iommu/vt-d: Make use of IOMMU sysfs support

Register our DRHD IOMMUs, cross link devices, and provide a base set
of attributes for the IOMMU. Note that IRQ remapping support parses
the DMAR table very early in boot, well before the iommu_class can
reasonably be setup, so our registration is split between
intel_iommu_init(), which occurs later, and alloc_iommu(), which
typically occurs much earlier, but may happen at any time later
with IOMMU hot-add support.

On a typical desktop system, this provides the following (pruned):

$ find /sys | grep dmar
/sys/devices/virtual/iommu/dmar0
/sys/devices/virtual/iommu/dmar0/devices
/sys/devices/virtual/iommu/dmar0/devices/0000:00:02.0
/sys/devices/virtual/iommu/dmar0/intel-iommu
/sys/devices/virtual/iommu/dmar0/intel-iommu/cap
/sys/devices/virtual/iommu/dmar0/intel-iommu/ecap
/sys/devices/virtual/iommu/dmar0/intel-iommu/address
/sys/devices/virtual/iommu/dmar0/intel-iommu/version
/sys/devices/virtual/iommu/dmar1
/sys/devices/virtual/iommu/dmar1/devices
/sys/devices/virtual/iommu/dmar1/devices/0000:00:00.0
/sys/devices/virtual/iommu/dmar1/devices/0000:00:01.0
/sys/devices/virtual/iommu/dmar1/devices/0000:00:16.0
/sys/devices/virtual/iommu/dmar1/devices/0000:00:1a.0
/sys/devices/virtual/iommu/dmar1/devices/0000:00:1b.0
/sys/devices/virtual/iommu/dmar1/devices/0000:00:1c.0
...
/sys/devices/virtual/iommu/dmar1/intel-iommu
/sys/devices/virtual/iommu/dmar1/intel-iommu/cap
/sys/devices/virtual/iommu/dmar1/intel-iommu/ecap
/sys/devices/virtual/iommu/dmar1/intel-iommu/address
/sys/devices/virtual/iommu/dmar1/intel-iommu/version
/sys/class/iommu/dmar0
/sys/class/iommu/dmar1

(devices also link back to the dmar units)

This makes address, version, capabilities, and extended capabilities
available, just like printed on boot. I've tried not to duplicate
data that can be found in the DMAR table, with the exception of the
address, which provides an easy way to associate the sysfs device with
a DRHD entry in the DMAR. It's tempting to add scopes and RMRR data
here, but the full DMAR table is already exposed under /sys/firmware/
and therefore already provides a way for userspace to learn such
details.

Signed-off-by: Alex Williamson <[e-mail]>
Signed-off-by: Joerg Roedel <[e-mail]>

Documentation/ABI/testing/sysfs-class-iommu-intel-iommu

···
+What:		/sys/class/iommu/<iommu>/intel-iommu/address
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <[e-mail]>
+Description:
+		Physical address of the VT-d DRHD for this IOMMU.
+		Format: %llx.  This allows association of a sysfs
+		intel-iommu with a DMAR DRHD table entry.
+
+What:		/sys/class/iommu/<iommu>/intel-iommu/cap
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <[e-mail]>
+Description:
+		The cached hardware capability register value
+		of this DRHD unit.  Format: %llx.
+
+What:		/sys/class/iommu/<iommu>/intel-iommu/ecap
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <[e-mail]>
+Description:
+		The cached hardware extended capability register
+		value of this DRHD unit.  Format: %llx.
+
+What:		/sys/class/iommu/<iommu>/intel-iommu/version
+Date:		June 2014
+KernelVersion:	3.17
+Contact:	Alex Williamson <[e-mail]>
+Description:
+		The architecture version as reported from the
+		VT-d VER_REG.  Format: %d:%d, major:minor

drivers/iommu/dmar.c

···
 #include <linux/tboot.h>
 #include <linux/dmi.h>
 #include <linux/slab.h>
+#include <linux/iommu.h>
 #include <asm/irq_remapping.h>
 #include <asm/iommu_table.h>
 
···
 	raw_spin_lock_init(&iommu->register_lock);
 
 	drhd->iommu = iommu;
+
+	if (intel_iommu_enabled)
+		iommu->iommu_dev = iommu_device_create(NULL, iommu,
+						       intel_iommu_groups,
+						       iommu->name);
+
 	return 0;
 
  err_unmap:
···
 
 static void free_iommu(struct intel_iommu *iommu)
 {
+	iommu_device_destroy(iommu->iommu_dev);
+
 	if (iommu->irq) {
 		free_irq(iommu->irq, iommu);
 		irq_set_handler_data(iommu->irq, NULL);

drivers/iommu/intel-iommu.c

···
 	.priority = 0
 };
 
+
+static ssize_t intel_iommu_show_version(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct intel_iommu *iommu = dev_get_drvdata(dev);
+	u32 ver = readl(iommu->reg + DMAR_VER_REG);
+	return sprintf(buf, "%d:%d\n",
+		       DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver));
+}
+static DEVICE_ATTR(version, S_IRUGO, intel_iommu_show_version, NULL);
+
+static ssize_t intel_iommu_show_address(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct intel_iommu *iommu = dev_get_drvdata(dev);
+	return sprintf(buf, "%llx\n", iommu->reg_phys);
+}
+static DEVICE_ATTR(address, S_IRUGO, intel_iommu_show_address, NULL);
+
+static ssize_t intel_iommu_show_cap(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct intel_iommu *iommu = dev_get_drvdata(dev);
+	return sprintf(buf, "%llx\n", iommu->cap);
+}
+static DEVICE_ATTR(cap, S_IRUGO, intel_iommu_show_cap, NULL);
+
+static ssize_t intel_iommu_show_ecap(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct intel_iommu *iommu = dev_get_drvdata(dev);
+	return sprintf(buf, "%llx\n", iommu->ecap);
+}
+static DEVICE_ATTR(ecap, S_IRUGO, intel_iommu_show_ecap, NULL);
+
+static struct attribute *intel_iommu_attrs[] = {
+	&dev_attr_version.attr,
+	&dev_attr_address.attr,
+	&dev_attr_cap.attr,
+	&dev_attr_ecap.attr,
+	NULL,
+};
+
+static struct attribute_group intel_iommu_group = {
+	.name = "intel-iommu",
+	.attrs = intel_iommu_attrs,
+};
+
+const struct attribute_group *intel_iommu_groups[] = {
+	&intel_iommu_group,
+	NULL,
+};
+
 int __init intel_iommu_init(void)
 {
 	int ret = -ENODEV;
···
 	dma_ops = &intel_dma_ops;
 
 	init_iommu_pm_ops();
+
+	for_each_active_iommu(iommu, drhd)
+		iommu->iommu_dev = iommu_device_create(NULL, iommu,
+						       intel_iommu_groups,
+						       iommu->name);
 
 	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
 	bus_register_notifier(&pci_bus_type, &device_nb);
···
 
 static int intel_iommu_add_device(struct device *dev)
 {
+	struct intel_iommu *iommu;
 	struct iommu_group *group;
 	u8 bus, devfn;
 
-	if (!device_to_iommu(dev, &bus, &devfn))
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
 		return -ENODEV;
+
+	iommu_device_link(iommu->iommu_dev, dev);
 
 	group = iommu_group_get_for_dev(dev);
 
···
 
 static void intel_iommu_remove_device(struct device *dev)
 {
+	struct intel_iommu *iommu;
+	u8 bus, devfn;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return;
+
 	iommu_group_remove_device(dev);
+
+	iommu_device_unlink(iommu->iommu_dev, dev);
 }
 
 static struct iommu_ops intel_iommu_ops = {

include/linux/intel-iommu.h

···
 #ifdef CONFIG_IRQ_REMAP
 	struct ir_table *ir_table;	/* Interrupt remapping info */
 #endif
+	struct device	*iommu_dev; /* IOMMU-sysfs device */
 	int		node;
 };
 
···
 extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);
 
 extern int dmar_ir_support(void);
+
+extern const struct attribute_group *intel_iommu_groups[];
 
 #endif