);
+
+	spin_lock_irqsave(&iommu->register_lock, flags);
+
+	sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	if (!(sts & DMA_GSTS_IRES))
+		goto end;
+
+	iommu->gcmd &= ~DMA_GCMD_IRE;
+	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+		      readl, !(sts & DMA_GSTS_IRES), sts);
+
+end:
+	spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+int __init intr_remapping_supported(void)
+{
+	struct dmar_drhd_unit *drhd;
+
+	if (disable_intremap)
+		return 0;
+
+	if (!dmar_ir_support())
+		return 0;
+
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (!ecap_ir_support(iommu->ecap))
+			return 0;
+	}
+
+	return 1;
+}
+
+int __init enable_intr_remapping(int eim)
+{
+	struct dmar_drhd_unit *drhd;
+	int setup = 0;
+
+	if (parse_ioapics_under_ir() != 1) {
+		printk(KERN_INFO "Not enable interrupt remapping\n");
+		return -1;
+	}
+
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		/*
+		 * If the queued invalidation is already initialized,
+		 * shouldn't disable it.
+		 */
+		if (iommu->qi)
+			continue;
+
+		/*
+		 * Clear previous faults.
+		 */
+		dmar_fault(-1, iommu);
+
+		/*
+		 * Disable intr remapping and queued invalidation, if already
+		 * enabled prior to OS handover.
+		 */
+		iommu_disable_intr_remapping(iommu);
+
+		dmar_disable_qi(iommu);
+	}
+
+	/*
+	 * check for the Interrupt-remapping support
+	 */
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		if (eim && !ecap_eim_support(iommu->ecap)) {
+			printk(KERN_INFO "DRHD %Lx: EIM not supported by DRHD, "
+			       " ecap %Lx\n", drhd->reg_base_addr, iommu->ecap);
+			return -1;
+		}
+	}
+
+	/*
+	 * Enable queued invalidation for all the DRHD's.
+	 */
+	for_each_drhd_unit(drhd) {
+		int ret;
+		struct intel_iommu *iommu = drhd->iommu;
+		ret = dmar_enable_qi(iommu);
+
+		if (ret) {
+			printk(KERN_ERR "DRHD %Lx: failed to enable queued, "
+			       " invalidation, ecap %Lx, ret %d\n",
+			       drhd->reg_base_addr, iommu->ecap, ret);
+			return -1;
+		}
+	}
+
+	/*
+	 * Setup Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		if (setup_intr_remapping(iommu, eim))
+			goto error;
+
+		setup = 1;
+	}
+
+	if (!setup)
+		goto error;
+
+	intr_remapping_enabled = 1;
+
+	return 0;
+
+error:
+	/*
+	 * handle error condition gracefully here!
+	 */
+	return -1;
+}
+
+static void ir_parse_one_hpet_scope(struct acpi_dmar_device_scope *scope,
+				      struct intel_iommu *iommu)
+{
+	struct acpi_dmar_pci_path *path;
+	u8 bus;
+	int count;
+
+	bus = scope->bus;
+	path = (struct acpi_dmar_pci_path *)(scope + 1);
+	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
+		/ sizeof(struct acpi_dmar_pci_path);
+
+	while (--count > 0) {
+		/*
+		 * Access PCI directly due to the PCI
+		 * subsystem isn't initialized yet.
+		 */
+		bus = read_pci_config_byte(bus, path->dev, path->fn,
+					   PCI_SECONDARY_BUS);
+		path++;
+	}
+	ir_hpet[ir_hpet_num].bus   = bus;
+	ir_hpet[ir_hpet_num].devfn = PCI_DEVFN(path->dev, path->fn);
+	ir_hpet[ir_hpet_num].iommu = iommu;
+	ir_hpet[ir_hpet_num].id    = scope->enumeration_id;
+	ir_hpet_num++;
+}
+
+static void ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope,
+				      struct intel_iommu *iommu)
+{
+	struct acpi_dmar_pci_path *path;
+	u8 bus;
+	int count;
+
+	bus = scope->bus;
+	path = (struct acpi_dmar_pci_path *)(scope + 1);
+	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
+		/ sizeof(struct acpi_dmar_pci_path);
+
+	while (--count > 0) {
+		/*
+		 * Access PCI directly due to the PCI
+		 * subsystem isn't initialized yet.
+		 */
+		bus = read_pci_config_byte(bus, path->dev, path->fn,
+					   PCI_SECONDARY_BUS);
+		path++;
+	}
+
+	ir_ioapic[ir_ioapic_num].bus   = bus;
+	ir_ioapic[ir_ioapic_num].devfn = PCI_DEVFN(path->dev, path->fn);
+	ir_ioapic[ir_ioapic_num].iommu = iommu;
+	ir_ioapic[ir_ioapic_num].id    = scope->enumeration_id;
+	ir_ioapic_num++;
+}
+
+static int ir_parse_ioapic_hpet_scope(struct acpi_dmar_header *header,
+				      struct intel_iommu *iommu)
+{
+	struct acpi_dmar_hardware_unit *drhd;
+	struct acpi_dmar_device_scope *scope;
+	void *start, *end;
+
+	drhd = (struct acpi_dmar_hardware_unit *)header;
+
+	start = (void *)(drhd + 1);
+	end = ((void *)drhd) + header->length;
+
+	while (start < end) {
+		scope = start;
+		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_IOAPIC) {
+			if (ir_ioapic_num == MAX_IO_APICS) {
+				printk(KERN_WARNING "Exceeded Max IO APICS\n");
+				return -1;
+			}
+
+			printk(KERN_INFO "IOAPIC id %d under DRHD base "
+			       " 0x%Lx IOMMU %d\n", scope->enumeration_id,
+			       drhd->address, iommu->seq_id);
+
+			ir_parse_one_ioapic_scope(scope, iommu);
+		} else if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_HPET) {
+			if (ir_hpet_num == MAX_HPET_TBS) {
+				printk(KERN_WARNING "Exceeded Max HPET blocks\n");
+				return -1;
+			}
+
+			printk(KERN_INFO "HPET id %d under DRHD base"
+			       " 0x%Lx\n", scope->enumeration_id,
+			       drhd->address);
+
+			ir_parse_one_hpet_scope(scope, iommu);
+		}
+		start += scope->length;
+	}
+
+	return 0;
+}
+
+/*
+ * Finds the assocaition between IOAPIC's and its Interrupt-remapping
+ * hardware unit.
+ */
+int __init parse_ioapics_under_ir(void)
+{
+	struct dmar_drhd_unit *drhd;
+	int ir_supported = 0;
+
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (ecap_ir_support(iommu->ecap)) {
+			if (ir_parse_ioapic_hpet_scope(drhd->hdr, iommu))
+				return -1;
+
+			ir_supported = 1;
+		}
+	}
+
+	if (ir_supported && ir_ioapic_num != nr_ioapics) {
+		printk(KERN_WARNING
+		       "Not all IO-APIC's listed under remapping hardware\n");
+		return -1;
+	}
+
+	return ir_supported;
+}
+
+void disable_intr_remapping(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+
+	/*
+	 * Disable Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_iommu(iommu, drhd) {
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		iommu_disable_intr_remapping(iommu);
+	}
+}
+
+int reenable_intr_remapping(int eim)
+{
+	struct dmar_drhd_unit *drhd;
+	int setup = 0;
+	struct intel_iommu *iommu = NULL;
+
+	for_each_iommu(iommu, drhd)
+		if (iommu->qi)
+			dmar_reenable_qi(iommu);
+
+	/*
+	 * Setup Interrupt-remapping for all the DRHD's now.
+	 */
+	for_each_iommu(iommu, drhd) {
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		/* Set up interrupt remapping for iommu.*/
+		iommu_set_intr_remapping(iommu, eim);
+		setup = 1;
+	}
+
+	if (!setup)
+		goto error;
+
+	return 0;
+
+error:
+	/*
+	 * handle error condition gracefully here!
+	 */
+	return -1;
+}
+

drivers/iommu/intr_remapping.h

@@ -0,0 +1,17 @@
+#include <linux/intel-iommu.h>
+
+struct ioapic_scope {
+	struct intel_iommu *iommu;
+	unsigned int id;
+	unsigned int bus;	/* PCI bus number */
+	unsigned int devfn;	/* PCI devfn number */
+};
+
+struct hpet_scope {
+	struct intel_iommu *iommu;
+	u8 id;
+	unsigned int bus;
+	unsigned int devfn;
+};
+
+#define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0)

drivers/iommu/iova.c

@@ -0,0 +1,435 @@
+/*
+ * Copyright © 2006-2009, 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
+ */
+
+#include <linux/iova.h>
+
+void
+init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit)
+{
+	spin_lock_init(&iovad->iova_rbtree_lock);
+	iovad->rbroot = RB_ROOT;
+	iovad->cached32_node = NULL;
+	iovad->dma_32bit_pfn = pfn_32bit;
+}
+
+static struct rb_node *
+__get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
+{
+	if ((*limit_pfn != iovad->dma_32bit_pfn) ||
+		(iovad->cached32_node == NULL))
+		return rb_last(&iovad->rbroot);
+	else {
+		struct rb_node *prev_node = rb_prev(iovad->cached32_node);
+		struct iova *curr_iova =
+			container_of(iovad->cached32_node, struct iova, node);
+		*limit_pfn = curr_iova->pfn_lo - 1;
+		return prev_node;
+	}
+}
+
+static void
+__cached_rbnode_insert_update(struct iova_domain *iovad,
+	unsigned long limit_pfn, struct iova *new)
+{
+	if (limit_pfn != iovad->dma_32bit_pfn)
+		return;
+	iovad->cached32_node = &new->node;
+}
+
+static void
+__cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
+{
+	struct iova *cached_iova;
+	struct rb_node *curr;
+
+	if (!iovad->cached32_node)
+		return;
+	curr = iovad->cached32_node;
+	cached_iova = container_of(curr, struct iova, node);
+
+	if (free->pfn_lo >= cached_iova->pfn_lo) {
+		struct rb_node *node = rb_next(&free->node);
+		struct iova *iova = container_of(node, struct iova, node);
+
+		/* only cache if it's below 32bit pfn */
+		if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
+			iovad->cached32_node = node;
+		else
+			iovad->cached32_node = NULL;
+	}
+}
+
+/* Computes the padding size required, to make the
+ * the start address naturally aligned on its size
+ */
+static int
+iova_get_pad_size(int size, unsigned int limit_pfn)
+{
+	unsigned int pad_size = 0;
+	unsigned int order = ilog2(size);
+
+	if (order)
+		pad_size = (limit_pfn + 1) % (1 << order);
+
+	return pad_size;
+}
+
+static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
+		unsigned long size, unsigned long limit_pfn,
+			struct iova *new, bool size_aligned)
+{
+	struct rb_node *prev, *curr = NULL;
+	unsigned long flags;
+	unsigned long saved_pfn;
+	unsigned int pad_size = 0;
+
+	/* Walk the tree backwards */
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	saved_pfn = limit_pfn;
+	curr = __get_cached_rbnode(iovad, &limit_pfn);
+	prev = curr;
+	while (curr) {
+		struct iova *curr_iova = container_of(curr, struct iova, node);
+
+		if (limit_pfn < curr_iova->pfn_lo)
+			goto move_left;
+		else if (limit_pfn < curr_iova->pfn_hi)
+			goto adjust_limit_pfn;
+		else {
+			if (size_aligned)
+				pad_size = iova_get_pad_size(size, limit_pfn);
+			if ((curr_iova->pfn_hi + size + pad_size) <= limit_pfn)
+				break;	/* found a free slot */
+		}
+adjust_limit_pfn:
+		limit_pfn = curr_iova->pfn_lo - 1;
+move_left:
+		prev = curr;
+		curr = rb_prev(curr);
+	}
+
+	if (!curr) {
+		if (size_aligned)
+			pad_size = iova_get_pad_size(size, limit_pfn);
+		if ((IOVA_START_PFN + size + pad_size) > limit_pfn) {
+			spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+			return -ENOMEM;
+		}
+	}
+
+	/* pfn_lo will point to size aligned address if size_aligned is set */
+	new->pfn_lo = limit_pfn - (size + pad_size) + 1;
+	new->pfn_hi = new->pfn_lo + size - 1;
+
+	/* Insert the new_iova into domain rbtree by holding writer lock */
+	/* Add new node and rebalance tree. */
+	{
+		struct rb_node **entry, *parent = NULL;
+
+		/* If we have 'prev', it's a valid place to start the
+		   insertion. Otherwise, start from the root. */
+		if (prev)
+			entry = &prev;
+		else
+			entry = &iovad->rbroot.rb_node;
+
+		/* Figure out where to put new node */
+		while (*entry) {
+			struct iova *this = container_of(*entry,
+							struct iova, node);
+			parent = *entry;
+
+			if (new->pfn_lo < this->pfn_lo)
+				entry = &((*entry)->rb_left);
+			else if (new->pfn_lo > this->pfn_lo)
+				entry = &((*entry)->rb_right);
+			else
+				BUG(); /* this should not happen */
+		}
+
+		/* Add new node and rebalance tree. */
+		rb_link_node(&new->node, parent, entry);
+		rb_insert_color(&new->node, &iovad->rbroot);
+	}
+	__cached_rbnode_insert_update(iovad, saved_pfn, new);
+
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+
+
+	return 0;
+}
+
+static void
+iova_insert_rbtree(struct rb_root *root, struct iova *iova)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	/* Figure out where to put new node */
+	while (*new) {
+		struct iova *this = container_of(*new, struct iova, node);
+		parent = *new;
+
+		if (iova->pfn_lo < this->pfn_lo)
+			new = &((*new)->rb_left);
+		else if (iova->pfn_lo > this->pfn_lo)
+			new = &((*new)->rb_right);
+		else
+			BUG(); /* this should not happen */
+	}
+	/* Add new node and rebalance tree. */
+	rb_link_node(&iova->node, parent, new);
+	rb_insert_color(&iova->node, root);
+}
+
+/**
+ * alloc_iova - allocates an iova
+ * @iovad - iova domain in question
+ * @size - size of page frames to allocate
+ * @limit_pfn - max limit address
+ * @size_aligned - set if size_aligned address range is required
+ * This function allocates an iova in the range limit_pfn to IOVA_START_PFN
+ * looking from limit_pfn instead from IOVA_START_PFN. If the size_aligned
+ * flag is set then the allocated address iova->pfn_lo will be naturally
+ * aligned on roundup_power_of_two(size).
+ */
+struct iova *
+alloc_iova(struct iova_domain *iovad, unsigned long size,
+	unsigned long limit_pfn,
+	bool size_aligned)
+{
+	struct iova *new_iova;
+	int ret;
+
+	new_iova = alloc_iova_mem();
+	if (!new_iova)
+		return NULL;
+
+	/* If size aligned is set then round the size to
+	 * to next power of two.
+	 */
+	if (size_aligned)
+		size = __roundup_pow_of_two(size);
+
+	ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn,
+			new_iova, size_aligned);
+
+	if (ret) {
+		free_iova_mem(new_iova);
+		return NULL;
+	}
+
+	return new_iova;
+}
+
+/**
+ * find_iova - find's an iova for a given pfn
+ * @iovad - iova domain in question.
+ * pfn - page frame number
+ * This function finds and returns an iova belonging to the
+ * given doamin which matches the given pfn.
+ */
+struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
+{
+	unsigned long flags;
+	struct rb_node *node;
+
+	/* Take the lock so that no other thread is manipulating the rbtree */
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	node = iovad->rbroot.rb_node;
+	while (node) {
+		struct iova *iova = container_of(node, struct iova, node);
+
+		/* If pfn falls within iova's range, return iova */
+		if ((pfn >= iova->pfn_lo) && (pfn <= iova->pfn_hi)) {
+			spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+			/* We are not holding the lock while this iova
+			 * is referenced by the caller as the same thread
+			 * which called this function also calls __free_iova()
+			 * and it is by desing that only one thread can possibly
+			 * reference a particular iova and hence no conflict.
+			 */
+			return iova;
+		}
+
+		if (pfn < iova->pfn_lo)
+			node = node->rb_left;
+		else if (pfn > iova->pfn_lo)
+			node = node->rb_right;
+	}
+
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	return NULL;
+}
+
+/**
+ * __free_iova - frees the given iova
+ * @iovad: iova domain in question.
+ * @iova: iova in question.
+ * Frees the given iova belonging to the giving domain
+ */
+void
+__free_iova(struct iova_domain *iovad, struct iova *iova)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	__cached_rbnode_delete_update(iovad, iova);
+	rb_erase(&iova->node, &iovad->rbroot);
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	free_iova_mem(iova);
+}
+
+/**
+ * free_iova - finds and frees the iova for a given pfn
+ * @iovad: - iova domain in question.
+ * @pfn: - pfn that is allocated previously
+ * This functions finds an iova for a given pfn and then
+ * frees the iova from that domain.
+ */
+void
+free_iova(struct iova_domain *iovad, unsigned long pfn)
+{
+	struct iova *iova = find_iova(iovad, pfn);
+	if (iova)
+		__free_iova(iovad, iova);
+
+}
+
+/**
+ * put_iova_domain - destroys the iova doamin
+ * @iovad: - iova domain in question.
+ * All the iova's in that domain are destroyed.
+ */
+void put_iova_domain(struct iova_domain *iovad)
+{
+	struct rb_node *node;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	node = rb_first(&iovad->rbroot);
+	while (node) {
+		struct iova *iova = container_of(node, struct iova, node);
+		rb_erase(node, &iovad->rbroot);
+		free_iova_mem(iova);
+		node = rb_first(&iovad->rbroot);
+	}
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+}
+
+static int
+__is_range_overlap(struct rb_node *node,
+	unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct iova *iova = container_of(node, struct iova, node);
+
+	if ((pfn_lo <= iova->pfn_hi) && (pfn_hi >= iova->pfn_lo))
+		return 1;
+	return 0;
+}
+
+static struct iova *
+__insert_new_range(struct iova_domain *iovad,
+	unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct iova *iova;
+
+	iova = alloc_iova_mem();
+	if (!iova)
+		return iova;
+
+	iova->pfn_hi = pfn_hi;
+	iova->pfn_lo = pfn_lo;
+	iova_insert_rbtree(&iovad->rbroot, iova);
+	return iova;
+}
+
+static void
+__adjust_overlap_range(struct iova *iova,
+	unsigned long *pfn_lo, unsigned long *pfn_hi)
+{
+	if (*pfn_lo < iova->pfn_lo)
+		iova->pfn_lo = *pfn_lo;
+	if (*pfn_hi > iova->pfn_hi)
+		*pfn_lo = iova->pfn_hi + 1;
+}
+
+/**
+ * reserve_iova - reserves an iova in the given range
+ * @iovad: - iova domain pointer
+ * @pfn_lo: - lower page frame address
+ * @pfn_hi:- higher pfn adderss
+ * This function allocates reserves the address range from pfn_lo to pfn_hi so
+ * that this address is not dished out as part of alloc_iova.
+ */
+struct iova *
+reserve_iova(struct iova_domain *iovad,
+	unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct rb_node *node;
+	unsigned long flags;
+	struct iova *iova;
+	unsigned int overlap = 0;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
+		if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
+			iova = container_of(node, struct iova, node);
+			__adjust_overlap_range(iova, &pfn_lo, &pfn_hi);
+			if ((pfn_lo >= iova->pfn_lo) &&
+				(pfn_hi <= iova->pfn_hi))
+				goto finish;
+			overlap = 1;
+
+		} else if (overlap)
+				break;
+	}
+
+	/* We are here either because this is the first reserver node
+	 * or need to insert remaining non overlap addr range
+	 */
+	iova = __insert_new_range(iovad, pfn_lo, pfn_hi);
+finish:
+
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	return iova;
+}
+
+/**
+ * copy_reserved_iova - copies the reserved between domains
+ * @from: - source doamin from where to copy
+ * @to: - destination domin where to copy
+ * This function copies reserved iova's from one doamin to
+ * other.
+ */
+void
+copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
+{
+	unsigned long flags;
+	struct rb_node *node;
+
+	spin_lock_irqsave(&from->iova_rbtree_lock, flags);
+	for (node = rb_first(&from->rbroot); node; node = rb_next(node)) {
+		struct iova *iova = container_of(node, struct iova, node);
+		struct iova *new_iova;
+		new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi);
+		if (!new_iova)
+			printk(KERN_ERR "Reserve iova range %lx@%lx failed\n",
+				iova->pfn_lo, iova->pfn_lo);
+	}
+	spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
+}

drivers/pci/Makefile

@@ -29,11 +29,6 @@ obj-$(CONFIG_PCI_MSI) += msi.o
 # Build the Hypertransport interrupt support
 obj-$(CONFIG_HT_IRQ) += htirq.o
 
-# Build Intel IOMMU support
-obj-$(CONFIG_DMAR) += dmar.o iova.o intel-iommu.o
-
-obj-$(CONFIG_INTR_REMAP) += dmar.o intr_remapping.o
-
 obj-$(CONFIG_PCI_IOV) += iov.o
 
 #

drivers/pci/pci.h

@@ -184,8 +184,6 @@ pci_match_one_device(const struct pci_device_id *id, const struct pci_dev *dev)
 	return NULL;
 }
 
-struct pci_dev *pci_find_upstream_pcie_bridge(struct pci_dev *pdev);
-
 /* PCI slot sysfs helper code */
 #define to_pci_slot(s) container_of(s, struct pci_slot, kobj)
 

include/linux/pci.h

@@ -1589,5 +1589,16 @@ int pci_vpd_find_tag(const u8 *buf, unsigned int off, unsigned int len, u8 rdt);
 int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off,
 			      unsigned int len, const char *kw);
 
+/**
+ * pci_find_upstream_pcie_bridge - find upstream PCIe-to-PCI bridge of a device
+ * @pdev: the PCI device
+ *
+ * if the device is PCIE, return NULL
+ * if the device isn't connected to a PCIe bridge (that is its parent is a
+ * legacy PCI bridge and the bridge is directly connected to bus 0), return its
+ * parent
+ */
+struct pci_dev *pci_find_upstream_pcie_bridge(struct pci_dev *pdev);
+
 #endif /* __KERNEL__ */
 #endif /* LINUX_PCI_H */