Merge tag 'iommu-updates-v3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "The updates are mostly about the x86 IOMMUs this time.

  Exceptions are the groundwork for the PAMU IOMMU from Freescale (for a
  PPC platform) and an extension to the IOMMU group interface.

  On the x86 side this includes a workaround for VT-d to disable
  interrupt remapping on broken chipsets.  On the AMD-Vi side the most
  important new feature is a kernel command-line interface to override
  broken information in IVRS ACPI tables and get interrupt remapping
  working this way.

  Besides that there are small fixes all over the place."

* tag 'iommu-updates-v3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (24 commits)
  iommu/tegra: Fix printk formats for dma_addr_t
  iommu: Add a function to find an iommu group by id
  iommu/vt-d: Remove warning for HPET scope type
  iommu: Move swap_pci_ref function to drivers/iommu/pci.h.
  iommu/vt-d: Disable translation if already enabled
  iommu/amd: fix error return code in early_amd_iommu_init()
  iommu/AMD: Per-thread IOMMU Interrupt Handling
  iommu: Include linux/err.h
  iommu/amd: Workaround for ERBT1312
  iommu/amd: Document ivrs_ioapic and ivrs_hpet parameters
  iommu/amd: Don't report firmware bugs with cmd-line ivrs overrides
  iommu/amd: Add ioapic and hpet ivrs override
  iommu/amd: Add early maps for ioapic and hpet
  iommu/amd: Extend IVRS special device data structure
  iommu/amd: Move add_special_device() to __init
  iommu: Fix compile warnings with forward declarations
  iommu/amd: Properly initialize irq-table lock
  iommu/amd: Use AMD specific data structure for irq remapping
  iommu/amd: Remove map_sg_no_iommu()
  iommu/vt-d: add quirk for broken interrupt remapping on 55XX chipsets
  ...

Documentation/kernel-parameters.txt

@@ -1277,6 +1277,20 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	iucv=		[HW,NET]
 
+	ivrs_ioapic	[HW,X86_64]
+			Provide an override to the IOAPIC-ID<->DEVICE-ID
+			mapping provided in the IVRS ACPI table. For
+			example, to map IOAPIC-ID decimal 10 to
+			PCI device 00:14.0 write the parameter as:
+				ivrs_ioapic[10]=00:14.0
+
+	ivrs_hpet	[HW,X86_64]
+			Provide an override to the HPET-ID<->DEVICE-ID
+			mapping provided in the IVRS ACPI table. For
+			example, to map HPET-ID decimal 0 to
+			PCI device 00:14.0 write the parameter as:
+				ivrs_hpet[0]=00:14.0
+
 	js=		[HW,JOY] Analog joystick
 			See Documentation/input/joystick.txt.
 

arch/x86/include/asm/irq_remapping.h

@@ -24,10 +24,18 @@
 
 #include <asm/io_apic.h>
 
+struct IO_APIC_route_entry;
+struct io_apic_irq_attr;
+struct irq_chip;
+struct msi_msg;
+struct pci_dev;
+struct irq_cfg;
+
 #ifdef CONFIG_IRQ_REMAP
 
 extern void setup_irq_remapping_ops(void);
 extern int irq_remapping_supported(void);
+extern void set_irq_remapping_broken(void);
 extern int irq_remapping_prepare(void);
 extern int irq_remapping_enable(void);
 extern void irq_remapping_disable(void);
@@ -54,6 +62,7 @@ void irq_remap_modify_chip_defaults(struct irq_chip *chip);
 
 static inline void setup_irq_remapping_ops(void) { }
 static inline int irq_remapping_supported(void) { return 0; }
+static inline void set_irq_remapping_broken(void) { }
 static inline int irq_remapping_prepare(void) { return -ENODEV; }
 static inline int irq_remapping_enable(void) { return -ENODEV; }
 static inline void irq_remapping_disable(void) { }

arch/x86/kernel/early-quirks.c

@@ -18,6 +18,7 @@
 #include <asm/apic.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
+#include <asm/irq_remapping.h>
 
 static void __init fix_hypertransport_config(int num, int slot, int func)
 {
@@ -192,6 +193,21 @@ static void __init ati_bugs_contd(int num, int slot, int func)
 }
 #endif
 
+static void __init intel_remapping_check(int num, int slot, int func)
+{
+	u8 revision;
+
+	revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
+
+	/*
+	 * Revision 0x13 of this chipset supports irq remapping
+	 * but has an erratum that breaks its behavior, flag it as such
+	 */
+	if (revision == 0x13)
+		set_irq_remapping_broken();
+
+}
+
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
 #define QFLAG_DONE		(QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -221,6 +237,10 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs },
 	{ PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
+	{ PCI_VENDOR_ID_INTEL, 0x3403, PCI_CLASS_BRIDGE_HOST,
+	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
+	{ PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST,
+	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
 	{}
 };
 

drivers/iommu/amd_iommu.c

@@ -46,6 +46,7 @@
 #include "amd_iommu_proto.h"
 #include "amd_iommu_types.h"
 #include "irq_remapping.h"
+#include "pci.h"
 
 #define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
 
@@ -263,12 +264,6 @@ static bool check_device(struct device *dev)
 	return true;
 }
 
-static void swap_pci_ref(struct pci_dev **from, struct pci_dev *to)
-{
-	pci_dev_put(*from);
-	*from = to;
-}
-
 static struct pci_bus *find_hosted_bus(struct pci_bus *bus)
 {
 	while (!bus->self) {
@@ -701,9 +696,6 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 static void iommu_poll_events(struct amd_iommu *iommu)
 {
 	u32 head, tail;
-	unsigned long flags;
-
-	spin_lock_irqsave(&iommu->lock, flags);
 
 	head = readl(iommu->mmio_base + MMIO_EVT_HEAD_OFFSET);
 	tail = readl(iommu->mmio_base + MMIO_EVT_TAIL_OFFSET);
@@ -714,8 +706,6 @@ static void iommu_poll_events(struct amd_iommu *iommu)
 	}
 
 	writel(head, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET);
-
-	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
 static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u64 *raw)
@@ -740,17 +730,11 @@ static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u64 *raw)
 
 static void iommu_poll_ppr_log(struct amd_iommu *iommu)
 {
-	unsigned long flags;
 	u32 head, tail;
 
 	if (iommu->ppr_log == NULL)
 		return;
 
-	/* enable ppr interrupts again */
-	writel(MMIO_STATUS_PPR_INT_MASK, iommu->mmio_base + MMIO_STATUS_OFFSET);
-
-	spin_lock_irqsave(&iommu->lock, flags);
-
 	head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
 	tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
 
@@ -786,34 +770,50 @@ static void iommu_poll_ppr_log(struct amd_iommu *iommu)
 		head = (head + PPR_ENTRY_SIZE) % PPR_LOG_SIZE;
 		writel(head, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
 
-		/*
-		 * Release iommu->lock because ppr-handling might need to
-		 * re-acquire it
-		 */
-		spin_unlock_irqrestore(&iommu->lock, flags);
-
 		/* Handle PPR entry */
 		iommu_handle_ppr_entry(iommu, entry);
 
-		spin_lock_irqsave(&iommu->lock, flags);
-
 		/* Refresh ring-buffer information */
 		head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
 		tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
 	}
-
-	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
 irqreturn_t amd_iommu_int_thread(int irq, void *data)
 {
-	struct amd_iommu *iommu;
+	struct amd_iommu *iommu = (struct amd_iommu *) data;
+	u32 status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
 
-	for_each_iommu(iommu) {
-		iommu_poll_events(iommu);
-		iommu_poll_ppr_log(iommu);
-	}
+	while (status & (MMIO_STATUS_EVT_INT_MASK | MMIO_STATUS_PPR_INT_MASK)) {
+		/* Enable EVT and PPR interrupts again */
+		writel((MMIO_STATUS_EVT_INT_MASK | MMIO_STATUS_PPR_INT_MASK),
+			iommu->mmio_base + MMIO_STATUS_OFFSET);
 
+		if (status & MMIO_STATUS_EVT_INT_MASK) {
+			pr_devel("AMD-Vi: Processing IOMMU Event Log\n");
+			iommu_poll_events(iommu);
+		}
+
+		if (status & MMIO_STATUS_PPR_INT_MASK) {
+			pr_devel("AMD-Vi: Processing IOMMU PPR Log\n");
+			iommu_poll_ppr_log(iommu);
+		}
+
+		/*
+		 * Hardware bug: ERBT1312
+		 * When re-enabling interrupt (by writing 1
+		 * to clear the bit), the hardware might also try to set
+		 * the interrupt bit in the event status register.
+		 * In this scenario, the bit will be set, and disable
+		 * subsequent interrupts.
+		 *
+		 * Workaround: The IOMMU driver should read back the
+		 * status register and check if the interrupt bits are cleared.
+		 * If not, driver will need to go through the interrupt handler
+		 * again and re-clear the bits
+		 */
+		status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+	}
 	return IRQ_HANDLED;
 }
 
@@ -2838,24 +2838,6 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
-/*
- * This is a special map_sg function which is used if we should map a
- * device which is not handled by an AMD IOMMU in the system.
- */
-static int map_sg_no_iommu(struct device *dev, struct scatterlist *sglist,
-			   int nelems, int dir)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sglist, s, nelems, i) {
-		s->dma_address = (dma_addr_t)sg_phys(s);
-		s->dma_length  = s->length;
-	}
-
-	return nelems;
-}
-
 /*
  * The exported map_sg function for dma_ops (handles scatter-gather
  * lists).
@@ -2875,9 +2857,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 	INC_STATS_COUNTER(cnt_map_sg);
 
 	domain = get_domain(dev);
-	if (PTR_ERR(domain) == -EINVAL)
-		return map_sg_no_iommu(dev, sglist, nelems, dir);
-	else if (IS_ERR(domain))
+	if (IS_ERR(domain))
 		return 0;
 
 	dma_mask = *dev->dma_mask;
@@ -3410,7 +3390,7 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
 }
 
 static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
-					  unsigned long iova)
+					  dma_addr_t iova)
 {
 	struct protection_domain *domain = dom->priv;
 	unsigned long offset_mask;
@@ -3947,6 +3927,9 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
 	if (!table)
 		goto out;
 
+	/* Initialize table spin-lock */
+	spin_lock_init(&table->lock);
+
 	if (ioapic)
 		/* Keep the first 32 indexes free for IOAPIC interrupts */
 		table->min_index = 32;
@@ -4007,7 +3990,7 @@ static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count)
 			c = 0;
 
 		if (c == count)	{
-			struct irq_2_iommu *irte_info;
+			struct irq_2_irte *irte_info;
 
 			for (; c != 0; --c)
 				table->table[index - c + 1] = IRTE_ALLOCATED;
@@ -4015,9 +3998,9 @@ static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count)
 			index -= count - 1;
 
 			cfg->remapped	      = 1;
-			irte_info             = &cfg->irq_2_iommu;
-			irte_info->sub_handle = devid;
-			irte_info->irte_index = index;
+			irte_info             = &cfg->irq_2_irte;
+			irte_info->devid      = devid;
+			irte_info->index      = index;
 
 			goto out;
 		}
@@ -4098,7 +4081,7 @@ static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
 			      struct io_apic_irq_attr *attr)
 {
 	struct irq_remap_table *table;
-	struct irq_2_iommu *irte_info;
+	struct irq_2_irte *irte_info;
 	struct irq_cfg *cfg;
 	union irte irte;
 	int ioapic_id;
@@ -4110,7 +4093,7 @@ static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
 	if (!cfg)
 		return -EINVAL;
 
-	irte_info = &cfg->irq_2_iommu;
+	irte_info = &cfg->irq_2_irte;
 	ioapic_id = mpc_ioapic_id(attr->ioapic);
 	devid     = get_ioapic_devid(ioapic_id);
 
@@ -4125,8 +4108,8 @@ static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
 
 	/* Setup IRQ remapping info */
 	cfg->remapped	      = 1;
-	irte_info->sub_handle = devid;
-	irte_info->irte_index = index;
+	irte_info->devid      = devid;
+	irte_info->index      = index;
 
 	/* Setup IRTE for IOMMU */
 	irte.val		= 0;
@@ -4160,7 +4143,7 @@ static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
 static int set_affinity(struct irq_data *data, const struct cpumask *mask,
 			bool force)
 {
-	struct irq_2_iommu *irte_info;
+	struct irq_2_irte *irte_info;
 	unsigned int dest, irq;
 	struct irq_cfg *cfg;
 	union irte irte;
@@ -4171,12 +4154,12 @@ static int set_affinity(struct irq_data *data, const struct cpumask *mask,
 
 	cfg       = data->chip_data;
 	irq       = data->irq;
-	irte_info = &cfg->irq_2_iommu;
+	irte_info = &cfg->irq_2_irte;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
 		return -EINVAL;
 
-	if (get_irte(irte_info->sub_handle, irte_info->irte_index, &irte))
+	if (get_irte(irte_info->devid, irte_info->index, &irte))
 		return -EBUSY;
 
 	if (assign_irq_vector(irq, cfg, mask))
@@ -4192,7 +4175,7 @@ static int set_affinity(struct irq_data *data, const struct cpumask *mask,
 	irte.fields.vector      = cfg->vector;
 	irte.fields.destination = dest;
 
-	modify_irte(irte_info->sub_handle, irte_info->irte_index, irte);
+	modify_irte(irte_info->devid, irte_info->index, irte);
 
 	if (cfg->move_in_progress)
 		send_cleanup_vector(cfg);
@@ -4204,16 +4187,16 @@ static int set_affinity(struct irq_data *data, const struct cpumask *mask,
 
 static int free_irq(int irq)
 {
-	struct irq_2_iommu *irte_info;
+	struct irq_2_irte *irte_info;
 	struct irq_cfg *cfg;
 
 	cfg = irq_get_chip_data(irq);
 	if (!cfg)
 		return -EINVAL;
 
-	irte_info = &cfg->irq_2_iommu;
+	irte_info = &cfg->irq_2_irte;
 
-	free_irte(irte_info->sub_handle, irte_info->irte_index);
+	free_irte(irte_info->devid, irte_info->index);
 
 	return 0;
 }
@@ -4222,7 +4205,7 @@ static void compose_msi_msg(struct pci_dev *pdev,
 			    unsigned int irq, unsigned int dest,
 			    struct msi_msg *msg, u8 hpet_id)
 {
-	struct irq_2_iommu *irte_info;
+	struct irq_2_irte *irte_info;
 	struct irq_cfg *cfg;
 	union irte irte;
 
@@ -4230,7 +4213,7 @@ static void compose_msi_msg(struct pci_dev *pdev,
 	if (!cfg)
 		return;
 
-	irte_info = &cfg->irq_2_iommu;
+	irte_info = &cfg->irq_2_irte;
 
 	irte.val		= 0;
 	irte.fields.vector	= cfg->vector;
@@ -4239,11 +4222,11 @@ static void compose_msi_msg(struct pci_dev *pdev,
 	irte.fields.dm		= apic->irq_dest_mode;
 	irte.fields.valid	= 1;
 
-	modify_irte(irte_info->sub_handle, irte_info->irte_index, irte);
+	modify_irte(irte_info->devid, irte_info->index, irte);
 
 	msg->address_hi = MSI_ADDR_BASE_HI;
 	msg->address_lo = MSI_ADDR_BASE_LO;
-	msg->data       = irte_info->irte_index;
+	msg->data       = irte_info->index;
 }
 
 static int msi_alloc_irq(struct pci_dev *pdev, int irq, int nvec)
@@ -4268,7 +4251,7 @@ static int msi_alloc_irq(struct pci_dev *pdev, int irq, int nvec)
 static int msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
 			 int index, int offset)
 {
-	struct irq_2_iommu *irte_info;
+	struct irq_2_irte *irte_info;
 	struct irq_cfg *cfg;
 	u16 devid;
 
@@ -4283,18 +4266,18 @@ static int msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
 		return 0;
 
 	devid		= get_device_id(&pdev->dev);
-	irte_info	= &cfg->irq_2_iommu;
+	irte_info	= &cfg->irq_2_irte;
 
 	cfg->remapped	      = 1;
-	irte_info->sub_handle = devid;
-	irte_info->irte_index = index + offset;
+	irte_info->devid      = devid;
+	irte_info->index      = index + offset;
 
 	return 0;
 }
 
 static int setup_hpet_msi(unsigned int irq, unsigned int id)
 {
-	struct irq_2_iommu *irte_info;
+	struct irq_2_irte *irte_info;
 	struct irq_cfg *cfg;
 	int index, devid;
 
@@ -4302,7 +4285,7 @@ static int setup_hpet_msi(unsigned int irq, unsigned int id)
 	if (!cfg)
 		return -EINVAL;
 
-	irte_info = &cfg->irq_2_iommu;
+	irte_info = &cfg->irq_2_irte;
 	devid     = get_hpet_devid(id);
 	if (devid < 0)
 		return devid;
@@ -4312,8 +4295,8 @@ static int setup_hpet_msi(unsigned int irq, unsigned int id)
 		return index;
 
 	cfg->remapped	      = 1;
-	irte_info->sub_handle = devid;
-	irte_info->irte_index = index;
+	irte_info->devid      = devid;
+	irte_info->index      = index;
 
 	return 0;
 }

drivers/iommu/amd_iommu_init.c

@@ -213,6 +213,14 @@ enum iommu_init_state {
 	IOMMU_INIT_ERROR,
 };
 
+/* Early ioapic and hpet maps from kernel command line */
+#define EARLY_MAP_SIZE		4
+static struct devid_map __initdata early_ioapic_map[EARLY_MAP_SIZE];
+static struct devid_map __initdata early_hpet_map[EARLY_MAP_SIZE];
+static int __initdata early_ioapic_map_size;
+static int __initdata early_hpet_map_size;
+static bool __initdata cmdline_maps;
+
 static enum iommu_init_state init_state = IOMMU_START_STATE;
 
 static int amd_iommu_enable_interrupts(void);
@@ -703,31 +711,66 @@ static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
 	set_iommu_for_device(iommu, devid);
 }
 
-static int add_special_device(u8 type, u8 id, u16 devid)
+static int __init add_special_device(u8 type, u8 id, u16 devid, bool cmd_line)
 {
 	struct devid_map *entry;
 	struct list_head *list;
 
-	if (type != IVHD_SPECIAL_IOAPIC && type != IVHD_SPECIAL_HPET)
+	if (type == IVHD_SPECIAL_IOAPIC)
+		list = &ioapic_map;
+	else if (type == IVHD_SPECIAL_HPET)
+		list = &hpet_map;
+	else
 		return -EINVAL;
 
+	list_for_each_entry(entry, list, list) {
+		if (!(entry->id == id && entry->cmd_line))
+			continue;
+
+		pr_info("AMD-Vi: Command-line override present for %s id %d - ignoring\n",
+			type == IVHD_SPECIAL_IOAPIC ? "IOAPIC" : "HPET", id);
+
+		return 0;
+	}
+
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
 		return -ENOMEM;
 
-	entry->id    = id;
-	entry->devid = devid;
-
-	if (type == IVHD_SPECIAL_IOAPIC)
-		list = &ioapic_map;
-	else
-		list = &hpet_map;
+	entry->id	= id;
+	entry->devid	= devid;
+	entry->cmd_line	= cmd_line;
 
 	list_add_tail(&entry->list, list);
 
 	return 0;
 }
 
+static int __init add_early_maps(void)
+{
+	int i, ret;
+
+	for (i = 0; i < early_ioapic_map_size; ++i) {
+		ret = add_special_device(IVHD_SPECIAL_IOAPIC,
+					 early_ioapic_map[i].id,
+					 early_ioapic_map[i].devid,
+					 early_ioapic_map[i].cmd_line);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < early_hpet_map_size; ++i) {
+		ret = add_special_device(IVHD_SPECIAL_HPET,
+					 early_hpet_map[i].id,
+					 early_hpet_map[i].devid,
+					 early_hpet_map[i].cmd_line);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 /*
  * Reads the device exclusion range from ACPI and initializes the IOMMU with
  * it
@@ -764,6 +807,12 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 	u32 dev_i, ext_flags = 0;
 	bool alias = false;
 	struct ivhd_entry *e;
+	int ret;
+
+
+	ret = add_early_maps();
+	if (ret)
+		return ret;
 
 	/*
 	 * First save the recommended feature enable bits from ACPI
@@ -929,7 +978,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 				    PCI_FUNC(devid));
 
 			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
-			ret = add_special_device(type, handle, devid);
+			ret = add_special_device(type, handle, devid, false);
 			if (ret)
 				return ret;
 			break;
@@ -1275,7 +1324,7 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
 				 amd_iommu_int_handler,
 				 amd_iommu_int_thread,
 				 0, "AMD-Vi",
-				 iommu->dev);
+				 iommu);
 
 	if (r) {
 		pci_disable_msi(iommu->dev);
@@ -1638,18 +1687,28 @@ static void __init free_on_init_error(void)
 
 static bool __init check_ioapic_information(void)
 {
+	const char *fw_bug = FW_BUG;
 	bool ret, has_sb_ioapic;
 	int idx;
 
 	has_sb_ioapic = false;
 	ret           = false;
 
+	/*
+	 * If we have map overrides on the kernel command line the
+	 * messages in this function might not describe firmware bugs
+	 * anymore - so be careful
+	 */
+	if (cmdline_maps)
+		fw_bug = "";
+
 	for (idx = 0; idx < nr_ioapics; idx++) {
 		int devid, id = mpc_ioapic_id(idx);
 
 		devid = get_ioapic_devid(id);
 		if (devid < 0) {
-			pr_err(FW_BUG "AMD-Vi: IOAPIC[%d] not in IVRS table\n", id);
+			pr_err("%sAMD-Vi: IOAPIC[%d] not in IVRS table\n",
+				fw_bug, id);
 			ret = false;
 		} else if (devid == IOAPIC_SB_DEVID) {
 			has_sb_ioapic = true;
@@ -1666,11 +1725,11 @@ static bool __init check_ioapic_information(void)
 		 * when the BIOS is buggy and provides us the wrong
 		 * device id for the IOAPIC in the system.
 		 */
-		pr_err(FW_BUG "AMD-Vi: No southbridge IOAPIC found in IVRS table\n");
+		pr_err("%sAMD-Vi: No southbridge IOAPIC found\n", fw_bug);
 	}
 
 	if (!ret)
-		pr_err("AMD-Vi: Disabling interrupt remapping due to BIOS Bug(s)\n");
+		pr_err("AMD-Vi: Disabling interrupt remapping\n");
 
 	return ret;
 }
@@ -1801,6 +1860,7 @@ static int __init early_amd_iommu_init(void)
 		 * Interrupt remapping enabled, create kmem_cache for the
 		 * remapping tables.
 		 */
+		ret = -ENOMEM;
 		amd_iommu_irq_cache = kmem_cache_create("irq_remap_cache",
 				MAX_IRQS_PER_TABLE * sizeof(u32),
 				IRQ_TABLE_ALIGNMENT,
@@ -2097,8 +2157,70 @@ static int __init parse_amd_iommu_options(char *str)
 	return 1;
 }
 
-__setup("amd_iommu_dump", parse_amd_iommu_dump);
-__setup("amd_iommu=", parse_amd_iommu_options);
+static int __init parse_ivrs_ioapic(char *str)
+{
+	unsigned int bus, dev, fn;
+	int ret, id, i;
+	u16 devid;
+
+	ret = sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn);
+
+	if (ret != 4) {
+		pr_err("AMD-Vi: Invalid command line: ivrs_ioapic%s\n", str);
+		return 1;
+	}
+
+	if (early_ioapic_map_size == EARLY_MAP_SIZE) {
+		pr_err("AMD-Vi: Early IOAPIC map overflow - ignoring ivrs_ioapic%s\n",
+			str);
+		return 1;
+	}
+
+	devid = ((bus & 0xff) << 8) | ((dev & 0x1f) << 3) | (fn & 0x7);
+
+	cmdline_maps			= true;
+	i				= early_ioapic_map_size++;
+	early_ioapic_map[i].id		= id;
+	early_ioapic_map[i].devid	= devid;
+	early_ioapic_map[i].cmd_line	= true;
+
+	return 1;
+}
+
+static int __init parse_ivrs_hpet(char *str)
+{
+	unsigned int bus, dev, fn;
+	int ret, id, i;
+	u16 devid;
+
+	ret = sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn);
+
+	if (ret != 4) {
+		pr_err("AMD-Vi: Invalid command line: ivrs_hpet%s\n", str);
+		return 1;
+	}
+
+	if (early_hpet_map_size == EARLY_MAP_SIZE) {
+		pr_err("AMD-Vi: Early HPET map overflow - ignoring ivrs_hpet%s\n",
+			str);
+		return 1;
+	}
+
+	devid = ((bus & 0xff) << 8) | ((dev & 0x1f) << 3) | (fn & 0x7);
+
+	cmdline_maps			= true;
+	i				= early_hpet_map_size++;
+	early_hpet_map[i].id		= id;
+	early_hpet_map[i].devid		= devid;
+	early_hpet_map[i].cmd_line	= true;
+
+	return 1;
+}
+
+__setup("amd_iommu_dump",	parse_amd_iommu_dump);
+__setup("amd_iommu=",		parse_amd_iommu_options);
+__setup("ivrs_ioapic",		parse_ivrs_ioapic);
+__setup("ivrs_hpet",		parse_ivrs_hpet);
 
 IOMMU_INIT_FINISH(amd_iommu_detect,
 		  gart_iommu_hole_init,

drivers/iommu/amd_iommu_types.h

@@ -100,6 +100,7 @@
 #define PASID_MASK		0x000fffff
 
 /* MMIO status bits */
+#define MMIO_STATUS_EVT_INT_MASK	(1 << 1)
 #define MMIO_STATUS_COM_WAIT_INT_MASK	(1 << 2)
 #define MMIO_STATUS_PPR_INT_MASK	(1 << 6)
 
@@ -589,6 +590,7 @@ struct devid_map {
 	struct list_head list;
 	u8 id;
 	u16 devid;
+	bool cmd_line;
 };
 
 /* Map HPET and IOAPIC ids to the devid used by the IOMMU */

drivers/iommu/dmar.c

@@ -646,7 +646,7 @@ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr)
 int alloc_iommu(struct dmar_drhd_unit *drhd)
 {
 	struct intel_iommu *iommu;
-	u32 ver;
+	u32 ver, sts;
 	static int iommu_allocated = 0;
 	int agaw = 0;
 	int msagaw = 0;
@@ -696,6 +696,15 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 		(unsigned long long)iommu->cap,
 		(unsigned long long)iommu->ecap);
 
+	/* Reflect status in gcmd */
+	sts = readl(iommu->reg + DMAR_GSTS_REG);
+	if (sts & DMA_GSTS_IRES)
+		iommu->gcmd |= DMA_GCMD_IRE;
+	if (sts & DMA_GSTS_TES)
+		iommu->gcmd |= DMA_GCMD_TE;
+	if (sts & DMA_GSTS_QIES)
+		iommu->gcmd |= DMA_GCMD_QIE;
+
 	raw_spin_lock_init(&iommu->register_lock);
 
 	drhd->iommu = iommu;
@@ -1205,7 +1214,7 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 
 	/* TBD: ignore advanced fault log currently */
 	if (!(fault_status & DMA_FSTS_PPF))
-		goto clear_rest;
+		goto unlock_exit;
 
 	fault_index = dma_fsts_fault_record_index(fault_status);
 	reg = cap_fault_reg_offset(iommu->cap);
@@ -1246,11 +1255,10 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 			fault_index = 0;
 		raw_spin_lock_irqsave(&iommu->register_lock, flag);
 	}
-clear_rest:
-	/* clear all the other faults */
-	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
-	writel(fault_status, iommu->reg + DMAR_FSTS_REG);
 
+	writel(DMA_FSTS_PFO | DMA_FSTS_PPF, iommu->reg + DMAR_FSTS_REG);
+
+unlock_exit:
 	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
 	return IRQ_HANDLED;
 }
@@ -1298,6 +1306,7 @@ int __init enable_drhd_fault_handling(void)
 	for_each_drhd_unit(drhd) {
 		int ret;
 		struct intel_iommu *iommu = drhd->iommu;
+		u32 fault_status;
 		ret = dmar_set_interrupt(iommu);
 
 		if (ret) {
@@ -1310,6 +1319,8 @@ int __init enable_drhd_fault_handling(void)
 		 * Clear any previous faults.
 		 */
 		dmar_fault(iommu->irq, iommu);
+		fault_status = readl(iommu->reg + DMAR_FSTS_REG);
+		writel(fault_status, iommu->reg + DMAR_FSTS_REG);
 	}
 
 	return 0;

drivers/iommu/exynos-iommu.c

@@ -1027,7 +1027,7 @@ static size_t exynos_iommu_unmap(struct iommu_domain *domain,
 }
 
 static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *domain,
-					  unsigned long iova)
+					  dma_addr_t iova)
 {
 	struct exynos_iommu_domain *priv = domain->priv;
 	unsigned long *entry;

drivers/iommu/intel-iommu.c

@@ -47,6 +47,7 @@
 #include <asm/iommu.h>
 
 #include "irq_remapping.h"
+#include "pci.h"
 
 #define ROOT_SIZE		VTD_PAGE_SIZE
 #define CONTEXT_SIZE		VTD_PAGE_SIZE
@@ -3665,6 +3666,7 @@ static struct notifier_block device_nb = {
 int __init intel_iommu_init(void)
 {
 	int ret = 0;
+	struct dmar_drhd_unit *drhd;
 
 	/* VT-d is required for a TXT/tboot launch, so enforce that */
 	force_on = tboot_force_iommu();
@@ -3675,6 +3677,20 @@ int __init intel_iommu_init(void)
 		return 	-ENODEV;
 	}
 
+	/*
+	 * Disable translation if already enabled prior to OS handover.
+	 */
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu;
+
+		if (drhd->ignored)
+			continue;
+
+		iommu = drhd->iommu;
+		if (iommu->gcmd & DMA_GCMD_TE)
+			iommu_disable_translation(iommu);
+	}
+
 	if (dmar_dev_scope_init() < 0) {
 		if (force_on)
 			panic("tboot: Failed to initialize DMAR device scope\n");
@@ -4111,7 +4127,7 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
 }
 
 static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
-					    unsigned long iova)
+					    dma_addr_t iova)
 {
 	struct dmar_domain *dmar_domain = domain->priv;
 	struct dma_pte *pte;
@@ -4137,12 +4153,6 @@ static int intel_iommu_domain_has_cap(struct iommu_domain *domain,
 	return 0;
 }
 
-static void swap_pci_ref(struct pci_dev **from, struct pci_dev *to)
-{
-	pci_dev_put(*from);
-	*from = to;
-}
-
 #define REQ_ACS_FLAGS	(PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)
 
 static int intel_iommu_add_device(struct device *dev)

drivers/iommu/intel_irq_remapping.c

@@ -524,6 +524,16 @@ static int __init intel_irq_remapping_supported(void)
 
 	if (disable_irq_remap)
 		return 0;
+	if (irq_remap_broken) {
+		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
+			   "This system BIOS has enabled interrupt remapping\n"
+			   "on a chipset that contains an erratum making that\n"
+			   "feature unstable.  To maintain system stability\n"
+			   "interrupt remapping is being disabled.  Please\n"
+			   "contact your BIOS vendor for an update\n");
+		disable_irq_remap = 1;
+		return 0;
+	}
 
 	if (!dmar_ir_support())
 		return 0;

drivers/iommu/iommu.c

@@ -204,6 +204,35 @@ struct iommu_group *iommu_group_alloc(void)
 }
 EXPORT_SYMBOL_GPL(iommu_group_alloc);
 
+struct iommu_group *iommu_group_get_by_id(int id)
+{
+	struct kobject *group_kobj;
+	struct iommu_group *group;
+	const char *name;
+
+	if (!iommu_group_kset)
+		return NULL;
+
+	name = kasprintf(GFP_KERNEL, "%d", id);
+	if (!name)
+		return NULL;
+
+	group_kobj = kset_find_obj(iommu_group_kset, name);
+	kfree(name);
+
+	if (!group_kobj)
+		return NULL;
+
+	group = container_of(group_kobj, struct iommu_group, kobj);
+	BUG_ON(group->id != id);
+
+	kobject_get(group->devices_kobj);
+	kobject_put(&group->kobj);
+
+	return group;
+}
+EXPORT_SYMBOL_GPL(iommu_group_get_by_id);
+
 /**
  * iommu_group_get_iommudata - retrieve iommu_data registered for a group
  * @group: the group
@@ -706,8 +735,7 @@ void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
 }
 EXPORT_SYMBOL_GPL(iommu_detach_group);
 
-phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
-			       unsigned long iova)
+phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 {
 	if (unlikely(domain->ops->iova_to_phys == NULL))
 		return 0;
@@ -854,12 +882,13 @@ EXPORT_SYMBOL_GPL(iommu_unmap);
 
 
 int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
-			       phys_addr_t paddr, u64 size)
+			       phys_addr_t paddr, u64 size, int prot)
 {
 	if (unlikely(domain->ops->domain_window_enable == NULL))
 		return -ENODEV;
 
-	return domain->ops->domain_window_enable(domain, wnd_nr, paddr, size);
+	return domain->ops->domain_window_enable(domain, wnd_nr, paddr, size,
+						 prot);
 }
 EXPORT_SYMBOL_GPL(iommu_domain_window_enable);
 

drivers/iommu/irq_remapping.c

@@ -18,6 +18,7 @@
 int irq_remapping_enabled;
 
 int disable_irq_remap;
+int irq_remap_broken;
 int disable_sourceid_checking;
 int no_x2apic_optout;
 
@@ -210,6 +211,11 @@ void __init setup_irq_remapping_ops(void)
 #endif
 }
 
+void set_irq_remapping_broken(void)
+{
+	irq_remap_broken = 1;
+}
+
 int irq_remapping_supported(void)
 {
 	if (disable_irq_remap)

drivers/iommu/irq_remapping.h

@@ -32,6 +32,7 @@ struct pci_dev;
 struct msi_msg;
 
 extern int disable_irq_remap;
+extern int irq_remap_broken;
 extern int disable_sourceid_checking;
 extern int no_x2apic_optout;
 extern int irq_remapping_enabled;
@@ -89,6 +90,7 @@ extern struct irq_remap_ops amd_iommu_irq_ops;
 
 #define irq_remapping_enabled 0
 #define disable_irq_remap     1
+#define irq_remap_broken      0
 
 #endif /* CONFIG_IRQ_REMAP */
 

drivers/iommu/msm_iommu.c

@@ -554,7 +554,7 @@ static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long va,
 }
 
 static phys_addr_t msm_iommu_iova_to_phys(struct iommu_domain *domain,
-					  unsigned long va)
+					  dma_addr_t va)
 {
 	struct msm_priv *priv;
 	struct msm_iommu_drvdata *iommu_drvdata;

drivers/iommu/omap-iommu.c

@@ -1219,7 +1219,7 @@ static void omap_iommu_domain_destroy(struct iommu_domain *domain)
 }
 
 static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain,
-					  unsigned long da)
+					  dma_addr_t da)
 {
 	struct omap_iommu_domain *omap_domain = domain->priv;
 	struct omap_iommu *oiommu = omap_domain->iommu_dev;

drivers/iommu/pci.h

+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2013 Red Hat, Inc.
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+#ifndef __IOMMU_PCI_H
+#define __IOMMU_PCI_H
+
+/* Helper function for swapping pci device reference */
+static inline void swap_pci_ref(struct pci_dev **from, struct pci_dev *to)
+{
+	pci_dev_put(*from);
+	*from = to;
+}
+
+#endif  /* __IOMMU_PCI_H */

drivers/iommu/shmobile-iommu.c

@@ -296,7 +296,7 @@ static size_t shmobile_iommu_unmap(struct iommu_domain *domain,
 }
 
 static phys_addr_t shmobile_iommu_iova_to_phys(struct iommu_domain *domain,
-					       unsigned long iova)
+					       dma_addr_t iova)
 {
 	struct shmobile_iommu_domain *sh_domain = domain->priv;
 	uint32_t l1entry = 0, l2entry = 0;

drivers/iommu/tegra-gart.c

@@ -279,7 +279,7 @@ static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 }
 
 static phys_addr_t gart_iommu_iova_to_phys(struct iommu_domain *domain,
-					   unsigned long iova)
+					   dma_addr_t iova)
 {
 	struct gart_device *gart = domain->priv;
 	unsigned long pte;
@@ -295,7 +295,8 @@ static phys_addr_t gart_iommu_iova_to_phys(struct iommu_domain *domain,
 
 	pa = (pte & GART_PAGE_MASK);
 	if (!pfn_valid(__phys_to_pfn(pa))) {
-		dev_err(gart->dev, "No entry for %08lx:%08x\n", iova, pa);
+		dev_err(gart->dev, "No entry for %08llx:%08x\n",
+			 (unsigned long long)iova, pa);
 		gart_dump_table(gart);
 		return -EINVAL;
 	}

drivers/iommu/tegra-smmu.c

@@ -757,7 +757,7 @@ static size_t smmu_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 }
 
 static phys_addr_t smmu_iommu_iova_to_phys(struct iommu_domain *domain,
-					   unsigned long iova)
+					   dma_addr_t iova)
 {
 	struct smmu_as *as = domain->priv;
 	unsigned long *pte;
@@ -772,7 +772,8 @@ static phys_addr_t smmu_iommu_iova_to_phys(struct iommu_domain *domain,
 	pfn = *pte & SMMU_PFN_MASK;
 	WARN_ON(!pfn_valid(pfn));
 	dev_dbg(as->smmu->dev,
-		"iova:%08lx pfn:%08lx asid:%d\n", iova, pfn, as->asid);
+		"iova:%08llx pfn:%08lx asid:%d\n", (unsigned long long)iova,
+		 pfn, as->asid);
 
 	spin_unlock_irqrestore(&as->lock, flags);
 	return PFN_PHYS(pfn);

include/linux/iommu.h

@@ -20,6 +20,7 @@
 #define __LINUX_IOMMU_H
 
 #include <linux/errno.h>
+#include <linux/err.h>
 #include <linux/types.h>
 
 #define IOMMU_READ	(1)
@@ -91,8 +92,7 @@ struct iommu_ops {
 		   phys_addr_t paddr, size_t size, int prot);
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size);
-	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
-				    unsigned long iova);
+	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova);
 	int (*domain_has_cap)(struct iommu_domain *domain,
 			      unsigned long cap);
 	int (*add_device)(struct device *dev);
@@ -105,7 +105,7 @@ struct iommu_ops {
 
 	/* Window handling functions */
 	int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr,
-				    phys_addr_t paddr, u64 size);
+				    phys_addr_t paddr, u64 size, int prot);
 	void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr);
 	/* Set the numer of window per domain */
 	int (*domain_set_windows)(struct iommu_domain *domain, u32 w_count);
@@ -125,6 +125,7 @@ struct iommu_ops {
 extern int bus_set_iommu(struct bus_type *bus, struct iommu_ops *ops);
 extern bool iommu_present(struct bus_type *bus);
 extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus);
+extern struct iommu_group *iommu_group_get_by_id(int id);
 extern void iommu_domain_free(struct iommu_domain *domain);
 extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
@@ -134,8 +135,7 @@ extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		     phys_addr_t paddr, size_t size, int prot);
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 		       size_t size);
-extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
-				      unsigned long iova);
+extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
 extern int iommu_domain_has_cap(struct iommu_domain *domain,
 				unsigned long cap);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
@@ -171,7 +171,8 @@ extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr,
 
 /* Window handling function prototypes */
 extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
-				      phys_addr_t offset, u64 size);
+				      phys_addr_t offset, u64 size,
+				      int prot);
 extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr);
 /**
  * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
@@ -257,7 +258,7 @@ static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 
 static inline int iommu_domain_window_enable(struct iommu_domain *domain,
 					     u32 wnd_nr, phys_addr_t paddr,
-					     u64 size)
+					     u64 size, int prot)
 {
 	return -ENODEV;
 }
@@ -267,8 +268,7 @@ static inline void iommu_domain_window_disable(struct iommu_domain *domain,
 {
 }
 
-static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
-					     unsigned long iova)
+static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 {
 	return 0;
 }